12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394959697989910010110210310410510610710810911011111211311411511611711811912012112212312412512612712812913013113213313413513613713813914014114214314414514614714814915015115215315415515615715815916016116216316416516616716816917017117217317417517617717817918018118218318418518618718818919019119219319419519619719819920020120220320420520620720820921021121221321421521621721821922022122222322422522622722822923023123223323423523623723823924024124224324424524624724824925025125225325425525625725825926026126226326426526626726826927027127227327427527627727827928028128228328428528628728828929029129229329429529629729829930030130230330430530630730830931031131231331431531631731831932032132232332432532632732832933033133233333433533633733833934034134234334434534634734834935035135235335435535635735835936036136236336436536636736836937037137237337437537637737837938038138238338438538638738838939039139239339439539639739839940040140240340440540640740840941041141241341441541641741841942042142242342442542642742842943043143243343443543643743843944044144244344444544644744844945045145245345445545645745845946046146246346446546646746846947047147247347447547647747847948048148248348448548648748848949049149249349449549649749849950050150250350450550650750850951051151251351451551651751851952052152252352452552652752852953053153253353453553653753853954054154254354454554654754854955055155255355455555655755855956056156256356456556656756856957057157257357457557657757857958058158258358458558658758858959059159259359459559659759859960060160260360460560660760860961061161261361461561661761861962062162262362462562662762862963063163263363463563663763863964064164264364464564664764864965065165265365465565665765865966066166266366466566666766866967067167267367467567667767867968068168268368468568668768868969069169269369469569669769869970070170270370470570670770870971071171271371471571671771871972072172272372472572672772872973073173273373473573673773873974074174274374474574674774874975075175275375475575675775875976076176276376476576676776876977077177277377477577677777877978078178278378478578678778878979079179279379479579679779879980080180280380480580680780880981081181281381481581681781881982082182282382482582682782882983083183283383483583683783883984084184284384484584684784884985085185285385485585685785885986086186286386486586686786886987087187287387487587687787887988088188288388488588688788888989089189289389489589689789889990090190290390490590690790890991091191291391491591691791891992092192292392492592692792892993093193293393493593693793893994094194294394494594694794894995095195295395495595695795895996096196296396496596696796896997097197297397497597697797897998098198298398498598698798898999099199299399499599699799899910001001100210031004100510061007100810091010101110121013101410151016101710181019102010211022102310241025102610271028102910301031103210331034103510361037103810391040104110421043104410451046104710481049105010511052105310541055105610571058105910601061106210631064106510661067106810691070107110721073107410751076107710781079108010811082108310841085108610871088108910901091109210931094109510961097109810991100110111021103110411051106110711081109111011111112111311141115111611171118111911201121112211231124112511261127112811291130113111321133113411351136113711381139114011411142114311441145114611471148114911501151115211531154115511561157115811591160116111621163116411651166116711681169117011711172117311741175117611771178117911801181118211831184118511861187118811891190119111921193119411951196119711981199120012011202120312041205120612071208120912101211121212131214121512161217121812191220122112221223122412251226122712281229123012311232123312341235123612371238123912401241124212431244124512461247124812491250125112521253125412551256125712581259126012611262126312641265126612671268126912701271127212731274127512761277127812791280128112821283128412851286128712881289129012911292129312941295129612971298129913001301130213031304130513061307130813091310131113121313131413151316131713181319132013211322132313241325132613271328132913301331133213331334133513361337133813391340134113421343134413451346134713481349135013511352135313541355135613571358135913601361136213631364136513661367136813691370137113721373137413751376137713781379138013811382138313841385138613871388138913901391139213931394139513961397139813991400140114021403140414051406140714081409141014111412141314141415141614171418141914201421142214231424142514261427142814291430143114321433143414351436143714381439144014411442144314441445144614471448144914501451145214531454145514561457145814591460146114621463146414651466146714681469147014711472147314741475147614771478147914801481148214831484148514861487148814891490149114921493149414951496149714981499150015011502150315041505150615071508150915101511151215131514151515161517151815191520152115221523152415251526152715281529153015311532153315341535153615371538153915401541154215431544154515461547154815491550155115521553155415551556155715581559156015611562156315641565156615671568156915701571157215731574157515761577157815791580158115821583158415851586158715881589159015911592159315941595159615971598159916001601160216031604160516061607160816091610161116121613161416151616161716181619162016211622162316241625162616271628162916301631163216331634163516361637163816391640164116421643164416451646164716481649165016511652165316541655165616571658165916601661166216631664166516661667166816691670167116721673167416751676167716781679168016811682168316841685168616871688168916901691169216931694169516961697169816991700170117021703170417051706170717081709171017111712171317141715171617171718171917201721172217231724172517261727172817291730173117321733173417351736173717381739174017411742174317441745174617471748174917501751175217531754175517561757175817591760176117621763176417651766176717681769177017711772177317741775177617771778177917801781178217831784178517861787178817891790179117921793179417951796179717981799180018011802180318041805180618071808180918101811181218131814181518161817181818191820182118221823182418251826182718281829183018311832183318341835183618371838183918401841184218431844184518461847184818491850185118521853185418551856185718581859186018611862186318641865186618671868186918701871187218731874187518761877187818791880188118821883188418851886188718881889189018911892189318941895189618971898189919001901190219031904190519061907190819091910191119121913191419151916191719181919192019211922192319241925192619271928192919301931193219331934193519361937193819391940194119421943194419451946194719481949195019511952195319541955195619571958195919601961196219631964196519661967196819691970197119721973197419751976197719781979198019811982198319841985198619871988198919901991199219931994199519961997199819992000200120022003200420052006200720082009201020112012201320142015201620172018201920202021202220232024202520262027202820292030203120322033203420352036203720382039204020412042204320442045204620472048204920502051205220532054205520562057205820592060206120622063206420652066206720682069207020712072207320742075207620772078207920802081208220832084208520862087208820892090209120922093209420952096209720982099210021012102210321042105210621072108210921102111211221132114211521162117211821192120212121222123212421252126212721282129213021312132213321342135213621372138213921402141214221432144214521462147214821492150215121522153215421552156215721582159216021612162216321642165216621672168216921702171217221732174217521762177217821792180218121822183218421852186218721882189219021912192219321942195219621972198219922002201220222032204220522062207220822092210221122122213221422152216221722182219222022212222222322242225222622272228222922302231223222332234223522362237223822392240224122422243224422452246224722482249225022512252225322542255225622572258225922602261226222632264226522662267226822692270227122722273227422752276227722782279228022812282228322842285228622872288228922902291229222932294229522962297229822992300230123022303230423052306230723082309231023112312231323142315231623172318231923202321232223232324232523262327232823292330233123322333233423352336233723382339234023412342234323442345234623472348234923502351235223532354235523562357235823592360236123622363236423652366236723682369237023712372237323742375237623772378237923802381238223832384238523862387238823892390239123922393239423952396239723982399240024012402240324042405240624072408240924102411241224132414241524162417241824192420242124222423242424252426242724282429243024312432243324342435243624372438243924402441244224432444244524462447244824492450245124522453245424552456245724582459246024612462246324642465246624672468246924702471247224732474247524762477247824792480248124822483248424852486248724882489249024912492249324942495249624972498249925002501250225032504250525062507250825092510251125122513251425152516251725182519252025212522252325242525252625272528252925302531253225332534253525362537253825392540254125422543254425452546254725482549255025512552255325542555255625572558255925602561256225632564256525662567256825692570257125722573257425752576257725782579258025812582258325842585258625872588258925902591259225932594259525962597259825992600260126022603260426052606260726082609261026112612261326142615261626172618261926202621262226232624262526262627262826292630263126322633263426352636263726382639264026412642264326442645264626472648264926502651265226532654265526562657265826592660266126622663266426652666266726682669267026712672267326742675267626772678267926802681268226832684268526862687268826892690269126922693269426952696269726982699270027012702270327042705270627072708270927102711271227132714271527162717271827192720272127222723272427252726272727282729273027312732273327342735273627372738273927402741274227432744274527462747274827492750275127522753275427552756275727582759276027612762276327642765276627672768276927702771277227732774277527762777277827792780278127822783278427852786278727882789279027912792279327942795279627972798279928002801280228032804280528062807280828092810281128122813281428152816281728182819282028212822282328242825282628272828282928302831283228332834283528362837283828392840284128422843284428452846284728482849285028512852285328542855285628572858285928602861286228632864286528662867286828692870287128722873287428752876287728782879288028812882288328842885288628872888288928902891289228932894289528962897289828992900290129022903290429052906290729082909291029112912291329142915291629172918291929202921292229232924292529262927292829292930293129322933293429352936293729382939294029412942294329442945294629472948294929502951295229532954295529562957295829592960296129622963296429652966296729682969297029712972297329742975297629772978297929802981298229832984298529862987298829892990299129922993299429952996299729982999300030013002300330043005300630073008300930103011301230133014301530163017301830193020302130223023302430253026302730283029303030313032303330343035303630373038303930403041304230433044304530463047304830493050305130523053305430553056305730583059306030613062306330643065306630673068306930703071307230733074307530763077307830793080308130823083308430853086308730883089309030913092309330943095309630973098309931003101310231033104310531063107310831093110311131123113311431153116311731183119312031213122312331243125312631273128312931303131313231333134313531363137313831393140314131423143314431453146314731483149315031513152315331543155315631573158315931603161316231633164316531663167316831693170317131723173317431753176317731783179318031813182318331843185318631873188318931903191319231933194319531963197319831993200320132023203320432053206320732083209321032113212321332143215321632173218321932203221322232233224322532263227322832293230323132323233323432353236323732383239324032413242324332443245324632473248324932503251325232533254325532563257325832593260326132623263326432653266326732683269327032713272327332743275327632773278327932803281328232833284328532863287328832893290329132923293329432953296329732983299330033013302330333043305330633073308330933103311331233133314331533163317331833193320332133223323332433253326332733283329333033313332333333343335333633373338333933403341334233433344334533463347334833493350335133523353335433553356335733583359336033613362336333643365336633673368336933703371337233733374337533763377337833793380338133823383338433853386338733883389339033913392339333943395339633973398339934003401340234033404340534063407340834093410341134123413341434153416341734183419342034213422342334243425342634273428342934303431343234333434343534363437343834393440344134423443344434453446344734483449345034513452345334543455345634573458345934603461346234633464346534663467346834693470347134723473347434753476347734783479348034813482348334843485348634873488348934903491349234933494349534963497349834993500350135023503350435053506350735083509351035113512351335143515351635173518351935203521352235233524352535263527352835293530353135323533353435353536353735383539354035413542354335443545354635473548354935503551355235533554355535563557355835593560356135623563356435653566356735683569357035713572357335743575357635773578357935803581358235833584358535863587358835893590359135923593359435953596359735983599360036013602360336043605360636073608360936103611361236133614361536163617361836193620362136223623362436253626362736283629363036313632363336343635363636373638363936403641364236433644364536463647364836493650365136523653365436553656365736583659366036613662366336643665366636673668 |
- // SPDX-License-Identifier: GPL-2.0-only
- /*
- * linux/mm/filemap.c
- *
- * Copyright (C) 1994-1999 Linus Torvalds
- */
- /*
- * This file handles the generic file mmap semantics used by
- * most "normal" filesystems (but you don't /have/ to use this:
- * the NFS filesystem used to do this differently, for example)
- */
- #include <linux/export.h>
- #include <linux/compiler.h>
- #include <linux/dax.h>
- #include <linux/fs.h>
- #include <linux/sched/signal.h>
- #include <linux/uaccess.h>
- #include <linux/capability.h>
- #include <linux/kernel_stat.h>
- #include <linux/gfp.h>
- #include <linux/mm.h>
- #include <linux/swap.h>
- #include <linux/mman.h>
- #include <linux/pagemap.h>
- #include <linux/file.h>
- #include <linux/uio.h>
- #include <linux/error-injection.h>
- #include <linux/hash.h>
- #include <linux/writeback.h>
- #include <linux/backing-dev.h>
- #include <linux/pagevec.h>
- #include <linux/blkdev.h>
- #include <linux/security.h>
- #include <linux/cpuset.h>
- #include <linux/hugetlb.h>
- #include <linux/memcontrol.h>
- #include <linux/cleancache.h>
- #include <linux/shmem_fs.h>
- #include <linux/rmap.h>
- #include <linux/delayacct.h>
- #include <linux/psi.h>
- #include <linux/ramfs.h>
- #include <linux/page_idle.h>
- #include <asm/pgalloc.h>
- #include <asm/tlbflush.h>
- #include "internal.h"
- #define CREATE_TRACE_POINTS
- #include <trace/events/filemap.h>
- #undef CREATE_TRACE_POINTS
- #include <trace/hooks/mm.h>
- /*
- * FIXME: remove all knowledge of the buffer layer from the core VM
- */
- #include <linux/buffer_head.h> /* for try_to_free_buffers */
- #include <asm/mman.h>
- /*
- * Shared mappings implemented 30.11.1994. It's not fully working yet,
- * though.
- *
- * Shared mappings now work. 15.8.1995 Bruno.
- *
- * finished 'unifying' the page and buffer cache and SMP-threaded the
- * page-cache, 21.05.1999, Ingo Molnar <mingo@redhat.com>
- *
- * SMP-threaded pagemap-LRU 1999, Andrea Arcangeli <andrea@suse.de>
- */
- /*
- * Lock ordering:
- *
- * ->i_mmap_rwsem (truncate_pagecache)
- * ->private_lock (__free_pte->__set_page_dirty_buffers)
- * ->swap_lock (exclusive_swap_page, others)
- * ->i_pages lock
- *
- * ->i_mutex
- * ->i_mmap_rwsem (truncate->unmap_mapping_range)
- *
- * ->mmap_lock
- * ->i_mmap_rwsem
- * ->page_table_lock or pte_lock (various, mainly in memory.c)
- * ->i_pages lock (arch-dependent flush_dcache_mmap_lock)
- *
- * ->mmap_lock
- * ->lock_page (access_process_vm)
- *
- * ->i_mutex (generic_perform_write)
- * ->mmap_lock (fault_in_pages_readable->do_page_fault)
- *
- * bdi->wb.list_lock
- * sb_lock (fs/fs-writeback.c)
- * ->i_pages lock (__sync_single_inode)
- *
- * ->i_mmap_rwsem
- * ->anon_vma.lock (vma_adjust)
- *
- * ->anon_vma.lock
- * ->page_table_lock or pte_lock (anon_vma_prepare and various)
- *
- * ->page_table_lock or pte_lock
- * ->swap_lock (try_to_unmap_one)
- * ->private_lock (try_to_unmap_one)
- * ->i_pages lock (try_to_unmap_one)
- * ->pgdat->lru_lock (follow_page->mark_page_accessed)
- * ->pgdat->lru_lock (check_pte_range->isolate_lru_page)
- * ->private_lock (page_remove_rmap->set_page_dirty)
- * ->i_pages lock (page_remove_rmap->set_page_dirty)
- * bdi.wb->list_lock (page_remove_rmap->set_page_dirty)
- * ->inode->i_lock (page_remove_rmap->set_page_dirty)
- * ->memcg->move_lock (page_remove_rmap->lock_page_memcg)
- * bdi.wb->list_lock (zap_pte_range->set_page_dirty)
- * ->inode->i_lock (zap_pte_range->set_page_dirty)
- * ->private_lock (zap_pte_range->__set_page_dirty_buffers)
- *
- * ->i_mmap_rwsem
- * ->tasklist_lock (memory_failure, collect_procs_ao)
- */
- static void page_cache_delete(struct address_space *mapping,
- struct page *page, void *shadow)
- {
- XA_STATE(xas, &mapping->i_pages, page->index);
- unsigned int nr = 1;
- mapping_set_update(&xas, mapping);
- /* hugetlb pages are represented by a single entry in the xarray */
- if (!PageHuge(page)) {
- xas_set_order(&xas, page->index, compound_order(page));
- nr = compound_nr(page);
- }
- VM_BUG_ON_PAGE(!PageLocked(page), page);
- VM_BUG_ON_PAGE(PageTail(page), page);
- VM_BUG_ON_PAGE(nr != 1 && shadow, page);
- xas_store(&xas, shadow);
- xas_init_marks(&xas);
- page->mapping = NULL;
- /* Leave page->index set: truncation lookup relies upon it */
- if (shadow) {
- mapping->nrexceptional += nr;
- /*
- * Make sure the nrexceptional update is committed before
- * the nrpages update so that final truncate racing
- * with reclaim does not see both counters 0 at the
- * same time and miss a shadow entry.
- */
- smp_wmb();
- }
- mapping->nrpages -= nr;
- }
- static void unaccount_page_cache_page(struct address_space *mapping,
- struct page *page)
- {
- int nr;
- /*
- * if we're uptodate, flush out into the cleancache, otherwise
- * invalidate any existing cleancache entries. We can't leave
- * stale data around in the cleancache once our page is gone
- */
- if (PageUptodate(page) && PageMappedToDisk(page))
- cleancache_put_page(page);
- else
- cleancache_invalidate_page(mapping, page);
- VM_BUG_ON_PAGE(PageTail(page), page);
- VM_BUG_ON_PAGE(page_mapped(page), page);
- if (!IS_ENABLED(CONFIG_DEBUG_VM) && unlikely(page_mapped(page))) {
- int mapcount;
- pr_alert("BUG: Bad page cache in process %s pfn:%05lx\n",
- current->comm, page_to_pfn(page));
- dump_page(page, "still mapped when deleted");
- dump_stack();
- add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
- mapcount = page_mapcount(page);
- if (mapping_exiting(mapping) &&
- page_count(page) >= mapcount + 2) {
- /*
- * All vmas have already been torn down, so it's
- * a good bet that actually the page is unmapped,
- * and we'd prefer not to leak it: if we're wrong,
- * some other bad page check should catch it later.
- */
- page_mapcount_reset(page);
- page_ref_sub(page, mapcount);
- }
- }
- /* hugetlb pages do not participate in page cache accounting. */
- if (PageHuge(page))
- return;
- nr = thp_nr_pages(page);
- __mod_lruvec_page_state(page, NR_FILE_PAGES, -nr);
- if (PageSwapBacked(page)) {
- __mod_lruvec_page_state(page, NR_SHMEM, -nr);
- if (PageTransHuge(page))
- __dec_node_page_state(page, NR_SHMEM_THPS);
- } else if (PageTransHuge(page)) {
- __dec_node_page_state(page, NR_FILE_THPS);
- filemap_nr_thps_dec(mapping);
- }
- /*
- * At this point page must be either written or cleaned by
- * truncate. Dirty page here signals a bug and loss of
- * unwritten data.
- *
- * This fixes dirty accounting after removing the page entirely
- * but leaves PageDirty set: it has no effect for truncated
- * page and anyway will be cleared before returning page into
- * buddy allocator.
- */
- if (WARN_ON_ONCE(PageDirty(page)))
- account_page_cleaned(page, mapping, inode_to_wb(mapping->host));
- }
- /*
- * Delete a page from the page cache and free it. Caller has to make
- * sure the page is locked and that nobody else uses it - or that usage
- * is safe. The caller must hold the i_pages lock.
- */
- void __delete_from_page_cache(struct page *page, void *shadow)
- {
- struct address_space *mapping = page->mapping;
- trace_mm_filemap_delete_from_page_cache(page);
- unaccount_page_cache_page(mapping, page);
- page_cache_delete(mapping, page, shadow);
- }
- static void page_cache_free_page(struct address_space *mapping,
- struct page *page)
- {
- void (*freepage)(struct page *);
- freepage = mapping->a_ops->freepage;
- if (freepage)
- freepage(page);
- if (PageTransHuge(page) && !PageHuge(page)) {
- page_ref_sub(page, thp_nr_pages(page));
- VM_BUG_ON_PAGE(page_count(page) <= 0, page);
- } else {
- put_page(page);
- }
- }
- /**
- * delete_from_page_cache - delete page from page cache
- * @page: the page which the kernel is trying to remove from page cache
- *
- * This must be called only on pages that have been verified to be in the page
- * cache and locked. It will never put the page into the free list, the caller
- * has a reference on the page.
- */
- void delete_from_page_cache(struct page *page)
- {
- struct address_space *mapping = page_mapping(page);
- unsigned long flags;
- BUG_ON(!PageLocked(page));
- xa_lock_irqsave(&mapping->i_pages, flags);
- __delete_from_page_cache(page, NULL);
- xa_unlock_irqrestore(&mapping->i_pages, flags);
- page_cache_free_page(mapping, page);
- }
- EXPORT_SYMBOL(delete_from_page_cache);
- /*
- * page_cache_delete_batch - delete several pages from page cache
- * @mapping: the mapping to which pages belong
- * @pvec: pagevec with pages to delete
- *
- * The function walks over mapping->i_pages and removes pages passed in @pvec
- * from the mapping. The function expects @pvec to be sorted by page index
- * and is optimised for it to be dense.
- * It tolerates holes in @pvec (mapping entries at those indices are not
- * modified). The function expects only THP head pages to be present in the
- * @pvec.
- *
- * The function expects the i_pages lock to be held.
- */
- static void page_cache_delete_batch(struct address_space *mapping,
- struct pagevec *pvec)
- {
- XA_STATE(xas, &mapping->i_pages, pvec->pages[0]->index);
- int total_pages = 0;
- int i = 0;
- struct page *page;
- mapping_set_update(&xas, mapping);
- xas_for_each(&xas, page, ULONG_MAX) {
- if (i >= pagevec_count(pvec))
- break;
- /* A swap/dax/shadow entry got inserted? Skip it. */
- if (xa_is_value(page))
- continue;
- /*
- * A page got inserted in our range? Skip it. We have our
- * pages locked so they are protected from being removed.
- * If we see a page whose index is higher than ours, it
- * means our page has been removed, which shouldn't be
- * possible because we're holding the PageLock.
- */
- if (page != pvec->pages[i]) {
- VM_BUG_ON_PAGE(page->index > pvec->pages[i]->index,
- page);
- continue;
- }
- WARN_ON_ONCE(!PageLocked(page));
- if (page->index == xas.xa_index)
- page->mapping = NULL;
- /* Leave page->index set: truncation lookup relies on it */
- /*
- * Move to the next page in the vector if this is a regular
- * page or the index is of the last sub-page of this compound
- * page.
- */
- if (page->index + compound_nr(page) - 1 == xas.xa_index)
- i++;
- xas_store(&xas, NULL);
- total_pages++;
- }
- mapping->nrpages -= total_pages;
- }
- void delete_from_page_cache_batch(struct address_space *mapping,
- struct pagevec *pvec)
- {
- int i;
- unsigned long flags;
- if (!pagevec_count(pvec))
- return;
- xa_lock_irqsave(&mapping->i_pages, flags);
- for (i = 0; i < pagevec_count(pvec); i++) {
- trace_mm_filemap_delete_from_page_cache(pvec->pages[i]);
- unaccount_page_cache_page(mapping, pvec->pages[i]);
- }
- page_cache_delete_batch(mapping, pvec);
- xa_unlock_irqrestore(&mapping->i_pages, flags);
- for (i = 0; i < pagevec_count(pvec); i++)
- page_cache_free_page(mapping, pvec->pages[i]);
- }
- int filemap_check_errors(struct address_space *mapping)
- {
- int ret = 0;
- /* Check for outstanding write errors */
- if (test_bit(AS_ENOSPC, &mapping->flags) &&
- test_and_clear_bit(AS_ENOSPC, &mapping->flags))
- ret = -ENOSPC;
- if (test_bit(AS_EIO, &mapping->flags) &&
- test_and_clear_bit(AS_EIO, &mapping->flags))
- ret = -EIO;
- return ret;
- }
- EXPORT_SYMBOL(filemap_check_errors);
- static int filemap_check_and_keep_errors(struct address_space *mapping)
- {
- /* Check for outstanding write errors */
- if (test_bit(AS_EIO, &mapping->flags))
- return -EIO;
- if (test_bit(AS_ENOSPC, &mapping->flags))
- return -ENOSPC;
- return 0;
- }
- /**
- * __filemap_fdatawrite_range - start writeback on mapping dirty pages in range
- * @mapping: address space structure to write
- * @start: offset in bytes where the range starts
- * @end: offset in bytes where the range ends (inclusive)
- * @sync_mode: enable synchronous operation
- *
- * Start writeback against all of a mapping's dirty pages that lie
- * within the byte offsets <start, end> inclusive.
- *
- * If sync_mode is WB_SYNC_ALL then this is a "data integrity" operation, as
- * opposed to a regular memory cleansing writeback. The difference between
- * these two operations is that if a dirty page/buffer is encountered, it must
- * be waited upon, and not just skipped over.
- *
- * Return: %0 on success, negative error code otherwise.
- */
- int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start,
- loff_t end, int sync_mode)
- {
- int ret;
- struct writeback_control wbc = {
- .sync_mode = sync_mode,
- .nr_to_write = LONG_MAX,
- .range_start = start,
- .range_end = end,
- };
- if (!mapping_can_writeback(mapping) ||
- !mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
- return 0;
- wbc_attach_fdatawrite_inode(&wbc, mapping->host);
- ret = do_writepages(mapping, &wbc);
- wbc_detach_inode(&wbc);
- return ret;
- }
- static inline int __filemap_fdatawrite(struct address_space *mapping,
- int sync_mode)
- {
- return __filemap_fdatawrite_range(mapping, 0, LLONG_MAX, sync_mode);
- }
- int filemap_fdatawrite(struct address_space *mapping)
- {
- return __filemap_fdatawrite(mapping, WB_SYNC_ALL);
- }
- EXPORT_SYMBOL(filemap_fdatawrite);
- int filemap_fdatawrite_range(struct address_space *mapping, loff_t start,
- loff_t end)
- {
- return __filemap_fdatawrite_range(mapping, start, end, WB_SYNC_ALL);
- }
- EXPORT_SYMBOL(filemap_fdatawrite_range);
- /**
- * filemap_flush - mostly a non-blocking flush
- * @mapping: target address_space
- *
- * This is a mostly non-blocking flush. Not suitable for data-integrity
- * purposes - I/O may not be started against all dirty pages.
- *
- * Return: %0 on success, negative error code otherwise.
- */
- int filemap_flush(struct address_space *mapping)
- {
- return __filemap_fdatawrite(mapping, WB_SYNC_NONE);
- }
- EXPORT_SYMBOL(filemap_flush);
- /**
- * filemap_range_has_page - check if a page exists in range.
- * @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.
- *
- * Return: %true if at least one page exists in the specified range,
- * %false otherwise.
- */
- bool filemap_range_has_page(struct address_space *mapping,
- loff_t start_byte, loff_t end_byte)
- {
- struct page *page;
- XA_STATE(xas, &mapping->i_pages, start_byte >> PAGE_SHIFT);
- pgoff_t max = end_byte >> PAGE_SHIFT;
- if (end_byte < start_byte)
- return false;
- rcu_read_lock();
- for (;;) {
- page = xas_find(&xas, max);
- if (xas_retry(&xas, page))
- continue;
- /* Shadow entries don't count */
- if (xa_is_value(page))
- continue;
- /*
- * We don't need to try to pin this page; we're about to
- * release the RCU lock anyway. It is enough to know that
- * there was a page here recently.
- */
- break;
- }
- rcu_read_unlock();
- return page != NULL;
- }
- EXPORT_SYMBOL(filemap_range_has_page);
- static void __filemap_fdatawait_range(struct address_space *mapping,
- loff_t start_byte, loff_t end_byte)
- {
- pgoff_t index = start_byte >> PAGE_SHIFT;
- pgoff_t end = end_byte >> PAGE_SHIFT;
- struct pagevec pvec;
- int nr_pages;
- if (end_byte < start_byte)
- return;
- pagevec_init(&pvec);
- while (index <= end) {
- unsigned i;
- nr_pages = pagevec_lookup_range_tag(&pvec, mapping, &index,
- end, PAGECACHE_TAG_WRITEBACK);
- if (!nr_pages)
- break;
- for (i = 0; i < nr_pages; i++) {
- struct page *page = pvec.pages[i];
- wait_on_page_writeback(page);
- ClearPageError(page);
- }
- pagevec_release(&pvec);
- cond_resched();
- }
- }
- /**
- * filemap_fdatawait_range - wait for writeback to complete
- * @mapping: address space structure to wait for
- * @start_byte: offset in bytes where the range starts
- * @end_byte: offset in bytes where the range ends (inclusive)
- *
- * Walk the list of under-writeback pages of the given address space
- * in the given range and wait for all of them. Check error status of
- * the address space and return it.
- *
- * Since the error status of the address space is cleared by this function,
- * callers are responsible for checking the return value and handling and/or
- * reporting the error.
- *
- * Return: error status of the address space.
- */
- int filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte,
- loff_t end_byte)
- {
- __filemap_fdatawait_range(mapping, start_byte, end_byte);
- return filemap_check_errors(mapping);
- }
- EXPORT_SYMBOL(filemap_fdatawait_range);
- /**
- * filemap_fdatawait_range_keep_errors - wait for writeback to complete
- * @mapping: address space structure to wait for
- * @start_byte: offset in bytes where the range starts
- * @end_byte: offset in bytes where the range ends (inclusive)
- *
- * Walk the list of under-writeback pages of the given address space in the
- * given range and wait for all of them. Unlike filemap_fdatawait_range(),
- * this function does not clear error status of the address space.
- *
- * Use this function if callers don't handle errors themselves. Expected
- * call sites are system-wide / filesystem-wide data flushers: e.g. sync(2),
- * fsfreeze(8)
- */
- int filemap_fdatawait_range_keep_errors(struct address_space *mapping,
- loff_t start_byte, loff_t end_byte)
- {
- __filemap_fdatawait_range(mapping, start_byte, end_byte);
- return filemap_check_and_keep_errors(mapping);
- }
- EXPORT_SYMBOL(filemap_fdatawait_range_keep_errors);
- /**
- * file_fdatawait_range - wait for writeback to complete
- * @file: file pointing to address space structure to wait for
- * @start_byte: offset in bytes where the range starts
- * @end_byte: offset in bytes where the range ends (inclusive)
- *
- * Walk the list of under-writeback pages of the address space that file
- * refers to, in the given range and wait for all of them. Check error
- * status of the address space vs. the file->f_wb_err cursor and return it.
- *
- * Since the error status of the file is advanced by this function,
- * callers are responsible for checking the return value and handling and/or
- * reporting the error.
- *
- * Return: error status of the address space vs. the file->f_wb_err cursor.
- */
- int file_fdatawait_range(struct file *file, loff_t start_byte, loff_t end_byte)
- {
- struct address_space *mapping = file->f_mapping;
- __filemap_fdatawait_range(mapping, start_byte, end_byte);
- return file_check_and_advance_wb_err(file);
- }
- EXPORT_SYMBOL(file_fdatawait_range);
- /**
- * filemap_fdatawait_keep_errors - wait for writeback without clearing errors
- * @mapping: address space structure to wait for
- *
- * Walk the list of under-writeback pages of the given address space
- * and wait for all of them. Unlike filemap_fdatawait(), this function
- * does not clear error status of the address space.
- *
- * Use this function if callers don't handle errors themselves. Expected
- * call sites are system-wide / filesystem-wide data flushers: e.g. sync(2),
- * fsfreeze(8)
- *
- * Return: error status of the address space.
- */
- int filemap_fdatawait_keep_errors(struct address_space *mapping)
- {
- __filemap_fdatawait_range(mapping, 0, LLONG_MAX);
- return filemap_check_and_keep_errors(mapping);
- }
- EXPORT_SYMBOL(filemap_fdatawait_keep_errors);
- /* Returns true if writeback might be needed or already in progress. */
- static bool mapping_needs_writeback(struct address_space *mapping)
- {
- if (dax_mapping(mapping))
- return mapping->nrexceptional;
- return mapping->nrpages;
- }
- /**
- * filemap_write_and_wait_range - write out & wait on a file range
- * @mapping: the address_space for the pages
- * @lstart: offset in bytes where the range starts
- * @lend: offset in bytes where the range ends (inclusive)
- *
- * Write out and wait upon file offsets lstart->lend, inclusive.
- *
- * Note that @lend is inclusive (describes the last byte to be written) so
- * that this function can be used to write to the very end-of-file (end = -1).
- *
- * Return: error status of the address space.
- */
- int filemap_write_and_wait_range(struct address_space *mapping,
- loff_t lstart, loff_t lend)
- {
- int err = 0;
- if (mapping_needs_writeback(mapping)) {
- err = __filemap_fdatawrite_range(mapping, lstart, lend,
- WB_SYNC_ALL);
- /*
- * Even if the above returned error, the pages may be
- * written partially (e.g. -ENOSPC), so we wait for it.
- * But the -EIO is special case, it may indicate the worst
- * thing (e.g. bug) happened, so we avoid waiting for it.
- */
- if (err != -EIO) {
- int err2 = filemap_fdatawait_range(mapping,
- lstart, lend);
- if (!err)
- err = err2;
- } else {
- /* Clear any previously stored errors */
- filemap_check_errors(mapping);
- }
- } else {
- err = filemap_check_errors(mapping);
- }
- return err;
- }
- EXPORT_SYMBOL(filemap_write_and_wait_range);
- void __filemap_set_wb_err(struct address_space *mapping, int err)
- {
- errseq_t eseq = errseq_set(&mapping->wb_err, err);
- trace_filemap_set_wb_err(mapping, eseq);
- }
- EXPORT_SYMBOL(__filemap_set_wb_err);
- /**
- * file_check_and_advance_wb_err - report wb error (if any) that was previously
- * and advance wb_err to current one
- * @file: struct file on which the error is being reported
- *
- * When userland calls fsync (or something like nfsd does the equivalent), we
- * want to report any writeback errors that occurred since the last fsync (or
- * since the file was opened if there haven't been any).
- *
- * Grab the wb_err from the mapping. If it matches what we have in the file,
- * then just quickly return 0. The file is all caught up.
- *
- * If it doesn't match, then take the mapping value, set the "seen" flag in
- * it and try to swap it into place. If it works, or another task beat us
- * to it with the new value, then update the f_wb_err and return the error
- * portion. The error at this point must be reported via proper channels
- * (a'la fsync, or NFS COMMIT operation, etc.).
- *
- * While we handle mapping->wb_err with atomic operations, the f_wb_err
- * value is protected by the f_lock since we must ensure that it reflects
- * the latest value swapped in for this file descriptor.
- *
- * Return: %0 on success, negative error code otherwise.
- */
- int file_check_and_advance_wb_err(struct file *file)
- {
- int err = 0;
- errseq_t old = READ_ONCE(file->f_wb_err);
- struct address_space *mapping = file->f_mapping;
- /* Locklessly handle the common case where nothing has changed */
- if (errseq_check(&mapping->wb_err, old)) {
- /* Something changed, must use slow path */
- spin_lock(&file->f_lock);
- old = file->f_wb_err;
- err = errseq_check_and_advance(&mapping->wb_err,
- &file->f_wb_err);
- trace_file_check_and_advance_wb_err(file, old);
- spin_unlock(&file->f_lock);
- }
- /*
- * We're mostly using this function as a drop in replacement for
- * filemap_check_errors. Clear AS_EIO/AS_ENOSPC to emulate the effect
- * that the legacy code would have had on these flags.
- */
- clear_bit(AS_EIO, &mapping->flags);
- clear_bit(AS_ENOSPC, &mapping->flags);
- return err;
- }
- EXPORT_SYMBOL(file_check_and_advance_wb_err);
- /**
- * file_write_and_wait_range - write out & wait on a file range
- * @file: file pointing to address_space with pages
- * @lstart: offset in bytes where the range starts
- * @lend: offset in bytes where the range ends (inclusive)
- *
- * Write out and wait upon file offsets lstart->lend, inclusive.
- *
- * Note that @lend is inclusive (describes the last byte to be written) so
- * that this function can be used to write to the very end-of-file (end = -1).
- *
- * After writing out and waiting on the data, we check and advance the
- * f_wb_err cursor to the latest value, and return any errors detected there.
- *
- * Return: %0 on success, negative error code otherwise.
- */
- int file_write_and_wait_range(struct file *file, loff_t lstart, loff_t lend)
- {
- int err = 0, err2;
- struct address_space *mapping = file->f_mapping;
- if (mapping_needs_writeback(mapping)) {
- err = __filemap_fdatawrite_range(mapping, lstart, lend,
- WB_SYNC_ALL);
- /* See comment of filemap_write_and_wait() */
- if (err != -EIO)
- __filemap_fdatawait_range(mapping, lstart, lend);
- }
- err2 = file_check_and_advance_wb_err(file);
- if (!err)
- err = err2;
- return err;
- }
- EXPORT_SYMBOL(file_write_and_wait_range);
- /**
- * replace_page_cache_page - replace a pagecache page with a new one
- * @old: page to be replaced
- * @new: page to replace with
- * @gfp_mask: allocation mode
- *
- * This function replaces a page in the pagecache with a new one. On
- * success it acquires the pagecache reference for the new page and
- * drops it for the old page. Both the old and new pages must be
- * locked. This function does not add the new page to the LRU, the
- * caller must do that.
- *
- * The remove + add is atomic. This function cannot fail.
- *
- * Return: %0
- */
- int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
- {
- struct address_space *mapping = old->mapping;
- void (*freepage)(struct page *) = mapping->a_ops->freepage;
- pgoff_t offset = old->index;
- XA_STATE(xas, &mapping->i_pages, offset);
- unsigned long flags;
- VM_BUG_ON_PAGE(!PageLocked(old), old);
- VM_BUG_ON_PAGE(!PageLocked(new), new);
- VM_BUG_ON_PAGE(new->mapping, new);
- get_page(new);
- new->mapping = mapping;
- new->index = offset;
- mem_cgroup_migrate(old, new);
- xas_lock_irqsave(&xas, flags);
- xas_store(&xas, new);
- old->mapping = NULL;
- /* hugetlb pages do not participate in page cache accounting. */
- if (!PageHuge(old))
- __dec_lruvec_page_state(old, NR_FILE_PAGES);
- if (!PageHuge(new))
- __inc_lruvec_page_state(new, NR_FILE_PAGES);
- if (PageSwapBacked(old))
- __dec_lruvec_page_state(old, NR_SHMEM);
- if (PageSwapBacked(new))
- __inc_lruvec_page_state(new, NR_SHMEM);
- xas_unlock_irqrestore(&xas, flags);
- if (freepage)
- freepage(old);
- put_page(old);
- return 0;
- }
- EXPORT_SYMBOL_GPL(replace_page_cache_page);
- noinline int __add_to_page_cache_locked(struct page *page,
- struct address_space *mapping,
- pgoff_t offset, gfp_t gfp,
- void **shadowp)
- {
- XA_STATE(xas, &mapping->i_pages, offset);
- int huge = PageHuge(page);
- int error;
- bool charged = false;
- VM_BUG_ON_PAGE(!PageLocked(page), page);
- VM_BUG_ON_PAGE(PageSwapBacked(page), page);
- mapping_set_update(&xas, mapping);
- get_page(page);
- page->mapping = mapping;
- page->index = offset;
- if (!huge) {
- error = mem_cgroup_charge(page, current->mm, gfp);
- if (error)
- goto error;
- charged = true;
- }
- gfp &= GFP_RECLAIM_MASK;
- do {
- unsigned int order = xa_get_order(xas.xa, xas.xa_index);
- void *entry, *old = NULL;
- if (order > thp_order(page))
- xas_split_alloc(&xas, xa_load(xas.xa, xas.xa_index),
- order, gfp);
- xas_lock_irq(&xas);
- xas_for_each_conflict(&xas, entry) {
- old = entry;
- if (!xa_is_value(entry)) {
- xas_set_err(&xas, -EEXIST);
- goto unlock;
- }
- }
- if (old) {
- if (shadowp)
- *shadowp = old;
- /* entry may have been split before we acquired lock */
- order = xa_get_order(xas.xa, xas.xa_index);
- if (order > thp_order(page)) {
- xas_split(&xas, old, order);
- xas_reset(&xas);
- }
- }
- xas_store(&xas, page);
- if (xas_error(&xas))
- goto unlock;
- if (old)
- mapping->nrexceptional--;
- mapping->nrpages++;
- /* hugetlb pages do not participate in page cache accounting */
- if (!huge)
- __inc_lruvec_page_state(page, NR_FILE_PAGES);
- unlock:
- xas_unlock_irq(&xas);
- } while (xas_nomem(&xas, gfp));
- if (xas_error(&xas)) {
- error = xas_error(&xas);
- if (charged)
- mem_cgroup_uncharge(page);
- goto error;
- }
- trace_mm_filemap_add_to_page_cache(page);
- return 0;
- error:
- page->mapping = NULL;
- /* Leave page->index set: truncation relies upon it */
- put_page(page);
- return error;
- }
- ALLOW_ERROR_INJECTION(__add_to_page_cache_locked, ERRNO);
- /**
- * add_to_page_cache_locked - add a locked page to the pagecache
- * @page: page to add
- * @mapping: the page's address_space
- * @offset: page index
- * @gfp_mask: page allocation mode
- *
- * This function is used to add a page to the pagecache. It must be locked.
- * This function does not add the page to the LRU. The caller must do that.
- *
- * Return: %0 on success, negative error code otherwise.
- */
- int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
- pgoff_t offset, gfp_t gfp_mask)
- {
- return __add_to_page_cache_locked(page, mapping, offset,
- gfp_mask, NULL);
- }
- EXPORT_SYMBOL(add_to_page_cache_locked);
- int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
- pgoff_t offset, gfp_t gfp_mask)
- {
- void *shadow = NULL;
- int ret;
- __SetPageLocked(page);
- ret = __add_to_page_cache_locked(page, mapping, offset,
- gfp_mask, &shadow);
- if (unlikely(ret))
- __ClearPageLocked(page);
- else {
- /*
- * The page might have been evicted from cache only
- * recently, in which case it should be activated like
- * any other repeatedly accessed page.
- * The exception is pages getting rewritten; evicting other
- * data from the working set, only to cache data that will
- * get overwritten with something else, is a waste of memory.
- */
- WARN_ON_ONCE(PageActive(page));
- if (!(gfp_mask & __GFP_WRITE) && shadow)
- workingset_refault(page, shadow);
- lru_cache_add(page);
- }
- return ret;
- }
- EXPORT_SYMBOL_GPL(add_to_page_cache_lru);
- #ifdef CONFIG_NUMA
- struct page *__page_cache_alloc(gfp_t gfp)
- {
- int n;
- struct page *page;
- if (cpuset_do_page_mem_spread()) {
- unsigned int cpuset_mems_cookie;
- do {
- cpuset_mems_cookie = read_mems_allowed_begin();
- n = cpuset_mem_spread_node();
- page = __alloc_pages_node(n, gfp, 0);
- } while (!page && read_mems_allowed_retry(cpuset_mems_cookie));
- return page;
- }
- return alloc_pages(gfp, 0);
- }
- EXPORT_SYMBOL(__page_cache_alloc);
- #endif
- /*
- * In order to wait for pages to become available there must be
- * waitqueues associated with pages. By using a hash table of
- * waitqueues where the bucket discipline is to maintain all
- * waiters on the same queue and wake all when any of the pages
- * become available, and for the woken contexts to check to be
- * sure the appropriate page became available, this saves space
- * at a cost of "thundering herd" phenomena during rare hash
- * collisions.
- */
- #define PAGE_WAIT_TABLE_BITS 8
- #define PAGE_WAIT_TABLE_SIZE (1 << PAGE_WAIT_TABLE_BITS)
- static wait_queue_head_t page_wait_table[PAGE_WAIT_TABLE_SIZE] __cacheline_aligned;
- static wait_queue_head_t *page_waitqueue(struct page *page)
- {
- return &page_wait_table[hash_ptr(page, PAGE_WAIT_TABLE_BITS)];
- }
- void __init pagecache_init(void)
- {
- int i;
- for (i = 0; i < PAGE_WAIT_TABLE_SIZE; i++)
- init_waitqueue_head(&page_wait_table[i]);
- page_writeback_init();
- }
- /*
- * The page wait code treats the "wait->flags" somewhat unusually, because
- * we have multiple different kinds of waits, not just the usual "exclusive"
- * one.
- *
- * We have:
- *
- * (a) no special bits set:
- *
- * We're just waiting for the bit to be released, and when a waker
- * calls the wakeup function, we set WQ_FLAG_WOKEN and wake it up,
- * and remove it from the wait queue.
- *
- * Simple and straightforward.
- *
- * (b) WQ_FLAG_EXCLUSIVE:
- *
- * The waiter is waiting to get the lock, and only one waiter should
- * be woken up to avoid any thundering herd behavior. We'll set the
- * WQ_FLAG_WOKEN bit, wake it up, and remove it from the wait queue.
- *
- * This is the traditional exclusive wait.
- *
- * (c) WQ_FLAG_EXCLUSIVE | WQ_FLAG_CUSTOM:
- *
- * The waiter is waiting to get the bit, and additionally wants the
- * lock to be transferred to it for fair lock behavior. If the lock
- * cannot be taken, we stop walking the wait queue without waking
- * the waiter.
- *
- * This is the "fair lock handoff" case, and in addition to setting
- * WQ_FLAG_WOKEN, we set WQ_FLAG_DONE to let the waiter easily see
- * that it now has the lock.
- */
- static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync, void *arg)
- {
- unsigned int flags;
- struct wait_page_key *key = arg;
- struct wait_page_queue *wait_page
- = container_of(wait, struct wait_page_queue, wait);
- if (!wake_page_match(wait_page, key))
- return 0;
- /*
- * If it's a lock handoff wait, we get the bit for it, and
- * stop walking (and do not wake it up) if we can't.
- */
- flags = wait->flags;
- if (flags & WQ_FLAG_EXCLUSIVE) {
- if (test_bit(key->bit_nr, &key->page->flags))
- return -1;
- if (flags & WQ_FLAG_CUSTOM) {
- if (test_and_set_bit(key->bit_nr, &key->page->flags))
- return -1;
- flags |= WQ_FLAG_DONE;
- }
- }
- /*
- * We are holding the wait-queue lock, but the waiter that
- * is waiting for this will be checking the flags without
- * any locking.
- *
- * So update the flags atomically, and wake up the waiter
- * afterwards to avoid any races. This store-release pairs
- * with the load-acquire in wait_on_page_bit_common().
- */
- smp_store_release(&wait->flags, flags | WQ_FLAG_WOKEN);
- wake_up_state(wait->private, mode);
- /*
- * Ok, we have successfully done what we're waiting for,
- * and we can unconditionally remove the wait entry.
- *
- * Note that this pairs with the "finish_wait()" in the
- * waiter, and has to be the absolute last thing we do.
- * After this list_del_init(&wait->entry) the wait entry
- * might be de-allocated and the process might even have
- * exited.
- */
- list_del_init_careful(&wait->entry);
- return (flags & WQ_FLAG_EXCLUSIVE) != 0;
- }
- static void wake_up_page_bit(struct page *page, int bit_nr)
- {
- wait_queue_head_t *q = page_waitqueue(page);
- struct wait_page_key key;
- unsigned long flags;
- wait_queue_entry_t bookmark;
- key.page = page;
- key.bit_nr = bit_nr;
- key.page_match = 0;
- bookmark.flags = 0;
- bookmark.private = NULL;
- bookmark.func = NULL;
- INIT_LIST_HEAD(&bookmark.entry);
- spin_lock_irqsave(&q->lock, flags);
- __wake_up_locked_key_bookmark(q, TASK_NORMAL, &key, &bookmark);
- while (bookmark.flags & WQ_FLAG_BOOKMARK) {
- /*
- * Take a breather from holding the lock,
- * allow pages that finish wake up asynchronously
- * to acquire the lock and remove themselves
- * from wait queue
- */
- spin_unlock_irqrestore(&q->lock, flags);
- cpu_relax();
- spin_lock_irqsave(&q->lock, flags);
- __wake_up_locked_key_bookmark(q, TASK_NORMAL, &key, &bookmark);
- }
- /*
- * It is possible for other pages to have collided on the waitqueue
- * hash, so in that case check for a page match. That prevents a long-
- * term waiter
- *
- * It is still possible to miss a case here, when we woke page waiters
- * and removed them from the waitqueue, but there are still other
- * page waiters.
- */
- if (!waitqueue_active(q) || !key.page_match) {
- ClearPageWaiters(page);
- /*
- * It's possible to miss clearing Waiters here, when we woke
- * our page waiters, but the hashed waitqueue has waiters for
- * other pages on it.
- *
- * That's okay, it's a rare case. The next waker will clear it.
- */
- }
- spin_unlock_irqrestore(&q->lock, flags);
- }
- static void wake_up_page(struct page *page, int bit)
- {
- if (!PageWaiters(page))
- return;
- wake_up_page_bit(page, bit);
- }
- /*
- * A choice of three behaviors for wait_on_page_bit_common():
- */
- enum behavior {
- EXCLUSIVE, /* Hold ref to page and take the bit when woken, like
- * __lock_page() waiting on then setting PG_locked.
- */
- SHARED, /* Hold ref to page and check the bit when woken, like
- * wait_on_page_writeback() waiting on PG_writeback.
- */
- DROP, /* Drop ref to page before wait, no check when woken,
- * like put_and_wait_on_page_locked() on PG_locked.
- */
- };
- /*
- * Attempt to check (or get) the page bit, and mark us done
- * if successful.
- */
- static inline bool trylock_page_bit_common(struct page *page, int bit_nr,
- struct wait_queue_entry *wait)
- {
- if (wait->flags & WQ_FLAG_EXCLUSIVE) {
- if (test_and_set_bit(bit_nr, &page->flags))
- return false;
- } else if (test_bit(bit_nr, &page->flags))
- return false;
- wait->flags |= WQ_FLAG_WOKEN | WQ_FLAG_DONE;
- return true;
- }
- /* How many times do we accept lock stealing from under a waiter? */
- int sysctl_page_lock_unfairness = 5;
- static inline __sched int wait_on_page_bit_common(wait_queue_head_t *q,
- struct page *page, int bit_nr, int state, enum behavior behavior)
- {
- int unfairness = sysctl_page_lock_unfairness;
- struct wait_page_queue wait_page;
- wait_queue_entry_t *wait = &wait_page.wait;
- bool thrashing = false;
- bool delayacct = false;
- unsigned long pflags;
- if (bit_nr == PG_locked &&
- !PageUptodate(page) && PageWorkingset(page)) {
- if (!PageSwapBacked(page)) {
- delayacct_thrashing_start();
- delayacct = true;
- }
- psi_memstall_enter(&pflags);
- thrashing = true;
- }
- init_wait(wait);
- wait->func = wake_page_function;
- wait_page.page = page;
- wait_page.bit_nr = bit_nr;
- repeat:
- wait->flags = 0;
- if (behavior == EXCLUSIVE) {
- wait->flags = WQ_FLAG_EXCLUSIVE;
- if (--unfairness < 0)
- wait->flags |= WQ_FLAG_CUSTOM;
- }
- /*
- * Do one last check whether we can get the
- * page bit synchronously.
- *
- * Do the SetPageWaiters() marking before that
- * to let any waker we _just_ missed know they
- * need to wake us up (otherwise they'll never
- * even go to the slow case that looks at the
- * page queue), and add ourselves to the wait
- * queue if we need to sleep.
- *
- * This part needs to be done under the queue
- * lock to avoid races.
- */
- spin_lock_irq(&q->lock);
- SetPageWaiters(page);
- if (!trylock_page_bit_common(page, bit_nr, wait))
- __add_wait_queue_entry_tail(q, wait);
- spin_unlock_irq(&q->lock);
- /*
- * From now on, all the logic will be based on
- * the WQ_FLAG_WOKEN and WQ_FLAG_DONE flag, to
- * see whether the page bit testing has already
- * been done by the wake function.
- *
- * We can drop our reference to the page.
- */
- if (behavior == DROP)
- put_page(page);
- /*
- * Note that until the "finish_wait()", or until
- * we see the WQ_FLAG_WOKEN flag, we need to
- * be very careful with the 'wait->flags', because
- * we may race with a waker that sets them.
- */
- for (;;) {
- unsigned int flags;
- set_current_state(state);
- /* Loop until we've been woken or interrupted */
- flags = smp_load_acquire(&wait->flags);
- if (!(flags & WQ_FLAG_WOKEN)) {
- if (signal_pending_state(state, current))
- break;
- io_schedule();
- continue;
- }
- /* If we were non-exclusive, we're done */
- if (behavior != EXCLUSIVE)
- break;
- /* If the waker got the lock for us, we're done */
- if (flags & WQ_FLAG_DONE)
- break;
- /*
- * Otherwise, if we're getting the lock, we need to
- * try to get it ourselves.
- *
- * And if that fails, we'll have to retry this all.
- */
- if (unlikely(test_and_set_bit(bit_nr, &page->flags)))
- goto repeat;
- wait->flags |= WQ_FLAG_DONE;
- break;
- }
- /*
- * If a signal happened, this 'finish_wait()' may remove the last
- * waiter from the wait-queues, but the PageWaiters bit will remain
- * set. That's ok. The next wakeup will take care of it, and trying
- * to do it here would be difficult and prone to races.
- */
- finish_wait(q, wait);
- if (thrashing) {
- if (delayacct)
- delayacct_thrashing_end();
- psi_memstall_leave(&pflags);
- }
- /*
- * NOTE! The wait->flags weren't stable until we've done the
- * 'finish_wait()', and we could have exited the loop above due
- * to a signal, and had a wakeup event happen after the signal
- * test but before the 'finish_wait()'.
- *
- * So only after the finish_wait() can we reliably determine
- * if we got woken up or not, so we can now figure out the final
- * return value based on that state without races.
- *
- * Also note that WQ_FLAG_WOKEN is sufficient for a non-exclusive
- * waiter, but an exclusive one requires WQ_FLAG_DONE.
- */
- if (behavior == EXCLUSIVE)
- return wait->flags & WQ_FLAG_DONE ? 0 : -EINTR;
- return wait->flags & WQ_FLAG_WOKEN ? 0 : -EINTR;
- }
- __sched void wait_on_page_bit(struct page *page, int bit_nr)
- {
- wait_queue_head_t *q = page_waitqueue(page);
- wait_on_page_bit_common(q, page, bit_nr, TASK_UNINTERRUPTIBLE, SHARED);
- }
- EXPORT_SYMBOL(wait_on_page_bit);
- __sched int wait_on_page_bit_killable(struct page *page, int bit_nr)
- {
- wait_queue_head_t *q = page_waitqueue(page);
- return wait_on_page_bit_common(q, page, bit_nr, TASK_KILLABLE, SHARED);
- }
- EXPORT_SYMBOL(wait_on_page_bit_killable);
- static int __wait_on_page_locked_async(struct page *page,
- struct wait_page_queue *wait, bool set)
- {
- struct wait_queue_head *q = page_waitqueue(page);
- int ret = 0;
- wait->page = page;
- wait->bit_nr = PG_locked;
- spin_lock_irq(&q->lock);
- __add_wait_queue_entry_tail(q, &wait->wait);
- SetPageWaiters(page);
- if (set)
- ret = !trylock_page(page);
- else
- ret = PageLocked(page);
- /*
- * If we were succesful now, we know we're still on the
- * waitqueue as we're still under the lock. This means it's
- * safe to remove and return success, we know the callback
- * isn't going to trigger.
- */
- if (!ret)
- __remove_wait_queue(q, &wait->wait);
- else
- ret = -EIOCBQUEUED;
- spin_unlock_irq(&q->lock);
- return ret;
- }
- static int wait_on_page_locked_async(struct page *page,
- struct wait_page_queue *wait)
- {
- if (!PageLocked(page))
- return 0;
- return __wait_on_page_locked_async(compound_head(page), wait, false);
- }
- /**
- * put_and_wait_on_page_locked - Drop a reference and wait for it to be unlocked
- * @page: The page to wait for.
- *
- * The caller should hold a reference on @page. They expect the page to
- * become unlocked relatively soon, but do not wish to hold up migration
- * (for example) by holding the reference while waiting for the page to
- * come unlocked. After this function returns, the caller should not
- * dereference @page.
- */
- void put_and_wait_on_page_locked(struct page *page)
- {
- wait_queue_head_t *q;
- page = compound_head(page);
- q = page_waitqueue(page);
- wait_on_page_bit_common(q, page, PG_locked, TASK_UNINTERRUPTIBLE, DROP);
- }
- /**
- * add_page_wait_queue - Add an arbitrary waiter to a page's wait queue
- * @page: Page defining the wait queue of interest
- * @waiter: Waiter to add to the queue
- *
- * Add an arbitrary @waiter to the wait queue for the nominated @page.
- */
- void add_page_wait_queue(struct page *page, wait_queue_entry_t *waiter)
- {
- wait_queue_head_t *q = page_waitqueue(page);
- unsigned long flags;
- spin_lock_irqsave(&q->lock, flags);
- __add_wait_queue_entry_tail(q, waiter);
- SetPageWaiters(page);
- spin_unlock_irqrestore(&q->lock, flags);
- }
- EXPORT_SYMBOL_GPL(add_page_wait_queue);
- #ifndef clear_bit_unlock_is_negative_byte
- /*
- * PG_waiters is the high bit in the same byte as PG_lock.
- *
- * On x86 (and on many other architectures), we can clear PG_lock and
- * test the sign bit at the same time. But if the architecture does
- * not support that special operation, we just do this all by hand
- * instead.
- *
- * The read of PG_waiters has to be after (or concurrently with) PG_locked
- * being cleared, but a memory barrier should be unnecessary since it is
- * in the same byte as PG_locked.
- */
- static inline bool clear_bit_unlock_is_negative_byte(long nr, volatile void *mem)
- {
- clear_bit_unlock(nr, mem);
- /* smp_mb__after_atomic(); */
- return test_bit(PG_waiters, mem);
- }
- #endif
- /**
- * unlock_page - unlock a locked page
- * @page: the page
- *
- * Unlocks the page and wakes up sleepers in wait_on_page_locked().
- * Also wakes sleepers in wait_on_page_writeback() because the wakeup
- * mechanism between PageLocked pages and PageWriteback pages is shared.
- * But that's OK - sleepers in wait_on_page_writeback() just go back to sleep.
- *
- * Note that this depends on PG_waiters being the sign bit in the byte
- * that contains PG_locked - thus the BUILD_BUG_ON(). That allows us to
- * clear the PG_locked bit and test PG_waiters at the same time fairly
- * portably (architectures that do LL/SC can test any bit, while x86 can
- * test the sign bit).
- */
- void unlock_page(struct page *page)
- {
- BUILD_BUG_ON(PG_waiters != 7);
- page = compound_head(page);
- VM_BUG_ON_PAGE(!PageLocked(page), page);
- if (clear_bit_unlock_is_negative_byte(PG_locked, &page->flags))
- wake_up_page_bit(page, PG_locked);
- }
- EXPORT_SYMBOL(unlock_page);
- /**
- * end_page_writeback - end writeback against a page
- * @page: the page
- */
- void end_page_writeback(struct page *page)
- {
- /*
- * TestClearPageReclaim could be used here but it is an atomic
- * operation and overkill in this particular case. Failing to
- * shuffle a page marked for immediate reclaim is too mild to
- * justify taking an atomic operation penalty at the end of
- * ever page writeback.
- */
- if (PageReclaim(page)) {
- ClearPageReclaim(page);
- rotate_reclaimable_page(page);
- }
- /*
- * Writeback does not hold a page reference of its own, relying
- * on truncation to wait for the clearing of PG_writeback.
- * But here we must make sure that the page is not freed and
- * reused before the wake_up_page().
- */
- get_page(page);
- if (!test_clear_page_writeback(page))
- BUG();
- smp_mb__after_atomic();
- wake_up_page(page, PG_writeback);
- put_page(page);
- }
- EXPORT_SYMBOL(end_page_writeback);
- /*
- * After completing I/O on a page, call this routine to update the page
- * flags appropriately
- */
- void page_endio(struct page *page, bool is_write, int err)
- {
- if (!is_write) {
- if (!err) {
- SetPageUptodate(page);
- } else {
- ClearPageUptodate(page);
- SetPageError(page);
- }
- unlock_page(page);
- } else {
- if (err) {
- struct address_space *mapping;
- SetPageError(page);
- mapping = page_mapping(page);
- if (mapping)
- mapping_set_error(mapping, err);
- }
- end_page_writeback(page);
- }
- }
- EXPORT_SYMBOL_GPL(page_endio);
- /**
- * __lock_page - get a lock on the page, assuming we need to sleep to get it
- * @__page: the page to lock
- */
- __sched void __lock_page(struct page *__page)
- {
- struct page *page = compound_head(__page);
- wait_queue_head_t *q = page_waitqueue(page);
- wait_on_page_bit_common(q, page, PG_locked, TASK_UNINTERRUPTIBLE,
- EXCLUSIVE);
- }
- EXPORT_SYMBOL(__lock_page);
- __sched int __lock_page_killable(struct page *__page)
- {
- struct page *page = compound_head(__page);
- wait_queue_head_t *q = page_waitqueue(page);
- return wait_on_page_bit_common(q, page, PG_locked, TASK_KILLABLE,
- EXCLUSIVE);
- }
- EXPORT_SYMBOL_GPL(__lock_page_killable);
- __sched int __lock_page_async(struct page *page, struct wait_page_queue *wait)
- {
- return __wait_on_page_locked_async(page, wait, true);
- }
- /*
- * Return values:
- * 1 - page is locked; mmap_lock is still held.
- * 0 - page is not locked.
- * mmap_lock has been released (mmap_read_unlock(), unless flags had both
- * FAULT_FLAG_ALLOW_RETRY and FAULT_FLAG_RETRY_NOWAIT set, in
- * which case mmap_lock is still held.
- *
- * If neither ALLOW_RETRY nor KILLABLE are set, will always return 1
- * with the page locked and the mmap_lock unperturbed.
- */
- __sched int __lock_page_or_retry(struct page *page, struct mm_struct *mm,
- unsigned int flags)
- {
- if (fault_flag_allow_retry_first(flags)) {
- /*
- * CAUTION! In this case, mmap_lock is not released
- * even though return 0.
- */
- if (flags & FAULT_FLAG_RETRY_NOWAIT)
- return 0;
- mmap_read_unlock(mm);
- if (flags & FAULT_FLAG_KILLABLE)
- wait_on_page_locked_killable(page);
- else
- wait_on_page_locked(page);
- return 0;
- } else {
- if (flags & FAULT_FLAG_KILLABLE) {
- int ret;
- ret = __lock_page_killable(page);
- if (ret) {
- mmap_read_unlock(mm);
- return 0;
- }
- } else
- __lock_page(page);
- return 1;
- }
- }
- /**
- * page_cache_next_miss() - Find the next gap in the page cache.
- * @mapping: Mapping.
- * @index: Index.
- * @max_scan: Maximum range to search.
- *
- * Search the range [index, min(index + max_scan - 1, ULONG_MAX)] for the
- * gap with the lowest index.
- *
- * This function may be called under the rcu_read_lock. However, this will
- * not atomically search a snapshot of the cache at a single point in time.
- * For example, if a gap is created at index 5, then subsequently a gap is
- * created at index 10, page_cache_next_miss covering both indices may
- * return 10 if called under the rcu_read_lock.
- *
- * Return: The index of the gap if found, otherwise an index outside the
- * range specified (in which case 'return - index >= max_scan' will be true).
- * In the rare case of index wrap-around, 0 will be returned.
- */
- pgoff_t page_cache_next_miss(struct address_space *mapping,
- pgoff_t index, unsigned long max_scan)
- {
- XA_STATE(xas, &mapping->i_pages, index);
- while (max_scan--) {
- void *entry = xas_next(&xas);
- if (!entry || xa_is_value(entry))
- break;
- if (xas.xa_index == 0)
- break;
- }
- return xas.xa_index;
- }
- EXPORT_SYMBOL(page_cache_next_miss);
- /**
- * page_cache_prev_miss() - Find the previous gap in the page cache.
- * @mapping: Mapping.
- * @index: Index.
- * @max_scan: Maximum range to search.
- *
- * Search the range [max(index - max_scan + 1, 0), index] for the
- * gap with the highest index.
- *
- * This function may be called under the rcu_read_lock. However, this will
- * not atomically search a snapshot of the cache at a single point in time.
- * For example, if a gap is created at index 10, then subsequently a gap is
- * created at index 5, page_cache_prev_miss() covering both indices may
- * return 5 if called under the rcu_read_lock.
- *
- * Return: The index of the gap if found, otherwise an index outside the
- * range specified (in which case 'index - return >= max_scan' will be true).
- * In the rare case of wrap-around, ULONG_MAX will be returned.
- */
- pgoff_t page_cache_prev_miss(struct address_space *mapping,
- pgoff_t index, unsigned long max_scan)
- {
- XA_STATE(xas, &mapping->i_pages, index);
- while (max_scan--) {
- void *entry = xas_prev(&xas);
- if (!entry || xa_is_value(entry))
- break;
- if (xas.xa_index == ULONG_MAX)
- break;
- }
- return xas.xa_index;
- }
- EXPORT_SYMBOL(page_cache_prev_miss);
- /**
- * find_get_entry - find and get a page cache entry
- * @mapping: the address_space to search
- * @index: The page cache index.
- *
- * Looks up the page cache slot at @mapping & @offset. If there is a
- * page cache page, the head page is returned with an increased refcount.
- *
- * If the slot holds a shadow entry of a previously evicted page, or a
- * swap entry from shmem/tmpfs, it is returned.
- *
- * Return: The head page or shadow entry, %NULL if nothing is found.
- */
- struct page *find_get_entry(struct address_space *mapping, pgoff_t index)
- {
- XA_STATE(xas, &mapping->i_pages, index);
- struct page *page;
- rcu_read_lock();
- repeat:
- xas_reset(&xas);
- page = xas_load(&xas);
- if (xas_retry(&xas, page))
- goto repeat;
- /*
- * A shadow entry of a recently evicted page, or a swap entry from
- * shmem/tmpfs. Return it without attempting to raise page count.
- */
- if (!page || xa_is_value(page))
- goto out;
- if (!page_cache_get_speculative(page))
- goto repeat;
- /*
- * Has the page moved or been split?
- * This is part of the lockless pagecache protocol. See
- * include/linux/pagemap.h for details.
- */
- if (unlikely(page != xas_reload(&xas))) {
- put_page(page);
- goto repeat;
- }
- out:
- rcu_read_unlock();
- return page;
- }
- /**
- * find_lock_entry - Locate and lock a page cache entry.
- * @mapping: The address_space to search.
- * @index: The page cache index.
- *
- * Looks up the page at @mapping & @index. If there is a page in the
- * cache, the head page is returned locked and with an increased refcount.
- *
- * If the slot holds a shadow entry of a previously evicted page, or a
- * swap entry from shmem/tmpfs, it is returned.
- *
- * Context: May sleep.
- * Return: The head page or shadow entry, %NULL if nothing is found.
- */
- struct page *find_lock_entry(struct address_space *mapping, pgoff_t index)
- {
- struct page *page;
- repeat:
- page = find_get_entry(mapping, index);
- if (page && !xa_is_value(page)) {
- lock_page(page);
- /* Has the page been truncated? */
- if (unlikely(page->mapping != mapping)) {
- unlock_page(page);
- put_page(page);
- goto repeat;
- }
- VM_BUG_ON_PAGE(!thp_contains(page, index), page);
- }
- return page;
- }
- /**
- * pagecache_get_page - Find and get a reference to a page.
- * @mapping: The address_space to search.
- * @index: The page index.
- * @fgp_flags: %FGP flags modify how the page is returned.
- * @gfp_mask: Memory allocation flags to use if %FGP_CREAT is specified.
- *
- * Looks up the page cache entry at @mapping & @index.
- *
- * @fgp_flags can be zero or more of these flags:
- *
- * * %FGP_ACCESSED - The page will be marked accessed.
- * * %FGP_LOCK - The page is returned locked.
- * * %FGP_HEAD - If the page is present and a THP, return the head page
- * rather than the exact page specified by the index.
- * * %FGP_CREAT - If no page is present then 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.
- * * %FGP_FOR_MMAP - The caller wants to do its own locking dance if the
- * page is already in cache. If the page was allocated, unlock it before
- * returning so the caller can do the same dance.
- * * %FGP_WRITE - The page will be written
- * * %FGP_NOFS - __GFP_FS will get cleared in gfp mask
- * * %FGP_NOWAIT - Don't get blocked by page lock
- *
- * If %FGP_LOCK or %FGP_CREAT are specified then the function may sleep even
- * if the %GFP flags specified for %FGP_CREAT are atomic.
- *
- * If there is a page cache page, it is returned with an increased refcount.
- *
- * Return: The found page or %NULL otherwise.
- */
- struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index,
- int fgp_flags, gfp_t gfp_mask)
- {
- struct page *page;
- repeat:
- page = find_get_entry(mapping, index);
- if (xa_is_value(page))
- page = NULL;
- trace_android_vh_pagecache_get_page(mapping, index, fgp_flags,
- gfp_mask, page);
- if (!page)
- goto no_page;
- if (fgp_flags & FGP_LOCK) {
- if (fgp_flags & FGP_NOWAIT) {
- if (!trylock_page(page)) {
- put_page(page);
- return NULL;
- }
- } else {
- lock_page(page);
- }
- /* Has the page been truncated? */
- if (unlikely(page->mapping != mapping)) {
- unlock_page(page);
- put_page(page);
- goto repeat;
- }
- VM_BUG_ON_PAGE(!thp_contains(page, index), page);
- }
- if (fgp_flags & FGP_ACCESSED)
- mark_page_accessed(page);
- else if (fgp_flags & FGP_WRITE) {
- /* Clear idle flag for buffer write */
- if (page_is_idle(page))
- clear_page_idle(page);
- }
- if (!(fgp_flags & FGP_HEAD))
- page = find_subpage(page, index);
- no_page:
- if (!page && (fgp_flags & FGP_CREAT)) {
- int err;
- if ((fgp_flags & FGP_WRITE) && mapping_can_writeback(mapping))
- gfp_mask |= __GFP_WRITE;
- if (fgp_flags & FGP_NOFS)
- gfp_mask &= ~__GFP_FS;
- page = __page_cache_alloc(gfp_mask);
- if (!page)
- return NULL;
- if (WARN_ON_ONCE(!(fgp_flags & (FGP_LOCK | FGP_FOR_MMAP))))
- fgp_flags |= FGP_LOCK;
- /* Init accessed so avoid atomic mark_page_accessed later */
- if (fgp_flags & FGP_ACCESSED)
- __SetPageReferenced(page);
- err = add_to_page_cache_lru(page, mapping, index, gfp_mask);
- if (unlikely(err)) {
- put_page(page);
- page = NULL;
- if (err == -EEXIST)
- goto repeat;
- }
- /*
- * add_to_page_cache_lru locks the page, and for mmap we expect
- * an unlocked page.
- */
- if (page && (fgp_flags & FGP_FOR_MMAP))
- unlock_page(page);
- }
- return page;
- }
- EXPORT_SYMBOL(pagecache_get_page);
- /**
- * find_get_entries - gang pagecache lookup
- * @mapping: The address_space to search
- * @start: The starting page cache index
- * @nr_entries: The maximum number of entries
- * @entries: Where the resulting entries are placed
- * @indices: The cache indices corresponding to the entries in @entries
- *
- * find_get_entries() will search for and return a group of up to
- * @nr_entries entries in the mapping. The entries are placed at
- * @entries. find_get_entries() takes a reference against any actual
- * pages it returns.
- *
- * The search returns a group of mapping-contiguous page cache entries
- * with ascending indexes. There may be holes in the indices due to
- * not-present pages.
- *
- * Any shadow entries of evicted pages, or swap entries from
- * shmem/tmpfs, are included in the returned array.
- *
- * If it finds a Transparent Huge Page, head or tail, find_get_entries()
- * stops at that page: the caller is likely to have a better way to handle
- * the compound page as a whole, and then skip its extent, than repeatedly
- * calling find_get_entries() to return all its tails.
- *
- * Return: the number of pages and shadow entries which were found.
- */
- unsigned find_get_entries(struct address_space *mapping,
- pgoff_t start, unsigned int nr_entries,
- struct page **entries, pgoff_t *indices)
- {
- XA_STATE(xas, &mapping->i_pages, start);
- struct page *page;
- unsigned int ret = 0;
- if (!nr_entries)
- return 0;
- rcu_read_lock();
- xas_for_each(&xas, page, ULONG_MAX) {
- if (xas_retry(&xas, page))
- continue;
- /*
- * A shadow entry of a recently evicted page, a swap
- * entry from shmem/tmpfs or a DAX entry. Return it
- * without attempting to raise page count.
- */
- if (xa_is_value(page))
- goto export;
- if (!page_cache_get_speculative(page))
- goto retry;
- /* Has the page moved or been split? */
- if (unlikely(page != xas_reload(&xas)))
- goto put_page;
- /*
- * Terminate early on finding a THP, to allow the caller to
- * handle it all at once; but continue if this is hugetlbfs.
- */
- if (PageTransHuge(page) && !PageHuge(page)) {
- page = find_subpage(page, xas.xa_index);
- nr_entries = ret + 1;
- }
- export:
- indices[ret] = xas.xa_index;
- entries[ret] = page;
- if (++ret == nr_entries)
- break;
- continue;
- put_page:
- put_page(page);
- retry:
- xas_reset(&xas);
- }
- rcu_read_unlock();
- return ret;
- }
- /**
- * find_get_pages_range - gang pagecache lookup
- * @mapping: The address_space to search
- * @start: The starting page index
- * @end: The final page index (inclusive)
- * @nr_pages: The maximum number of pages
- * @pages: Where the resulting pages are placed
- *
- * find_get_pages_range() will search for and return a group of up to @nr_pages
- * pages in the mapping starting at index @start and up to index @end
- * (inclusive). The pages are placed at @pages. find_get_pages_range() takes
- * a reference against the returned pages.
- *
- * The search returns a group of mapping-contiguous pages with ascending
- * indexes. There may be holes in the indices due to not-present pages.
- * We also update @start to index the next page for the traversal.
- *
- * Return: the number of pages which were found. If this number is
- * smaller than @nr_pages, the end of specified range has been
- * reached.
- */
- unsigned find_get_pages_range(struct address_space *mapping, pgoff_t *start,
- pgoff_t end, unsigned int nr_pages,
- struct page **pages)
- {
- XA_STATE(xas, &mapping->i_pages, *start);
- struct page *page;
- unsigned ret = 0;
- if (unlikely(!nr_pages))
- return 0;
- rcu_read_lock();
- xas_for_each(&xas, page, end) {
- if (xas_retry(&xas, page))
- continue;
- /* Skip over shadow, swap and DAX entries */
- if (xa_is_value(page))
- continue;
- if (!page_cache_get_speculative(page))
- goto retry;
- /* Has the page moved or been split? */
- if (unlikely(page != xas_reload(&xas)))
- goto put_page;
- pages[ret] = find_subpage(page, xas.xa_index);
- if (++ret == nr_pages) {
- *start = xas.xa_index + 1;
- goto out;
- }
- continue;
- put_page:
- put_page(page);
- retry:
- xas_reset(&xas);
- }
- /*
- * We come here when there is no page beyond @end. We take care to not
- * overflow the index @start as it confuses some of the callers. This
- * breaks the iteration when there is a page at index -1 but that is
- * already broken anyway.
- */
- if (end == (pgoff_t)-1)
- *start = (pgoff_t)-1;
- else
- *start = end + 1;
- out:
- rcu_read_unlock();
- return ret;
- }
- /**
- * find_get_pages_contig - gang contiguous pagecache lookup
- * @mapping: The address_space to search
- * @index: The starting page index
- * @nr_pages: The maximum number of pages
- * @pages: Where the resulting pages are placed
- *
- * find_get_pages_contig() works exactly like find_get_pages(), except
- * that the returned number of pages are guaranteed to be contiguous.
- *
- * Return: the number of pages which were found.
- */
- unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index,
- unsigned int nr_pages, struct page **pages)
- {
- XA_STATE(xas, &mapping->i_pages, index);
- struct page *page;
- unsigned int ret = 0;
- if (unlikely(!nr_pages))
- return 0;
- rcu_read_lock();
- for (page = xas_load(&xas); page; page = xas_next(&xas)) {
- if (xas_retry(&xas, page))
- continue;
- /*
- * If the entry has been swapped out, we can stop looking.
- * No current caller is looking for DAX entries.
- */
- if (xa_is_value(page))
- break;
- if (!page_cache_get_speculative(page))
- goto retry;
- /* Has the page moved or been split? */
- if (unlikely(page != xas_reload(&xas)))
- goto put_page;
- pages[ret] = find_subpage(page, xas.xa_index);
- if (++ret == nr_pages)
- break;
- continue;
- put_page:
- put_page(page);
- retry:
- xas_reset(&xas);
- }
- rcu_read_unlock();
- return ret;
- }
- EXPORT_SYMBOL(find_get_pages_contig);
- /**
- * find_get_pages_range_tag - find and return pages in given range matching @tag
- * @mapping: the address_space to search
- * @index: the starting page index
- * @end: The final page index (inclusive)
- * @tag: the tag index
- * @nr_pages: the maximum number of pages
- * @pages: where the resulting pages are placed
- *
- * Like find_get_pages, except we only return pages which are tagged with
- * @tag. We update @index to index the next page for the traversal.
- *
- * Return: the number of pages which were found.
- */
- 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)
- {
- XA_STATE(xas, &mapping->i_pages, *index);
- struct page *page;
- unsigned ret = 0;
- if (unlikely(!nr_pages))
- return 0;
- rcu_read_lock();
- xas_for_each_marked(&xas, page, end, tag) {
- if (xas_retry(&xas, page))
- continue;
- /*
- * Shadow entries should never be tagged, but this iteration
- * is lockless so there is a window for page reclaim to evict
- * a page we saw tagged. Skip over it.
- */
- if (xa_is_value(page))
- continue;
- if (!page_cache_get_speculative(page))
- goto retry;
- /* Has the page moved or been split? */
- if (unlikely(page != xas_reload(&xas)))
- goto put_page;
- pages[ret] = find_subpage(page, xas.xa_index);
- if (++ret == nr_pages) {
- *index = xas.xa_index + 1;
- goto out;
- }
- continue;
- put_page:
- put_page(page);
- retry:
- xas_reset(&xas);
- }
- /*
- * We come here when we got to @end. We take care to not overflow the
- * index @index as it confuses some of the callers. This breaks the
- * iteration when there is a page at index -1 but that is already
- * broken anyway.
- */
- if (end == (pgoff_t)-1)
- *index = (pgoff_t)-1;
- else
- *index = end + 1;
- out:
- rcu_read_unlock();
- return ret;
- }
- EXPORT_SYMBOL(find_get_pages_range_tag);
- /*
- * CD/DVDs are error prone. When a medium error occurs, the driver may fail
- * a _large_ part of the i/o request. Imagine the worst scenario:
- *
- * ---R__________________________________________B__________
- * ^ reading here ^ bad block(assume 4k)
- *
- * read(R) => miss => readahead(R...B) => media error => frustrating retries
- * => failing the whole request => read(R) => read(R+1) =>
- * readahead(R+1...B+1) => bang => read(R+2) => read(R+3) =>
- * readahead(R+3...B+2) => bang => read(R+3) => read(R+4) =>
- * readahead(R+4...B+3) => bang => read(R+4) => read(R+5) => ......
- *
- * It is going insane. Fix it by quickly scaling down the readahead size.
- */
- static void shrink_readahead_size_eio(struct file_ra_state *ra)
- {
- ra->ra_pages /= 4;
- }
- /**
- * generic_file_buffered_read - generic file read routine
- * @iocb: the iocb to read
- * @iter: data destination
- * @written: already copied
- *
- * This is a generic file read routine, and uses the
- * mapping->a_ops->readpage() function for the actual low-level stuff.
- *
- * This is really ugly. But the goto's actually try to clarify some
- * of the logic when it comes to error handling etc.
- *
- * Return:
- * * total number of bytes copied, including those the were already @written
- * * negative error code if nothing was copied
- */
- ssize_t generic_file_buffered_read(struct kiocb *iocb,
- struct iov_iter *iter, ssize_t written)
- {
- struct file *filp = iocb->ki_filp;
- struct address_space *mapping = filp->f_mapping;
- struct inode *inode = mapping->host;
- struct file_ra_state *ra = &filp->f_ra;
- loff_t *ppos = &iocb->ki_pos;
- pgoff_t index;
- pgoff_t last_index;
- pgoff_t prev_index;
- unsigned long offset; /* offset into pagecache page */
- unsigned int prev_offset;
- int error = 0;
- if (unlikely(*ppos >= inode->i_sb->s_maxbytes))
- return 0;
- iov_iter_truncate(iter, inode->i_sb->s_maxbytes);
- index = *ppos >> PAGE_SHIFT;
- prev_index = ra->prev_pos >> PAGE_SHIFT;
- prev_offset = ra->prev_pos & (PAGE_SIZE-1);
- last_index = (*ppos + iter->count + PAGE_SIZE-1) >> PAGE_SHIFT;
- offset = *ppos & ~PAGE_MASK;
- /*
- * If we've already successfully copied some data, then we
- * can no longer safely return -EIOCBQUEUED. Hence mark
- * an async read NOWAIT at that point.
- */
- if (written && (iocb->ki_flags & IOCB_WAITQ))
- iocb->ki_flags |= IOCB_NOWAIT;
- for (;;) {
- struct page *page;
- pgoff_t end_index;
- loff_t isize;
- unsigned long nr, ret;
- cond_resched();
- find_page:
- if (fatal_signal_pending(current)) {
- error = -EINTR;
- goto out;
- }
- page = find_get_page(mapping, index);
- if (!page) {
- if (iocb->ki_flags & IOCB_NOIO)
- goto would_block;
- page_cache_sync_readahead(mapping,
- ra, filp,
- index, last_index - index);
- page = find_get_page(mapping, index);
- if (unlikely(page == NULL))
- goto no_cached_page;
- }
- if (PageReadahead(page)) {
- if (iocb->ki_flags & IOCB_NOIO) {
- put_page(page);
- goto out;
- }
- page_cache_async_readahead(mapping,
- ra, filp, page,
- index, last_index - index);
- }
- if (!PageUptodate(page)) {
- /*
- * See comment in do_read_cache_page on why
- * wait_on_page_locked is used to avoid unnecessarily
- * serialisations and why it's safe.
- */
- if (iocb->ki_flags & IOCB_WAITQ) {
- if (written) {
- put_page(page);
- goto out;
- }
- error = wait_on_page_locked_async(page,
- iocb->ki_waitq);
- } else {
- if (iocb->ki_flags & IOCB_NOWAIT) {
- put_page(page);
- goto would_block;
- }
- error = wait_on_page_locked_killable(page);
- }
- if (unlikely(error))
- goto readpage_error;
- if (PageUptodate(page))
- goto page_ok;
- if (inode->i_blkbits == PAGE_SHIFT ||
- !mapping->a_ops->is_partially_uptodate)
- goto page_not_up_to_date;
- /* pipes can't handle partially uptodate pages */
- if (unlikely(iov_iter_is_pipe(iter)))
- goto page_not_up_to_date;
- if (!trylock_page(page))
- goto page_not_up_to_date;
- /* Did it get truncated before we got the lock? */
- if (!page->mapping)
- goto page_not_up_to_date_locked;
- if (!mapping->a_ops->is_partially_uptodate(page,
- offset, iter->count))
- goto page_not_up_to_date_locked;
- unlock_page(page);
- }
- page_ok:
- /*
- * i_size must be checked after we know the page is Uptodate.
- *
- * Checking i_size after the check allows us to calculate
- * the correct value for "nr", which means the zero-filled
- * part of the page is not copied back to userspace (unless
- * another truncate extends the file - this is desired though).
- */
- isize = i_size_read(inode);
- end_index = (isize - 1) >> PAGE_SHIFT;
- if (unlikely(!isize || index > end_index)) {
- put_page(page);
- goto out;
- }
- /* nr is the maximum number of bytes to copy from this page */
- nr = PAGE_SIZE;
- if (index == end_index) {
- nr = ((isize - 1) & ~PAGE_MASK) + 1;
- if (nr <= offset) {
- put_page(page);
- goto out;
- }
- }
- nr = nr - offset;
- /* If users can be writing to this page using arbitrary
- * virtual addresses, take care about potential aliasing
- * before reading the page on the kernel side.
- */
- if (mapping_writably_mapped(mapping))
- flush_dcache_page(page);
- /*
- * When a sequential read accesses a page several times,
- * only mark it as accessed the first time.
- */
- if (prev_index != index || offset != prev_offset)
- mark_page_accessed(page);
- prev_index = index;
- /*
- * Ok, we have the page, and it's up-to-date, so
- * now we can copy it to user space...
- */
- ret = copy_page_to_iter(page, offset, nr, iter);
- offset += ret;
- index += offset >> PAGE_SHIFT;
- offset &= ~PAGE_MASK;
- prev_offset = offset;
- put_page(page);
- written += ret;
- if (!iov_iter_count(iter))
- goto out;
- if (ret < nr) {
- error = -EFAULT;
- goto out;
- }
- continue;
- page_not_up_to_date:
- /* Get exclusive access to the page ... */
- if (iocb->ki_flags & IOCB_WAITQ) {
- if (written) {
- put_page(page);
- goto out;
- }
- error = lock_page_async(page, iocb->ki_waitq);
- } else {
- error = lock_page_killable(page);
- }
- if (unlikely(error))
- goto readpage_error;
- page_not_up_to_date_locked:
- /* Did it get truncated before we got the lock? */
- if (!page->mapping) {
- unlock_page(page);
- put_page(page);
- continue;
- }
- /* Did somebody else fill it already? */
- if (PageUptodate(page)) {
- unlock_page(page);
- goto page_ok;
- }
- readpage:
- if (iocb->ki_flags & (IOCB_NOIO | IOCB_NOWAIT)) {
- unlock_page(page);
- put_page(page);
- goto would_block;
- }
- /*
- * A previous I/O error may have been due to temporary
- * failures, eg. multipath errors.
- * PG_error will be set again if readpage fails.
- */
- ClearPageError(page);
- /* Start the actual read. The read will unlock the page. */
- error = mapping->a_ops->readpage(filp, page);
- if (unlikely(error)) {
- if (error == AOP_TRUNCATED_PAGE) {
- put_page(page);
- error = 0;
- goto find_page;
- }
- goto readpage_error;
- }
- if (!PageUptodate(page)) {
- if (iocb->ki_flags & IOCB_WAITQ) {
- if (written) {
- put_page(page);
- goto out;
- }
- error = lock_page_async(page, iocb->ki_waitq);
- } else {
- error = lock_page_killable(page);
- }
- if (unlikely(error))
- goto readpage_error;
- if (!PageUptodate(page)) {
- if (page->mapping == NULL) {
- /*
- * invalidate_mapping_pages got it
- */
- unlock_page(page);
- put_page(page);
- goto find_page;
- }
- unlock_page(page);
- shrink_readahead_size_eio(ra);
- error = -EIO;
- goto readpage_error;
- }
- unlock_page(page);
- }
- goto page_ok;
- readpage_error:
- /* UHHUH! A synchronous read error occurred. Report it */
- put_page(page);
- goto out;
- no_cached_page:
- /*
- * Ok, it wasn't cached, so we need to create a new
- * page..
- */
- page = page_cache_alloc(mapping);
- if (!page) {
- error = -ENOMEM;
- goto out;
- }
- error = add_to_page_cache_lru(page, mapping, index,
- mapping_gfp_constraint(mapping, GFP_KERNEL));
- if (error) {
- put_page(page);
- if (error == -EEXIST) {
- error = 0;
- goto find_page;
- }
- goto out;
- }
- goto readpage;
- }
- would_block:
- error = -EAGAIN;
- out:
- ra->prev_pos = prev_index;
- ra->prev_pos <<= PAGE_SHIFT;
- ra->prev_pos |= prev_offset;
- *ppos = ((loff_t)index << PAGE_SHIFT) + offset;
- file_accessed(filp);
- return written ? written : error;
- }
- EXPORT_SYMBOL_GPL(generic_file_buffered_read);
- /**
- * generic_file_read_iter - generic filesystem read routine
- * @iocb: kernel I/O control block
- * @iter: destination for the data read
- *
- * This is the "read_iter()" routine for all filesystems
- * that can use the page cache directly.
- *
- * The IOCB_NOWAIT flag in iocb->ki_flags indicates that -EAGAIN shall
- * be returned when no data can be read without waiting for I/O requests
- * to complete; it doesn't prevent readahead.
- *
- * The IOCB_NOIO flag in iocb->ki_flags indicates that no new I/O
- * requests shall be made for the read or for readahead. When no data
- * can be read, -EAGAIN shall be returned. When readahead would be
- * triggered, a partial, possibly empty read shall be returned.
- *
- * Return:
- * * number of bytes copied, even for partial reads
- * * negative error code (or 0 if IOCB_NOIO) if nothing was read
- */
- ssize_t
- generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
- {
- size_t count = iov_iter_count(iter);
- ssize_t retval = 0;
- if (!count)
- goto out; /* skip atime */
- if (iocb->ki_flags & IOCB_DIRECT) {
- struct file *file = iocb->ki_filp;
- struct address_space *mapping = file->f_mapping;
- struct inode *inode = mapping->host;
- loff_t size;
- size = i_size_read(inode);
- if (iocb->ki_flags & IOCB_NOWAIT) {
- if (filemap_range_has_page(mapping, iocb->ki_pos,
- iocb->ki_pos + count - 1))
- return -EAGAIN;
- } else {
- retval = filemap_write_and_wait_range(mapping,
- iocb->ki_pos,
- iocb->ki_pos + count - 1);
- if (retval < 0)
- goto out;
- }
- file_accessed(file);
- retval = mapping->a_ops->direct_IO(iocb, iter);
- if (retval >= 0) {
- iocb->ki_pos += retval;
- count -= retval;
- }
- iov_iter_revert(iter, count - iov_iter_count(iter));
- /*
- * Btrfs can have a short DIO read if we encounter
- * compressed extents, so if there was an error, or if
- * we've already read everything we wanted to, or if
- * there was a short read because we hit EOF, go ahead
- * and return. Otherwise fallthrough to buffered io for
- * the rest of the read. Buffered reads will not work for
- * DAX files, so don't bother trying.
- */
- if (retval < 0 || !count || iocb->ki_pos >= size ||
- IS_DAX(inode))
- goto out;
- }
- retval = generic_file_buffered_read(iocb, iter, retval);
- out:
- return retval;
- }
- EXPORT_SYMBOL(generic_file_read_iter);
- #ifdef CONFIG_MMU
- #define MMAP_LOTSAMISS (100)
- /*
- * lock_page_maybe_drop_mmap - lock the page, possibly dropping the mmap_lock
- * @vmf - the vm_fault for this fault.
- * @page - the page to lock.
- * @fpin - the pointer to the file we may pin (or is already pinned).
- *
- * This works similar to lock_page_or_retry in that it can drop the mmap_lock.
- * It differs in that it actually returns the page locked if it returns 1 and 0
- * if it couldn't lock the page. If we did have to drop the mmap_lock then fpin
- * will point to the pinned file and needs to be fput()'ed at a later point.
- */
- static int lock_page_maybe_drop_mmap(struct vm_fault *vmf, struct page *page,
- struct file **fpin)
- {
- if (trylock_page(page))
- return 1;
- /*
- * NOTE! This will make us return with VM_FAULT_RETRY, but with
- * the mmap_lock still held. That's how FAULT_FLAG_RETRY_NOWAIT
- * is supposed to work. We have way too many special cases..
- */
- if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT)
- return 0;
- *fpin = maybe_unlock_mmap_for_io(vmf, *fpin);
- if (vmf->flags & FAULT_FLAG_KILLABLE) {
- if (__lock_page_killable(page)) {
- /*
- * We didn't have the right flags to drop the mmap_lock,
- * but all fault_handlers only check for fatal signals
- * if we return VM_FAULT_RETRY, so we need to drop the
- * mmap_lock here and return 0 if we don't have a fpin.
- */
- if (*fpin == NULL)
- mmap_read_unlock(vmf->vma->vm_mm);
- return 0;
- }
- } else
- __lock_page(page);
- return 1;
- }
- /*
- * Synchronous readahead happens when we don't even find a page in the page
- * cache at all. We don't want to perform IO under the mmap sem, so if we have
- * to drop the mmap sem we return the file that was pinned in order for us to do
- * that. If we didn't pin a file then we return NULL. The file that is
- * returned needs to be fput()'ed when we're done with it.
- */
- static struct file *do_sync_mmap_readahead(struct vm_fault *vmf)
- {
- struct file *file = vmf->vma->vm_file;
- struct file_ra_state *ra = &file->f_ra;
- struct address_space *mapping = file->f_mapping;
- DEFINE_READAHEAD(ractl, file, mapping, vmf->pgoff);
- struct file *fpin = NULL;
- unsigned int mmap_miss;
- /* If we don't want any read-ahead, don't bother */
- if (vmf->vma->vm_flags & VM_RAND_READ)
- return fpin;
- if (!ra->ra_pages)
- return fpin;
- if (vmf->vma->vm_flags & VM_SEQ_READ) {
- fpin = maybe_unlock_mmap_for_io(vmf, fpin);
- page_cache_sync_ra(&ractl, ra, ra->ra_pages);
- return fpin;
- }
- /* Avoid banging the cache line if not needed */
- mmap_miss = READ_ONCE(ra->mmap_miss);
- if (mmap_miss < MMAP_LOTSAMISS * 10)
- WRITE_ONCE(ra->mmap_miss, ++mmap_miss);
- /*
- * Do we miss much more than hit in this file? If so,
- * stop bothering with read-ahead. It will only hurt.
- */
- if (mmap_miss > MMAP_LOTSAMISS)
- return fpin;
- /*
- * mmap read-around
- */
- fpin = maybe_unlock_mmap_for_io(vmf, fpin);
- ra->start = max_t(long, 0, vmf->pgoff - ra->ra_pages / 2);
- ra->size = ra->ra_pages;
- ra->async_size = ra->ra_pages / 4;
- ractl._index = ra->start;
- do_page_cache_ra(&ractl, ra->size, ra->async_size);
- return fpin;
- }
- /*
- * Asynchronous readahead happens when we find the page and PG_readahead,
- * so we want to possibly extend the readahead further. We return the file that
- * was pinned if we have to drop the mmap_lock in order to do IO.
- */
- static struct file *do_async_mmap_readahead(struct vm_fault *vmf,
- struct page *page)
- {
- struct file *file = vmf->vma->vm_file;
- struct file_ra_state *ra = &file->f_ra;
- struct address_space *mapping = file->f_mapping;
- struct file *fpin = NULL;
- unsigned int mmap_miss;
- pgoff_t offset = vmf->pgoff;
- /* If we don't want any read-ahead, don't bother */
- if (vmf->vma->vm_flags & VM_RAND_READ || !ra->ra_pages)
- return fpin;
- mmap_miss = READ_ONCE(ra->mmap_miss);
- if (mmap_miss)
- WRITE_ONCE(ra->mmap_miss, --mmap_miss);
- if (PageReadahead(page)) {
- fpin = maybe_unlock_mmap_for_io(vmf, fpin);
- page_cache_async_readahead(mapping, ra, file,
- page, offset, ra->ra_pages);
- }
- return fpin;
- }
- /**
- * filemap_fault - read in file data for page fault handling
- * @vmf: struct vm_fault containing details of the fault
- *
- * filemap_fault() is invoked via the vma operations vector for a
- * mapped memory region to read in file data during a page fault.
- *
- * The goto's are kind of ugly, but this streamlines the normal case of having
- * it in the page cache, and handles the special cases reasonably without
- * having a lot of duplicated code.
- *
- * vma->vm_mm->mmap_lock must be held on entry.
- *
- * If our return value has VM_FAULT_RETRY set, it's because the mmap_lock
- * may be dropped before doing I/O or by lock_page_maybe_drop_mmap().
- *
- * If our return value does not have VM_FAULT_RETRY set, the mmap_lock
- * has not been released.
- *
- * We never return with VM_FAULT_RETRY and a bit from VM_FAULT_ERROR set.
- *
- * Return: bitwise-OR of %VM_FAULT_ codes.
- */
- vm_fault_t filemap_fault(struct vm_fault *vmf)
- {
- int error;
- struct file *file = vmf->vma->vm_file;
- struct file *fpin = NULL;
- struct address_space *mapping = file->f_mapping;
- struct file_ra_state *ra = &file->f_ra;
- struct inode *inode = mapping->host;
- pgoff_t offset = vmf->pgoff;
- pgoff_t max_off;
- struct page *page = NULL;
- vm_fault_t ret = 0;
- bool retry = false;
- max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
- if (unlikely(offset >= max_off))
- return VM_FAULT_SIGBUS;
- trace_android_vh_filemap_fault_get_page(vmf, &page, &retry);
- if (unlikely(retry))
- goto out_retry;
- if (unlikely(page))
- goto page_ok;
- /*
- * Do we have something in the page cache already?
- */
- page = find_get_page(mapping, offset);
- if (likely(page) && !(vmf->flags & FAULT_FLAG_TRIED)) {
- /*
- * We found the page, so try async readahead before
- * waiting for the lock.
- */
- fpin = do_async_mmap_readahead(vmf, page);
- } else if (!page) {
- /* No page in the page cache at all */
- count_vm_event(PGMAJFAULT);
- count_memcg_event_mm(vmf->vma->vm_mm, PGMAJFAULT);
- ret = VM_FAULT_MAJOR;
- fpin = do_sync_mmap_readahead(vmf);
- retry_find:
- page = pagecache_get_page(mapping, offset,
- FGP_CREAT|FGP_FOR_MMAP,
- vmf->gfp_mask);
- if (!page) {
- if (fpin)
- goto out_retry;
- return VM_FAULT_OOM;
- }
- }
- if (!lock_page_maybe_drop_mmap(vmf, page, &fpin))
- goto out_retry;
- /* Did it get truncated? */
- if (unlikely(compound_head(page)->mapping != mapping)) {
- unlock_page(page);
- put_page(page);
- goto retry_find;
- }
- VM_BUG_ON_PAGE(page_to_pgoff(page) != offset, page);
- /*
- * We have a locked page in the page cache, now we need to check
- * that it's up-to-date. If not, it is going to be due to an error.
- */
- if (unlikely(!PageUptodate(page)))
- goto page_not_uptodate;
- /*
- * We've made it this far and we had to drop our mmap_lock, now is the
- * time to return to the upper layer and have it re-find the vma and
- * redo the fault.
- */
- if (fpin) {
- unlock_page(page);
- goto out_retry;
- }
- page_ok:
- /*
- * Found the page and have a reference on it.
- * We must recheck i_size under page lock.
- */
- max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
- if (unlikely(offset >= max_off)) {
- unlock_page(page);
- put_page(page);
- return VM_FAULT_SIGBUS;
- }
- vmf->page = page;
- return ret | VM_FAULT_LOCKED;
- page_not_uptodate:
- /*
- * Umm, take care of errors if the page isn't up-to-date.
- * Try to re-read it _once_. We do this synchronously,
- * because there really aren't any performance issues here
- * and we need to check for errors.
- */
- ClearPageError(page);
- fpin = maybe_unlock_mmap_for_io(vmf, fpin);
- error = mapping->a_ops->readpage(file, page);
- if (!error) {
- wait_on_page_locked(page);
- if (!PageUptodate(page))
- error = -EIO;
- }
- if (fpin)
- goto out_retry;
- put_page(page);
- if (!error || error == AOP_TRUNCATED_PAGE)
- goto retry_find;
- shrink_readahead_size_eio(ra);
- return VM_FAULT_SIGBUS;
- out_retry:
- /*
- * We dropped the mmap_lock, we need to return to the fault handler to
- * re-find the vma and come back and find our hopefully still populated
- * page.
- */
- if (page) {
- trace_android_vh_filemap_fault_cache_page(vmf, page);
- put_page(page);
- }
- if (fpin)
- fput(fpin);
- return ret | VM_FAULT_RETRY;
- }
- EXPORT_SYMBOL(filemap_fault);
- static bool filemap_map_pmd(struct vm_fault *vmf, struct page *page)
- {
- struct mm_struct *mm = vmf->vma->vm_mm;
- /* Huge page is mapped? No need to proceed. */
- if (pmd_trans_huge(*vmf->pmd)) {
- unlock_page(page);
- put_page(page);
- return true;
- }
- if (pmd_none(*vmf->pmd) && PageTransHuge(page)) {
- vm_fault_t ret = do_set_pmd(vmf, page);
- if (!ret) {
- /* The page is mapped successfully, reference consumed. */
- unlock_page(page);
- return true;
- }
- }
- if (pmd_none(*vmf->pmd)) {
- if (vmf->flags & FAULT_FLAG_SPECULATIVE) {
- unlock_page(page);
- put_page(page);
- return true;
- }
- vmf->ptl = pmd_lock(mm, vmf->pmd);
- if (likely(pmd_none(*vmf->pmd))) {
- mm_inc_nr_ptes(mm);
- pmd_populate(mm, vmf->pmd, vmf->prealloc_pte);
- vmf->prealloc_pte = NULL;
- }
- spin_unlock(vmf->ptl);
- }
- /* See comment in handle_pte_fault() */
- if (pmd_devmap_trans_unstable(vmf->pmd)) {
- unlock_page(page);
- put_page(page);
- return true;
- }
- return false;
- }
- static struct page *next_uptodate_page(struct page *page,
- struct address_space *mapping,
- struct xa_state *xas, pgoff_t end_pgoff)
- {
- unsigned long max_idx;
- do {
- if (!page)
- return NULL;
- if (xas_retry(xas, page))
- continue;
- if (xa_is_value(page))
- continue;
- if (PageLocked(page))
- continue;
- if (!page_cache_get_speculative(page))
- continue;
- /* Has the page moved or been split? */
- if (unlikely(page != xas_reload(xas)))
- goto skip;
- if (!PageUptodate(page) || PageReadahead(page))
- goto skip;
- if (PageHWPoison(page))
- goto skip;
- if (!trylock_page(page))
- goto skip;
- if (page->mapping != mapping)
- goto unlock;
- if (!PageUptodate(page))
- goto unlock;
- max_idx = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE);
- if (xas->xa_index >= max_idx)
- goto unlock;
- return page;
- unlock:
- unlock_page(page);
- skip:
- put_page(page);
- } while ((page = xas_next_entry(xas, end_pgoff)) != NULL);
- return NULL;
- }
- static inline struct page *first_map_page(struct address_space *mapping,
- struct xa_state *xas,
- pgoff_t end_pgoff)
- {
- return next_uptodate_page(xas_find(xas, end_pgoff),
- mapping, xas, end_pgoff);
- }
- static inline struct page *next_map_page(struct address_space *mapping,
- struct xa_state *xas,
- pgoff_t end_pgoff)
- {
- return next_uptodate_page(xas_next_entry(xas, end_pgoff),
- mapping, xas, end_pgoff);
- }
- #ifdef CONFIG_SPECULATIVE_PAGE_FAULT
- bool filemap_allow_speculation(void)
- {
- return true;
- }
- EXPORT_SYMBOL_GPL(filemap_allow_speculation);
- #endif
- vm_fault_t filemap_map_pages(struct vm_fault *vmf,
- pgoff_t start_pgoff, pgoff_t end_pgoff)
- {
- struct vm_area_struct *vma = vmf->vma;
- struct file *file = vma->vm_file;
- struct address_space *mapping = file->f_mapping;
- pgoff_t last_pgoff = start_pgoff;
- unsigned long addr;
- XA_STATE(xas, &mapping->i_pages, start_pgoff);
- struct page *head, *page;
- unsigned int mmap_miss = READ_ONCE(file->f_ra.mmap_miss);
- vm_fault_t ret = 0;
- rcu_read_lock();
- head = first_map_page(mapping, &xas, end_pgoff);
- if (!head)
- goto out;
- if (filemap_map_pmd(vmf, head)) {
- if (pmd_none(*vmf->pmd) &&
- vmf->flags & FAULT_FLAG_SPECULATIVE) {
- ret = VM_FAULT_RETRY;
- goto out;
- }
- ret = VM_FAULT_NOPAGE;
- goto out;
- }
- addr = vma->vm_start + ((start_pgoff - vma->vm_pgoff) << PAGE_SHIFT);
- if (!pte_map_lock_addr(vmf, addr)) {
- unlock_page(head);
- put_page(head);
- ret = VM_FAULT_RETRY;
- goto out;
- }
- do {
- page = find_subpage(head, xas.xa_index);
- if (PageHWPoison(page))
- goto unlock;
- if (mmap_miss > 0)
- mmap_miss--;
- addr += (xas.xa_index - last_pgoff) << PAGE_SHIFT;
- vmf->pte += xas.xa_index - last_pgoff;
- last_pgoff = xas.xa_index;
- if (!pte_none(*vmf->pte))
- goto unlock;
- /* We're about to handle the fault */
- if (vmf->address == addr)
- ret = VM_FAULT_NOPAGE;
- do_set_pte(vmf, page, addr);
- /* no need to invalidate: a not-present page won't be cached */
- update_mmu_cache(vma, addr, vmf->pte);
- unlock_page(head);
- continue;
- unlock:
- unlock_page(head);
- put_page(head);
- } while ((head = next_map_page(mapping, &xas, end_pgoff)) != NULL);
- pte_unmap_unlock(vmf->pte, vmf->ptl);
- out:
- rcu_read_unlock();
- WRITE_ONCE(file->f_ra.mmap_miss, mmap_miss);
- return ret;
- }
- EXPORT_SYMBOL(filemap_map_pages);
- vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf)
- {
- struct page *page = vmf->page;
- struct inode *inode = file_inode(vmf->vma->vm_file);
- vm_fault_t ret = VM_FAULT_LOCKED;
- sb_start_pagefault(inode->i_sb);
- file_update_time(vmf->vma->vm_file);
- lock_page(page);
- if (page->mapping != inode->i_mapping) {
- unlock_page(page);
- ret = VM_FAULT_NOPAGE;
- goto out;
- }
- /*
- * We mark the page dirty already here so that when freeze is in
- * progress, we are guaranteed that writeback during freezing will
- * see the dirty page and writeprotect it again.
- */
- set_page_dirty(page);
- wait_for_stable_page(page);
- out:
- sb_end_pagefault(inode->i_sb);
- return ret;
- }
- const struct vm_operations_struct generic_file_vm_ops = {
- .fault = filemap_fault,
- .map_pages = filemap_map_pages,
- .page_mkwrite = filemap_page_mkwrite,
- #ifdef CONFIG_SPECULATIVE_PAGE_FAULT
- .allow_speculation = filemap_allow_speculation,
- #endif
- };
- /* This is used for a general mmap of a disk file */
- int generic_file_mmap(struct file * file, struct vm_area_struct * vma)
- {
- struct address_space *mapping = file->f_mapping;
- if (!mapping->a_ops->readpage)
- return -ENOEXEC;
- file_accessed(file);
- vma->vm_ops = &generic_file_vm_ops;
- return 0;
- }
- /*
- * This is for filesystems which do not implement ->writepage.
- */
- int generic_file_readonly_mmap(struct file *file, struct vm_area_struct *vma)
- {
- if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_MAYWRITE))
- return -EINVAL;
- return generic_file_mmap(file, vma);
- }
- #else
- vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf)
- {
- return VM_FAULT_SIGBUS;
- }
- int generic_file_mmap(struct file * file, struct vm_area_struct * vma)
- {
- return -ENOSYS;
- }
- int generic_file_readonly_mmap(struct file * file, struct vm_area_struct * vma)
- {
- return -ENOSYS;
- }
- #endif /* CONFIG_MMU */
- EXPORT_SYMBOL(filemap_page_mkwrite);
- EXPORT_SYMBOL(generic_file_mmap);
- EXPORT_SYMBOL(generic_file_readonly_mmap);
- static struct page *wait_on_page_read(struct page *page)
- {
- if (!IS_ERR(page)) {
- wait_on_page_locked(page);
- if (!PageUptodate(page)) {
- put_page(page);
- page = ERR_PTR(-EIO);
- }
- }
- return page;
- }
- static struct page *do_read_cache_page(struct address_space *mapping,
- pgoff_t index,
- int (*filler)(void *, struct page *),
- void *data,
- gfp_t gfp)
- {
- struct page *page;
- int err;
- repeat:
- page = find_get_page(mapping, index);
- if (!page) {
- page = __page_cache_alloc(gfp);
- if (!page)
- return ERR_PTR(-ENOMEM);
- err = add_to_page_cache_lru(page, mapping, index, gfp);
- if (unlikely(err)) {
- put_page(page);
- if (err == -EEXIST)
- goto repeat;
- /* Presumably ENOMEM for xarray node */
- return ERR_PTR(err);
- }
- filler:
- if (filler)
- err = filler(data, page);
- else
- err = mapping->a_ops->readpage(data, page);
- if (err < 0) {
- put_page(page);
- return ERR_PTR(err);
- }
- page = wait_on_page_read(page);
- if (IS_ERR(page))
- return page;
- goto out;
- }
- if (PageUptodate(page))
- goto out;
- /*
- * Page is not up to date and may be locked due to one of the following
- * case a: Page is being filled and the page lock is held
- * case b: Read/write error clearing the page uptodate status
- * case c: Truncation in progress (page locked)
- * case d: Reclaim in progress
- *
- * Case a, the page will be up to date when the page is unlocked.
- * There is no need to serialise on the page lock here as the page
- * is pinned so the lock gives no additional protection. Even if the
- * page is truncated, the data is still valid if PageUptodate as
- * it's a race vs truncate race.
- * Case b, the page will not be up to date
- * Case c, the page may be truncated but in itself, the data may still
- * be valid after IO completes as it's a read vs truncate race. The
- * operation must restart if the page is not uptodate on unlock but
- * otherwise serialising on page lock to stabilise the mapping gives
- * no additional guarantees to the caller as the page lock is
- * released before return.
- * Case d, similar to truncation. If reclaim holds the page lock, it
- * will be a race with remove_mapping that determines if the mapping
- * is valid on unlock but otherwise the data is valid and there is
- * no need to serialise with page lock.
- *
- * As the page lock gives no additional guarantee, we optimistically
- * wait on the page to be unlocked and check if it's up to date and
- * use the page if it is. Otherwise, the page lock is required to
- * distinguish between the different cases. The motivation is that we
- * avoid spurious serialisations and wakeups when multiple processes
- * wait on the same page for IO to complete.
- */
- wait_on_page_locked(page);
- if (PageUptodate(page))
- goto out;
- /* Distinguish between all the cases under the safety of the lock */
- lock_page(page);
- /* Case c or d, restart the operation */
- if (!page->mapping) {
- unlock_page(page);
- put_page(page);
- goto repeat;
- }
- /* Someone else locked and filled the page in a very small window */
- if (PageUptodate(page)) {
- unlock_page(page);
- goto out;
- }
- /*
- * A previous I/O error may have been due to temporary
- * failures.
- * Clear page error before actual read, PG_error will be
- * set again if read page fails.
- */
- ClearPageError(page);
- goto filler;
- out:
- mark_page_accessed(page);
- return page;
- }
- /**
- * read_cache_page - read into page cache, fill it if needed
- * @mapping: the page's address_space
- * @index: the page index
- * @filler: function to perform the read
- * @data: first arg to filler(data, page) function, often left as NULL
- *
- * Read into the page cache. If a page already exists, and PageUptodate() is
- * not set, try to fill the page and wait for it to become unlocked.
- *
- * If the page does not get brought uptodate, return -EIO.
- *
- * Return: up to date page on success, ERR_PTR() on failure.
- */
- struct page *read_cache_page(struct address_space *mapping,
- pgoff_t index,
- int (*filler)(void *, struct page *),
- void *data)
- {
- return do_read_cache_page(mapping, index, filler, data,
- mapping_gfp_mask(mapping));
- }
- EXPORT_SYMBOL(read_cache_page);
- /**
- * read_cache_page_gfp - read into page cache, using specified page allocation flags.
- * @mapping: the page's address_space
- * @index: the page index
- * @gfp: the page allocator flags to use if allocating
- *
- * This is the same as "read_mapping_page(mapping, index, NULL)", but with
- * any new page allocations done using the specified allocation flags.
- *
- * If the page does not get brought uptodate, return -EIO.
- *
- * Return: up to date page on success, ERR_PTR() on failure.
- */
- struct page *read_cache_page_gfp(struct address_space *mapping,
- pgoff_t index,
- gfp_t gfp)
- {
- return do_read_cache_page(mapping, index, NULL, NULL, gfp);
- }
- EXPORT_SYMBOL(read_cache_page_gfp);
- int pagecache_write_begin(struct file *file, struct address_space *mapping,
- loff_t pos, unsigned len, unsigned flags,
- struct page **pagep, void **fsdata)
- {
- const struct address_space_operations *aops = mapping->a_ops;
- return aops->write_begin(file, mapping, pos, len, flags,
- pagep, fsdata);
- }
- EXPORT_SYMBOL(pagecache_write_begin);
- int pagecache_write_end(struct file *file, struct address_space *mapping,
- loff_t pos, unsigned len, unsigned copied,
- struct page *page, void *fsdata)
- {
- const struct address_space_operations *aops = mapping->a_ops;
- return aops->write_end(file, mapping, pos, len, copied, page, fsdata);
- }
- EXPORT_SYMBOL(pagecache_write_end);
- /*
- * Warn about a page cache invalidation failure during a direct I/O write.
- */
- void dio_warn_stale_pagecache(struct file *filp)
- {
- static DEFINE_RATELIMIT_STATE(_rs, 86400 * HZ, DEFAULT_RATELIMIT_BURST);
- char pathname[128];
- struct inode *inode = file_inode(filp);
- char *path;
- errseq_set(&inode->i_mapping->wb_err, -EIO);
- if (__ratelimit(&_rs)) {
- path = file_path(filp, pathname, sizeof(pathname));
- if (IS_ERR(path))
- path = "(unknown)";
- pr_crit("Page cache invalidation failure on direct I/O. Possible data corruption due to collision with buffered I/O!\n");
- pr_crit("File: %s PID: %d Comm: %.20s\n", path, current->pid,
- current->comm);
- }
- }
- ssize_t
- generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from)
- {
- struct file *file = iocb->ki_filp;
- struct address_space *mapping = file->f_mapping;
- struct inode *inode = mapping->host;
- loff_t pos = iocb->ki_pos;
- ssize_t written;
- size_t write_len;
- pgoff_t end;
- write_len = iov_iter_count(from);
- end = (pos + write_len - 1) >> PAGE_SHIFT;
- if (iocb->ki_flags & IOCB_NOWAIT) {
- /* If there are pages to writeback, return */
- if (filemap_range_has_page(inode->i_mapping, pos,
- pos + write_len - 1))
- return -EAGAIN;
- } else {
- written = filemap_write_and_wait_range(mapping, pos,
- pos + write_len - 1);
- if (written)
- goto out;
- }
- /*
- * After a write we want buffered reads to be sure to go to disk to get
- * the new data. We invalidate clean cached page from the region we're
- * about to write. We do this *before* the write so that we can return
- * without clobbering -EIOCBQUEUED from ->direct_IO().
- */
- written = invalidate_inode_pages2_range(mapping,
- pos >> PAGE_SHIFT, end);
- /*
- * If a page can not be invalidated, return 0 to fall back
- * to buffered write.
- */
- if (written) {
- if (written == -EBUSY)
- return 0;
- goto out;
- }
- written = mapping->a_ops->direct_IO(iocb, from);
- /*
- * Finally, try again to invalidate clean pages which might have been
- * cached by non-direct readahead, or faulted in by get_user_pages()
- * if the source of the write was an mmap'ed region of the file
- * we're writing. Either one is a pretty crazy thing to do,
- * so we don't support it 100%. If this invalidation
- * fails, tough, the write still worked...
- *
- * Most of the time we do not need this since dio_complete() will do
- * the invalidation for us. However there are some file systems that
- * do not end up with dio_complete() being called, so let's not break
- * them by removing it completely.
- *
- * Noticeable example is a blkdev_direct_IO().
- *
- * Skip invalidation for async writes or if mapping has no pages.
- */
- if (written > 0 && mapping->nrpages &&
- invalidate_inode_pages2_range(mapping, pos >> PAGE_SHIFT, end))
- dio_warn_stale_pagecache(file);
- if (written > 0) {
- pos += written;
- write_len -= written;
- if (pos > i_size_read(inode) && !S_ISBLK(inode->i_mode)) {
- i_size_write(inode, pos);
- mark_inode_dirty(inode);
- }
- iocb->ki_pos = pos;
- }
- iov_iter_revert(from, write_len - iov_iter_count(from));
- out:
- return written;
- }
- EXPORT_SYMBOL(generic_file_direct_write);
- /*
- * Find or create a page at the given pagecache position. Return the locked
- * page. This function is specifically for buffered writes.
- */
- struct page *grab_cache_page_write_begin(struct address_space *mapping,
- pgoff_t index, unsigned flags)
- {
- struct page *page;
- int fgp_flags = FGP_LOCK|FGP_WRITE|FGP_CREAT;
- if (flags & AOP_FLAG_NOFS)
- fgp_flags |= FGP_NOFS;
- page = pagecache_get_page(mapping, index, fgp_flags,
- mapping_gfp_mask(mapping));
- if (page)
- wait_for_stable_page(page);
- return page;
- }
- EXPORT_SYMBOL(grab_cache_page_write_begin);
- ssize_t generic_perform_write(struct file *file,
- struct iov_iter *i, loff_t pos)
- {
- struct address_space *mapping = file->f_mapping;
- const struct address_space_operations *a_ops = mapping->a_ops;
- long status = 0;
- ssize_t written = 0;
- unsigned int flags = 0;
- do {
- struct page *page;
- unsigned long offset; /* Offset into pagecache page */
- unsigned long bytes; /* Bytes to write to page */
- size_t copied; /* Bytes copied from user */
- void *fsdata;
- offset = (pos & (PAGE_SIZE - 1));
- bytes = min_t(unsigned long, PAGE_SIZE - offset,
- iov_iter_count(i));
- again:
- /*
- * Bring in the user page that we will copy from _first_.
- * Otherwise there's a nasty deadlock on copying from the
- * same page as we're writing to, without it being marked
- * up-to-date.
- *
- * Not only is this an optimisation, but it is also required
- * to check that the address is actually valid, when atomic
- * usercopies are used, below.
- */
- if (unlikely(iov_iter_fault_in_readable(i, bytes))) {
- status = -EFAULT;
- break;
- }
- if (fatal_signal_pending(current)) {
- status = -EINTR;
- break;
- }
- status = a_ops->write_begin(file, mapping, pos, bytes, flags,
- &page, &fsdata);
- if (unlikely(status < 0))
- break;
- if (mapping_writably_mapped(mapping))
- flush_dcache_page(page);
- copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes);
- flush_dcache_page(page);
- status = a_ops->write_end(file, mapping, pos, bytes, copied,
- page, fsdata);
- if (unlikely(status < 0))
- break;
- copied = status;
- cond_resched();
- iov_iter_advance(i, copied);
- if (unlikely(copied == 0)) {
- /*
- * If we were unable to copy any data at all, we must
- * fall back to a single segment length write.
- *
- * If we didn't fallback here, we could livelock
- * because not all segments in the iov can be copied at
- * once without a pagefault.
- */
- bytes = min_t(unsigned long, PAGE_SIZE - offset,
- iov_iter_single_seg_count(i));
- goto again;
- }
- pos += copied;
- written += copied;
- balance_dirty_pages_ratelimited(mapping);
- } while (iov_iter_count(i));
- return written ? written : status;
- }
- EXPORT_SYMBOL(generic_perform_write);
- /**
- * __generic_file_write_iter - write data to a file
- * @iocb: IO state structure (file, offset, etc.)
- * @from: iov_iter with data to write
- *
- * This function does all the work needed for actually writing data to a
- * file. It does all basic checks, removes SUID from the file, updates
- * modification times and calls proper subroutines depending on whether we
- * do direct IO or a standard buffered write.
- *
- * It expects i_mutex to be grabbed unless we work on a block device or similar
- * object which does not need locking at all.
- *
- * This function does *not* take care of syncing data in case of O_SYNC write.
- * A caller has to handle it. This is mainly due to the fact that we want to
- * avoid syncing under i_mutex.
- *
- * Return:
- * * number of bytes written, even for truncated writes
- * * negative error code if no data has been written at all
- */
- ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
- {
- struct file *file = iocb->ki_filp;
- struct address_space * mapping = file->f_mapping;
- struct inode *inode = mapping->host;
- ssize_t written = 0;
- ssize_t err;
- ssize_t status;
- /* We can write back this queue in page reclaim */
- current->backing_dev_info = inode_to_bdi(inode);
- err = file_remove_privs(file);
- if (err)
- goto out;
- err = file_update_time(file);
- if (err)
- goto out;
- if (iocb->ki_flags & IOCB_DIRECT) {
- loff_t pos, endbyte;
- written = generic_file_direct_write(iocb, from);
- /*
- * If the write stopped short of completing, fall back to
- * buffered writes. Some filesystems do this for writes to
- * holes, for example. For DAX files, a buffered write will
- * not succeed (even if it did, DAX does not handle dirty
- * page-cache pages correctly).
- */
- if (written < 0 || !iov_iter_count(from) || IS_DAX(inode))
- goto out;
- status = generic_perform_write(file, from, pos = iocb->ki_pos);
- /*
- * If generic_perform_write() returned a synchronous error
- * then we want to return the number of bytes which were
- * direct-written, or the error code if that was zero. Note
- * that this differs from normal direct-io semantics, which
- * will return -EFOO even if some bytes were written.
- */
- if (unlikely(status < 0)) {
- err = status;
- goto out;
- }
- /*
- * We need to ensure that the page cache pages are written to
- * disk and invalidated to preserve the expected O_DIRECT
- * semantics.
- */
- endbyte = pos + status - 1;
- err = filemap_write_and_wait_range(mapping, pos, endbyte);
- if (err == 0) {
- iocb->ki_pos = endbyte + 1;
- written += status;
- invalidate_mapping_pages(mapping,
- pos >> PAGE_SHIFT,
- endbyte >> PAGE_SHIFT);
- } else {
- /*
- * We don't know how much we wrote, so just return
- * the number of bytes which were direct-written
- */
- }
- } else {
- written = generic_perform_write(file, from, iocb->ki_pos);
- if (likely(written > 0))
- iocb->ki_pos += written;
- }
- out:
- current->backing_dev_info = NULL;
- return written ? written : err;
- }
- EXPORT_SYMBOL(__generic_file_write_iter);
- /**
- * generic_file_write_iter - write data to a file
- * @iocb: IO state structure
- * @from: iov_iter with data to write
- *
- * This is a wrapper around __generic_file_write_iter() to be used by most
- * filesystems. It takes care of syncing the file in case of O_SYNC file
- * and acquires i_mutex as needed.
- * Return:
- * * negative error code if no data has been written at all of
- * vfs_fsync_range() failed for a synchronous write
- * * number of bytes written, even for truncated writes
- */
- ssize_t generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
- {
- struct file *file = iocb->ki_filp;
- struct inode *inode = file->f_mapping->host;
- ssize_t ret;
- inode_lock(inode);
- ret = generic_write_checks(iocb, from);
- if (ret > 0)
- ret = __generic_file_write_iter(iocb, from);
- inode_unlock(inode);
- if (ret > 0)
- ret = generic_write_sync(iocb, ret);
- return ret;
- }
- EXPORT_SYMBOL(generic_file_write_iter);
- /**
- * try_to_release_page() - release old fs-specific metadata on a page
- *
- * @page: the page which the kernel is trying to free
- * @gfp_mask: memory allocation flags (and I/O mode)
- *
- * The address_space is to try to release any data against the page
- * (presumably at page->private).
- *
- * This may also be called if PG_fscache is set on a page, indicating that the
- * page is known to the local caching routines.
- *
- * The @gfp_mask argument specifies whether I/O may be performed to release
- * this page (__GFP_IO), and whether the call may block (__GFP_RECLAIM & __GFP_FS).
- *
- * Return: %1 if the release was successful, otherwise return zero.
- */
- int try_to_release_page(struct page *page, gfp_t gfp_mask)
- {
- struct address_space * const mapping = page->mapping;
- BUG_ON(!PageLocked(page));
- if (PageWriteback(page))
- return 0;
- if (mapping && mapping->a_ops->releasepage)
- return mapping->a_ops->releasepage(page, gfp_mask);
- return try_to_free_buffers(page);
- }
- EXPORT_SYMBOL(try_to_release_page);
|