| Author | Tokens | Token Proportion | Commits | Commit Proportion |
|---|---|---|---|---|
| Pablo Neira Ayuso | 32781 | 54.98% | 388 | 54.65% |
| Patrick McHardy | 12929 | 21.68% | 53 | 7.46% |
| Florian Westphal | 4747 | 7.96% | 88 | 12.39% |
| Arturo Borrero Gonzalez | 2663 | 4.47% | 8 | 1.13% |
| Phil Sutter | 2405 | 4.03% | 37 | 5.21% |
| Fernando Fernandez Mancera | 720 | 1.21% | 4 | 0.56% |
| Richard Guy Briggs | 527 | 0.88% | 3 | 0.42% |
| Harsha Sharma | 491 | 0.82% | 1 | 0.14% |
| Stefano Brivio | 393 | 0.66% | 4 | 0.56% |
| Jose M. Guisado Gomez | 305 | 0.51% | 5 | 0.70% |
| Liping Zhang | 136 | 0.23% | 6 | 0.85% |
| Laura Garcia Liebana | 122 | 0.20% | 3 | 0.42% |
| Taehee Yoo | 121 | 0.20% | 7 | 0.99% |
| Eric Leblond | 101 | 0.17% | 2 | 0.28% |
| Carlos Falgueras García | 97 | 0.16% | 1 | 0.14% |
| Linus Torvalds (pre-git) | 84 | 0.14% | 4 | 0.56% |
| Pablo M. Bermudo Garay | 73 | 0.12% | 1 | 0.14% |
| Vasily Averin | 70 | 0.12% | 3 | 0.42% |
| Thadeu Lima de Souza Cascardo | 70 | 0.12% | 4 | 0.56% |
| Gao Feng | 68 | 0.11% | 3 | 0.42% |
| Dongliang Mu | 56 | 0.09% | 1 | 0.14% |
| Quan Tian | 56 | 0.09% | 1 | 0.14% |
| Johannes Berg | 54 | 0.09% | 3 | 0.42% |
| Gustavo A. R. Silva | 50 | 0.08% | 3 | 0.42% |
| Eric Dumazet | 41 | 0.07% | 5 | 0.70% |
| wenxu | 39 | 0.07% | 2 | 0.28% |
| Ziyang Xuan | 37 | 0.06% | 3 | 0.42% |
| Paul Gortmaker | 34 | 0.06% | 1 | 0.14% |
| Kazunori Miyazawa | 25 | 0.04% | 1 | 0.14% |
| Tomasz Bursztyka | 24 | 0.04% | 2 | 0.28% |
| Tetsuo Handa | 23 | 0.04% | 2 | 0.28% |
| Harald Welte | 18 | 0.03% | 3 | 0.42% |
| Felix Fietkau | 18 | 0.03% | 1 | 0.14% |
| Dan Carpenter | 17 | 0.03% | 6 | 0.85% |
| Nicolas Dichtel | 16 | 0.03% | 1 | 0.14% |
| Alexey Dobriyan | 16 | 0.03% | 3 | 0.42% |
| Michal Kubeček | 13 | 0.02% | 1 | 0.14% |
| Phil Turnbull | 12 | 0.02% | 1 | 0.14% |
| Alok Tiwari | 12 | 0.02% | 1 | 0.14% |
| Anders K. Pedersen | 11 | 0.02% | 2 | 0.28% |
| Alexey Kodanev | 10 | 0.02% | 1 | 0.14% |
| Andrew Lunn | 10 | 0.02% | 2 | 0.28% |
| Arvind Yadav | 9 | 0.02% | 1 | 0.14% |
| Saeed Mirzamohammadi | 9 | 0.02% | 1 | 0.14% |
| Jeremy Sowden | 8 | 0.01% | 1 | 0.14% |
| Gavrilov Ilia | 8 | 0.01% | 1 | 0.14% |
| Daniel Borkmann | 7 | 0.01% | 1 | 0.14% |
| Mirek Kratochvil | 7 | 0.01% | 1 | 0.14% |
| Xingyuan Mo | 6 | 0.01% | 1 | 0.14% |
| Herbert Xu | 6 | 0.01% | 2 | 0.28% |
| Thomas Graf | 6 | 0.01% | 2 | 0.28% |
| Colin Ian King | 6 | 0.01% | 2 | 0.28% |
| Paul E. McKenney | 6 | 0.01% | 1 | 0.14% |
| Thomas Gleixner | 4 | 0.01% | 2 | 0.28% |
| Máté Eckl | 4 | 0.01% | 1 | 0.14% |
| Wei Wang | 4 | 0.01% | 1 | 0.14% |
| Linus Torvalds | 4 | 0.01% | 1 | 0.14% |
| JingPiao Chen | 3 | 0.01% | 1 | 0.14% |
| Eric W. Biedermann | 3 | 0.01% | 1 | 0.14% |
| Francis Laniel | 3 | 0.01% | 1 | 0.14% |
| Andrew Morton | 3 | 0.01% | 1 | 0.14% |
| Yasuyuki Kozakai | 2 | 0.00% | 1 | 0.14% |
| Kees Cook | 2 | 0.00% | 1 | 0.14% |
| Pankaj Bharadiya | 2 | 0.00% | 1 | 0.14% |
| Jakob Koschel | 2 | 0.00% | 1 | 0.14% |
| Li RongQing | 2 | 0.00% | 1 | 0.14% |
| Fengguang Wu | 2 | 0.00% | 1 | 0.14% |
| Jason A. Donenfeld | 2 | 0.00% | 1 | 0.14% |
| Xin Long | 1 | 0.00% | 1 | 0.14% |
| Yang Yingliang | 1 | 0.00% | 1 | 0.14% |
| Wolfram Sang | 1 | 0.00% | 1 | 0.14% |
| Chen Aotian | 1 | 0.00% | 1 | 0.14% |
| Julia Lawall | 1 | 0.00% | 1 | 0.14% |
| Paul Moore | 1 | 0.00% | 1 | 0.14% |
| Qian Cai | 1 | 0.00% | 1 | 0.14% |
| Ingo Molnar | 1 | 0.00% | 1 | 0.14% |
| Wei Yongjun | 1 | 0.00% | 1 | 0.14% |
| Total | 59624 | 710 |
123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773774775776777778779780781782783784785786787788789790791792793794795796797798799800801802803804805806807808809810811812813814815816817818819820821822823824825826827828829830831832833834835836837838839840841842843844845846847848849850851852853854855856857858859860861862863864865866867868869870871872873874875876877878879880881882883884885886887888889890891892893894895896897898899900901902903904905906907908909910911912913914915916917918919920921922923924925926927928929930931932933934935936937938939940941942943944945946947948949950951952953954955956957958959960961962963964965966967968969970971972973974975976977978979980981982983984985986987988989990991992993994995996997998999100010011002100310041005100610071008100910101011101210131014101510161017101810191020102110221023102410251026102710281029103010311032103310341035103610371038103910401041104210431044104510461047104810491050105110521053105410551056105710581059106010611062106310641065106610671068106910701071107210731074107510761077107810791080108110821083108410851086108710881089109010911092109310941095109610971098109911001101110211031104110511061107110811091110111111121113111411151116111711181119112011211122112311241125112611271128112911301131113211331134113511361137113811391140114111421143114411451146114711481149115011511152115311541155115611571158115911601161116211631164116511661167116811691170117111721173117411751176117711781179118011811182118311841185118611871188118911901191119211931194119511961197119811991200120112021203120412051206120712081209121012111212121312141215121612171218121912201221122212231224122512261227122812291230123112321233123412351236123712381239124012411242124312441245124612471248124912501251125212531254125512561257125812591260126112621263126412651266126712681269127012711272127312741275127612771278127912801281128212831284128512861287128812891290129112921293129412951296129712981299130013011302130313041305130613071308130913101311131213131314131513161317131813191320132113221323132413251326132713281329133013311332133313341335133613371338133913401341134213431344134513461347134813491350135113521353135413551356135713581359136013611362136313641365136613671368136913701371137213731374137513761377137813791380138113821383138413851386138713881389139013911392139313941395139613971398139914001401140214031404140514061407140814091410141114121413141414151416141714181419142014211422142314241425142614271428142914301431143214331434143514361437143814391440144114421443144414451446144714481449145014511452145314541455145614571458145914601461146214631464146514661467146814691470147114721473147414751476147714781479148014811482148314841485148614871488148914901491149214931494149514961497149814991500150115021503150415051506150715081509151015111512151315141515151615171518151915201521152215231524152515261527152815291530153115321533153415351536153715381539154015411542154315441545154615471548154915501551155215531554155515561557155815591560156115621563156415651566156715681569157015711572157315741575157615771578157915801581158215831584158515861587158815891590159115921593159415951596159715981599160016011602160316041605160616071608160916101611161216131614161516161617161816191620162116221623162416251626162716281629163016311632163316341635163616371638163916401641164216431644164516461647164816491650165116521653165416551656165716581659166016611662166316641665166616671668166916701671167216731674167516761677167816791680168116821683168416851686168716881689169016911692169316941695169616971698169917001701170217031704170517061707170817091710171117121713171417151716171717181719172017211722172317241725172617271728172917301731173217331734173517361737173817391740174117421743174417451746174717481749175017511752175317541755175617571758175917601761176217631764176517661767176817691770177117721773177417751776177717781779178017811782178317841785178617871788178917901791179217931794179517961797179817991800180118021803180418051806180718081809181018111812181318141815181618171818181918201821182218231824182518261827182818291830183118321833183418351836183718381839184018411842184318441845184618471848184918501851185218531854185518561857185818591860186118621863186418651866186718681869187018711872187318741875187618771878187918801881188218831884188518861887188818891890189118921893189418951896189718981899190019011902190319041905190619071908190919101911191219131914191519161917191819191920192119221923192419251926192719281929193019311932193319341935193619371938193919401941194219431944194519461947194819491950195119521953195419551956195719581959196019611962196319641965196619671968196919701971197219731974197519761977197819791980198119821983198419851986198719881989199019911992199319941995199619971998199920002001200220032004200520062007200820092010201120122013201420152016201720182019202020212022202320242025202620272028202920302031203220332034203520362037203820392040204120422043204420452046204720482049205020512052205320542055205620572058205920602061206220632064206520662067206820692070207120722073207420752076207720782079208020812082208320842085208620872088208920902091209220932094209520962097209820992100210121022103210421052106210721082109211021112112211321142115211621172118211921202121212221232124212521262127212821292130213121322133213421352136213721382139214021412142214321442145214621472148214921502151215221532154215521562157215821592160216121622163216421652166216721682169217021712172217321742175217621772178217921802181218221832184218521862187218821892190219121922193219421952196219721982199220022012202220322042205220622072208220922102211221222132214221522162217221822192220222122222223222422252226222722282229223022312232223322342235223622372238223922402241224222432244224522462247224822492250225122522253225422552256225722582259226022612262226322642265226622672268226922702271227222732274227522762277227822792280228122822283228422852286228722882289229022912292229322942295229622972298229923002301230223032304230523062307230823092310231123122313231423152316231723182319232023212322232323242325232623272328232923302331233223332334233523362337233823392340234123422343234423452346234723482349235023512352235323542355235623572358235923602361236223632364236523662367236823692370237123722373237423752376237723782379238023812382238323842385238623872388238923902391239223932394239523962397239823992400240124022403240424052406240724082409241024112412241324142415241624172418241924202421242224232424242524262427242824292430243124322433243424352436243724382439244024412442244324442445244624472448244924502451245224532454245524562457245824592460246124622463246424652466246724682469247024712472247324742475247624772478247924802481248224832484248524862487248824892490249124922493249424952496249724982499250025012502250325042505250625072508250925102511251225132514251525162517251825192520252125222523252425252526252725282529253025312532253325342535253625372538253925402541254225432544254525462547254825492550255125522553255425552556255725582559256025612562256325642565256625672568256925702571257225732574257525762577257825792580258125822583258425852586258725882589259025912592259325942595259625972598259926002601260226032604260526062607260826092610261126122613261426152616261726182619262026212622262326242625262626272628262926302631263226332634263526362637263826392640264126422643264426452646264726482649265026512652265326542655265626572658265926602661266226632664266526662667266826692670267126722673267426752676267726782679268026812682268326842685268626872688268926902691269226932694269526962697269826992700270127022703270427052706270727082709271027112712271327142715271627172718271927202721272227232724272527262727272827292730273127322733273427352736273727382739274027412742274327442745274627472748274927502751275227532754275527562757275827592760276127622763276427652766276727682769277027712772277327742775277627772778277927802781278227832784278527862787278827892790279127922793279427952796279727982799280028012802280328042805280628072808280928102811281228132814281528162817281828192820282128222823282428252826282728282829283028312832283328342835283628372838283928402841284228432844284528462847284828492850285128522853285428552856285728582859286028612862286328642865286628672868286928702871287228732874287528762877287828792880288128822883288428852886288728882889289028912892289328942895289628972898289929002901290229032904290529062907290829092910291129122913291429152916291729182919292029212922292329242925292629272928292929302931293229332934293529362937293829392940294129422943294429452946294729482949295029512952295329542955295629572958295929602961296229632964296529662967296829692970297129722973297429752976297729782979298029812982298329842985298629872988298929902991299229932994299529962997299829993000300130023003300430053006300730083009301030113012301330143015301630173018301930203021302230233024302530263027302830293030303130323033303430353036303730383039304030413042304330443045304630473048304930503051305230533054305530563057305830593060306130623063306430653066306730683069307030713072307330743075307630773078307930803081308230833084308530863087308830893090309130923093309430953096309730983099310031013102310331043105310631073108310931103111311231133114311531163117311831193120312131223123312431253126312731283129313031313132313331343135313631373138313931403141314231433144314531463147314831493150315131523153315431553156315731583159316031613162316331643165316631673168316931703171317231733174317531763177317831793180318131823183318431853186318731883189319031913192319331943195319631973198319932003201320232033204320532063207320832093210321132123213321432153216321732183219322032213222322332243225322632273228322932303231323232333234323532363237323832393240324132423243324432453246324732483249325032513252325332543255325632573258325932603261326232633264326532663267326832693270327132723273327432753276327732783279328032813282328332843285328632873288328932903291329232933294329532963297329832993300330133023303330433053306330733083309331033113312331333143315331633173318331933203321332233233324332533263327332833293330333133323333333433353336333733383339334033413342334333443345334633473348334933503351335233533354335533563357335833593360336133623363336433653366336733683369337033713372337333743375337633773378337933803381338233833384338533863387338833893390339133923393339433953396339733983399340034013402340334043405340634073408340934103411341234133414341534163417341834193420342134223423342434253426342734283429343034313432343334343435343634373438343934403441344234433444344534463447344834493450345134523453345434553456345734583459346034613462346334643465346634673468346934703471347234733474347534763477347834793480348134823483348434853486348734883489349034913492349334943495349634973498349935003501350235033504350535063507350835093510351135123513351435153516351735183519352035213522352335243525352635273528352935303531353235333534353535363537353835393540354135423543354435453546354735483549355035513552355335543555355635573558355935603561356235633564356535663567356835693570357135723573357435753576357735783579358035813582358335843585358635873588358935903591359235933594359535963597359835993600360136023603360436053606360736083609361036113612361336143615361636173618361936203621362236233624362536263627362836293630363136323633363436353636363736383639364036413642364336443645364636473648364936503651365236533654365536563657365836593660366136623663366436653666366736683669367036713672367336743675367636773678367936803681368236833684368536863687368836893690369136923693369436953696369736983699370037013702370337043705370637073708370937103711371237133714371537163717371837193720372137223723372437253726372737283729373037313732373337343735373637373738373937403741374237433744374537463747374837493750375137523753375437553756375737583759376037613762376337643765376637673768376937703771377237733774377537763777377837793780378137823783378437853786378737883789379037913792379337943795379637973798379938003801380238033804380538063807380838093810381138123813381438153816381738183819382038213822382338243825382638273828382938303831383238333834383538363837383838393840384138423843384438453846384738483849385038513852385338543855385638573858385938603861386238633864386538663867386838693870387138723873387438753876387738783879388038813882388338843885388638873888388938903891389238933894389538963897389838993900390139023903390439053906390739083909391039113912391339143915391639173918391939203921392239233924392539263927392839293930393139323933393439353936393739383939394039413942394339443945394639473948394939503951395239533954395539563957395839593960396139623963396439653966396739683969397039713972397339743975397639773978397939803981398239833984398539863987398839893990399139923993399439953996399739983999400040014002400340044005400640074008400940104011401240134014401540164017401840194020402140224023402440254026402740284029403040314032403340344035403640374038403940404041404240434044404540464047404840494050405140524053405440554056405740584059406040614062406340644065406640674068406940704071407240734074407540764077407840794080408140824083408440854086408740884089409040914092409340944095409640974098409941004101410241034104410541064107410841094110411141124113411441154116411741184119412041214122412341244125412641274128412941304131413241334134413541364137413841394140414141424143414441454146414741484149415041514152415341544155415641574158415941604161416241634164416541664167416841694170417141724173417441754176417741784179418041814182418341844185418641874188418941904191419241934194419541964197419841994200420142024203420442054206420742084209421042114212421342144215421642174218421942204221422242234224422542264227422842294230423142324233423442354236423742384239424042414242424342444245424642474248424942504251425242534254425542564257425842594260426142624263426442654266426742684269427042714272427342744275427642774278427942804281428242834284428542864287428842894290429142924293429442954296429742984299430043014302430343044305430643074308430943104311431243134314431543164317431843194320432143224323432443254326432743284329433043314332433343344335433643374338433943404341434243434344434543464347434843494350435143524353435443554356435743584359436043614362436343644365436643674368436943704371437243734374437543764377437843794380438143824383438443854386438743884389439043914392439343944395439643974398439944004401440244034404440544064407440844094410441144124413441444154416441744184419442044214422442344244425442644274428442944304431443244334434443544364437443844394440444144424443444444454446444744484449445044514452445344544455445644574458445944604461446244634464446544664467446844694470447144724473447444754476447744784479448044814482448344844485448644874488448944904491449244934494449544964497449844994500450145024503450445054506450745084509451045114512451345144515451645174518451945204521452245234524452545264527452845294530453145324533453445354536453745384539454045414542454345444545454645474548454945504551455245534554455545564557455845594560456145624563456445654566456745684569457045714572457345744575457645774578457945804581458245834584458545864587458845894590459145924593459445954596459745984599460046014602460346044605460646074608460946104611461246134614461546164617461846194620462146224623462446254626462746284629463046314632463346344635463646374638463946404641464246434644464546464647464846494650465146524653465446554656465746584659466046614662466346644665466646674668466946704671467246734674467546764677467846794680468146824683468446854686468746884689469046914692469346944695469646974698469947004701470247034704470547064707470847094710471147124713471447154716471747184719472047214722472347244725472647274728472947304731473247334734473547364737473847394740474147424743474447454746474747484749475047514752475347544755475647574758475947604761476247634764476547664767476847694770477147724773477447754776477747784779478047814782478347844785478647874788478947904791479247934794479547964797479847994800480148024803480448054806480748084809481048114812481348144815481648174818481948204821482248234824482548264827482848294830483148324833483448354836483748384839484048414842484348444845484648474848484948504851485248534854485548564857485848594860486148624863486448654866486748684869487048714872487348744875487648774878487948804881488248834884488548864887488848894890489148924893489448954896489748984899490049014902490349044905490649074908490949104911491249134914491549164917491849194920492149224923492449254926492749284929493049314932493349344935493649374938493949404941494249434944494549464947494849494950495149524953495449554956495749584959496049614962496349644965496649674968496949704971497249734974497549764977497849794980498149824983498449854986498749884989499049914992499349944995499649974998499950005001500250035004500550065007500850095010501150125013501450155016501750185019502050215022502350245025502650275028502950305031503250335034503550365037503850395040504150425043504450455046504750485049505050515052505350545055505650575058505950605061506250635064506550665067506850695070507150725073507450755076507750785079508050815082508350845085508650875088508950905091509250935094509550965097509850995100510151025103510451055106510751085109511051115112511351145115511651175118511951205121512251235124512551265127512851295130513151325133513451355136513751385139514051415142514351445145514651475148514951505151515251535154515551565157515851595160516151625163516451655166516751685169517051715172517351745175517651775178517951805181518251835184518551865187518851895190519151925193519451955196519751985199520052015202520352045205520652075208520952105211521252135214521552165217521852195220522152225223522452255226522752285229523052315232523352345235523652375238523952405241524252435244524552465247524852495250525152525253525452555256525752585259526052615262526352645265526652675268526952705271527252735274527552765277527852795280528152825283528452855286528752885289529052915292529352945295529652975298529953005301530253035304530553065307530853095310531153125313531453155316531753185319532053215322532353245325532653275328532953305331533253335334533553365337533853395340534153425343534453455346534753485349535053515352535353545355535653575358535953605361536253635364536553665367536853695370537153725373537453755376537753785379538053815382538353845385538653875388538953905391539253935394539553965397539853995400540154025403540454055406540754085409541054115412541354145415541654175418541954205421542254235424542554265427542854295430543154325433543454355436543754385439544054415442544354445445544654475448544954505451545254535454545554565457545854595460546154625463546454655466546754685469547054715472547354745475547654775478547954805481548254835484548554865487548854895490549154925493549454955496549754985499550055015502550355045505550655075508550955105511551255135514551555165517551855195520552155225523552455255526552755285529553055315532553355345535553655375538553955405541554255435544554555465547554855495550555155525553555455555556555755585559556055615562556355645565556655675568556955705571557255735574557555765577557855795580558155825583558455855586558755885589559055915592559355945595559655975598559956005601560256035604560556065607560856095610561156125613561456155616561756185619562056215622562356245625562656275628562956305631563256335634563556365637563856395640564156425643564456455646564756485649565056515652565356545655565656575658565956605661566256635664566556665667566856695670567156725673567456755676567756785679568056815682568356845685568656875688568956905691569256935694569556965697569856995700570157025703570457055706570757085709571057115712571357145715571657175718571957205721572257235724572557265727572857295730573157325733573457355736573757385739574057415742574357445745574657475748574957505751575257535754575557565757575857595760576157625763576457655766576757685769577057715772577357745775577657775778577957805781578257835784578557865787578857895790579157925793579457955796579757985799580058015802580358045805580658075808580958105811581258135814581558165817581858195820582158225823582458255826582758285829583058315832583358345835583658375838583958405841584258435844584558465847584858495850585158525853585458555856585758585859586058615862586358645865586658675868586958705871587258735874587558765877587858795880588158825883588458855886588758885889589058915892589358945895589658975898589959005901590259035904590559065907590859095910591159125913591459155916591759185919592059215922592359245925592659275928592959305931593259335934593559365937593859395940594159425943594459455946594759485949595059515952595359545955595659575958595959605961596259635964596559665967596859695970597159725973597459755976597759785979598059815982598359845985598659875988598959905991599259935994599559965997599859996000600160026003600460056006600760086009601060116012601360146015601660176018601960206021602260236024602560266027602860296030603160326033603460356036603760386039604060416042604360446045604660476048604960506051605260536054605560566057605860596060606160626063606460656066606760686069607060716072607360746075607660776078607960806081608260836084608560866087608860896090609160926093609460956096609760986099610061016102610361046105610661076108610961106111611261136114611561166117611861196120612161226123612461256126612761286129613061316132613361346135613661376138613961406141614261436144614561466147614861496150615161526153615461556156615761586159616061616162616361646165616661676168616961706171617261736174617561766177617861796180618161826183618461856186618761886189619061916192619361946195619661976198619962006201620262036204620562066207620862096210621162126213621462156216621762186219622062216222622362246225622662276228622962306231623262336234623562366237623862396240624162426243624462456246624762486249625062516252625362546255625662576258625962606261626262636264626562666267626862696270627162726273627462756276627762786279628062816282628362846285628662876288628962906291629262936294629562966297629862996300630163026303630463056306630763086309631063116312631363146315631663176318631963206321632263236324632563266327632863296330633163326333633463356336633763386339634063416342634363446345634663476348634963506351635263536354635563566357635863596360636163626363636463656366636763686369637063716372637363746375637663776378637963806381638263836384638563866387638863896390639163926393639463956396639763986399640064016402640364046405640664076408640964106411641264136414641564166417641864196420642164226423642464256426642764286429643064316432643364346435643664376438643964406441644264436444644564466447644864496450645164526453645464556456645764586459646064616462646364646465646664676468646964706471647264736474647564766477647864796480648164826483648464856486648764886489649064916492649364946495649664976498649965006501650265036504650565066507650865096510651165126513651465156516651765186519652065216522652365246525652665276528652965306531653265336534653565366537653865396540654165426543654465456546654765486549655065516552655365546555655665576558655965606561656265636564656565666567656865696570657165726573657465756576657765786579658065816582658365846585658665876588658965906591659265936594659565966597659865996600660166026603660466056606660766086609661066116612661366146615661666176618661966206621662266236624662566266627662866296630663166326633663466356636663766386639664066416642664366446645664666476648664966506651665266536654665566566657665866596660666166626663666466656666666766686669667066716672667366746675667666776678667966806681668266836684668566866687668866896690669166926693669466956696669766986699670067016702670367046705670667076708670967106711671267136714671567166717671867196720672167226723672467256726672767286729673067316732673367346735673667376738673967406741674267436744674567466747674867496750675167526753675467556756675767586759676067616762676367646765676667676768676967706771677267736774677567766777677867796780678167826783678467856786678767886789679067916792679367946795679667976798679968006801680268036804680568066807680868096810681168126813681468156816681768186819682068216822682368246825682668276828682968306831683268336834683568366837683868396840684168426843684468456846684768486849685068516852685368546855685668576858685968606861686268636864686568666867686868696870687168726873687468756876687768786879688068816882688368846885688668876888688968906891689268936894689568966897689868996900690169026903690469056906690769086909691069116912691369146915691669176918691969206921692269236924692569266927692869296930693169326933693469356936693769386939694069416942694369446945694669476948694969506951695269536954695569566957695869596960696169626963696469656966696769686969697069716972697369746975697669776978697969806981698269836984698569866987698869896990699169926993699469956996699769986999700070017002700370047005700670077008700970107011701270137014701570167017701870197020702170227023702470257026702770287029703070317032703370347035703670377038703970407041704270437044704570467047704870497050705170527053705470557056705770587059706070617062706370647065706670677068706970707071707270737074707570767077707870797080708170827083708470857086708770887089709070917092709370947095709670977098709971007101710271037104710571067107710871097110711171127113711471157116711771187119712071217122712371247125712671277128712971307131713271337134713571367137713871397140714171427143714471457146714771487149715071517152715371547155715671577158715971607161716271637164716571667167716871697170717171727173717471757176717771787179718071817182718371847185718671877188718971907191719271937194719571967197719871997200720172027203720472057206720772087209721072117212721372147215721672177218721972207221722272237224722572267227722872297230723172327233723472357236723772387239724072417242724372447245724672477248724972507251725272537254725572567257725872597260726172627263726472657266726772687269727072717272727372747275727672777278727972807281728272837284728572867287728872897290729172927293729472957296729772987299730073017302730373047305730673077308730973107311731273137314731573167317731873197320732173227323732473257326732773287329733073317332733373347335733673377338733973407341734273437344734573467347734873497350735173527353735473557356735773587359736073617362736373647365736673677368736973707371737273737374737573767377737873797380738173827383738473857386738773887389739073917392739373947395739673977398739974007401740274037404740574067407740874097410741174127413741474157416741774187419742074217422742374247425742674277428742974307431743274337434743574367437743874397440744174427443744474457446744774487449745074517452745374547455745674577458745974607461746274637464746574667467746874697470747174727473747474757476747774787479748074817482748374847485748674877488748974907491749274937494749574967497749874997500750175027503750475057506750775087509751075117512751375147515751675177518751975207521752275237524752575267527752875297530753175327533753475357536753775387539754075417542754375447545754675477548754975507551755275537554755575567557755875597560756175627563756475657566756775687569757075717572757375747575757675777578757975807581758275837584758575867587758875897590759175927593759475957596759775987599760076017602760376047605760676077608760976107611761276137614761576167617761876197620762176227623762476257626762776287629763076317632763376347635763676377638763976407641764276437644764576467647764876497650765176527653765476557656765776587659766076617662766376647665766676677668766976707671767276737674767576767677767876797680768176827683768476857686768776887689769076917692769376947695769676977698769977007701770277037704770577067707770877097710771177127713771477157716771777187719772077217722772377247725772677277728772977307731773277337734773577367737773877397740774177427743774477457746774777487749775077517752775377547755775677577758775977607761776277637764776577667767776877697770777177727773777477757776777777787779778077817782778377847785778677877788778977907791779277937794779577967797779877997800780178027803780478057806780778087809781078117812781378147815781678177818781978207821782278237824782578267827782878297830783178327833783478357836783778387839784078417842784378447845784678477848784978507851785278537854785578567857785878597860786178627863786478657866786778687869787078717872787378747875787678777878787978807881788278837884788578867887788878897890789178927893789478957896789778987899790079017902790379047905790679077908790979107911791279137914791579167917791879197920792179227923792479257926792779287929793079317932793379347935793679377938793979407941794279437944794579467947794879497950795179527953795479557956795779587959796079617962796379647965796679677968796979707971797279737974797579767977797879797980798179827983798479857986798779887989799079917992799379947995799679977998799980008001800280038004800580068007800880098010801180128013801480158016801780188019802080218022802380248025802680278028802980308031803280338034803580368037803880398040804180428043804480458046804780488049805080518052805380548055805680578058805980608061806280638064806580668067806880698070807180728073807480758076807780788079808080818082808380848085808680878088808980908091809280938094809580968097809880998100810181028103810481058106810781088109811081118112811381148115811681178118811981208121812281238124812581268127812881298130813181328133813481358136813781388139814081418142814381448145814681478148814981508151815281538154815581568157815881598160816181628163816481658166816781688169817081718172817381748175817681778178817981808181818281838184818581868187818881898190819181928193819481958196819781988199820082018202820382048205820682078208820982108211821282138214821582168217821882198220822182228223822482258226822782288229823082318232823382348235823682378238823982408241824282438244824582468247824882498250825182528253825482558256825782588259826082618262826382648265826682678268826982708271827282738274827582768277827882798280828182828283828482858286828782888289829082918292829382948295829682978298829983008301830283038304830583068307830883098310831183128313831483158316831783188319832083218322832383248325832683278328832983308331833283338334833583368337833883398340834183428343834483458346834783488349835083518352835383548355835683578358835983608361836283638364836583668367836883698370837183728373837483758376837783788379838083818382838383848385838683878388838983908391839283938394839583968397839883998400840184028403840484058406840784088409841084118412841384148415841684178418841984208421842284238424842584268427842884298430843184328433843484358436843784388439844084418442844384448445844684478448844984508451845284538454845584568457845884598460846184628463846484658466846784688469847084718472847384748475847684778478847984808481848284838484848584868487848884898490849184928493849484958496849784988499850085018502850385048505850685078508850985108511851285138514851585168517851885198520852185228523852485258526852785288529853085318532853385348535853685378538853985408541854285438544854585468547854885498550855185528553855485558556855785588559856085618562856385648565856685678568856985708571857285738574857585768577857885798580858185828583858485858586858785888589859085918592859385948595859685978598859986008601860286038604860586068607860886098610861186128613861486158616861786188619862086218622862386248625862686278628862986308631863286338634863586368637863886398640864186428643864486458646864786488649865086518652865386548655865686578658865986608661866286638664866586668667866886698670867186728673867486758676867786788679868086818682868386848685868686878688868986908691869286938694869586968697869886998700870187028703870487058706870787088709871087118712871387148715871687178718871987208721872287238724872587268727872887298730873187328733873487358736873787388739874087418742874387448745874687478748874987508751875287538754875587568757875887598760876187628763876487658766876787688769877087718772877387748775877687778778877987808781878287838784878587868787878887898790879187928793879487958796879787988799880088018802880388048805880688078808880988108811881288138814881588168817881888198820882188228823882488258826882788288829883088318832883388348835883688378838883988408841884288438844884588468847884888498850885188528853885488558856885788588859886088618862886388648865886688678868886988708871887288738874887588768877887888798880888188828883888488858886888788888889889088918892889388948895889688978898889989008901890289038904890589068907890889098910891189128913891489158916891789188919892089218922892389248925892689278928892989308931893289338934893589368937893889398940894189428943894489458946894789488949895089518952895389548955895689578958895989608961896289638964896589668967896889698970897189728973897489758976897789788979898089818982898389848985898689878988898989908991899289938994899589968997899889999000900190029003900490059006900790089009901090119012901390149015901690179018901990209021902290239024902590269027902890299030903190329033903490359036903790389039904090419042904390449045904690479048904990509051905290539054905590569057905890599060906190629063906490659066906790689069907090719072907390749075907690779078907990809081908290839084908590869087908890899090909190929093909490959096909790989099910091019102910391049105910691079108910991109111911291139114911591169117911891199120912191229123912491259126912791289129913091319132913391349135913691379138913991409141914291439144914591469147914891499150915191529153915491559156915791589159916091619162916391649165916691679168916991709171917291739174917591769177917891799180918191829183918491859186918791889189919091919192919391949195919691979198919992009201920292039204920592069207920892099210921192129213921492159216921792189219922092219222922392249225922692279228922992309231923292339234923592369237923892399240924192429243924492459246924792489249925092519252925392549255925692579258925992609261926292639264926592669267926892699270927192729273927492759276927792789279928092819282928392849285928692879288928992909291929292939294929592969297929892999300930193029303930493059306930793089309931093119312931393149315931693179318931993209321932293239324932593269327932893299330933193329333933493359336933793389339934093419342934393449345934693479348934993509351935293539354935593569357935893599360936193629363936493659366936793689369937093719372937393749375937693779378937993809381938293839384938593869387938893899390939193929393939493959396939793989399940094019402940394049405940694079408940994109411941294139414941594169417941894199420942194229423942494259426942794289429943094319432943394349435943694379438943994409441944294439444944594469447944894499450945194529453945494559456945794589459946094619462946394649465946694679468946994709471947294739474947594769477947894799480948194829483948494859486948794889489949094919492949394949495949694979498949995009501950295039504950595069507950895099510951195129513951495159516951795189519952095219522952395249525952695279528952995309531953295339534953595369537953895399540954195429543954495459546954795489549955095519552955395549555955695579558955995609561956295639564956595669567956895699570957195729573957495759576957795789579958095819582958395849585958695879588958995909591959295939594959595969597959895999600960196029603960496059606960796089609961096119612961396149615961696179618961996209621962296239624962596269627962896299630963196329633963496359636963796389639964096419642964396449645964696479648964996509651965296539654965596569657965896599660966196629663966496659666966796689669967096719672967396749675967696779678967996809681968296839684968596869687968896899690969196929693969496959696969796989699970097019702970397049705970697079708970997109711971297139714971597169717971897199720972197229723972497259726972797289729973097319732973397349735973697379738973997409741974297439744974597469747974897499750975197529753975497559756975797589759976097619762976397649765976697679768976997709771977297739774977597769777977897799780978197829783978497859786978797889789979097919792979397949795979697979798979998009801980298039804980598069807980898099810981198129813981498159816981798189819982098219822982398249825982698279828982998309831983298339834983598369837983898399840984198429843984498459846984798489849985098519852985398549855985698579858985998609861986298639864986598669867986898699870987198729873987498759876987798789879988098819882988398849885988698879888988998909891989298939894989598969897989898999900990199029903990499059906990799089909991099119912991399149915991699179918991999209921992299239924992599269927992899299930993199329933993499359936993799389939994099419942994399449945994699479948994999509951995299539954995599569957995899599960996199629963996499659966996799689969997099719972997399749975997699779978997999809981998299839984998599869987998899899990999199929993999499959996999799989999100001000110002100031000410005100061000710008100091001010011100121001310014100151001610017100181001910020100211002210023100241002510026100271002810029100301003110032100331003410035100361003710038100391004010041100421004310044100451004610047100481004910050100511005210053100541005510056100571005810059100601006110062100631006410065100661006710068100691007010071100721007310074100751007610077100781007910080100811008210083100841008510086100871008810089100901009110092100931009410095100961009710098100991010010101101021010310104101051010610107101081010910110101111011210113101141011510116101171011810119101201012110122101231012410125101261012710128101291013010131101321013310134101351013610137101381013910140101411014210143101441014510146101471014810149101501015110152101531015410155101561015710158101591016010161101621016310164101651016610167101681016910170101711017210173101741017510176101771017810179101801018110182101831018410185101861018710188101891019010191101921019310194101951019610197101981019910200102011020210203102041020510206102071020810209102101021110212102131021410215102161021710218102191022010221102221022310224102251022610227102281022910230102311023210233102341023510236102371023810239102401024110242102431024410245102461024710248102491025010251102521025310254102551025610257102581025910260102611026210263102641026510266102671026810269102701027110272102731027410275102761027710278102791028010281102821028310284102851028610287102881028910290102911029210293102941029510296102971029810299103001030110302103031030410305103061030710308103091031010311103121031310314103151031610317103181031910320103211032210323103241032510326103271032810329103301033110332103331033410335103361033710338103391034010341103421034310344103451034610347103481034910350103511035210353103541035510356103571035810359103601036110362103631036410365103661036710368103691037010371103721037310374103751037610377103781037910380103811038210383103841038510386103871038810389103901039110392103931039410395103961039710398103991040010401104021040310404104051040610407104081040910410104111041210413104141041510416104171041810419104201042110422104231042410425104261042710428104291043010431104321043310434104351043610437104381043910440104411044210443104441044510446104471044810449104501045110452104531045410455104561045710458104591046010461104621046310464104651046610467104681046910470104711047210473104741047510476104771047810479104801048110482104831048410485104861048710488104891049010491104921049310494104951049610497104981049910500105011050210503105041050510506105071050810509105101051110512105131051410515105161051710518105191052010521105221052310524105251052610527105281052910530105311053210533105341053510536105371053810539105401054110542105431054410545105461054710548105491055010551105521055310554105551055610557105581055910560105611056210563105641056510566105671056810569105701057110572105731057410575105761057710578105791058010581105821058310584105851058610587105881058910590105911059210593105941059510596105971059810599106001060110602106031060410605106061060710608106091061010611106121061310614106151061610617106181061910620106211062210623106241062510626106271062810629106301063110632106331063410635106361063710638106391064010641106421064310644106451064610647106481064910650106511065210653106541065510656106571065810659106601066110662106631066410665106661066710668106691067010671106721067310674106751067610677106781067910680106811068210683106841068510686106871068810689106901069110692106931069410695106961069710698106991070010701107021070310704107051070610707107081070910710107111071210713107141071510716107171071810719107201072110722107231072410725107261072710728107291073010731107321073310734107351073610737107381073910740107411074210743107441074510746107471074810749107501075110752107531075410755107561075710758107591076010761107621076310764107651076610767107681076910770107711077210773107741077510776107771077810779107801078110782107831078410785107861078710788107891079010791107921079310794107951079610797107981079910800108011080210803108041080510806108071080810809108101081110812108131081410815108161081710818108191082010821108221082310824108251082610827108281082910830108311083210833108341083510836108371083810839108401084110842108431084410845108461084710848108491085010851108521085310854108551085610857108581085910860108611086210863108641086510866108671086810869108701087110872108731087410875108761087710878108791088010881108821088310884108851088610887108881088910890108911089210893108941089510896108971089810899109001090110902109031090410905109061090710908109091091010911109121091310914109151091610917109181091910920109211092210923109241092510926109271092810929109301093110932109331093410935109361093710938109391094010941109421094310944109451094610947109481094910950109511095210953109541095510956109571095810959109601096110962109631096410965109661096710968109691097010971109721097310974109751097610977109781097910980109811098210983109841098510986109871098810989109901099110992109931099410995109961099710998109991100011001110021100311004110051100611007110081100911010110111101211013110141101511016110171101811019110201102111022110231102411025110261102711028110291103011031110321103311034110351103611037110381103911040110411104211043110441104511046110471104811049110501105111052110531105411055110561105711058110591106011061110621106311064110651106611067110681106911070110711107211073110741107511076110771107811079110801108111082110831108411085110861108711088110891109011091110921109311094110951109611097110981109911100111011110211103111041110511106111071110811109111101111111112111131111411115111161111711118111191112011121111221112311124111251112611127111281112911130111311113211133111341113511136111371113811139111401114111142111431114411145111461114711148111491115011151111521115311154111551115611157111581115911160111611116211163111641116511166111671116811169111701117111172111731117411175111761117711178111791118011181111821118311184111851118611187111881118911190111911119211193111941119511196111971119811199112001120111202112031120411205112061120711208112091121011211112121121311214112151121611217112181121911220112211122211223112241122511226112271122811229112301123111232112331123411235112361123711238112391124011241112421124311244112451124611247112481124911250112511125211253112541125511256112571125811259112601126111262112631126411265112661126711268112691127011271112721127311274112751127611277112781127911280112811128211283112841128511286112871128811289112901129111292112931129411295112961129711298112991130011301113021130311304113051130611307113081130911310113111131211313113141131511316113171131811319113201132111322113231132411325113261132711328113291133011331113321133311334113351133611337113381133911340113411134211343113441134511346113471134811349113501135111352113531135411355113561135711358113591136011361113621136311364113651136611367113681136911370113711137211373113741137511376113771137811379113801138111382113831138411385113861138711388113891139011391113921139311394113951139611397113981139911400114011140211403114041140511406114071140811409114101141111412114131141411415114161141711418114191142011421114221142311424114251142611427114281142911430114311143211433114341143511436114371143811439114401144111442114431144411445114461144711448114491145011451114521145311454114551145611457114581145911460114611146211463114641146511466114671146811469114701147111472114731147411475114761147711478114791148011481114821148311484114851148611487114881148911490114911149211493114941149511496114971149811499115001150111502115031150411505115061150711508115091151011511115121151311514115151151611517115181151911520115211152211523115241152511526115271152811529115301153111532115331153411535115361153711538115391154011541115421154311544115451154611547115481154911550115511155211553115541155511556115571155811559115601156111562115631156411565115661156711568115691157011571115721157311574115751157611577115781157911580115811158211583115841158511586115871158811589115901159111592115931159411595115961159711598115991160011601116021160311604116051160611607116081160911610116111161211613116141161511616116171161811619116201162111622116231162411625116261162711628116291163011631116321163311634116351163611637116381163911640116411164211643116441164511646116471164811649116501165111652116531165411655116561165711658116591166011661116621166311664
// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2007-2009 Patrick McHardy <kaber@trash.net> * * Development of this code funded by Astaro AG (http://www.astaro.com/) */ #include <linux/module.h> #include <linux/init.h> #include <linux/list.h> #include <linux/skbuff.h> #include <linux/netlink.h> #include <linux/vmalloc.h> #include <linux/rhashtable.h> #include <linux/audit.h> #include <linux/netfilter.h> #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_flow_table.h> #include <net/netfilter/nf_tables_core.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nf_tables_offload.h> #include <net/net_namespace.h> #include <net/sock.h> #define NFT_MODULE_AUTOLOAD_LIMIT (MODULE_NAME_LEN - sizeof("nft-expr-255-")) #define NFT_SET_MAX_ANONLEN 16 unsigned int nf_tables_net_id __read_mostly; static LIST_HEAD(nf_tables_expressions); static LIST_HEAD(nf_tables_objects); static LIST_HEAD(nf_tables_flowtables); static LIST_HEAD(nf_tables_destroy_list); static LIST_HEAD(nf_tables_gc_list); static DEFINE_SPINLOCK(nf_tables_destroy_list_lock); static DEFINE_SPINLOCK(nf_tables_gc_list_lock); enum { NFT_VALIDATE_SKIP = 0, NFT_VALIDATE_NEED, NFT_VALIDATE_DO, }; static struct rhltable nft_objname_ht; static u32 nft_chain_hash(const void *data, u32 len, u32 seed); static u32 nft_chain_hash_obj(const void *data, u32 len, u32 seed); static int nft_chain_hash_cmp(struct rhashtable_compare_arg *, const void *); static u32 nft_objname_hash(const void *data, u32 len, u32 seed); static u32 nft_objname_hash_obj(const void *data, u32 len, u32 seed); static int nft_objname_hash_cmp(struct rhashtable_compare_arg *, const void *); static const struct rhashtable_params nft_chain_ht_params = { .head_offset = offsetof(struct nft_chain, rhlhead), .key_offset = offsetof(struct nft_chain, name), .hashfn = nft_chain_hash, .obj_hashfn = nft_chain_hash_obj, .obj_cmpfn = nft_chain_hash_cmp, .automatic_shrinking = true, }; static const struct rhashtable_params nft_objname_ht_params = { .head_offset = offsetof(struct nft_object, rhlhead), .key_offset = offsetof(struct nft_object, key), .hashfn = nft_objname_hash, .obj_hashfn = nft_objname_hash_obj, .obj_cmpfn = nft_objname_hash_cmp, .automatic_shrinking = true, }; struct nft_audit_data { struct nft_table *table; int entries; int op; struct list_head list; }; static const u8 nft2audit_op[NFT_MSG_MAX] = { // enum nf_tables_msg_types [NFT_MSG_NEWTABLE] = AUDIT_NFT_OP_TABLE_REGISTER, [NFT_MSG_GETTABLE] = AUDIT_NFT_OP_INVALID, [NFT_MSG_DELTABLE] = AUDIT_NFT_OP_TABLE_UNREGISTER, [NFT_MSG_NEWCHAIN] = AUDIT_NFT_OP_CHAIN_REGISTER, [NFT_MSG_GETCHAIN] = AUDIT_NFT_OP_INVALID, [NFT_MSG_DELCHAIN] = AUDIT_NFT_OP_CHAIN_UNREGISTER, [NFT_MSG_NEWRULE] = AUDIT_NFT_OP_RULE_REGISTER, [NFT_MSG_GETRULE] = AUDIT_NFT_OP_INVALID, [NFT_MSG_DELRULE] = AUDIT_NFT_OP_RULE_UNREGISTER, [NFT_MSG_NEWSET] = AUDIT_NFT_OP_SET_REGISTER, [NFT_MSG_GETSET] = AUDIT_NFT_OP_INVALID, [NFT_MSG_DELSET] = AUDIT_NFT_OP_SET_UNREGISTER, [NFT_MSG_NEWSETELEM] = AUDIT_NFT_OP_SETELEM_REGISTER, [NFT_MSG_GETSETELEM] = AUDIT_NFT_OP_INVALID, [NFT_MSG_DELSETELEM] = AUDIT_NFT_OP_SETELEM_UNREGISTER, [NFT_MSG_NEWGEN] = AUDIT_NFT_OP_GEN_REGISTER, [NFT_MSG_GETGEN] = AUDIT_NFT_OP_INVALID, [NFT_MSG_TRACE] = AUDIT_NFT_OP_INVALID, [NFT_MSG_NEWOBJ] = AUDIT_NFT_OP_OBJ_REGISTER, [NFT_MSG_GETOBJ] = AUDIT_NFT_OP_INVALID, [NFT_MSG_DELOBJ] = AUDIT_NFT_OP_OBJ_UNREGISTER, [NFT_MSG_GETOBJ_RESET] = AUDIT_NFT_OP_OBJ_RESET, [NFT_MSG_NEWFLOWTABLE] = AUDIT_NFT_OP_FLOWTABLE_REGISTER, [NFT_MSG_GETFLOWTABLE] = AUDIT_NFT_OP_INVALID, [NFT_MSG_DELFLOWTABLE] = AUDIT_NFT_OP_FLOWTABLE_UNREGISTER, [NFT_MSG_GETSETELEM_RESET] = AUDIT_NFT_OP_SETELEM_RESET, }; static void nft_validate_state_update(struct nft_table *table, u8 new_validate_state) { switch (table->validate_state) { case NFT_VALIDATE_SKIP: WARN_ON_ONCE(new_validate_state == NFT_VALIDATE_DO); break; case NFT_VALIDATE_NEED: break; case NFT_VALIDATE_DO: if (new_validate_state == NFT_VALIDATE_NEED) return; } table->validate_state = new_validate_state; } static void nf_tables_trans_destroy_work(struct work_struct *w); static DECLARE_WORK(trans_destroy_work, nf_tables_trans_destroy_work); static void nft_trans_gc_work(struct work_struct *work); static DECLARE_WORK(trans_gc_work, nft_trans_gc_work); static void nft_ctx_init(struct nft_ctx *ctx, struct net *net, const struct sk_buff *skb, const struct nlmsghdr *nlh, u8 family, struct nft_table *table, struct nft_chain *chain, const struct nlattr * const *nla) { ctx->net = net; ctx->family = family; ctx->level = 0; ctx->table = table; ctx->chain = chain; ctx->nla = nla; ctx->portid = NETLINK_CB(skb).portid; ctx->report = nlmsg_report(nlh); ctx->flags = nlh->nlmsg_flags; ctx->seq = nlh->nlmsg_seq; } static struct nft_trans *nft_trans_alloc_gfp(const struct nft_ctx *ctx, int msg_type, u32 size, gfp_t gfp) { struct nft_trans *trans; trans = kzalloc(sizeof(struct nft_trans) + size, gfp); if (trans == NULL) return NULL; INIT_LIST_HEAD(&trans->list); INIT_LIST_HEAD(&trans->binding_list); trans->msg_type = msg_type; trans->ctx = *ctx; return trans; } static struct nft_trans *nft_trans_alloc(const struct nft_ctx *ctx, int msg_type, u32 size) { return nft_trans_alloc_gfp(ctx, msg_type, size, GFP_KERNEL); } static void nft_trans_list_del(struct nft_trans *trans) { list_del(&trans->list); list_del(&trans->binding_list); } static void nft_trans_destroy(struct nft_trans *trans) { nft_trans_list_del(trans); kfree(trans); } static void __nft_set_trans_bind(const struct nft_ctx *ctx, struct nft_set *set, bool bind) { struct nftables_pernet *nft_net; struct net *net = ctx->net; struct nft_trans *trans; if (!nft_set_is_anonymous(set)) return; nft_net = nft_pernet(net); list_for_each_entry_reverse(trans, &nft_net->commit_list, list) { switch (trans->msg_type) { case NFT_MSG_NEWSET: if (nft_trans_set(trans) == set) nft_trans_set_bound(trans) = bind; break; case NFT_MSG_NEWSETELEM: if (nft_trans_elem_set(trans) == set) nft_trans_elem_set_bound(trans) = bind; break; } } } static void nft_set_trans_bind(const struct nft_ctx *ctx, struct nft_set *set) { return __nft_set_trans_bind(ctx, set, true); } static void nft_set_trans_unbind(const struct nft_ctx *ctx, struct nft_set *set) { return __nft_set_trans_bind(ctx, set, false); } static void __nft_chain_trans_bind(const struct nft_ctx *ctx, struct nft_chain *chain, bool bind) { struct nftables_pernet *nft_net; struct net *net = ctx->net; struct nft_trans *trans; if (!nft_chain_binding(chain)) return; nft_net = nft_pernet(net); list_for_each_entry_reverse(trans, &nft_net->commit_list, list) { switch (trans->msg_type) { case NFT_MSG_NEWCHAIN: if (nft_trans_chain(trans) == chain) nft_trans_chain_bound(trans) = bind; break; case NFT_MSG_NEWRULE: if (trans->ctx.chain == chain) nft_trans_rule_bound(trans) = bind; break; } } } static void nft_chain_trans_bind(const struct nft_ctx *ctx, struct nft_chain *chain) { __nft_chain_trans_bind(ctx, chain, true); } int nf_tables_bind_chain(const struct nft_ctx *ctx, struct nft_chain *chain) { if (!nft_chain_binding(chain)) return 0; if (nft_chain_binding(ctx->chain)) return -EOPNOTSUPP; if (chain->bound) return -EBUSY; if (!nft_use_inc(&chain->use)) return -EMFILE; chain->bound = true; nft_chain_trans_bind(ctx, chain); return 0; } void nf_tables_unbind_chain(const struct nft_ctx *ctx, struct nft_chain *chain) { __nft_chain_trans_bind(ctx, chain, false); } static int nft_netdev_register_hooks(struct net *net, struct list_head *hook_list) { struct nft_hook *hook; int err, j; j = 0; list_for_each_entry(hook, hook_list, list) { err = nf_register_net_hook(net, &hook->ops); if (err < 0) goto err_register; j++; } return 0; err_register: list_for_each_entry(hook, hook_list, list) { if (j-- <= 0) break; nf_unregister_net_hook(net, &hook->ops); } return err; } static void nft_netdev_unregister_hooks(struct net *net, struct list_head *hook_list, bool release_netdev) { struct nft_hook *hook, *next; list_for_each_entry_safe(hook, next, hook_list, list) { nf_unregister_net_hook(net, &hook->ops); if (release_netdev) { list_del(&hook->list); kfree_rcu(hook, rcu); } } } static int nf_tables_register_hook(struct net *net, const struct nft_table *table, struct nft_chain *chain) { struct nft_base_chain *basechain; const struct nf_hook_ops *ops; if (table->flags & NFT_TABLE_F_DORMANT || !nft_is_base_chain(chain)) return 0; basechain = nft_base_chain(chain); ops = &basechain->ops; if (basechain->type->ops_register) return basechain->type->ops_register(net, ops); if (nft_base_chain_netdev(table->family, basechain->ops.hooknum)) return nft_netdev_register_hooks(net, &basechain->hook_list); return nf_register_net_hook(net, &basechain->ops); } static void __nf_tables_unregister_hook(struct net *net, const struct nft_table *table, struct nft_chain *chain, bool release_netdev) { struct nft_base_chain *basechain; const struct nf_hook_ops *ops; if (table->flags & NFT_TABLE_F_DORMANT || !nft_is_base_chain(chain)) return; basechain = nft_base_chain(chain); ops = &basechain->ops; if (basechain->type->ops_unregister) return basechain->type->ops_unregister(net, ops); if (nft_base_chain_netdev(table->family, basechain->ops.hooknum)) nft_netdev_unregister_hooks(net, &basechain->hook_list, release_netdev); else nf_unregister_net_hook(net, &basechain->ops); } static void nf_tables_unregister_hook(struct net *net, const struct nft_table *table, struct nft_chain *chain) { return __nf_tables_unregister_hook(net, table, chain, false); } static void nft_trans_commit_list_add_tail(struct net *net, struct nft_trans *trans) { struct nftables_pernet *nft_net = nft_pernet(net); switch (trans->msg_type) { case NFT_MSG_NEWSET: if (!nft_trans_set_update(trans) && nft_set_is_anonymous(nft_trans_set(trans))) list_add_tail(&trans->binding_list, &nft_net->binding_list); break; case NFT_MSG_NEWCHAIN: if (!nft_trans_chain_update(trans) && nft_chain_binding(nft_trans_chain(trans))) list_add_tail(&trans->binding_list, &nft_net->binding_list); break; } list_add_tail(&trans->list, &nft_net->commit_list); } static int nft_trans_table_add(struct nft_ctx *ctx, int msg_type) { struct nft_trans *trans; trans = nft_trans_alloc(ctx, msg_type, sizeof(struct nft_trans_table)); if (trans == NULL) return -ENOMEM; if (msg_type == NFT_MSG_NEWTABLE) nft_activate_next(ctx->net, ctx->table); nft_trans_commit_list_add_tail(ctx->net, trans); return 0; } static int nft_deltable(struct nft_ctx *ctx) { int err; err = nft_trans_table_add(ctx, NFT_MSG_DELTABLE); if (err < 0) return err; nft_deactivate_next(ctx->net, ctx->table); return err; } static struct nft_trans *nft_trans_chain_add(struct nft_ctx *ctx, int msg_type) { struct nft_trans *trans; trans = nft_trans_alloc(ctx, msg_type, sizeof(struct nft_trans_chain)); if (trans == NULL) return ERR_PTR(-ENOMEM); if (msg_type == NFT_MSG_NEWCHAIN) { nft_activate_next(ctx->net, ctx->chain); if (ctx->nla[NFTA_CHAIN_ID]) { nft_trans_chain_id(trans) = ntohl(nla_get_be32(ctx->nla[NFTA_CHAIN_ID])); } } nft_trans_chain(trans) = ctx->chain; nft_trans_commit_list_add_tail(ctx->net, trans); return trans; } static int nft_delchain(struct nft_ctx *ctx) { struct nft_trans *trans; trans = nft_trans_chain_add(ctx, NFT_MSG_DELCHAIN); if (IS_ERR(trans)) return PTR_ERR(trans); nft_use_dec(&ctx->table->use); nft_deactivate_next(ctx->net, ctx->chain); return 0; } void nft_rule_expr_activate(const struct nft_ctx *ctx, struct nft_rule *rule) { struct nft_expr *expr; expr = nft_expr_first(rule); while (nft_expr_more(rule, expr)) { if (expr->ops->activate) expr->ops->activate(ctx, expr); expr = nft_expr_next(expr); } } void nft_rule_expr_deactivate(const struct nft_ctx *ctx, struct nft_rule *rule, enum nft_trans_phase phase) { struct nft_expr *expr; expr = nft_expr_first(rule); while (nft_expr_more(rule, expr)) { if (expr->ops->deactivate) expr->ops->deactivate(ctx, expr, phase); expr = nft_expr_next(expr); } } static int nf_tables_delrule_deactivate(struct nft_ctx *ctx, struct nft_rule *rule) { /* You cannot delete the same rule twice */ if (nft_is_active_next(ctx->net, rule)) { nft_deactivate_next(ctx->net, rule); nft_use_dec(&ctx->chain->use); return 0; } return -ENOENT; } static struct nft_trans *nft_trans_rule_add(struct nft_ctx *ctx, int msg_type, struct nft_rule *rule) { struct nft_trans *trans; trans = nft_trans_alloc(ctx, msg_type, sizeof(struct nft_trans_rule)); if (trans == NULL) return NULL; if (msg_type == NFT_MSG_NEWRULE && ctx->nla[NFTA_RULE_ID] != NULL) { nft_trans_rule_id(trans) = ntohl(nla_get_be32(ctx->nla[NFTA_RULE_ID])); } nft_trans_rule(trans) = rule; nft_trans_commit_list_add_tail(ctx->net, trans); return trans; } static int nft_delrule(struct nft_ctx *ctx, struct nft_rule *rule) { struct nft_flow_rule *flow; struct nft_trans *trans; int err; trans = nft_trans_rule_add(ctx, NFT_MSG_DELRULE, rule); if (trans == NULL) return -ENOMEM; if (ctx->chain->flags & NFT_CHAIN_HW_OFFLOAD) { flow = nft_flow_rule_create(ctx->net, rule); if (IS_ERR(flow)) { nft_trans_destroy(trans); return PTR_ERR(flow); } nft_trans_flow_rule(trans) = flow; } err = nf_tables_delrule_deactivate(ctx, rule); if (err < 0) { nft_trans_destroy(trans); return err; } nft_rule_expr_deactivate(ctx, rule, NFT_TRANS_PREPARE); return 0; } static int nft_delrule_by_chain(struct nft_ctx *ctx) { struct nft_rule *rule; int err; list_for_each_entry(rule, &ctx->chain->rules, list) { if (!nft_is_active_next(ctx->net, rule)) continue; err = nft_delrule(ctx, rule); if (err < 0) return err; } return 0; } static int __nft_trans_set_add(const struct nft_ctx *ctx, int msg_type, struct nft_set *set, const struct nft_set_desc *desc) { struct nft_trans *trans; trans = nft_trans_alloc(ctx, msg_type, sizeof(struct nft_trans_set)); if (trans == NULL) return -ENOMEM; if (msg_type == NFT_MSG_NEWSET && ctx->nla[NFTA_SET_ID] && !desc) { nft_trans_set_id(trans) = ntohl(nla_get_be32(ctx->nla[NFTA_SET_ID])); nft_activate_next(ctx->net, set); } nft_trans_set(trans) = set; if (desc) { nft_trans_set_update(trans) = true; nft_trans_set_gc_int(trans) = desc->gc_int; nft_trans_set_timeout(trans) = desc->timeout; nft_trans_set_size(trans) = desc->size; } nft_trans_commit_list_add_tail(ctx->net, trans); return 0; } static int nft_trans_set_add(const struct nft_ctx *ctx, int msg_type, struct nft_set *set) { return __nft_trans_set_add(ctx, msg_type, set, NULL); } static int nft_mapelem_deactivate(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_set_iter *iter, struct nft_elem_priv *elem_priv) { struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); if (!nft_set_elem_active(ext, iter->genmask)) return 0; nft_set_elem_change_active(ctx->net, set, ext); nft_setelem_data_deactivate(ctx->net, set, elem_priv); return 0; } struct nft_set_elem_catchall { struct list_head list; struct rcu_head rcu; struct nft_elem_priv *elem; }; static void nft_map_catchall_deactivate(const struct nft_ctx *ctx, struct nft_set *set) { u8 genmask = nft_genmask_next(ctx->net); struct nft_set_elem_catchall *catchall; struct nft_set_ext *ext; list_for_each_entry(catchall, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); if (!nft_set_elem_active(ext, genmask)) continue; nft_set_elem_change_active(ctx->net, set, ext); nft_setelem_data_deactivate(ctx->net, set, catchall->elem); break; } } static void nft_map_deactivate(const struct nft_ctx *ctx, struct nft_set *set) { struct nft_set_iter iter = { .genmask = nft_genmask_next(ctx->net), .type = NFT_ITER_UPDATE, .fn = nft_mapelem_deactivate, }; set->ops->walk(ctx, set, &iter); WARN_ON_ONCE(iter.err); nft_map_catchall_deactivate(ctx, set); } static int nft_delset(const struct nft_ctx *ctx, struct nft_set *set) { int err; err = nft_trans_set_add(ctx, NFT_MSG_DELSET, set); if (err < 0) return err; if (set->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) nft_map_deactivate(ctx, set); nft_deactivate_next(ctx->net, set); nft_use_dec(&ctx->table->use); return err; } static int nft_trans_obj_add(struct nft_ctx *ctx, int msg_type, struct nft_object *obj) { struct nft_trans *trans; trans = nft_trans_alloc(ctx, msg_type, sizeof(struct nft_trans_obj)); if (trans == NULL) return -ENOMEM; if (msg_type == NFT_MSG_NEWOBJ) nft_activate_next(ctx->net, obj); nft_trans_obj(trans) = obj; nft_trans_commit_list_add_tail(ctx->net, trans); return 0; } static int nft_delobj(struct nft_ctx *ctx, struct nft_object *obj) { int err; err = nft_trans_obj_add(ctx, NFT_MSG_DELOBJ, obj); if (err < 0) return err; nft_deactivate_next(ctx->net, obj); nft_use_dec(&ctx->table->use); return err; } static struct nft_trans * nft_trans_flowtable_add(struct nft_ctx *ctx, int msg_type, struct nft_flowtable *flowtable) { struct nft_trans *trans; trans = nft_trans_alloc(ctx, msg_type, sizeof(struct nft_trans_flowtable)); if (trans == NULL) return ERR_PTR(-ENOMEM); if (msg_type == NFT_MSG_NEWFLOWTABLE) nft_activate_next(ctx->net, flowtable); INIT_LIST_HEAD(&nft_trans_flowtable_hooks(trans)); nft_trans_flowtable(trans) = flowtable; nft_trans_commit_list_add_tail(ctx->net, trans); return trans; } static int nft_delflowtable(struct nft_ctx *ctx, struct nft_flowtable *flowtable) { struct nft_trans *trans; trans = nft_trans_flowtable_add(ctx, NFT_MSG_DELFLOWTABLE, flowtable); if (IS_ERR(trans)) return PTR_ERR(trans); nft_deactivate_next(ctx->net, flowtable); nft_use_dec(&ctx->table->use); return 0; } static void __nft_reg_track_clobber(struct nft_regs_track *track, u8 dreg) { int i; for (i = track->regs[dreg].num_reg; i > 0; i--) __nft_reg_track_cancel(track, dreg - i); } static void __nft_reg_track_update(struct nft_regs_track *track, const struct nft_expr *expr, u8 dreg, u8 num_reg) { track->regs[dreg].selector = expr; track->regs[dreg].bitwise = NULL; track->regs[dreg].num_reg = num_reg; } void nft_reg_track_update(struct nft_regs_track *track, const struct nft_expr *expr, u8 dreg, u8 len) { unsigned int regcount; int i; __nft_reg_track_clobber(track, dreg); regcount = DIV_ROUND_UP(len, NFT_REG32_SIZE); for (i = 0; i < regcount; i++, dreg++) __nft_reg_track_update(track, expr, dreg, i); } EXPORT_SYMBOL_GPL(nft_reg_track_update); void nft_reg_track_cancel(struct nft_regs_track *track, u8 dreg, u8 len) { unsigned int regcount; int i; __nft_reg_track_clobber(track, dreg); regcount = DIV_ROUND_UP(len, NFT_REG32_SIZE); for (i = 0; i < regcount; i++, dreg++) __nft_reg_track_cancel(track, dreg); } EXPORT_SYMBOL_GPL(nft_reg_track_cancel); void __nft_reg_track_cancel(struct nft_regs_track *track, u8 dreg) { track->regs[dreg].selector = NULL; track->regs[dreg].bitwise = NULL; track->regs[dreg].num_reg = 0; } EXPORT_SYMBOL_GPL(__nft_reg_track_cancel); /* * Tables */ static struct nft_table *nft_table_lookup(const struct net *net, const struct nlattr *nla, u8 family, u8 genmask, u32 nlpid) { struct nftables_pernet *nft_net; struct nft_table *table; if (nla == NULL) return ERR_PTR(-EINVAL); nft_net = nft_pernet(net); list_for_each_entry_rcu(table, &nft_net->tables, list, lockdep_is_held(&nft_net->commit_mutex)) { if (!nla_strcmp(nla, table->name) && table->family == family && nft_active_genmask(table, genmask)) { if (nft_table_has_owner(table) && nlpid && table->nlpid != nlpid) return ERR_PTR(-EPERM); return table; } } return ERR_PTR(-ENOENT); } static struct nft_table *nft_table_lookup_byhandle(const struct net *net, const struct nlattr *nla, int family, u8 genmask, u32 nlpid) { struct nftables_pernet *nft_net; struct nft_table *table; nft_net = nft_pernet(net); list_for_each_entry(table, &nft_net->tables, list) { if (be64_to_cpu(nla_get_be64(nla)) == table->handle && table->family == family && nft_active_genmask(table, genmask)) { if (nft_table_has_owner(table) && nlpid && table->nlpid != nlpid) return ERR_PTR(-EPERM); return table; } } return ERR_PTR(-ENOENT); } static inline u64 nf_tables_alloc_handle(struct nft_table *table) { return ++table->hgenerator; } static const struct nft_chain_type *chain_type[NFPROTO_NUMPROTO][NFT_CHAIN_T_MAX]; static const struct nft_chain_type * __nft_chain_type_get(u8 family, enum nft_chain_types type) { if (family >= NFPROTO_NUMPROTO || type >= NFT_CHAIN_T_MAX) return NULL; return chain_type[family][type]; } static const struct nft_chain_type * __nf_tables_chain_type_lookup(const struct nlattr *nla, u8 family) { const struct nft_chain_type *type; int i; for (i = 0; i < NFT_CHAIN_T_MAX; i++) { type = __nft_chain_type_get(family, i); if (!type) continue; if (!nla_strcmp(nla, type->name)) return type; } return NULL; } struct nft_module_request { struct list_head list; char module[MODULE_NAME_LEN]; bool done; }; #ifdef CONFIG_MODULES __printf(2, 3) int nft_request_module(struct net *net, const char *fmt, ...) { char module_name[MODULE_NAME_LEN]; struct nftables_pernet *nft_net; struct nft_module_request *req; va_list args; int ret; va_start(args, fmt); ret = vsnprintf(module_name, MODULE_NAME_LEN, fmt, args); va_end(args); if (ret >= MODULE_NAME_LEN) return 0; nft_net = nft_pernet(net); list_for_each_entry(req, &nft_net->module_list, list) { if (!strcmp(req->module, module_name)) { if (req->done) return 0; /* A request to load this module already exists. */ return -EAGAIN; } } req = kmalloc(sizeof(*req), GFP_KERNEL); if (!req) return -ENOMEM; req->done = false; strscpy(req->module, module_name, MODULE_NAME_LEN); list_add_tail(&req->list, &nft_net->module_list); return -EAGAIN; } EXPORT_SYMBOL_GPL(nft_request_module); #endif static void lockdep_nfnl_nft_mutex_not_held(void) { #ifdef CONFIG_PROVE_LOCKING if (debug_locks) WARN_ON_ONCE(lockdep_nfnl_is_held(NFNL_SUBSYS_NFTABLES)); #endif } static const struct nft_chain_type * nf_tables_chain_type_lookup(struct net *net, const struct nlattr *nla, u8 family, bool autoload) { const struct nft_chain_type *type; type = __nf_tables_chain_type_lookup(nla, family); if (type != NULL) return type; lockdep_nfnl_nft_mutex_not_held(); #ifdef CONFIG_MODULES if (autoload) { if (nft_request_module(net, "nft-chain-%u-%.*s", family, nla_len(nla), (const char *)nla_data(nla)) == -EAGAIN) return ERR_PTR(-EAGAIN); } #endif return ERR_PTR(-ENOENT); } static __be16 nft_base_seq(const struct net *net) { struct nftables_pernet *nft_net = nft_pernet(net); return htons(nft_net->base_seq & 0xffff); } static const struct nla_policy nft_table_policy[NFTA_TABLE_MAX + 1] = { [NFTA_TABLE_NAME] = { .type = NLA_STRING, .len = NFT_TABLE_MAXNAMELEN - 1 }, [NFTA_TABLE_FLAGS] = { .type = NLA_U32 }, [NFTA_TABLE_HANDLE] = { .type = NLA_U64 }, [NFTA_TABLE_USERDATA] = { .type = NLA_BINARY, .len = NFT_USERDATA_MAXLEN } }; static int nf_tables_fill_table_info(struct sk_buff *skb, struct net *net, u32 portid, u32 seq, int event, u32 flags, int family, const struct nft_table *table) { struct nlmsghdr *nlh; event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event); nlh = nfnl_msg_put(skb, portid, seq, event, flags, family, NFNETLINK_V0, nft_base_seq(net)); if (!nlh) goto nla_put_failure; if (nla_put_string(skb, NFTA_TABLE_NAME, table->name) || nla_put_be32(skb, NFTA_TABLE_USE, htonl(table->use)) || nla_put_be64(skb, NFTA_TABLE_HANDLE, cpu_to_be64(table->handle), NFTA_TABLE_PAD)) goto nla_put_failure; if (event == NFT_MSG_DELTABLE) { nlmsg_end(skb, nlh); return 0; } if (nla_put_be32(skb, NFTA_TABLE_FLAGS, htonl(table->flags & NFT_TABLE_F_MASK))) goto nla_put_failure; if (nft_table_has_owner(table) && nla_put_be32(skb, NFTA_TABLE_OWNER, htonl(table->nlpid))) goto nla_put_failure; if (table->udata) { if (nla_put(skb, NFTA_TABLE_USERDATA, table->udlen, table->udata)) goto nla_put_failure; } nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_trim(skb, nlh); return -1; } struct nftnl_skb_parms { bool report; }; #define NFT_CB(skb) (*(struct nftnl_skb_parms*)&((skb)->cb)) static void nft_notify_enqueue(struct sk_buff *skb, bool report, struct list_head *notify_list) { NFT_CB(skb).report = report; list_add_tail(&skb->list, notify_list); } static void nf_tables_table_notify(const struct nft_ctx *ctx, int event) { struct nftables_pernet *nft_net; struct sk_buff *skb; u16 flags = 0; int err; if (!ctx->report && !nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES)) return; skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); if (skb == NULL) goto err; if (ctx->flags & (NLM_F_CREATE | NLM_F_EXCL)) flags |= ctx->flags & (NLM_F_CREATE | NLM_F_EXCL); err = nf_tables_fill_table_info(skb, ctx->net, ctx->portid, ctx->seq, event, flags, ctx->family, ctx->table); if (err < 0) { kfree_skb(skb); goto err; } nft_net = nft_pernet(ctx->net); nft_notify_enqueue(skb, ctx->report, &nft_net->notify_list); return; err: nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, -ENOBUFS); } static int nf_tables_dump_tables(struct sk_buff *skb, struct netlink_callback *cb) { const struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); struct nftables_pernet *nft_net; const struct nft_table *table; unsigned int idx = 0, s_idx = cb->args[0]; struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; rcu_read_lock(); nft_net = nft_pernet(net); cb->seq = READ_ONCE(nft_net->base_seq); list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) continue; if (idx < s_idx) goto cont; if (idx > s_idx) memset(&cb->args[1], 0, sizeof(cb->args) - sizeof(cb->args[0])); if (!nft_is_active(net, table)) continue; if (nf_tables_fill_table_info(skb, net, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NFT_MSG_NEWTABLE, NLM_F_MULTI, table->family, table) < 0) goto done; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); cont: idx++; } done: rcu_read_unlock(); cb->args[0] = idx; return skb->len; } static int nft_netlink_dump_start_rcu(struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, struct netlink_dump_control *c) { int err; if (!try_module_get(THIS_MODULE)) return -EINVAL; rcu_read_unlock(); err = netlink_dump_start(nlsk, skb, nlh, c); rcu_read_lock(); module_put(THIS_MODULE); return err; } /* called with rcu_read_lock held */ static int nf_tables_gettable(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_cur(info->net); u8 family = info->nfmsg->nfgen_family; const struct nft_table *table; struct net *net = info->net; struct sk_buff *skb2; int err; if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .dump = nf_tables_dump_tables, .module = THIS_MODULE, }; return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); } table = nft_table_lookup(net, nla[NFTA_TABLE_NAME], family, genmask, 0); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_TABLE_NAME]); return PTR_ERR(table); } skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC); if (!skb2) return -ENOMEM; err = nf_tables_fill_table_info(skb2, net, NETLINK_CB(skb).portid, info->nlh->nlmsg_seq, NFT_MSG_NEWTABLE, 0, family, table); if (err < 0) goto err_fill_table_info; return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); err_fill_table_info: kfree_skb(skb2); return err; } static void nft_table_disable(struct net *net, struct nft_table *table, u32 cnt) { struct nft_chain *chain; u32 i = 0; list_for_each_entry(chain, &table->chains, list) { if (!nft_is_active_next(net, chain)) continue; if (!nft_is_base_chain(chain)) continue; if (cnt && i++ == cnt) break; nf_tables_unregister_hook(net, table, chain); } } static int nf_tables_table_enable(struct net *net, struct nft_table *table) { struct nft_chain *chain; int err, i = 0; list_for_each_entry(chain, &table->chains, list) { if (!nft_is_active_next(net, chain)) continue; if (!nft_is_base_chain(chain)) continue; err = nf_tables_register_hook(net, table, chain); if (err < 0) goto err_register_hooks; i++; } return 0; err_register_hooks: if (i) nft_table_disable(net, table, i); return err; } static void nf_tables_table_disable(struct net *net, struct nft_table *table) { table->flags &= ~NFT_TABLE_F_DORMANT; nft_table_disable(net, table, 0); table->flags |= NFT_TABLE_F_DORMANT; } #define __NFT_TABLE_F_INTERNAL (NFT_TABLE_F_MASK + 1) #define __NFT_TABLE_F_WAS_DORMANT (__NFT_TABLE_F_INTERNAL << 0) #define __NFT_TABLE_F_WAS_AWAKEN (__NFT_TABLE_F_INTERNAL << 1) #define __NFT_TABLE_F_WAS_ORPHAN (__NFT_TABLE_F_INTERNAL << 2) #define __NFT_TABLE_F_UPDATE (__NFT_TABLE_F_WAS_DORMANT | \ __NFT_TABLE_F_WAS_AWAKEN | \ __NFT_TABLE_F_WAS_ORPHAN) static bool nft_table_pending_update(const struct nft_ctx *ctx) { struct nftables_pernet *nft_net = nft_pernet(ctx->net); struct nft_trans *trans; if (ctx->table->flags & __NFT_TABLE_F_UPDATE) return true; list_for_each_entry(trans, &nft_net->commit_list, list) { if (trans->ctx.table == ctx->table && ((trans->msg_type == NFT_MSG_NEWCHAIN && nft_trans_chain_update(trans)) || (trans->msg_type == NFT_MSG_DELCHAIN && nft_is_base_chain(trans->ctx.chain)))) return true; } return false; } static int nf_tables_updtable(struct nft_ctx *ctx) { struct nft_trans *trans; u32 flags; int ret; if (!ctx->nla[NFTA_TABLE_FLAGS]) return 0; flags = ntohl(nla_get_be32(ctx->nla[NFTA_TABLE_FLAGS])); if (flags & ~NFT_TABLE_F_MASK) return -EOPNOTSUPP; if (flags == (ctx->table->flags & NFT_TABLE_F_MASK)) return 0; if ((nft_table_has_owner(ctx->table) && !(flags & NFT_TABLE_F_OWNER)) || (flags & NFT_TABLE_F_OWNER && !nft_table_is_orphan(ctx->table))) return -EOPNOTSUPP; if ((flags ^ ctx->table->flags) & NFT_TABLE_F_PERSIST) return -EOPNOTSUPP; /* No dormant off/on/off/on games in single transaction */ if (nft_table_pending_update(ctx)) return -EINVAL; trans = nft_trans_alloc(ctx, NFT_MSG_NEWTABLE, sizeof(struct nft_trans_table)); if (trans == NULL) return -ENOMEM; if ((flags & NFT_TABLE_F_DORMANT) && !(ctx->table->flags & NFT_TABLE_F_DORMANT)) { ctx->table->flags |= NFT_TABLE_F_DORMANT; if (!(ctx->table->flags & __NFT_TABLE_F_UPDATE)) ctx->table->flags |= __NFT_TABLE_F_WAS_AWAKEN; } else if (!(flags & NFT_TABLE_F_DORMANT) && ctx->table->flags & NFT_TABLE_F_DORMANT) { ctx->table->flags &= ~NFT_TABLE_F_DORMANT; if (!(ctx->table->flags & __NFT_TABLE_F_UPDATE)) { ret = nf_tables_table_enable(ctx->net, ctx->table); if (ret < 0) goto err_register_hooks; ctx->table->flags |= __NFT_TABLE_F_WAS_DORMANT; } } if ((flags & NFT_TABLE_F_OWNER) && !nft_table_has_owner(ctx->table)) { ctx->table->nlpid = ctx->portid; ctx->table->flags |= NFT_TABLE_F_OWNER | __NFT_TABLE_F_WAS_ORPHAN; } nft_trans_table_update(trans) = true; nft_trans_commit_list_add_tail(ctx->net, trans); return 0; err_register_hooks: ctx->table->flags |= NFT_TABLE_F_DORMANT; nft_trans_destroy(trans); return ret; } static u32 nft_chain_hash(const void *data, u32 len, u32 seed) { const char *name = data; return jhash(name, strlen(name), seed); } static u32 nft_chain_hash_obj(const void *data, u32 len, u32 seed) { const struct nft_chain *chain = data; return nft_chain_hash(chain->name, 0, seed); } static int nft_chain_hash_cmp(struct rhashtable_compare_arg *arg, const void *ptr) { const struct nft_chain *chain = ptr; const char *name = arg->key; return strcmp(chain->name, name); } static u32 nft_objname_hash(const void *data, u32 len, u32 seed) { const struct nft_object_hash_key *k = data; seed ^= hash_ptr(k->table, 32); return jhash(k->name, strlen(k->name), seed); } static u32 nft_objname_hash_obj(const void *data, u32 len, u32 seed) { const struct nft_object *obj = data; return nft_objname_hash(&obj->key, 0, seed); } static int nft_objname_hash_cmp(struct rhashtable_compare_arg *arg, const void *ptr) { const struct nft_object_hash_key *k = arg->key; const struct nft_object *obj = ptr; if (obj->key.table != k->table) return -1; return strcmp(obj->key.name, k->name); } static bool nft_supported_family(u8 family) { return false #ifdef CONFIG_NF_TABLES_INET || family == NFPROTO_INET #endif #ifdef CONFIG_NF_TABLES_IPV4 || family == NFPROTO_IPV4 #endif #ifdef CONFIG_NF_TABLES_ARP || family == NFPROTO_ARP #endif #ifdef CONFIG_NF_TABLES_NETDEV || family == NFPROTO_NETDEV #endif #if IS_ENABLED(CONFIG_NF_TABLES_BRIDGE) || family == NFPROTO_BRIDGE #endif #ifdef CONFIG_NF_TABLES_IPV6 || family == NFPROTO_IPV6 #endif ; } static int nf_tables_newtable(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct nftables_pernet *nft_net = nft_pernet(info->net); struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); u8 family = info->nfmsg->nfgen_family; struct net *net = info->net; const struct nlattr *attr; struct nft_table *table; struct nft_ctx ctx; u32 flags = 0; int err; if (!nft_supported_family(family)) return -EOPNOTSUPP; lockdep_assert_held(&nft_net->commit_mutex); attr = nla[NFTA_TABLE_NAME]; table = nft_table_lookup(net, attr, family, genmask, NETLINK_CB(skb).portid); if (IS_ERR(table)) { if (PTR_ERR(table) != -ENOENT) return PTR_ERR(table); } else { if (info->nlh->nlmsg_flags & NLM_F_EXCL) { NL_SET_BAD_ATTR(extack, attr); return -EEXIST; } if (info->nlh->nlmsg_flags & NLM_F_REPLACE) return -EOPNOTSUPP; nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); return nf_tables_updtable(&ctx); } if (nla[NFTA_TABLE_FLAGS]) { flags = ntohl(nla_get_be32(nla[NFTA_TABLE_FLAGS])); if (flags & ~NFT_TABLE_F_MASK) return -EOPNOTSUPP; } err = -ENOMEM; table = kzalloc(sizeof(*table), GFP_KERNEL_ACCOUNT); if (table == NULL) goto err_kzalloc; table->validate_state = nft_net->validate_state; table->name = nla_strdup(attr, GFP_KERNEL_ACCOUNT); if (table->name == NULL) goto err_strdup; if (nla[NFTA_TABLE_USERDATA]) { table->udata = nla_memdup(nla[NFTA_TABLE_USERDATA], GFP_KERNEL_ACCOUNT); if (table->udata == NULL) goto err_table_udata; table->udlen = nla_len(nla[NFTA_TABLE_USERDATA]); } err = rhltable_init(&table->chains_ht, &nft_chain_ht_params); if (err) goto err_chain_ht; INIT_LIST_HEAD(&table->chains); INIT_LIST_HEAD(&table->sets); INIT_LIST_HEAD(&table->objects); INIT_LIST_HEAD(&table->flowtables); table->family = family; table->flags = flags; table->handle = ++nft_net->table_handle; if (table->flags & NFT_TABLE_F_OWNER) table->nlpid = NETLINK_CB(skb).portid; nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); err = nft_trans_table_add(&ctx, NFT_MSG_NEWTABLE); if (err < 0) goto err_trans; list_add_tail_rcu(&table->list, &nft_net->tables); return 0; err_trans: rhltable_destroy(&table->chains_ht); err_chain_ht: kfree(table->udata); err_table_udata: kfree(table->name); err_strdup: kfree(table); err_kzalloc: return err; } static int nft_flush_table(struct nft_ctx *ctx) { struct nft_flowtable *flowtable, *nft; struct nft_chain *chain, *nc; struct nft_object *obj, *ne; struct nft_set *set, *ns; int err; list_for_each_entry(chain, &ctx->table->chains, list) { if (!nft_is_active_next(ctx->net, chain)) continue; if (nft_chain_binding(chain)) continue; ctx->chain = chain; err = nft_delrule_by_chain(ctx); if (err < 0) goto out; } list_for_each_entry_safe(set, ns, &ctx->table->sets, list) { if (!nft_is_active_next(ctx->net, set)) continue; if (nft_set_is_anonymous(set)) continue; err = nft_delset(ctx, set); if (err < 0) goto out; } list_for_each_entry_safe(flowtable, nft, &ctx->table->flowtables, list) { if (!nft_is_active_next(ctx->net, flowtable)) continue; err = nft_delflowtable(ctx, flowtable); if (err < 0) goto out; } list_for_each_entry_safe(obj, ne, &ctx->table->objects, list) { if (!nft_is_active_next(ctx->net, obj)) continue; err = nft_delobj(ctx, obj); if (err < 0) goto out; } list_for_each_entry_safe(chain, nc, &ctx->table->chains, list) { if (!nft_is_active_next(ctx->net, chain)) continue; if (nft_chain_binding(chain)) continue; ctx->chain = chain; err = nft_delchain(ctx); if (err < 0) goto out; } err = nft_deltable(ctx); out: return err; } static int nft_flush(struct nft_ctx *ctx, int family) { struct nftables_pernet *nft_net = nft_pernet(ctx->net); const struct nlattr * const *nla = ctx->nla; struct nft_table *table, *nt; int err = 0; list_for_each_entry_safe(table, nt, &nft_net->tables, list) { if (family != AF_UNSPEC && table->family != family) continue; ctx->family = table->family; if (!nft_is_active_next(ctx->net, table)) continue; if (nft_table_has_owner(table) && table->nlpid != ctx->portid) continue; if (nla[NFTA_TABLE_NAME] && nla_strcmp(nla[NFTA_TABLE_NAME], table->name) != 0) continue; ctx->table = table; err = nft_flush_table(ctx); if (err < 0) goto out; } out: return err; } static int nf_tables_deltable(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); u8 family = info->nfmsg->nfgen_family; struct net *net = info->net; const struct nlattr *attr; struct nft_table *table; struct nft_ctx ctx; nft_ctx_init(&ctx, net, skb, info->nlh, 0, NULL, NULL, nla); if (family == AF_UNSPEC || (!nla[NFTA_TABLE_NAME] && !nla[NFTA_TABLE_HANDLE])) return nft_flush(&ctx, family); if (nla[NFTA_TABLE_HANDLE]) { attr = nla[NFTA_TABLE_HANDLE]; table = nft_table_lookup_byhandle(net, attr, family, genmask, NETLINK_CB(skb).portid); } else { attr = nla[NFTA_TABLE_NAME]; table = nft_table_lookup(net, attr, family, genmask, NETLINK_CB(skb).portid); } if (IS_ERR(table)) { if (PTR_ERR(table) == -ENOENT && NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_DESTROYTABLE) return 0; NL_SET_BAD_ATTR(extack, attr); return PTR_ERR(table); } if (info->nlh->nlmsg_flags & NLM_F_NONREC && table->use > 0) return -EBUSY; ctx.family = family; ctx.table = table; return nft_flush_table(&ctx); } static void nf_tables_table_destroy(struct nft_ctx *ctx) { if (WARN_ON(ctx->table->use > 0)) return; rhltable_destroy(&ctx->table->chains_ht); kfree(ctx->table->name); kfree(ctx->table->udata); kfree(ctx->table); } void nft_register_chain_type(const struct nft_chain_type *ctype) { nfnl_lock(NFNL_SUBSYS_NFTABLES); if (WARN_ON(__nft_chain_type_get(ctype->family, ctype->type))) { nfnl_unlock(NFNL_SUBSYS_NFTABLES); return; } chain_type[ctype->family][ctype->type] = ctype; nfnl_unlock(NFNL_SUBSYS_NFTABLES); } EXPORT_SYMBOL_GPL(nft_register_chain_type); void nft_unregister_chain_type(const struct nft_chain_type *ctype) { nfnl_lock(NFNL_SUBSYS_NFTABLES); chain_type[ctype->family][ctype->type] = NULL; nfnl_unlock(NFNL_SUBSYS_NFTABLES); } EXPORT_SYMBOL_GPL(nft_unregister_chain_type); /* * Chains */ static struct nft_chain * nft_chain_lookup_byhandle(const struct nft_table *table, u64 handle, u8 genmask) { struct nft_chain *chain; list_for_each_entry(chain, &table->chains, list) { if (chain->handle == handle && nft_active_genmask(chain, genmask)) return chain; } return ERR_PTR(-ENOENT); } static bool lockdep_commit_lock_is_held(const struct net *net) { #ifdef CONFIG_PROVE_LOCKING struct nftables_pernet *nft_net = nft_pernet(net); return lockdep_is_held(&nft_net->commit_mutex); #else return true; #endif } static struct nft_chain *nft_chain_lookup(struct net *net, struct nft_table *table, const struct nlattr *nla, u8 genmask) { char search[NFT_CHAIN_MAXNAMELEN + 1]; struct rhlist_head *tmp, *list; struct nft_chain *chain; if (nla == NULL) return ERR_PTR(-EINVAL); nla_strscpy(search, nla, sizeof(search)); WARN_ON(!rcu_read_lock_held() && !lockdep_commit_lock_is_held(net)); chain = ERR_PTR(-ENOENT); rcu_read_lock(); list = rhltable_lookup(&table->chains_ht, search, nft_chain_ht_params); if (!list) goto out_unlock; rhl_for_each_entry_rcu(chain, tmp, list, rhlhead) { if (nft_active_genmask(chain, genmask)) goto out_unlock; } chain = ERR_PTR(-ENOENT); out_unlock: rcu_read_unlock(); return chain; } static const struct nla_policy nft_chain_policy[NFTA_CHAIN_MAX + 1] = { [NFTA_CHAIN_TABLE] = { .type = NLA_STRING, .len = NFT_TABLE_MAXNAMELEN - 1 }, [NFTA_CHAIN_HANDLE] = { .type = NLA_U64 }, [NFTA_CHAIN_NAME] = { .type = NLA_STRING, .len = NFT_CHAIN_MAXNAMELEN - 1 }, [NFTA_CHAIN_HOOK] = { .type = NLA_NESTED }, [NFTA_CHAIN_POLICY] = { .type = NLA_U32 }, [NFTA_CHAIN_TYPE] = { .type = NLA_STRING, .len = NFT_MODULE_AUTOLOAD_LIMIT }, [NFTA_CHAIN_COUNTERS] = { .type = NLA_NESTED }, [NFTA_CHAIN_FLAGS] = { .type = NLA_U32 }, [NFTA_CHAIN_ID] = { .type = NLA_U32 }, [NFTA_CHAIN_USERDATA] = { .type = NLA_BINARY, .len = NFT_USERDATA_MAXLEN }, }; static const struct nla_policy nft_hook_policy[NFTA_HOOK_MAX + 1] = { [NFTA_HOOK_HOOKNUM] = { .type = NLA_U32 }, [NFTA_HOOK_PRIORITY] = { .type = NLA_U32 }, [NFTA_HOOK_DEV] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, }; static int nft_dump_stats(struct sk_buff *skb, struct nft_stats __percpu *stats) { struct nft_stats *cpu_stats, total; struct nlattr *nest; unsigned int seq; u64 pkts, bytes; int cpu; if (!stats) return 0; memset(&total, 0, sizeof(total)); for_each_possible_cpu(cpu) { cpu_stats = per_cpu_ptr(stats, cpu); do { seq = u64_stats_fetch_begin(&cpu_stats->syncp); pkts = cpu_stats->pkts; bytes = cpu_stats->bytes; } while (u64_stats_fetch_retry(&cpu_stats->syncp, seq)); total.pkts += pkts; total.bytes += bytes; } nest = nla_nest_start_noflag(skb, NFTA_CHAIN_COUNTERS); if (nest == NULL) goto nla_put_failure; if (nla_put_be64(skb, NFTA_COUNTER_PACKETS, cpu_to_be64(total.pkts), NFTA_COUNTER_PAD) || nla_put_be64(skb, NFTA_COUNTER_BYTES, cpu_to_be64(total.bytes), NFTA_COUNTER_PAD)) goto nla_put_failure; nla_nest_end(skb, nest); return 0; nla_put_failure: return -ENOSPC; } static int nft_dump_basechain_hook(struct sk_buff *skb, int family, const struct nft_base_chain *basechain, const struct list_head *hook_list) { const struct nf_hook_ops *ops = &basechain->ops; struct nft_hook *hook, *first = NULL; struct nlattr *nest, *nest_devs; int n = 0; nest = nla_nest_start_noflag(skb, NFTA_CHAIN_HOOK); if (nest == NULL) goto nla_put_failure; if (nla_put_be32(skb, NFTA_HOOK_HOOKNUM, htonl(ops->hooknum))) goto nla_put_failure; if (nla_put_be32(skb, NFTA_HOOK_PRIORITY, htonl(ops->priority))) goto nla_put_failure; if (nft_base_chain_netdev(family, ops->hooknum)) { nest_devs = nla_nest_start_noflag(skb, NFTA_HOOK_DEVS); if (!nest_devs) goto nla_put_failure; if (!hook_list) hook_list = &basechain->hook_list; list_for_each_entry(hook, hook_list, list) { if (!first) first = hook; if (nla_put_string(skb, NFTA_DEVICE_NAME, hook->ops.dev->name)) goto nla_put_failure; n++; } nla_nest_end(skb, nest_devs); if (n == 1 && nla_put_string(skb, NFTA_HOOK_DEV, first->ops.dev->name)) goto nla_put_failure; } nla_nest_end(skb, nest); return 0; nla_put_failure: return -1; } static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net, u32 portid, u32 seq, int event, u32 flags, int family, const struct nft_table *table, const struct nft_chain *chain, const struct list_head *hook_list) { struct nlmsghdr *nlh; event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event); nlh = nfnl_msg_put(skb, portid, seq, event, flags, family, NFNETLINK_V0, nft_base_seq(net)); if (!nlh) goto nla_put_failure; if (nla_put_string(skb, NFTA_CHAIN_TABLE, table->name) || nla_put_string(skb, NFTA_CHAIN_NAME, chain->name) || nla_put_be64(skb, NFTA_CHAIN_HANDLE, cpu_to_be64(chain->handle), NFTA_CHAIN_PAD)) goto nla_put_failure; if (event == NFT_MSG_DELCHAIN && !hook_list) { nlmsg_end(skb, nlh); return 0; } if (nft_is_base_chain(chain)) { const struct nft_base_chain *basechain = nft_base_chain(chain); struct nft_stats __percpu *stats; if (nft_dump_basechain_hook(skb, family, basechain, hook_list)) goto nla_put_failure; if (nla_put_be32(skb, NFTA_CHAIN_POLICY, htonl(basechain->policy))) goto nla_put_failure; if (nla_put_string(skb, NFTA_CHAIN_TYPE, basechain->type->name)) goto nla_put_failure; stats = rcu_dereference_check(basechain->stats, lockdep_commit_lock_is_held(net)); if (nft_dump_stats(skb, stats)) goto nla_put_failure; } if (chain->flags && nla_put_be32(skb, NFTA_CHAIN_FLAGS, htonl(chain->flags))) goto nla_put_failure; if (nla_put_be32(skb, NFTA_CHAIN_USE, htonl(chain->use))) goto nla_put_failure; if (chain->udata && nla_put(skb, NFTA_CHAIN_USERDATA, chain->udlen, chain->udata)) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_trim(skb, nlh); return -1; } static void nf_tables_chain_notify(const struct nft_ctx *ctx, int event, const struct list_head *hook_list) { struct nftables_pernet *nft_net; struct sk_buff *skb; u16 flags = 0; int err; if (!ctx->report && !nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES)) return; skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); if (skb == NULL) goto err; if (ctx->flags & (NLM_F_CREATE | NLM_F_EXCL)) flags |= ctx->flags & (NLM_F_CREATE | NLM_F_EXCL); err = nf_tables_fill_chain_info(skb, ctx->net, ctx->portid, ctx->seq, event, flags, ctx->family, ctx->table, ctx->chain, hook_list); if (err < 0) { kfree_skb(skb); goto err; } nft_net = nft_pernet(ctx->net); nft_notify_enqueue(skb, ctx->report, &nft_net->notify_list); return; err: nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, -ENOBUFS); } static int nf_tables_dump_chains(struct sk_buff *skb, struct netlink_callback *cb) { const struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); unsigned int idx = 0, s_idx = cb->args[0]; struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; struct nftables_pernet *nft_net; const struct nft_table *table; const struct nft_chain *chain; rcu_read_lock(); nft_net = nft_pernet(net); cb->seq = READ_ONCE(nft_net->base_seq); list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) continue; list_for_each_entry_rcu(chain, &table->chains, list) { if (idx < s_idx) goto cont; if (idx > s_idx) memset(&cb->args[1], 0, sizeof(cb->args) - sizeof(cb->args[0])); if (!nft_is_active(net, chain)) continue; if (nf_tables_fill_chain_info(skb, net, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NFT_MSG_NEWCHAIN, NLM_F_MULTI, table->family, table, chain, NULL) < 0) goto done; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); cont: idx++; } } done: rcu_read_unlock(); cb->args[0] = idx; return skb->len; } /* called with rcu_read_lock held */ static int nf_tables_getchain(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_cur(info->net); u8 family = info->nfmsg->nfgen_family; const struct nft_chain *chain; struct net *net = info->net; struct nft_table *table; struct sk_buff *skb2; int err; if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .dump = nf_tables_dump_chains, .module = THIS_MODULE, }; return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); } table = nft_table_lookup(net, nla[NFTA_CHAIN_TABLE], family, genmask, 0); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_TABLE]); return PTR_ERR(table); } chain = nft_chain_lookup(net, table, nla[NFTA_CHAIN_NAME], genmask); if (IS_ERR(chain)) { NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_NAME]); return PTR_ERR(chain); } skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC); if (!skb2) return -ENOMEM; err = nf_tables_fill_chain_info(skb2, net, NETLINK_CB(skb).portid, info->nlh->nlmsg_seq, NFT_MSG_NEWCHAIN, 0, family, table, chain, NULL); if (err < 0) goto err_fill_chain_info; return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); err_fill_chain_info: kfree_skb(skb2); return err; } static const struct nla_policy nft_counter_policy[NFTA_COUNTER_MAX + 1] = { [NFTA_COUNTER_PACKETS] = { .type = NLA_U64 }, [NFTA_COUNTER_BYTES] = { .type = NLA_U64 }, }; static struct nft_stats __percpu *nft_stats_alloc(const struct nlattr *attr) { struct nlattr *tb[NFTA_COUNTER_MAX+1]; struct nft_stats __percpu *newstats; struct nft_stats *stats; int err; err = nla_parse_nested_deprecated(tb, NFTA_COUNTER_MAX, attr, nft_counter_policy, NULL); if (err < 0) return ERR_PTR(err); if (!tb[NFTA_COUNTER_BYTES] || !tb[NFTA_COUNTER_PACKETS]) return ERR_PTR(-EINVAL); newstats = netdev_alloc_pcpu_stats(struct nft_stats); if (newstats == NULL) return ERR_PTR(-ENOMEM); /* Restore old counters on this cpu, no problem. Per-cpu statistics * are not exposed to userspace. */ preempt_disable(); stats = this_cpu_ptr(newstats); stats->bytes = be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_BYTES])); stats->pkts = be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_PACKETS])); preempt_enable(); return newstats; } static void nft_chain_stats_replace(struct nft_trans *trans) { struct nft_base_chain *chain = nft_base_chain(trans->ctx.chain); if (!nft_trans_chain_stats(trans)) return; nft_trans_chain_stats(trans) = rcu_replace_pointer(chain->stats, nft_trans_chain_stats(trans), lockdep_commit_lock_is_held(trans->ctx.net)); if (!nft_trans_chain_stats(trans)) static_branch_inc(&nft_counters_enabled); } static void nf_tables_chain_free_chain_rules(struct nft_chain *chain) { struct nft_rule_blob *g0 = rcu_dereference_raw(chain->blob_gen_0); struct nft_rule_blob *g1 = rcu_dereference_raw(chain->blob_gen_1); if (g0 != g1) kvfree(g1); kvfree(g0); /* should be NULL either via abort or via successful commit */ WARN_ON_ONCE(chain->blob_next); kvfree(chain->blob_next); } void nf_tables_chain_destroy(struct nft_ctx *ctx) { struct nft_chain *chain = ctx->chain; struct nft_hook *hook, *next; if (WARN_ON(chain->use > 0)) return; /* no concurrent access possible anymore */ nf_tables_chain_free_chain_rules(chain); if (nft_is_base_chain(chain)) { struct nft_base_chain *basechain = nft_base_chain(chain); if (nft_base_chain_netdev(ctx->family, basechain->ops.hooknum)) { list_for_each_entry_safe(hook, next, &basechain->hook_list, list) { list_del_rcu(&hook->list); kfree_rcu(hook, rcu); } } module_put(basechain->type->owner); if (rcu_access_pointer(basechain->stats)) { static_branch_dec(&nft_counters_enabled); free_percpu(rcu_dereference_raw(basechain->stats)); } kfree(chain->name); kfree(chain->udata); kfree(basechain); } else { kfree(chain->name); kfree(chain->udata); kfree(chain); } } static struct nft_hook *nft_netdev_hook_alloc(struct net *net, const struct nlattr *attr) { struct net_device *dev; char ifname[IFNAMSIZ]; struct nft_hook *hook; int err; hook = kzalloc(sizeof(struct nft_hook), GFP_KERNEL_ACCOUNT); if (!hook) { err = -ENOMEM; goto err_hook_alloc; } nla_strscpy(ifname, attr, IFNAMSIZ); /* nf_tables_netdev_event() is called under rtnl_mutex, this is * indirectly serializing all the other holders of the commit_mutex with * the rtnl_mutex. */ dev = __dev_get_by_name(net, ifname); if (!dev) { err = -ENOENT; goto err_hook_dev; } hook->ops.dev = dev; return hook; err_hook_dev: kfree(hook); err_hook_alloc: return ERR_PTR(err); } static struct nft_hook *nft_hook_list_find(struct list_head *hook_list, const struct nft_hook *this) { struct nft_hook *hook; list_for_each_entry(hook, hook_list, list) { if (this->ops.dev == hook->ops.dev) return hook; } return NULL; } static int nf_tables_parse_netdev_hooks(struct net *net, const struct nlattr *attr, struct list_head *hook_list, struct netlink_ext_ack *extack) { struct nft_hook *hook, *next; const struct nlattr *tmp; int rem, n = 0, err; nla_for_each_nested(tmp, attr, rem) { if (nla_type(tmp) != NFTA_DEVICE_NAME) { err = -EINVAL; goto err_hook; } hook = nft_netdev_hook_alloc(net, tmp); if (IS_ERR(hook)) { NL_SET_BAD_ATTR(extack, tmp); err = PTR_ERR(hook); goto err_hook; } if (nft_hook_list_find(hook_list, hook)) { NL_SET_BAD_ATTR(extack, tmp); kfree(hook); err = -EEXIST; goto err_hook; } list_add_tail(&hook->list, hook_list); n++; if (n == NFT_NETDEVICE_MAX) { err = -EFBIG; goto err_hook; } } return 0; err_hook: list_for_each_entry_safe(hook, next, hook_list, list) { list_del(&hook->list); kfree(hook); } return err; } struct nft_chain_hook { u32 num; s32 priority; const struct nft_chain_type *type; struct list_head list; }; static int nft_chain_parse_netdev(struct net *net, struct nlattr *tb[], struct list_head *hook_list, struct netlink_ext_ack *extack, u32 flags) { struct nft_hook *hook; int err; if (tb[NFTA_HOOK_DEV]) { hook = nft_netdev_hook_alloc(net, tb[NFTA_HOOK_DEV]); if (IS_ERR(hook)) { NL_SET_BAD_ATTR(extack, tb[NFTA_HOOK_DEV]); return PTR_ERR(hook); } list_add_tail(&hook->list, hook_list); } else if (tb[NFTA_HOOK_DEVS]) { err = nf_tables_parse_netdev_hooks(net, tb[NFTA_HOOK_DEVS], hook_list, extack); if (err < 0) return err; } if (flags & NFT_CHAIN_HW_OFFLOAD && list_empty(hook_list)) return -EINVAL; return 0; } static int nft_chain_parse_hook(struct net *net, struct nft_base_chain *basechain, const struct nlattr * const nla[], struct nft_chain_hook *hook, u8 family, u32 flags, struct netlink_ext_ack *extack) { struct nftables_pernet *nft_net = nft_pernet(net); struct nlattr *ha[NFTA_HOOK_MAX + 1]; const struct nft_chain_type *type; int err; lockdep_assert_held(&nft_net->commit_mutex); lockdep_nfnl_nft_mutex_not_held(); err = nla_parse_nested_deprecated(ha, NFTA_HOOK_MAX, nla[NFTA_CHAIN_HOOK], nft_hook_policy, NULL); if (err < 0) return err; if (!basechain) { if (!ha[NFTA_HOOK_HOOKNUM] || !ha[NFTA_HOOK_PRIORITY]) { NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_NAME]); return -ENOENT; } hook->num = ntohl(nla_get_be32(ha[NFTA_HOOK_HOOKNUM])); hook->priority = ntohl(nla_get_be32(ha[NFTA_HOOK_PRIORITY])); type = __nft_chain_type_get(family, NFT_CHAIN_T_DEFAULT); if (!type) return -EOPNOTSUPP; if (nla[NFTA_CHAIN_TYPE]) { type = nf_tables_chain_type_lookup(net, nla[NFTA_CHAIN_TYPE], family, true); if (IS_ERR(type)) { NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_TYPE]); return PTR_ERR(type); } } if (hook->num >= NFT_MAX_HOOKS || !(type->hook_mask & (1 << hook->num))) return -EOPNOTSUPP; if (type->type == NFT_CHAIN_T_NAT && hook->priority <= NF_IP_PRI_CONNTRACK) return -EOPNOTSUPP; } else { if (ha[NFTA_HOOK_HOOKNUM]) { hook->num = ntohl(nla_get_be32(ha[NFTA_HOOK_HOOKNUM])); if (hook->num != basechain->ops.hooknum) return -EOPNOTSUPP; } if (ha[NFTA_HOOK_PRIORITY]) { hook->priority = ntohl(nla_get_be32(ha[NFTA_HOOK_PRIORITY])); if (hook->priority != basechain->ops.priority) return -EOPNOTSUPP; } if (nla[NFTA_CHAIN_TYPE]) { type = __nf_tables_chain_type_lookup(nla[NFTA_CHAIN_TYPE], family); if (!type) { NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_TYPE]); return -ENOENT; } } else { type = basechain->type; } } if (!try_module_get(type->owner)) { if (nla[NFTA_CHAIN_TYPE]) NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_TYPE]); return -ENOENT; } hook->type = type; INIT_LIST_HEAD(&hook->list); if (nft_base_chain_netdev(family, hook->num)) { err = nft_chain_parse_netdev(net, ha, &hook->list, extack, flags); if (err < 0) { module_put(type->owner); return err; } } else if (ha[NFTA_HOOK_DEV] || ha[NFTA_HOOK_DEVS]) { module_put(type->owner); return -EOPNOTSUPP; } return 0; } static void nft_chain_release_hook(struct nft_chain_hook *hook) { struct nft_hook *h, *next; list_for_each_entry_safe(h, next, &hook->list, list) { list_del(&h->list); kfree(h); } module_put(hook->type->owner); } static void nft_last_rule(const struct nft_chain *chain, const void *ptr) { struct nft_rule_dp_last *lrule; BUILD_BUG_ON(offsetof(struct nft_rule_dp_last, end) != 0); lrule = (struct nft_rule_dp_last *)ptr; lrule->end.is_last = 1; lrule->chain = chain; /* blob size does not include the trailer rule */ } static struct nft_rule_blob *nf_tables_chain_alloc_rules(const struct nft_chain *chain, unsigned int size) { struct nft_rule_blob *blob; if (size > INT_MAX) return NULL; size += sizeof(struct nft_rule_blob) + sizeof(struct nft_rule_dp_last); blob = kvmalloc(size, GFP_KERNEL_ACCOUNT); if (!blob) return NULL; blob->size = 0; nft_last_rule(chain, blob->data); return blob; } static void nft_basechain_hook_init(struct nf_hook_ops *ops, u8 family, const struct nft_chain_hook *hook, struct nft_chain *chain) { ops->pf = family; ops->hooknum = hook->num; ops->priority = hook->priority; ops->priv = chain; ops->hook = hook->type->hooks[ops->hooknum]; ops->hook_ops_type = NF_HOOK_OP_NF_TABLES; } static int nft_basechain_init(struct nft_base_chain *basechain, u8 family, struct nft_chain_hook *hook, u32 flags) { struct nft_chain *chain; struct nft_hook *h; basechain->type = hook->type; INIT_LIST_HEAD(&basechain->hook_list); chain = &basechain->chain; if (nft_base_chain_netdev(family, hook->num)) { list_splice_init(&hook->list, &basechain->hook_list); list_for_each_entry(h, &basechain->hook_list, list) nft_basechain_hook_init(&h->ops, family, hook, chain); } nft_basechain_hook_init(&basechain->ops, family, hook, chain); chain->flags |= NFT_CHAIN_BASE | flags; basechain->policy = NF_ACCEPT; if (chain->flags & NFT_CHAIN_HW_OFFLOAD && !nft_chain_offload_support(basechain)) { list_splice_init(&basechain->hook_list, &hook->list); return -EOPNOTSUPP; } flow_block_init(&basechain->flow_block); return 0; } int nft_chain_add(struct nft_table *table, struct nft_chain *chain) { int err; err = rhltable_insert_key(&table->chains_ht, chain->name, &chain->rhlhead, nft_chain_ht_params); if (err) return err; list_add_tail_rcu(&chain->list, &table->chains); return 0; } static u64 chain_id; static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, u8 policy, u32 flags, struct netlink_ext_ack *extack) { const struct nlattr * const *nla = ctx->nla; struct nft_table *table = ctx->table; struct nft_base_chain *basechain; struct net *net = ctx->net; char name[NFT_NAME_MAXLEN]; struct nft_rule_blob *blob; struct nft_trans *trans; struct nft_chain *chain; int err; if (nla[NFTA_CHAIN_HOOK]) { struct nft_stats __percpu *stats = NULL; struct nft_chain_hook hook = {}; if (table->flags & __NFT_TABLE_F_UPDATE) return -EINVAL; if (flags & NFT_CHAIN_BINDING) return -EOPNOTSUPP; err = nft_chain_parse_hook(net, NULL, nla, &hook, family, flags, extack); if (err < 0) return err; basechain = kzalloc(sizeof(*basechain), GFP_KERNEL_ACCOUNT); if (basechain == NULL) { nft_chain_release_hook(&hook); return -ENOMEM; } chain = &basechain->chain; if (nla[NFTA_CHAIN_COUNTERS]) { stats = nft_stats_alloc(nla[NFTA_CHAIN_COUNTERS]); if (IS_ERR(stats)) { nft_chain_release_hook(&hook); kfree(basechain); return PTR_ERR(stats); } rcu_assign_pointer(basechain->stats, stats); } err = nft_basechain_init(basechain, family, &hook, flags); if (err < 0) { nft_chain_release_hook(&hook); kfree(basechain); free_percpu(stats); return err; } if (stats) static_branch_inc(&nft_counters_enabled); } else { if (flags & NFT_CHAIN_BASE) return -EINVAL; if (flags & NFT_CHAIN_HW_OFFLOAD) return -EOPNOTSUPP; chain = kzalloc(sizeof(*chain), GFP_KERNEL_ACCOUNT); if (chain == NULL) return -ENOMEM; chain->flags = flags; } ctx->chain = chain; INIT_LIST_HEAD(&chain->rules); chain->handle = nf_tables_alloc_handle(table); chain->table = table; if (nla[NFTA_CHAIN_NAME]) { chain->name = nla_strdup(nla[NFTA_CHAIN_NAME], GFP_KERNEL_ACCOUNT); } else { if (!(flags & NFT_CHAIN_BINDING)) { err = -EINVAL; goto err_destroy_chain; } snprintf(name, sizeof(name), "__chain%llu", ++chain_id); chain->name = kstrdup(name, GFP_KERNEL_ACCOUNT); } if (!chain->name) { err = -ENOMEM; goto err_destroy_chain; } if (nla[NFTA_CHAIN_USERDATA]) { chain->udata = nla_memdup(nla[NFTA_CHAIN_USERDATA], GFP_KERNEL_ACCOUNT); if (chain->udata == NULL) { err = -ENOMEM; goto err_destroy_chain; } chain->udlen = nla_len(nla[NFTA_CHAIN_USERDATA]); } blob = nf_tables_chain_alloc_rules(chain, 0); if (!blob) { err = -ENOMEM; goto err_destroy_chain; } RCU_INIT_POINTER(chain->blob_gen_0, blob); RCU_INIT_POINTER(chain->blob_gen_1, blob); if (!nft_use_inc(&table->use)) { err = -EMFILE; goto err_destroy_chain; } trans = nft_trans_chain_add(ctx, NFT_MSG_NEWCHAIN); if (IS_ERR(trans)) { err = PTR_ERR(trans); goto err_trans; } nft_trans_chain_policy(trans) = NFT_CHAIN_POLICY_UNSET; if (nft_is_base_chain(chain)) nft_trans_chain_policy(trans) = policy; err = nft_chain_add(table, chain); if (err < 0) goto err_chain_add; /* This must be LAST to ensure no packets are walking over this chain. */ err = nf_tables_register_hook(net, table, chain); if (err < 0) goto err_register_hook; return 0; err_register_hook: nft_chain_del(chain); err_chain_add: nft_trans_destroy(trans); err_trans: nft_use_dec_restore(&table->use); err_destroy_chain: nf_tables_chain_destroy(ctx); return err; } static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, u32 flags, const struct nlattr *attr, struct netlink_ext_ack *extack) { const struct nlattr * const *nla = ctx->nla; struct nft_base_chain *basechain = NULL; struct nft_table *table = ctx->table; struct nft_chain *chain = ctx->chain; struct nft_chain_hook hook = {}; struct nft_stats *stats = NULL; struct nft_hook *h, *next; struct nf_hook_ops *ops; struct nft_trans *trans; bool unregister = false; int err; if (chain->flags ^ flags) return -EOPNOTSUPP; INIT_LIST_HEAD(&hook.list); if (nla[NFTA_CHAIN_HOOK]) { if (!nft_is_base_chain(chain)) { NL_SET_BAD_ATTR(extack, attr); return -EEXIST; } basechain = nft_base_chain(chain); err = nft_chain_parse_hook(ctx->net, basechain, nla, &hook, ctx->family, flags, extack); if (err < 0) return err; if (basechain->type != hook.type) { nft_chain_release_hook(&hook); NL_SET_BAD_ATTR(extack, attr); return -EEXIST; } if (nft_base_chain_netdev(ctx->family, basechain->ops.hooknum)) { list_for_each_entry_safe(h, next, &hook.list, list) { h->ops.pf = basechain->ops.pf; h->ops.hooknum = basechain->ops.hooknum; h->ops.priority = basechain->ops.priority; h->ops.priv = basechain->ops.priv; h->ops.hook = basechain->ops.hook; if (nft_hook_list_find(&basechain->hook_list, h)) { list_del(&h->list); kfree(h); } } } else { ops = &basechain->ops; if (ops->hooknum != hook.num || ops->priority != hook.priority) { nft_chain_release_hook(&hook); NL_SET_BAD_ATTR(extack, attr); return -EEXIST; } } } if (nla[NFTA_CHAIN_HANDLE] && nla[NFTA_CHAIN_NAME]) { struct nft_chain *chain2; chain2 = nft_chain_lookup(ctx->net, table, nla[NFTA_CHAIN_NAME], genmask); if (!IS_ERR(chain2)) { NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_NAME]); err = -EEXIST; goto err_hooks; } } if (table->flags & __NFT_TABLE_F_UPDATE && !list_empty(&hook.list)) { NL_SET_BAD_ATTR(extack, attr); err = -EOPNOTSUPP; goto err_hooks; } if (!(table->flags & NFT_TABLE_F_DORMANT) && nft_is_base_chain(chain) && !list_empty(&hook.list)) { basechain = nft_base_chain(chain); ops = &basechain->ops; if (nft_base_chain_netdev(table->family, basechain->ops.hooknum)) { err = nft_netdev_register_hooks(ctx->net, &hook.list); if (err < 0) goto err_hooks; } } unregister = true; if (nla[NFTA_CHAIN_COUNTERS]) { if (!nft_is_base_chain(chain)) { err = -EOPNOTSUPP; goto err_hooks; } stats = nft_stats_alloc(nla[NFTA_CHAIN_COUNTERS]); if (IS_ERR(stats)) { err = PTR_ERR(stats); goto err_hooks; } } err = -ENOMEM; trans = nft_trans_alloc(ctx, NFT_MSG_NEWCHAIN, sizeof(struct nft_trans_chain)); if (trans == NULL) goto err_trans; nft_trans_chain_stats(trans) = stats; nft_trans_chain_update(trans) = true; if (nla[NFTA_CHAIN_POLICY]) nft_trans_chain_policy(trans) = policy; else nft_trans_chain_policy(trans) = -1; if (nla[NFTA_CHAIN_HANDLE] && nla[NFTA_CHAIN_NAME]) { struct nftables_pernet *nft_net = nft_pernet(ctx->net); struct nft_trans *tmp; char *name; err = -ENOMEM; name = nla_strdup(nla[NFTA_CHAIN_NAME], GFP_KERNEL_ACCOUNT); if (!name) goto err_trans; err = -EEXIST; list_for_each_entry(tmp, &nft_net->commit_list, list) { if (tmp->msg_type == NFT_MSG_NEWCHAIN && tmp->ctx.table == table && nft_trans_chain_update(tmp) && nft_trans_chain_name(tmp) && strcmp(name, nft_trans_chain_name(tmp)) == 0) { NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_NAME]); kfree(name); goto err_trans; } } nft_trans_chain_name(trans) = name; } nft_trans_basechain(trans) = basechain; INIT_LIST_HEAD(&nft_trans_chain_hooks(trans)); list_splice(&hook.list, &nft_trans_chain_hooks(trans)); if (nla[NFTA_CHAIN_HOOK]) module_put(hook.type->owner); nft_trans_commit_list_add_tail(ctx->net, trans); return 0; err_trans: free_percpu(stats); kfree(trans); err_hooks: if (nla[NFTA_CHAIN_HOOK]) { list_for_each_entry_safe(h, next, &hook.list, list) { if (unregister) nf_unregister_net_hook(ctx->net, &h->ops); list_del(&h->list); kfree_rcu(h, rcu); } module_put(hook.type->owner); } return err; } static struct nft_chain *nft_chain_lookup_byid(const struct net *net, const struct nft_table *table, const struct nlattr *nla, u8 genmask) { struct nftables_pernet *nft_net = nft_pernet(net); u32 id = ntohl(nla_get_be32(nla)); struct nft_trans *trans; list_for_each_entry(trans, &nft_net->commit_list, list) { struct nft_chain *chain = trans->ctx.chain; if (trans->msg_type == NFT_MSG_NEWCHAIN && chain->table == table && id == nft_trans_chain_id(trans) && nft_active_genmask(chain, genmask)) return chain; } return ERR_PTR(-ENOENT); } static int nf_tables_newchain(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct nftables_pernet *nft_net = nft_pernet(info->net); struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); u8 family = info->nfmsg->nfgen_family; struct nft_chain *chain = NULL; struct net *net = info->net; const struct nlattr *attr; struct nft_table *table; u8 policy = NF_ACCEPT; struct nft_ctx ctx; u64 handle = 0; u32 flags = 0; lockdep_assert_held(&nft_net->commit_mutex); table = nft_table_lookup(net, nla[NFTA_CHAIN_TABLE], family, genmask, NETLINK_CB(skb).portid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_TABLE]); return PTR_ERR(table); } chain = NULL; attr = nla[NFTA_CHAIN_NAME]; if (nla[NFTA_CHAIN_HANDLE]) { handle = be64_to_cpu(nla_get_be64(nla[NFTA_CHAIN_HANDLE])); chain = nft_chain_lookup_byhandle(table, handle, genmask); if (IS_ERR(chain)) { NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_HANDLE]); return PTR_ERR(chain); } attr = nla[NFTA_CHAIN_HANDLE]; } else if (nla[NFTA_CHAIN_NAME]) { chain = nft_chain_lookup(net, table, attr, genmask); if (IS_ERR(chain)) { if (PTR_ERR(chain) != -ENOENT) { NL_SET_BAD_ATTR(extack, attr); return PTR_ERR(chain); } chain = NULL; } } else if (!nla[NFTA_CHAIN_ID]) { return -EINVAL; } if (nla[NFTA_CHAIN_POLICY]) { if (chain != NULL && !nft_is_base_chain(chain)) { NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_POLICY]); return -EOPNOTSUPP; } if (chain == NULL && nla[NFTA_CHAIN_HOOK] == NULL) { NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_POLICY]); return -EOPNOTSUPP; } policy = ntohl(nla_get_be32(nla[NFTA_CHAIN_POLICY])); switch (policy) { case NF_DROP: case NF_ACCEPT: break; default: return -EINVAL; } } if (nla[NFTA_CHAIN_FLAGS]) flags = ntohl(nla_get_be32(nla[NFTA_CHAIN_FLAGS])); else if (chain) flags = chain->flags; if (flags & ~NFT_CHAIN_FLAGS) return -EOPNOTSUPP; nft_ctx_init(&ctx, net, skb, info->nlh, family, table, chain, nla); if (chain != NULL) { if (chain->flags & NFT_CHAIN_BINDING) return -EINVAL; if (info->nlh->nlmsg_flags & NLM_F_EXCL) { NL_SET_BAD_ATTR(extack, attr); return -EEXIST; } if (info->nlh->nlmsg_flags & NLM_F_REPLACE) return -EOPNOTSUPP; flags |= chain->flags & NFT_CHAIN_BASE; return nf_tables_updchain(&ctx, genmask, policy, flags, attr, extack); } return nf_tables_addchain(&ctx, family, genmask, policy, flags, extack); } static int nft_delchain_hook(struct nft_ctx *ctx, struct nft_base_chain *basechain, struct netlink_ext_ack *extack) { const struct nft_chain *chain = &basechain->chain; const struct nlattr * const *nla = ctx->nla; struct nft_chain_hook chain_hook = {}; struct nft_hook *this, *hook; LIST_HEAD(chain_del_list); struct nft_trans *trans; int err; if (ctx->table->flags & __NFT_TABLE_F_UPDATE) return -EOPNOTSUPP; err = nft_chain_parse_hook(ctx->net, basechain, nla, &chain_hook, ctx->family, chain->flags, extack); if (err < 0) return err; list_for_each_entry(this, &chain_hook.list, list) { hook = nft_hook_list_find(&basechain->hook_list, this); if (!hook) { err = -ENOENT; goto err_chain_del_hook; } list_move(&hook->list, &chain_del_list); } trans = nft_trans_alloc(ctx, NFT_MSG_DELCHAIN, sizeof(struct nft_trans_chain)); if (!trans) { err = -ENOMEM; goto err_chain_del_hook; } nft_trans_basechain(trans) = basechain; nft_trans_chain_update(trans) = true; INIT_LIST_HEAD(&nft_trans_chain_hooks(trans)); list_splice(&chain_del_list, &nft_trans_chain_hooks(trans)); nft_chain_release_hook(&chain_hook); nft_trans_commit_list_add_tail(ctx->net, trans); return 0; err_chain_del_hook: list_splice(&chain_del_list, &basechain->hook_list); nft_chain_release_hook(&chain_hook); return err; } static int nf_tables_delchain(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); u8 family = info->nfmsg->nfgen_family; struct net *net = info->net; const struct nlattr *attr; struct nft_table *table; struct nft_chain *chain; struct nft_rule *rule; struct nft_ctx ctx; u64 handle; u32 use; int err; table = nft_table_lookup(net, nla[NFTA_CHAIN_TABLE], family, genmask, NETLINK_CB(skb).portid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_TABLE]); return PTR_ERR(table); } if (nla[NFTA_CHAIN_HANDLE]) { attr = nla[NFTA_CHAIN_HANDLE]; handle = be64_to_cpu(nla_get_be64(attr)); chain = nft_chain_lookup_byhandle(table, handle, genmask); } else { attr = nla[NFTA_CHAIN_NAME]; chain = nft_chain_lookup(net, table, attr, genmask); } if (IS_ERR(chain)) { if (PTR_ERR(chain) == -ENOENT && NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_DESTROYCHAIN) return 0; NL_SET_BAD_ATTR(extack, attr); return PTR_ERR(chain); } if (nft_chain_binding(chain)) return -EOPNOTSUPP; nft_ctx_init(&ctx, net, skb, info->nlh, family, table, chain, nla); if (nla[NFTA_CHAIN_HOOK]) { if (NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_DESTROYCHAIN || chain->flags & NFT_CHAIN_HW_OFFLOAD) return -EOPNOTSUPP; if (nft_is_base_chain(chain)) { struct nft_base_chain *basechain = nft_base_chain(chain); if (nft_base_chain_netdev(table->family, basechain->ops.hooknum)) return nft_delchain_hook(&ctx, basechain, extack); } } if (info->nlh->nlmsg_flags & NLM_F_NONREC && chain->use > 0) return -EBUSY; use = chain->use; list_for_each_entry(rule, &chain->rules, list) { if (!nft_is_active_next(net, rule)) continue; use--; err = nft_delrule(&ctx, rule); if (err < 0) return err; } /* There are rules and elements that are still holding references to us, * we cannot do a recursive removal in this case. */ if (use > 0) { NL_SET_BAD_ATTR(extack, attr); return -EBUSY; } return nft_delchain(&ctx); } /* * Expressions */ /** * nft_register_expr - register nf_tables expr type * @type: expr type * * Registers the expr type for use with nf_tables. Returns zero on * success or a negative errno code otherwise. */ int nft_register_expr(struct nft_expr_type *type) { if (WARN_ON_ONCE(type->maxattr > NFT_EXPR_MAXATTR)) return -ENOMEM; nfnl_lock(NFNL_SUBSYS_NFTABLES); if (type->family == NFPROTO_UNSPEC) list_add_tail_rcu(&type->list, &nf_tables_expressions); else list_add_rcu(&type->list, &nf_tables_expressions); nfnl_unlock(NFNL_SUBSYS_NFTABLES); return 0; } EXPORT_SYMBOL_GPL(nft_register_expr); /** * nft_unregister_expr - unregister nf_tables expr type * @type: expr type * * Unregisters the expr typefor use with nf_tables. */ void nft_unregister_expr(struct nft_expr_type *type) { nfnl_lock(NFNL_SUBSYS_NFTABLES); list_del_rcu(&type->list); nfnl_unlock(NFNL_SUBSYS_NFTABLES); } EXPORT_SYMBOL_GPL(nft_unregister_expr); static const struct nft_expr_type *__nft_expr_type_get(u8 family, struct nlattr *nla) { const struct nft_expr_type *type, *candidate = NULL; list_for_each_entry_rcu(type, &nf_tables_expressions, list) { if (!nla_strcmp(nla, type->name)) { if (!type->family && !candidate) candidate = type; else if (type->family == family) candidate = type; } } return candidate; } #ifdef CONFIG_MODULES static int nft_expr_type_request_module(struct net *net, u8 family, struct nlattr *nla) { if (nft_request_module(net, "nft-expr-%u-%.*s", family, nla_len(nla), (char *)nla_data(nla)) == -EAGAIN) return -EAGAIN; return 0; } #endif static const struct nft_expr_type *nft_expr_type_get(struct net *net, u8 family, struct nlattr *nla) { const struct nft_expr_type *type; if (nla == NULL) return ERR_PTR(-EINVAL); rcu_read_lock(); type = __nft_expr_type_get(family, nla); if (type != NULL && try_module_get(type->owner)) { rcu_read_unlock(); return type; } rcu_read_unlock(); lockdep_nfnl_nft_mutex_not_held(); #ifdef CONFIG_MODULES if (type == NULL) { if (nft_expr_type_request_module(net, family, nla) == -EAGAIN) return ERR_PTR(-EAGAIN); if (nft_request_module(net, "nft-expr-%.*s", nla_len(nla), (char *)nla_data(nla)) == -EAGAIN) return ERR_PTR(-EAGAIN); } #endif return ERR_PTR(-ENOENT); } static const struct nla_policy nft_expr_policy[NFTA_EXPR_MAX + 1] = { [NFTA_EXPR_NAME] = { .type = NLA_STRING, .len = NFT_MODULE_AUTOLOAD_LIMIT }, [NFTA_EXPR_DATA] = { .type = NLA_NESTED }, }; static int nf_tables_fill_expr_info(struct sk_buff *skb, const struct nft_expr *expr, bool reset) { if (nla_put_string(skb, NFTA_EXPR_NAME, expr->ops->type->name)) goto nla_put_failure; if (expr->ops->dump) { struct nlattr *data = nla_nest_start_noflag(skb, NFTA_EXPR_DATA); if (data == NULL) goto nla_put_failure; if (expr->ops->dump(skb, expr, reset) < 0) goto nla_put_failure; nla_nest_end(skb, data); } return skb->len; nla_put_failure: return -1; }; int nft_expr_dump(struct sk_buff *skb, unsigned int attr, const struct nft_expr *expr, bool reset) { struct nlattr *nest; nest = nla_nest_start_noflag(skb, attr); if (!nest) goto nla_put_failure; if (nf_tables_fill_expr_info(skb, expr, reset) < 0) goto nla_put_failure; nla_nest_end(skb, nest); return 0; nla_put_failure: return -1; } struct nft_expr_info { const struct nft_expr_ops *ops; const struct nlattr *attr; struct nlattr *tb[NFT_EXPR_MAXATTR + 1]; }; static int nf_tables_expr_parse(const struct nft_ctx *ctx, const struct nlattr *nla, struct nft_expr_info *info) { const struct nft_expr_type *type; const struct nft_expr_ops *ops; struct nlattr *tb[NFTA_EXPR_MAX + 1]; int err; err = nla_parse_nested_deprecated(tb, NFTA_EXPR_MAX, nla, nft_expr_policy, NULL); if (err < 0) return err; type = nft_expr_type_get(ctx->net, ctx->family, tb[NFTA_EXPR_NAME]); if (IS_ERR(type)) return PTR_ERR(type); if (tb[NFTA_EXPR_DATA]) { err = nla_parse_nested_deprecated(info->tb, type->maxattr, tb[NFTA_EXPR_DATA], type->policy, NULL); if (err < 0) goto err1; } else memset(info->tb, 0, sizeof(info->tb[0]) * (type->maxattr + 1)); if (type->select_ops != NULL) { ops = type->select_ops(ctx, (const struct nlattr * const *)info->tb); if (IS_ERR(ops)) { err = PTR_ERR(ops); #ifdef CONFIG_MODULES if (err == -EAGAIN) if (nft_expr_type_request_module(ctx->net, ctx->family, tb[NFTA_EXPR_NAME]) != -EAGAIN) err = -ENOENT; #endif goto err1; } } else ops = type->ops; info->attr = nla; info->ops = ops; return 0; err1: module_put(type->owner); return err; } int nft_expr_inner_parse(const struct nft_ctx *ctx, const struct nlattr *nla, struct nft_expr_info *info) { struct nlattr *tb[NFTA_EXPR_MAX + 1]; const struct nft_expr_type *type; int err; err = nla_parse_nested_deprecated(tb, NFTA_EXPR_MAX, nla, nft_expr_policy, NULL); if (err < 0) return err; if (!tb[NFTA_EXPR_DATA] || !tb[NFTA_EXPR_NAME]) return -EINVAL; type = __nft_expr_type_get(ctx->family, tb[NFTA_EXPR_NAME]); if (!type) return -ENOENT; if (!type->inner_ops) return -EOPNOTSUPP; err = nla_parse_nested_deprecated(info->tb, type->maxattr, tb[NFTA_EXPR_DATA], type->policy, NULL); if (err < 0) goto err_nla_parse; info->attr = nla; info->ops = type->inner_ops; return 0; err_nla_parse: return err; } static int nf_tables_newexpr(const struct nft_ctx *ctx, const struct nft_expr_info *expr_info, struct nft_expr *expr) { const struct nft_expr_ops *ops = expr_info->ops; int err; expr->ops = ops; if (ops->init) { err = ops->init(ctx, expr, (const struct nlattr **)expr_info->tb); if (err < 0) goto err1; } return 0; err1: expr->ops = NULL; return err; } static void nf_tables_expr_destroy(const struct nft_ctx *ctx, struct nft_expr *expr) { const struct nft_expr_type *type = expr->ops->type; if (expr->ops->destroy) expr->ops->destroy(ctx, expr); module_put(type->owner); } static struct nft_expr *nft_expr_init(const struct nft_ctx *ctx, const struct nlattr *nla) { struct nft_expr_info expr_info; struct nft_expr *expr; struct module *owner; int err; err = nf_tables_expr_parse(ctx, nla, &expr_info); if (err < 0) goto err_expr_parse; err = -EOPNOTSUPP; if (!(expr_info.ops->type->flags & NFT_EXPR_STATEFUL)) goto err_expr_stateful; err = -ENOMEM; expr = kzalloc(expr_info.ops->size, GFP_KERNEL_ACCOUNT); if (expr == NULL) goto err_expr_stateful; err = nf_tables_newexpr(ctx, &expr_info, expr); if (err < 0) goto err_expr_new; return expr; err_expr_new: kfree(expr); err_expr_stateful: owner = expr_info.ops->type->owner; if (expr_info.ops->type->release_ops) expr_info.ops->type->release_ops(expr_info.ops); module_put(owner); err_expr_parse: return ERR_PTR(err); } int nft_expr_clone(struct nft_expr *dst, struct nft_expr *src) { int err; if (WARN_ON_ONCE(!src->ops->clone)) return -EINVAL; dst->ops = src->ops; err = src->ops->clone(dst, src); if (err < 0) return err; __module_get(src->ops->type->owner); return 0; } void nft_expr_destroy(const struct nft_ctx *ctx, struct nft_expr *expr) { nf_tables_expr_destroy(ctx, expr); kfree(expr); } /* * Rules */ static struct nft_rule *__nft_rule_lookup(const struct nft_chain *chain, u64 handle) { struct nft_rule *rule; // FIXME: this sucks list_for_each_entry_rcu(rule, &chain->rules, list) { if (handle == rule->handle) return rule; } return ERR_PTR(-ENOENT); } static struct nft_rule *nft_rule_lookup(const struct nft_chain *chain, const struct nlattr *nla) { if (nla == NULL) return ERR_PTR(-EINVAL); return __nft_rule_lookup(chain, be64_to_cpu(nla_get_be64(nla))); } static const struct nla_policy nft_rule_policy[NFTA_RULE_MAX + 1] = { [NFTA_RULE_TABLE] = { .type = NLA_STRING, .len = NFT_TABLE_MAXNAMELEN - 1 }, [NFTA_RULE_CHAIN] = { .type = NLA_STRING, .len = NFT_CHAIN_MAXNAMELEN - 1 }, [NFTA_RULE_HANDLE] = { .type = NLA_U64 }, [NFTA_RULE_EXPRESSIONS] = NLA_POLICY_NESTED_ARRAY(nft_expr_policy), [NFTA_RULE_COMPAT] = { .type = NLA_NESTED }, [NFTA_RULE_POSITION] = { .type = NLA_U64 }, [NFTA_RULE_USERDATA] = { .type = NLA_BINARY, .len = NFT_USERDATA_MAXLEN }, [NFTA_RULE_ID] = { .type = NLA_U32 }, [NFTA_RULE_POSITION_ID] = { .type = NLA_U32 }, [NFTA_RULE_CHAIN_ID] = { .type = NLA_U32 }, }; static int nf_tables_fill_rule_info(struct sk_buff *skb, struct net *net, u32 portid, u32 seq, int event, u32 flags, int family, const struct nft_table *table, const struct nft_chain *chain, const struct nft_rule *rule, u64 handle, bool reset) { struct nlmsghdr *nlh; const struct nft_expr *expr, *next; struct nlattr *list; u16 type = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event); nlh = nfnl_msg_put(skb, portid, seq, type, flags, family, NFNETLINK_V0, nft_base_seq(net)); if (!nlh) goto nla_put_failure; if (nla_put_string(skb, NFTA_RULE_TABLE, table->name)) goto nla_put_failure; if (nla_put_string(skb, NFTA_RULE_CHAIN, chain->name)) goto nla_put_failure; if (nla_put_be64(skb, NFTA_RULE_HANDLE, cpu_to_be64(rule->handle), NFTA_RULE_PAD)) goto nla_put_failure; if (event != NFT_MSG_DELRULE && handle) { if (nla_put_be64(skb, NFTA_RULE_POSITION, cpu_to_be64(handle), NFTA_RULE_PAD)) goto nla_put_failure; } if (chain->flags & NFT_CHAIN_HW_OFFLOAD) nft_flow_rule_stats(chain, rule); list = nla_nest_start_noflag(skb, NFTA_RULE_EXPRESSIONS); if (list == NULL) goto nla_put_failure; nft_rule_for_each_expr(expr, next, rule) { if (nft_expr_dump(skb, NFTA_LIST_ELEM, expr, reset) < 0) goto nla_put_failure; } nla_nest_end(skb, list); if (rule->udata) { struct nft_userdata *udata = nft_userdata(rule); if (nla_put(skb, NFTA_RULE_USERDATA, udata->len + 1, udata->data) < 0) goto nla_put_failure; } nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_trim(skb, nlh); return -1; } static void nf_tables_rule_notify(const struct nft_ctx *ctx, const struct nft_rule *rule, int event) { struct nftables_pernet *nft_net = nft_pernet(ctx->net); const struct nft_rule *prule; struct sk_buff *skb; u64 handle = 0; u16 flags = 0; int err; if (!ctx->report && !nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES)) return; skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); if (skb == NULL) goto err; if (event == NFT_MSG_NEWRULE && !list_is_first(&rule->list, &ctx->chain->rules) && !list_is_last(&rule->list, &ctx->chain->rules)) { prule = list_prev_entry(rule, list); handle = prule->handle; } if (ctx->flags & (NLM_F_APPEND | NLM_F_REPLACE)) flags |= NLM_F_APPEND; if (ctx->flags & (NLM_F_CREATE | NLM_F_EXCL)) flags |= ctx->flags & (NLM_F_CREATE | NLM_F_EXCL); err = nf_tables_fill_rule_info(skb, ctx->net, ctx->portid, ctx->seq, event, flags, ctx->family, ctx->table, ctx->chain, rule, handle, false); if (err < 0) { kfree_skb(skb); goto err; } nft_notify_enqueue(skb, ctx->report, &nft_net->notify_list); return; err: nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, -ENOBUFS); } static void audit_log_rule_reset(const struct nft_table *table, unsigned int base_seq, unsigned int nentries) { char *buf = kasprintf(GFP_ATOMIC, "%s:%u", table->name, base_seq); audit_log_nfcfg(buf, table->family, nentries, AUDIT_NFT_OP_RULE_RESET, GFP_ATOMIC); kfree(buf); } struct nft_rule_dump_ctx { unsigned int s_idx; char *table; char *chain; bool reset; }; static int __nf_tables_dump_rules(struct sk_buff *skb, unsigned int *idx, struct netlink_callback *cb, const struct nft_table *table, const struct nft_chain *chain) { struct nft_rule_dump_ctx *ctx = (void *)cb->ctx; struct net *net = sock_net(skb->sk); const struct nft_rule *rule, *prule; unsigned int entries = 0; int ret = 0; u64 handle; prule = NULL; list_for_each_entry_rcu(rule, &chain->rules, list) { if (!nft_is_active(net, rule)) goto cont_skip; if (*idx < ctx->s_idx) goto cont; if (prule) handle = prule->handle; else handle = 0; if (nf_tables_fill_rule_info(skb, net, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NFT_MSG_NEWRULE, NLM_F_MULTI | NLM_F_APPEND, table->family, table, chain, rule, handle, ctx->reset) < 0) { ret = 1; break; } entries++; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); cont: prule = rule; cont_skip: (*idx)++; } if (ctx->reset && entries) audit_log_rule_reset(table, cb->seq, entries); return ret; } static int nf_tables_dump_rules(struct sk_buff *skb, struct netlink_callback *cb) { const struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); struct nft_rule_dump_ctx *ctx = (void *)cb->ctx; struct nft_table *table; const struct nft_chain *chain; unsigned int idx = 0; struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; struct nftables_pernet *nft_net; rcu_read_lock(); nft_net = nft_pernet(net); cb->seq = READ_ONCE(nft_net->base_seq); list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) continue; if (ctx->table && strcmp(ctx->table, table->name) != 0) continue; if (ctx->table && ctx->chain) { struct rhlist_head *list, *tmp; list = rhltable_lookup(&table->chains_ht, ctx->chain, nft_chain_ht_params); if (!list) goto done; rhl_for_each_entry_rcu(chain, tmp, list, rhlhead) { if (!nft_is_active(net, chain)) continue; __nf_tables_dump_rules(skb, &idx, cb, table, chain); break; } goto done; } list_for_each_entry_rcu(chain, &table->chains, list) { if (__nf_tables_dump_rules(skb, &idx, cb, table, chain)) goto done; } if (ctx->table) break; } done: rcu_read_unlock(); ctx->s_idx = idx; return skb->len; } static int nf_tables_dumpreset_rules(struct sk_buff *skb, struct netlink_callback *cb) { struct nftables_pernet *nft_net = nft_pernet(sock_net(skb->sk)); int ret; /* Mutex is held is to prevent that two concurrent dump-and-reset calls * do not underrun counters and quotas. The commit_mutex is used for * the lack a better lock, this is not transaction path. */ mutex_lock(&nft_net->commit_mutex); ret = nf_tables_dump_rules(skb, cb); mutex_unlock(&nft_net->commit_mutex); return ret; } static int nf_tables_dump_rules_start(struct netlink_callback *cb) { struct nft_rule_dump_ctx *ctx = (void *)cb->ctx; const struct nlattr * const *nla = cb->data; BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx)); if (nla[NFTA_RULE_TABLE]) { ctx->table = nla_strdup(nla[NFTA_RULE_TABLE], GFP_ATOMIC); if (!ctx->table) return -ENOMEM; } if (nla[NFTA_RULE_CHAIN]) { ctx->chain = nla_strdup(nla[NFTA_RULE_CHAIN], GFP_ATOMIC); if (!ctx->chain) { kfree(ctx->table); return -ENOMEM; } } return 0; } static int nf_tables_dumpreset_rules_start(struct netlink_callback *cb) { struct nft_rule_dump_ctx *ctx = (void *)cb->ctx; ctx->reset = true; return nf_tables_dump_rules_start(cb); } static int nf_tables_dump_rules_done(struct netlink_callback *cb) { struct nft_rule_dump_ctx *ctx = (void *)cb->ctx; kfree(ctx->table); kfree(ctx->chain); return 0; } /* called with rcu_read_lock held */ static struct sk_buff * nf_tables_getrule_single(u32 portid, const struct nfnl_info *info, const struct nlattr * const nla[], bool reset) { struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_cur(info->net); u8 family = info->nfmsg->nfgen_family; const struct nft_chain *chain; const struct nft_rule *rule; struct net *net = info->net; struct nft_table *table; struct sk_buff *skb2; int err; table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask, 0); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_TABLE]); return ERR_CAST(table); } chain = nft_chain_lookup(net, table, nla[NFTA_RULE_CHAIN], genmask); if (IS_ERR(chain)) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN]); return ERR_CAST(chain); } rule = nft_rule_lookup(chain, nla[NFTA_RULE_HANDLE]); if (IS_ERR(rule)) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_HANDLE]); return ERR_CAST(rule); } skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC); if (!skb2) return ERR_PTR(-ENOMEM); err = nf_tables_fill_rule_info(skb2, net, portid, info->nlh->nlmsg_seq, NFT_MSG_NEWRULE, 0, family, table, chain, rule, 0, reset); if (err < 0) { kfree_skb(skb2); return ERR_PTR(err); } return skb2; } static int nf_tables_getrule(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { u32 portid = NETLINK_CB(skb).portid; struct net *net = info->net; struct sk_buff *skb2; if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .start= nf_tables_dump_rules_start, .dump = nf_tables_dump_rules, .done = nf_tables_dump_rules_done, .module = THIS_MODULE, .data = (void *)nla, }; return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); } skb2 = nf_tables_getrule_single(portid, info, nla, false); if (IS_ERR(skb2)) return PTR_ERR(skb2); return nfnetlink_unicast(skb2, net, portid); } static int nf_tables_getrule_reset(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct nftables_pernet *nft_net = nft_pernet(info->net); u32 portid = NETLINK_CB(skb).portid; struct net *net = info->net; struct sk_buff *skb2; char *buf; if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .start= nf_tables_dumpreset_rules_start, .dump = nf_tables_dumpreset_rules, .done = nf_tables_dump_rules_done, .module = THIS_MODULE, .data = (void *)nla, }; return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); } if (!try_module_get(THIS_MODULE)) return -EINVAL; rcu_read_unlock(); mutex_lock(&nft_net->commit_mutex); skb2 = nf_tables_getrule_single(portid, info, nla, true); mutex_unlock(&nft_net->commit_mutex); rcu_read_lock(); module_put(THIS_MODULE); if (IS_ERR(skb2)) return PTR_ERR(skb2); buf = kasprintf(GFP_ATOMIC, "%.*s:%u", nla_len(nla[NFTA_RULE_TABLE]), (char *)nla_data(nla[NFTA_RULE_TABLE]), nft_net->base_seq); audit_log_nfcfg(buf, info->nfmsg->nfgen_family, 1, AUDIT_NFT_OP_RULE_RESET, GFP_ATOMIC); kfree(buf); return nfnetlink_unicast(skb2, net, portid); } void nf_tables_rule_destroy(const struct nft_ctx *ctx, struct nft_rule *rule) { struct nft_expr *expr, *next; /* * Careful: some expressions might not be initialized in case this * is called on error from nf_tables_newrule(). */ expr = nft_expr_first(rule); while (nft_expr_more(rule, expr)) { next = nft_expr_next(expr); nf_tables_expr_destroy(ctx, expr); expr = next; } kfree(rule); } static void nf_tables_rule_release(const struct nft_ctx *ctx, struct nft_rule *rule) { nft_rule_expr_deactivate(ctx, rule, NFT_TRANS_RELEASE); nf_tables_rule_destroy(ctx, rule); } int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain) { struct nft_expr *expr, *last; const struct nft_data *data; struct nft_rule *rule; int err; if (ctx->level == NFT_JUMP_STACK_SIZE) return -EMLINK; list_for_each_entry(rule, &chain->rules, list) { if (fatal_signal_pending(current)) return -EINTR; if (!nft_is_active_next(ctx->net, rule)) continue; nft_rule_for_each_expr(expr, last, rule) { if (!expr->ops->validate) continue; err = expr->ops->validate(ctx, expr, &data); if (err < 0) return err; } } return 0; } EXPORT_SYMBOL_GPL(nft_chain_validate); static int nft_table_validate(struct net *net, const struct nft_table *table) { struct nft_chain *chain; struct nft_ctx ctx = { .net = net, .family = table->family, }; int err; list_for_each_entry(chain, &table->chains, list) { if (!nft_is_base_chain(chain)) continue; ctx.chain = chain; err = nft_chain_validate(&ctx, chain); if (err < 0) return err; cond_resched(); } return 0; } int nft_setelem_validate(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_set_iter *iter, struct nft_elem_priv *elem_priv) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); struct nft_ctx *pctx = (struct nft_ctx *)ctx; const struct nft_data *data; int err; if (!nft_set_elem_active(ext, iter->genmask)) return 0; if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && *nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END) return 0; data = nft_set_ext_data(ext); switch (data->verdict.code) { case NFT_JUMP: case NFT_GOTO: pctx->level++; err = nft_chain_validate(ctx, data->verdict.chain); if (err < 0) return err; pctx->level--; break; default: break; } return 0; } int nft_set_catchall_validate(const struct nft_ctx *ctx, struct nft_set *set) { struct nft_set_iter dummy_iter = { .genmask = nft_genmask_next(ctx->net), }; struct nft_set_elem_catchall *catchall; struct nft_set_ext *ext; int ret = 0; list_for_each_entry_rcu(catchall, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); if (!nft_set_elem_active(ext, dummy_iter.genmask)) continue; ret = nft_setelem_validate(ctx, set, &dummy_iter, catchall->elem); if (ret < 0) return ret; } return ret; } static struct nft_rule *nft_rule_lookup_byid(const struct net *net, const struct nft_chain *chain, const struct nlattr *nla); #define NFT_RULE_MAXEXPRS 128 static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct nftables_pernet *nft_net = nft_pernet(info->net); struct netlink_ext_ack *extack = info->extack; unsigned int size, i, n, ulen = 0, usize = 0; u8 genmask = nft_genmask_next(info->net); struct nft_rule *rule, *old_rule = NULL; struct nft_expr_info *expr_info = NULL; u8 family = info->nfmsg->nfgen_family; struct nft_flow_rule *flow = NULL; struct net *net = info->net; struct nft_userdata *udata; struct nft_table *table; struct nft_chain *chain; struct nft_trans *trans; u64 handle, pos_handle; struct nft_expr *expr; struct nft_ctx ctx; struct nlattr *tmp; int err, rem; lockdep_assert_held(&nft_net->commit_mutex); table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask, NETLINK_CB(skb).portid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_TABLE]); return PTR_ERR(table); } if (nla[NFTA_RULE_CHAIN]) { chain = nft_chain_lookup(net, table, nla[NFTA_RULE_CHAIN], genmask); if (IS_ERR(chain)) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN]); return PTR_ERR(chain); } } else if (nla[NFTA_RULE_CHAIN_ID]) { chain = nft_chain_lookup_byid(net, table, nla[NFTA_RULE_CHAIN_ID], genmask); if (IS_ERR(chain)) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN_ID]); return PTR_ERR(chain); } } else { return -EINVAL; } if (nft_chain_is_bound(chain)) return -EOPNOTSUPP; if (nla[NFTA_RULE_HANDLE]) { handle = be64_to_cpu(nla_get_be64(nla[NFTA_RULE_HANDLE])); rule = __nft_rule_lookup(chain, handle); if (IS_ERR(rule)) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_HANDLE]); return PTR_ERR(rule); } if (info->nlh->nlmsg_flags & NLM_F_EXCL) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_HANDLE]); return -EEXIST; } if (info->nlh->nlmsg_flags & NLM_F_REPLACE) old_rule = rule; else return -EOPNOTSUPP; } else { if (!(info->nlh->nlmsg_flags & NLM_F_CREATE) || info->nlh->nlmsg_flags & NLM_F_REPLACE) return -EINVAL; handle = nf_tables_alloc_handle(table); if (nla[NFTA_RULE_POSITION]) { pos_handle = be64_to_cpu(nla_get_be64(nla[NFTA_RULE_POSITION])); old_rule = __nft_rule_lookup(chain, pos_handle); if (IS_ERR(old_rule)) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_POSITION]); return PTR_ERR(old_rule); } } else if (nla[NFTA_RULE_POSITION_ID]) { old_rule = nft_rule_lookup_byid(net, chain, nla[NFTA_RULE_POSITION_ID]); if (IS_ERR(old_rule)) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_POSITION_ID]); return PTR_ERR(old_rule); } } } nft_ctx_init(&ctx, net, skb, info->nlh, family, table, chain, nla); n = 0; size = 0; if (nla[NFTA_RULE_EXPRESSIONS]) { expr_info = kvmalloc_array(NFT_RULE_MAXEXPRS, sizeof(struct nft_expr_info), GFP_KERNEL); if (!expr_info) return -ENOMEM; nla_for_each_nested(tmp, nla[NFTA_RULE_EXPRESSIONS], rem) { err = -EINVAL; if (nla_type(tmp) != NFTA_LIST_ELEM) goto err_release_expr; if (n == NFT_RULE_MAXEXPRS) goto err_release_expr; err = nf_tables_expr_parse(&ctx, tmp, &expr_info[n]); if (err < 0) { NL_SET_BAD_ATTR(extack, tmp); goto err_release_expr; } size += expr_info[n].ops->size; n++; } } /* Check for overflow of dlen field */ err = -EFBIG; if (size >= 1 << 12) goto err_release_expr; if (nla[NFTA_RULE_USERDATA]) { ulen = nla_len(nla[NFTA_RULE_USERDATA]); if (ulen > 0) usize = sizeof(struct nft_userdata) + ulen; } err = -ENOMEM; rule = kzalloc(sizeof(*rule) + size + usize, GFP_KERNEL_ACCOUNT); if (rule == NULL) goto err_release_expr; nft_activate_next(net, rule); rule->handle = handle; rule->dlen = size; rule->udata = ulen ? 1 : 0; if (ulen) { udata = nft_userdata(rule); udata->len = ulen - 1; nla_memcpy(udata->data, nla[NFTA_RULE_USERDATA], ulen); } expr = nft_expr_first(rule); for (i = 0; i < n; i++) { err = nf_tables_newexpr(&ctx, &expr_info[i], expr); if (err < 0) { NL_SET_BAD_ATTR(extack, expr_info[i].attr); goto err_release_rule; } if (expr_info[i].ops->validate) nft_validate_state_update(table, NFT_VALIDATE_NEED); expr_info[i].ops = NULL; expr = nft_expr_next(expr); } if (chain->flags & NFT_CHAIN_HW_OFFLOAD) { flow = nft_flow_rule_create(net, rule); if (IS_ERR(flow)) { err = PTR_ERR(flow); goto err_release_rule; } } if (!nft_use_inc(&chain->use)) { err = -EMFILE; goto err_release_rule; } if (info->nlh->nlmsg_flags & NLM_F_REPLACE) { if (nft_chain_binding(chain)) { err = -EOPNOTSUPP; goto err_destroy_flow_rule; } err = nft_delrule(&ctx, old_rule); if (err < 0) goto err_destroy_flow_rule; trans = nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule); if (trans == NULL) { err = -ENOMEM; goto err_destroy_flow_rule; } list_add_tail_rcu(&rule->list, &old_rule->list); } else { trans = nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule); if (!trans) { err = -ENOMEM; goto err_destroy_flow_rule; } if (info->nlh->nlmsg_flags & NLM_F_APPEND) { if (old_rule) list_add_rcu(&rule->list, &old_rule->list); else list_add_tail_rcu(&rule->list, &chain->rules); } else { if (old_rule) list_add_tail_rcu(&rule->list, &old_rule->list); else list_add_rcu(&rule->list, &chain->rules); } } kvfree(expr_info); if (flow) nft_trans_flow_rule(trans) = flow; if (table->validate_state == NFT_VALIDATE_DO) return nft_table_validate(net, table); return 0; err_destroy_flow_rule: nft_use_dec_restore(&chain->use); if (flow) nft_flow_rule_destroy(flow); err_release_rule: nft_rule_expr_deactivate(&ctx, rule, NFT_TRANS_PREPARE_ERROR); nf_tables_rule_destroy(&ctx, rule); err_release_expr: for (i = 0; i < n; i++) { if (expr_info[i].ops) { module_put(expr_info[i].ops->type->owner); if (expr_info[i].ops->type->release_ops) expr_info[i].ops->type->release_ops(expr_info[i].ops); } } kvfree(expr_info); return err; } static struct nft_rule *nft_rule_lookup_byid(const struct net *net, const struct nft_chain *chain, const struct nlattr *nla) { struct nftables_pernet *nft_net = nft_pernet(net); u32 id = ntohl(nla_get_be32(nla)); struct nft_trans *trans; list_for_each_entry(trans, &nft_net->commit_list, list) { if (trans->msg_type == NFT_MSG_NEWRULE && trans->ctx.chain == chain && id == nft_trans_rule_id(trans)) return nft_trans_rule(trans); } return ERR_PTR(-ENOENT); } static int nf_tables_delrule(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); u8 family = info->nfmsg->nfgen_family; struct nft_chain *chain = NULL; struct net *net = info->net; struct nft_table *table; struct nft_rule *rule; struct nft_ctx ctx; int err = 0; table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask, NETLINK_CB(skb).portid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_TABLE]); return PTR_ERR(table); } if (nla[NFTA_RULE_CHAIN]) { chain = nft_chain_lookup(net, table, nla[NFTA_RULE_CHAIN], genmask); if (IS_ERR(chain)) { if (PTR_ERR(chain) == -ENOENT && NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_DESTROYRULE) return 0; NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN]); return PTR_ERR(chain); } if (nft_chain_binding(chain)) return -EOPNOTSUPP; } nft_ctx_init(&ctx, net, skb, info->nlh, family, table, chain, nla); if (chain) { if (nla[NFTA_RULE_HANDLE]) { rule = nft_rule_lookup(chain, nla[NFTA_RULE_HANDLE]); if (IS_ERR(rule)) { if (PTR_ERR(rule) == -ENOENT && NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_DESTROYRULE) return 0; NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_HANDLE]); return PTR_ERR(rule); } err = nft_delrule(&ctx, rule); } else if (nla[NFTA_RULE_ID]) { rule = nft_rule_lookup_byid(net, chain, nla[NFTA_RULE_ID]); if (IS_ERR(rule)) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_ID]); return PTR_ERR(rule); } err = nft_delrule(&ctx, rule); } else { err = nft_delrule_by_chain(&ctx); } } else { list_for_each_entry(chain, &table->chains, list) { if (!nft_is_active_next(net, chain)) continue; if (nft_chain_binding(chain)) continue; ctx.chain = chain; err = nft_delrule_by_chain(&ctx); if (err < 0) break; } } return err; } /* * Sets */ static const struct nft_set_type *nft_set_types[] = { &nft_set_hash_fast_type, &nft_set_hash_type, &nft_set_rhash_type, &nft_set_bitmap_type, &nft_set_rbtree_type, #if defined(CONFIG_X86_64) && !defined(CONFIG_UML) &nft_set_pipapo_avx2_type, #endif &nft_set_pipapo_type, }; #define NFT_SET_FEATURES (NFT_SET_INTERVAL | NFT_SET_MAP | \ NFT_SET_TIMEOUT | NFT_SET_OBJECT | \ NFT_SET_EVAL) static bool nft_set_ops_candidate(const struct nft_set_type *type, u32 flags) { return (flags & type->features) == (flags & NFT_SET_FEATURES); } /* * Select a set implementation based on the data characteristics and the * given policy. The total memory use might not be known if no size is * given, in that case the amount of memory per element is used. */ static const struct nft_set_ops * nft_select_set_ops(const struct nft_ctx *ctx, u32 flags, const struct nft_set_desc *desc) { struct nftables_pernet *nft_net = nft_pernet(ctx->net); const struct nft_set_ops *ops, *bops; struct nft_set_estimate est, best; const struct nft_set_type *type; int i; lockdep_assert_held(&nft_net->commit_mutex); lockdep_nfnl_nft_mutex_not_held(); bops = NULL; best.size = ~0; best.lookup = ~0; best.space = ~0; for (i = 0; i < ARRAY_SIZE(nft_set_types); i++) { type = nft_set_types[i]; ops = &type->ops; if (!nft_set_ops_candidate(type, flags)) continue; if (!ops->estimate(desc, flags, &est)) continue; switch (desc->policy) { case NFT_SET_POL_PERFORMANCE: if (est.lookup < best.lookup) break; if (est.lookup == best.lookup && est.space < best.space) break; continue; case NFT_SET_POL_MEMORY: if (!desc->size) { if (est.space < best.space) break; if (est.space == best.space && est.lookup < best.lookup) break; } else if (est.size < best.size || !bops) { break; } continue; default: break; } bops = ops; best = est; } if (bops != NULL) return bops; return ERR_PTR(-EOPNOTSUPP); } static const struct nla_policy nft_set_policy[NFTA_SET_MAX + 1] = { [NFTA_SET_TABLE] = { .type = NLA_STRING, .len = NFT_TABLE_MAXNAMELEN - 1 }, [NFTA_SET_NAME] = { .type = NLA_STRING, .len = NFT_SET_MAXNAMELEN - 1 }, [NFTA_SET_FLAGS] = { .type = NLA_U32 }, [NFTA_SET_KEY_TYPE] = { .type = NLA_U32 }, [NFTA_SET_KEY_LEN] = { .type = NLA_U32 }, [NFTA_SET_DATA_TYPE] = { .type = NLA_U32 }, [NFTA_SET_DATA_LEN] = { .type = NLA_U32 }, [NFTA_SET_POLICY] = { .type = NLA_U32 }, [NFTA_SET_DESC] = { .type = NLA_NESTED }, [NFTA_SET_ID] = { .type = NLA_U32 }, [NFTA_SET_TIMEOUT] = { .type = NLA_U64 }, [NFTA_SET_GC_INTERVAL] = { .type = NLA_U32 }, [NFTA_SET_USERDATA] = { .type = NLA_BINARY, .len = NFT_USERDATA_MAXLEN }, [NFTA_SET_OBJ_TYPE] = { .type = NLA_U32 }, [NFTA_SET_HANDLE] = { .type = NLA_U64 }, [NFTA_SET_EXPR] = { .type = NLA_NESTED }, [NFTA_SET_EXPRESSIONS] = NLA_POLICY_NESTED_ARRAY(nft_expr_policy), }; static const struct nla_policy nft_concat_policy[NFTA_SET_FIELD_MAX + 1] = { [NFTA_SET_FIELD_LEN] = { .type = NLA_U32 }, }; static const struct nla_policy nft_set_desc_policy[NFTA_SET_DESC_MAX + 1] = { [NFTA_SET_DESC_SIZE] = { .type = NLA_U32 }, [NFTA_SET_DESC_CONCAT] = NLA_POLICY_NESTED_ARRAY(nft_concat_policy), }; static struct nft_set *nft_set_lookup(const struct nft_table *table, const struct nlattr *nla, u8 genmask) { struct nft_set *set; if (nla == NULL) return ERR_PTR(-EINVAL); list_for_each_entry_rcu(set, &table->sets, list) { if (!nla_strcmp(nla, set->name) && nft_active_genmask(set, genmask)) return set; } return ERR_PTR(-ENOENT); } static struct nft_set *nft_set_lookup_byhandle(const struct nft_table *table, const struct nlattr *nla, u8 genmask) { struct nft_set *set; list_for_each_entry(set, &table->sets, list) { if (be64_to_cpu(nla_get_be64(nla)) == set->handle && nft_active_genmask(set, genmask)) return set; } return ERR_PTR(-ENOENT); } static struct nft_set *nft_set_lookup_byid(const struct net *net, const struct nft_table *table, const struct nlattr *nla, u8 genmask) { struct nftables_pernet *nft_net = nft_pernet(net); u32 id = ntohl(nla_get_be32(nla)); struct nft_trans *trans; list_for_each_entry(trans, &nft_net->commit_list, list) { if (trans->msg_type == NFT_MSG_NEWSET) { struct nft_set *set = nft_trans_set(trans); if (id == nft_trans_set_id(trans) && set->table == table && nft_active_genmask(set, genmask)) return set; } } return ERR_PTR(-ENOENT); } struct nft_set *nft_set_lookup_global(const struct net *net, const struct nft_table *table, const struct nlattr *nla_set_name, const struct nlattr *nla_set_id, u8 genmask) { struct nft_set *set; set = nft_set_lookup(table, nla_set_name, genmask); if (IS_ERR(set)) { if (!nla_set_id) return set; set = nft_set_lookup_byid(net, table, nla_set_id, genmask); } return set; } EXPORT_SYMBOL_GPL(nft_set_lookup_global); static int nf_tables_set_alloc_name(struct nft_ctx *ctx, struct nft_set *set, const char *name) { const struct nft_set *i; const char *p; unsigned long *inuse; unsigned int n = 0, min = 0; p = strchr(name, '%'); if (p != NULL) { if (p[1] != 'd' || strchr(p + 2, '%')) return -EINVAL; if (strnlen(name, NFT_SET_MAX_ANONLEN) >= NFT_SET_MAX_ANONLEN) return -EINVAL; inuse = (unsigned long *)get_zeroed_page(GFP_KERNEL); if (inuse == NULL) return -ENOMEM; cont: list_for_each_entry(i, &ctx->table->sets, list) { int tmp; if (!nft_is_active_next(ctx->net, i)) continue; if (!sscanf(i->name, name, &tmp)) continue; if (tmp < min || tmp >= min + BITS_PER_BYTE * PAGE_SIZE) continue; set_bit(tmp - min, inuse); } n = find_first_zero_bit(inuse, BITS_PER_BYTE * PAGE_SIZE); if (n >= BITS_PER_BYTE * PAGE_SIZE) { min += BITS_PER_BYTE * PAGE_SIZE; memset(inuse, 0, PAGE_SIZE); goto cont; } free_page((unsigned long)inuse); } set->name = kasprintf(GFP_KERNEL_ACCOUNT, name, min + n); if (!set->name) return -ENOMEM; list_for_each_entry(i, &ctx->table->sets, list) { if (!nft_is_active_next(ctx->net, i)) continue; if (!strcmp(set->name, i->name)) { kfree(set->name); set->name = NULL; return -ENFILE; } } return 0; } int nf_msecs_to_jiffies64(const struct nlattr *nla, u64 *result) { u64 ms = be64_to_cpu(nla_get_be64(nla)); u64 max = (u64)(~((u64)0)); max = div_u64(max, NSEC_PER_MSEC); if (ms >= max) return -ERANGE; ms *= NSEC_PER_MSEC; *result = nsecs_to_jiffies64(ms); return 0; } __be64 nf_jiffies64_to_msecs(u64 input) { return cpu_to_be64(jiffies64_to_msecs(input)); } static int nf_tables_fill_set_concat(struct sk_buff *skb, const struct nft_set *set) { struct nlattr *concat, *field; int i; concat = nla_nest_start_noflag(skb, NFTA_SET_DESC_CONCAT); if (!concat) return -ENOMEM; for (i = 0; i < set->field_count; i++) { field = nla_nest_start_noflag(skb, NFTA_LIST_ELEM); if (!field) return -ENOMEM; if (nla_put_be32(skb, NFTA_SET_FIELD_LEN, htonl(set->field_len[i]))) return -ENOMEM; nla_nest_end(skb, field); } nla_nest_end(skb, concat); return 0; } static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx, const struct nft_set *set, u16 event, u16 flags) { u64 timeout = READ_ONCE(set->timeout); u32 gc_int = READ_ONCE(set->gc_int); u32 portid = ctx->portid; struct nlmsghdr *nlh; struct nlattr *nest; u32 seq = ctx->seq; int i; event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event); nlh = nfnl_msg_put(skb, portid, seq, event, flags, ctx->family, NFNETLINK_V0, nft_base_seq(ctx->net)); if (!nlh) goto nla_put_failure; if (nla_put_string(skb, NFTA_SET_TABLE, ctx->table->name)) goto nla_put_failure; if (nla_put_string(skb, NFTA_SET_NAME, set->name)) goto nla_put_failure; if (nla_put_be64(skb, NFTA_SET_HANDLE, cpu_to_be64(set->handle), NFTA_SET_PAD)) goto nla_put_failure; if (event == NFT_MSG_DELSET) { nlmsg_end(skb, nlh); return 0; } if (set->flags != 0) if (nla_put_be32(skb, NFTA_SET_FLAGS, htonl(set->flags))) goto nla_put_failure; if (nla_put_be32(skb, NFTA_SET_KEY_TYPE, htonl(set->ktype))) goto nla_put_failure; if (nla_put_be32(skb, NFTA_SET_KEY_LEN, htonl(set->klen))) goto nla_put_failure; if (set->flags & NFT_SET_MAP) { if (nla_put_be32(skb, NFTA_SET_DATA_TYPE, htonl(set->dtype))) goto nla_put_failure; if (nla_put_be32(skb, NFTA_SET_DATA_LEN, htonl(set->dlen))) goto nla_put_failure; } if (set->flags & NFT_SET_OBJECT && nla_put_be32(skb, NFTA_SET_OBJ_TYPE, htonl(set->objtype))) goto nla_put_failure; if (timeout && nla_put_be64(skb, NFTA_SET_TIMEOUT, nf_jiffies64_to_msecs(timeout), NFTA_SET_PAD)) goto nla_put_failure; if (gc_int && nla_put_be32(skb, NFTA_SET_GC_INTERVAL, htonl(gc_int))) goto nla_put_failure; if (set->policy != NFT_SET_POL_PERFORMANCE) { if (nla_put_be32(skb, NFTA_SET_POLICY, htonl(set->policy))) goto nla_put_failure; } if (set->udata && nla_put(skb, NFTA_SET_USERDATA, set->udlen, set->udata)) goto nla_put_failure; nest = nla_nest_start_noflag(skb, NFTA_SET_DESC); if (!nest) goto nla_put_failure; if (set->size && nla_put_be32(skb, NFTA_SET_DESC_SIZE, htonl(set->size))) goto nla_put_failure; if (set->field_count > 1 && nf_tables_fill_set_concat(skb, set)) goto nla_put_failure; nla_nest_end(skb, nest); if (set->num_exprs == 1) { nest = nla_nest_start_noflag(skb, NFTA_SET_EXPR); if (nf_tables_fill_expr_info(skb, set->exprs[0], false) < 0) goto nla_put_failure; nla_nest_end(skb, nest); } else if (set->num_exprs > 1) { nest = nla_nest_start_noflag(skb, NFTA_SET_EXPRESSIONS); if (nest == NULL) goto nla_put_failure; for (i = 0; i < set->num_exprs; i++) { if (nft_expr_dump(skb, NFTA_LIST_ELEM, set->exprs[i], false) < 0) goto nla_put_failure; } nla_nest_end(skb, nest); } nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_trim(skb, nlh); return -1; } static void nf_tables_set_notify(const struct nft_ctx *ctx, const struct nft_set *set, int event, gfp_t gfp_flags) { struct nftables_pernet *nft_net = nft_pernet(ctx->net); u32 portid = ctx->portid; struct sk_buff *skb; u16 flags = 0; int err; if (!ctx->report && !nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES)) return; skb = nlmsg_new(NLMSG_GOODSIZE, gfp_flags); if (skb == NULL) goto err; if (ctx->flags & (NLM_F_CREATE | NLM_F_EXCL)) flags |= ctx->flags & (NLM_F_CREATE | NLM_F_EXCL); err = nf_tables_fill_set(skb, ctx, set, event, flags); if (err < 0) { kfree_skb(skb); goto err; } nft_notify_enqueue(skb, ctx->report, &nft_net->notify_list); return; err: nfnetlink_set_err(ctx->net, portid, NFNLGRP_NFTABLES, -ENOBUFS); } static int nf_tables_dump_sets(struct sk_buff *skb, struct netlink_callback *cb) { const struct nft_set *set; unsigned int idx, s_idx = cb->args[0]; struct nft_table *table, *cur_table = (struct nft_table *)cb->args[2]; struct net *net = sock_net(skb->sk); struct nft_ctx *ctx = cb->data, ctx_set; struct nftables_pernet *nft_net; if (cb->args[1]) return skb->len; rcu_read_lock(); nft_net = nft_pernet(net); cb->seq = READ_ONCE(nft_net->base_seq); list_for_each_entry_rcu(table, &nft_net->tables, list) { if (ctx->family != NFPROTO_UNSPEC && ctx->family != table->family) continue; if (ctx->table && ctx->table != table) continue; if (cur_table) { if (cur_table != table) continue; cur_table = NULL; } idx = 0; list_for_each_entry_rcu(set, &table->sets, list) { if (idx < s_idx) goto cont; if (!nft_is_active(net, set)) goto cont; ctx_set = *ctx; ctx_set.table = table; ctx_set.family = table->family; if (nf_tables_fill_set(skb, &ctx_set, set, NFT_MSG_NEWSET, NLM_F_MULTI) < 0) { cb->args[0] = idx; cb->args[2] = (unsigned long) table; goto done; } nl_dump_check_consistent(cb, nlmsg_hdr(skb)); cont: idx++; } if (s_idx) s_idx = 0; } cb->args[1] = 1; done: rcu_read_unlock(); return skb->len; } static int nf_tables_dump_sets_start(struct netlink_callback *cb) { struct nft_ctx *ctx_dump = NULL; ctx_dump = kmemdup(cb->data, sizeof(*ctx_dump), GFP_ATOMIC); if (ctx_dump == NULL) return -ENOMEM; cb->data = ctx_dump; return 0; } static int nf_tables_dump_sets_done(struct netlink_callback *cb) { kfree(cb->data); return 0; } /* called with rcu_read_lock held */ static int nf_tables_getset(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_cur(info->net); u8 family = info->nfmsg->nfgen_family; struct nft_table *table = NULL; struct net *net = info->net; const struct nft_set *set; struct sk_buff *skb2; struct nft_ctx ctx; int err; if (nla[NFTA_SET_TABLE]) { table = nft_table_lookup(net, nla[NFTA_SET_TABLE], family, genmask, 0); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_SET_TABLE]); return PTR_ERR(table); } } nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .start = nf_tables_dump_sets_start, .dump = nf_tables_dump_sets, .done = nf_tables_dump_sets_done, .data = &ctx, .module = THIS_MODULE, }; return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); } /* Only accept unspec with dump */ if (info->nfmsg->nfgen_family == NFPROTO_UNSPEC) return -EAFNOSUPPORT; if (!nla[NFTA_SET_TABLE]) return -EINVAL; set = nft_set_lookup(table, nla[NFTA_SET_NAME], genmask); if (IS_ERR(set)) { NL_SET_BAD_ATTR(extack, nla[NFTA_SET_NAME]); return PTR_ERR(set); } skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC); if (skb2 == NULL) return -ENOMEM; err = nf_tables_fill_set(skb2, &ctx, set, NFT_MSG_NEWSET, 0); if (err < 0) goto err_fill_set_info; return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); err_fill_set_info: kfree_skb(skb2); return err; } static int nft_set_desc_concat_parse(const struct nlattr *attr, struct nft_set_desc *desc) { struct nlattr *tb[NFTA_SET_FIELD_MAX + 1]; u32 len; int err; if (desc->field_count >= ARRAY_SIZE(desc->field_len)) return -E2BIG; err = nla_parse_nested_deprecated(tb, NFTA_SET_FIELD_MAX, attr, nft_concat_policy, NULL); if (err < 0) return err; if (!tb[NFTA_SET_FIELD_LEN]) return -EINVAL; len = ntohl(nla_get_be32(tb[NFTA_SET_FIELD_LEN])); if (!len || len > U8_MAX) return -EINVAL; desc->field_len[desc->field_count++] = len; return 0; } static int nft_set_desc_concat(struct nft_set_desc *desc, const struct nlattr *nla) { u32 num_regs = 0, key_num_regs = 0; struct nlattr *attr; int rem, err, i; nla_for_each_nested(attr, nla, rem) { if (nla_type(attr) != NFTA_LIST_ELEM) return -EINVAL; err = nft_set_desc_concat_parse(attr, desc); if (err < 0) return err; } for (i = 0; i < desc->field_count; i++) num_regs += DIV_ROUND_UP(desc->field_len[i], sizeof(u32)); key_num_regs = DIV_ROUND_UP(desc->klen, sizeof(u32)); if (key_num_regs != num_regs) return -EINVAL; if (num_regs > NFT_REG32_COUNT) return -E2BIG; return 0; } static int nf_tables_set_desc_parse(struct nft_set_desc *desc, const struct nlattr *nla) { struct nlattr *da[NFTA_SET_DESC_MAX + 1]; int err; err = nla_parse_nested_deprecated(da, NFTA_SET_DESC_MAX, nla, nft_set_desc_policy, NULL); if (err < 0) return err; if (da[NFTA_SET_DESC_SIZE] != NULL) desc->size = ntohl(nla_get_be32(da[NFTA_SET_DESC_SIZE])); if (da[NFTA_SET_DESC_CONCAT]) err = nft_set_desc_concat(desc, da[NFTA_SET_DESC_CONCAT]); return err; } static int nft_set_expr_alloc(struct nft_ctx *ctx, struct nft_set *set, const struct nlattr * const *nla, struct nft_expr **exprs, int *num_exprs, u32 flags) { struct nft_expr *expr; int err, i; if (nla[NFTA_SET_EXPR]) { expr = nft_set_elem_expr_alloc(ctx, set, nla[NFTA_SET_EXPR]); if (IS_ERR(expr)) { err = PTR_ERR(expr); goto err_set_expr_alloc; } exprs[0] = expr; (*num_exprs)++; } else if (nla[NFTA_SET_EXPRESSIONS]) { struct nlattr *tmp; int left; if (!(flags & NFT_SET_EXPR)) { err = -EINVAL; goto err_set_expr_alloc; } i = 0; nla_for_each_nested(tmp, nla[NFTA_SET_EXPRESSIONS], left) { if (i == NFT_SET_EXPR_MAX) { err = -E2BIG; goto err_set_expr_alloc; } if (nla_type(tmp) != NFTA_LIST_ELEM) { err = -EINVAL; goto err_set_expr_alloc; } expr = nft_set_elem_expr_alloc(ctx, set, tmp); if (IS_ERR(expr)) { err = PTR_ERR(expr); goto err_set_expr_alloc; } exprs[i++] = expr; (*num_exprs)++; } } return 0; err_set_expr_alloc: for (i = 0; i < *num_exprs; i++) nft_expr_destroy(ctx, exprs[i]); return err; } static bool nft_set_is_same(const struct nft_set *set, const struct nft_set_desc *desc, struct nft_expr *exprs[], u32 num_exprs, u32 flags) { int i; if (set->ktype != desc->ktype || set->dtype != desc->dtype || set->flags != flags || set->klen != desc->klen || set->dlen != desc->dlen || set->field_count != desc->field_count || set->num_exprs != num_exprs) return false; for (i = 0; i < desc->field_count; i++) { if (set->field_len[i] != desc->field_len[i]) return false; } for (i = 0; i < num_exprs; i++) { if (set->exprs[i]->ops != exprs[i]->ops) return false; } return true; } static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); u8 family = info->nfmsg->nfgen_family; const struct nft_set_ops *ops; struct net *net = info->net; struct nft_set_desc desc; struct nft_table *table; unsigned char *udata; struct nft_set *set; struct nft_ctx ctx; size_t alloc_size; int num_exprs = 0; char *name; int err, i; u16 udlen; u32 flags; u64 size; if (nla[NFTA_SET_TABLE] == NULL || nla[NFTA_SET_NAME] == NULL || nla[NFTA_SET_KEY_LEN] == NULL || nla[NFTA_SET_ID] == NULL) return -EINVAL; memset(&desc, 0, sizeof(desc)); desc.ktype = NFT_DATA_VALUE; if (nla[NFTA_SET_KEY_TYPE] != NULL) { desc.ktype = ntohl(nla_get_be32(nla[NFTA_SET_KEY_TYPE])); if ((desc.ktype & NFT_DATA_RESERVED_MASK) == NFT_DATA_RESERVED_MASK) return -EINVAL; } desc.klen = ntohl(nla_get_be32(nla[NFTA_SET_KEY_LEN])); if (desc.klen == 0 || desc.klen > NFT_DATA_VALUE_MAXLEN) return -EINVAL; flags = 0; if (nla[NFTA_SET_FLAGS] != NULL) { flags = ntohl(nla_get_be32(nla[NFTA_SET_FLAGS])); if (flags & ~(NFT_SET_ANONYMOUS | NFT_SET_CONSTANT | NFT_SET_INTERVAL | NFT_SET_TIMEOUT | NFT_SET_MAP | NFT_SET_EVAL | NFT_SET_OBJECT | NFT_SET_CONCAT | NFT_SET_EXPR)) return -EOPNOTSUPP; /* Only one of these operations is supported */ if ((flags & (NFT_SET_MAP | NFT_SET_OBJECT)) == (NFT_SET_MAP | NFT_SET_OBJECT)) return -EOPNOTSUPP; if ((flags & (NFT_SET_EVAL | NFT_SET_OBJECT)) == (NFT_SET_EVAL | NFT_SET_OBJECT)) return -EOPNOTSUPP; if ((flags & (NFT_SET_ANONYMOUS | NFT_SET_TIMEOUT | NFT_SET_EVAL)) == (NFT_SET_ANONYMOUS | NFT_SET_TIMEOUT)) return -EOPNOTSUPP; if ((flags & (NFT_SET_CONSTANT | NFT_SET_TIMEOUT)) == (NFT_SET_CONSTANT | NFT_SET_TIMEOUT)) return -EOPNOTSUPP; } desc.dtype = 0; if (nla[NFTA_SET_DATA_TYPE] != NULL) { if (!(flags & NFT_SET_MAP)) return -EINVAL; desc.dtype = ntohl(nla_get_be32(nla[NFTA_SET_DATA_TYPE])); if ((desc.dtype & NFT_DATA_RESERVED_MASK) == NFT_DATA_RESERVED_MASK && desc.dtype != NFT_DATA_VERDICT) return -EINVAL; if (desc.dtype != NFT_DATA_VERDICT) { if (nla[NFTA_SET_DATA_LEN] == NULL) return -EINVAL; desc.dlen = ntohl(nla_get_be32(nla[NFTA_SET_DATA_LEN])); if (desc.dlen == 0 || desc.dlen > NFT_DATA_VALUE_MAXLEN) return -EINVAL; } else desc.dlen = sizeof(struct nft_verdict); } else if (flags & NFT_SET_MAP) return -EINVAL; if (nla[NFTA_SET_OBJ_TYPE] != NULL) { if (!(flags & NFT_SET_OBJECT)) return -EINVAL; desc.objtype = ntohl(nla_get_be32(nla[NFTA_SET_OBJ_TYPE])); if (desc.objtype == NFT_OBJECT_UNSPEC || desc.objtype > NFT_OBJECT_MAX) return -EOPNOTSUPP; } else if (flags & NFT_SET_OBJECT) return -EINVAL; else desc.objtype = NFT_OBJECT_UNSPEC; desc.timeout = 0; if (nla[NFTA_SET_TIMEOUT] != NULL) { if (!(flags & NFT_SET_TIMEOUT)) return -EINVAL; if (flags & NFT_SET_ANONYMOUS) return -EOPNOTSUPP; err = nf_msecs_to_jiffies64(nla[NFTA_SET_TIMEOUT], &desc.timeout); if (err) return err; } desc.gc_int = 0; if (nla[NFTA_SET_GC_INTERVAL] != NULL) { if (!(flags & NFT_SET_TIMEOUT)) return -EINVAL; if (flags & NFT_SET_ANONYMOUS) return -EOPNOTSUPP; desc.gc_int = ntohl(nla_get_be32(nla[NFTA_SET_GC_INTERVAL])); } desc.policy = NFT_SET_POL_PERFORMANCE; if (nla[NFTA_SET_POLICY] != NULL) { desc.policy = ntohl(nla_get_be32(nla[NFTA_SET_POLICY])); switch (desc.policy) { case NFT_SET_POL_PERFORMANCE: case NFT_SET_POL_MEMORY: break; default: return -EOPNOTSUPP; } } if (nla[NFTA_SET_DESC] != NULL) { err = nf_tables_set_desc_parse(&desc, nla[NFTA_SET_DESC]); if (err < 0) return err; if (desc.field_count > 1) { if (!(flags & NFT_SET_CONCAT)) return -EINVAL; } else if (flags & NFT_SET_CONCAT) { return -EINVAL; } } else if (flags & NFT_SET_CONCAT) { return -EINVAL; } if (nla[NFTA_SET_EXPR] || nla[NFTA_SET_EXPRESSIONS]) desc.expr = true; table = nft_table_lookup(net, nla[NFTA_SET_TABLE], family, genmask, NETLINK_CB(skb).portid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_SET_TABLE]); return PTR_ERR(table); } nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); set = nft_set_lookup(table, nla[NFTA_SET_NAME], genmask); if (IS_ERR(set)) { if (PTR_ERR(set) != -ENOENT) { NL_SET_BAD_ATTR(extack, nla[NFTA_SET_NAME]); return PTR_ERR(set); } } else { struct nft_expr *exprs[NFT_SET_EXPR_MAX] = {}; if (info->nlh->nlmsg_flags & NLM_F_EXCL) { NL_SET_BAD_ATTR(extack, nla[NFTA_SET_NAME]); return -EEXIST; } if (info->nlh->nlmsg_flags & NLM_F_REPLACE) return -EOPNOTSUPP; if (nft_set_is_anonymous(set)) return -EOPNOTSUPP; err = nft_set_expr_alloc(&ctx, set, nla, exprs, &num_exprs, flags); if (err < 0) return err; err = 0; if (!nft_set_is_same(set, &desc, exprs, num_exprs, flags)) { NL_SET_BAD_ATTR(extack, nla[NFTA_SET_NAME]); err = -EEXIST; } for (i = 0; i < num_exprs; i++) nft_expr_destroy(&ctx, exprs[i]); if (err < 0) return err; return __nft_trans_set_add(&ctx, NFT_MSG_NEWSET, set, &desc); } if (!(info->nlh->nlmsg_flags & NLM_F_CREATE)) return -ENOENT; ops = nft_select_set_ops(&ctx, flags, &desc); if (IS_ERR(ops)) return PTR_ERR(ops); udlen = 0; if (nla[NFTA_SET_USERDATA]) udlen = nla_len(nla[NFTA_SET_USERDATA]); size = 0; if (ops->privsize != NULL) size = ops->privsize(nla, &desc); alloc_size = sizeof(*set) + size + udlen; if (alloc_size < size || alloc_size > INT_MAX) return -ENOMEM; if (!nft_use_inc(&table->use)) return -EMFILE; set = kvzalloc(alloc_size, GFP_KERNEL_ACCOUNT); if (!set) { err = -ENOMEM; goto err_alloc; } name = nla_strdup(nla[NFTA_SET_NAME], GFP_KERNEL_ACCOUNT); if (!name) { err = -ENOMEM; goto err_set_name; } err = nf_tables_set_alloc_name(&ctx, set, name); kfree(name); if (err < 0) goto err_set_name; udata = NULL; if (udlen) { udata = set->data + size; nla_memcpy(udata, nla[NFTA_SET_USERDATA], udlen); } INIT_LIST_HEAD(&set->bindings); INIT_LIST_HEAD(&set->catchall_list); refcount_set(&set->refs, 1); set->table = table; write_pnet(&set->net, net); set->ops = ops; set->ktype = desc.ktype; set->klen = desc.klen; set->dtype = desc.dtype; set->objtype = desc.objtype; set->dlen = desc.dlen; set->flags = flags; set->size = desc.size; set->policy = desc.policy; set->udlen = udlen; set->udata = udata; set->timeout = desc.timeout; set->gc_int = desc.gc_int; set->field_count = desc.field_count; for (i = 0; i < desc.field_count; i++) set->field_len[i] = desc.field_len[i]; err = ops->init(set, &desc, nla); if (err < 0) goto err_set_init; err = nft_set_expr_alloc(&ctx, set, nla, set->exprs, &num_exprs, flags); if (err < 0) goto err_set_destroy; set->num_exprs = num_exprs; set->handle = nf_tables_alloc_handle(table); INIT_LIST_HEAD(&set->pending_update); err = nft_trans_set_add(&ctx, NFT_MSG_NEWSET, set); if (err < 0) goto err_set_expr_alloc; list_add_tail_rcu(&set->list, &table->sets); return 0; err_set_expr_alloc: for (i = 0; i < set->num_exprs; i++) nft_expr_destroy(&ctx, set->exprs[i]); err_set_destroy: ops->destroy(&ctx, set); err_set_init: kfree(set->name); err_set_name: kvfree(set); err_alloc: nft_use_dec_restore(&table->use); return err; } static void nft_set_catchall_destroy(const struct nft_ctx *ctx, struct nft_set *set) { struct nft_set_elem_catchall *next, *catchall; list_for_each_entry_safe(catchall, next, &set->catchall_list, list) { list_del_rcu(&catchall->list); nf_tables_set_elem_destroy(ctx, set, catchall->elem); kfree_rcu(catchall, rcu); } } static void nft_set_put(struct nft_set *set) { if (refcount_dec_and_test(&set->refs)) { kfree(set->name); kvfree(set); } } static void nft_set_destroy(const struct nft_ctx *ctx, struct nft_set *set) { int i; if (WARN_ON(set->use > 0)) return; for (i = 0; i < set->num_exprs; i++) nft_expr_destroy(ctx, set->exprs[i]); set->ops->destroy(ctx, set); nft_set_catchall_destroy(ctx, set); nft_set_put(set); } static int nf_tables_delset(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); u8 family = info->nfmsg->nfgen_family; struct net *net = info->net; const struct nlattr *attr; struct nft_table *table; struct nft_set *set; struct nft_ctx ctx; if (info->nfmsg->nfgen_family == NFPROTO_UNSPEC) return -EAFNOSUPPORT; table = nft_table_lookup(net, nla[NFTA_SET_TABLE], family, genmask, NETLINK_CB(skb).portid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_SET_TABLE]); return PTR_ERR(table); } if (nla[NFTA_SET_HANDLE]) { attr = nla[NFTA_SET_HANDLE]; set = nft_set_lookup_byhandle(table, attr, genmask); } else { attr = nla[NFTA_SET_NAME]; set = nft_set_lookup(table, attr, genmask); } if (IS_ERR(set)) { if (PTR_ERR(set) == -ENOENT && NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_DESTROYSET) return 0; NL_SET_BAD_ATTR(extack, attr); return PTR_ERR(set); } if (set->use || (info->nlh->nlmsg_flags & NLM_F_NONREC && atomic_read(&set->nelems) > 0)) { NL_SET_BAD_ATTR(extack, attr); return -EBUSY; } nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); return nft_delset(&ctx, set); } static int nft_validate_register_store(const struct nft_ctx *ctx, enum nft_registers reg, const struct nft_data *data, enum nft_data_types type, unsigned int len); static int nft_setelem_data_validate(const struct nft_ctx *ctx, struct nft_set *set, struct nft_elem_priv *elem_priv) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); enum nft_registers dreg; dreg = nft_type_to_reg(set->dtype); return nft_validate_register_store(ctx, dreg, nft_set_ext_data(ext), set->dtype == NFT_DATA_VERDICT ? NFT_DATA_VERDICT : NFT_DATA_VALUE, set->dlen); } static int nf_tables_bind_check_setelem(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_set_iter *iter, struct nft_elem_priv *elem_priv) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); if (!nft_set_elem_active(ext, iter->genmask)) return 0; return nft_setelem_data_validate(ctx, set, elem_priv); } static int nft_set_catchall_bind_check(const struct nft_ctx *ctx, struct nft_set *set) { u8 genmask = nft_genmask_next(ctx->net); struct nft_set_elem_catchall *catchall; struct nft_set_ext *ext; int ret = 0; list_for_each_entry_rcu(catchall, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); if (!nft_set_elem_active(ext, genmask)) continue; ret = nft_setelem_data_validate(ctx, set, catchall->elem); if (ret < 0) break; } return ret; } int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_binding *binding) { struct nft_set_binding *i; struct nft_set_iter iter; if (!list_empty(&set->bindings) && nft_set_is_anonymous(set)) return -EBUSY; if (binding->flags & NFT_SET_MAP) { /* If the set is already bound to the same chain all * jumps are already validated for that chain. */ list_for_each_entry(i, &set->bindings, list) { if (i->flags & NFT_SET_MAP && i->chain == binding->chain) goto bind; } iter.genmask = nft_genmask_next(ctx->net); iter.type = NFT_ITER_UPDATE; iter.skip = 0; iter.count = 0; iter.err = 0; iter.fn = nf_tables_bind_check_setelem; set->ops->walk(ctx, set, &iter); if (!iter.err) iter.err = nft_set_catchall_bind_check(ctx, set); if (iter.err < 0) return iter.err; } bind: if (!nft_use_inc(&set->use)) return -EMFILE; binding->chain = ctx->chain; list_add_tail_rcu(&binding->list, &set->bindings); nft_set_trans_bind(ctx, set); return 0; } EXPORT_SYMBOL_GPL(nf_tables_bind_set); static void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_binding *binding, bool event) { list_del_rcu(&binding->list); if (list_empty(&set->bindings) && nft_set_is_anonymous(set)) { list_del_rcu(&set->list); set->dead = 1; if (event) nf_tables_set_notify(ctx, set, NFT_MSG_DELSET, GFP_KERNEL); } } static void nft_setelem_data_activate(const struct net *net, const struct nft_set *set, struct nft_elem_priv *elem_priv); static int nft_mapelem_activate(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_set_iter *iter, struct nft_elem_priv *elem_priv) { struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); /* called from abort path, reverse check to undo changes. */ if (nft_set_elem_active(ext, iter->genmask)) return 0; nft_clear(ctx->net, ext); nft_setelem_data_activate(ctx->net, set, elem_priv); return 0; } static void nft_map_catchall_activate(const struct nft_ctx *ctx, struct nft_set *set) { u8 genmask = nft_genmask_next(ctx->net); struct nft_set_elem_catchall *catchall; struct nft_set_ext *ext; list_for_each_entry(catchall, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); if (!nft_set_elem_active(ext, genmask)) continue; nft_clear(ctx->net, ext); nft_setelem_data_activate(ctx->net, set, catchall->elem); break; } } static void nft_map_activate(const struct nft_ctx *ctx, struct nft_set *set) { struct nft_set_iter iter = { .genmask = nft_genmask_next(ctx->net), .type = NFT_ITER_UPDATE, .fn = nft_mapelem_activate, }; set->ops->walk(ctx, set, &iter); WARN_ON_ONCE(iter.err); nft_map_catchall_activate(ctx, set); } void nf_tables_activate_set(const struct nft_ctx *ctx, struct nft_set *set) { if (nft_set_is_anonymous(set)) { if (set->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) nft_map_activate(ctx, set); nft_clear(ctx->net, set); } nft_use_inc_restore(&set->use); } EXPORT_SYMBOL_GPL(nf_tables_activate_set); void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_binding *binding, enum nft_trans_phase phase) { switch (phase) { case NFT_TRANS_PREPARE_ERROR: nft_set_trans_unbind(ctx, set); if (nft_set_is_anonymous(set)) nft_deactivate_next(ctx->net, set); else list_del_rcu(&binding->list); nft_use_dec(&set->use); break; case NFT_TRANS_PREPARE: if (nft_set_is_anonymous(set)) { if (set->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) nft_map_deactivate(ctx, set); nft_deactivate_next(ctx->net, set); } nft_use_dec(&set->use); return; case NFT_TRANS_ABORT: case NFT_TRANS_RELEASE: if (nft_set_is_anonymous(set) && set->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) nft_map_deactivate(ctx, set); nft_use_dec(&set->use); fallthrough; default: nf_tables_unbind_set(ctx, set, binding, phase == NFT_TRANS_COMMIT); } } EXPORT_SYMBOL_GPL(nf_tables_deactivate_set); void nf_tables_destroy_set(const struct nft_ctx *ctx, struct nft_set *set) { if (list_empty(&set->bindings) && nft_set_is_anonymous(set)) nft_set_destroy(ctx, set); } EXPORT_SYMBOL_GPL(nf_tables_destroy_set); const struct nft_set_ext_type nft_set_ext_types[] = { [NFT_SET_EXT_KEY] = { .align = __alignof__(u32), }, [NFT_SET_EXT_DATA] = { .align = __alignof__(u32), }, [NFT_SET_EXT_EXPRESSIONS] = { .align = __alignof__(struct nft_set_elem_expr), }, [NFT_SET_EXT_OBJREF] = { .len = sizeof(struct nft_object *), .align = __alignof__(struct nft_object *), }, [NFT_SET_EXT_FLAGS] = { .len = sizeof(u8), .align = __alignof__(u8), }, [NFT_SET_EXT_TIMEOUT] = { .len = sizeof(u64), .align = __alignof__(u64), }, [NFT_SET_EXT_EXPIRATION] = { .len = sizeof(u64), .align = __alignof__(u64), }, [NFT_SET_EXT_USERDATA] = { .len = sizeof(struct nft_userdata), .align = __alignof__(struct nft_userdata), }, [NFT_SET_EXT_KEY_END] = { .align = __alignof__(u32), }, }; /* * Set elements */ static const struct nla_policy nft_set_elem_policy[NFTA_SET_ELEM_MAX + 1] = { [NFTA_SET_ELEM_KEY] = { .type = NLA_NESTED }, [NFTA_SET_ELEM_DATA] = { .type = NLA_NESTED }, [NFTA_SET_ELEM_FLAGS] = { .type = NLA_U32 }, [NFTA_SET_ELEM_TIMEOUT] = { .type = NLA_U64 }, [NFTA_SET_ELEM_EXPIRATION] = { .type = NLA_U64 }, [NFTA_SET_ELEM_USERDATA] = { .type = NLA_BINARY, .len = NFT_USERDATA_MAXLEN }, [NFTA_SET_ELEM_EXPR] = { .type = NLA_NESTED }, [NFTA_SET_ELEM_OBJREF] = { .type = NLA_STRING, .len = NFT_OBJ_MAXNAMELEN - 1 }, [NFTA_SET_ELEM_KEY_END] = { .type = NLA_NESTED }, [NFTA_SET_ELEM_EXPRESSIONS] = NLA_POLICY_NESTED_ARRAY(nft_expr_policy), }; static const struct nla_policy nft_set_elem_list_policy[NFTA_SET_ELEM_LIST_MAX + 1] = { [NFTA_SET_ELEM_LIST_TABLE] = { .type = NLA_STRING, .len = NFT_TABLE_MAXNAMELEN - 1 }, [NFTA_SET_ELEM_LIST_SET] = { .type = NLA_STRING, .len = NFT_SET_MAXNAMELEN - 1 }, [NFTA_SET_ELEM_LIST_ELEMENTS] = NLA_POLICY_NESTED_ARRAY(nft_set_elem_policy), [NFTA_SET_ELEM_LIST_SET_ID] = { .type = NLA_U32 }, }; static int nft_set_elem_expr_dump(struct sk_buff *skb, const struct nft_set *set, const struct nft_set_ext *ext, bool reset) { struct nft_set_elem_expr *elem_expr; u32 size, num_exprs = 0; struct nft_expr *expr; struct nlattr *nest; elem_expr = nft_set_ext_expr(ext); nft_setelem_expr_foreach(expr, elem_expr, size) num_exprs++; if (num_exprs == 1) { expr = nft_setelem_expr_at(elem_expr, 0); if (nft_expr_dump(skb, NFTA_SET_ELEM_EXPR, expr, reset) < 0) return -1; return 0; } else if (num_exprs > 1) { nest = nla_nest_start_noflag(skb, NFTA_SET_ELEM_EXPRESSIONS); if (nest == NULL) goto nla_put_failure; nft_setelem_expr_foreach(expr, elem_expr, size) { expr = nft_setelem_expr_at(elem_expr, size); if (nft_expr_dump(skb, NFTA_LIST_ELEM, expr, reset) < 0) goto nla_put_failure; } nla_nest_end(skb, nest); } return 0; nla_put_failure: return -1; } static int nf_tables_fill_setelem(struct sk_buff *skb, const struct nft_set *set, const struct nft_elem_priv *elem_priv, bool reset) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); unsigned char *b = skb_tail_pointer(skb); struct nlattr *nest; nest = nla_nest_start_noflag(skb, NFTA_LIST_ELEM); if (nest == NULL) goto nla_put_failure; if (nft_set_ext_exists(ext, NFT_SET_EXT_KEY) && nft_data_dump(skb, NFTA_SET_ELEM_KEY, nft_set_ext_key(ext), NFT_DATA_VALUE, set->klen) < 0) goto nla_put_failure; if (nft_set_ext_exists(ext, NFT_SET_EXT_KEY_END) && nft_data_dump(skb, NFTA_SET_ELEM_KEY_END, nft_set_ext_key_end(ext), NFT_DATA_VALUE, set->klen) < 0) goto nla_put_failure; if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA) && nft_data_dump(skb, NFTA_SET_ELEM_DATA, nft_set_ext_data(ext), set->dtype == NFT_DATA_VERDICT ? NFT_DATA_VERDICT : NFT_DATA_VALUE, set->dlen) < 0) goto nla_put_failure; if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPRESSIONS) && nft_set_elem_expr_dump(skb, set, ext, reset)) goto nla_put_failure; if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF) && nla_put_string(skb, NFTA_SET_ELEM_OBJREF, (*nft_set_ext_obj(ext))->key.name) < 0) goto nla_put_failure; if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && nla_put_be32(skb, NFTA_SET_ELEM_FLAGS, htonl(*nft_set_ext_flags(ext)))) goto nla_put_failure; if (nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT) && nla_put_be64(skb, NFTA_SET_ELEM_TIMEOUT, nf_jiffies64_to_msecs(*nft_set_ext_timeout(ext)), NFTA_SET_ELEM_PAD)) goto nla_put_failure; if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION)) { u64 expires, now = get_jiffies_64(); expires = *nft_set_ext_expiration(ext); if (time_before64(now, expires)) expires -= now; else expires = 0; if (nla_put_be64(skb, NFTA_SET_ELEM_EXPIRATION, nf_jiffies64_to_msecs(expires), NFTA_SET_ELEM_PAD)) goto nla_put_failure; } if (nft_set_ext_exists(ext, NFT_SET_EXT_USERDATA)) { struct nft_userdata *udata; udata = nft_set_ext_userdata(ext); if (nla_put(skb, NFTA_SET_ELEM_USERDATA, udata->len + 1, udata->data)) goto nla_put_failure; } nla_nest_end(skb, nest); return 0; nla_put_failure: nlmsg_trim(skb, b); return -EMSGSIZE; } struct nft_set_dump_args { const struct netlink_callback *cb; struct nft_set_iter iter; struct sk_buff *skb; bool reset; }; static int nf_tables_dump_setelem(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_set_iter *iter, struct nft_elem_priv *elem_priv) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); struct nft_set_dump_args *args; if (!nft_set_elem_active(ext, iter->genmask)) return 0; if (nft_set_elem_expired(ext) || nft_set_elem_is_dead(ext)) return 0; args = container_of(iter, struct nft_set_dump_args, iter); return nf_tables_fill_setelem(args->skb, set, elem_priv, args->reset); } static void audit_log_nft_set_reset(const struct nft_table *table, unsigned int base_seq, unsigned int nentries) { char *buf = kasprintf(GFP_ATOMIC, "%s:%u", table->name, base_seq); audit_log_nfcfg(buf, table->family, nentries, AUDIT_NFT_OP_SETELEM_RESET, GFP_ATOMIC); kfree(buf); } struct nft_set_dump_ctx { const struct nft_set *set; struct nft_ctx ctx; bool reset; }; static int nft_set_catchall_dump(struct net *net, struct sk_buff *skb, const struct nft_set *set, bool reset, unsigned int base_seq) { struct nft_set_elem_catchall *catchall; u8 genmask = nft_genmask_cur(net); struct nft_set_ext *ext; int ret = 0; list_for_each_entry_rcu(catchall, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); if (!nft_set_elem_active(ext, genmask) || nft_set_elem_expired(ext)) continue; ret = nf_tables_fill_setelem(skb, set, catchall->elem, reset); if (reset && !ret) audit_log_nft_set_reset(set->table, base_seq, 1); break; } return ret; } static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb) { struct nft_set_dump_ctx *dump_ctx = cb->data; struct net *net = sock_net(skb->sk); struct nftables_pernet *nft_net; struct nft_table *table; struct nft_set *set; struct nft_set_dump_args args; bool set_found = false; struct nlmsghdr *nlh; struct nlattr *nest; u32 portid, seq; int event; rcu_read_lock(); nft_net = nft_pernet(net); cb->seq = READ_ONCE(nft_net->base_seq); list_for_each_entry_rcu(table, &nft_net->tables, list) { if (dump_ctx->ctx.family != NFPROTO_UNSPEC && dump_ctx->ctx.family != table->family) continue; if (table != dump_ctx->ctx.table) continue; list_for_each_entry_rcu(set, &table->sets, list) { if (set == dump_ctx->set) { set_found = true; break; } } break; } if (!set_found) { rcu_read_unlock(); return -ENOENT; } event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, NFT_MSG_NEWSETELEM); portid = NETLINK_CB(cb->skb).portid; seq = cb->nlh->nlmsg_seq; nlh = nfnl_msg_put(skb, portid, seq, event, NLM_F_MULTI, table->family, NFNETLINK_V0, nft_base_seq(net)); if (!nlh) goto nla_put_failure; if (nla_put_string(skb, NFTA_SET_ELEM_LIST_TABLE, table->name)) goto nla_put_failure; if (nla_put_string(skb, NFTA_SET_ELEM_LIST_SET, set->name)) goto nla_put_failure; nest = nla_nest_start_noflag(skb, NFTA_SET_ELEM_LIST_ELEMENTS); if (nest == NULL) goto nla_put_failure; args.cb = cb; args.skb = skb; args.reset = dump_ctx->reset; args.iter.genmask = nft_genmask_cur(net); args.iter.type = NFT_ITER_READ; args.iter.skip = cb->args[0]; args.iter.count = 0; args.iter.err = 0; args.iter.fn = nf_tables_dump_setelem; set->ops->walk(&dump_ctx->ctx, set, &args.iter); if (!args.iter.err && args.iter.count == cb->args[0]) args.iter.err = nft_set_catchall_dump(net, skb, set, dump_ctx->reset, cb->seq); nla_nest_end(skb, nest); nlmsg_end(skb, nlh); rcu_read_unlock(); if (args.iter.err && args.iter.err != -EMSGSIZE) return args.iter.err; if (args.iter.count == cb->args[0]) return 0; cb->args[0] = args.iter.count; return skb->len; nla_put_failure: rcu_read_unlock(); return -ENOSPC; } static int nf_tables_dumpreset_set(struct sk_buff *skb, struct netlink_callback *cb) { struct nftables_pernet *nft_net = nft_pernet(sock_net(skb->sk)); struct nft_set_dump_ctx *dump_ctx = cb->data; int ret, skip = cb->args[0]; mutex_lock(&nft_net->commit_mutex); ret = nf_tables_dump_set(skb, cb); if (cb->args[0] > skip) audit_log_nft_set_reset(dump_ctx->ctx.table, cb->seq, cb->args[0] - skip); mutex_unlock(&nft_net->commit_mutex); return ret; } static int nf_tables_dump_set_start(struct netlink_callback *cb) { struct nft_set_dump_ctx *dump_ctx = cb->data; cb->data = kmemdup(dump_ctx, sizeof(*dump_ctx), GFP_ATOMIC); return cb->data ? 0 : -ENOMEM; } static int nf_tables_dump_set_done(struct netlink_callback *cb) { kfree(cb->data); return 0; } static int nf_tables_fill_setelem_info(struct sk_buff *skb, const struct nft_ctx *ctx, u32 seq, u32 portid, int event, u16 flags, const struct nft_set *set, const struct nft_elem_priv *elem_priv, bool reset) { struct nlmsghdr *nlh; struct nlattr *nest; int err; event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event); nlh = nfnl_msg_put(skb, portid, seq, event, flags, ctx->family, NFNETLINK_V0, nft_base_seq(ctx->net)); if (!nlh) goto nla_put_failure; if (nla_put_string(skb, NFTA_SET_TABLE, ctx->table->name)) goto nla_put_failure; if (nla_put_string(skb, NFTA_SET_NAME, set->name)) goto nla_put_failure; nest = nla_nest_start_noflag(skb, NFTA_SET_ELEM_LIST_ELEMENTS); if (nest == NULL) goto nla_put_failure; err = nf_tables_fill_setelem(skb, set, elem_priv, reset); if (err < 0) goto nla_put_failure; nla_nest_end(skb, nest); nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_trim(skb, nlh); return -1; } static int nft_setelem_parse_flags(const struct nft_set *set, const struct nlattr *attr, u32 *flags) { if (attr == NULL) return 0; *flags = ntohl(nla_get_be32(attr)); if (*flags & ~(NFT_SET_ELEM_INTERVAL_END | NFT_SET_ELEM_CATCHALL)) return -EOPNOTSUPP; if (!(set->flags & NFT_SET_INTERVAL) && *flags & NFT_SET_ELEM_INTERVAL_END) return -EINVAL; if ((*flags & (NFT_SET_ELEM_INTERVAL_END | NFT_SET_ELEM_CATCHALL)) == (NFT_SET_ELEM_INTERVAL_END | NFT_SET_ELEM_CATCHALL)) return -EINVAL; return 0; } static int nft_setelem_parse_key(struct nft_ctx *ctx, const struct nft_set *set, struct nft_data *key, struct nlattr *attr) { struct nft_data_desc desc = { .type = NFT_DATA_VALUE, .size = NFT_DATA_VALUE_MAXLEN, .len = set->klen, }; return nft_data_init(ctx, key, &desc, attr); } static int nft_setelem_parse_data(struct nft_ctx *ctx, struct nft_set *set, struct nft_data_desc *desc, struct nft_data *data, struct nlattr *attr) { u32 dtype; if (set->dtype == NFT_DATA_VERDICT) dtype = NFT_DATA_VERDICT; else dtype = NFT_DATA_VALUE; desc->type = dtype; desc->size = NFT_DATA_VALUE_MAXLEN; desc->len = set->dlen; desc->flags = NFT_DATA_DESC_SETELEM; return nft_data_init(ctx, data, desc, attr); } static void *nft_setelem_catchall_get(const struct net *net, const struct nft_set *set) { struct nft_set_elem_catchall *catchall; u8 genmask = nft_genmask_cur(net); struct nft_set_ext *ext; void *priv = NULL; list_for_each_entry_rcu(catchall, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); if (!nft_set_elem_active(ext, genmask) || nft_set_elem_expired(ext)) continue; priv = catchall->elem; break; } return priv; } static int nft_setelem_get(struct nft_ctx *ctx, const struct nft_set *set, struct nft_set_elem *elem, u32 flags) { void *priv; if (!(flags & NFT_SET_ELEM_CATCHALL)) { priv = set->ops->get(ctx->net, set, elem, flags); if (IS_ERR(priv)) return PTR_ERR(priv); } else { priv = nft_setelem_catchall_get(ctx->net, set); if (!priv) return -ENOENT; } elem->priv = priv; return 0; } static int nft_get_set_elem(struct nft_ctx *ctx, const struct nft_set *set, const struct nlattr *attr, bool reset) { struct nlattr *nla[NFTA_SET_ELEM_MAX + 1]; struct nft_set_elem elem; struct sk_buff *skb; uint32_t flags = 0; int err; err = nla_parse_nested_deprecated(nla, NFTA_SET_ELEM_MAX, attr, nft_set_elem_policy, NULL); if (err < 0) return err; err = nft_setelem_parse_flags(set, nla[NFTA_SET_ELEM_FLAGS], &flags); if (err < 0) return err; if (!nla[NFTA_SET_ELEM_KEY] && !(flags & NFT_SET_ELEM_CATCHALL)) return -EINVAL; if (nla[NFTA_SET_ELEM_KEY]) { err = nft_setelem_parse_key(ctx, set, &elem.key.val, nla[NFTA_SET_ELEM_KEY]); if (err < 0) return err; } if (nla[NFTA_SET_ELEM_KEY_END]) { err = nft_setelem_parse_key(ctx, set, &elem.key_end.val, nla[NFTA_SET_ELEM_KEY_END]); if (err < 0) return err; } err = nft_setelem_get(ctx, set, &elem, flags); if (err < 0) return err; err = -ENOMEM; skb = nlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC); if (skb == NULL) return err; err = nf_tables_fill_setelem_info(skb, ctx, ctx->seq, ctx->portid, NFT_MSG_NEWSETELEM, 0, set, elem.priv, reset); if (err < 0) goto err_fill_setelem; return nfnetlink_unicast(skb, ctx->net, ctx->portid); err_fill_setelem: kfree_skb(skb); return err; } static int nft_set_dump_ctx_init(struct nft_set_dump_ctx *dump_ctx, const struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[], bool reset) { struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_cur(info->net); u8 family = info->nfmsg->nfgen_family; struct net *net = info->net; struct nft_table *table; struct nft_set *set; table = nft_table_lookup(net, nla[NFTA_SET_ELEM_LIST_TABLE], family, genmask, 0); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_SET_ELEM_LIST_TABLE]); return PTR_ERR(table); } set = nft_set_lookup(table, nla[NFTA_SET_ELEM_LIST_SET], genmask); if (IS_ERR(set)) { NL_SET_BAD_ATTR(extack, nla[NFTA_SET_ELEM_LIST_SET]); return PTR_ERR(set); } nft_ctx_init(&dump_ctx->ctx, net, skb, info->nlh, family, table, NULL, nla); dump_ctx->set = set; dump_ctx->reset = reset; return 0; } /* called with rcu_read_lock held */ static int nf_tables_getsetelem(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct netlink_ext_ack *extack = info->extack; struct nft_set_dump_ctx dump_ctx; struct nlattr *attr; int rem, err = 0; if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .start = nf_tables_dump_set_start, .dump = nf_tables_dump_set, .done = nf_tables_dump_set_done, .module = THIS_MODULE, }; err = nft_set_dump_ctx_init(&dump_ctx, skb, info, nla, false); if (err) return err; c.data = &dump_ctx; return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); } if (!nla[NFTA_SET_ELEM_LIST_ELEMENTS]) return -EINVAL; err = nft_set_dump_ctx_init(&dump_ctx, skb, info, nla, false); if (err) return err; nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) { err = nft_get_set_elem(&dump_ctx.ctx, dump_ctx.set, attr, false); if (err < 0) { NL_SET_BAD_ATTR(extack, attr); break; } } return err; } static int nf_tables_getsetelem_reset(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct nftables_pernet *nft_net = nft_pernet(info->net); struct netlink_ext_ack *extack = info->extack; struct nft_set_dump_ctx dump_ctx; int rem, err = 0, nelems = 0; struct nlattr *attr; if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .start = nf_tables_dump_set_start, .dump = nf_tables_dumpreset_set, .done = nf_tables_dump_set_done, .module = THIS_MODULE, }; err = nft_set_dump_ctx_init(&dump_ctx, skb, info, nla, true); if (err) return err; c.data = &dump_ctx; return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); } if (!nla[NFTA_SET_ELEM_LIST_ELEMENTS]) return -EINVAL; if (!try_module_get(THIS_MODULE)) return -EINVAL; rcu_read_unlock(); mutex_lock(&nft_net->commit_mutex); rcu_read_lock(); err = nft_set_dump_ctx_init(&dump_ctx, skb, info, nla, true); if (err) goto out_unlock; nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) { err = nft_get_set_elem(&dump_ctx.ctx, dump_ctx.set, attr, true); if (err < 0) { NL_SET_BAD_ATTR(extack, attr); break; } nelems++; } audit_log_nft_set_reset(dump_ctx.ctx.table, nft_net->base_seq, nelems); out_unlock: rcu_read_unlock(); mutex_unlock(&nft_net->commit_mutex); rcu_read_lock(); module_put(THIS_MODULE); return err; } static void nf_tables_setelem_notify(const struct nft_ctx *ctx, const struct nft_set *set, const struct nft_elem_priv *elem_priv, int event) { struct nftables_pernet *nft_net; struct net *net = ctx->net; u32 portid = ctx->portid; struct sk_buff *skb; u16 flags = 0; int err; if (!ctx->report && !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES)) return; skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); if (skb == NULL) goto err; if (ctx->flags & (NLM_F_CREATE | NLM_F_EXCL)) flags |= ctx->flags & (NLM_F_CREATE | NLM_F_EXCL); err = nf_tables_fill_setelem_info(skb, ctx, 0, portid, event, flags, set, elem_priv, false); if (err < 0) { kfree_skb(skb); goto err; } nft_net = nft_pernet(net); nft_notify_enqueue(skb, ctx->report, &nft_net->notify_list); return; err: nfnetlink_set_err(net, portid, NFNLGRP_NFTABLES, -ENOBUFS); } static struct nft_trans *nft_trans_elem_alloc(struct nft_ctx *ctx, int msg_type, struct nft_set *set) { struct nft_trans *trans; trans = nft_trans_alloc(ctx, msg_type, sizeof(struct nft_trans_elem)); if (trans == NULL) return NULL; nft_trans_elem_set(trans) = set; return trans; } struct nft_expr *nft_set_elem_expr_alloc(const struct nft_ctx *ctx, const struct nft_set *set, const struct nlattr *attr) { struct nft_expr *expr; int err; expr = nft_expr_init(ctx, attr); if (IS_ERR(expr)) return expr; err = -EOPNOTSUPP; if (expr->ops->type->flags & NFT_EXPR_GC) { if (set->flags & NFT_SET_TIMEOUT) goto err_set_elem_expr; if (!set->ops->gc_init) goto err_set_elem_expr; set->ops->gc_init(set); } return expr; err_set_elem_expr: nft_expr_destroy(ctx, expr); return ERR_PTR(err); } static int nft_set_ext_check(const struct nft_set_ext_tmpl *tmpl, u8 id, u32 len) { len += nft_set_ext_types[id].len; if (len > tmpl->ext_len[id] || len > U8_MAX) return -1; return 0; } static int nft_set_ext_memcpy(const struct nft_set_ext_tmpl *tmpl, u8 id, void *to, const void *from, u32 len) { if (nft_set_ext_check(tmpl, id, len) < 0) return -1; memcpy(to, from, len); return 0; } struct nft_elem_priv *nft_set_elem_init(const struct nft_set *set, const struct nft_set_ext_tmpl *tmpl, const u32 *key, const u32 *key_end, const u32 *data, u64 timeout, u64 expiration, gfp_t gfp) { struct nft_set_ext *ext; void *elem; elem = kzalloc(set->ops->elemsize + tmpl->len, gfp); if (elem == NULL) return ERR_PTR(-ENOMEM); ext = nft_set_elem_ext(set, elem); nft_set_ext_init(ext, tmpl); if (nft_set_ext_exists(ext, NFT_SET_EXT_KEY) && nft_set_ext_memcpy(tmpl, NFT_SET_EXT_KEY, nft_set_ext_key(ext), key, set->klen) < 0) goto err_ext_check; if (nft_set_ext_exists(ext, NFT_SET_EXT_KEY_END) && nft_set_ext_memcpy(tmpl, NFT_SET_EXT_KEY_END, nft_set_ext_key_end(ext), key_end, set->klen) < 0) goto err_ext_check; if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA) && nft_set_ext_memcpy(tmpl, NFT_SET_EXT_DATA, nft_set_ext_data(ext), data, set->dlen) < 0) goto err_ext_check; if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION)) { *nft_set_ext_expiration(ext) = get_jiffies_64() + expiration; if (expiration == 0) *nft_set_ext_expiration(ext) += timeout; } if (nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT)) *nft_set_ext_timeout(ext) = timeout; return elem; err_ext_check: kfree(elem); return ERR_PTR(-EINVAL); } static void __nft_set_elem_expr_destroy(const struct nft_ctx *ctx, struct nft_expr *expr) { if (expr->ops->destroy_clone) { expr->ops->destroy_clone(ctx, expr); module_put(expr->ops->type->owner); } else { nf_tables_expr_destroy(ctx, expr); } } static void nft_set_elem_expr_destroy(const struct nft_ctx *ctx, struct nft_set_elem_expr *elem_expr) { struct nft_expr *expr; u32 size; nft_setelem_expr_foreach(expr, elem_expr, size) __nft_set_elem_expr_destroy(ctx, expr); } /* Drop references and destroy. Called from gc, dynset and abort path. */ void nft_set_elem_destroy(const struct nft_set *set, const struct nft_elem_priv *elem_priv, bool destroy_expr) { struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); struct nft_ctx ctx = { .net = read_pnet(&set->net), .family = set->table->family, }; nft_data_release(nft_set_ext_key(ext), NFT_DATA_VALUE); if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA)) nft_data_release(nft_set_ext_data(ext), set->dtype); if (destroy_expr && nft_set_ext_exists(ext, NFT_SET_EXT_EXPRESSIONS)) nft_set_elem_expr_destroy(&ctx, nft_set_ext_expr(ext)); if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF)) nft_use_dec(&(*nft_set_ext_obj(ext))->use); kfree(elem_priv); } EXPORT_SYMBOL_GPL(nft_set_elem_destroy); /* Destroy element. References have been already dropped in the preparation * path via nft_setelem_data_deactivate(). */ void nf_tables_set_elem_destroy(const struct nft_ctx *ctx, const struct nft_set *set, const struct nft_elem_priv *elem_priv) { struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPRESSIONS)) nft_set_elem_expr_destroy(ctx, nft_set_ext_expr(ext)); kfree(elem_priv); } int nft_set_elem_expr_clone(const struct nft_ctx *ctx, struct nft_set *set, struct nft_expr *expr_array[]) { struct nft_expr *expr; int err, i, k; for (i = 0; i < set->num_exprs; i++) { expr = kzalloc(set->exprs[i]->ops->size, GFP_KERNEL_ACCOUNT); if (!expr) goto err_expr; err = nft_expr_clone(expr, set->exprs[i]); if (err < 0) { kfree(expr); goto err_expr; } expr_array[i] = expr; } return 0; err_expr: for (k = i - 1; k >= 0; k--) nft_expr_destroy(ctx, expr_array[k]); return -ENOMEM; } static int nft_set_elem_expr_setup(struct nft_ctx *ctx, const struct nft_set_ext_tmpl *tmpl, const struct nft_set_ext *ext, struct nft_expr *expr_array[], u32 num_exprs) { struct nft_set_elem_expr *elem_expr = nft_set_ext_expr(ext); u32 len = sizeof(struct nft_set_elem_expr); struct nft_expr *expr; int i, err; if (num_exprs == 0) return 0; for (i = 0; i < num_exprs; i++) len += expr_array[i]->ops->size; if (nft_set_ext_check(tmpl, NFT_SET_EXT_EXPRESSIONS, len) < 0) return -EINVAL; for (i = 0; i < num_exprs; i++) { expr = nft_setelem_expr_at(elem_expr, elem_expr->size); err = nft_expr_clone(expr, expr_array[i]); if (err < 0) goto err_elem_expr_setup; elem_expr->size += expr_array[i]->ops->size; nft_expr_destroy(ctx, expr_array[i]); expr_array[i] = NULL; } return 0; err_elem_expr_setup: for (; i < num_exprs; i++) { nft_expr_destroy(ctx, expr_array[i]); expr_array[i] = NULL; } return -ENOMEM; } struct nft_set_ext *nft_set_catchall_lookup(const struct net *net, const struct nft_set *set) { struct nft_set_elem_catchall *catchall; u8 genmask = nft_genmask_cur(net); struct nft_set_ext *ext; list_for_each_entry_rcu(catchall, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); if (nft_set_elem_active(ext, genmask) && !nft_set_elem_expired(ext) && !nft_set_elem_is_dead(ext)) return ext; } return NULL; } EXPORT_SYMBOL_GPL(nft_set_catchall_lookup); static int nft_setelem_catchall_insert(const struct net *net, struct nft_set *set, const struct nft_set_elem *elem, struct nft_elem_priv **priv) { struct nft_set_elem_catchall *catchall; u8 genmask = nft_genmask_next(net); struct nft_set_ext *ext; list_for_each_entry(catchall, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); if (nft_set_elem_active(ext, genmask)) { *priv = catchall->elem; return -EEXIST; } } catchall = kmalloc(sizeof(*catchall), GFP_KERNEL); if (!catchall) return -ENOMEM; catchall->elem = elem->priv; list_add_tail_rcu(&catchall->list, &set->catchall_list); return 0; } static int nft_setelem_insert(const struct net *net, struct nft_set *set, const struct nft_set_elem *elem, struct nft_elem_priv **elem_priv, unsigned int flags) { int ret; if (flags & NFT_SET_ELEM_CATCHALL) ret = nft_setelem_catchall_insert(net, set, elem, elem_priv); else ret = set->ops->insert(net, set, elem, elem_priv); return ret; } static bool nft_setelem_is_catchall(const struct nft_set *set, const struct nft_elem_priv *elem_priv) { struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && *nft_set_ext_flags(ext) & NFT_SET_ELEM_CATCHALL) return true; return false; } static void nft_setelem_activate(struct net *net, struct nft_set *set, struct nft_elem_priv *elem_priv) { struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); if (nft_setelem_is_catchall(set, elem_priv)) { nft_clear(net, ext); } else { set->ops->activate(net, set, elem_priv); } } static int nft_setelem_catchall_deactivate(const struct net *net, struct nft_set *set, struct nft_set_elem *elem) { struct nft_set_elem_catchall *catchall; struct nft_set_ext *ext; list_for_each_entry(catchall, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); if (!nft_is_active_next(net, ext)) continue; kfree(elem->priv); elem->priv = catchall->elem; nft_set_elem_change_active(net, set, ext); return 0; } return -ENOENT; } static int __nft_setelem_deactivate(const struct net *net, struct nft_set *set, struct nft_set_elem *elem) { void *priv; priv = set->ops->deactivate(net, set, elem); if (!priv) return -ENOENT; kfree(elem->priv); elem->priv = priv; set->ndeact++; return 0; } static int nft_setelem_deactivate(const struct net *net, struct nft_set *set, struct nft_set_elem *elem, u32 flags) { int ret; if (flags & NFT_SET_ELEM_CATCHALL) ret = nft_setelem_catchall_deactivate(net, set, elem); else ret = __nft_setelem_deactivate(net, set, elem); return ret; } static void nft_setelem_catchall_destroy(struct nft_set_elem_catchall *catchall) { list_del_rcu(&catchall->list); kfree_rcu(catchall, rcu); } static void nft_setelem_catchall_remove(const struct net *net, const struct nft_set *set, struct nft_elem_priv *elem_priv) { struct nft_set_elem_catchall *catchall, *next; list_for_each_entry_safe(catchall, next, &set->catchall_list, list) { if (catchall->elem == elem_priv) { nft_setelem_catchall_destroy(catchall); break; } } } static void nft_setelem_remove(const struct net *net, const struct nft_set *set, struct nft_elem_priv *elem_priv) { if (nft_setelem_is_catchall(set, elem_priv)) nft_setelem_catchall_remove(net, set, elem_priv); else set->ops->remove(net, set, elem_priv); } static bool nft_setelem_valid_key_end(const struct nft_set *set, struct nlattr **nla, u32 flags) { if ((set->flags & (NFT_SET_CONCAT | NFT_SET_INTERVAL)) == (NFT_SET_CONCAT | NFT_SET_INTERVAL)) { if (flags & NFT_SET_ELEM_INTERVAL_END) return false; if (nla[NFTA_SET_ELEM_KEY_END] && flags & NFT_SET_ELEM_CATCHALL) return false; } else { if (nla[NFTA_SET_ELEM_KEY_END]) return false; } return true; } static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, const struct nlattr *attr, u32 nlmsg_flags) { struct nft_expr *expr_array[NFT_SET_EXPR_MAX] = {}; struct nlattr *nla[NFTA_SET_ELEM_MAX + 1]; u8 genmask = nft_genmask_next(ctx->net); u32 flags = 0, size = 0, num_exprs = 0; struct nft_set_ext_tmpl tmpl; struct nft_set_ext *ext, *ext2; struct nft_set_elem elem; struct nft_set_binding *binding; struct nft_elem_priv *elem_priv; struct nft_object *obj = NULL; struct nft_userdata *udata; struct nft_data_desc desc; enum nft_registers dreg; struct nft_trans *trans; u64 expiration; u64 timeout; int err, i; u8 ulen; err = nla_parse_nested_deprecated(nla, NFTA_SET_ELEM_MAX, attr, nft_set_elem_policy, NULL); if (err < 0) return err; nft_set_ext_prepare(&tmpl); err = nft_setelem_parse_flags(set, nla[NFTA_SET_ELEM_FLAGS], &flags); if (err < 0) return err; if (((flags & NFT_SET_ELEM_CATCHALL) && nla[NFTA_SET_ELEM_KEY]) || (!(flags & NFT_SET_ELEM_CATCHALL) && !nla[NFTA_SET_ELEM_KEY])) return -EINVAL; if (flags != 0) { err = nft_set_ext_add(&tmpl, NFT_SET_EXT_FLAGS); if (err < 0) return err; } if (set->flags & NFT_SET_MAP) { if (nla[NFTA_SET_ELEM_DATA] == NULL && !(flags & NFT_SET_ELEM_INTERVAL_END)) return -EINVAL; } else { if (nla[NFTA_SET_ELEM_DATA] != NULL) return -EINVAL; } if (set->flags & NFT_SET_OBJECT) { if (!nla[NFTA_SET_ELEM_OBJREF] && !(flags & NFT_SET_ELEM_INTERVAL_END)) return -EINVAL; } else { if (nla[NFTA_SET_ELEM_OBJREF]) return -EINVAL; } if (!nft_setelem_valid_key_end(set, nla, flags)) return -EINVAL; if ((flags & NFT_SET_ELEM_INTERVAL_END) && (nla[NFTA_SET_ELEM_DATA] || nla[NFTA_SET_ELEM_OBJREF] || nla[NFTA_SET_ELEM_TIMEOUT] || nla[NFTA_SET_ELEM_EXPIRATION] || nla[NFTA_SET_ELEM_USERDATA] || nla[NFTA_SET_ELEM_EXPR] || nla[NFTA_SET_ELEM_KEY_END] || nla[NFTA_SET_ELEM_EXPRESSIONS])) return -EINVAL; timeout = 0; if (nla[NFTA_SET_ELEM_TIMEOUT] != NULL) { if (!(set->flags & NFT_SET_TIMEOUT)) return -EINVAL; err = nf_msecs_to_jiffies64(nla[NFTA_SET_ELEM_TIMEOUT], &timeout); if (err) return err; } else if (set->flags & NFT_SET_TIMEOUT && !(flags & NFT_SET_ELEM_INTERVAL_END)) { timeout = READ_ONCE(set->timeout); } expiration = 0; if (nla[NFTA_SET_ELEM_EXPIRATION] != NULL) { if (!(set->flags & NFT_SET_TIMEOUT)) return -EINVAL; err = nf_msecs_to_jiffies64(nla[NFTA_SET_ELEM_EXPIRATION], &expiration); if (err) return err; } if (nla[NFTA_SET_ELEM_EXPR]) { struct nft_expr *expr; if (set->num_exprs && set->num_exprs != 1) return -EOPNOTSUPP; expr = nft_set_elem_expr_alloc(ctx, set, nla[NFTA_SET_ELEM_EXPR]); if (IS_ERR(expr)) return PTR_ERR(expr); expr_array[0] = expr; num_exprs = 1; if (set->num_exprs && set->exprs[0]->ops != expr->ops) { err = -EOPNOTSUPP; goto err_set_elem_expr; } } else if (nla[NFTA_SET_ELEM_EXPRESSIONS]) { struct nft_expr *expr; struct nlattr *tmp; int left; i = 0; nla_for_each_nested(tmp, nla[NFTA_SET_ELEM_EXPRESSIONS], left) { if (i == NFT_SET_EXPR_MAX || (set->num_exprs && set->num_exprs == i)) { err = -E2BIG; goto err_set_elem_expr; } if (nla_type(tmp) != NFTA_LIST_ELEM) { err = -EINVAL; goto err_set_elem_expr; } expr = nft_set_elem_expr_alloc(ctx, set, tmp); if (IS_ERR(expr)) { err = PTR_ERR(expr); goto err_set_elem_expr; } expr_array[i] = expr; num_exprs++; if (set->num_exprs && expr->ops != set->exprs[i]->ops) { err = -EOPNOTSUPP; goto err_set_elem_expr; } i++; } if (set->num_exprs && set->num_exprs != i) { err = -EOPNOTSUPP; goto err_set_elem_expr; } } else if (set->num_exprs > 0 && !(flags & NFT_SET_ELEM_INTERVAL_END)) { err = nft_set_elem_expr_clone(ctx, set, expr_array); if (err < 0) goto err_set_elem_expr_clone; num_exprs = set->num_exprs; } if (nla[NFTA_SET_ELEM_KEY]) { err = nft_setelem_parse_key(ctx, set, &elem.key.val, nla[NFTA_SET_ELEM_KEY]); if (err < 0) goto err_set_elem_expr; err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, set->klen); if (err < 0) goto err_parse_key; } if (nla[NFTA_SET_ELEM_KEY_END]) { err = nft_setelem_parse_key(ctx, set, &elem.key_end.val, nla[NFTA_SET_ELEM_KEY_END]); if (err < 0) goto err_parse_key; err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY_END, set->klen); if (err < 0) goto err_parse_key_end; } if (timeout > 0) { err = nft_set_ext_add(&tmpl, NFT_SET_EXT_EXPIRATION); if (err < 0) goto err_parse_key_end; if (timeout != READ_ONCE(set->timeout)) { err = nft_set_ext_add(&tmpl, NFT_SET_EXT_TIMEOUT); if (err < 0) goto err_parse_key_end; } } if (num_exprs) { for (i = 0; i < num_exprs; i++) size += expr_array[i]->ops->size; err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_EXPRESSIONS, sizeof(struct nft_set_elem_expr) + size); if (err < 0) goto err_parse_key_end; } if (nla[NFTA_SET_ELEM_OBJREF] != NULL) { obj = nft_obj_lookup(ctx->net, ctx->table, nla[NFTA_SET_ELEM_OBJREF], set->objtype, genmask); if (IS_ERR(obj)) { err = PTR_ERR(obj); obj = NULL; goto err_parse_key_end; } if (!nft_use_inc(&obj->use)) { err = -EMFILE; obj = NULL; goto err_parse_key_end; } err = nft_set_ext_add(&tmpl, NFT_SET_EXT_OBJREF); if (err < 0) goto err_parse_key_end; } if (nla[NFTA_SET_ELEM_DATA] != NULL) { err = nft_setelem_parse_data(ctx, set, &desc, &elem.data.val, nla[NFTA_SET_ELEM_DATA]); if (err < 0) goto err_parse_key_end; dreg = nft_type_to_reg(set->dtype); list_for_each_entry(binding, &set->bindings, list) { struct nft_ctx bind_ctx = { .net = ctx->net, .family = ctx->family, .table = ctx->table, .chain = (struct nft_chain *)binding->chain, }; if (!(binding->flags & NFT_SET_MAP)) continue; err = nft_validate_register_store(&bind_ctx, dreg, &elem.data.val, desc.type, desc.len); if (err < 0) goto err_parse_data; if (desc.type == NFT_DATA_VERDICT && (elem.data.val.verdict.code == NFT_GOTO || elem.data.val.verdict.code == NFT_JUMP)) nft_validate_state_update(ctx->table, NFT_VALIDATE_NEED); } err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_DATA, desc.len); if (err < 0) goto err_parse_data; } /* The full maximum length of userdata can exceed the maximum * offset value (U8_MAX) for following extensions, therefor it * must be the last extension added. */ ulen = 0; if (nla[NFTA_SET_ELEM_USERDATA] != NULL) { ulen = nla_len(nla[NFTA_SET_ELEM_USERDATA]); if (ulen > 0) { err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_USERDATA, ulen); if (err < 0) goto err_parse_data; } } elem.priv = nft_set_elem_init(set, &tmpl, elem.key.val.data, elem.key_end.val.data, elem.data.val.data, timeout, expiration, GFP_KERNEL_ACCOUNT); if (IS_ERR(elem.priv)) { err = PTR_ERR(elem.priv); goto err_parse_data; } ext = nft_set_elem_ext(set, elem.priv); if (flags) *nft_set_ext_flags(ext) = flags; if (obj) *nft_set_ext_obj(ext) = obj; if (ulen > 0) { if (nft_set_ext_check(&tmpl, NFT_SET_EXT_USERDATA, ulen) < 0) { err = -EINVAL; goto err_elem_free; } udata = nft_set_ext_userdata(ext); udata->len = ulen - 1; nla_memcpy(&udata->data, nla[NFTA_SET_ELEM_USERDATA], ulen); } err = nft_set_elem_expr_setup(ctx, &tmpl, ext, expr_array, num_exprs); if (err < 0) goto err_elem_free; trans = nft_trans_elem_alloc(ctx, NFT_MSG_NEWSETELEM, set); if (trans == NULL) { err = -ENOMEM; goto err_elem_free; } ext->genmask = nft_genmask_cur(ctx->net); err = nft_setelem_insert(ctx->net, set, &elem, &elem_priv, flags); if (err) { if (err == -EEXIST) { ext2 = nft_set_elem_ext(set, elem_priv); if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA) ^ nft_set_ext_exists(ext2, NFT_SET_EXT_DATA) || nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF) ^ nft_set_ext_exists(ext2, NFT_SET_EXT_OBJREF)) goto err_element_clash; if ((nft_set_ext_exists(ext, NFT_SET_EXT_DATA) && nft_set_ext_exists(ext2, NFT_SET_EXT_DATA) && memcmp(nft_set_ext_data(ext), nft_set_ext_data(ext2), set->dlen) != 0) || (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF) && nft_set_ext_exists(ext2, NFT_SET_EXT_OBJREF) && *nft_set_ext_obj(ext) != *nft_set_ext_obj(ext2))) goto err_element_clash; else if (!(nlmsg_flags & NLM_F_EXCL)) err = 0; } else if (err == -ENOTEMPTY) { /* ENOTEMPTY reports overlapping between this element * and an existing one. */ err = -EEXIST; } goto err_element_clash; } if (!(flags & NFT_SET_ELEM_CATCHALL)) { unsigned int max = set->size ? set->size + set->ndeact : UINT_MAX; if (!atomic_add_unless(&set->nelems, 1, max)) { err = -ENFILE; goto err_set_full; } } nft_trans_elem_priv(trans) = elem.priv; nft_trans_commit_list_add_tail(ctx->net, trans); return 0; err_set_full: nft_setelem_remove(ctx->net, set, elem.priv); err_element_clash: kfree(trans); err_elem_free: nf_tables_set_elem_destroy(ctx, set, elem.priv); err_parse_data: if (nla[NFTA_SET_ELEM_DATA] != NULL) nft_data_release(&elem.data.val, desc.type); err_parse_key_end: if (obj) nft_use_dec_restore(&obj->use); nft_data_release(&elem.key_end.val, NFT_DATA_VALUE); err_parse_key: nft_data_release(&elem.key.val, NFT_DATA_VALUE); err_set_elem_expr: for (i = 0; i < num_exprs && expr_array[i]; i++) nft_expr_destroy(ctx, expr_array[i]); err_set_elem_expr_clone: return err; } static int nf_tables_newsetelem(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); u8 family = info->nfmsg->nfgen_family; struct net *net = info->net; const struct nlattr *attr; struct nft_table *table; struct nft_set *set; struct nft_ctx ctx; int rem, err; if (nla[NFTA_SET_ELEM_LIST_ELEMENTS] == NULL) return -EINVAL; table = nft_table_lookup(net, nla[NFTA_SET_ELEM_LIST_TABLE], family, genmask, NETLINK_CB(skb).portid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_SET_ELEM_LIST_TABLE]); return PTR_ERR(table); } set = nft_set_lookup_global(net, table, nla[NFTA_SET_ELEM_LIST_SET], nla[NFTA_SET_ELEM_LIST_SET_ID], genmask); if (IS_ERR(set)) { NL_SET_BAD_ATTR(extack, nla[NFTA_SET_ELEM_LIST_SET]); return PTR_ERR(set); } if (!list_empty(&set->bindings) && (set->flags & (NFT_SET_CONSTANT | NFT_SET_ANONYMOUS))) return -EBUSY; nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) { err = nft_add_set_elem(&ctx, set, attr, info->nlh->nlmsg_flags); if (err < 0) { NL_SET_BAD_ATTR(extack, attr); return err; } } if (table->validate_state == NFT_VALIDATE_DO) return nft_table_validate(net, table); return 0; } /** * nft_data_hold - hold a nft_data item * * @data: struct nft_data to release * @type: type of data * * Hold a nft_data item. NFT_DATA_VALUE types can be silently discarded, * NFT_DATA_VERDICT bumps the reference to chains in case of NFT_JUMP and * NFT_GOTO verdicts. This function must be called on active data objects * from the second phase of the commit protocol. */ void nft_data_hold(const struct nft_data *data, enum nft_data_types type) { struct nft_chain *chain; if (type == NFT_DATA_VERDICT) { switch (data->verdict.code) { case NFT_JUMP: case NFT_GOTO: chain = data->verdict.chain; nft_use_inc_restore(&chain->use); break; } } } static int nft_setelem_active_next(const struct net *net, const struct nft_set *set, struct nft_elem_priv *elem_priv) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); u8 genmask = nft_genmask_next(net); return nft_set_elem_active(ext, genmask); } static void nft_setelem_data_activate(const struct net *net, const struct nft_set *set, struct nft_elem_priv *elem_priv) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA)) nft_data_hold(nft_set_ext_data(ext), set->dtype); if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF)) nft_use_inc_restore(&(*nft_set_ext_obj(ext))->use); } void nft_setelem_data_deactivate(const struct net *net, const struct nft_set *set, struct nft_elem_priv *elem_priv) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA)) nft_data_release(nft_set_ext_data(ext), set->dtype); if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF)) nft_use_dec(&(*nft_set_ext_obj(ext))->use); } static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, const struct nlattr *attr) { struct nlattr *nla[NFTA_SET_ELEM_MAX + 1]; struct nft_set_ext_tmpl tmpl; struct nft_set_elem elem; struct nft_set_ext *ext; struct nft_trans *trans; u32 flags = 0; int err; err = nla_parse_nested_deprecated(nla, NFTA_SET_ELEM_MAX, attr, nft_set_elem_policy, NULL); if (err < 0) return err; err = nft_setelem_parse_flags(set, nla[NFTA_SET_ELEM_FLAGS], &flags); if (err < 0) return err; if (!nla[NFTA_SET_ELEM_KEY] && !(flags & NFT_SET_ELEM_CATCHALL)) return -EINVAL; if (!nft_setelem_valid_key_end(set, nla, flags)) return -EINVAL; nft_set_ext_prepare(&tmpl); if (flags != 0) { err = nft_set_ext_add(&tmpl, NFT_SET_EXT_FLAGS); if (err < 0) return err; } if (nla[NFTA_SET_ELEM_KEY]) { err = nft_setelem_parse_key(ctx, set, &elem.key.val, nla[NFTA_SET_ELEM_KEY]); if (err < 0) return err; err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, set->klen); if (err < 0) goto fail_elem; } if (nla[NFTA_SET_ELEM_KEY_END]) { err = nft_setelem_parse_key(ctx, set, &elem.key_end.val, nla[NFTA_SET_ELEM_KEY_END]); if (err < 0) goto fail_elem; err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY_END, set->klen); if (err < 0) goto fail_elem_key_end; } err = -ENOMEM; elem.priv = nft_set_elem_init(set, &tmpl, elem.key.val.data, elem.key_end.val.data, NULL, 0, 0, GFP_KERNEL_ACCOUNT); if (IS_ERR(elem.priv)) { err = PTR_ERR(elem.priv); goto fail_elem_key_end; } ext = nft_set_elem_ext(set, elem.priv); if (flags) *nft_set_ext_flags(ext) = flags; trans = nft_trans_elem_alloc(ctx, NFT_MSG_DELSETELEM, set); if (trans == NULL) goto fail_trans; err = nft_setelem_deactivate(ctx->net, set, &elem, flags); if (err < 0) goto fail_ops; nft_setelem_data_deactivate(ctx->net, set, elem.priv); nft_trans_elem_priv(trans) = elem.priv; nft_trans_commit_list_add_tail(ctx->net, trans); return 0; fail_ops: kfree(trans); fail_trans: kfree(elem.priv); fail_elem_key_end: nft_data_release(&elem.key_end.val, NFT_DATA_VALUE); fail_elem: nft_data_release(&elem.key.val, NFT_DATA_VALUE); return err; } static int nft_setelem_flush(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_set_iter *iter, struct nft_elem_priv *elem_priv) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); struct nft_trans *trans; if (!nft_set_elem_active(ext, iter->genmask)) return 0; trans = nft_trans_alloc_gfp(ctx, NFT_MSG_DELSETELEM, sizeof(struct nft_trans_elem), GFP_ATOMIC); if (!trans) return -ENOMEM; set->ops->flush(ctx->net, set, elem_priv); set->ndeact++; nft_setelem_data_deactivate(ctx->net, set, elem_priv); nft_trans_elem_set(trans) = set; nft_trans_elem_priv(trans) = elem_priv; nft_trans_commit_list_add_tail(ctx->net, trans); return 0; } static int __nft_set_catchall_flush(const struct nft_ctx *ctx, struct nft_set *set, struct nft_elem_priv *elem_priv) { struct nft_trans *trans; trans = nft_trans_alloc_gfp(ctx, NFT_MSG_DELSETELEM, sizeof(struct nft_trans_elem), GFP_KERNEL); if (!trans) return -ENOMEM; nft_setelem_data_deactivate(ctx->net, set, elem_priv); nft_trans_elem_set(trans) = set; nft_trans_elem_priv(trans) = elem_priv; nft_trans_commit_list_add_tail(ctx->net, trans); return 0; } static int nft_set_catchall_flush(const struct nft_ctx *ctx, struct nft_set *set) { u8 genmask = nft_genmask_next(ctx->net); struct nft_set_elem_catchall *catchall; struct nft_set_ext *ext; int ret = 0; list_for_each_entry_rcu(catchall, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); if (!nft_set_elem_active(ext, genmask)) continue; ret = __nft_set_catchall_flush(ctx, set, catchall->elem); if (ret < 0) break; nft_set_elem_change_active(ctx->net, set, ext); } return ret; } static int nft_set_flush(struct nft_ctx *ctx, struct nft_set *set, u8 genmask) { struct nft_set_iter iter = { .genmask = genmask, .type = NFT_ITER_UPDATE, .fn = nft_setelem_flush, }; set->ops->walk(ctx, set, &iter); if (!iter.err) iter.err = nft_set_catchall_flush(ctx, set); return iter.err; } static int nf_tables_delsetelem(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); u8 family = info->nfmsg->nfgen_family; struct net *net = info->net; const struct nlattr *attr; struct nft_table *table; struct nft_set *set; struct nft_ctx ctx; int rem, err = 0; table = nft_table_lookup(net, nla[NFTA_SET_ELEM_LIST_TABLE], family, genmask, NETLINK_CB(skb).portid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_SET_ELEM_LIST_TABLE]); return PTR_ERR(table); } set = nft_set_lookup(table, nla[NFTA_SET_ELEM_LIST_SET], genmask); if (IS_ERR(set)) { NL_SET_BAD_ATTR(extack, nla[NFTA_SET_ELEM_LIST_SET]); return PTR_ERR(set); } if (nft_set_is_anonymous(set)) return -EOPNOTSUPP; if (!list_empty(&set->bindings) && (set->flags & NFT_SET_CONSTANT)) return -EBUSY; nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); if (!nla[NFTA_SET_ELEM_LIST_ELEMENTS]) return nft_set_flush(&ctx, set, genmask); nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) { err = nft_del_setelem(&ctx, set, attr); if (err == -ENOENT && NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_DESTROYSETELEM) continue; if (err < 0) { NL_SET_BAD_ATTR(extack, attr); return err; } } return 0; } /* * Stateful objects */ /** * nft_register_obj- register nf_tables stateful object type * @obj_type: object type * * Registers the object type for use with nf_tables. Returns zero on * success or a negative errno code otherwise. */ int nft_register_obj(struct nft_object_type *obj_type) { if (obj_type->type == NFT_OBJECT_UNSPEC) return -EINVAL; nfnl_lock(NFNL_SUBSYS_NFTABLES); list_add_rcu(&obj_type->list, &nf_tables_objects); nfnl_unlock(NFNL_SUBSYS_NFTABLES); return 0; } EXPORT_SYMBOL_GPL(nft_register_obj); /** * nft_unregister_obj - unregister nf_tables object type * @obj_type: object type * * Unregisters the object type for use with nf_tables. */ void nft_unregister_obj(struct nft_object_type *obj_type) { nfnl_lock(NFNL_SUBSYS_NFTABLES); list_del_rcu(&obj_type->list); nfnl_unlock(NFNL_SUBSYS_NFTABLES); } EXPORT_SYMBOL_GPL(nft_unregister_obj); struct nft_object *nft_obj_lookup(const struct net *net, const struct nft_table *table, const struct nlattr *nla, u32 objtype, u8 genmask) { struct nft_object_hash_key k = { .table = table }; char search[NFT_OBJ_MAXNAMELEN]; struct rhlist_head *tmp, *list; struct nft_object *obj; nla_strscpy(search, nla, sizeof(search)); k.name = search; WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_commit_lock_is_held(net)); rcu_read_lock(); list = rhltable_lookup(&nft_objname_ht, &k, nft_objname_ht_params); if (!list) goto out; rhl_for_each_entry_rcu(obj, tmp, list, rhlhead) { if (objtype == obj->ops->type->type && nft_active_genmask(obj, genmask)) { rcu_read_unlock(); return obj; } } out: rcu_read_unlock(); return ERR_PTR(-ENOENT); } EXPORT_SYMBOL_GPL(nft_obj_lookup); static struct nft_object *nft_obj_lookup_byhandle(const struct nft_table *table, const struct nlattr *nla, u32 objtype, u8 genmask) { struct nft_object *obj; list_for_each_entry(obj, &table->objects, list) { if (be64_to_cpu(nla_get_be64(nla)) == obj->handle && objtype == obj->ops->type->type && nft_active_genmask(obj, genmask)) return obj; } return ERR_PTR(-ENOENT); } static const struct nla_policy nft_obj_policy[NFTA_OBJ_MAX + 1] = { [NFTA_OBJ_TABLE] = { .type = NLA_STRING, .len = NFT_TABLE_MAXNAMELEN - 1 }, [NFTA_OBJ_NAME] = { .type = NLA_STRING, .len = NFT_OBJ_MAXNAMELEN - 1 }, [NFTA_OBJ_TYPE] = { .type = NLA_U32 }, [NFTA_OBJ_DATA] = { .type = NLA_NESTED }, [NFTA_OBJ_HANDLE] = { .type = NLA_U64}, [NFTA_OBJ_USERDATA] = { .type = NLA_BINARY, .len = NFT_USERDATA_MAXLEN }, }; static struct nft_object *nft_obj_init(const struct nft_ctx *ctx, const struct nft_object_type *type, const struct nlattr *attr) { struct nlattr **tb; const struct nft_object_ops *ops; struct nft_object *obj; int err = -ENOMEM; tb = kmalloc_array(type->maxattr + 1, sizeof(*tb), GFP_KERNEL); if (!tb) goto err1; if (attr) { err = nla_parse_nested_deprecated(tb, type->maxattr, attr, type->policy, NULL); if (err < 0) goto err2; } else { memset(tb, 0, sizeof(tb[0]) * (type->maxattr + 1)); } if (type->select_ops) { ops = type->select_ops(ctx, (const struct nlattr * const *)tb); if (IS_ERR(ops)) { err = PTR_ERR(ops); goto err2; } } else { ops = type->ops; } err = -ENOMEM; obj = kzalloc(sizeof(*obj) + ops->size, GFP_KERNEL_ACCOUNT); if (!obj) goto err2; err = ops->init(ctx, (const struct nlattr * const *)tb, obj); if (err < 0) goto err3; obj->ops = ops; kfree(tb); return obj; err3: kfree(obj); err2: kfree(tb); err1: return ERR_PTR(err); } static int nft_object_dump(struct sk_buff *skb, unsigned int attr, struct nft_object *obj, bool reset) { struct nlattr *nest; nest = nla_nest_start_noflag(skb, attr); if (!nest) goto nla_put_failure; if (obj->ops->dump(skb, obj, reset) < 0) goto nla_put_failure; nla_nest_end(skb, nest); return 0; nla_put_failure: return -1; } static const struct nft_object_type *__nft_obj_type_get(u32 objtype, u8 family) { const struct nft_object_type *type; list_for_each_entry_rcu(type, &nf_tables_objects, list) { if (type->family != NFPROTO_UNSPEC && type->family != family) continue; if (objtype == type->type) return type; } return NULL; } static const struct nft_object_type * nft_obj_type_get(struct net *net, u32 objtype, u8 family) { const struct nft_object_type *type; rcu_read_lock(); type = __nft_obj_type_get(objtype, family); if (type != NULL && try_module_get(type->owner)) { rcu_read_unlock(); return type; } rcu_read_unlock(); lockdep_nfnl_nft_mutex_not_held(); #ifdef CONFIG_MODULES if (type == NULL) { if (nft_request_module(net, "nft-obj-%u", objtype) == -EAGAIN) return ERR_PTR(-EAGAIN); } #endif return ERR_PTR(-ENOENT); } static int nf_tables_updobj(const struct nft_ctx *ctx, const struct nft_object_type *type, const struct nlattr *attr, struct nft_object *obj) { struct nft_object *newobj; struct nft_trans *trans; int err = -ENOMEM; if (!try_module_get(type->owner)) return -ENOENT; trans = nft_trans_alloc(ctx, NFT_MSG_NEWOBJ, sizeof(struct nft_trans_obj)); if (!trans) goto err_trans; newobj = nft_obj_init(ctx, type, attr); if (IS_ERR(newobj)) { err = PTR_ERR(newobj); goto err_free_trans; } nft_trans_obj(trans) = obj; nft_trans_obj_update(trans) = true; nft_trans_obj_newobj(trans) = newobj; nft_trans_commit_list_add_tail(ctx->net, trans); return 0; err_free_trans: kfree(trans); err_trans: module_put(type->owner); return err; } static int nf_tables_newobj(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); u8 family = info->nfmsg->nfgen_family; const struct nft_object_type *type; struct net *net = info->net; struct nft_table *table; struct nft_object *obj; struct nft_ctx ctx; u32 objtype; int err; if (!nla[NFTA_OBJ_TYPE] || !nla[NFTA_OBJ_NAME] || !nla[NFTA_OBJ_DATA]) return -EINVAL; table = nft_table_lookup(net, nla[NFTA_OBJ_TABLE], family, genmask, NETLINK_CB(skb).portid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_TABLE]); return PTR_ERR(table); } objtype = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE])); obj = nft_obj_lookup(net, table, nla[NFTA_OBJ_NAME], objtype, genmask); if (IS_ERR(obj)) { err = PTR_ERR(obj); if (err != -ENOENT) { NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_NAME]); return err; } } else { if (info->nlh->nlmsg_flags & NLM_F_EXCL) { NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_NAME]); return -EEXIST; } if (info->nlh->nlmsg_flags & NLM_F_REPLACE) return -EOPNOTSUPP; type = __nft_obj_type_get(objtype, family); if (WARN_ON_ONCE(!type)) return -ENOENT; nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); return nf_tables_updobj(&ctx, type, nla[NFTA_OBJ_DATA], obj); } nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); if (!nft_use_inc(&table->use)) return -EMFILE; type = nft_obj_type_get(net, objtype, family); if (IS_ERR(type)) { err = PTR_ERR(type); goto err_type; } obj = nft_obj_init(&ctx, type, nla[NFTA_OBJ_DATA]); if (IS_ERR(obj)) { err = PTR_ERR(obj); goto err_init; } obj->key.table = table; obj->handle = nf_tables_alloc_handle(table); obj->key.name = nla_strdup(nla[NFTA_OBJ_NAME], GFP_KERNEL_ACCOUNT); if (!obj->key.name) { err = -ENOMEM; goto err_strdup; } if (nla[NFTA_OBJ_USERDATA]) { obj->udata = nla_memdup(nla[NFTA_OBJ_USERDATA], GFP_KERNEL_ACCOUNT); if (obj->udata == NULL) goto err_userdata; obj->udlen = nla_len(nla[NFTA_OBJ_USERDATA]); } err = nft_trans_obj_add(&ctx, NFT_MSG_NEWOBJ, obj); if (err < 0) goto err_trans; err = rhltable_insert(&nft_objname_ht, &obj->rhlhead, nft_objname_ht_params); if (err < 0) goto err_obj_ht; list_add_tail_rcu(&obj->list, &table->objects); return 0; err_obj_ht: /* queued in transaction log */ INIT_LIST_HEAD(&obj->list); return err; err_trans: kfree(obj->udata); err_userdata: kfree(obj->key.name); err_strdup: if (obj->ops->destroy) obj->ops->destroy(&ctx, obj); kfree(obj); err_init: module_put(type->owner); err_type: nft_use_dec_restore(&table->use); return err; } static int nf_tables_fill_obj_info(struct sk_buff *skb, struct net *net, u32 portid, u32 seq, int event, u32 flags, int family, const struct nft_table *table, struct nft_object *obj, bool reset) { struct nlmsghdr *nlh; event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event); nlh = nfnl_msg_put(skb, portid, seq, event, flags, family, NFNETLINK_V0, nft_base_seq(net)); if (!nlh) goto nla_put_failure; if (nla_put_string(skb, NFTA_OBJ_TABLE, table->name) || nla_put_string(skb, NFTA_OBJ_NAME, obj->key.name) || nla_put_be64(skb, NFTA_OBJ_HANDLE, cpu_to_be64(obj->handle), NFTA_OBJ_PAD)) goto nla_put_failure; if (event == NFT_MSG_DELOBJ) { nlmsg_end(skb, nlh); return 0; } if (nla_put_be32(skb, NFTA_OBJ_TYPE, htonl(obj->ops->type->type)) || nla_put_be32(skb, NFTA_OBJ_USE, htonl(obj->use)) || nft_object_dump(skb, NFTA_OBJ_DATA, obj, reset)) goto nla_put_failure; if (obj->udata && nla_put(skb, NFTA_OBJ_USERDATA, obj->udlen, obj->udata)) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_trim(skb, nlh); return -1; } static void audit_log_obj_reset(const struct nft_table *table, unsigned int base_seq, unsigned int nentries) { char *buf = kasprintf(GFP_ATOMIC, "%s:%u", table->name, base_seq); audit_log_nfcfg(buf, table->family, nentries, AUDIT_NFT_OP_OBJ_RESET, GFP_ATOMIC); kfree(buf); } struct nft_obj_dump_ctx { unsigned int s_idx; char *table; u32 type; bool reset; }; static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb) { const struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); struct nft_obj_dump_ctx *ctx = (void *)cb->ctx; struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; struct nftables_pernet *nft_net; const struct nft_table *table; unsigned int entries = 0; struct nft_object *obj; unsigned int idx = 0; int rc = 0; rcu_read_lock(); nft_net = nft_pernet(net); cb->seq = READ_ONCE(nft_net->base_seq); list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) continue; entries = 0; list_for_each_entry_rcu(obj, &table->objects, list) { if (!nft_is_active(net, obj)) goto cont; if (idx < ctx->s_idx) goto cont; if (ctx->table && strcmp(ctx->table, table->name)) goto cont; if (ctx->type != NFT_OBJECT_UNSPEC && obj->ops->type->type != ctx->type) goto cont; rc = nf_tables_fill_obj_info(skb, net, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NFT_MSG_NEWOBJ, NLM_F_MULTI | NLM_F_APPEND, table->family, table, obj, ctx->reset); if (rc < 0) break; entries++; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); cont: idx++; } if (ctx->reset && entries) audit_log_obj_reset(table, nft_net->base_seq, entries); if (rc < 0) break; } rcu_read_unlock(); ctx->s_idx = idx; return skb->len; } static int nf_tables_dump_obj_start(struct netlink_callback *cb) { struct nft_obj_dump_ctx *ctx = (void *)cb->ctx; const struct nlattr * const *nla = cb->data; BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx)); if (nla[NFTA_OBJ_TABLE]) { ctx->table = nla_strdup(nla[NFTA_OBJ_TABLE], GFP_ATOMIC); if (!ctx->table) return -ENOMEM; } if (nla[NFTA_OBJ_TYPE]) ctx->type = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE])); if (NFNL_MSG_TYPE(cb->nlh->nlmsg_type) == NFT_MSG_GETOBJ_RESET) ctx->reset = true; return 0; } static int nf_tables_dump_obj_done(struct netlink_callback *cb) { struct nft_obj_dump_ctx *ctx = (void *)cb->ctx; kfree(ctx->table); return 0; } /* called with rcu_read_lock held */ static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_cur(info->net); u8 family = info->nfmsg->nfgen_family; const struct nft_table *table; struct net *net = info->net; struct nft_object *obj; struct sk_buff *skb2; bool reset = false; u32 objtype; int err; if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .start = nf_tables_dump_obj_start, .dump = nf_tables_dump_obj, .done = nf_tables_dump_obj_done, .module = THIS_MODULE, .data = (void *)nla, }; return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); } if (!nla[NFTA_OBJ_NAME] || !nla[NFTA_OBJ_TYPE]) return -EINVAL; table = nft_table_lookup(net, nla[NFTA_OBJ_TABLE], family, genmask, 0); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_TABLE]); return PTR_ERR(table); } objtype = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE])); obj = nft_obj_lookup(net, table, nla[NFTA_OBJ_NAME], objtype, genmask); if (IS_ERR(obj)) { NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_NAME]); return PTR_ERR(obj); } skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC); if (!skb2) return -ENOMEM; if (NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_GETOBJ_RESET) reset = true; if (reset) { const struct nftables_pernet *nft_net; char *buf; nft_net = nft_pernet(net); buf = kasprintf(GFP_ATOMIC, "%s:%u", table->name, nft_net->base_seq); audit_log_nfcfg(buf, family, 1, AUDIT_NFT_OP_OBJ_RESET, GFP_ATOMIC); kfree(buf); } err = nf_tables_fill_obj_info(skb2, net, NETLINK_CB(skb).portid, info->nlh->nlmsg_seq, NFT_MSG_NEWOBJ, 0, family, table, obj, reset); if (err < 0) goto err_fill_obj_info; return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); err_fill_obj_info: kfree_skb(skb2); return err; } static void nft_obj_destroy(const struct nft_ctx *ctx, struct nft_object *obj) { if (obj->ops->destroy) obj->ops->destroy(ctx, obj); module_put(obj->ops->type->owner); kfree(obj->key.name); kfree(obj->udata); kfree(obj); } static int nf_tables_delobj(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); u8 family = info->nfmsg->nfgen_family; struct net *net = info->net; const struct nlattr *attr; struct nft_table *table; struct nft_object *obj; struct nft_ctx ctx; u32 objtype; if (!nla[NFTA_OBJ_TYPE] || (!nla[NFTA_OBJ_NAME] && !nla[NFTA_OBJ_HANDLE])) return -EINVAL; table = nft_table_lookup(net, nla[NFTA_OBJ_TABLE], family, genmask, NETLINK_CB(skb).portid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_TABLE]); return PTR_ERR(table); } objtype = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE])); if (nla[NFTA_OBJ_HANDLE]) { attr = nla[NFTA_OBJ_HANDLE]; obj = nft_obj_lookup_byhandle(table, attr, objtype, genmask); } else { attr = nla[NFTA_OBJ_NAME]; obj = nft_obj_lookup(net, table, attr, objtype, genmask); } if (IS_ERR(obj)) { if (PTR_ERR(obj) == -ENOENT && NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_DESTROYOBJ) return 0; NL_SET_BAD_ATTR(extack, attr); return PTR_ERR(obj); } if (obj->use > 0) { NL_SET_BAD_ATTR(extack, attr); return -EBUSY; } nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); return nft_delobj(&ctx, obj); } static void __nft_obj_notify(struct net *net, const struct nft_table *table, struct nft_object *obj, u32 portid, u32 seq, int event, u16 flags, int family, int report, gfp_t gfp) { struct nftables_pernet *nft_net = nft_pernet(net); struct sk_buff *skb; int err; if (!report && !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES)) return; skb = nlmsg_new(NLMSG_GOODSIZE, gfp); if (skb == NULL) goto err; err = nf_tables_fill_obj_info(skb, net, portid, seq, event, flags & (NLM_F_CREATE | NLM_F_EXCL), family, table, obj, false); if (err < 0) { kfree_skb(skb); goto err; } nft_notify_enqueue(skb, report, &nft_net->notify_list); return; err: nfnetlink_set_err(net, portid, NFNLGRP_NFTABLES, -ENOBUFS); } void nft_obj_notify(struct net *net, const struct nft_table *table, struct nft_object *obj, u32 portid, u32 seq, int event, u16 flags, int family, int report, gfp_t gfp) { struct nftables_pernet *nft_net = nft_pernet(net); char *buf = kasprintf(gfp, "%s:%u", table->name, nft_net->base_seq); audit_log_nfcfg(buf, family, obj->handle, event == NFT_MSG_NEWOBJ ? AUDIT_NFT_OP_OBJ_REGISTER : AUDIT_NFT_OP_OBJ_UNREGISTER, gfp); kfree(buf); __nft_obj_notify(net, table, obj, portid, seq, event, flags, family, report, gfp); } EXPORT_SYMBOL_GPL(nft_obj_notify); static void nf_tables_obj_notify(const struct nft_ctx *ctx, struct nft_object *obj, int event) { __nft_obj_notify(ctx->net, ctx->table, obj, ctx->portid, ctx->seq, event, ctx->flags, ctx->family, ctx->report, GFP_KERNEL); } /* * Flow tables */ void nft_register_flowtable_type(struct nf_flowtable_type *type) { nfnl_lock(NFNL_SUBSYS_NFTABLES); list_add_tail_rcu(&type->list, &nf_tables_flowtables); nfnl_unlock(NFNL_SUBSYS_NFTABLES); } EXPORT_SYMBOL_GPL(nft_register_flowtable_type); void nft_unregister_flowtable_type(struct nf_flowtable_type *type) { nfnl_lock(NFNL_SUBSYS_NFTABLES); list_del_rcu(&type->list); nfnl_unlock(NFNL_SUBSYS_NFTABLES); } EXPORT_SYMBOL_GPL(nft_unregister_flowtable_type); static const struct nla_policy nft_flowtable_policy[NFTA_FLOWTABLE_MAX + 1] = { [NFTA_FLOWTABLE_TABLE] = { .type = NLA_STRING, .len = NFT_NAME_MAXLEN - 1 }, [NFTA_FLOWTABLE_NAME] = { .type = NLA_STRING, .len = NFT_NAME_MAXLEN - 1 }, [NFTA_FLOWTABLE_HOOK] = { .type = NLA_NESTED }, [NFTA_FLOWTABLE_HANDLE] = { .type = NLA_U64 }, [NFTA_FLOWTABLE_FLAGS] = { .type = NLA_U32 }, }; struct nft_flowtable *nft_flowtable_lookup(const struct nft_table *table, const struct nlattr *nla, u8 genmask) { struct nft_flowtable *flowtable; list_for_each_entry_rcu(flowtable, &table->flowtables, list) { if (!nla_strcmp(nla, flowtable->name) && nft_active_genmask(flowtable, genmask)) return flowtable; } return ERR_PTR(-ENOENT); } EXPORT_SYMBOL_GPL(nft_flowtable_lookup); void nf_tables_deactivate_flowtable(const struct nft_ctx *ctx, struct nft_flowtable *flowtable, enum nft_trans_phase phase) { switch (phase) { case NFT_TRANS_PREPARE_ERROR: case NFT_TRANS_PREPARE: case NFT_TRANS_ABORT: case NFT_TRANS_RELEASE: nft_use_dec(&flowtable->use); fallthrough; default: return; } } EXPORT_SYMBOL_GPL(nf_tables_deactivate_flowtable); static struct nft_flowtable * nft_flowtable_lookup_byhandle(const struct nft_table *table, const struct nlattr *nla, u8 genmask) { struct nft_flowtable *flowtable; list_for_each_entry(flowtable, &table->flowtables, list) { if (be64_to_cpu(nla_get_be64(nla)) == flowtable->handle && nft_active_genmask(flowtable, genmask)) return flowtable; } return ERR_PTR(-ENOENT); } struct nft_flowtable_hook { u32 num; int priority; struct list_head list; }; static const struct nla_policy nft_flowtable_hook_policy[NFTA_FLOWTABLE_HOOK_MAX + 1] = { [NFTA_FLOWTABLE_HOOK_NUM] = { .type = NLA_U32 }, [NFTA_FLOWTABLE_HOOK_PRIORITY] = { .type = NLA_U32 }, [NFTA_FLOWTABLE_HOOK_DEVS] = { .type = NLA_NESTED }, }; static int nft_flowtable_parse_hook(const struct nft_ctx *ctx, const struct nlattr * const nla[], struct nft_flowtable_hook *flowtable_hook, struct nft_flowtable *flowtable, struct netlink_ext_ack *extack, bool add) { struct nlattr *tb[NFTA_FLOWTABLE_HOOK_MAX + 1]; struct nft_hook *hook; int hooknum, priority; int err; INIT_LIST_HEAD(&flowtable_hook->list); err = nla_parse_nested_deprecated(tb, NFTA_FLOWTABLE_HOOK_MAX, nla[NFTA_FLOWTABLE_HOOK], nft_flowtable_hook_policy, NULL); if (err < 0) return err; if (add) { if (!tb[NFTA_FLOWTABLE_HOOK_NUM] || !tb[NFTA_FLOWTABLE_HOOK_PRIORITY]) { NL_SET_BAD_ATTR(extack, nla[NFTA_FLOWTABLE_NAME]); return -ENOENT; } hooknum = ntohl(nla_get_be32(tb[NFTA_FLOWTABLE_HOOK_NUM])); if (hooknum != NF_NETDEV_INGRESS) return -EOPNOTSUPP; priority = ntohl(nla_get_be32(tb[NFTA_FLOWTABLE_HOOK_PRIORITY])); flowtable_hook->priority = priority; flowtable_hook->num = hooknum; } else { if (tb[NFTA_FLOWTABLE_HOOK_NUM]) { hooknum = ntohl(nla_get_be32(tb[NFTA_FLOWTABLE_HOOK_NUM])); if (hooknum != flowtable->hooknum) return -EOPNOTSUPP; } if (tb[NFTA_FLOWTABLE_HOOK_PRIORITY]) { priority = ntohl(nla_get_be32(tb[NFTA_FLOWTABLE_HOOK_PRIORITY])); if (priority != flowtable->data.priority) return -EOPNOTSUPP; } flowtable_hook->priority = flowtable->data.priority; flowtable_hook->num = flowtable->hooknum; } if (tb[NFTA_FLOWTABLE_HOOK_DEVS]) { err = nf_tables_parse_netdev_hooks(ctx->net, tb[NFTA_FLOWTABLE_HOOK_DEVS], &flowtable_hook->list, extack); if (err < 0) return err; } list_for_each_entry(hook, &flowtable_hook->list, list) { hook->ops.pf = NFPROTO_NETDEV; hook->ops.hooknum = flowtable_hook->num; hook->ops.priority = flowtable_hook->priority; hook->ops.priv = &flowtable->data; hook->ops.hook = flowtable->data.type->hook; } return err; } /* call under rcu_read_lock */ static const struct nf_flowtable_type *__nft_flowtable_type_get(u8 family) { const struct nf_flowtable_type *type; list_for_each_entry_rcu(type, &nf_tables_flowtables, list) { if (family == type->family) return type; } return NULL; } static const struct nf_flowtable_type * nft_flowtable_type_get(struct net *net, u8 family) { const struct nf_flowtable_type *type; rcu_read_lock(); type = __nft_flowtable_type_get(family); if (type != NULL && try_module_get(type->owner)) { rcu_read_unlock(); return type; } rcu_read_unlock(); lockdep_nfnl_nft_mutex_not_held(); #ifdef CONFIG_MODULES if (type == NULL) { if (nft_request_module(net, "nf-flowtable-%u", family) == -EAGAIN) return ERR_PTR(-EAGAIN); } #endif return ERR_PTR(-ENOENT); } /* Only called from error and netdev event paths. */ static void nft_unregister_flowtable_hook(struct net *net, struct nft_flowtable *flowtable, struct nft_hook *hook) { nf_unregister_net_hook(net, &hook->ops); flowtable->data.type->setup(&flowtable->data, hook->ops.dev, FLOW_BLOCK_UNBIND); } static void __nft_unregister_flowtable_net_hooks(struct net *net, struct list_head *hook_list, bool release_netdev) { struct nft_hook *hook, *next; list_for_each_entry_safe(hook, next, hook_list, list) { nf_unregister_net_hook(net, &hook->ops); if (release_netdev) { list_del(&hook->list); kfree_rcu(hook, rcu); } } } static void nft_unregister_flowtable_net_hooks(struct net *net, struct list_head *hook_list) { __nft_unregister_flowtable_net_hooks(net, hook_list, false); } static int nft_register_flowtable_net_hooks(struct net *net, struct nft_table *table, struct list_head *hook_list, struct nft_flowtable *flowtable) { struct nft_hook *hook, *hook2, *next; struct nft_flowtable *ft; int err, i = 0; list_for_each_entry(hook, hook_list, list) { list_for_each_entry(ft, &table->flowtables, list) { if (!nft_is_active_next(net, ft)) continue; list_for_each_entry(hook2, &ft->hook_list, list) { if (hook->ops.dev == hook2->ops.dev && hook->ops.pf == hook2->ops.pf) { err = -EEXIST; goto err_unregister_net_hooks; } } } err = flowtable->data.type->setup(&flowtable->data, hook->ops.dev, FLOW_BLOCK_BIND); if (err < 0) goto err_unregister_net_hooks; err = nf_register_net_hook(net, &hook->ops); if (err < 0) { flowtable->data.type->setup(&flowtable->data, hook->ops.dev, FLOW_BLOCK_UNBIND); goto err_unregister_net_hooks; } i++; } return 0; err_unregister_net_hooks: list_for_each_entry_safe(hook, next, hook_list, list) { if (i-- <= 0) break; nft_unregister_flowtable_hook(net, flowtable, hook); list_del_rcu(&hook->list); kfree_rcu(hook, rcu); } return err; } static void nft_hooks_destroy(struct list_head *hook_list) { struct nft_hook *hook, *next; list_for_each_entry_safe(hook, next, hook_list, list) { list_del_rcu(&hook->list); kfree_rcu(hook, rcu); } } static int nft_flowtable_update(struct nft_ctx *ctx, const struct nlmsghdr *nlh, struct nft_flowtable *flowtable, struct netlink_ext_ack *extack) { const struct nlattr * const *nla = ctx->nla; struct nft_flowtable_hook flowtable_hook; struct nft_hook *hook, *next; struct nft_trans *trans; bool unregister = false; u32 flags; int err; err = nft_flowtable_parse_hook(ctx, nla, &flowtable_hook, flowtable, extack, false); if (err < 0) return err; list_for_each_entry_safe(hook, next, &flowtable_hook.list, list) { if (nft_hook_list_find(&flowtable->hook_list, hook)) { list_del(&hook->list); kfree(hook); } } if (nla[NFTA_FLOWTABLE_FLAGS]) { flags = ntohl(nla_get_be32(nla[NFTA_FLOWTABLE_FLAGS])); if (flags & ~NFT_FLOWTABLE_MASK) { err = -EOPNOTSUPP; goto err_flowtable_update_hook; } if ((flowtable->data.flags & NFT_FLOWTABLE_HW_OFFLOAD) ^ (flags & NFT_FLOWTABLE_HW_OFFLOAD)) { err = -EOPNOTSUPP; goto err_flowtable_update_hook; } } else { flags = flowtable->data.flags; } err = nft_register_flowtable_net_hooks(ctx->net, ctx->table, &flowtable_hook.list, flowtable); if (err < 0) goto err_flowtable_update_hook; trans = nft_trans_alloc(ctx, NFT_MSG_NEWFLOWTABLE, sizeof(struct nft_trans_flowtable)); if (!trans) { unregister = true; err = -ENOMEM; goto err_flowtable_update_hook; } nft_trans_flowtable_flags(trans) = flags; nft_trans_flowtable(trans) = flowtable; nft_trans_flowtable_update(trans) = true; INIT_LIST_HEAD(&nft_trans_flowtable_hooks(trans)); list_splice(&flowtable_hook.list, &nft_trans_flowtable_hooks(trans)); nft_trans_commit_list_add_tail(ctx->net, trans); return 0; err_flowtable_update_hook: list_for_each_entry_safe(hook, next, &flowtable_hook.list, list) { if (unregister) nft_unregister_flowtable_hook(ctx->net, flowtable, hook); list_del_rcu(&hook->list); kfree_rcu(hook, rcu); } return err; } static int nf_tables_newflowtable(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct netlink_ext_ack *extack = info->extack; struct nft_flowtable_hook flowtable_hook; u8 genmask = nft_genmask_next(info->net); u8 family = info->nfmsg->nfgen_family; const struct nf_flowtable_type *type; struct nft_flowtable *flowtable; struct net *net = info->net; struct nft_table *table; struct nft_trans *trans; struct nft_ctx ctx; int err; if (!nla[NFTA_FLOWTABLE_TABLE] || !nla[NFTA_FLOWTABLE_NAME] || !nla[NFTA_FLOWTABLE_HOOK]) return -EINVAL; table = nft_table_lookup(net, nla[NFTA_FLOWTABLE_TABLE], family, genmask, NETLINK_CB(skb).portid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_FLOWTABLE_TABLE]); return PTR_ERR(table); } flowtable = nft_flowtable_lookup(table, nla[NFTA_FLOWTABLE_NAME], genmask); if (IS_ERR(flowtable)) { err = PTR_ERR(flowtable); if (err != -ENOENT) { NL_SET_BAD_ATTR(extack, nla[NFTA_FLOWTABLE_NAME]); return err; } } else { if (info->nlh->nlmsg_flags & NLM_F_EXCL) { NL_SET_BAD_ATTR(extack, nla[NFTA_FLOWTABLE_NAME]); return -EEXIST; } nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); return nft_flowtable_update(&ctx, info->nlh, flowtable, extack); } nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); if (!nft_use_inc(&table->use)) return -EMFILE; flowtable = kzalloc(sizeof(*flowtable), GFP_KERNEL_ACCOUNT); if (!flowtable) { err = -ENOMEM; goto flowtable_alloc; } flowtable->table = table; flowtable->handle = nf_tables_alloc_handle(table); INIT_LIST_HEAD(&flowtable->hook_list); flowtable->name = nla_strdup(nla[NFTA_FLOWTABLE_NAME], GFP_KERNEL_ACCOUNT); if (!flowtable->name) { err = -ENOMEM; goto err1; } type = nft_flowtable_type_get(net, family); if (IS_ERR(type)) { err = PTR_ERR(type); goto err2; } if (nla[NFTA_FLOWTABLE_FLAGS]) { flowtable->data.flags = ntohl(nla_get_be32(nla[NFTA_FLOWTABLE_FLAGS])); if (flowtable->data.flags & ~NFT_FLOWTABLE_MASK) { err = -EOPNOTSUPP; goto err3; } } write_pnet(&flowtable->data.net, net); flowtable->data.type = type; err = type->init(&flowtable->data); if (err < 0) goto err3; err = nft_flowtable_parse_hook(&ctx, nla, &flowtable_hook, flowtable, extack, true); if (err < 0) goto err_flowtable_parse_hooks; list_splice(&flowtable_hook.list, &flowtable->hook_list); flowtable->data.priority = flowtable_hook.priority; flowtable->hooknum = flowtable_hook.num; trans = nft_trans_flowtable_add(&ctx, NFT_MSG_NEWFLOWTABLE, flowtable); if (IS_ERR(trans)) { err = PTR_ERR(trans); goto err_flowtable_trans; } /* This must be LAST to ensure no packets are walking over this flowtable. */ err = nft_register_flowtable_net_hooks(ctx.net, table, &flowtable->hook_list, flowtable); if (err < 0) goto err_flowtable_hooks; list_add_tail_rcu(&flowtable->list, &table->flowtables); return 0; err_flowtable_hooks: nft_trans_destroy(trans); err_flowtable_trans: nft_hooks_destroy(&flowtable->hook_list); err_flowtable_parse_hooks: flowtable->data.type->free(&flowtable->data); err3: module_put(type->owner); err2: kfree(flowtable->name); err1: kfree(flowtable); flowtable_alloc: nft_use_dec_restore(&table->use); return err; } static void nft_flowtable_hook_release(struct nft_flowtable_hook *flowtable_hook) { struct nft_hook *this, *next; list_for_each_entry_safe(this, next, &flowtable_hook->list, list) { list_del(&this->list); kfree(this); } } static int nft_delflowtable_hook(struct nft_ctx *ctx, struct nft_flowtable *flowtable, struct netlink_ext_ack *extack) { const struct nlattr * const *nla = ctx->nla; struct nft_flowtable_hook flowtable_hook; LIST_HEAD(flowtable_del_list); struct nft_hook *this, *hook; struct nft_trans *trans; int err; err = nft_flowtable_parse_hook(ctx, nla, &flowtable_hook, flowtable, extack, false); if (err < 0) return err; list_for_each_entry(this, &flowtable_hook.list, list) { hook = nft_hook_list_find(&flowtable->hook_list, this); if (!hook) { err = -ENOENT; goto err_flowtable_del_hook; } list_move(&hook->list, &flowtable_del_list); } trans = nft_trans_alloc(ctx, NFT_MSG_DELFLOWTABLE, sizeof(struct nft_trans_flowtable)); if (!trans) { err = -ENOMEM; goto err_flowtable_del_hook; } nft_trans_flowtable(trans) = flowtable; nft_trans_flowtable_update(trans) = true; INIT_LIST_HEAD(&nft_trans_flowtable_hooks(trans)); list_splice(&flowtable_del_list, &nft_trans_flowtable_hooks(trans)); nft_flowtable_hook_release(&flowtable_hook); nft_trans_commit_list_add_tail(ctx->net, trans); return 0; err_flowtable_del_hook: list_splice(&flowtable_del_list, &flowtable->hook_list); nft_flowtable_hook_release(&flowtable_hook); return err; } static int nf_tables_delflowtable(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); u8 family = info->nfmsg->nfgen_family; struct nft_flowtable *flowtable; struct net *net = info->net; const struct nlattr *attr; struct nft_table *table; struct nft_ctx ctx; if (!nla[NFTA_FLOWTABLE_TABLE] || (!nla[NFTA_FLOWTABLE_NAME] && !nla[NFTA_FLOWTABLE_HANDLE])) return -EINVAL; table = nft_table_lookup(net, nla[NFTA_FLOWTABLE_TABLE], family, genmask, NETLINK_CB(skb).portid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_FLOWTABLE_TABLE]); return PTR_ERR(table); } if (nla[NFTA_FLOWTABLE_HANDLE]) { attr = nla[NFTA_FLOWTABLE_HANDLE]; flowtable = nft_flowtable_lookup_byhandle(table, attr, genmask); } else { attr = nla[NFTA_FLOWTABLE_NAME]; flowtable = nft_flowtable_lookup(table, attr, genmask); } if (IS_ERR(flowtable)) { if (PTR_ERR(flowtable) == -ENOENT && NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_DESTROYFLOWTABLE) return 0; NL_SET_BAD_ATTR(extack, attr); return PTR_ERR(flowtable); } nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); if (nla[NFTA_FLOWTABLE_HOOK]) return nft_delflowtable_hook(&ctx, flowtable, extack); if (flowtable->use > 0) { NL_SET_BAD_ATTR(extack, attr); return -EBUSY; } return nft_delflowtable(&ctx, flowtable); } static int nf_tables_fill_flowtable_info(struct sk_buff *skb, struct net *net, u32 portid, u32 seq, int event, u32 flags, int family, struct nft_flowtable *flowtable, struct list_head *hook_list) { struct nlattr *nest, *nest_devs; struct nft_hook *hook; struct nlmsghdr *nlh; event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event); nlh = nfnl_msg_put(skb, portid, seq, event, flags, family, NFNETLINK_V0, nft_base_seq(net)); if (!nlh) goto nla_put_failure; if (nla_put_string(skb, NFTA_FLOWTABLE_TABLE, flowtable->table->name) || nla_put_string(skb, NFTA_FLOWTABLE_NAME, flowtable->name) || nla_put_be64(skb, NFTA_FLOWTABLE_HANDLE, cpu_to_be64(flowtable->handle), NFTA_FLOWTABLE_PAD)) goto nla_put_failure; if (event == NFT_MSG_DELFLOWTABLE && !hook_list) { nlmsg_end(skb, nlh); return 0; } if (nla_put_be32(skb, NFTA_FLOWTABLE_USE, htonl(flowtable->use)) || nla_put_be32(skb, NFTA_FLOWTABLE_FLAGS, htonl(flowtable->data.flags))) goto nla_put_failure; nest = nla_nest_start_noflag(skb, NFTA_FLOWTABLE_HOOK); if (!nest) goto nla_put_failure; if (nla_put_be32(skb, NFTA_FLOWTABLE_HOOK_NUM, htonl(flowtable->hooknum)) || nla_put_be32(skb, NFTA_FLOWTABLE_HOOK_PRIORITY, htonl(flowtable->data.priority))) goto nla_put_failure; nest_devs = nla_nest_start_noflag(skb, NFTA_FLOWTABLE_HOOK_DEVS); if (!nest_devs) goto nla_put_failure; if (!hook_list) hook_list = &flowtable->hook_list; list_for_each_entry_rcu(hook, hook_list, list) { if (nla_put_string(skb, NFTA_DEVICE_NAME, hook->ops.dev->name)) goto nla_put_failure; } nla_nest_end(skb, nest_devs); nla_nest_end(skb, nest); nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_trim(skb, nlh); return -1; } struct nft_flowtable_filter { char *table; }; static int nf_tables_dump_flowtable(struct sk_buff *skb, struct netlink_callback *cb) { const struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); struct nft_flowtable_filter *filter = cb->data; unsigned int idx = 0, s_idx = cb->args[0]; struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; struct nft_flowtable *flowtable; struct nftables_pernet *nft_net; const struct nft_table *table; rcu_read_lock(); nft_net = nft_pernet(net); cb->seq = READ_ONCE(nft_net->base_seq); list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) continue; list_for_each_entry_rcu(flowtable, &table->flowtables, list) { if (!nft_is_active(net, flowtable)) goto cont; if (idx < s_idx) goto cont; if (idx > s_idx) memset(&cb->args[1], 0, sizeof(cb->args) - sizeof(cb->args[0])); if (filter && filter->table && strcmp(filter->table, table->name)) goto cont; if (nf_tables_fill_flowtable_info(skb, net, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NFT_MSG_NEWFLOWTABLE, NLM_F_MULTI | NLM_F_APPEND, table->family, flowtable, NULL) < 0) goto done; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); cont: idx++; } } done: rcu_read_unlock(); cb->args[0] = idx; return skb->len; } static int nf_tables_dump_flowtable_start(struct netlink_callback *cb) { const struct nlattr * const *nla = cb->data; struct nft_flowtable_filter *filter = NULL; if (nla[NFTA_FLOWTABLE_TABLE]) { filter = kzalloc(sizeof(*filter), GFP_ATOMIC); if (!filter) return -ENOMEM; filter->table = nla_strdup(nla[NFTA_FLOWTABLE_TABLE], GFP_ATOMIC); if (!filter->table) { kfree(filter); return -ENOMEM; } } cb->data = filter; return 0; } static int nf_tables_dump_flowtable_done(struct netlink_callback *cb) { struct nft_flowtable_filter *filter = cb->data; if (!filter) return 0; kfree(filter->table); kfree(filter); return 0; } /* called with rcu_read_lock held */ static int nf_tables_getflowtable(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_cur(info->net); u8 family = info->nfmsg->nfgen_family; struct nft_flowtable *flowtable; const struct nft_table *table; struct net *net = info->net; struct sk_buff *skb2; int err; if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .start = nf_tables_dump_flowtable_start, .dump = nf_tables_dump_flowtable, .done = nf_tables_dump_flowtable_done, .module = THIS_MODULE, .data = (void *)nla, }; return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); } if (!nla[NFTA_FLOWTABLE_NAME]) return -EINVAL; table = nft_table_lookup(net, nla[NFTA_FLOWTABLE_TABLE], family, genmask, 0); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_FLOWTABLE_TABLE]); return PTR_ERR(table); } flowtable = nft_flowtable_lookup(table, nla[NFTA_FLOWTABLE_NAME], genmask); if (IS_ERR(flowtable)) { NL_SET_BAD_ATTR(extack, nla[NFTA_FLOWTABLE_NAME]); return PTR_ERR(flowtable); } skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC); if (!skb2) return -ENOMEM; err = nf_tables_fill_flowtable_info(skb2, net, NETLINK_CB(skb).portid, info->nlh->nlmsg_seq, NFT_MSG_NEWFLOWTABLE, 0, family, flowtable, NULL); if (err < 0) goto err_fill_flowtable_info; return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); err_fill_flowtable_info: kfree_skb(skb2); return err; } static void nf_tables_flowtable_notify(struct nft_ctx *ctx, struct nft_flowtable *flowtable, struct list_head *hook_list, int event) { struct nftables_pernet *nft_net = nft_pernet(ctx->net); struct sk_buff *skb; u16 flags = 0; int err; if (!ctx->report && !nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES)) return; skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); if (skb == NULL) goto err; if (ctx->flags & (NLM_F_CREATE | NLM_F_EXCL)) flags |= ctx->flags & (NLM_F_CREATE | NLM_F_EXCL); err = nf_tables_fill_flowtable_info(skb, ctx->net, ctx->portid, ctx->seq, event, flags, ctx->family, flowtable, hook_list); if (err < 0) { kfree_skb(skb); goto err; } nft_notify_enqueue(skb, ctx->report, &nft_net->notify_list); return; err: nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, -ENOBUFS); } static void nf_tables_flowtable_destroy(struct nft_flowtable *flowtable) { struct nft_hook *hook, *next; flowtable->data.type->free(&flowtable->data); list_for_each_entry_safe(hook, next, &flowtable->hook_list, list) { flowtable->data.type->setup(&flowtable->data, hook->ops.dev, FLOW_BLOCK_UNBIND); list_del_rcu(&hook->list); kfree(hook); } kfree(flowtable->name); module_put(flowtable->data.type->owner); kfree(flowtable); } static int nf_tables_fill_gen_info(struct sk_buff *skb, struct net *net, u32 portid, u32 seq) { struct nftables_pernet *nft_net = nft_pernet(net); struct nlmsghdr *nlh; char buf[TASK_COMM_LEN]; int event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, NFT_MSG_NEWGEN); nlh = nfnl_msg_put(skb, portid, seq, event, 0, AF_UNSPEC, NFNETLINK_V0, nft_base_seq(net)); if (!nlh) goto nla_put_failure; if (nla_put_be32(skb, NFTA_GEN_ID, htonl(nft_net->base_seq)) || nla_put_be32(skb, NFTA_GEN_PROC_PID, htonl(task_pid_nr(current))) || nla_put_string(skb, NFTA_GEN_PROC_NAME, get_task_comm(buf, current))) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_trim(skb, nlh); return -EMSGSIZE; } static void nft_flowtable_event(unsigned long event, struct net_device *dev, struct nft_flowtable *flowtable) { struct nft_hook *hook; list_for_each_entry(hook, &flowtable->hook_list, list) { if (hook->ops.dev != dev) continue; /* flow_offload_netdev_event() cleans up entries for us. */ nft_unregister_flowtable_hook(dev_net(dev), flowtable, hook); list_del_rcu(&hook->list); kfree_rcu(hook, rcu); break; } } static int nf_tables_flowtable_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct nft_flowtable *flowtable; struct nftables_pernet *nft_net; struct nft_table *table; struct net *net; if (event != NETDEV_UNREGISTER) return 0; net = dev_net(dev); nft_net = nft_pernet(net); mutex_lock(&nft_net->commit_mutex); list_for_each_entry(table, &nft_net->tables, list) { list_for_each_entry(flowtable, &table->flowtables, list) { nft_flowtable_event(event, dev, flowtable); } } mutex_unlock(&nft_net->commit_mutex); return NOTIFY_DONE; } static struct notifier_block nf_tables_flowtable_notifier = { .notifier_call = nf_tables_flowtable_event, }; static void nf_tables_gen_notify(struct net *net, struct sk_buff *skb, int event) { struct nlmsghdr *nlh = nlmsg_hdr(skb); struct sk_buff *skb2; int err; if (!nlmsg_report(nlh) && !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES)) return; skb2 = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); if (skb2 == NULL) goto err; err = nf_tables_fill_gen_info(skb2, net, NETLINK_CB(skb).portid, nlh->nlmsg_seq); if (err < 0) { kfree_skb(skb2); goto err; } nfnetlink_send(skb2, net, NETLINK_CB(skb).portid, NFNLGRP_NFTABLES, nlmsg_report(nlh), GFP_KERNEL); return; err: nfnetlink_set_err(net, NETLINK_CB(skb).portid, NFNLGRP_NFTABLES, -ENOBUFS); } static int nf_tables_getgen(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct sk_buff *skb2; int err; skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC); if (skb2 == NULL) return -ENOMEM; err = nf_tables_fill_gen_info(skb2, info->net, NETLINK_CB(skb).portid, info->nlh->nlmsg_seq); if (err < 0) goto err_fill_gen_info; return nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid); err_fill_gen_info: kfree_skb(skb2); return err; } static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { [NFT_MSG_NEWTABLE] = { .call = nf_tables_newtable, .type = NFNL_CB_BATCH, .attr_count = NFTA_TABLE_MAX, .policy = nft_table_policy, }, [NFT_MSG_GETTABLE] = { .call = nf_tables_gettable, .type = NFNL_CB_RCU, .attr_count = NFTA_TABLE_MAX, .policy = nft_table_policy, }, [NFT_MSG_DELTABLE] = { .call = nf_tables_deltable, .type = NFNL_CB_BATCH, .attr_count = NFTA_TABLE_MAX, .policy = nft_table_policy, }, [NFT_MSG_DESTROYTABLE] = { .call = nf_tables_deltable, .type = NFNL_CB_BATCH, .attr_count = NFTA_TABLE_MAX, .policy = nft_table_policy, }, [NFT_MSG_NEWCHAIN] = { .call = nf_tables_newchain, .type = NFNL_CB_BATCH, .attr_count = NFTA_CHAIN_MAX, .policy = nft_chain_policy, }, [NFT_MSG_GETCHAIN] = { .call = nf_tables_getchain, .type = NFNL_CB_RCU, .attr_count = NFTA_CHAIN_MAX, .policy = nft_chain_policy, }, [NFT_MSG_DELCHAIN] = { .call = nf_tables_delchain, .type = NFNL_CB_BATCH, .attr_count = NFTA_CHAIN_MAX, .policy = nft_chain_policy, }, [NFT_MSG_DESTROYCHAIN] = { .call = nf_tables_delchain, .type = NFNL_CB_BATCH, .attr_count = NFTA_CHAIN_MAX, .policy = nft_chain_policy, }, [NFT_MSG_NEWRULE] = { .call = nf_tables_newrule, .type = NFNL_CB_BATCH, .attr_count = NFTA_RULE_MAX, .policy = nft_rule_policy, }, [NFT_MSG_GETRULE] = { .call = nf_tables_getrule, .type = NFNL_CB_RCU, .attr_count = NFTA_RULE_MAX, .policy = nft_rule_policy, }, [NFT_MSG_GETRULE_RESET] = { .call = nf_tables_getrule_reset, .type = NFNL_CB_RCU, .attr_count = NFTA_RULE_MAX, .policy = nft_rule_policy, }, [NFT_MSG_DELRULE] = { .call = nf_tables_delrule, .type = NFNL_CB_BATCH, .attr_count = NFTA_RULE_MAX, .policy = nft_rule_policy, }, [NFT_MSG_DESTROYRULE] = { .call = nf_tables_delrule, .type = NFNL_CB_BATCH, .attr_count = NFTA_RULE_MAX, .policy = nft_rule_policy, }, [NFT_MSG_NEWSET] = { .call = nf_tables_newset, .type = NFNL_CB_BATCH, .attr_count = NFTA_SET_MAX, .policy = nft_set_policy, }, [NFT_MSG_GETSET] = { .call = nf_tables_getset, .type = NFNL_CB_RCU, .attr_count = NFTA_SET_MAX, .policy = nft_set_policy, }, [NFT_MSG_DELSET] = { .call = nf_tables_delset, .type = NFNL_CB_BATCH, .attr_count = NFTA_SET_MAX, .policy = nft_set_policy, }, [NFT_MSG_DESTROYSET] = { .call = nf_tables_delset, .type = NFNL_CB_BATCH, .attr_count = NFTA_SET_MAX, .policy = nft_set_policy, }, [NFT_MSG_NEWSETELEM] = { .call = nf_tables_newsetelem, .type = NFNL_CB_BATCH, .attr_count = NFTA_SET_ELEM_LIST_MAX, .policy = nft_set_elem_list_policy, }, [NFT_MSG_GETSETELEM] = { .call = nf_tables_getsetelem, .type = NFNL_CB_RCU, .attr_count = NFTA_SET_ELEM_LIST_MAX, .policy = nft_set_elem_list_policy, }, [NFT_MSG_GETSETELEM_RESET] = { .call = nf_tables_getsetelem_reset, .type = NFNL_CB_RCU, .attr_count = NFTA_SET_ELEM_LIST_MAX, .policy = nft_set_elem_list_policy, }, [NFT_MSG_DELSETELEM] = { .call = nf_tables_delsetelem, .type = NFNL_CB_BATCH, .attr_count = NFTA_SET_ELEM_LIST_MAX, .policy = nft_set_elem_list_policy, }, [NFT_MSG_DESTROYSETELEM] = { .call = nf_tables_delsetelem, .type = NFNL_CB_BATCH, .attr_count = NFTA_SET_ELEM_LIST_MAX, .policy = nft_set_elem_list_policy, }, [NFT_MSG_GETGEN] = { .call = nf_tables_getgen, .type = NFNL_CB_RCU, }, [NFT_MSG_NEWOBJ] = { .call = nf_tables_newobj, .type = NFNL_CB_BATCH, .attr_count = NFTA_OBJ_MAX, .policy = nft_obj_policy, }, [NFT_MSG_GETOBJ] = { .call = nf_tables_getobj, .type = NFNL_CB_RCU, .attr_count = NFTA_OBJ_MAX, .policy = nft_obj_policy, }, [NFT_MSG_DELOBJ] = { .call = nf_tables_delobj, .type = NFNL_CB_BATCH, .attr_count = NFTA_OBJ_MAX, .policy = nft_obj_policy, }, [NFT_MSG_DESTROYOBJ] = { .call = nf_tables_delobj, .type = NFNL_CB_BATCH, .attr_count = NFTA_OBJ_MAX, .policy = nft_obj_policy, }, [NFT_MSG_GETOBJ_RESET] = { .call = nf_tables_getobj, .type = NFNL_CB_RCU, .attr_count = NFTA_OBJ_MAX, .policy = nft_obj_policy, }, [NFT_MSG_NEWFLOWTABLE] = { .call = nf_tables_newflowtable, .type = NFNL_CB_BATCH, .attr_count = NFTA_FLOWTABLE_MAX, .policy = nft_flowtable_policy, }, [NFT_MSG_GETFLOWTABLE] = { .call = nf_tables_getflowtable, .type = NFNL_CB_RCU, .attr_count = NFTA_FLOWTABLE_MAX, .policy = nft_flowtable_policy, }, [NFT_MSG_DELFLOWTABLE] = { .call = nf_tables_delflowtable, .type = NFNL_CB_BATCH, .attr_count = NFTA_FLOWTABLE_MAX, .policy = nft_flowtable_policy, }, [NFT_MSG_DESTROYFLOWTABLE] = { .call = nf_tables_delflowtable, .type = NFNL_CB_BATCH, .attr_count = NFTA_FLOWTABLE_MAX, .policy = nft_flowtable_policy, }, }; static int nf_tables_validate(struct net *net) { struct nftables_pernet *nft_net = nft_pernet(net); struct nft_table *table; list_for_each_entry(table, &nft_net->tables, list) { switch (table->validate_state) { case NFT_VALIDATE_SKIP: continue; case NFT_VALIDATE_NEED: nft_validate_state_update(table, NFT_VALIDATE_DO); fallthrough; case NFT_VALIDATE_DO: if (nft_table_validate(net, table) < 0) return -EAGAIN; nft_validate_state_update(table, NFT_VALIDATE_SKIP); break; } } return 0; } /* a drop policy has to be deferred until all rules have been activated, * otherwise a large ruleset that contains a drop-policy base chain will * cause all packets to get dropped until the full transaction has been * processed. * * We defer the drop policy until the transaction has been finalized. */ static void nft_chain_commit_drop_policy(struct nft_trans *trans) { struct nft_base_chain *basechain; if (nft_trans_chain_policy(trans) != NF_DROP) return; if (!nft_is_base_chain(trans->ctx.chain)) return; basechain = nft_base_chain(trans->ctx.chain); basechain->policy = NF_DROP; } static void nft_chain_commit_update(struct nft_trans *trans) { struct nft_base_chain *basechain; if (nft_trans_chain_name(trans)) { rhltable_remove(&trans->ctx.table->chains_ht, &trans->ctx.chain->rhlhead, nft_chain_ht_params); swap(trans->ctx.chain->name, nft_trans_chain_name(trans)); rhltable_insert_key(&trans->ctx.table->chains_ht, trans->ctx.chain->name, &trans->ctx.chain->rhlhead, nft_chain_ht_params); } if (!nft_is_base_chain(trans->ctx.chain)) return; nft_chain_stats_replace(trans); basechain = nft_base_chain(trans->ctx.chain); switch (nft_trans_chain_policy(trans)) { case NF_DROP: case NF_ACCEPT: basechain->policy = nft_trans_chain_policy(trans); break; } } static void nft_obj_commit_update(struct nft_trans *trans) { struct nft_object *newobj; struct nft_object *obj; obj = nft_trans_obj(trans); newobj = nft_trans_obj_newobj(trans); if (obj->ops->update) obj->ops->update(obj, newobj); nft_obj_destroy(&trans->ctx, newobj); } static void nft_commit_release(struct nft_trans *trans) { switch (trans->msg_type) { case NFT_MSG_DELTABLE: case NFT_MSG_DESTROYTABLE: nf_tables_table_destroy(&trans->ctx); break; case NFT_MSG_NEWCHAIN: free_percpu(nft_trans_chain_stats(trans)); kfree(nft_trans_chain_name(trans)); break; case NFT_MSG_DELCHAIN: case NFT_MSG_DESTROYCHAIN: if (nft_trans_chain_update(trans)) nft_hooks_destroy(&nft_trans_chain_hooks(trans)); else nf_tables_chain_destroy(&trans->ctx); break; case NFT_MSG_DELRULE: case NFT_MSG_DESTROYRULE: nf_tables_rule_destroy(&trans->ctx, nft_trans_rule(trans)); break; case NFT_MSG_DELSET: case NFT_MSG_DESTROYSET: nft_set_destroy(&trans->ctx, nft_trans_set(trans)); break; case NFT_MSG_DELSETELEM: case NFT_MSG_DESTROYSETELEM: nf_tables_set_elem_destroy(&trans->ctx, nft_trans_elem_set(trans), nft_trans_elem_priv(trans)); break; case NFT_MSG_DELOBJ: case NFT_MSG_DESTROYOBJ: nft_obj_destroy(&trans->ctx, nft_trans_obj(trans)); break; case NFT_MSG_DELFLOWTABLE: case NFT_MSG_DESTROYFLOWTABLE: if (nft_trans_flowtable_update(trans)) nft_hooks_destroy(&nft_trans_flowtable_hooks(trans)); else nf_tables_flowtable_destroy(nft_trans_flowtable(trans)); break; } if (trans->put_net) put_net(trans->ctx.net); kfree(trans); } static void nf_tables_trans_destroy_work(struct work_struct *w) { struct nft_trans *trans, *next; LIST_HEAD(head); spin_lock(&nf_tables_destroy_list_lock); list_splice_init(&nf_tables_destroy_list, &head); spin_unlock(&nf_tables_destroy_list_lock); if (list_empty(&head)) return; synchronize_rcu(); list_for_each_entry_safe(trans, next, &head, list) { nft_trans_list_del(trans); nft_commit_release(trans); } } void nf_tables_trans_destroy_flush_work(void) { flush_work(&trans_destroy_work); } EXPORT_SYMBOL_GPL(nf_tables_trans_destroy_flush_work); static bool nft_expr_reduce(struct nft_regs_track *track, const struct nft_expr *expr) { return false; } static int nf_tables_commit_chain_prepare(struct net *net, struct nft_chain *chain) { const struct nft_expr *expr, *last; struct nft_regs_track track = {}; unsigned int size, data_size; void *data, *data_boundary; struct nft_rule_dp *prule; struct nft_rule *rule; /* already handled or inactive chain? */ if (chain->blob_next || !nft_is_active_next(net, chain)) return 0; data_size = 0; list_for_each_entry(rule, &chain->rules, list) { if (nft_is_active_next(net, rule)) { data_size += sizeof(*prule) + rule->dlen; if (data_size > INT_MAX) return -ENOMEM; } } chain->blob_next = nf_tables_chain_alloc_rules(chain, data_size); if (!chain->blob_next) return -ENOMEM; data = (void *)chain->blob_next->data; data_boundary = data + data_size; size = 0; list_for_each_entry(rule, &chain->rules, list) { if (!nft_is_active_next(net, rule)) continue; prule = (struct nft_rule_dp *)data; data += offsetof(struct nft_rule_dp, data); if (WARN_ON_ONCE(data > data_boundary)) return -ENOMEM; size = 0; track.last = nft_expr_last(rule); nft_rule_for_each_expr(expr, last, rule) { track.cur = expr; if (nft_expr_reduce(&track, expr)) { expr = track.cur; continue; } if (WARN_ON_ONCE(data + size + expr->ops->size > data_boundary)) return -ENOMEM; memcpy(data + size, expr, expr->ops->size); size += expr->ops->size; } if (WARN_ON_ONCE(size >= 1 << 12)) return -ENOMEM; prule->handle = rule->handle; prule->dlen = size; prule->is_last = 0; data += size; size = 0; chain->blob_next->size += (unsigned long)(data - (void *)prule); } if (WARN_ON_ONCE(data > data_boundary)) return -ENOMEM; prule = (struct nft_rule_dp *)data; nft_last_rule(chain, prule); return 0; } static void nf_tables_commit_chain_prepare_cancel(struct net *net) { struct nftables_pernet *nft_net = nft_pernet(net); struct nft_trans *trans, *next; list_for_each_entry_safe(trans, next, &nft_net->commit_list, list) { struct nft_chain *chain = trans->ctx.chain; if (trans->msg_type == NFT_MSG_NEWRULE || trans->msg_type == NFT_MSG_DELRULE) { kvfree(chain->blob_next); chain->blob_next = NULL; } } } static void __nf_tables_commit_chain_free_rules(struct rcu_head *h) { struct nft_rule_dp_last *l = container_of(h, struct nft_rule_dp_last, h); kvfree(l->blob); } static void nf_tables_commit_chain_free_rules_old(struct nft_rule_blob *blob) { struct nft_rule_dp_last *last; /* last rule trailer is after end marker */ last = (void *)blob + sizeof(*blob) + blob->size; last->blob = blob; call_rcu(&last->h, __nf_tables_commit_chain_free_rules); } static void nf_tables_commit_chain(struct net *net, struct nft_chain *chain) { struct nft_rule_blob *g0, *g1; bool next_genbit; next_genbit = nft_gencursor_next(net); g0 = rcu_dereference_protected(chain->blob_gen_0, lockdep_commit_lock_is_held(net)); g1 = rcu_dereference_protected(chain->blob_gen_1, lockdep_commit_lock_is_held(net)); /* No changes to this chain? */ if (chain->blob_next == NULL) { /* chain had no change in last or next generation */ if (g0 == g1) return; /* * chain had no change in this generation; make sure next * one uses same rules as current generation. */ if (next_genbit) { rcu_assign_pointer(chain->blob_gen_1, g0); nf_tables_commit_chain_free_rules_old(g1); } else { rcu_assign_pointer(chain->blob_gen_0, g1); nf_tables_commit_chain_free_rules_old(g0); } return; } if (next_genbit) rcu_assign_pointer(chain->blob_gen_1, chain->blob_next); else rcu_assign_pointer(chain->blob_gen_0, chain->blob_next); chain->blob_next = NULL; if (g0 == g1) return; if (next_genbit) nf_tables_commit_chain_free_rules_old(g1); else nf_tables_commit_chain_free_rules_old(g0); } static void nft_obj_del(struct nft_object *obj) { rhltable_remove(&nft_objname_ht, &obj->rhlhead, nft_objname_ht_params); list_del_rcu(&obj->list); } void nft_chain_del(struct nft_chain *chain) { struct nft_table *table = chain->table; WARN_ON_ONCE(rhltable_remove(&table->chains_ht, &chain->rhlhead, nft_chain_ht_params)); list_del_rcu(&chain->list); } static void nft_trans_gc_setelem_remove(struct nft_ctx *ctx, struct nft_trans_gc *trans) { struct nft_elem_priv **priv = trans->priv; unsigned int i; for (i = 0; i < trans->count; i++) { nft_setelem_data_deactivate(ctx->net, trans->set, priv[i]); nft_setelem_remove(ctx->net, trans->set, priv[i]); } } void nft_trans_gc_destroy(struct nft_trans_gc *trans) { nft_set_put(trans->set); put_net(trans->net); kfree(trans); } static void nft_trans_gc_trans_free(struct rcu_head *rcu) { struct nft_elem_priv *elem_priv; struct nft_trans_gc *trans; struct nft_ctx ctx = {}; unsigned int i; trans = container_of(rcu, struct nft_trans_gc, rcu); ctx.net = read_pnet(&trans->set->net); for (i = 0; i < trans->count; i++) { elem_priv = trans->priv[i]; if (!nft_setelem_is_catchall(trans->set, elem_priv)) atomic_dec(&trans->set->nelems); nf_tables_set_elem_destroy(&ctx, trans->set, elem_priv); } nft_trans_gc_destroy(trans); } static bool nft_trans_gc_work_done(struct nft_trans_gc *trans) { struct nftables_pernet *nft_net; struct nft_ctx ctx = {}; nft_net = nft_pernet(trans->net); mutex_lock(&nft_net->commit_mutex); /* Check for race with transaction, otherwise this batch refers to * stale objects that might not be there anymore. Skip transaction if * set has been destroyed from control plane transaction in case gc * worker loses race. */ if (READ_ONCE(nft_net->gc_seq) != trans->seq || trans->set->dead) { mutex_unlock(&nft_net->commit_mutex); return false; } ctx.net = trans->net; ctx.table = trans->set->table; nft_trans_gc_setelem_remove(&ctx, trans); mutex_unlock(&nft_net->commit_mutex); return true; } static void nft_trans_gc_work(struct work_struct *work) { struct nft_trans_gc *trans, *next; LIST_HEAD(trans_gc_list); spin_lock(&nf_tables_gc_list_lock); list_splice_init(&nf_tables_gc_list, &trans_gc_list); spin_unlock(&nf_tables_gc_list_lock); list_for_each_entry_safe(trans, next, &trans_gc_list, list) { list_del(&trans->list); if (!nft_trans_gc_work_done(trans)) { nft_trans_gc_destroy(trans); continue; } call_rcu(&trans->rcu, nft_trans_gc_trans_free); } } struct nft_trans_gc *nft_trans_gc_alloc(struct nft_set *set, unsigned int gc_seq, gfp_t gfp) { struct net *net = read_pnet(&set->net); struct nft_trans_gc *trans; trans = kzalloc(sizeof(*trans), gfp); if (!trans) return NULL; trans->net = maybe_get_net(net); if (!trans->net) { kfree(trans); return NULL; } refcount_inc(&set->refs); trans->set = set; trans->seq = gc_seq; return trans; } void nft_trans_gc_elem_add(struct nft_trans_gc *trans, void *priv) { trans->priv[trans->count++] = priv; } static void nft_trans_gc_queue_work(struct nft_trans_gc *trans) { spin_lock(&nf_tables_gc_list_lock); list_add_tail(&trans->list, &nf_tables_gc_list); spin_unlock(&nf_tables_gc_list_lock); schedule_work(&trans_gc_work); } static int nft_trans_gc_space(struct nft_trans_gc *trans) { return NFT_TRANS_GC_BATCHCOUNT - trans->count; } struct nft_trans_gc *nft_trans_gc_queue_async(struct nft_trans_gc *gc, unsigned int gc_seq, gfp_t gfp) { struct nft_set *set; if (nft_trans_gc_space(gc)) return gc; set = gc->set; nft_trans_gc_queue_work(gc); return nft_trans_gc_alloc(set, gc_seq, gfp); } void nft_trans_gc_queue_async_done(struct nft_trans_gc *trans) { if (trans->count == 0) { nft_trans_gc_destroy(trans); return; } nft_trans_gc_queue_work(trans); } struct nft_trans_gc *nft_trans_gc_queue_sync(struct nft_trans_gc *gc, gfp_t gfp) { struct nft_set *set; if (WARN_ON_ONCE(!lockdep_commit_lock_is_held(gc->net))) return NULL; if (nft_trans_gc_space(gc)) return gc; set = gc->set; call_rcu(&gc->rcu, nft_trans_gc_trans_free); return nft_trans_gc_alloc(set, 0, gfp); } void nft_trans_gc_queue_sync_done(struct nft_trans_gc *trans) { WARN_ON_ONCE(!lockdep_commit_lock_is_held(trans->net)); if (trans->count == 0) { nft_trans_gc_destroy(trans); return; } call_rcu(&trans->rcu, nft_trans_gc_trans_free); } struct nft_trans_gc *nft_trans_gc_catchall_async(struct nft_trans_gc *gc, unsigned int gc_seq) { struct nft_set_elem_catchall *catchall; const struct nft_set *set = gc->set; struct nft_set_ext *ext; list_for_each_entry_rcu(catchall, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); if (!nft_set_elem_expired(ext)) continue; if (nft_set_elem_is_dead(ext)) goto dead_elem; nft_set_elem_dead(ext); dead_elem: gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC); if (!gc) return NULL; nft_trans_gc_elem_add(gc, catchall->elem); } return gc; } struct nft_trans_gc *nft_trans_gc_catchall_sync(struct nft_trans_gc *gc) { struct nft_set_elem_catchall *catchall, *next; u64 tstamp = nft_net_tstamp(gc->net); const struct nft_set *set = gc->set; struct nft_elem_priv *elem_priv; struct nft_set_ext *ext; WARN_ON_ONCE(!lockdep_commit_lock_is_held(gc->net)); list_for_each_entry_safe(catchall, next, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); if (!__nft_set_elem_expired(ext, tstamp)) continue; gc = nft_trans_gc_queue_sync(gc, GFP_KERNEL); if (!gc) return NULL; elem_priv = catchall->elem; nft_setelem_data_deactivate(gc->net, gc->set, elem_priv); nft_setelem_catchall_destroy(catchall); nft_trans_gc_elem_add(gc, elem_priv); } return gc; } static void nf_tables_module_autoload_cleanup(struct net *net) { struct nftables_pernet *nft_net = nft_pernet(net); struct nft_module_request *req, *next; WARN_ON_ONCE(!list_empty(&nft_net->commit_list)); list_for_each_entry_safe(req, next, &nft_net->module_list, list) { WARN_ON_ONCE(!req->done); list_del(&req->list); kfree(req); } } static void nf_tables_commit_release(struct net *net) { struct nftables_pernet *nft_net = nft_pernet(net); struct nft_trans *trans; /* all side effects have to be made visible. * For example, if a chain named 'foo' has been deleted, a * new transaction must not find it anymore. * * Memory reclaim happens asynchronously from work queue * to prevent expensive synchronize_rcu() in commit phase. */ if (list_empty(&nft_net->commit_list)) { nf_tables_module_autoload_cleanup(net); mutex_unlock(&nft_net->commit_mutex); return; } trans = list_last_entry(&nft_net->commit_list, struct nft_trans, list); get_net(trans->ctx.net); WARN_ON_ONCE(trans->put_net); trans->put_net = true; spin_lock(&nf_tables_destroy_list_lock); list_splice_tail_init(&nft_net->commit_list, &nf_tables_destroy_list); spin_unlock(&nf_tables_destroy_list_lock); nf_tables_module_autoload_cleanup(net); schedule_work(&trans_destroy_work); mutex_unlock(&nft_net->commit_mutex); } static void nft_commit_notify(struct net *net, u32 portid) { struct nftables_pernet *nft_net = nft_pernet(net); struct sk_buff *batch_skb = NULL, *nskb, *skb; unsigned char *data; int len; list_for_each_entry_safe(skb, nskb, &nft_net->notify_list, list) { if (!batch_skb) { new_batch: batch_skb = skb; len = NLMSG_GOODSIZE - skb->len; list_del(&skb->list); continue; } len -= skb->len; if (len > 0 && NFT_CB(skb).report == NFT_CB(batch_skb).report) { data = skb_put(batch_skb, skb->len); memcpy(data, skb->data, skb->len); list_del(&skb->list); kfree_skb(skb); continue; } nfnetlink_send(batch_skb, net, portid, NFNLGRP_NFTABLES, NFT_CB(batch_skb).report, GFP_KERNEL); goto new_batch; } if (batch_skb) { nfnetlink_send(batch_skb, net, portid, NFNLGRP_NFTABLES, NFT_CB(batch_skb).report, GFP_KERNEL); } WARN_ON_ONCE(!list_empty(&nft_net->notify_list)); } static int nf_tables_commit_audit_alloc(struct list_head *adl, struct nft_table *table) { struct nft_audit_data *adp; list_for_each_entry(adp, adl, list) { if (adp->table == table) return 0; } adp = kzalloc(sizeof(*adp), GFP_KERNEL); if (!adp) return -ENOMEM; adp->table = table; list_add(&adp->list, adl); return 0; } static void nf_tables_commit_audit_free(struct list_head *adl) { struct nft_audit_data *adp, *adn; list_for_each_entry_safe(adp, adn, adl, list) { list_del(&adp->list); kfree(adp); } } static void nf_tables_commit_audit_collect(struct list_head *adl, struct nft_table *table, u32 op) { struct nft_audit_data *adp; list_for_each_entry(adp, adl, list) { if (adp->table == table) goto found; } WARN_ONCE(1, "table=%s not expected in commit list", table->name); return; found: adp->entries++; if (!adp->op || adp->op > op) adp->op = op; } #define AUNFTABLENAMELEN (NFT_TABLE_MAXNAMELEN + 22) static void nf_tables_commit_audit_log(struct list_head *adl, u32 generation) { struct nft_audit_data *adp, *adn; char aubuf[AUNFTABLENAMELEN]; list_for_each_entry_safe(adp, adn, adl, list) { snprintf(aubuf, AUNFTABLENAMELEN, "%s:%u", adp->table->name, generation); audit_log_nfcfg(aubuf, adp->table->family, adp->entries, nft2audit_op[adp->op], GFP_KERNEL); list_del(&adp->list); kfree(adp); } } static void nft_set_commit_update(struct list_head *set_update_list) { struct nft_set *set, *next; list_for_each_entry_safe(set, next, set_update_list, pending_update) { list_del_init(&set->pending_update); if (!set->ops->commit || set->dead) continue; set->ops->commit(set); } } static unsigned int nft_gc_seq_begin(struct nftables_pernet *nft_net) { unsigned int gc_seq; /* Bump gc counter, it becomes odd, this is the busy mark. */ gc_seq = READ_ONCE(nft_net->gc_seq); WRITE_ONCE(nft_net->gc_seq, ++gc_seq); return gc_seq; } static void nft_gc_seq_end(struct nftables_pernet *nft_net, unsigned int gc_seq) { WRITE_ONCE(nft_net->gc_seq, ++gc_seq); } static int nf_tables_commit(struct net *net, struct sk_buff *skb) { struct nftables_pernet *nft_net = nft_pernet(net); struct nft_trans *trans, *next; unsigned int base_seq, gc_seq; LIST_HEAD(set_update_list); struct nft_trans_elem *te; struct nft_chain *chain; struct nft_table *table; LIST_HEAD(adl); int err; if (list_empty(&nft_net->commit_list)) { mutex_unlock(&nft_net->commit_mutex); return 0; } list_for_each_entry(trans, &nft_net->binding_list, binding_list) { switch (trans->msg_type) { case NFT_MSG_NEWSET: if (!nft_trans_set_update(trans) && nft_set_is_anonymous(nft_trans_set(trans)) && !nft_trans_set_bound(trans)) { pr_warn_once("nftables ruleset with unbound set\n"); return -EINVAL; } break; case NFT_MSG_NEWCHAIN: if (!nft_trans_chain_update(trans) && nft_chain_binding(nft_trans_chain(trans)) && !nft_trans_chain_bound(trans)) { pr_warn_once("nftables ruleset with unbound chain\n"); return -EINVAL; } break; } } /* 0. Validate ruleset, otherwise roll back for error reporting. */ if (nf_tables_validate(net) < 0) { nft_net->validate_state = NFT_VALIDATE_DO; return -EAGAIN; } err = nft_flow_rule_offload_commit(net); if (err < 0) return err; /* 1. Allocate space for next generation rules_gen_X[] */ list_for_each_entry_safe(trans, next, &nft_net->commit_list, list) { int ret; ret = nf_tables_commit_audit_alloc(&adl, trans->ctx.table); if (ret) { nf_tables_commit_chain_prepare_cancel(net); nf_tables_commit_audit_free(&adl); return ret; } if (trans->msg_type == NFT_MSG_NEWRULE || trans->msg_type == NFT_MSG_DELRULE) { chain = trans->ctx.chain; ret = nf_tables_commit_chain_prepare(net, chain); if (ret < 0) { nf_tables_commit_chain_prepare_cancel(net); nf_tables_commit_audit_free(&adl); return ret; } } } /* step 2. Make rules_gen_X visible to packet path */ list_for_each_entry(table, &nft_net->tables, list) { list_for_each_entry(chain, &table->chains, list) nf_tables_commit_chain(net, chain); } /* * Bump generation counter, invalidate any dump in progress. * Cannot fail after this point. */ base_seq = READ_ONCE(nft_net->base_seq); while (++base_seq == 0) ; WRITE_ONCE(nft_net->base_seq, base_seq); gc_seq = nft_gc_seq_begin(nft_net); /* step 3. Start new generation, rules_gen_X now in use. */ net->nft.gencursor = nft_gencursor_next(net); list_for_each_entry_safe(trans, next, &nft_net->commit_list, list) { nf_tables_commit_audit_collect(&adl, trans->ctx.table, trans->msg_type); switch (trans->msg_type) { case NFT_MSG_NEWTABLE: if (nft_trans_table_update(trans)) { if (!(trans->ctx.table->flags & __NFT_TABLE_F_UPDATE)) { nft_trans_destroy(trans); break; } if (trans->ctx.table->flags & NFT_TABLE_F_DORMANT) nf_tables_table_disable(net, trans->ctx.table); trans->ctx.table->flags &= ~__NFT_TABLE_F_UPDATE; } else { nft_clear(net, trans->ctx.table); } nf_tables_table_notify(&trans->ctx, NFT_MSG_NEWTABLE); nft_trans_destroy(trans); break; case NFT_MSG_DELTABLE: case NFT_MSG_DESTROYTABLE: list_del_rcu(&trans->ctx.table->list); nf_tables_table_notify(&trans->ctx, trans->msg_type); break; case NFT_MSG_NEWCHAIN: if (nft_trans_chain_update(trans)) { nft_chain_commit_update(trans); nf_tables_chain_notify(&trans->ctx, NFT_MSG_NEWCHAIN, &nft_trans_chain_hooks(trans)); list_splice(&nft_trans_chain_hooks(trans), &nft_trans_basechain(trans)->hook_list); /* trans destroyed after rcu grace period */ } else { nft_chain_commit_drop_policy(trans); nft_clear(net, trans->ctx.chain); nf_tables_chain_notify(&trans->ctx, NFT_MSG_NEWCHAIN, NULL); nft_trans_destroy(trans); } break; case NFT_MSG_DELCHAIN: case NFT_MSG_DESTROYCHAIN: if (nft_trans_chain_update(trans)) { nf_tables_chain_notify(&trans->ctx, NFT_MSG_DELCHAIN, &nft_trans_chain_hooks(trans)); if (!(trans->ctx.table->flags & NFT_TABLE_F_DORMANT)) { nft_netdev_unregister_hooks(net, &nft_trans_chain_hooks(trans), true); } } else { nft_chain_del(trans->ctx.chain); nf_tables_chain_notify(&trans->ctx, NFT_MSG_DELCHAIN, NULL); nf_tables_unregister_hook(trans->ctx.net, trans->ctx.table, trans->ctx.chain); } break; case NFT_MSG_NEWRULE: nft_clear(trans->ctx.net, nft_trans_rule(trans)); nf_tables_rule_notify(&trans->ctx, nft_trans_rule(trans), NFT_MSG_NEWRULE); if (trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD) nft_flow_rule_destroy(nft_trans_flow_rule(trans)); nft_trans_destroy(trans); break; case NFT_MSG_DELRULE: case NFT_MSG_DESTROYRULE: list_del_rcu(&nft_trans_rule(trans)->list); nf_tables_rule_notify(&trans->ctx, nft_trans_rule(trans), trans->msg_type); nft_rule_expr_deactivate(&trans->ctx, nft_trans_rule(trans), NFT_TRANS_COMMIT); if (trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD) nft_flow_rule_destroy(nft_trans_flow_rule(trans)); break; case NFT_MSG_NEWSET: if (nft_trans_set_update(trans)) { struct nft_set *set = nft_trans_set(trans); WRITE_ONCE(set->timeout, nft_trans_set_timeout(trans)); WRITE_ONCE(set->gc_int, nft_trans_set_gc_int(trans)); if (nft_trans_set_size(trans)) WRITE_ONCE(set->size, nft_trans_set_size(trans)); } else { nft_clear(net, nft_trans_set(trans)); /* This avoids hitting -EBUSY when deleting the table * from the transaction. */ if (nft_set_is_anonymous(nft_trans_set(trans)) && !list_empty(&nft_trans_set(trans)->bindings)) nft_use_dec(&trans->ctx.table->use); } nf_tables_set_notify(&trans->ctx, nft_trans_set(trans), NFT_MSG_NEWSET, GFP_KERNEL); nft_trans_destroy(trans); break; case NFT_MSG_DELSET: case NFT_MSG_DESTROYSET: nft_trans_set(trans)->dead = 1; list_del_rcu(&nft_trans_set(trans)->list); nf_tables_set_notify(&trans->ctx, nft_trans_set(trans), trans->msg_type, GFP_KERNEL); break; case NFT_MSG_NEWSETELEM: te = (struct nft_trans_elem *)trans->data; nft_setelem_activate(net, te->set, te->elem_priv); nf_tables_setelem_notify(&trans->ctx, te->set, te->elem_priv, NFT_MSG_NEWSETELEM); if (te->set->ops->commit && list_empty(&te->set->pending_update)) { list_add_tail(&te->set->pending_update, &set_update_list); } nft_trans_destroy(trans); break; case NFT_MSG_DELSETELEM: case NFT_MSG_DESTROYSETELEM: te = (struct nft_trans_elem *)trans->data; nf_tables_setelem_notify(&trans->ctx, te->set, te->elem_priv, trans->msg_type); nft_setelem_remove(net, te->set, te->elem_priv); if (!nft_setelem_is_catchall(te->set, te->elem_priv)) { atomic_dec(&te->set->nelems); te->set->ndeact--; } if (te->set->ops->commit && list_empty(&te->set->pending_update)) { list_add_tail(&te->set->pending_update, &set_update_list); } break; case NFT_MSG_NEWOBJ: if (nft_trans_obj_update(trans)) { nft_obj_commit_update(trans); nf_tables_obj_notify(&trans->ctx, nft_trans_obj(trans), NFT_MSG_NEWOBJ); } else { nft_clear(net, nft_trans_obj(trans)); nf_tables_obj_notify(&trans->ctx, nft_trans_obj(trans), NFT_MSG_NEWOBJ); nft_trans_destroy(trans); } break; case NFT_MSG_DELOBJ: case NFT_MSG_DESTROYOBJ: nft_obj_del(nft_trans_obj(trans)); nf_tables_obj_notify(&trans->ctx, nft_trans_obj(trans), trans->msg_type); break; case NFT_MSG_NEWFLOWTABLE: if (nft_trans_flowtable_update(trans)) { nft_trans_flowtable(trans)->data.flags = nft_trans_flowtable_flags(trans); nf_tables_flowtable_notify(&trans->ctx, nft_trans_flowtable(trans), &nft_trans_flowtable_hooks(trans), NFT_MSG_NEWFLOWTABLE); list_splice(&nft_trans_flowtable_hooks(trans), &nft_trans_flowtable(trans)->hook_list); } else { nft_clear(net, nft_trans_flowtable(trans)); nf_tables_flowtable_notify(&trans->ctx, nft_trans_flowtable(trans), NULL, NFT_MSG_NEWFLOWTABLE); } nft_trans_destroy(trans); break; case NFT_MSG_DELFLOWTABLE: case NFT_MSG_DESTROYFLOWTABLE: if (nft_trans_flowtable_update(trans)) { nf_tables_flowtable_notify(&trans->ctx, nft_trans_flowtable(trans), &nft_trans_flowtable_hooks(trans), trans->msg_type); nft_unregister_flowtable_net_hooks(net, &nft_trans_flowtable_hooks(trans)); } else { list_del_rcu(&nft_trans_flowtable(trans)->list); nf_tables_flowtable_notify(&trans->ctx, nft_trans_flowtable(trans), NULL, trans->msg_type); nft_unregister_flowtable_net_hooks(net, &nft_trans_flowtable(trans)->hook_list); } break; } } nft_set_commit_update(&set_update_list); nft_commit_notify(net, NETLINK_CB(skb).portid); nf_tables_gen_notify(net, skb, NFT_MSG_NEWGEN); nf_tables_commit_audit_log(&adl, nft_net->base_seq); nft_gc_seq_end(nft_net, gc_seq); nft_net->validate_state = NFT_VALIDATE_SKIP; nf_tables_commit_release(net); return 0; } static void nf_tables_module_autoload(struct net *net) { struct nftables_pernet *nft_net = nft_pernet(net); struct nft_module_request *req, *next; LIST_HEAD(module_list); list_splice_init(&nft_net->module_list, &module_list); mutex_unlock(&nft_net->commit_mutex); list_for_each_entry_safe(req, next, &module_list, list) { request_module("%s", req->module); req->done = true; } mutex_lock(&nft_net->commit_mutex); list_splice(&module_list, &nft_net->module_list); } static void nf_tables_abort_release(struct nft_trans *trans) { switch (trans->msg_type) { case NFT_MSG_NEWTABLE: nf_tables_table_destroy(&trans->ctx); break; case NFT_MSG_NEWCHAIN: if (nft_trans_chain_update(trans)) nft_hooks_destroy(&nft_trans_chain_hooks(trans)); else nf_tables_chain_destroy(&trans->ctx); break; case NFT_MSG_NEWRULE: nf_tables_rule_destroy(&trans->ctx, nft_trans_rule(trans)); break; case NFT_MSG_NEWSET: nft_set_destroy(&trans->ctx, nft_trans_set(trans)); break; case NFT_MSG_NEWSETELEM: nft_set_elem_destroy(nft_trans_elem_set(trans), nft_trans_elem_priv(trans), true); break; case NFT_MSG_NEWOBJ: nft_obj_destroy(&trans->ctx, nft_trans_obj(trans)); break; case NFT_MSG_NEWFLOWTABLE: if (nft_trans_flowtable_update(trans)) nft_hooks_destroy(&nft_trans_flowtable_hooks(trans)); else nf_tables_flowtable_destroy(nft_trans_flowtable(trans)); break; } kfree(trans); } static void nft_set_abort_update(struct list_head *set_update_list) { struct nft_set *set, *next; list_for_each_entry_safe(set, next, set_update_list, pending_update) { list_del_init(&set->pending_update); if (!set->ops->abort) continue; set->ops->abort(set); } } static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) { struct nftables_pernet *nft_net = nft_pernet(net); struct nft_trans *trans, *next; LIST_HEAD(set_update_list); struct nft_trans_elem *te; int err = 0; if (action == NFNL_ABORT_VALIDATE && nf_tables_validate(net) < 0) err = -EAGAIN; list_for_each_entry_safe_reverse(trans, next, &nft_net->commit_list, list) { switch (trans->msg_type) { case NFT_MSG_NEWTABLE: if (nft_trans_table_update(trans)) { if (!(trans->ctx.table->flags & __NFT_TABLE_F_UPDATE)) { nft_trans_destroy(trans); break; } if (trans->ctx.table->flags & __NFT_TABLE_F_WAS_DORMANT) { nf_tables_table_disable(net, trans->ctx.table); trans->ctx.table->flags |= NFT_TABLE_F_DORMANT; } else if (trans->ctx.table->flags & __NFT_TABLE_F_WAS_AWAKEN) { trans->ctx.table->flags &= ~NFT_TABLE_F_DORMANT; } if (trans->ctx.table->flags & __NFT_TABLE_F_WAS_ORPHAN) { trans->ctx.table->flags &= ~NFT_TABLE_F_OWNER; trans->ctx.table->nlpid = 0; } trans->ctx.table->flags &= ~__NFT_TABLE_F_UPDATE; nft_trans_destroy(trans); } else { list_del_rcu(&trans->ctx.table->list); } break; case NFT_MSG_DELTABLE: case NFT_MSG_DESTROYTABLE: nft_clear(trans->ctx.net, trans->ctx.table); nft_trans_destroy(trans); break; case NFT_MSG_NEWCHAIN: if (nft_trans_chain_update(trans)) { if (!(trans->ctx.table->flags & NFT_TABLE_F_DORMANT)) { nft_netdev_unregister_hooks(net, &nft_trans_chain_hooks(trans), true); } free_percpu(nft_trans_chain_stats(trans)); kfree(nft_trans_chain_name(trans)); nft_trans_destroy(trans); } else { if (nft_trans_chain_bound(trans)) { nft_trans_destroy(trans); break; } nft_use_dec_restore(&trans->ctx.table->use); nft_chain_del(trans->ctx.chain); nf_tables_unregister_hook(trans->ctx.net, trans->ctx.table, trans->ctx.chain); } break; case NFT_MSG_DELCHAIN: case NFT_MSG_DESTROYCHAIN: if (nft_trans_chain_update(trans)) { list_splice(&nft_trans_chain_hooks(trans), &nft_trans_basechain(trans)->hook_list); } else { nft_use_inc_restore(&trans->ctx.table->use); nft_clear(trans->ctx.net, trans->ctx.chain); } nft_trans_destroy(trans); break; case NFT_MSG_NEWRULE: if (nft_trans_rule_bound(trans)) { nft_trans_destroy(trans); break; } nft_use_dec_restore(&trans->ctx.chain->use); list_del_rcu(&nft_trans_rule(trans)->list); nft_rule_expr_deactivate(&trans->ctx, nft_trans_rule(trans), NFT_TRANS_ABORT); if (trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD) nft_flow_rule_destroy(nft_trans_flow_rule(trans)); break; case NFT_MSG_DELRULE: case NFT_MSG_DESTROYRULE: nft_use_inc_restore(&trans->ctx.chain->use); nft_clear(trans->ctx.net, nft_trans_rule(trans)); nft_rule_expr_activate(&trans->ctx, nft_trans_rule(trans)); if (trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD) nft_flow_rule_destroy(nft_trans_flow_rule(trans)); nft_trans_destroy(trans); break; case NFT_MSG_NEWSET: if (nft_trans_set_update(trans)) { nft_trans_destroy(trans); break; } nft_use_dec_restore(&trans->ctx.table->use); if (nft_trans_set_bound(trans)) { nft_trans_destroy(trans); break; } nft_trans_set(trans)->dead = 1; list_del_rcu(&nft_trans_set(trans)->list); break; case NFT_MSG_DELSET: case NFT_MSG_DESTROYSET: nft_use_inc_restore(&trans->ctx.table->use); nft_clear(trans->ctx.net, nft_trans_set(trans)); if (nft_trans_set(trans)->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) nft_map_activate(&trans->ctx, nft_trans_set(trans)); nft_trans_destroy(trans); break; case NFT_MSG_NEWSETELEM: if (nft_trans_elem_set_bound(trans)) { nft_trans_destroy(trans); break; } te = (struct nft_trans_elem *)trans->data; nft_setelem_remove(net, te->set, te->elem_priv); if (!nft_setelem_is_catchall(te->set, te->elem_priv)) atomic_dec(&te->set->nelems); if (te->set->ops->abort && list_empty(&te->set->pending_update)) { list_add_tail(&te->set->pending_update, &set_update_list); } break; case NFT_MSG_DELSETELEM: case NFT_MSG_DESTROYSETELEM: te = (struct nft_trans_elem *)trans->data; if (!nft_setelem_active_next(net, te->set, te->elem_priv)) { nft_setelem_data_activate(net, te->set, te->elem_priv); nft_setelem_activate(net, te->set, te->elem_priv); } if (!nft_setelem_is_catchall(te->set, te->elem_priv)) te->set->ndeact--; if (te->set->ops->abort && list_empty(&te->set->pending_update)) { list_add_tail(&te->set->pending_update, &set_update_list); } nft_trans_destroy(trans); break; case NFT_MSG_NEWOBJ: if (nft_trans_obj_update(trans)) { nft_obj_destroy(&trans->ctx, nft_trans_obj_newobj(trans)); nft_trans_destroy(trans); } else { nft_use_dec_restore(&trans->ctx.table->use); nft_obj_del(nft_trans_obj(trans)); } break; case NFT_MSG_DELOBJ: case NFT_MSG_DESTROYOBJ: nft_use_inc_restore(&trans->ctx.table->use); nft_clear(trans->ctx.net, nft_trans_obj(trans)); nft_trans_destroy(trans); break; case NFT_MSG_NEWFLOWTABLE: if (nft_trans_flowtable_update(trans)) { nft_unregister_flowtable_net_hooks(net, &nft_trans_flowtable_hooks(trans)); } else { nft_use_dec_restore(&trans->ctx.table->use); list_del_rcu(&nft_trans_flowtable(trans)->list); nft_unregister_flowtable_net_hooks(net, &nft_trans_flowtable(trans)->hook_list); } break; case NFT_MSG_DELFLOWTABLE: case NFT_MSG_DESTROYFLOWTABLE: if (nft_trans_flowtable_update(trans)) { list_splice(&nft_trans_flowtable_hooks(trans), &nft_trans_flowtable(trans)->hook_list); } else { nft_use_inc_restore(&trans->ctx.table->use); nft_clear(trans->ctx.net, nft_trans_flowtable(trans)); } nft_trans_destroy(trans); break; } } nft_set_abort_update(&set_update_list); synchronize_rcu(); list_for_each_entry_safe_reverse(trans, next, &nft_net->commit_list, list) { nft_trans_list_del(trans); nf_tables_abort_release(trans); } return err; } static int nf_tables_abort(struct net *net, struct sk_buff *skb, enum nfnl_abort_action action) { struct nftables_pernet *nft_net = nft_pernet(net); unsigned int gc_seq; int ret; gc_seq = nft_gc_seq_begin(nft_net); ret = __nf_tables_abort(net, action); nft_gc_seq_end(nft_net, gc_seq); WARN_ON_ONCE(!list_empty(&nft_net->commit_list)); /* module autoload needs to happen after GC sequence update because it * temporarily releases and grabs mutex again. */ if (action == NFNL_ABORT_AUTOLOAD) nf_tables_module_autoload(net); else nf_tables_module_autoload_cleanup(net); mutex_unlock(&nft_net->commit_mutex); return ret; } static bool nf_tables_valid_genid(struct net *net, u32 genid) { struct nftables_pernet *nft_net = nft_pernet(net); bool genid_ok; mutex_lock(&nft_net->commit_mutex); nft_net->tstamp = get_jiffies_64(); genid_ok = genid == 0 || nft_net->base_seq == genid; if (!genid_ok) mutex_unlock(&nft_net->commit_mutex); /* else, commit mutex has to be released by commit or abort function */ return genid_ok; } static const struct nfnetlink_subsystem nf_tables_subsys = { .name = "nf_tables", .subsys_id = NFNL_SUBSYS_NFTABLES, .cb_count = NFT_MSG_MAX, .cb = nf_tables_cb, .commit = nf_tables_commit, .abort = nf_tables_abort, .valid_genid = nf_tables_valid_genid, .owner = THIS_MODULE, }; int nft_chain_validate_dependency(const struct nft_chain *chain, enum nft_chain_types type) { const struct nft_base_chain *basechain; if (nft_is_base_chain(chain)) { basechain = nft_base_chain(chain); if (basechain->type->type != type) return -EOPNOTSUPP; } return 0; } EXPORT_SYMBOL_GPL(nft_chain_validate_dependency); int nft_chain_validate_hooks(const struct nft_chain *chain, unsigned int hook_flags) { struct nft_base_chain *basechain; if (nft_is_base_chain(chain)) { basechain = nft_base_chain(chain); if ((1 << basechain->ops.hooknum) & hook_flags) return 0; return -EOPNOTSUPP; } return 0; } EXPORT_SYMBOL_GPL(nft_chain_validate_hooks); /* * Loop detection - walk through the ruleset beginning at the destination chain * of a new jump until either the source chain is reached (loop) or all * reachable chains have been traversed. * * The loop check is performed whenever a new jump verdict is added to an * expression or verdict map or a verdict map is bound to a new chain. */ static int nf_tables_check_loops(const struct nft_ctx *ctx, const struct nft_chain *chain); static int nft_check_loops(const struct nft_ctx *ctx, const struct nft_set_ext *ext) { const struct nft_data *data; int ret; data = nft_set_ext_data(ext); switch (data->verdict.code) { case NFT_JUMP: case NFT_GOTO: ret = nf_tables_check_loops(ctx, data->verdict.chain); break; default: ret = 0; break; } return ret; } static int nf_tables_loop_check_setelem(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_set_iter *iter, struct nft_elem_priv *elem_priv) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); if (!nft_set_elem_active(ext, iter->genmask)) return 0; if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && *nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END) return 0; return nft_check_loops(ctx, ext); } static int nft_set_catchall_loops(const struct nft_ctx *ctx, struct nft_set *set) { u8 genmask = nft_genmask_next(ctx->net); struct nft_set_elem_catchall *catchall; struct nft_set_ext *ext; int ret = 0; list_for_each_entry_rcu(catchall, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); if (!nft_set_elem_active(ext, genmask)) continue; ret = nft_check_loops(ctx, ext); if (ret < 0) return ret; } return ret; } static int nf_tables_check_loops(const struct nft_ctx *ctx, const struct nft_chain *chain) { const struct nft_rule *rule; const struct nft_expr *expr, *last; struct nft_set *set; struct nft_set_binding *binding; struct nft_set_iter iter; if (ctx->chain == chain) return -ELOOP; if (fatal_signal_pending(current)) return -EINTR; list_for_each_entry(rule, &chain->rules, list) { nft_rule_for_each_expr(expr, last, rule) { struct nft_immediate_expr *priv; const struct nft_data *data; int err; if (strcmp(expr->ops->type->name, "immediate")) continue; priv = nft_expr_priv(expr); if (priv->dreg != NFT_REG_VERDICT) continue; data = &priv->data; switch (data->verdict.code) { case NFT_JUMP: case NFT_GOTO: err = nf_tables_check_loops(ctx, data->verdict.chain); if (err < 0) return err; break; default: break; } } } list_for_each_entry(set, &ctx->table->sets, list) { if (!nft_is_active_next(ctx->net, set)) continue; if (!(set->flags & NFT_SET_MAP) || set->dtype != NFT_DATA_VERDICT) continue; list_for_each_entry(binding, &set->bindings, list) { if (!(binding->flags & NFT_SET_MAP) || binding->chain != chain) continue; iter.genmask = nft_genmask_next(ctx->net); iter.type = NFT_ITER_UPDATE; iter.skip = 0; iter.count = 0; iter.err = 0; iter.fn = nf_tables_loop_check_setelem; set->ops->walk(ctx, set, &iter); if (!iter.err) iter.err = nft_set_catchall_loops(ctx, set); if (iter.err < 0) return iter.err; } } return 0; } /** * nft_parse_u32_check - fetch u32 attribute and check for maximum value * * @attr: netlink attribute to fetch value from * @max: maximum value to be stored in dest * @dest: pointer to the variable * * Parse, check and store a given u32 netlink attribute into variable. * This function returns -ERANGE if the value goes over maximum value. * Otherwise a 0 is returned and the attribute value is stored in the * destination variable. */ int nft_parse_u32_check(const struct nlattr *attr, int max, u32 *dest) { u32 val; val = ntohl(nla_get_be32(attr)); if (val > max) return -ERANGE; *dest = val; return 0; } EXPORT_SYMBOL_GPL(nft_parse_u32_check); static int nft_parse_register(const struct nlattr *attr, u32 *preg) { unsigned int reg; reg = ntohl(nla_get_be32(attr)); switch (reg) { case NFT_REG_VERDICT...NFT_REG_4: *preg = reg * NFT_REG_SIZE / NFT_REG32_SIZE; break; case NFT_REG32_00...NFT_REG32_15: *preg = reg + NFT_REG_SIZE / NFT_REG32_SIZE - NFT_REG32_00; break; default: return -ERANGE; } return 0; } /** * nft_dump_register - dump a register value to a netlink attribute * * @skb: socket buffer * @attr: attribute number * @reg: register number * * Construct a netlink attribute containing the register number. For * compatibility reasons, register numbers being a multiple of 4 are * translated to the corresponding 128 bit register numbers. */ int nft_dump_register(struct sk_buff *skb, unsigned int attr, unsigned int reg) { if (reg % (NFT_REG_SIZE / NFT_REG32_SIZE) == 0) reg = reg / (NFT_REG_SIZE / NFT_REG32_SIZE); else reg = reg - NFT_REG_SIZE / NFT_REG32_SIZE + NFT_REG32_00; return nla_put_be32(skb, attr, htonl(reg)); } EXPORT_SYMBOL_GPL(nft_dump_register); static int nft_validate_register_load(enum nft_registers reg, unsigned int len) { if (reg < NFT_REG_1 * NFT_REG_SIZE / NFT_REG32_SIZE) return -EINVAL; if (len == 0) return -EINVAL; if (reg * NFT_REG32_SIZE + len > sizeof_field(struct nft_regs, data)) return -ERANGE; return 0; } int nft_parse_register_load(const struct nlattr *attr, u8 *sreg, u32 len) { u32 reg; int err; err = nft_parse_register(attr, ®); if (err < 0) return err; err = nft_validate_register_load(reg, len); if (err < 0) return err; *sreg = reg; return 0; } EXPORT_SYMBOL_GPL(nft_parse_register_load); static int nft_validate_register_store(const struct nft_ctx *ctx, enum nft_registers reg, const struct nft_data *data, enum nft_data_types type, unsigned int len) { int err; switch (reg) { case NFT_REG_VERDICT: if (type != NFT_DATA_VERDICT) return -EINVAL; if (data != NULL && (data->verdict.code == NFT_GOTO || data->verdict.code == NFT_JUMP)) { err = nf_tables_check_loops(ctx, data->verdict.chain); if (err < 0) return err; } return 0; default: if (reg < NFT_REG_1 * NFT_REG_SIZE / NFT_REG32_SIZE) return -EINVAL; if (len == 0) return -EINVAL; if (reg * NFT_REG32_SIZE + len > sizeof_field(struct nft_regs, data)) return -ERANGE; if (data != NULL && type != NFT_DATA_VALUE) return -EINVAL; return 0; } } int nft_parse_register_store(const struct nft_ctx *ctx, const struct nlattr *attr, u8 *dreg, const struct nft_data *data, enum nft_data_types type, unsigned int len) { int err; u32 reg; err = nft_parse_register(attr, ®); if (err < 0) return err; err = nft_validate_register_store(ctx, reg, data, type, len); if (err < 0) return err; *dreg = reg; return 0; } EXPORT_SYMBOL_GPL(nft_parse_register_store); static const struct nla_policy nft_verdict_policy[NFTA_VERDICT_MAX + 1] = { [NFTA_VERDICT_CODE] = { .type = NLA_U32 }, [NFTA_VERDICT_CHAIN] = { .type = NLA_STRING, .len = NFT_CHAIN_MAXNAMELEN - 1 }, [NFTA_VERDICT_CHAIN_ID] = { .type = NLA_U32 }, }; static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, struct nft_data_desc *desc, const struct nlattr *nla) { u8 genmask = nft_genmask_next(ctx->net); struct nlattr *tb[NFTA_VERDICT_MAX + 1]; struct nft_chain *chain; int err; err = nla_parse_nested_deprecated(tb, NFTA_VERDICT_MAX, nla, nft_verdict_policy, NULL); if (err < 0) return err; if (!tb[NFTA_VERDICT_CODE]) return -EINVAL; /* zero padding hole for memcmp */ memset(data, 0, sizeof(*data)); data->verdict.code = ntohl(nla_get_be32(tb[NFTA_VERDICT_CODE])); switch (data->verdict.code) { case NF_ACCEPT: case NF_DROP: case NF_QUEUE: break; case NFT_CONTINUE: case NFT_BREAK: case NFT_RETURN: break; case NFT_JUMP: case NFT_GOTO: if (tb[NFTA_VERDICT_CHAIN]) { chain = nft_chain_lookup(ctx->net, ctx->table, tb[NFTA_VERDICT_CHAIN], genmask); } else if (tb[NFTA_VERDICT_CHAIN_ID]) { chain = nft_chain_lookup_byid(ctx->net, ctx->table, tb[NFTA_VERDICT_CHAIN_ID], genmask); if (IS_ERR(chain)) return PTR_ERR(chain); } else { return -EINVAL; } if (IS_ERR(chain)) return PTR_ERR(chain); if (nft_is_base_chain(chain)) return -EOPNOTSUPP; if (nft_chain_is_bound(chain)) return -EINVAL; if (desc->flags & NFT_DATA_DESC_SETELEM && chain->flags & NFT_CHAIN_BINDING) return -EINVAL; if (!nft_use_inc(&chain->use)) return -EMFILE; data->verdict.chain = chain; break; default: return -EINVAL; } desc->len = sizeof(data->verdict); return 0; } static void nft_verdict_uninit(const struct nft_data *data) { struct nft_chain *chain; switch (data->verdict.code) { case NFT_JUMP: case NFT_GOTO: chain = data->verdict.chain; nft_use_dec(&chain->use); break; } } int nft_verdict_dump(struct sk_buff *skb, int type, const struct nft_verdict *v) { struct nlattr *nest; nest = nla_nest_start_noflag(skb, type); if (!nest) goto nla_put_failure; if (nla_put_be32(skb, NFTA_VERDICT_CODE, htonl(v->code))) goto nla_put_failure; switch (v->code) { case NFT_JUMP: case NFT_GOTO: if (nla_put_string(skb, NFTA_VERDICT_CHAIN, v->chain->name)) goto nla_put_failure; } nla_nest_end(skb, nest); return 0; nla_put_failure: return -1; } static int nft_value_init(const struct nft_ctx *ctx, struct nft_data *data, struct nft_data_desc *desc, const struct nlattr *nla) { unsigned int len; len = nla_len(nla); if (len == 0) return -EINVAL; if (len > desc->size) return -EOVERFLOW; if (desc->len) { if (len != desc->len) return -EINVAL; } else { desc->len = len; } nla_memcpy(data->data, nla, len); return 0; } static int nft_value_dump(struct sk_buff *skb, const struct nft_data *data, unsigned int len) { return nla_put(skb, NFTA_DATA_VALUE, len, data->data); } static const struct nla_policy nft_data_policy[NFTA_DATA_MAX + 1] = { [NFTA_DATA_VALUE] = { .type = NLA_BINARY }, [NFTA_DATA_VERDICT] = { .type = NLA_NESTED }, }; /** * nft_data_init - parse nf_tables data netlink attributes * * @ctx: context of the expression using the data * @data: destination struct nft_data * @desc: data description * @nla: netlink attribute containing data * * Parse the netlink data attributes and initialize a struct nft_data. * The type and length of data are returned in the data description. * * The caller can indicate that it only wants to accept data of type * NFT_DATA_VALUE by passing NULL for the ctx argument. */ int nft_data_init(const struct nft_ctx *ctx, struct nft_data *data, struct nft_data_desc *desc, const struct nlattr *nla) { struct nlattr *tb[NFTA_DATA_MAX + 1]; int err; if (WARN_ON_ONCE(!desc->size)) return -EINVAL; err = nla_parse_nested_deprecated(tb, NFTA_DATA_MAX, nla, nft_data_policy, NULL); if (err < 0) return err; if (tb[NFTA_DATA_VALUE]) { if (desc->type != NFT_DATA_VALUE) return -EINVAL; err = nft_value_init(ctx, data, desc, tb[NFTA_DATA_VALUE]); } else if (tb[NFTA_DATA_VERDICT] && ctx != NULL) { if (desc->type != NFT_DATA_VERDICT) return -EINVAL; err = nft_verdict_init(ctx, data, desc, tb[NFTA_DATA_VERDICT]); } else { err = -EINVAL; } return err; } EXPORT_SYMBOL_GPL(nft_data_init); /** * nft_data_release - release a nft_data item * * @data: struct nft_data to release * @type: type of data * * Release a nft_data item. NFT_DATA_VALUE types can be silently discarded, * all others need to be released by calling this function. */ void nft_data_release(const struct nft_data *data, enum nft_data_types type) { if (type < NFT_DATA_VERDICT) return; switch (type) { case NFT_DATA_VERDICT: return nft_verdict_uninit(data); default: WARN_ON(1); } } EXPORT_SYMBOL_GPL(nft_data_release); int nft_data_dump(struct sk_buff *skb, int attr, const struct nft_data *data, enum nft_data_types type, unsigned int len) { struct nlattr *nest; int err; nest = nla_nest_start_noflag(skb, attr); if (nest == NULL) return -1; switch (type) { case NFT_DATA_VALUE: err = nft_value_dump(skb, data, len); break; case NFT_DATA_VERDICT: err = nft_verdict_dump(skb, NFTA_DATA_VERDICT, &data->verdict); break; default: err = -EINVAL; WARN_ON(1); } nla_nest_end(skb, nest); return err; } EXPORT_SYMBOL_GPL(nft_data_dump); int __nft_release_basechain(struct nft_ctx *ctx) { struct nft_rule *rule, *nr; if (WARN_ON(!nft_is_base_chain(ctx->chain))) return 0; nf_tables_unregister_hook(ctx->net, ctx->chain->table, ctx->chain); list_for_each_entry_safe(rule, nr, &ctx->chain->rules, list) { list_del(&rule->list); nft_use_dec(&ctx->chain->use); nf_tables_rule_release(ctx, rule); } nft_chain_del(ctx->chain); nft_use_dec(&ctx->table->use); nf_tables_chain_destroy(ctx); return 0; } EXPORT_SYMBOL_GPL(__nft_release_basechain); static void __nft_release_hook(struct net *net, struct nft_table *table) { struct nft_flowtable *flowtable; struct nft_chain *chain; list_for_each_entry(chain, &table->chains, list) __nf_tables_unregister_hook(net, table, chain, true); list_for_each_entry(flowtable, &table->flowtables, list) __nft_unregister_flowtable_net_hooks(net, &flowtable->hook_list, true); } static void __nft_release_hooks(struct net *net) { struct nftables_pernet *nft_net = nft_pernet(net); struct nft_table *table; list_for_each_entry(table, &nft_net->tables, list) { if (nft_table_has_owner(table)) continue; __nft_release_hook(net, table); } } static void __nft_release_table(struct net *net, struct nft_table *table) { struct nft_flowtable *flowtable, *nf; struct nft_chain *chain, *nc; struct nft_object *obj, *ne; struct nft_rule *rule, *nr; struct nft_set *set, *ns; struct nft_ctx ctx = { .net = net, .family = NFPROTO_NETDEV, }; ctx.family = table->family; ctx.table = table; list_for_each_entry(chain, &table->chains, list) { if (nft_chain_binding(chain)) continue; ctx.chain = chain; list_for_each_entry_safe(rule, nr, &chain->rules, list) { list_del(&rule->list); nft_use_dec(&chain->use); nf_tables_rule_release(&ctx, rule); } } list_for_each_entry_safe(flowtable, nf, &table->flowtables, list) { list_del(&flowtable->list); nft_use_dec(&table->use); nf_tables_flowtable_destroy(flowtable); } list_for_each_entry_safe(set, ns, &table->sets, list) { list_del(&set->list); nft_use_dec(&table->use); if (set->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) nft_map_deactivate(&ctx, set); nft_set_destroy(&ctx, set); } list_for_each_entry_safe(obj, ne, &table->objects, list) { nft_obj_del(obj); nft_use_dec(&table->use); nft_obj_destroy(&ctx, obj); } list_for_each_entry_safe(chain, nc, &table->chains, list) { ctx.chain = chain; nft_chain_del(chain); nft_use_dec(&table->use); nf_tables_chain_destroy(&ctx); } nf_tables_table_destroy(&ctx); } static void __nft_release_tables(struct net *net) { struct nftables_pernet *nft_net = nft_pernet(net); struct nft_table *table, *nt; list_for_each_entry_safe(table, nt, &nft_net->tables, list) { if (nft_table_has_owner(table)) continue; list_del(&table->list); __nft_release_table(net, table); } } static int nft_rcv_nl_event(struct notifier_block *this, unsigned long event, void *ptr) { struct nft_table *table, *to_delete[8]; struct nftables_pernet *nft_net; struct netlink_notify *n = ptr; struct net *net = n->net; unsigned int deleted; bool restart = false; unsigned int gc_seq; if (event != NETLINK_URELEASE || n->protocol != NETLINK_NETFILTER) return NOTIFY_DONE; nft_net = nft_pernet(net); deleted = 0; mutex_lock(&nft_net->commit_mutex); gc_seq = nft_gc_seq_begin(nft_net); if (!list_empty(&nf_tables_destroy_list)) nf_tables_trans_destroy_flush_work(); again: list_for_each_entry(table, &nft_net->tables, list) { if (nft_table_has_owner(table) && n->portid == table->nlpid) { if (table->flags & NFT_TABLE_F_PERSIST) { table->flags &= ~NFT_TABLE_F_OWNER; continue; } __nft_release_hook(net, table); list_del_rcu(&table->list); to_delete[deleted++] = table; if (deleted >= ARRAY_SIZE(to_delete)) break; } } if (deleted) { restart = deleted >= ARRAY_SIZE(to_delete); synchronize_rcu(); while (deleted) __nft_release_table(net, to_delete[--deleted]); if (restart) goto again; } nft_gc_seq_end(nft_net, gc_seq); mutex_unlock(&nft_net->commit_mutex); return NOTIFY_DONE; } static struct notifier_block nft_nl_notifier = { .notifier_call = nft_rcv_nl_event, }; static int __net_init nf_tables_init_net(struct net *net) { struct nftables_pernet *nft_net = nft_pernet(net); INIT_LIST_HEAD(&nft_net->tables); INIT_LIST_HEAD(&nft_net->commit_list); INIT_LIST_HEAD(&nft_net->binding_list); INIT_LIST_HEAD(&nft_net->module_list); INIT_LIST_HEAD(&nft_net->notify_list); mutex_init(&nft_net->commit_mutex); nft_net->base_seq = 1; nft_net->gc_seq = 0; nft_net->validate_state = NFT_VALIDATE_SKIP; return 0; } static void __net_exit nf_tables_pre_exit_net(struct net *net) { struct nftables_pernet *nft_net = nft_pernet(net); mutex_lock(&nft_net->commit_mutex); __nft_release_hooks(net); mutex_unlock(&nft_net->commit_mutex); } static void __net_exit nf_tables_exit_net(struct net *net) { struct nftables_pernet *nft_net = nft_pernet(net); unsigned int gc_seq; mutex_lock(&nft_net->commit_mutex); gc_seq = nft_gc_seq_begin(nft_net); WARN_ON_ONCE(!list_empty(&nft_net->commit_list)); if (!list_empty(&nft_net->module_list)) nf_tables_module_autoload_cleanup(net); __nft_release_tables(net); nft_gc_seq_end(nft_net, gc_seq); mutex_unlock(&nft_net->commit_mutex); WARN_ON_ONCE(!list_empty(&nft_net->tables)); WARN_ON_ONCE(!list_empty(&nft_net->module_list)); WARN_ON_ONCE(!list_empty(&nft_net->notify_list)); } static void nf_tables_exit_batch(struct list_head *net_exit_list) { flush_work(&trans_gc_work); } static struct pernet_operations nf_tables_net_ops = { .init = nf_tables_init_net, .pre_exit = nf_tables_pre_exit_net, .exit = nf_tables_exit_net, .exit_batch = nf_tables_exit_batch, .id = &nf_tables_net_id, .size = sizeof(struct nftables_pernet), }; static int __init nf_tables_module_init(void) { int err; err = register_pernet_subsys(&nf_tables_net_ops); if (err < 0) return err; err = nft_chain_filter_init(); if (err < 0) goto err_chain_filter; err = nf_tables_core_module_init(); if (err < 0) goto err_core_module; err = register_netdevice_notifier(&nf_tables_flowtable_notifier); if (err < 0) goto err_netdev_notifier; err = rhltable_init(&nft_objname_ht, &nft_objname_ht_params); if (err < 0) goto err_rht_objname; err = nft_offload_init(); if (err < 0) goto err_offload; err = netlink_register_notifier(&nft_nl_notifier); if (err < 0) goto err_netlink_notifier; /* must be last */ err = nfnetlink_subsys_register(&nf_tables_subsys); if (err < 0) goto err_nfnl_subsys; nft_chain_route_init(); return err; err_nfnl_subsys: netlink_unregister_notifier(&nft_nl_notifier); err_netlink_notifier: nft_offload_exit(); err_offload: rhltable_destroy(&nft_objname_ht); err_rht_objname: unregister_netdevice_notifier(&nf_tables_flowtable_notifier); err_netdev_notifier: nf_tables_core_module_exit(); err_core_module: nft_chain_filter_fini(); err_chain_filter: unregister_pernet_subsys(&nf_tables_net_ops); return err; } static void __exit nf_tables_module_exit(void) { nfnetlink_subsys_unregister(&nf_tables_subsys); netlink_unregister_notifier(&nft_nl_notifier); nft_offload_exit(); unregister_netdevice_notifier(&nf_tables_flowtable_notifier); nft_chain_filter_fini(); nft_chain_route_fini(); nf_tables_trans_destroy_flush_work(); unregister_pernet_subsys(&nf_tables_net_ops); cancel_work_sync(&trans_gc_work); cancel_work_sync(&trans_destroy_work); rcu_barrier(); rhltable_destroy(&nft_objname_ht); nf_tables_core_module_exit(); } module_init(nf_tables_module_init); module_exit(nf_tables_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); MODULE_DESCRIPTION("Framework for packet filtering and classification"); MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_NFTABLES);
Information contained on this website is for historical information purposes only and does not indicate or represent copyright ownership.
Created with Cregit http://github.com/cregit/cregit
Version 2.0-RC1