12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394959697989910010110210310410510610710810911011111211311411511611711811912012112212312412512612712812913013113213313413513613713813914014114214314414514614714814915015115215315415515615715815916016116216316416516616716816917017117217317417517617717817918018118218318418518618718818919019119219319419519619719819920020120220320420520620720820921021121221321421521621721821922022122222322422522622722822923023123223323423523623723823924024124224324424524624724824925025125225325425525625725825926026126226326426526626726826927027127227327427527627727827928028128228328428528628728828929029129229329429529629729829930030130230330430530630730830931031131231331431531631731831932032132232332432532632732832933033133233333433533633733833934034134234334434534634734834935035135235335435535635735835936036136236336436536636736836937037137237337437537637737837938038138238338438538638738838939039139239339439539639739839940040140240340440540640740840941041141241341441541641741841942042142242342442542642742842943043143243343443543643743843944044144244344444544644744844945045145245345445545645745845946046146246346446546646746846947047147247347447547647747847948048148248348448548648748848949049149249349449549649749849950050150250350450550650750850951051151251351451551651751851952052152252352452552652752852953053153253353453553653753853954054154254354454554654754854955055155255355455555655755855956056156256356456556656756856957057157257357457557657757857958058158258358458558658758858959059159259359459559659759859960060160260360460560660760860961061161261361461561661761861962062162262362462562662762862963063163263363463563663763863964064164264364464564664764864965065165265365465565665765865966066166266366466566666766866967067167267367467567667767867968068168268368468568668768868969069169269369469569669769869970070170270370470570670770870971071171271371471571671771871972072172272372472572672772872973073173273373473573673773873974074174274374474574674774874975075175275375475575675775875976076176276376476576676776876977077177277377477577677777877978078178278378478578678778878979079179279379479579679779879980080180280380480580680780880981081181281381481581681781881982082182282382482582682782882983083183283383483583683783883984084184284384484584684784884985085185285385485585685785885986086186286386486586686786886987087187287387487587687787887988088188288388488588688788888989089189289389489589689789889990090190290390490590690790890991091191291391491591691791891992092192292392492592692792892993093193293393493593693793893994094194294394494594694794894995095195295395495595695795895996096196296396496596696796896997097197297397497597697797897998098198298398498598698798898999099199299399499599699799899910001001100210031004100510061007100810091010101110121013101410151016101710181019102010211022102310241025102610271028102910301031103210331034103510361037103810391040104110421043104410451046104710481049105010511052105310541055105610571058105910601061106210631064106510661067106810691070107110721073107410751076107710781079108010811082108310841085108610871088108910901091109210931094109510961097109810991100110111021103110411051106110711081109111011111112111311141115111611171118111911201121112211231124112511261127112811291130113111321133113411351136113711381139114011411142114311441145114611471148114911501151115211531154115511561157115811591160116111621163116411651166116711681169117011711172117311741175117611771178117911801181118211831184118511861187118811891190119111921193119411951196119711981199120012011202120312041205120612071208120912101211121212131214121512161217121812191220122112221223122412251226122712281229123012311232123312341235123612371238123912401241124212431244124512461247124812491250125112521253125412551256125712581259126012611262126312641265126612671268126912701271127212731274127512761277127812791280128112821283128412851286128712881289129012911292129312941295129612971298129913001301130213031304130513061307130813091310131113121313131413151316131713181319132013211322132313241325132613271328132913301331133213331334133513361337133813391340134113421343134413451346134713481349135013511352135313541355135613571358135913601361136213631364136513661367136813691370137113721373137413751376137713781379138013811382138313841385138613871388138913901391139213931394139513961397139813991400140114021403140414051406140714081409141014111412141314141415141614171418141914201421142214231424142514261427142814291430143114321433143414351436143714381439144014411442144314441445144614471448144914501451145214531454145514561457145814591460146114621463146414651466146714681469147014711472147314741475147614771478147914801481148214831484148514861487148814891490149114921493149414951496149714981499150015011502150315041505150615071508150915101511151215131514151515161517151815191520152115221523152415251526152715281529153015311532153315341535153615371538153915401541154215431544154515461547154815491550155115521553155415551556155715581559156015611562156315641565156615671568156915701571157215731574157515761577157815791580158115821583158415851586158715881589159015911592159315941595159615971598159916001601160216031604160516061607160816091610161116121613161416151616161716181619162016211622162316241625162616271628162916301631163216331634163516361637163816391640164116421643164416451646164716481649165016511652165316541655165616571658165916601661166216631664166516661667166816691670167116721673167416751676167716781679168016811682168316841685168616871688168916901691169216931694169516961697169816991700170117021703170417051706170717081709171017111712171317141715171617171718171917201721172217231724172517261727172817291730173117321733173417351736173717381739174017411742174317441745174617471748174917501751175217531754175517561757175817591760176117621763176417651766176717681769177017711772177317741775177617771778177917801781178217831784178517861787178817891790179117921793179417951796179717981799180018011802180318041805180618071808180918101811181218131814181518161817181818191820182118221823182418251826182718281829183018311832183318341835183618371838183918401841184218431844184518461847184818491850185118521853185418551856185718581859186018611862186318641865186618671868186918701871187218731874187518761877187818791880188118821883188418851886188718881889189018911892189318941895189618971898189919001901190219031904190519061907190819091910191119121913191419151916191719181919192019211922192319241925192619271928192919301931193219331934193519361937193819391940194119421943194419451946194719481949195019511952195319541955195619571958195919601961196219631964196519661967196819691970197119721973197419751976197719781979198019811982198319841985198619871988198919901991199219931994199519961997199819992000200120022003200420052006200720082009201020112012201320142015201620172018201920202021202220232024202520262027202820292030203120322033203420352036203720382039204020412042204320442045204620472048204920502051205220532054205520562057205820592060206120622063206420652066206720682069207020712072207320742075207620772078207920802081208220832084208520862087208820892090209120922093209420952096209720982099210021012102210321042105210621072108210921102111211221132114211521162117211821192120212121222123212421252126212721282129213021312132213321342135213621372138213921402141214221432144214521462147214821492150215121522153215421552156215721582159216021612162216321642165216621672168216921702171217221732174217521762177217821792180218121822183218421852186218721882189219021912192219321942195219621972198219922002201220222032204220522062207220822092210221122122213221422152216221722182219222022212222222322242225222622272228222922302231223222332234223522362237223822392240224122422243224422452246224722482249225022512252225322542255225622572258225922602261226222632264226522662267226822692270227122722273227422752276227722782279228022812282228322842285228622872288228922902291229222932294229522962297229822992300230123022303230423052306230723082309231023112312231323142315231623172318231923202321232223232324232523262327232823292330233123322333233423352336233723382339234023412342234323442345234623472348234923502351235223532354235523562357235823592360236123622363236423652366236723682369237023712372237323742375237623772378237923802381238223832384238523862387238823892390239123922393239423952396239723982399240024012402240324042405240624072408240924102411241224132414241524162417241824192420242124222423242424252426242724282429243024312432243324342435243624372438243924402441244224432444244524462447244824492450245124522453245424552456245724582459246024612462246324642465246624672468246924702471247224732474247524762477247824792480248124822483248424852486248724882489249024912492249324942495249624972498249925002501250225032504250525062507250825092510251125122513251425152516251725182519252025212522252325242525252625272528252925302531253225332534253525362537253825392540254125422543254425452546254725482549255025512552255325542555255625572558255925602561256225632564256525662567256825692570257125722573257425752576257725782579258025812582258325842585258625872588258925902591259225932594259525962597259825992600260126022603260426052606260726082609261026112612261326142615261626172618261926202621262226232624262526262627262826292630263126322633263426352636263726382639264026412642264326442645264626472648264926502651265226532654265526562657265826592660266126622663266426652666266726682669267026712672267326742675267626772678267926802681268226832684268526862687268826892690269126922693269426952696269726982699270027012702270327042705270627072708270927102711271227132714271527162717271827192720272127222723272427252726272727282729273027312732273327342735273627372738273927402741274227432744274527462747274827492750275127522753275427552756275727582759276027612762276327642765276627672768276927702771277227732774277527762777277827792780278127822783278427852786278727882789279027912792279327942795279627972798279928002801280228032804280528062807280828092810281128122813281428152816281728182819282028212822282328242825282628272828282928302831283228332834283528362837283828392840284128422843284428452846284728482849285028512852285328542855285628572858285928602861286228632864286528662867286828692870287128722873287428752876287728782879288028812882288328842885288628872888288928902891289228932894289528962897289828992900290129022903290429052906290729082909291029112912291329142915291629172918291929202921292229232924292529262927292829292930293129322933293429352936293729382939294029412942294329442945294629472948294929502951295229532954295529562957295829592960296129622963296429652966296729682969297029712972297329742975297629772978297929802981298229832984298529862987298829892990299129922993299429952996299729982999300030013002300330043005300630073008300930103011301230133014301530163017301830193020302130223023302430253026302730283029303030313032303330343035303630373038303930403041304230433044304530463047304830493050305130523053305430553056305730583059306030613062306330643065306630673068306930703071307230733074307530763077307830793080308130823083308430853086308730883089309030913092309330943095309630973098309931003101310231033104310531063107310831093110311131123113311431153116311731183119312031213122312331243125312631273128312931303131313231333134313531363137313831393140314131423143314431453146314731483149315031513152315331543155315631573158315931603161316231633164316531663167316831693170317131723173317431753176317731783179318031813182318331843185318631873188318931903191319231933194319531963197319831993200320132023203320432053206320732083209321032113212321332143215321632173218321932203221322232233224322532263227322832293230323132323233323432353236323732383239324032413242324332443245324632473248324932503251325232533254325532563257325832593260326132623263326432653266326732683269327032713272327332743275327632773278327932803281328232833284328532863287328832893290329132923293329432953296329732983299330033013302330333043305330633073308330933103311331233133314331533163317331833193320332133223323332433253326332733283329333033313332333333343335333633373338333933403341334233433344334533463347334833493350335133523353335433553356335733583359336033613362336333643365336633673368336933703371337233733374337533763377337833793380338133823383338433853386338733883389339033913392339333943395339633973398339934003401340234033404340534063407340834093410341134123413341434153416341734183419342034213422342334243425342634273428342934303431343234333434343534363437343834393440344134423443344434453446344734483449345034513452345334543455345634573458345934603461346234633464346534663467346834693470347134723473347434753476347734783479348034813482348334843485348634873488348934903491349234933494349534963497349834993500350135023503350435053506350735083509351035113512351335143515351635173518351935203521352235233524352535263527352835293530353135323533353435353536353735383539354035413542354335443545354635473548354935503551355235533554355535563557355835593560356135623563356435653566356735683569357035713572357335743575357635773578357935803581358235833584358535863587358835893590359135923593359435953596359735983599360036013602360336043605360636073608360936103611361236133614361536163617361836193620362136223623362436253626362736283629363036313632363336343635363636373638363936403641364236433644364536463647364836493650365136523653365436553656365736583659366036613662366336643665366636673668366936703671367236733674367536763677367836793680368136823683368436853686368736883689369036913692369336943695369636973698369937003701370237033704370537063707370837093710371137123713371437153716371737183719372037213722372337243725372637273728372937303731373237333734373537363737373837393740374137423743374437453746374737483749375037513752375337543755375637573758375937603761376237633764376537663767376837693770377137723773377437753776377737783779378037813782378337843785378637873788378937903791379237933794379537963797379837993800380138023803380438053806380738083809381038113812381338143815381638173818381938203821382238233824382538263827382838293830383138323833383438353836383738383839384038413842384338443845384638473848384938503851385238533854385538563857385838593860386138623863386438653866386738683869387038713872387338743875387638773878387938803881388238833884388538863887388838893890389138923893389438953896389738983899390039013902390339043905390639073908390939103911391239133914391539163917391839193920392139223923392439253926392739283929393039313932393339343935393639373938393939403941394239433944394539463947394839493950395139523953395439553956395739583959396039613962396339643965396639673968396939703971397239733974397539763977397839793980398139823983398439853986398739883989399039913992399339943995399639973998399940004001400240034004400540064007400840094010401140124013401440154016401740184019402040214022402340244025402640274028402940304031403240334034403540364037403840394040404140424043404440454046404740484049405040514052405340544055405640574058405940604061406240634064406540664067406840694070407140724073407440754076407740784079408040814082408340844085408640874088408940904091409240934094409540964097409840994100410141024103410441054106410741084109411041114112411341144115411641174118411941204121412241234124412541264127412841294130413141324133413441354136413741384139414041414142414341444145414641474148414941504151415241534154415541564157415841594160416141624163416441654166416741684169417041714172417341744175417641774178417941804181418241834184418541864187418841894190419141924193419441954196419741984199420042014202420342044205420642074208420942104211421242134214421542164217421842194220422142224223422442254226422742284229423042314232423342344235423642374238423942404241424242434244424542464247424842494250425142524253425442554256425742584259426042614262426342644265426642674268426942704271427242734274427542764277427842794280428142824283428442854286428742884289429042914292429342944295429642974298429943004301430243034304430543064307430843094310431143124313431443154316431743184319432043214322432343244325432643274328432943304331433243334334433543364337433843394340434143424343434443454346434743484349435043514352435343544355435643574358435943604361436243634364436543664367436843694370437143724373437443754376437743784379438043814382438343844385438643874388438943904391439243934394439543964397439843994400440144024403440444054406440744084409441044114412441344144415441644174418441944204421442244234424442544264427442844294430443144324433443444354436443744384439444044414442444344444445444644474448444944504451445244534454445544564457445844594460446144624463446444654466446744684469447044714472447344744475447644774478447944804481448244834484448544864487448844894490449144924493449444954496449744984499450045014502450345044505450645074508450945104511451245134514451545164517451845194520452145224523452445254526452745284529453045314532453345344535453645374538453945404541454245434544454545464547454845494550455145524553455445554556455745584559456045614562456345644565456645674568456945704571457245734574457545764577457845794580458145824583458445854586458745884589459045914592459345944595459645974598459946004601460246034604460546064607460846094610461146124613461446154616461746184619462046214622462346244625462646274628462946304631463246334634463546364637463846394640464146424643464446454646464746484649465046514652465346544655465646574658465946604661466246634664466546664667466846694670467146724673467446754676467746784679468046814682468346844685468646874688468946904691469246934694469546964697469846994700470147024703470447054706470747084709471047114712471347144715471647174718471947204721472247234724472547264727472847294730473147324733473447354736473747384739474047414742474347444745474647474748474947504751475247534754475547564757475847594760476147624763476447654766476747684769477047714772477347744775477647774778477947804781478247834784478547864787478847894790479147924793479447954796479747984799480048014802480348044805480648074808480948104811481248134814481548164817481848194820482148224823482448254826482748284829483048314832483348344835483648374838483948404841484248434844484548464847484848494850485148524853485448554856485748584859486048614862486348644865486648674868486948704871487248734874487548764877487848794880488148824883488448854886488748884889489048914892489348944895489648974898489949004901490249034904490549064907490849094910491149124913491449154916491749184919492049214922492349244925492649274928492949304931493249334934493549364937493849394940494149424943494449454946494749484949495049514952495349544955495649574958495949604961496249634964496549664967496849694970497149724973497449754976497749784979498049814982498349844985498649874988498949904991499249934994499549964997499849995000500150025003500450055006500750085009501050115012501350145015501650175018501950205021502250235024502550265027502850295030503150325033503450355036503750385039504050415042504350445045504650475048504950505051505250535054505550565057505850595060506150625063506450655066506750685069507050715072507350745075507650775078507950805081508250835084508550865087508850895090509150925093509450955096509750985099510051015102510351045105510651075108510951105111511251135114511551165117511851195120512151225123512451255126512751285129513051315132513351345135513651375138513951405141514251435144514551465147514851495150515151525153515451555156515751585159516051615162516351645165516651675168516951705171517251735174517551765177517851795180518151825183518451855186518751885189519051915192519351945195519651975198519952005201520252035204520552065207520852095210521152125213521452155216521752185219522052215222522352245225522652275228522952305231523252335234523552365237523852395240524152425243524452455246524752485249525052515252525352545255525652575258525952605261526252635264526552665267526852695270527152725273527452755276527752785279528052815282528352845285528652875288528952905291529252935294529552965297529852995300530153025303530453055306530753085309531053115312531353145315531653175318531953205321532253235324532553265327532853295330533153325333533453355336533753385339534053415342534353445345534653475348534953505351535253535354535553565357535853595360536153625363536453655366536753685369537053715372537353745375537653775378537953805381538253835384538553865387538853895390539153925393539453955396539753985399540054015402540354045405540654075408540954105411541254135414541554165417541854195420542154225423542454255426542754285429543054315432543354345435543654375438543954405441544254435444544554465447544854495450545154525453545454555456545754585459546054615462546354645465546654675468546954705471547254735474547554765477547854795480548154825483548454855486548754885489549054915492549354945495549654975498549955005501550255035504550555065507550855095510551155125513551455155516551755185519552055215522552355245525552655275528552955305531553255335534553555365537553855395540554155425543554455455546554755485549555055515552555355545555555655575558555955605561556255635564556555665567556855695570557155725573557455755576557755785579558055815582558355845585558655875588558955905591559255935594559555965597559855995600560156025603560456055606560756085609561056115612561356145615561656175618561956205621562256235624562556265627562856295630563156325633563456355636563756385639564056415642564356445645564656475648564956505651565256535654565556565657565856595660566156625663566456655666566756685669567056715672567356745675567656775678567956805681568256835684568556865687568856895690569156925693569456955696569756985699570057015702570357045705570657075708570957105711571257135714571557165717571857195720572157225723572457255726572757285729573057315732573357345735573657375738573957405741574257435744574557465747574857495750575157525753575457555756575757585759576057615762576357645765576657675768576957705771577257735774577557765777577857795780578157825783578457855786578757885789579057915792579357945795579657975798579958005801580258035804580558065807580858095810581158125813581458155816581758185819582058215822582358245825582658275828582958305831583258335834583558365837583858395840584158425843584458455846584758485849585058515852585358545855585658575858585958605861586258635864586558665867586858695870587158725873587458755876587758785879588058815882588358845885588658875888588958905891589258935894589558965897589858995900590159025903590459055906590759085909591059115912591359145915591659175918591959205921592259235924592559265927592859295930593159325933593459355936593759385939594059415942594359445945594659475948594959505951595259535954595559565957595859595960596159625963596459655966596759685969597059715972597359745975597659775978597959805981598259835984598559865987598859895990599159925993599459955996599759985999600060016002600360046005600660076008600960106011601260136014601560166017601860196020602160226023602460256026602760286029603060316032603360346035603660376038603960406041604260436044604560466047604860496050605160526053605460556056605760586059606060616062606360646065606660676068606960706071607260736074607560766077607860796080608160826083608460856086608760886089609060916092609360946095609660976098609961006101610261036104610561066107610861096110611161126113611461156116611761186119612061216122612361246125612661276128612961306131613261336134613561366137613861396140614161426143614461456146614761486149615061516152615361546155615661576158615961606161616261636164616561666167616861696170617161726173617461756176617761786179618061816182618361846185618661876188618961906191619261936194619561966197619861996200620162026203620462056206620762086209621062116212621362146215621662176218621962206221622262236224622562266227622862296230623162326233623462356236623762386239624062416242624362446245624662476248624962506251625262536254625562566257625862596260626162626263626462656266626762686269627062716272627362746275627662776278627962806281628262836284628562866287628862896290629162926293629462956296629762986299630063016302630363046305630663076308630963106311631263136314631563166317631863196320632163226323632463256326632763286329633063316332633363346335633663376338633963406341634263436344634563466347634863496350635163526353635463556356635763586359636063616362636363646365636663676368636963706371637263736374637563766377637863796380638163826383638463856386638763886389639063916392639363946395639663976398639964006401640264036404640564066407640864096410641164126413641464156416641764186419642064216422642364246425642664276428642964306431643264336434643564366437643864396440644164426443644464456446644764486449645064516452645364546455645664576458645964606461646264636464646564666467646864696470647164726473647464756476647764786479648064816482648364846485648664876488648964906491649264936494649564966497649864996500650165026503650465056506650765086509651065116512651365146515651665176518651965206521652265236524652565266527652865296530653165326533653465356536653765386539654065416542654365446545654665476548654965506551655265536554655565566557655865596560656165626563656465656566656765686569657065716572657365746575657665776578657965806581658265836584658565866587658865896590659165926593659465956596659765986599660066016602660366046605660666076608660966106611661266136614661566166617661866196620662166226623662466256626662766286629663066316632663366346635663666376638663966406641664266436644664566466647664866496650665166526653665466556656665766586659666066616662666366646665666666676668666966706671667266736674667566766677667866796680668166826683668466856686668766886689669066916692669366946695669666976698669967006701670267036704670567066707670867096710671167126713671467156716671767186719672067216722672367246725672667276728672967306731673267336734673567366737673867396740674167426743674467456746674767486749675067516752675367546755675667576758675967606761676267636764676567666767676867696770677167726773677467756776677767786779678067816782678367846785678667876788678967906791679267936794679567966797679867996800680168026803680468056806680768086809681068116812681368146815681668176818681968206821682268236824682568266827682868296830683168326833683468356836683768386839684068416842684368446845684668476848684968506851685268536854685568566857685868596860686168626863686468656866686768686869687068716872687368746875687668776878687968806881688268836884688568866887688868896890689168926893689468956896689768986899690069016902690369046905690669076908690969106911691269136914691569166917691869196920692169226923692469256926692769286929693069316932693369346935693669376938693969406941694269436944694569466947694869496950695169526953695469556956695769586959696069616962696369646965696669676968696969706971697269736974697569766977697869796980698169826983698469856986698769886989699069916992699369946995699669976998699970007001700270037004700570067007700870097010701170127013701470157016701770187019702070217022702370247025702670277028702970307031703270337034703570367037703870397040704170427043704470457046704770487049705070517052705370547055705670577058705970607061706270637064706570667067706870697070707170727073707470757076707770787079708070817082708370847085708670877088708970907091709270937094709570967097709870997100710171027103710471057106710771087109711071117112711371147115711671177118711971207121712271237124712571267127712871297130713171327133713471357136713771387139714071417142714371447145714671477148714971507151715271537154715571567157715871597160716171627163716471657166716771687169717071717172717371747175717671777178717971807181718271837184718571867187718871897190719171927193719471957196719771987199720072017202720372047205720672077208720972107211721272137214721572167217721872197220722172227223722472257226722772287229723072317232723372347235723672377238723972407241724272437244724572467247724872497250725172527253725472557256725772587259726072617262726372647265726672677268726972707271727272737274727572767277727872797280728172827283728472857286728772887289729072917292729372947295729672977298729973007301730273037304730573067307730873097310731173127313731473157316731773187319732073217322732373247325732673277328732973307331733273337334733573367337733873397340734173427343734473457346734773487349735073517352735373547355735673577358735973607361736273637364736573667367736873697370737173727373737473757376737773787379738073817382738373847385738673877388738973907391739273937394739573967397739873997400740174027403740474057406740774087409741074117412741374147415741674177418741974207421742274237424742574267427742874297430743174327433743474357436743774387439744074417442744374447445744674477448744974507451745274537454745574567457745874597460746174627463746474657466746774687469747074717472747374747475747674777478747974807481748274837484748574867487748874897490749174927493749474957496749774987499750075017502750375047505750675077508750975107511751275137514751575167517751875197520752175227523752475257526752775287529753075317532753375347535753675377538753975407541754275437544754575467547754875497550755175527553755475557556755775587559756075617562756375647565756675677568756975707571757275737574757575767577757875797580758175827583758475857586758775887589759075917592759375947595759675977598759976007601760276037604760576067607760876097610761176127613761476157616761776187619762076217622762376247625762676277628762976307631763276337634763576367637763876397640764176427643764476457646764776487649765076517652765376547655765676577658765976607661766276637664766576667667766876697670767176727673767476757676767776787679768076817682768376847685768676877688768976907691769276937694769576967697769876997700770177027703770477057706770777087709771077117712771377147715771677177718771977207721772277237724772577267727772877297730773177327733773477357736773777387739774077417742774377447745774677477748774977507751775277537754775577567757775877597760776177627763776477657766776777687769777077717772777377747775777677777778777977807781778277837784778577867787778877897790779177927793779477957796779777987799780078017802780378047805780678077808780978107811781278137814781578167817781878197820782178227823782478257826782778287829 |
- // SPDX-License-Identifier: GPL-2.0-or-later
- /* memcontrol.c - Memory Controller
- *
- * Copyright IBM Corporation, 2007
- * Author Balbir Singh <[email protected]>
- *
- * Copyright 2007 OpenVZ SWsoft Inc
- * Author: Pavel Emelianov <[email protected]>
- *
- * Memory thresholds
- * Copyright (C) 2009 Nokia Corporation
- * Author: Kirill A. Shutemov
- *
- * Kernel Memory Controller
- * Copyright (C) 2012 Parallels Inc. and Google Inc.
- * Authors: Glauber Costa and Suleiman Souhlal
- *
- * Native page reclaim
- * Charge lifetime sanitation
- * Lockless page tracking & accounting
- * Unified hierarchy configuration model
- * Copyright (C) 2015 Red Hat, Inc., Johannes Weiner
- *
- * Per memcg lru locking
- * Copyright (C) 2020 Alibaba, Inc, Alex Shi
- */
- #include <linux/page_counter.h>
- #include <linux/memcontrol.h>
- #include <linux/cgroup.h>
- #include <linux/pagewalk.h>
- #include <linux/sched/mm.h>
- #include <linux/shmem_fs.h>
- #include <linux/hugetlb.h>
- #include <linux/pagemap.h>
- #include <linux/vm_event_item.h>
- #include <linux/smp.h>
- #include <linux/page-flags.h>
- #include <linux/backing-dev.h>
- #include <linux/bit_spinlock.h>
- #include <linux/rcupdate.h>
- #include <linux/limits.h>
- #include <linux/export.h>
- #include <linux/mutex.h>
- #include <linux/rbtree.h>
- #include <linux/slab.h>
- #include <linux/swap.h>
- #include <linux/swapops.h>
- #include <linux/spinlock.h>
- #include <linux/eventfd.h>
- #include <linux/poll.h>
- #include <linux/sort.h>
- #include <linux/fs.h>
- #include <linux/seq_file.h>
- #include <linux/vmpressure.h>
- #include <linux/memremap.h>
- #include <linux/mm_inline.h>
- #include <linux/swap_cgroup.h>
- #include <linux/cpu.h>
- #include <linux/oom.h>
- #include <linux/lockdep.h>
- #include <linux/file.h>
- #include <linux/resume_user_mode.h>
- #include <linux/psi.h>
- #include <linux/seq_buf.h>
- #include "internal.h"
- #include <net/sock.h>
- #include <net/ip.h>
- #include "slab.h"
- #include "swap.h"
- #include <linux/uaccess.h>
- #include <trace/events/vmscan.h>
- #include <trace/hooks/mm.h>
- struct cgroup_subsys memory_cgrp_subsys __read_mostly;
- EXPORT_SYMBOL(memory_cgrp_subsys);
- struct mem_cgroup *root_mem_cgroup __read_mostly;
- EXPORT_SYMBOL_GPL(root_mem_cgroup);
- /* Active memory cgroup to use from an interrupt context */
- DEFINE_PER_CPU(struct mem_cgroup *, int_active_memcg);
- EXPORT_PER_CPU_SYMBOL_GPL(int_active_memcg);
- /* Socket memory accounting disabled? */
- static bool cgroup_memory_nosocket __ro_after_init;
- /* Kernel memory accounting disabled? */
- static bool cgroup_memory_nokmem __ro_after_init;
- #ifdef CONFIG_CGROUP_WRITEBACK
- static DECLARE_WAIT_QUEUE_HEAD(memcg_cgwb_frn_waitq);
- #endif
- /* Whether legacy memory+swap accounting is active */
- static bool do_memsw_account(void)
- {
- return !cgroup_subsys_on_dfl(memory_cgrp_subsys);
- }
- #define THRESHOLDS_EVENTS_TARGET 128
- #define SOFTLIMIT_EVENTS_TARGET 1024
- /*
- * Cgroups above their limits are maintained in a RB-Tree, independent of
- * their hierarchy representation
- */
- struct mem_cgroup_tree_per_node {
- struct rb_root rb_root;
- struct rb_node *rb_rightmost;
- spinlock_t lock;
- };
- struct mem_cgroup_tree {
- struct mem_cgroup_tree_per_node *rb_tree_per_node[MAX_NUMNODES];
- };
- static struct mem_cgroup_tree soft_limit_tree __read_mostly;
- /* for OOM */
- struct mem_cgroup_eventfd_list {
- struct list_head list;
- struct eventfd_ctx *eventfd;
- };
- /*
- * cgroup_event represents events which userspace want to receive.
- */
- struct mem_cgroup_event {
- /*
- * memcg which the event belongs to.
- */
- struct mem_cgroup *memcg;
- /*
- * eventfd to signal userspace about the event.
- */
- struct eventfd_ctx *eventfd;
- /*
- * Each of these stored in a list by the cgroup.
- */
- struct list_head list;
- /*
- * register_event() callback will be used to add new userspace
- * waiter for changes related to this event. Use eventfd_signal()
- * on eventfd to send notification to userspace.
- */
- int (*register_event)(struct mem_cgroup *memcg,
- struct eventfd_ctx *eventfd, const char *args);
- /*
- * unregister_event() callback will be called when userspace closes
- * the eventfd or on cgroup removing. This callback must be set,
- * if you want provide notification functionality.
- */
- void (*unregister_event)(struct mem_cgroup *memcg,
- struct eventfd_ctx *eventfd);
- /*
- * All fields below needed to unregister event when
- * userspace closes eventfd.
- */
- poll_table pt;
- wait_queue_head_t *wqh;
- wait_queue_entry_t wait;
- struct work_struct remove;
- };
- static void mem_cgroup_threshold(struct mem_cgroup *memcg);
- static void mem_cgroup_oom_notify(struct mem_cgroup *memcg);
- /* Stuffs for move charges at task migration. */
- /*
- * Types of charges to be moved.
- */
- #define MOVE_ANON 0x1U
- #define MOVE_FILE 0x2U
- #define MOVE_MASK (MOVE_ANON | MOVE_FILE)
- /* "mc" and its members are protected by cgroup_mutex */
- static struct move_charge_struct {
- spinlock_t lock; /* for from, to */
- struct mm_struct *mm;
- struct mem_cgroup *from;
- struct mem_cgroup *to;
- unsigned long flags;
- unsigned long precharge;
- unsigned long moved_charge;
- unsigned long moved_swap;
- struct task_struct *moving_task; /* a task moving charges */
- wait_queue_head_t waitq; /* a waitq for other context */
- } mc = {
- .lock = __SPIN_LOCK_UNLOCKED(mc.lock),
- .waitq = __WAIT_QUEUE_HEAD_INITIALIZER(mc.waitq),
- };
- /*
- * Maximum loops in mem_cgroup_hierarchical_reclaim(), used for soft
- * limit reclaim to prevent infinite loops, if they ever occur.
- */
- #define MEM_CGROUP_MAX_RECLAIM_LOOPS 100
- #define MEM_CGROUP_MAX_SOFT_LIMIT_RECLAIM_LOOPS 2
- /* for encoding cft->private value on file */
- enum res_type {
- _MEM,
- _MEMSWAP,
- _KMEM,
- _TCP,
- };
- #define MEMFILE_PRIVATE(x, val) ((x) << 16 | (val))
- #define MEMFILE_TYPE(val) ((val) >> 16 & 0xffff)
- #define MEMFILE_ATTR(val) ((val) & 0xffff)
- /*
- * Iteration constructs for visiting all cgroups (under a tree). If
- * loops are exited prematurely (break), mem_cgroup_iter_break() must
- * be used for reference counting.
- */
- #define for_each_mem_cgroup_tree(iter, root) \
- for (iter = mem_cgroup_iter(root, NULL, NULL); \
- iter != NULL; \
- iter = mem_cgroup_iter(root, iter, NULL))
- #define for_each_mem_cgroup(iter) \
- for (iter = mem_cgroup_iter(NULL, NULL, NULL); \
- iter != NULL; \
- iter = mem_cgroup_iter(NULL, iter, NULL))
- static inline bool task_is_dying(void)
- {
- return tsk_is_oom_victim(current) || fatal_signal_pending(current) ||
- (current->flags & PF_EXITING);
- }
- /* Some nice accessors for the vmpressure. */
- struct vmpressure *memcg_to_vmpressure(struct mem_cgroup *memcg)
- {
- if (!memcg)
- memcg = root_mem_cgroup;
- return &memcg->vmpressure;
- }
- struct mem_cgroup *vmpressure_to_memcg(struct vmpressure *vmpr)
- {
- return container_of(vmpr, struct mem_cgroup, vmpressure);
- }
- #ifdef CONFIG_MEMCG_KMEM
- static DEFINE_SPINLOCK(objcg_lock);
- bool mem_cgroup_kmem_disabled(void)
- {
- return cgroup_memory_nokmem;
- }
- static void obj_cgroup_uncharge_pages(struct obj_cgroup *objcg,
- unsigned int nr_pages);
- static void obj_cgroup_release(struct percpu_ref *ref)
- {
- struct obj_cgroup *objcg = container_of(ref, struct obj_cgroup, refcnt);
- unsigned int nr_bytes;
- unsigned int nr_pages;
- unsigned long flags;
- /*
- * At this point all allocated objects are freed, and
- * objcg->nr_charged_bytes can't have an arbitrary byte value.
- * However, it can be PAGE_SIZE or (x * PAGE_SIZE).
- *
- * The following sequence can lead to it:
- * 1) CPU0: objcg == stock->cached_objcg
- * 2) CPU1: we do a small allocation (e.g. 92 bytes),
- * PAGE_SIZE bytes are charged
- * 3) CPU1: a process from another memcg is allocating something,
- * the stock if flushed,
- * objcg->nr_charged_bytes = PAGE_SIZE - 92
- * 5) CPU0: we do release this object,
- * 92 bytes are added to stock->nr_bytes
- * 6) CPU0: stock is flushed,
- * 92 bytes are added to objcg->nr_charged_bytes
- *
- * In the result, nr_charged_bytes == PAGE_SIZE.
- * This page will be uncharged in obj_cgroup_release().
- */
- nr_bytes = atomic_read(&objcg->nr_charged_bytes);
- WARN_ON_ONCE(nr_bytes & (PAGE_SIZE - 1));
- nr_pages = nr_bytes >> PAGE_SHIFT;
- if (nr_pages)
- obj_cgroup_uncharge_pages(objcg, nr_pages);
- spin_lock_irqsave(&objcg_lock, flags);
- list_del(&objcg->list);
- spin_unlock_irqrestore(&objcg_lock, flags);
- percpu_ref_exit(ref);
- kfree_rcu(objcg, rcu);
- }
- static struct obj_cgroup *obj_cgroup_alloc(void)
- {
- struct obj_cgroup *objcg;
- int ret;
- objcg = kzalloc(sizeof(struct obj_cgroup), GFP_KERNEL);
- if (!objcg)
- return NULL;
- ret = percpu_ref_init(&objcg->refcnt, obj_cgroup_release, 0,
- GFP_KERNEL);
- if (ret) {
- kfree(objcg);
- return NULL;
- }
- INIT_LIST_HEAD(&objcg->list);
- return objcg;
- }
- static void memcg_reparent_objcgs(struct mem_cgroup *memcg,
- struct mem_cgroup *parent)
- {
- struct obj_cgroup *objcg, *iter;
- objcg = rcu_replace_pointer(memcg->objcg, NULL, true);
- spin_lock_irq(&objcg_lock);
- /* 1) Ready to reparent active objcg. */
- list_add(&objcg->list, &memcg->objcg_list);
- /* 2) Reparent active objcg and already reparented objcgs to parent. */
- list_for_each_entry(iter, &memcg->objcg_list, list)
- WRITE_ONCE(iter->memcg, parent);
- /* 3) Move already reparented objcgs to the parent's list */
- list_splice(&memcg->objcg_list, &parent->objcg_list);
- spin_unlock_irq(&objcg_lock);
- percpu_ref_kill(&objcg->refcnt);
- }
- /*
- * A lot of the calls to the cache allocation functions are expected to be
- * inlined by the compiler. Since the calls to memcg_slab_pre_alloc_hook() are
- * conditional to this static branch, we'll have to allow modules that does
- * kmem_cache_alloc and the such to see this symbol as well
- */
- DEFINE_STATIC_KEY_FALSE(memcg_kmem_enabled_key);
- EXPORT_SYMBOL(memcg_kmem_enabled_key);
- #endif
- /**
- * mem_cgroup_css_from_page - css of the memcg associated with a page
- * @page: page of interest
- *
- * If memcg is bound to the default hierarchy, css of the memcg associated
- * with @page is returned. The returned css remains associated with @page
- * until it is released.
- *
- * If memcg is bound to a traditional hierarchy, the css of root_mem_cgroup
- * is returned.
- */
- struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page)
- {
- struct mem_cgroup *memcg;
- memcg = page_memcg(page);
- if (!memcg || !cgroup_subsys_on_dfl(memory_cgrp_subsys))
- memcg = root_mem_cgroup;
- return &memcg->css;
- }
- /**
- * page_cgroup_ino - return inode number of the memcg a page is charged to
- * @page: the page
- *
- * Look up the closest online ancestor of the memory cgroup @page is charged to
- * and return its inode number or 0 if @page is not charged to any cgroup. It
- * is safe to call this function without holding a reference to @page.
- *
- * Note, this function is inherently racy, because there is nothing to prevent
- * the cgroup inode from getting torn down and potentially reallocated a moment
- * after page_cgroup_ino() returns, so it only should be used by callers that
- * do not care (such as procfs interfaces).
- */
- ino_t page_cgroup_ino(struct page *page)
- {
- struct mem_cgroup *memcg;
- unsigned long ino = 0;
- rcu_read_lock();
- memcg = page_memcg_check(page);
- while (memcg && !(memcg->css.flags & CSS_ONLINE))
- memcg = parent_mem_cgroup(memcg);
- if (memcg)
- ino = cgroup_ino(memcg->css.cgroup);
- rcu_read_unlock();
- return ino;
- }
- static void __mem_cgroup_insert_exceeded(struct mem_cgroup_per_node *mz,
- struct mem_cgroup_tree_per_node *mctz,
- unsigned long new_usage_in_excess)
- {
- struct rb_node **p = &mctz->rb_root.rb_node;
- struct rb_node *parent = NULL;
- struct mem_cgroup_per_node *mz_node;
- bool rightmost = true;
- if (mz->on_tree)
- return;
- mz->usage_in_excess = new_usage_in_excess;
- if (!mz->usage_in_excess)
- return;
- while (*p) {
- parent = *p;
- mz_node = rb_entry(parent, struct mem_cgroup_per_node,
- tree_node);
- if (mz->usage_in_excess < mz_node->usage_in_excess) {
- p = &(*p)->rb_left;
- rightmost = false;
- } else {
- p = &(*p)->rb_right;
- }
- }
- if (rightmost)
- mctz->rb_rightmost = &mz->tree_node;
- rb_link_node(&mz->tree_node, parent, p);
- rb_insert_color(&mz->tree_node, &mctz->rb_root);
- mz->on_tree = true;
- }
- static void __mem_cgroup_remove_exceeded(struct mem_cgroup_per_node *mz,
- struct mem_cgroup_tree_per_node *mctz)
- {
- if (!mz->on_tree)
- return;
- if (&mz->tree_node == mctz->rb_rightmost)
- mctz->rb_rightmost = rb_prev(&mz->tree_node);
- rb_erase(&mz->tree_node, &mctz->rb_root);
- mz->on_tree = false;
- }
- static void mem_cgroup_remove_exceeded(struct mem_cgroup_per_node *mz,
- struct mem_cgroup_tree_per_node *mctz)
- {
- unsigned long flags;
- spin_lock_irqsave(&mctz->lock, flags);
- __mem_cgroup_remove_exceeded(mz, mctz);
- spin_unlock_irqrestore(&mctz->lock, flags);
- }
- static unsigned long soft_limit_excess(struct mem_cgroup *memcg)
- {
- unsigned long nr_pages = page_counter_read(&memcg->memory);
- unsigned long soft_limit = READ_ONCE(memcg->soft_limit);
- unsigned long excess = 0;
- if (nr_pages > soft_limit)
- excess = nr_pages - soft_limit;
- return excess;
- }
- static void mem_cgroup_update_tree(struct mem_cgroup *memcg, int nid)
- {
- unsigned long excess;
- struct mem_cgroup_per_node *mz;
- struct mem_cgroup_tree_per_node *mctz;
- if (lru_gen_enabled()) {
- if (soft_limit_excess(memcg))
- lru_gen_soft_reclaim(&memcg->nodeinfo[nid]->lruvec);
- return;
- }
- mctz = soft_limit_tree.rb_tree_per_node[nid];
- if (!mctz)
- return;
- /*
- * Necessary to update all ancestors when hierarchy is used.
- * because their event counter is not touched.
- */
- for (; memcg; memcg = parent_mem_cgroup(memcg)) {
- mz = memcg->nodeinfo[nid];
- excess = soft_limit_excess(memcg);
- /*
- * We have to update the tree if mz is on RB-tree or
- * mem is over its softlimit.
- */
- if (excess || mz->on_tree) {
- unsigned long flags;
- spin_lock_irqsave(&mctz->lock, flags);
- /* if on-tree, remove it */
- if (mz->on_tree)
- __mem_cgroup_remove_exceeded(mz, mctz);
- /*
- * Insert again. mz->usage_in_excess will be updated.
- * If excess is 0, no tree ops.
- */
- __mem_cgroup_insert_exceeded(mz, mctz, excess);
- spin_unlock_irqrestore(&mctz->lock, flags);
- }
- }
- }
- static void mem_cgroup_remove_from_trees(struct mem_cgroup *memcg)
- {
- struct mem_cgroup_tree_per_node *mctz;
- struct mem_cgroup_per_node *mz;
- int nid;
- for_each_node(nid) {
- mz = memcg->nodeinfo[nid];
- mctz = soft_limit_tree.rb_tree_per_node[nid];
- if (mctz)
- mem_cgroup_remove_exceeded(mz, mctz);
- }
- }
- static struct mem_cgroup_per_node *
- __mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_node *mctz)
- {
- struct mem_cgroup_per_node *mz;
- retry:
- mz = NULL;
- if (!mctz->rb_rightmost)
- goto done; /* Nothing to reclaim from */
- mz = rb_entry(mctz->rb_rightmost,
- struct mem_cgroup_per_node, tree_node);
- /*
- * Remove the node now but someone else can add it back,
- * we will to add it back at the end of reclaim to its correct
- * position in the tree.
- */
- __mem_cgroup_remove_exceeded(mz, mctz);
- if (!soft_limit_excess(mz->memcg) ||
- !css_tryget(&mz->memcg->css))
- goto retry;
- done:
- return mz;
- }
- static struct mem_cgroup_per_node *
- mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_node *mctz)
- {
- struct mem_cgroup_per_node *mz;
- spin_lock_irq(&mctz->lock);
- mz = __mem_cgroup_largest_soft_limit_node(mctz);
- spin_unlock_irq(&mctz->lock);
- return mz;
- }
- /*
- * memcg and lruvec stats flushing
- *
- * Many codepaths leading to stats update or read are performance sensitive and
- * adding stats flushing in such codepaths is not desirable. So, to optimize the
- * flushing the kernel does:
- *
- * 1) Periodically and asynchronously flush the stats every 2 seconds to not let
- * rstat update tree grow unbounded.
- *
- * 2) Flush the stats synchronously on reader side only when there are more than
- * (MEMCG_CHARGE_BATCH * nr_cpus) update events. Though this optimization
- * will let stats be out of sync by atmost (MEMCG_CHARGE_BATCH * nr_cpus) but
- * only for 2 seconds due to (1).
- */
- static void flush_memcg_stats_dwork(struct work_struct *w);
- static DECLARE_DEFERRABLE_WORK(stats_flush_dwork, flush_memcg_stats_dwork);
- static DEFINE_SPINLOCK(stats_flush_lock);
- static DEFINE_PER_CPU(unsigned int, stats_updates);
- static atomic_t stats_flush_threshold = ATOMIC_INIT(0);
- static u64 flush_next_time;
- #define FLUSH_TIME (2UL*HZ)
- /*
- * Accessors to ensure that preemption is disabled on PREEMPT_RT because it can
- * not rely on this as part of an acquired spinlock_t lock. These functions are
- * never used in hardirq context on PREEMPT_RT and therefore disabling preemtion
- * is sufficient.
- */
- static void memcg_stats_lock(void)
- {
- preempt_disable_nested();
- VM_WARN_ON_IRQS_ENABLED();
- }
- static void __memcg_stats_lock(void)
- {
- preempt_disable_nested();
- }
- static void memcg_stats_unlock(void)
- {
- preempt_enable_nested();
- }
- static inline void memcg_rstat_updated(struct mem_cgroup *memcg, int val)
- {
- unsigned int x;
- cgroup_rstat_updated(memcg->css.cgroup, smp_processor_id());
- x = __this_cpu_add_return(stats_updates, abs(val));
- if (x > MEMCG_CHARGE_BATCH) {
- /*
- * If stats_flush_threshold exceeds the threshold
- * (>num_online_cpus()), cgroup stats update will be triggered
- * in __mem_cgroup_flush_stats(). Increasing this var further
- * is redundant and simply adds overhead in atomic update.
- */
- if (atomic_read(&stats_flush_threshold) <= num_online_cpus())
- atomic_add(x / MEMCG_CHARGE_BATCH, &stats_flush_threshold);
- __this_cpu_write(stats_updates, 0);
- }
- }
- static void __mem_cgroup_flush_stats(void)
- {
- unsigned long flag;
- if (!spin_trylock_irqsave(&stats_flush_lock, flag))
- return;
- flush_next_time = jiffies_64 + 2*FLUSH_TIME;
- cgroup_rstat_flush_irqsafe(root_mem_cgroup->css.cgroup);
- atomic_set(&stats_flush_threshold, 0);
- spin_unlock_irqrestore(&stats_flush_lock, flag);
- }
- void mem_cgroup_flush_stats(void)
- {
- if (atomic_read(&stats_flush_threshold) > num_online_cpus())
- __mem_cgroup_flush_stats();
- }
- void mem_cgroup_flush_stats_delayed(void)
- {
- if (time_after64(jiffies_64, flush_next_time))
- mem_cgroup_flush_stats();
- }
- static void flush_memcg_stats_dwork(struct work_struct *w)
- {
- __mem_cgroup_flush_stats();
- queue_delayed_work(system_unbound_wq, &stats_flush_dwork, FLUSH_TIME);
- }
- /* Subset of vm_event_item to report for memcg event stats */
- static const unsigned int memcg_vm_event_stat[] = {
- PGPGIN,
- PGPGOUT,
- PGSCAN_KSWAPD,
- PGSCAN_DIRECT,
- PGSTEAL_KSWAPD,
- PGSTEAL_DIRECT,
- PGFAULT,
- PGMAJFAULT,
- PGREFILL,
- PGACTIVATE,
- PGDEACTIVATE,
- PGLAZYFREE,
- PGLAZYFREED,
- #if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP)
- ZSWPIN,
- ZSWPOUT,
- #endif
- #ifdef CONFIG_TRANSPARENT_HUGEPAGE
- THP_FAULT_ALLOC,
- THP_COLLAPSE_ALLOC,
- #endif
- };
- #define NR_MEMCG_EVENTS ARRAY_SIZE(memcg_vm_event_stat)
- static int mem_cgroup_events_index[NR_VM_EVENT_ITEMS] __read_mostly;
- static void init_memcg_events(void)
- {
- int i;
- for (i = 0; i < NR_MEMCG_EVENTS; ++i)
- mem_cgroup_events_index[memcg_vm_event_stat[i]] = i + 1;
- }
- static inline int memcg_events_index(enum vm_event_item idx)
- {
- return mem_cgroup_events_index[idx] - 1;
- }
- struct memcg_vmstats_percpu {
- /* Local (CPU and cgroup) page state & events */
- long state[MEMCG_NR_STAT];
- unsigned long events[NR_MEMCG_EVENTS];
- /* Delta calculation for lockless upward propagation */
- long state_prev[MEMCG_NR_STAT];
- unsigned long events_prev[NR_MEMCG_EVENTS];
- /* Cgroup1: threshold notifications & softlimit tree updates */
- unsigned long nr_page_events;
- unsigned long targets[MEM_CGROUP_NTARGETS];
- };
- struct memcg_vmstats {
- /* Aggregated (CPU and subtree) page state & events */
- long state[MEMCG_NR_STAT];
- unsigned long events[NR_MEMCG_EVENTS];
- /* Pending child counts during tree propagation */
- long state_pending[MEMCG_NR_STAT];
- unsigned long events_pending[NR_MEMCG_EVENTS];
- };
- unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx)
- {
- long x = READ_ONCE(memcg->vmstats->state[idx]);
- #ifdef CONFIG_SMP
- if (x < 0)
- x = 0;
- #endif
- return x;
- }
- /**
- * __mod_memcg_state - update cgroup memory statistics
- * @memcg: the memory cgroup
- * @idx: the stat item - can be enum memcg_stat_item or enum node_stat_item
- * @val: delta to add to the counter, can be negative
- */
- void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int val)
- {
- if (mem_cgroup_disabled())
- return;
- __this_cpu_add(memcg->vmstats_percpu->state[idx], val);
- memcg_rstat_updated(memcg, val);
- }
- /* idx can be of type enum memcg_stat_item or node_stat_item. */
- static unsigned long memcg_page_state_local(struct mem_cgroup *memcg, int idx)
- {
- long x = 0;
- int cpu;
- for_each_possible_cpu(cpu)
- x += per_cpu(memcg->vmstats_percpu->state[idx], cpu);
- #ifdef CONFIG_SMP
- if (x < 0)
- x = 0;
- #endif
- return x;
- }
- void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
- int val)
- {
- struct mem_cgroup_per_node *pn;
- struct mem_cgroup *memcg;
- pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
- memcg = pn->memcg;
- /*
- * The caller from rmap relay on disabled preemption becase they never
- * update their counter from in-interrupt context. For these two
- * counters we check that the update is never performed from an
- * interrupt context while other caller need to have disabled interrupt.
- */
- __memcg_stats_lock();
- if (IS_ENABLED(CONFIG_DEBUG_VM)) {
- switch (idx) {
- case NR_ANON_MAPPED:
- case NR_FILE_MAPPED:
- case NR_ANON_THPS:
- case NR_SHMEM_PMDMAPPED:
- case NR_FILE_PMDMAPPED:
- WARN_ON_ONCE(!in_task());
- break;
- default:
- VM_WARN_ON_IRQS_ENABLED();
- }
- }
- /* Update memcg */
- __this_cpu_add(memcg->vmstats_percpu->state[idx], val);
- /* Update lruvec */
- __this_cpu_add(pn->lruvec_stats_percpu->state[idx], val);
- memcg_rstat_updated(memcg, val);
- memcg_stats_unlock();
- }
- /**
- * __mod_lruvec_state - update lruvec memory statistics
- * @lruvec: the lruvec
- * @idx: the stat item
- * @val: delta to add to the counter, can be negative
- *
- * The lruvec is the intersection of the NUMA node and a cgroup. This
- * function updates the all three counters that are affected by a
- * change of state at this level: per-node, per-cgroup, per-lruvec.
- */
- void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
- int val)
- {
- /* Update node */
- __mod_node_page_state(lruvec_pgdat(lruvec), idx, val);
- /* Update memcg and lruvec */
- if (!mem_cgroup_disabled())
- __mod_memcg_lruvec_state(lruvec, idx, val);
- }
- EXPORT_SYMBOL_GPL(__mod_lruvec_state);
- void __mod_lruvec_page_state(struct page *page, enum node_stat_item idx,
- int val)
- {
- struct page *head = compound_head(page); /* rmap on tail pages */
- struct mem_cgroup *memcg;
- pg_data_t *pgdat = page_pgdat(page);
- struct lruvec *lruvec;
- rcu_read_lock();
- memcg = page_memcg(head);
- /* Untracked pages have no memcg, no lruvec. Update only the node */
- if (!memcg) {
- rcu_read_unlock();
- __mod_node_page_state(pgdat, idx, val);
- return;
- }
- lruvec = mem_cgroup_lruvec(memcg, pgdat);
- __mod_lruvec_state(lruvec, idx, val);
- rcu_read_unlock();
- }
- EXPORT_SYMBOL(__mod_lruvec_page_state);
- void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val)
- {
- pg_data_t *pgdat = page_pgdat(virt_to_page(p));
- struct mem_cgroup *memcg;
- struct lruvec *lruvec;
- rcu_read_lock();
- memcg = mem_cgroup_from_slab_obj(p);
- /*
- * Untracked pages have no memcg, no lruvec. Update only the
- * node. If we reparent the slab objects to the root memcg,
- * when we free the slab object, we need to update the per-memcg
- * vmstats to keep it correct for the root memcg.
- */
- if (!memcg) {
- __mod_node_page_state(pgdat, idx, val);
- } else {
- lruvec = mem_cgroup_lruvec(memcg, pgdat);
- __mod_lruvec_state(lruvec, idx, val);
- }
- rcu_read_unlock();
- }
- /**
- * __count_memcg_events - account VM events in a cgroup
- * @memcg: the memory cgroup
- * @idx: the event item
- * @count: the number of events that occurred
- */
- void __count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx,
- unsigned long count)
- {
- int index = memcg_events_index(idx);
- if (mem_cgroup_disabled() || index < 0)
- return;
- memcg_stats_lock();
- __this_cpu_add(memcg->vmstats_percpu->events[index], count);
- memcg_rstat_updated(memcg, count);
- memcg_stats_unlock();
- }
- static unsigned long memcg_events(struct mem_cgroup *memcg, int event)
- {
- int index = memcg_events_index(event);
- if (index < 0)
- return 0;
- return READ_ONCE(memcg->vmstats->events[index]);
- }
- static unsigned long memcg_events_local(struct mem_cgroup *memcg, int event)
- {
- long x = 0;
- int cpu;
- int index = memcg_events_index(event);
- if (index < 0)
- return 0;
- for_each_possible_cpu(cpu)
- x += per_cpu(memcg->vmstats_percpu->events[index], cpu);
- return x;
- }
- static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg,
- int nr_pages)
- {
- /* pagein of a big page is an event. So, ignore page size */
- if (nr_pages > 0)
- __count_memcg_events(memcg, PGPGIN, 1);
- else {
- __count_memcg_events(memcg, PGPGOUT, 1);
- nr_pages = -nr_pages; /* for event */
- }
- __this_cpu_add(memcg->vmstats_percpu->nr_page_events, nr_pages);
- }
- static bool mem_cgroup_event_ratelimit(struct mem_cgroup *memcg,
- enum mem_cgroup_events_target target)
- {
- unsigned long val, next;
- val = __this_cpu_read(memcg->vmstats_percpu->nr_page_events);
- next = __this_cpu_read(memcg->vmstats_percpu->targets[target]);
- /* from time_after() in jiffies.h */
- if ((long)(next - val) < 0) {
- switch (target) {
- case MEM_CGROUP_TARGET_THRESH:
- next = val + THRESHOLDS_EVENTS_TARGET;
- break;
- case MEM_CGROUP_TARGET_SOFTLIMIT:
- next = val + SOFTLIMIT_EVENTS_TARGET;
- break;
- default:
- break;
- }
- __this_cpu_write(memcg->vmstats_percpu->targets[target], next);
- return true;
- }
- return false;
- }
- /*
- * Check events in order.
- *
- */
- static void memcg_check_events(struct mem_cgroup *memcg, int nid)
- {
- if (IS_ENABLED(CONFIG_PREEMPT_RT))
- return;
- /* threshold event is triggered in finer grain than soft limit */
- if (unlikely(mem_cgroup_event_ratelimit(memcg,
- MEM_CGROUP_TARGET_THRESH))) {
- bool do_softlimit;
- do_softlimit = mem_cgroup_event_ratelimit(memcg,
- MEM_CGROUP_TARGET_SOFTLIMIT);
- mem_cgroup_threshold(memcg);
- if (unlikely(do_softlimit))
- mem_cgroup_update_tree(memcg, nid);
- }
- }
- struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
- {
- /*
- * mm_update_next_owner() may clear mm->owner to NULL
- * if it races with swapoff, page migration, etc.
- * So this can be called with p == NULL.
- */
- if (unlikely(!p))
- return NULL;
- return mem_cgroup_from_css(task_css(p, memory_cgrp_id));
- }
- EXPORT_SYMBOL(mem_cgroup_from_task);
- static __always_inline struct mem_cgroup *active_memcg(void)
- {
- if (!in_task())
- return this_cpu_read(int_active_memcg);
- else
- return current->active_memcg;
- }
- /**
- * get_mem_cgroup_from_mm: Obtain a reference on given mm_struct's memcg.
- * @mm: mm from which memcg should be extracted. It can be NULL.
- *
- * Obtain a reference on mm->memcg and returns it if successful. If mm
- * is NULL, then the memcg is chosen as follows:
- * 1) The active memcg, if set.
- * 2) current->mm->memcg, if available
- * 3) root memcg
- * If mem_cgroup is disabled, NULL is returned.
- */
- struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm)
- {
- struct mem_cgroup *memcg;
- if (mem_cgroup_disabled())
- return NULL;
- /*
- * Page cache insertions can happen without an
- * actual mm context, e.g. during disk probing
- * on boot, loopback IO, acct() writes etc.
- *
- * No need to css_get on root memcg as the reference
- * counting is disabled on the root level in the
- * cgroup core. See CSS_NO_REF.
- */
- if (unlikely(!mm)) {
- memcg = active_memcg();
- if (unlikely(memcg)) {
- /* remote memcg must hold a ref */
- css_get(&memcg->css);
- return memcg;
- }
- mm = current->mm;
- if (unlikely(!mm))
- return root_mem_cgroup;
- }
- rcu_read_lock();
- do {
- memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
- if (unlikely(!memcg))
- memcg = root_mem_cgroup;
- } while (!css_tryget(&memcg->css));
- rcu_read_unlock();
- return memcg;
- }
- EXPORT_SYMBOL(get_mem_cgroup_from_mm);
- static __always_inline bool memcg_kmem_bypass(void)
- {
- /* Allow remote memcg charging from any context. */
- if (unlikely(active_memcg()))
- return false;
- /* Memcg to charge can't be determined. */
- if (!in_task() || !current->mm || (current->flags & PF_KTHREAD))
- return true;
- return false;
- }
- /**
- * mem_cgroup_iter - iterate over memory cgroup hierarchy
- * @root: hierarchy root
- * @prev: previously returned memcg, NULL on first invocation
- * @reclaim: cookie for shared reclaim walks, NULL for full walks
- *
- * Returns references to children of the hierarchy below @root, or
- * @root itself, or %NULL after a full round-trip.
- *
- * Caller must pass the return value in @prev on subsequent
- * invocations for reference counting, or use mem_cgroup_iter_break()
- * to cancel a hierarchy walk before the round-trip is complete.
- *
- * Reclaimers can specify a node in @reclaim to divide up the memcgs
- * in the hierarchy among all concurrent reclaimers operating on the
- * same node.
- */
- struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
- struct mem_cgroup *prev,
- struct mem_cgroup_reclaim_cookie *reclaim)
- {
- struct mem_cgroup_reclaim_iter *iter;
- struct cgroup_subsys_state *css = NULL;
- struct mem_cgroup *memcg = NULL;
- struct mem_cgroup *pos = NULL;
- if (mem_cgroup_disabled())
- return NULL;
- if (!root)
- root = root_mem_cgroup;
- rcu_read_lock();
- if (reclaim) {
- struct mem_cgroup_per_node *mz;
- mz = root->nodeinfo[reclaim->pgdat->node_id];
- iter = &mz->iter;
- /*
- * On start, join the current reclaim iteration cycle.
- * Exit when a concurrent walker completes it.
- */
- if (!prev)
- reclaim->generation = iter->generation;
- else if (reclaim->generation != iter->generation)
- goto out_unlock;
- while (1) {
- pos = READ_ONCE(iter->position);
- if (!pos || css_tryget(&pos->css))
- break;
- /*
- * css reference reached zero, so iter->position will
- * be cleared by ->css_released. However, we should not
- * rely on this happening soon, because ->css_released
- * is called from a work queue, and by busy-waiting we
- * might block it. So we clear iter->position right
- * away.
- */
- (void)cmpxchg(&iter->position, pos, NULL);
- }
- } else if (prev) {
- pos = prev;
- }
- if (pos)
- css = &pos->css;
- for (;;) {
- css = css_next_descendant_pre(css, &root->css);
- if (!css) {
- /*
- * Reclaimers share the hierarchy walk, and a
- * new one might jump in right at the end of
- * the hierarchy - make sure they see at least
- * one group and restart from the beginning.
- */
- if (!prev)
- continue;
- break;
- }
- /*
- * Verify the css and acquire a reference. The root
- * is provided by the caller, so we know it's alive
- * and kicking, and don't take an extra reference.
- */
- if (css == &root->css || css_tryget(css)) {
- memcg = mem_cgroup_from_css(css);
- break;
- }
- }
- if (reclaim) {
- /*
- * The position could have already been updated by a competing
- * thread, so check that the value hasn't changed since we read
- * it to avoid reclaiming from the same cgroup twice.
- */
- (void)cmpxchg(&iter->position, pos, memcg);
- if (pos)
- css_put(&pos->css);
- if (!memcg)
- iter->generation++;
- }
- out_unlock:
- rcu_read_unlock();
- if (prev && prev != root)
- css_put(&prev->css);
- return memcg;
- }
- /**
- * mem_cgroup_iter_break - abort a hierarchy walk prematurely
- * @root: hierarchy root
- * @prev: last visited hierarchy member as returned by mem_cgroup_iter()
- */
- void mem_cgroup_iter_break(struct mem_cgroup *root,
- struct mem_cgroup *prev)
- {
- if (!root)
- root = root_mem_cgroup;
- if (prev && prev != root)
- css_put(&prev->css);
- }
- static void __invalidate_reclaim_iterators(struct mem_cgroup *from,
- struct mem_cgroup *dead_memcg)
- {
- struct mem_cgroup_reclaim_iter *iter;
- struct mem_cgroup_per_node *mz;
- int nid;
- for_each_node(nid) {
- mz = from->nodeinfo[nid];
- iter = &mz->iter;
- cmpxchg(&iter->position, dead_memcg, NULL);
- }
- }
- static void invalidate_reclaim_iterators(struct mem_cgroup *dead_memcg)
- {
- struct mem_cgroup *memcg = dead_memcg;
- struct mem_cgroup *last;
- do {
- __invalidate_reclaim_iterators(memcg, dead_memcg);
- last = memcg;
- } while ((memcg = parent_mem_cgroup(memcg)));
- /*
- * When cgroup1 non-hierarchy mode is used,
- * parent_mem_cgroup() does not walk all the way up to the
- * cgroup root (root_mem_cgroup). So we have to handle
- * dead_memcg from cgroup root separately.
- */
- if (last != root_mem_cgroup)
- __invalidate_reclaim_iterators(root_mem_cgroup,
- dead_memcg);
- }
- /**
- * mem_cgroup_scan_tasks - iterate over tasks of a memory cgroup hierarchy
- * @memcg: hierarchy root
- * @fn: function to call for each task
- * @arg: argument passed to @fn
- *
- * This function iterates over tasks attached to @memcg or to any of its
- * descendants and calls @fn for each task. If @fn returns a non-zero
- * value, the function breaks the iteration loop and returns the value.
- * Otherwise, it will iterate over all tasks and return 0.
- *
- * This function must not be called for the root memory cgroup.
- */
- int mem_cgroup_scan_tasks(struct mem_cgroup *memcg,
- int (*fn)(struct task_struct *, void *), void *arg)
- {
- struct mem_cgroup *iter;
- int ret = 0;
- BUG_ON(memcg == root_mem_cgroup);
- for_each_mem_cgroup_tree(iter, memcg) {
- struct css_task_iter it;
- struct task_struct *task;
- css_task_iter_start(&iter->css, CSS_TASK_ITER_PROCS, &it);
- while (!ret && (task = css_task_iter_next(&it)))
- ret = fn(task, arg);
- css_task_iter_end(&it);
- if (ret) {
- mem_cgroup_iter_break(memcg, iter);
- break;
- }
- }
- return ret;
- }
- #ifdef CONFIG_DEBUG_VM
- void lruvec_memcg_debug(struct lruvec *lruvec, struct folio *folio)
- {
- struct mem_cgroup *memcg;
- if (mem_cgroup_disabled())
- return;
- memcg = folio_memcg(folio);
- if (!memcg)
- VM_BUG_ON_FOLIO(lruvec_memcg(lruvec) != root_mem_cgroup, folio);
- else
- VM_BUG_ON_FOLIO(lruvec_memcg(lruvec) != memcg, folio);
- }
- #endif
- /**
- * folio_lruvec_lock - Lock the lruvec for a folio.
- * @folio: Pointer to the folio.
- *
- * These functions are safe to use under any of the following conditions:
- * - folio locked
- * - folio_test_lru false
- * - folio_memcg_lock()
- * - folio frozen (refcount of 0)
- *
- * Return: The lruvec this folio is on with its lock held.
- */
- struct lruvec *folio_lruvec_lock(struct folio *folio)
- {
- struct lruvec *lruvec = folio_lruvec(folio);
- spin_lock(&lruvec->lru_lock);
- lruvec_memcg_debug(lruvec, folio);
- return lruvec;
- }
- /**
- * folio_lruvec_lock_irq - Lock the lruvec for a folio.
- * @folio: Pointer to the folio.
- *
- * These functions are safe to use under any of the following conditions:
- * - folio locked
- * - folio_test_lru false
- * - folio_memcg_lock()
- * - folio frozen (refcount of 0)
- *
- * Return: The lruvec this folio is on with its lock held and interrupts
- * disabled.
- */
- struct lruvec *folio_lruvec_lock_irq(struct folio *folio)
- {
- struct lruvec *lruvec = folio_lruvec(folio);
- spin_lock_irq(&lruvec->lru_lock);
- lruvec_memcg_debug(lruvec, folio);
- return lruvec;
- }
- /**
- * folio_lruvec_lock_irqsave - Lock the lruvec for a folio.
- * @folio: Pointer to the folio.
- * @flags: Pointer to irqsave flags.
- *
- * These functions are safe to use under any of the following conditions:
- * - folio locked
- * - folio_test_lru false
- * - folio_memcg_lock()
- * - folio frozen (refcount of 0)
- *
- * Return: The lruvec this folio is on with its lock held and interrupts
- * disabled.
- */
- struct lruvec *folio_lruvec_lock_irqsave(struct folio *folio,
- unsigned long *flags)
- {
- struct lruvec *lruvec = folio_lruvec(folio);
- spin_lock_irqsave(&lruvec->lru_lock, *flags);
- lruvec_memcg_debug(lruvec, folio);
- return lruvec;
- }
- /**
- * mem_cgroup_update_lru_size - account for adding or removing an lru page
- * @lruvec: mem_cgroup per zone lru vector
- * @lru: index of lru list the page is sitting on
- * @zid: zone id of the accounted pages
- * @nr_pages: positive when adding or negative when removing
- *
- * This function must be called under lru_lock, just before a page is added
- * to or just after a page is removed from an lru list.
- */
- void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru,
- int zid, int nr_pages)
- {
- struct mem_cgroup_per_node *mz;
- unsigned long *lru_size;
- long size;
- if (mem_cgroup_disabled())
- return;
- mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
- lru_size = &mz->lru_zone_size[zid][lru];
- if (nr_pages < 0)
- *lru_size += nr_pages;
- size = *lru_size;
- if (WARN_ONCE(size < 0,
- "%s(%p, %d, %d): lru_size %ld\n",
- __func__, lruvec, lru, nr_pages, size)) {
- VM_BUG_ON(1);
- *lru_size = 0;
- }
- if (nr_pages > 0)
- *lru_size += nr_pages;
- }
- EXPORT_SYMBOL_GPL(mem_cgroup_update_lru_size);
- /**
- * mem_cgroup_margin - calculate chargeable space of a memory cgroup
- * @memcg: the memory cgroup
- *
- * Returns the maximum amount of memory @mem can be charged with, in
- * pages.
- */
- static unsigned long mem_cgroup_margin(struct mem_cgroup *memcg)
- {
- unsigned long margin = 0;
- unsigned long count;
- unsigned long limit;
- count = page_counter_read(&memcg->memory);
- limit = READ_ONCE(memcg->memory.max);
- if (count < limit)
- margin = limit - count;
- if (do_memsw_account()) {
- count = page_counter_read(&memcg->memsw);
- limit = READ_ONCE(memcg->memsw.max);
- if (count < limit)
- margin = min(margin, limit - count);
- else
- margin = 0;
- }
- return margin;
- }
- /*
- * A routine for checking "mem" is under move_account() or not.
- *
- * Checking a cgroup is mc.from or mc.to or under hierarchy of
- * moving cgroups. This is for waiting at high-memory pressure
- * caused by "move".
- */
- static bool mem_cgroup_under_move(struct mem_cgroup *memcg)
- {
- struct mem_cgroup *from;
- struct mem_cgroup *to;
- bool ret = false;
- /*
- * Unlike task_move routines, we access mc.to, mc.from not under
- * mutual exclusion by cgroup_mutex. Here, we take spinlock instead.
- */
- spin_lock(&mc.lock);
- from = mc.from;
- to = mc.to;
- if (!from)
- goto unlock;
- ret = mem_cgroup_is_descendant(from, memcg) ||
- mem_cgroup_is_descendant(to, memcg);
- unlock:
- spin_unlock(&mc.lock);
- return ret;
- }
- static bool mem_cgroup_wait_acct_move(struct mem_cgroup *memcg)
- {
- if (mc.moving_task && current != mc.moving_task) {
- if (mem_cgroup_under_move(memcg)) {
- DEFINE_WAIT(wait);
- prepare_to_wait(&mc.waitq, &wait, TASK_INTERRUPTIBLE);
- /* moving charge context might have finished. */
- if (mc.moving_task)
- schedule();
- finish_wait(&mc.waitq, &wait);
- return true;
- }
- }
- return false;
- }
- struct memory_stat {
- const char *name;
- unsigned int idx;
- };
- static const struct memory_stat memory_stats[] = {
- { "anon", NR_ANON_MAPPED },
- { "file", NR_FILE_PAGES },
- { "kernel", MEMCG_KMEM },
- { "kernel_stack", NR_KERNEL_STACK_KB },
- { "pagetables", NR_PAGETABLE },
- { "sec_pagetables", NR_SECONDARY_PAGETABLE },
- { "percpu", MEMCG_PERCPU_B },
- { "sock", MEMCG_SOCK },
- { "vmalloc", MEMCG_VMALLOC },
- { "shmem", NR_SHMEM },
- #if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP)
- { "zswap", MEMCG_ZSWAP_B },
- { "zswapped", MEMCG_ZSWAPPED },
- #endif
- { "file_mapped", NR_FILE_MAPPED },
- { "file_dirty", NR_FILE_DIRTY },
- { "file_writeback", NR_WRITEBACK },
- #ifdef CONFIG_SWAP
- { "swapcached", NR_SWAPCACHE },
- #endif
- #ifdef CONFIG_TRANSPARENT_HUGEPAGE
- { "anon_thp", NR_ANON_THPS },
- { "file_thp", NR_FILE_THPS },
- { "shmem_thp", NR_SHMEM_THPS },
- #endif
- { "inactive_anon", NR_INACTIVE_ANON },
- { "active_anon", NR_ACTIVE_ANON },
- { "inactive_file", NR_INACTIVE_FILE },
- { "active_file", NR_ACTIVE_FILE },
- { "unevictable", NR_UNEVICTABLE },
- { "slab_reclaimable", NR_SLAB_RECLAIMABLE_B },
- { "slab_unreclaimable", NR_SLAB_UNRECLAIMABLE_B },
- /* The memory events */
- { "workingset_refault_anon", WORKINGSET_REFAULT_ANON },
- { "workingset_refault_file", WORKINGSET_REFAULT_FILE },
- { "workingset_activate_anon", WORKINGSET_ACTIVATE_ANON },
- { "workingset_activate_file", WORKINGSET_ACTIVATE_FILE },
- { "workingset_restore_anon", WORKINGSET_RESTORE_ANON },
- { "workingset_restore_file", WORKINGSET_RESTORE_FILE },
- { "workingset_nodereclaim", WORKINGSET_NODERECLAIM },
- };
- /* Translate stat items to the correct unit for memory.stat output */
- static int memcg_page_state_unit(int item)
- {
- switch (item) {
- case MEMCG_PERCPU_B:
- case MEMCG_ZSWAP_B:
- case NR_SLAB_RECLAIMABLE_B:
- case NR_SLAB_UNRECLAIMABLE_B:
- case WORKINGSET_REFAULT_ANON:
- case WORKINGSET_REFAULT_FILE:
- case WORKINGSET_ACTIVATE_ANON:
- case WORKINGSET_ACTIVATE_FILE:
- case WORKINGSET_RESTORE_ANON:
- case WORKINGSET_RESTORE_FILE:
- case WORKINGSET_NODERECLAIM:
- return 1;
- case NR_KERNEL_STACK_KB:
- return SZ_1K;
- default:
- return PAGE_SIZE;
- }
- }
- static inline unsigned long memcg_page_state_output(struct mem_cgroup *memcg,
- int item)
- {
- return memcg_page_state(memcg, item) * memcg_page_state_unit(item);
- }
- static void memory_stat_format(struct mem_cgroup *memcg, char *buf, int bufsize)
- {
- struct seq_buf s;
- int i;
- seq_buf_init(&s, buf, bufsize);
- /*
- * Provide statistics on the state of the memory subsystem as
- * well as cumulative event counters that show past behavior.
- *
- * This list is ordered following a combination of these gradients:
- * 1) generic big picture -> specifics and details
- * 2) reflecting userspace activity -> reflecting kernel heuristics
- *
- * Current memory state:
- */
- mem_cgroup_flush_stats();
- for (i = 0; i < ARRAY_SIZE(memory_stats); i++) {
- u64 size;
- size = memcg_page_state_output(memcg, memory_stats[i].idx);
- seq_buf_printf(&s, "%s %llu\n", memory_stats[i].name, size);
- if (unlikely(memory_stats[i].idx == NR_SLAB_UNRECLAIMABLE_B)) {
- size += memcg_page_state_output(memcg,
- NR_SLAB_RECLAIMABLE_B);
- seq_buf_printf(&s, "slab %llu\n", size);
- }
- }
- /* Accumulated memory events */
- seq_buf_printf(&s, "pgscan %lu\n",
- memcg_events(memcg, PGSCAN_KSWAPD) +
- memcg_events(memcg, PGSCAN_DIRECT));
- seq_buf_printf(&s, "pgsteal %lu\n",
- memcg_events(memcg, PGSTEAL_KSWAPD) +
- memcg_events(memcg, PGSTEAL_DIRECT));
- for (i = 0; i < ARRAY_SIZE(memcg_vm_event_stat); i++) {
- if (memcg_vm_event_stat[i] == PGPGIN ||
- memcg_vm_event_stat[i] == PGPGOUT)
- continue;
- seq_buf_printf(&s, "%s %lu\n",
- vm_event_name(memcg_vm_event_stat[i]),
- memcg_events(memcg, memcg_vm_event_stat[i]));
- }
- /* The above should easily fit into one page */
- WARN_ON_ONCE(seq_buf_has_overflowed(&s));
- }
- #define K(x) ((x) << (PAGE_SHIFT-10))
- /**
- * mem_cgroup_print_oom_context: Print OOM information relevant to
- * memory controller.
- * @memcg: The memory cgroup that went over limit
- * @p: Task that is going to be killed
- *
- * NOTE: @memcg and @p's mem_cgroup can be different when hierarchy is
- * enabled
- */
- void mem_cgroup_print_oom_context(struct mem_cgroup *memcg, struct task_struct *p)
- {
- rcu_read_lock();
- if (memcg) {
- pr_cont(",oom_memcg=");
- pr_cont_cgroup_path(memcg->css.cgroup);
- } else
- pr_cont(",global_oom");
- if (p) {
- pr_cont(",task_memcg=");
- pr_cont_cgroup_path(task_cgroup(p, memory_cgrp_id));
- }
- rcu_read_unlock();
- }
- /**
- * mem_cgroup_print_oom_meminfo: Print OOM memory information relevant to
- * memory controller.
- * @memcg: The memory cgroup that went over limit
- */
- void mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg)
- {
- /* Use static buffer, for the caller is holding oom_lock. */
- static char buf[PAGE_SIZE];
- lockdep_assert_held(&oom_lock);
- pr_info("memory: usage %llukB, limit %llukB, failcnt %lu\n",
- K((u64)page_counter_read(&memcg->memory)),
- K((u64)READ_ONCE(memcg->memory.max)), memcg->memory.failcnt);
- if (cgroup_subsys_on_dfl(memory_cgrp_subsys))
- pr_info("swap: usage %llukB, limit %llukB, failcnt %lu\n",
- K((u64)page_counter_read(&memcg->swap)),
- K((u64)READ_ONCE(memcg->swap.max)), memcg->swap.failcnt);
- else {
- pr_info("memory+swap: usage %llukB, limit %llukB, failcnt %lu\n",
- K((u64)page_counter_read(&memcg->memsw)),
- K((u64)memcg->memsw.max), memcg->memsw.failcnt);
- pr_info("kmem: usage %llukB, limit %llukB, failcnt %lu\n",
- K((u64)page_counter_read(&memcg->kmem)),
- K((u64)memcg->kmem.max), memcg->kmem.failcnt);
- }
- pr_info("Memory cgroup stats for ");
- pr_cont_cgroup_path(memcg->css.cgroup);
- pr_cont(":");
- memory_stat_format(memcg, buf, sizeof(buf));
- pr_info("%s", buf);
- }
- /*
- * Return the memory (and swap, if configured) limit for a memcg.
- */
- unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg)
- {
- unsigned long max = READ_ONCE(memcg->memory.max);
- if (do_memsw_account()) {
- if (mem_cgroup_swappiness(memcg)) {
- /* Calculate swap excess capacity from memsw limit */
- unsigned long swap = READ_ONCE(memcg->memsw.max) - max;
- max += min(swap, (unsigned long)total_swap_pages);
- }
- } else {
- if (mem_cgroup_swappiness(memcg))
- max += min(READ_ONCE(memcg->swap.max),
- (unsigned long)total_swap_pages);
- }
- return max;
- }
- unsigned long mem_cgroup_size(struct mem_cgroup *memcg)
- {
- return page_counter_read(&memcg->memory);
- }
- static bool mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
- int order)
- {
- struct oom_control oc = {
- .zonelist = NULL,
- .nodemask = NULL,
- .memcg = memcg,
- .gfp_mask = gfp_mask,
- .order = order,
- };
- bool ret = true;
- if (mutex_lock_killable(&oom_lock))
- return true;
- if (mem_cgroup_margin(memcg) >= (1 << order))
- goto unlock;
- /*
- * A few threads which were not waiting at mutex_lock_killable() can
- * fail to bail out. Therefore, check again after holding oom_lock.
- */
- ret = task_is_dying() || out_of_memory(&oc);
- unlock:
- mutex_unlock(&oom_lock);
- return ret;
- }
- static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg,
- pg_data_t *pgdat,
- gfp_t gfp_mask,
- unsigned long *total_scanned)
- {
- struct mem_cgroup *victim = NULL;
- int total = 0;
- int loop = 0;
- unsigned long excess;
- unsigned long nr_scanned;
- struct mem_cgroup_reclaim_cookie reclaim = {
- .pgdat = pgdat,
- };
- excess = soft_limit_excess(root_memcg);
- while (1) {
- victim = mem_cgroup_iter(root_memcg, victim, &reclaim);
- if (!victim) {
- loop++;
- if (loop >= 2) {
- /*
- * If we have not been able to reclaim
- * anything, it might because there are
- * no reclaimable pages under this hierarchy
- */
- if (!total)
- break;
- /*
- * We want to do more targeted reclaim.
- * excess >> 2 is not to excessive so as to
- * reclaim too much, nor too less that we keep
- * coming back to reclaim from this cgroup
- */
- if (total >= (excess >> 2) ||
- (loop > MEM_CGROUP_MAX_RECLAIM_LOOPS))
- break;
- }
- continue;
- }
- total += mem_cgroup_shrink_node(victim, gfp_mask, false,
- pgdat, &nr_scanned);
- *total_scanned += nr_scanned;
- if (!soft_limit_excess(root_memcg))
- break;
- }
- mem_cgroup_iter_break(root_memcg, victim);
- return total;
- }
- #ifdef CONFIG_LOCKDEP
- static struct lockdep_map memcg_oom_lock_dep_map = {
- .name = "memcg_oom_lock",
- };
- #endif
- static DEFINE_SPINLOCK(memcg_oom_lock);
- /*
- * Check OOM-Killer is already running under our hierarchy.
- * If someone is running, return false.
- */
- static bool mem_cgroup_oom_trylock(struct mem_cgroup *memcg)
- {
- struct mem_cgroup *iter, *failed = NULL;
- spin_lock(&memcg_oom_lock);
- for_each_mem_cgroup_tree(iter, memcg) {
- if (iter->oom_lock) {
- /*
- * this subtree of our hierarchy is already locked
- * so we cannot give a lock.
- */
- failed = iter;
- mem_cgroup_iter_break(memcg, iter);
- break;
- } else
- iter->oom_lock = true;
- }
- if (failed) {
- /*
- * OK, we failed to lock the whole subtree so we have
- * to clean up what we set up to the failing subtree
- */
- for_each_mem_cgroup_tree(iter, memcg) {
- if (iter == failed) {
- mem_cgroup_iter_break(memcg, iter);
- break;
- }
- iter->oom_lock = false;
- }
- } else
- mutex_acquire(&memcg_oom_lock_dep_map, 0, 1, _RET_IP_);
- spin_unlock(&memcg_oom_lock);
- return !failed;
- }
- static void mem_cgroup_oom_unlock(struct mem_cgroup *memcg)
- {
- struct mem_cgroup *iter;
- spin_lock(&memcg_oom_lock);
- mutex_release(&memcg_oom_lock_dep_map, _RET_IP_);
- for_each_mem_cgroup_tree(iter, memcg)
- iter->oom_lock = false;
- spin_unlock(&memcg_oom_lock);
- }
- static void mem_cgroup_mark_under_oom(struct mem_cgroup *memcg)
- {
- struct mem_cgroup *iter;
- spin_lock(&memcg_oom_lock);
- for_each_mem_cgroup_tree(iter, memcg)
- iter->under_oom++;
- spin_unlock(&memcg_oom_lock);
- }
- static void mem_cgroup_unmark_under_oom(struct mem_cgroup *memcg)
- {
- struct mem_cgroup *iter;
- /*
- * Be careful about under_oom underflows because a child memcg
- * could have been added after mem_cgroup_mark_under_oom.
- */
- spin_lock(&memcg_oom_lock);
- for_each_mem_cgroup_tree(iter, memcg)
- if (iter->under_oom > 0)
- iter->under_oom--;
- spin_unlock(&memcg_oom_lock);
- }
- static DECLARE_WAIT_QUEUE_HEAD(memcg_oom_waitq);
- struct oom_wait_info {
- struct mem_cgroup *memcg;
- wait_queue_entry_t wait;
- };
- static int memcg_oom_wake_function(wait_queue_entry_t *wait,
- unsigned mode, int sync, void *arg)
- {
- struct mem_cgroup *wake_memcg = (struct mem_cgroup *)arg;
- struct mem_cgroup *oom_wait_memcg;
- struct oom_wait_info *oom_wait_info;
- oom_wait_info = container_of(wait, struct oom_wait_info, wait);
- oom_wait_memcg = oom_wait_info->memcg;
- if (!mem_cgroup_is_descendant(wake_memcg, oom_wait_memcg) &&
- !mem_cgroup_is_descendant(oom_wait_memcg, wake_memcg))
- return 0;
- return autoremove_wake_function(wait, mode, sync, arg);
- }
- static void memcg_oom_recover(struct mem_cgroup *memcg)
- {
- /*
- * For the following lockless ->under_oom test, the only required
- * guarantee is that it must see the state asserted by an OOM when
- * this function is called as a result of userland actions
- * triggered by the notification of the OOM. This is trivially
- * achieved by invoking mem_cgroup_mark_under_oom() before
- * triggering notification.
- */
- if (memcg && memcg->under_oom)
- __wake_up(&memcg_oom_waitq, TASK_NORMAL, 0, memcg);
- }
- /*
- * Returns true if successfully killed one or more processes. Though in some
- * corner cases it can return true even without killing any process.
- */
- static bool mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order)
- {
- bool locked, ret;
- if (order > PAGE_ALLOC_COSTLY_ORDER)
- return false;
- memcg_memory_event(memcg, MEMCG_OOM);
- /*
- * We are in the middle of the charge context here, so we
- * don't want to block when potentially sitting on a callstack
- * that holds all kinds of filesystem and mm locks.
- *
- * cgroup1 allows disabling the OOM killer and waiting for outside
- * handling until the charge can succeed; remember the context and put
- * the task to sleep at the end of the page fault when all locks are
- * released.
- *
- * On the other hand, in-kernel OOM killer allows for an async victim
- * memory reclaim (oom_reaper) and that means that we are not solely
- * relying on the oom victim to make a forward progress and we can
- * invoke the oom killer here.
- *
- * Please note that mem_cgroup_out_of_memory might fail to find a
- * victim and then we have to bail out from the charge path.
- */
- if (memcg->oom_kill_disable) {
- if (current->in_user_fault) {
- css_get(&memcg->css);
- current->memcg_in_oom = memcg;
- current->memcg_oom_gfp_mask = mask;
- current->memcg_oom_order = order;
- }
- return false;
- }
- mem_cgroup_mark_under_oom(memcg);
- locked = mem_cgroup_oom_trylock(memcg);
- if (locked)
- mem_cgroup_oom_notify(memcg);
- mem_cgroup_unmark_under_oom(memcg);
- ret = mem_cgroup_out_of_memory(memcg, mask, order);
- if (locked)
- mem_cgroup_oom_unlock(memcg);
- return ret;
- }
- /**
- * mem_cgroup_oom_synchronize - complete memcg OOM handling
- * @handle: actually kill/wait or just clean up the OOM state
- *
- * This has to be called at the end of a page fault if the memcg OOM
- * handler was enabled.
- *
- * Memcg supports userspace OOM handling where failed allocations must
- * sleep on a waitqueue until the userspace task resolves the
- * situation. Sleeping directly in the charge context with all kinds
- * of locks held is not a good idea, instead we remember an OOM state
- * in the task and mem_cgroup_oom_synchronize() has to be called at
- * the end of the page fault to complete the OOM handling.
- *
- * Returns %true if an ongoing memcg OOM situation was detected and
- * completed, %false otherwise.
- */
- bool mem_cgroup_oom_synchronize(bool handle)
- {
- struct mem_cgroup *memcg = current->memcg_in_oom;
- struct oom_wait_info owait;
- bool locked;
- /* OOM is global, do not handle */
- if (!memcg)
- return false;
- if (!handle)
- goto cleanup;
- owait.memcg = memcg;
- owait.wait.flags = 0;
- owait.wait.func = memcg_oom_wake_function;
- owait.wait.private = current;
- INIT_LIST_HEAD(&owait.wait.entry);
- prepare_to_wait(&memcg_oom_waitq, &owait.wait, TASK_KILLABLE);
- mem_cgroup_mark_under_oom(memcg);
- locked = mem_cgroup_oom_trylock(memcg);
- if (locked)
- mem_cgroup_oom_notify(memcg);
- if (locked && !memcg->oom_kill_disable) {
- mem_cgroup_unmark_under_oom(memcg);
- finish_wait(&memcg_oom_waitq, &owait.wait);
- mem_cgroup_out_of_memory(memcg, current->memcg_oom_gfp_mask,
- current->memcg_oom_order);
- } else {
- schedule();
- mem_cgroup_unmark_under_oom(memcg);
- finish_wait(&memcg_oom_waitq, &owait.wait);
- }
- if (locked) {
- mem_cgroup_oom_unlock(memcg);
- /*
- * There is no guarantee that an OOM-lock contender
- * sees the wakeups triggered by the OOM kill
- * uncharges. Wake any sleepers explicitly.
- */
- memcg_oom_recover(memcg);
- }
- cleanup:
- current->memcg_in_oom = NULL;
- css_put(&memcg->css);
- return true;
- }
- /**
- * mem_cgroup_get_oom_group - get a memory cgroup to clean up after OOM
- * @victim: task to be killed by the OOM killer
- * @oom_domain: memcg in case of memcg OOM, NULL in case of system-wide OOM
- *
- * Returns a pointer to a memory cgroup, which has to be cleaned up
- * by killing all belonging OOM-killable tasks.
- *
- * Caller has to call mem_cgroup_put() on the returned non-NULL memcg.
- */
- struct mem_cgroup *mem_cgroup_get_oom_group(struct task_struct *victim,
- struct mem_cgroup *oom_domain)
- {
- struct mem_cgroup *oom_group = NULL;
- struct mem_cgroup *memcg;
- if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
- return NULL;
- if (!oom_domain)
- oom_domain = root_mem_cgroup;
- rcu_read_lock();
- memcg = mem_cgroup_from_task(victim);
- if (memcg == root_mem_cgroup)
- goto out;
- /*
- * If the victim task has been asynchronously moved to a different
- * memory cgroup, we might end up killing tasks outside oom_domain.
- * In this case it's better to ignore memory.group.oom.
- */
- if (unlikely(!mem_cgroup_is_descendant(memcg, oom_domain)))
- goto out;
- /*
- * Traverse the memory cgroup hierarchy from the victim task's
- * cgroup up to the OOMing cgroup (or root) to find the
- * highest-level memory cgroup with oom.group set.
- */
- for (; memcg; memcg = parent_mem_cgroup(memcg)) {
- if (memcg->oom_group)
- oom_group = memcg;
- if (memcg == oom_domain)
- break;
- }
- if (oom_group)
- css_get(&oom_group->css);
- out:
- rcu_read_unlock();
- return oom_group;
- }
- void mem_cgroup_print_oom_group(struct mem_cgroup *memcg)
- {
- pr_info("Tasks in ");
- pr_cont_cgroup_path(memcg->css.cgroup);
- pr_cont(" are going to be killed due to memory.oom.group set\n");
- }
- /**
- * folio_memcg_lock - Bind a folio to its memcg.
- * @folio: The folio.
- *
- * This function prevents unlocked LRU folios from being moved to
- * another cgroup.
- *
- * It ensures lifetime of the bound memcg. The caller is responsible
- * for the lifetime of the folio.
- */
- void folio_memcg_lock(struct folio *folio)
- {
- struct mem_cgroup *memcg;
- unsigned long flags;
- /*
- * The RCU lock is held throughout the transaction. The fast
- * path can get away without acquiring the memcg->move_lock
- * because page moving starts with an RCU grace period.
- */
- rcu_read_lock();
- if (mem_cgroup_disabled())
- return;
- again:
- memcg = folio_memcg(folio);
- if (unlikely(!memcg))
- return;
- #ifdef CONFIG_PROVE_LOCKING
- local_irq_save(flags);
- might_lock(&memcg->move_lock);
- local_irq_restore(flags);
- #endif
- if (atomic_read(&memcg->moving_account) <= 0)
- return;
- spin_lock_irqsave(&memcg->move_lock, flags);
- if (memcg != folio_memcg(folio)) {
- spin_unlock_irqrestore(&memcg->move_lock, flags);
- goto again;
- }
- /*
- * When charge migration first begins, we can have multiple
- * critical sections holding the fast-path RCU lock and one
- * holding the slowpath move_lock. Track the task who has the
- * move_lock for unlock_page_memcg().
- */
- memcg->move_lock_task = current;
- memcg->move_lock_flags = flags;
- }
- void lock_page_memcg(struct page *page)
- {
- folio_memcg_lock(page_folio(page));
- }
- static void __folio_memcg_unlock(struct mem_cgroup *memcg)
- {
- if (memcg && memcg->move_lock_task == current) {
- unsigned long flags = memcg->move_lock_flags;
- memcg->move_lock_task = NULL;
- memcg->move_lock_flags = 0;
- spin_unlock_irqrestore(&memcg->move_lock, flags);
- }
- rcu_read_unlock();
- }
- /**
- * folio_memcg_unlock - Release the binding between a folio and its memcg.
- * @folio: The folio.
- *
- * This releases the binding created by folio_memcg_lock(). This does
- * not change the accounting of this folio to its memcg, but it does
- * permit others to change it.
- */
- void folio_memcg_unlock(struct folio *folio)
- {
- __folio_memcg_unlock(folio_memcg(folio));
- }
- void unlock_page_memcg(struct page *page)
- {
- folio_memcg_unlock(page_folio(page));
- }
- struct memcg_stock_pcp {
- local_lock_t stock_lock;
- struct mem_cgroup *cached; /* this never be root cgroup */
- unsigned int nr_pages;
- #ifdef CONFIG_MEMCG_KMEM
- struct obj_cgroup *cached_objcg;
- struct pglist_data *cached_pgdat;
- unsigned int nr_bytes;
- int nr_slab_reclaimable_b;
- int nr_slab_unreclaimable_b;
- #endif
- struct work_struct work;
- unsigned long flags;
- #define FLUSHING_CACHED_CHARGE 0
- };
- static DEFINE_PER_CPU(struct memcg_stock_pcp, memcg_stock) = {
- .stock_lock = INIT_LOCAL_LOCK(stock_lock),
- };
- static DEFINE_MUTEX(percpu_charge_mutex);
- #ifdef CONFIG_MEMCG_KMEM
- static struct obj_cgroup *drain_obj_stock(struct memcg_stock_pcp *stock);
- static bool obj_stock_flush_required(struct memcg_stock_pcp *stock,
- struct mem_cgroup *root_memcg);
- static void memcg_account_kmem(struct mem_cgroup *memcg, int nr_pages);
- #else
- static inline struct obj_cgroup *drain_obj_stock(struct memcg_stock_pcp *stock)
- {
- return NULL;
- }
- static bool obj_stock_flush_required(struct memcg_stock_pcp *stock,
- struct mem_cgroup *root_memcg)
- {
- return false;
- }
- static void memcg_account_kmem(struct mem_cgroup *memcg, int nr_pages)
- {
- }
- #endif
- /**
- * consume_stock: Try to consume stocked charge on this cpu.
- * @memcg: memcg to consume from.
- * @nr_pages: how many pages to charge.
- *
- * The charges will only happen if @memcg matches the current cpu's memcg
- * stock, and at least @nr_pages are available in that stock. Failure to
- * service an allocation will refill the stock.
- *
- * returns true if successful, false otherwise.
- */
- static bool consume_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
- {
- struct memcg_stock_pcp *stock;
- unsigned long flags;
- bool ret = false;
- if (nr_pages > MEMCG_CHARGE_BATCH)
- return ret;
- local_lock_irqsave(&memcg_stock.stock_lock, flags);
- stock = this_cpu_ptr(&memcg_stock);
- if (memcg == stock->cached && stock->nr_pages >= nr_pages) {
- stock->nr_pages -= nr_pages;
- ret = true;
- }
- local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
- return ret;
- }
- /*
- * Returns stocks cached in percpu and reset cached information.
- */
- static void drain_stock(struct memcg_stock_pcp *stock)
- {
- struct mem_cgroup *old = stock->cached;
- if (!old)
- return;
- if (stock->nr_pages) {
- page_counter_uncharge(&old->memory, stock->nr_pages);
- if (do_memsw_account())
- page_counter_uncharge(&old->memsw, stock->nr_pages);
- stock->nr_pages = 0;
- }
- css_put(&old->css);
- stock->cached = NULL;
- }
- static void drain_local_stock(struct work_struct *dummy)
- {
- struct memcg_stock_pcp *stock;
- struct obj_cgroup *old = NULL;
- unsigned long flags;
- /*
- * The only protection from cpu hotplug (memcg_hotplug_cpu_dead) vs.
- * drain_stock races is that we always operate on local CPU stock
- * here with IRQ disabled
- */
- local_lock_irqsave(&memcg_stock.stock_lock, flags);
- stock = this_cpu_ptr(&memcg_stock);
- old = drain_obj_stock(stock);
- drain_stock(stock);
- clear_bit(FLUSHING_CACHED_CHARGE, &stock->flags);
- local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
- if (old)
- obj_cgroup_put(old);
- }
- /*
- * Cache charges(val) to local per_cpu area.
- * This will be consumed by consume_stock() function, later.
- */
- static void __refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
- {
- struct memcg_stock_pcp *stock;
- stock = this_cpu_ptr(&memcg_stock);
- if (stock->cached != memcg) { /* reset if necessary */
- drain_stock(stock);
- css_get(&memcg->css);
- stock->cached = memcg;
- }
- stock->nr_pages += nr_pages;
- if (stock->nr_pages > MEMCG_CHARGE_BATCH)
- drain_stock(stock);
- }
- static void refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
- {
- unsigned long flags;
- local_lock_irqsave(&memcg_stock.stock_lock, flags);
- __refill_stock(memcg, nr_pages);
- local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
- }
- /*
- * Drains all per-CPU charge caches for given root_memcg resp. subtree
- * of the hierarchy under it.
- */
- static void drain_all_stock(struct mem_cgroup *root_memcg)
- {
- int cpu, curcpu;
- /* If someone's already draining, avoid adding running more workers. */
- if (!mutex_trylock(&percpu_charge_mutex))
- return;
- /*
- * Notify other cpus that system-wide "drain" is running
- * We do not care about races with the cpu hotplug because cpu down
- * as well as workers from this path always operate on the local
- * per-cpu data. CPU up doesn't touch memcg_stock at all.
- */
- migrate_disable();
- curcpu = smp_processor_id();
- for_each_online_cpu(cpu) {
- struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu);
- struct mem_cgroup *memcg;
- bool flush = false;
- rcu_read_lock();
- memcg = stock->cached;
- if (memcg && stock->nr_pages &&
- mem_cgroup_is_descendant(memcg, root_memcg))
- flush = true;
- else if (obj_stock_flush_required(stock, root_memcg))
- flush = true;
- rcu_read_unlock();
- if (flush &&
- !test_and_set_bit(FLUSHING_CACHED_CHARGE, &stock->flags)) {
- if (cpu == curcpu)
- drain_local_stock(&stock->work);
- else
- schedule_work_on(cpu, &stock->work);
- }
- }
- migrate_enable();
- mutex_unlock(&percpu_charge_mutex);
- }
- static int memcg_hotplug_cpu_dead(unsigned int cpu)
- {
- struct memcg_stock_pcp *stock;
- stock = &per_cpu(memcg_stock, cpu);
- drain_stock(stock);
- return 0;
- }
- static unsigned long reclaim_high(struct mem_cgroup *memcg,
- unsigned int nr_pages,
- gfp_t gfp_mask)
- {
- unsigned long nr_reclaimed = 0;
- do {
- unsigned long pflags;
- if (page_counter_read(&memcg->memory) <=
- READ_ONCE(memcg->memory.high))
- continue;
- memcg_memory_event(memcg, MEMCG_HIGH);
- psi_memstall_enter(&pflags);
- nr_reclaimed += try_to_free_mem_cgroup_pages(memcg, nr_pages,
- gfp_mask,
- MEMCG_RECLAIM_MAY_SWAP);
- psi_memstall_leave(&pflags);
- } while ((memcg = parent_mem_cgroup(memcg)) &&
- !mem_cgroup_is_root(memcg));
- return nr_reclaimed;
- }
- static void high_work_func(struct work_struct *work)
- {
- struct mem_cgroup *memcg;
- memcg = container_of(work, struct mem_cgroup, high_work);
- reclaim_high(memcg, MEMCG_CHARGE_BATCH, GFP_KERNEL);
- }
- /*
- * Clamp the maximum sleep time per allocation batch to 2 seconds. This is
- * enough to still cause a significant slowdown in most cases, while still
- * allowing diagnostics and tracing to proceed without becoming stuck.
- */
- #define MEMCG_MAX_HIGH_DELAY_JIFFIES (2UL*HZ)
- /*
- * When calculating the delay, we use these either side of the exponentiation to
- * maintain precision and scale to a reasonable number of jiffies (see the table
- * below.
- *
- * - MEMCG_DELAY_PRECISION_SHIFT: Extra precision bits while translating the
- * overage ratio to a delay.
- * - MEMCG_DELAY_SCALING_SHIFT: The number of bits to scale down the
- * proposed penalty in order to reduce to a reasonable number of jiffies, and
- * to produce a reasonable delay curve.
- *
- * MEMCG_DELAY_SCALING_SHIFT just happens to be a number that produces a
- * reasonable delay curve compared to precision-adjusted overage, not
- * penalising heavily at first, but still making sure that growth beyond the
- * limit penalises misbehaviour cgroups by slowing them down exponentially. For
- * example, with a high of 100 megabytes:
- *
- * +-------+------------------------+
- * | usage | time to allocate in ms |
- * +-------+------------------------+
- * | 100M | 0 |
- * | 101M | 6 |
- * | 102M | 25 |
- * | 103M | 57 |
- * | 104M | 102 |
- * | 105M | 159 |
- * | 106M | 230 |
- * | 107M | 313 |
- * | 108M | 409 |
- * | 109M | 518 |
- * | 110M | 639 |
- * | 111M | 774 |
- * | 112M | 921 |
- * | 113M | 1081 |
- * | 114M | 1254 |
- * | 115M | 1439 |
- * | 116M | 1638 |
- * | 117M | 1849 |
- * | 118M | 2000 |
- * | 119M | 2000 |
- * | 120M | 2000 |
- * +-------+------------------------+
- */
- #define MEMCG_DELAY_PRECISION_SHIFT 20
- #define MEMCG_DELAY_SCALING_SHIFT 14
- static u64 calculate_overage(unsigned long usage, unsigned long high)
- {
- u64 overage;
- if (usage <= high)
- return 0;
- /*
- * Prevent division by 0 in overage calculation by acting as if
- * it was a threshold of 1 page
- */
- high = max(high, 1UL);
- overage = usage - high;
- overage <<= MEMCG_DELAY_PRECISION_SHIFT;
- return div64_u64(overage, high);
- }
- static u64 mem_find_max_overage(struct mem_cgroup *memcg)
- {
- u64 overage, max_overage = 0;
- do {
- overage = calculate_overage(page_counter_read(&memcg->memory),
- READ_ONCE(memcg->memory.high));
- max_overage = max(overage, max_overage);
- } while ((memcg = parent_mem_cgroup(memcg)) &&
- !mem_cgroup_is_root(memcg));
- return max_overage;
- }
- static u64 swap_find_max_overage(struct mem_cgroup *memcg)
- {
- u64 overage, max_overage = 0;
- do {
- overage = calculate_overage(page_counter_read(&memcg->swap),
- READ_ONCE(memcg->swap.high));
- if (overage)
- memcg_memory_event(memcg, MEMCG_SWAP_HIGH);
- max_overage = max(overage, max_overage);
- } while ((memcg = parent_mem_cgroup(memcg)) &&
- !mem_cgroup_is_root(memcg));
- return max_overage;
- }
- /*
- * Get the number of jiffies that we should penalise a mischievous cgroup which
- * is exceeding its memory.high by checking both it and its ancestors.
- */
- static unsigned long calculate_high_delay(struct mem_cgroup *memcg,
- unsigned int nr_pages,
- u64 max_overage)
- {
- unsigned long penalty_jiffies;
- if (!max_overage)
- return 0;
- /*
- * We use overage compared to memory.high to calculate the number of
- * jiffies to sleep (penalty_jiffies). Ideally this value should be
- * fairly lenient on small overages, and increasingly harsh when the
- * memcg in question makes it clear that it has no intention of stopping
- * its crazy behaviour, so we exponentially increase the delay based on
- * overage amount.
- */
- penalty_jiffies = max_overage * max_overage * HZ;
- penalty_jiffies >>= MEMCG_DELAY_PRECISION_SHIFT;
- penalty_jiffies >>= MEMCG_DELAY_SCALING_SHIFT;
- /*
- * Factor in the task's own contribution to the overage, such that four
- * N-sized allocations are throttled approximately the same as one
- * 4N-sized allocation.
- *
- * MEMCG_CHARGE_BATCH pages is nominal, so work out how much smaller or
- * larger the current charge patch is than that.
- */
- return penalty_jiffies * nr_pages / MEMCG_CHARGE_BATCH;
- }
- /*
- * Scheduled by try_charge() to be executed from the userland return path
- * and reclaims memory over the high limit.
- */
- void mem_cgroup_handle_over_high(gfp_t gfp_mask)
- {
- unsigned long penalty_jiffies;
- unsigned long pflags;
- unsigned long nr_reclaimed;
- unsigned int nr_pages = current->memcg_nr_pages_over_high;
- int nr_retries = MAX_RECLAIM_RETRIES;
- struct mem_cgroup *memcg;
- bool in_retry = false;
- if (likely(!nr_pages))
- return;
- memcg = get_mem_cgroup_from_mm(current->mm);
- current->memcg_nr_pages_over_high = 0;
- retry_reclaim:
- /*
- * The allocating task should reclaim at least the batch size, but for
- * subsequent retries we only want to do what's necessary to prevent oom
- * or breaching resource isolation.
- *
- * This is distinct from memory.max or page allocator behaviour because
- * memory.high is currently batched, whereas memory.max and the page
- * allocator run every time an allocation is made.
- */
- nr_reclaimed = reclaim_high(memcg,
- in_retry ? SWAP_CLUSTER_MAX : nr_pages,
- gfp_mask);
- /*
- * memory.high is breached and reclaim is unable to keep up. Throttle
- * allocators proactively to slow down excessive growth.
- */
- penalty_jiffies = calculate_high_delay(memcg, nr_pages,
- mem_find_max_overage(memcg));
- penalty_jiffies += calculate_high_delay(memcg, nr_pages,
- swap_find_max_overage(memcg));
- /*
- * Clamp the max delay per usermode return so as to still keep the
- * application moving forwards and also permit diagnostics, albeit
- * extremely slowly.
- */
- penalty_jiffies = min(penalty_jiffies, MEMCG_MAX_HIGH_DELAY_JIFFIES);
- /*
- * Don't sleep if the amount of jiffies this memcg owes us is so low
- * that it's not even worth doing, in an attempt to be nice to those who
- * go only a small amount over their memory.high value and maybe haven't
- * been aggressively reclaimed enough yet.
- */
- if (penalty_jiffies <= HZ / 100)
- goto out;
- /*
- * If reclaim is making forward progress but we're still over
- * memory.high, we want to encourage that rather than doing allocator
- * throttling.
- */
- if (nr_reclaimed || nr_retries--) {
- in_retry = true;
- goto retry_reclaim;
- }
- /*
- * If we exit early, we're guaranteed to die (since
- * schedule_timeout_killable sets TASK_KILLABLE). This means we don't
- * need to account for any ill-begotten jiffies to pay them off later.
- */
- psi_memstall_enter(&pflags);
- schedule_timeout_killable(penalty_jiffies);
- psi_memstall_leave(&pflags);
- out:
- css_put(&memcg->css);
- }
- static int try_charge_memcg(struct mem_cgroup *memcg, gfp_t gfp_mask,
- unsigned int nr_pages)
- {
- unsigned int batch = max(MEMCG_CHARGE_BATCH, nr_pages);
- int nr_retries = MAX_RECLAIM_RETRIES;
- struct mem_cgroup *mem_over_limit;
- struct page_counter *counter;
- unsigned long nr_reclaimed;
- bool passed_oom = false;
- unsigned int reclaim_options = MEMCG_RECLAIM_MAY_SWAP;
- bool drained = false;
- bool raised_max_event = false;
- unsigned long pflags;
- retry:
- if (consume_stock(memcg, nr_pages))
- return 0;
- if (!do_memsw_account() ||
- page_counter_try_charge(&memcg->memsw, batch, &counter)) {
- if (page_counter_try_charge(&memcg->memory, batch, &counter))
- goto done_restock;
- if (do_memsw_account())
- page_counter_uncharge(&memcg->memsw, batch);
- mem_over_limit = mem_cgroup_from_counter(counter, memory);
- } else {
- mem_over_limit = mem_cgroup_from_counter(counter, memsw);
- reclaim_options &= ~MEMCG_RECLAIM_MAY_SWAP;
- }
- if (batch > nr_pages) {
- batch = nr_pages;
- goto retry;
- }
- /*
- * Prevent unbounded recursion when reclaim operations need to
- * allocate memory. This might exceed the limits temporarily,
- * but we prefer facilitating memory reclaim and getting back
- * under the limit over triggering OOM kills in these cases.
- */
- if (unlikely(current->flags & PF_MEMALLOC))
- goto force;
- if (unlikely(task_in_memcg_oom(current)))
- goto nomem;
- if (!gfpflags_allow_blocking(gfp_mask))
- goto nomem;
- memcg_memory_event(mem_over_limit, MEMCG_MAX);
- raised_max_event = true;
- psi_memstall_enter(&pflags);
- nr_reclaimed = try_to_free_mem_cgroup_pages(mem_over_limit, nr_pages,
- gfp_mask, reclaim_options);
- psi_memstall_leave(&pflags);
- if (mem_cgroup_margin(mem_over_limit) >= nr_pages)
- goto retry;
- if (!drained) {
- drain_all_stock(mem_over_limit);
- drained = true;
- goto retry;
- }
- if (gfp_mask & __GFP_NORETRY)
- goto nomem;
- /*
- * Even though the limit is exceeded at this point, reclaim
- * may have been able to free some pages. Retry the charge
- * before killing the task.
- *
- * Only for regular pages, though: huge pages are rather
- * unlikely to succeed so close to the limit, and we fall back
- * to regular pages anyway in case of failure.
- */
- if (nr_reclaimed && nr_pages <= (1 << PAGE_ALLOC_COSTLY_ORDER))
- goto retry;
- /*
- * At task move, charge accounts can be doubly counted. So, it's
- * better to wait until the end of task_move if something is going on.
- */
- if (mem_cgroup_wait_acct_move(mem_over_limit))
- goto retry;
- if (nr_retries--)
- goto retry;
- if (gfp_mask & __GFP_RETRY_MAYFAIL)
- goto nomem;
- /* Avoid endless loop for tasks bypassed by the oom killer */
- if (passed_oom && task_is_dying())
- goto nomem;
- /*
- * keep retrying as long as the memcg oom killer is able to make
- * a forward progress or bypass the charge if the oom killer
- * couldn't make any progress.
- */
- if (mem_cgroup_oom(mem_over_limit, gfp_mask,
- get_order(nr_pages * PAGE_SIZE))) {
- passed_oom = true;
- nr_retries = MAX_RECLAIM_RETRIES;
- goto retry;
- }
- nomem:
- /*
- * Memcg doesn't have a dedicated reserve for atomic
- * allocations. But like the global atomic pool, we need to
- * put the burden of reclaim on regular allocation requests
- * and let these go through as privileged allocations.
- */
- if (!(gfp_mask & (__GFP_NOFAIL | __GFP_HIGH)))
- return -ENOMEM;
- force:
- /*
- * If the allocation has to be enforced, don't forget to raise
- * a MEMCG_MAX event.
- */
- if (!raised_max_event)
- memcg_memory_event(mem_over_limit, MEMCG_MAX);
- /*
- * The allocation either can't fail or will lead to more memory
- * being freed very soon. Allow memory usage go over the limit
- * temporarily by force charging it.
- */
- page_counter_charge(&memcg->memory, nr_pages);
- if (do_memsw_account())
- page_counter_charge(&memcg->memsw, nr_pages);
- return 0;
- done_restock:
- if (batch > nr_pages)
- refill_stock(memcg, batch - nr_pages);
- /*
- * If the hierarchy is above the normal consumption range, schedule
- * reclaim on returning to userland. We can perform reclaim here
- * if __GFP_RECLAIM but let's always punt for simplicity and so that
- * GFP_KERNEL can consistently be used during reclaim. @memcg is
- * not recorded as it most likely matches current's and won't
- * change in the meantime. As high limit is checked again before
- * reclaim, the cost of mismatch is negligible.
- */
- do {
- bool mem_high, swap_high;
- mem_high = page_counter_read(&memcg->memory) >
- READ_ONCE(memcg->memory.high);
- swap_high = page_counter_read(&memcg->swap) >
- READ_ONCE(memcg->swap.high);
- /* Don't bother a random interrupted task */
- if (!in_task()) {
- if (mem_high) {
- schedule_work(&memcg->high_work);
- break;
- }
- continue;
- }
- if (mem_high || swap_high) {
- /*
- * The allocating tasks in this cgroup will need to do
- * reclaim or be throttled to prevent further growth
- * of the memory or swap footprints.
- *
- * Target some best-effort fairness between the tasks,
- * and distribute reclaim work and delay penalties
- * based on how much each task is actually allocating.
- */
- current->memcg_nr_pages_over_high += batch;
- set_notify_resume(current);
- break;
- }
- } while ((memcg = parent_mem_cgroup(memcg)));
- if (current->memcg_nr_pages_over_high > MEMCG_CHARGE_BATCH &&
- !(current->flags & PF_MEMALLOC) &&
- gfpflags_allow_blocking(gfp_mask)) {
- mem_cgroup_handle_over_high(gfp_mask);
- }
- return 0;
- }
- static inline int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
- unsigned int nr_pages)
- {
- if (mem_cgroup_is_root(memcg))
- return 0;
- return try_charge_memcg(memcg, gfp_mask, nr_pages);
- }
- static inline void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages)
- {
- if (mem_cgroup_is_root(memcg))
- return;
- page_counter_uncharge(&memcg->memory, nr_pages);
- if (do_memsw_account())
- page_counter_uncharge(&memcg->memsw, nr_pages);
- }
- static void commit_charge(struct folio *folio, struct mem_cgroup *memcg)
- {
- VM_BUG_ON_FOLIO(folio_memcg(folio), folio);
- /*
- * Any of the following ensures page's memcg stability:
- *
- * - the page lock
- * - LRU isolation
- * - lock_page_memcg()
- * - exclusive reference
- * - mem_cgroup_trylock_pages()
- */
- folio->memcg_data = (unsigned long)memcg;
- }
- #ifdef CONFIG_MEMCG_KMEM
- /*
- * The allocated objcg pointers array is not accounted directly.
- * Moreover, it should not come from DMA buffer and is not readily
- * reclaimable. So those GFP bits should be masked off.
- */
- #define OBJCGS_CLEAR_MASK (__GFP_DMA | __GFP_RECLAIMABLE | \
- __GFP_ACCOUNT | __GFP_NOFAIL)
- /*
- * mod_objcg_mlstate() may be called with irq enabled, so
- * mod_memcg_lruvec_state() should be used.
- */
- static inline void mod_objcg_mlstate(struct obj_cgroup *objcg,
- struct pglist_data *pgdat,
- enum node_stat_item idx, int nr)
- {
- struct mem_cgroup *memcg;
- struct lruvec *lruvec;
- rcu_read_lock();
- memcg = obj_cgroup_memcg(objcg);
- lruvec = mem_cgroup_lruvec(memcg, pgdat);
- mod_memcg_lruvec_state(lruvec, idx, nr);
- rcu_read_unlock();
- }
- int memcg_alloc_slab_cgroups(struct slab *slab, struct kmem_cache *s,
- gfp_t gfp, bool new_slab)
- {
- unsigned int objects = objs_per_slab(s, slab);
- unsigned long memcg_data;
- void *vec;
- gfp &= ~OBJCGS_CLEAR_MASK;
- vec = kcalloc_node(objects, sizeof(struct obj_cgroup *), gfp,
- slab_nid(slab));
- if (!vec)
- return -ENOMEM;
- memcg_data = (unsigned long) vec | MEMCG_DATA_OBJCGS;
- if (new_slab) {
- /*
- * If the slab is brand new and nobody can yet access its
- * memcg_data, no synchronization is required and memcg_data can
- * be simply assigned.
- */
- slab->memcg_data = memcg_data;
- } else if (cmpxchg(&slab->memcg_data, 0, memcg_data)) {
- /*
- * If the slab is already in use, somebody can allocate and
- * assign obj_cgroups in parallel. In this case the existing
- * objcg vector should be reused.
- */
- kfree(vec);
- return 0;
- }
- kmemleak_not_leak(vec);
- return 0;
- }
- static __always_inline
- struct mem_cgroup *mem_cgroup_from_obj_folio(struct folio *folio, void *p)
- {
- /*
- * Slab objects are accounted individually, not per-page.
- * Memcg membership data for each individual object is saved in
- * slab->memcg_data.
- */
- if (folio_test_slab(folio)) {
- struct obj_cgroup **objcgs;
- struct slab *slab;
- unsigned int off;
- slab = folio_slab(folio);
- objcgs = slab_objcgs(slab);
- if (!objcgs)
- return NULL;
- off = obj_to_index(slab->slab_cache, slab, p);
- if (objcgs[off])
- return obj_cgroup_memcg(objcgs[off]);
- return NULL;
- }
- /*
- * page_memcg_check() is used here, because in theory we can encounter
- * a folio where the slab flag has been cleared already, but
- * slab->memcg_data has not been freed yet
- * page_memcg_check(page) will guarantee that a proper memory
- * cgroup pointer or NULL will be returned.
- */
- return page_memcg_check(folio_page(folio, 0));
- }
- /*
- * Returns a pointer to the memory cgroup to which the kernel object is charged.
- *
- * A passed kernel object can be a slab object, vmalloc object or a generic
- * kernel page, so different mechanisms for getting the memory cgroup pointer
- * should be used.
- *
- * In certain cases (e.g. kernel stacks or large kmallocs with SLUB) the caller
- * can not know for sure how the kernel object is implemented.
- * mem_cgroup_from_obj() can be safely used in such cases.
- *
- * The caller must ensure the memcg lifetime, e.g. by taking rcu_read_lock(),
- * cgroup_mutex, etc.
- */
- struct mem_cgroup *mem_cgroup_from_obj(void *p)
- {
- struct folio *folio;
- if (mem_cgroup_disabled())
- return NULL;
- if (unlikely(is_vmalloc_addr(p)))
- folio = page_folio(vmalloc_to_page(p));
- else
- folio = virt_to_folio(p);
- return mem_cgroup_from_obj_folio(folio, p);
- }
- /*
- * Returns a pointer to the memory cgroup to which the kernel object is charged.
- * Similar to mem_cgroup_from_obj(), but faster and not suitable for objects,
- * allocated using vmalloc().
- *
- * A passed kernel object must be a slab object or a generic kernel page.
- *
- * The caller must ensure the memcg lifetime, e.g. by taking rcu_read_lock(),
- * cgroup_mutex, etc.
- */
- struct mem_cgroup *mem_cgroup_from_slab_obj(void *p)
- {
- if (mem_cgroup_disabled())
- return NULL;
- return mem_cgroup_from_obj_folio(virt_to_folio(p), p);
- }
- static struct obj_cgroup *__get_obj_cgroup_from_memcg(struct mem_cgroup *memcg)
- {
- struct obj_cgroup *objcg = NULL;
- for (; memcg != root_mem_cgroup; memcg = parent_mem_cgroup(memcg)) {
- objcg = rcu_dereference(memcg->objcg);
- if (objcg && obj_cgroup_tryget(objcg))
- break;
- objcg = NULL;
- }
- return objcg;
- }
- __always_inline struct obj_cgroup *get_obj_cgroup_from_current(void)
- {
- struct obj_cgroup *objcg = NULL;
- struct mem_cgroup *memcg;
- if (memcg_kmem_bypass())
- return NULL;
- rcu_read_lock();
- if (unlikely(active_memcg()))
- memcg = active_memcg();
- else
- memcg = mem_cgroup_from_task(current);
- objcg = __get_obj_cgroup_from_memcg(memcg);
- rcu_read_unlock();
- return objcg;
- }
- struct obj_cgroup *get_obj_cgroup_from_page(struct page *page)
- {
- struct obj_cgroup *objcg;
- if (!memcg_kmem_enabled())
- return NULL;
- if (PageMemcgKmem(page)) {
- objcg = __folio_objcg(page_folio(page));
- obj_cgroup_get(objcg);
- } else {
- struct mem_cgroup *memcg;
- rcu_read_lock();
- memcg = __folio_memcg(page_folio(page));
- if (memcg)
- objcg = __get_obj_cgroup_from_memcg(memcg);
- else
- objcg = NULL;
- rcu_read_unlock();
- }
- return objcg;
- }
- static void memcg_account_kmem(struct mem_cgroup *memcg, int nr_pages)
- {
- mod_memcg_state(memcg, MEMCG_KMEM, nr_pages);
- if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) {
- if (nr_pages > 0)
- page_counter_charge(&memcg->kmem, nr_pages);
- else
- page_counter_uncharge(&memcg->kmem, -nr_pages);
- }
- }
- /*
- * obj_cgroup_uncharge_pages: uncharge a number of kernel pages from a objcg
- * @objcg: object cgroup to uncharge
- * @nr_pages: number of pages to uncharge
- */
- static void obj_cgroup_uncharge_pages(struct obj_cgroup *objcg,
- unsigned int nr_pages)
- {
- struct mem_cgroup *memcg;
- memcg = get_mem_cgroup_from_objcg(objcg);
- memcg_account_kmem(memcg, -nr_pages);
- refill_stock(memcg, nr_pages);
- css_put(&memcg->css);
- }
- /*
- * obj_cgroup_charge_pages: charge a number of kernel pages to a objcg
- * @objcg: object cgroup to charge
- * @gfp: reclaim mode
- * @nr_pages: number of pages to charge
- *
- * Returns 0 on success, an error code on failure.
- */
- static int obj_cgroup_charge_pages(struct obj_cgroup *objcg, gfp_t gfp,
- unsigned int nr_pages)
- {
- struct mem_cgroup *memcg;
- int ret;
- memcg = get_mem_cgroup_from_objcg(objcg);
- ret = try_charge_memcg(memcg, gfp, nr_pages);
- if (ret)
- goto out;
- memcg_account_kmem(memcg, nr_pages);
- out:
- css_put(&memcg->css);
- return ret;
- }
- /**
- * __memcg_kmem_charge_page: charge a kmem page to the current memory cgroup
- * @page: page to charge
- * @gfp: reclaim mode
- * @order: allocation order
- *
- * Returns 0 on success, an error code on failure.
- */
- int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order)
- {
- struct obj_cgroup *objcg;
- int ret = 0;
- objcg = get_obj_cgroup_from_current();
- if (objcg) {
- ret = obj_cgroup_charge_pages(objcg, gfp, 1 << order);
- if (!ret) {
- page->memcg_data = (unsigned long)objcg |
- MEMCG_DATA_KMEM;
- return 0;
- }
- obj_cgroup_put(objcg);
- }
- return ret;
- }
- /**
- * __memcg_kmem_uncharge_page: uncharge a kmem page
- * @page: page to uncharge
- * @order: allocation order
- */
- void __memcg_kmem_uncharge_page(struct page *page, int order)
- {
- struct folio *folio = page_folio(page);
- struct obj_cgroup *objcg;
- unsigned int nr_pages = 1 << order;
- if (!folio_memcg_kmem(folio))
- return;
- objcg = __folio_objcg(folio);
- obj_cgroup_uncharge_pages(objcg, nr_pages);
- folio->memcg_data = 0;
- obj_cgroup_put(objcg);
- }
- void mod_objcg_state(struct obj_cgroup *objcg, struct pglist_data *pgdat,
- enum node_stat_item idx, int nr)
- {
- struct memcg_stock_pcp *stock;
- struct obj_cgroup *old = NULL;
- unsigned long flags;
- int *bytes;
- local_lock_irqsave(&memcg_stock.stock_lock, flags);
- stock = this_cpu_ptr(&memcg_stock);
- /*
- * Save vmstat data in stock and skip vmstat array update unless
- * accumulating over a page of vmstat data or when pgdat or idx
- * changes.
- */
- if (READ_ONCE(stock->cached_objcg) != objcg) {
- old = drain_obj_stock(stock);
- obj_cgroup_get(objcg);
- stock->nr_bytes = atomic_read(&objcg->nr_charged_bytes)
- ? atomic_xchg(&objcg->nr_charged_bytes, 0) : 0;
- WRITE_ONCE(stock->cached_objcg, objcg);
- stock->cached_pgdat = pgdat;
- } else if (stock->cached_pgdat != pgdat) {
- /* Flush the existing cached vmstat data */
- struct pglist_data *oldpg = stock->cached_pgdat;
- if (stock->nr_slab_reclaimable_b) {
- mod_objcg_mlstate(objcg, oldpg, NR_SLAB_RECLAIMABLE_B,
- stock->nr_slab_reclaimable_b);
- stock->nr_slab_reclaimable_b = 0;
- }
- if (stock->nr_slab_unreclaimable_b) {
- mod_objcg_mlstate(objcg, oldpg, NR_SLAB_UNRECLAIMABLE_B,
- stock->nr_slab_unreclaimable_b);
- stock->nr_slab_unreclaimable_b = 0;
- }
- stock->cached_pgdat = pgdat;
- }
- bytes = (idx == NR_SLAB_RECLAIMABLE_B) ? &stock->nr_slab_reclaimable_b
- : &stock->nr_slab_unreclaimable_b;
- /*
- * Even for large object >= PAGE_SIZE, the vmstat data will still be
- * cached locally at least once before pushing it out.
- */
- if (!*bytes) {
- *bytes = nr;
- nr = 0;
- } else {
- *bytes += nr;
- if (abs(*bytes) > PAGE_SIZE) {
- nr = *bytes;
- *bytes = 0;
- } else {
- nr = 0;
- }
- }
- if (nr)
- mod_objcg_mlstate(objcg, pgdat, idx, nr);
- local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
- if (old)
- obj_cgroup_put(old);
- }
- static bool consume_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes)
- {
- struct memcg_stock_pcp *stock;
- unsigned long flags;
- bool ret = false;
- local_lock_irqsave(&memcg_stock.stock_lock, flags);
- stock = this_cpu_ptr(&memcg_stock);
- if (objcg == READ_ONCE(stock->cached_objcg) && stock->nr_bytes >= nr_bytes) {
- stock->nr_bytes -= nr_bytes;
- ret = true;
- }
- local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
- return ret;
- }
- static struct obj_cgroup *drain_obj_stock(struct memcg_stock_pcp *stock)
- {
- struct obj_cgroup *old = READ_ONCE(stock->cached_objcg);
- if (!old)
- return NULL;
- if (stock->nr_bytes) {
- unsigned int nr_pages = stock->nr_bytes >> PAGE_SHIFT;
- unsigned int nr_bytes = stock->nr_bytes & (PAGE_SIZE - 1);
- if (nr_pages) {
- struct mem_cgroup *memcg;
- memcg = get_mem_cgroup_from_objcg(old);
- memcg_account_kmem(memcg, -nr_pages);
- __refill_stock(memcg, nr_pages);
- css_put(&memcg->css);
- }
- /*
- * The leftover is flushed to the centralized per-memcg value.
- * On the next attempt to refill obj stock it will be moved
- * to a per-cpu stock (probably, on an other CPU), see
- * refill_obj_stock().
- *
- * How often it's flushed is a trade-off between the memory
- * limit enforcement accuracy and potential CPU contention,
- * so it might be changed in the future.
- */
- atomic_add(nr_bytes, &old->nr_charged_bytes);
- stock->nr_bytes = 0;
- }
- /*
- * Flush the vmstat data in current stock
- */
- if (stock->nr_slab_reclaimable_b || stock->nr_slab_unreclaimable_b) {
- if (stock->nr_slab_reclaimable_b) {
- mod_objcg_mlstate(old, stock->cached_pgdat,
- NR_SLAB_RECLAIMABLE_B,
- stock->nr_slab_reclaimable_b);
- stock->nr_slab_reclaimable_b = 0;
- }
- if (stock->nr_slab_unreclaimable_b) {
- mod_objcg_mlstate(old, stock->cached_pgdat,
- NR_SLAB_UNRECLAIMABLE_B,
- stock->nr_slab_unreclaimable_b);
- stock->nr_slab_unreclaimable_b = 0;
- }
- stock->cached_pgdat = NULL;
- }
- WRITE_ONCE(stock->cached_objcg, NULL);
- /*
- * The `old' objects needs to be released by the caller via
- * obj_cgroup_put() outside of memcg_stock_pcp::stock_lock.
- */
- return old;
- }
- static bool obj_stock_flush_required(struct memcg_stock_pcp *stock,
- struct mem_cgroup *root_memcg)
- {
- struct obj_cgroup *objcg = READ_ONCE(stock->cached_objcg);
- struct mem_cgroup *memcg;
- if (objcg) {
- memcg = obj_cgroup_memcg(objcg);
- if (memcg && mem_cgroup_is_descendant(memcg, root_memcg))
- return true;
- }
- return false;
- }
- static void refill_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes,
- bool allow_uncharge)
- {
- struct memcg_stock_pcp *stock;
- struct obj_cgroup *old = NULL;
- unsigned long flags;
- unsigned int nr_pages = 0;
- local_lock_irqsave(&memcg_stock.stock_lock, flags);
- stock = this_cpu_ptr(&memcg_stock);
- if (READ_ONCE(stock->cached_objcg) != objcg) { /* reset if necessary */
- old = drain_obj_stock(stock);
- obj_cgroup_get(objcg);
- WRITE_ONCE(stock->cached_objcg, objcg);
- stock->nr_bytes = atomic_read(&objcg->nr_charged_bytes)
- ? atomic_xchg(&objcg->nr_charged_bytes, 0) : 0;
- allow_uncharge = true; /* Allow uncharge when objcg changes */
- }
- stock->nr_bytes += nr_bytes;
- if (allow_uncharge && (stock->nr_bytes > PAGE_SIZE)) {
- nr_pages = stock->nr_bytes >> PAGE_SHIFT;
- stock->nr_bytes &= (PAGE_SIZE - 1);
- }
- local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
- if (old)
- obj_cgroup_put(old);
- if (nr_pages)
- obj_cgroup_uncharge_pages(objcg, nr_pages);
- }
- int obj_cgroup_charge(struct obj_cgroup *objcg, gfp_t gfp, size_t size)
- {
- unsigned int nr_pages, nr_bytes;
- int ret;
- if (consume_obj_stock(objcg, size))
- return 0;
- /*
- * In theory, objcg->nr_charged_bytes can have enough
- * pre-charged bytes to satisfy the allocation. However,
- * flushing objcg->nr_charged_bytes requires two atomic
- * operations, and objcg->nr_charged_bytes can't be big.
- * The shared objcg->nr_charged_bytes can also become a
- * performance bottleneck if all tasks of the same memcg are
- * trying to update it. So it's better to ignore it and try
- * grab some new pages. The stock's nr_bytes will be flushed to
- * objcg->nr_charged_bytes later on when objcg changes.
- *
- * The stock's nr_bytes may contain enough pre-charged bytes
- * to allow one less page from being charged, but we can't rely
- * on the pre-charged bytes not being changed outside of
- * consume_obj_stock() or refill_obj_stock(). So ignore those
- * pre-charged bytes as well when charging pages. To avoid a
- * page uncharge right after a page charge, we set the
- * allow_uncharge flag to false when calling refill_obj_stock()
- * to temporarily allow the pre-charged bytes to exceed the page
- * size limit. The maximum reachable value of the pre-charged
- * bytes is (sizeof(object) + PAGE_SIZE - 2) if there is no data
- * race.
- */
- nr_pages = size >> PAGE_SHIFT;
- nr_bytes = size & (PAGE_SIZE - 1);
- if (nr_bytes)
- nr_pages += 1;
- ret = obj_cgroup_charge_pages(objcg, gfp, nr_pages);
- if (!ret && nr_bytes)
- refill_obj_stock(objcg, PAGE_SIZE - nr_bytes, false);
- return ret;
- }
- void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size)
- {
- refill_obj_stock(objcg, size, true);
- }
- #endif /* CONFIG_MEMCG_KMEM */
- /*
- * Because page_memcg(head) is not set on tails, set it now.
- */
- void split_page_memcg(struct page *head, unsigned int nr)
- {
- struct folio *folio = page_folio(head);
- struct mem_cgroup *memcg = folio_memcg(folio);
- int i;
- if (mem_cgroup_disabled() || !memcg)
- return;
- for (i = 1; i < nr; i++)
- folio_page(folio, i)->memcg_data = folio->memcg_data;
- if (folio_memcg_kmem(folio))
- obj_cgroup_get_many(__folio_objcg(folio), nr - 1);
- else
- css_get_many(&memcg->css, nr - 1);
- }
- #ifdef CONFIG_SWAP
- /**
- * mem_cgroup_move_swap_account - move swap charge and swap_cgroup's record.
- * @entry: swap entry to be moved
- * @from: mem_cgroup which the entry is moved from
- * @to: mem_cgroup which the entry is moved to
- *
- * It succeeds only when the swap_cgroup's record for this entry is the same
- * as the mem_cgroup's id of @from.
- *
- * Returns 0 on success, -EINVAL on failure.
- *
- * The caller must have charged to @to, IOW, called page_counter_charge() about
- * both res and memsw, and called css_get().
- */
- static int mem_cgroup_move_swap_account(swp_entry_t entry,
- struct mem_cgroup *from, struct mem_cgroup *to)
- {
- unsigned short old_id, new_id;
- old_id = mem_cgroup_id(from);
- new_id = mem_cgroup_id(to);
- if (swap_cgroup_cmpxchg(entry, old_id, new_id) == old_id) {
- mod_memcg_state(from, MEMCG_SWAP, -1);
- mod_memcg_state(to, MEMCG_SWAP, 1);
- return 0;
- }
- return -EINVAL;
- }
- #else
- static inline int mem_cgroup_move_swap_account(swp_entry_t entry,
- struct mem_cgroup *from, struct mem_cgroup *to)
- {
- return -EINVAL;
- }
- #endif
- static DEFINE_MUTEX(memcg_max_mutex);
- static int mem_cgroup_resize_max(struct mem_cgroup *memcg,
- unsigned long max, bool memsw)
- {
- bool enlarge = false;
- bool drained = false;
- int ret;
- bool limits_invariant;
- struct page_counter *counter = memsw ? &memcg->memsw : &memcg->memory;
- do {
- if (signal_pending(current)) {
- ret = -EINTR;
- break;
- }
- mutex_lock(&memcg_max_mutex);
- /*
- * Make sure that the new limit (memsw or memory limit) doesn't
- * break our basic invariant rule memory.max <= memsw.max.
- */
- limits_invariant = memsw ? max >= READ_ONCE(memcg->memory.max) :
- max <= memcg->memsw.max;
- if (!limits_invariant) {
- mutex_unlock(&memcg_max_mutex);
- ret = -EINVAL;
- break;
- }
- if (max > counter->max)
- enlarge = true;
- ret = page_counter_set_max(counter, max);
- mutex_unlock(&memcg_max_mutex);
- if (!ret)
- break;
- if (!drained) {
- drain_all_stock(memcg);
- drained = true;
- continue;
- }
- if (!try_to_free_mem_cgroup_pages(memcg, 1, GFP_KERNEL,
- memsw ? 0 : MEMCG_RECLAIM_MAY_SWAP)) {
- ret = -EBUSY;
- break;
- }
- } while (true);
- if (!ret && enlarge)
- memcg_oom_recover(memcg);
- return ret;
- }
- unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
- gfp_t gfp_mask,
- unsigned long *total_scanned)
- {
- unsigned long nr_reclaimed = 0;
- struct mem_cgroup_per_node *mz, *next_mz = NULL;
- unsigned long reclaimed;
- int loop = 0;
- struct mem_cgroup_tree_per_node *mctz;
- unsigned long excess;
- if (lru_gen_enabled())
- return 0;
- if (order > 0)
- return 0;
- mctz = soft_limit_tree.rb_tree_per_node[pgdat->node_id];
- /*
- * Do not even bother to check the largest node if the root
- * is empty. Do it lockless to prevent lock bouncing. Races
- * are acceptable as soft limit is best effort anyway.
- */
- if (!mctz || RB_EMPTY_ROOT(&mctz->rb_root))
- return 0;
- /*
- * This loop can run a while, specially if mem_cgroup's continuously
- * keep exceeding their soft limit and putting the system under
- * pressure
- */
- do {
- if (next_mz)
- mz = next_mz;
- else
- mz = mem_cgroup_largest_soft_limit_node(mctz);
- if (!mz)
- break;
- reclaimed = mem_cgroup_soft_reclaim(mz->memcg, pgdat,
- gfp_mask, total_scanned);
- nr_reclaimed += reclaimed;
- spin_lock_irq(&mctz->lock);
- /*
- * If we failed to reclaim anything from this memory cgroup
- * it is time to move on to the next cgroup
- */
- next_mz = NULL;
- if (!reclaimed)
- next_mz = __mem_cgroup_largest_soft_limit_node(mctz);
- excess = soft_limit_excess(mz->memcg);
- /*
- * One school of thought says that we should not add
- * back the node to the tree if reclaim returns 0.
- * But our reclaim could return 0, simply because due
- * to priority we are exposing a smaller subset of
- * memory to reclaim from. Consider this as a longer
- * term TODO.
- */
- /* If excess == 0, no tree ops */
- __mem_cgroup_insert_exceeded(mz, mctz, excess);
- spin_unlock_irq(&mctz->lock);
- css_put(&mz->memcg->css);
- loop++;
- /*
- * Could not reclaim anything and there are no more
- * mem cgroups to try or we seem to be looping without
- * reclaiming anything.
- */
- if (!nr_reclaimed &&
- (next_mz == NULL ||
- loop > MEM_CGROUP_MAX_SOFT_LIMIT_RECLAIM_LOOPS))
- break;
- } while (!nr_reclaimed);
- if (next_mz)
- css_put(&next_mz->memcg->css);
- return nr_reclaimed;
- }
- /*
- * Reclaims as many pages from the given memcg as possible.
- *
- * Caller is responsible for holding css reference for memcg.
- */
- static int mem_cgroup_force_empty(struct mem_cgroup *memcg)
- {
- int nr_retries = MAX_RECLAIM_RETRIES;
- /* we call try-to-free pages for make this cgroup empty */
- lru_add_drain_all();
- drain_all_stock(memcg);
- /* try to free all pages in this cgroup */
- while (nr_retries && page_counter_read(&memcg->memory)) {
- if (signal_pending(current))
- return -EINTR;
- if (!try_to_free_mem_cgroup_pages(memcg, 1, GFP_KERNEL,
- MEMCG_RECLAIM_MAY_SWAP))
- nr_retries--;
- }
- return 0;
- }
- static ssize_t mem_cgroup_force_empty_write(struct kernfs_open_file *of,
- char *buf, size_t nbytes,
- loff_t off)
- {
- struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
- if (mem_cgroup_is_root(memcg))
- return -EINVAL;
- return mem_cgroup_force_empty(memcg) ?: nbytes;
- }
- static u64 mem_cgroup_hierarchy_read(struct cgroup_subsys_state *css,
- struct cftype *cft)
- {
- return 1;
- }
- static int mem_cgroup_hierarchy_write(struct cgroup_subsys_state *css,
- struct cftype *cft, u64 val)
- {
- if (val == 1)
- return 0;
- pr_warn_once("Non-hierarchical mode is deprecated. "
- "Please report your usecase to [email protected] if you "
- "depend on this functionality.\n");
- return -EINVAL;
- }
- static unsigned long mem_cgroup_usage(struct mem_cgroup *memcg, bool swap)
- {
- unsigned long val;
- if (mem_cgroup_is_root(memcg)) {
- mem_cgroup_flush_stats();
- val = memcg_page_state(memcg, NR_FILE_PAGES) +
- memcg_page_state(memcg, NR_ANON_MAPPED);
- if (swap)
- val += memcg_page_state(memcg, MEMCG_SWAP);
- } else {
- if (!swap)
- val = page_counter_read(&memcg->memory);
- else
- val = page_counter_read(&memcg->memsw);
- }
- return val;
- }
- enum {
- RES_USAGE,
- RES_LIMIT,
- RES_MAX_USAGE,
- RES_FAILCNT,
- RES_SOFT_LIMIT,
- };
- static u64 mem_cgroup_read_u64(struct cgroup_subsys_state *css,
- struct cftype *cft)
- {
- struct mem_cgroup *memcg = mem_cgroup_from_css(css);
- struct page_counter *counter;
- switch (MEMFILE_TYPE(cft->private)) {
- case _MEM:
- counter = &memcg->memory;
- break;
- case _MEMSWAP:
- counter = &memcg->memsw;
- break;
- case _KMEM:
- counter = &memcg->kmem;
- break;
- case _TCP:
- counter = &memcg->tcpmem;
- break;
- default:
- BUG();
- }
- switch (MEMFILE_ATTR(cft->private)) {
- case RES_USAGE:
- if (counter == &memcg->memory)
- return (u64)mem_cgroup_usage(memcg, false) * PAGE_SIZE;
- if (counter == &memcg->memsw)
- return (u64)mem_cgroup_usage(memcg, true) * PAGE_SIZE;
- return (u64)page_counter_read(counter) * PAGE_SIZE;
- case RES_LIMIT:
- return (u64)counter->max * PAGE_SIZE;
- case RES_MAX_USAGE:
- return (u64)counter->watermark * PAGE_SIZE;
- case RES_FAILCNT:
- return counter->failcnt;
- case RES_SOFT_LIMIT:
- return (u64)memcg->soft_limit * PAGE_SIZE;
- default:
- BUG();
- }
- }
- #ifdef CONFIG_MEMCG_KMEM
- static int memcg_online_kmem(struct mem_cgroup *memcg)
- {
- struct obj_cgroup *objcg;
- if (mem_cgroup_kmem_disabled())
- return 0;
- if (unlikely(mem_cgroup_is_root(memcg)))
- return 0;
- objcg = obj_cgroup_alloc();
- if (!objcg)
- return -ENOMEM;
- objcg->memcg = memcg;
- rcu_assign_pointer(memcg->objcg, objcg);
- static_branch_enable(&memcg_kmem_enabled_key);
- memcg->kmemcg_id = memcg->id.id;
- return 0;
- }
- static void memcg_offline_kmem(struct mem_cgroup *memcg)
- {
- struct mem_cgroup *parent;
- if (mem_cgroup_kmem_disabled())
- return;
- if (unlikely(mem_cgroup_is_root(memcg)))
- return;
- parent = parent_mem_cgroup(memcg);
- if (!parent)
- parent = root_mem_cgroup;
- memcg_reparent_objcgs(memcg, parent);
- /*
- * After we have finished memcg_reparent_objcgs(), all list_lrus
- * corresponding to this cgroup are guaranteed to remain empty.
- * The ordering is imposed by list_lru_node->lock taken by
- * memcg_reparent_list_lrus().
- */
- memcg_reparent_list_lrus(memcg, parent);
- }
- #else
- static int memcg_online_kmem(struct mem_cgroup *memcg)
- {
- return 0;
- }
- static void memcg_offline_kmem(struct mem_cgroup *memcg)
- {
- }
- #endif /* CONFIG_MEMCG_KMEM */
- static int memcg_update_tcp_max(struct mem_cgroup *memcg, unsigned long max)
- {
- int ret;
- mutex_lock(&memcg_max_mutex);
- ret = page_counter_set_max(&memcg->tcpmem, max);
- if (ret)
- goto out;
- if (!memcg->tcpmem_active) {
- /*
- * The active flag needs to be written after the static_key
- * update. This is what guarantees that the socket activation
- * function is the last one to run. See mem_cgroup_sk_alloc()
- * for details, and note that we don't mark any socket as
- * belonging to this memcg until that flag is up.
- *
- * We need to do this, because static_keys will span multiple
- * sites, but we can't control their order. If we mark a socket
- * as accounted, but the accounting functions are not patched in
- * yet, we'll lose accounting.
- *
- * We never race with the readers in mem_cgroup_sk_alloc(),
- * because when this value change, the code to process it is not
- * patched in yet.
- */
- static_branch_inc(&memcg_sockets_enabled_key);
- memcg->tcpmem_active = true;
- }
- out:
- mutex_unlock(&memcg_max_mutex);
- return ret;
- }
- /*
- * The user of this function is...
- * RES_LIMIT.
- */
- static ssize_t mem_cgroup_write(struct kernfs_open_file *of,
- char *buf, size_t nbytes, loff_t off)
- {
- struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
- unsigned long nr_pages;
- int ret;
- buf = strstrip(buf);
- ret = page_counter_memparse(buf, "-1", &nr_pages);
- if (ret)
- return ret;
- switch (MEMFILE_ATTR(of_cft(of)->private)) {
- case RES_LIMIT:
- if (mem_cgroup_is_root(memcg)) { /* Can't set limit on root */
- ret = -EINVAL;
- break;
- }
- switch (MEMFILE_TYPE(of_cft(of)->private)) {
- case _MEM:
- ret = mem_cgroup_resize_max(memcg, nr_pages, false);
- break;
- case _MEMSWAP:
- ret = mem_cgroup_resize_max(memcg, nr_pages, true);
- break;
- case _KMEM:
- pr_warn_once("kmem.limit_in_bytes is deprecated and will be removed. "
- "Writing any value to this file has no effect. "
- "Please report your usecase to [email protected] if you "
- "depend on this functionality.\n");
- ret = 0;
- break;
- case _TCP:
- ret = memcg_update_tcp_max(memcg, nr_pages);
- break;
- }
- break;
- case RES_SOFT_LIMIT:
- if (IS_ENABLED(CONFIG_PREEMPT_RT)) {
- ret = -EOPNOTSUPP;
- } else {
- memcg->soft_limit = nr_pages;
- ret = 0;
- }
- break;
- }
- return ret ?: nbytes;
- }
- static ssize_t mem_cgroup_reset(struct kernfs_open_file *of, char *buf,
- size_t nbytes, loff_t off)
- {
- struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
- struct page_counter *counter;
- switch (MEMFILE_TYPE(of_cft(of)->private)) {
- case _MEM:
- counter = &memcg->memory;
- break;
- case _MEMSWAP:
- counter = &memcg->memsw;
- break;
- case _KMEM:
- counter = &memcg->kmem;
- break;
- case _TCP:
- counter = &memcg->tcpmem;
- break;
- default:
- BUG();
- }
- switch (MEMFILE_ATTR(of_cft(of)->private)) {
- case RES_MAX_USAGE:
- page_counter_reset_watermark(counter);
- break;
- case RES_FAILCNT:
- counter->failcnt = 0;
- break;
- default:
- BUG();
- }
- return nbytes;
- }
- static u64 mem_cgroup_move_charge_read(struct cgroup_subsys_state *css,
- struct cftype *cft)
- {
- return mem_cgroup_from_css(css)->move_charge_at_immigrate;
- }
- #ifdef CONFIG_MMU
- static int mem_cgroup_move_charge_write(struct cgroup_subsys_state *css,
- struct cftype *cft, u64 val)
- {
- struct mem_cgroup *memcg = mem_cgroup_from_css(css);
- pr_warn_once("Cgroup memory moving (move_charge_at_immigrate) is deprecated. "
- "Please report your usecase to [email protected] if you "
- "depend on this functionality.\n");
- if (val & ~MOVE_MASK)
- return -EINVAL;
- /*
- * No kind of locking is needed in here, because ->can_attach() will
- * check this value once in the beginning of the process, and then carry
- * on with stale data. This means that changes to this value will only
- * affect task migrations starting after the change.
- */
- memcg->move_charge_at_immigrate = val;
- return 0;
- }
- #else
- static int mem_cgroup_move_charge_write(struct cgroup_subsys_state *css,
- struct cftype *cft, u64 val)
- {
- return -ENOSYS;
- }
- #endif
- #ifdef CONFIG_NUMA
- #define LRU_ALL_FILE (BIT(LRU_INACTIVE_FILE) | BIT(LRU_ACTIVE_FILE))
- #define LRU_ALL_ANON (BIT(LRU_INACTIVE_ANON) | BIT(LRU_ACTIVE_ANON))
- #define LRU_ALL ((1 << NR_LRU_LISTS) - 1)
- static unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg,
- int nid, unsigned int lru_mask, bool tree)
- {
- struct lruvec *lruvec = mem_cgroup_lruvec(memcg, NODE_DATA(nid));
- unsigned long nr = 0;
- enum lru_list lru;
- VM_BUG_ON((unsigned)nid >= nr_node_ids);
- for_each_lru(lru) {
- if (!(BIT(lru) & lru_mask))
- continue;
- if (tree)
- nr += lruvec_page_state(lruvec, NR_LRU_BASE + lru);
- else
- nr += lruvec_page_state_local(lruvec, NR_LRU_BASE + lru);
- }
- return nr;
- }
- static unsigned long mem_cgroup_nr_lru_pages(struct mem_cgroup *memcg,
- unsigned int lru_mask,
- bool tree)
- {
- unsigned long nr = 0;
- enum lru_list lru;
- for_each_lru(lru) {
- if (!(BIT(lru) & lru_mask))
- continue;
- if (tree)
- nr += memcg_page_state(memcg, NR_LRU_BASE + lru);
- else
- nr += memcg_page_state_local(memcg, NR_LRU_BASE + lru);
- }
- return nr;
- }
- static int memcg_numa_stat_show(struct seq_file *m, void *v)
- {
- struct numa_stat {
- const char *name;
- unsigned int lru_mask;
- };
- static const struct numa_stat stats[] = {
- { "total", LRU_ALL },
- { "file", LRU_ALL_FILE },
- { "anon", LRU_ALL_ANON },
- { "unevictable", BIT(LRU_UNEVICTABLE) },
- };
- const struct numa_stat *stat;
- int nid;
- struct mem_cgroup *memcg = mem_cgroup_from_seq(m);
- mem_cgroup_flush_stats();
- for (stat = stats; stat < stats + ARRAY_SIZE(stats); stat++) {
- seq_printf(m, "%s=%lu", stat->name,
- mem_cgroup_nr_lru_pages(memcg, stat->lru_mask,
- false));
- for_each_node_state(nid, N_MEMORY)
- seq_printf(m, " N%d=%lu", nid,
- mem_cgroup_node_nr_lru_pages(memcg, nid,
- stat->lru_mask, false));
- seq_putc(m, '\n');
- }
- for (stat = stats; stat < stats + ARRAY_SIZE(stats); stat++) {
- seq_printf(m, "hierarchical_%s=%lu", stat->name,
- mem_cgroup_nr_lru_pages(memcg, stat->lru_mask,
- true));
- for_each_node_state(nid, N_MEMORY)
- seq_printf(m, " N%d=%lu", nid,
- mem_cgroup_node_nr_lru_pages(memcg, nid,
- stat->lru_mask, true));
- seq_putc(m, '\n');
- }
- return 0;
- }
- #endif /* CONFIG_NUMA */
- static const unsigned int memcg1_stats[] = {
- NR_FILE_PAGES,
- NR_ANON_MAPPED,
- #ifdef CONFIG_TRANSPARENT_HUGEPAGE
- NR_ANON_THPS,
- #endif
- NR_SHMEM,
- NR_FILE_MAPPED,
- NR_FILE_DIRTY,
- NR_WRITEBACK,
- WORKINGSET_REFAULT_ANON,
- WORKINGSET_REFAULT_FILE,
- MEMCG_SWAP,
- };
- static const char *const memcg1_stat_names[] = {
- "cache",
- "rss",
- #ifdef CONFIG_TRANSPARENT_HUGEPAGE
- "rss_huge",
- #endif
- "shmem",
- "mapped_file",
- "dirty",
- "writeback",
- "workingset_refault_anon",
- "workingset_refault_file",
- "swap",
- };
- /* Universal VM events cgroup1 shows, original sort order */
- static const unsigned int memcg1_events[] = {
- PGPGIN,
- PGPGOUT,
- PGFAULT,
- PGMAJFAULT,
- };
- static int memcg_stat_show(struct seq_file *m, void *v)
- {
- struct mem_cgroup *memcg = mem_cgroup_from_seq(m);
- unsigned long memory, memsw;
- struct mem_cgroup *mi;
- unsigned int i;
- BUILD_BUG_ON(ARRAY_SIZE(memcg1_stat_names) != ARRAY_SIZE(memcg1_stats));
- mem_cgroup_flush_stats();
- for (i = 0; i < ARRAY_SIZE(memcg1_stats); i++) {
- unsigned long nr;
- if (memcg1_stats[i] == MEMCG_SWAP && !do_memsw_account())
- continue;
- nr = memcg_page_state_local(memcg, memcg1_stats[i]);
- seq_printf(m, "%s %lu\n", memcg1_stat_names[i],
- nr * memcg_page_state_unit(memcg1_stats[i]));
- }
- for (i = 0; i < ARRAY_SIZE(memcg1_events); i++)
- seq_printf(m, "%s %lu\n", vm_event_name(memcg1_events[i]),
- memcg_events_local(memcg, memcg1_events[i]));
- for (i = 0; i < NR_LRU_LISTS; i++)
- seq_printf(m, "%s %lu\n", lru_list_name(i),
- memcg_page_state_local(memcg, NR_LRU_BASE + i) *
- PAGE_SIZE);
- /* Hierarchical information */
- memory = memsw = PAGE_COUNTER_MAX;
- for (mi = memcg; mi; mi = parent_mem_cgroup(mi)) {
- memory = min(memory, READ_ONCE(mi->memory.max));
- memsw = min(memsw, READ_ONCE(mi->memsw.max));
- }
- seq_printf(m, "hierarchical_memory_limit %llu\n",
- (u64)memory * PAGE_SIZE);
- if (do_memsw_account())
- seq_printf(m, "hierarchical_memsw_limit %llu\n",
- (u64)memsw * PAGE_SIZE);
- for (i = 0; i < ARRAY_SIZE(memcg1_stats); i++) {
- unsigned long nr;
- if (memcg1_stats[i] == MEMCG_SWAP && !do_memsw_account())
- continue;
- nr = memcg_page_state(memcg, memcg1_stats[i]);
- seq_printf(m, "total_%s %llu\n", memcg1_stat_names[i],
- (u64)nr * memcg_page_state_unit(memcg1_stats[i]));
- }
- for (i = 0; i < ARRAY_SIZE(memcg1_events); i++)
- seq_printf(m, "total_%s %llu\n",
- vm_event_name(memcg1_events[i]),
- (u64)memcg_events(memcg, memcg1_events[i]));
- for (i = 0; i < NR_LRU_LISTS; i++)
- seq_printf(m, "total_%s %llu\n", lru_list_name(i),
- (u64)memcg_page_state(memcg, NR_LRU_BASE + i) *
- PAGE_SIZE);
- #ifdef CONFIG_DEBUG_VM
- {
- pg_data_t *pgdat;
- struct mem_cgroup_per_node *mz;
- unsigned long anon_cost = 0;
- unsigned long file_cost = 0;
- for_each_online_pgdat(pgdat) {
- mz = memcg->nodeinfo[pgdat->node_id];
- anon_cost += mz->lruvec.anon_cost;
- file_cost += mz->lruvec.file_cost;
- }
- seq_printf(m, "anon_cost %lu\n", anon_cost);
- seq_printf(m, "file_cost %lu\n", file_cost);
- }
- #endif
- return 0;
- }
- static u64 mem_cgroup_swappiness_read(struct cgroup_subsys_state *css,
- struct cftype *cft)
- {
- struct mem_cgroup *memcg = mem_cgroup_from_css(css);
- return mem_cgroup_swappiness(memcg);
- }
- static int mem_cgroup_swappiness_write(struct cgroup_subsys_state *css,
- struct cftype *cft, u64 val)
- {
- struct mem_cgroup *memcg = mem_cgroup_from_css(css);
- if (val > 200)
- return -EINVAL;
- if (!mem_cgroup_is_root(memcg))
- memcg->swappiness = val;
- else
- vm_swappiness = val;
- return 0;
- }
- static void __mem_cgroup_threshold(struct mem_cgroup *memcg, bool swap)
- {
- struct mem_cgroup_threshold_ary *t;
- unsigned long usage;
- int i;
- rcu_read_lock();
- if (!swap)
- t = rcu_dereference(memcg->thresholds.primary);
- else
- t = rcu_dereference(memcg->memsw_thresholds.primary);
- if (!t)
- goto unlock;
- usage = mem_cgroup_usage(memcg, swap);
- /*
- * current_threshold points to threshold just below or equal to usage.
- * If it's not true, a threshold was crossed after last
- * call of __mem_cgroup_threshold().
- */
- i = t->current_threshold;
- /*
- * Iterate backward over array of thresholds starting from
- * current_threshold and check if a threshold is crossed.
- * If none of thresholds below usage is crossed, we read
- * only one element of the array here.
- */
- for (; i >= 0 && unlikely(t->entries[i].threshold > usage); i--)
- eventfd_signal(t->entries[i].eventfd, 1);
- /* i = current_threshold + 1 */
- i++;
- /*
- * Iterate forward over array of thresholds starting from
- * current_threshold+1 and check if a threshold is crossed.
- * If none of thresholds above usage is crossed, we read
- * only one element of the array here.
- */
- for (; i < t->size && unlikely(t->entries[i].threshold <= usage); i++)
- eventfd_signal(t->entries[i].eventfd, 1);
- /* Update current_threshold */
- t->current_threshold = i - 1;
- unlock:
- rcu_read_unlock();
- }
- static void mem_cgroup_threshold(struct mem_cgroup *memcg)
- {
- while (memcg) {
- __mem_cgroup_threshold(memcg, false);
- if (do_memsw_account())
- __mem_cgroup_threshold(memcg, true);
- memcg = parent_mem_cgroup(memcg);
- }
- }
- static int compare_thresholds(const void *a, const void *b)
- {
- const struct mem_cgroup_threshold *_a = a;
- const struct mem_cgroup_threshold *_b = b;
- if (_a->threshold > _b->threshold)
- return 1;
- if (_a->threshold < _b->threshold)
- return -1;
- return 0;
- }
- static int mem_cgroup_oom_notify_cb(struct mem_cgroup *memcg)
- {
- struct mem_cgroup_eventfd_list *ev;
- spin_lock(&memcg_oom_lock);
- list_for_each_entry(ev, &memcg->oom_notify, list)
- eventfd_signal(ev->eventfd, 1);
- spin_unlock(&memcg_oom_lock);
- return 0;
- }
- static void mem_cgroup_oom_notify(struct mem_cgroup *memcg)
- {
- struct mem_cgroup *iter;
- for_each_mem_cgroup_tree(iter, memcg)
- mem_cgroup_oom_notify_cb(iter);
- }
- static int __mem_cgroup_usage_register_event(struct mem_cgroup *memcg,
- struct eventfd_ctx *eventfd, const char *args, enum res_type type)
- {
- struct mem_cgroup_thresholds *thresholds;
- struct mem_cgroup_threshold_ary *new;
- unsigned long threshold;
- unsigned long usage;
- int i, size, ret;
- ret = page_counter_memparse(args, "-1", &threshold);
- if (ret)
- return ret;
- mutex_lock(&memcg->thresholds_lock);
- if (type == _MEM) {
- thresholds = &memcg->thresholds;
- usage = mem_cgroup_usage(memcg, false);
- } else if (type == _MEMSWAP) {
- thresholds = &memcg->memsw_thresholds;
- usage = mem_cgroup_usage(memcg, true);
- } else
- BUG();
- /* Check if a threshold crossed before adding a new one */
- if (thresholds->primary)
- __mem_cgroup_threshold(memcg, type == _MEMSWAP);
- size = thresholds->primary ? thresholds->primary->size + 1 : 1;
- /* Allocate memory for new array of thresholds */
- new = kmalloc(struct_size(new, entries, size), GFP_KERNEL);
- if (!new) {
- ret = -ENOMEM;
- goto unlock;
- }
- new->size = size;
- /* Copy thresholds (if any) to new array */
- if (thresholds->primary)
- memcpy(new->entries, thresholds->primary->entries,
- flex_array_size(new, entries, size - 1));
- /* Add new threshold */
- new->entries[size - 1].eventfd = eventfd;
- new->entries[size - 1].threshold = threshold;
- /* Sort thresholds. Registering of new threshold isn't time-critical */
- sort(new->entries, size, sizeof(*new->entries),
- compare_thresholds, NULL);
- /* Find current threshold */
- new->current_threshold = -1;
- for (i = 0; i < size; i++) {
- if (new->entries[i].threshold <= usage) {
- /*
- * new->current_threshold will not be used until
- * rcu_assign_pointer(), so it's safe to increment
- * it here.
- */
- ++new->current_threshold;
- } else
- break;
- }
- /* Free old spare buffer and save old primary buffer as spare */
- kfree(thresholds->spare);
- thresholds->spare = thresholds->primary;
- rcu_assign_pointer(thresholds->primary, new);
- /* To be sure that nobody uses thresholds */
- synchronize_rcu();
- unlock:
- mutex_unlock(&memcg->thresholds_lock);
- return ret;
- }
- static int mem_cgroup_usage_register_event(struct mem_cgroup *memcg,
- struct eventfd_ctx *eventfd, const char *args)
- {
- return __mem_cgroup_usage_register_event(memcg, eventfd, args, _MEM);
- }
- static int memsw_cgroup_usage_register_event(struct mem_cgroup *memcg,
- struct eventfd_ctx *eventfd, const char *args)
- {
- return __mem_cgroup_usage_register_event(memcg, eventfd, args, _MEMSWAP);
- }
- static void __mem_cgroup_usage_unregister_event(struct mem_cgroup *memcg,
- struct eventfd_ctx *eventfd, enum res_type type)
- {
- struct mem_cgroup_thresholds *thresholds;
- struct mem_cgroup_threshold_ary *new;
- unsigned long usage;
- int i, j, size, entries;
- mutex_lock(&memcg->thresholds_lock);
- if (type == _MEM) {
- thresholds = &memcg->thresholds;
- usage = mem_cgroup_usage(memcg, false);
- } else if (type == _MEMSWAP) {
- thresholds = &memcg->memsw_thresholds;
- usage = mem_cgroup_usage(memcg, true);
- } else
- BUG();
- if (!thresholds->primary)
- goto unlock;
- /* Check if a threshold crossed before removing */
- __mem_cgroup_threshold(memcg, type == _MEMSWAP);
- /* Calculate new number of threshold */
- size = entries = 0;
- for (i = 0; i < thresholds->primary->size; i++) {
- if (thresholds->primary->entries[i].eventfd != eventfd)
- size++;
- else
- entries++;
- }
- new = thresholds->spare;
- /* If no items related to eventfd have been cleared, nothing to do */
- if (!entries)
- goto unlock;
- /* Set thresholds array to NULL if we don't have thresholds */
- if (!size) {
- kfree(new);
- new = NULL;
- goto swap_buffers;
- }
- new->size = size;
- /* Copy thresholds and find current threshold */
- new->current_threshold = -1;
- for (i = 0, j = 0; i < thresholds->primary->size; i++) {
- if (thresholds->primary->entries[i].eventfd == eventfd)
- continue;
- new->entries[j] = thresholds->primary->entries[i];
- if (new->entries[j].threshold <= usage) {
- /*
- * new->current_threshold will not be used
- * until rcu_assign_pointer(), so it's safe to increment
- * it here.
- */
- ++new->current_threshold;
- }
- j++;
- }
- swap_buffers:
- /* Swap primary and spare array */
- thresholds->spare = thresholds->primary;
- rcu_assign_pointer(thresholds->primary, new);
- /* To be sure that nobody uses thresholds */
- synchronize_rcu();
- /* If all events are unregistered, free the spare array */
- if (!new) {
- kfree(thresholds->spare);
- thresholds->spare = NULL;
- }
- unlock:
- mutex_unlock(&memcg->thresholds_lock);
- }
- static void mem_cgroup_usage_unregister_event(struct mem_cgroup *memcg,
- struct eventfd_ctx *eventfd)
- {
- return __mem_cgroup_usage_unregister_event(memcg, eventfd, _MEM);
- }
- static void memsw_cgroup_usage_unregister_event(struct mem_cgroup *memcg,
- struct eventfd_ctx *eventfd)
- {
- return __mem_cgroup_usage_unregister_event(memcg, eventfd, _MEMSWAP);
- }
- static int mem_cgroup_oom_register_event(struct mem_cgroup *memcg,
- struct eventfd_ctx *eventfd, const char *args)
- {
- struct mem_cgroup_eventfd_list *event;
- event = kmalloc(sizeof(*event), GFP_KERNEL);
- if (!event)
- return -ENOMEM;
- spin_lock(&memcg_oom_lock);
- event->eventfd = eventfd;
- list_add(&event->list, &memcg->oom_notify);
- /* already in OOM ? */
- if (memcg->under_oom)
- eventfd_signal(eventfd, 1);
- spin_unlock(&memcg_oom_lock);
- return 0;
- }
- static void mem_cgroup_oom_unregister_event(struct mem_cgroup *memcg,
- struct eventfd_ctx *eventfd)
- {
- struct mem_cgroup_eventfd_list *ev, *tmp;
- spin_lock(&memcg_oom_lock);
- list_for_each_entry_safe(ev, tmp, &memcg->oom_notify, list) {
- if (ev->eventfd == eventfd) {
- list_del(&ev->list);
- kfree(ev);
- }
- }
- spin_unlock(&memcg_oom_lock);
- }
- static int mem_cgroup_oom_control_read(struct seq_file *sf, void *v)
- {
- struct mem_cgroup *memcg = mem_cgroup_from_seq(sf);
- seq_printf(sf, "oom_kill_disable %d\n", memcg->oom_kill_disable);
- seq_printf(sf, "under_oom %d\n", (bool)memcg->under_oom);
- seq_printf(sf, "oom_kill %lu\n",
- atomic_long_read(&memcg->memory_events[MEMCG_OOM_KILL]));
- return 0;
- }
- static int mem_cgroup_oom_control_write(struct cgroup_subsys_state *css,
- struct cftype *cft, u64 val)
- {
- struct mem_cgroup *memcg = mem_cgroup_from_css(css);
- /* cannot set to root cgroup and only 0 and 1 are allowed */
- if (mem_cgroup_is_root(memcg) || !((val == 0) || (val == 1)))
- return -EINVAL;
- memcg->oom_kill_disable = val;
- if (!val)
- memcg_oom_recover(memcg);
- return 0;
- }
- #ifdef CONFIG_CGROUP_WRITEBACK
- #include <trace/events/writeback.h>
- static int memcg_wb_domain_init(struct mem_cgroup *memcg, gfp_t gfp)
- {
- return wb_domain_init(&memcg->cgwb_domain, gfp);
- }
- static void memcg_wb_domain_exit(struct mem_cgroup *memcg)
- {
- wb_domain_exit(&memcg->cgwb_domain);
- }
- static void memcg_wb_domain_size_changed(struct mem_cgroup *memcg)
- {
- wb_domain_size_changed(&memcg->cgwb_domain);
- }
- struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb)
- {
- struct mem_cgroup *memcg = mem_cgroup_from_css(wb->memcg_css);
- if (!memcg->css.parent)
- return NULL;
- return &memcg->cgwb_domain;
- }
- /**
- * mem_cgroup_wb_stats - retrieve writeback related stats from its memcg
- * @wb: bdi_writeback in question
- * @pfilepages: out parameter for number of file pages
- * @pheadroom: out parameter for number of allocatable pages according to memcg
- * @pdirty: out parameter for number of dirty pages
- * @pwriteback: out parameter for number of pages under writeback
- *
- * Determine the numbers of file, headroom, dirty, and writeback pages in
- * @wb's memcg. File, dirty and writeback are self-explanatory. Headroom
- * is a bit more involved.
- *
- * A memcg's headroom is "min(max, high) - used". In the hierarchy, the
- * headroom is calculated as the lowest headroom of itself and the
- * ancestors. Note that this doesn't consider the actual amount of
- * available memory in the system. The caller should further cap
- * *@pheadroom accordingly.
- */
- void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages,
- unsigned long *pheadroom, unsigned long *pdirty,
- unsigned long *pwriteback)
- {
- struct mem_cgroup *memcg = mem_cgroup_from_css(wb->memcg_css);
- struct mem_cgroup *parent;
- mem_cgroup_flush_stats();
- *pdirty = memcg_page_state(memcg, NR_FILE_DIRTY);
- *pwriteback = memcg_page_state(memcg, NR_WRITEBACK);
- *pfilepages = memcg_page_state(memcg, NR_INACTIVE_FILE) +
- memcg_page_state(memcg, NR_ACTIVE_FILE);
- *pheadroom = PAGE_COUNTER_MAX;
- while ((parent = parent_mem_cgroup(memcg))) {
- unsigned long ceiling = min(READ_ONCE(memcg->memory.max),
- READ_ONCE(memcg->memory.high));
- unsigned long used = page_counter_read(&memcg->memory);
- *pheadroom = min(*pheadroom, ceiling - min(ceiling, used));
- memcg = parent;
- }
- }
- /*
- * Foreign dirty flushing
- *
- * There's an inherent mismatch between memcg and writeback. The former
- * tracks ownership per-page while the latter per-inode. This was a
- * deliberate design decision because honoring per-page ownership in the
- * writeback path is complicated, may lead to higher CPU and IO overheads
- * and deemed unnecessary given that write-sharing an inode across
- * different cgroups isn't a common use-case.
- *
- * Combined with inode majority-writer ownership switching, this works well
- * enough in most cases but there are some pathological cases. For
- * example, let's say there are two cgroups A and B which keep writing to
- * different but confined parts of the same inode. B owns the inode and
- * A's memory is limited far below B's. A's dirty ratio can rise enough to
- * trigger balance_dirty_pages() sleeps but B's can be low enough to avoid
- * triggering background writeback. A will be slowed down without a way to
- * make writeback of the dirty pages happen.
- *
- * Conditions like the above can lead to a cgroup getting repeatedly and
- * severely throttled after making some progress after each
- * dirty_expire_interval while the underlying IO device is almost
- * completely idle.
- *
- * Solving this problem completely requires matching the ownership tracking
- * granularities between memcg and writeback in either direction. However,
- * the more egregious behaviors can be avoided by simply remembering the
- * most recent foreign dirtying events and initiating remote flushes on
- * them when local writeback isn't enough to keep the memory clean enough.
- *
- * The following two functions implement such mechanism. When a foreign
- * page - a page whose memcg and writeback ownerships don't match - is
- * dirtied, mem_cgroup_track_foreign_dirty() records the inode owning
- * bdi_writeback on the page owning memcg. When balance_dirty_pages()
- * decides that the memcg needs to sleep due to high dirty ratio, it calls
- * mem_cgroup_flush_foreign() which queues writeback on the recorded
- * foreign bdi_writebacks which haven't expired. Both the numbers of
- * recorded bdi_writebacks and concurrent in-flight foreign writebacks are
- * limited to MEMCG_CGWB_FRN_CNT.
- *
- * The mechanism only remembers IDs and doesn't hold any object references.
- * As being wrong occasionally doesn't matter, updates and accesses to the
- * records are lockless and racy.
- */
- void mem_cgroup_track_foreign_dirty_slowpath(struct folio *folio,
- struct bdi_writeback *wb)
- {
- struct mem_cgroup *memcg = folio_memcg(folio);
- struct memcg_cgwb_frn *frn;
- u64 now = get_jiffies_64();
- u64 oldest_at = now;
- int oldest = -1;
- int i;
- trace_track_foreign_dirty(folio, wb);
- /*
- * Pick the slot to use. If there is already a slot for @wb, keep
- * using it. If not replace the oldest one which isn't being
- * written out.
- */
- for (i = 0; i < MEMCG_CGWB_FRN_CNT; i++) {
- frn = &memcg->cgwb_frn[i];
- if (frn->bdi_id == wb->bdi->id &&
- frn->memcg_id == wb->memcg_css->id)
- break;
- if (time_before64(frn->at, oldest_at) &&
- atomic_read(&frn->done.cnt) == 1) {
- oldest = i;
- oldest_at = frn->at;
- }
- }
- if (i < MEMCG_CGWB_FRN_CNT) {
- /*
- * Re-using an existing one. Update timestamp lazily to
- * avoid making the cacheline hot. We want them to be
- * reasonably up-to-date and significantly shorter than
- * dirty_expire_interval as that's what expires the record.
- * Use the shorter of 1s and dirty_expire_interval / 8.
- */
- unsigned long update_intv =
- min_t(unsigned long, HZ,
- msecs_to_jiffies(dirty_expire_interval * 10) / 8);
- if (time_before64(frn->at, now - update_intv))
- frn->at = now;
- } else if (oldest >= 0) {
- /* replace the oldest free one */
- frn = &memcg->cgwb_frn[oldest];
- frn->bdi_id = wb->bdi->id;
- frn->memcg_id = wb->memcg_css->id;
- frn->at = now;
- }
- }
- /* issue foreign writeback flushes for recorded foreign dirtying events */
- void mem_cgroup_flush_foreign(struct bdi_writeback *wb)
- {
- struct mem_cgroup *memcg = mem_cgroup_from_css(wb->memcg_css);
- unsigned long intv = msecs_to_jiffies(dirty_expire_interval * 10);
- u64 now = jiffies_64;
- int i;
- for (i = 0; i < MEMCG_CGWB_FRN_CNT; i++) {
- struct memcg_cgwb_frn *frn = &memcg->cgwb_frn[i];
- /*
- * If the record is older than dirty_expire_interval,
- * writeback on it has already started. No need to kick it
- * off again. Also, don't start a new one if there's
- * already one in flight.
- */
- if (time_after64(frn->at, now - intv) &&
- atomic_read(&frn->done.cnt) == 1) {
- frn->at = 0;
- trace_flush_foreign(wb, frn->bdi_id, frn->memcg_id);
- cgroup_writeback_by_id(frn->bdi_id, frn->memcg_id,
- WB_REASON_FOREIGN_FLUSH,
- &frn->done);
- }
- }
- }
- #else /* CONFIG_CGROUP_WRITEBACK */
- static int memcg_wb_domain_init(struct mem_cgroup *memcg, gfp_t gfp)
- {
- return 0;
- }
- static void memcg_wb_domain_exit(struct mem_cgroup *memcg)
- {
- }
- static void memcg_wb_domain_size_changed(struct mem_cgroup *memcg)
- {
- }
- #endif /* CONFIG_CGROUP_WRITEBACK */
- /*
- * DO NOT USE IN NEW FILES.
- *
- * "cgroup.event_control" implementation.
- *
- * This is way over-engineered. It tries to support fully configurable
- * events for each user. Such level of flexibility is completely
- * unnecessary especially in the light of the planned unified hierarchy.
- *
- * Please deprecate this and replace with something simpler if at all
- * possible.
- */
- /*
- * Unregister event and free resources.
- *
- * Gets called from workqueue.
- */
- static void memcg_event_remove(struct work_struct *work)
- {
- struct mem_cgroup_event *event =
- container_of(work, struct mem_cgroup_event, remove);
- struct mem_cgroup *memcg = event->memcg;
- remove_wait_queue(event->wqh, &event->wait);
- event->unregister_event(memcg, event->eventfd);
- /* Notify userspace the event is going away. */
- eventfd_signal(event->eventfd, 1);
- eventfd_ctx_put(event->eventfd);
- kfree(event);
- css_put(&memcg->css);
- }
- /*
- * Gets called on EPOLLHUP on eventfd when user closes it.
- *
- * Called with wqh->lock held and interrupts disabled.
- */
- static int memcg_event_wake(wait_queue_entry_t *wait, unsigned mode,
- int sync, void *key)
- {
- struct mem_cgroup_event *event =
- container_of(wait, struct mem_cgroup_event, wait);
- struct mem_cgroup *memcg = event->memcg;
- __poll_t flags = key_to_poll(key);
- if (flags & EPOLLHUP) {
- /*
- * If the event has been detached at cgroup removal, we
- * can simply return knowing the other side will cleanup
- * for us.
- *
- * We can't race against event freeing since the other
- * side will require wqh->lock via remove_wait_queue(),
- * which we hold.
- */
- spin_lock(&memcg->event_list_lock);
- if (!list_empty(&event->list)) {
- list_del_init(&event->list);
- /*
- * We are in atomic context, but cgroup_event_remove()
- * may sleep, so we have to call it in workqueue.
- */
- schedule_work(&event->remove);
- }
- spin_unlock(&memcg->event_list_lock);
- }
- return 0;
- }
- static void memcg_event_ptable_queue_proc(struct file *file,
- wait_queue_head_t *wqh, poll_table *pt)
- {
- struct mem_cgroup_event *event =
- container_of(pt, struct mem_cgroup_event, pt);
- event->wqh = wqh;
- add_wait_queue(wqh, &event->wait);
- }
- /*
- * DO NOT USE IN NEW FILES.
- *
- * Parse input and register new cgroup event handler.
- *
- * Input must be in format '<event_fd> <control_fd> <args>'.
- * Interpretation of args is defined by control file implementation.
- */
- static ssize_t memcg_write_event_control(struct kernfs_open_file *of,
- char *buf, size_t nbytes, loff_t off)
- {
- struct cgroup_subsys_state *css = of_css(of);
- struct mem_cgroup *memcg = mem_cgroup_from_css(css);
- struct mem_cgroup_event *event;
- struct cgroup_subsys_state *cfile_css;
- unsigned int efd, cfd;
- struct fd efile;
- struct fd cfile;
- struct dentry *cdentry;
- const char *name;
- char *endp;
- int ret;
- if (IS_ENABLED(CONFIG_PREEMPT_RT))
- return -EOPNOTSUPP;
- buf = strstrip(buf);
- efd = simple_strtoul(buf, &endp, 10);
- if (*endp != ' ')
- return -EINVAL;
- buf = endp + 1;
- cfd = simple_strtoul(buf, &endp, 10);
- if ((*endp != ' ') && (*endp != '\0'))
- return -EINVAL;
- buf = endp + 1;
- event = kzalloc(sizeof(*event), GFP_KERNEL);
- if (!event)
- return -ENOMEM;
- event->memcg = memcg;
- INIT_LIST_HEAD(&event->list);
- init_poll_funcptr(&event->pt, memcg_event_ptable_queue_proc);
- init_waitqueue_func_entry(&event->wait, memcg_event_wake);
- INIT_WORK(&event->remove, memcg_event_remove);
- efile = fdget(efd);
- if (!efile.file) {
- ret = -EBADF;
- goto out_kfree;
- }
- event->eventfd = eventfd_ctx_fileget(efile.file);
- if (IS_ERR(event->eventfd)) {
- ret = PTR_ERR(event->eventfd);
- goto out_put_efile;
- }
- cfile = fdget(cfd);
- if (!cfile.file) {
- ret = -EBADF;
- goto out_put_eventfd;
- }
- /* the process need read permission on control file */
- /* AV: shouldn't we check that it's been opened for read instead? */
- ret = file_permission(cfile.file, MAY_READ);
- if (ret < 0)
- goto out_put_cfile;
- /*
- * The control file must be a regular cgroup1 file. As a regular cgroup
- * file can't be renamed, it's safe to access its name afterwards.
- */
- cdentry = cfile.file->f_path.dentry;
- if (cdentry->d_sb->s_type != &cgroup_fs_type || !d_is_reg(cdentry)) {
- ret = -EINVAL;
- goto out_put_cfile;
- }
- /*
- * Determine the event callbacks and set them in @event. This used
- * to be done via struct cftype but cgroup core no longer knows
- * about these events. The following is crude but the whole thing
- * is for compatibility anyway.
- *
- * DO NOT ADD NEW FILES.
- */
- name = cdentry->d_name.name;
- if (!strcmp(name, "memory.usage_in_bytes")) {
- event->register_event = mem_cgroup_usage_register_event;
- event->unregister_event = mem_cgroup_usage_unregister_event;
- } else if (!strcmp(name, "memory.oom_control")) {
- event->register_event = mem_cgroup_oom_register_event;
- event->unregister_event = mem_cgroup_oom_unregister_event;
- } else if (!strcmp(name, "memory.pressure_level")) {
- event->register_event = vmpressure_register_event;
- event->unregister_event = vmpressure_unregister_event;
- } else if (!strcmp(name, "memory.memsw.usage_in_bytes")) {
- event->register_event = memsw_cgroup_usage_register_event;
- event->unregister_event = memsw_cgroup_usage_unregister_event;
- } else {
- ret = -EINVAL;
- goto out_put_cfile;
- }
- /*
- * Verify @cfile should belong to @css. Also, remaining events are
- * automatically removed on cgroup destruction but the removal is
- * asynchronous, so take an extra ref on @css.
- */
- cfile_css = css_tryget_online_from_dir(cdentry->d_parent,
- &memory_cgrp_subsys);
- ret = -EINVAL;
- if (IS_ERR(cfile_css))
- goto out_put_cfile;
- if (cfile_css != css) {
- css_put(cfile_css);
- goto out_put_cfile;
- }
- ret = event->register_event(memcg, event->eventfd, buf);
- if (ret)
- goto out_put_css;
- vfs_poll(efile.file, &event->pt);
- spin_lock_irq(&memcg->event_list_lock);
- list_add(&event->list, &memcg->event_list);
- spin_unlock_irq(&memcg->event_list_lock);
- fdput(cfile);
- fdput(efile);
- return nbytes;
- out_put_css:
- css_put(css);
- out_put_cfile:
- fdput(cfile);
- out_put_eventfd:
- eventfd_ctx_put(event->eventfd);
- out_put_efile:
- fdput(efile);
- out_kfree:
- kfree(event);
- return ret;
- }
- #if defined(CONFIG_MEMCG_KMEM) && (defined(CONFIG_SLAB) || defined(CONFIG_SLUB_DEBUG))
- static int mem_cgroup_slab_show(struct seq_file *m, void *p)
- {
- /*
- * Deprecated.
- * Please, take a look at tools/cgroup/memcg_slabinfo.py .
- */
- return 0;
- }
- #endif
- static struct cftype mem_cgroup_legacy_files[] = {
- {
- .name = "usage_in_bytes",
- .private = MEMFILE_PRIVATE(_MEM, RES_USAGE),
- .read_u64 = mem_cgroup_read_u64,
- },
- {
- .name = "max_usage_in_bytes",
- .private = MEMFILE_PRIVATE(_MEM, RES_MAX_USAGE),
- .write = mem_cgroup_reset,
- .read_u64 = mem_cgroup_read_u64,
- },
- {
- .name = "limit_in_bytes",
- .private = MEMFILE_PRIVATE(_MEM, RES_LIMIT),
- .write = mem_cgroup_write,
- .read_u64 = mem_cgroup_read_u64,
- },
- {
- .name = "soft_limit_in_bytes",
- .private = MEMFILE_PRIVATE(_MEM, RES_SOFT_LIMIT),
- .write = mem_cgroup_write,
- .read_u64 = mem_cgroup_read_u64,
- },
- {
- .name = "failcnt",
- .private = MEMFILE_PRIVATE(_MEM, RES_FAILCNT),
- .write = mem_cgroup_reset,
- .read_u64 = mem_cgroup_read_u64,
- },
- {
- .name = "stat",
- .seq_show = memcg_stat_show,
- },
- {
- .name = "force_empty",
- .write = mem_cgroup_force_empty_write,
- },
- {
- .name = "use_hierarchy",
- .write_u64 = mem_cgroup_hierarchy_write,
- .read_u64 = mem_cgroup_hierarchy_read,
- },
- {
- .name = "cgroup.event_control", /* XXX: for compat */
- .write = memcg_write_event_control,
- .flags = CFTYPE_NO_PREFIX | CFTYPE_WORLD_WRITABLE,
- },
- {
- .name = "swappiness",
- .read_u64 = mem_cgroup_swappiness_read,
- .write_u64 = mem_cgroup_swappiness_write,
- },
- {
- .name = "move_charge_at_immigrate",
- .read_u64 = mem_cgroup_move_charge_read,
- .write_u64 = mem_cgroup_move_charge_write,
- },
- {
- .name = "oom_control",
- .seq_show = mem_cgroup_oom_control_read,
- .write_u64 = mem_cgroup_oom_control_write,
- },
- {
- .name = "pressure_level",
- },
- #ifdef CONFIG_NUMA
- {
- .name = "numa_stat",
- .seq_show = memcg_numa_stat_show,
- },
- #endif
- {
- .name = "kmem.limit_in_bytes",
- .private = MEMFILE_PRIVATE(_KMEM, RES_LIMIT),
- .write = mem_cgroup_write,
- .read_u64 = mem_cgroup_read_u64,
- },
- {
- .name = "kmem.usage_in_bytes",
- .private = MEMFILE_PRIVATE(_KMEM, RES_USAGE),
- .read_u64 = mem_cgroup_read_u64,
- },
- {
- .name = "kmem.failcnt",
- .private = MEMFILE_PRIVATE(_KMEM, RES_FAILCNT),
- .write = mem_cgroup_reset,
- .read_u64 = mem_cgroup_read_u64,
- },
- {
- .name = "kmem.max_usage_in_bytes",
- .private = MEMFILE_PRIVATE(_KMEM, RES_MAX_USAGE),
- .write = mem_cgroup_reset,
- .read_u64 = mem_cgroup_read_u64,
- },
- #if defined(CONFIG_MEMCG_KMEM) && \
- (defined(CONFIG_SLAB) || defined(CONFIG_SLUB_DEBUG))
- {
- .name = "kmem.slabinfo",
- .seq_show = mem_cgroup_slab_show,
- },
- #endif
- {
- .name = "kmem.tcp.limit_in_bytes",
- .private = MEMFILE_PRIVATE(_TCP, RES_LIMIT),
- .write = mem_cgroup_write,
- .read_u64 = mem_cgroup_read_u64,
- },
- {
- .name = "kmem.tcp.usage_in_bytes",
- .private = MEMFILE_PRIVATE(_TCP, RES_USAGE),
- .read_u64 = mem_cgroup_read_u64,
- },
- {
- .name = "kmem.tcp.failcnt",
- .private = MEMFILE_PRIVATE(_TCP, RES_FAILCNT),
- .write = mem_cgroup_reset,
- .read_u64 = mem_cgroup_read_u64,
- },
- {
- .name = "kmem.tcp.max_usage_in_bytes",
- .private = MEMFILE_PRIVATE(_TCP, RES_MAX_USAGE),
- .write = mem_cgroup_reset,
- .read_u64 = mem_cgroup_read_u64,
- },
- { }, /* terminate */
- };
- /*
- * Private memory cgroup IDR
- *
- * Swap-out records and page cache shadow entries need to store memcg
- * references in constrained space, so we maintain an ID space that is
- * limited to 16 bit (MEM_CGROUP_ID_MAX), limiting the total number of
- * memory-controlled cgroups to 64k.
- *
- * However, there usually are many references to the offline CSS after
- * the cgroup has been destroyed, such as page cache or reclaimable
- * slab objects, that don't need to hang on to the ID. We want to keep
- * those dead CSS from occupying IDs, or we might quickly exhaust the
- * relatively small ID space and prevent the creation of new cgroups
- * even when there are much fewer than 64k cgroups - possibly none.
- *
- * Maintain a private 16-bit ID space for memcg, and allow the ID to
- * be freed and recycled when it's no longer needed, which is usually
- * when the CSS is offlined.
- *
- * The only exception to that are records of swapped out tmpfs/shmem
- * pages that need to be attributed to live ancestors on swapin. But
- * those references are manageable from userspace.
- */
- static DEFINE_IDR(mem_cgroup_idr);
- static void mem_cgroup_id_remove(struct mem_cgroup *memcg)
- {
- if (memcg->id.id > 0) {
- trace_android_vh_mem_cgroup_id_remove(memcg);
- idr_remove(&mem_cgroup_idr, memcg->id.id);
- memcg->id.id = 0;
- }
- }
- static void __maybe_unused mem_cgroup_id_get_many(struct mem_cgroup *memcg,
- unsigned int n)
- {
- refcount_add(n, &memcg->id.ref);
- }
- static void mem_cgroup_id_put_many(struct mem_cgroup *memcg, unsigned int n)
- {
- if (refcount_sub_and_test(n, &memcg->id.ref)) {
- mem_cgroup_id_remove(memcg);
- /* Memcg ID pins CSS */
- css_put(&memcg->css);
- }
- }
- static inline void mem_cgroup_id_put(struct mem_cgroup *memcg)
- {
- mem_cgroup_id_put_many(memcg, 1);
- }
- /**
- * mem_cgroup_from_id - look up a memcg from a memcg id
- * @id: the memcg id to look up
- *
- * Caller must hold rcu_read_lock().
- */
- struct mem_cgroup *mem_cgroup_from_id(unsigned short id)
- {
- WARN_ON_ONCE(!rcu_read_lock_held());
- return idr_find(&mem_cgroup_idr, id);
- }
- EXPORT_SYMBOL_GPL(mem_cgroup_from_id);
- #ifdef CONFIG_SHRINKER_DEBUG
- struct mem_cgroup *mem_cgroup_get_from_ino(unsigned long ino)
- {
- struct cgroup *cgrp;
- struct cgroup_subsys_state *css;
- struct mem_cgroup *memcg;
- cgrp = cgroup_get_from_id(ino);
- if (IS_ERR(cgrp))
- return ERR_CAST(cgrp);
- css = cgroup_get_e_css(cgrp, &memory_cgrp_subsys);
- if (css)
- memcg = container_of(css, struct mem_cgroup, css);
- else
- memcg = ERR_PTR(-ENOENT);
- cgroup_put(cgrp);
- return memcg;
- }
- #endif
- static int alloc_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node)
- {
- struct mem_cgroup_per_node *pn;
- pn = kzalloc_node(sizeof(*pn), GFP_KERNEL, node);
- if (!pn)
- return 1;
- pn->lruvec_stats_percpu = alloc_percpu_gfp(struct lruvec_stats_percpu,
- GFP_KERNEL_ACCOUNT);
- if (!pn->lruvec_stats_percpu) {
- kfree(pn);
- return 1;
- }
- lruvec_init(&pn->lruvec);
- pn->memcg = memcg;
- memcg->nodeinfo[node] = pn;
- return 0;
- }
- static void free_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node)
- {
- struct mem_cgroup_per_node *pn = memcg->nodeinfo[node];
- if (!pn)
- return;
- free_percpu(pn->lruvec_stats_percpu);
- kfree(pn);
- }
- static void __mem_cgroup_free(struct mem_cgroup *memcg)
- {
- int node;
- trace_android_vh_mem_cgroup_free(memcg);
- for_each_node(node)
- free_mem_cgroup_per_node_info(memcg, node);
- kfree(memcg->vmstats);
- free_percpu(memcg->vmstats_percpu);
- kfree(memcg);
- }
- static void mem_cgroup_free(struct mem_cgroup *memcg)
- {
- lru_gen_exit_memcg(memcg);
- memcg_wb_domain_exit(memcg);
- __mem_cgroup_free(memcg);
- }
- static struct mem_cgroup *mem_cgroup_alloc(void)
- {
- struct mem_cgroup *memcg;
- int node;
- int __maybe_unused i;
- long error = -ENOMEM;
- memcg = kzalloc(struct_size(memcg, nodeinfo, nr_node_ids), GFP_KERNEL);
- if (!memcg)
- return ERR_PTR(error);
- memcg->id.id = idr_alloc(&mem_cgroup_idr, NULL,
- 1, MEM_CGROUP_ID_MAX + 1, GFP_KERNEL);
- if (memcg->id.id < 0) {
- error = memcg->id.id;
- goto fail;
- }
- memcg->vmstats = kzalloc(sizeof(struct memcg_vmstats), GFP_KERNEL);
- if (!memcg->vmstats)
- goto fail;
- memcg->vmstats_percpu = alloc_percpu_gfp(struct memcg_vmstats_percpu,
- GFP_KERNEL_ACCOUNT);
- if (!memcg->vmstats_percpu)
- goto fail;
- for_each_node(node)
- if (alloc_mem_cgroup_per_node_info(memcg, node))
- goto fail;
- if (memcg_wb_domain_init(memcg, GFP_KERNEL))
- goto fail;
- INIT_WORK(&memcg->high_work, high_work_func);
- INIT_LIST_HEAD(&memcg->oom_notify);
- mutex_init(&memcg->thresholds_lock);
- spin_lock_init(&memcg->move_lock);
- vmpressure_init(&memcg->vmpressure);
- INIT_LIST_HEAD(&memcg->event_list);
- spin_lock_init(&memcg->event_list_lock);
- memcg->socket_pressure = jiffies;
- #ifdef CONFIG_MEMCG_KMEM
- memcg->kmemcg_id = -1;
- INIT_LIST_HEAD(&memcg->objcg_list);
- #endif
- #ifdef CONFIG_CGROUP_WRITEBACK
- INIT_LIST_HEAD(&memcg->cgwb_list);
- for (i = 0; i < MEMCG_CGWB_FRN_CNT; i++)
- memcg->cgwb_frn[i].done =
- __WB_COMPLETION_INIT(&memcg_cgwb_frn_waitq);
- #endif
- #ifdef CONFIG_TRANSPARENT_HUGEPAGE
- spin_lock_init(&memcg->deferred_split_queue.split_queue_lock);
- INIT_LIST_HEAD(&memcg->deferred_split_queue.split_queue);
- memcg->deferred_split_queue.split_queue_len = 0;
- #endif
- idr_replace(&mem_cgroup_idr, memcg, memcg->id.id);
- lru_gen_init_memcg(memcg);
- trace_android_vh_mem_cgroup_alloc(memcg);
- return memcg;
- fail:
- mem_cgroup_id_remove(memcg);
- __mem_cgroup_free(memcg);
- return ERR_PTR(error);
- }
- static struct cgroup_subsys_state * __ref
- mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
- {
- struct mem_cgroup *parent = mem_cgroup_from_css(parent_css);
- struct mem_cgroup *memcg, *old_memcg;
- old_memcg = set_active_memcg(parent);
- memcg = mem_cgroup_alloc();
- set_active_memcg(old_memcg);
- if (IS_ERR(memcg))
- return ERR_CAST(memcg);
- page_counter_set_high(&memcg->memory, PAGE_COUNTER_MAX);
- memcg->soft_limit = PAGE_COUNTER_MAX;
- #if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP)
- memcg->zswap_max = PAGE_COUNTER_MAX;
- #endif
- page_counter_set_high(&memcg->swap, PAGE_COUNTER_MAX);
- if (parent) {
- memcg->swappiness = mem_cgroup_swappiness(parent);
- memcg->oom_kill_disable = parent->oom_kill_disable;
- page_counter_init(&memcg->memory, &parent->memory);
- page_counter_init(&memcg->swap, &parent->swap);
- page_counter_init(&memcg->kmem, &parent->kmem);
- page_counter_init(&memcg->tcpmem, &parent->tcpmem);
- } else {
- init_memcg_events();
- page_counter_init(&memcg->memory, NULL);
- page_counter_init(&memcg->swap, NULL);
- page_counter_init(&memcg->kmem, NULL);
- page_counter_init(&memcg->tcpmem, NULL);
- root_mem_cgroup = memcg;
- return &memcg->css;
- }
- if (cgroup_subsys_on_dfl(memory_cgrp_subsys) && !cgroup_memory_nosocket)
- static_branch_inc(&memcg_sockets_enabled_key);
- return &memcg->css;
- }
- static int mem_cgroup_css_online(struct cgroup_subsys_state *css)
- {
- struct mem_cgroup *memcg = mem_cgroup_from_css(css);
- if (memcg_online_kmem(memcg))
- goto remove_id;
- /*
- * A memcg must be visible for expand_shrinker_info()
- * by the time the maps are allocated. So, we allocate maps
- * here, when for_each_mem_cgroup() can't skip it.
- */
- if (alloc_shrinker_info(memcg))
- goto offline_kmem;
- /* Online state pins memcg ID, memcg ID pins CSS */
- refcount_set(&memcg->id.ref, 1);
- css_get(css);
- if (unlikely(mem_cgroup_is_root(memcg)) && !mem_cgroup_disabled())
- queue_delayed_work(system_unbound_wq, &stats_flush_dwork,
- 2UL*HZ);
- lru_gen_online_memcg(memcg);
- trace_android_vh_mem_cgroup_css_online(css, memcg);
- return 0;
- offline_kmem:
- memcg_offline_kmem(memcg);
- remove_id:
- mem_cgroup_id_remove(memcg);
- return -ENOMEM;
- }
- static void mem_cgroup_css_offline(struct cgroup_subsys_state *css)
- {
- struct mem_cgroup *memcg = mem_cgroup_from_css(css);
- struct mem_cgroup_event *event, *tmp;
- trace_android_vh_mem_cgroup_css_offline(css, memcg);
- /*
- * Unregister events and notify userspace.
- * Notify userspace about cgroup removing only after rmdir of cgroup
- * directory to avoid race between userspace and kernelspace.
- */
- spin_lock_irq(&memcg->event_list_lock);
- list_for_each_entry_safe(event, tmp, &memcg->event_list, list) {
- list_del_init(&event->list);
- schedule_work(&event->remove);
- }
- spin_unlock_irq(&memcg->event_list_lock);
- page_counter_set_min(&memcg->memory, 0);
- page_counter_set_low(&memcg->memory, 0);
- memcg_offline_kmem(memcg);
- reparent_shrinker_deferred(memcg);
- wb_memcg_offline(memcg);
- lru_gen_offline_memcg(memcg);
- drain_all_stock(memcg);
- mem_cgroup_id_put(memcg);
- }
- static void mem_cgroup_css_released(struct cgroup_subsys_state *css)
- {
- struct mem_cgroup *memcg = mem_cgroup_from_css(css);
- invalidate_reclaim_iterators(memcg);
- lru_gen_release_memcg(memcg);
- }
- static void mem_cgroup_css_free(struct cgroup_subsys_state *css)
- {
- struct mem_cgroup *memcg = mem_cgroup_from_css(css);
- int __maybe_unused i;
- #ifdef CONFIG_CGROUP_WRITEBACK
- for (i = 0; i < MEMCG_CGWB_FRN_CNT; i++)
- wb_wait_for_completion(&memcg->cgwb_frn[i].done);
- #endif
- if (cgroup_subsys_on_dfl(memory_cgrp_subsys) && !cgroup_memory_nosocket)
- static_branch_dec(&memcg_sockets_enabled_key);
- if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && memcg->tcpmem_active)
- static_branch_dec(&memcg_sockets_enabled_key);
- vmpressure_cleanup(&memcg->vmpressure);
- cancel_work_sync(&memcg->high_work);
- mem_cgroup_remove_from_trees(memcg);
- free_shrinker_info(memcg);
- mem_cgroup_free(memcg);
- }
- /**
- * mem_cgroup_css_reset - reset the states of a mem_cgroup
- * @css: the target css
- *
- * Reset the states of the mem_cgroup associated with @css. This is
- * invoked when the userland requests disabling on the default hierarchy
- * but the memcg is pinned through dependency. The memcg should stop
- * applying policies and should revert to the vanilla state as it may be
- * made visible again.
- *
- * The current implementation only resets the essential configurations.
- * This needs to be expanded to cover all the visible parts.
- */
- static void mem_cgroup_css_reset(struct cgroup_subsys_state *css)
- {
- struct mem_cgroup *memcg = mem_cgroup_from_css(css);
- page_counter_set_max(&memcg->memory, PAGE_COUNTER_MAX);
- page_counter_set_max(&memcg->swap, PAGE_COUNTER_MAX);
- page_counter_set_max(&memcg->kmem, PAGE_COUNTER_MAX);
- page_counter_set_max(&memcg->tcpmem, PAGE_COUNTER_MAX);
- page_counter_set_min(&memcg->memory, 0);
- page_counter_set_low(&memcg->memory, 0);
- page_counter_set_high(&memcg->memory, PAGE_COUNTER_MAX);
- memcg->soft_limit = PAGE_COUNTER_MAX;
- page_counter_set_high(&memcg->swap, PAGE_COUNTER_MAX);
- memcg_wb_domain_size_changed(memcg);
- }
- static void mem_cgroup_css_rstat_flush(struct cgroup_subsys_state *css, int cpu)
- {
- struct mem_cgroup *memcg = mem_cgroup_from_css(css);
- struct mem_cgroup *parent = parent_mem_cgroup(memcg);
- struct memcg_vmstats_percpu *statc;
- long delta, v;
- int i, nid;
- statc = per_cpu_ptr(memcg->vmstats_percpu, cpu);
- for (i = 0; i < MEMCG_NR_STAT; i++) {
- /*
- * Collect the aggregated propagation counts of groups
- * below us. We're in a per-cpu loop here and this is
- * a global counter, so the first cycle will get them.
- */
- delta = memcg->vmstats->state_pending[i];
- if (delta)
- memcg->vmstats->state_pending[i] = 0;
- /* Add CPU changes on this level since the last flush */
- v = READ_ONCE(statc->state[i]);
- if (v != statc->state_prev[i]) {
- delta += v - statc->state_prev[i];
- statc->state_prev[i] = v;
- }
- if (!delta)
- continue;
- /* Aggregate counts on this level and propagate upwards */
- memcg->vmstats->state[i] += delta;
- if (parent)
- parent->vmstats->state_pending[i] += delta;
- }
- for (i = 0; i < NR_MEMCG_EVENTS; i++) {
- delta = memcg->vmstats->events_pending[i];
- if (delta)
- memcg->vmstats->events_pending[i] = 0;
- v = READ_ONCE(statc->events[i]);
- if (v != statc->events_prev[i]) {
- delta += v - statc->events_prev[i];
- statc->events_prev[i] = v;
- }
- if (!delta)
- continue;
- memcg->vmstats->events[i] += delta;
- if (parent)
- parent->vmstats->events_pending[i] += delta;
- }
- for_each_node_state(nid, N_MEMORY) {
- struct mem_cgroup_per_node *pn = memcg->nodeinfo[nid];
- struct mem_cgroup_per_node *ppn = NULL;
- struct lruvec_stats_percpu *lstatc;
- if (parent)
- ppn = parent->nodeinfo[nid];
- lstatc = per_cpu_ptr(pn->lruvec_stats_percpu, cpu);
- for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) {
- delta = pn->lruvec_stats.state_pending[i];
- if (delta)
- pn->lruvec_stats.state_pending[i] = 0;
- v = READ_ONCE(lstatc->state[i]);
- if (v != lstatc->state_prev[i]) {
- delta += v - lstatc->state_prev[i];
- lstatc->state_prev[i] = v;
- }
- if (!delta)
- continue;
- pn->lruvec_stats.state[i] += delta;
- if (ppn)
- ppn->lruvec_stats.state_pending[i] += delta;
- }
- }
- }
- #ifdef CONFIG_MMU
- /* Handlers for move charge at task migration. */
- static int mem_cgroup_do_precharge(unsigned long count)
- {
- int ret;
- /* Try a single bulk charge without reclaim first, kswapd may wake */
- ret = try_charge(mc.to, GFP_KERNEL & ~__GFP_DIRECT_RECLAIM, count);
- if (!ret) {
- mc.precharge += count;
- return ret;
- }
- /* Try charges one by one with reclaim, but do not retry */
- while (count--) {
- ret = try_charge(mc.to, GFP_KERNEL | __GFP_NORETRY, 1);
- if (ret)
- return ret;
- mc.precharge++;
- cond_resched();
- }
- return 0;
- }
- union mc_target {
- struct page *page;
- swp_entry_t ent;
- };
- enum mc_target_type {
- MC_TARGET_NONE = 0,
- MC_TARGET_PAGE,
- MC_TARGET_SWAP,
- MC_TARGET_DEVICE,
- };
- static struct page *mc_handle_present_pte(struct vm_area_struct *vma,
- unsigned long addr, pte_t ptent)
- {
- struct page *page = vm_normal_page(vma, addr, ptent);
- if (!page || !page_mapped(page))
- return NULL;
- if (PageAnon(page)) {
- if (!(mc.flags & MOVE_ANON))
- return NULL;
- } else {
- if (!(mc.flags & MOVE_FILE))
- return NULL;
- }
- if (!get_page_unless_zero(page))
- return NULL;
- return page;
- }
- #if defined(CONFIG_SWAP) || defined(CONFIG_DEVICE_PRIVATE)
- static struct page *mc_handle_swap_pte(struct vm_area_struct *vma,
- pte_t ptent, swp_entry_t *entry)
- {
- struct page *page = NULL;
- swp_entry_t ent = pte_to_swp_entry(ptent);
- if (!(mc.flags & MOVE_ANON))
- return NULL;
- /*
- * Handle device private pages that are not accessible by the CPU, but
- * stored as special swap entries in the page table.
- */
- if (is_device_private_entry(ent)) {
- page = pfn_swap_entry_to_page(ent);
- if (!get_page_unless_zero(page))
- return NULL;
- return page;
- }
- if (non_swap_entry(ent))
- return NULL;
- /*
- * Because swap_cache_get_folio() updates some statistics counter,
- * we call find_get_page() with swapper_space directly.
- */
- page = find_get_page(swap_address_space(ent), swp_offset(ent));
- entry->val = ent.val;
- return page;
- }
- #else
- static struct page *mc_handle_swap_pte(struct vm_area_struct *vma,
- pte_t ptent, swp_entry_t *entry)
- {
- return NULL;
- }
- #endif
- static struct page *mc_handle_file_pte(struct vm_area_struct *vma,
- unsigned long addr, pte_t ptent)
- {
- if (!vma->vm_file) /* anonymous vma */
- return NULL;
- if (!(mc.flags & MOVE_FILE))
- return NULL;
- /* page is moved even if it's not RSS of this task(page-faulted). */
- /* shmem/tmpfs may report page out on swap: account for that too. */
- return find_get_incore_page(vma->vm_file->f_mapping,
- linear_page_index(vma, addr));
- }
- /**
- * mem_cgroup_move_account - move account of the page
- * @page: the page
- * @compound: charge the page as compound or small page
- * @from: mem_cgroup which the page is moved from.
- * @to: mem_cgroup which the page is moved to. @from != @to.
- *
- * The caller must make sure the page is not on LRU (isolate_page() is useful.)
- *
- * This function doesn't do "charge" to new cgroup and doesn't do "uncharge"
- * from old cgroup.
- */
- static int mem_cgroup_move_account(struct page *page,
- bool compound,
- struct mem_cgroup *from,
- struct mem_cgroup *to)
- {
- struct folio *folio = page_folio(page);
- struct lruvec *from_vec, *to_vec;
- struct pglist_data *pgdat;
- unsigned int nr_pages = compound ? folio_nr_pages(folio) : 1;
- int nid, ret;
- VM_BUG_ON(from == to);
- VM_BUG_ON_FOLIO(folio_test_lru(folio), folio);
- VM_BUG_ON(compound && !folio_test_large(folio));
- /*
- * Prevent mem_cgroup_migrate() from looking at
- * page's memory cgroup of its source page while we change it.
- */
- ret = -EBUSY;
- if (!folio_trylock(folio))
- goto out;
- ret = -EINVAL;
- if (folio_memcg(folio) != from)
- goto out_unlock;
- pgdat = folio_pgdat(folio);
- from_vec = mem_cgroup_lruvec(from, pgdat);
- to_vec = mem_cgroup_lruvec(to, pgdat);
- folio_memcg_lock(folio);
- if (folio_test_anon(folio)) {
- if (folio_mapped(folio)) {
- __mod_lruvec_state(from_vec, NR_ANON_MAPPED, -nr_pages);
- __mod_lruvec_state(to_vec, NR_ANON_MAPPED, nr_pages);
- if (folio_test_transhuge(folio)) {
- __mod_lruvec_state(from_vec, NR_ANON_THPS,
- -nr_pages);
- __mod_lruvec_state(to_vec, NR_ANON_THPS,
- nr_pages);
- }
- }
- } else {
- __mod_lruvec_state(from_vec, NR_FILE_PAGES, -nr_pages);
- __mod_lruvec_state(to_vec, NR_FILE_PAGES, nr_pages);
- if (folio_test_swapbacked(folio)) {
- __mod_lruvec_state(from_vec, NR_SHMEM, -nr_pages);
- __mod_lruvec_state(to_vec, NR_SHMEM, nr_pages);
- }
- if (folio_mapped(folio)) {
- __mod_lruvec_state(from_vec, NR_FILE_MAPPED, -nr_pages);
- __mod_lruvec_state(to_vec, NR_FILE_MAPPED, nr_pages);
- }
- if (folio_test_dirty(folio)) {
- struct address_space *mapping = folio_mapping(folio);
- if (mapping_can_writeback(mapping)) {
- __mod_lruvec_state(from_vec, NR_FILE_DIRTY,
- -nr_pages);
- __mod_lruvec_state(to_vec, NR_FILE_DIRTY,
- nr_pages);
- }
- }
- }
- if (folio_test_writeback(folio)) {
- __mod_lruvec_state(from_vec, NR_WRITEBACK, -nr_pages);
- __mod_lruvec_state(to_vec, NR_WRITEBACK, nr_pages);
- }
- /*
- * All state has been migrated, let's switch to the new memcg.
- *
- * It is safe to change page's memcg here because the page
- * is referenced, charged, isolated, and locked: we can't race
- * with (un)charging, migration, LRU putback, or anything else
- * that would rely on a stable page's memory cgroup.
- *
- * Note that lock_page_memcg is a memcg lock, not a page lock,
- * to save space. As soon as we switch page's memory cgroup to a
- * new memcg that isn't locked, the above state can change
- * concurrently again. Make sure we're truly done with it.
- */
- smp_mb();
- css_get(&to->css);
- css_put(&from->css);
- folio->memcg_data = (unsigned long)to;
- __folio_memcg_unlock(from);
- ret = 0;
- nid = folio_nid(folio);
- local_irq_disable();
- mem_cgroup_charge_statistics(to, nr_pages);
- memcg_check_events(to, nid);
- mem_cgroup_charge_statistics(from, -nr_pages);
- memcg_check_events(from, nid);
- local_irq_enable();
- out_unlock:
- folio_unlock(folio);
- out:
- return ret;
- }
- /**
- * get_mctgt_type - get target type of moving charge
- * @vma: the vma the pte to be checked belongs
- * @addr: the address corresponding to the pte to be checked
- * @ptent: the pte to be checked
- * @target: the pointer the target page or swap ent will be stored(can be NULL)
- *
- * Returns
- * 0(MC_TARGET_NONE): if the pte is not a target for move charge.
- * 1(MC_TARGET_PAGE): if the page corresponding to this pte is a target for
- * move charge. if @target is not NULL, the page is stored in target->page
- * with extra refcnt got(Callers should handle it).
- * 2(MC_TARGET_SWAP): if the swap entry corresponding to this pte is a
- * target for charge migration. if @target is not NULL, the entry is stored
- * in target->ent.
- * 3(MC_TARGET_DEVICE): like MC_TARGET_PAGE but page is device memory and
- * thus not on the lru.
- * For now we such page is charge like a regular page would be as for all
- * intent and purposes it is just special memory taking the place of a
- * regular page.
- *
- * See Documentations/vm/hmm.txt and include/linux/hmm.h
- *
- * Called with pte lock held.
- */
- static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma,
- unsigned long addr, pte_t ptent, union mc_target *target)
- {
- struct page *page = NULL;
- enum mc_target_type ret = MC_TARGET_NONE;
- swp_entry_t ent = { .val = 0 };
- if (pte_present(ptent))
- page = mc_handle_present_pte(vma, addr, ptent);
- else if (pte_none_mostly(ptent))
- /*
- * PTE markers should be treated as a none pte here, separated
- * from other swap handling below.
- */
- page = mc_handle_file_pte(vma, addr, ptent);
- else if (is_swap_pte(ptent))
- page = mc_handle_swap_pte(vma, ptent, &ent);
- if (!page && !ent.val)
- return ret;
- if (page) {
- /*
- * Do only loose check w/o serialization.
- * mem_cgroup_move_account() checks the page is valid or
- * not under LRU exclusion.
- */
- if (page_memcg(page) == mc.from) {
- ret = MC_TARGET_PAGE;
- if (is_device_private_page(page) ||
- is_device_coherent_page(page))
- ret = MC_TARGET_DEVICE;
- if (target)
- target->page = page;
- }
- if (!ret || !target)
- put_page(page);
- }
- /*
- * There is a swap entry and a page doesn't exist or isn't charged.
- * But we cannot move a tail-page in a THP.
- */
- if (ent.val && !ret && (!page || !PageTransCompound(page)) &&
- mem_cgroup_id(mc.from) == lookup_swap_cgroup_id(ent)) {
- ret = MC_TARGET_SWAP;
- if (target)
- target->ent = ent;
- }
- return ret;
- }
- #ifdef CONFIG_TRANSPARENT_HUGEPAGE
- /*
- * We don't consider PMD mapped swapping or file mapped pages because THP does
- * not support them for now.
- * Caller should make sure that pmd_trans_huge(pmd) is true.
- */
- static enum mc_target_type get_mctgt_type_thp(struct vm_area_struct *vma,
- unsigned long addr, pmd_t pmd, union mc_target *target)
- {
- struct page *page = NULL;
- enum mc_target_type ret = MC_TARGET_NONE;
- if (unlikely(is_swap_pmd(pmd))) {
- VM_BUG_ON(thp_migration_supported() &&
- !is_pmd_migration_entry(pmd));
- return ret;
- }
- page = pmd_page(pmd);
- VM_BUG_ON_PAGE(!page || !PageHead(page), page);
- if (!(mc.flags & MOVE_ANON))
- return ret;
- if (page_memcg(page) == mc.from) {
- ret = MC_TARGET_PAGE;
- if (target) {
- get_page(page);
- target->page = page;
- }
- }
- return ret;
- }
- #else
- static inline enum mc_target_type get_mctgt_type_thp(struct vm_area_struct *vma,
- unsigned long addr, pmd_t pmd, union mc_target *target)
- {
- return MC_TARGET_NONE;
- }
- #endif
- static int mem_cgroup_count_precharge_pte_range(pmd_t *pmd,
- unsigned long addr, unsigned long end,
- struct mm_walk *walk)
- {
- struct vm_area_struct *vma = walk->vma;
- pte_t *pte;
- spinlock_t *ptl;
- ptl = pmd_trans_huge_lock(pmd, vma);
- if (ptl) {
- /*
- * Note their can not be MC_TARGET_DEVICE for now as we do not
- * support transparent huge page with MEMORY_DEVICE_PRIVATE but
- * this might change.
- */
- if (get_mctgt_type_thp(vma, addr, *pmd, NULL) == MC_TARGET_PAGE)
- mc.precharge += HPAGE_PMD_NR;
- spin_unlock(ptl);
- return 0;
- }
- if (pmd_trans_unstable(pmd))
- return 0;
- pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
- for (; addr != end; pte++, addr += PAGE_SIZE)
- if (get_mctgt_type(vma, addr, *pte, NULL))
- mc.precharge++; /* increment precharge temporarily */
- pte_unmap_unlock(pte - 1, ptl);
- cond_resched();
- return 0;
- }
- static const struct mm_walk_ops precharge_walk_ops = {
- .pmd_entry = mem_cgroup_count_precharge_pte_range,
- .walk_lock = PGWALK_RDLOCK,
- };
- static unsigned long mem_cgroup_count_precharge(struct mm_struct *mm)
- {
- unsigned long precharge;
- mmap_read_lock(mm);
- walk_page_range(mm, 0, ULONG_MAX, &precharge_walk_ops, NULL);
- mmap_read_unlock(mm);
- precharge = mc.precharge;
- mc.precharge = 0;
- return precharge;
- }
- static int mem_cgroup_precharge_mc(struct mm_struct *mm)
- {
- unsigned long precharge = mem_cgroup_count_precharge(mm);
- VM_BUG_ON(mc.moving_task);
- mc.moving_task = current;
- return mem_cgroup_do_precharge(precharge);
- }
- /* cancels all extra charges on mc.from and mc.to, and wakes up all waiters. */
- static void __mem_cgroup_clear_mc(void)
- {
- struct mem_cgroup *from = mc.from;
- struct mem_cgroup *to = mc.to;
- /* we must uncharge all the leftover precharges from mc.to */
- if (mc.precharge) {
- cancel_charge(mc.to, mc.precharge);
- mc.precharge = 0;
- }
- /*
- * we didn't uncharge from mc.from at mem_cgroup_move_account(), so
- * we must uncharge here.
- */
- if (mc.moved_charge) {
- cancel_charge(mc.from, mc.moved_charge);
- mc.moved_charge = 0;
- }
- /* we must fixup refcnts and charges */
- if (mc.moved_swap) {
- /* uncharge swap account from the old cgroup */
- if (!mem_cgroup_is_root(mc.from))
- page_counter_uncharge(&mc.from->memsw, mc.moved_swap);
- mem_cgroup_id_put_many(mc.from, mc.moved_swap);
- /*
- * we charged both to->memory and to->memsw, so we
- * should uncharge to->memory.
- */
- if (!mem_cgroup_is_root(mc.to))
- page_counter_uncharge(&mc.to->memory, mc.moved_swap);
- mc.moved_swap = 0;
- }
- memcg_oom_recover(from);
- memcg_oom_recover(to);
- wake_up_all(&mc.waitq);
- }
- static void mem_cgroup_clear_mc(void)
- {
- struct mm_struct *mm = mc.mm;
- /*
- * we must clear moving_task before waking up waiters at the end of
- * task migration.
- */
- mc.moving_task = NULL;
- __mem_cgroup_clear_mc();
- spin_lock(&mc.lock);
- mc.from = NULL;
- mc.to = NULL;
- mc.mm = NULL;
- spin_unlock(&mc.lock);
- mmput(mm);
- }
- static int mem_cgroup_can_attach(struct cgroup_taskset *tset)
- {
- struct cgroup_subsys_state *css;
- struct mem_cgroup *memcg = NULL; /* unneeded init to make gcc happy */
- struct mem_cgroup *from;
- struct task_struct *leader, *p;
- struct mm_struct *mm;
- unsigned long move_flags;
- int ret = 0;
- /* charge immigration isn't supported on the default hierarchy */
- if (cgroup_subsys_on_dfl(memory_cgrp_subsys))
- return 0;
- /*
- * Multi-process migrations only happen on the default hierarchy
- * where charge immigration is not used. Perform charge
- * immigration if @tset contains a leader and whine if there are
- * multiple.
- */
- p = NULL;
- cgroup_taskset_for_each_leader(leader, css, tset) {
- WARN_ON_ONCE(p);
- p = leader;
- memcg = mem_cgroup_from_css(css);
- }
- if (!p)
- return 0;
- /*
- * We are now committed to this value whatever it is. Changes in this
- * tunable will only affect upcoming migrations, not the current one.
- * So we need to save it, and keep it going.
- */
- move_flags = READ_ONCE(memcg->move_charge_at_immigrate);
- if (!move_flags)
- return 0;
- from = mem_cgroup_from_task(p);
- VM_BUG_ON(from == memcg);
- mm = get_task_mm(p);
- if (!mm)
- return 0;
- /* We move charges only when we move a owner of the mm */
- if (mm->owner == p) {
- VM_BUG_ON(mc.from);
- VM_BUG_ON(mc.to);
- VM_BUG_ON(mc.precharge);
- VM_BUG_ON(mc.moved_charge);
- VM_BUG_ON(mc.moved_swap);
- spin_lock(&mc.lock);
- mc.mm = mm;
- mc.from = from;
- mc.to = memcg;
- mc.flags = move_flags;
- spin_unlock(&mc.lock);
- /* We set mc.moving_task later */
- ret = mem_cgroup_precharge_mc(mm);
- if (ret)
- mem_cgroup_clear_mc();
- } else {
- mmput(mm);
- }
- return ret;
- }
- static void mem_cgroup_cancel_attach(struct cgroup_taskset *tset)
- {
- if (mc.to)
- mem_cgroup_clear_mc();
- }
- static int mem_cgroup_move_charge_pte_range(pmd_t *pmd,
- unsigned long addr, unsigned long end,
- struct mm_walk *walk)
- {
- int ret = 0;
- struct vm_area_struct *vma = walk->vma;
- pte_t *pte;
- spinlock_t *ptl;
- enum mc_target_type target_type;
- union mc_target target;
- struct page *page;
- ptl = pmd_trans_huge_lock(pmd, vma);
- if (ptl) {
- if (mc.precharge < HPAGE_PMD_NR) {
- spin_unlock(ptl);
- return 0;
- }
- target_type = get_mctgt_type_thp(vma, addr, *pmd, &target);
- if (target_type == MC_TARGET_PAGE) {
- page = target.page;
- if (!isolate_lru_page(page)) {
- if (!mem_cgroup_move_account(page, true,
- mc.from, mc.to)) {
- mc.precharge -= HPAGE_PMD_NR;
- mc.moved_charge += HPAGE_PMD_NR;
- }
- putback_lru_page(page);
- }
- put_page(page);
- } else if (target_type == MC_TARGET_DEVICE) {
- page = target.page;
- if (!mem_cgroup_move_account(page, true,
- mc.from, mc.to)) {
- mc.precharge -= HPAGE_PMD_NR;
- mc.moved_charge += HPAGE_PMD_NR;
- }
- put_page(page);
- }
- spin_unlock(ptl);
- return 0;
- }
- if (pmd_trans_unstable(pmd))
- return 0;
- retry:
- pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
- for (; addr != end; addr += PAGE_SIZE) {
- pte_t ptent = *(pte++);
- bool device = false;
- swp_entry_t ent;
- if (!mc.precharge)
- break;
- switch (get_mctgt_type(vma, addr, ptent, &target)) {
- case MC_TARGET_DEVICE:
- device = true;
- fallthrough;
- case MC_TARGET_PAGE:
- page = target.page;
- /*
- * We can have a part of the split pmd here. Moving it
- * can be done but it would be too convoluted so simply
- * ignore such a partial THP and keep it in original
- * memcg. There should be somebody mapping the head.
- */
- if (PageTransCompound(page))
- goto put;
- if (!device && isolate_lru_page(page))
- goto put;
- if (!mem_cgroup_move_account(page, false,
- mc.from, mc.to)) {
- mc.precharge--;
- /* we uncharge from mc.from later. */
- mc.moved_charge++;
- }
- if (!device)
- putback_lru_page(page);
- put: /* get_mctgt_type() gets the page */
- put_page(page);
- break;
- case MC_TARGET_SWAP:
- ent = target.ent;
- if (!mem_cgroup_move_swap_account(ent, mc.from, mc.to)) {
- mc.precharge--;
- mem_cgroup_id_get_many(mc.to, 1);
- /* we fixup other refcnts and charges later. */
- mc.moved_swap++;
- }
- break;
- default:
- break;
- }
- }
- pte_unmap_unlock(pte - 1, ptl);
- cond_resched();
- if (addr != end) {
- /*
- * We have consumed all precharges we got in can_attach().
- * We try charge one by one, but don't do any additional
- * charges to mc.to if we have failed in charge once in attach()
- * phase.
- */
- ret = mem_cgroup_do_precharge(1);
- if (!ret)
- goto retry;
- }
- return ret;
- }
- static const struct mm_walk_ops charge_walk_ops = {
- .pmd_entry = mem_cgroup_move_charge_pte_range,
- .walk_lock = PGWALK_RDLOCK,
- };
- static void mem_cgroup_move_charge(void)
- {
- lru_add_drain_all();
- /*
- * Signal lock_page_memcg() to take the memcg's move_lock
- * while we're moving its pages to another memcg. Then wait
- * for already started RCU-only updates to finish.
- */
- atomic_inc(&mc.from->moving_account);
- synchronize_rcu();
- retry:
- if (unlikely(!mmap_read_trylock(mc.mm))) {
- /*
- * Someone who are holding the mmap_lock might be waiting in
- * waitq. So we cancel all extra charges, wake up all waiters,
- * and retry. Because we cancel precharges, we might not be able
- * to move enough charges, but moving charge is a best-effort
- * feature anyway, so it wouldn't be a big problem.
- */
- __mem_cgroup_clear_mc();
- cond_resched();
- goto retry;
- }
- /*
- * When we have consumed all precharges and failed in doing
- * additional charge, the page walk just aborts.
- */
- walk_page_range(mc.mm, 0, ULONG_MAX, &charge_walk_ops, NULL);
- mmap_read_unlock(mc.mm);
- atomic_dec(&mc.from->moving_account);
- }
- static void mem_cgroup_move_task(void)
- {
- if (mc.to) {
- mem_cgroup_move_charge();
- mem_cgroup_clear_mc();
- }
- }
- #else /* !CONFIG_MMU */
- static int mem_cgroup_can_attach(struct cgroup_taskset *tset)
- {
- return 0;
- }
- static void mem_cgroup_cancel_attach(struct cgroup_taskset *tset)
- {
- }
- static void mem_cgroup_move_task(void)
- {
- }
- #endif
- #ifdef CONFIG_LRU_GEN
- static void mem_cgroup_attach(struct cgroup_taskset *tset)
- {
- struct task_struct *task;
- struct cgroup_subsys_state *css;
- /* find the first leader if there is any */
- cgroup_taskset_for_each_leader(task, css, tset)
- break;
- if (!task)
- return;
- task_lock(task);
- if (task->mm && READ_ONCE(task->mm->owner) == task)
- lru_gen_migrate_mm(task->mm);
- task_unlock(task);
- }
- #else
- static void mem_cgroup_attach(struct cgroup_taskset *tset)
- {
- }
- #endif /* CONFIG_LRU_GEN */
- static int seq_puts_memcg_tunable(struct seq_file *m, unsigned long value)
- {
- if (value == PAGE_COUNTER_MAX)
- seq_puts(m, "max\n");
- else
- seq_printf(m, "%llu\n", (u64)value * PAGE_SIZE);
- return 0;
- }
- static u64 memory_current_read(struct cgroup_subsys_state *css,
- struct cftype *cft)
- {
- struct mem_cgroup *memcg = mem_cgroup_from_css(css);
- return (u64)page_counter_read(&memcg->memory) * PAGE_SIZE;
- }
- static u64 memory_peak_read(struct cgroup_subsys_state *css,
- struct cftype *cft)
- {
- struct mem_cgroup *memcg = mem_cgroup_from_css(css);
- return (u64)memcg->memory.watermark * PAGE_SIZE;
- }
- static int memory_min_show(struct seq_file *m, void *v)
- {
- return seq_puts_memcg_tunable(m,
- READ_ONCE(mem_cgroup_from_seq(m)->memory.min));
- }
- static ssize_t memory_min_write(struct kernfs_open_file *of,
- char *buf, size_t nbytes, loff_t off)
- {
- struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
- unsigned long min;
- int err;
- buf = strstrip(buf);
- err = page_counter_memparse(buf, "max", &min);
- if (err)
- return err;
- page_counter_set_min(&memcg->memory, min);
- return nbytes;
- }
- static int memory_low_show(struct seq_file *m, void *v)
- {
- return seq_puts_memcg_tunable(m,
- READ_ONCE(mem_cgroup_from_seq(m)->memory.low));
- }
- static ssize_t memory_low_write(struct kernfs_open_file *of,
- char *buf, size_t nbytes, loff_t off)
- {
- struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
- unsigned long low;
- int err;
- buf = strstrip(buf);
- err = page_counter_memparse(buf, "max", &low);
- if (err)
- return err;
- page_counter_set_low(&memcg->memory, low);
- return nbytes;
- }
- static int memory_high_show(struct seq_file *m, void *v)
- {
- return seq_puts_memcg_tunable(m,
- READ_ONCE(mem_cgroup_from_seq(m)->memory.high));
- }
- static ssize_t memory_high_write(struct kernfs_open_file *of,
- char *buf, size_t nbytes, loff_t off)
- {
- struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
- unsigned int nr_retries = MAX_RECLAIM_RETRIES;
- bool drained = false;
- unsigned long high;
- int err;
- buf = strstrip(buf);
- err = page_counter_memparse(buf, "max", &high);
- if (err)
- return err;
- page_counter_set_high(&memcg->memory, high);
- for (;;) {
- unsigned long nr_pages = page_counter_read(&memcg->memory);
- unsigned long reclaimed;
- if (nr_pages <= high)
- break;
- if (signal_pending(current))
- break;
- if (!drained) {
- drain_all_stock(memcg);
- drained = true;
- continue;
- }
- reclaimed = try_to_free_mem_cgroup_pages(memcg, nr_pages - high,
- GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP);
- if (!reclaimed && !nr_retries--)
- break;
- }
- memcg_wb_domain_size_changed(memcg);
- return nbytes;
- }
- static int memory_max_show(struct seq_file *m, void *v)
- {
- return seq_puts_memcg_tunable(m,
- READ_ONCE(mem_cgroup_from_seq(m)->memory.max));
- }
- static ssize_t memory_max_write(struct kernfs_open_file *of,
- char *buf, size_t nbytes, loff_t off)
- {
- struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
- unsigned int nr_reclaims = MAX_RECLAIM_RETRIES;
- bool drained = false;
- unsigned long max;
- int err;
- buf = strstrip(buf);
- err = page_counter_memparse(buf, "max", &max);
- if (err)
- return err;
- xchg(&memcg->memory.max, max);
- for (;;) {
- unsigned long nr_pages = page_counter_read(&memcg->memory);
- if (nr_pages <= max)
- break;
- if (signal_pending(current))
- break;
- if (!drained) {
- drain_all_stock(memcg);
- drained = true;
- continue;
- }
- if (nr_reclaims) {
- if (!try_to_free_mem_cgroup_pages(memcg, nr_pages - max,
- GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP))
- nr_reclaims--;
- continue;
- }
- memcg_memory_event(memcg, MEMCG_OOM);
- if (!mem_cgroup_out_of_memory(memcg, GFP_KERNEL, 0))
- break;
- }
- memcg_wb_domain_size_changed(memcg);
- return nbytes;
- }
- static void __memory_events_show(struct seq_file *m, atomic_long_t *events)
- {
- seq_printf(m, "low %lu\n", atomic_long_read(&events[MEMCG_LOW]));
- seq_printf(m, "high %lu\n", atomic_long_read(&events[MEMCG_HIGH]));
- seq_printf(m, "max %lu\n", atomic_long_read(&events[MEMCG_MAX]));
- seq_printf(m, "oom %lu\n", atomic_long_read(&events[MEMCG_OOM]));
- seq_printf(m, "oom_kill %lu\n",
- atomic_long_read(&events[MEMCG_OOM_KILL]));
- seq_printf(m, "oom_group_kill %lu\n",
- atomic_long_read(&events[MEMCG_OOM_GROUP_KILL]));
- }
- static int memory_events_show(struct seq_file *m, void *v)
- {
- struct mem_cgroup *memcg = mem_cgroup_from_seq(m);
- __memory_events_show(m, memcg->memory_events);
- return 0;
- }
- static int memory_events_local_show(struct seq_file *m, void *v)
- {
- struct mem_cgroup *memcg = mem_cgroup_from_seq(m);
- __memory_events_show(m, memcg->memory_events_local);
- return 0;
- }
- static int memory_stat_show(struct seq_file *m, void *v)
- {
- struct mem_cgroup *memcg = mem_cgroup_from_seq(m);
- char *buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
- if (!buf)
- return -ENOMEM;
- memory_stat_format(memcg, buf, PAGE_SIZE);
- seq_puts(m, buf);
- kfree(buf);
- return 0;
- }
- #ifdef CONFIG_NUMA
- static inline unsigned long lruvec_page_state_output(struct lruvec *lruvec,
- int item)
- {
- return lruvec_page_state(lruvec, item) * memcg_page_state_unit(item);
- }
- static int memory_numa_stat_show(struct seq_file *m, void *v)
- {
- int i;
- struct mem_cgroup *memcg = mem_cgroup_from_seq(m);
- mem_cgroup_flush_stats();
- for (i = 0; i < ARRAY_SIZE(memory_stats); i++) {
- int nid;
- if (memory_stats[i].idx >= NR_VM_NODE_STAT_ITEMS)
- continue;
- seq_printf(m, "%s", memory_stats[i].name);
- for_each_node_state(nid, N_MEMORY) {
- u64 size;
- struct lruvec *lruvec;
- lruvec = mem_cgroup_lruvec(memcg, NODE_DATA(nid));
- size = lruvec_page_state_output(lruvec,
- memory_stats[i].idx);
- seq_printf(m, " N%d=%llu", nid, size);
- }
- seq_putc(m, '\n');
- }
- return 0;
- }
- #endif
- static int memory_oom_group_show(struct seq_file *m, void *v)
- {
- struct mem_cgroup *memcg = mem_cgroup_from_seq(m);
- seq_printf(m, "%d\n", memcg->oom_group);
- return 0;
- }
- static ssize_t memory_oom_group_write(struct kernfs_open_file *of,
- char *buf, size_t nbytes, loff_t off)
- {
- struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
- int ret, oom_group;
- buf = strstrip(buf);
- if (!buf)
- return -EINVAL;
- ret = kstrtoint(buf, 0, &oom_group);
- if (ret)
- return ret;
- if (oom_group != 0 && oom_group != 1)
- return -EINVAL;
- memcg->oom_group = oom_group;
- return nbytes;
- }
- static ssize_t memory_reclaim(struct kernfs_open_file *of, char *buf,
- size_t nbytes, loff_t off)
- {
- struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
- unsigned int nr_retries = MAX_RECLAIM_RETRIES;
- unsigned long nr_to_reclaim, nr_reclaimed = 0;
- unsigned int reclaim_options;
- int err;
- buf = strstrip(buf);
- err = page_counter_memparse(buf, "", &nr_to_reclaim);
- if (err)
- return err;
- reclaim_options = MEMCG_RECLAIM_MAY_SWAP | MEMCG_RECLAIM_PROACTIVE;
- while (nr_reclaimed < nr_to_reclaim) {
- unsigned long reclaimed;
- if (signal_pending(current))
- return -EINTR;
- /*
- * This is the final attempt, drain percpu lru caches in the
- * hope of introducing more evictable pages for
- * try_to_free_mem_cgroup_pages().
- */
- if (!nr_retries)
- lru_add_drain_all();
- reclaimed = try_to_free_mem_cgroup_pages(memcg,
- nr_to_reclaim - nr_reclaimed,
- GFP_KERNEL, reclaim_options);
- if (!reclaimed && !nr_retries--)
- return -EAGAIN;
- nr_reclaimed += reclaimed;
- }
- return nbytes;
- }
- static struct cftype memory_files[] = {
- {
- .name = "current",
- .flags = CFTYPE_NOT_ON_ROOT,
- .read_u64 = memory_current_read,
- },
- {
- .name = "peak",
- .flags = CFTYPE_NOT_ON_ROOT,
- .read_u64 = memory_peak_read,
- },
- {
- .name = "min",
- .flags = CFTYPE_NOT_ON_ROOT,
- .seq_show = memory_min_show,
- .write = memory_min_write,
- },
- {
- .name = "low",
- .flags = CFTYPE_NOT_ON_ROOT,
- .seq_show = memory_low_show,
- .write = memory_low_write,
- },
- {
- .name = "high",
- .flags = CFTYPE_NOT_ON_ROOT,
- .seq_show = memory_high_show,
- .write = memory_high_write,
- },
- {
- .name = "max",
- .flags = CFTYPE_NOT_ON_ROOT,
- .seq_show = memory_max_show,
- .write = memory_max_write,
- },
- {
- .name = "events",
- .flags = CFTYPE_NOT_ON_ROOT,
- .file_offset = offsetof(struct mem_cgroup, events_file),
- .seq_show = memory_events_show,
- },
- {
- .name = "events.local",
- .flags = CFTYPE_NOT_ON_ROOT,
- .file_offset = offsetof(struct mem_cgroup, events_local_file),
- .seq_show = memory_events_local_show,
- },
- {
- .name = "stat",
- .seq_show = memory_stat_show,
- },
- #ifdef CONFIG_NUMA
- {
- .name = "numa_stat",
- .seq_show = memory_numa_stat_show,
- },
- #endif
- {
- .name = "oom.group",
- .flags = CFTYPE_NOT_ON_ROOT | CFTYPE_NS_DELEGATABLE,
- .seq_show = memory_oom_group_show,
- .write = memory_oom_group_write,
- },
- {
- .name = "reclaim",
- .flags = CFTYPE_NS_DELEGATABLE,
- .write = memory_reclaim,
- },
- { } /* terminate */
- };
- struct cgroup_subsys memory_cgrp_subsys = {
- .css_alloc = mem_cgroup_css_alloc,
- .css_online = mem_cgroup_css_online,
- .css_offline = mem_cgroup_css_offline,
- .css_released = mem_cgroup_css_released,
- .css_free = mem_cgroup_css_free,
- .css_reset = mem_cgroup_css_reset,
- .css_rstat_flush = mem_cgroup_css_rstat_flush,
- .can_attach = mem_cgroup_can_attach,
- .attach = mem_cgroup_attach,
- .cancel_attach = mem_cgroup_cancel_attach,
- .post_attach = mem_cgroup_move_task,
- .dfl_cftypes = memory_files,
- .legacy_cftypes = mem_cgroup_legacy_files,
- .early_init = 0,
- };
- /*
- * This function calculates an individual cgroup's effective
- * protection which is derived from its own memory.min/low, its
- * parent's and siblings' settings, as well as the actual memory
- * distribution in the tree.
- *
- * The following rules apply to the effective protection values:
- *
- * 1. At the first level of reclaim, effective protection is equal to
- * the declared protection in memory.min and memory.low.
- *
- * 2. To enable safe delegation of the protection configuration, at
- * subsequent levels the effective protection is capped to the
- * parent's effective protection.
- *
- * 3. To make complex and dynamic subtrees easier to configure, the
- * user is allowed to overcommit the declared protection at a given
- * level. If that is the case, the parent's effective protection is
- * distributed to the children in proportion to how much protection
- * they have declared and how much of it they are utilizing.
- *
- * This makes distribution proportional, but also work-conserving:
- * if one cgroup claims much more protection than it uses memory,
- * the unused remainder is available to its siblings.
- *
- * 4. Conversely, when the declared protection is undercommitted at a
- * given level, the distribution of the larger parental protection
- * budget is NOT proportional. A cgroup's protection from a sibling
- * is capped to its own memory.min/low setting.
- *
- * 5. However, to allow protecting recursive subtrees from each other
- * without having to declare each individual cgroup's fixed share
- * of the ancestor's claim to protection, any unutilized -
- * "floating" - protection from up the tree is distributed in
- * proportion to each cgroup's *usage*. This makes the protection
- * neutral wrt sibling cgroups and lets them compete freely over
- * the shared parental protection budget, but it protects the
- * subtree as a whole from neighboring subtrees.
- *
- * Note that 4. and 5. are not in conflict: 4. is about protecting
- * against immediate siblings whereas 5. is about protecting against
- * neighboring subtrees.
- */
- static unsigned long effective_protection(unsigned long usage,
- unsigned long parent_usage,
- unsigned long setting,
- unsigned long parent_effective,
- unsigned long siblings_protected)
- {
- unsigned long protected;
- unsigned long ep;
- protected = min(usage, setting);
- /*
- * If all cgroups at this level combined claim and use more
- * protection then what the parent affords them, distribute
- * shares in proportion to utilization.
- *
- * We are using actual utilization rather than the statically
- * claimed protection in order to be work-conserving: claimed
- * but unused protection is available to siblings that would
- * otherwise get a smaller chunk than what they claimed.
- */
- if (siblings_protected > parent_effective)
- return protected * parent_effective / siblings_protected;
- /*
- * Ok, utilized protection of all children is within what the
- * parent affords them, so we know whatever this child claims
- * and utilizes is effectively protected.
- *
- * If there is unprotected usage beyond this value, reclaim
- * will apply pressure in proportion to that amount.
- *
- * If there is unutilized protection, the cgroup will be fully
- * shielded from reclaim, but we do return a smaller value for
- * protection than what the group could enjoy in theory. This
- * is okay. With the overcommit distribution above, effective
- * protection is always dependent on how memory is actually
- * consumed among the siblings anyway.
- */
- ep = protected;
- /*
- * If the children aren't claiming (all of) the protection
- * afforded to them by the parent, distribute the remainder in
- * proportion to the (unprotected) memory of each cgroup. That
- * way, cgroups that aren't explicitly prioritized wrt each
- * other compete freely over the allowance, but they are
- * collectively protected from neighboring trees.
- *
- * We're using unprotected memory for the weight so that if
- * some cgroups DO claim explicit protection, we don't protect
- * the same bytes twice.
- *
- * Check both usage and parent_usage against the respective
- * protected values. One should imply the other, but they
- * aren't read atomically - make sure the division is sane.
- */
- if (!(cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_RECURSIVE_PROT))
- return ep;
- if (parent_effective > siblings_protected &&
- parent_usage > siblings_protected &&
- usage > protected) {
- unsigned long unclaimed;
- unclaimed = parent_effective - siblings_protected;
- unclaimed *= usage - protected;
- unclaimed /= parent_usage - siblings_protected;
- ep += unclaimed;
- }
- return ep;
- }
- /**
- * mem_cgroup_calculate_protection - check if memory consumption is in the normal range
- * @root: the top ancestor of the sub-tree being checked
- * @memcg: the memory cgroup to check
- *
- * WARNING: This function is not stateless! It can only be used as part
- * of a top-down tree iteration, not for isolated queries.
- */
- void mem_cgroup_calculate_protection(struct mem_cgroup *root,
- struct mem_cgroup *memcg)
- {
- unsigned long usage, parent_usage;
- struct mem_cgroup *parent;
- if (mem_cgroup_disabled())
- return;
- if (!root)
- root = root_mem_cgroup;
- /*
- * Effective values of the reclaim targets are ignored so they
- * can be stale. Have a look at mem_cgroup_protection for more
- * details.
- * TODO: calculation should be more robust so that we do not need
- * that special casing.
- */
- if (memcg == root)
- return;
- usage = page_counter_read(&memcg->memory);
- if (!usage)
- return;
- parent = parent_mem_cgroup(memcg);
- if (parent == root) {
- memcg->memory.emin = READ_ONCE(memcg->memory.min);
- memcg->memory.elow = READ_ONCE(memcg->memory.low);
- return;
- }
- parent_usage = page_counter_read(&parent->memory);
- WRITE_ONCE(memcg->memory.emin, effective_protection(usage, parent_usage,
- READ_ONCE(memcg->memory.min),
- READ_ONCE(parent->memory.emin),
- atomic_long_read(&parent->memory.children_min_usage)));
- WRITE_ONCE(memcg->memory.elow, effective_protection(usage, parent_usage,
- READ_ONCE(memcg->memory.low),
- READ_ONCE(parent->memory.elow),
- atomic_long_read(&parent->memory.children_low_usage)));
- }
- static int charge_memcg(struct folio *folio, struct mem_cgroup *memcg,
- gfp_t gfp)
- {
- long nr_pages = folio_nr_pages(folio);
- int ret;
- ret = try_charge(memcg, gfp, nr_pages);
- if (ret)
- goto out;
- css_get(&memcg->css);
- commit_charge(folio, memcg);
- local_irq_disable();
- mem_cgroup_charge_statistics(memcg, nr_pages);
- memcg_check_events(memcg, folio_nid(folio));
- local_irq_enable();
- out:
- return ret;
- }
- int __mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, gfp_t gfp)
- {
- struct mem_cgroup *memcg;
- int ret;
- memcg = get_mem_cgroup_from_mm(mm);
- ret = charge_memcg(folio, memcg, gfp);
- css_put(&memcg->css);
- return ret;
- }
- /**
- * mem_cgroup_swapin_charge_folio - Charge a newly allocated folio for swapin.
- * @folio: folio to charge.
- * @mm: mm context of the victim
- * @gfp: reclaim mode
- * @entry: swap entry for which the folio is allocated
- *
- * This function charges a folio allocated for swapin. Please call this before
- * adding the folio to the swapcache.
- *
- * Returns 0 on success. Otherwise, an error code is returned.
- */
- int mem_cgroup_swapin_charge_folio(struct folio *folio, struct mm_struct *mm,
- gfp_t gfp, swp_entry_t entry)
- {
- struct mem_cgroup *memcg;
- unsigned short id;
- int ret;
- if (mem_cgroup_disabled())
- return 0;
- id = lookup_swap_cgroup_id(entry);
- rcu_read_lock();
- memcg = mem_cgroup_from_id(id);
- if (!memcg || !css_tryget_online(&memcg->css))
- memcg = get_mem_cgroup_from_mm(mm);
- rcu_read_unlock();
- ret = charge_memcg(folio, memcg, gfp);
- css_put(&memcg->css);
- return ret;
- }
- /*
- * mem_cgroup_swapin_uncharge_swap - uncharge swap slot
- * @entry: swap entry for which the page is charged
- *
- * Call this function after successfully adding the charged page to swapcache.
- *
- * Note: This function assumes the page for which swap slot is being uncharged
- * is order 0 page.
- */
- void mem_cgroup_swapin_uncharge_swap(swp_entry_t entry)
- {
- /*
- * Cgroup1's unified memory+swap counter has been charged with the
- * new swapcache page, finish the transfer by uncharging the swap
- * slot. The swap slot would also get uncharged when it dies, but
- * it can stick around indefinitely and we'd count the page twice
- * the entire time.
- *
- * Cgroup2 has separate resource counters for memory and swap,
- * so this is a non-issue here. Memory and swap charge lifetimes
- * correspond 1:1 to page and swap slot lifetimes: we charge the
- * page to memory here, and uncharge swap when the slot is freed.
- */
- if (!mem_cgroup_disabled() && do_memsw_account()) {
- /*
- * The swap entry might not get freed for a long time,
- * let's not wait for it. The page already received a
- * memory+swap charge, drop the swap entry duplicate.
- */
- mem_cgroup_uncharge_swap(entry, 1);
- }
- }
- struct uncharge_gather {
- struct mem_cgroup *memcg;
- unsigned long nr_memory;
- unsigned long pgpgout;
- unsigned long nr_kmem;
- int nid;
- };
- static inline void uncharge_gather_clear(struct uncharge_gather *ug)
- {
- memset(ug, 0, sizeof(*ug));
- }
- static void uncharge_batch(const struct uncharge_gather *ug)
- {
- unsigned long flags;
- if (ug->nr_memory) {
- page_counter_uncharge(&ug->memcg->memory, ug->nr_memory);
- if (do_memsw_account())
- page_counter_uncharge(&ug->memcg->memsw, ug->nr_memory);
- if (ug->nr_kmem)
- memcg_account_kmem(ug->memcg, -ug->nr_kmem);
- memcg_oom_recover(ug->memcg);
- }
- local_irq_save(flags);
- __count_memcg_events(ug->memcg, PGPGOUT, ug->pgpgout);
- __this_cpu_add(ug->memcg->vmstats_percpu->nr_page_events, ug->nr_memory);
- memcg_check_events(ug->memcg, ug->nid);
- local_irq_restore(flags);
- /* drop reference from uncharge_folio */
- css_put(&ug->memcg->css);
- }
- static void uncharge_folio(struct folio *folio, struct uncharge_gather *ug)
- {
- long nr_pages;
- struct mem_cgroup *memcg;
- struct obj_cgroup *objcg;
- VM_BUG_ON_FOLIO(folio_test_lru(folio), folio);
- /*
- * Nobody should be changing or seriously looking at
- * folio memcg or objcg at this point, we have fully
- * exclusive access to the folio.
- */
- if (folio_memcg_kmem(folio)) {
- objcg = __folio_objcg(folio);
- /*
- * This get matches the put at the end of the function and
- * kmem pages do not hold memcg references anymore.
- */
- memcg = get_mem_cgroup_from_objcg(objcg);
- } else {
- memcg = __folio_memcg(folio);
- }
- if (!memcg)
- return;
- if (ug->memcg != memcg) {
- if (ug->memcg) {
- uncharge_batch(ug);
- uncharge_gather_clear(ug);
- }
- ug->memcg = memcg;
- ug->nid = folio_nid(folio);
- /* pairs with css_put in uncharge_batch */
- css_get(&memcg->css);
- }
- nr_pages = folio_nr_pages(folio);
- if (folio_memcg_kmem(folio)) {
- ug->nr_memory += nr_pages;
- ug->nr_kmem += nr_pages;
- folio->memcg_data = 0;
- obj_cgroup_put(objcg);
- } else {
- /* LRU pages aren't accounted at the root level */
- if (!mem_cgroup_is_root(memcg))
- ug->nr_memory += nr_pages;
- ug->pgpgout++;
- folio->memcg_data = 0;
- }
- css_put(&memcg->css);
- }
- void __mem_cgroup_uncharge(struct folio *folio)
- {
- struct uncharge_gather ug;
- /* Don't touch folio->lru of any random page, pre-check: */
- if (!folio_memcg(folio))
- return;
- uncharge_gather_clear(&ug);
- uncharge_folio(folio, &ug);
- uncharge_batch(&ug);
- }
- /**
- * __mem_cgroup_uncharge_list - uncharge a list of page
- * @page_list: list of pages to uncharge
- *
- * Uncharge a list of pages previously charged with
- * __mem_cgroup_charge().
- */
- void __mem_cgroup_uncharge_list(struct list_head *page_list)
- {
- struct uncharge_gather ug;
- struct folio *folio;
- uncharge_gather_clear(&ug);
- list_for_each_entry(folio, page_list, lru)
- uncharge_folio(folio, &ug);
- if (ug.memcg)
- uncharge_batch(&ug);
- }
- /**
- * mem_cgroup_migrate - Charge a folio's replacement.
- * @old: Currently circulating folio.
- * @new: Replacement folio.
- *
- * Charge @new as a replacement folio for @old. @old will
- * be uncharged upon free.
- *
- * Both folios must be locked, @new->mapping must be set up.
- */
- void mem_cgroup_migrate(struct folio *old, struct folio *new)
- {
- struct mem_cgroup *memcg;
- long nr_pages = folio_nr_pages(new);
- unsigned long flags;
- VM_BUG_ON_FOLIO(!folio_test_locked(old), old);
- VM_BUG_ON_FOLIO(!folio_test_locked(new), new);
- VM_BUG_ON_FOLIO(folio_test_anon(old) != folio_test_anon(new), new);
- VM_BUG_ON_FOLIO(folio_nr_pages(old) != nr_pages, new);
- if (mem_cgroup_disabled())
- return;
- /* Page cache replacement: new folio already charged? */
- if (folio_memcg(new))
- return;
- memcg = folio_memcg(old);
- VM_WARN_ON_ONCE_FOLIO(!memcg, old);
- if (!memcg)
- return;
- /* Force-charge the new page. The old one will be freed soon */
- if (!mem_cgroup_is_root(memcg)) {
- page_counter_charge(&memcg->memory, nr_pages);
- if (do_memsw_account())
- page_counter_charge(&memcg->memsw, nr_pages);
- }
- css_get(&memcg->css);
- commit_charge(new, memcg);
- local_irq_save(flags);
- mem_cgroup_charge_statistics(memcg, nr_pages);
- memcg_check_events(memcg, folio_nid(new));
- local_irq_restore(flags);
- }
- DEFINE_STATIC_KEY_FALSE(memcg_sockets_enabled_key);
- EXPORT_SYMBOL(memcg_sockets_enabled_key);
- void mem_cgroup_sk_alloc(struct sock *sk)
- {
- struct mem_cgroup *memcg;
- if (!mem_cgroup_sockets_enabled)
- return;
- /* Do not associate the sock with unrelated interrupted task's memcg. */
- if (!in_task())
- return;
- rcu_read_lock();
- memcg = mem_cgroup_from_task(current);
- if (memcg == root_mem_cgroup)
- goto out;
- if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && !memcg->tcpmem_active)
- goto out;
- if (css_tryget(&memcg->css))
- sk->sk_memcg = memcg;
- out:
- rcu_read_unlock();
- }
- void mem_cgroup_sk_free(struct sock *sk)
- {
- if (sk->sk_memcg)
- css_put(&sk->sk_memcg->css);
- }
- /**
- * mem_cgroup_charge_skmem - charge socket memory
- * @memcg: memcg to charge
- * @nr_pages: number of pages to charge
- * @gfp_mask: reclaim mode
- *
- * Charges @nr_pages to @memcg. Returns %true if the charge fit within
- * @memcg's configured limit, %false if it doesn't.
- */
- bool mem_cgroup_charge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages,
- gfp_t gfp_mask)
- {
- if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) {
- struct page_counter *fail;
- if (page_counter_try_charge(&memcg->tcpmem, nr_pages, &fail)) {
- memcg->tcpmem_pressure = 0;
- return true;
- }
- memcg->tcpmem_pressure = 1;
- if (gfp_mask & __GFP_NOFAIL) {
- page_counter_charge(&memcg->tcpmem, nr_pages);
- return true;
- }
- return false;
- }
- if (try_charge(memcg, gfp_mask, nr_pages) == 0) {
- mod_memcg_state(memcg, MEMCG_SOCK, nr_pages);
- return true;
- }
- return false;
- }
- /**
- * mem_cgroup_uncharge_skmem - uncharge socket memory
- * @memcg: memcg to uncharge
- * @nr_pages: number of pages to uncharge
- */
- void mem_cgroup_uncharge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages)
- {
- if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) {
- page_counter_uncharge(&memcg->tcpmem, nr_pages);
- return;
- }
- mod_memcg_state(memcg, MEMCG_SOCK, -nr_pages);
- refill_stock(memcg, nr_pages);
- }
- static int __init cgroup_memory(char *s)
- {
- char *token;
- while ((token = strsep(&s, ",")) != NULL) {
- if (!*token)
- continue;
- if (!strcmp(token, "nosocket"))
- cgroup_memory_nosocket = true;
- if (!strcmp(token, "nokmem"))
- cgroup_memory_nokmem = true;
- }
- return 1;
- }
- __setup("cgroup.memory=", cgroup_memory);
- /*
- * subsys_initcall() for memory controller.
- *
- * Some parts like memcg_hotplug_cpu_dead() have to be initialized from this
- * context because of lock dependencies (cgroup_lock -> cpu hotplug) but
- * basically everything that doesn't depend on a specific mem_cgroup structure
- * should be initialized from here.
- */
- static int __init mem_cgroup_init(void)
- {
- int cpu, node;
- /*
- * Currently s32 type (can refer to struct batched_lruvec_stat) is
- * used for per-memcg-per-cpu caching of per-node statistics. In order
- * to work fine, we should make sure that the overfill threshold can't
- * exceed S32_MAX / PAGE_SIZE.
- */
- BUILD_BUG_ON(MEMCG_CHARGE_BATCH > S32_MAX / PAGE_SIZE);
- cpuhp_setup_state_nocalls(CPUHP_MM_MEMCQ_DEAD, "mm/memctrl:dead", NULL,
- memcg_hotplug_cpu_dead);
- for_each_possible_cpu(cpu)
- INIT_WORK(&per_cpu_ptr(&memcg_stock, cpu)->work,
- drain_local_stock);
- for_each_node(node) {
- struct mem_cgroup_tree_per_node *rtpn;
- rtpn = kzalloc_node(sizeof(*rtpn), GFP_KERNEL,
- node_online(node) ? node : NUMA_NO_NODE);
- rtpn->rb_root = RB_ROOT;
- rtpn->rb_rightmost = NULL;
- spin_lock_init(&rtpn->lock);
- soft_limit_tree.rb_tree_per_node[node] = rtpn;
- }
- return 0;
- }
- subsys_initcall(mem_cgroup_init);
- #ifdef CONFIG_SWAP
- static struct mem_cgroup *mem_cgroup_id_get_online(struct mem_cgroup *memcg)
- {
- while (!refcount_inc_not_zero(&memcg->id.ref)) {
- /*
- * The root cgroup cannot be destroyed, so it's refcount must
- * always be >= 1.
- */
- if (WARN_ON_ONCE(memcg == root_mem_cgroup)) {
- VM_BUG_ON(1);
- break;
- }
- memcg = parent_mem_cgroup(memcg);
- if (!memcg)
- memcg = root_mem_cgroup;
- }
- return memcg;
- }
- /**
- * mem_cgroup_swapout - transfer a memsw charge to swap
- * @folio: folio whose memsw charge to transfer
- * @entry: swap entry to move the charge to
- *
- * Transfer the memsw charge of @folio to @entry.
- */
- void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry)
- {
- struct mem_cgroup *memcg, *swap_memcg;
- unsigned int nr_entries;
- unsigned short oldid;
- VM_BUG_ON_FOLIO(folio_test_lru(folio), folio);
- VM_BUG_ON_FOLIO(folio_ref_count(folio), folio);
- if (mem_cgroup_disabled())
- return;
- if (!do_memsw_account())
- return;
- memcg = folio_memcg(folio);
- VM_WARN_ON_ONCE_FOLIO(!memcg, folio);
- if (!memcg)
- return;
- /*
- * In case the memcg owning these pages has been offlined and doesn't
- * have an ID allocated to it anymore, charge the closest online
- * ancestor for the swap instead and transfer the memory+swap charge.
- */
- swap_memcg = mem_cgroup_id_get_online(memcg);
- nr_entries = folio_nr_pages(folio);
- /* Get references for the tail pages, too */
- if (nr_entries > 1)
- mem_cgroup_id_get_many(swap_memcg, nr_entries - 1);
- oldid = swap_cgroup_record(entry, mem_cgroup_id(swap_memcg),
- nr_entries);
- VM_BUG_ON_FOLIO(oldid, folio);
- mod_memcg_state(swap_memcg, MEMCG_SWAP, nr_entries);
- folio->memcg_data = 0;
- if (!mem_cgroup_is_root(memcg))
- page_counter_uncharge(&memcg->memory, nr_entries);
- if (memcg != swap_memcg) {
- if (!mem_cgroup_is_root(swap_memcg))
- page_counter_charge(&swap_memcg->memsw, nr_entries);
- page_counter_uncharge(&memcg->memsw, nr_entries);
- }
- /*
- * Interrupts should be disabled here because the caller holds the
- * i_pages lock which is taken with interrupts-off. It is
- * important here to have the interrupts disabled because it is the
- * only synchronisation we have for updating the per-CPU variables.
- */
- memcg_stats_lock();
- mem_cgroup_charge_statistics(memcg, -nr_entries);
- memcg_stats_unlock();
- memcg_check_events(memcg, folio_nid(folio));
- css_put(&memcg->css);
- }
- /**
- * __mem_cgroup_try_charge_swap - try charging swap space for a folio
- * @folio: folio being added to swap
- * @entry: swap entry to charge
- *
- * Try to charge @folio's memcg for the swap space at @entry.
- *
- * Returns 0 on success, -ENOMEM on failure.
- */
- int __mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry)
- {
- unsigned int nr_pages = folio_nr_pages(folio);
- struct page_counter *counter;
- struct mem_cgroup *memcg;
- unsigned short oldid;
- if (do_memsw_account())
- return 0;
- memcg = folio_memcg(folio);
- VM_WARN_ON_ONCE_FOLIO(!memcg, folio);
- if (!memcg)
- return 0;
- if (!entry.val) {
- memcg_memory_event(memcg, MEMCG_SWAP_FAIL);
- return 0;
- }
- memcg = mem_cgroup_id_get_online(memcg);
- if (!mem_cgroup_is_root(memcg) &&
- !page_counter_try_charge(&memcg->swap, nr_pages, &counter)) {
- memcg_memory_event(memcg, MEMCG_SWAP_MAX);
- memcg_memory_event(memcg, MEMCG_SWAP_FAIL);
- mem_cgroup_id_put(memcg);
- return -ENOMEM;
- }
- /* Get references for the tail pages, too */
- if (nr_pages > 1)
- mem_cgroup_id_get_many(memcg, nr_pages - 1);
- oldid = swap_cgroup_record(entry, mem_cgroup_id(memcg), nr_pages);
- VM_BUG_ON_FOLIO(oldid, folio);
- mod_memcg_state(memcg, MEMCG_SWAP, nr_pages);
- return 0;
- }
- /**
- * __mem_cgroup_uncharge_swap - uncharge swap space
- * @entry: swap entry to uncharge
- * @nr_pages: the amount of swap space to uncharge
- */
- void __mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages)
- {
- struct mem_cgroup *memcg;
- unsigned short id;
- if (mem_cgroup_disabled())
- return;
- id = swap_cgroup_record(entry, 0, nr_pages);
- rcu_read_lock();
- memcg = mem_cgroup_from_id(id);
- if (memcg) {
- if (!mem_cgroup_is_root(memcg)) {
- if (do_memsw_account())
- page_counter_uncharge(&memcg->memsw, nr_pages);
- else
- page_counter_uncharge(&memcg->swap, nr_pages);
- }
- mod_memcg_state(memcg, MEMCG_SWAP, -nr_pages);
- mem_cgroup_id_put_many(memcg, nr_pages);
- }
- rcu_read_unlock();
- }
- long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg)
- {
- long nr_swap_pages = get_nr_swap_pages();
- if (mem_cgroup_disabled() || do_memsw_account())
- return nr_swap_pages;
- for (; memcg != root_mem_cgroup; memcg = parent_mem_cgroup(memcg))
- nr_swap_pages = min_t(long, nr_swap_pages,
- READ_ONCE(memcg->swap.max) -
- page_counter_read(&memcg->swap));
- return nr_swap_pages;
- }
- bool mem_cgroup_swap_full(struct folio *folio)
- {
- struct mem_cgroup *memcg;
- VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
- if (vm_swap_full())
- return true;
- if (do_memsw_account())
- return false;
- memcg = folio_memcg(folio);
- if (!memcg)
- return false;
- for (; memcg != root_mem_cgroup; memcg = parent_mem_cgroup(memcg)) {
- unsigned long usage = page_counter_read(&memcg->swap);
- if (usage * 2 >= READ_ONCE(memcg->swap.high) ||
- usage * 2 >= READ_ONCE(memcg->swap.max))
- return true;
- }
- return false;
- }
- static int __init setup_swap_account(char *s)
- {
- pr_warn_once("The swapaccount= commandline option is deprecated. "
- "Please report your usecase to [email protected] if you "
- "depend on this functionality.\n");
- return 1;
- }
- __setup("swapaccount=", setup_swap_account);
- static u64 swap_current_read(struct cgroup_subsys_state *css,
- struct cftype *cft)
- {
- struct mem_cgroup *memcg = mem_cgroup_from_css(css);
- return (u64)page_counter_read(&memcg->swap) * PAGE_SIZE;
- }
- static int swap_high_show(struct seq_file *m, void *v)
- {
- return seq_puts_memcg_tunable(m,
- READ_ONCE(mem_cgroup_from_seq(m)->swap.high));
- }
- static ssize_t swap_high_write(struct kernfs_open_file *of,
- char *buf, size_t nbytes, loff_t off)
- {
- struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
- unsigned long high;
- int err;
- buf = strstrip(buf);
- err = page_counter_memparse(buf, "max", &high);
- if (err)
- return err;
- page_counter_set_high(&memcg->swap, high);
- return nbytes;
- }
- static int swap_max_show(struct seq_file *m, void *v)
- {
- return seq_puts_memcg_tunable(m,
- READ_ONCE(mem_cgroup_from_seq(m)->swap.max));
- }
- static ssize_t swap_max_write(struct kernfs_open_file *of,
- char *buf, size_t nbytes, loff_t off)
- {
- struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
- unsigned long max;
- int err;
- buf = strstrip(buf);
- err = page_counter_memparse(buf, "max", &max);
- if (err)
- return err;
- xchg(&memcg->swap.max, max);
- return nbytes;
- }
- static int swap_events_show(struct seq_file *m, void *v)
- {
- struct mem_cgroup *memcg = mem_cgroup_from_seq(m);
- seq_printf(m, "high %lu\n",
- atomic_long_read(&memcg->memory_events[MEMCG_SWAP_HIGH]));
- seq_printf(m, "max %lu\n",
- atomic_long_read(&memcg->memory_events[MEMCG_SWAP_MAX]));
- seq_printf(m, "fail %lu\n",
- atomic_long_read(&memcg->memory_events[MEMCG_SWAP_FAIL]));
- return 0;
- }
- static struct cftype swap_files[] = {
- {
- .name = "swap.current",
- .flags = CFTYPE_NOT_ON_ROOT,
- .read_u64 = swap_current_read,
- },
- {
- .name = "swap.high",
- .flags = CFTYPE_NOT_ON_ROOT,
- .seq_show = swap_high_show,
- .write = swap_high_write,
- },
- {
- .name = "swap.max",
- .flags = CFTYPE_NOT_ON_ROOT,
- .seq_show = swap_max_show,
- .write = swap_max_write,
- },
- {
- .name = "swap.events",
- .flags = CFTYPE_NOT_ON_ROOT,
- .file_offset = offsetof(struct mem_cgroup, swap_events_file),
- .seq_show = swap_events_show,
- },
- { } /* terminate */
- };
- static struct cftype memsw_files[] = {
- {
- .name = "memsw.usage_in_bytes",
- .private = MEMFILE_PRIVATE(_MEMSWAP, RES_USAGE),
- .read_u64 = mem_cgroup_read_u64,
- },
- {
- .name = "memsw.max_usage_in_bytes",
- .private = MEMFILE_PRIVATE(_MEMSWAP, RES_MAX_USAGE),
- .write = mem_cgroup_reset,
- .read_u64 = mem_cgroup_read_u64,
- },
- {
- .name = "memsw.limit_in_bytes",
- .private = MEMFILE_PRIVATE(_MEMSWAP, RES_LIMIT),
- .write = mem_cgroup_write,
- .read_u64 = mem_cgroup_read_u64,
- },
- {
- .name = "memsw.failcnt",
- .private = MEMFILE_PRIVATE(_MEMSWAP, RES_FAILCNT),
- .write = mem_cgroup_reset,
- .read_u64 = mem_cgroup_read_u64,
- },
- { }, /* terminate */
- };
- #if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP)
- /**
- * obj_cgroup_may_zswap - check if this cgroup can zswap
- * @objcg: the object cgroup
- *
- * Check if the hierarchical zswap limit has been reached.
- *
- * This doesn't check for specific headroom, and it is not atomic
- * either. But with zswap, the size of the allocation is only known
- * once compression has occured, and this optimistic pre-check avoids
- * spending cycles on compression when there is already no room left
- * or zswap is disabled altogether somewhere in the hierarchy.
- */
- bool obj_cgroup_may_zswap(struct obj_cgroup *objcg)
- {
- struct mem_cgroup *memcg, *original_memcg;
- bool ret = true;
- if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
- return true;
- original_memcg = get_mem_cgroup_from_objcg(objcg);
- for (memcg = original_memcg; memcg != root_mem_cgroup;
- memcg = parent_mem_cgroup(memcg)) {
- unsigned long max = READ_ONCE(memcg->zswap_max);
- unsigned long pages;
- if (max == PAGE_COUNTER_MAX)
- continue;
- if (max == 0) {
- ret = false;
- break;
- }
- cgroup_rstat_flush(memcg->css.cgroup);
- pages = memcg_page_state(memcg, MEMCG_ZSWAP_B) / PAGE_SIZE;
- if (pages < max)
- continue;
- ret = false;
- break;
- }
- mem_cgroup_put(original_memcg);
- return ret;
- }
- /**
- * obj_cgroup_charge_zswap - charge compression backend memory
- * @objcg: the object cgroup
- * @size: size of compressed object
- *
- * This forces the charge after obj_cgroup_may_swap() allowed
- * compression and storage in zwap for this cgroup to go ahead.
- */
- void obj_cgroup_charge_zswap(struct obj_cgroup *objcg, size_t size)
- {
- struct mem_cgroup *memcg;
- if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
- return;
- VM_WARN_ON_ONCE(!(current->flags & PF_MEMALLOC));
- /* PF_MEMALLOC context, charging must succeed */
- if (obj_cgroup_charge(objcg, GFP_KERNEL, size))
- VM_WARN_ON_ONCE(1);
- rcu_read_lock();
- memcg = obj_cgroup_memcg(objcg);
- mod_memcg_state(memcg, MEMCG_ZSWAP_B, size);
- mod_memcg_state(memcg, MEMCG_ZSWAPPED, 1);
- rcu_read_unlock();
- }
- /**
- * obj_cgroup_uncharge_zswap - uncharge compression backend memory
- * @objcg: the object cgroup
- * @size: size of compressed object
- *
- * Uncharges zswap memory on page in.
- */
- void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg, size_t size)
- {
- struct mem_cgroup *memcg;
- if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
- return;
- obj_cgroup_uncharge(objcg, size);
- rcu_read_lock();
- memcg = obj_cgroup_memcg(objcg);
- mod_memcg_state(memcg, MEMCG_ZSWAP_B, -size);
- mod_memcg_state(memcg, MEMCG_ZSWAPPED, -1);
- rcu_read_unlock();
- }
- static u64 zswap_current_read(struct cgroup_subsys_state *css,
- struct cftype *cft)
- {
- cgroup_rstat_flush(css->cgroup);
- return memcg_page_state(mem_cgroup_from_css(css), MEMCG_ZSWAP_B);
- }
- static int zswap_max_show(struct seq_file *m, void *v)
- {
- return seq_puts_memcg_tunable(m,
- READ_ONCE(mem_cgroup_from_seq(m)->zswap_max));
- }
- static ssize_t zswap_max_write(struct kernfs_open_file *of,
- char *buf, size_t nbytes, loff_t off)
- {
- struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
- unsigned long max;
- int err;
- buf = strstrip(buf);
- err = page_counter_memparse(buf, "max", &max);
- if (err)
- return err;
- xchg(&memcg->zswap_max, max);
- return nbytes;
- }
- static struct cftype zswap_files[] = {
- {
- .name = "zswap.current",
- .flags = CFTYPE_NOT_ON_ROOT,
- .read_u64 = zswap_current_read,
- },
- {
- .name = "zswap.max",
- .flags = CFTYPE_NOT_ON_ROOT,
- .seq_show = zswap_max_show,
- .write = zswap_max_write,
- },
- { } /* terminate */
- };
- #endif /* CONFIG_MEMCG_KMEM && CONFIG_ZSWAP */
- static int __init mem_cgroup_swap_init(void)
- {
- if (mem_cgroup_disabled())
- return 0;
- WARN_ON(cgroup_add_dfl_cftypes(&memory_cgrp_subsys, swap_files));
- WARN_ON(cgroup_add_legacy_cftypes(&memory_cgrp_subsys, memsw_files));
- #if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP)
- WARN_ON(cgroup_add_dfl_cftypes(&memory_cgrp_subsys, zswap_files));
- #endif
- return 0;
- }
- subsys_initcall(mem_cgroup_swap_init);
- #endif /* CONFIG_SWAP */
|