123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773774775776777778779780781782783784785786787788789790791792793794795796797798799800801802803804805806807808809810811812813814815816817818819820821822823824825826827828829830831832833834835836837838839840841842843844845846847848849850851852853854855856857858859860861862863864865866867868869870871872873874875876877878879880881882883884885886887888889890891892893894895896897898899900901902903904905906907908909910911912913914915916917918919920921922923924925926927928929930931932933934935936937938939940941942943944945946947948949950951952953954955956957958959960961962963964965966967968969970971972973974975976977978979980981982983984985986987988989990991992993994995996997998999100010011002100310041005100610071008100910101011101210131014101510161017101810191020102110221023102410251026102710281029103010311032103310341035103610371038103910401041104210431044104510461047104810491050105110521053105410551056105710581059106010611062106310641065106610671068106910701071107210731074107510761077107810791080108110821083108410851086108710881089109010911092109310941095109610971098109911001101110211031104110511061107110811091110111111121113111411151116111711181119112011211122112311241125112611271128112911301131113211331134113511361137113811391140114111421143114411451146114711481149115011511152115311541155115611571158115911601161116211631164116511661167116811691170117111721173117411751176117711781179118011811182118311841185118611871188118911901191119211931194119511961197119811991200120112021203120412051206120712081209121012111212121312141215121612171218121912201221122212231224122512261227122812291230123112321233123412351236123712381239124012411242124312441245124612471248124912501251125212531254125512561257125812591260126112621263126412651266126712681269127012711272127312741275127612771278127912801281128212831284128512861287128812891290129112921293129412951296129712981299130013011302130313041305130613071308130913101311131213131314131513161317131813191320132113221323132413251326132713281329133013311332133313341335133613371338133913401341134213431344134513461347134813491350135113521353135413551356135713581359136013611362136313641365136613671368136913701371137213731374137513761377137813791380138113821383138413851386138713881389139013911392139313941395139613971398139914001401140214031404140514061407140814091410141114121413141414151416141714181419142014211422142314241425142614271428142914301431143214331434143514361437143814391440144114421443144414451446144714481449145014511452145314541455145614571458145914601461146214631464146514661467146814691470147114721473147414751476147714781479148014811482148314841485148614871488148914901491149214931494149514961497149814991500150115021503150415051506150715081509151015111512151315141515151615171518151915201521152215231524152515261527152815291530153115321533153415351536153715381539154015411542154315441545154615471548154915501551155215531554155515561557155815591560156115621563156415651566156715681569157015711572157315741575157615771578157915801581158215831584158515861587158815891590159115921593159415951596159715981599160016011602160316041605160616071608160916101611161216131614161516161617161816191620162116221623162416251626162716281629163016311632163316341635163616371638163916401641164216431644164516461647164816491650165116521653165416551656165716581659166016611662166316641665166616671668166916701671167216731674167516761677167816791680168116821683168416851686168716881689169016911692169316941695169616971698169917001701170217031704170517061707170817091710171117121713171417151716171717181719172017211722172317241725172617271728172917301731173217331734173517361737173817391740174117421743174417451746174717481749175017511752175317541755175617571758175917601761176217631764176517661767176817691770177117721773177417751776177717781779178017811782178317841785178617871788178917901791179217931794179517961797179817991800180118021803180418051806180718081809181018111812181318141815181618171818181918201821182218231824182518261827182818291830183118321833183418351836183718381839184018411842184318441845184618471848184918501851185218531854185518561857185818591860186118621863186418651866186718681869187018711872187318741875187618771878187918801881188218831884188518861887188818891890189118921893189418951896189718981899190019011902190319041905190619071908190919101911191219131914191519161917191819191920192119221923192419251926192719281929193019311932193319341935193619371938193919401941194219431944194519461947194819491950195119521953195419551956195719581959196019611962196319641965196619671968196919701971197219731974197519761977197819791980198119821983198419851986198719881989199019911992199319941995199619971998199920002001200220032004200520062007200820092010201120122013201420152016201720182019202020212022202320242025202620272028202920302031203220332034203520362037203820392040204120422043204420452046204720482049205020512052205320542055205620572058205920602061206220632064206520662067206820692070207120722073207420752076207720782079208020812082208320842085208620872088208920902091209220932094209520962097209820992100210121022103210421052106210721082109211021112112211321142115211621172118211921202121212221232124212521262127212821292130213121322133213421352136213721382139214021412142214321442145214621472148214921502151215221532154215521562157215821592160216121622163216421652166216721682169217021712172217321742175217621772178217921802181218221832184218521862187218821892190219121922193219421952196219721982199220022012202220322042205220622072208220922102211221222132214221522162217221822192220222122222223222422252226222722282229223022312232223322342235223622372238223922402241224222432244224522462247224822492250225122522253225422552256225722582259226022612262226322642265226622672268226922702271227222732274227522762277227822792280228122822283228422852286228722882289229022912292229322942295229622972298229923002301230223032304230523062307230823092310231123122313231423152316231723182319232023212322232323242325232623272328232923302331233223332334233523362337233823392340234123422343234423452346234723482349235023512352235323542355235623572358235923602361236223632364236523662367236823692370237123722373237423752376237723782379238023812382238323842385238623872388238923902391239223932394239523962397239823992400240124022403240424052406240724082409241024112412241324142415241624172418241924202421242224232424242524262427242824292430243124322433243424352436243724382439244024412442244324442445244624472448244924502451245224532454245524562457245824592460246124622463246424652466246724682469247024712472247324742475247624772478247924802481248224832484248524862487248824892490249124922493249424952496249724982499250025012502250325042505250625072508250925102511251225132514251525162517251825192520252125222523252425252526252725282529253025312532253325342535253625372538253925402541254225432544254525462547254825492550255125522553255425552556255725582559256025612562256325642565256625672568256925702571257225732574257525762577257825792580258125822583258425852586258725882589259025912592259325942595259625972598259926002601260226032604260526062607260826092610261126122613261426152616261726182619262026212622262326242625262626272628262926302631263226332634263526362637263826392640264126422643264426452646264726482649265026512652265326542655265626572658265926602661266226632664266526662667266826692670267126722673267426752676267726782679268026812682268326842685268626872688268926902691269226932694269526962697269826992700270127022703270427052706270727082709271027112712271327142715271627172718271927202721272227232724272527262727272827292730273127322733273427352736273727382739274027412742274327442745274627472748274927502751275227532754275527562757275827592760276127622763276427652766276727682769277027712772277327742775277627772778277927802781278227832784278527862787278827892790279127922793279427952796279727982799280028012802280328042805280628072808280928102811281228132814281528162817281828192820282128222823282428252826282728282829283028312832283328342835283628372838283928402841284228432844284528462847284828492850285128522853285428552856285728582859286028612862286328642865286628672868286928702871287228732874287528762877287828792880288128822883288428852886288728882889289028912892289328942895289628972898289929002901290229032904290529062907290829092910291129122913291429152916291729182919292029212922292329242925292629272928292929302931293229332934293529362937293829392940294129422943294429452946294729482949295029512952295329542955295629572958295929602961296229632964296529662967296829692970297129722973297429752976297729782979298029812982298329842985298629872988298929902991299229932994299529962997299829993000300130023003300430053006300730083009301030113012301330143015301630173018301930203021302230233024302530263027302830293030303130323033303430353036303730383039304030413042304330443045304630473048304930503051305230533054305530563057305830593060306130623063306430653066306730683069307030713072307330743075307630773078307930803081308230833084308530863087308830893090309130923093309430953096309730983099310031013102310331043105310631073108310931103111311231133114311531163117311831193120312131223123312431253126312731283129313031313132313331343135313631373138313931403141314231433144314531463147314831493150315131523153315431553156315731583159316031613162316331643165316631673168316931703171317231733174317531763177317831793180318131823183318431853186318731883189319031913192319331943195319631973198319932003201320232033204320532063207320832093210321132123213321432153216321732183219322032213222322332243225322632273228322932303231323232333234323532363237323832393240324132423243324432453246324732483249325032513252325332543255325632573258325932603261326232633264326532663267326832693270327132723273327432753276327732783279328032813282328332843285328632873288328932903291329232933294329532963297329832993300330133023303330433053306330733083309331033113312331333143315331633173318331933203321332233233324332533263327332833293330333133323333333433353336333733383339334033413342334333443345334633473348334933503351335233533354335533563357335833593360336133623363336433653366336733683369337033713372337333743375337633773378337933803381338233833384338533863387338833893390339133923393339433953396339733983399340034013402340334043405340634073408340934103411341234133414341534163417341834193420342134223423342434253426342734283429343034313432343334343435343634373438343934403441344234433444344534463447344834493450345134523453345434553456345734583459346034613462346334643465346634673468346934703471347234733474347534763477347834793480348134823483348434853486348734883489349034913492349334943495349634973498349935003501350235033504350535063507350835093510351135123513351435153516351735183519352035213522352335243525352635273528352935303531353235333534353535363537353835393540354135423543354435453546354735483549355035513552355335543555355635573558355935603561356235633564356535663567356835693570357135723573357435753576357735783579358035813582358335843585358635873588358935903591359235933594359535963597359835993600360136023603360436053606360736083609361036113612361336143615361636173618361936203621362236233624362536263627362836293630363136323633363436353636363736383639364036413642364336443645364636473648364936503651365236533654365536563657365836593660366136623663366436653666366736683669367036713672367336743675367636773678367936803681368236833684368536863687368836893690369136923693369436953696369736983699370037013702370337043705370637073708370937103711371237133714371537163717371837193720372137223723372437253726372737283729373037313732373337343735373637373738373937403741374237433744374537463747374837493750375137523753375437553756375737583759376037613762376337643765376637673768376937703771377237733774377537763777377837793780378137823783378437853786378737883789379037913792379337943795379637973798379938003801380238033804380538063807380838093810381138123813381438153816381738183819382038213822382338243825382638273828382938303831383238333834383538363837383838393840384138423843384438453846384738483849385038513852385338543855385638573858385938603861386238633864386538663867386838693870387138723873387438753876387738783879388038813882388338843885388638873888388938903891389238933894389538963897389838993900390139023903390439053906390739083909391039113912391339143915391639173918391939203921392239233924392539263927392839293930393139323933393439353936393739383939394039413942394339443945394639473948394939503951395239533954395539563957395839593960396139623963396439653966396739683969397039713972397339743975397639773978397939803981398239833984398539863987398839893990399139923993399439953996399739983999400040014002400340044005400640074008400940104011401240134014401540164017401840194020402140224023402440254026402740284029403040314032403340344035403640374038403940404041404240434044404540464047404840494050405140524053405440554056405740584059406040614062406340644065406640674068406940704071407240734074407540764077407840794080408140824083408440854086408740884089409040914092409340944095409640974098409941004101410241034104410541064107410841094110411141124113411441154116411741184119412041214122412341244125412641274128412941304131413241334134413541364137413841394140414141424143414441454146414741484149415041514152415341544155415641574158415941604161416241634164416541664167416841694170417141724173417441754176417741784179418041814182418341844185418641874188418941904191419241934194419541964197419841994200420142024203420442054206420742084209421042114212421342144215421642174218421942204221422242234224422542264227422842294230423142324233423442354236423742384239424042414242424342444245424642474248424942504251425242534254425542564257425842594260426142624263426442654266426742684269427042714272427342744275427642774278427942804281428242834284428542864287428842894290429142924293429442954296429742984299430043014302430343044305430643074308430943104311431243134314431543164317431843194320432143224323432443254326432743284329433043314332433343344335433643374338433943404341434243434344434543464347434843494350435143524353435443554356435743584359436043614362436343644365436643674368436943704371437243734374437543764377437843794380438143824383438443854386438743884389439043914392439343944395439643974398439944004401440244034404440544064407440844094410441144124413441444154416441744184419442044214422442344244425442644274428442944304431443244334434443544364437443844394440444144424443444444454446444744484449445044514452445344544455445644574458445944604461446244634464446544664467446844694470447144724473447444754476447744784479448044814482448344844485448644874488448944904491449244934494449544964497449844994500450145024503450445054506450745084509451045114512451345144515451645174518451945204521452245234524452545264527452845294530453145324533453445354536453745384539454045414542454345444545454645474548454945504551455245534554455545564557455845594560456145624563456445654566456745684569457045714572457345744575457645774578457945804581458245834584458545864587458845894590459145924593459445954596459745984599460046014602460346044605460646074608460946104611461246134614461546164617461846194620462146224623462446254626462746284629463046314632463346344635463646374638463946404641464246434644464546464647464846494650465146524653465446554656465746584659466046614662466346644665466646674668466946704671467246734674467546764677467846794680468146824683468446854686468746884689469046914692469346944695469646974698469947004701470247034704470547064707470847094710471147124713471447154716471747184719472047214722472347244725472647274728472947304731473247334734473547364737473847394740474147424743474447454746474747484749475047514752475347544755475647574758475947604761476247634764476547664767476847694770477147724773477447754776477747784779478047814782478347844785478647874788478947904791479247934794479547964797479847994800480148024803480448054806480748084809481048114812481348144815481648174818481948204821482248234824482548264827482848294830483148324833483448354836483748384839484048414842484348444845484648474848484948504851485248534854485548564857485848594860486148624863486448654866486748684869487048714872487348744875487648774878487948804881488248834884488548864887488848894890489148924893489448954896489748984899490049014902490349044905490649074908490949104911491249134914491549164917491849194920492149224923492449254926492749284929493049314932493349344935493649374938493949404941494249434944494549464947494849494950495149524953495449554956495749584959496049614962496349644965496649674968496949704971497249734974497549764977497849794980498149824983498449854986498749884989499049914992499349944995499649974998499950005001500250035004500550065007500850095010501150125013501450155016501750185019502050215022502350245025502650275028502950305031503250335034503550365037503850395040504150425043504450455046504750485049505050515052505350545055505650575058505950605061506250635064506550665067506850695070507150725073507450755076507750785079508050815082508350845085508650875088508950905091509250935094509550965097509850995100510151025103510451055106510751085109511051115112511351145115511651175118511951205121512251235124512551265127512851295130513151325133513451355136513751385139514051415142514351445145514651475148514951505151515251535154515551565157515851595160516151625163516451655166516751685169517051715172517351745175517651775178517951805181518251835184518551865187518851895190519151925193519451955196519751985199520052015202520352045205520652075208520952105211521252135214521552165217521852195220522152225223522452255226522752285229523052315232523352345235523652375238523952405241524252435244524552465247524852495250525152525253525452555256525752585259526052615262526352645265526652675268526952705271527252735274527552765277527852795280528152825283528452855286528752885289529052915292529352945295529652975298529953005301530253035304530553065307530853095310531153125313531453155316531753185319532053215322532353245325532653275328532953305331533253335334533553365337533853395340534153425343534453455346534753485349535053515352535353545355535653575358535953605361536253635364536553665367536853695370537153725373537453755376537753785379538053815382538353845385538653875388538953905391539253935394539553965397539853995400540154025403540454055406540754085409541054115412541354145415541654175418541954205421542254235424542554265427542854295430543154325433543454355436543754385439544054415442544354445445544654475448544954505451545254535454545554565457545854595460546154625463546454655466546754685469547054715472547354745475547654775478547954805481548254835484548554865487548854895490549154925493549454955496549754985499550055015502550355045505550655075508550955105511551255135514551555165517551855195520552155225523552455255526552755285529553055315532553355345535553655375538553955405541554255435544554555465547554855495550555155525553555455555556555755585559556055615562556355645565556655675568556955705571557255735574557555765577557855795580558155825583558455855586558755885589559055915592559355945595559655975598559956005601560256035604560556065607560856095610561156125613561456155616561756185619562056215622562356245625562656275628562956305631563256335634563556365637563856395640564156425643564456455646564756485649565056515652565356545655565656575658565956605661566256635664566556665667566856695670567156725673567456755676567756785679568056815682568356845685568656875688568956905691569256935694569556965697569856995700570157025703570457055706570757085709571057115712571357145715571657175718571957205721572257235724572557265727572857295730573157325733573457355736573757385739574057415742574357445745574657475748574957505751575257535754575557565757575857595760576157625763576457655766576757685769577057715772577357745775577657775778577957805781578257835784578557865787578857895790579157925793579457955796579757985799580058015802580358045805580658075808580958105811581258135814581558165817581858195820582158225823582458255826582758285829583058315832583358345835583658375838583958405841584258435844584558465847584858495850585158525853585458555856585758585859586058615862586358645865586658675868586958705871587258735874587558765877587858795880588158825883588458855886588758885889589058915892589358945895589658975898589959005901590259035904590559065907590859095910591159125913591459155916591759185919592059215922592359245925592659275928592959305931593259335934593559365937593859395940594159425943594459455946594759485949595059515952595359545955595659575958595959605961596259635964596559665967596859695970597159725973597459755976597759785979598059815982598359845985598659875988598959905991599259935994599559965997599859996000600160026003600460056006600760086009601060116012601360146015601660176018601960206021602260236024602560266027602860296030603160326033603460356036603760386039604060416042604360446045604660476048604960506051605260536054605560566057605860596060606160626063606460656066606760686069607060716072607360746075607660776078607960806081608260836084608560866087608860896090609160926093609460956096609760986099610061016102610361046105610661076108610961106111611261136114611561166117611861196120612161226123612461256126612761286129613061316132613361346135613661376138613961406141614261436144614561466147614861496150615161526153615461556156615761586159616061616162616361646165616661676168616961706171617261736174617561766177617861796180618161826183618461856186618761886189619061916192619361946195619661976198619962006201620262036204620562066207620862096210621162126213621462156216621762186219622062216222622362246225622662276228622962306231623262336234623562366237623862396240624162426243624462456246624762486249625062516252625362546255625662576258625962606261626262636264626562666267626862696270627162726273627462756276627762786279628062816282628362846285628662876288628962906291629262936294629562966297629862996300630163026303630463056306630763086309631063116312631363146315631663176318631963206321632263236324632563266327632863296330633163326333633463356336633763386339634063416342634363446345634663476348634963506351635263536354635563566357635863596360636163626363636463656366636763686369637063716372637363746375637663776378637963806381638263836384638563866387638863896390639163926393639463956396639763986399640064016402640364046405640664076408640964106411641264136414641564166417641864196420642164226423642464256426642764286429643064316432643364346435643664376438643964406441644264436444644564466447644864496450645164526453645464556456645764586459646064616462646364646465646664676468646964706471647264736474647564766477647864796480648164826483648464856486648764886489649064916492649364946495649664976498649965006501650265036504650565066507650865096510651165126513651465156516651765186519652065216522652365246525652665276528652965306531653265336534653565366537653865396540654165426543654465456546654765486549655065516552655365546555655665576558655965606561656265636564656565666567656865696570657165726573657465756576657765786579658065816582658365846585658665876588658965906591659265936594659565966597659865996600660166026603660466056606660766086609661066116612661366146615661666176618661966206621662266236624662566266627662866296630663166326633663466356636663766386639664066416642664366446645664666476648664966506651665266536654 |
- #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
- #include <linux/cgroup.h>
- #include <linux/cred.h>
- #include <linux/ctype.h>
- #include <linux/errno.h>
- #include <linux/init_task.h>
- #include <linux/kernel.h>
- #include <linux/list.h>
- #include <linux/magic.h>
- #include <linux/mm.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/slab.h>
- #include <linux/spinlock.h>
- #include <linux/percpu-rwsem.h>
- #include <linux/string.h>
- #include <linux/sort.h>
- #include <linux/kmod.h>
- #include <linux/delayacct.h>
- #include <linux/cgroupstats.h>
- #include <linux/hashtable.h>
- #include <linux/pid_namespace.h>
- #include <linux/idr.h>
- #include <linux/vmalloc.h>
- #include <linux/kthread.h>
- #include <linux/delay.h>
- #include <linux/atomic.h>
- #include <linux/cpuset.h>
- #include <linux/proc_ns.h>
- #include <linux/nsproxy.h>
- #include <linux/file.h>
- #include <net/sock.h>
- #define CREATE_TRACE_POINTS
- #include <trace/events/cgroup.h>
- #define CGROUP_PIDLIST_DESTROY_DELAY HZ
- #define CGROUP_FILE_NAME_MAX (MAX_CGROUP_TYPE_NAMELEN + \
- MAX_CFTYPE_NAME + 2)
- #ifdef CONFIG_PROVE_RCU
- DEFINE_MUTEX(cgroup_mutex);
- DEFINE_SPINLOCK(css_set_lock);
- EXPORT_SYMBOL_GPL(cgroup_mutex);
- EXPORT_SYMBOL_GPL(css_set_lock);
- #else
- static DEFINE_MUTEX(cgroup_mutex);
- static DEFINE_SPINLOCK(css_set_lock);
- #endif
- static DEFINE_SPINLOCK(cgroup_idr_lock);
- static DEFINE_SPINLOCK(cgroup_file_kn_lock);
- static DEFINE_SPINLOCK(release_agent_path_lock);
- struct percpu_rw_semaphore 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");
- static struct workqueue_struct *cgroup_destroy_wq;
- static struct workqueue_struct *cgroup_pidlist_destroy_wq;
- #define SUBSYS(_x) [_x ## _cgrp_id] = &_x ## _cgrp_subsys,
- static struct cgroup_subsys *cgroup_subsys[] = {
- #include <linux/cgroup_subsys.h>
- };
- #undef SUBSYS
- #define SUBSYS(_x) [_x ## _cgrp_id] = #_x,
- static const char *cgroup_subsys_name[] = {
- #include <linux/cgroup_subsys.h>
- };
- #undef SUBSYS
- #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
- struct cgroup_root cgrp_dfl_root;
- EXPORT_SYMBOL_GPL(cgrp_dfl_root);
- static bool cgrp_dfl_visible;
- static u16 cgroup_no_v1_mask;
- static u16 cgrp_dfl_inhibit_ss_mask;
- static unsigned long cgrp_dfl_implicit_ss_mask;
- static LIST_HEAD(cgroup_roots);
- static int cgroup_root_count;
- static DEFINE_IDR(cgroup_hierarchy_idr);
- static u64 css_serial_nr_next = 1;
- static u16 have_fork_callback __read_mostly;
- static u16 have_exit_callback __read_mostly;
- static u16 have_free_callback __read_mostly;
- struct cgroup_namespace init_cgroup_ns = {
- .count = { .counter = 2, },
- .user_ns = &init_user_ns,
- .ns.ops = &cgroupns_operations,
- .ns.inum = PROC_CGROUP_INIT_INO,
- .root_cset = &init_css_set,
- };
- static u16 have_canfork_callback __read_mostly;
- static struct file_system_type cgroup2_fs_type;
- static struct cftype cgroup_dfl_base_files[];
- static struct cftype cgroup_legacy_base_files[];
- static int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask);
- static void cgroup_lock_and_drain_offline(struct cgroup *cgrp);
- static int cgroup_apply_control(struct cgroup *cgrp);
- static void cgroup_finalize_control(struct cgroup *cgrp, int ret);
- static void css_task_iter_advance(struct css_task_iter *it);
- static int cgroup_destroy_locked(struct cgroup *cgrp);
- static struct cgroup_subsys_state *css_create(struct cgroup *cgrp,
- struct cgroup_subsys *ss);
- static void css_release(struct percpu_ref *ref);
- static void kill_css(struct cgroup_subsys_state *css);
- static int cgroup_addrm_files(struct cgroup_subsys_state *css,
- struct cgroup *cgrp, struct cftype cfts[],
- bool is_add);
- static bool cgroup_ssid_enabled(int ssid)
- {
- if (CGROUP_SUBSYS_COUNT == 0)
- return false;
- return static_key_enabled(cgroup_subsys_enabled_key[ssid]);
- }
- static bool cgroup_ssid_no_v1(int ssid)
- {
- return cgroup_no_v1_mask & (1 << ssid);
- }
- static bool cgroup_on_dfl(const struct cgroup *cgrp)
- {
- return cgrp->root == &cgrp_dfl_root;
- }
- 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 struct cgroup *cgroup_parent(struct cgroup *cgrp)
- {
- struct cgroup_subsys_state *parent_css = cgrp->self.parent;
- if (parent_css)
- return container_of(parent_css, struct cgroup, self);
- return NULL;
- }
- static u16 cgroup_control(struct cgroup *cgrp)
- {
- struct cgroup *parent = cgroup_parent(cgrp);
- u16 root_ss_mask = cgrp->root->subsys_mask;
- if (parent)
- return parent->subtree_control;
- if (cgroup_on_dfl(cgrp))
- root_ss_mask &= ~(cgrp_dfl_inhibit_ss_mask |
- cgrp_dfl_implicit_ss_mask);
- return root_ss_mask;
- }
- static u16 cgroup_ss_mask(struct cgroup *cgrp)
- {
- struct cgroup *parent = cgroup_parent(cgrp);
- if (parent)
- return parent->subtree_ss_mask;
- return cgrp->root->subsys_mask;
- }
- static struct cgroup_subsys_state *cgroup_css(struct cgroup *cgrp,
- struct cgroup_subsys *ss)
- {
- if (ss)
- return rcu_dereference_check(cgrp->subsys[ss->id],
- lockdep_is_held(&cgroup_mutex));
- else
- return &cgrp->self;
- }
- static struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgrp,
- struct cgroup_subsys *ss)
- {
- lockdep_assert_held(&cgroup_mutex);
- if (!ss)
- return &cgrp->self;
-
- while (!(cgroup_ss_mask(cgrp) & (1 << ss->id))) {
- cgrp = cgroup_parent(cgrp);
- if (!cgrp)
- return NULL;
- }
- return cgroup_css(cgrp, ss);
- }
- struct cgroup_subsys_state *cgroup_get_e_css(struct cgroup *cgrp,
- struct cgroup_subsys *ss)
- {
- struct cgroup_subsys_state *css;
- 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;
- }
- static inline bool cgroup_is_dead(const struct cgroup *cgrp)
- {
- return !(cgrp->self.flags & CSS_ONLINE);
- }
- static void cgroup_get(struct cgroup *cgrp)
- {
- WARN_ON_ONCE(cgroup_is_dead(cgrp));
- css_get(&cgrp->self);
- }
- static bool cgroup_tryget(struct cgroup *cgrp)
- {
- return css_tryget(&cgrp->self);
- }
- struct cgroup_subsys_state *of_css(struct kernfs_open_file *of)
- {
- struct cgroup *cgrp = of->kn->parent->priv;
- struct cftype *cft = of_cft(of);
-
- if (cft->ss)
- return rcu_dereference_raw(cgrp->subsys[cft->ss->id]);
- else
- return &cgrp->self;
- }
- EXPORT_SYMBOL_GPL(of_css);
- static int notify_on_release(const struct cgroup *cgrp)
- {
- return test_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
- }
- #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
- #define for_each_e_css(css, ssid, cgrp) \
- for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT; (ssid)++) \
- if (!((css) = cgroup_e_css(cgrp, cgroup_subsys[(ssid)]))) \
- ; \
- else
- /**
- * for_each_subsys - iterate all enabled cgroup subsystems
- * @ss: the iteration cursor
- * @ssid: the index of @ss, CGROUP_SUBSYS_COUNT after reaching the end
- */
- #define for_each_subsys(ss, ssid) \
- for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT && \
- (((ss) = cgroup_subsys[ssid]) || true); (ssid)++)
- /**
- * 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_SUBSYS_COUNT) { /* to avoid spurious gcc warning */ \
- (ssid) = 0; \
- break; \
- } \
- for_each_set_bit(ssid, &__ss_mask, CGROUP_SUBSYS_COUNT) { \
- (ss) = cgroup_subsys[ssid]; \
- {
- #define while_each_subsys_mask() \
- } \
- } \
- } while (false)
- /* iterate across the hierarchies */
- #define for_each_root(root) \
- list_for_each_entry((root), &cgroup_roots, root_list)
- /* iterate over child cgrps, lock should be held throughout iteration */
- #define cgroup_for_each_live_child(child, cgrp) \
- list_for_each_entry((child), &(cgrp)->self.children, self.sibling) \
- if (({ lockdep_assert_held(&cgroup_mutex); \
- cgroup_is_dead(child); })) \
- ; \
- else
- #define cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) \
- css_for_each_descendant_pre((d_css), cgroup_css((cgrp), NULL)) \
- if (({ lockdep_assert_held(&cgroup_mutex); \
- (dsct) = (d_css)->cgroup; \
- cgroup_is_dead(dsct); })) \
- ; \
- else
- #define cgroup_for_each_live_descendant_post(dsct, d_css, cgrp) \
- css_for_each_descendant_post((d_css), cgroup_css((cgrp), NULL)) \
- if (({ lockdep_assert_held(&cgroup_mutex); \
- (dsct) = (d_css)->cgroup; \
- cgroup_is_dead(dsct); })) \
- ; \
- else
- static void cgroup_release_agent(struct work_struct *work);
- static void check_for_release(struct cgroup *cgrp);
- struct cgrp_cset_link {
-
- struct cgroup *cgrp;
- struct css_set *cset;
-
- struct list_head cset_link;
-
- struct list_head cgrp_link;
- };
- struct css_set init_css_set = {
- .refcount = ATOMIC_INIT(1),
- .cgrp_links = LIST_HEAD_INIT(init_css_set.cgrp_links),
- .tasks = LIST_HEAD_INIT(init_css_set.tasks),
- .mg_tasks = LIST_HEAD_INIT(init_css_set.mg_tasks),
- .mg_preload_node = LIST_HEAD_INIT(init_css_set.mg_preload_node),
- .mg_node = LIST_HEAD_INIT(init_css_set.mg_node),
- .task_iters = LIST_HEAD_INIT(init_css_set.task_iters),
- };
- static int css_set_count = 1;
- 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);
- }
- static void cgroup_update_populated(struct cgroup *cgrp, bool populated)
- {
- lockdep_assert_held(&css_set_lock);
- do {
- bool trigger;
- if (populated)
- trigger = !cgrp->populated_cnt++;
- else
- trigger = !--cgrp->populated_cnt;
- if (!trigger)
- break;
- check_for_release(cgrp);
- cgroup_file_notify(&cgrp->events_file);
- cgrp = cgroup_parent(cgrp);
- } while (cgrp);
- }
- static void css_set_update_populated(struct css_set *cset, bool populated)
- {
- struct cgrp_cset_link *link;
- lockdep_assert_held(&css_set_lock);
- list_for_each_entry(link, &cset->cgrp_links, cgrp_link)
- cgroup_update_populated(link->cgrp, populated);
- }
- 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) {
- struct css_task_iter *it, *pos;
- WARN_ON_ONCE(list_empty(&task->cg_list));
-
- list_for_each_entry_safe(it, pos, &from_cset->task_iters,
- iters_node)
- if (it->task_pos == &task->cg_list)
- css_task_iter_advance(it);
- 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) {
-
- WARN_ON_ONCE(task->flags & PF_EXITING);
- rcu_assign_pointer(task->cgroups, to_cset);
- list_add_tail(&task->cg_list, use_mg_tasks ? &to_cset->mg_tasks :
- &to_cset->tasks);
- }
- }
- #define CSS_SET_HASH_BITS 7
- static 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;
- }
- static 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 (!atomic_dec_and_test(&cset->refcount))
- return;
-
- 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);
- }
- kfree_rcu(cset, rcu_head);
- }
- static void put_css_set(struct css_set *cset)
- {
- unsigned long flags;
-
- if (atomic_add_unless(&cset->refcount, -1, 1))
- return;
- spin_lock_irqsave(&css_set_lock, flags);
- put_css_set_locked(cset);
- spin_unlock_irqrestore(&css_set_lock, flags);
- }
- static inline void get_css_set(struct css_set *cset)
- {
- atomic_inc(&cset->refcount);
- }
- static bool compare_css_sets(struct css_set *cset,
- struct css_set *old_cset,
- struct cgroup *new_cgrp,
- struct cgroup_subsys_state *template[])
- {
- struct list_head *l1, *l2;
-
- if (memcmp(template, cset->subsys, sizeof(cset->subsys)))
- return false;
-
- 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;
-
- if (l1 == &cset->cgrp_links) {
- BUG_ON(l2 != &old_cset->cgrp_links);
- break;
- } else {
- BUG_ON(l2 == &old_cset->cgrp_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;
-
- BUG_ON(cgrp1->root != cgrp2->root);
-
- if (cgrp1->root == new_cgrp->root) {
- if (cgrp1 != new_cgrp)
- return false;
- } else {
- if (cgrp1 != cgrp2)
- return false;
- }
- }
- return true;
- }
- 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;
-
- for_each_subsys(ss, i) {
- if (root->subsys_mask & (1UL << i)) {
-
- template[i] = cgroup_e_css(cgrp, ss);
- } else {
-
- 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;
-
- return cset;
- }
-
- 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);
- }
- }
- 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(sizeof(*link), GFP_KERNEL);
- if (!link) {
- free_cgrp_cset_links(tmp_links);
- return -ENOMEM;
- }
- list_add(&link->cset_link, tmp_links);
- }
- return 0;
- }
- 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;
-
- list_move_tail(&link->cset_link, &cgrp->cset_links);
- list_add_tail(&link->cgrp_link, &cset->cgrp_links);
- if (cgroup_parent(cgrp))
- cgroup_get(cgrp);
- }
- 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);
-
- 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(sizeof(*cset), GFP_KERNEL);
- if (!cset)
- return NULL;
-
- if (allocate_cgrp_cset_links(cgroup_root_count, &tmp_links) < 0) {
- kfree(cset);
- return NULL;
- }
- atomic_set(&cset->refcount, 1);
- INIT_LIST_HEAD(&cset->cgrp_links);
- INIT_LIST_HEAD(&cset->tasks);
- INIT_LIST_HEAD(&cset->mg_tasks);
- INIT_LIST_HEAD(&cset->mg_preload_node);
- INIT_LIST_HEAD(&cset->mg_node);
- INIT_LIST_HEAD(&cset->task_iters);
- INIT_HLIST_NODE(&cset->hlist);
-
- memcpy(cset->subsys, template, sizeof(cset->subsys));
- spin_lock_irq(&css_set_lock);
-
- 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++;
-
- 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);
- return cset;
- }
- static struct cgroup_root *cgroup_root_from_kf(struct kernfs_root *kf_root)
- {
- struct cgroup *root_cgrp = kf_root->kn->priv;
- return root_cgrp->root;
- }
- 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);
- }
- static void cgroup_free_root(struct cgroup_root *root)
- {
- if (root) {
- idr_destroy(&root->cgroup_idr);
- kfree(root);
- }
- }
- static void cgroup_destroy_root(struct cgroup_root *root)
- {
- struct cgroup *cgrp = &root->cgrp;
- struct cgrp_cset_link *link, *tmp_link;
- 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));
-
- WARN_ON(rebind_subsystems(&cgrp_dfl_root, root->subsys_mask));
-
- 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);
- if (!list_empty(&root->root_list)) {
- list_del(&root->root_list);
- cgroup_root_count--;
- }
- cgroup_exit_root_id(root);
- mutex_unlock(&cgroup_mutex);
- kernfs_destroy_root(root->kf_root);
- cgroup_free_root(root);
- }
- 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;
- if (cset == &init_css_set) {
- res = &root->cgrp;
- } else {
- struct cgrp_cset_link *link;
- list_for_each_entry(link, &cset->cgrp_links, cgrp_link) {
- struct cgroup *c = link->cgrp;
- if (c->root == root) {
- res = c;
- break;
- }
- }
- }
- rcu_read_unlock();
- BUG_ON(!res);
- return res;
- }
- static struct cgroup *cset_cgroup_from_root(struct css_set *cset,
- struct cgroup_root *root)
- {
- struct cgroup *res = NULL;
- lockdep_assert_held(&cgroup_mutex);
- lockdep_assert_held(&css_set_lock);
- if (cset == &init_css_set) {
- res = &root->cgrp;
- } else {
- struct cgrp_cset_link *link;
- list_for_each_entry(link, &cset->cgrp_links, cgrp_link) {
- struct cgroup *c = link->cgrp;
- if (c->root == root) {
- res = c;
- break;
- }
- }
- }
- BUG_ON(!res);
- return res;
- }
- static struct cgroup *task_cgroup_from_root(struct task_struct *task,
- struct cgroup_root *root)
- {
-
- return cset_cgroup_from_root(task_css_set(task), root);
- }
- static struct kernfs_syscall_ops cgroup_kf_syscall_ops;
- static const struct file_operations proc_cgroupstats_operations;
- 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))
- snprintf(buf, CGROUP_FILE_NAME_MAX, "%s.%s",
- cgroup_on_dfl(cgrp) ? ss->name : ss->legacy_name,
- cft->name);
- else
- strncpy(buf, cft->name, CGROUP_FILE_NAME_MAX);
- return buf;
- }
- 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;
- }
- static u16 cgroup_calc_subtree_ss_mask(u16 subtree_control, u16 this_ss_mask)
- {
- u16 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) {
- u16 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();
-
- new_ss_mask &= this_ss_mask;
- if (new_ss_mask == cur_ss_mask)
- break;
- cur_ss_mask = new_ss_mask;
- }
- return cur_ss_mask;
- }
- static void cgroup_kn_unlock(struct kernfs_node *kn)
- {
- struct cgroup *cgrp;
- if (kernfs_type(kn) == KERNFS_DIR)
- cgrp = kn->priv;
- else
- cgrp = kn->parent->priv;
- mutex_unlock(&cgroup_mutex);
- kernfs_unbreak_active_protection(kn);
- cgroup_put(cgrp);
- }
- static 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->parent->priv;
-
- if (!cgroup_tryget(cgrp))
- return NULL;
- kernfs_break_active_protection(kn);
- if (drain_offline)
- cgroup_lock_and_drain_offline(cgrp);
- else
- mutex_lock(&cgroup_mutex);
- 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(&cgroup_file_kn_lock);
- cfile->kn = NULL;
- spin_unlock_irq(&cgroup_file_kn_lock);
- }
- kernfs_remove_by_name(cgrp->kn, cgroup_file_name(cgrp, cft, name));
- }
- 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;
- list_for_each_entry(cfts, &css->ss->cfts, node)
- cgroup_addrm_files(css, cgrp, cfts, false);
- }
- 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) || !cgrp->kn)
- return 0;
- if (!css->ss) {
- if (cgroup_on_dfl(cgrp))
- cfts = cgroup_dfl_base_files;
- else
- cfts = cgroup_legacy_base_files;
- return cgroup_addrm_files(&cgrp->self, cgrp, cfts, true);
- }
- 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;
- }
- static int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask)
- {
- struct cgroup *dcgrp = &dst_root->cgrp;
- struct cgroup_subsys *ss;
- int ssid, i, ret;
- lockdep_assert_held(&cgroup_mutex);
- do_each_subsys_mask(ss, ssid, ss_mask) {
-
- if (css_next_child(NULL, cgroup_css(&ss->root->cgrp, ss)) &&
- !ss->implicit_on_dfl)
- return -EBUSY;
-
- if (ss->root != &cgrp_dfl_root && dst_root != &cgrp_dfl_root)
- return -EBUSY;
- } while_each_subsys_mask();
- 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;
- WARN_ON(!css || cgroup_css(dcgrp, ss));
-
- src_root->subsys_mask &= ~(1 << ssid);
- WARN_ON(cgroup_apply_control(scgrp));
- cgroup_finalize_control(scgrp, 0);
-
- RCU_INIT_POINTER(scgrp->subsys[ssid], NULL);
- rcu_assign_pointer(dcgrp->subsys[ssid], css);
- ss->root = dst_root;
- css->cgroup = dcgrp;
- spin_lock_irq(&css_set_lock);
- hash_for_each(css_set_table, i, cset, hlist)
- list_move_tail(&cset->e_cset_node[ss->id],
- &dcgrp->e_csets[ss->id]);
- spin_unlock_irq(&css_set_lock);
-
- 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;
- }
- static 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 >= PATH_MAX)
- len = -ERANGE;
- else if (len > 0) {
- seq_escape(sf, buf, " \t\n\\");
- len = 0;
- }
- kfree(buf);
- return len;
- }
- static int cgroup_show_options(struct seq_file *seq,
- struct kernfs_root *kf_root)
- {
- struct cgroup_root *root = cgroup_root_from_kf(kf_root);
- struct cgroup_subsys *ss;
- int ssid;
- if (root != &cgrp_dfl_root)
- for_each_subsys(ss, ssid)
- if (root->subsys_mask & (1 << ssid))
- seq_show_option(seq, ss->legacy_name, NULL);
- if (root->flags & CGRP_ROOT_NOPREFIX)
- seq_puts(seq, ",noprefix");
- if (root->flags & CGRP_ROOT_XATTR)
- seq_puts(seq, ",xattr");
- spin_lock(&release_agent_path_lock);
- if (strlen(root->release_agent_path))
- seq_show_option(seq, "release_agent",
- root->release_agent_path);
- spin_unlock(&release_agent_path_lock);
- if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags))
- seq_puts(seq, ",clone_children");
- if (strlen(root->name))
- seq_show_option(seq, "name", root->name);
- return 0;
- }
- struct cgroup_sb_opts {
- u16 subsys_mask;
- unsigned int flags;
- char *release_agent;
- bool cpuset_clone_children;
- char *name;
-
- bool none;
- };
- static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
- {
- char *token, *o = data;
- bool all_ss = false, one_ss = false;
- u16 mask = U16_MAX;
- struct cgroup_subsys *ss;
- int nr_opts = 0;
- int i;
- #ifdef CONFIG_CPUSETS
- mask = ~((u16)1 << cpuset_cgrp_id);
- #endif
- memset(opts, 0, sizeof(*opts));
- while ((token = strsep(&o, ",")) != NULL) {
- nr_opts++;
- if (!*token)
- return -EINVAL;
- if (!strcmp(token, "none")) {
-
- opts->none = true;
- continue;
- }
- if (!strcmp(token, "all")) {
-
- if (one_ss)
- return -EINVAL;
- all_ss = true;
- continue;
- }
- if (!strcmp(token, "noprefix")) {
- opts->flags |= CGRP_ROOT_NOPREFIX;
- continue;
- }
- if (!strcmp(token, "clone_children")) {
- opts->cpuset_clone_children = true;
- continue;
- }
- if (!strcmp(token, "xattr")) {
- opts->flags |= CGRP_ROOT_XATTR;
- continue;
- }
- if (!strncmp(token, "release_agent=", 14)) {
-
- if (opts->release_agent)
- return -EINVAL;
- opts->release_agent =
- kstrndup(token + 14, PATH_MAX - 1, GFP_KERNEL);
- if (!opts->release_agent)
- return -ENOMEM;
- continue;
- }
- if (!strncmp(token, "name=", 5)) {
- const char *name = token + 5;
-
- if (!strlen(name))
- return -EINVAL;
-
- for (i = 0; i < strlen(name); i++) {
- char c = name[i];
- if (isalnum(c))
- continue;
- if ((c == '.') || (c == '-') || (c == '_'))
- continue;
- return -EINVAL;
- }
-
- if (opts->name)
- return -EINVAL;
- opts->name = kstrndup(name,
- MAX_CGROUP_ROOT_NAMELEN - 1,
- GFP_KERNEL);
- if (!opts->name)
- return -ENOMEM;
- continue;
- }
- for_each_subsys(ss, i) {
- if (strcmp(token, ss->legacy_name))
- continue;
- if (!cgroup_ssid_enabled(i))
- continue;
- if (cgroup_ssid_no_v1(i))
- continue;
-
- if (all_ss)
- return -EINVAL;
- opts->subsys_mask |= (1 << i);
- one_ss = true;
- break;
- }
- if (i == CGROUP_SUBSYS_COUNT)
- return -ENOENT;
- }
-
- if (all_ss || (!one_ss && !opts->none && !opts->name))
- for_each_subsys(ss, i)
- if (cgroup_ssid_enabled(i) && !cgroup_ssid_no_v1(i))
- opts->subsys_mask |= (1 << i);
-
- if (!opts->subsys_mask && !opts->name)
- return -EINVAL;
-
- if ((opts->flags & CGRP_ROOT_NOPREFIX) && (opts->subsys_mask & mask))
- return -EINVAL;
-
- if (opts->subsys_mask && opts->none)
- return -EINVAL;
- return 0;
- }
- static int cgroup_remount(struct kernfs_root *kf_root, int *flags, char *data)
- {
- int ret = 0;
- struct cgroup_root *root = cgroup_root_from_kf(kf_root);
- struct cgroup_sb_opts opts;
- u16 added_mask, removed_mask;
- if (root == &cgrp_dfl_root) {
- pr_err("remount is not allowed\n");
- return -EINVAL;
- }
- cgroup_lock_and_drain_offline(&cgrp_dfl_root.cgrp);
-
- ret = parse_cgroupfs_options(data, &opts);
- if (ret)
- goto out_unlock;
- if (opts.subsys_mask != root->subsys_mask || opts.release_agent)
- pr_warn("option changes via remount are deprecated (pid=%d comm=%s)\n",
- task_tgid_nr(current), current->comm);
- added_mask = opts.subsys_mask & ~root->subsys_mask;
- removed_mask = root->subsys_mask & ~opts.subsys_mask;
-
- if ((opts.flags ^ root->flags) ||
- (opts.name && strcmp(opts.name, root->name))) {
- pr_err("option or name mismatch, new: 0x%x \"%s\", old: 0x%x \"%s\"\n",
- opts.flags, opts.name ?: "", root->flags, root->name);
- ret = -EINVAL;
- goto out_unlock;
- }
-
- if (!list_empty(&root->cgrp.self.children)) {
- ret = -EBUSY;
- goto out_unlock;
- }
- ret = rebind_subsystems(root, added_mask);
- if (ret)
- goto out_unlock;
- WARN_ON(rebind_subsystems(&cgrp_dfl_root, removed_mask));
- if (opts.release_agent) {
- spin_lock(&release_agent_path_lock);
- strcpy(root->release_agent_path, opts.release_agent);
- spin_unlock(&release_agent_path_lock);
- }
- trace_cgroup_remount(root);
- out_unlock:
- kfree(opts.release_agent);
- kfree(opts.name);
- mutex_unlock(&cgroup_mutex);
- return ret;
- }
- static bool use_task_css_set_links __read_mostly;
- static void cgroup_enable_task_cg_lists(void)
- {
- struct task_struct *p, *g;
- spin_lock_irq(&css_set_lock);
- if (use_task_css_set_links)
- goto out_unlock;
- use_task_css_set_links = true;
-
- read_lock(&tasklist_lock);
- do_each_thread(g, p) {
- WARN_ON_ONCE(!list_empty(&p->cg_list) ||
- task_css_set(p) != &init_css_set);
-
- spin_lock(&p->sighand->siglock);
- if (!(p->flags & PF_EXITING)) {
- struct css_set *cset = task_css_set(p);
- if (!css_set_populated(cset))
- css_set_update_populated(cset, true);
- list_add_tail(&p->cg_list, &cset->tasks);
- get_css_set(cset);
- }
- spin_unlock(&p->sighand->siglock);
- } while_each_thread(g, p);
- read_unlock(&tasklist_lock);
- out_unlock:
- spin_unlock_irq(&css_set_lock);
- }
- 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;
- for_each_subsys(ss, ssid)
- INIT_LIST_HEAD(&cgrp->e_csets[ssid]);
- init_waitqueue_head(&cgrp->offline_waitq);
- INIT_WORK(&cgrp->release_agent_work, cgroup_release_agent);
- }
- static void init_cgroup_root(struct cgroup_root *root,
- struct cgroup_sb_opts *opts)
- {
- struct cgroup *cgrp = &root->cgrp;
- INIT_LIST_HEAD(&root->root_list);
- atomic_set(&root->nr_cgrps, 1);
- cgrp->root = root;
- init_cgroup_housekeeping(cgrp);
- idr_init(&root->cgroup_idr);
- root->flags = opts->flags;
- if (opts->release_agent)
- strcpy(root->release_agent_path, opts->release_agent);
- if (opts->name)
- strcpy(root->name, opts->name);
- if (opts->cpuset_clone_children)
- set_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags);
- }
- static int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask)
- {
- LIST_HEAD(tmp_links);
- struct cgroup *root_cgrp = &root->cgrp;
- struct css_set *cset;
- int i, ret;
- lockdep_assert_held(&cgroup_mutex);
- ret = cgroup_idr_alloc(&root->cgroup_idr, root_cgrp, 1, 2, GFP_KERNEL);
- if (ret < 0)
- goto out;
- root_cgrp->id = ret;
- root_cgrp->ancestor_ids[0] = ret;
- ret = percpu_ref_init(&root_cgrp->self.refcnt, css_release, 0,
- GFP_KERNEL);
- if (ret)
- goto out;
-
- 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;
- root->kf_root = kernfs_create_root(&cgroup_kf_syscall_ops,
- KERNFS_ROOT_CREATE_DEACTIVATED,
- root_cgrp);
- if (IS_ERR(root->kf_root)) {
- ret = PTR_ERR(root->kf_root);
- goto exit_root_id;
- }
- root_cgrp->kn = root->kf_root->kn;
- ret = css_populate_dir(&root_cgrp->self);
- if (ret)
- goto destroy_root;
- ret = rebind_subsystems(root, ss_mask);
- if (ret)
- goto destroy_root;
- trace_cgroup_setup_root(root);
-
- list_add(&root->root_list, &cgroup_roots);
- cgroup_root_count++;
-
- 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))
- cgroup_update_populated(root_cgrp, true);
- }
- spin_unlock_irq(&css_set_lock);
- BUG_ON(!list_empty(&root_cgrp->self.children));
- BUG_ON(atomic_read(&root->nr_cgrps) != 1);
- kernfs_activate(root_cgrp->kn);
- ret = 0;
- goto out;
- 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;
- }
- static struct dentry *cgroup_mount(struct file_system_type *fs_type,
- int flags, const char *unused_dev_name,
- void *data)
- {
- bool is_v2 = fs_type == &cgroup2_fs_type;
- struct super_block *pinned_sb = NULL;
- struct cgroup_namespace *ns = current->nsproxy->cgroup_ns;
- struct cgroup_subsys *ss;
- struct cgroup_root *root;
- struct cgroup_sb_opts opts;
- struct dentry *dentry;
- int ret;
- int i;
- bool new_sb;
- get_cgroup_ns(ns);
-
- if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN)) {
- put_cgroup_ns(ns);
- return ERR_PTR(-EPERM);
- }
-
- if (!use_task_css_set_links)
- cgroup_enable_task_cg_lists();
- if (is_v2) {
- if (data) {
- pr_err("cgroup2: unknown option \"%s\"\n", (char *)data);
- put_cgroup_ns(ns);
- return ERR_PTR(-EINVAL);
- }
- cgrp_dfl_visible = true;
- root = &cgrp_dfl_root;
- cgroup_get(&root->cgrp);
- goto out_mount;
- }
- cgroup_lock_and_drain_offline(&cgrp_dfl_root.cgrp);
-
- ret = parse_cgroupfs_options(data, &opts);
- if (ret)
- goto out_unlock;
-
- for_each_subsys(ss, i) {
- if (!(opts.subsys_mask & (1 << i)) ||
- ss->root == &cgrp_dfl_root)
- continue;
- if (!percpu_ref_tryget_live(&ss->root->cgrp.self.refcnt)) {
- mutex_unlock(&cgroup_mutex);
- msleep(10);
- ret = restart_syscall();
- goto out_free;
- }
- cgroup_put(&ss->root->cgrp);
- }
- for_each_root(root) {
- bool name_match = false;
- if (root == &cgrp_dfl_root)
- continue;
-
- if (opts.name) {
- if (strcmp(opts.name, root->name))
- continue;
- name_match = true;
- }
-
- if ((opts.subsys_mask || opts.none) &&
- (opts.subsys_mask != root->subsys_mask)) {
- if (!name_match)
- continue;
- ret = -EBUSY;
- goto out_unlock;
- }
- if (root->flags ^ opts.flags)
- pr_warn("new mount options do not match the existing superblock, will be ignored\n");
-
- pinned_sb = kernfs_pin_sb(root->kf_root, NULL);
- if (IS_ERR(pinned_sb) ||
- !percpu_ref_tryget_live(&root->cgrp.self.refcnt)) {
- mutex_unlock(&cgroup_mutex);
- if (!IS_ERR_OR_NULL(pinned_sb))
- deactivate_super(pinned_sb);
- msleep(10);
- ret = restart_syscall();
- goto out_free;
- }
- ret = 0;
- goto out_unlock;
- }
-
- if (!opts.subsys_mask && !opts.none) {
- ret = -EINVAL;
- goto out_unlock;
- }
-
- if (ns != &init_cgroup_ns) {
- ret = -EPERM;
- goto out_unlock;
- }
- root = kzalloc(sizeof(*root), GFP_KERNEL);
- if (!root) {
- ret = -ENOMEM;
- goto out_unlock;
- }
- init_cgroup_root(root, &opts);
- ret = cgroup_setup_root(root, opts.subsys_mask);
- if (ret)
- cgroup_free_root(root);
- out_unlock:
- mutex_unlock(&cgroup_mutex);
- out_free:
- kfree(opts.release_agent);
- kfree(opts.name);
- if (ret) {
- put_cgroup_ns(ns);
- return ERR_PTR(ret);
- }
- out_mount:
- dentry = kernfs_mount(fs_type, flags, root->kf_root,
- is_v2 ? CGROUP2_SUPER_MAGIC : CGROUP_SUPER_MAGIC,
- &new_sb);
-
- if (!IS_ERR(dentry) && ns != &init_cgroup_ns) {
- struct dentry *nsdentry;
- struct cgroup *cgrp;
- mutex_lock(&cgroup_mutex);
- spin_lock_irq(&css_set_lock);
- cgrp = cset_cgroup_from_root(ns->root_cset, root);
- spin_unlock_irq(&css_set_lock);
- mutex_unlock(&cgroup_mutex);
- nsdentry = kernfs_node_dentry(cgrp->kn, dentry->d_sb);
- dput(dentry);
- dentry = nsdentry;
- }
- if (IS_ERR(dentry) || !new_sb)
- cgroup_put(&root->cgrp);
-
- if (pinned_sb) {
- WARN_ON(new_sb);
- deactivate_super(pinned_sb);
- }
- put_cgroup_ns(ns);
- return dentry;
- }
- 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 (!list_empty(&root->cgrp.self.children) ||
- root == &cgrp_dfl_root)
- cgroup_put(&root->cgrp);
- else
- percpu_ref_kill(&root->cgrp.self.refcnt);
- kernfs_kill_sb(sb);
- }
- static struct file_system_type cgroup_fs_type = {
- .name = "cgroup",
- .mount = cgroup_mount,
- .kill_sb = cgroup_kill_sb,
- .fs_flags = FS_USERNS_MOUNT,
- };
- static struct file_system_type cgroup2_fs_type = {
- .name = "cgroup2",
- .mount = cgroup_mount,
- .kill_sb = cgroup_kill_sb,
- .fs_flags = FS_USERNS_MOUNT,
- };
- static 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;
- mutex_lock(&cgroup_mutex);
- spin_lock_irq(&css_set_lock);
- ret = cgroup_path_ns_locked(cgrp, buf, buflen, ns);
- spin_unlock_irq(&css_set_lock);
- mutex_unlock(&cgroup_mutex);
- return ret;
- }
- EXPORT_SYMBOL_GPL(cgroup_path_ns);
- int task_cgroup_path(struct task_struct *task, char *buf, size_t buflen)
- {
- struct cgroup_root *root;
- struct cgroup *cgrp;
- int hierarchy_id = 1;
- int ret;
- mutex_lock(&cgroup_mutex);
- spin_lock_irq(&css_set_lock);
- root = idr_get_next(&cgroup_hierarchy_idr, &hierarchy_id);
- if (root) {
- cgrp = task_cgroup_from_root(task, root);
- ret = cgroup_path_ns_locked(cgrp, buf, buflen, &init_cgroup_ns);
- } else {
-
- ret = strlcpy(buf, "/", buflen);
- }
- spin_unlock_irq(&css_set_lock);
- mutex_unlock(&cgroup_mutex);
- return ret;
- }
- EXPORT_SYMBOL_GPL(task_cgroup_path);
- struct cgroup_taskset {
-
- struct list_head src_csets;
- struct list_head dst_csets;
-
- int ssid;
-
- struct list_head *csets;
- struct css_set *cur_cset;
- struct task_struct *cur_task;
- };
- #define CGROUP_TASKSET_INIT(tset) (struct cgroup_taskset){ \
- .src_csets = LIST_HEAD_INIT(tset.src_csets), \
- .dst_csets = LIST_HEAD_INIT(tset.dst_csets), \
- .csets = &tset.src_csets, \
- }
- static void cgroup_taskset_add(struct task_struct *task,
- struct cgroup_taskset *tset)
- {
- struct css_set *cset;
- lockdep_assert_held(&css_set_lock);
-
- if (task->flags & PF_EXITING)
- return;
-
- if (list_empty(&task->cg_list))
- return;
- cset = task_css_set(task);
- if (!cset->mg_src_cgrp)
- return;
- list_move_tail(&task->cg_list, &cset->mg_tasks);
- if (list_empty(&cset->mg_node))
- list_add_tail(&cset->mg_node, &tset->src_csets);
- if (list_empty(&cset->mg_dst_cset->mg_node))
- list_move_tail(&cset->mg_dst_cset->mg_node,
- &tset->dst_csets);
- }
- 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);
- }
- 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 (&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;
-
- 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;
- }
- static int cgroup_taskset_migrate(struct cgroup_taskset *tset,
- struct cgroup_root *root)
- {
- struct cgroup_subsys *ss;
- struct task_struct *task, *tmp_task;
- struct css_set *cset, *tmp_cset;
- int ssid, failed_ssid, ret;
-
- if (list_empty(&tset->src_csets))
- return 0;
-
- do_each_subsys_mask(ss, ssid, root->subsys_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();
-
- 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);
- css_set_move_task(task, from_cset, to_cset, true);
- put_css_set_locked(from_cset);
- }
- }
- spin_unlock_irq(&css_set_lock);
-
- tset->csets = &tset->dst_csets;
- do_each_subsys_mask(ss, ssid, root->subsys_mask) {
- if (ss->attach) {
- tset->ssid = ssid;
- ss->attach(tset);
- }
- } while_each_subsys_mask();
- ret = 0;
- goto out_release_tset;
- out_cancel_attach:
- do_each_subsys_mask(ss, ssid, root->subsys_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);
- return ret;
- }
- static bool cgroup_may_migrate_to(struct cgroup *dst_cgrp)
- {
- return !cgroup_on_dfl(dst_cgrp) || !cgroup_parent(dst_cgrp) ||
- !dst_cgrp->subtree_control;
- }
- static void cgroup_migrate_finish(struct list_head *preloaded_csets)
- {
- 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, preloaded_csets, mg_preload_node) {
- cset->mg_src_cgrp = NULL;
- cset->mg_dst_cgrp = NULL;
- cset->mg_dst_cset = NULL;
- list_del_init(&cset->mg_preload_node);
- put_css_set_locked(cset);
- }
- spin_unlock_irq(&css_set_lock);
- }
- static void cgroup_migrate_add_src(struct css_set *src_cset,
- struct cgroup *dst_cgrp,
- struct list_head *preloaded_csets)
- {
- struct cgroup *src_cgrp;
- lockdep_assert_held(&cgroup_mutex);
- lockdep_assert_held(&css_set_lock);
-
- if (src_cset->dead)
- return;
- src_cgrp = cset_cgroup_from_root(src_cset, dst_cgrp->root);
- if (!list_empty(&src_cset->mg_preload_node))
- return;
- 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(&src_cset->mg_preload_node, preloaded_csets);
- }
- static int cgroup_migrate_prepare_dst(struct list_head *preloaded_csets)
- {
- LIST_HEAD(csets);
- struct css_set *src_cset, *tmp_cset;
- lockdep_assert_held(&cgroup_mutex);
-
- list_for_each_entry_safe(src_cset, tmp_cset, preloaded_csets, mg_preload_node) {
- struct css_set *dst_cset;
- dst_cset = find_css_set(src_cset, src_cset->mg_dst_cgrp);
- if (!dst_cset)
- goto err;
- WARN_ON_ONCE(src_cset->mg_dst_cset || dst_cset->mg_dst_cset);
-
- if (src_cset == dst_cset) {
- src_cset->mg_src_cgrp = NULL;
- src_cset->mg_dst_cgrp = NULL;
- list_del_init(&src_cset->mg_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_preload_node))
- list_add(&dst_cset->mg_preload_node, &csets);
- else
- put_css_set(dst_cset);
- }
- list_splice_tail(&csets, preloaded_csets);
- return 0;
- err:
- cgroup_migrate_finish(&csets);
- return -ENOMEM;
- }
- static int cgroup_migrate(struct task_struct *leader, bool threadgroup,
- struct cgroup_root *root)
- {
- struct cgroup_taskset tset = CGROUP_TASKSET_INIT(tset);
- struct task_struct *task;
-
- spin_lock_irq(&css_set_lock);
- rcu_read_lock();
- task = leader;
- do {
- cgroup_taskset_add(task, &tset);
- if (!threadgroup)
- break;
- } while_each_thread(leader, task);
- rcu_read_unlock();
- spin_unlock_irq(&css_set_lock);
- return cgroup_taskset_migrate(&tset, root);
- }
- static int cgroup_attach_task(struct cgroup *dst_cgrp,
- struct task_struct *leader, bool threadgroup)
- {
- LIST_HEAD(preloaded_csets);
- struct task_struct *task;
- int ret;
- if (!cgroup_may_migrate_to(dst_cgrp))
- return -EBUSY;
-
- spin_lock_irq(&css_set_lock);
- rcu_read_lock();
- task = leader;
- do {
- cgroup_migrate_add_src(task_css_set(task), dst_cgrp,
- &preloaded_csets);
- if (!threadgroup)
- break;
- } while_each_thread(leader, task);
- rcu_read_unlock();
- spin_unlock_irq(&css_set_lock);
-
- ret = cgroup_migrate_prepare_dst(&preloaded_csets);
- if (!ret)
- ret = cgroup_migrate(leader, threadgroup, dst_cgrp->root);
- cgroup_migrate_finish(&preloaded_csets);
- if (!ret)
- trace_cgroup_attach_task(dst_cgrp, leader, threadgroup);
- return ret;
- }
- static int cgroup_procs_write_permission(struct task_struct *task,
- struct cgroup *dst_cgrp,
- struct kernfs_open_file *of)
- {
- const struct cred *cred = current_cred();
- const struct cred *tcred = get_task_cred(task);
- int ret = 0;
-
- if (!uid_eq(cred->euid, GLOBAL_ROOT_UID) &&
- !uid_eq(cred->euid, tcred->uid) &&
- !uid_eq(cred->euid, tcred->suid))
- ret = -EACCES;
- if (!ret && cgroup_on_dfl(dst_cgrp)) {
- struct super_block *sb = of->file->f_path.dentry->d_sb;
- struct cgroup *cgrp;
- struct inode *inode;
- spin_lock_irq(&css_set_lock);
- cgrp = task_cgroup_from_root(task, &cgrp_dfl_root);
- spin_unlock_irq(&css_set_lock);
- while (!cgroup_is_descendant(dst_cgrp, cgrp))
- cgrp = cgroup_parent(cgrp);
- ret = -ENOMEM;
- inode = kernfs_get_inode(sb, cgrp->procs_file.kn);
- if (inode) {
- ret = inode_permission(inode, MAY_WRITE);
- iput(inode);
- }
- }
- put_cred(tcred);
- return ret;
- }
- static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf,
- size_t nbytes, loff_t off, bool threadgroup)
- {
- struct task_struct *tsk;
- struct cgroup_subsys *ss;
- struct cgroup *cgrp;
- pid_t pid;
- int ssid, ret;
- if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0)
- return -EINVAL;
- cgrp = cgroup_kn_lock_live(of->kn, false);
- if (!cgrp)
- return -ENODEV;
- percpu_down_write(&cgroup_threadgroup_rwsem);
- rcu_read_lock();
- if (pid) {
- tsk = find_task_by_vpid(pid);
- if (!tsk) {
- ret = -ESRCH;
- goto out_unlock_rcu;
- }
- } else {
- tsk = current;
- }
- if (threadgroup)
- tsk = tsk->group_leader;
-
- if (tsk->no_cgroup_migration || (tsk->flags & PF_NO_SETAFFINITY)) {
- ret = -EINVAL;
- goto out_unlock_rcu;
- }
- get_task_struct(tsk);
- rcu_read_unlock();
- ret = cgroup_procs_write_permission(tsk, cgrp, of);
- if (!ret)
- ret = cgroup_attach_task(cgrp, tsk, threadgroup);
- put_task_struct(tsk);
- goto out_unlock_threadgroup;
- out_unlock_rcu:
- rcu_read_unlock();
- out_unlock_threadgroup:
- percpu_up_write(&cgroup_threadgroup_rwsem);
- for_each_subsys(ss, ssid)
- if (ss->post_attach)
- ss->post_attach();
- cgroup_kn_unlock(of->kn);
- return ret ?: nbytes;
- }
- int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk)
- {
- struct cgroup_root *root;
- int retval = 0;
- mutex_lock(&cgroup_mutex);
- percpu_down_write(&cgroup_threadgroup_rwsem);
- for_each_root(root) {
- struct cgroup *from_cgrp;
- if (root == &cgrp_dfl_root)
- continue;
- spin_lock_irq(&css_set_lock);
- from_cgrp = task_cgroup_from_root(from, root);
- spin_unlock_irq(&css_set_lock);
- retval = cgroup_attach_task(from_cgrp, tsk, false);
- if (retval)
- break;
- }
- percpu_up_write(&cgroup_threadgroup_rwsem);
- mutex_unlock(&cgroup_mutex);
- return retval;
- }
- EXPORT_SYMBOL_GPL(cgroup_attach_task_all);
- static ssize_t cgroup_tasks_write(struct kernfs_open_file *of,
- char *buf, size_t nbytes, loff_t off)
- {
- return __cgroup_procs_write(of, buf, nbytes, off, false);
- }
- 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, nbytes, off, true);
- }
- static ssize_t cgroup_release_agent_write(struct kernfs_open_file *of,
- char *buf, size_t nbytes, loff_t off)
- {
- struct cgroup *cgrp;
- BUILD_BUG_ON(sizeof(cgrp->root->release_agent_path) < PATH_MAX);
- cgrp = cgroup_kn_lock_live(of->kn, false);
- if (!cgrp)
- return -ENODEV;
- spin_lock(&release_agent_path_lock);
- strlcpy(cgrp->root->release_agent_path, strstrip(buf),
- sizeof(cgrp->root->release_agent_path));
- spin_unlock(&release_agent_path_lock);
- cgroup_kn_unlock(of->kn);
- return nbytes;
- }
- static int cgroup_release_agent_show(struct seq_file *seq, void *v)
- {
- struct cgroup *cgrp = seq_css(seq)->cgroup;
- spin_lock(&release_agent_path_lock);
- seq_puts(seq, cgrp->root->release_agent_path);
- spin_unlock(&release_agent_path_lock);
- seq_putc(seq, '\n');
- return 0;
- }
- static int cgroup_sane_behavior_show(struct seq_file *seq, void *v)
- {
- seq_puts(seq, "0\n");
- return 0;
- }
- static void cgroup_print_ss_mask(struct seq_file *seq, u16 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_printf(seq, "%s", ss->name);
- printed = true;
- } while_each_subsys_mask();
- if (printed)
- seq_putc(seq, '\n');
- }
- 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;
- }
- 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;
- }
- static int cgroup_update_dfl_csses(struct cgroup *cgrp)
- {
- LIST_HEAD(preloaded_csets);
- struct cgroup_taskset tset = CGROUP_TASKSET_INIT(tset);
- struct cgroup_subsys_state *d_css;
- struct cgroup *dsct;
- struct css_set *src_cset;
- int ret;
- lockdep_assert_held(&cgroup_mutex);
- percpu_down_write(&cgroup_threadgroup_rwsem);
-
- spin_lock_irq(&css_set_lock);
- cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) {
- struct cgrp_cset_link *link;
- list_for_each_entry(link, &dsct->cset_links, cset_link)
- cgroup_migrate_add_src(link->cset, dsct,
- &preloaded_csets);
- }
- spin_unlock_irq(&css_set_lock);
-
- ret = cgroup_migrate_prepare_dst(&preloaded_csets);
- if (ret)
- goto out_finish;
- spin_lock_irq(&css_set_lock);
- list_for_each_entry(src_cset, &preloaded_csets, mg_preload_node) {
- struct task_struct *task, *ntask;
-
- if (!src_cset->mg_src_cgrp)
- break;
-
- list_for_each_entry_safe(task, ntask, &src_cset->tasks, cg_list)
- cgroup_taskset_add(task, &tset);
- }
- spin_unlock_irq(&css_set_lock);
- ret = cgroup_taskset_migrate(&tset, cgrp->root);
- out_finish:
- cgroup_migrate_finish(&preloaded_csets);
- percpu_up_write(&cgroup_threadgroup_rwsem);
- return ret;
- }
- static 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:
- mutex_lock(&cgroup_mutex);
- 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 || !percpu_ref_is_dying(&css->refcnt))
- continue;
- cgroup_get(dsct);
- prepare_to_wait(&dsct->offline_waitq, &wait,
- TASK_UNINTERRUPTIBLE);
- mutex_unlock(&cgroup_mutex);
- schedule();
- finish_wait(&dsct->offline_waitq, &wait);
- cgroup_put(dsct);
- goto restart;
- }
- }
- }
- 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;
- }
- }
- 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));
- }
- }
- 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;
- }
- }
- 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;
- }
- 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);
- WARN_ON_ONCE(css && percpu_ref_is_dying(&css->refcnt));
- if (!(cgroup_ss_mask(dsct) & (1 << ss->id)))
- continue;
- if (!css) {
- css = css_create(dsct, ss);
- if (IS_ERR(css))
- return PTR_ERR(css);
- }
- if (css_visible(css)) {
- ret = css_populate_dir(css);
- if (ret)
- return ret;
- }
- }
- }
- return 0;
- }
- 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);
- WARN_ON_ONCE(css && percpu_ref_is_dying(&css->refcnt));
- if (!css)
- continue;
- if (css->parent &&
- !(cgroup_ss_mask(dsct) & (1 << ss->id))) {
- kill_css(css);
- } else if (!css_visible(css)) {
- css_clear_dir(css);
- if (ss->css_reset)
- ss->css_reset(css);
- }
- }
- }
- }
- static int cgroup_apply_control(struct cgroup *cgrp)
- {
- int ret;
- cgroup_propagate_control(cgrp);
- ret = cgroup_apply_control_enable(cgrp);
- if (ret)
- return ret;
-
- ret = cgroup_update_dfl_csses(cgrp);
- if (ret)
- return ret;
- return 0;
- }
- 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 ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of,
- char *buf, size_t nbytes,
- loff_t off)
- {
- u16 enable = 0, disable = 0;
- struct cgroup *cgrp, *child;
- struct cgroup_subsys *ss;
- char *tok;
- int ssid, ret;
-
- 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;
- }
-
- 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;
- }
-
- if (enable && cgroup_parent(cgrp)) {
- struct cgrp_cset_link *link;
-
- spin_lock_irq(&css_set_lock);
- ret = 0;
- list_for_each_entry(link, &cgrp->cset_links, cset_link) {
- if (css_set_populated(link->cset)) {
- ret = -EBUSY;
- break;
- }
- }
- spin_unlock_irq(&css_set_lock);
- if (ret)
- goto out_unlock;
- }
-
- 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;
- }
- static int cgroup_events_show(struct seq_file *seq, void *v)
- {
- seq_printf(seq, "populated %d\n",
- cgroup_is_populated(seq_css(seq)->cgroup));
- return 0;
- }
- static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf,
- size_t nbytes, loff_t off)
- {
- struct cgroup *cgrp = of->kn->parent->priv;
- struct cftype *cft = of->kn->priv;
- struct cgroup_subsys_state *css;
- int ret;
- if (cft->write)
- return cft->write(of, buf, nbytes, off);
-
- 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 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)
- {
- 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,
- .write = cgroup_file_write,
- .seq_show = cgroup_seqfile_show,
- };
- static struct kernfs_ops cgroup_kf_ops = {
- .atomic_write_len = PAGE_SIZE,
- .write = cgroup_file_write,
- .seq_start = cgroup_seqfile_start,
- .seq_next = cgroup_seqfile_next,
- .seq_stop = cgroup_seqfile_stop,
- .seq_show = cgroup_seqfile_show,
- };
- static int cgroup_rename(struct kernfs_node *kn, struct kernfs_node *new_parent,
- const char *new_name_str)
- {
- struct cgroup *cgrp = kn->priv;
- int ret;
- if (kernfs_type(kn) != KERNFS_DIR)
- return -ENOTDIR;
- if (kn->parent != new_parent)
- return -EIO;
-
- if (cgroup_on_dfl(cgrp))
- return -EPERM;
-
- kernfs_break_active_protection(new_parent);
- kernfs_break_active_protection(kn);
- mutex_lock(&cgroup_mutex);
- ret = kernfs_rename(kn, new_parent, new_name_str);
- if (!ret)
- trace_cgroup_rename(cgrp);
- mutex_unlock(&cgroup_mutex);
- kernfs_unbreak_active_protection(kn);
- kernfs_unbreak_active_protection(new_parent);
- return ret;
- }
- static int cgroup_kn_set_ugid(struct kernfs_node *kn)
- {
- struct iattr iattr = { .ia_valid = ATTR_UID | ATTR_GID,
- .ia_uid = current_fsuid(),
- .ia_gid = current_fsgid(), };
- if (uid_eq(iattr.ia_uid, GLOBAL_ROOT_UID) &&
- gid_eq(iattr.ia_gid, GLOBAL_ROOT_GID))
- return 0;
- return kernfs_setattr(kn, &iattr);
- }
- 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;
- int ret;
- #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), 0, cft->kf_ops, cft,
- NULL, key);
- if (IS_ERR(kn))
- return PTR_ERR(kn);
- ret = cgroup_kn_set_ugid(kn);
- if (ret) {
- kernfs_remove(kn);
- return ret;
- }
- if (cft->file_offset) {
- struct cgroup_file *cfile = (void *)css + cft->file_offset;
- spin_lock_irq(&cgroup_file_kn_lock);
- cfile->kn = kn;
- spin_unlock_irq(&cgroup_file_kn_lock);
- }
- return 0;
- }
- 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++) {
-
- 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 (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)
- {
- LIST_HEAD(pending);
- 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);
-
- 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++) {
-
- if (cft->max_write_len && cft->max_write_len != PAGE_SIZE)
- kfree(cft->kf_ops);
- cft->kf_ops = NULL;
- cft->ss = NULL;
-
- cft->flags &= ~(__CFTYPE_ONLY_ON_DFL | __CFTYPE_NOT_ON_DFL);
- }
- }
- static int cgroup_init_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
- {
- struct cftype *cft;
- for (cft = cfts; cft->name[0] != '\0'; cft++) {
- struct kernfs_ops *kf_ops;
- WARN_ON(cft->ss || cft->kf_ops);
- if (cft->seq_start)
- kf_ops = &cgroup_kf_ops;
- else
- kf_ops = &cgroup_kf_single_ops;
-
- if (cft->max_write_len && cft->max_write_len != PAGE_SIZE) {
- kf_ops = kmemdup(kf_ops, sizeof(*kf_ops), GFP_KERNEL);
- if (!kf_ops) {
- cgroup_exit_cftypes(cfts);
- return -ENOMEM;
- }
- kf_ops->atomic_write_len = cft->max_write_len;
- }
- cft->kf_ops = kf_ops;
- cft->ss = ss;
- }
- return 0;
- }
- static int cgroup_rm_cftypes_locked(struct cftype *cfts)
- {
- lockdep_assert_held(&cgroup_mutex);
- if (!cfts || !cfts[0].ss)
- return -ENOENT;
- list_del(&cfts->node);
- cgroup_apply_cftypes(cfts, false);
- cgroup_exit_cftypes(cfts);
- return 0;
- }
- int cgroup_rm_cftypes(struct cftype *cfts)
- {
- int ret;
- mutex_lock(&cgroup_mutex);
- ret = cgroup_rm_cftypes_locked(cfts);
- mutex_unlock(&cgroup_mutex);
- return ret;
- }
- static 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;
- mutex_lock(&cgroup_mutex);
- list_add_tail(&cfts->node, &ss->cfts);
- ret = cgroup_apply_cftypes(cfts, true);
- if (ret)
- cgroup_rm_cftypes_locked(cfts);
- mutex_unlock(&cgroup_mutex);
- return ret;
- }
- 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);
- }
- 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);
- }
- void cgroup_file_notify(struct cgroup_file *cfile)
- {
- unsigned long flags;
- spin_lock_irqsave(&cgroup_file_kn_lock, flags);
- if (cfile->kn)
- kernfs_notify(cfile->kn);
- spin_unlock_irqrestore(&cgroup_file_kn_lock, flags);
- }
- static int cgroup_task_count(const struct cgroup *cgrp)
- {
- int count = 0;
- struct cgrp_cset_link *link;
- spin_lock_irq(&css_set_lock);
- list_for_each_entry(link, &cgrp->cset_links, cset_link)
- count += atomic_read(&link->cset->refcount);
- spin_unlock_irq(&css_set_lock);
- return count;
- }
- 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();
-
- 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)
- if (next->serial_nr > pos->serial_nr)
- break;
- }
-
- if (&next->sibling != &parent->children)
- return next;
- return NULL;
- }
- 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 (!pos)
- return root;
-
- next = css_next_child(NULL, pos);
- if (next)
- return next;
-
- while (pos != root) {
- next = css_next_child(pos, pos->parent);
- if (next)
- return next;
- pos = pos->parent;
- }
- return NULL;
- }
- 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;
-
- 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;
- }
- 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 (!pos)
- return css_leftmost_descendant(root);
-
- if (pos == root)
- return NULL;
-
- next = css_next_child(pos, pos->parent);
- if (next)
- return css_leftmost_descendant(next);
-
- return pos->parent;
- }
- 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 (child->flags & CSS_ONLINE) {
- ret = true;
- break;
- }
- }
- rcu_read_unlock();
- return ret;
- }
- static void css_task_iter_advance_css_set(struct css_task_iter *it)
- {
- struct list_head *l = it->cset_pos;
- struct cgrp_cset_link *link;
- struct css_set *cset;
- lockdep_assert_held(&css_set_lock);
-
- do {
- l = l->next;
- if (l == it->cset_head) {
- it->cset_pos = NULL;
- it->task_pos = NULL;
- return;
- }
- 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;
- }
- } while (!css_set_populated(cset));
- it->cset_pos = l;
- if (!list_empty(&cset->tasks))
- it->task_pos = cset->tasks.next;
- else
- it->task_pos = cset->mg_tasks.next;
- it->tasks_head = &cset->tasks;
- it->mg_tasks_head = &cset->mg_tasks;
-
- 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_advance(struct css_task_iter *it)
- {
- struct list_head *l = it->task_pos;
- lockdep_assert_held(&css_set_lock);
- WARN_ON_ONCE(!l);
-
- l = l->next;
- if (l == it->tasks_head)
- l = it->mg_tasks_head->next;
- if (l == it->mg_tasks_head)
- css_task_iter_advance_css_set(it);
- else
- it->task_pos = l;
- }
- void css_task_iter_start(struct cgroup_subsys_state *css,
- struct css_task_iter *it)
- {
-
- WARN_ON_ONCE(!use_task_css_set_links);
- memset(it, 0, sizeof(*it));
- spin_lock_irq(&css_set_lock);
- it->ss = css->ss;
- if (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_css_set(it);
- spin_unlock_irq(&css_set_lock);
- }
- struct task_struct *css_task_iter_next(struct css_task_iter *it)
- {
- if (it->cur_task) {
- put_task_struct(it->cur_task);
- it->cur_task = NULL;
- }
- spin_lock_irq(&css_set_lock);
- 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_irq(&css_set_lock);
- return it->cur_task;
- }
- void css_task_iter_end(struct css_task_iter *it)
- {
- if (it->cur_cset) {
- spin_lock_irq(&css_set_lock);
- list_del(&it->iters_node);
- put_css_set_locked(it->cur_cset);
- spin_unlock_irq(&css_set_lock);
- }
- if (it->cur_task)
- put_task_struct(it->cur_task);
- }
- int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from)
- {
- LIST_HEAD(preloaded_csets);
- struct cgrp_cset_link *link;
- struct css_task_iter it;
- struct task_struct *task;
- int ret;
- if (!cgroup_may_migrate_to(to))
- return -EBUSY;
- mutex_lock(&cgroup_mutex);
- percpu_down_write(&cgroup_threadgroup_rwsem);
-
- spin_lock_irq(&css_set_lock);
- list_for_each_entry(link, &from->cset_links, cset_link)
- cgroup_migrate_add_src(link->cset, to, &preloaded_csets);
- spin_unlock_irq(&css_set_lock);
- ret = cgroup_migrate_prepare_dst(&preloaded_csets);
- if (ret)
- goto out_err;
-
- do {
- css_task_iter_start(&from->self, &it);
- do {
- task = css_task_iter_next(&it);
- } while (task && (task->flags & PF_EXITING));
- if (task)
- get_task_struct(task);
- css_task_iter_end(&it);
- if (task) {
- ret = cgroup_migrate(task, false, to->root);
- if (!ret)
- trace_cgroup_transfer_tasks(to, task, false);
- put_task_struct(task);
- }
- } while (task && !ret);
- out_err:
- cgroup_migrate_finish(&preloaded_csets);
- percpu_up_write(&cgroup_threadgroup_rwsem);
- mutex_unlock(&cgroup_mutex);
- return ret;
- }
- enum cgroup_filetype {
- CGROUP_FILE_PROCS,
- CGROUP_FILE_TASKS,
- };
- struct cgroup_pidlist {
-
- struct { enum cgroup_filetype type; struct pid_namespace *ns; } key;
-
- pid_t *list;
-
- int length;
-
- struct list_head links;
-
- struct cgroup *owner;
-
- struct delayed_work destroy_dwork;
- };
- #define PIDLIST_TOO_LARGE(c) ((c) * sizeof(pid_t) > (PAGE_SIZE * 2))
- static void *pidlist_allocate(int count)
- {
- if (PIDLIST_TOO_LARGE(count))
- return vmalloc(count * sizeof(pid_t));
- else
- return kmalloc(count * sizeof(pid_t), GFP_KERNEL);
- }
- static void pidlist_free(void *p)
- {
- kvfree(p);
- }
- static void cgroup_pidlist_destroy_all(struct cgroup *cgrp)
- {
- struct cgroup_pidlist *l, *tmp_l;
- mutex_lock(&cgrp->pidlist_mutex);
- list_for_each_entry_safe(l, tmp_l, &cgrp->pidlists, links)
- mod_delayed_work(cgroup_pidlist_destroy_wq, &l->destroy_dwork, 0);
- mutex_unlock(&cgrp->pidlist_mutex);
- flush_workqueue(cgroup_pidlist_destroy_wq);
- BUG_ON(!list_empty(&cgrp->pidlists));
- }
- static void cgroup_pidlist_destroy_work_fn(struct work_struct *work)
- {
- struct delayed_work *dwork = to_delayed_work(work);
- struct cgroup_pidlist *l = container_of(dwork, struct cgroup_pidlist,
- destroy_dwork);
- struct cgroup_pidlist *tofree = NULL;
- mutex_lock(&l->owner->pidlist_mutex);
-
- if (!delayed_work_pending(dwork)) {
- list_del(&l->links);
- pidlist_free(l->list);
- put_pid_ns(l->key.ns);
- tofree = l;
- }
- mutex_unlock(&l->owner->pidlist_mutex);
- kfree(tofree);
- }
- static int pidlist_uniq(pid_t *list, int length)
- {
- int src, dest = 1;
-
- if (length == 0 || length == 1)
- return length;
-
- for (src = 1; src < length; src++) {
-
- while (list[src] == list[src-1]) {
- src++;
- if (src == length)
- goto after;
- }
-
- list[dest] = list[src];
- dest++;
- }
- after:
- return dest;
- }
- static pid_t pid_fry(pid_t pid)
- {
- unsigned a = pid & 0x55555555;
- unsigned b = pid & 0xAAAAAAAA;
- return (a << 1) | (b >> 1);
- }
- static pid_t cgroup_pid_fry(struct cgroup *cgrp, pid_t pid)
- {
- if (cgroup_on_dfl(cgrp))
- return pid_fry(pid);
- else
- return pid;
- }
- static int cmppid(const void *a, const void *b)
- {
- return *(pid_t *)a - *(pid_t *)b;
- }
- static int fried_cmppid(const void *a, const void *b)
- {
- return pid_fry(*(pid_t *)a) - pid_fry(*(pid_t *)b);
- }
- static struct cgroup_pidlist *cgroup_pidlist_find(struct cgroup *cgrp,
- enum cgroup_filetype type)
- {
- struct cgroup_pidlist *l;
-
- struct pid_namespace *ns = task_active_pid_ns(current);
- lockdep_assert_held(&cgrp->pidlist_mutex);
- list_for_each_entry(l, &cgrp->pidlists, links)
- if (l->key.type == type && l->key.ns == ns)
- return l;
- return NULL;
- }
- static struct cgroup_pidlist *cgroup_pidlist_find_create(struct cgroup *cgrp,
- enum cgroup_filetype type)
- {
- struct cgroup_pidlist *l;
- lockdep_assert_held(&cgrp->pidlist_mutex);
- l = cgroup_pidlist_find(cgrp, type);
- if (l)
- return l;
-
- l = kzalloc(sizeof(struct cgroup_pidlist), GFP_KERNEL);
- if (!l)
- return l;
- INIT_DELAYED_WORK(&l->destroy_dwork, cgroup_pidlist_destroy_work_fn);
- l->key.type = type;
-
- l->key.ns = get_pid_ns(task_active_pid_ns(current));
- l->owner = cgrp;
- list_add(&l->links, &cgrp->pidlists);
- return l;
- }
- static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type,
- struct cgroup_pidlist **lp)
- {
- pid_t *array;
- int length;
- int pid, n = 0;
- struct css_task_iter it;
- struct task_struct *tsk;
- struct cgroup_pidlist *l;
- lockdep_assert_held(&cgrp->pidlist_mutex);
-
- length = cgroup_task_count(cgrp);
- array = pidlist_allocate(length);
- if (!array)
- return -ENOMEM;
-
- css_task_iter_start(&cgrp->self, &it);
- while ((tsk = css_task_iter_next(&it))) {
- if (unlikely(n == length))
- break;
-
- if (type == CGROUP_FILE_PROCS)
- pid = task_tgid_vnr(tsk);
- else
- pid = task_pid_vnr(tsk);
- if (pid > 0)
- array[n++] = pid;
- }
- css_task_iter_end(&it);
- length = n;
-
- if (cgroup_on_dfl(cgrp))
- sort(array, length, sizeof(pid_t), fried_cmppid, NULL);
- else
- sort(array, length, sizeof(pid_t), cmppid, NULL);
- if (type == CGROUP_FILE_PROCS)
- length = pidlist_uniq(array, length);
- l = cgroup_pidlist_find_create(cgrp, type);
- if (!l) {
- pidlist_free(array);
- return -ENOMEM;
- }
-
- pidlist_free(l->list);
- l->list = array;
- l->length = length;
- *lp = l;
- return 0;
- }
- int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry)
- {
- struct kernfs_node *kn = kernfs_node_from_dentry(dentry);
- struct cgroup *cgrp;
- struct css_task_iter it;
- struct task_struct *tsk;
-
- if (dentry->d_sb->s_type != &cgroup_fs_type || !kn ||
- kernfs_type(kn) != KERNFS_DIR)
- return -EINVAL;
- mutex_lock(&cgroup_mutex);
-
- rcu_read_lock();
- cgrp = rcu_dereference(kn->priv);
- if (!cgrp || cgroup_is_dead(cgrp)) {
- rcu_read_unlock();
- mutex_unlock(&cgroup_mutex);
- return -ENOENT;
- }
- rcu_read_unlock();
- css_task_iter_start(&cgrp->self, &it);
- while ((tsk = css_task_iter_next(&it))) {
- switch (tsk->state) {
- case TASK_RUNNING:
- stats->nr_running++;
- break;
- case TASK_INTERRUPTIBLE:
- stats->nr_sleeping++;
- break;
- case TASK_UNINTERRUPTIBLE:
- stats->nr_uninterruptible++;
- break;
- case TASK_STOPPED:
- stats->nr_stopped++;
- break;
- default:
- if (delayacct_is_task_waiting_on_io(tsk))
- stats->nr_io_wait++;
- break;
- }
- }
- css_task_iter_end(&it);
- mutex_unlock(&cgroup_mutex);
- return 0;
- }
- static void *cgroup_pidlist_start(struct seq_file *s, loff_t *pos)
- {
-
- struct kernfs_open_file *of = s->private;
- struct cgroup *cgrp = seq_css(s)->cgroup;
- struct cgroup_pidlist *l;
- enum cgroup_filetype type = seq_cft(s)->private;
- int index = 0, pid = *pos;
- int *iter, ret;
- mutex_lock(&cgrp->pidlist_mutex);
-
- if (of->priv)
- of->priv = cgroup_pidlist_find(cgrp, type);
-
- if (!of->priv) {
- ret = pidlist_array_load(cgrp, type,
- (struct cgroup_pidlist **)&of->priv);
- if (ret)
- return ERR_PTR(ret);
- }
- l = of->priv;
- if (pid) {
- int end = l->length;
- while (index < end) {
- int mid = (index + end) / 2;
- if (cgroup_pid_fry(cgrp, l->list[mid]) == pid) {
- index = mid;
- break;
- } else if (cgroup_pid_fry(cgrp, l->list[mid]) <= pid)
- index = mid + 1;
- else
- end = mid;
- }
- }
-
- if (index >= l->length)
- return NULL;
-
- iter = l->list + index;
- *pos = cgroup_pid_fry(cgrp, *iter);
- return iter;
- }
- static void cgroup_pidlist_stop(struct seq_file *s, void *v)
- {
- struct kernfs_open_file *of = s->private;
- struct cgroup_pidlist *l = of->priv;
- if (l)
- mod_delayed_work(cgroup_pidlist_destroy_wq, &l->destroy_dwork,
- CGROUP_PIDLIST_DESTROY_DELAY);
- mutex_unlock(&seq_css(s)->cgroup->pidlist_mutex);
- }
- static void *cgroup_pidlist_next(struct seq_file *s, void *v, loff_t *pos)
- {
- struct kernfs_open_file *of = s->private;
- struct cgroup_pidlist *l = of->priv;
- pid_t *p = v;
- pid_t *end = l->list + l->length;
-
- p++;
- if (p >= end) {
- return NULL;
- } else {
- *pos = cgroup_pid_fry(seq_css(s)->cgroup, *p);
- return p;
- }
- }
- static int cgroup_pidlist_show(struct seq_file *s, void *v)
- {
- seq_printf(s, "%d\n", *(int *)v);
- return 0;
- }
- static u64 cgroup_read_notify_on_release(struct cgroup_subsys_state *css,
- struct cftype *cft)
- {
- return notify_on_release(css->cgroup);
- }
- static int cgroup_write_notify_on_release(struct cgroup_subsys_state *css,
- struct cftype *cft, u64 val)
- {
- if (val)
- set_bit(CGRP_NOTIFY_ON_RELEASE, &css->cgroup->flags);
- else
- clear_bit(CGRP_NOTIFY_ON_RELEASE, &css->cgroup->flags);
- return 0;
- }
- static u64 cgroup_clone_children_read(struct cgroup_subsys_state *css,
- struct cftype *cft)
- {
- return test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags);
- }
- static int cgroup_clone_children_write(struct cgroup_subsys_state *css,
- struct cftype *cft, u64 val)
- {
- if (val)
- set_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags);
- else
- clear_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags);
- return 0;
- }
- static struct cftype cgroup_dfl_base_files[] = {
- {
- .name = "cgroup.procs",
- .file_offset = offsetof(struct cgroup, procs_file),
- .seq_start = cgroup_pidlist_start,
- .seq_next = cgroup_pidlist_next,
- .seq_stop = cgroup_pidlist_stop,
- .seq_show = cgroup_pidlist_show,
- .private = CGROUP_FILE_PROCS,
- .write = cgroup_procs_write,
- },
- {
- .name = "cgroup.controllers",
- .seq_show = cgroup_controllers_show,
- },
- {
- .name = "cgroup.subtree_control",
- .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,
- },
- { }
- };
- static struct cftype cgroup_legacy_base_files[] = {
- {
- .name = "cgroup.procs",
- .seq_start = cgroup_pidlist_start,
- .seq_next = cgroup_pidlist_next,
- .seq_stop = cgroup_pidlist_stop,
- .seq_show = cgroup_pidlist_show,
- .private = CGROUP_FILE_PROCS,
- .write = cgroup_procs_write,
- },
- {
- .name = "cgroup.clone_children",
- .read_u64 = cgroup_clone_children_read,
- .write_u64 = cgroup_clone_children_write,
- },
- {
- .name = "cgroup.sane_behavior",
- .flags = CFTYPE_ONLY_ON_ROOT,
- .seq_show = cgroup_sane_behavior_show,
- },
- {
- .name = "tasks",
- .seq_start = cgroup_pidlist_start,
- .seq_next = cgroup_pidlist_next,
- .seq_stop = cgroup_pidlist_stop,
- .seq_show = cgroup_pidlist_show,
- .private = CGROUP_FILE_TASKS,
- .write = cgroup_tasks_write,
- },
- {
- .name = "notify_on_release",
- .read_u64 = cgroup_read_notify_on_release,
- .write_u64 = cgroup_write_notify_on_release,
- },
- {
- .name = "release_agent",
- .flags = CFTYPE_ONLY_ON_ROOT,
- .seq_show = cgroup_release_agent_show,
- .write = cgroup_release_agent_write,
- .max_write_len = PATH_MAX - 1,
- },
- { }
- };
- static void css_free_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;
- percpu_ref_exit(&css->refcnt);
- if (ss) {
-
- 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 {
-
- atomic_dec(&cgrp->root->nr_cgrps);
- cgroup_pidlist_destroy_all(cgrp);
- cancel_work_sync(&cgrp->release_agent_work);
- if (cgroup_parent(cgrp)) {
-
- cgroup_put(cgroup_parent(cgrp));
- kernfs_put(cgrp->kn);
- kfree(cgrp);
- } else {
-
- cgroup_destroy_root(cgrp->root);
- }
- }
- }
- static void css_free_rcu_fn(struct rcu_head *rcu_head)
- {
- struct cgroup_subsys_state *css =
- container_of(rcu_head, struct cgroup_subsys_state, rcu_head);
- INIT_WORK(&css->destroy_work, css_free_work_fn);
- queue_work(cgroup_destroy_wq, &css->destroy_work);
- }
- 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;
- mutex_lock(&cgroup_mutex);
- css->flags |= CSS_RELEASED;
- list_del_rcu(&css->sibling);
- if (ss) {
-
- cgroup_idr_replace(&ss->css_idr, NULL, css->id);
- if (ss->css_released)
- ss->css_released(css);
- } else {
-
- trace_cgroup_release(cgrp);
- cgroup_idr_remove(&cgrp->root->cgroup_idr, cgrp->id);
- cgrp->id = -1;
-
- if (cgrp->kn)
- RCU_INIT_POINTER(*(void __rcu __force **)&cgrp->kn->priv,
- NULL);
- }
- mutex_unlock(&cgroup_mutex);
- call_rcu(&css->rcu_head, css_free_rcu_fn);
- }
- 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_destroy_wq, &css->destroy_work);
- }
- 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(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);
- 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));
- }
- 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);
- }
- return ret;
- }
- static void offline_css(struct cgroup_subsys_state *css)
- {
- struct cgroup_subsys *ss = css->ss;
- lockdep_assert_held(&cgroup_mutex);
- if (!(css->flags & CSS_ONLINE))
- return;
- if (ss->css_reset)
- ss->css_reset(css);
- 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);
- }
- 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;
-
- 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;
- if (ss->broken_hierarchy && !ss->warned_broken_hierarchy &&
- cgroup_parent(parent)) {
- pr_warn("%s (%d) created nested cgroup for controller \"%s\" which has incomplete hierarchy support. Nested cgroups may change behavior in the future.\n",
- current->comm, current->pid, ss->name);
- if (!strcmp(ss->name, "memory"))
- pr_warn("\"memory\" requires setting use_hierarchy to 1 on the root\n");
- ss->warned_broken_hierarchy = true;
- }
- return css;
- err_list_del:
- list_del_rcu(&css->sibling);
- err_free_css:
- call_rcu(&css->rcu_head, css_free_rcu_fn);
- return ERR_PTR(err);
- }
- static struct cgroup *cgroup_create(struct cgroup *parent)
- {
- struct cgroup_root *root = parent->root;
- struct cgroup *cgrp, *tcgrp;
- int level = parent->level + 1;
- int ret;
-
- cgrp = kzalloc(sizeof(*cgrp) +
- sizeof(cgrp->ancestor_ids[0]) * (level + 1), GFP_KERNEL);
- if (!cgrp)
- return ERR_PTR(-ENOMEM);
- ret = percpu_ref_init(&cgrp->self.refcnt, css_release, 0, GFP_KERNEL);
- if (ret)
- goto out_free_cgrp;
-
- cgrp->id = cgroup_idr_alloc(&root->cgroup_idr, NULL, 2, 0, GFP_KERNEL);
- if (cgrp->id < 0) {
- ret = -ENOMEM;
- goto out_cancel_ref;
- }
- init_cgroup_housekeeping(cgrp);
- cgrp->self.parent = &parent->self;
- cgrp->root = root;
- cgrp->level = level;
- for (tcgrp = cgrp; tcgrp; tcgrp = cgroup_parent(tcgrp))
- cgrp->ancestor_ids[tcgrp->level] = tcgrp->id;
- 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++;
-
- list_add_tail_rcu(&cgrp->self.sibling, &cgroup_parent(cgrp)->self.children);
- atomic_inc(&root->nr_cgrps);
- cgroup_get(parent);
-
- cgroup_idr_replace(&root->cgroup_idr, cgrp, cgrp->id);
-
- if (!cgroup_on_dfl(cgrp))
- cgrp->subtree_control = cgroup_control(cgrp);
- cgroup_propagate_control(cgrp);
- return cgrp;
- out_cancel_ref:
- percpu_ref_exit(&cgrp->self.refcnt);
- out_free_cgrp:
- kfree(cgrp);
- return ERR_PTR(ret);
- }
- static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
- umode_t mode)
- {
- struct cgroup *parent, *cgrp;
- struct kernfs_node *kn;
- int ret;
-
- if (strchr(name, '\n'))
- return -EINVAL;
- parent = cgroup_kn_lock_live(parent_kn, false);
- if (!parent)
- return -ENODEV;
- cgrp = cgroup_create(parent);
- if (IS_ERR(cgrp)) {
- ret = PTR_ERR(cgrp);
- goto out_unlock;
- }
-
- kn = kernfs_create_dir(parent->kn, name, mode, cgrp);
- if (IS_ERR(kn)) {
- ret = PTR_ERR(kn);
- goto out_destroy;
- }
- cgrp->kn = kn;
-
- kernfs_get(kn);
- ret = cgroup_kn_set_ugid(kn);
- if (ret)
- goto out_destroy;
- ret = css_populate_dir(&cgrp->self);
- if (ret)
- goto out_destroy;
- ret = cgroup_apply_control_enable(cgrp);
- if (ret)
- goto out_destroy;
- trace_cgroup_mkdir(cgrp);
-
- kernfs_activate(kn);
- ret = 0;
- goto out_unlock;
- out_destroy:
- cgroup_destroy_locked(cgrp);
- out_unlock:
- cgroup_kn_unlock(parent_kn);
- return ret;
- }
- static void css_killed_work_fn(struct work_struct *work)
- {
- struct cgroup_subsys_state *css =
- container_of(work, struct cgroup_subsys_state, destroy_work);
- mutex_lock(&cgroup_mutex);
- do {
- offline_css(css);
- css_put(css);
-
- css = css->parent;
- } while (css && atomic_dec_and_test(&css->online_cnt));
- mutex_unlock(&cgroup_mutex);
- }
- 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_WORK(&css->destroy_work, css_killed_work_fn);
- queue_work(cgroup_destroy_wq, &css->destroy_work);
- }
- }
- static void kill_css(struct cgroup_subsys_state *css)
- {
- lockdep_assert_held(&cgroup_mutex);
- if (css->flags & CSS_DYING)
- return;
- css->flags |= CSS_DYING;
-
- css_clear_dir(css);
-
- css_get(css);
-
- percpu_ref_kill_and_confirm(&css->refcnt, css_killed_ref_fn);
- }
- static int cgroup_destroy_locked(struct cgroup *cgrp)
- __releases(&cgroup_mutex) __acquires(&cgroup_mutex)
- {
- struct cgroup_subsys_state *css;
- struct cgrp_cset_link *link;
- int ssid;
- lockdep_assert_held(&cgroup_mutex);
-
- if (cgroup_is_populated(cgrp))
- return -EBUSY;
-
- if (css_has_online_children(&cgrp->self))
- return -EBUSY;
-
- 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(css);
-
- kernfs_remove(cgrp->kn);
- check_for_release(cgroup_parent(cgrp));
-
- percpu_ref_kill(&cgrp->self.refcnt);
- return 0;
- };
- static 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_rmdir(cgrp);
- cgroup_kn_unlock(kn);
- return ret;
- }
- static struct kernfs_syscall_ops cgroup_kf_syscall_ops = {
- .remount_fs = cgroup_remount,
- .show_options = cgroup_show_options,
- .mkdir = cgroup_mkdir,
- .rmdir = cgroup_rmdir,
- .rename = cgroup_rename,
- .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);
- mutex_lock(&cgroup_mutex);
- idr_init(&ss->css_idr);
- INIT_LIST_HEAD(&ss->cfts);
-
- ss->root = &cgrp_dfl_root;
- css = ss->css_alloc(cgroup_css(&cgrp_dfl_root.cgrp, ss));
-
- BUG_ON(IS_ERR(css));
- init_and_link_css(css, ss, &cgrp_dfl_root.cgrp);
-
- css->flags |= CSS_NO_REF;
- if (early) {
-
- css->id = 1;
- } else {
- css->id = cgroup_idr_alloc(&ss->css_idr, css, 1, 2, GFP_KERNEL);
- BUG_ON(css->id < 0);
- }
-
- init_css_set.subsys[ss->id] = css;
- have_fork_callback |= (bool)ss->fork << ss->id;
- have_exit_callback |= (bool)ss->exit << ss->id;
- have_free_callback |= (bool)ss->free << ss->id;
- have_canfork_callback |= (bool)ss->can_fork << ss->id;
-
- BUG_ON(!list_empty(&init_task.tasks));
- BUG_ON(online_css(css));
- mutex_unlock(&cgroup_mutex);
- }
- int __init cgroup_init_early(void)
- {
- static struct cgroup_sb_opts __initdata opts;
- struct cgroup_subsys *ss;
- int i;
- init_cgroup_root(&cgrp_dfl_root, &opts);
- 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]);
- 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;
- }
- static u16 cgroup_disable_mask __initdata;
- int __init cgroup_init(void)
- {
- struct cgroup_subsys *ss;
- int ssid;
- BUILD_BUG_ON(CGROUP_SUBSYS_COUNT > 16);
- BUG_ON(percpu_init_rwsem(&cgroup_threadgroup_rwsem));
- BUG_ON(cgroup_init_cftypes(NULL, cgroup_dfl_base_files));
- BUG_ON(cgroup_init_cftypes(NULL, cgroup_legacy_base_files));
-
- rcu_sync_enter_start(&cgroup_threadgroup_rwsem.rss);
- get_user_ns(init_cgroup_ns.user_ns);
- mutex_lock(&cgroup_mutex);
-
- hash_add(css_set_table, &init_css_set.hlist,
- css_set_hash(init_css_set.subsys));
- BUG_ON(cgroup_setup_root(&cgrp_dfl_root, 0));
- mutex_unlock(&cgroup_mutex);
- 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]);
-
- if (cgroup_disable_mask & (1 << ssid)) {
- static_branch_disable(cgroup_subsys_enabled_key[ssid]);
- printk(KERN_INFO "Disabling %s control group subsystem\n",
- ss->name);
- continue;
- }
- if (cgroup_ssid_no_v1(ssid))
- printk(KERN_INFO "Disabling %s control group subsystem in v1 mounts\n",
- ss->name);
- cgrp_dfl_root.subsys_mask |= 1 << ss->id;
- 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->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]);
- mutex_lock(&cgroup_mutex);
- css_populate_dir(init_css_set.subsys[ssid]);
- mutex_unlock(&cgroup_mutex);
- }
-
- 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("cgroups", 0, NULL, &proc_cgroupstats_operations));
- return 0;
- }
- static int __init cgroup_wq_init(void)
- {
-
- cgroup_destroy_wq = alloc_workqueue("cgroup_destroy", 0, 1);
- BUG_ON(!cgroup_destroy_wq);
-
- cgroup_pidlist_destroy_wq = alloc_workqueue("cgroup_pidlist_destroy",
- 0, 1);
- BUG_ON(!cgroup_pidlist_destroy_wq);
- return 0;
- }
- core_initcall(cgroup_wq_init);
- 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;
- mutex_lock(&cgroup_mutex);
- 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 && !cgrp_dfl_visible)
- 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, ':');
- cgrp = task_cgroup_from_root(tsk, root);
-
- if (cgroup_on_dfl(cgrp) || !(tsk->flags & PF_EXITING)) {
- retval = cgroup_path_ns_locked(cgrp, buf, PATH_MAX,
- current->nsproxy->cgroup_ns);
- if (retval >= PATH_MAX)
- 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);
- mutex_unlock(&cgroup_mutex);
- kfree(buf);
- out:
- return retval;
- }
- static int proc_cgroupstats_show(struct seq_file *m, void *v)
- {
- struct cgroup_subsys *ss;
- int i;
- seq_puts(m, "#subsys_name\thierarchy\tnum_cgroups\tenabled\n");
-
- mutex_lock(&cgroup_mutex);
- for_each_subsys(ss, i)
- seq_printf(m, "%s\t%d\t%d\t%d\n",
- ss->legacy_name, ss->root->hierarchy_id,
- atomic_read(&ss->root->nr_cgrps),
- cgroup_ssid_enabled(i));
- mutex_unlock(&cgroup_mutex);
- return 0;
- }
- static int cgroupstats_open(struct inode *inode, struct file *file)
- {
- return single_open(file, proc_cgroupstats_show, NULL);
- }
- static const struct file_operations proc_cgroupstats_operations = {
- .open = cgroupstats_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
- };
- void cgroup_fork(struct task_struct *child)
- {
- RCU_INIT_POINTER(child->cgroups, &init_css_set);
- INIT_LIST_HEAD(&child->cg_list);
- }
- int cgroup_can_fork(struct task_struct *child)
- {
- struct cgroup_subsys *ss;
- int i, j, ret;
- do_each_subsys_mask(ss, i, have_canfork_callback) {
- ret = ss->can_fork(child);
- 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);
- }
- return ret;
- }
- void cgroup_cancel_fork(struct task_struct *child)
- {
- struct cgroup_subsys *ss;
- int i;
- for_each_subsys(ss, i)
- if (ss->cancel_fork)
- ss->cancel_fork(child);
- }
- void cgroup_post_fork(struct task_struct *child)
- {
- struct cgroup_subsys *ss;
- int i;
-
- if (use_task_css_set_links) {
- struct css_set *cset;
- spin_lock_irq(&css_set_lock);
- cset = task_css_set(current);
- if (list_empty(&child->cg_list)) {
- get_css_set(cset);
- css_set_move_task(child, NULL, cset, false);
- }
- spin_unlock_irq(&css_set_lock);
- }
-
- do_each_subsys_mask(ss, i, have_fork_callback) {
- ss->fork(child);
- } while_each_subsys_mask();
- }
- void cgroup_exit(struct task_struct *tsk)
- {
- struct cgroup_subsys *ss;
- struct css_set *cset;
- int i;
-
- cset = task_css_set(tsk);
- if (!list_empty(&tsk->cg_list)) {
- spin_lock_irq(&css_set_lock);
- css_set_move_task(tsk, cset, NULL, false);
- spin_unlock_irq(&css_set_lock);
- } else {
- get_css_set(cset);
- }
-
- do_each_subsys_mask(ss, i, have_exit_callback) {
- ss->exit(tsk);
- } while_each_subsys_mask();
- }
- void cgroup_free(struct task_struct *task)
- {
- struct css_set *cset = task_css_set(task);
- struct cgroup_subsys *ss;
- int ssid;
- do_each_subsys_mask(ss, ssid, have_free_callback) {
- ss->free(task);
- } while_each_subsys_mask();
- put_css_set(cset);
- }
- static void check_for_release(struct cgroup *cgrp)
- {
- if (notify_on_release(cgrp) && !cgroup_is_populated(cgrp) &&
- !css_has_online_children(&cgrp->self) && !cgroup_is_dead(cgrp))
- schedule_work(&cgrp->release_agent_work);
- }
- static void cgroup_release_agent(struct work_struct *work)
- {
- struct cgroup *cgrp =
- container_of(work, struct cgroup, release_agent_work);
- char *pathbuf = NULL, *agentbuf = NULL;
- char *argv[3], *envp[3];
- int ret;
- mutex_lock(&cgroup_mutex);
- pathbuf = kmalloc(PATH_MAX, GFP_KERNEL);
- agentbuf = kstrdup(cgrp->root->release_agent_path, GFP_KERNEL);
- if (!pathbuf || !agentbuf)
- goto out;
- spin_lock_irq(&css_set_lock);
- ret = cgroup_path_ns_locked(cgrp, pathbuf, PATH_MAX, &init_cgroup_ns);
- spin_unlock_irq(&css_set_lock);
- if (ret < 0 || ret >= PATH_MAX)
- goto out;
- argv[0] = agentbuf;
- argv[1] = pathbuf;
- argv[2] = NULL;
-
- envp[0] = "HOME=/";
- envp[1] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin";
- envp[2] = NULL;
- mutex_unlock(&cgroup_mutex);
- call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC);
- goto out_free;
- out:
- mutex_unlock(&cgroup_mutex);
- out_free:
- kfree(agentbuf);
- kfree(pathbuf);
- }
- 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;
- cgroup_disable_mask |= 1 << i;
- }
- }
- return 1;
- }
- __setup("cgroup_disable=", cgroup_disable);
- static int __init cgroup_no_v1(char *str)
- {
- struct cgroup_subsys *ss;
- char *token;
- int i;
- while ((token = strsep(&str, ",")) != NULL) {
- if (!*token)
- continue;
- if (!strcmp(token, "all")) {
- cgroup_no_v1_mask = U16_MAX;
- break;
- }
- for_each_subsys(ss, i) {
- if (strcmp(token, ss->name) &&
- strcmp(token, ss->legacy_name))
- continue;
- cgroup_no_v1_mask |= 1 << i;
- }
- }
- return 1;
- }
- __setup("cgroup_no_v1=", cgroup_no_v1);
- 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;
-
- if ((s_type != &cgroup_fs_type && s_type != &cgroup2_fs_type) ||
- !kn || kernfs_type(kn) != KERNFS_DIR)
- return ERR_PTR(-EBADF);
- rcu_read_lock();
-
- cgrp = rcu_dereference(kn->priv);
- if (cgrp)
- css = cgroup_css(cgrp, ss);
- if (!css || !css_tryget_online(css))
- css = ERR_PTR(-ENOENT);
- rcu_read_unlock();
- return css;
- }
- 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);
- }
- struct cgroup *cgroup_get_from_path(const char *path)
- {
- struct kernfs_node *kn;
- struct cgroup *cgrp;
- mutex_lock(&cgroup_mutex);
- kn = kernfs_walk_and_get(cgrp_dfl_root.cgrp.kn, path);
- if (kn) {
- if (kernfs_type(kn) == KERNFS_DIR) {
- cgrp = kn->priv;
- cgroup_get(cgrp);
- } else {
- cgrp = ERR_PTR(-ENOTDIR);
- }
- kernfs_put(kn);
- } else {
- cgrp = ERR_PTR(-ENOENT);
- }
- mutex_unlock(&cgroup_mutex);
- return cgrp;
- }
- EXPORT_SYMBOL_GPL(cgroup_get_from_path);
- struct cgroup *cgroup_get_from_fd(int fd)
- {
- struct cgroup_subsys_state *css;
- struct cgroup *cgrp;
- struct file *f;
- f = fget_raw(fd);
- if (!f)
- return ERR_PTR(-EBADF);
- css = css_tryget_online_from_dir(f->f_path.dentry, NULL);
- fput(f);
- if (IS_ERR(css))
- return ERR_CAST(css);
- cgrp = css->cgroup;
- if (!cgroup_on_dfl(cgrp)) {
- cgroup_put(cgrp);
- return ERR_PTR(-EBADF);
- }
- return cgrp;
- }
- EXPORT_SYMBOL_GPL(cgroup_get_from_fd);
- #ifdef CONFIG_SOCK_CGROUP_DATA
- #if defined(CONFIG_CGROUP_NET_PRIO) || defined(CONFIG_CGROUP_NET_CLASSID)
- DEFINE_SPINLOCK(cgroup_sk_update_lock);
- static bool cgroup_sk_alloc_disabled __read_mostly;
- void cgroup_sk_alloc_disable(void)
- {
- if (cgroup_sk_alloc_disabled)
- return;
- pr_info("cgroup: disabling cgroup2 socket matching due to net_prio or net_cls activation\n");
- cgroup_sk_alloc_disabled = true;
- }
- #else
- #define cgroup_sk_alloc_disabled false
- #endif
- void cgroup_sk_alloc(struct sock_cgroup_data *skcd)
- {
- if (cgroup_sk_alloc_disabled)
- return;
-
- if (skcd->val) {
- cgroup_get(sock_cgroup_ptr(skcd));
- return;
- }
- rcu_read_lock();
- while (true) {
- struct css_set *cset;
- cset = task_css_set(current);
- if (likely(cgroup_tryget(cset->dfl_cgrp))) {
- skcd->val = (unsigned long)cset->dfl_cgrp;
- break;
- }
- cpu_relax();
- }
- rcu_read_unlock();
- }
- void cgroup_sk_free(struct sock_cgroup_data *skcd)
- {
- cgroup_put(sock_cgroup_ptr(skcd));
- }
- #endif
- static struct ucounts *inc_cgroup_namespaces(struct user_namespace *ns)
- {
- return inc_ucount(ns, current_euid(), UCOUNT_CGROUP_NAMESPACES);
- }
- static void dec_cgroup_namespaces(struct ucounts *ucounts)
- {
- dec_ucount(ucounts, UCOUNT_CGROUP_NAMESPACES);
- }
- static struct cgroup_namespace *alloc_cgroup_ns(void)
- {
- struct cgroup_namespace *new_ns;
- int ret;
- new_ns = kzalloc(sizeof(struct cgroup_namespace), GFP_KERNEL);
- if (!new_ns)
- return ERR_PTR(-ENOMEM);
- ret = ns_alloc_inum(&new_ns->ns);
- if (ret) {
- kfree(new_ns);
- return ERR_PTR(ret);
- }
- atomic_set(&new_ns->count, 1);
- new_ns->ns.ops = &cgroupns_operations;
- return new_ns;
- }
- void free_cgroup_ns(struct cgroup_namespace *ns)
- {
- put_css_set(ns->root_cset);
- dec_cgroup_namespaces(ns->ucounts);
- put_user_ns(ns->user_ns);
- ns_free_inum(&ns->ns);
- kfree(ns);
- }
- EXPORT_SYMBOL(free_cgroup_ns);
- struct cgroup_namespace *copy_cgroup_ns(unsigned long flags,
- struct user_namespace *user_ns,
- struct cgroup_namespace *old_ns)
- {
- struct cgroup_namespace *new_ns;
- struct ucounts *ucounts;
- struct css_set *cset;
- BUG_ON(!old_ns);
- if (!(flags & CLONE_NEWCGROUP)) {
- get_cgroup_ns(old_ns);
- return old_ns;
- }
-
- if (!ns_capable(user_ns, CAP_SYS_ADMIN))
- return ERR_PTR(-EPERM);
- ucounts = inc_cgroup_namespaces(user_ns);
- if (!ucounts)
- return ERR_PTR(-ENOSPC);
-
- spin_lock_irq(&css_set_lock);
- cset = task_css_set(current);
- get_css_set(cset);
- spin_unlock_irq(&css_set_lock);
- new_ns = alloc_cgroup_ns();
- if (IS_ERR(new_ns)) {
- put_css_set(cset);
- dec_cgroup_namespaces(ucounts);
- return new_ns;
- }
- new_ns->user_ns = get_user_ns(user_ns);
- new_ns->ucounts = ucounts;
- new_ns->root_cset = cset;
- return new_ns;
- }
- static inline struct cgroup_namespace *to_cg_ns(struct ns_common *ns)
- {
- return container_of(ns, struct cgroup_namespace, ns);
- }
- static int cgroupns_install(struct nsproxy *nsproxy, struct ns_common *ns)
- {
- struct cgroup_namespace *cgroup_ns = to_cg_ns(ns);
- if (!ns_capable(current_user_ns(), CAP_SYS_ADMIN) ||
- !ns_capable(cgroup_ns->user_ns, CAP_SYS_ADMIN))
- return -EPERM;
-
- if (cgroup_ns == nsproxy->cgroup_ns)
- return 0;
- get_cgroup_ns(cgroup_ns);
- put_cgroup_ns(nsproxy->cgroup_ns);
- nsproxy->cgroup_ns = cgroup_ns;
- return 0;
- }
- static struct ns_common *cgroupns_get(struct task_struct *task)
- {
- struct cgroup_namespace *ns = NULL;
- struct nsproxy *nsproxy;
- task_lock(task);
- nsproxy = task->nsproxy;
- if (nsproxy) {
- ns = nsproxy->cgroup_ns;
- get_cgroup_ns(ns);
- }
- task_unlock(task);
- return ns ? &ns->ns : NULL;
- }
- static void cgroupns_put(struct ns_common *ns)
- {
- put_cgroup_ns(to_cg_ns(ns));
- }
- static struct user_namespace *cgroupns_owner(struct ns_common *ns)
- {
- return to_cg_ns(ns)->user_ns;
- }
- const struct proc_ns_operations cgroupns_operations = {
- .name = "cgroup",
- .type = CLONE_NEWCGROUP,
- .get = cgroupns_get,
- .put = cgroupns_put,
- .install = cgroupns_install,
- .owner = cgroupns_owner,
- };
- static __init int cgroup_namespaces_init(void)
- {
- return 0;
- }
- subsys_initcall(cgroup_namespaces_init);
- #ifdef CONFIG_CGROUP_DEBUG
- static struct cgroup_subsys_state *
- debug_css_alloc(struct cgroup_subsys_state *parent_css)
- {
- struct cgroup_subsys_state *css = kzalloc(sizeof(*css), GFP_KERNEL);
- if (!css)
- return ERR_PTR(-ENOMEM);
- return css;
- }
- static void debug_css_free(struct cgroup_subsys_state *css)
- {
- kfree(css);
- }
- static u64 debug_taskcount_read(struct cgroup_subsys_state *css,
- struct cftype *cft)
- {
- return cgroup_task_count(css->cgroup);
- }
- static u64 current_css_set_read(struct cgroup_subsys_state *css,
- struct cftype *cft)
- {
- return (u64)(unsigned long)current->cgroups;
- }
- static u64 current_css_set_refcount_read(struct cgroup_subsys_state *css,
- struct cftype *cft)
- {
- u64 count;
- rcu_read_lock();
- count = atomic_read(&task_css_set(current)->refcount);
- rcu_read_unlock();
- return count;
- }
- static int current_css_set_cg_links_read(struct seq_file *seq, void *v)
- {
- struct cgrp_cset_link *link;
- struct css_set *cset;
- char *name_buf;
- name_buf = kmalloc(NAME_MAX + 1, GFP_KERNEL);
- if (!name_buf)
- return -ENOMEM;
- spin_lock_irq(&css_set_lock);
- rcu_read_lock();
- cset = rcu_dereference(current->cgroups);
- list_for_each_entry(link, &cset->cgrp_links, cgrp_link) {
- struct cgroup *c = link->cgrp;
- cgroup_name(c, name_buf, NAME_MAX + 1);
- seq_printf(seq, "Root %d group %s\n",
- c->root->hierarchy_id, name_buf);
- }
- rcu_read_unlock();
- spin_unlock_irq(&css_set_lock);
- kfree(name_buf);
- return 0;
- }
- #define MAX_TASKS_SHOWN_PER_CSS 25
- static int cgroup_css_links_read(struct seq_file *seq, void *v)
- {
- struct cgroup_subsys_state *css = seq_css(seq);
- struct cgrp_cset_link *link;
- spin_lock_irq(&css_set_lock);
- list_for_each_entry(link, &css->cgroup->cset_links, cset_link) {
- struct css_set *cset = link->cset;
- struct task_struct *task;
- int count = 0;
- seq_printf(seq, "css_set %p\n", cset);
- list_for_each_entry(task, &cset->tasks, cg_list) {
- if (count++ > MAX_TASKS_SHOWN_PER_CSS)
- goto overflow;
- seq_printf(seq, " task %d\n", task_pid_vnr(task));
- }
- list_for_each_entry(task, &cset->mg_tasks, cg_list) {
- if (count++ > MAX_TASKS_SHOWN_PER_CSS)
- goto overflow;
- seq_printf(seq, " task %d\n", task_pid_vnr(task));
- }
- continue;
- overflow:
- seq_puts(seq, " ...\n");
- }
- spin_unlock_irq(&css_set_lock);
- return 0;
- }
- static u64 releasable_read(struct cgroup_subsys_state *css, struct cftype *cft)
- {
- return (!cgroup_is_populated(css->cgroup) &&
- !css_has_online_children(&css->cgroup->self));
- }
- static struct cftype debug_files[] = {
- {
- .name = "taskcount",
- .read_u64 = debug_taskcount_read,
- },
- {
- .name = "current_css_set",
- .read_u64 = current_css_set_read,
- },
- {
- .name = "current_css_set_refcount",
- .read_u64 = current_css_set_refcount_read,
- },
- {
- .name = "current_css_set_cg_links",
- .seq_show = current_css_set_cg_links_read,
- },
- {
- .name = "cgroup_css_links",
- .seq_show = cgroup_css_links_read,
- },
- {
- .name = "releasable",
- .read_u64 = releasable_read,
- },
- { }
- };
- struct cgroup_subsys debug_cgrp_subsys = {
- .css_alloc = debug_css_alloc,
- .css_free = debug_css_free,
- .legacy_cftypes = debug_files,
- };
- #endif
|