Something went wrong. Try again.
Linux kernel mirror (for testing) git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
Something went wrong. Try again.
123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773774775776777778779780781782783784785786787788789790791792793794795796797798799800801802803804805806807808809810811812813814815816817818819820821822823824825826827828829830831832833834835836837838839840841842843844845846847848849850851852853854855856857858859860861862863864865866867868869870871872873874875876877878879880881882883884885886887888889890891892893894895896897898899900901902903904905906907908909910911912913914915916917918919920921922923924925926927928929930931932933934935936937938939940941942943944945946947948949950951952953954955956957958959960961962963964965966967968969970971972973974975976977978979980981982983984985986987988989990991992993994995996997998999100010011002100310041005100610071008100910101011101210131014101510161017101810191020102110221023102410251026102710281029103010311032103310341035103610371038103910401041104210431044104510461047104810491050105110521053105410551056105710581059106010611062106310641065106610671068106910701071107210731074107510761077107810791080108110821083108410851086108710881089109010911092109310941095109610971098109911001101110211031104110511061107110811091110111111121113111411151116111711181119112011211122112311241125112611271128112911301131113211331134113511361137113811391140114111421143114411451146114711481149115011511152115311541155115611571158115911601161116211631164116511661167116811691170117111721173117411751176117711781179118011811182118311841185118611871188118911901191119211931194119511961197119811991200120112021203120412051206120712081209121012111212121312141215121612171218121912201221122212231224122512261227122812291230123112321233123412351236123712381239124012411242124312441245124612471248124912501251125212531254125512561257125812591260126112621263126412651266126712681269127012711272127312741275127612771278127912801281128212831284128512861287128812891290129112921293129412951296129712981299130013011302130313041305130613071308130913101311131213131314131513161317131813191320132113221323132413251326132713281329133013311332133313341335133613371338133913401341134213431344134513461347134813491350135113521353135413551356135713581359136013611362136313641365136613671368136913701371137213731374137513761377137813791380138113821383138413851386138713881389139013911392139313941395139613971398139914001401140214031404140514061407140814091410141114121413141414151416141714181419142014211422142314241425142614271428142914301431143214331434143514361437143814391440144114421443144414451446144714481449145014511452145314541455145614571458145914601461146214631464146514661467146814691470147114721473147414751476147714781479148014811482148314841485148614871488148914901491149214931494149514961497149814991500150115021503150415051506150715081509151015111512151315141515151615171518151915201521152215231524152515261527152815291530153115321533153415351536153715381539154015411542154315441545154615471548154915501551155215531554155515561557155815591560156115621563156415651566156715681569157015711572157315741575157615771578157915801581158215831584158515861587158815891590159115921593159415951596159715981599160016011602160316041605160616071608160916101611161216131614161516161617161816191620162116221623162416251626162716281629163016311632163316341635163616371638163916401641164216431644164516461647164816491650165116521653165416551656165716581659166016611662166316641665166616671668166916701671167216731674167516761677167816791680168116821683168416851686168716881689169016911692169316941695169616971698169917001701170217031704170517061707170817091710171117121713171417151716171717181719172017211722172317241725172617271728172917301731173217331734173517361737173817391740174117421743174417451746174717481749175017511752175317541755175617571758175917601761176217631764176517661767176817691770177117721773177417751776177717781779178017811782178317841785178617871788178917901791179217931794179517961797179817991800180118021803180418051806180718081809181018111812181318141815181618171818181918201821182218231824182518261827182818291830183118321833183418351836183718381839184018411842184318441845184618471848184918501851185218531854185518561857185818591860186118621863186418651866186718681869187018711872187318741875187618771878187918801881188218831884188518861887188818891890189118921893189418951896189718981899190019011902190319041905190619071908190919101911191219131914191519161917191819191920192119221923192419251926192719281929193019311932193319341935193619371938193919401941194219431944194519461947194819491950195119521953195419551956195719581959196019611962196319641965196619671968196919701971197219731974197519761977197819791980198119821983198419851986198719881989199019911992199319941995199619971998199920002001200220032004200520062007200820092010201120122013201420152016201720182019202020212022202320242025202620272028202920302031203220332034203520362037203820392040204120422043204420452046204720482049205020512052205320542055205620572058205920602061206220632064206520662067206820692070207120722073207420752076207720782079208020812082208320842085208620872088208920902091209220932094209520962097209820992100210121022103210421052106210721082109211021112112211321142115211621172118211921202121212221232124212521262127212821292130213121322133213421352136213721382139214021412142214321442145214621472148214921502151215221532154215521562157215821592160216121622163216421652166216721682169217021712172217321742175217621772178217921802181218221832184218521862187218821892190219121922193219421952196219721982199220022012202220322042205220622072208220922102211221222132214221522162217221822192220222122222223222422252226222722282229223022312232223322342235223622372238223922402241224222432244224522462247224822492250225122522253225422552256225722582259226022612262226322642265226622672268226922702271227222732274227522762277227822792280228122822283228422852286228722882289229022912292229322942295229622972298229923002301230223032304230523062307230823092310231123122313231423152316231723182319232023212322232323242325232623272328232923302331233223332334233523362337233823392340234123422343234423452346234723482349235023512352235323542355235623572358235923602361236223632364236523662367236823692370237123722373237423752376237723782379238023812382238323842385238623872388238923902391239223932394239523962397239823992400240124022403240424052406240724082409241024112412241324142415241624172418241924202421242224232424242524262427242824292430243124322433243424352436243724382439244024412442244324442445244624472448244924502451245224532454245524562457245824592460246124622463246424652466246724682469247024712472247324742475247624772478247924802481248224832484248524862487248824892490249124922493249424952496249724982499250025012502250325042505250625072508250925102511251225132514251525162517251825192520252125222523252425252526252725282529253025312532253325342535253625372538253925402541254225432544254525462547254825492550255125522553255425552556255725582559256025612562256325642565256625672568256925702571257225732574257525762577257825792580258125822583258425852586258725882589259025912592259325942595259625972598259926002601260226032604260526062607260826092610261126122613261426152616261726182619262026212622262326242625262626272628262926302631263226332634263526362637263826392640264126422643264426452646264726482649265026512652265326542655265626572658265926602661266226632664266526662667266826692670267126722673267426752676267726782679268026812682268326842685268626872688268926902691269226932694269526962697269826992700270127022703270427052706270727082709271027112712271327142715271627172718271927202721272227232724272527262727272827292730273127322733273427352736273727382739274027412742274327442745274627472748274927502751275227532754275527562757275827592760276127622763276427652766276727682769277027712772277327742775277627772778277927802781278227832784278527862787278827892790279127922793279427952796279727982799280028012802280328042805280628072808280928102811281228132814281528162817281828192820282128222823282428252826282728282829283028312832283328342835283628372838283928402841284228432844284528462847284828492850285128522853285428552856285728582859286028612862286328642865286628672868286928702871287228732874287528762877287828792880288128822883288428852886288728882889289028912892289328942895289628972898289929002901290229032904290529062907290829092910291129122913291429152916291729182919292029212922292329242925292629272928292929302931293229332934293529362937293829392940294129422943294429452946294729482949295029512952295329542955295629572958295929602961296229632964296529662967296829692970297129722973297429752976297729782979298029812982298329842985298629872988298929902991299229932994299529962997299829993000300130023003300430053006300730083009301030113012301330143015301630173018301930203021302230233024302530263027302830293030303130323033303430353036303730383039304030413042304330443045304630473048304930503051305230533054305530563057305830593060306130623063306430653066306730683069307030713072307330743075307630773078307930803081308230833084308530863087308830893090309130923093309430953096309730983099310031013102310331043105310631073108310931103111311231133114311531163117311831193120312131223123312431253126312731283129313031313132313331343135313631373138313931403141314231433144314531463147314831493150315131523153315431553156315731583159316031613162316331643165316631673168316931703171317231733174317531763177317831793180318131823183318431853186318731883189319031913192319331943195319631973198319932003201320232033204320532063207320832093210321132123213321432153216321732183219322032213222322332243225322632273228322932303231323232333234323532363237323832393240324132423243324432453246324732483249325032513252325332543255325632573258325932603261326232633264326532663267326832693270327132723273327432753276327732783279328032813282328332843285328632873288328932903291329232933294329532963297329832993300330133023303330433053306330733083309331033113312331333143315331633173318331933203321332233233324332533263327332833293330333133323333333433353336333733383339334033413342334333443345334633473348334933503351335233533354335533563357335833593360336133623363336433653366336733683369337033713372337333743375337633773378337933803381338233833384338533863387338833893390339133923393339433953396339733983399340034013402340334043405340634073408340934103411341234133414341534163417341834193420342134223423342434253426342734283429343034313432343334343435343634373438343934403441344234433444344534463447344834493450345134523453345434553456345734583459346034613462346334643465346634673468346934703471347234733474347534763477347834793480348134823483348434853486348734883489349034913492349334943495349634973498349935003501350235033504350535063507350835093510351135123513351435153516351735183519352035213522352335243525352635273528352935303531353235333534353535363537353835393540354135423543354435453546354735483549355035513552355335543555355635573558355935603561356235633564356535663567356835693570357135723573357435753576357735783579358035813582358335843585358635873588358935903591359235933594359535963597359835993600360136023603360436053606360736083609361036113612361336143615361636173618361936203621362236233624362536263627362836293630363136323633363436353636363736383639364036413642364336443645364636473648364936503651365236533654365536563657365836593660366136623663366436653666366736683669367036713672367336743675367636773678367936803681368236833684368536863687368836893690369136923693369436953696369736983699370037013702370337043705370637073708370937103711371237133714371537163717371837193720372137223723372437253726372737283729373037313732373337343735373637373738373937403741374237433744374537463747374837493750375137523753375437553756375737583759376037613762376337643765376637673768376937703771377237733774377537763777377837793780378137823783378437853786378737883789379037913792379337943795379637973798379938003801380238033804380538063807380838093810381138123813381438153816381738183819382038213822382338243825382638273828382938303831383238333834383538363837383838393840384138423843384438453846384738483849385038513852385338543855385638573858385938603861386238633864386538663867386838693870387138723873387438753876387738783879388038813882388338843885388638873888388938903891389238933894389538963897389838993900390139023903390439053906390739083909391039113912391339143915391639173918391939203921392239233924392539263927392839293930393139323933393439353936393739383939394039413942394339443945394639473948394939503951395239533954395539563957395839593960396139623963396439653966396739683969397039713972397339743975397639773978397939803981398239833984398539863987398839893990399139923993399439953996399739983999400040014002400340044005400640074008400940104011401240134014401540164017401840194020402140224023402440254026402740284029403040314032403340344035403640374038403940404041404240434044404540464047404840494050405140524053405440554056405740584059406040614062406340644065406640674068406940704071407240734074407540764077407840794080408140824083408440854086408740884089409040914092409340944095409640974098409941004101410241034104410541064107410841094110411141124113411441154116411741184119412041214122412341244125412641274128412941304131413241334134413541364137413841394140414141424143414441454146414741484149415041514152415341544155415641574158415941604161416241634164416541664167416841694170417141724173417441754176417741784179418041814182418341844185418641874188418941904191419241934194419541964197419841994200420142024203420442054206420742084209421042114212421342144215421642174218421942204221422242234224422542264227422842294230423142324233423442354236423742384239424042414242424342444245424642474248424942504251425242534254425542564257425842594260426142624263426442654266426742684269427042714272427342744275427642774278427942804281428242834284428542864287428842894290429142924293429442954296429742984299430043014302430343044305430643074308430943104311431243134314431543164317431843194320432143224323432443254326432743284329433043314332433343344335433643374338433943404341434243434344434543464347434843494350435143524353435443554356435743584359436043614362436343644365436643674368436943704371437243734374437543764377437843794380438143824383438443854386438743884389439043914392439343944395439643974398439944004401440244034404440544064407440844094410441144124413441444154416441744184419442044214422442344244425442644274428442944304431443244334434443544364437443844394440444144424443444444454446444744484449445044514452445344544455445644574458445944604461446244634464446544664467446844694470447144724473447444754476447744784479448044814482448344844485448644874488448944904491449244934494449544964497449844994500450145024503450445054506450745084509451045114512451345144515451645174518451945204521452245234524452545264527452845294530453145324533453445354536453745384539454045414542454345444545454645474548454945504551455245534554455545564557455845594560456145624563456445654566456745684569457045714572457345744575457645774578457945804581458245834584458545864587458845894590459145924593459445954596459745984599460046014602460346044605460646074608460946104611461246134614461546164617461846194620462146224623462446254626462746284629463046314632463346344635463646374638463946404641464246434644464546464647464846494650465146524653465446554656465746584659466046614662466346644665466646674668466946704671467246734674467546764677467846794680468146824683468446854686468746884689469046914692469346944695469646974698469947004701470247034704470547064707470847094710471147124713471447154716471747184719472047214722472347244725472647274728472947304731473247334734473547364737473847394740474147424743474447454746474747484749475047514752475347544755475647574758475947604761476247634764476547664767476847694770477147724773477447754776477747784779478047814782478347844785478647874788478947904791479247934794479547964797479847994800480148024803480448054806480748084809481048114812481348144815481648174818481948204821482248234824482548264827482848294830483148324833483448354836483748384839484048414842484348444845484648474848484948504851485248534854485548564857485848594860486148624863486448654866486748684869487048714872487348744875487648774878487948804881488248834884488548864887488848894890489148924893489448954896489748984899490049014902490349044905490649074908490949104911491249134914491549164917491849194920492149224923492449254926492749284929493049314932493349344935493649374938493949404941494249434944494549464947494849494950495149524953495449554956495749584959496049614962496349644965496649674968496949704971497249734974497549764977497849794980498149824983498449854986498749884989499049914992499349944995499649974998499950005001500250035004500550065007500850095010501150125013501450155016501750185019502050215022502350245025502650275028502950305031503250335034503550365037503850395040504150425043504450455046504750485049505050515052505350545055505650575058505950605061506250635064506550665067506850695070507150725073507450755076507750785079508050815082508350845085508650875088508950905091509250935094509550965097509850995100510151025103510451055106510751085109511051115112511351145115511651175118511951205121512251235124512551265127512851295130513151325133513451355136513751385139514051415142514351445145514651475148514951505151515251535154515551565157515851595160516151625163516451655166516751685169517051715172517351745175517651775178517951805181518251835184518551865187518851895190519151925193519451955196519751985199520052015202520352045205520652075208520952105211521252135214521552165217521852195220522152225223522452255226522752285229523052315232523352345235523652375238523952405241524252435244524552465247524852495250525152525253525452555256525752585259526052615262526352645265526652675268526952705271527252735274527552765277527852795280528152825283528452855286528752885289529052915292529352945295529652975298529953005301530253035304530553065307530853095310531153125313531453155316531753185319532053215322532353245325532653275328532953305331533253335334533553365337533853395340534153425343534453455346534753485349535053515352535353545355535653575358535953605361536253635364536553665367536853695370537153725373537453755376537753785379538053815382538353845385538653875388538953905391539253935394539553965397539853995400540154025403540454055406540754085409541054115412541354145415541654175418541954205421542254235424542554265427542854295430543154325433543454355436543754385439544054415442544354445445544654475448544954505451545254535454545554565457545854595460546154625463546454655466546754685469547054715472547354745475547654775478547954805481548254835484548554865487548854895490549154925493549454955496549754985499550055015502550355045505550655075508550955105511551255135514551555165517551855195520552155225523552455255526552755285529553055315532553355345535553655375538553955405541554255435544554555465547554855495550555155525553555455555556555755585559556055615562556355645565556655675568556955705571557255735574557555765577557855795580558155825583558455855586558755885589559055915592559355945595559655975598559956005601560256035604560556065607560856095610561156125613561456155616561756185619562056215622562356245625562656275628562956305631563256335634563556365637563856395640564156425643564456455646564756485649565056515652565356545655565656575658565956605661566256635664566556665667566856695670567156725673567456755676567756785679568056815682568356845685568656875688568956905691569256935694569556965697569856995700570157025703570457055706570757085709571057115712571357145715571657175718571957205721572257235724572557265727572857295730573157325733573457355736573757385739574057415742574357445745574657475748574957505751575257535754575557565757575857595760576157625763576457655766576757685769577057715772577357745775577657775778577957805781578257835784578557865787578857895790579157925793579457955796579757985799580058015802580358045805580658075808580958105811581258135814581558165817581858195820582158225823582458255826582758285829583058315832583358345835583658375838583958405841584258435844584558465847584858495850585158525853585458555856585758585859586058615862586358645865586658675868586958705871587258735874587558765877587858795880588158825883588458855886588758885889589058915892589358945895589658975898589959005901590259035904590559065907590859095910591159125913591459155916591759185919592059215922592359245925592659275928592959305931593259335934593559365937593859395940594159425943594459455946594759485949595059515952595359545955595659575958595959605961596259635964596559665967596859695970597159725973597459755976597759785979598059815982598359845985598659875988598959905991599259935994599559965997599859996000600160026003600460056006600760086009601060116012601360146015601660176018601960206021602260236024602560266027602860296030603160326033603460356036603760386039604060416042604360446045604660476048604960506051605260536054605560566057605860596060606160626063606460656066606760686069607060716072607360746075607660776078607960806081608260836084608560866087608860896090609160926093609460956096609760986099610061016102610361046105610661076108610961106111611261136114611561166117611861196120612161226123612461256126612761286129613061316132613361346135613661376138613961406141614261436144614561466147614861496150615161526153615461556156615761586159616061616162616361646165616661676168616961706171617261736174617561766177617861796180618161826183618461856186618761886189619061916192619361946195619661976198619962006201620262036204620562066207620862096210621162126213621462156216621762186219622062216222622362246225622662276228622962306231623262336234623562366237623862396240624162426243624462456246624762486249625062516252625362546255625662576258625962606261626262636264626562666267626862696270627162726273627462756276627762786279628062816282628362846285628662876288628962906291629262936294629562966297629862996300630163026303630463056306630763086309631063116312631363146315631663176318631963206321632263236324632563266327632863296330633163326333633463356336633763386339634063416342634363446345634663476348634963506351635263536354635563566357635863596360636163626363636463656366636763686369637063716372637363746375637663776378637963806381638263836384638563866387638863896390639163926393639463956396639763986399640064016402640364046405640664076408640964106411641264136414641564166417641864196420642164226423642464256426642764286429643064316432643364346435643664376438643964406441644264436444644564466447644864496450645164526453645464556456645764586459646064616462646364646465646664676468646964706471647264736474647564766477647864796480648164826483648464856486648764886489649064916492649364946495649664976498649965006501650265036504650565066507650865096510651165126513651465156516651765186519652065216522652365246525652665276528652965306531653265336534653565366537653865396540654165426543654465456546654765486549655065516552655365546555655665576558655965606561656265636564656565666567656865696570657165726573657465756576657765786579658065816582658365846585658665876588658965906591659265936594659565966597659865996600660166026603660466056606660766086609661066116612661366146615661666176618661966206621662266236624662566266627662866296630663166326633663466356636663766386639664066416642664366446645664666476648664966506651665266536654665566566657665866596660666166626663666466656666666766686669667066716672667366746675667666776678667966806681668266836684668566866687668866896690669166926693669466956696669766986699670067016702670367046705670667076708670967106711671267136714671567166717671867196720672167226723672467256726672767286729673067316732673367346735673667376738673967406741674267436744674567466747674867496750675167526753675467556756675767586759676067616762676367646765676667676768676967706771677267736774677567766777677867796780678167826783678467856786678767886789679067916792679367946795679667976798679968006801680268036804680568066807680868096810681168126813681468156816681768186819682068216822682368246825682668276828682968306831683268336834683568366837683868396840684168426843684468456846684768486849685068516852685368546855685668576858685968606861686268636864686568666867686868696870687168726873687468756876687768786879688068816882688368846885688668876888688968906891689268936894689568966897689868996900690169026903690469056906690769086909691069116912691369146915691669176918691969206921692269236924692569266927692869296930693169326933693469356936693769386939694069416942694369446945694669476948694969506951695269536954695569566957695869596960696169626963696469656966696769686969697069716972697369746975697669776978697969806981698269836984698569866987698869896990699169926993699469956996699769986999700070017002700370047005700670077008700970107011701270137014701570167017701870197020702170227023702470257026702770287029703070317032703370347035703670377038703970407041704270437044704570467047704870497050705170527053705470557056705770587059706070617062706370647065706670677068706970707071707270737074707570767077707870797080708170827083708470857086708770887089709070917092709370947095709670977098709971007101710271037104710571067107710871097110711171127113711471157116711771187119712071217122712371247125712671277128712971307131713271337134713571367137713871397140714171427143714471457146714771487149715071517152715371547155715671577158715971607161716271637164716571667167716871697170717171727173717471757176717771787179718071817182718371847185718671877188718971907191719271937194719571967197719871997200720172027203720472057206720772087209721072117212721372147215721672177218721972207221722272237224722572267227722872297230723172327233723472357236723772387239724072417242724372447245724672477248724972507251725272537254725572567257725872597260726172627263726472657266726772687269727072717272727372747275727672777278727972807281728272837284728572867287728872897290729172927293729472957296729772987299730073017302730373047305730673077308730973107311731273137314731573167317731873197320732173227323732473257326732773287329733073317332733373347335733673377338733973407341734273437344734573467347734873497350735173527353735473557356735773587359736073617362736373647365736673677368736973707371737273737374737573767377737873797380738173827383738473857386738773887389739073917392739373947395739673977398739974007401740274037404740574067407740874097410741174127413741474157416741774187419742074217422742374247425742674277428742974307431743274337434743574367437743874397440744174427443744474457446744774487449745074517452745374547455745674577458745974607461746274637464746574667467746874697470747174727473747474757476747774787479748074817482748374847485748674877488748974907491749274937494749574967497749874997500750175027503750475057506750775087509751075117512751375147515751675177518751975207521752275237524// SPDX-License-Identifier: GPL-2.0/* * Generic process-grouping system. * * Based originally on the cpuset system, extracted by Paul Menage * Copyright (C) 2006 Google, Inc * * Notifications support * Copyright (C) 2009 Nokia Corporation * Author: Kirill A. Shutemov * * Copyright notices from the original cpuset code: * -------------------------------------------------- * Copyright (C) 2003 BULL SA. * Copyright (C) 2004-2006 Silicon Graphics, Inc. * * Portions derived from Patrick Mochel's sysfs code. * sysfs is Copyright (c) 2001-3 Patrick Mochel * * 2003-10-10 Written by Simon Derr. * 2003-10-22 Updates by Stephen Hemminger. * 2004 May-July Rework by Paul Jackson. * --------------------------------------------------- */
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include "cgroup-internal.h"
#include <linux/bpf-cgroup.h>#include <linux/cred.h>#include <linux/errno.h>#include <linux/init_task.h>#include <linux/kernel.h>#include <linux/magic.h>#include <linux/mutex.h>#include <linux/mount.h>#include <linux/pagemap.h>#include <linux/proc_fs.h>#include <linux/rcupdate.h>#include <linux/sched.h>#include <linux/sched/task.h>#include <linux/slab.h>#include <linux/spinlock.h>#include <linux/percpu-rwsem.h>#include <linux/string.h>#include <linux/hashtable.h>#include <linux/idr.h>#include <linux/kthread.h>#include <linux/atomic.h>#include <linux/cpuset.h>#include <linux/proc_ns.h>#include <linux/nsproxy.h>#include <linux/file.h>#include <linux/fs_parser.h>#include <linux/sched/cputime.h>#include <linux/sched/deadline.h>#include <linux/psi.h>#include <linux/nstree.h>#include <linux/irq_work.h>#include <net/sock.h>
#define CREATE_TRACE_POINTS#include <trace/events/cgroup.h>
#define CGROUP_FILE_NAME_MAX (MAX_CGROUP_TYPE_NAMELEN + \ MAX_CFTYPE_NAME + 2)/* let's not notify more than 100 times per second */#define CGROUP_FILE_NOTIFY_MIN_INTV DIV_ROUND_UP(HZ, 100)
/* * cgroup_mutex is the master lock. Any modification to cgroup or its * hierarchy must be performed while holding it. * * css_set_lock protects task->cgroups pointer, the list of css_set * objects, and the chain of tasks off each css_set. * * These locks are exported if CONFIG_PROVE_RCU so that accessors in * cgroup.h can use them for lockdep annotations. */DEFINE_MUTEX(cgroup_mutex);DEFINE_SPINLOCK(css_set_lock);
#if (defined CONFIG_PROVE_RCU || defined CONFIG_LOCKDEP)EXPORT_SYMBOL_GPL(cgroup_mutex);EXPORT_SYMBOL_GPL(css_set_lock);#endif
struct blocking_notifier_head cgroup_lifetime_notifier = BLOCKING_NOTIFIER_INIT(cgroup_lifetime_notifier);
DEFINE_SPINLOCK(trace_cgroup_path_lock);char trace_cgroup_path[TRACE_CGROUP_PATH_LEN];static bool cgroup_debug __read_mostly;
/* * Protects cgroup_idr and css_idr so that IDs can be released without * grabbing cgroup_mutex. */static DEFINE_SPINLOCK(cgroup_idr_lock);
DEFINE_PERCPU_RWSEM(cgroup_threadgroup_rwsem);
#define cgroup_assert_mutex_or_rcu_locked() \ RCU_LOCKDEP_WARN(!rcu_read_lock_held() && \ !lockdep_is_held(&cgroup_mutex), \ "cgroup_mutex or RCU read lock required");
/* * cgroup destruction makes heavy use of work items and there can be a lot * of concurrent destructions. Use a separate workqueue so that cgroup * destruction work items don't end up filling up max_active of system_percpu_wq * which may lead to deadlock. * * A cgroup destruction should enqueue work sequentially to: * cgroup_offline_wq: use for css offline work * cgroup_release_wq: use for css release work * cgroup_free_wq: use for free work * * Rationale for using separate workqueues: * The cgroup root free work may depend on completion of other css offline * operations. If all tasks were enqueued to a single workqueue, this could * create a deadlock scenario where: * - Free work waits for other css offline work to complete. * - But other css offline work is queued after free work in the same queue. * * Example deadlock scenario with single workqueue (cgroup_destroy_wq): * 1. umount net_prio * 2. net_prio root destruction enqueues work to cgroup_destroy_wq (CPUx) * 3. perf_event CSS A offline enqueues work to same cgroup_destroy_wq (CPUx) * 4. net_prio cgroup_destroy_root->cgroup_lock_and_drain_offline. * 5. net_prio root destruction blocks waiting for perf_event CSS A offline, * which can never complete as it's behind in the same queue and * workqueue's max_active is 1. */static struct workqueue_struct *cgroup_offline_wq;static struct workqueue_struct *cgroup_release_wq;static struct workqueue_struct *cgroup_free_wq;
/* generate an array of cgroup subsystem pointers */#define SUBSYS(_x) [_x ## _cgrp_id] = &_x ## _cgrp_subsys,struct cgroup_subsys *cgroup_subsys[] = {#include <linux/cgroup_subsys.h>};#undef SUBSYS
/* array of cgroup subsystem names */#define SUBSYS(_x) [_x ## _cgrp_id] = #_x,static const char *cgroup_subsys_name[] = {#include <linux/cgroup_subsys.h>};#undef SUBSYS
/* array of static_keys for cgroup_subsys_enabled() and cgroup_subsys_on_dfl() */#define SUBSYS(_x) \ DEFINE_STATIC_KEY_TRUE(_x ## _cgrp_subsys_enabled_key); \ DEFINE_STATIC_KEY_TRUE(_x ## _cgrp_subsys_on_dfl_key); \ EXPORT_SYMBOL_GPL(_x ## _cgrp_subsys_enabled_key); \ EXPORT_SYMBOL_GPL(_x ## _cgrp_subsys_on_dfl_key);#include <linux/cgroup_subsys.h>#undef SUBSYS
#define SUBSYS(_x) [_x ## _cgrp_id] = &_x ## _cgrp_subsys_enabled_key,static struct static_key_true *cgroup_subsys_enabled_key[] = {#include <linux/cgroup_subsys.h>};#undef SUBSYS
#define SUBSYS(_x) [_x ## _cgrp_id] = &_x ## _cgrp_subsys_on_dfl_key,static struct static_key_true *cgroup_subsys_on_dfl_key[] = {#include <linux/cgroup_subsys.h>};#undef SUBSYS
static DEFINE_PER_CPU(struct css_rstat_cpu, root_rstat_cpu);static DEFINE_PER_CPU(struct cgroup_rstat_base_cpu, root_rstat_base_cpu);
/* the default hierarchy */struct cgroup_root cgrp_dfl_root = { .cgrp.self.rstat_cpu = &root_rstat_cpu, .cgrp.rstat_base_cpu = &root_rstat_base_cpu,};EXPORT_SYMBOL_GPL(cgrp_dfl_root);
/* * The default hierarchy always exists but is hidden until mounted for the * first time. This is for backward compatibility. */bool cgrp_dfl_visible;
/* some controllers are not supported in the default hierarchy */static u32 cgrp_dfl_inhibit_ss_mask;
/* some controllers are implicitly enabled on the default hierarchy */static u32 cgrp_dfl_implicit_ss_mask;
/* some controllers can be threaded on the default hierarchy */static u32 cgrp_dfl_threaded_ss_mask;
/* * Set across rebind_subsystems() to the controllers leaving a hierarchy. * Guarded by cgroup_mutex. Makes find_existing_css_set() resolve them to the * root css so the affected tasks are migrated there before * cgroup_apply_control_disable() kills the per-cgroup csses. */static u32 cgroup_rebind_ss_mask;
/* The list of hierarchy roots */LIST_HEAD(cgroup_roots);static int cgroup_root_count;
/* hierarchy ID allocation and mapping, protected by cgroup_mutex */static DEFINE_IDR(cgroup_hierarchy_idr);
/* * Assign a monotonically increasing serial number to csses. It guarantees * cgroups with bigger numbers are newer than those with smaller numbers. * Also, as csses are always appended to the parent's ->children list, it * guarantees that sibling csses are always sorted in the ascending serial * number order on the list. Protected by cgroup_mutex. */static u64 css_serial_nr_next = 1;
/* * These bitmasks identify subsystems with specific features to avoid * having to do iterative checks repeatedly. */static u32 have_fork_callback __read_mostly;static u32 have_exit_callback __read_mostly;static u32 have_release_callback __read_mostly;static u32 have_canfork_callback __read_mostly;
static bool have_favordynmods __ro_after_init = IS_ENABLED(CONFIG_CGROUP_FAVOR_DYNMODS);
/* * Write protected by cgroup_mutex and write-lock of cgroup_threadgroup_rwsem, * read protected by either. * * Can only be turned on, but not turned off. */bool cgroup_enable_per_threadgroup_rwsem __read_mostly;
/* cgroup namespace for init task */struct cgroup_namespace init_cgroup_ns = { .ns = NS_COMMON_INIT(init_cgroup_ns), .user_ns = &init_user_ns, .root_cset = &init_css_set,};
static struct file_system_type cgroup2_fs_type;static struct cftype cgroup_base_files[];static struct cftype cgroup_psi_files[];
/* cgroup optional features */enum cgroup_opt_features {#ifdef CONFIG_PSI OPT_FEATURE_PRESSURE,#endif OPT_FEATURE_COUNT};
static const char *cgroup_opt_feature_names[OPT_FEATURE_COUNT] = {#ifdef CONFIG_PSI "pressure",#endif};
static u16 cgroup_feature_disable_mask __read_mostly;
static int cgroup_apply_control(struct cgroup *cgrp);static void cgroup_finalize_control(struct cgroup *cgrp, int ret);static void css_task_iter_skip(struct css_task_iter *it, struct task_struct *task);static int cgroup_destroy_locked(struct cgroup *cgrp);static void kill_css_sync(struct cgroup_subsys_state *css);static void kill_css_finish(struct cgroup_subsys_state *css);static struct cgroup_subsys_state *css_create(struct cgroup *cgrp, struct cgroup_subsys *ss);static void css_release(struct percpu_ref *ref);static int cgroup_addrm_files(struct cgroup_subsys_state *css, struct cgroup *cgrp, struct cftype cfts[], bool is_add);static void cgroup_rt_init(void);
#ifdef CONFIG_DEBUG_CGROUP_REF#define CGROUP_REF_FN_ATTRS noinline#define CGROUP_REF_EXPORT(fn) EXPORT_SYMBOL_GPL(fn);#include <linux/cgroup_refcnt.h>#endif
/** * cgroup_ssid_enabled - cgroup subsys enabled test by subsys ID * @ssid: subsys ID of interest * * cgroup_subsys_enabled() can only be used with literal subsys names which * is fine for individual subsystems but unsuitable for cgroup core. This * is slower static_key_enabled() based test indexed by @ssid. */bool cgroup_ssid_enabled(int ssid){ if (!CGROUP_HAS_SUBSYS_CONFIG) return false;
return static_key_enabled(cgroup_subsys_enabled_key[ssid]);}
/** * cgroup_on_dfl - test whether a cgroup is on the default hierarchy * @cgrp: the cgroup of interest * * The default hierarchy is the v2 interface of cgroup and this function * can be used to test whether a cgroup is on the default hierarchy for * cases where a subsystem should behave differently depending on the * interface version. * * List of changed behaviors: * * - Mount options "noprefix", "xattr", "clone_children", "release_agent" * and "name" are disallowed. * * - When mounting an existing superblock, mount options should match. * * - rename(2) is disallowed. * * - "tasks" is removed. Everything should be at process granularity. Use * "cgroup.procs" instead. * * - "cgroup.procs" is not sorted. pids will be unique unless they got * recycled in-between reads. * * - "release_agent" and "notify_on_release" are removed. Replacement * notification mechanism will be implemented. * * - "cgroup.clone_children" is removed. * * - "cgroup.subtree_populated" is available. Its value is 0 if the cgroup * and its descendants contain no task; otherwise, 1. The file also * generates kernfs notification which can be monitored through poll and * [di]notify when the value of the file changes. * * - cpuset: tasks will be kept in empty cpusets when hotplug happens and * take masks of ancestors with non-empty cpus/mems, instead of being * moved to an ancestor. * * - cpuset: a task can be moved into an empty cpuset, and again it takes * masks of ancestors. * * - blkcg: blk-throttle becomes properly hierarchical. */bool cgroup_on_dfl(const struct cgroup *cgrp){ return cgrp->root == &cgrp_dfl_root;}
/* IDR wrappers which synchronize using cgroup_idr_lock */static int cgroup_idr_alloc(struct idr *idr, void *ptr, int start, int end, gfp_t gfp_mask){ int ret;
idr_preload(gfp_mask); spin_lock_bh(&cgroup_idr_lock); ret = idr_alloc(idr, ptr, start, end, gfp_mask & ~__GFP_DIRECT_RECLAIM); spin_unlock_bh(&cgroup_idr_lock); idr_preload_end(); return ret;}
static void *cgroup_idr_replace(struct idr *idr, void *ptr, int id){ void *ret;
spin_lock_bh(&cgroup_idr_lock); ret = idr_replace(idr, ptr, id); spin_unlock_bh(&cgroup_idr_lock); return ret;}
static void cgroup_idr_remove(struct idr *idr, int id){ spin_lock_bh(&cgroup_idr_lock); idr_remove(idr, id); spin_unlock_bh(&cgroup_idr_lock);}
static bool cgroup_is_threaded(struct cgroup *cgrp){ return cgrp->dom_cgrp != cgrp;}
/* can @cgrp host both domain and threaded children? */static bool cgroup_is_mixable(struct cgroup *cgrp){ /* * Root isn't under domain level resource control exempting it from * the no-internal-process constraint, so it can serve as a thread * root and a parent of resource domains at the same time. */ return !cgroup_parent(cgrp);}
/* can @cgrp become a thread root? Should always be true for a thread root */static bool cgroup_can_be_thread_root(struct cgroup *cgrp){ /* mixables don't care */ if (cgroup_is_mixable(cgrp)) return true;
/* domain roots can't be nested under threaded */ if (cgroup_is_threaded(cgrp)) return false;
/* can only have either domain or threaded children */ if (READ_ONCE(cgrp->nr_populated_domain_children)) return false;
/* and no domain controllers can be enabled */ if (cgrp->subtree_control & ~cgrp_dfl_threaded_ss_mask) return false;
return true;}
/* is @cgrp root of a threaded subtree? */static bool cgroup_is_thread_root(struct cgroup *cgrp){ /* thread root should be a domain */ if (cgroup_is_threaded(cgrp)) return false;
/* a domain w/ threaded children is a thread root */ if (cgrp->nr_threaded_children) return true;
/* * A domain which has tasks and explicit threaded controllers * enabled is a thread root. */ if (cgroup_has_tasks(cgrp) && (cgrp->subtree_control & cgrp_dfl_threaded_ss_mask)) return true;
return false;}
/* a domain which isn't connected to the root w/o brekage can't be used */static bool cgroup_is_valid_domain(struct cgroup *cgrp){ /* the cgroup itself can be a thread root */ if (cgroup_is_threaded(cgrp)) return false;
/* but the ancestors can't be unless mixable */ while ((cgrp = cgroup_parent(cgrp))) { if (!cgroup_is_mixable(cgrp) && cgroup_is_thread_root(cgrp)) return false; if (cgroup_is_threaded(cgrp)) return false; }
return true;}
/* subsystems visibly enabled on a cgroup */static u32 cgroup_control(struct cgroup *cgrp){ struct cgroup *parent = cgroup_parent(cgrp); u32 root_ss_mask = cgrp->root->subsys_mask;
if (parent) { u32 ss_mask = parent->subtree_control;
/* threaded cgroups can only have threaded controllers */ if (cgroup_is_threaded(cgrp)) ss_mask &= cgrp_dfl_threaded_ss_mask; return ss_mask; }
if (cgroup_on_dfl(cgrp)) root_ss_mask &= ~(cgrp_dfl_inhibit_ss_mask | cgrp_dfl_implicit_ss_mask); return root_ss_mask;}
/* subsystems enabled on a cgroup */static u32 cgroup_ss_mask(struct cgroup *cgrp){ struct cgroup *parent = cgroup_parent(cgrp);
if (parent) { u32 ss_mask = parent->subtree_ss_mask;
/* threaded cgroups can only have threaded controllers */ if (cgroup_is_threaded(cgrp)) ss_mask &= cgrp_dfl_threaded_ss_mask; return ss_mask; }
return cgrp->root->subsys_mask;}
/** * cgroup_e_css_by_mask - obtain a cgroup's effective css for the specified ss * @cgrp: the cgroup of interest * @ss: the subsystem of interest (%NULL returns @cgrp->self) * * Similar to cgroup_css() but returns the effective css, which is defined * as the matching css of the nearest ancestor including self which has @ss * enabled. If @ss is associated with the hierarchy @cgrp is on, this * function is guaranteed to return non-NULL css. */static struct cgroup_subsys_state *cgroup_e_css_by_mask(struct cgroup *cgrp, struct cgroup_subsys *ss){ lockdep_assert_held(&cgroup_mutex);
if (!ss) return &cgrp->self;
/* * This function is used while updating css associations and thus * can't test the csses directly. Test ss_mask. */ while (!(cgroup_ss_mask(cgrp) & (1 << ss->id))) { cgrp = cgroup_parent(cgrp); if (!cgrp) return NULL; }
return cgroup_css(cgrp, ss);}
/** * cgroup_e_css - obtain a cgroup's effective css for the specified subsystem * @cgrp: the cgroup of interest * @ss: the subsystem of interest * * Find and get the effective css of @cgrp for @ss. The effective css is * defined as the matching css of the nearest ancestor including self which * has @ss enabled. If @ss is not mounted on the hierarchy @cgrp is on, * the root css is returned, so this function always returns a valid css. * * The returned css is not guaranteed to be online, and therefore it is the * callers responsibility to try get a reference for it. */struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgrp, struct cgroup_subsys *ss){ struct cgroup_subsys_state *css;
if (!CGROUP_HAS_SUBSYS_CONFIG) return NULL;
do { css = cgroup_css(cgrp, ss);
if (css) return css; cgrp = cgroup_parent(cgrp); } while (cgrp);
return init_css_set.subsys[ss->id];}
/** * cgroup_get_e_css - get a cgroup's effective css for the specified subsystem * @cgrp: the cgroup of interest * @ss: the subsystem of interest * * Find and get the effective css of @cgrp for @ss. The effective css is * defined as the matching css of the nearest ancestor including self which * has @ss enabled. If @ss is not mounted on the hierarchy @cgrp is on, * the root css is returned, so this function always returns a valid css. * The returned css must be put using css_put(). */struct cgroup_subsys_state *cgroup_get_e_css(struct cgroup *cgrp, struct cgroup_subsys *ss){ struct cgroup_subsys_state *css;
if (!CGROUP_HAS_SUBSYS_CONFIG) return NULL;
rcu_read_lock();
do { css = cgroup_css(cgrp, ss);
if (css && css_tryget_online(css)) goto out_unlock; cgrp = cgroup_parent(cgrp); } while (cgrp);
css = init_css_set.subsys[ss->id]; css_get(css);out_unlock: rcu_read_unlock(); return css;}EXPORT_SYMBOL_GPL(cgroup_get_e_css);
static void cgroup_get_live(struct cgroup *cgrp){ WARN_ON_ONCE(cgroup_is_dead(cgrp)); cgroup_get(cgrp);}
/** * __cgroup_task_count - count the number of tasks in a cgroup. The caller * is responsible for taking the css_set_lock. * @cgrp: the cgroup in question */int __cgroup_task_count(const struct cgroup *cgrp){ int count = 0; struct cgrp_cset_link *link;
lockdep_assert_held(&css_set_lock);
list_for_each_entry(link, &cgrp->cset_links, cset_link) count += link->cset->nr_tasks;
return count;}
/** * cgroup_task_count - count the number of tasks in a cgroup. * @cgrp: the cgroup in question */int cgroup_task_count(const struct cgroup *cgrp){ int count;
spin_lock_irq(&css_set_lock); count = __cgroup_task_count(cgrp); spin_unlock_irq(&css_set_lock);
return count;}
static struct cgroup *kn_priv(struct kernfs_node *kn){ struct kernfs_node *parent; /* * The parent can not be replaced due to KERNFS_ROOT_INVARIANT_PARENT. * Therefore it is always safe to dereference this pointer outside of a * RCU section. */ parent = rcu_dereference_check(kn->__parent, kernfs_root_flags(kn) & KERNFS_ROOT_INVARIANT_PARENT); return parent->priv;}
struct cgroup_subsys_state *of_css(struct kernfs_open_file *of){ struct cgroup *cgrp = kn_priv(of->kn); struct cftype *cft = of_cft(of);
/* * This is open and unprotected implementation of cgroup_css(). * seq_css() is only called from a kernfs file operation which has * an active reference on the file. Because all the subsystem * files are drained before a css is disassociated with a cgroup, * the matching css from the cgroup's subsys table is guaranteed to * be and stay valid until the enclosing operation is complete. */ if (CGROUP_HAS_SUBSYS_CONFIG && cft->ss) return rcu_dereference_raw(cgrp->subsys[cft->ss->id]); else return &cgrp->self;}EXPORT_SYMBOL_GPL(of_css);
/** * for_each_css - iterate all css's of a cgroup * @css: the iteration cursor * @ssid: the index of the subsystem, CGROUP_SUBSYS_COUNT after reaching the end * @cgrp: the target cgroup to iterate css's of * * Should be called under cgroup_mutex. */#define for_each_css(css, ssid, cgrp) \ for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT; (ssid)++) \ if (!((css) = rcu_dereference_check( \ (cgrp)->subsys[(ssid)], \ lockdep_is_held(&cgroup_mutex)))) { } \ else
/** * do_each_subsys_mask - filter for_each_subsys with a bitmask * @ss: the iteration cursor * @ssid: the index of @ss, CGROUP_SUBSYS_COUNT after reaching the end * @ss_mask: the bitmask * * The block will only run for cases where the ssid-th bit (1 << ssid) of * @ss_mask is set. */#define do_each_subsys_mask(ss, ssid, ss_mask) do { \ unsigned long __ss_mask = (ss_mask); \ if (!CGROUP_HAS_SUBSYS_CONFIG) { \ (ssid) = 0; \ break; \ } \ for_each_set_bit(ssid, &__ss_mask, CGROUP_SUBSYS_COUNT) { \ (ss) = cgroup_subsys[ssid]; \ {
#define while_each_subsys_mask() \ } \ } \} while (false)
/* * The default css_set - used by init and its children prior to any * hierarchies being mounted. It contains a pointer to the root state * for each subsystem. Also used to anchor the list of css_sets. Not * reference-counted, to improve performance when child cgroups * haven't been created. */struct css_set init_css_set = { .refcount = REFCOUNT_INIT(1), .dom_cset = &init_css_set, .tasks = LIST_HEAD_INIT(init_css_set.tasks), .mg_tasks = LIST_HEAD_INIT(init_css_set.mg_tasks), .dying_tasks = LIST_HEAD_INIT(init_css_set.dying_tasks), .task_iters = LIST_HEAD_INIT(init_css_set.task_iters), .threaded_csets = LIST_HEAD_INIT(init_css_set.threaded_csets), .cgrp_links = LIST_HEAD_INIT(init_css_set.cgrp_links), .mg_src_preload_node = LIST_HEAD_INIT(init_css_set.mg_src_preload_node), .mg_dst_preload_node = LIST_HEAD_INIT(init_css_set.mg_dst_preload_node), .mg_node = LIST_HEAD_INIT(init_css_set.mg_node),
/* * The following field is re-initialized when this cset gets linked * in cgroup_init(). However, let's initialize the field * statically too so that the default cgroup can be accessed safely * early during boot. */ .dfl_cgrp = &cgrp_dfl_root.cgrp,};
static int css_set_count = 1; /* 1 for init_css_set */
static bool css_set_threaded(struct css_set *cset){ return cset->dom_cset != cset;}
/** * css_set_populated - does a css_set contain any tasks? * @cset: target css_set * * css_set_populated() should be the same as !!cset->nr_tasks at steady * state. However, css_set_populated() can be called while a task is being * added to or removed from the linked list before the nr_tasks is * properly updated. Hence, we can't just look at ->nr_tasks here. */static bool css_set_populated(struct css_set *cset){ lockdep_assert_held(&css_set_lock);
return !list_empty(&cset->tasks) || !list_empty(&cset->mg_tasks);}
/** * css_update_populated - update the populated state of a css and ancestors * @css: leaf css whose own populated count is changing * @populated: inc or dec * * One of the css_sets pinned by @css is getting its first task or losing the * last. Propagate the transition up the parent chain so that a css's * nr_populated_children is zero iff none of its descendants contain any tasks. * * For a cgroup->self walk, also runs cgroup-side bookkeeping at each level: * domain/threaded child split, deferred-destroy trigger, and notification via * "cgroup.populated" (zero iff cgrp->self has neither populated csets nor * populated children; userland is notified on transitions). */static void css_update_populated(struct cgroup_subsys_state *css, bool populated){ struct cgroup_subsys_state *child = NULL; int adj = populated ? 1 : -1;
lockdep_assert_held(&css_set_lock);
do { /* non-NULL only on the cgroup->self walk */ struct cgroup *cgrp = css_is_self(css) ? css->cgroup : NULL; bool was_populated = css_is_populated(css);
if (!child) { WRITE_ONCE(css->nr_populated_csets, css->nr_populated_csets + adj); } else { WRITE_ONCE(css->nr_populated_children, css->nr_populated_children + adj); if (cgrp) { if (cgroup_is_threaded(child->cgroup)) WRITE_ONCE(cgrp->nr_populated_threaded_children, cgrp->nr_populated_threaded_children + adj); else WRITE_ONCE(cgrp->nr_populated_domain_children, cgrp->nr_populated_domain_children + adj); } }
if (was_populated == css_is_populated(css)) break;
/* * Pair with smp_mb() in kill_css_sync(). Either we observe * CSS_DYING and queue, or the caller observes our decrement * and fires synchronously. */ smp_mb();
/* * Subtree just emptied below a dying css. Fire deferred kill. * The transition is one-shot for a dying css. */ if (was_populated && css_is_dying(css)) { css_get(css); WARN_ON_ONCE(!queue_work(cgroup_offline_wq, &css->kill_finish_work)); }
if (cgrp) { cgroup1_check_for_release(cgrp); TRACE_CGROUP_PATH(notify_populated, cgrp, cgroup_is_populated(cgrp)); cgroup_file_notify(&cgrp->events_file); }
child = css; css = css->parent; } while (css);}
/** * css_set_update_populated - update populated state of a css_set * @cset: target css_set * @populated: whether @cset is populated or depopulated * * @cset is either getting the first task or losing the last. Update the * populated counters along each linked cgroup's self chain and each * subsystem css that @cset pins. */static void css_set_update_populated(struct css_set *cset, bool populated){ struct cgrp_cset_link *link; struct cgroup_subsys *ss; int ssid;
lockdep_assert_held(&css_set_lock);
list_for_each_entry(link, &cset->cgrp_links, cgrp_link) css_update_populated(&link->cgrp->self, populated);
for_each_subsys(ss, ssid) { struct cgroup_subsys_state *css = cset->subsys[ssid];
if (css) css_update_populated(css, populated); }}
/* * @task is leaving, advance task iterators which are pointing to it so * that they can resume at the next position. Advancing an iterator might * remove it from the list, use safe walk. See css_task_iter_skip() for * details. */static void css_set_skip_task_iters(struct css_set *cset, struct task_struct *task){ struct css_task_iter *it, *pos;
list_for_each_entry_safe(it, pos, &cset->task_iters, iters_node) css_task_iter_skip(it, task);}
/** * css_set_move_task - move a task from one css_set to another * @task: task being moved * @from_cset: css_set @task currently belongs to (may be NULL) * @to_cset: new css_set @task is being moved to (may be NULL) * @use_mg_tasks: move to @to_cset->mg_tasks instead of ->tasks * * Move @task from @from_cset to @to_cset. If @task didn't belong to any * css_set, @from_cset can be NULL. If @task is being disassociated * instead of moved, @to_cset can be NULL. * * This function automatically handles populated counter updates and * css_task_iter adjustments but the caller is responsible for managing * @from_cset and @to_cset's reference counts. */static void css_set_move_task(struct task_struct *task, struct css_set *from_cset, struct css_set *to_cset, bool use_mg_tasks){ lockdep_assert_held(&css_set_lock);
if (to_cset && !css_set_populated(to_cset)) css_set_update_populated(to_cset, true);
if (from_cset) { WARN_ON_ONCE(list_empty(&task->cg_list));
css_set_skip_task_iters(from_cset, task); list_del_init(&task->cg_list); if (!css_set_populated(from_cset)) css_set_update_populated(from_cset, false); } else { WARN_ON_ONCE(!list_empty(&task->cg_list)); }
if (to_cset) { /* * We are synchronized through cgroup_threadgroup_rwsem * against PF_EXITING setting such that we can't race * against cgroup_task_dead()/cgroup_task_free() dropping * the css_set. */ WARN_ON_ONCE(task->flags & PF_EXITING);
cgroup_move_task(task, to_cset); list_add_tail(&task->cg_list, use_mg_tasks ? &to_cset->mg_tasks : &to_cset->tasks); }}
/* * hash table for cgroup groups. This improves the performance to find * an existing css_set. This hash doesn't (currently) take into * account cgroups in empty hierarchies. */#define CSS_SET_HASH_BITS 7static DEFINE_HASHTABLE(css_set_table, CSS_SET_HASH_BITS);
static unsigned long css_set_hash(struct cgroup_subsys_state **css){ unsigned long key = 0UL; struct cgroup_subsys *ss; int i;
for_each_subsys(ss, i) key += (unsigned long)css[i]; key = (key >> 16) ^ key;
return key;}
void put_css_set_locked(struct css_set *cset){ struct cgrp_cset_link *link, *tmp_link; struct cgroup_subsys *ss; int ssid;
lockdep_assert_held(&css_set_lock);
if (!refcount_dec_and_test(&cset->refcount)) return;
WARN_ON_ONCE(!list_empty(&cset->threaded_csets));
/* This css_set is dead. Unlink it and release cgroup and css refs */ for_each_subsys(ss, ssid) { list_del(&cset->e_cset_node[ssid]); css_put(cset->subsys[ssid]); } hash_del(&cset->hlist); css_set_count--;
list_for_each_entry_safe(link, tmp_link, &cset->cgrp_links, cgrp_link) { list_del(&link->cset_link); list_del(&link->cgrp_link); if (cgroup_parent(link->cgrp)) cgroup_put(link->cgrp); kfree(link); }
if (css_set_threaded(cset)) { list_del(&cset->threaded_csets_node); put_css_set_locked(cset->dom_cset); }
kfree_rcu(cset, rcu_head);}
/** * compare_css_sets - helper function for find_existing_css_set(). * @cset: candidate css_set being tested * @old_cset: existing css_set for a task * @new_cgrp: cgroup that's being entered by the task * @template: desired set of css pointers in css_set (pre-calculated) * * Returns true if "cset" matches "old_cset" except for the hierarchy * which "new_cgrp" belongs to, for which it should match "new_cgrp". */static bool compare_css_sets(struct css_set *cset, struct css_set *old_cset, struct cgroup *new_cgrp, struct cgroup_subsys_state *template[]){ struct cgroup *new_dfl_cgrp; struct list_head *l1, *l2;
/* * On the default hierarchy, there can be csets which are * associated with the same set of cgroups but different csses. * Let's first ensure that csses match. */ if (memcmp(template, cset->subsys, sizeof(cset->subsys))) return false;
/* @cset's domain should match the default cgroup's */ if (cgroup_on_dfl(new_cgrp)) new_dfl_cgrp = new_cgrp; else new_dfl_cgrp = old_cset->dfl_cgrp;
if (new_dfl_cgrp->dom_cgrp != cset->dom_cset->dfl_cgrp) return false;
/* * Compare cgroup pointers in order to distinguish between * different cgroups in hierarchies. As different cgroups may * share the same effective css, this comparison is always * necessary. */ l1 = &cset->cgrp_links; l2 = &old_cset->cgrp_links; while (1) { struct cgrp_cset_link *link1, *link2; struct cgroup *cgrp1, *cgrp2;
l1 = l1->next; l2 = l2->next; /* See if we reached the end - both lists are equal length. */ if (l1 == &cset->cgrp_links) { BUG_ON(l2 != &old_cset->cgrp_links); break; } else { BUG_ON(l2 == &old_cset->cgrp_links); } /* Locate the cgroups associated with these links. */ link1 = list_entry(l1, struct cgrp_cset_link, cgrp_link); link2 = list_entry(l2, struct cgrp_cset_link, cgrp_link); cgrp1 = link1->cgrp; cgrp2 = link2->cgrp; /* Hierarchies should be linked in the same order. */ BUG_ON(cgrp1->root != cgrp2->root);
/* * If this hierarchy is the hierarchy of the cgroup * that's changing, then we need to check that this * css_set points to the new cgroup; if it's any other * hierarchy, then this css_set should point to the * same cgroup as the old css_set. */ if (cgrp1->root == new_cgrp->root) { if (cgrp1 != new_cgrp) return false; } else { if (cgrp1 != cgrp2) return false; } } return true;}
/** * find_existing_css_set - init css array and find the matching css_set * @old_cset: the css_set that we're using before the cgroup transition * @cgrp: the cgroup that we're moving into * @template: out param for the new set of csses, should be clear on entry */static struct css_set *find_existing_css_set(struct css_set *old_cset, struct cgroup *cgrp, struct cgroup_subsys_state **template){ struct cgroup_root *root = cgrp->root; struct cgroup_subsys *ss; struct css_set *cset; unsigned long key; int i;
/* * Build the set of subsystem state objects that we want to see in the * new css_set. While subsystems can change globally, the entries here * won't change, so no need for locking. */ for_each_subsys(ss, i) { if (unlikely(cgroup_rebind_ss_mask & (1UL << i))) { /* * @ss is leaving this hierarchy and its per-cgroup * csses are about to be killed. Resolve to the * surviving root css so the tasks are migrated there. */ template[i] = cgroup_css(&root->cgrp, ss); WARN_ON_ONCE(!template[i]); } else if (root->subsys_mask & (1UL << i)) { /* * @ss is in this hierarchy, so we want the * effective css from @cgrp. */ template[i] = cgroup_e_css_by_mask(cgrp, ss); } else { /* * @ss is not in this hierarchy, so we don't want * to change the css. */ template[i] = old_cset->subsys[i]; } }
key = css_set_hash(template); hash_for_each_possible(css_set_table, cset, hlist, key) { if (!compare_css_sets(cset, old_cset, cgrp, template)) continue;
/* This css_set matches what we need */ return cset; }
/* No existing cgroup group matched */ return NULL;}
static void free_cgrp_cset_links(struct list_head *links_to_free){ struct cgrp_cset_link *link, *tmp_link;
list_for_each_entry_safe(link, tmp_link, links_to_free, cset_link) { list_del(&link->cset_link); kfree(link); }}
/** * allocate_cgrp_cset_links - allocate cgrp_cset_links * @count: the number of links to allocate * @tmp_links: list_head the allocated links are put on * * Allocate @count cgrp_cset_link structures and chain them on @tmp_links * through ->cset_link. Returns 0 on success or -errno. */static int allocate_cgrp_cset_links(int count, struct list_head *tmp_links){ struct cgrp_cset_link *link; int i;
INIT_LIST_HEAD(tmp_links);
for (i = 0; i < count; i++) { link = kzalloc_obj(*link); if (!link) { free_cgrp_cset_links(tmp_links); return -ENOMEM; } list_add(&link->cset_link, tmp_links); } return 0;}
/** * link_css_set - a helper function to link a css_set to a cgroup * @tmp_links: cgrp_cset_link objects allocated by allocate_cgrp_cset_links() * @cset: the css_set to be linked * @cgrp: the destination cgroup */static void link_css_set(struct list_head *tmp_links, struct css_set *cset, struct cgroup *cgrp){ struct cgrp_cset_link *link;
BUG_ON(list_empty(tmp_links));
if (cgroup_on_dfl(cgrp)) cset->dfl_cgrp = cgrp;
link = list_first_entry(tmp_links, struct cgrp_cset_link, cset_link); link->cset = cset; link->cgrp = cgrp;
/* * Always add links to the tail of the lists so that the lists are * in chronological order. */ list_move_tail(&link->cset_link, &cgrp->cset_links); list_add_tail(&link->cgrp_link, &cset->cgrp_links);
if (cgroup_parent(cgrp)) cgroup_get_live(cgrp);}
/** * find_css_set - return a new css_set with one cgroup updated * @old_cset: the baseline css_set * @cgrp: the cgroup to be updated * * Return a new css_set that's equivalent to @old_cset, but with @cgrp * substituted into the appropriate hierarchy. */static struct css_set *find_css_set(struct css_set *old_cset, struct cgroup *cgrp){ struct cgroup_subsys_state *template[CGROUP_SUBSYS_COUNT] = { }; struct css_set *cset; struct list_head tmp_links; struct cgrp_cset_link *link; struct cgroup_subsys *ss; unsigned long key; int ssid;
lockdep_assert_held(&cgroup_mutex);
/* First see if we already have a cgroup group that matches * the desired set */ spin_lock_irq(&css_set_lock); cset = find_existing_css_set(old_cset, cgrp, template); if (cset) get_css_set(cset); spin_unlock_irq(&css_set_lock);
if (cset) return cset;
cset = kzalloc_obj(*cset); if (!cset) return NULL;
/* Allocate all the cgrp_cset_link objects that we'll need */ if (allocate_cgrp_cset_links(cgroup_root_count, &tmp_links) < 0) { kfree(cset); return NULL; }
refcount_set(&cset->refcount, 1); cset->dom_cset = cset; INIT_LIST_HEAD(&cset->tasks); INIT_LIST_HEAD(&cset->mg_tasks); INIT_LIST_HEAD(&cset->dying_tasks); INIT_LIST_HEAD(&cset->task_iters); INIT_LIST_HEAD(&cset->threaded_csets); INIT_HLIST_NODE(&cset->hlist); INIT_LIST_HEAD(&cset->cgrp_links); INIT_LIST_HEAD(&cset->mg_src_preload_node); INIT_LIST_HEAD(&cset->mg_dst_preload_node); INIT_LIST_HEAD(&cset->mg_node);
/* Copy the set of subsystem state objects generated in * find_existing_css_set() */ memcpy(cset->subsys, template, sizeof(cset->subsys));
spin_lock_irq(&css_set_lock); /* Add reference counts and links from the new css_set. */ list_for_each_entry(link, &old_cset->cgrp_links, cgrp_link) { struct cgroup *c = link->cgrp;
if (c->root == cgrp->root) c = cgrp; link_css_set(&tmp_links, cset, c); }
BUG_ON(!list_empty(&tmp_links));
css_set_count++;
/* Add @cset to the hash table */ key = css_set_hash(cset->subsys); hash_add(css_set_table, &cset->hlist, key);
for_each_subsys(ss, ssid) { struct cgroup_subsys_state *css = cset->subsys[ssid];
list_add_tail(&cset->e_cset_node[ssid], &css->cgroup->e_csets[ssid]); css_get(css); }
spin_unlock_irq(&css_set_lock);
/* * If @cset should be threaded, look up the matching dom_cset and * link them up. We first fully initialize @cset then look for the * dom_cset. It's simpler this way and safe as @cset is guaranteed * to stay empty until we return. */ if (cgroup_is_threaded(cset->dfl_cgrp)) { struct css_set *dcset;
dcset = find_css_set(cset, cset->dfl_cgrp->dom_cgrp); if (!dcset) { put_css_set(cset); return NULL; }
spin_lock_irq(&css_set_lock); cset->dom_cset = dcset; list_add_tail(&cset->threaded_csets_node, &dcset->threaded_csets); spin_unlock_irq(&css_set_lock); }
return cset;}
struct cgroup_root *cgroup_root_from_kf(struct kernfs_root *kf_root){ struct cgroup *root_cgrp = kernfs_root_to_node(kf_root)->priv;
return root_cgrp->root;}
void cgroup_favor_dynmods(struct cgroup_root *root, bool favor){ bool favoring = root->flags & CGRP_ROOT_FAVOR_DYNMODS;
/* * see the comment above CGRP_ROOT_FAVOR_DYNMODS definition. * favordynmods can flip while task is between * cgroup_threadgroup_change_begin() and end(), so down_write global * cgroup_threadgroup_rwsem to synchronize them. * * Once cgroup_enable_per_threadgroup_rwsem is enabled, holding * cgroup_threadgroup_rwsem doesn't exlude tasks between * cgroup_thread_group_change_begin() and end() and thus it's unsafe to * turn off. As the scenario is unlikely, simply disallow disabling once * enabled and print out a warning. */ percpu_down_write(&cgroup_threadgroup_rwsem); if (favor && !favoring) { cgroup_enable_per_threadgroup_rwsem = true; rcu_sync_enter(&cgroup_threadgroup_rwsem.rss); root->flags |= CGRP_ROOT_FAVOR_DYNMODS; } else if (!favor && favoring) { if (cgroup_enable_per_threadgroup_rwsem) pr_warn_once("cgroup favordynmods: per threadgroup rwsem mechanism can't be disabled\n"); rcu_sync_exit(&cgroup_threadgroup_rwsem.rss); root->flags &= ~CGRP_ROOT_FAVOR_DYNMODS; } percpu_up_write(&cgroup_threadgroup_rwsem);}
static int cgroup_init_root_id(struct cgroup_root *root){ int id;
lockdep_assert_held(&cgroup_mutex);
id = idr_alloc_cyclic(&cgroup_hierarchy_idr, root, 0, 0, GFP_KERNEL); if (id < 0) return id;
root->hierarchy_id = id; return 0;}
static void cgroup_exit_root_id(struct cgroup_root *root){ lockdep_assert_held(&cgroup_mutex);
idr_remove(&cgroup_hierarchy_idr, root->hierarchy_id);}
void cgroup_free_root(struct cgroup_root *root){ kfree_rcu(root, rcu);}
static void cgroup_destroy_root(struct cgroup_root *root){ struct cgroup *cgrp = &root->cgrp; struct cgrp_cset_link *link, *tmp_link; int ret;
trace_cgroup_destroy_root(root);
cgroup_lock_and_drain_offline(&cgrp_dfl_root.cgrp);
BUG_ON(atomic_read(&root->nr_cgrps)); BUG_ON(!list_empty(&cgrp->self.children));
ret = blocking_notifier_call_chain(&cgroup_lifetime_notifier, CGROUP_LIFETIME_OFFLINE, cgrp); WARN_ON_ONCE(notifier_to_errno(ret));
/* Rebind all subsystems back to the default hierarchy */ WARN_ON(rebind_subsystems(&cgrp_dfl_root, root->subsys_mask));
/* * Release all the links from cset_links to this hierarchy's * root cgroup */ spin_lock_irq(&css_set_lock);
list_for_each_entry_safe(link, tmp_link, &cgrp->cset_links, cset_link) { list_del(&link->cset_link); list_del(&link->cgrp_link); kfree(link); }
spin_unlock_irq(&css_set_lock);
WARN_ON_ONCE(list_empty(&root->root_list)); list_del_rcu(&root->root_list); cgroup_root_count--;
if (!have_favordynmods) cgroup_favor_dynmods(root, false);
cgroup_exit_root_id(root);
cgroup_unlock();
kernfs_destroy_root(root->kf_root); cgroup_free_root(root);}
/* * Returned cgroup is without refcount but it's valid as long as cset pins it. */static inline struct cgroup *__cset_cgroup_from_root(struct css_set *cset, struct cgroup_root *root){ struct cgroup *res_cgroup = NULL;
if (cset == &init_css_set) { res_cgroup = &root->cgrp; } else if (root == &cgrp_dfl_root) { res_cgroup = cset->dfl_cgrp; } else { struct cgrp_cset_link *link; lockdep_assert_held(&css_set_lock);
list_for_each_entry(link, &cset->cgrp_links, cgrp_link) { struct cgroup *c = link->cgrp;
if (c->root == root) { res_cgroup = c; break; } } }
/* * If cgroup_mutex is not held, the cgrp_cset_link will be freed * before we remove the cgroup root from the root_list. Consequently, * when accessing a cgroup root, the cset_link may have already been * freed, resulting in a NULL res_cgroup. However, by holding the * cgroup_mutex, we ensure that res_cgroup can't be NULL. * If we don't hold cgroup_mutex in the caller, we must do the NULL * check. */ return res_cgroup;}
/* * look up cgroup associated with current task's cgroup namespace on the * specified hierarchy */static struct cgroup *current_cgns_cgroup_from_root(struct cgroup_root *root){ struct cgroup *res = NULL; struct css_set *cset;
lockdep_assert_held(&css_set_lock);
rcu_read_lock();
cset = current->nsproxy->cgroup_ns->root_cset; res = __cset_cgroup_from_root(cset, root);
rcu_read_unlock();
/* * The namespace_sem is held by current, so the root cgroup can't * be umounted. Therefore, we can ensure that the res is non-NULL. */ WARN_ON_ONCE(!res); return res;}
/* * Look up cgroup associated with current task's cgroup namespace on the default * hierarchy. * * Unlike current_cgns_cgroup_from_root(), this doesn't need locks: * - Internal rcu_read_lock is unnecessary because we don't dereference any rcu * pointers. * - css_set_lock is not needed because we just read cset->dfl_cgrp. * - As a bonus returned cgrp is pinned with the current because it cannot * switch cgroup_ns asynchronously. */static struct cgroup *current_cgns_cgroup_dfl(void){ struct css_set *cset;
if (current->nsproxy) { cset = current->nsproxy->cgroup_ns->root_cset; return __cset_cgroup_from_root(cset, &cgrp_dfl_root); } else { /* * NOTE: This function may be called from bpf_cgroup_from_id() * on a task which has already passed exit_nsproxy_namespaces() * and nsproxy == NULL. Fall back to cgrp_dfl_root which will * make all cgroups visible for lookups. */ return &cgrp_dfl_root.cgrp; }}
/* look up cgroup associated with given css_set on the specified hierarchy */static struct cgroup *cset_cgroup_from_root(struct css_set *cset, struct cgroup_root *root){ lockdep_assert_held(&css_set_lock);
return __cset_cgroup_from_root(cset, root);}
/* * Return the cgroup for "task" from the given hierarchy. Must be * called with css_set_lock held to prevent task's groups from being modified. * Must be called with either cgroup_mutex or rcu read lock to prevent the * cgroup root from being destroyed. */struct cgroup *task_cgroup_from_root(struct task_struct *task, struct cgroup_root *root){ /* * No need to lock the task - since we hold css_set_lock the * task can't change groups. */ return cset_cgroup_from_root(task_css_set(task), root);}
/* * A task must hold cgroup_mutex to modify cgroups. * * Any task can increment and decrement the count field without lock. * So in general, code holding cgroup_mutex can't rely on the count * field not changing. However, if the count goes to zero, then only * cgroup_attach_task() can increment it again. Because a count of zero * means that no tasks are currently attached, therefore there is no * way a task attached to that cgroup can fork (the other way to * increment the count). So code holding cgroup_mutex can safely * assume that if the count is zero, it will stay zero. Similarly, if * a task holds cgroup_mutex on a cgroup with zero count, it * knows that the cgroup won't be removed, as cgroup_rmdir() * needs that mutex. * * A cgroup can only be deleted if both its 'count' of using tasks * is zero, and its list of 'children' cgroups is empty. Since all * tasks in the system use _some_ cgroup, and since there is always at * least one task in the system (init, pid == 1), therefore, root cgroup * always has either children cgroups and/or using tasks. So we don't * need a special hack to ensure that root cgroup cannot be deleted. * * P.S. One more locking exception. RCU is used to guard the * update of a tasks cgroup pointer by cgroup_attach_task() */
static struct kernfs_syscall_ops cgroup_kf_syscall_ops;
static char *cgroup_file_name(struct cgroup *cgrp, const struct cftype *cft, char *buf){ struct cgroup_subsys *ss = cft->ss;
if (cft->ss && !(cft->flags & CFTYPE_NO_PREFIX) && !(cgrp->root->flags & CGRP_ROOT_NOPREFIX)) { const char *dbg = (cft->flags & CFTYPE_DEBUG) ? ".__DEBUG__." : "";
snprintf(buf, CGROUP_FILE_NAME_MAX, "%s%s.%s", dbg, cgroup_on_dfl(cgrp) ? ss->name : ss->legacy_name, cft->name); } else { strscpy(buf, cft->name, CGROUP_FILE_NAME_MAX); } return buf;}
/** * cgroup_file_mode - deduce file mode of a control file * @cft: the control file in question * * S_IRUGO for read, S_IWUSR for write. */static umode_t cgroup_file_mode(const struct cftype *cft){ umode_t mode = 0;
if (cft->read_u64 || cft->read_s64 || cft->seq_show) mode |= S_IRUGO;
if (cft->write_u64 || cft->write_s64 || cft->write) { if (cft->flags & CFTYPE_WORLD_WRITABLE) mode |= S_IWUGO; else mode |= S_IWUSR; }
return mode;}
/** * cgroup_calc_subtree_ss_mask - calculate subtree_ss_mask * @subtree_control: the new subtree_control mask to consider * @this_ss_mask: available subsystems * * On the default hierarchy, a subsystem may request other subsystems to be * enabled together through its ->depends_on mask. In such cases, more * subsystems than specified in "cgroup.subtree_control" may be enabled. * * This function calculates which subsystems need to be enabled if * @subtree_control is to be applied while restricted to @this_ss_mask. */static u32 cgroup_calc_subtree_ss_mask(u32 subtree_control, u32 this_ss_mask){ u32 cur_ss_mask = subtree_control; struct cgroup_subsys *ss; int ssid;
lockdep_assert_held(&cgroup_mutex);
cur_ss_mask |= cgrp_dfl_implicit_ss_mask;
while (true) { u32 new_ss_mask = cur_ss_mask;
do_each_subsys_mask(ss, ssid, cur_ss_mask) { new_ss_mask |= ss->depends_on; } while_each_subsys_mask();
/* * Mask out subsystems which aren't available. This can * happen only if some depended-upon subsystems were bound * to non-default hierarchies. */ new_ss_mask &= this_ss_mask;
if (new_ss_mask == cur_ss_mask) break; cur_ss_mask = new_ss_mask; }
return cur_ss_mask;}
/** * cgroup_kn_unlock - unlocking helper for cgroup kernfs methods * @kn: the kernfs_node being serviced * * This helper undoes cgroup_kn_lock_live() and should be invoked before * the method finishes if locking succeeded. Note that once this function * returns the cgroup returned by cgroup_kn_lock_live() may become * inaccessible any time. If the caller intends to continue to access the * cgroup, it should pin it before invoking this function. */void cgroup_kn_unlock(struct kernfs_node *kn){ struct cgroup *cgrp;
if (kernfs_type(kn) == KERNFS_DIR) cgrp = kn->priv; else cgrp = kn_priv(kn);
cgroup_unlock();
kernfs_unbreak_active_protection(kn); cgroup_put(cgrp);}
/** * cgroup_kn_lock_live - locking helper for cgroup kernfs methods * @kn: the kernfs_node being serviced * @drain_offline: perform offline draining on the cgroup * * This helper is to be used by a cgroup kernfs method currently servicing * @kn. It breaks the active protection, performs cgroup locking and * verifies that the associated cgroup is alive. Returns the cgroup if * alive; otherwise, %NULL. A successful return should be undone by a * matching cgroup_kn_unlock() invocation. If @drain_offline is %true, the * cgroup is drained of offlining csses before return. * * Any cgroup kernfs method implementation which requires locking the * associated cgroup should use this helper. It avoids nesting cgroup * locking under kernfs active protection and allows all kernfs operations * including self-removal. */struct cgroup *cgroup_kn_lock_live(struct kernfs_node *kn, bool drain_offline){ struct cgroup *cgrp;
if (kernfs_type(kn) == KERNFS_DIR) cgrp = kn->priv; else cgrp = kn_priv(kn);
/* * We're gonna grab cgroup_mutex which nests outside kernfs * active_ref. cgroup liveliness check alone provides enough * protection against removal. Ensure @cgrp stays accessible and * break the active_ref protection. */ if (!cgroup_tryget(cgrp)) return NULL; kernfs_break_active_protection(kn);
if (drain_offline) cgroup_lock_and_drain_offline(cgrp); else cgroup_lock();
if (!cgroup_is_dead(cgrp)) return cgrp;
cgroup_kn_unlock(kn); return NULL;}
static void cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft){ char name[CGROUP_FILE_NAME_MAX];
lockdep_assert_held(&cgroup_mutex);
if (cft->file_offset) { struct cgroup_subsys_state *css = cgroup_css(cgrp, cft->ss); struct cgroup_file *cfile = (void *)css + cft->file_offset;
spin_lock_irq(&cfile->lock); WRITE_ONCE(cfile->kn, NULL); spin_unlock_irq(&cfile->lock);
timer_delete_sync(&cfile->notify_timer); }
kernfs_remove_by_name(cgrp->kn, cgroup_file_name(cgrp, cft, name));}
/** * css_clear_dir - remove subsys files in a cgroup directory * @css: target css */static void css_clear_dir(struct cgroup_subsys_state *css){ struct cgroup *cgrp = css->cgroup; struct cftype *cfts;
if (!(css->flags & CSS_VISIBLE)) return;
css->flags &= ~CSS_VISIBLE;
if (css_is_self(css)) { if (cgroup_on_dfl(cgrp)) { cgroup_addrm_files(css, cgrp, cgroup_base_files, false); if (cgroup_psi_enabled()) cgroup_addrm_files(css, cgrp, cgroup_psi_files, false); } else { cgroup_addrm_files(css, cgrp, cgroup1_base_files, false); } } else { list_for_each_entry(cfts, &css->ss->cfts, node) cgroup_addrm_files(css, cgrp, cfts, false); }}
/** * css_populate_dir - create subsys files in a cgroup directory * @css: target css * * On failure, no file is added. */static int css_populate_dir(struct cgroup_subsys_state *css){ struct cgroup *cgrp = css->cgroup; struct cftype *cfts, *failed_cfts; int ret;
if (css->flags & CSS_VISIBLE) return 0;
if (css_is_self(css)) { if (cgroup_on_dfl(cgrp)) { ret = cgroup_addrm_files(css, cgrp, cgroup_base_files, true); if (ret < 0) return ret;
if (cgroup_psi_enabled()) { ret = cgroup_addrm_files(css, cgrp, cgroup_psi_files, true); if (ret < 0) { cgroup_addrm_files(css, cgrp, cgroup_base_files, false); return ret; } } } else { ret = cgroup_addrm_files(css, cgrp, cgroup1_base_files, true); if (ret < 0) return ret; } } else { list_for_each_entry(cfts, &css->ss->cfts, node) { ret = cgroup_addrm_files(css, cgrp, cfts, true); if (ret < 0) { failed_cfts = cfts; goto err; } } }
css->flags |= CSS_VISIBLE;
return 0;err: list_for_each_entry(cfts, &css->ss->cfts, node) { if (cfts == failed_cfts) break; cgroup_addrm_files(css, cgrp, cfts, false); } return ret;}
int rebind_subsystems(struct cgroup_root *dst_root, u32 ss_mask){ struct cgroup *dcgrp = &dst_root->cgrp; struct cgroup_subsys *ss; int ssid, ret; u32 dfl_disable_ss_mask = 0;
lockdep_assert_held(&cgroup_mutex);
do_each_subsys_mask(ss, ssid, ss_mask) { /* * If @ss has non-root csses attached to it, can't move. * If @ss is an implicit controller, it is exempt from this * rule and can be stolen. */ if (css_next_child(NULL, cgroup_css(&ss->root->cgrp, ss)) && !ss->implicit_on_dfl) return -EBUSY;
/* can't move between two non-dummy roots either */ if (ss->root != &cgrp_dfl_root && dst_root != &cgrp_dfl_root) return -EBUSY;
/* * Collect ssid's that need to be disabled from default * hierarchy. */ if (ss->root == &cgrp_dfl_root) dfl_disable_ss_mask |= 1 << ssid;
} while_each_subsys_mask();
if (dfl_disable_ss_mask) { struct cgroup *scgrp = &cgrp_dfl_root.cgrp;
/* * Controllers leaving the default hierarchy are disabled * together. cgroup_rebind_ss_mask makes cgroup_apply_control() * migrate their tasks to the root css, so the per-cgroup csses * are unpopulated when cgroup_finalize_control() kills them. * Clear it before cgroup_finalize_control(), which does no * css_set lookup. */ cgrp_dfl_root.subsys_mask &= ~dfl_disable_ss_mask; cgroup_rebind_ss_mask = dfl_disable_ss_mask; WARN_ON(cgroup_apply_control(scgrp)); cgroup_rebind_ss_mask = 0; cgroup_finalize_control(scgrp, 0); }
do_each_subsys_mask(ss, ssid, ss_mask) { struct cgroup_root *src_root = ss->root; struct cgroup *scgrp = &src_root->cgrp; struct cgroup_subsys_state *css = cgroup_css(scgrp, ss); struct css_set *cset, *cset_pos; struct css_task_iter *it;
WARN_ON(!css || cgroup_css(dcgrp, ss));
if (src_root != &cgrp_dfl_root) { /* * Disable from the source, migrating its tasks to the * root css first (see cgroup_rebind_ss_mask). */ src_root->subsys_mask &= ~(1 << ssid); cgroup_rebind_ss_mask = 1 << ssid; WARN_ON(cgroup_apply_control(scgrp)); cgroup_rebind_ss_mask = 0; cgroup_finalize_control(scgrp, 0); }
/* rebind */ RCU_INIT_POINTER(scgrp->subsys[ssid], NULL); rcu_assign_pointer(dcgrp->subsys[ssid], css); ss->root = dst_root;
spin_lock_irq(&css_set_lock); css->cgroup = dcgrp; WARN_ON(!list_empty(&dcgrp->e_csets[ss->id])); list_for_each_entry_safe(cset, cset_pos, &scgrp->e_csets[ss->id], e_cset_node[ss->id]) { list_move_tail(&cset->e_cset_node[ss->id], &dcgrp->e_csets[ss->id]); /* * all css_sets of scgrp together in same order to dcgrp, * patch in-flight iterators to preserve correct iteration. * since the iterator is always advanced right away and * finished when it->cset_pos meets it->cset_head, so only * update it->cset_head is enough here. */ list_for_each_entry(it, &cset->task_iters, iters_node) if (it->cset_head == &scgrp->e_csets[ss->id]) it->cset_head = &dcgrp->e_csets[ss->id]; } spin_unlock_irq(&css_set_lock);
/* default hierarchy doesn't enable controllers by default */ dst_root->subsys_mask |= 1 << ssid; if (dst_root == &cgrp_dfl_root) { static_branch_enable(cgroup_subsys_on_dfl_key[ssid]); } else { dcgrp->subtree_control |= 1 << ssid; static_branch_disable(cgroup_subsys_on_dfl_key[ssid]); }
ret = cgroup_apply_control(dcgrp); if (ret) pr_warn("partial failure to rebind %s controller (err=%d)\n", ss->name, ret);
if (ss->bind) ss->bind(css); } while_each_subsys_mask();
kernfs_activate(dcgrp->kn); return 0;}
int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node, struct kernfs_root *kf_root){ int len = 0; char *buf = NULL; struct cgroup_root *kf_cgroot = cgroup_root_from_kf(kf_root); struct cgroup *ns_cgroup;
buf = kmalloc(PATH_MAX, GFP_KERNEL); if (!buf) return -ENOMEM;
spin_lock_irq(&css_set_lock); ns_cgroup = current_cgns_cgroup_from_root(kf_cgroot); len = kernfs_path_from_node(kf_node, ns_cgroup->kn, buf, PATH_MAX); spin_unlock_irq(&css_set_lock);
if (len == -E2BIG) len = -ERANGE; else if (len > 0) { seq_escape(sf, buf, " \t\n\\"); len = 0; } kfree(buf); return len;}
enum cgroup2_param { Opt_nsdelegate, Opt_favordynmods, Opt_memory_localevents, Opt_memory_recursiveprot, Opt_memory_hugetlb_accounting, Opt_pids_localevents, nr__cgroup2_params};
static const struct fs_parameter_spec cgroup2_fs_parameters[] = { fsparam_flag("nsdelegate", Opt_nsdelegate), fsparam_flag("favordynmods", Opt_favordynmods), fsparam_flag("memory_localevents", Opt_memory_localevents), fsparam_flag("memory_recursiveprot", Opt_memory_recursiveprot), fsparam_flag("memory_hugetlb_accounting", Opt_memory_hugetlb_accounting), fsparam_flag("pids_localevents", Opt_pids_localevents), {}};
static int cgroup2_parse_param(struct fs_context *fc, struct fs_parameter *param){ struct cgroup_fs_context *ctx = cgroup_fc2context(fc); struct fs_parse_result result; int opt;
opt = fs_parse(fc, cgroup2_fs_parameters, param, &result); if (opt < 0) return opt;
switch (opt) { case Opt_nsdelegate: ctx->flags |= CGRP_ROOT_NS_DELEGATE; return 0; case Opt_favordynmods: ctx->flags |= CGRP_ROOT_FAVOR_DYNMODS; return 0; case Opt_memory_localevents: ctx->flags |= CGRP_ROOT_MEMORY_LOCAL_EVENTS; return 0; case Opt_memory_recursiveprot: ctx->flags |= CGRP_ROOT_MEMORY_RECURSIVE_PROT; return 0; case Opt_memory_hugetlb_accounting: ctx->flags |= CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING; return 0; case Opt_pids_localevents: ctx->flags |= CGRP_ROOT_PIDS_LOCAL_EVENTS; return 0; } return -EINVAL;}
struct cgroup_of_peak *of_peak(struct kernfs_open_file *of){ struct cgroup_file_ctx *ctx = of->priv;
return &ctx->peak;}
static void apply_cgroup_root_flags(unsigned int root_flags){ if (current->nsproxy->cgroup_ns == &init_cgroup_ns) { if (root_flags & CGRP_ROOT_NS_DELEGATE) cgrp_dfl_root.flags |= CGRP_ROOT_NS_DELEGATE; else cgrp_dfl_root.flags &= ~CGRP_ROOT_NS_DELEGATE;
cgroup_favor_dynmods(&cgrp_dfl_root, root_flags & CGRP_ROOT_FAVOR_DYNMODS);
if (root_flags & CGRP_ROOT_MEMORY_LOCAL_EVENTS) cgrp_dfl_root.flags |= CGRP_ROOT_MEMORY_LOCAL_EVENTS; else cgrp_dfl_root.flags &= ~CGRP_ROOT_MEMORY_LOCAL_EVENTS;
if (root_flags & CGRP_ROOT_MEMORY_RECURSIVE_PROT) cgrp_dfl_root.flags |= CGRP_ROOT_MEMORY_RECURSIVE_PROT; else cgrp_dfl_root.flags &= ~CGRP_ROOT_MEMORY_RECURSIVE_PROT;
if (root_flags & CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING) cgrp_dfl_root.flags |= CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING; else cgrp_dfl_root.flags &= ~CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING;
if (root_flags & CGRP_ROOT_PIDS_LOCAL_EVENTS) cgrp_dfl_root.flags |= CGRP_ROOT_PIDS_LOCAL_EVENTS; else cgrp_dfl_root.flags &= ~CGRP_ROOT_PIDS_LOCAL_EVENTS; }}
static int cgroup_show_options(struct seq_file *seq, struct kernfs_root *kf_root){ if (cgrp_dfl_root.flags & CGRP_ROOT_NS_DELEGATE) seq_puts(seq, ",nsdelegate"); if (cgrp_dfl_root.flags & CGRP_ROOT_FAVOR_DYNMODS) seq_puts(seq, ",favordynmods"); if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_LOCAL_EVENTS) seq_puts(seq, ",memory_localevents"); if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_RECURSIVE_PROT) seq_puts(seq, ",memory_recursiveprot"); if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING) seq_puts(seq, ",memory_hugetlb_accounting"); if (cgrp_dfl_root.flags & CGRP_ROOT_PIDS_LOCAL_EVENTS) seq_puts(seq, ",pids_localevents"); return 0;}
static int cgroup_reconfigure(struct fs_context *fc){ struct cgroup_fs_context *ctx = cgroup_fc2context(fc);
apply_cgroup_root_flags(ctx->flags); return 0;}
static void init_cgroup_housekeeping(struct cgroup *cgrp){ struct cgroup_subsys *ss; int ssid;
INIT_LIST_HEAD(&cgrp->self.sibling); INIT_LIST_HEAD(&cgrp->self.children); INIT_LIST_HEAD(&cgrp->cset_links); INIT_LIST_HEAD(&cgrp->pidlists); mutex_init(&cgrp->pidlist_mutex); cgrp->self.cgroup = cgrp; cgrp->self.flags |= CSS_ONLINE; cgrp->dom_cgrp = cgrp; cgrp->max_descendants = INT_MAX; cgrp->max_depth = INT_MAX; prev_cputime_init(&cgrp->prev_cputime);
for_each_subsys(ss, ssid) INIT_LIST_HEAD(&cgrp->e_csets[ssid]);
#ifdef CONFIG_CGROUP_BPF for (int i = 0; i < ARRAY_SIZE(cgrp->bpf.revisions); i++) cgrp->bpf.revisions[i] = 1;#endif
init_waitqueue_head(&cgrp->offline_waitq); INIT_WORK(&cgrp->release_agent_work, cgroup1_release_agent);}
void init_cgroup_root(struct cgroup_fs_context *ctx){ struct cgroup_root *root = ctx->root; struct cgroup *cgrp = &root->cgrp;
INIT_LIST_HEAD_RCU(&root->root_list); atomic_set(&root->nr_cgrps, 1); cgrp->root = root; init_cgroup_housekeeping(cgrp);
/* DYNMODS must be modified through cgroup_favor_dynmods() */ root->flags = ctx->flags & ~CGRP_ROOT_FAVOR_DYNMODS; if (ctx->release_agent) strscpy(root->release_agent_path, ctx->release_agent, PATH_MAX); if (ctx->name) strscpy(root->name, ctx->name, MAX_CGROUP_ROOT_NAMELEN); if (ctx->cpuset_clone_children) set_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags);}
int cgroup_setup_root(struct cgroup_root *root, u32 ss_mask){ LIST_HEAD(tmp_links); struct cgroup *root_cgrp = &root->cgrp; struct kernfs_syscall_ops *kf_sops; struct css_set *cset; int i, ret;
lockdep_assert_held(&cgroup_mutex);
ret = percpu_ref_init(&root_cgrp->self.refcnt, css_release, 0, GFP_KERNEL); if (ret) goto out;
/* * We're accessing css_set_count without locking css_set_lock here, * but that's OK - it can only be increased by someone holding * cgroup_lock, and that's us. Later rebinding may disable * controllers on the default hierarchy and thus create new csets, * which can't be more than the existing ones. Allocate 2x. */ ret = allocate_cgrp_cset_links(2 * css_set_count, &tmp_links); if (ret) goto cancel_ref;
ret = cgroup_init_root_id(root); if (ret) goto cancel_ref;
kf_sops = root == &cgrp_dfl_root ? &cgroup_kf_syscall_ops : &cgroup1_kf_syscall_ops;
root->kf_root = kernfs_create_root(kf_sops, KERNFS_ROOT_CREATE_DEACTIVATED | KERNFS_ROOT_SUPPORT_EXPORTOP | KERNFS_ROOT_SUPPORT_USER_XATTR | KERNFS_ROOT_INVARIANT_PARENT, root_cgrp); if (IS_ERR(root->kf_root)) { ret = PTR_ERR(root->kf_root); goto exit_root_id; } root_cgrp->kn = kernfs_root_to_node(root->kf_root); WARN_ON_ONCE(cgroup_ino(root_cgrp) != 1); root_cgrp->ancestors[0] = root_cgrp;
ret = css_populate_dir(&root_cgrp->self); if (ret) goto destroy_root;
ret = css_rstat_init(&root_cgrp->self); if (ret) goto destroy_root;
ret = rebind_subsystems(root, ss_mask); if (ret) goto exit_stats;
ret = blocking_notifier_call_chain(&cgroup_lifetime_notifier, CGROUP_LIFETIME_ONLINE, root_cgrp); WARN_ON_ONCE(notifier_to_errno(ret));
trace_cgroup_setup_root(root);
/* * There must be no failure case after here, since rebinding takes * care of subsystems' refcounts, which are explicitly dropped in * the failure exit path. */ list_add_rcu(&root->root_list, &cgroup_roots); cgroup_root_count++;
/* * Link the root cgroup in this hierarchy into all the css_set * objects. */ spin_lock_irq(&css_set_lock); hash_for_each(css_set_table, i, cset, hlist) { link_css_set(&tmp_links, cset, root_cgrp); if (css_set_populated(cset)) css_update_populated(&root_cgrp->self, true); } spin_unlock_irq(&css_set_lock);
BUG_ON(!list_empty(&root_cgrp->self.children)); BUG_ON(atomic_read(&root->nr_cgrps) != 1);
ret = 0; goto out;
exit_stats: css_rstat_exit(&root_cgrp->self);destroy_root: kernfs_destroy_root(root->kf_root); root->kf_root = NULL;exit_root_id: cgroup_exit_root_id(root);cancel_ref: percpu_ref_exit(&root_cgrp->self.refcnt);out: free_cgrp_cset_links(&tmp_links); return ret;}
int cgroup_do_get_tree(struct fs_context *fc){ struct cgroup_fs_context *ctx = cgroup_fc2context(fc); int ret;
ctx->kfc.root = ctx->root->kf_root; if (fc->fs_type == &cgroup2_fs_type) ctx->kfc.magic = CGROUP2_SUPER_MAGIC; else ctx->kfc.magic = CGROUP_SUPER_MAGIC; ret = kernfs_get_tree(fc);
/* * In non-init cgroup namespace, instead of root cgroup's dentry, * we return the dentry corresponding to the cgroupns->root_cgrp. */ if (!ret && ctx->ns != &init_cgroup_ns) { struct dentry *nsdentry; struct super_block *sb = fc->root->d_sb; struct cgroup *cgrp;
cgroup_lock(); spin_lock_irq(&css_set_lock);
cgrp = cset_cgroup_from_root(ctx->ns->root_cset, ctx->root);
spin_unlock_irq(&css_set_lock); cgroup_unlock();
nsdentry = kernfs_node_dentry(cgrp->kn, sb); dput(fc->root); if (IS_ERR(nsdentry)) { deactivate_locked_super(sb); ret = PTR_ERR(nsdentry); nsdentry = NULL; } fc->root = nsdentry; }
if (!ctx->kfc.new_sb_created) cgroup_put(&ctx->root->cgrp);
return ret;}
/* * Destroy a cgroup filesystem context. */static void cgroup_fs_context_free(struct fs_context *fc){ struct cgroup_fs_context *ctx = cgroup_fc2context(fc);
kfree(ctx->name); kfree(ctx->release_agent); put_cgroup_ns(ctx->ns); kernfs_free_fs_context(fc); kfree(ctx);}
static int cgroup_get_tree(struct fs_context *fc){ struct cgroup_fs_context *ctx = cgroup_fc2context(fc); int ret;
WRITE_ONCE(cgrp_dfl_visible, true); cgroup_get_live(&cgrp_dfl_root.cgrp); ctx->root = &cgrp_dfl_root;
ret = cgroup_do_get_tree(fc); if (!ret) apply_cgroup_root_flags(ctx->flags); return ret;}
static const struct fs_context_operations cgroup_fs_context_ops = { .free = cgroup_fs_context_free, .parse_param = cgroup2_parse_param, .get_tree = cgroup_get_tree, .reconfigure = cgroup_reconfigure,};
static const struct fs_context_operations cgroup1_fs_context_ops = { .free = cgroup_fs_context_free, .parse_param = cgroup1_parse_param, .get_tree = cgroup1_get_tree, .reconfigure = cgroup1_reconfigure,};
/* * Initialise the cgroup filesystem creation/reconfiguration context. Notably, * we select the namespace we're going to use. */static int cgroup_init_fs_context(struct fs_context *fc){ struct cgroup_fs_context *ctx;
ctx = kzalloc_obj(struct cgroup_fs_context); if (!ctx) return -ENOMEM;
ctx->ns = current->nsproxy->cgroup_ns; get_cgroup_ns(ctx->ns); fc->fs_private = &ctx->kfc; if (fc->fs_type == &cgroup2_fs_type) fc->ops = &cgroup_fs_context_ops; else fc->ops = &cgroup1_fs_context_ops; put_user_ns(fc->user_ns); fc->user_ns = get_user_ns(ctx->ns->user_ns); fc->global = true;
if (have_favordynmods) ctx->flags |= CGRP_ROOT_FAVOR_DYNMODS;
return 0;}
static void cgroup_kill_sb(struct super_block *sb){ struct kernfs_root *kf_root = kernfs_root_from_sb(sb); struct cgroup_root *root = cgroup_root_from_kf(kf_root);
/* * If @root doesn't have any children, start killing it. * This prevents new mounts by disabling percpu_ref_tryget_live(). * * And don't kill the default root. */ if (list_empty(&root->cgrp.self.children) && root != &cgrp_dfl_root && !percpu_ref_is_dying(&root->cgrp.self.refcnt)) percpu_ref_kill(&root->cgrp.self.refcnt); cgroup_put(&root->cgrp); kernfs_kill_sb(sb);}
struct file_system_type cgroup_fs_type = { .name = "cgroup", .init_fs_context = cgroup_init_fs_context, .parameters = cgroup1_fs_parameters, .kill_sb = cgroup_kill_sb, .fs_flags = FS_USERNS_MOUNT,};
static struct file_system_type cgroup2_fs_type = { .name = "cgroup2", .init_fs_context = cgroup_init_fs_context, .parameters = cgroup2_fs_parameters, .kill_sb = cgroup_kill_sb, .fs_flags = FS_USERNS_MOUNT,};
#ifdef CONFIG_CPUSETS_V1enum cpuset_param { Opt_cpuset_v2_mode,};
static const struct fs_parameter_spec cpuset_fs_parameters[] = { fsparam_flag ("cpuset_v2_mode", Opt_cpuset_v2_mode), {}};
static int cpuset_parse_param(struct fs_context *fc, struct fs_parameter *param){ struct cgroup_fs_context *ctx = cgroup_fc2context(fc); struct fs_parse_result result; int opt;
opt = fs_parse(fc, cpuset_fs_parameters, param, &result); if (opt < 0) return opt;
switch (opt) { case Opt_cpuset_v2_mode: ctx->flags |= CGRP_ROOT_CPUSET_V2_MODE; return 0; } return -EINVAL;}
static const struct fs_context_operations cpuset_fs_context_ops = { .get_tree = cgroup1_get_tree, .free = cgroup_fs_context_free, .parse_param = cpuset_parse_param,};
/* * This is ugly, but preserves the userspace API for existing cpuset * users. If someone tries to mount the "cpuset" filesystem, we * silently switch it to mount "cgroup" instead */static int cpuset_init_fs_context(struct fs_context *fc){ char *agent = kstrdup("/sbin/cpuset_release_agent", GFP_USER); struct cgroup_fs_context *ctx; int err;
err = cgroup_init_fs_context(fc); if (err) { kfree(agent); return err; }
fc->ops = &cpuset_fs_context_ops;
ctx = cgroup_fc2context(fc); ctx->subsys_mask = 1 << cpuset_cgrp_id; ctx->flags |= CGRP_ROOT_NOPREFIX; ctx->release_agent = agent;
get_filesystem(&cgroup_fs_type); put_filesystem(fc->fs_type); fc->fs_type = &cgroup_fs_type;
return 0;}
static struct file_system_type cpuset_fs_type = { .name = "cpuset", .init_fs_context = cpuset_init_fs_context, .parameters = cpuset_fs_parameters, .fs_flags = FS_USERNS_MOUNT,};#endif
int cgroup_path_ns_locked(struct cgroup *cgrp, char *buf, size_t buflen, struct cgroup_namespace *ns){ struct cgroup *root = cset_cgroup_from_root(ns->root_cset, cgrp->root);
return kernfs_path_from_node(cgrp->kn, root->kn, buf, buflen);}
int cgroup_path_ns(struct cgroup *cgrp, char *buf, size_t buflen, struct cgroup_namespace *ns){ int ret;
cgroup_lock(); spin_lock_irq(&css_set_lock);
ret = cgroup_path_ns_locked(cgrp, buf, buflen, ns);
spin_unlock_irq(&css_set_lock); cgroup_unlock();
return ret;}EXPORT_SYMBOL_GPL(cgroup_path_ns);
/** * cgroup_attach_lock - Lock for ->attach() * @lock_mode: whether acquire and acquire which rwsem * @tsk: thread group to lock * * cgroup migration sometimes needs to stabilize threadgroups against forks and * exits by write-locking cgroup_threadgroup_rwsem. However, some ->attach() * implementations (e.g. cpuset), also need to disable CPU hotplug. * Unfortunately, letting ->attach() operations acquire cpus_read_lock() can * lead to deadlocks. * * Bringing up a CPU may involve creating and destroying tasks which requires * read-locking threadgroup_rwsem, so threadgroup_rwsem nests inside * cpus_read_lock(). If we call an ->attach() which acquires the cpus lock while * write-locking threadgroup_rwsem, the locking order is reversed and we end up * waiting for an on-going CPU hotplug operation which in turn is waiting for * the threadgroup_rwsem to be released to create new tasks. For more details: * * http://lkml.kernel.org/r/20220711174629.uehfmqegcwn2lqzu@wubuntu * * Resolve the situation by always acquiring cpus_read_lock() before optionally * write-locking cgroup_threadgroup_rwsem. This allows ->attach() to assume that * CPU hotplug is disabled on entry. * * When favordynmods is enabled, take per threadgroup rwsem to reduce overhead * on dynamic cgroup modifications. see the comment above * CGRP_ROOT_FAVOR_DYNMODS definition. * * tsk is not NULL only when writing to cgroup.procs. */void cgroup_attach_lock(enum cgroup_attach_lock_mode lock_mode, struct task_struct *tsk){ cpus_read_lock();
switch (lock_mode) { case CGRP_ATTACH_LOCK_NONE: break; case CGRP_ATTACH_LOCK_GLOBAL: percpu_down_write(&cgroup_threadgroup_rwsem); break; case CGRP_ATTACH_LOCK_PER_THREADGROUP: down_write(&tsk->signal->cgroup_threadgroup_rwsem); break; default: pr_warn("cgroup: Unexpected attach lock mode."); break; }}
/** * cgroup_attach_unlock - Undo cgroup_attach_lock() * @lock_mode: whether release and release which rwsem * @tsk: thread group to lock */void cgroup_attach_unlock(enum cgroup_attach_lock_mode lock_mode, struct task_struct *tsk){ switch (lock_mode) { case CGRP_ATTACH_LOCK_NONE: break; case CGRP_ATTACH_LOCK_GLOBAL: percpu_up_write(&cgroup_threadgroup_rwsem); break; case CGRP_ATTACH_LOCK_PER_THREADGROUP: up_write(&tsk->signal->cgroup_threadgroup_rwsem); break; default: pr_warn("cgroup: Unexpected attach lock mode."); break; }
cpus_read_unlock();}
/** * cgroup_migrate_add_task - add a migration target task to a migration context * @task: target task * @mgctx: target migration context * * Add @task, which is a migration target, to @mgctx->tset. This function * becomes noop if @task doesn't need to be migrated. @task's css_set * should have been added as a migration source and @task->cg_list will be * moved from the css_set's tasks list to mg_tasks one. */static void cgroup_migrate_add_task(struct task_struct *task, struct cgroup_mgctx *mgctx){ struct css_set *cset;
lockdep_assert_held(&css_set_lock);
/* @task either already exited or can't exit until the end */ if (task->flags & PF_EXITING) return;
/* cgroup_threadgroup_rwsem protects racing against forks */ WARN_ON_ONCE(list_empty(&task->cg_list));
cset = task_css_set(task); if (!cset->mg_src_cgrp) return;
mgctx->tset.nr_tasks++;
css_set_skip_task_iters(cset, task); list_move_tail(&task->cg_list, &cset->mg_tasks); if (list_empty(&cset->mg_node)) list_add_tail(&cset->mg_node, &mgctx->tset.src_csets); if (list_empty(&cset->mg_dst_cset->mg_node)) list_add_tail(&cset->mg_dst_cset->mg_node, &mgctx->tset.dst_csets);}
/** * cgroup_taskset_first - reset taskset and return the first task * @tset: taskset of interest * @dst_cssp: output variable for the destination css * * @tset iteration is initialized and the first task is returned. */struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset, struct cgroup_subsys_state **dst_cssp){ tset->cur_cset = list_first_entry(tset->csets, struct css_set, mg_node); tset->cur_task = NULL;
return cgroup_taskset_next(tset, dst_cssp);}
/** * cgroup_taskset_next - iterate to the next task in taskset * @tset: taskset of interest * @dst_cssp: output variable for the destination css * * Return the next task in @tset. Iteration must have been initialized * with cgroup_taskset_first(). */struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset, struct cgroup_subsys_state **dst_cssp){ struct css_set *cset = tset->cur_cset; struct task_struct *task = tset->cur_task;
while (CGROUP_HAS_SUBSYS_CONFIG && &cset->mg_node != tset->csets) { if (!task) task = list_first_entry(&cset->mg_tasks, struct task_struct, cg_list); else task = list_next_entry(task, cg_list);
if (&task->cg_list != &cset->mg_tasks) { tset->cur_cset = cset; tset->cur_task = task;
/* * This function may be called both before and * after cgroup_migrate_execute(). The two cases * can be distinguished by looking at whether @cset * has its ->mg_dst_cset set. */ if (cset->mg_dst_cset) *dst_cssp = cset->mg_dst_cset->subsys[tset->ssid]; else *dst_cssp = cset->subsys[tset->ssid];
return task; }
cset = list_next_entry(cset, mg_node); task = NULL; }
return NULL;}
/** * cgroup_migrate_execute - migrate a taskset * @mgctx: migration context * * Migrate tasks in @mgctx as setup by migration preparation functions. * This function fails iff one of the ->can_attach callbacks fails and * guarantees that either all or none of the tasks in @mgctx are migrated. * @mgctx is consumed regardless of success. */static int cgroup_migrate_execute(struct cgroup_mgctx *mgctx){ struct cgroup_taskset *tset = &mgctx->tset; struct cgroup_subsys *ss; struct task_struct *task, *tmp_task; struct css_set *cset, *tmp_cset; int ssid, failed_ssid, ret;
/* check that we can legitimately attach to the cgroup */ if (tset->nr_tasks) { do_each_subsys_mask(ss, ssid, mgctx->ss_mask) { if (ss->can_attach) { tset->ssid = ssid; ret = ss->can_attach(tset); if (ret) { failed_ssid = ssid; goto out_cancel_attach; } } } while_each_subsys_mask(); }
/* * Now that we're guaranteed success, proceed to move all tasks to * the new cgroup. There are no failure cases after here, so this * is the commit point. */ spin_lock_irq(&css_set_lock); list_for_each_entry(cset, &tset->src_csets, mg_node) { list_for_each_entry_safe(task, tmp_task, &cset->mg_tasks, cg_list) { struct css_set *from_cset = task_css_set(task); struct css_set *to_cset = cset->mg_dst_cset;
get_css_set(to_cset); to_cset->nr_tasks++; css_set_move_task(task, from_cset, to_cset, true); from_cset->nr_tasks--; /* * If the source or destination cgroup is frozen, * the task might require to change its state. */ cgroup_freezer_migrate_task(task, from_cset->dfl_cgrp, to_cset->dfl_cgrp); put_css_set_locked(from_cset);
} } spin_unlock_irq(&css_set_lock);
/* * Migration is committed, all target tasks are now on dst_csets. * Nothing is sensitive to fork() after this point. Notify * controllers that migration is complete. */ tset->csets = &tset->dst_csets;
if (tset->nr_tasks) { do_each_subsys_mask(ss, ssid, mgctx->ss_mask) { if (ss->attach) { tset->ssid = ssid; ss->attach(tset); } } while_each_subsys_mask(); }
ret = 0; goto out_release_tset;
out_cancel_attach: if (tset->nr_tasks) { do_each_subsys_mask(ss, ssid, mgctx->ss_mask) { if (ssid == failed_ssid) break; if (ss->cancel_attach) { tset->ssid = ssid; ss->cancel_attach(tset); } } while_each_subsys_mask(); }out_release_tset: spin_lock_irq(&css_set_lock); list_splice_init(&tset->dst_csets, &tset->src_csets); list_for_each_entry_safe(cset, tmp_cset, &tset->src_csets, mg_node) { list_splice_tail_init(&cset->mg_tasks, &cset->tasks); list_del_init(&cset->mg_node); } spin_unlock_irq(&css_set_lock);
/* * Re-initialize the cgroup_taskset structure in case it is reused * again in another cgroup_migrate_add_task()/cgroup_migrate_execute() * iteration. */ tset->nr_tasks = 0; tset->csets = &tset->src_csets; return ret;}
/** * cgroup_migrate_vet_dst - verify whether a cgroup can be migration destination * @dst_cgrp: destination cgroup to test * * On the default hierarchy, except for the mixable, (possible) thread root * and threaded cgroups, subtree_control must be zero for migration * destination cgroups with tasks so that child cgroups don't compete * against tasks. */int cgroup_migrate_vet_dst(struct cgroup *dst_cgrp){ /* v1 doesn't have any restriction */ if (!cgroup_on_dfl(dst_cgrp)) return 0;
/* verify @dst_cgrp can host resources */ if (!cgroup_is_valid_domain(dst_cgrp->dom_cgrp)) return -EOPNOTSUPP;
/* * If @dst_cgrp is already or can become a thread root or is * threaded, it doesn't matter. */ if (cgroup_can_be_thread_root(dst_cgrp) || cgroup_is_threaded(dst_cgrp)) return 0;
/* apply no-internal-process constraint */ if (dst_cgrp->subtree_control) return -EBUSY;
return 0;}
/** * cgroup_migrate_finish - cleanup after attach * @mgctx: migration context * * Undo cgroup_migrate_add_src() and cgroup_migrate_prepare_dst(). See * those functions for details. */void cgroup_migrate_finish(struct cgroup_mgctx *mgctx){ struct css_set *cset, *tmp_cset;
lockdep_assert_held(&cgroup_mutex);
spin_lock_irq(&css_set_lock);
list_for_each_entry_safe(cset, tmp_cset, &mgctx->preloaded_src_csets, mg_src_preload_node) { cset->mg_src_cgrp = NULL; cset->mg_dst_cgrp = NULL; cset->mg_dst_cset = NULL; list_del_init(&cset->mg_src_preload_node); put_css_set_locked(cset); }
list_for_each_entry_safe(cset, tmp_cset, &mgctx->preloaded_dst_csets, mg_dst_preload_node) { cset->mg_src_cgrp = NULL; cset->mg_dst_cgrp = NULL; cset->mg_dst_cset = NULL; list_del_init(&cset->mg_dst_preload_node); put_css_set_locked(cset); }
spin_unlock_irq(&css_set_lock);}
/** * cgroup_migrate_add_src - add a migration source css_set * @src_cset: the source css_set to add * @dst_cgrp: the destination cgroup * @mgctx: migration context * * Tasks belonging to @src_cset are about to be migrated to @dst_cgrp. Pin * @src_cset and add it to @mgctx->src_csets, which should later be cleaned * up by cgroup_migrate_finish(). * * This function may be called without holding cgroup_threadgroup_rwsem * even if the target is a process. Threads may be created and destroyed * but as long as cgroup_mutex is not dropped, no new css_set can be put * into play and the preloaded css_sets are guaranteed to cover all * migrations. */void cgroup_migrate_add_src(struct css_set *src_cset, struct cgroup *dst_cgrp, struct cgroup_mgctx *mgctx){ struct cgroup *src_cgrp;
lockdep_assert_held(&cgroup_mutex); lockdep_assert_held(&css_set_lock);
/* * If ->dead, @src_set is associated with one or more dead cgroups * and doesn't contain any migratable tasks. Ignore it early so * that the rest of migration path doesn't get confused by it. */ if (src_cset->dead) return;
if (!list_empty(&src_cset->mg_src_preload_node)) return;
src_cgrp = cset_cgroup_from_root(src_cset, dst_cgrp->root);
WARN_ON(src_cset->mg_src_cgrp); WARN_ON(src_cset->mg_dst_cgrp); WARN_ON(!list_empty(&src_cset->mg_tasks)); WARN_ON(!list_empty(&src_cset->mg_node));
src_cset->mg_src_cgrp = src_cgrp; src_cset->mg_dst_cgrp = dst_cgrp; get_css_set(src_cset); list_add_tail(&src_cset->mg_src_preload_node, &mgctx->preloaded_src_csets);}
/** * cgroup_migrate_prepare_dst - prepare destination css_sets for migration * @mgctx: migration context * * Tasks are about to be moved and all the source css_sets have been * preloaded to @mgctx->preloaded_src_csets. This function looks up and * pins all destination css_sets, links each to its source, and append them * to @mgctx->preloaded_dst_csets. * * This function must be called after cgroup_migrate_add_src() has been * called on each migration source css_set. After migration is performed * using cgroup_migrate(), cgroup_migrate_finish() must be called on * @mgctx. */int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx){ struct css_set *src_cset, *tmp_cset;
lockdep_assert_held(&cgroup_mutex);
/* look up the dst cset for each src cset and link it to src */ list_for_each_entry_safe(src_cset, tmp_cset, &mgctx->preloaded_src_csets, mg_src_preload_node) { struct css_set *dst_cset; struct cgroup_subsys *ss; int ssid;
dst_cset = find_css_set(src_cset, src_cset->mg_dst_cgrp); if (!dst_cset) return -ENOMEM;
WARN_ON_ONCE(src_cset->mg_dst_cset || dst_cset->mg_dst_cset);
/* * If src cset equals dst, it's noop. Drop the src. * cgroup_migrate() will skip the cset too. Note that we * can't handle src == dst as some nodes are used by both. */ if (src_cset == dst_cset) { src_cset->mg_src_cgrp = NULL; src_cset->mg_dst_cgrp = NULL; list_del_init(&src_cset->mg_src_preload_node); put_css_set(src_cset); put_css_set(dst_cset); continue; }
src_cset->mg_dst_cset = dst_cset;
if (list_empty(&dst_cset->mg_dst_preload_node)) list_add_tail(&dst_cset->mg_dst_preload_node, &mgctx->preloaded_dst_csets); else put_css_set(dst_cset);
for_each_subsys(ss, ssid) if (src_cset->subsys[ssid] != dst_cset->subsys[ssid]) mgctx->ss_mask |= 1 << ssid; }
return 0;}
/** * cgroup_migrate - migrate a process or task to a cgroup * @leader: the leader of the process or the task to migrate * @threadgroup: whether @leader points to the whole process or a single task * @mgctx: migration context * * Migrate a process or task denoted by @leader. If migrating a process, * the caller must be holding cgroup_threadgroup_rwsem. The caller is also * responsible for invoking cgroup_migrate_add_src() and * cgroup_migrate_prepare_dst() on the targets before invoking this * function and following up with cgroup_migrate_finish(). * * As long as a controller's ->can_attach() doesn't fail, this function is * guaranteed to succeed. This means that, excluding ->can_attach() * failure, when migrating multiple targets, the success or failure can be * decided for all targets by invoking group_migrate_prepare_dst() before * actually starting migrating. */int cgroup_migrate(struct task_struct *leader, bool threadgroup, struct cgroup_mgctx *mgctx){ struct task_struct *task;
/* * The following thread iteration should be inside an RCU critical * section to prevent tasks from being freed while taking the snapshot. * spin_lock_irq() implies RCU critical section here. */ spin_lock_irq(&css_set_lock); task = leader; do { cgroup_migrate_add_task(task, mgctx); if (!threadgroup) break; } while_each_thread(leader, task); spin_unlock_irq(&css_set_lock);
return cgroup_migrate_execute(mgctx);}
/** * cgroup_attach_task - attach a task or a whole threadgroup to a cgroup * @dst_cgrp: the cgroup to attach to * @leader: the task or the leader of the threadgroup to be attached * @threadgroup: attach the whole threadgroup? * * Call holding cgroup_mutex and cgroup_threadgroup_rwsem. */int cgroup_attach_task(struct cgroup *dst_cgrp, struct task_struct *leader, bool threadgroup){ DEFINE_CGROUP_MGCTX(mgctx); struct task_struct *task; int ret = 0;
/* look up all src csets */ spin_lock_irq(&css_set_lock); task = leader; do { cgroup_migrate_add_src(task_css_set(task), dst_cgrp, &mgctx); if (!threadgroup) break; } while_each_thread(leader, task); spin_unlock_irq(&css_set_lock);
/* prepare dst csets and commit */ ret = cgroup_migrate_prepare_dst(&mgctx); if (!ret) ret = cgroup_migrate(leader, threadgroup, &mgctx);
cgroup_migrate_finish(&mgctx);
if (!ret) TRACE_CGROUP_PATH(attach_task, dst_cgrp, leader, threadgroup);
return ret;}
struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup, enum cgroup_attach_lock_mode *lock_mode){ struct task_struct *tsk; pid_t pid;
if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0) return ERR_PTR(-EINVAL);
retry_find_task: rcu_read_lock(); if (pid) { tsk = find_task_by_vpid(pid); if (!tsk) { tsk = ERR_PTR(-ESRCH); goto out_unlock_rcu; } } else { tsk = current; }
if (threadgroup) tsk = tsk->group_leader;
/* * kthreads may acquire PF_NO_SETAFFINITY during initialization. * If userland migrates such a kthread to a non-root cgroup, it can * become trapped in a cpuset, or RT kthread may be born in a * cgroup with no rt_runtime allocated. Just say no. */ if (tsk->no_cgroup_migration || (tsk->flags & PF_NO_SETAFFINITY)) { tsk = ERR_PTR(-EINVAL); goto out_unlock_rcu; } get_task_struct(tsk); rcu_read_unlock();
/* * If we migrate a single thread, we don't care about threadgroup * stability. If the thread is `current`, it won't exit(2) under our * hands or change PID through exec(2). We exclude * cgroup_update_dfl_csses and other cgroup_{proc,thread}s_write callers * by cgroup_mutex. Therefore, we can skip the global lock. */ lockdep_assert_held(&cgroup_mutex);
if (pid || threadgroup) { if (cgroup_enable_per_threadgroup_rwsem) *lock_mode = CGRP_ATTACH_LOCK_PER_THREADGROUP; else *lock_mode = CGRP_ATTACH_LOCK_GLOBAL; } else { *lock_mode = CGRP_ATTACH_LOCK_NONE; }
cgroup_attach_lock(*lock_mode, tsk);
if (threadgroup) { if (!thread_group_leader(tsk)) { /* * A race with de_thread from another thread's exec() * may strip us of our leadership. If this happens, * throw this task away and try again. */ cgroup_attach_unlock(*lock_mode, tsk); put_task_struct(tsk); goto retry_find_task; } }
return tsk;
out_unlock_rcu: rcu_read_unlock(); return tsk;}
void cgroup_procs_write_finish(struct task_struct *task, enum cgroup_attach_lock_mode lock_mode){ cgroup_attach_unlock(lock_mode, task);
/* release reference from cgroup_procs_write_start() */ put_task_struct(task);}
static void cgroup_print_ss_mask(struct seq_file *seq, u32 ss_mask){ struct cgroup_subsys *ss; bool printed = false; int ssid;
do_each_subsys_mask(ss, ssid, ss_mask) { if (printed) seq_putc(seq, ' '); seq_puts(seq, ss->name); printed = true; } while_each_subsys_mask(); if (printed) seq_putc(seq, '\n');}
/* show controllers which are enabled from the parent */static int cgroup_controllers_show(struct seq_file *seq, void *v){ struct cgroup *cgrp = seq_css(seq)->cgroup;
cgroup_print_ss_mask(seq, cgroup_control(cgrp)); return 0;}
/* show controllers which are enabled for a given cgroup's children */static int cgroup_subtree_control_show(struct seq_file *seq, void *v){ struct cgroup *cgrp = seq_css(seq)->cgroup;
cgroup_print_ss_mask(seq, cgrp->subtree_control); return 0;}
/** * cgroup_update_dfl_csses - update css assoc of a subtree in default hierarchy * @cgrp: root of the subtree to update csses for * * @cgrp's control masks have changed and its subtree's css associations * need to be updated accordingly. This function looks up all css_sets * which are attached to the subtree, creates the matching updated css_sets * and migrates the tasks to the new ones. */static int cgroup_update_dfl_csses(struct cgroup *cgrp){ DEFINE_CGROUP_MGCTX(mgctx); struct cgroup_subsys_state *d_css; struct cgroup *dsct; struct css_set *src_cset; enum cgroup_attach_lock_mode lock_mode; bool has_tasks; int ret;
lockdep_assert_held(&cgroup_mutex);
/* look up all csses currently attached to @cgrp's subtree */ spin_lock_irq(&css_set_lock); cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) { struct cgrp_cset_link *link;
/* * As cgroup_update_dfl_csses() is only called by * cgroup_apply_control(). The csses associated with the * given cgrp will not be affected by changes made to * its subtree_control file. We can skip them. */ if (dsct == cgrp) continue;
list_for_each_entry(link, &dsct->cset_links, cset_link) cgroup_migrate_add_src(link->cset, dsct, &mgctx); } spin_unlock_irq(&css_set_lock);
/* * We need to write-lock threadgroup_rwsem while migrating tasks. * However, if there are no source csets for @cgrp, changing its * controllers isn't gonna produce any task migrations and the * write-locking can be skipped safely. */ has_tasks = !list_empty(&mgctx.preloaded_src_csets);
if (has_tasks) lock_mode = CGRP_ATTACH_LOCK_GLOBAL; else lock_mode = CGRP_ATTACH_LOCK_NONE;
cgroup_attach_lock(lock_mode, NULL);
/* NULL dst indicates self on default hierarchy */ ret = cgroup_migrate_prepare_dst(&mgctx); if (ret) goto out_finish;
spin_lock_irq(&css_set_lock); list_for_each_entry(src_cset, &mgctx.preloaded_src_csets, mg_src_preload_node) { struct task_struct *task, *ntask;
/* all tasks in src_csets need to be migrated */ list_for_each_entry_safe(task, ntask, &src_cset->tasks, cg_list) cgroup_migrate_add_task(task, &mgctx); } spin_unlock_irq(&css_set_lock);
ret = cgroup_migrate_execute(&mgctx);out_finish: cgroup_migrate_finish(&mgctx); cgroup_attach_unlock(lock_mode, NULL); return ret;}
/** * cgroup_lock_and_drain_offline - lock cgroup_mutex and drain offlined csses * @cgrp: root of the target subtree * * Because css offlining is asynchronous, userland may try to re-enable a * controller while the previous css is still around. This function grabs * cgroup_mutex and drains the previous css instances of @cgrp's subtree. */void cgroup_lock_and_drain_offline(struct cgroup *cgrp) __acquires(&cgroup_mutex){ struct cgroup *dsct; struct cgroup_subsys_state *d_css; struct cgroup_subsys *ss; int ssid;
restart: cgroup_lock();
cgroup_for_each_live_descendant_post(dsct, d_css, cgrp) { for_each_subsys(ss, ssid) { struct cgroup_subsys_state *css = cgroup_css(dsct, ss); DEFINE_WAIT(wait);
if (!css || !css_is_dying(css)) continue;
cgroup_get_live(dsct); prepare_to_wait(&dsct->offline_waitq, &wait, TASK_UNINTERRUPTIBLE);
cgroup_unlock(); schedule(); finish_wait(&dsct->offline_waitq, &wait);
cgroup_put(dsct); goto restart; } }}
/** * cgroup_save_control - save control masks and dom_cgrp of a subtree * @cgrp: root of the target subtree * * Save ->subtree_control, ->subtree_ss_mask and ->dom_cgrp to the * respective old_ prefixed fields for @cgrp's subtree including @cgrp * itself. */static void cgroup_save_control(struct cgroup *cgrp){ struct cgroup *dsct; struct cgroup_subsys_state *d_css;
cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) { dsct->old_subtree_control = dsct->subtree_control; dsct->old_subtree_ss_mask = dsct->subtree_ss_mask; dsct->old_dom_cgrp = dsct->dom_cgrp; }}
/** * cgroup_propagate_control - refresh control masks of a subtree * @cgrp: root of the target subtree * * For @cgrp and its subtree, ensure ->subtree_ss_mask matches * ->subtree_control and propagate controller availability through the * subtree so that descendants don't have unavailable controllers enabled. */static void cgroup_propagate_control(struct cgroup *cgrp){ struct cgroup *dsct; struct cgroup_subsys_state *d_css;
cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) { dsct->subtree_control &= cgroup_control(dsct); dsct->subtree_ss_mask = cgroup_calc_subtree_ss_mask(dsct->subtree_control, cgroup_ss_mask(dsct)); }}
/** * cgroup_restore_control - restore control masks and dom_cgrp of a subtree * @cgrp: root of the target subtree * * Restore ->subtree_control, ->subtree_ss_mask and ->dom_cgrp from the * respective old_ prefixed fields for @cgrp's subtree including @cgrp * itself. */static void cgroup_restore_control(struct cgroup *cgrp){ struct cgroup *dsct; struct cgroup_subsys_state *d_css;
cgroup_for_each_live_descendant_post(dsct, d_css, cgrp) { dsct->subtree_control = dsct->old_subtree_control; dsct->subtree_ss_mask = dsct->old_subtree_ss_mask; dsct->dom_cgrp = dsct->old_dom_cgrp; }}
static bool css_visible(struct cgroup_subsys_state *css){ struct cgroup_subsys *ss = css->ss; struct cgroup *cgrp = css->cgroup;
if (cgroup_control(cgrp) & (1 << ss->id)) return true; if (!(cgroup_ss_mask(cgrp) & (1 << ss->id))) return false; return cgroup_on_dfl(cgrp) && ss->implicit_on_dfl;}
/** * cgroup_apply_control_enable - enable or show csses according to control * @cgrp: root of the target subtree * * Walk @cgrp's subtree and create new csses or make the existing ones * visible. A css is created invisible if it's being implicitly enabled * through dependency. An invisible css is made visible when the userland * explicitly enables it. * * Returns 0 on success, -errno on failure. On failure, csses which have * been processed already aren't cleaned up. The caller is responsible for * cleaning up with cgroup_apply_control_disable(). */static int cgroup_apply_control_enable(struct cgroup *cgrp){ struct cgroup *dsct; struct cgroup_subsys_state *d_css; struct cgroup_subsys *ss; int ssid, ret;
cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) { for_each_subsys(ss, ssid) { struct cgroup_subsys_state *css = cgroup_css(dsct, ss);
if (!(cgroup_ss_mask(dsct) & (1 << ss->id))) continue;
if (!css) { css = css_create(dsct, ss); if (IS_ERR(css)) return PTR_ERR(css); }
WARN_ON_ONCE(percpu_ref_is_dying(&css->refcnt));
if (css_visible(css)) { ret = css_populate_dir(css); if (ret) return ret; } } }
return 0;}
/** * cgroup_apply_control_disable - kill or hide csses according to control * @cgrp: root of the target subtree * * Walk @cgrp's subtree and kill and hide csses so that they match * cgroup_ss_mask() and cgroup_visible_mask(). * * A css is hidden when the userland requests it to be disabled while other * subsystems are still depending on it. The css must not actively control * resources and be in the vanilla state if it's made visible again later. * Controllers which may be depended upon should provide ->css_reset() for * this purpose. */static void cgroup_apply_control_disable(struct cgroup *cgrp){ struct cgroup *dsct; struct cgroup_subsys_state *d_css; struct cgroup_subsys *ss; int ssid;
cgroup_for_each_live_descendant_post(dsct, d_css, cgrp) { for_each_subsys(ss, ssid) { struct cgroup_subsys_state *css = cgroup_css(dsct, ss);
if (!css) continue;
WARN_ON_ONCE(percpu_ref_is_dying(&css->refcnt));
if (css->parent && !(cgroup_ss_mask(dsct) & (1 << ss->id))) { kill_css_sync(css); if (!css_is_populated(css)) kill_css_finish(css); } else if (!css_visible(css)) { css_clear_dir(css); if (ss->css_reset) ss->css_reset(css); } } }}
/** * cgroup_apply_control - apply control mask updates to the subtree * @cgrp: root of the target subtree * * subsystems can be enabled and disabled in a subtree using the following * steps. * * 1. Call cgroup_save_control() to stash the current state. * 2. Update ->subtree_control masks in the subtree as desired. * 3. Call cgroup_apply_control() to apply the changes. * 4. Optionally perform other related operations. * 5. Call cgroup_finalize_control() to finish up. * * This function implements step 3 and propagates the mask changes * throughout @cgrp's subtree, updates csses accordingly and perform * process migrations. */static int cgroup_apply_control(struct cgroup *cgrp){ int ret;
cgroup_propagate_control(cgrp);
ret = cgroup_apply_control_enable(cgrp); if (ret) return ret;
/* * At this point, cgroup_e_css_by_mask() results reflect the new csses * making the following cgroup_update_dfl_csses() properly update * css associations of all tasks in the subtree. */ return cgroup_update_dfl_csses(cgrp);}
/** * cgroup_finalize_control - finalize control mask update * @cgrp: root of the target subtree * @ret: the result of the update * * Finalize control mask update. See cgroup_apply_control() for more info. */static void cgroup_finalize_control(struct cgroup *cgrp, int ret){ if (ret) { cgroup_restore_control(cgrp); cgroup_propagate_control(cgrp); }
cgroup_apply_control_disable(cgrp);}
static int cgroup_vet_subtree_control_enable(struct cgroup *cgrp, u32 enable){ u32 domain_enable = enable & ~cgrp_dfl_threaded_ss_mask;
/* if nothing is getting enabled, nothing to worry about */ if (!enable) return 0;
/* can @cgrp host any resources? */ if (!cgroup_is_valid_domain(cgrp->dom_cgrp)) return -EOPNOTSUPP;
/* mixables don't care */ if (cgroup_is_mixable(cgrp)) return 0;
if (domain_enable) { /* can't enable domain controllers inside a thread subtree */ if (cgroup_is_thread_root(cgrp) || cgroup_is_threaded(cgrp)) return -EOPNOTSUPP; } else { /* * Threaded controllers can handle internal competitions * and are always allowed inside a (prospective) thread * subtree. */ if (cgroup_can_be_thread_root(cgrp) || cgroup_is_threaded(cgrp)) return 0; }
/* * Controllers can't be enabled for a cgroup with tasks to avoid * child cgroups competing against tasks. */ if (cgroup_has_tasks(cgrp)) return -EBUSY;
return 0;}
/* change the enabled child controllers for a cgroup in the default hierarchy */static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off){ u32 enable = 0, disable = 0; struct cgroup *cgrp, *child; struct cgroup_subsys *ss; char *tok; int ssid, ret;
/* * Parse input - space separated list of subsystem names prefixed * with either + or -. */ buf = strstrip(buf); while ((tok = strsep(&buf, " "))) { if (tok[0] == '\0') continue; do_each_subsys_mask(ss, ssid, ~cgrp_dfl_inhibit_ss_mask) { if (!cgroup_ssid_enabled(ssid) || strcmp(tok + 1, ss->name)) continue;
if (*tok == '+') { enable |= 1 << ssid; disable &= ~(1 << ssid); } else if (*tok == '-') { disable |= 1 << ssid; enable &= ~(1 << ssid); } else { return -EINVAL; } break; } while_each_subsys_mask(); if (ssid == CGROUP_SUBSYS_COUNT) return -EINVAL; }
cgrp = cgroup_kn_lock_live(of->kn, true); if (!cgrp) return -ENODEV;
for_each_subsys(ss, ssid) { if (enable & (1 << ssid)) { if (cgrp->subtree_control & (1 << ssid)) { enable &= ~(1 << ssid); continue; }
if (!(cgroup_control(cgrp) & (1 << ssid))) { ret = -ENOENT; goto out_unlock; } } else if (disable & (1 << ssid)) { if (!(cgrp->subtree_control & (1 << ssid))) { disable &= ~(1 << ssid); continue; }
/* a child has it enabled? */ cgroup_for_each_live_child(child, cgrp) { if (child->subtree_control & (1 << ssid)) { ret = -EBUSY; goto out_unlock; } } } }
if (!enable && !disable) { ret = 0; goto out_unlock; }
ret = cgroup_vet_subtree_control_enable(cgrp, enable); if (ret) goto out_unlock;
/* save and update control masks and prepare csses */ cgroup_save_control(cgrp);
cgrp->subtree_control |= enable; cgrp->subtree_control &= ~disable;
ret = cgroup_apply_control(cgrp); cgroup_finalize_control(cgrp, ret); if (ret) goto out_unlock;
kernfs_activate(cgrp->kn);out_unlock: cgroup_kn_unlock(of->kn); return ret ?: nbytes;}
/** * cgroup_enable_threaded - make @cgrp threaded * @cgrp: the target cgroup * * Called when "threaded" is written to the cgroup.type interface file and * tries to make @cgrp threaded and join the parent's resource domain. * This function is never called on the root cgroup as cgroup.type doesn't * exist on it. */static int cgroup_enable_threaded(struct cgroup *cgrp){ struct cgroup *parent = cgroup_parent(cgrp); struct cgroup *dom_cgrp = parent->dom_cgrp; struct cgroup *dsct; struct cgroup_subsys_state *d_css; int ret;
lockdep_assert_held(&cgroup_mutex);
/* noop if already threaded */ if (cgroup_is_threaded(cgrp)) return 0;
/* * If @cgroup is populated or has domain controllers enabled, it * can't be switched. While the below cgroup_can_be_thread_root() * test can catch the same conditions, that's only when @parent is * not mixable, so let's check it explicitly. */ if (cgroup_is_populated(cgrp) || cgrp->subtree_control & ~cgrp_dfl_threaded_ss_mask) return -EOPNOTSUPP;
/* we're joining the parent's domain, ensure its validity */ if (!cgroup_is_valid_domain(dom_cgrp) || !cgroup_can_be_thread_root(dom_cgrp)) return -EOPNOTSUPP;
/* * The following shouldn't cause actual migrations and should * always succeed. */ cgroup_save_control(cgrp);
cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) if (dsct == cgrp || cgroup_is_threaded(dsct)) dsct->dom_cgrp = dom_cgrp;
ret = cgroup_apply_control(cgrp); if (!ret) parent->nr_threaded_children++;
cgroup_finalize_control(cgrp, ret); return ret;}
static int cgroup_type_show(struct seq_file *seq, void *v){ struct cgroup *cgrp = seq_css(seq)->cgroup;
if (cgroup_is_threaded(cgrp)) seq_puts(seq, "threaded\n"); else if (!cgroup_is_valid_domain(cgrp)) seq_puts(seq, "domain invalid\n"); else if (cgroup_is_thread_root(cgrp)) seq_puts(seq, "domain threaded\n"); else seq_puts(seq, "domain\n");
return 0;}
static ssize_t cgroup_type_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off){ struct cgroup *cgrp; int ret;
/* only switching to threaded mode is supported */ if (strcmp(strstrip(buf), "threaded")) return -EINVAL;
/* drain dying csses before we re-apply (threaded) subtree control */ cgrp = cgroup_kn_lock_live(of->kn, true); if (!cgrp) return -ENOENT;
/* threaded can only be enabled */ ret = cgroup_enable_threaded(cgrp);
cgroup_kn_unlock(of->kn); return ret ?: nbytes;}
static int cgroup_max_descendants_show(struct seq_file *seq, void *v){ struct cgroup *cgrp = seq_css(seq)->cgroup; int descendants = READ_ONCE(cgrp->max_descendants);
if (descendants == INT_MAX) seq_puts(seq, "max\n"); else seq_printf(seq, "%d\n", descendants);
return 0;}
static ssize_t cgroup_max_descendants_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off){ struct cgroup *cgrp; int descendants; ssize_t ret;
buf = strstrip(buf); if (!strcmp(buf, "max")) { descendants = INT_MAX; } else { ret = kstrtoint(buf, 0, &descendants); if (ret) return ret; }
if (descendants < 0) return -ERANGE;
cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENOENT;
WRITE_ONCE(cgrp->max_descendants, descendants);
cgroup_kn_unlock(of->kn);
return nbytes;}
static int cgroup_max_depth_show(struct seq_file *seq, void *v){ struct cgroup *cgrp = seq_css(seq)->cgroup; int depth = READ_ONCE(cgrp->max_depth);
if (depth == INT_MAX) seq_puts(seq, "max\n"); else seq_printf(seq, "%d\n", depth);
return 0;}
static ssize_t cgroup_max_depth_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off){ struct cgroup *cgrp; ssize_t ret; int depth;
buf = strstrip(buf); if (!strcmp(buf, "max")) { depth = INT_MAX; } else { ret = kstrtoint(buf, 0, &depth); if (ret) return ret; }
if (depth < 0) return -ERANGE;
cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENOENT;
WRITE_ONCE(cgrp->max_depth, depth);
cgroup_kn_unlock(of->kn);
return nbytes;}
static int cgroup_events_show(struct seq_file *seq, void *v){ struct cgroup *cgrp = seq_css(seq)->cgroup;
seq_printf(seq, "populated %d\n", cgroup_is_populated(cgrp)); seq_printf(seq, "frozen %d\n", test_bit(CGRP_FROZEN, &cgrp->flags));
return 0;}
static int cgroup_stat_show(struct seq_file *seq, void *v){ struct cgroup *cgroup = seq_css(seq)->cgroup; struct cgroup_subsys_state *css; int dying_cnt[CGROUP_SUBSYS_COUNT]; int ssid;
seq_printf(seq, "nr_descendants %d\n", cgroup->nr_descendants);
/* * Show the number of live and dying csses associated with each of * non-inhibited cgroup subsystems that is bound to cgroup v2. * * Without proper lock protection, racing is possible. So the * numbers may not be consistent when that happens. */ rcu_read_lock(); for (ssid = 0; ssid < CGROUP_SUBSYS_COUNT; ssid++) { dying_cnt[ssid] = -1; if ((BIT(ssid) & cgrp_dfl_inhibit_ss_mask) || (cgroup_subsys[ssid]->root != &cgrp_dfl_root)) continue; css = rcu_dereference_raw(cgroup->subsys[ssid]); dying_cnt[ssid] = cgroup->nr_dying_subsys[ssid]; seq_printf(seq, "nr_subsys_%s %d\n", cgroup_subsys[ssid]->name, css ? (css->nr_descendants + 1) : 0); }
seq_printf(seq, "nr_dying_descendants %d\n", cgroup->nr_dying_descendants); for (ssid = 0; ssid < CGROUP_SUBSYS_COUNT; ssid++) { if (dying_cnt[ssid] >= 0) seq_printf(seq, "nr_dying_subsys_%s %d\n", cgroup_subsys[ssid]->name, dying_cnt[ssid]); } rcu_read_unlock(); return 0;}
static int cgroup_core_local_stat_show(struct seq_file *seq, void *v){ struct cgroup *cgrp = seq_css(seq)->cgroup; unsigned int sequence; u64 freeze_time;
do { sequence = read_seqcount_begin(&cgrp->freezer.freeze_seq); freeze_time = cgrp->freezer.frozen_nsec; /* Add in current freezer interval if the cgroup is freezing. */ if (test_bit(CGRP_FREEZE, &cgrp->flags)) freeze_time += (ktime_get_ns() - cgrp->freezer.freeze_start_nsec); } while (read_seqcount_retry(&cgrp->freezer.freeze_seq, sequence));
do_div(freeze_time, NSEC_PER_USEC); seq_printf(seq, "frozen_usec %llu\n", freeze_time);
return 0;}
#ifdef CONFIG_CGROUP_SCHED/** * cgroup_tryget_css - try to get a cgroup's css for the specified subsystem * @cgrp: the cgroup of interest * @ss: the subsystem of interest * * Find and get @cgrp's css associated with @ss. If the css doesn't exist * or is offline, %NULL is returned. */static struct cgroup_subsys_state *cgroup_tryget_css(struct cgroup *cgrp, struct cgroup_subsys *ss){ struct cgroup_subsys_state *css;
rcu_read_lock(); css = cgroup_css(cgrp, ss); if (css && !css_tryget_online(css)) css = NULL; rcu_read_unlock();
return css;}
static int cgroup_extra_stat_show(struct seq_file *seq, int ssid){ struct cgroup *cgrp = seq_css(seq)->cgroup; struct cgroup_subsys *ss = cgroup_subsys[ssid]; struct cgroup_subsys_state *css; int ret;
if (!ss->css_extra_stat_show) return 0;
css = cgroup_tryget_css(cgrp, ss); if (!css) return 0;
ret = ss->css_extra_stat_show(seq, css); css_put(css); return ret;}
static int cgroup_local_stat_show(struct seq_file *seq, struct cgroup *cgrp, int ssid){ struct cgroup_subsys *ss = cgroup_subsys[ssid]; struct cgroup_subsys_state *css; int ret;
if (!ss->css_local_stat_show) return 0;
css = cgroup_tryget_css(cgrp, ss); if (!css) return 0;
ret = ss->css_local_stat_show(seq, css); css_put(css); return ret;}#endif
static int cpu_stat_show(struct seq_file *seq, void *v){ int ret = 0;
cgroup_base_stat_cputime_show(seq);#ifdef CONFIG_CGROUP_SCHED ret = cgroup_extra_stat_show(seq, cpu_cgrp_id);#endif return ret;}
static int cpu_local_stat_show(struct seq_file *seq, void *v){ struct cgroup __maybe_unused *cgrp = seq_css(seq)->cgroup; int ret = 0;
#ifdef CONFIG_CGROUP_SCHED ret = cgroup_local_stat_show(seq, cgrp, cpu_cgrp_id);#endif return ret;}
#ifdef CONFIG_PSIstatic int cgroup_io_pressure_show(struct seq_file *seq, void *v){ struct cgroup *cgrp = seq_css(seq)->cgroup; struct psi_group *psi = cgroup_psi(cgrp);
return psi_show(seq, psi, PSI_IO);}static int cgroup_memory_pressure_show(struct seq_file *seq, void *v){ struct cgroup *cgrp = seq_css(seq)->cgroup; struct psi_group *psi = cgroup_psi(cgrp);
return psi_show(seq, psi, PSI_MEM);}static int cgroup_cpu_pressure_show(struct seq_file *seq, void *v){ struct cgroup *cgrp = seq_css(seq)->cgroup; struct psi_group *psi = cgroup_psi(cgrp);
return psi_show(seq, psi, PSI_CPU);}
static ssize_t pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, enum psi_res res){ struct cgroup_file_ctx *ctx; struct psi_trigger *new; struct cgroup *cgrp; struct psi_group *psi; ssize_t ret = 0;
cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENODEV;
ctx = of->priv; if (!ctx) { ret = -ENODEV; goto out_unlock; }
/* Allow only one trigger per file descriptor */ if (ctx->psi.trigger) { ret = -EBUSY; goto out_unlock; }
psi = cgroup_psi(cgrp); new = psi_trigger_create(psi, buf, res, of->file, of); if (IS_ERR(new)) { ret = PTR_ERR(new); goto out_unlock; }
smp_store_release(&ctx->psi.trigger, new);
out_unlock: cgroup_kn_unlock(of->kn); if (ret) return ret;
return nbytes;}
static ssize_t cgroup_io_pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off){ return pressure_write(of, buf, nbytes, PSI_IO);}
static ssize_t cgroup_memory_pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off){ return pressure_write(of, buf, nbytes, PSI_MEM);}
static ssize_t cgroup_cpu_pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off){ return pressure_write(of, buf, nbytes, PSI_CPU);}
#ifdef CONFIG_IRQ_TIME_ACCOUNTINGstatic int cgroup_irq_pressure_show(struct seq_file *seq, void *v){ struct cgroup *cgrp = seq_css(seq)->cgroup; struct psi_group *psi = cgroup_psi(cgrp);
return psi_show(seq, psi, PSI_IRQ);}
static ssize_t cgroup_irq_pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off){ return pressure_write(of, buf, nbytes, PSI_IRQ);}#endif
static int cgroup_pressure_show(struct seq_file *seq, void *v){ struct cgroup *cgrp = seq_css(seq)->cgroup; struct psi_group *psi = cgroup_psi(cgrp);
seq_printf(seq, "%d\n", psi->enabled);
return 0;}
static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off){ ssize_t ret; int enable; struct cgroup *cgrp; struct psi_group *psi;
ret = kstrtoint(strstrip(buf), 0, &enable); if (ret) return ret;
if (enable < 0 || enable > 1) return -ERANGE;
cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENOENT;
psi = cgroup_psi(cgrp); if (psi->enabled != enable) { int i;
/* show or hide {cpu,memory,io,irq}.pressure files */ for (i = 0; i < NR_PSI_RESOURCES; i++) cgroup_file_show(&cgrp->psi_files[i], enable);
psi->enabled = enable; if (enable) psi_cgroup_restart(psi); }
cgroup_kn_unlock(of->kn);
return nbytes;}
static __poll_t cgroup_pressure_poll(struct kernfs_open_file *of, poll_table *pt){ struct cgroup_file_ctx *ctx = of->priv;
return psi_trigger_poll(&ctx->psi.trigger, of->file, pt);}
static void cgroup_pressure_release(struct kernfs_open_file *of){ struct cgroup_file_ctx *ctx = of->priv;
psi_trigger_destroy(ctx->psi.trigger);}
bool cgroup_psi_enabled(void){ if (static_branch_likely(&psi_disabled)) return false;
return (cgroup_feature_disable_mask & (1 << OPT_FEATURE_PRESSURE)) == 0;}
#else /* CONFIG_PSI */bool cgroup_psi_enabled(void){ return false;}
#endif /* CONFIG_PSI */
static int cgroup_freeze_show(struct seq_file *seq, void *v){ struct cgroup *cgrp = seq_css(seq)->cgroup;
seq_printf(seq, "%d\n", cgrp->freezer.freeze);
return 0;}
static ssize_t cgroup_freeze_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off){ struct cgroup *cgrp; ssize_t ret; int freeze;
ret = kstrtoint(strstrip(buf), 0, &freeze); if (ret) return ret;
if (freeze < 0 || freeze > 1) return -ERANGE;
cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENOENT;
cgroup_freeze(cgrp, freeze);
cgroup_kn_unlock(of->kn);
return nbytes;}
static void __cgroup_kill(struct cgroup *cgrp){ struct css_task_iter it; struct task_struct *task;
lockdep_assert_held(&cgroup_mutex);
spin_lock_irq(&css_set_lock); cgrp->kill_seq++; spin_unlock_irq(&css_set_lock);
css_task_iter_start(&cgrp->self, CSS_TASK_ITER_PROCS | CSS_TASK_ITER_THREADED, &it); while ((task = css_task_iter_next(&it))) { /* Ignore kernel threads here. */ if (task->flags & PF_KTHREAD) continue;
/* Skip tasks that are already dying. */ if (__fatal_signal_pending(task)) continue;
send_sig(SIGKILL, task, 0); } css_task_iter_end(&it);}
static void cgroup_kill(struct cgroup *cgrp){ struct cgroup_subsys_state *css; struct cgroup *dsct;
lockdep_assert_held(&cgroup_mutex);
cgroup_for_each_live_descendant_pre(dsct, css, cgrp) __cgroup_kill(dsct);}
static ssize_t cgroup_kill_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off){ ssize_t ret = 0; int kill; struct cgroup *cgrp;
ret = kstrtoint(strstrip(buf), 0, &kill); if (ret) return ret;
if (kill != 1) return -ERANGE;
cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENOENT;
/* * Killing is a process directed operation, i.e. the whole thread-group * is taken down so act like we do for cgroup.procs and only make this * writable in non-threaded cgroups. */ if (cgroup_is_threaded(cgrp)) ret = -EOPNOTSUPP; else cgroup_kill(cgrp);
cgroup_kn_unlock(of->kn);
return ret ?: nbytes;}
static int cgroup_file_open(struct kernfs_open_file *of){ struct cftype *cft = of_cft(of); struct cgroup_file_ctx *ctx; int ret;
ctx = kzalloc_obj(*ctx); if (!ctx) return -ENOMEM;
ctx->ns = current->nsproxy->cgroup_ns; get_cgroup_ns(ctx->ns); of->priv = ctx;
if (!cft->open) return 0;
ret = cft->open(of); if (ret) { put_cgroup_ns(ctx->ns); kfree(ctx); } return ret;}
static void cgroup_file_release(struct kernfs_open_file *of){ struct cftype *cft = of_cft(of); struct cgroup_file_ctx *ctx = of->priv;
if (cft->release) cft->release(of); put_cgroup_ns(ctx->ns); kfree(ctx); of->priv = NULL;}
static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off){ struct cgroup_file_ctx *ctx = of->priv; struct cgroup *cgrp = kn_priv(of->kn); struct cftype *cft = of_cft(of); struct cgroup_subsys_state *css; int ret;
if (!nbytes) return 0;
/* * If namespaces are delegation boundaries, disallow writes to * files in an non-init namespace root from inside the namespace * except for the files explicitly marked delegatable - * eg. cgroup.procs, cgroup.threads and cgroup.subtree_control. */ if ((cgrp->root->flags & CGRP_ROOT_NS_DELEGATE) && !(cft->flags & CFTYPE_NS_DELEGATABLE) && ctx->ns != &init_cgroup_ns && ctx->ns->root_cset->dfl_cgrp == cgrp) return -EPERM;
if (cft->write) return cft->write(of, buf, nbytes, off);
/* * kernfs guarantees that a file isn't deleted with operations in * flight, which means that the matching css is and stays alive and * doesn't need to be pinned. The RCU locking is not necessary * either. It's just for the convenience of using cgroup_css(). */ rcu_read_lock(); css = cgroup_css(cgrp, cft->ss); rcu_read_unlock();
if (cft->write_u64) { unsigned long long v; ret = kstrtoull(buf, 0, &v); if (!ret) ret = cft->write_u64(css, cft, v); } else if (cft->write_s64) { long long v; ret = kstrtoll(buf, 0, &v); if (!ret) ret = cft->write_s64(css, cft, v); } else { ret = -EINVAL; }
return ret ?: nbytes;}
static __poll_t cgroup_file_poll(struct kernfs_open_file *of, poll_table *pt){ struct cftype *cft = of_cft(of);
if (cft->poll) return cft->poll(of, pt);
return kernfs_generic_poll(of, pt);}
static void *cgroup_seqfile_start(struct seq_file *seq, loff_t *ppos){ return seq_cft(seq)->seq_start(seq, ppos);}
static void *cgroup_seqfile_next(struct seq_file *seq, void *v, loff_t *ppos){ return seq_cft(seq)->seq_next(seq, v, ppos);}
static void cgroup_seqfile_stop(struct seq_file *seq, void *v){ if (seq_cft(seq)->seq_stop) seq_cft(seq)->seq_stop(seq, v);}
static int cgroup_seqfile_show(struct seq_file *m, void *arg){ struct cftype *cft = seq_cft(m); struct cgroup_subsys_state *css = seq_css(m);
if (cft->seq_show) return cft->seq_show(m, arg);
if (cft->read_u64) seq_printf(m, "%llu\n", cft->read_u64(css, cft)); else if (cft->read_s64) seq_printf(m, "%lld\n", cft->read_s64(css, cft)); else return -EINVAL; return 0;}
static struct kernfs_ops cgroup_kf_single_ops = { .atomic_write_len = PAGE_SIZE, .open = cgroup_file_open, .release = cgroup_file_release, .write = cgroup_file_write, .poll = cgroup_file_poll, .seq_show = cgroup_seqfile_show,};
static struct kernfs_ops cgroup_kf_ops = { .atomic_write_len = PAGE_SIZE, .open = cgroup_file_open, .release = cgroup_file_release, .write = cgroup_file_write, .poll = cgroup_file_poll, .seq_start = cgroup_seqfile_start, .seq_next = cgroup_seqfile_next, .seq_stop = cgroup_seqfile_stop, .seq_show = cgroup_seqfile_show,};
static void cgroup_file_notify_timer(struct timer_list *timer){ cgroup_file_notify(container_of(timer, struct cgroup_file, notify_timer));}
static int cgroup_add_file(struct cgroup_subsys_state *css, struct cgroup *cgrp, struct cftype *cft){ char name[CGROUP_FILE_NAME_MAX]; struct kernfs_node *kn; struct lock_class_key *key = NULL;
#ifdef CONFIG_DEBUG_LOCK_ALLOC key = &cft->lockdep_key;#endif kn = __kernfs_create_file(cgrp->kn, cgroup_file_name(cgrp, cft, name), cgroup_file_mode(cft), current_fsuid(), current_fsgid(), 0, cft->kf_ops, cft, NULL, key); if (IS_ERR(kn)) return PTR_ERR(kn);
if (cft->file_offset) { struct cgroup_file *cfile = (void *)css + cft->file_offset;
timer_setup(&cfile->notify_timer, cgroup_file_notify_timer, 0); spin_lock_init(&cfile->lock); cfile->kn = kn; }
return 0;}
/** * cgroup_addrm_files - add or remove files to a cgroup directory * @css: the target css * @cgrp: the target cgroup (usually css->cgroup) * @cfts: array of cftypes to be added * @is_add: whether to add or remove * * Depending on @is_add, add or remove files defined by @cfts on @cgrp. * For removals, this function never fails. */static int cgroup_addrm_files(struct cgroup_subsys_state *css, struct cgroup *cgrp, struct cftype cfts[], bool is_add){ struct cftype *cft, *cft_end = NULL; int ret = 0;
lockdep_assert_held(&cgroup_mutex);
restart: for (cft = cfts; cft != cft_end && cft->name[0] != '\0'; cft++) { /* does cft->flags tell us to skip this file on @cgrp? */ if ((cft->flags & __CFTYPE_ONLY_ON_DFL) && !cgroup_on_dfl(cgrp)) continue; if ((cft->flags & __CFTYPE_NOT_ON_DFL) && cgroup_on_dfl(cgrp)) continue; if ((cft->flags & CFTYPE_NOT_ON_ROOT) && !cgroup_parent(cgrp)) continue; if ((cft->flags & CFTYPE_ONLY_ON_ROOT) && cgroup_parent(cgrp)) continue; if ((cft->flags & CFTYPE_DEBUG) && !cgroup_debug) continue; if (is_add) { ret = cgroup_add_file(css, cgrp, cft); if (ret) { pr_warn("%s: failed to add %s, err=%d\n", __func__, cft->name, ret); cft_end = cft; is_add = false; goto restart; } } else { cgroup_rm_file(cgrp, cft); } } return ret;}
static int cgroup_apply_cftypes(struct cftype *cfts, bool is_add){ struct cgroup_subsys *ss = cfts[0].ss; struct cgroup *root = &ss->root->cgrp; struct cgroup_subsys_state *css; int ret = 0;
lockdep_assert_held(&cgroup_mutex);
/* add/rm files for all cgroups created before */ css_for_each_descendant_pre(css, cgroup_css(root, ss)) { struct cgroup *cgrp = css->cgroup;
if (!(css->flags & CSS_VISIBLE)) continue;
ret = cgroup_addrm_files(css, cgrp, cfts, is_add); if (ret) break; }
if (is_add && !ret) kernfs_activate(root->kn); return ret;}
static void cgroup_exit_cftypes(struct cftype *cfts){ struct cftype *cft;
for (cft = cfts; cft->name[0] != '\0'; cft++) { /* free copy for custom atomic_write_len, see init_cftypes() */ if (cft->max_write_len && cft->max_write_len != PAGE_SIZE) kfree(cft->kf_ops); cft->kf_ops = NULL; cft->ss = NULL;
/* revert flags set by cgroup core while adding @cfts */ cft->flags &= ~(__CFTYPE_ONLY_ON_DFL | __CFTYPE_NOT_ON_DFL | __CFTYPE_ADDED); }}
static int cgroup_init_cftypes(struct cgroup_subsys *ss, struct cftype *cfts){ struct cftype *cft; int ret = 0;
for (cft = cfts; cft->name[0] != '\0'; cft++) { struct kernfs_ops *kf_ops;
WARN_ON(cft->ss || cft->kf_ops);
if (cft->flags & __CFTYPE_ADDED) { ret = -EBUSY; break; }
if (cft->seq_start) kf_ops = &cgroup_kf_ops; else kf_ops = &cgroup_kf_single_ops;
/* * Ugh... if @cft wants a custom max_write_len, we need to * make a copy of kf_ops to set its atomic_write_len. */ if (cft->max_write_len && cft->max_write_len != PAGE_SIZE) { kf_ops = kmemdup(kf_ops, sizeof(*kf_ops), GFP_KERNEL); if (!kf_ops) { ret = -ENOMEM; break; } kf_ops->atomic_write_len = cft->max_write_len; }
cft->kf_ops = kf_ops; cft->ss = ss; cft->flags |= __CFTYPE_ADDED; }
if (ret) cgroup_exit_cftypes(cfts); return ret;}
static void cgroup_rm_cftypes_locked(struct cftype *cfts){ lockdep_assert_held(&cgroup_mutex);
list_del(&cfts->node); cgroup_apply_cftypes(cfts, false); cgroup_exit_cftypes(cfts);}
/** * cgroup_rm_cftypes - remove an array of cftypes from a subsystem * @cfts: zero-length name terminated array of cftypes * * Unregister @cfts. Files described by @cfts are removed from all * existing cgroups and all future cgroups won't have them either. This * function can be called anytime whether @cfts' subsys is attached or not. * * Returns 0 on successful unregistration, -ENOENT if @cfts is not * registered. */int cgroup_rm_cftypes(struct cftype *cfts){ if (!cfts || cfts[0].name[0] == '\0') return 0;
if (!(cfts[0].flags & __CFTYPE_ADDED)) return -ENOENT;
cgroup_lock(); cgroup_rm_cftypes_locked(cfts); cgroup_unlock(); return 0;}
/** * cgroup_add_cftypes - add an array of cftypes to a subsystem * @ss: target cgroup subsystem * @cfts: zero-length name terminated array of cftypes * * Register @cfts to @ss. Files described by @cfts are created for all * existing cgroups to which @ss is attached and all future cgroups will * have them too. This function can be called anytime whether @ss is * attached or not. * * Returns 0 on successful registration, -errno on failure. Note that this * function currently returns 0 as long as @cfts registration is successful * even if some file creation attempts on existing cgroups fail. */int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts){ int ret;
if (!cgroup_ssid_enabled(ss->id)) return 0;
if (!cfts || cfts[0].name[0] == '\0') return 0;
ret = cgroup_init_cftypes(ss, cfts); if (ret) return ret;
cgroup_lock();
list_add_tail(&cfts->node, &ss->cfts); ret = cgroup_apply_cftypes(cfts, true); if (ret) cgroup_rm_cftypes_locked(cfts);
cgroup_unlock(); return ret;}
/** * cgroup_add_dfl_cftypes - add an array of cftypes for default hierarchy * @ss: target cgroup subsystem * @cfts: zero-length name terminated array of cftypes * * Similar to cgroup_add_cftypes() but the added files are only used for * the default hierarchy. */int cgroup_add_dfl_cftypes(struct cgroup_subsys *ss, struct cftype *cfts){ struct cftype *cft;
for (cft = cfts; cft && cft->name[0] != '\0'; cft++) cft->flags |= __CFTYPE_ONLY_ON_DFL; return cgroup_add_cftypes(ss, cfts);}
/** * cgroup_add_legacy_cftypes - add an array of cftypes for legacy hierarchies * @ss: target cgroup subsystem * @cfts: zero-length name terminated array of cftypes * * Similar to cgroup_add_cftypes() but the added files are only used for * the legacy hierarchies. */int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts){ struct cftype *cft;
for (cft = cfts; cft && cft->name[0] != '\0'; cft++) cft->flags |= __CFTYPE_NOT_ON_DFL; return cgroup_add_cftypes(ss, cfts);}
/** * cgroup_file_notify - generate a file modified event for a cgroup_file * @cfile: target cgroup_file * * @cfile must have been obtained by setting cftype->file_offset. */void cgroup_file_notify(struct cgroup_file *cfile){ unsigned long flags, last, next; struct kernfs_node *kn = NULL;
if (!READ_ONCE(cfile->kn)) return;
last = READ_ONCE(cfile->notified_at); next = last + CGROUP_FILE_NOTIFY_MIN_INTV; if (time_in_range(jiffies, last, next)) { timer_reduce(&cfile->notify_timer, next); if (timer_pending(&cfile->notify_timer)) return; }
spin_lock_irqsave(&cfile->lock, flags); if (cfile->kn) { kn = cfile->kn; kernfs_get(kn); WRITE_ONCE(cfile->notified_at, jiffies); } spin_unlock_irqrestore(&cfile->lock, flags);
if (kn) { kernfs_notify(kn); kernfs_put(kn); }}EXPORT_SYMBOL_GPL(cgroup_file_notify);
/** * cgroup_file_show - show or hide a hidden cgroup file * @cfile: target cgroup_file obtained by setting cftype->file_offset * @show: whether to show or hide */void cgroup_file_show(struct cgroup_file *cfile, bool show){ struct kernfs_node *kn;
spin_lock_irq(&cfile->lock); kn = cfile->kn; kernfs_get(kn); spin_unlock_irq(&cfile->lock);
if (kn) kernfs_show(kn, show);
kernfs_put(kn);}
/** * css_next_child - find the next child of a given css * @pos: the current position (%NULL to initiate traversal) * @parent: css whose children to walk * * This function returns the next child of @parent and should be called * under either cgroup_mutex or RCU read lock. The only requirement is * that @parent and @pos are accessible. The next sibling is guaranteed to * be returned regardless of their states. * * If a subsystem synchronizes ->css_online() and the start of iteration, a * css which finished ->css_online() is guaranteed to be visible in the * future iterations and will stay visible until the last reference is put. * A css which hasn't finished ->css_online() or already finished * ->css_offline() may show up during traversal. It's each subsystem's * responsibility to synchronize against on/offlining. */struct cgroup_subsys_state *css_next_child(struct cgroup_subsys_state *pos, struct cgroup_subsys_state *parent){ struct cgroup_subsys_state *next;
cgroup_assert_mutex_or_rcu_locked();
/* * @pos could already have been unlinked from the sibling list. * Once a cgroup is removed, its ->sibling.next is no longer * updated when its next sibling changes. CSS_RELEASED is set when * @pos is taken off list, at which time its next pointer is valid, * and, as releases are serialized, the one pointed to by the next * pointer is guaranteed to not have started release yet. This * implies that if we observe !CSS_RELEASED on @pos in this RCU * critical section, the one pointed to by its next pointer is * guaranteed to not have finished its RCU grace period even if we * have dropped rcu_read_lock() in-between iterations. * * If @pos has CSS_RELEASED set, its next pointer can't be * dereferenced; however, as each css is given a monotonically * increasing unique serial number and always appended to the * sibling list, the next one can be found by walking the parent's * children until the first css with higher serial number than * @pos's. While this path can be slower, it happens iff iteration * races against release and the race window is very small. */ if (!pos) { next = list_entry_rcu(parent->children.next, struct cgroup_subsys_state, sibling); } else if (likely(!(pos->flags & CSS_RELEASED))) { next = list_entry_rcu(pos->sibling.next, struct cgroup_subsys_state, sibling); } else { list_for_each_entry_rcu(next, &parent->children, sibling, lockdep_is_held(&cgroup_mutex)) if (next->serial_nr > pos->serial_nr) break; }
/* * @next, if not pointing to the head, can be dereferenced and is * the next sibling. */ if (&next->sibling != &parent->children) return next; return NULL;}
/** * css_next_descendant_pre - find the next descendant for pre-order walk * @pos: the current position (%NULL to initiate traversal) * @root: css whose descendants to walk * * To be used by css_for_each_descendant_pre(). Find the next descendant * to visit for pre-order traversal of @root's descendants. @root is * included in the iteration and the first node to be visited. * * While this function requires cgroup_mutex or RCU read locking, it * doesn't require the whole traversal to be contained in a single critical * section. Additionally, it isn't necessary to hold onto a reference to @pos. * This function will return the correct next descendant as long as both @pos * and @root are accessible and @pos is a descendant of @root. * * If a subsystem synchronizes ->css_online() and the start of iteration, a * css which finished ->css_online() is guaranteed to be visible in the * future iterations and will stay visible until the last reference is put. * A css which hasn't finished ->css_online() or already finished * ->css_offline() may show up during traversal. It's each subsystem's * responsibility to synchronize against on/offlining. */struct cgroup_subsys_state *css_next_descendant_pre(struct cgroup_subsys_state *pos, struct cgroup_subsys_state *root){ struct cgroup_subsys_state *next;
cgroup_assert_mutex_or_rcu_locked();
/* if first iteration, visit @root */ if (!pos) return root;
/* visit the first child if exists */ next = css_next_child(NULL, pos); if (next) return next;
/* no child, visit my or the closest ancestor's next sibling */ while (pos != root) { next = css_next_child(pos, pos->parent); if (next) return next; pos = pos->parent; }
return NULL;}EXPORT_SYMBOL_GPL(css_next_descendant_pre);
/** * css_rightmost_descendant - return the rightmost descendant of a css * @pos: css of interest * * Return the rightmost descendant of @pos. If there's no descendant, @pos * is returned. This can be used during pre-order traversal to skip * subtree of @pos. * * While this function requires cgroup_mutex or RCU read locking, it * doesn't require the whole traversal to be contained in a single critical * section. Additionally, it isn't necessary to hold onto a reference to @pos. * This function will return the correct rightmost descendant as long as @pos * is accessible. */struct cgroup_subsys_state *css_rightmost_descendant(struct cgroup_subsys_state *pos){ struct cgroup_subsys_state *last, *tmp;
cgroup_assert_mutex_or_rcu_locked();
do { last = pos; /* ->prev isn't RCU safe, walk ->next till the end */ pos = NULL; css_for_each_child(tmp, last) pos = tmp; } while (pos);
return last;}
static struct cgroup_subsys_state *css_leftmost_descendant(struct cgroup_subsys_state *pos){ struct cgroup_subsys_state *last;
do { last = pos; pos = css_next_child(NULL, pos); } while (pos);
return last;}
/** * css_next_descendant_post - find the next descendant for post-order walk * @pos: the current position (%NULL to initiate traversal) * @root: css whose descendants to walk * * To be used by css_for_each_descendant_post(). Find the next descendant * to visit for post-order traversal of @root's descendants. @root is * included in the iteration and the last node to be visited. * * While this function requires cgroup_mutex or RCU read locking, it * doesn't require the whole traversal to be contained in a single critical * section. Additionally, it isn't necessary to hold onto a reference to @pos. * This function will return the correct next descendant as long as both @pos * and @cgroup are accessible and @pos is a descendant of @cgroup. * * If a subsystem synchronizes ->css_online() and the start of iteration, a * css which finished ->css_online() is guaranteed to be visible in the * future iterations and will stay visible until the last reference is put. * A css which hasn't finished ->css_online() or already finished * ->css_offline() may show up during traversal. It's each subsystem's * responsibility to synchronize against on/offlining. */struct cgroup_subsys_state *css_next_descendant_post(struct cgroup_subsys_state *pos, struct cgroup_subsys_state *root){ struct cgroup_subsys_state *next;
cgroup_assert_mutex_or_rcu_locked();
/* if first iteration, visit leftmost descendant which may be @root */ if (!pos) return css_leftmost_descendant(root);
/* if we visited @root, we're done */ if (pos == root) return NULL;
/* if there's an unvisited sibling, visit its leftmost descendant */ next = css_next_child(pos, pos->parent); if (next) return css_leftmost_descendant(next);
/* no sibling left, visit parent */ return pos->parent;}
/** * css_has_online_children - does a css have online children * @css: the target css * * Returns %true if @css has any online children; otherwise, %false. This * function can be called from any context but the caller is responsible * for synchronizing against on/offlining as necessary. */bool css_has_online_children(struct cgroup_subsys_state *css){ struct cgroup_subsys_state *child; bool ret = false;
rcu_read_lock(); css_for_each_child(child, css) { if (css_is_online(child)) { ret = true; break; } } rcu_read_unlock(); return ret;}
static struct css_set *css_task_iter_next_css_set(struct css_task_iter *it){ struct list_head *l; struct cgrp_cset_link *link; struct css_set *cset;
lockdep_assert_held(&css_set_lock);
/* find the next threaded cset */ if (it->tcset_pos) { l = it->tcset_pos->next;
if (l != it->tcset_head) { it->tcset_pos = l; return container_of(l, struct css_set, threaded_csets_node); }
it->tcset_pos = NULL; }
/* find the next cset */ l = it->cset_pos; l = l->next; if (l == it->cset_head) { it->cset_pos = NULL; return NULL; }
if (it->ss) { cset = container_of(l, struct css_set, e_cset_node[it->ss->id]); } else { link = list_entry(l, struct cgrp_cset_link, cset_link); cset = link->cset; }
it->cset_pos = l;
/* initialize threaded css_set walking */ if (it->flags & CSS_TASK_ITER_THREADED) { if (it->cur_dcset) put_css_set_locked(it->cur_dcset); it->cur_dcset = cset; get_css_set(cset);
it->tcset_head = &cset->threaded_csets; it->tcset_pos = &cset->threaded_csets; }
return cset;}
/** * css_task_iter_advance_css_set - advance a task iterator to the next css_set * @it: the iterator to advance * * Advance @it to the next css_set to walk. */static void css_task_iter_advance_css_set(struct css_task_iter *it){ struct css_set *cset;
lockdep_assert_held(&css_set_lock);
/* Advance to the next non-empty css_set and find first non-empty tasks list*/ while ((cset = css_task_iter_next_css_set(it))) { if (!list_empty(&cset->tasks)) { it->cur_tasks_head = &cset->tasks; break; } else if (!list_empty(&cset->mg_tasks)) { it->cur_tasks_head = &cset->mg_tasks; break; } else if (!list_empty(&cset->dying_tasks)) { it->cur_tasks_head = &cset->dying_tasks; break; } } if (!cset) { it->task_pos = NULL; return; } it->task_pos = it->cur_tasks_head->next;
/* * We don't keep css_sets locked across iteration steps and thus * need to take steps to ensure that iteration can be resumed after * the lock is re-acquired. Iteration is performed at two levels - * css_sets and tasks in them. * * Once created, a css_set never leaves its cgroup lists, so a * pinned css_set is guaranteed to stay put and we can resume * iteration afterwards. * * Tasks may leave @cset across iteration steps. This is resolved * by registering each iterator with the css_set currently being * walked and making css_set_move_task() advance iterators whose * next task is leaving. */ if (it->cur_cset) { list_del(&it->iters_node); put_css_set_locked(it->cur_cset); } get_css_set(cset); it->cur_cset = cset; list_add(&it->iters_node, &cset->task_iters);}
static void css_task_iter_skip(struct css_task_iter *it, struct task_struct *task){ lockdep_assert_held(&css_set_lock);
if (it->task_pos == &task->cg_list) { it->task_pos = it->task_pos->next; it->flags |= CSS_TASK_ITER_SKIPPED; }}
static void css_task_iter_advance(struct css_task_iter *it){ struct task_struct *task;
lockdep_assert_held(&css_set_lock);repeat: if (it->task_pos) { /* * Advance iterator to find next entry. We go through cset * tasks, mg_tasks and dying_tasks, when consumed we move onto * the next cset. */ if (it->flags & CSS_TASK_ITER_SKIPPED) it->flags &= ~CSS_TASK_ITER_SKIPPED; else it->task_pos = it->task_pos->next;
if (it->task_pos == &it->cur_cset->tasks) { it->cur_tasks_head = &it->cur_cset->mg_tasks; it->task_pos = it->cur_tasks_head->next; } if (it->task_pos == &it->cur_cset->mg_tasks) { it->cur_tasks_head = &it->cur_cset->dying_tasks; it->task_pos = it->cur_tasks_head->next; } if (it->task_pos == &it->cur_cset->dying_tasks) css_task_iter_advance_css_set(it); } else { /* called from start, proceed to the first cset */ css_task_iter_advance_css_set(it); }
if (!it->task_pos) return;
task = list_entry(it->task_pos, struct task_struct, cg_list); /* * Hide tasks that are exiting but not yet removed by default. Keep * zombie leaders with live threads visible. Usages that need to walk * every existing task can opt out via CSS_TASK_ITER_WITH_DEAD. */ if (!(it->flags & CSS_TASK_ITER_WITH_DEAD) && (task->flags & PF_EXITING) && !atomic_read(&task->signal->live)) goto repeat;
if (it->flags & CSS_TASK_ITER_PROCS) { /* if PROCS, skip over tasks which aren't group leaders */ if (!thread_group_leader(task)) goto repeat;
/* and dying leaders w/o live member threads */ if (it->cur_tasks_head == &it->cur_cset->dying_tasks && !atomic_read(&task->signal->live)) goto repeat; } else { /* skip all dying ones */ if (it->cur_tasks_head == &it->cur_cset->dying_tasks) goto repeat; }}
/** * css_task_iter_start - initiate task iteration * @css: the css to walk tasks of * @flags: CSS_TASK_ITER_* flags * @it: the task iterator to use * * Initiate iteration through the tasks of @css. The caller can call * css_task_iter_next() to walk through the tasks until the function * returns NULL. On completion of iteration, css_task_iter_end() must be * called. */void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags, struct css_task_iter *it){ unsigned long irqflags;
memset(it, 0, sizeof(*it));
spin_lock_irqsave(&css_set_lock, irqflags);
it->ss = css->ss; it->flags = flags;
if (CGROUP_HAS_SUBSYS_CONFIG && it->ss) it->cset_pos = &css->cgroup->e_csets[css->ss->id]; else it->cset_pos = &css->cgroup->cset_links;
it->cset_head = it->cset_pos;
css_task_iter_advance(it);
spin_unlock_irqrestore(&css_set_lock, irqflags);}
/** * css_task_iter_next - return the next task for the iterator * @it: the task iterator being iterated * * The "next" function for task iteration. @it should have been * initialized via css_task_iter_start(). Returns NULL when the iteration * reaches the end. */struct task_struct *css_task_iter_next(struct css_task_iter *it){ unsigned long irqflags;
if (it->cur_task) { put_task_struct(it->cur_task); it->cur_task = NULL; }
spin_lock_irqsave(&css_set_lock, irqflags);
/* @it may be half-advanced by skips, finish advancing */ if (it->flags & CSS_TASK_ITER_SKIPPED) css_task_iter_advance(it);
if (it->task_pos) { it->cur_task = list_entry(it->task_pos, struct task_struct, cg_list); get_task_struct(it->cur_task); css_task_iter_advance(it); }
spin_unlock_irqrestore(&css_set_lock, irqflags);
return it->cur_task;}
/** * css_task_iter_end - finish task iteration * @it: the task iterator to finish * * Finish task iteration started by css_task_iter_start(). */void css_task_iter_end(struct css_task_iter *it){ unsigned long irqflags;
if (it->cur_cset) { spin_lock_irqsave(&css_set_lock, irqflags); list_del(&it->iters_node); put_css_set_locked(it->cur_cset); spin_unlock_irqrestore(&css_set_lock, irqflags); }
if (it->cur_dcset) put_css_set(it->cur_dcset);
if (it->cur_task) put_task_struct(it->cur_task);}
static void cgroup_procs_release(struct kernfs_open_file *of){ struct cgroup_file_ctx *ctx = of->priv;
if (ctx->procs.started) css_task_iter_end(&ctx->procs.iter);}
static void *cgroup_procs_next(struct seq_file *s, void *v, loff_t *pos){ struct kernfs_open_file *of = s->private; struct cgroup_file_ctx *ctx = of->priv;
if (pos) (*pos)++;
return css_task_iter_next(&ctx->procs.iter);}
static void *__cgroup_procs_start(struct seq_file *s, loff_t *pos, unsigned int iter_flags){ struct kernfs_open_file *of = s->private; struct cgroup *cgrp = seq_css(s)->cgroup; struct cgroup_file_ctx *ctx = of->priv; struct css_task_iter *it = &ctx->procs.iter;
/* * When a seq_file is seeked, it's always traversed sequentially * from position 0, so we can simply keep iterating on !0 *pos. */ if (!ctx->procs.started) { if (WARN_ON_ONCE((*pos))) return ERR_PTR(-EINVAL); css_task_iter_start(&cgrp->self, iter_flags, it); ctx->procs.started = true; } else if (!(*pos)) { css_task_iter_end(it); css_task_iter_start(&cgrp->self, iter_flags, it); } else return it->cur_task;
return cgroup_procs_next(s, NULL, NULL);}
static void *cgroup_procs_start(struct seq_file *s, loff_t *pos){ struct cgroup *cgrp = seq_css(s)->cgroup;
/* * All processes of a threaded subtree belong to the domain cgroup * of the subtree. Only threads can be distributed across the * subtree. Reject reads on cgroup.procs in the subtree proper. * They're always empty anyway. */ if (cgroup_is_threaded(cgrp)) return ERR_PTR(-EOPNOTSUPP);
return __cgroup_procs_start(s, pos, CSS_TASK_ITER_PROCS | CSS_TASK_ITER_THREADED);}
static int cgroup_procs_show(struct seq_file *s, void *v){ seq_printf(s, "%d\n", task_pid_vnr(v)); return 0;}
static int cgroup_may_write(const struct cgroup *cgrp, struct super_block *sb){ int ret; struct inode *inode;
lockdep_assert_held(&cgroup_mutex);
inode = kernfs_get_inode(sb, cgrp->procs_file.kn); if (!inode) return -ENOMEM;
ret = inode_permission(&nop_mnt_idmap, inode, MAY_WRITE); iput(inode); return ret;}
static int cgroup_procs_write_permission(struct cgroup *src_cgrp, struct cgroup *dst_cgrp, struct super_block *sb, struct cgroup_namespace *ns){ struct cgroup *com_cgrp = src_cgrp; int ret;
lockdep_assert_held(&cgroup_mutex);
/* find the common ancestor */ while (!cgroup_is_descendant(dst_cgrp, com_cgrp)) com_cgrp = cgroup_parent(com_cgrp);
/* %current should be authorized to migrate to the common ancestor */ ret = cgroup_may_write(com_cgrp, sb); if (ret) return ret;
/* * If namespaces are delegation boundaries, %current must be able * to see both source and destination cgroups from its namespace. */ if ((cgrp_dfl_root.flags & CGRP_ROOT_NS_DELEGATE) && (!cgroup_is_descendant(src_cgrp, ns->root_cset->dfl_cgrp) || !cgroup_is_descendant(dst_cgrp, ns->root_cset->dfl_cgrp))) return -ENOENT;
return 0;}
static int cgroup_attach_permissions(struct cgroup *src_cgrp, struct cgroup *dst_cgrp, struct super_block *sb, bool threadgroup, struct cgroup_namespace *ns){ int ret = 0;
ret = cgroup_procs_write_permission(src_cgrp, dst_cgrp, sb, ns); if (ret) return ret;
ret = cgroup_migrate_vet_dst(dst_cgrp); if (ret) return ret;
if (!threadgroup && (src_cgrp->dom_cgrp != dst_cgrp->dom_cgrp)) ret = -EOPNOTSUPP;
return ret;}
static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf, bool threadgroup){ struct cgroup_file_ctx *ctx = of->priv; struct cgroup *src_cgrp, *dst_cgrp; struct task_struct *task; ssize_t ret; enum cgroup_attach_lock_mode lock_mode;
dst_cgrp = cgroup_kn_lock_live(of->kn, false); if (!dst_cgrp) return -ENODEV;
task = cgroup_procs_write_start(buf, threadgroup, &lock_mode); ret = PTR_ERR_OR_ZERO(task); if (ret) goto out_unlock;
/* find the source cgroup */ spin_lock_irq(&css_set_lock); src_cgrp = task_cgroup_from_root(task, &cgrp_dfl_root); spin_unlock_irq(&css_set_lock);
/* * Process and thread migrations follow same delegation rule. Check * permissions using the credentials from file open to protect against * inherited fd attacks. */ scoped_with_creds(of->file->f_cred) ret = cgroup_attach_permissions(src_cgrp, dst_cgrp, of->file->f_path.dentry->d_sb, threadgroup, ctx->ns); if (ret) goto out_finish;
ret = cgroup_attach_task(dst_cgrp, task, threadgroup);
out_finish: cgroup_procs_write_finish(task, lock_mode);out_unlock: cgroup_kn_unlock(of->kn);
return ret;}
static ssize_t cgroup_procs_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off){ return __cgroup_procs_write(of, buf, true) ?: nbytes;}
static void *cgroup_threads_start(struct seq_file *s, loff_t *pos){ return __cgroup_procs_start(s, pos, 0);}
static ssize_t cgroup_threads_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off){ return __cgroup_procs_write(of, buf, false) ?: nbytes;}
/* cgroup core interface files for the default hierarchy */static struct cftype cgroup_base_files[] = { { .name = "cgroup.type", .flags = CFTYPE_NOT_ON_ROOT, .seq_show = cgroup_type_show, .write = cgroup_type_write, }, { .name = "cgroup.procs", .flags = CFTYPE_NS_DELEGATABLE, .file_offset = offsetof(struct cgroup, procs_file), .release = cgroup_procs_release, .seq_start = cgroup_procs_start, .seq_next = cgroup_procs_next, .seq_show = cgroup_procs_show, .write = cgroup_procs_write, }, { .name = "cgroup.threads", .flags = CFTYPE_NS_DELEGATABLE, .release = cgroup_procs_release, .seq_start = cgroup_threads_start, .seq_next = cgroup_procs_next, .seq_show = cgroup_procs_show, .write = cgroup_threads_write, }, { .name = "cgroup.controllers", .seq_show = cgroup_controllers_show, }, { .name = "cgroup.subtree_control", .flags = CFTYPE_NS_DELEGATABLE, .seq_show = cgroup_subtree_control_show, .write = cgroup_subtree_control_write, }, { .name = "cgroup.events", .flags = CFTYPE_NOT_ON_ROOT, .file_offset = offsetof(struct cgroup, events_file), .seq_show = cgroup_events_show, }, { .name = "cgroup.max.descendants", .seq_show = cgroup_max_descendants_show, .write = cgroup_max_descendants_write, }, { .name = "cgroup.max.depth", .seq_show = cgroup_max_depth_show, .write = cgroup_max_depth_write, }, { .name = "cgroup.stat", .seq_show = cgroup_stat_show, }, { .name = "cgroup.stat.local", .flags = CFTYPE_NOT_ON_ROOT, .seq_show = cgroup_core_local_stat_show, }, { .name = "cgroup.freeze", .flags = CFTYPE_NOT_ON_ROOT, .seq_show = cgroup_freeze_show, .write = cgroup_freeze_write, }, { .name = "cgroup.kill", .flags = CFTYPE_NOT_ON_ROOT, .write = cgroup_kill_write, }, { .name = "cpu.stat", .seq_show = cpu_stat_show, }, { .name = "cpu.stat.local", .seq_show = cpu_local_stat_show, }, { } /* terminate */};
static struct cftype cgroup_psi_files[] = {#ifdef CONFIG_PSI { .name = "io.pressure", .file_offset = offsetof(struct cgroup, psi_files[PSI_IO]), .seq_show = cgroup_io_pressure_show, .write = cgroup_io_pressure_write, .poll = cgroup_pressure_poll, .release = cgroup_pressure_release, }, { .name = "memory.pressure", .file_offset = offsetof(struct cgroup, psi_files[PSI_MEM]), .seq_show = cgroup_memory_pressure_show, .write = cgroup_memory_pressure_write, .poll = cgroup_pressure_poll, .release = cgroup_pressure_release, }, { .name = "cpu.pressure", .file_offset = offsetof(struct cgroup, psi_files[PSI_CPU]), .seq_show = cgroup_cpu_pressure_show, .write = cgroup_cpu_pressure_write, .poll = cgroup_pressure_poll, .release = cgroup_pressure_release, },#ifdef CONFIG_IRQ_TIME_ACCOUNTING { .name = "irq.pressure", .file_offset = offsetof(struct cgroup, psi_files[PSI_IRQ]), .seq_show = cgroup_irq_pressure_show, .write = cgroup_irq_pressure_write, .poll = cgroup_pressure_poll, .release = cgroup_pressure_release, },#endif { .name = "cgroup.pressure", .seq_show = cgroup_pressure_show, .write = cgroup_pressure_write, },#endif /* CONFIG_PSI */ { } /* terminate */};
/* * css destruction is four-stage process. * * 1. Destruction starts. Killing of the percpu_ref is initiated. * Implemented in kill_css_finish(). * * 2. When the percpu_ref is confirmed to be visible as killed on all CPUs * and thus css_tryget_online() is guaranteed to fail, the css can be * offlined by invoking offline_css(). After offlining, the base ref is * put. Implemented in css_killed_work_fn(). * * 3. When the percpu_ref reaches zero, the only possible remaining * accessors are inside RCU read sections. css_release() schedules the * RCU callback. * * 4. After the grace period, the css can be freed. Implemented in * css_free_rwork_fn(). * * It is actually hairier because both step 2 and 4 require process context * and thus involve punting to css->destroy_work adding two additional * steps to the already complex sequence. */static void css_free_rwork_fn(struct work_struct *work){ struct cgroup_subsys_state *css = container_of(to_rcu_work(work), struct cgroup_subsys_state, destroy_rwork); struct cgroup_subsys *ss = css->ss; struct cgroup *cgrp = css->cgroup;
percpu_ref_exit(&css->refcnt); css_rstat_exit(css);
if (!css_is_self(css)) { /* css free path */ struct cgroup_subsys_state *parent = css->parent; int id = css->id;
ss->css_free(css); cgroup_idr_remove(&ss->css_idr, id); cgroup_put(cgrp);
if (parent) css_put(parent); } else { /* cgroup free path */ atomic_dec(&cgrp->root->nr_cgrps); if (!cgroup_on_dfl(cgrp)) cgroup1_pidlist_destroy_all(cgrp); cancel_work_sync(&cgrp->release_agent_work); bpf_cgrp_storage_free(cgrp);
if (cgroup_parent(cgrp)) { /* * We get a ref to the parent, and put the ref when * this cgroup is being freed, so it's guaranteed * that the parent won't be destroyed before its * children. */ cgroup_put(cgroup_parent(cgrp)); kernfs_put(cgrp->kn); psi_cgroup_free(cgrp); kfree(cgrp); } else { /* * This is root cgroup's refcnt reaching zero, * which indicates that the root should be * released. */ cgroup_destroy_root(cgrp->root); } }}
static void css_release_work_fn(struct work_struct *work){ struct cgroup_subsys_state *css = container_of(work, struct cgroup_subsys_state, destroy_work); struct cgroup_subsys *ss = css->ss; struct cgroup *cgrp = css->cgroup;
cgroup_lock();
css->flags |= CSS_RELEASED; list_del_rcu(&css->sibling);
if (!css_is_self(css)) { struct cgroup *parent_cgrp;
css_rstat_flush(css);
cgroup_idr_replace(&ss->css_idr, NULL, css->id); if (ss->css_released) ss->css_released(css);
cgrp->nr_dying_subsys[ss->id]--; /* * When a css is released and ready to be freed, its * nr_descendants must be zero. However, the corresponding * cgrp->nr_dying_subsys[ss->id] may not be 0 if a subsystem * is activated and deactivated multiple times with one or * more of its previous activation leaving behind dying csses. */ WARN_ON_ONCE(css->nr_descendants); parent_cgrp = cgroup_parent(cgrp); while (parent_cgrp) { parent_cgrp->nr_dying_subsys[ss->id]--; parent_cgrp = cgroup_parent(parent_cgrp); } } else { struct cgroup *tcgrp;
/* cgroup release path */ TRACE_CGROUP_PATH(release, cgrp);
css_rstat_flush(&cgrp->self);
spin_lock_irq(&css_set_lock); for (tcgrp = cgroup_parent(cgrp); tcgrp; tcgrp = cgroup_parent(tcgrp)) tcgrp->nr_dying_descendants--; spin_unlock_irq(&css_set_lock);
/* * There are two control paths which try to determine * cgroup from dentry without going through kernfs - * cgroupstats_build() and css_tryget_online_from_dir(). * Those are supported by RCU protecting clearing of * cgrp->kn->priv backpointer. */ if (cgrp->kn) RCU_INIT_POINTER(*(void __rcu __force **)&cgrp->kn->priv, NULL); }
cgroup_unlock();
INIT_RCU_WORK(&css->destroy_rwork, css_free_rwork_fn); queue_rcu_work(cgroup_free_wq, &css->destroy_rwork);}
static void css_release(struct percpu_ref *ref){ struct cgroup_subsys_state *css = container_of(ref, struct cgroup_subsys_state, refcnt);
INIT_WORK(&css->destroy_work, css_release_work_fn); queue_work(cgroup_release_wq, &css->destroy_work);}
/* * Deferred kill_css_finish() fired from css_update_populated() once a dying * css's hierarchical populated state drops to zero. Pinned by css_get() at the * queue site; matched by css_put() here. */static void kill_css_finish_work_fn(struct work_struct *work){ struct cgroup_subsys_state *css = container_of(work, struct cgroup_subsys_state, kill_finish_work);
cgroup_lock(); kill_css_finish(css); cgroup_unlock(); css_put(css);}
static void init_and_link_css(struct cgroup_subsys_state *css, struct cgroup_subsys *ss, struct cgroup *cgrp){ lockdep_assert_held(&cgroup_mutex);
cgroup_get_live(cgrp);
memset(css, 0, sizeof(*css)); css->cgroup = cgrp; css->ss = ss; css->id = -1; INIT_LIST_HEAD(&css->sibling); INIT_LIST_HEAD(&css->children); INIT_WORK(&css->kill_finish_work, kill_css_finish_work_fn); css->serial_nr = css_serial_nr_next++; atomic_set(&css->online_cnt, 0);
if (cgroup_parent(cgrp)) { css->parent = cgroup_css(cgroup_parent(cgrp), ss); css_get(css->parent); }
BUG_ON(cgroup_css(cgrp, ss));}
/* invoke ->css_online() on a new CSS and mark it online if successful */static int online_css(struct cgroup_subsys_state *css){ struct cgroup_subsys *ss = css->ss; int ret = 0;
lockdep_assert_held(&cgroup_mutex);
if (ss->css_online) ret = ss->css_online(css); if (!ret) { css->flags |= CSS_ONLINE; rcu_assign_pointer(css->cgroup->subsys[ss->id], css);
atomic_inc(&css->online_cnt); if (css->parent) { atomic_inc(&css->parent->online_cnt); while ((css = css->parent)) css->nr_descendants++; } } return ret;}
/* if the CSS is online, invoke ->css_offline() on it and mark it offline */static void offline_css(struct cgroup_subsys_state *css){ struct cgroup_subsys *ss = css->ss;
lockdep_assert_held(&cgroup_mutex);
if (!css_is_online(css)) return;
if (ss->css_offline) ss->css_offline(css);
css->flags &= ~CSS_ONLINE; RCU_INIT_POINTER(css->cgroup->subsys[ss->id], NULL);
wake_up_all(&css->cgroup->offline_waitq);}
/** * css_create - create a cgroup_subsys_state * @cgrp: the cgroup new css will be associated with * @ss: the subsys of new css * * Create a new css associated with @cgrp - @ss pair. On success, the new * css is online and installed in @cgrp. This function doesn't create the * interface files. Returns 0 on success, -errno on failure. */static struct cgroup_subsys_state *css_create(struct cgroup *cgrp, struct cgroup_subsys *ss){ struct cgroup *parent = cgroup_parent(cgrp); struct cgroup_subsys_state *parent_css = cgroup_css(parent, ss); struct cgroup_subsys_state *css; int err;
lockdep_assert_held(&cgroup_mutex);
css = ss->css_alloc(parent_css); if (!css) css = ERR_PTR(-ENOMEM); if (IS_ERR(css)) return css;
init_and_link_css(css, ss, cgrp);
err = percpu_ref_init(&css->refcnt, css_release, 0, GFP_KERNEL); if (err) goto err_free_css;
err = cgroup_idr_alloc(&ss->css_idr, NULL, 2, 0, GFP_KERNEL); if (err < 0) goto err_free_css; css->id = err;
err = css_rstat_init(css); if (err) goto err_free_css;
/* @css is ready to be brought online now, make it visible */ list_add_tail_rcu(&css->sibling, &parent_css->children); cgroup_idr_replace(&ss->css_idr, css, css->id);
err = online_css(css); if (err) goto err_list_del;
return css;
err_list_del: list_del_rcu(&css->sibling);err_free_css: INIT_RCU_WORK(&css->destroy_rwork, css_free_rwork_fn); queue_rcu_work(cgroup_free_wq, &css->destroy_rwork); return ERR_PTR(err);}
/* * The returned cgroup is fully initialized including its control mask, but * it doesn't have the control mask applied. */static struct cgroup *cgroup_create(struct cgroup *parent, const char *name, umode_t mode){ struct cgroup_root *root = parent->root; struct cgroup *cgrp, *tcgrp; struct kernfs_node *kn; int i, level = parent->level + 1; int ret;
/* allocate the cgroup and its ID, 0 is reserved for the root */ cgrp = kzalloc_flex(*cgrp, _low_ancestors, level); if (!cgrp) return ERR_PTR(-ENOMEM);
ret = percpu_ref_init(&cgrp->self.refcnt, css_release, 0, GFP_KERNEL); if (ret) goto out_free_cgrp;
/* create the directory */ kn = kernfs_create_dir_ns(parent->kn, name, mode, current_fsuid(), current_fsgid(), cgrp, NULL); if (IS_ERR(kn)) { ret = PTR_ERR(kn); goto out_cancel_ref; } cgrp->kn = kn;
init_cgroup_housekeeping(cgrp);
cgrp->self.parent = &parent->self; cgrp->root = root; cgrp->level = level;
/* * Now that init_cgroup_housekeeping() has been called and cgrp->self * is setup, it is safe to perform rstat initialization on it. */ ret = css_rstat_init(&cgrp->self); if (ret) goto out_kernfs_remove;
ret = psi_cgroup_alloc(cgrp); if (ret) goto out_stat_exit;
for (tcgrp = cgrp; tcgrp; tcgrp = cgroup_parent(tcgrp)) cgrp->ancestors[tcgrp->level] = tcgrp;
/* * New cgroup inherits effective freeze counter, and * if the parent has to be frozen, the child has too. */ cgrp->freezer.e_freeze = parent->freezer.e_freeze; seqcount_spinlock_init(&cgrp->freezer.freeze_seq, &css_set_lock); if (cgrp->freezer.e_freeze) { /* * Set the CGRP_FREEZE flag, so when a process will be * attached to the child cgroup, it will become frozen. * At this point the new cgroup is unpopulated, so we can * consider it frozen immediately. */ set_bit(CGRP_FREEZE, &cgrp->flags); cgrp->freezer.freeze_start_nsec = ktime_get_ns(); set_bit(CGRP_FROZEN, &cgrp->flags); }
if (notify_on_release(parent)) set_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &parent->flags)) set_bit(CGRP_CPUSET_CLONE_CHILDREN, &cgrp->flags);
cgrp->self.serial_nr = css_serial_nr_next++;
ret = blocking_notifier_call_chain_robust(&cgroup_lifetime_notifier, CGROUP_LIFETIME_ONLINE, CGROUP_LIFETIME_OFFLINE, cgrp); ret = notifier_to_errno(ret); if (ret) goto out_psi_free;
/* allocation complete, commit to creation */ spin_lock_irq(&css_set_lock); for (i = 0; i < level; i++) { tcgrp = cgrp->ancestors[i]; tcgrp->nr_descendants++;
/* * If the new cgroup is frozen, all ancestor cgroups get a new * frozen descendant, but their state can't change because of * this. */ if (cgrp->freezer.e_freeze) tcgrp->freezer.nr_frozen_descendants++; } spin_unlock_irq(&css_set_lock);
list_add_tail_rcu(&cgrp->self.sibling, &cgroup_parent(cgrp)->self.children); atomic_inc(&root->nr_cgrps); cgroup_get_live(parent);
/* * On the default hierarchy, a child doesn't automatically inherit * subtree_control from the parent. Each is configured manually. */ if (!cgroup_on_dfl(cgrp)) cgrp->subtree_control = cgroup_control(cgrp);
cgroup_propagate_control(cgrp);
return cgrp;
out_psi_free: psi_cgroup_free(cgrp);out_stat_exit: css_rstat_exit(&cgrp->self);out_kernfs_remove: kernfs_remove(cgrp->kn);out_cancel_ref: percpu_ref_exit(&cgrp->self.refcnt);out_free_cgrp: kfree(cgrp); return ERR_PTR(ret);}
static bool cgroup_check_hierarchy_limits(struct cgroup *parent){ struct cgroup *cgroup; int ret = false; int level = 0;
lockdep_assert_held(&cgroup_mutex);
for (cgroup = parent; cgroup; cgroup = cgroup_parent(cgroup)) { if (cgroup->nr_descendants >= cgroup->max_descendants) goto fail;
if (level >= cgroup->max_depth) goto fail;
level++; }
ret = true;fail: return ret;}
int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, umode_t mode){ struct cgroup *parent, *cgrp; int ret;
/* do not accept '\n' to prevent making /proc/<pid>/cgroup unparsable */ if (strchr(name, '\n')) return -EINVAL;
parent = cgroup_kn_lock_live(parent_kn, false); if (!parent) return -ENODEV;
if (!cgroup_check_hierarchy_limits(parent)) { ret = -EAGAIN; goto out_unlock; }
cgrp = cgroup_create(parent, name, mode); if (IS_ERR(cgrp)) { ret = PTR_ERR(cgrp); goto out_unlock; }
/* * This extra ref will be put in css_free_rwork_fn() and guarantees * that @cgrp->kn is always accessible. */ kernfs_get(cgrp->kn);
ret = css_populate_dir(&cgrp->self); if (ret) goto out_destroy;
ret = cgroup_apply_control_enable(cgrp); if (ret) goto out_destroy;
TRACE_CGROUP_PATH(mkdir, cgrp);
/* let's create and online css's */ kernfs_activate(cgrp->kn);
ret = 0; goto out_unlock;
out_destroy: cgroup_destroy_locked(cgrp);out_unlock: cgroup_kn_unlock(parent_kn); return ret;}
/* * This is called when the refcnt of a css is confirmed to be killed. * css_tryget_online() is now guaranteed to fail. Tell the subsystem to * initiate destruction and put the css ref from kill_css_finish(). */static void css_killed_work_fn(struct work_struct *work){ struct cgroup_subsys_state *css;
css = container_of(to_rcu_work(work), struct cgroup_subsys_state, destroy_rwork);
cgroup_lock();
do { offline_css(css); css_put(css); /* @css can't go away while we're holding cgroup_mutex */ css = css->parent; } while (css && atomic_dec_and_test(&css->online_cnt));
cgroup_unlock();}
/* css kill confirmation processing requires process context, bounce */static void css_killed_ref_fn(struct percpu_ref *ref){ struct cgroup_subsys_state *css = container_of(ref, struct cgroup_subsys_state, refcnt);
if (atomic_dec_and_test(&css->online_cnt)) { INIT_RCU_WORK(&css->destroy_rwork, css_killed_work_fn); queue_rcu_work(cgroup_offline_wq, &css->destroy_rwork); }}
/** * kill_css_sync - synchronous half of css teardown * @css: css being killed * * See cgroup_destroy_locked(). */static void kill_css_sync(struct cgroup_subsys_state *css){ struct cgroup_subsys *ss = css->ss;
lockdep_assert_held(&cgroup_mutex);
if (css->flags & CSS_DYING) return;
/* * Call css_killed(), if defined, before setting the CSS_DYING flag */ if (css->ss->css_killed) css->ss->css_killed(css);
css->flags |= CSS_DYING;
/* * Pair with smp_mb() in css_update_populated(). Either our * caller observes the walker's decrement and fires * synchronously, or the walker observes CSS_DYING and queues. */ smp_mb();
/* * This must happen before css is disassociated with its cgroup. * See seq_css() for details. */ css_clear_dir(css);
css->cgroup->nr_dying_subsys[ss->id]++; /* * Parent css and cgroup cannot be freed until after the freeing * of child css, see css_free_rwork_fn(). */ while ((css = css->parent)) { css->nr_descendants--; css->cgroup->nr_dying_subsys[ss->id]++; }}
/** * kill_css_finish - deferred half of css teardown * @css: css being killed * * See cgroup_destroy_locked(). */static void kill_css_finish(struct cgroup_subsys_state *css){ lockdep_assert_held(&cgroup_mutex);
/* * Skip on re-entry: cgroup_apply_control_disable() may have killed @css * earlier. cgroup_destroy_locked() can still walk it because * offline_css() (which NULLs cgrp->subsys[ssid]) runs async. */ if (percpu_ref_is_dying(&css->refcnt)) return;
/* * Killing would put the base ref, but we need to keep it alive until * after ->css_offline(). */ css_get(css);
/* * cgroup core guarantees that, by the time ->css_offline() is invoked, * no new css reference will be given out via css_tryget_online(). We * can't simply call percpu_ref_kill() and proceed to offlining css's * because percpu_ref_kill() doesn't guarantee that the ref is seen as * killed on all CPUs on return. * * Use percpu_ref_kill_and_confirm() to get notifications as each css is * confirmed to be seen as killed on all CPUs. */ percpu_ref_kill_and_confirm(&css->refcnt, css_killed_ref_fn);}
/** * cgroup_destroy_locked - destroy @cgrp (called on rmdir) * @cgrp: cgroup to be destroyed * * Tear down @cgrp on behalf of rmdir. Constraints: * * - Userspace: rmdir must succeed when cgroup.procs and friends are empty. * * - Kernel: subsystem ->css_offline() must not run while any task in @cgrp's * subtree is still doing kernel work. A task hidden from cgroup.procs (past * exit_signals() with signal->live cleared) can still schedule, allocate, and * consume resources until its final context switch. Dying descendants in the * subtree can host such tasks too. * * - Kernel: css_tryget_online() must fail by the time ->css_offline() runs. * * The destruction runs in three parts: * * - This function: synchronous user-visible state teardown plus kill_css_sync() * on each subsystem css. * * - For each subsys css: fire kill_css_finish() synchronously if the subtree is * already drained, otherwise rely on css_update_populated() to queue * kill_finish_work when the last populated cset under the css empties. * * - The percpu_ref kill chain: css_killed_ref_fn -> css_killed_work_fn -> * ->css_offline() -> release/free. * * Return 0 on success, -EBUSY if a userspace-visible task or an online child * remains. */static int cgroup_destroy_locked(struct cgroup *cgrp){ struct cgroup *tcgrp, *parent = cgroup_parent(cgrp); struct cgroup_subsys_state *css; struct cgrp_cset_link *link; struct css_task_iter it; struct task_struct *task; int ssid, ret;
lockdep_assert_held(&cgroup_mutex);
css_task_iter_start(&cgrp->self, 0, &it); task = css_task_iter_next(&it); css_task_iter_end(&it); if (task) return -EBUSY;
/* * Make sure there's no live children. We can't test emptiness of * ->self.children as dead children linger on it while being * drained; otherwise, "rmdir parent/child parent" may fail. */ if (css_has_online_children(&cgrp->self)) return -EBUSY;
/* * Mark @cgrp and the associated csets dead. The former prevents * further task migration and child creation by disabling * cgroup_kn_lock_live(). The latter makes the csets ignored by * the migration path. */ cgrp->self.flags &= ~CSS_ONLINE;
spin_lock_irq(&css_set_lock); list_for_each_entry(link, &cgrp->cset_links, cset_link) link->cset->dead = true; spin_unlock_irq(&css_set_lock);
for_each_css(css, ssid, cgrp) kill_css_sync(css);
/* clear and remove @cgrp dir, @cgrp has an extra ref on its kn */ css_clear_dir(&cgrp->self); kernfs_remove(cgrp->kn);
if (cgroup_is_threaded(cgrp)) parent->nr_threaded_children--;
spin_lock_irq(&css_set_lock); for (tcgrp = parent; tcgrp; tcgrp = cgroup_parent(tcgrp)) { tcgrp->nr_descendants--; tcgrp->nr_dying_descendants++; /* * If the dying cgroup is frozen, decrease frozen descendants * counters of ancestor cgroups. */ if (test_bit(CGRP_FROZEN, &cgrp->flags)) tcgrp->freezer.nr_frozen_descendants--; } spin_unlock_irq(&css_set_lock);
cgroup1_check_for_release(parent);
ret = blocking_notifier_call_chain(&cgroup_lifetime_notifier, CGROUP_LIFETIME_OFFLINE, cgrp); WARN_ON_ONCE(notifier_to_errno(ret));
/* put the base reference */ percpu_ref_kill(&cgrp->self.refcnt);
for_each_css(css, ssid, cgrp) { if (!css_is_populated(css)) kill_css_finish(css); }
return 0;};
int cgroup_rmdir(struct kernfs_node *kn){ struct cgroup *cgrp; int ret = 0;
cgrp = cgroup_kn_lock_live(kn, false); if (!cgrp) return 0;
ret = cgroup_destroy_locked(cgrp); if (!ret) TRACE_CGROUP_PATH(rmdir, cgrp);
cgroup_kn_unlock(kn); return ret;}
static struct kernfs_syscall_ops cgroup_kf_syscall_ops = { .show_options = cgroup_show_options, .mkdir = cgroup_mkdir, .rmdir = cgroup_rmdir, .show_path = cgroup_show_path,};
static void __init cgroup_init_subsys(struct cgroup_subsys *ss, bool early){ struct cgroup_subsys_state *css;
pr_debug("Initializing cgroup subsys %s\n", ss->name);
cgroup_lock();
idr_init(&ss->css_idr); INIT_LIST_HEAD(&ss->cfts);
/* Create the root cgroup state for this subsystem */ ss->root = &cgrp_dfl_root; css = ss->css_alloc(NULL); /* We don't handle early failures gracefully */ BUG_ON(IS_ERR(css)); init_and_link_css(css, ss, &cgrp_dfl_root.cgrp);
/* * Root csses are never destroyed and we can't initialize * percpu_ref during early init. Disable refcnting. */ css->flags |= CSS_NO_REF;
if (early) { /* allocation can't be done safely during early init */ css->id = 1; } else { css->id = cgroup_idr_alloc(&ss->css_idr, css, 1, 2, GFP_KERNEL); BUG_ON(css->id < 0);
BUG_ON(ss_rstat_init(ss)); BUG_ON(css_rstat_init(css)); }
/* Update the init_css_set to contain a subsys * pointer to this state - since the subsystem is * newly registered, all tasks and hence the * init_css_set is in the subsystem's root cgroup. */ init_css_set.subsys[ss->id] = css;
have_fork_callback |= (bool)ss->fork << ss->id; have_exit_callback |= (bool)ss->exit << ss->id; have_release_callback |= (bool)ss->release << ss->id; have_canfork_callback |= (bool)ss->can_fork << ss->id;
/* At system boot, before all subsystems have been * registered, no tasks have been forked, so we don't * need to invoke fork callbacks here. */ BUG_ON(!list_empty(&init_task.tasks));
BUG_ON(online_css(css));
cgroup_unlock();}
/** * cgroup_init_early - cgroup initialization at system boot * * Initialize cgroups at system boot, and initialize any * subsystems that request early init. */int __init cgroup_init_early(void){ static struct cgroup_fs_context __initdata ctx; struct cgroup_subsys *ss; int i;
ctx.root = &cgrp_dfl_root; init_cgroup_root(&ctx); cgrp_dfl_root.cgrp.self.flags |= CSS_NO_REF;
RCU_INIT_POINTER(init_task.cgroups, &init_css_set);
for_each_subsys(ss, i) { WARN(!ss->css_alloc || !ss->css_free || ss->name || ss->id, "invalid cgroup_subsys %d:%s css_alloc=%p css_free=%p id:name=%d:%s\n", i, cgroup_subsys_name[i], ss->css_alloc, ss->css_free, ss->id, ss->name); WARN(strlen(cgroup_subsys_name[i]) > MAX_CGROUP_TYPE_NAMELEN, "cgroup_subsys_name %s too long\n", cgroup_subsys_name[i]); WARN(ss->early_init && ss->css_rstat_flush, "cgroup rstat cannot be used with early init subsystem\n");
ss->id = i; ss->name = cgroup_subsys_name[i]; if (!ss->legacy_name) ss->legacy_name = cgroup_subsys_name[i];
if (ss->early_init) cgroup_init_subsys(ss, true); } return 0;}
/** * cgroup_init - cgroup initialization * * Register cgroup filesystem and /proc file, and initialize * any subsystems that didn't request early init. */int __init cgroup_init(void){ struct cgroup_subsys *ss; int ssid;
BUILD_BUG_ON(CGROUP_SUBSYS_COUNT > 32); BUG_ON(cgroup_init_cftypes(NULL, cgroup_base_files)); BUG_ON(cgroup_init_cftypes(NULL, cgroup_psi_files)); BUG_ON(cgroup_init_cftypes(NULL, cgroup1_base_files));
BUG_ON(ss_rstat_init(NULL));
get_user_ns(init_cgroup_ns.user_ns); cgroup_rt_init();
cgroup_lock();
/* * Add init_css_set to the hash table so that dfl_root can link to * it during init. */ hash_add(css_set_table, &init_css_set.hlist, css_set_hash(init_css_set.subsys));
cgroup_bpf_lifetime_notifier_init();
BUG_ON(cgroup_setup_root(&cgrp_dfl_root, 0));
cgroup_unlock();
for_each_subsys(ss, ssid) { if (ss->early_init) { struct cgroup_subsys_state *css = init_css_set.subsys[ss->id];
css->id = cgroup_idr_alloc(&ss->css_idr, css, 1, 2, GFP_KERNEL); BUG_ON(css->id < 0); } else { cgroup_init_subsys(ss, false); }
list_add_tail(&init_css_set.e_cset_node[ssid], &cgrp_dfl_root.cgrp.e_csets[ssid]);
/* * Setting dfl_root subsys_mask needs to consider the * disabled flag and cftype registration needs kmalloc, * both of which aren't available during early_init. */ if (!cgroup_ssid_enabled(ssid)) continue;
if (cgroup1_ssid_disabled(ssid)) pr_info("Disabling %s control group subsystem in v1 mounts\n", ss->legacy_name);
cgrp_dfl_root.subsys_mask |= 1 << ss->id;
/* implicit controllers must be threaded too */ WARN_ON(ss->implicit_on_dfl && !ss->threaded);
if (ss->implicit_on_dfl) cgrp_dfl_implicit_ss_mask |= 1 << ss->id; else if (!ss->dfl_cftypes) cgrp_dfl_inhibit_ss_mask |= 1 << ss->id;
if (ss->threaded) cgrp_dfl_threaded_ss_mask |= 1 << ss->id;
if (ss->dfl_cftypes == ss->legacy_cftypes) { WARN_ON(cgroup_add_cftypes(ss, ss->dfl_cftypes)); } else { WARN_ON(cgroup_add_dfl_cftypes(ss, ss->dfl_cftypes)); WARN_ON(cgroup_add_legacy_cftypes(ss, ss->legacy_cftypes)); }
if (ss->bind) ss->bind(init_css_set.subsys[ssid]);
cgroup_lock(); css_populate_dir(init_css_set.subsys[ssid]); cgroup_unlock(); }
/* init_css_set.subsys[] has been updated, re-hash */ hash_del(&init_css_set.hlist); hash_add(css_set_table, &init_css_set.hlist, css_set_hash(init_css_set.subsys));
WARN_ON(sysfs_create_mount_point(fs_kobj, "cgroup")); WARN_ON(register_filesystem(&cgroup_fs_type)); WARN_ON(register_filesystem(&cgroup2_fs_type)); WARN_ON(!proc_create_single("cgroups", 0, NULL, proc_cgroupstats_show));#ifdef CONFIG_CPUSETS_V1 WARN_ON(register_filesystem(&cpuset_fs_type));#endif
ns_tree_add(&init_cgroup_ns); return 0;}
static int __init cgroup_wq_init(void){ /* * There isn't much point in executing destruction path in * parallel. Good chunk is serialized with cgroup_mutex anyway. * Use 1 for @max_active. * * We would prefer to do this in cgroup_init() above, but that * is called before init_workqueues(): so leave this until after. */ cgroup_offline_wq = alloc_workqueue("cgroup_offline", WQ_PERCPU, 1); BUG_ON(!cgroup_offline_wq);
cgroup_release_wq = alloc_workqueue("cgroup_release", WQ_PERCPU, 1); BUG_ON(!cgroup_release_wq);
cgroup_free_wq = alloc_workqueue("cgroup_free", WQ_PERCPU, 1); BUG_ON(!cgroup_free_wq); return 0;}core_initcall(cgroup_wq_init);
void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen){ struct kernfs_node *kn;
kn = kernfs_find_and_get_node_by_id(cgrp_dfl_root.kf_root, id); if (!kn) return; kernfs_path(kn, buf, buflen); kernfs_put(kn);}
/* * __cgroup_get_from_id : get the cgroup associated with cgroup id * @id: cgroup id * On success return the cgrp or ERR_PTR on failure * There are no cgroup NS restrictions. */struct cgroup *__cgroup_get_from_id(u64 id){ struct kernfs_node *kn; struct cgroup *cgrp;
kn = kernfs_find_and_get_node_by_id(cgrp_dfl_root.kf_root, id); if (!kn) return ERR_PTR(-ENOENT);
if (kernfs_type(kn) != KERNFS_DIR) { kernfs_put(kn); return ERR_PTR(-ENOENT); }
rcu_read_lock();
cgrp = rcu_dereference(*(void __rcu __force **)&kn->priv); if (cgrp && !cgroup_tryget(cgrp)) cgrp = NULL;
rcu_read_unlock(); kernfs_put(kn);
if (!cgrp) return ERR_PTR(-ENOENT); return cgrp;}
/* * cgroup_get_from_id : get the cgroup associated with cgroup id * @id: cgroup id * On success return the cgrp or ERR_PTR on failure * Only cgroups within current task's cgroup NS are valid. */struct cgroup *cgroup_get_from_id(u64 id){ struct cgroup *cgrp, *root_cgrp;
cgrp = __cgroup_get_from_id(id); if (IS_ERR(cgrp)) return cgrp;
root_cgrp = current_cgns_cgroup_dfl(); if (!cgroup_is_descendant(cgrp, root_cgrp)) { cgroup_put(cgrp); return ERR_PTR(-ENOENT); }
return cgrp;}EXPORT_SYMBOL_GPL(cgroup_get_from_id);
/* * proc_cgroup_show() * - Print task's cgroup paths into seq_file, one line for each hierarchy * - Used for /proc/<pid>/cgroup. */int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *tsk){ char *buf; int retval; struct cgroup_root *root;
retval = -ENOMEM; buf = kmalloc(PATH_MAX, GFP_KERNEL); if (!buf) goto out;
rcu_read_lock(); spin_lock_irq(&css_set_lock);
for_each_root(root) { struct cgroup_subsys *ss; struct cgroup *cgrp; int ssid, count = 0;
if (root == &cgrp_dfl_root && !READ_ONCE(cgrp_dfl_visible)) continue;
cgrp = task_cgroup_from_root(tsk, root); /* The root has already been unmounted. */ if (!cgrp) continue;
seq_printf(m, "%d:", root->hierarchy_id); if (root != &cgrp_dfl_root) for_each_subsys(ss, ssid) if (root->subsys_mask & (1 << ssid)) seq_printf(m, "%s%s", count++ ? "," : "", ss->legacy_name); if (strlen(root->name)) seq_printf(m, "%sname=%s", count ? "," : "", root->name); seq_putc(m, ':'); /* * On traditional hierarchies, all zombie tasks show up as * belonging to the root cgroup. On the default hierarchy, * while a zombie doesn't show up in "cgroup.procs" and * thus can't be migrated, its /proc/PID/cgroup keeps * reporting the cgroup it belonged to before exiting. If * the cgroup is removed before the zombie is reaped, * " (deleted)" is appended to the cgroup path. */ if (cgroup_on_dfl(cgrp) || !(tsk->flags & PF_EXITING)) { retval = cgroup_path_ns_locked(cgrp, buf, PATH_MAX, current->nsproxy->cgroup_ns); if (retval == -E2BIG) retval = -ENAMETOOLONG; if (retval < 0) goto out_unlock;
seq_puts(m, buf); } else { seq_puts(m, "/"); }
if (cgroup_on_dfl(cgrp) && cgroup_is_dead(cgrp)) seq_puts(m, " (deleted)\n"); else seq_putc(m, '\n'); }
retval = 0;out_unlock: spin_unlock_irq(&css_set_lock); rcu_read_unlock(); kfree(buf);out: return retval;}
/** * cgroup_fork - initialize cgroup related fields during copy_process() * @child: pointer to task_struct of forking parent process. * * A task is associated with the init_css_set until cgroup_post_fork() * attaches it to the target css_set. */void cgroup_fork(struct task_struct *child){ RCU_INIT_POINTER(child->cgroups, &init_css_set); INIT_LIST_HEAD(&child->cg_list);}
/** * cgroup_v1v2_get_from_file - get a cgroup pointer from a file pointer * @f: file corresponding to cgroup_dir * * Find the cgroup from a file pointer associated with a cgroup directory. * Returns a pointer to the cgroup on success. ERR_PTR is returned if the * cgroup cannot be found. */static struct cgroup *cgroup_v1v2_get_from_file(struct file *f){ struct cgroup_subsys_state *css;
css = css_tryget_online_from_dir(f->f_path.dentry, NULL); if (IS_ERR(css)) return ERR_CAST(css);
return css->cgroup;}
/** * cgroup_get_from_file - same as cgroup_v1v2_get_from_file, but only supports * cgroup2. * @f: file corresponding to cgroup2_dir */static struct cgroup *cgroup_get_from_file(struct file *f){ struct cgroup *cgrp = cgroup_v1v2_get_from_file(f);
if (IS_ERR(cgrp)) return ERR_CAST(cgrp);
if (!cgroup_on_dfl(cgrp)) { cgroup_put(cgrp); return ERR_PTR(-EBADF); }
return cgrp;}
/** * cgroup_css_set_fork - find or create a css_set for a child process * @kargs: the arguments passed to create the child process * * This functions finds or creates a new css_set which the child * process will be attached to in cgroup_post_fork(). By default, * the child process will be given the same css_set as its parent. * * If CLONE_INTO_CGROUP is specified this function will try to find an * existing css_set which includes the requested cgroup and if not create * a new css_set that the child will be attached to later. If this function * succeeds it will hold cgroup_threadgroup_rwsem on return. If * CLONE_INTO_CGROUP is requested this function will grab cgroup mutex * before grabbing cgroup_threadgroup_rwsem and will hold a reference * to the target cgroup. */static int cgroup_css_set_fork(struct kernel_clone_args *kargs) __acquires(&cgroup_mutex) __acquires(&cgroup_threadgroup_rwsem){ int ret; struct cgroup *dst_cgrp = NULL; struct css_set *cset; struct super_block *sb;
if (kargs->flags & CLONE_INTO_CGROUP) cgroup_lock();
cgroup_threadgroup_change_begin(current);
spin_lock_irq(&css_set_lock); cset = task_css_set(current); get_css_set(cset); if (kargs->cgrp) kargs->kill_seq = kargs->cgrp->kill_seq; else kargs->kill_seq = cset->dfl_cgrp->kill_seq; spin_unlock_irq(&css_set_lock);
if (!(kargs->flags & CLONE_INTO_CGROUP)) { kargs->cset = cset; return 0; }
CLASS(fd_raw, f)(kargs->cgroup); if (fd_empty(f)) { ret = -EBADF; goto err; } sb = fd_file(f)->f_path.dentry->d_sb;
dst_cgrp = cgroup_get_from_file(fd_file(f)); if (IS_ERR(dst_cgrp)) { ret = PTR_ERR(dst_cgrp); dst_cgrp = NULL; goto err; }
if (cgroup_is_dead(dst_cgrp)) { ret = -ENODEV; goto err; }
/* * Verify that we the target cgroup is writable for us. This is * usually done by the vfs layer but since we're not going through * the vfs layer here we need to do it "manually". */ ret = cgroup_may_write(dst_cgrp, sb); if (ret) goto err;
/* * Spawning a task directly into a cgroup works by passing a file * descriptor to the target cgroup directory. This can even be an O_PATH * file descriptor. But it can never be a cgroup.procs file descriptor. * This was done on purpose so spawning into a cgroup could be * conceptualized as an atomic * * fd = openat(dfd_cgroup, "cgroup.procs", ...); * write(fd, <child-pid>, ...); * * sequence, i.e. it's a shorthand for the caller opening and writing * cgroup.procs of the cgroup indicated by @dfd_cgroup. This allows us * to always use the caller's credentials. */ ret = cgroup_attach_permissions(cset->dfl_cgrp, dst_cgrp, sb, !(kargs->flags & CLONE_THREAD), current->nsproxy->cgroup_ns); if (ret) goto err;
kargs->cset = find_css_set(cset, dst_cgrp); if (!kargs->cset) { ret = -ENOMEM; goto err; }
put_css_set(cset); kargs->cgrp = dst_cgrp; return ret;
err: cgroup_threadgroup_change_end(current); cgroup_unlock(); if (dst_cgrp) cgroup_put(dst_cgrp); put_css_set(cset); if (kargs->cset) put_css_set(kargs->cset); return ret;}
/** * cgroup_css_set_put_fork - drop references we took during fork * @kargs: the arguments passed to create the child process * * Drop references to the prepared css_set and target cgroup if * CLONE_INTO_CGROUP was requested. */static void cgroup_css_set_put_fork(struct kernel_clone_args *kargs) __releases(&cgroup_threadgroup_rwsem) __releases(&cgroup_mutex){ struct cgroup *cgrp = kargs->cgrp; struct css_set *cset = kargs->cset;
cgroup_threadgroup_change_end(current);
if (cset) { put_css_set(cset); kargs->cset = NULL; }
if (kargs->flags & CLONE_INTO_CGROUP) { cgroup_unlock(); if (cgrp) { cgroup_put(cgrp); kargs->cgrp = NULL; } }}
/** * cgroup_can_fork - called on a new task before the process is exposed * @child: the child process * @kargs: the arguments passed to create the child process * * This prepares a new css_set for the child process which the child will * be attached to in cgroup_post_fork(). * This calls the subsystem can_fork() callbacks. If the cgroup_can_fork() * callback returns an error, the fork aborts with that error code. This * allows for a cgroup subsystem to conditionally allow or deny new forks. */int cgroup_can_fork(struct task_struct *child, struct kernel_clone_args *kargs){ struct cgroup_subsys *ss; int i, j, ret;
ret = cgroup_css_set_fork(kargs); if (ret) return ret;
do_each_subsys_mask(ss, i, have_canfork_callback) { ret = ss->can_fork(child, kargs->cset); if (ret) goto out_revert; } while_each_subsys_mask();
return 0;
out_revert: for_each_subsys(ss, j) { if (j >= i) break; if (ss->cancel_fork) ss->cancel_fork(child, kargs->cset); }
cgroup_css_set_put_fork(kargs);
return ret;}
/** * cgroup_cancel_fork - called if a fork failed after cgroup_can_fork() * @child: the child process * @kargs: the arguments passed to create the child process * * This calls the cancel_fork() callbacks if a fork failed *after* * cgroup_can_fork() succeeded and cleans up references we took to * prepare a new css_set for the child process in cgroup_can_fork(). */void cgroup_cancel_fork(struct task_struct *child, struct kernel_clone_args *kargs){ struct cgroup_subsys *ss; int i;
for_each_subsys(ss, i) if (ss->cancel_fork) ss->cancel_fork(child, kargs->cset);
cgroup_css_set_put_fork(kargs);}
/** * cgroup_post_fork - finalize cgroup setup for the child process * @child: the child process * @kargs: the arguments passed to create the child process * * Attach the child process to its css_set calling the subsystem fork() * callbacks. */void cgroup_post_fork(struct task_struct *child, struct kernel_clone_args *kargs) __releases(&cgroup_threadgroup_rwsem) __releases(&cgroup_mutex){ unsigned int cgrp_kill_seq = 0; unsigned long cgrp_flags = 0; bool kill = false; struct cgroup_subsys *ss; struct css_set *cset; int i;
cset = kargs->cset; kargs->cset = NULL;
spin_lock_irq(&css_set_lock);
/* init tasks are special, only link regular threads */ if (likely(child->pid)) { if (kargs->cgrp) { cgrp_flags = kargs->cgrp->flags; cgrp_kill_seq = kargs->cgrp->kill_seq; } else { cgrp_flags = cset->dfl_cgrp->flags; cgrp_kill_seq = cset->dfl_cgrp->kill_seq; }
WARN_ON_ONCE(!list_empty(&child->cg_list)); cset->nr_tasks++; css_set_move_task(child, NULL, cset, false); } else { put_css_set(cset); cset = NULL; }
if (!(child->flags & PF_KTHREAD)) { if (unlikely(test_bit(CGRP_FREEZE, &cgrp_flags))) { /* * If the cgroup has to be frozen, the new task has * too. Let's set the JOBCTL_TRAP_FREEZE jobctl bit to * get the task into the frozen state. */ spin_lock(&child->sighand->siglock); WARN_ON_ONCE(child->frozen); child->jobctl |= JOBCTL_TRAP_FREEZE; spin_unlock(&child->sighand->siglock);
/* * Calling cgroup_update_frozen() isn't required here, * because it will be called anyway a bit later from * do_freezer_trap(). So we avoid cgroup's transient * switch from the frozen state and back. */ }
/* * If the cgroup is to be killed notice it now and take the * child down right after we finished preparing it for * userspace. */ kill = kargs->kill_seq != cgrp_kill_seq; }
spin_unlock_irq(&css_set_lock);
/* * Call ss->fork(). This must happen after @child is linked on * css_set; otherwise, @child might change state between ->fork() * and addition to css_set. */ do_each_subsys_mask(ss, i, have_fork_callback) { ss->fork(child); } while_each_subsys_mask();
/* Make the new cset the root_cset of the new cgroup namespace. */ if (kargs->flags & CLONE_NEWCGROUP) { struct css_set *rcset = child->nsproxy->cgroup_ns->root_cset;
get_css_set(cset); child->nsproxy->cgroup_ns->root_cset = cset; put_css_set(rcset); }
/* Cgroup has to be killed so take down child immediately. */ if (unlikely(kill)) do_send_sig_info(SIGKILL, SEND_SIG_NOINFO, child, PIDTYPE_TGID);
cgroup_css_set_put_fork(kargs);}
/** * cgroup_task_exit - detach cgroup from exiting task * @tsk: pointer to task_struct of exiting process * * Description: Detach cgroup from @tsk. * */void cgroup_task_exit(struct task_struct *tsk){ struct cgroup_subsys *ss; int i;
/* see cgroup_post_fork() for details */ do_each_subsys_mask(ss, i, have_exit_callback) { ss->exit(tsk); } while_each_subsys_mask();}
static void do_cgroup_task_dead(struct task_struct *tsk){ struct css_set *cset; unsigned long flags;
spin_lock_irqsave(&css_set_lock, flags);
WARN_ON_ONCE(list_empty(&tsk->cg_list)); cset = task_css_set(tsk); css_set_move_task(tsk, cset, NULL, false); cset->nr_tasks--; /* matches the signal->live check in css_task_iter_advance() */ if (thread_group_leader(tsk) && atomic_read(&tsk->signal->live)) list_add_tail(&tsk->cg_list, &cset->dying_tasks);
if (dl_task(tsk)) dec_dl_tasks_cs(tsk);
WARN_ON_ONCE(cgroup_task_frozen(tsk)); if (unlikely(!(tsk->flags & PF_KTHREAD) && test_bit(CGRP_FREEZE, &task_dfl_cgroup(tsk)->flags))) cgroup_update_frozen(task_dfl_cgroup(tsk));
spin_unlock_irqrestore(&css_set_lock, flags);}
#ifdef CONFIG_PREEMPT_RT/* * cgroup_task_dead() is called from finish_task_switch() which doesn't allow * scheduling even in RT. As the task_dead path requires grabbing css_set_lock, * this lead to sleeping in the invalid context warning bug. css_set_lock is too * big to become a raw_spinlock. The task_dead path doesn't need to run * synchronously but can't be delayed indefinitely either as the dead task pins * the cgroup and task_struct can be pinned indefinitely. Bounce through lazy * irq_work to allow batching while ensuring timely completion. */static DEFINE_PER_CPU(struct llist_head, cgrp_dead_tasks);static DEFINE_PER_CPU(struct irq_work, cgrp_dead_tasks_iwork);
static void cgrp_dead_tasks_iwork_fn(struct irq_work *iwork){ struct llist_node *lnode; struct task_struct *task, *next;
lnode = llist_del_all(this_cpu_ptr(&cgrp_dead_tasks)); llist_for_each_entry_safe(task, next, lnode, cg_dead_lnode) { do_cgroup_task_dead(task); put_task_struct(task); }}
static void __init cgroup_rt_init(void){ int cpu;
for_each_possible_cpu(cpu) { init_llist_head(per_cpu_ptr(&cgrp_dead_tasks, cpu)); per_cpu(cgrp_dead_tasks_iwork, cpu) = IRQ_WORK_INIT_LAZY(cgrp_dead_tasks_iwork_fn); }}
void cgroup_task_dead(struct task_struct *task){ get_task_struct(task); llist_add(&task->cg_dead_lnode, this_cpu_ptr(&cgrp_dead_tasks)); irq_work_queue(this_cpu_ptr(&cgrp_dead_tasks_iwork));}#else /* CONFIG_PREEMPT_RT */static void __init cgroup_rt_init(void) {}
void cgroup_task_dead(struct task_struct *task){ do_cgroup_task_dead(task);}#endif /* CONFIG_PREEMPT_RT */
void cgroup_task_release(struct task_struct *task){ struct cgroup_subsys *ss; int ssid;
do_each_subsys_mask(ss, ssid, have_release_callback) { ss->release(task); } while_each_subsys_mask();}
void cgroup_task_free(struct task_struct *task){ struct css_set *cset = task_css_set(task);
if (!list_empty(&task->cg_list)) { spin_lock_irq(&css_set_lock); css_set_skip_task_iters(task_css_set(task), task); list_del_init(&task->cg_list); spin_unlock_irq(&css_set_lock); }
put_css_set(cset);}
static int __init cgroup_disable(char *str){ struct cgroup_subsys *ss; char *token; int i;
while ((token = strsep(&str, ",")) != NULL) { if (!*token) continue;
for_each_subsys(ss, i) { if (strcmp(token, ss->name) && strcmp(token, ss->legacy_name)) continue;
static_branch_disable(cgroup_subsys_enabled_key[i]); pr_info("Disabling %s control group subsystem\n", ss->name); }
for (i = 0; i < OPT_FEATURE_COUNT; i++) { if (strcmp(token, cgroup_opt_feature_names[i])) continue; cgroup_feature_disable_mask |= 1 << i; pr_info("Disabling %s control group feature\n", cgroup_opt_feature_names[i]); break; } } return 1;}__setup("cgroup_disable=", cgroup_disable);
void __init __weak enable_debug_cgroup(void) { }
static int __init enable_cgroup_debug(char *str){ cgroup_debug = true; enable_debug_cgroup(); return 1;}__setup("cgroup_debug", enable_cgroup_debug);
static int __init cgroup_favordynmods_setup(char *str){ return (kstrtobool(str, &have_favordynmods) == 0);}__setup("cgroup_favordynmods=", cgroup_favordynmods_setup);
/** * css_tryget_online_from_dir - get corresponding css from a cgroup dentry * @dentry: directory dentry of interest * @ss: subsystem of interest * * If @dentry is a directory for a cgroup which has @ss enabled on it, try * to get the corresponding css and return it. If such css doesn't exist * or can't be pinned, an ERR_PTR value is returned. */struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry, struct cgroup_subsys *ss){ struct kernfs_node *kn = kernfs_node_from_dentry(dentry); struct file_system_type *s_type = dentry->d_sb->s_type; struct cgroup_subsys_state *css = NULL; struct cgroup *cgrp;
/* is @dentry a cgroup dir? */ if ((s_type != &cgroup_fs_type && s_type != &cgroup2_fs_type) || !kn || kernfs_type(kn) != KERNFS_DIR) return ERR_PTR(-EBADF);
rcu_read_lock();
/* * This path doesn't originate from kernfs and @kn could already * have been or be removed at any point. @kn->priv is RCU * protected for this access. See css_release_work_fn() for details. */ cgrp = rcu_dereference(*(void __rcu __force **)&kn->priv); if (cgrp) css = cgroup_css(cgrp, ss);
if (!css || !css_tryget_online(css)) css = ERR_PTR(-ENOENT);
rcu_read_unlock(); return css;}
/** * css_from_id - lookup css by id * @id: the cgroup id * @ss: cgroup subsys to be looked into * * Returns the css if there's valid one with @id, otherwise returns NULL. * Should be called under rcu_read_lock(). */struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss){ WARN_ON_ONCE(!rcu_read_lock_held()); return idr_find(&ss->css_idr, id);}
/** * cgroup_get_from_path - lookup and get a cgroup from its default hierarchy path * @path: path on the default hierarchy * * Find the cgroup at @path on the default hierarchy, increment its * reference count and return it. Returns pointer to the found cgroup on * success, ERR_PTR(-ENOENT) if @path doesn't exist or if the cgroup has already * been released and ERR_PTR(-ENOTDIR) if @path points to a non-directory. */struct cgroup *cgroup_get_from_path(const char *path){ struct kernfs_node *kn; struct cgroup *cgrp = ERR_PTR(-ENOENT); struct cgroup *root_cgrp;
root_cgrp = current_cgns_cgroup_dfl(); kn = kernfs_walk_and_get(root_cgrp->kn, path); if (!kn) goto out;
if (kernfs_type(kn) != KERNFS_DIR) { cgrp = ERR_PTR(-ENOTDIR); goto out_kernfs; }
rcu_read_lock();
cgrp = rcu_dereference(*(void __rcu __force **)&kn->priv); if (!cgrp || !cgroup_tryget(cgrp)) cgrp = ERR_PTR(-ENOENT);
rcu_read_unlock();
out_kernfs: kernfs_put(kn);out: return cgrp;}EXPORT_SYMBOL_GPL(cgroup_get_from_path);
/** * cgroup_v1v2_get_from_fd - get a cgroup pointer from a fd * @fd: fd obtained by open(cgroup_dir) * * Find the cgroup from a fd which should be obtained * by opening a cgroup directory. Returns a pointer to the * cgroup on success. ERR_PTR is returned if the cgroup * cannot be found. */struct cgroup *cgroup_v1v2_get_from_fd(int fd){ CLASS(fd_raw, f)(fd); if (fd_empty(f)) return ERR_PTR(-EBADF);
return cgroup_v1v2_get_from_file(fd_file(f));}
/** * cgroup_get_from_fd - same as cgroup_v1v2_get_from_fd, but only supports * cgroup2. * @fd: fd obtained by open(cgroup2_dir) */struct cgroup *cgroup_get_from_fd(int fd){ struct cgroup *cgrp = cgroup_v1v2_get_from_fd(fd);
if (IS_ERR(cgrp)) return ERR_CAST(cgrp);
if (!cgroup_on_dfl(cgrp)) { cgroup_put(cgrp); return ERR_PTR(-EBADF); } return cgrp;}EXPORT_SYMBOL_GPL(cgroup_get_from_fd);
static u64 power_of_ten(int power){ u64 v = 1; while (power--) v *= 10; return v;}
/** * cgroup_parse_float - parse a floating number * @input: input string * @dec_shift: number of decimal digits to shift * @v: output * * Parse a decimal floating point number in @input and store the result in * @v with decimal point right shifted @dec_shift times. For example, if * @input is "12.3456" and @dec_shift is 3, *@v will be set to 12345. * Returns 0 on success, -errno otherwise. * * There's nothing cgroup specific about this function except that it's * currently the only user. */int cgroup_parse_float(const char *input, unsigned dec_shift, s64 *v){ s64 whole, frac = 0; int fstart = 0, fend = 0, flen;
if (!sscanf(input, "%lld.%n%lld%n", &whole, &fstart, &frac, &fend)) return -EINVAL; if (frac < 0) return -EINVAL;
flen = fend > fstart ? fend - fstart : 0; if (flen < dec_shift) frac *= power_of_ten(dec_shift - flen); else frac = DIV_ROUND_CLOSEST_ULL(frac, power_of_ten(flen - dec_shift));
*v = whole * power_of_ten(dec_shift) + frac; return 0;}
/* * sock->sk_cgrp_data handling. For more info, see sock_cgroup_data * definition in cgroup-defs.h. */#ifdef CONFIG_SOCK_CGROUP_DATA
void cgroup_sk_alloc(struct sock_cgroup_data *skcd){ struct cgroup *cgroup;
rcu_read_lock(); /* Don't associate the sock with unrelated interrupted task's cgroup. */ if (in_interrupt()) { cgroup = &cgrp_dfl_root.cgrp; cgroup_get(cgroup); goto out; }
while (true) { struct css_set *cset;
cset = task_css_set(current); if (likely(cgroup_tryget(cset->dfl_cgrp))) { cgroup = cset->dfl_cgrp; break; } cpu_relax(); }out: skcd->cgroup = cgroup; cgroup_bpf_get(cgroup); rcu_read_unlock();}
void cgroup_sk_clone(struct sock_cgroup_data *skcd){ struct cgroup *cgrp = sock_cgroup_ptr(skcd);
/* * We might be cloning a socket which is left in an empty * cgroup and the cgroup might have already been rmdir'd. * Don't use cgroup_get_live(). */ cgroup_get(cgrp); cgroup_bpf_get(cgrp);}
void cgroup_sk_free(struct sock_cgroup_data *skcd){ struct cgroup *cgrp = sock_cgroup_ptr(skcd);
cgroup_bpf_put(cgrp); cgroup_put(cgrp);}
#endif /* CONFIG_SOCK_CGROUP_DATA */
#ifdef CONFIG_SYSFSstatic ssize_t show_delegatable_files(struct cftype *files, char *buf, ssize_t size, const char *prefix){ struct cftype *cft; ssize_t ret = 0;
for (cft = files; cft && cft->name[0] != '\0'; cft++) { if (!(cft->flags & CFTYPE_NS_DELEGATABLE)) continue;
if (prefix) ret += snprintf(buf + ret, size - ret, "%s.", prefix);
ret += snprintf(buf + ret, size - ret, "%s\n", cft->name);
if (WARN_ON(ret >= size)) break; }
return ret;}
static ssize_t delegate_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf){ struct cgroup_subsys *ss; int ssid; ssize_t ret = 0;
ret = show_delegatable_files(cgroup_base_files, buf + ret, PAGE_SIZE - ret, NULL); if (cgroup_psi_enabled()) ret += show_delegatable_files(cgroup_psi_files, buf + ret, PAGE_SIZE - ret, NULL);
for_each_subsys(ss, ssid) ret += show_delegatable_files(ss->dfl_cftypes, buf + ret, PAGE_SIZE - ret, cgroup_subsys_name[ssid]);
return ret;}static struct kobj_attribute cgroup_delegate_attr = __ATTR_RO(delegate);
static ssize_t features_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf){ return snprintf(buf, PAGE_SIZE, "nsdelegate\n" "favordynmods\n" "memory_localevents\n" "memory_recursiveprot\n" "memory_hugetlb_accounting\n" "pids_localevents\n");}static struct kobj_attribute cgroup_features_attr = __ATTR_RO(features);
static struct attribute *cgroup_sysfs_attrs[] = { &cgroup_delegate_attr.attr, &cgroup_features_attr.attr, NULL,};
static const struct attribute_group cgroup_sysfs_attr_group = { .attrs = cgroup_sysfs_attrs, .name = "cgroup",};
static int __init cgroup_sysfs_init(void){ return sysfs_create_group(kernel_kobj, &cgroup_sysfs_attr_group);}subsys_initcall(cgroup_sysfs_init);
#endif /* CONFIG_SYSFS */