| Author | Tokens | Token Proportion | Commits | Commit Proportion |
|---|---|---|---|---|
| David S. Miller | 4807 | 26.16% | 95 | 14.09% |
| Linus Torvalds (pre-git) | 1952 | 10.62% | 66 | 9.79% |
| David Ahern | 1364 | 7.42% | 52 | 7.72% |
| Eric Dumazet | 1204 | 6.55% | 67 | 9.94% |
| Ido Schimmel | 948 | 5.16% | 13 | 1.93% |
| Roopa Prabhu | 629 | 3.42% | 7 | 1.04% |
| Julian Anastasov | 555 | 3.02% | 14 | 2.08% |
| Stephen Suryaputra | 531 | 2.89% | 5 | 0.74% |
| lkml@einar-lueck.de | 492 | 2.68% | 1 | 0.15% |
| Timo Teräs | 383 | 2.08% | 5 | 0.74% |
| Stefano Brivio | 377 | 2.05% | 4 | 0.59% |
| Denis V. Lunev | 376 | 2.05% | 20 | 2.97% |
| Nikolay Aleksandrov | 341 | 1.86% | 2 | 0.30% |
| Jakub Kiciński | 333 | 1.81% | 2 | 0.30% |
| Steffen Klassert | 314 | 1.71% | 13 | 1.93% |
| Thomas Graf | 258 | 1.40% | 9 | 1.34% |
| Paolo Abeni | 220 | 1.20% | 5 | 0.74% |
| Menglong Dong | 209 | 1.14% | 9 | 1.34% |
| Lorenzo Colitti | 164 | 0.89% | 6 | 0.89% |
| Rusty Russell | 162 | 0.88% | 3 | 0.45% |
| xu xin | 157 | 0.85% | 3 | 0.45% |
| Linus Torvalds | 156 | 0.85% | 5 | 0.74% |
| Peter Christensen | 149 | 0.81% | 2 | 0.30% |
| Pavel Emelyanov | 147 | 0.80% | 10 | 1.48% |
| Arnaldo Carvalho de Melo | 139 | 0.76% | 8 | 1.19% |
| Xin Long | 103 | 0.56% | 6 | 0.89% |
| Sabrina Dubroca | 96 | 0.52% | 3 | 0.45% |
| Stephen Hemminger | 88 | 0.48% | 7 | 1.04% |
| Guillaume Nault | 86 | 0.47% | 15 | 2.23% |
| Vladimir Vdovin | 80 | 0.44% | 1 | 0.15% |
| Nicolas Dichtel | 72 | 0.39% | 3 | 0.45% |
| Alexey Kuznetsov | 69 | 0.38% | 8 | 1.19% |
| Wei Wang | 65 | 0.35% | 7 | 1.04% |
| Hideaki Yoshifuji / 吉藤英明 | 53 | 0.29% | 7 | 1.04% |
| Kuniyuki Iwashima | 50 | 0.27% | 5 | 0.74% |
| Alexey Dobriyan | 49 | 0.27% | 5 | 0.74% |
| Eric W. Biedermann | 48 | 0.26% | 11 | 1.63% |
| Hannes Frederic Sowa | 45 | 0.24% | 4 | 0.59% |
| Zhengchao Shao | 43 | 0.23% | 1 | 0.15% |
| Robert Olsson | 38 | 0.21% | 4 | 0.59% |
| Eyal Birger | 36 | 0.20% | 2 | 0.30% |
| Al Viro | 35 | 0.19% | 7 | 1.04% |
| Gao Feng | 33 | 0.18% | 3 | 0.45% |
| Neil Horman | 30 | 0.16% | 2 | 0.30% |
| Duan Jiong | 29 | 0.16% | 2 | 0.30% |
| Joe Perches | 28 | 0.15% | 7 | 1.04% |
| Oliver Herms | 28 | 0.15% | 1 | 0.15% |
| Chris Friesen | 27 | 0.15% | 1 | 0.15% |
| Herbert Xu | 25 | 0.14% | 8 | 1.19% |
| Kyle Zeng | 24 | 0.13% | 1 | 0.15% |
| Stephen Suryaputra Lin | 23 | 0.13% | 1 | 0.15% |
| Christian Brauner | 23 | 0.13% | 1 | 0.15% |
| wenxu | 22 | 0.12% | 1 | 0.15% |
| Maciej Żenczykowski | 21 | 0.11% | 4 | 0.59% |
| Patrick McHardy | 21 | 0.11% | 3 | 0.45% |
| Johannes Berg | 20 | 0.11% | 3 | 0.45% |
| Shmulik Ladkani | 20 | 0.11% | 1 | 0.15% |
| John Fastabend | 19 | 0.10% | 1 | 0.15% |
| Petr Machata | 18 | 0.10% | 1 | 0.15% |
| Michal Kubeček | 17 | 0.09% | 1 | 0.15% |
| elueck@de.ibm.com | 16 | 0.09% | 1 | 0.15% |
| Roland Dreier | 15 | 0.08% | 1 | 0.15% |
| Joel Granados | 15 | 0.08% | 3 | 0.45% |
| Hangbin Liu | 14 | 0.08% | 3 | 0.45% |
| Daniel Borkmann | 14 | 0.08% | 1 | 0.15% |
| Alexei Starovoitov | 14 | 0.08% | 1 | 0.15% |
| Brian Vazquez | 14 | 0.08% | 3 | 0.45% |
| Adrian Bunk | 14 | 0.08% | 3 | 0.45% |
| Florian Larysch | 13 | 0.07% | 1 | 0.15% |
| Miaohe Lin | 13 | 0.07% | 2 | 0.30% |
| Jiri Benc | 13 | 0.07% | 4 | 0.59% |
| Wangyang Guo | 13 | 0.07% | 1 | 0.15% |
| Harald Welte | 13 | 0.07% | 1 | 0.15% |
| OGAWA Hirofumi | 12 | 0.07% | 1 | 0.15% |
| Martin KaFai Lau | 12 | 0.07% | 1 | 0.15% |
| Benjamin Poirier | 11 | 0.06% | 1 | 0.15% |
| Lorenzo Bianconi | 11 | 0.06% | 1 | 0.15% |
| Ian Morris | 10 | 0.05% | 1 | 0.15% |
| Andy Gospodarek | 10 | 0.05% | 1 | 0.15% |
| Ravikiran G. Thirumalai | 10 | 0.05% | 1 | 0.15% |
| Edward Chron | 9 | 0.05% | 1 | 0.15% |
| Dipankar Sarma | 9 | 0.05% | 1 | 0.15% |
| Florian Westphal | 8 | 0.04% | 1 | 0.15% |
| Ingo Molnar | 8 | 0.04% | 2 | 0.30% |
| David L Stevens | 8 | 0.04% | 1 | 0.15% |
| Robert Shearman | 8 | 0.04% | 2 | 0.30% |
| Nikola Forró | 7 | 0.04% | 1 | 0.15% |
| Shubhankar Kuranagatti | 7 | 0.04% | 2 | 0.30% |
| Benjamin Thery | 7 | 0.04% | 1 | 0.15% |
| Li Wei | 6 | 0.03% | 1 | 0.15% |
| Jason A. Donenfeld | 6 | 0.03% | 4 | 0.59% |
| Andy Walls | 6 | 0.03% | 1 | 0.15% |
| Andrew Lunn | 6 | 0.03% | 1 | 0.15% |
| Vasily Averin | 6 | 0.03% | 1 | 0.15% |
| James Chapman | 6 | 0.03% | 1 | 0.15% |
| Amit Cohen | 6 | 0.03% | 1 | 0.15% |
| Joel Sing | 6 | 0.03% | 1 | 0.15% |
| Yajun Deng | 5 | 0.03% | 1 | 0.15% |
| Octavian Purdila | 5 | 0.03% | 1 | 0.15% |
| Chris Elston | 5 | 0.03% | 1 | 0.15% |
| Jinyu Qi | 5 | 0.03% | 1 | 0.15% |
| Arnd Bergmann | 5 | 0.03% | 1 | 0.15% |
| Lokesh Dhoundiyal | 5 | 0.03% | 1 | 0.15% |
| Tom Herbert | 5 | 0.03% | 2 | 0.30% |
| Andi Kleen | 5 | 0.03% | 1 | 0.15% |
| Amir Vadai | 5 | 0.03% | 1 | 0.15% |
| Fan Du | 5 | 0.03% | 1 | 0.15% |
| Nicolas Cavallari | 5 | 0.03% | 1 | 0.15% |
| Kunwu Chan | 5 | 0.03% | 2 | 0.30% |
| Harvey Harrison | 5 | 0.03% | 1 | 0.15% |
| Alan Cox | 5 | 0.03% | 1 | 0.15% |
| Américo Wang | 5 | 0.03% | 2 | 0.30% |
| Li Yewang | 4 | 0.02% | 1 | 0.15% |
| Edward Cree | 4 | 0.02% | 1 | 0.15% |
| Matteo Croce | 4 | 0.02% | 1 | 0.15% |
| Yejune Deng | 4 | 0.02% | 1 | 0.15% |
| Mitsuru Chinen | 4 | 0.02% | 1 | 0.15% |
| Alexander Duyck | 4 | 0.02% | 1 | 0.15% |
| Sriram Yagnaraman | 3 | 0.02% | 1 | 0.15% |
| Antoine Tenart | 3 | 0.02% | 1 | 0.15% |
| Held Bernhard | 3 | 0.02% | 1 | 0.15% |
| Kees Cook | 3 | 0.02% | 2 | 0.30% |
| Dave Jones | 3 | 0.02% | 1 | 0.15% |
| Tom Tucker | 3 | 0.02% | 1 | 0.15% |
| Christoph Lameter | 3 | 0.02% | 2 | 0.30% |
| Jesper Dangaard Brouer | 3 | 0.02% | 1 | 0.15% |
| Li RongQing | 2 | 0.01% | 1 | 0.15% |
| Christoph Hellwig | 2 | 0.01% | 1 | 0.15% |
| Vadim Fedorenko | 2 | 0.01% | 1 | 0.15% |
| Michael Smith | 2 | 0.01% | 1 | 0.15% |
| Vincent Bernat | 2 | 0.01% | 1 | 0.15% |
| Philippe De Muyter | 1 | 0.01% | 1 | 0.15% |
| Changli Gao | 1 | 0.01% | 1 | 0.15% |
| Tejun Heo | 1 | 0.01% | 1 | 0.15% |
| Hiroaki SHIMODA | 1 | 0.01% | 1 | 0.15% |
| Thomas Gleixner | 1 | 0.01% | 1 | 0.15% |
| Daniel Lezcano | 1 | 0.01% | 1 | 0.15% |
| Gerrit Renker | 1 | 0.01% | 1 | 0.15% |
| Tim Hansen | 1 | 0.01% | 1 | 0.15% |
| Julian Wiedmann | 1 | 0.01% | 1 | 0.15% |
| Jamal Hadi Salim | 1 | 0.01% | 1 | 0.15% |
| Jianpeng Ma | 1 | 0.01% | 1 | 0.15% |
| Dan Siemon | 1 | 0.01% | 1 | 0.15% |
| Thomas Weißschuh | 1 | 0.01% | 1 | 0.15% |
| Jan Engelhardt | 1 | 0.01% | 1 | 0.15% |
| Mahesh Bandewar | 1 | 0.01% | 1 | 0.15% |
| Mark Rutland | 1 | 0.01% | 1 | 0.15% |
| Total | 18376 | 674 |
123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773774775776777778779780781782783784785786787788789790791792793794795796797798799800801802803804805806807808809810811812813814815816817818819820821822823824825826827828829830831832833834835836837838839840841842843844845846847848849850851852853854855856857858859860861862863864865866867868869870871872873874875876877878879880881882883884885886887888889890891892893894895896897898899900901902903904905906907908909910911912913914915916917918919920921922923924925926927928929930931932933934935936937938939940941942943944945946947948949950951952953954955956957958959960961962963964965966967968969970971972973974975976977978979980981982983984985986987988989990991992993994995996997998999100010011002100310041005100610071008100910101011101210131014101510161017101810191020102110221023102410251026102710281029103010311032103310341035103610371038103910401041104210431044104510461047104810491050105110521053105410551056105710581059106010611062106310641065106610671068106910701071107210731074107510761077107810791080108110821083108410851086108710881089109010911092109310941095109610971098109911001101110211031104110511061107110811091110111111121113111411151116111711181119112011211122112311241125112611271128112911301131113211331134113511361137113811391140114111421143114411451146114711481149115011511152115311541155115611571158115911601161116211631164116511661167116811691170117111721173117411751176117711781179118011811182118311841185118611871188118911901191119211931194119511961197119811991200120112021203120412051206120712081209121012111212121312141215121612171218121912201221122212231224122512261227122812291230123112321233123412351236123712381239124012411242124312441245124612471248124912501251125212531254125512561257125812591260126112621263126412651266126712681269127012711272127312741275127612771278127912801281128212831284128512861287128812891290129112921293129412951296129712981299130013011302130313041305130613071308130913101311131213131314131513161317131813191320132113221323132413251326132713281329133013311332133313341335133613371338133913401341134213431344134513461347134813491350135113521353135413551356135713581359136013611362136313641365136613671368136913701371137213731374137513761377137813791380138113821383138413851386138713881389139013911392139313941395139613971398139914001401140214031404140514061407140814091410141114121413141414151416141714181419142014211422142314241425142614271428142914301431143214331434143514361437143814391440144114421443144414451446144714481449145014511452145314541455145614571458145914601461146214631464146514661467146814691470147114721473147414751476147714781479148014811482148314841485148614871488148914901491149214931494149514961497149814991500150115021503150415051506150715081509151015111512151315141515151615171518151915201521152215231524152515261527152815291530153115321533153415351536153715381539154015411542154315441545154615471548154915501551155215531554155515561557155815591560156115621563156415651566156715681569157015711572157315741575157615771578157915801581158215831584158515861587158815891590159115921593159415951596159715981599160016011602160316041605160616071608160916101611161216131614161516161617161816191620162116221623162416251626162716281629163016311632163316341635163616371638163916401641164216431644164516461647164816491650165116521653165416551656165716581659166016611662166316641665166616671668166916701671167216731674167516761677167816791680168116821683168416851686168716881689169016911692169316941695169616971698169917001701170217031704170517061707170817091710171117121713171417151716171717181719172017211722172317241725172617271728172917301731173217331734173517361737173817391740174117421743174417451746174717481749175017511752175317541755175617571758175917601761176217631764176517661767176817691770177117721773177417751776177717781779178017811782178317841785178617871788178917901791179217931794179517961797179817991800180118021803180418051806180718081809181018111812181318141815181618171818181918201821182218231824182518261827182818291830183118321833183418351836183718381839184018411842184318441845184618471848184918501851185218531854185518561857185818591860186118621863186418651866186718681869187018711872187318741875187618771878187918801881188218831884188518861887188818891890189118921893189418951896189718981899190019011902190319041905190619071908190919101911191219131914191519161917191819191920192119221923192419251926192719281929193019311932193319341935193619371938193919401941194219431944194519461947194819491950195119521953195419551956195719581959196019611962196319641965196619671968196919701971197219731974197519761977197819791980198119821983198419851986198719881989199019911992199319941995199619971998199920002001200220032004200520062007200820092010201120122013201420152016201720182019202020212022202320242025202620272028202920302031203220332034203520362037203820392040204120422043204420452046204720482049205020512052205320542055205620572058205920602061206220632064206520662067206820692070207120722073207420752076207720782079208020812082208320842085208620872088208920902091209220932094209520962097209820992100210121022103210421052106210721082109211021112112211321142115211621172118211921202121212221232124212521262127212821292130213121322133213421352136213721382139214021412142214321442145214621472148214921502151215221532154215521562157215821592160216121622163216421652166216721682169217021712172217321742175217621772178217921802181218221832184218521862187218821892190219121922193219421952196219721982199220022012202220322042205220622072208220922102211221222132214221522162217221822192220222122222223222422252226222722282229223022312232223322342235223622372238223922402241224222432244224522462247224822492250225122522253225422552256225722582259226022612262226322642265226622672268226922702271227222732274227522762277227822792280228122822283228422852286228722882289229022912292229322942295229622972298229923002301230223032304230523062307230823092310231123122313231423152316231723182319232023212322232323242325232623272328232923302331233223332334233523362337233823392340234123422343234423452346234723482349235023512352235323542355235623572358235923602361236223632364236523662367236823692370237123722373237423752376237723782379238023812382238323842385238623872388238923902391239223932394239523962397239823992400240124022403240424052406240724082409241024112412241324142415241624172418241924202421242224232424242524262427242824292430243124322433243424352436243724382439244024412442244324442445244624472448244924502451245224532454245524562457245824592460246124622463246424652466246724682469247024712472247324742475247624772478247924802481248224832484248524862487248824892490249124922493249424952496249724982499250025012502250325042505250625072508250925102511251225132514251525162517251825192520252125222523252425252526252725282529253025312532253325342535253625372538253925402541254225432544254525462547254825492550255125522553255425552556255725582559256025612562256325642565256625672568256925702571257225732574257525762577257825792580258125822583258425852586258725882589259025912592259325942595259625972598259926002601260226032604260526062607260826092610261126122613261426152616261726182619262026212622262326242625262626272628262926302631263226332634263526362637263826392640264126422643264426452646264726482649265026512652265326542655265626572658265926602661266226632664266526662667266826692670267126722673267426752676267726782679268026812682268326842685268626872688268926902691269226932694269526962697269826992700270127022703270427052706270727082709271027112712271327142715271627172718271927202721272227232724272527262727272827292730273127322733273427352736273727382739274027412742274327442745274627472748274927502751275227532754275527562757275827592760276127622763276427652766276727682769277027712772277327742775277627772778277927802781278227832784278527862787278827892790279127922793279427952796279727982799280028012802280328042805280628072808280928102811281228132814281528162817281828192820282128222823282428252826282728282829283028312832283328342835283628372838283928402841284228432844284528462847284828492850285128522853285428552856285728582859286028612862286328642865286628672868286928702871287228732874287528762877287828792880288128822883288428852886288728882889289028912892289328942895289628972898289929002901290229032904290529062907290829092910291129122913291429152916291729182919292029212922292329242925292629272928292929302931293229332934293529362937293829392940294129422943294429452946294729482949295029512952295329542955295629572958295929602961296229632964296529662967296829692970297129722973297429752976297729782979298029812982298329842985298629872988298929902991299229932994299529962997299829993000300130023003300430053006300730083009301030113012301330143015301630173018301930203021302230233024302530263027302830293030303130323033303430353036303730383039304030413042304330443045304630473048304930503051305230533054305530563057305830593060306130623063306430653066306730683069307030713072307330743075307630773078307930803081308230833084308530863087308830893090309130923093309430953096309730983099310031013102310331043105310631073108310931103111311231133114311531163117311831193120312131223123312431253126312731283129313031313132313331343135313631373138313931403141314231433144314531463147314831493150315131523153315431553156315731583159316031613162316331643165316631673168316931703171317231733174317531763177317831793180318131823183318431853186318731883189319031913192319331943195319631973198319932003201320232033204320532063207320832093210321132123213321432153216321732183219322032213222322332243225322632273228322932303231323232333234323532363237323832393240324132423243324432453246324732483249325032513252325332543255325632573258325932603261326232633264326532663267326832693270327132723273327432753276327732783279328032813282328332843285328632873288328932903291329232933294329532963297329832993300330133023303330433053306330733083309331033113312331333143315331633173318331933203321332233233324332533263327332833293330333133323333333433353336333733383339334033413342334333443345334633473348334933503351335233533354335533563357335833593360336133623363336433653366336733683369337033713372337333743375337633773378337933803381338233833384338533863387338833893390339133923393339433953396339733983399340034013402340334043405340634073408340934103411341234133414341534163417341834193420342134223423342434253426342734283429343034313432343334343435343634373438343934403441344234433444344534463447344834493450345134523453345434553456345734583459346034613462346334643465346634673468346934703471347234733474347534763477347834793480348134823483348434853486348734883489349034913492349334943495349634973498349935003501350235033504350535063507350835093510351135123513351435153516351735183519352035213522352335243525352635273528352935303531353235333534353535363537353835393540354135423543354435453546354735483549355035513552355335543555355635573558355935603561356235633564356535663567356835693570357135723573357435753576357735783579358035813582358335843585358635873588358935903591359235933594359535963597359835993600360136023603360436053606360736083609361036113612361336143615361636173618361936203621362236233624362536263627362836293630363136323633363436353636363736383639364036413642364336443645364636473648364936503651365236533654365536563657365836593660366136623663366436653666366736683669367036713672367336743675367636773678367936803681368236833684368536863687368836893690369136923693369436953696369736983699370037013702370337043705370637073708370937103711371237133714371537163717371837193720372137223723372437253726372737283729373037313732373337343735373637373738373937403741374237433744374537463747374837493750375137523753375437553756375737583759376037613762376337643765
// SPDX-License-Identifier: GPL-2.0-or-later /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * ROUTE - implementation of the IP router. * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Alan Cox, <gw4pts@gw4pts.ampr.org> * Linus Torvalds, <Linus.Torvalds@helsinki.fi> * Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * * Fixes: * Alan Cox : Verify area fixes. * Alan Cox : cli() protects routing changes * Rui Oliveira : ICMP routing table updates * (rco@di.uminho.pt) Routing table insertion and update * Linus Torvalds : Rewrote bits to be sensible * Alan Cox : Added BSD route gw semantics * Alan Cox : Super /proc >4K * Alan Cox : MTU in route table * Alan Cox : MSS actually. Also added the window * clamper. * Sam Lantinga : Fixed route matching in rt_del() * Alan Cox : Routing cache support. * Alan Cox : Removed compatibility cruft. * Alan Cox : RTF_REJECT support. * Alan Cox : TCP irtt support. * Jonathan Naylor : Added Metric support. * Miquel van Smoorenburg : BSD API fixes. * Miquel van Smoorenburg : Metrics. * Alan Cox : Use __u32 properly * Alan Cox : Aligned routing errors more closely with BSD * our system is still very different. * Alan Cox : Faster /proc handling * Alexey Kuznetsov : Massive rework to support tree based routing, * routing caches and better behaviour. * * Olaf Erb : irtt wasn't being copied right. * Bjorn Ekwall : Kerneld route support. * Alan Cox : Multicast fixed (I hope) * Pavel Krauz : Limited broadcast fixed * Mike McLagan : Routing by source * Alexey Kuznetsov : End of old history. Split to fib.c and * route.c and rewritten from scratch. * Andi Kleen : Load-limit warning messages. * Vitaly E. Lavrov : Transparent proxy revived after year coma. * Vitaly E. Lavrov : Race condition in ip_route_input_slow. * Tobias Ringstrom : Uninitialized res.type in ip_route_output_slow. * Vladimir V. Ivanov : IP rule info (flowid) is really useful. * Marc Boucher : routing by fwmark * Robert Olsson : Added rt_cache statistics * Arnaldo C. Melo : Convert proc stuff to seq_file * Eric Dumazet : hashed spinlocks and rt_check_expire() fixes. * Ilia Sotnikov : Ignore TOS on PMTUD and Redirect * Ilia Sotnikov : Removed TOS from hash calculations */ #define pr_fmt(fmt) "IPv4: " fmt #include <linux/module.h> #include <linux/bitops.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/memblock.h> #include <linux/socket.h> #include <linux/errno.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/proc_fs.h> #include <linux/init.h> #include <linux/skbuff.h> #include <linux/inetdevice.h> #include <linux/igmp.h> #include <linux/pkt_sched.h> #include <linux/mroute.h> #include <linux/netfilter_ipv4.h> #include <linux/random.h> #include <linux/rcupdate.h> #include <linux/slab.h> #include <linux/jhash.h> #include <net/dst.h> #include <net/dst_metadata.h> #include <net/inet_dscp.h> #include <net/net_namespace.h> #include <net/ip.h> #include <net/route.h> #include <net/inetpeer.h> #include <net/sock.h> #include <net/ip_fib.h> #include <net/nexthop.h> #include <net/tcp.h> #include <net/icmp.h> #include <net/xfrm.h> #include <net/lwtunnel.h> #include <net/netevent.h> #include <net/rtnetlink.h> #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif #include <net/secure_seq.h> #include <net/ip_tunnels.h> #include "fib_lookup.h" #define RT_GC_TIMEOUT (300*HZ) #define DEFAULT_MIN_PMTU (512 + 20 + 20) #define DEFAULT_MTU_EXPIRES (10 * 60 * HZ) #define DEFAULT_MIN_ADVMSS 256 static int ip_rt_max_size; static int ip_rt_redirect_number __read_mostly = 9; static int ip_rt_redirect_load __read_mostly = HZ / 50; static int ip_rt_redirect_silence __read_mostly = ((HZ / 50) << (9 + 1)); static int ip_rt_error_cost __read_mostly = HZ; static int ip_rt_error_burst __read_mostly = 5 * HZ; static int ip_rt_gc_timeout __read_mostly = RT_GC_TIMEOUT; /* * Interface to generic destination cache. */ INDIRECT_CALLABLE_SCOPE struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie); static unsigned int ipv4_default_advmss(const struct dst_entry *dst); INDIRECT_CALLABLE_SCOPE unsigned int ipv4_mtu(const struct dst_entry *dst); static void ipv4_negative_advice(struct sock *sk, struct dst_entry *dst); static void ipv4_link_failure(struct sk_buff *skb); static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, bool confirm_neigh); static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb); static void ipv4_dst_destroy(struct dst_entry *dst); static u32 *ipv4_cow_metrics(struct dst_entry *dst, unsigned long old) { WARN_ON(1); return NULL; } static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, struct sk_buff *skb, const void *daddr); static void ipv4_confirm_neigh(const struct dst_entry *dst, const void *daddr); static struct dst_ops ipv4_dst_ops = { .family = AF_INET, .check = ipv4_dst_check, .default_advmss = ipv4_default_advmss, .mtu = ipv4_mtu, .cow_metrics = ipv4_cow_metrics, .destroy = ipv4_dst_destroy, .negative_advice = ipv4_negative_advice, .link_failure = ipv4_link_failure, .update_pmtu = ip_rt_update_pmtu, .redirect = ip_do_redirect, .local_out = __ip_local_out, .neigh_lookup = ipv4_neigh_lookup, .confirm_neigh = ipv4_confirm_neigh, }; #define ECN_OR_COST(class) TC_PRIO_##class const __u8 ip_tos2prio[16] = { TC_PRIO_BESTEFFORT, ECN_OR_COST(BESTEFFORT), TC_PRIO_BESTEFFORT, ECN_OR_COST(BESTEFFORT), TC_PRIO_BULK, ECN_OR_COST(BULK), TC_PRIO_BULK, ECN_OR_COST(BULK), TC_PRIO_INTERACTIVE, ECN_OR_COST(INTERACTIVE), TC_PRIO_INTERACTIVE, ECN_OR_COST(INTERACTIVE), TC_PRIO_INTERACTIVE_BULK, ECN_OR_COST(INTERACTIVE_BULK), TC_PRIO_INTERACTIVE_BULK, ECN_OR_COST(INTERACTIVE_BULK) }; EXPORT_SYMBOL(ip_tos2prio); static DEFINE_PER_CPU(struct rt_cache_stat, rt_cache_stat); #define RT_CACHE_STAT_INC(field) raw_cpu_inc(rt_cache_stat.field) #ifdef CONFIG_PROC_FS static void *rt_cache_seq_start(struct seq_file *seq, loff_t *pos) { if (*pos) return NULL; return SEQ_START_TOKEN; } static void *rt_cache_seq_next(struct seq_file *seq, void *v, loff_t *pos) { ++*pos; return NULL; } static void rt_cache_seq_stop(struct seq_file *seq, void *v) { } static int rt_cache_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) seq_printf(seq, "%-127s\n", "Iface\tDestination\tGateway \tFlags\t\tRefCnt\tUse\t" "Metric\tSource\t\tMTU\tWindow\tIRTT\tTOS\tHHRef\t" "HHUptod\tSpecDst"); return 0; } static const struct seq_operations rt_cache_seq_ops = { .start = rt_cache_seq_start, .next = rt_cache_seq_next, .stop = rt_cache_seq_stop, .show = rt_cache_seq_show, }; static void *rt_cpu_seq_start(struct seq_file *seq, loff_t *pos) { int cpu; if (*pos == 0) return SEQ_START_TOKEN; for (cpu = *pos-1; cpu < nr_cpu_ids; ++cpu) { if (!cpu_possible(cpu)) continue; *pos = cpu+1; return &per_cpu(rt_cache_stat, cpu); } return NULL; } static void *rt_cpu_seq_next(struct seq_file *seq, void *v, loff_t *pos) { int cpu; for (cpu = *pos; cpu < nr_cpu_ids; ++cpu) { if (!cpu_possible(cpu)) continue; *pos = cpu+1; return &per_cpu(rt_cache_stat, cpu); } (*pos)++; return NULL; } static void rt_cpu_seq_stop(struct seq_file *seq, void *v) { } static int rt_cpu_seq_show(struct seq_file *seq, void *v) { struct rt_cache_stat *st = v; if (v == SEQ_START_TOKEN) { seq_puts(seq, "entries in_hit in_slow_tot in_slow_mc in_no_route in_brd in_martian_dst in_martian_src out_hit out_slow_tot out_slow_mc gc_total gc_ignored gc_goal_miss gc_dst_overflow in_hlist_search out_hlist_search\n"); return 0; } seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x " "%08x %08x %08x %08x %08x %08x " "%08x %08x %08x %08x\n", dst_entries_get_slow(&ipv4_dst_ops), 0, /* st->in_hit */ st->in_slow_tot, st->in_slow_mc, st->in_no_route, st->in_brd, st->in_martian_dst, st->in_martian_src, 0, /* st->out_hit */ st->out_slow_tot, st->out_slow_mc, 0, /* st->gc_total */ 0, /* st->gc_ignored */ 0, /* st->gc_goal_miss */ 0, /* st->gc_dst_overflow */ 0, /* st->in_hlist_search */ 0 /* st->out_hlist_search */ ); return 0; } static const struct seq_operations rt_cpu_seq_ops = { .start = rt_cpu_seq_start, .next = rt_cpu_seq_next, .stop = rt_cpu_seq_stop, .show = rt_cpu_seq_show, }; #ifdef CONFIG_IP_ROUTE_CLASSID static int rt_acct_proc_show(struct seq_file *m, void *v) { struct ip_rt_acct *dst, *src; unsigned int i, j; dst = kcalloc(256, sizeof(struct ip_rt_acct), GFP_KERNEL); if (!dst) return -ENOMEM; for_each_possible_cpu(i) { src = (struct ip_rt_acct *)per_cpu_ptr(ip_rt_acct, i); for (j = 0; j < 256; j++) { dst[j].o_bytes += src[j].o_bytes; dst[j].o_packets += src[j].o_packets; dst[j].i_bytes += src[j].i_bytes; dst[j].i_packets += src[j].i_packets; } } seq_write(m, dst, 256 * sizeof(struct ip_rt_acct)); kfree(dst); return 0; } #endif static int __net_init ip_rt_do_proc_init(struct net *net) { struct proc_dir_entry *pde; pde = proc_create_seq("rt_cache", 0444, net->proc_net, &rt_cache_seq_ops); if (!pde) goto err1; pde = proc_create_seq("rt_cache", 0444, net->proc_net_stat, &rt_cpu_seq_ops); if (!pde) goto err2; #ifdef CONFIG_IP_ROUTE_CLASSID pde = proc_create_single("rt_acct", 0, net->proc_net, rt_acct_proc_show); if (!pde) goto err3; #endif return 0; #ifdef CONFIG_IP_ROUTE_CLASSID err3: remove_proc_entry("rt_cache", net->proc_net_stat); #endif err2: remove_proc_entry("rt_cache", net->proc_net); err1: return -ENOMEM; } static void __net_exit ip_rt_do_proc_exit(struct net *net) { remove_proc_entry("rt_cache", net->proc_net_stat); remove_proc_entry("rt_cache", net->proc_net); #ifdef CONFIG_IP_ROUTE_CLASSID remove_proc_entry("rt_acct", net->proc_net); #endif } static struct pernet_operations ip_rt_proc_ops __net_initdata = { .init = ip_rt_do_proc_init, .exit = ip_rt_do_proc_exit, }; static int __init ip_rt_proc_init(void) { return register_pernet_subsys(&ip_rt_proc_ops); } #else static inline int ip_rt_proc_init(void) { return 0; } #endif /* CONFIG_PROC_FS */ static inline bool rt_is_expired(const struct rtable *rth) { return rth->rt_genid != rt_genid_ipv4(dev_net(rth->dst.dev)); } void rt_cache_flush(struct net *net) { rt_genid_bump_ipv4(net); } static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, struct sk_buff *skb, const void *daddr) { const struct rtable *rt = container_of(dst, struct rtable, dst); struct net_device *dev = dst->dev; struct neighbour *n; rcu_read_lock(); if (likely(rt->rt_gw_family == AF_INET)) { n = ip_neigh_gw4(dev, rt->rt_gw4); } else if (rt->rt_gw_family == AF_INET6) { n = ip_neigh_gw6(dev, &rt->rt_gw6); } else { __be32 pkey; pkey = skb ? ip_hdr(skb)->daddr : *((__be32 *) daddr); n = ip_neigh_gw4(dev, pkey); } if (!IS_ERR(n) && !refcount_inc_not_zero(&n->refcnt)) n = NULL; rcu_read_unlock(); return n; } static void ipv4_confirm_neigh(const struct dst_entry *dst, const void *daddr) { const struct rtable *rt = container_of(dst, struct rtable, dst); struct net_device *dev = dst->dev; const __be32 *pkey = daddr; if (rt->rt_gw_family == AF_INET) { pkey = (const __be32 *)&rt->rt_gw4; } else if (rt->rt_gw_family == AF_INET6) { return __ipv6_confirm_neigh_stub(dev, &rt->rt_gw6); } else if (!daddr || (rt->rt_flags & (RTCF_MULTICAST | RTCF_BROADCAST | RTCF_LOCAL))) { return; } __ipv4_confirm_neigh(dev, *(__force u32 *)pkey); } /* Hash tables of size 2048..262144 depending on RAM size. * Each bucket uses 8 bytes. */ static u32 ip_idents_mask __read_mostly; static atomic_t *ip_idents __read_mostly; static u32 *ip_tstamps __read_mostly; /* In order to protect privacy, we add a perturbation to identifiers * if one generator is seldom used. This makes hard for an attacker * to infer how many packets were sent between two points in time. */ static u32 ip_idents_reserve(u32 hash, int segs) { u32 bucket, old, now = (u32)jiffies; atomic_t *p_id; u32 *p_tstamp; u32 delta = 0; bucket = hash & ip_idents_mask; p_tstamp = ip_tstamps + bucket; p_id = ip_idents + bucket; old = READ_ONCE(*p_tstamp); if (old != now && cmpxchg(p_tstamp, old, now) == old) delta = get_random_u32_below(now - old); /* If UBSAN reports an error there, please make sure your compiler * supports -fno-strict-overflow before reporting it that was a bug * in UBSAN, and it has been fixed in GCC-8. */ return atomic_add_return(segs + delta, p_id) - segs; } void __ip_select_ident(struct net *net, struct iphdr *iph, int segs) { u32 hash, id; /* Note the following code is not safe, but this is okay. */ if (unlikely(siphash_key_is_zero(&net->ipv4.ip_id_key))) get_random_bytes(&net->ipv4.ip_id_key, sizeof(net->ipv4.ip_id_key)); hash = siphash_3u32((__force u32)iph->daddr, (__force u32)iph->saddr, iph->protocol, &net->ipv4.ip_id_key); id = ip_idents_reserve(hash, segs); iph->id = htons(id); } EXPORT_SYMBOL(__ip_select_ident); static void __build_flow_key(const struct net *net, struct flowi4 *fl4, const struct sock *sk, const struct iphdr *iph, int oif, __u8 tos, u8 prot, u32 mark, int flow_flags) { __u8 scope = RT_SCOPE_UNIVERSE; if (sk) { oif = sk->sk_bound_dev_if; mark = READ_ONCE(sk->sk_mark); tos = ip_sock_rt_tos(sk); scope = ip_sock_rt_scope(sk); prot = inet_test_bit(HDRINCL, sk) ? IPPROTO_RAW : sk->sk_protocol; } flowi4_init_output(fl4, oif, mark, tos & INET_DSCP_MASK, scope, prot, flow_flags, iph->daddr, iph->saddr, 0, 0, sock_net_uid(net, sk)); } static void build_skb_flow_key(struct flowi4 *fl4, const struct sk_buff *skb, const struct sock *sk) { const struct net *net = dev_net(skb->dev); const struct iphdr *iph = ip_hdr(skb); int oif = skb->dev->ifindex; u8 prot = iph->protocol; u32 mark = skb->mark; __u8 tos = iph->tos; __build_flow_key(net, fl4, sk, iph, oif, tos, prot, mark, 0); } static void build_sk_flow_key(struct flowi4 *fl4, const struct sock *sk) { const struct inet_sock *inet = inet_sk(sk); const struct ip_options_rcu *inet_opt; __be32 daddr = inet->inet_daddr; rcu_read_lock(); inet_opt = rcu_dereference(inet->inet_opt); if (inet_opt && inet_opt->opt.srr) daddr = inet_opt->opt.faddr; flowi4_init_output(fl4, sk->sk_bound_dev_if, READ_ONCE(sk->sk_mark), ip_sock_rt_tos(sk), ip_sock_rt_scope(sk), inet_test_bit(HDRINCL, sk) ? IPPROTO_RAW : sk->sk_protocol, inet_sk_flowi_flags(sk), daddr, inet->inet_saddr, 0, 0, sk->sk_uid); rcu_read_unlock(); } static void ip_rt_build_flow_key(struct flowi4 *fl4, const struct sock *sk, const struct sk_buff *skb) { if (skb) build_skb_flow_key(fl4, skb, sk); else build_sk_flow_key(fl4, sk); } static DEFINE_SPINLOCK(fnhe_lock); static void fnhe_flush_routes(struct fib_nh_exception *fnhe) { struct rtable *rt; rt = rcu_dereference(fnhe->fnhe_rth_input); if (rt) { RCU_INIT_POINTER(fnhe->fnhe_rth_input, NULL); dst_dev_put(&rt->dst); dst_release(&rt->dst); } rt = rcu_dereference(fnhe->fnhe_rth_output); if (rt) { RCU_INIT_POINTER(fnhe->fnhe_rth_output, NULL); dst_dev_put(&rt->dst); dst_release(&rt->dst); } } static void fnhe_remove_oldest(struct fnhe_hash_bucket *hash) { struct fib_nh_exception __rcu **fnhe_p, **oldest_p; struct fib_nh_exception *fnhe, *oldest = NULL; for (fnhe_p = &hash->chain; ; fnhe_p = &fnhe->fnhe_next) { fnhe = rcu_dereference_protected(*fnhe_p, lockdep_is_held(&fnhe_lock)); if (!fnhe) break; if (!oldest || time_before(fnhe->fnhe_stamp, oldest->fnhe_stamp)) { oldest = fnhe; oldest_p = fnhe_p; } } fnhe_flush_routes(oldest); *oldest_p = oldest->fnhe_next; kfree_rcu(oldest, rcu); } static u32 fnhe_hashfun(__be32 daddr) { static siphash_aligned_key_t fnhe_hash_key; u64 hval; net_get_random_once(&fnhe_hash_key, sizeof(fnhe_hash_key)); hval = siphash_1u32((__force u32)daddr, &fnhe_hash_key); return hash_64(hval, FNHE_HASH_SHIFT); } static void fill_route_from_fnhe(struct rtable *rt, struct fib_nh_exception *fnhe) { rt->rt_pmtu = fnhe->fnhe_pmtu; rt->rt_mtu_locked = fnhe->fnhe_mtu_locked; rt->dst.expires = fnhe->fnhe_expires; if (fnhe->fnhe_gw) { rt->rt_flags |= RTCF_REDIRECTED; rt->rt_uses_gateway = 1; rt->rt_gw_family = AF_INET; rt->rt_gw4 = fnhe->fnhe_gw; } } static void update_or_create_fnhe(struct fib_nh_common *nhc, __be32 daddr, __be32 gw, u32 pmtu, bool lock, unsigned long expires) { struct fnhe_hash_bucket *hash; struct fib_nh_exception *fnhe; struct rtable *rt; u32 genid, hval; unsigned int i; int depth; genid = fnhe_genid(dev_net(nhc->nhc_dev)); hval = fnhe_hashfun(daddr); spin_lock_bh(&fnhe_lock); hash = rcu_dereference(nhc->nhc_exceptions); if (!hash) { hash = kcalloc(FNHE_HASH_SIZE, sizeof(*hash), GFP_ATOMIC); if (!hash) goto out_unlock; rcu_assign_pointer(nhc->nhc_exceptions, hash); } hash += hval; depth = 0; for (fnhe = rcu_dereference(hash->chain); fnhe; fnhe = rcu_dereference(fnhe->fnhe_next)) { if (fnhe->fnhe_daddr == daddr) break; depth++; } if (fnhe) { if (fnhe->fnhe_genid != genid) fnhe->fnhe_genid = genid; if (gw) fnhe->fnhe_gw = gw; if (pmtu) { fnhe->fnhe_pmtu = pmtu; fnhe->fnhe_mtu_locked = lock; } fnhe->fnhe_expires = max(1UL, expires); /* Update all cached dsts too */ rt = rcu_dereference(fnhe->fnhe_rth_input); if (rt) fill_route_from_fnhe(rt, fnhe); rt = rcu_dereference(fnhe->fnhe_rth_output); if (rt) fill_route_from_fnhe(rt, fnhe); } else { /* Randomize max depth to avoid some side channels attacks. */ int max_depth = FNHE_RECLAIM_DEPTH + get_random_u32_below(FNHE_RECLAIM_DEPTH); while (depth > max_depth) { fnhe_remove_oldest(hash); depth--; } fnhe = kzalloc(sizeof(*fnhe), GFP_ATOMIC); if (!fnhe) goto out_unlock; fnhe->fnhe_next = hash->chain; fnhe->fnhe_genid = genid; fnhe->fnhe_daddr = daddr; fnhe->fnhe_gw = gw; fnhe->fnhe_pmtu = pmtu; fnhe->fnhe_mtu_locked = lock; fnhe->fnhe_expires = max(1UL, expires); rcu_assign_pointer(hash->chain, fnhe); /* Exception created; mark the cached routes for the nexthop * stale, so anyone caching it rechecks if this exception * applies to them. */ rt = rcu_dereference(nhc->nhc_rth_input); if (rt) rt->dst.obsolete = DST_OBSOLETE_KILL; for_each_possible_cpu(i) { struct rtable __rcu **prt; prt = per_cpu_ptr(nhc->nhc_pcpu_rth_output, i); rt = rcu_dereference(*prt); if (rt) rt->dst.obsolete = DST_OBSOLETE_KILL; } } fnhe->fnhe_stamp = jiffies; out_unlock: spin_unlock_bh(&fnhe_lock); } static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flowi4 *fl4, bool kill_route) { __be32 new_gw = icmp_hdr(skb)->un.gateway; __be32 old_gw = ip_hdr(skb)->saddr; struct net_device *dev = skb->dev; struct in_device *in_dev; struct fib_result res; struct neighbour *n; struct net *net; switch (icmp_hdr(skb)->code & 7) { case ICMP_REDIR_NET: case ICMP_REDIR_NETTOS: case ICMP_REDIR_HOST: case ICMP_REDIR_HOSTTOS: break; default: return; } if (rt->rt_gw_family != AF_INET || rt->rt_gw4 != old_gw) return; in_dev = __in_dev_get_rcu(dev); if (!in_dev) return; net = dev_net(dev); if (new_gw == old_gw || !IN_DEV_RX_REDIRECTS(in_dev) || ipv4_is_multicast(new_gw) || ipv4_is_lbcast(new_gw) || ipv4_is_zeronet(new_gw)) goto reject_redirect; if (!IN_DEV_SHARED_MEDIA(in_dev)) { if (!inet_addr_onlink(in_dev, new_gw, old_gw)) goto reject_redirect; if (IN_DEV_SEC_REDIRECTS(in_dev) && ip_fib_check_default(new_gw, dev)) goto reject_redirect; } else { if (inet_addr_type(net, new_gw) != RTN_UNICAST) goto reject_redirect; } n = __ipv4_neigh_lookup(rt->dst.dev, (__force u32)new_gw); if (!n) n = neigh_create(&arp_tbl, &new_gw, rt->dst.dev); if (!IS_ERR(n)) { if (!(READ_ONCE(n->nud_state) & NUD_VALID)) { neigh_event_send(n, NULL); } else { if (fib_lookup(net, fl4, &res, 0) == 0) { struct fib_nh_common *nhc; fib_select_path(net, &res, fl4, skb); nhc = FIB_RES_NHC(res); update_or_create_fnhe(nhc, fl4->daddr, new_gw, 0, false, jiffies + ip_rt_gc_timeout); } if (kill_route) rt->dst.obsolete = DST_OBSOLETE_KILL; call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, n); } neigh_release(n); } return; reject_redirect: #ifdef CONFIG_IP_ROUTE_VERBOSE if (IN_DEV_LOG_MARTIANS(in_dev)) { const struct iphdr *iph = (const struct iphdr *) skb->data; __be32 daddr = iph->daddr; __be32 saddr = iph->saddr; net_info_ratelimited("Redirect from %pI4 on %s about %pI4 ignored\n" " Advised path = %pI4 -> %pI4\n", &old_gw, dev->name, &new_gw, &saddr, &daddr); } #endif ; } static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb) { struct rtable *rt; struct flowi4 fl4; const struct iphdr *iph = (const struct iphdr *) skb->data; struct net *net = dev_net(skb->dev); int oif = skb->dev->ifindex; u8 prot = iph->protocol; u32 mark = skb->mark; __u8 tos = iph->tos; rt = dst_rtable(dst); __build_flow_key(net, &fl4, sk, iph, oif, tos, prot, mark, 0); __ip_do_redirect(rt, skb, &fl4, true); } static void ipv4_negative_advice(struct sock *sk, struct dst_entry *dst) { struct rtable *rt = dst_rtable(dst); if ((dst->obsolete > 0) || (rt->rt_flags & RTCF_REDIRECTED) || rt->dst.expires) sk_dst_reset(sk); } /* * Algorithm: * 1. The first ip_rt_redirect_number redirects are sent * with exponential backoff, then we stop sending them at all, * assuming that the host ignores our redirects. * 2. If we did not see packets requiring redirects * during ip_rt_redirect_silence, we assume that the host * forgot redirected route and start to send redirects again. * * This algorithm is much cheaper and more intelligent than dumb load limiting * in icmp.c. * * NOTE. Do not forget to inhibit load limiting for redirects (redundant) * and "frag. need" (breaks PMTU discovery) in icmp.c. */ void ip_rt_send_redirect(struct sk_buff *skb) { struct rtable *rt = skb_rtable(skb); struct in_device *in_dev; struct inet_peer *peer; struct net *net; int log_martians; int vif; rcu_read_lock(); in_dev = __in_dev_get_rcu(rt->dst.dev); if (!in_dev || !IN_DEV_TX_REDIRECTS(in_dev)) { rcu_read_unlock(); return; } log_martians = IN_DEV_LOG_MARTIANS(in_dev); vif = l3mdev_master_ifindex_rcu(rt->dst.dev); rcu_read_unlock(); net = dev_net(rt->dst.dev); peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr, vif, 1); if (!peer) { icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, rt_nexthop(rt, ip_hdr(skb)->daddr)); return; } /* No redirected packets during ip_rt_redirect_silence; * reset the algorithm. */ if (time_after(jiffies, peer->rate_last + ip_rt_redirect_silence)) { peer->rate_tokens = 0; peer->n_redirects = 0; } /* Too many ignored redirects; do not send anything * set dst.rate_last to the last seen redirected packet. */ if (peer->n_redirects >= ip_rt_redirect_number) { peer->rate_last = jiffies; goto out_put_peer; } /* Check for load limit; set rate_last to the latest sent * redirect. */ if (peer->n_redirects == 0 || time_after(jiffies, (peer->rate_last + (ip_rt_redirect_load << peer->n_redirects)))) { __be32 gw = rt_nexthop(rt, ip_hdr(skb)->daddr); icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, gw); peer->rate_last = jiffies; ++peer->n_redirects; if (IS_ENABLED(CONFIG_IP_ROUTE_VERBOSE) && log_martians && peer->n_redirects == ip_rt_redirect_number) net_warn_ratelimited("host %pI4/if%d ignores redirects for %pI4 to %pI4\n", &ip_hdr(skb)->saddr, inet_iif(skb), &ip_hdr(skb)->daddr, &gw); } out_put_peer: inet_putpeer(peer); } static int ip_error(struct sk_buff *skb) { struct rtable *rt = skb_rtable(skb); struct net_device *dev = skb->dev; struct in_device *in_dev; struct inet_peer *peer; unsigned long now; struct net *net; SKB_DR(reason); bool send; int code; if (netif_is_l3_master(skb->dev)) { dev = __dev_get_by_index(dev_net(skb->dev), IPCB(skb)->iif); if (!dev) goto out; } in_dev = __in_dev_get_rcu(dev); /* IP on this device is disabled. */ if (!in_dev) goto out; net = dev_net(rt->dst.dev); if (!IN_DEV_FORWARD(in_dev)) { switch (rt->dst.error) { case EHOSTUNREACH: SKB_DR_SET(reason, IP_INADDRERRORS); __IP_INC_STATS(net, IPSTATS_MIB_INADDRERRORS); break; case ENETUNREACH: SKB_DR_SET(reason, IP_INNOROUTES); __IP_INC_STATS(net, IPSTATS_MIB_INNOROUTES); break; } goto out; } switch (rt->dst.error) { case EINVAL: default: goto out; case EHOSTUNREACH: code = ICMP_HOST_UNREACH; break; case ENETUNREACH: code = ICMP_NET_UNREACH; SKB_DR_SET(reason, IP_INNOROUTES); __IP_INC_STATS(net, IPSTATS_MIB_INNOROUTES); break; case EACCES: code = ICMP_PKT_FILTERED; break; } peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr, l3mdev_master_ifindex(skb->dev), 1); send = true; if (peer) { now = jiffies; peer->rate_tokens += now - peer->rate_last; if (peer->rate_tokens > ip_rt_error_burst) peer->rate_tokens = ip_rt_error_burst; peer->rate_last = now; if (peer->rate_tokens >= ip_rt_error_cost) peer->rate_tokens -= ip_rt_error_cost; else send = false; inet_putpeer(peer); } if (send) icmp_send(skb, ICMP_DEST_UNREACH, code, 0); out: kfree_skb_reason(skb, reason); return 0; } static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) { struct dst_entry *dst = &rt->dst; struct net *net = dev_net(dst->dev); struct fib_result res; bool lock = false; u32 old_mtu; if (ip_mtu_locked(dst)) return; old_mtu = ipv4_mtu(dst); if (old_mtu < mtu) return; if (mtu < net->ipv4.ip_rt_min_pmtu) { lock = true; mtu = min(old_mtu, net->ipv4.ip_rt_min_pmtu); } if (rt->rt_pmtu == mtu && !lock && time_before(jiffies, dst->expires - net->ipv4.ip_rt_mtu_expires / 2)) return; rcu_read_lock(); if (fib_lookup(net, fl4, &res, 0) == 0) { struct fib_nh_common *nhc; fib_select_path(net, &res, fl4, NULL); #ifdef CONFIG_IP_ROUTE_MULTIPATH if (fib_info_num_path(res.fi) > 1) { int nhsel; for (nhsel = 0; nhsel < fib_info_num_path(res.fi); nhsel++) { nhc = fib_info_nhc(res.fi, nhsel); update_or_create_fnhe(nhc, fl4->daddr, 0, mtu, lock, jiffies + net->ipv4.ip_rt_mtu_expires); } rcu_read_unlock(); return; } #endif /* CONFIG_IP_ROUTE_MULTIPATH */ nhc = FIB_RES_NHC(res); update_or_create_fnhe(nhc, fl4->daddr, 0, mtu, lock, jiffies + net->ipv4.ip_rt_mtu_expires); } rcu_read_unlock(); } static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, bool confirm_neigh) { struct rtable *rt = dst_rtable(dst); struct flowi4 fl4; ip_rt_build_flow_key(&fl4, sk, skb); /* Don't make lookup fail for bridged encapsulations */ if (skb && netif_is_any_bridge_port(skb->dev)) fl4.flowi4_oif = 0; __ip_rt_update_pmtu(rt, &fl4, mtu); } void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu, int oif, u8 protocol) { const struct iphdr *iph = (const struct iphdr *)skb->data; struct flowi4 fl4; struct rtable *rt; u32 mark = IP4_REPLY_MARK(net, skb->mark); __build_flow_key(net, &fl4, NULL, iph, oif, iph->tos, protocol, mark, 0); rt = __ip_route_output_key(net, &fl4); if (!IS_ERR(rt)) { __ip_rt_update_pmtu(rt, &fl4, mtu); ip_rt_put(rt); } } EXPORT_SYMBOL_GPL(ipv4_update_pmtu); static void __ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) { const struct iphdr *iph = (const struct iphdr *)skb->data; struct flowi4 fl4; struct rtable *rt; __build_flow_key(sock_net(sk), &fl4, sk, iph, 0, 0, 0, 0, 0); if (!fl4.flowi4_mark) fl4.flowi4_mark = IP4_REPLY_MARK(sock_net(sk), skb->mark); rt = __ip_route_output_key(sock_net(sk), &fl4); if (!IS_ERR(rt)) { __ip_rt_update_pmtu(rt, &fl4, mtu); ip_rt_put(rt); } } void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) { const struct iphdr *iph = (const struct iphdr *)skb->data; struct flowi4 fl4; struct rtable *rt; struct dst_entry *odst = NULL; bool new = false; struct net *net = sock_net(sk); bh_lock_sock(sk); if (!ip_sk_accept_pmtu(sk)) goto out; odst = sk_dst_get(sk); if (sock_owned_by_user(sk) || !odst) { __ipv4_sk_update_pmtu(skb, sk, mtu); goto out; } __build_flow_key(net, &fl4, sk, iph, 0, 0, 0, 0, 0); rt = dst_rtable(odst); if (odst->obsolete && !odst->ops->check(odst, 0)) { rt = ip_route_output_flow(sock_net(sk), &fl4, sk); if (IS_ERR(rt)) goto out; new = true; } __ip_rt_update_pmtu(dst_rtable(xfrm_dst_path(&rt->dst)), &fl4, mtu); if (!dst_check(&rt->dst, 0)) { if (new) dst_release(&rt->dst); rt = ip_route_output_flow(sock_net(sk), &fl4, sk); if (IS_ERR(rt)) goto out; new = true; } if (new) sk_dst_set(sk, &rt->dst); out: bh_unlock_sock(sk); dst_release(odst); } EXPORT_SYMBOL_GPL(ipv4_sk_update_pmtu); void ipv4_redirect(struct sk_buff *skb, struct net *net, int oif, u8 protocol) { const struct iphdr *iph = (const struct iphdr *)skb->data; struct flowi4 fl4; struct rtable *rt; __build_flow_key(net, &fl4, NULL, iph, oif, iph->tos, protocol, 0, 0); rt = __ip_route_output_key(net, &fl4); if (!IS_ERR(rt)) { __ip_do_redirect(rt, skb, &fl4, false); ip_rt_put(rt); } } EXPORT_SYMBOL_GPL(ipv4_redirect); void ipv4_sk_redirect(struct sk_buff *skb, struct sock *sk) { const struct iphdr *iph = (const struct iphdr *)skb->data; struct flowi4 fl4; struct rtable *rt; struct net *net = sock_net(sk); __build_flow_key(net, &fl4, sk, iph, 0, 0, 0, 0, 0); rt = __ip_route_output_key(net, &fl4); if (!IS_ERR(rt)) { __ip_do_redirect(rt, skb, &fl4, false); ip_rt_put(rt); } } EXPORT_SYMBOL_GPL(ipv4_sk_redirect); INDIRECT_CALLABLE_SCOPE struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie) { struct rtable *rt = dst_rtable(dst); /* All IPV4 dsts are created with ->obsolete set to the value * DST_OBSOLETE_FORCE_CHK which forces validation calls down * into this function always. * * When a PMTU/redirect information update invalidates a route, * this is indicated by setting obsolete to DST_OBSOLETE_KILL or * DST_OBSOLETE_DEAD. */ if (dst->obsolete != DST_OBSOLETE_FORCE_CHK || rt_is_expired(rt)) return NULL; return dst; } EXPORT_INDIRECT_CALLABLE(ipv4_dst_check); static void ipv4_send_dest_unreach(struct sk_buff *skb) { struct net_device *dev; struct ip_options opt; int res; /* Recompile ip options since IPCB may not be valid anymore. * Also check we have a reasonable ipv4 header. */ if (!pskb_network_may_pull(skb, sizeof(struct iphdr)) || ip_hdr(skb)->version != 4 || ip_hdr(skb)->ihl < 5) return; memset(&opt, 0, sizeof(opt)); if (ip_hdr(skb)->ihl > 5) { if (!pskb_network_may_pull(skb, ip_hdr(skb)->ihl * 4)) return; opt.optlen = ip_hdr(skb)->ihl * 4 - sizeof(struct iphdr); rcu_read_lock(); dev = skb->dev ? skb->dev : skb_rtable(skb)->dst.dev; res = __ip_options_compile(dev_net(dev), &opt, skb, NULL); rcu_read_unlock(); if (res) return; } __icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0, &opt); } static void ipv4_link_failure(struct sk_buff *skb) { struct rtable *rt; ipv4_send_dest_unreach(skb); rt = skb_rtable(skb); if (rt) dst_set_expires(&rt->dst, 0); } static int ip_rt_bug(struct net *net, struct sock *sk, struct sk_buff *skb) { pr_debug("%s: %pI4 -> %pI4, %s\n", __func__, &ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, skb->dev ? skb->dev->name : "?"); kfree_skb(skb); WARN_ON(1); return 0; } /* * We do not cache source address of outgoing interface, * because it is used only by IP RR, TS and SRR options, * so that it out of fast path. * * BTW remember: "addr" is allowed to be not aligned * in IP options! */ void ip_rt_get_source(u8 *addr, struct sk_buff *skb, struct rtable *rt) { __be32 src; if (rt_is_output_route(rt)) src = ip_hdr(skb)->saddr; else { struct fib_result res; struct iphdr *iph = ip_hdr(skb); struct flowi4 fl4 = { .daddr = iph->daddr, .saddr = iph->saddr, .flowi4_tos = inet_dscp_to_dsfield(ip4h_dscp(iph)), .flowi4_oif = rt->dst.dev->ifindex, .flowi4_iif = skb->dev->ifindex, .flowi4_mark = skb->mark, }; rcu_read_lock(); if (fib_lookup(dev_net(rt->dst.dev), &fl4, &res, 0) == 0) src = fib_result_prefsrc(dev_net(rt->dst.dev), &res); else src = inet_select_addr(rt->dst.dev, rt_nexthop(rt, iph->daddr), RT_SCOPE_UNIVERSE); rcu_read_unlock(); } memcpy(addr, &src, 4); } #ifdef CONFIG_IP_ROUTE_CLASSID static void set_class_tag(struct rtable *rt, u32 tag) { if (!(rt->dst.tclassid & 0xFFFF)) rt->dst.tclassid |= tag & 0xFFFF; if (!(rt->dst.tclassid & 0xFFFF0000)) rt->dst.tclassid |= tag & 0xFFFF0000; } #endif static unsigned int ipv4_default_advmss(const struct dst_entry *dst) { struct net *net = dev_net(dst->dev); unsigned int header_size = sizeof(struct tcphdr) + sizeof(struct iphdr); unsigned int advmss = max_t(unsigned int, ipv4_mtu(dst) - header_size, net->ipv4.ip_rt_min_advmss); return min(advmss, IPV4_MAX_PMTU - header_size); } INDIRECT_CALLABLE_SCOPE unsigned int ipv4_mtu(const struct dst_entry *dst) { return ip_dst_mtu_maybe_forward(dst, false); } EXPORT_INDIRECT_CALLABLE(ipv4_mtu); static void ip_del_fnhe(struct fib_nh_common *nhc, __be32 daddr) { struct fnhe_hash_bucket *hash; struct fib_nh_exception *fnhe, __rcu **fnhe_p; u32 hval = fnhe_hashfun(daddr); spin_lock_bh(&fnhe_lock); hash = rcu_dereference_protected(nhc->nhc_exceptions, lockdep_is_held(&fnhe_lock)); hash += hval; fnhe_p = &hash->chain; fnhe = rcu_dereference_protected(*fnhe_p, lockdep_is_held(&fnhe_lock)); while (fnhe) { if (fnhe->fnhe_daddr == daddr) { rcu_assign_pointer(*fnhe_p, rcu_dereference_protected( fnhe->fnhe_next, lockdep_is_held(&fnhe_lock))); /* set fnhe_daddr to 0 to ensure it won't bind with * new dsts in rt_bind_exception(). */ fnhe->fnhe_daddr = 0; fnhe_flush_routes(fnhe); kfree_rcu(fnhe, rcu); break; } fnhe_p = &fnhe->fnhe_next; fnhe = rcu_dereference_protected(fnhe->fnhe_next, lockdep_is_held(&fnhe_lock)); } spin_unlock_bh(&fnhe_lock); } static struct fib_nh_exception *find_exception(struct fib_nh_common *nhc, __be32 daddr) { struct fnhe_hash_bucket *hash = rcu_dereference(nhc->nhc_exceptions); struct fib_nh_exception *fnhe; u32 hval; if (!hash) return NULL; hval = fnhe_hashfun(daddr); for (fnhe = rcu_dereference(hash[hval].chain); fnhe; fnhe = rcu_dereference(fnhe->fnhe_next)) { if (fnhe->fnhe_daddr == daddr) { if (fnhe->fnhe_expires && time_after(jiffies, fnhe->fnhe_expires)) { ip_del_fnhe(nhc, daddr); break; } return fnhe; } } return NULL; } /* MTU selection: * 1. mtu on route is locked - use it * 2. mtu from nexthop exception * 3. mtu from egress device */ u32 ip_mtu_from_fib_result(struct fib_result *res, __be32 daddr) { struct fib_nh_common *nhc = res->nhc; struct net_device *dev = nhc->nhc_dev; struct fib_info *fi = res->fi; u32 mtu = 0; if (READ_ONCE(dev_net(dev)->ipv4.sysctl_ip_fwd_use_pmtu) || fi->fib_metrics->metrics[RTAX_LOCK - 1] & (1 << RTAX_MTU)) mtu = fi->fib_mtu; if (likely(!mtu)) { struct fib_nh_exception *fnhe; fnhe = find_exception(nhc, daddr); if (fnhe && !time_after_eq(jiffies, fnhe->fnhe_expires)) mtu = fnhe->fnhe_pmtu; } if (likely(!mtu)) mtu = min(READ_ONCE(dev->mtu), IP_MAX_MTU); return mtu - lwtunnel_headroom(nhc->nhc_lwtstate, mtu); } static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe, __be32 daddr, const bool do_cache) { bool ret = false; spin_lock_bh(&fnhe_lock); if (daddr == fnhe->fnhe_daddr) { struct rtable __rcu **porig; struct rtable *orig; int genid = fnhe_genid(dev_net(rt->dst.dev)); if (rt_is_input_route(rt)) porig = &fnhe->fnhe_rth_input; else porig = &fnhe->fnhe_rth_output; orig = rcu_dereference(*porig); if (fnhe->fnhe_genid != genid) { fnhe->fnhe_genid = genid; fnhe->fnhe_gw = 0; fnhe->fnhe_pmtu = 0; fnhe->fnhe_expires = 0; fnhe->fnhe_mtu_locked = false; fnhe_flush_routes(fnhe); orig = NULL; } fill_route_from_fnhe(rt, fnhe); if (!rt->rt_gw4) { rt->rt_gw4 = daddr; rt->rt_gw_family = AF_INET; } if (do_cache) { dst_hold(&rt->dst); rcu_assign_pointer(*porig, rt); if (orig) { dst_dev_put(&orig->dst); dst_release(&orig->dst); } ret = true; } fnhe->fnhe_stamp = jiffies; } spin_unlock_bh(&fnhe_lock); return ret; } static bool rt_cache_route(struct fib_nh_common *nhc, struct rtable *rt) { struct rtable *orig, *prev, **p; bool ret = true; if (rt_is_input_route(rt)) { p = (struct rtable **)&nhc->nhc_rth_input; } else { p = (struct rtable **)raw_cpu_ptr(nhc->nhc_pcpu_rth_output); } orig = *p; /* hold dst before doing cmpxchg() to avoid race condition * on this dst */ dst_hold(&rt->dst); prev = cmpxchg(p, orig, rt); if (prev == orig) { if (orig) { rt_add_uncached_list(orig); dst_release(&orig->dst); } } else { dst_release(&rt->dst); ret = false; } return ret; } struct uncached_list { spinlock_t lock; struct list_head head; }; static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt_uncached_list); void rt_add_uncached_list(struct rtable *rt) { struct uncached_list *ul = raw_cpu_ptr(&rt_uncached_list); rt->dst.rt_uncached_list = ul; spin_lock_bh(&ul->lock); list_add_tail(&rt->dst.rt_uncached, &ul->head); spin_unlock_bh(&ul->lock); } void rt_del_uncached_list(struct rtable *rt) { if (!list_empty(&rt->dst.rt_uncached)) { struct uncached_list *ul = rt->dst.rt_uncached_list; spin_lock_bh(&ul->lock); list_del_init(&rt->dst.rt_uncached); spin_unlock_bh(&ul->lock); } } static void ipv4_dst_destroy(struct dst_entry *dst) { ip_dst_metrics_put(dst); rt_del_uncached_list(dst_rtable(dst)); } void rt_flush_dev(struct net_device *dev) { struct rtable *rt, *safe; int cpu; for_each_possible_cpu(cpu) { struct uncached_list *ul = &per_cpu(rt_uncached_list, cpu); if (list_empty(&ul->head)) continue; spin_lock_bh(&ul->lock); list_for_each_entry_safe(rt, safe, &ul->head, dst.rt_uncached) { if (rt->dst.dev != dev) continue; rt->dst.dev = blackhole_netdev; netdev_ref_replace(dev, blackhole_netdev, &rt->dst.dev_tracker, GFP_ATOMIC); list_del_init(&rt->dst.rt_uncached); } spin_unlock_bh(&ul->lock); } } static bool rt_cache_valid(const struct rtable *rt) { return rt && rt->dst.obsolete == DST_OBSOLETE_FORCE_CHK && !rt_is_expired(rt); } static void rt_set_nexthop(struct rtable *rt, __be32 daddr, const struct fib_result *res, struct fib_nh_exception *fnhe, struct fib_info *fi, u16 type, u32 itag, const bool do_cache) { bool cached = false; if (fi) { struct fib_nh_common *nhc = FIB_RES_NHC(*res); if (nhc->nhc_gw_family && nhc->nhc_scope == RT_SCOPE_LINK) { rt->rt_uses_gateway = 1; rt->rt_gw_family = nhc->nhc_gw_family; /* only INET and INET6 are supported */ if (likely(nhc->nhc_gw_family == AF_INET)) rt->rt_gw4 = nhc->nhc_gw.ipv4; else rt->rt_gw6 = nhc->nhc_gw.ipv6; } ip_dst_init_metrics(&rt->dst, fi->fib_metrics); #ifdef CONFIG_IP_ROUTE_CLASSID if (nhc->nhc_family == AF_INET) { struct fib_nh *nh; nh = container_of(nhc, struct fib_nh, nh_common); rt->dst.tclassid = nh->nh_tclassid; } #endif rt->dst.lwtstate = lwtstate_get(nhc->nhc_lwtstate); if (unlikely(fnhe)) cached = rt_bind_exception(rt, fnhe, daddr, do_cache); else if (do_cache) cached = rt_cache_route(nhc, rt); if (unlikely(!cached)) { /* Routes we intend to cache in nexthop exception or * FIB nexthop have the DST_NOCACHE bit clear. * However, if we are unsuccessful at storing this * route into the cache we really need to set it. */ if (!rt->rt_gw4) { rt->rt_gw_family = AF_INET; rt->rt_gw4 = daddr; } rt_add_uncached_list(rt); } } else rt_add_uncached_list(rt); #ifdef CONFIG_IP_ROUTE_CLASSID #ifdef CONFIG_IP_MULTIPLE_TABLES set_class_tag(rt, res->tclassid); #endif set_class_tag(rt, itag); #endif } struct rtable *rt_dst_alloc(struct net_device *dev, unsigned int flags, u16 type, bool noxfrm) { struct rtable *rt; rt = dst_alloc(&ipv4_dst_ops, dev, DST_OBSOLETE_FORCE_CHK, (noxfrm ? DST_NOXFRM : 0)); if (rt) { rt->rt_genid = rt_genid_ipv4(dev_net(dev)); rt->rt_flags = flags; rt->rt_type = type; rt->rt_is_input = 0; rt->rt_iif = 0; rt->rt_pmtu = 0; rt->rt_mtu_locked = 0; rt->rt_uses_gateway = 0; rt->rt_gw_family = 0; rt->rt_gw4 = 0; rt->dst.output = ip_output; if (flags & RTCF_LOCAL) rt->dst.input = ip_local_deliver; } return rt; } EXPORT_SYMBOL(rt_dst_alloc); struct rtable *rt_dst_clone(struct net_device *dev, struct rtable *rt) { struct rtable *new_rt; new_rt = dst_alloc(&ipv4_dst_ops, dev, DST_OBSOLETE_FORCE_CHK, rt->dst.flags); if (new_rt) { new_rt->rt_genid = rt_genid_ipv4(dev_net(dev)); new_rt->rt_flags = rt->rt_flags; new_rt->rt_type = rt->rt_type; new_rt->rt_is_input = rt->rt_is_input; new_rt->rt_iif = rt->rt_iif; new_rt->rt_pmtu = rt->rt_pmtu; new_rt->rt_mtu_locked = rt->rt_mtu_locked; new_rt->rt_gw_family = rt->rt_gw_family; if (rt->rt_gw_family == AF_INET) new_rt->rt_gw4 = rt->rt_gw4; else if (rt->rt_gw_family == AF_INET6) new_rt->rt_gw6 = rt->rt_gw6; new_rt->dst.input = rt->dst.input; new_rt->dst.output = rt->dst.output; new_rt->dst.error = rt->dst.error; new_rt->dst.lastuse = jiffies; new_rt->dst.lwtstate = lwtstate_get(rt->dst.lwtstate); } return new_rt; } EXPORT_SYMBOL(rt_dst_clone); /* called in rcu_read_lock() section */ enum skb_drop_reason ip_mc_validate_source(struct sk_buff *skb, __be32 daddr, __be32 saddr, dscp_t dscp, struct net_device *dev, struct in_device *in_dev, u32 *itag) { enum skb_drop_reason reason; /* Primary sanity checks. */ if (!in_dev) return SKB_DROP_REASON_NOT_SPECIFIED; if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr)) return SKB_DROP_REASON_IP_INVALID_SOURCE; if (skb->protocol != htons(ETH_P_IP)) return SKB_DROP_REASON_INVALID_PROTO; if (ipv4_is_loopback(saddr) && !IN_DEV_ROUTE_LOCALNET(in_dev)) return SKB_DROP_REASON_IP_LOCALNET; if (ipv4_is_zeronet(saddr)) { if (!ipv4_is_local_multicast(daddr) && ip_hdr(skb)->protocol != IPPROTO_IGMP) return SKB_DROP_REASON_IP_INVALID_SOURCE; } else { reason = fib_validate_source_reason(skb, saddr, 0, dscp, 0, dev, in_dev, itag); if (reason) return reason; } return SKB_NOT_DROPPED_YET; } /* called in rcu_read_lock() section */ static enum skb_drop_reason ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, dscp_t dscp, struct net_device *dev, int our) { struct in_device *in_dev = __in_dev_get_rcu(dev); unsigned int flags = RTCF_MULTICAST; enum skb_drop_reason reason; struct rtable *rth; u32 itag = 0; reason = ip_mc_validate_source(skb, daddr, saddr, dscp, dev, in_dev, &itag); if (reason) return reason; if (our) flags |= RTCF_LOCAL; if (IN_DEV_ORCONF(in_dev, NOPOLICY)) IPCB(skb)->flags |= IPSKB_NOPOLICY; rth = rt_dst_alloc(dev_net(dev)->loopback_dev, flags, RTN_MULTICAST, false); if (!rth) return SKB_DROP_REASON_NOMEM; #ifdef CONFIG_IP_ROUTE_CLASSID rth->dst.tclassid = itag; #endif rth->dst.output = ip_rt_bug; rth->rt_is_input= 1; #ifdef CONFIG_IP_MROUTE if (!ipv4_is_local_multicast(daddr) && IN_DEV_MFORWARD(in_dev)) rth->dst.input = ip_mr_input; #endif RT_CACHE_STAT_INC(in_slow_mc); skb_dst_drop(skb); skb_dst_set(skb, &rth->dst); return SKB_NOT_DROPPED_YET; } static void ip_handle_martian_source(struct net_device *dev, struct in_device *in_dev, struct sk_buff *skb, __be32 daddr, __be32 saddr) { RT_CACHE_STAT_INC(in_martian_src); #ifdef CONFIG_IP_ROUTE_VERBOSE if (IN_DEV_LOG_MARTIANS(in_dev) && net_ratelimit()) { /* * RFC1812 recommendation, if source is martian, * the only hint is MAC header. */ pr_warn("martian source %pI4 from %pI4, on dev %s\n", &daddr, &saddr, dev->name); if (dev->hard_header_len && skb_mac_header_was_set(skb)) { print_hex_dump(KERN_WARNING, "ll header: ", DUMP_PREFIX_OFFSET, 16, 1, skb_mac_header(skb), dev->hard_header_len, false); } } #endif } /* called in rcu_read_lock() section */ static enum skb_drop_reason __mkroute_input(struct sk_buff *skb, const struct fib_result *res, struct in_device *in_dev, __be32 daddr, __be32 saddr, dscp_t dscp) { enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED; struct fib_nh_common *nhc = FIB_RES_NHC(*res); struct net_device *dev = nhc->nhc_dev; struct fib_nh_exception *fnhe; struct rtable *rth; int err; struct in_device *out_dev; bool do_cache; u32 itag = 0; /* get a working reference to the output device */ out_dev = __in_dev_get_rcu(dev); if (!out_dev) { net_crit_ratelimited("Bug in ip_route_input_slow(). Please report.\n"); return reason; } err = fib_validate_source(skb, saddr, daddr, dscp, FIB_RES_OIF(*res), in_dev->dev, in_dev, &itag); if (err < 0) { reason = -err; ip_handle_martian_source(in_dev->dev, in_dev, skb, daddr, saddr); goto cleanup; } do_cache = res->fi && !itag; if (out_dev == in_dev && err && IN_DEV_TX_REDIRECTS(out_dev) && skb->protocol == htons(ETH_P_IP)) { __be32 gw; gw = nhc->nhc_gw_family == AF_INET ? nhc->nhc_gw.ipv4 : 0; if (IN_DEV_SHARED_MEDIA(out_dev) || inet_addr_onlink(out_dev, saddr, gw)) IPCB(skb)->flags |= IPSKB_DOREDIRECT; } if (skb->protocol != htons(ETH_P_IP)) { /* Not IP (i.e. ARP). Do not create route, if it is * invalid for proxy arp. DNAT routes are always valid. * * Proxy arp feature have been extended to allow, ARP * replies back to the same interface, to support * Private VLAN switch technologies. See arp.c. */ if (out_dev == in_dev && IN_DEV_PROXY_ARP_PVLAN(in_dev) == 0) { reason = SKB_DROP_REASON_ARP_PVLAN_DISABLE; goto cleanup; } } if (IN_DEV_ORCONF(in_dev, NOPOLICY)) IPCB(skb)->flags |= IPSKB_NOPOLICY; fnhe = find_exception(nhc, daddr); if (do_cache) { if (fnhe) rth = rcu_dereference(fnhe->fnhe_rth_input); else rth = rcu_dereference(nhc->nhc_rth_input); if (rt_cache_valid(rth)) { skb_dst_set_noref(skb, &rth->dst); goto out; } } rth = rt_dst_alloc(out_dev->dev, 0, res->type, IN_DEV_ORCONF(out_dev, NOXFRM)); if (!rth) { reason = SKB_DROP_REASON_NOMEM; goto cleanup; } rth->rt_is_input = 1; RT_CACHE_STAT_INC(in_slow_tot); rth->dst.input = ip_forward; rt_set_nexthop(rth, daddr, res, fnhe, res->fi, res->type, itag, do_cache); lwtunnel_set_redirect(&rth->dst); skb_dst_set(skb, &rth->dst); out: reason = SKB_NOT_DROPPED_YET; cleanup: return reason; } #ifdef CONFIG_IP_ROUTE_MULTIPATH /* To make ICMP packets follow the right flow, the multipath hash is * calculated from the inner IP addresses. */ static void ip_multipath_l3_keys(const struct sk_buff *skb, struct flow_keys *hash_keys) { const struct iphdr *outer_iph = ip_hdr(skb); const struct iphdr *key_iph = outer_iph; const struct iphdr *inner_iph; const struct icmphdr *icmph; struct iphdr _inner_iph; struct icmphdr _icmph; if (likely(outer_iph->protocol != IPPROTO_ICMP)) goto out; if (unlikely((outer_iph->frag_off & htons(IP_OFFSET)) != 0)) goto out; icmph = skb_header_pointer(skb, outer_iph->ihl * 4, sizeof(_icmph), &_icmph); if (!icmph) goto out; if (!icmp_is_err(icmph->type)) goto out; inner_iph = skb_header_pointer(skb, outer_iph->ihl * 4 + sizeof(_icmph), sizeof(_inner_iph), &_inner_iph); if (!inner_iph) goto out; key_iph = inner_iph; out: hash_keys->addrs.v4addrs.src = key_iph->saddr; hash_keys->addrs.v4addrs.dst = key_iph->daddr; } static u32 fib_multipath_custom_hash_outer(const struct net *net, const struct sk_buff *skb, bool *p_has_inner) { u32 hash_fields = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_fields); struct flow_keys keys, hash_keys; if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_OUTER_MASK)) return 0; memset(&hash_keys, 0, sizeof(hash_keys)); skb_flow_dissect_flow_keys(skb, &keys, FLOW_DISSECTOR_F_STOP_AT_ENCAP); hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_IP) hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_IP) hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_IP_PROTO) hash_keys.basic.ip_proto = keys.basic.ip_proto; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_PORT) hash_keys.ports.src = keys.ports.src; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_PORT) hash_keys.ports.dst = keys.ports.dst; *p_has_inner = !!(keys.control.flags & FLOW_DIS_ENCAPSULATION); return fib_multipath_hash_from_keys(net, &hash_keys); } static u32 fib_multipath_custom_hash_inner(const struct net *net, const struct sk_buff *skb, bool has_inner) { u32 hash_fields = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_fields); struct flow_keys keys, hash_keys; /* We assume the packet carries an encapsulation, but if none was * encountered during dissection of the outer flow, then there is no * point in calling the flow dissector again. */ if (!has_inner) return 0; if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_MASK)) return 0; memset(&hash_keys, 0, sizeof(hash_keys)); skb_flow_dissect_flow_keys(skb, &keys, 0); if (!(keys.control.flags & FLOW_DIS_ENCAPSULATION)) return 0; if (keys.control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP) hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP) hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst; } else if (keys.control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP) hash_keys.addrs.v6addrs.src = keys.addrs.v6addrs.src; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP) hash_keys.addrs.v6addrs.dst = keys.addrs.v6addrs.dst; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_FLOWLABEL) hash_keys.tags.flow_label = keys.tags.flow_label; } if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_IP_PROTO) hash_keys.basic.ip_proto = keys.basic.ip_proto; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_PORT) hash_keys.ports.src = keys.ports.src; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_PORT) hash_keys.ports.dst = keys.ports.dst; return fib_multipath_hash_from_keys(net, &hash_keys); } static u32 fib_multipath_custom_hash_skb(const struct net *net, const struct sk_buff *skb) { u32 mhash, mhash_inner; bool has_inner = true; mhash = fib_multipath_custom_hash_outer(net, skb, &has_inner); mhash_inner = fib_multipath_custom_hash_inner(net, skb, has_inner); return jhash_2words(mhash, mhash_inner, 0); } static u32 fib_multipath_custom_hash_fl4(const struct net *net, const struct flowi4 *fl4) { u32 hash_fields = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_fields); struct flow_keys hash_keys; if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_OUTER_MASK)) return 0; memset(&hash_keys, 0, sizeof(hash_keys)); hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_IP) hash_keys.addrs.v4addrs.src = fl4->saddr; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_IP) hash_keys.addrs.v4addrs.dst = fl4->daddr; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_IP_PROTO) hash_keys.basic.ip_proto = fl4->flowi4_proto; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_PORT) hash_keys.ports.src = fl4->fl4_sport; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_PORT) hash_keys.ports.dst = fl4->fl4_dport; return fib_multipath_hash_from_keys(net, &hash_keys); } /* if skb is set it will be used and fl4 can be NULL */ int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4, const struct sk_buff *skb, struct flow_keys *flkeys) { u32 multipath_hash = fl4 ? fl4->flowi4_multipath_hash : 0; struct flow_keys hash_keys; u32 mhash = 0; switch (READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_policy)) { case 0: memset(&hash_keys, 0, sizeof(hash_keys)); hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; if (skb) { ip_multipath_l3_keys(skb, &hash_keys); } else { hash_keys.addrs.v4addrs.src = fl4->saddr; hash_keys.addrs.v4addrs.dst = fl4->daddr; } mhash = fib_multipath_hash_from_keys(net, &hash_keys); break; case 1: /* skb is currently provided only when forwarding */ if (skb) { unsigned int flag = FLOW_DISSECTOR_F_STOP_AT_ENCAP; struct flow_keys keys; /* short-circuit if we already have L4 hash present */ if (skb->l4_hash) return skb_get_hash_raw(skb) >> 1; memset(&hash_keys, 0, sizeof(hash_keys)); if (!flkeys) { skb_flow_dissect_flow_keys(skb, &keys, flag); flkeys = &keys; } hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; hash_keys.addrs.v4addrs.src = flkeys->addrs.v4addrs.src; hash_keys.addrs.v4addrs.dst = flkeys->addrs.v4addrs.dst; hash_keys.ports.src = flkeys->ports.src; hash_keys.ports.dst = flkeys->ports.dst; hash_keys.basic.ip_proto = flkeys->basic.ip_proto; } else { memset(&hash_keys, 0, sizeof(hash_keys)); hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; hash_keys.addrs.v4addrs.src = fl4->saddr; hash_keys.addrs.v4addrs.dst = fl4->daddr; hash_keys.ports.src = fl4->fl4_sport; hash_keys.ports.dst = fl4->fl4_dport; hash_keys.basic.ip_proto = fl4->flowi4_proto; } mhash = fib_multipath_hash_from_keys(net, &hash_keys); break; case 2: memset(&hash_keys, 0, sizeof(hash_keys)); /* skb is currently provided only when forwarding */ if (skb) { struct flow_keys keys; skb_flow_dissect_flow_keys(skb, &keys, 0); /* Inner can be v4 or v6 */ if (keys.control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src; hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst; } else if (keys.control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; hash_keys.addrs.v6addrs.src = keys.addrs.v6addrs.src; hash_keys.addrs.v6addrs.dst = keys.addrs.v6addrs.dst; hash_keys.tags.flow_label = keys.tags.flow_label; hash_keys.basic.ip_proto = keys.basic.ip_proto; } else { /* Same as case 0 */ hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; ip_multipath_l3_keys(skb, &hash_keys); } } else { /* Same as case 0 */ hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; hash_keys.addrs.v4addrs.src = fl4->saddr; hash_keys.addrs.v4addrs.dst = fl4->daddr; } mhash = fib_multipath_hash_from_keys(net, &hash_keys); break; case 3: if (skb) mhash = fib_multipath_custom_hash_skb(net, skb); else mhash = fib_multipath_custom_hash_fl4(net, fl4); break; } if (multipath_hash) mhash = jhash_2words(mhash, multipath_hash, 0); return mhash >> 1; } #endif /* CONFIG_IP_ROUTE_MULTIPATH */ static enum skb_drop_reason ip_mkroute_input(struct sk_buff *skb, struct fib_result *res, struct in_device *in_dev, __be32 daddr, __be32 saddr, dscp_t dscp, struct flow_keys *hkeys) { #ifdef CONFIG_IP_ROUTE_MULTIPATH if (res->fi && fib_info_num_path(res->fi) > 1) { int h = fib_multipath_hash(res->fi->fib_net, NULL, skb, hkeys); fib_select_multipath(res, h); IPCB(skb)->flags |= IPSKB_MULTIPATH; } #endif /* create a routing cache entry */ return __mkroute_input(skb, res, in_dev, daddr, saddr, dscp); } /* Implements all the saddr-related checks as ip_route_input_slow(), * assuming daddr is valid and the destination is not a local broadcast one. * Uses the provided hint instead of performing a route lookup. */ enum skb_drop_reason ip_route_use_hint(struct sk_buff *skb, __be32 daddr, __be32 saddr, dscp_t dscp, struct net_device *dev, const struct sk_buff *hint) { enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED; struct in_device *in_dev = __in_dev_get_rcu(dev); struct rtable *rt = skb_rtable(hint); struct net *net = dev_net(dev); u32 tag = 0; if (!in_dev) return reason; if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr)) { reason = SKB_DROP_REASON_IP_INVALID_SOURCE; goto martian_source; } if (ipv4_is_zeronet(saddr)) { reason = SKB_DROP_REASON_IP_INVALID_SOURCE; goto martian_source; } if (ipv4_is_loopback(saddr) && !IN_DEV_NET_ROUTE_LOCALNET(in_dev, net)) { reason = SKB_DROP_REASON_IP_LOCALNET; goto martian_source; } if (rt->rt_type != RTN_LOCAL) goto skip_validate_source; reason = fib_validate_source_reason(skb, saddr, daddr, dscp, 0, dev, in_dev, &tag); if (reason) goto martian_source; skip_validate_source: skb_dst_copy(skb, hint); return SKB_NOT_DROPPED_YET; martian_source: ip_handle_martian_source(dev, in_dev, skb, daddr, saddr); return reason; } /* get device for dst_alloc with local routes */ static struct net_device *ip_rt_get_dev(struct net *net, const struct fib_result *res) { struct fib_nh_common *nhc = res->fi ? res->nhc : NULL; struct net_device *dev = NULL; if (nhc) dev = l3mdev_master_dev_rcu(nhc->nhc_dev); return dev ? : net->loopback_dev; } /* * NOTE. We drop all the packets that has local source * addresses, because every properly looped back packet * must have correct destination already attached by output routine. * Changes in the enforced policies must be applied also to * ip_route_use_hint(). * * Such approach solves two big problems: * 1. Not simplex devices are handled properly. * 2. IP spoofing attempts are filtered with 100% of guarantee. * called with rcu_read_lock() */ static enum skb_drop_reason ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, dscp_t dscp, struct net_device *dev, struct fib_result *res) { enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED; struct in_device *in_dev = __in_dev_get_rcu(dev); struct flow_keys *flkeys = NULL, _flkeys; struct net *net = dev_net(dev); struct ip_tunnel_info *tun_info; int err = -EINVAL; unsigned int flags = 0; u32 itag = 0; struct rtable *rth; struct flowi4 fl4; bool do_cache = true; /* IP on this device is disabled. */ if (!in_dev) goto out; /* Check for the most weird martians, which can be not detected * by fib_lookup. */ tun_info = skb_tunnel_info(skb); if (tun_info && !(tun_info->mode & IP_TUNNEL_INFO_TX)) fl4.flowi4_tun_key.tun_id = tun_info->key.tun_id; else fl4.flowi4_tun_key.tun_id = 0; skb_dst_drop(skb); if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr)) { reason = SKB_DROP_REASON_IP_INVALID_SOURCE; goto martian_source; } res->fi = NULL; res->table = NULL; if (ipv4_is_lbcast(daddr) || (saddr == 0 && daddr == 0)) goto brd_input; /* Accept zero addresses only to limited broadcast; * I even do not know to fix it or not. Waiting for complains :-) */ if (ipv4_is_zeronet(saddr)) { reason = SKB_DROP_REASON_IP_INVALID_SOURCE; goto martian_source; } if (ipv4_is_zeronet(daddr)) { reason = SKB_DROP_REASON_IP_INVALID_DEST; goto martian_destination; } /* Following code try to avoid calling IN_DEV_NET_ROUTE_LOCALNET(), * and call it once if daddr or/and saddr are loopback addresses */ if (ipv4_is_loopback(daddr)) { if (!IN_DEV_NET_ROUTE_LOCALNET(in_dev, net)) { reason = SKB_DROP_REASON_IP_LOCALNET; goto martian_destination; } } else if (ipv4_is_loopback(saddr)) { if (!IN_DEV_NET_ROUTE_LOCALNET(in_dev, net)) { reason = SKB_DROP_REASON_IP_LOCALNET; goto martian_source; } } /* * Now we are ready to route packet. */ fl4.flowi4_l3mdev = 0; fl4.flowi4_oif = 0; fl4.flowi4_iif = dev->ifindex; fl4.flowi4_mark = skb->mark; fl4.flowi4_tos = inet_dscp_to_dsfield(dscp); fl4.flowi4_scope = RT_SCOPE_UNIVERSE; fl4.flowi4_flags = 0; fl4.daddr = daddr; fl4.saddr = saddr; fl4.flowi4_uid = sock_net_uid(net, NULL); fl4.flowi4_multipath_hash = 0; if (fib4_rules_early_flow_dissect(net, skb, &fl4, &_flkeys)) { flkeys = &_flkeys; } else { fl4.flowi4_proto = 0; fl4.fl4_sport = 0; fl4.fl4_dport = 0; } err = fib_lookup(net, &fl4, res, 0); if (err != 0) { if (!IN_DEV_FORWARD(in_dev)) err = -EHOSTUNREACH; goto no_route; } if (res->type == RTN_BROADCAST) { if (IN_DEV_BFORWARD(in_dev)) goto make_route; /* not do cache if bc_forwarding is enabled */ if (IPV4_DEVCONF_ALL_RO(net, BC_FORWARDING)) do_cache = false; goto brd_input; } err = -EINVAL; if (res->type == RTN_LOCAL) { reason = fib_validate_source_reason(skb, saddr, daddr, dscp, 0, dev, in_dev, &itag); if (reason) goto martian_source; goto local_input; } if (!IN_DEV_FORWARD(in_dev)) { err = -EHOSTUNREACH; goto no_route; } if (res->type != RTN_UNICAST) { reason = SKB_DROP_REASON_IP_INVALID_DEST; goto martian_destination; } make_route: reason = ip_mkroute_input(skb, res, in_dev, daddr, saddr, dscp, flkeys); out: return reason; brd_input: if (skb->protocol != htons(ETH_P_IP)) { reason = SKB_DROP_REASON_INVALID_PROTO; goto out; } if (!ipv4_is_zeronet(saddr)) { reason = fib_validate_source_reason(skb, saddr, 0, dscp, 0, dev, in_dev, &itag); if (reason) goto martian_source; } flags |= RTCF_BROADCAST; res->type = RTN_BROADCAST; RT_CACHE_STAT_INC(in_brd); local_input: if (IN_DEV_ORCONF(in_dev, NOPOLICY)) IPCB(skb)->flags |= IPSKB_NOPOLICY; do_cache &= res->fi && !itag; if (do_cache) { struct fib_nh_common *nhc = FIB_RES_NHC(*res); rth = rcu_dereference(nhc->nhc_rth_input); if (rt_cache_valid(rth)) { skb_dst_set_noref(skb, &rth->dst); reason = SKB_NOT_DROPPED_YET; goto out; } } rth = rt_dst_alloc(ip_rt_get_dev(net, res), flags | RTCF_LOCAL, res->type, false); if (!rth) goto e_nobufs; rth->dst.output= ip_rt_bug; #ifdef CONFIG_IP_ROUTE_CLASSID rth->dst.tclassid = itag; #endif rth->rt_is_input = 1; RT_CACHE_STAT_INC(in_slow_tot); if (res->type == RTN_UNREACHABLE) { rth->dst.input= ip_error; rth->dst.error= -err; rth->rt_flags &= ~RTCF_LOCAL; } if (do_cache) { struct fib_nh_common *nhc = FIB_RES_NHC(*res); rth->dst.lwtstate = lwtstate_get(nhc->nhc_lwtstate); if (lwtunnel_input_redirect(rth->dst.lwtstate)) { WARN_ON(rth->dst.input == lwtunnel_input); rth->dst.lwtstate->orig_input = rth->dst.input; rth->dst.input = lwtunnel_input; } if (unlikely(!rt_cache_route(nhc, rth))) rt_add_uncached_list(rth); } skb_dst_set(skb, &rth->dst); reason = SKB_NOT_DROPPED_YET; goto out; no_route: RT_CACHE_STAT_INC(in_no_route); res->type = RTN_UNREACHABLE; res->fi = NULL; res->table = NULL; goto local_input; /* * Do not cache martian addresses: they should be logged (RFC1812) */ martian_destination: RT_CACHE_STAT_INC(in_martian_dst); #ifdef CONFIG_IP_ROUTE_VERBOSE if (IN_DEV_LOG_MARTIANS(in_dev)) net_warn_ratelimited("martian destination %pI4 from %pI4, dev %s\n", &daddr, &saddr, dev->name); #endif goto out; e_nobufs: reason = SKB_DROP_REASON_NOMEM; goto out; martian_source: ip_handle_martian_source(dev, in_dev, skb, daddr, saddr); goto out; } /* called with rcu_read_lock held */ static enum skb_drop_reason ip_route_input_rcu(struct sk_buff *skb, __be32 daddr, __be32 saddr, dscp_t dscp, struct net_device *dev, struct fib_result *res) { /* Multicast recognition logic is moved from route cache to here. * The problem was that too many Ethernet cards have broken/missing * hardware multicast filters :-( As result the host on multicasting * network acquires a lot of useless route cache entries, sort of * SDR messages from all the world. Now we try to get rid of them. * Really, provided software IP multicast filter is organized * reasonably (at least, hashed), it does not result in a slowdown * comparing with route cache reject entries. * Note, that multicast routers are not affected, because * route cache entry is created eventually. */ if (ipv4_is_multicast(daddr)) { enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED; struct in_device *in_dev = __in_dev_get_rcu(dev); int our = 0; if (!in_dev) return reason; our = ip_check_mc_rcu(in_dev, daddr, saddr, ip_hdr(skb)->protocol); /* check l3 master if no match yet */ if (!our && netif_is_l3_slave(dev)) { struct in_device *l3_in_dev; l3_in_dev = __in_dev_get_rcu(skb->dev); if (l3_in_dev) our = ip_check_mc_rcu(l3_in_dev, daddr, saddr, ip_hdr(skb)->protocol); } if (our #ifdef CONFIG_IP_MROUTE || (!ipv4_is_local_multicast(daddr) && IN_DEV_MFORWARD(in_dev)) #endif ) { reason = ip_route_input_mc(skb, daddr, saddr, dscp, dev, our); } return reason; } return ip_route_input_slow(skb, daddr, saddr, dscp, dev, res); } enum skb_drop_reason ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr, dscp_t dscp, struct net_device *dev) { enum skb_drop_reason reason; struct fib_result res; rcu_read_lock(); reason = ip_route_input_rcu(skb, daddr, saddr, dscp, dev, &res); rcu_read_unlock(); return reason; } EXPORT_SYMBOL(ip_route_input_noref); /* called with rcu_read_lock() */ static struct rtable *__mkroute_output(const struct fib_result *res, const struct flowi4 *fl4, int orig_oif, struct net_device *dev_out, unsigned int flags) { struct fib_info *fi = res->fi; struct fib_nh_exception *fnhe; struct in_device *in_dev; u16 type = res->type; struct rtable *rth; bool do_cache; in_dev = __in_dev_get_rcu(dev_out); if (!in_dev) return ERR_PTR(-EINVAL); if (likely(!IN_DEV_ROUTE_LOCALNET(in_dev))) if (ipv4_is_loopback(fl4->saddr) && !(dev_out->flags & IFF_LOOPBACK) && !netif_is_l3_master(dev_out)) return ERR_PTR(-EINVAL); if (ipv4_is_lbcast(fl4->daddr)) type = RTN_BROADCAST; else if (ipv4_is_multicast(fl4->daddr)) type = RTN_MULTICAST; else if (ipv4_is_zeronet(fl4->daddr)) return ERR_PTR(-EINVAL); if (dev_out->flags & IFF_LOOPBACK) flags |= RTCF_LOCAL; do_cache = true; if (type == RTN_BROADCAST) { flags |= RTCF_BROADCAST | RTCF_LOCAL; fi = NULL; } else if (type == RTN_MULTICAST) { flags |= RTCF_MULTICAST | RTCF_LOCAL; if (!ip_check_mc_rcu(in_dev, fl4->daddr, fl4->saddr, fl4->flowi4_proto)) flags &= ~RTCF_LOCAL; else do_cache = false; /* If multicast route do not exist use * default one, but do not gateway in this case. * Yes, it is hack. */ if (fi && res->prefixlen < 4) fi = NULL; } else if ((type == RTN_LOCAL) && (orig_oif != 0) && (orig_oif != dev_out->ifindex)) { /* For local routes that require a particular output interface * we do not want to cache the result. Caching the result * causes incorrect behaviour when there are multiple source * addresses on the interface, the end result being that if the * intended recipient is waiting on that interface for the * packet he won't receive it because it will be delivered on * the loopback interface and the IP_PKTINFO ipi_ifindex will * be set to the loopback interface as well. */ do_cache = false; } fnhe = NULL; do_cache &= fi != NULL; if (fi) { struct fib_nh_common *nhc = FIB_RES_NHC(*res); struct rtable __rcu **prth; fnhe = find_exception(nhc, fl4->daddr); if (!do_cache) goto add; if (fnhe) { prth = &fnhe->fnhe_rth_output; } else { if (unlikely(fl4->flowi4_flags & FLOWI_FLAG_KNOWN_NH && !(nhc->nhc_gw_family && nhc->nhc_scope == RT_SCOPE_LINK))) { do_cache = false; goto add; } prth = raw_cpu_ptr(nhc->nhc_pcpu_rth_output); } rth = rcu_dereference(*prth); if (rt_cache_valid(rth) && dst_hold_safe(&rth->dst)) return rth; } add: rth = rt_dst_alloc(dev_out, flags, type, IN_DEV_ORCONF(in_dev, NOXFRM)); if (!rth) return ERR_PTR(-ENOBUFS); rth->rt_iif = orig_oif; RT_CACHE_STAT_INC(out_slow_tot); if (flags & (RTCF_BROADCAST | RTCF_MULTICAST)) { if (flags & RTCF_LOCAL && !(dev_out->flags & IFF_LOOPBACK)) { rth->dst.output = ip_mc_output; RT_CACHE_STAT_INC(out_slow_mc); } #ifdef CONFIG_IP_MROUTE if (type == RTN_MULTICAST) { if (IN_DEV_MFORWARD(in_dev) && !ipv4_is_local_multicast(fl4->daddr)) { rth->dst.input = ip_mr_input; rth->dst.output = ip_mc_output; } } #endif } rt_set_nexthop(rth, fl4->daddr, res, fnhe, fi, type, 0, do_cache); lwtunnel_set_redirect(&rth->dst); return rth; } /* * Major route resolver routine. */ struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *fl4, const struct sk_buff *skb) { struct fib_result res = { .type = RTN_UNSPEC, .fi = NULL, .table = NULL, .tclassid = 0, }; struct rtable *rth; fl4->flowi4_iif = LOOPBACK_IFINDEX; fl4->flowi4_tos &= INET_DSCP_MASK; rcu_read_lock(); rth = ip_route_output_key_hash_rcu(net, fl4, &res, skb); rcu_read_unlock(); return rth; } EXPORT_SYMBOL_GPL(ip_route_output_key_hash); struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *fl4, struct fib_result *res, const struct sk_buff *skb) { struct net_device *dev_out = NULL; int orig_oif = fl4->flowi4_oif; unsigned int flags = 0; struct rtable *rth; int err; if (fl4->saddr) { if (ipv4_is_multicast(fl4->saddr) || ipv4_is_lbcast(fl4->saddr) || ipv4_is_zeronet(fl4->saddr)) { rth = ERR_PTR(-EINVAL); goto out; } rth = ERR_PTR(-ENETUNREACH); /* I removed check for oif == dev_out->oif here. * It was wrong for two reasons: * 1. ip_dev_find(net, saddr) can return wrong iface, if saddr * is assigned to multiple interfaces. * 2. Moreover, we are allowed to send packets with saddr * of another iface. --ANK */ if (fl4->flowi4_oif == 0 && (ipv4_is_multicast(fl4->daddr) || ipv4_is_lbcast(fl4->daddr))) { /* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */ dev_out = __ip_dev_find(net, fl4->saddr, false); if (!dev_out) goto out; /* Special hack: user can direct multicasts * and limited broadcast via necessary interface * without fiddling with IP_MULTICAST_IF or IP_PKTINFO. * This hack is not just for fun, it allows * vic,vat and friends to work. * They bind socket to loopback, set ttl to zero * and expect that it will work. * From the viewpoint of routing cache they are broken, * because we are not allowed to build multicast path * with loopback source addr (look, routing cache * cannot know, that ttl is zero, so that packet * will not leave this host and route is valid). * Luckily, this hack is good workaround. */ fl4->flowi4_oif = dev_out->ifindex; goto make_route; } if (!(fl4->flowi4_flags & FLOWI_FLAG_ANYSRC)) { /* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */ if (!__ip_dev_find(net, fl4->saddr, false)) goto out; } } if (fl4->flowi4_oif) { dev_out = dev_get_by_index_rcu(net, fl4->flowi4_oif); rth = ERR_PTR(-ENODEV); if (!dev_out) goto out; /* RACE: Check return value of inet_select_addr instead. */ if (!(dev_out->flags & IFF_UP) || !__in_dev_get_rcu(dev_out)) { rth = ERR_PTR(-ENETUNREACH); goto out; } if (ipv4_is_local_multicast(fl4->daddr) || ipv4_is_lbcast(fl4->daddr) || fl4->flowi4_proto == IPPROTO_IGMP) { if (!fl4->saddr) fl4->saddr = inet_select_addr(dev_out, 0, RT_SCOPE_LINK); goto make_route; } if (!fl4->saddr) { if (ipv4_is_multicast(fl4->daddr)) fl4->saddr = inet_select_addr(dev_out, 0, fl4->flowi4_scope); else if (!fl4->daddr) fl4->saddr = inet_select_addr(dev_out, 0, RT_SCOPE_HOST); } } if (!fl4->daddr) { fl4->daddr = fl4->saddr; if (!fl4->daddr) fl4->daddr = fl4->saddr = htonl(INADDR_LOOPBACK); dev_out = net->loopback_dev; fl4->flowi4_oif = LOOPBACK_IFINDEX; res->type = RTN_LOCAL; flags |= RTCF_LOCAL; goto make_route; } err = fib_lookup(net, fl4, res, 0); if (err) { res->fi = NULL; res->table = NULL; if (fl4->flowi4_oif && (ipv4_is_multicast(fl4->daddr) || !fl4->flowi4_l3mdev)) { /* Apparently, routing tables are wrong. Assume, * that the destination is on link. * * WHY? DW. * Because we are allowed to send to iface * even if it has NO routes and NO assigned * addresses. When oif is specified, routing * tables are looked up with only one purpose: * to catch if destination is gatewayed, rather than * direct. Moreover, if MSG_DONTROUTE is set, * we send packet, ignoring both routing tables * and ifaddr state. --ANK * * * We could make it even if oif is unknown, * likely IPv6, but we do not. */ if (fl4->saddr == 0) fl4->saddr = inet_select_addr(dev_out, 0, RT_SCOPE_LINK); res->type = RTN_UNICAST; goto make_route; } rth = ERR_PTR(err); goto out; } if (res->type == RTN_LOCAL) { if (!fl4->saddr) { if (res->fi->fib_prefsrc) fl4->saddr = res->fi->fib_prefsrc; else fl4->saddr = fl4->daddr; } /* L3 master device is the loopback for that domain */ dev_out = l3mdev_master_dev_rcu(FIB_RES_DEV(*res)) ? : net->loopback_dev; /* make sure orig_oif points to fib result device even * though packet rx/tx happens over loopback or l3mdev */ orig_oif = FIB_RES_OIF(*res); fl4->flowi4_oif = dev_out->ifindex; flags |= RTCF_LOCAL; goto make_route; } fib_select_path(net, res, fl4, skb); dev_out = FIB_RES_DEV(*res); make_route: rth = __mkroute_output(res, fl4, orig_oif, dev_out, flags); out: return rth; } static struct dst_ops ipv4_dst_blackhole_ops = { .family = AF_INET, .default_advmss = ipv4_default_advmss, .neigh_lookup = ipv4_neigh_lookup, .check = dst_blackhole_check, .cow_metrics = dst_blackhole_cow_metrics, .update_pmtu = dst_blackhole_update_pmtu, .redirect = dst_blackhole_redirect, .mtu = dst_blackhole_mtu, }; struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_orig) { struct rtable *ort = dst_rtable(dst_orig); struct rtable *rt; rt = dst_alloc(&ipv4_dst_blackhole_ops, NULL, DST_OBSOLETE_DEAD, 0); if (rt) { struct dst_entry *new = &rt->dst; new->__use = 1; new->input = dst_discard; new->output = dst_discard_out; new->dev = net->loopback_dev; netdev_hold(new->dev, &new->dev_tracker, GFP_ATOMIC); rt->rt_is_input = ort->rt_is_input; rt->rt_iif = ort->rt_iif; rt->rt_pmtu = ort->rt_pmtu; rt->rt_mtu_locked = ort->rt_mtu_locked; rt->rt_genid = rt_genid_ipv4(net); rt->rt_flags = ort->rt_flags; rt->rt_type = ort->rt_type; rt->rt_uses_gateway = ort->rt_uses_gateway; rt->rt_gw_family = ort->rt_gw_family; if (rt->rt_gw_family == AF_INET) rt->rt_gw4 = ort->rt_gw4; else if (rt->rt_gw_family == AF_INET6) rt->rt_gw6 = ort->rt_gw6; } dst_release(dst_orig); return rt ? &rt->dst : ERR_PTR(-ENOMEM); } struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4, const struct sock *sk) { struct rtable *rt = __ip_route_output_key(net, flp4); if (IS_ERR(rt)) return rt; if (flp4->flowi4_proto) { flp4->flowi4_oif = rt->dst.dev->ifindex; rt = dst_rtable(xfrm_lookup_route(net, &rt->dst, flowi4_to_flowi(flp4), sk, 0)); } return rt; } EXPORT_SYMBOL_GPL(ip_route_output_flow); /* called with rcu_read_lock held */ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, struct rtable *rt, u32 table_id, dscp_t dscp, struct flowi4 *fl4, struct sk_buff *skb, u32 portid, u32 seq, unsigned int flags) { struct rtmsg *r; struct nlmsghdr *nlh; unsigned long expires = 0; u32 error; u32 metrics[RTAX_MAX]; nlh = nlmsg_put(skb, portid, seq, RTM_NEWROUTE, sizeof(*r), flags); if (!nlh) return -EMSGSIZE; r = nlmsg_data(nlh); r->rtm_family = AF_INET; r->rtm_dst_len = 32; r->rtm_src_len = 0; r->rtm_tos = inet_dscp_to_dsfield(dscp); r->rtm_table = table_id < 256 ? table_id : RT_TABLE_COMPAT; if (nla_put_u32(skb, RTA_TABLE, table_id)) goto nla_put_failure; r->rtm_type = rt->rt_type; r->rtm_scope = RT_SCOPE_UNIVERSE; r->rtm_protocol = RTPROT_UNSPEC; r->rtm_flags = (rt->rt_flags & ~0xFFFF) | RTM_F_CLONED; if (rt->rt_flags & RTCF_NOTIFY) r->rtm_flags |= RTM_F_NOTIFY; if (IPCB(skb)->flags & IPSKB_DOREDIRECT) r->rtm_flags |= RTCF_DOREDIRECT; if (nla_put_in_addr(skb, RTA_DST, dst)) goto nla_put_failure; if (src) { r->rtm_src_len = 32; if (nla_put_in_addr(skb, RTA_SRC, src)) goto nla_put_failure; } if (rt->dst.dev && nla_put_u32(skb, RTA_OIF, rt->dst.dev->ifindex)) goto nla_put_failure; if (rt->dst.lwtstate && lwtunnel_fill_encap(skb, rt->dst.lwtstate, RTA_ENCAP, RTA_ENCAP_TYPE) < 0) goto nla_put_failure; #ifdef CONFIG_IP_ROUTE_CLASSID if (rt->dst.tclassid && nla_put_u32(skb, RTA_FLOW, rt->dst.tclassid)) goto nla_put_failure; #endif if (fl4 && !rt_is_input_route(rt) && fl4->saddr != src) { if (nla_put_in_addr(skb, RTA_PREFSRC, fl4->saddr)) goto nla_put_failure; } if (rt->rt_uses_gateway) { if (rt->rt_gw_family == AF_INET && nla_put_in_addr(skb, RTA_GATEWAY, rt->rt_gw4)) { goto nla_put_failure; } else if (rt->rt_gw_family == AF_INET6) { int alen = sizeof(struct in6_addr); struct nlattr *nla; struct rtvia *via; nla = nla_reserve(skb, RTA_VIA, alen + 2); if (!nla) goto nla_put_failure; via = nla_data(nla); via->rtvia_family = AF_INET6; memcpy(via->rtvia_addr, &rt->rt_gw6, alen); } } expires = rt->dst.expires; if (expires) { unsigned long now = jiffies; if (time_before(now, expires)) expires -= now; else expires = 0; } memcpy(metrics, dst_metrics_ptr(&rt->dst), sizeof(metrics)); if (rt->rt_pmtu && expires) metrics[RTAX_MTU - 1] = rt->rt_pmtu; if (rt->rt_mtu_locked && expires) metrics[RTAX_LOCK - 1] |= BIT(RTAX_MTU); if (rtnetlink_put_metrics(skb, metrics) < 0) goto nla_put_failure; if (fl4) { if (fl4->flowi4_mark && nla_put_u32(skb, RTA_MARK, fl4->flowi4_mark)) goto nla_put_failure; if (!uid_eq(fl4->flowi4_uid, INVALID_UID) && nla_put_u32(skb, RTA_UID, from_kuid_munged(current_user_ns(), fl4->flowi4_uid))) goto nla_put_failure; if (rt_is_input_route(rt)) { #ifdef CONFIG_IP_MROUTE if (ipv4_is_multicast(dst) && !ipv4_is_local_multicast(dst) && IPV4_DEVCONF_ALL_RO(net, MC_FORWARDING)) { int err = ipmr_get_route(net, skb, fl4->saddr, fl4->daddr, r, portid); if (err <= 0) { if (err == 0) return 0; goto nla_put_failure; } } else #endif if (nla_put_u32(skb, RTA_IIF, fl4->flowi4_iif)) goto nla_put_failure; } } error = rt->dst.error; if (rtnl_put_cacheinfo(skb, &rt->dst, 0, expires, error) < 0) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static int fnhe_dump_bucket(struct net *net, struct sk_buff *skb, struct netlink_callback *cb, u32 table_id, struct fnhe_hash_bucket *bucket, int genid, int *fa_index, int fa_start, unsigned int flags) { int i; for (i = 0; i < FNHE_HASH_SIZE; i++) { struct fib_nh_exception *fnhe; for (fnhe = rcu_dereference(bucket[i].chain); fnhe; fnhe = rcu_dereference(fnhe->fnhe_next)) { struct rtable *rt; int err; if (*fa_index < fa_start) goto next; if (fnhe->fnhe_genid != genid) goto next; if (fnhe->fnhe_expires && time_after(jiffies, fnhe->fnhe_expires)) goto next; rt = rcu_dereference(fnhe->fnhe_rth_input); if (!rt) rt = rcu_dereference(fnhe->fnhe_rth_output); if (!rt) goto next; err = rt_fill_info(net, fnhe->fnhe_daddr, 0, rt, table_id, 0, NULL, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, flags); if (err) return err; next: (*fa_index)++; } } return 0; } int fib_dump_info_fnhe(struct sk_buff *skb, struct netlink_callback *cb, u32 table_id, struct fib_info *fi, int *fa_index, int fa_start, unsigned int flags) { struct net *net = sock_net(cb->skb->sk); int nhsel, genid = fnhe_genid(net); for (nhsel = 0; nhsel < fib_info_num_path(fi); nhsel++) { struct fib_nh_common *nhc = fib_info_nhc(fi, nhsel); struct fnhe_hash_bucket *bucket; int err; if (nhc->nhc_flags & RTNH_F_DEAD) continue; rcu_read_lock(); bucket = rcu_dereference(nhc->nhc_exceptions); err = 0; if (bucket) err = fnhe_dump_bucket(net, skb, cb, table_id, bucket, genid, fa_index, fa_start, flags); rcu_read_unlock(); if (err) return err; } return 0; } static struct sk_buff *inet_rtm_getroute_build_skb(__be32 src, __be32 dst, u8 ip_proto, __be16 sport, __be16 dport) { struct sk_buff *skb; struct iphdr *iph; skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) return NULL; /* Reserve room for dummy headers, this skb can pass * through good chunk of routing engine. */ skb_reset_mac_header(skb); skb_reset_network_header(skb); skb->protocol = htons(ETH_P_IP); iph = skb_put(skb, sizeof(struct iphdr)); iph->protocol = ip_proto; iph->saddr = src; iph->daddr = dst; iph->version = 0x4; iph->frag_off = 0; iph->ihl = 0x5; skb_set_transport_header(skb, skb->len); switch (iph->protocol) { case IPPROTO_UDP: { struct udphdr *udph; udph = skb_put_zero(skb, sizeof(struct udphdr)); udph->source = sport; udph->dest = dport; udph->len = htons(sizeof(struct udphdr)); udph->check = 0; break; } case IPPROTO_TCP: { struct tcphdr *tcph; tcph = skb_put_zero(skb, sizeof(struct tcphdr)); tcph->source = sport; tcph->dest = dport; tcph->doff = sizeof(struct tcphdr) / 4; tcph->rst = 1; tcph->check = ~tcp_v4_check(sizeof(struct tcphdr), src, dst, 0); break; } case IPPROTO_ICMP: { struct icmphdr *icmph; icmph = skb_put_zero(skb, sizeof(struct icmphdr)); icmph->type = ICMP_ECHO; icmph->code = 0; } } return skb; } static int inet_rtm_valid_getroute_req(struct sk_buff *skb, const struct nlmsghdr *nlh, struct nlattr **tb, struct netlink_ext_ack *extack) { struct rtmsg *rtm; int i, err; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*rtm))) { NL_SET_ERR_MSG(extack, "ipv4: Invalid header for route get request"); return -EINVAL; } if (!netlink_strict_get_check(skb)) return nlmsg_parse_deprecated(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy, extack); rtm = nlmsg_data(nlh); if ((rtm->rtm_src_len && rtm->rtm_src_len != 32) || (rtm->rtm_dst_len && rtm->rtm_dst_len != 32) || rtm->rtm_table || rtm->rtm_protocol || rtm->rtm_scope || rtm->rtm_type) { NL_SET_ERR_MSG(extack, "ipv4: Invalid values in header for route get request"); return -EINVAL; } if (rtm->rtm_flags & ~(RTM_F_NOTIFY | RTM_F_LOOKUP_TABLE | RTM_F_FIB_MATCH)) { NL_SET_ERR_MSG(extack, "ipv4: Unsupported rtm_flags for route get request"); return -EINVAL; } err = nlmsg_parse_deprecated_strict(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy, extack); if (err) return err; if ((tb[RTA_SRC] && !rtm->rtm_src_len) || (tb[RTA_DST] && !rtm->rtm_dst_len)) { NL_SET_ERR_MSG(extack, "ipv4: rtm_src_len and rtm_dst_len must be 32 for IPv4"); return -EINVAL; } for (i = 0; i <= RTA_MAX; i++) { if (!tb[i]) continue; switch (i) { case RTA_IIF: case RTA_OIF: case RTA_SRC: case RTA_DST: case RTA_IP_PROTO: case RTA_SPORT: case RTA_DPORT: case RTA_MARK: case RTA_UID: break; default: NL_SET_ERR_MSG(extack, "ipv4: Unsupported attribute in route get request"); return -EINVAL; } } return 0; } static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(in_skb->sk); struct nlattr *tb[RTA_MAX+1]; u32 table_id = RT_TABLE_MAIN; __be16 sport = 0, dport = 0; struct fib_result res = {}; u8 ip_proto = IPPROTO_UDP; struct rtable *rt = NULL; struct sk_buff *skb; struct rtmsg *rtm; struct flowi4 fl4 = {}; __be32 dst = 0; __be32 src = 0; kuid_t uid; u32 iif; int err; int mark; err = inet_rtm_valid_getroute_req(in_skb, nlh, tb, extack); if (err < 0) return err; rtm = nlmsg_data(nlh); src = nla_get_in_addr_default(tb[RTA_SRC], 0); dst = nla_get_in_addr_default(tb[RTA_DST], 0); iif = nla_get_u32_default(tb[RTA_IIF], 0); mark = nla_get_u32_default(tb[RTA_MARK], 0); if (tb[RTA_UID]) uid = make_kuid(current_user_ns(), nla_get_u32(tb[RTA_UID])); else uid = (iif ? INVALID_UID : current_uid()); if (tb[RTA_IP_PROTO]) { err = rtm_getroute_parse_ip_proto(tb[RTA_IP_PROTO], &ip_proto, AF_INET, extack); if (err) return err; } if (tb[RTA_SPORT]) sport = nla_get_be16(tb[RTA_SPORT]); if (tb[RTA_DPORT]) dport = nla_get_be16(tb[RTA_DPORT]); skb = inet_rtm_getroute_build_skb(src, dst, ip_proto, sport, dport); if (!skb) return -ENOBUFS; fl4.daddr = dst; fl4.saddr = src; fl4.flowi4_tos = rtm->rtm_tos & INET_DSCP_MASK; fl4.flowi4_oif = nla_get_u32_default(tb[RTA_OIF], 0); fl4.flowi4_mark = mark; fl4.flowi4_uid = uid; if (sport) fl4.fl4_sport = sport; if (dport) fl4.fl4_dport = dport; fl4.flowi4_proto = ip_proto; rcu_read_lock(); if (iif) { struct net_device *dev; dev = dev_get_by_index_rcu(net, iif); if (!dev) { err = -ENODEV; goto errout_rcu; } fl4.flowi4_iif = iif; /* for rt_fill_info */ skb->dev = dev; skb->mark = mark; err = ip_route_input_rcu(skb, dst, src, inet_dsfield_to_dscp(rtm->rtm_tos), dev, &res) ? -EINVAL : 0; rt = skb_rtable(skb); if (err == 0 && rt->dst.error) err = -rt->dst.error; } else { fl4.flowi4_iif = LOOPBACK_IFINDEX; skb->dev = net->loopback_dev; rt = ip_route_output_key_hash_rcu(net, &fl4, &res, skb); err = 0; if (IS_ERR(rt)) err = PTR_ERR(rt); else skb_dst_set(skb, &rt->dst); } if (err) goto errout_rcu; if (rtm->rtm_flags & RTM_F_NOTIFY) rt->rt_flags |= RTCF_NOTIFY; if (rtm->rtm_flags & RTM_F_LOOKUP_TABLE) table_id = res.table ? res.table->tb_id : 0; /* reset skb for netlink reply msg */ skb_trim(skb, 0); skb_reset_network_header(skb); skb_reset_transport_header(skb); skb_reset_mac_header(skb); if (rtm->rtm_flags & RTM_F_FIB_MATCH) { struct fib_rt_info fri; if (!res.fi) { err = fib_props[res.type].error; if (!err) err = -EHOSTUNREACH; goto errout_rcu; } fri.fi = res.fi; fri.tb_id = table_id; fri.dst = res.prefix; fri.dst_len = res.prefixlen; fri.dscp = res.dscp; fri.type = rt->rt_type; fri.offload = 0; fri.trap = 0; fri.offload_failed = 0; if (res.fa_head) { struct fib_alias *fa; hlist_for_each_entry_rcu(fa, res.fa_head, fa_list) { u8 slen = 32 - fri.dst_len; if (fa->fa_slen == slen && fa->tb_id == fri.tb_id && fa->fa_dscp == fri.dscp && fa->fa_info == res.fi && fa->fa_type == fri.type) { fri.offload = READ_ONCE(fa->offload); fri.trap = READ_ONCE(fa->trap); fri.offload_failed = READ_ONCE(fa->offload_failed); break; } } } err = fib_dump_info(skb, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, RTM_NEWROUTE, &fri, 0); } else { err = rt_fill_info(net, dst, src, rt, table_id, res.dscp, &fl4, skb, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, 0); } if (err < 0) goto errout_rcu; rcu_read_unlock(); err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); errout_free: return err; errout_rcu: rcu_read_unlock(); kfree_skb(skb); goto errout_free; } void ip_rt_multicast_event(struct in_device *in_dev) { rt_cache_flush(dev_net(in_dev->dev)); } #ifdef CONFIG_SYSCTL static int ip_rt_gc_interval __read_mostly = 60 * HZ; static int ip_rt_gc_min_interval __read_mostly = HZ / 2; static int ip_rt_gc_elasticity __read_mostly = 8; static int ip_min_valid_pmtu __read_mostly = IPV4_MIN_MTU; static int ipv4_sysctl_rtcache_flush(const struct ctl_table *__ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = (struct net *)__ctl->extra1; if (write) { rt_cache_flush(net); fnhe_genid_bump(net); return 0; } return -EINVAL; } static struct ctl_table ipv4_route_table[] = { { .procname = "gc_thresh", .data = &ipv4_dst_ops.gc_thresh, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "max_size", .data = &ip_rt_max_size, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { /* Deprecated. Use gc_min_interval_ms */ .procname = "gc_min_interval", .data = &ip_rt_gc_min_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "gc_min_interval_ms", .data = &ip_rt_gc_min_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_ms_jiffies, }, { .procname = "gc_timeout", .data = &ip_rt_gc_timeout, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "gc_interval", .data = &ip_rt_gc_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "redirect_load", .data = &ip_rt_redirect_load, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "redirect_number", .data = &ip_rt_redirect_number, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "redirect_silence", .data = &ip_rt_redirect_silence, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "error_cost", .data = &ip_rt_error_cost, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "error_burst", .data = &ip_rt_error_burst, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "gc_elasticity", .data = &ip_rt_gc_elasticity, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, }; static const char ipv4_route_flush_procname[] = "flush"; static struct ctl_table ipv4_route_netns_table[] = { { .procname = ipv4_route_flush_procname, .maxlen = sizeof(int), .mode = 0200, .proc_handler = ipv4_sysctl_rtcache_flush, }, { .procname = "min_pmtu", .data = &init_net.ipv4.ip_rt_min_pmtu, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &ip_min_valid_pmtu, }, { .procname = "mtu_expires", .data = &init_net.ipv4.ip_rt_mtu_expires, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "min_adv_mss", .data = &init_net.ipv4.ip_rt_min_advmss, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, }; static __net_init int sysctl_route_net_init(struct net *net) { struct ctl_table *tbl; size_t table_size = ARRAY_SIZE(ipv4_route_netns_table); tbl = ipv4_route_netns_table; if (!net_eq(net, &init_net)) { int i; tbl = kmemdup(tbl, sizeof(ipv4_route_netns_table), GFP_KERNEL); if (!tbl) goto err_dup; /* Don't export non-whitelisted sysctls to unprivileged users */ if (net->user_ns != &init_user_ns) { if (tbl[0].procname != ipv4_route_flush_procname) table_size = 0; } /* Update the variables to point into the current struct net * except for the first element flush */ for (i = 1; i < table_size; i++) tbl[i].data += (void *)net - (void *)&init_net; } tbl[0].extra1 = net; net->ipv4.route_hdr = register_net_sysctl_sz(net, "net/ipv4/route", tbl, table_size); if (!net->ipv4.route_hdr) goto err_reg; return 0; err_reg: if (tbl != ipv4_route_netns_table) kfree(tbl); err_dup: return -ENOMEM; } static __net_exit void sysctl_route_net_exit(struct net *net) { const struct ctl_table *tbl; tbl = net->ipv4.route_hdr->ctl_table_arg; unregister_net_sysctl_table(net->ipv4.route_hdr); BUG_ON(tbl == ipv4_route_netns_table); kfree(tbl); } static __net_initdata struct pernet_operations sysctl_route_ops = { .init = sysctl_route_net_init, .exit = sysctl_route_net_exit, }; #endif static __net_init int netns_ip_rt_init(struct net *net) { /* Set default value for namespaceified sysctls */ net->ipv4.ip_rt_min_pmtu = DEFAULT_MIN_PMTU; net->ipv4.ip_rt_mtu_expires = DEFAULT_MTU_EXPIRES; net->ipv4.ip_rt_min_advmss = DEFAULT_MIN_ADVMSS; return 0; } static struct pernet_operations __net_initdata ip_rt_ops = { .init = netns_ip_rt_init, }; static __net_init int rt_genid_init(struct net *net) { atomic_set(&net->ipv4.rt_genid, 0); atomic_set(&net->fnhe_genid, 0); atomic_set(&net->ipv4.dev_addr_genid, get_random_u32()); return 0; } static __net_initdata struct pernet_operations rt_genid_ops = { .init = rt_genid_init, }; static int __net_init ipv4_inetpeer_init(struct net *net) { struct inet_peer_base *bp = kmalloc(sizeof(*bp), GFP_KERNEL); if (!bp) return -ENOMEM; inet_peer_base_init(bp); net->ipv4.peers = bp; return 0; } static void __net_exit ipv4_inetpeer_exit(struct net *net) { struct inet_peer_base *bp = net->ipv4.peers; net->ipv4.peers = NULL; inetpeer_invalidate_tree(bp); kfree(bp); } static __net_initdata struct pernet_operations ipv4_inetpeer_ops = { .init = ipv4_inetpeer_init, .exit = ipv4_inetpeer_exit, }; #ifdef CONFIG_IP_ROUTE_CLASSID struct ip_rt_acct __percpu *ip_rt_acct __read_mostly; #endif /* CONFIG_IP_ROUTE_CLASSID */ static const struct rtnl_msg_handler ip_rt_rtnl_msg_handlers[] __initconst = { {.protocol = PF_INET, .msgtype = RTM_GETROUTE, .doit = inet_rtm_getroute, .flags = RTNL_FLAG_DOIT_UNLOCKED}, }; int __init ip_rt_init(void) { void *idents_hash; int cpu; /* For modern hosts, this will use 2 MB of memory */ idents_hash = alloc_large_system_hash("IP idents", sizeof(*ip_idents) + sizeof(*ip_tstamps), 0, 16, /* one bucket per 64 KB */ HASH_ZERO, NULL, &ip_idents_mask, 2048, 256*1024); ip_idents = idents_hash; get_random_bytes(ip_idents, (ip_idents_mask + 1) * sizeof(*ip_idents)); ip_tstamps = idents_hash + (ip_idents_mask + 1) * sizeof(*ip_idents); for_each_possible_cpu(cpu) { struct uncached_list *ul = &per_cpu(rt_uncached_list, cpu); INIT_LIST_HEAD(&ul->head); spin_lock_init(&ul->lock); } #ifdef CONFIG_IP_ROUTE_CLASSID ip_rt_acct = __alloc_percpu(256 * sizeof(struct ip_rt_acct), __alignof__(struct ip_rt_acct)); if (!ip_rt_acct) panic("IP: failed to allocate ip_rt_acct\n"); #endif ipv4_dst_ops.kmem_cachep = KMEM_CACHE(rtable, SLAB_HWCACHE_ALIGN | SLAB_PANIC); ipv4_dst_blackhole_ops.kmem_cachep = ipv4_dst_ops.kmem_cachep; if (dst_entries_init(&ipv4_dst_ops) < 0) panic("IP: failed to allocate ipv4_dst_ops counter\n"); if (dst_entries_init(&ipv4_dst_blackhole_ops) < 0) panic("IP: failed to allocate ipv4_dst_blackhole_ops counter\n"); ipv4_dst_ops.gc_thresh = ~0; ip_rt_max_size = INT_MAX; devinet_init(); ip_fib_init(); if (ip_rt_proc_init()) pr_err("Unable to create route proc files\n"); #ifdef CONFIG_XFRM xfrm_init(); xfrm4_init(); #endif rtnl_register_many(ip_rt_rtnl_msg_handlers); #ifdef CONFIG_SYSCTL register_pernet_subsys(&sysctl_route_ops); #endif register_pernet_subsys(&ip_rt_ops); register_pernet_subsys(&rt_genid_ops); register_pernet_subsys(&ipv4_inetpeer_ops); return 0; } #ifdef CONFIG_SYSCTL /* * We really need to sanitize the damn ipv4 init order, then all * this nonsense will go away. */ void __init ip_static_sysctl_init(void) { register_net_sysctl(&init_net, "net/ipv4/route", ipv4_route_table); } #endif
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