123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773774775776777778779780781782783784785786787788789790791792793794795796797798799800801802803804805806807808809810811812813814815816817818819820821822823824825826827828829830831832833834835836837838839840841842843844845846847848849850851852853854855856857858859860861862863864865866867868869870871872873874875876877878879880881882883884885886887888889890891892893894895896897898899900901902903904905906907908909910911912913914915916917918919920921922923924925926927928929930931932933934935936937938939940941942943944945946947948949950951952953954955956957958959960961962963964965966967968969970971972973974975976977978979980981982983984985986987988989990991992993994995996997998999100010011002100310041005100610071008100910101011101210131014101510161017101810191020102110221023102410251026102710281029103010311032103310341035103610371038103910401041104210431044104510461047104810491050105110521053105410551056105710581059106010611062106310641065106610671068106910701071107210731074107510761077107810791080108110821083108410851086108710881089109010911092109310941095109610971098109911001101110211031104110511061107110811091110111111121113111411151116111711181119112011211122112311241125112611271128112911301131113211331134113511361137113811391140114111421143114411451146114711481149115011511152115311541155115611571158115911601161116211631164116511661167116811691170117111721173117411751176117711781179118011811182118311841185118611871188118911901191119211931194119511961197119811991200120112021203120412051206120712081209121012111212121312141215121612171218121912201221122212231224122512261227122812291230123112321233123412351236123712381239124012411242124312441245124612471248124912501251125212531254125512561257125812591260126112621263126412651266126712681269127012711272127312741275127612771278127912801281128212831284128512861287128812891290129112921293129412951296129712981299130013011302130313041305130613071308130913101311131213131314131513161317131813191320132113221323132413251326132713281329133013311332133313341335133613371338133913401341134213431344134513461347134813491350135113521353135413551356135713581359136013611362136313641365136613671368136913701371137213731374137513761377137813791380138113821383138413851386138713881389139013911392139313941395139613971398139914001401140214031404140514061407140814091410141114121413141414151416141714181419142014211422142314241425142614271428142914301431143214331434143514361437143814391440144114421443144414451446144714481449145014511452145314541455145614571458145914601461146214631464146514661467146814691470147114721473147414751476147714781479148014811482148314841485148614871488148914901491149214931494149514961497149814991500150115021503150415051506150715081509151015111512151315141515151615171518151915201521152215231524152515261527152815291530153115321533153415351536153715381539154015411542154315441545154615471548154915501551155215531554155515561557155815591560156115621563156415651566156715681569157015711572157315741575157615771578157915801581158215831584158515861587158815891590159115921593159415951596159715981599160016011602160316041605160616071608160916101611161216131614161516161617161816191620162116221623162416251626162716281629163016311632163316341635163616371638163916401641164216431644164516461647164816491650165116521653165416551656165716581659166016611662166316641665166616671668166916701671167216731674167516761677167816791680168116821683168416851686168716881689169016911692169316941695169616971698169917001701170217031704170517061707170817091710171117121713171417151716171717181719172017211722172317241725172617271728172917301731173217331734173517361737173817391740174117421743174417451746174717481749175017511752175317541755175617571758175917601761176217631764176517661767176817691770177117721773177417751776177717781779178017811782178317841785178617871788178917901791179217931794179517961797179817991800180118021803180418051806180718081809181018111812181318141815181618171818181918201821182218231824182518261827182818291830183118321833183418351836183718381839184018411842184318441845184618471848184918501851185218531854185518561857185818591860186118621863186418651866186718681869187018711872187318741875187618771878187918801881188218831884188518861887188818891890189118921893189418951896189718981899190019011902190319041905190619071908190919101911191219131914191519161917191819191920192119221923192419251926192719281929193019311932193319341935193619371938193919401941194219431944194519461947194819491950195119521953195419551956195719581959196019611962196319641965196619671968196919701971197219731974197519761977197819791980198119821983198419851986198719881989199019911992199319941995199619971998199920002001200220032004200520062007200820092010201120122013201420152016201720182019202020212022202320242025202620272028202920302031203220332034203520362037203820392040204120422043204420452046204720482049205020512052205320542055205620572058205920602061206220632064206520662067206820692070207120722073207420752076207720782079208020812082208320842085208620872088208920902091209220932094209520962097209820992100210121022103210421052106210721082109211021112112211321142115211621172118211921202121212221232124212521262127212821292130213121322133213421352136213721382139214021412142214321442145214621472148214921502151215221532154215521562157215821592160216121622163216421652166216721682169217021712172217321742175217621772178217921802181218221832184218521862187218821892190219121922193219421952196219721982199220022012202220322042205220622072208220922102211221222132214221522162217221822192220222122222223222422252226222722282229223022312232223322342235223622372238223922402241224222432244224522462247224822492250225122522253225422552256225722582259226022612262226322642265226622672268226922702271227222732274227522762277227822792280228122822283228422852286228722882289229022912292229322942295229622972298229923002301230223032304230523062307230823092310231123122313231423152316231723182319232023212322232323242325232623272328232923302331233223332334233523362337233823392340234123422343234423452346234723482349235023512352235323542355235623572358235923602361236223632364236523662367236823692370237123722373237423752376237723782379238023812382238323842385238623872388238923902391239223932394239523962397239823992400240124022403240424052406240724082409241024112412241324142415241624172418241924202421242224232424242524262427242824292430243124322433243424352436243724382439244024412442244324442445244624472448244924502451245224532454245524562457245824592460246124622463246424652466246724682469247024712472247324742475247624772478247924802481248224832484248524862487248824892490249124922493249424952496249724982499250025012502250325042505250625072508250925102511251225132514251525162517251825192520252125222523252425252526252725282529253025312532253325342535253625372538253925402541254225432544254525462547254825492550255125522553255425552556255725582559256025612562256325642565256625672568256925702571257225732574257525762577257825792580258125822583258425852586258725882589259025912592259325942595259625972598259926002601260226032604260526062607260826092610261126122613261426152616261726182619262026212622262326242625262626272628262926302631263226332634263526362637263826392640264126422643264426452646264726482649265026512652265326542655265626572658265926602661266226632664266526662667266826692670267126722673267426752676267726782679268026812682268326842685268626872688268926902691269226932694269526962697269826992700270127022703270427052706270727082709271027112712271327142715271627172718271927202721272227232724272527262727272827292730273127322733273427352736273727382739274027412742274327442745274627472748274927502751275227532754275527562757275827592760276127622763276427652766276727682769277027712772277327742775277627772778277927802781278227832784278527862787278827892790279127922793279427952796279727982799280028012802280328042805280628072808280928102811281228132814281528162817281828192820282128222823282428252826282728282829283028312832283328342835283628372838283928402841284228432844284528462847284828492850285128522853285428552856285728582859286028612862286328642865286628672868286928702871287228732874287528762877287828792880288128822883288428852886288728882889289028912892289328942895289628972898289929002901290229032904290529062907290829092910291129122913291429152916291729182919292029212922292329242925292629272928292929302931293229332934293529362937293829392940294129422943294429452946294729482949295029512952295329542955295629572958295929602961296229632964296529662967296829692970297129722973297429752976297729782979298029812982298329842985298629872988298929902991299229932994299529962997299829993000300130023003300430053006300730083009301030113012301330143015301630173018301930203021302230233024302530263027302830293030303130323033303430353036303730383039304030413042304330443045304630473048304930503051305230533054305530563057305830593060306130623063306430653066306730683069307030713072307330743075307630773078307930803081308230833084308530863087308830893090309130923093309430953096309730983099310031013102310331043105310631073108310931103111311231133114311531163117311831193120312131223123312431253126312731283129313031313132313331343135313631373138313931403141314231433144314531463147314831493150315131523153315431553156315731583159316031613162316331643165316631673168316931703171317231733174317531763177317831793180318131823183318431853186318731883189319031913192319331943195319631973198319932003201320232033204320532063207320832093210321132123213321432153216321732183219322032213222322332243225322632273228322932303231323232333234323532363237323832393240324132423243324432453246324732483249325032513252325332543255325632573258325932603261326232633264326532663267326832693270327132723273327432753276327732783279328032813282328332843285328632873288328932903291329232933294329532963297329832993300330133023303330433053306330733083309331033113312331333143315331633173318331933203321332233233324332533263327332833293330333133323333333433353336333733383339334033413342334333443345334633473348334933503351335233533354335533563357335833593360336133623363336433653366336733683369337033713372337333743375337633773378337933803381338233833384338533863387338833893390339133923393339433953396339733983399340034013402340334043405340634073408340934103411341234133414341534163417341834193420342134223423342434253426342734283429343034313432343334343435343634373438343934403441344234433444344534463447344834493450345134523453345434553456345734583459346034613462346334643465346634673468346934703471347234733474347534763477347834793480348134823483348434853486348734883489349034913492349334943495349634973498349935003501350235033504350535063507350835093510351135123513351435153516351735183519352035213522352335243525352635273528352935303531353235333534353535363537353835393540354135423543354435453546354735483549355035513552355335543555355635573558355935603561356235633564356535663567356835693570357135723573357435753576357735783579358035813582358335843585358635873588358935903591359235933594359535963597359835993600360136023603360436053606360736083609361036113612361336143615361636173618361936203621362236233624362536263627362836293630363136323633363436353636363736383639364036413642364336443645364636473648364936503651365236533654365536563657365836593660366136623663366436653666366736683669367036713672367336743675367636773678367936803681368236833684368536863687368836893690369136923693369436953696369736983699370037013702370337043705370637073708370937103711371237133714371537163717371837193720372137223723372437253726372737283729373037313732373337343735373637373738373937403741374237433744374537463747374837493750375137523753375437553756375737583759376037613762376337643765376637673768376937703771377237733774377537763777377837793780378137823783378437853786378737883789379037913792379337943795379637973798379938003801380238033804380538063807380838093810381138123813381438153816381738183819382038213822382338243825382638273828382938303831383238333834383538363837383838393840384138423843384438453846384738483849385038513852385338543855385638573858385938603861386238633864386538663867386838693870387138723873387438753876387738783879388038813882388338843885388638873888388938903891389238933894389538963897389838993900390139023903390439053906390739083909391039113912391339143915391639173918391939203921392239233924392539263927392839293930393139323933393439353936393739383939394039413942394339443945394639473948394939503951395239533954395539563957395839593960396139623963396439653966396739683969397039713972397339743975397639773978397939803981398239833984398539863987398839893990399139923993399439953996399739983999400040014002400340044005400640074008400940104011401240134014401540164017401840194020402140224023402440254026402740284029403040314032403340344035403640374038403940404041404240434044404540464047404840494050405140524053405440554056405740584059406040614062406340644065406640674068406940704071407240734074407540764077407840794080408140824083408440854086408740884089409040914092409340944095409640974098409941004101410241034104410541064107410841094110411141124113411441154116411741184119412041214122412341244125412641274128412941304131413241334134413541364137413841394140414141424143414441454146414741484149415041514152415341544155415641574158415941604161416241634164416541664167416841694170417141724173417441754176417741784179418041814182418341844185418641874188418941904191419241934194419541964197419841994200420142024203420442054206420742084209421042114212421342144215421642174218421942204221422242234224422542264227422842294230423142324233423442354236423742384239424042414242424342444245424642474248424942504251425242534254425542564257425842594260426142624263426442654266426742684269427042714272427342744275427642774278427942804281428242834284428542864287428842894290429142924293429442954296429742984299430043014302430343044305430643074308430943104311431243134314431543164317431843194320432143224323432443254326432743284329433043314332433343344335433643374338433943404341434243434344434543464347434843494350435143524353435443554356435743584359436043614362436343644365436643674368436943704371437243734374437543764377437843794380438143824383438443854386438743884389439043914392439343944395439643974398439944004401440244034404440544064407440844094410441144124413441444154416441744184419442044214422442344244425442644274428442944304431443244334434443544364437443844394440444144424443444444454446444744484449445044514452445344544455445644574458445944604461446244634464446544664467446844694470447144724473447444754476447744784479448044814482448344844485448644874488448944904491449244934494449544964497449844994500450145024503450445054506450745084509451045114512451345144515451645174518451945204521452245234524452545264527452845294530453145324533453445354536453745384539454045414542454345444545454645474548454945504551455245534554455545564557455845594560456145624563456445654566456745684569457045714572457345744575457645774578457945804581458245834584458545864587458845894590459145924593459445954596459745984599460046014602460346044605460646074608460946104611461246134614461546164617461846194620462146224623462446254626462746284629463046314632463346344635463646374638463946404641464246434644464546464647464846494650465146524653465446554656465746584659466046614662466346644665466646674668466946704671467246734674467546764677467846794680468146824683468446854686468746884689469046914692469346944695469646974698469947004701470247034704470547064707470847094710471147124713471447154716471747184719472047214722472347244725472647274728472947304731473247334734473547364737473847394740474147424743474447454746474747484749475047514752475347544755475647574758475947604761476247634764476547664767476847694770477147724773477447754776477747784779478047814782478347844785478647874788478947904791479247934794479547964797479847994800480148024803480448054806480748084809481048114812481348144815481648174818481948204821482248234824482548264827482848294830483148324833483448354836483748384839484048414842484348444845484648474848484948504851485248534854485548564857485848594860486148624863486448654866486748684869487048714872487348744875487648774878487948804881488248834884488548864887488848894890489148924893489448954896489748984899490049014902490349044905490649074908490949104911491249134914491549164917491849194920492149224923492449254926492749284929493049314932493349344935493649374938493949404941494249434944494549464947494849494950495149524953495449554956495749584959496049614962496349644965496649674968496949704971497249734974497549764977497849794980498149824983498449854986498749884989499049914992499349944995499649974998499950005001500250035004500550065007500850095010501150125013501450155016501750185019502050215022502350245025502650275028502950305031503250335034503550365037503850395040504150425043504450455046504750485049505050515052505350545055505650575058505950605061506250635064506550665067506850695070507150725073507450755076507750785079508050815082508350845085508650875088508950905091509250935094509550965097509850995100510151025103510451055106510751085109511051115112511351145115511651175118511951205121512251235124512551265127512851295130513151325133513451355136513751385139514051415142514351445145514651475148514951505151515251535154515551565157515851595160516151625163516451655166516751685169517051715172517351745175517651775178517951805181518251835184518551865187518851895190519151925193519451955196519751985199520052015202520352045205520652075208520952105211521252135214521552165217521852195220522152225223522452255226522752285229523052315232523352345235523652375238523952405241524252435244524552465247524852495250525152525253525452555256525752585259526052615262526352645265526652675268526952705271527252735274527552765277527852795280528152825283528452855286528752885289529052915292529352945295529652975298529953005301530253035304530553065307530853095310531153125313531453155316531753185319532053215322532353245325532653275328532953305331533253335334533553365337533853395340534153425343534453455346534753485349535053515352535353545355535653575358535953605361536253635364536553665367536853695370537153725373537453755376537753785379538053815382538353845385538653875388538953905391539253935394539553965397539853995400540154025403540454055406540754085409541054115412541354145415541654175418541954205421542254235424542554265427542854295430543154325433543454355436543754385439544054415442544354445445544654475448544954505451545254535454545554565457545854595460546154625463546454655466546754685469547054715472547354745475547654775478547954805481548254835484548554865487548854895490549154925493549454955496549754985499550055015502550355045505550655075508550955105511551255135514551555165517551855195520552155225523552455255526552755285529553055315532553355345535553655375538553955405541554255435544554555465547554855495550555155525553555455555556555755585559556055615562556355645565556655675568556955705571557255735574557555765577557855795580558155825583558455855586558755885589559055915592559355945595559655975598559956005601560256035604560556065607560856095610561156125613561456155616561756185619562056215622562356245625562656275628562956305631563256335634563556365637563856395640564156425643564456455646564756485649565056515652565356545655565656575658565956605661566256635664566556665667566856695670567156725673567456755676567756785679568056815682568356845685568656875688568956905691569256935694569556965697569856995700570157025703570457055706570757085709571057115712571357145715571657175718571957205721572257235724572557265727572857295730573157325733573457355736573757385739574057415742574357445745574657475748574957505751575257535754575557565757575857595760576157625763576457655766576757685769577057715772577357745775577657775778577957805781578257835784578557865787578857895790579157925793579457955796579757985799580058015802580358045805580658075808580958105811581258135814581558165817581858195820582158225823582458255826582758285829583058315832583358345835583658375838583958405841584258435844584558465847584858495850585158525853585458555856585758585859586058615862586358645865586658675868586958705871587258735874587558765877587858795880588158825883588458855886588758885889589058915892589358945895589658975898589959005901590259035904590559065907590859095910591159125913591459155916591759185919592059215922592359245925592659275928592959305931593259335934593559365937593859395940594159425943594459455946594759485949595059515952595359545955595659575958595959605961596259635964596559665967596859695970597159725973597459755976597759785979598059815982598359845985598659875988598959905991599259935994599559965997599859996000600160026003600460056006600760086009601060116012601360146015601660176018601960206021602260236024602560266027602860296030603160326033603460356036603760386039604060416042604360446045604660476048604960506051605260536054605560566057605860596060606160626063606460656066606760686069607060716072607360746075607660776078607960806081608260836084608560866087608860896090609160926093609460956096609760986099610061016102610361046105610661076108610961106111611261136114611561166117611861196120612161226123612461256126612761286129613061316132613361346135613661376138613961406141614261436144614561466147614861496150615161526153615461556156615761586159616061616162616361646165616661676168616961706171617261736174617561766177617861796180618161826183618461856186618761886189619061916192619361946195619661976198619962006201620262036204620562066207620862096210621162126213621462156216621762186219622062216222622362246225622662276228622962306231623262336234623562366237623862396240624162426243624462456246624762486249625062516252625362546255625662576258625962606261626262636264626562666267626862696270627162726273627462756276627762786279628062816282628362846285628662876288628962906291629262936294629562966297629862996300630163026303630463056306630763086309631063116312631363146315631663176318631963206321632263236324632563266327632863296330633163326333633463356336633763386339634063416342634363446345634663476348634963506351635263536354635563566357635863596360636163626363636463656366636763686369637063716372637363746375637663776378637963806381638263836384638563866387638863896390639163926393639463956396639763986399640064016402640364046405640664076408640964106411641264136414641564166417641864196420642164226423642464256426642764286429643064316432643364346435643664376438643964406441644264436444644564466447644864496450645164526453645464556456645764586459646064616462646364646465646664676468646964706471647264736474647564766477647864796480648164826483648464856486648764886489649064916492649364946495649664976498649965006501650265036504650565066507650865096510651165126513651465156516651765186519652065216522652365246525652665276528652965306531653265336534653565366537653865396540654165426543654465456546654765486549655065516552655365546555655665576558655965606561656265636564656565666567656865696570657165726573657465756576657765786579658065816582658365846585658665876588658965906591659265936594659565966597659865996600660166026603660466056606660766086609661066116612661366146615661666176618661966206621662266236624662566266627662866296630663166326633663466356636663766386639664066416642664366446645664666476648664966506651665266536654665566566657665866596660666166626663666466656666666766686669667066716672667366746675667666776678667966806681668266836684668566866687668866896690669166926693669466956696669766986699670067016702670367046705670667076708670967106711671267136714671567166717671867196720672167226723672467256726672767286729673067316732673367346735673667376738673967406741674267436744674567466747674867496750675167526753675467556756675767586759676067616762676367646765676667676768676967706771677267736774677567766777677867796780678167826783678467856786678767886789679067916792679367946795679667976798679968006801680268036804680568066807680868096810681168126813681468156816681768186819682068216822682368246825682668276828682968306831683268336834683568366837683868396840684168426843684468456846684768486849685068516852685368546855685668576858685968606861686268636864686568666867686868696870687168726873687468756876687768786879688068816882688368846885688668876888688968906891689268936894689568966897689868996900690169026903690469056906690769086909691069116912691369146915691669176918691969206921692269236924692569266927692869296930693169326933693469356936693769386939694069416942694369446945694669476948694969506951695269536954695569566957695869596960696169626963696469656966696769686969697069716972697369746975697669776978697969806981698269836984698569866987698869896990699169926993699469956996699769986999700070017002700370047005700670077008700970107011701270137014701570167017701870197020702170227023702470257026702770287029703070317032703370347035703670377038703970407041704270437044704570467047704870497050705170527053705470557056705770587059706070617062706370647065706670677068706970707071707270737074707570767077707870797080708170827083708470857086708770887089709070917092709370947095709670977098709971007101710271037104710571067107710871097110711171127113711471157116711771187119712071217122712371247125712671277128712971307131713271337134713571367137713871397140714171427143714471457146714771487149715071517152715371547155715671577158715971607161716271637164716571667167716871697170717171727173717471757176717771787179718071817182718371847185718671877188718971907191719271937194719571967197719871997200720172027203720472057206720772087209721072117212721372147215721672177218721972207221722272237224722572267227722872297230723172327233723472357236723772387239724072417242724372447245724672477248724972507251725272537254725572567257725872597260726172627263726472657266726772687269727072717272727372747275727672777278727972807281728272837284728572867287728872897290729172927293729472957296729772987299730073017302730373047305730673077308730973107311731273137314731573167317731873197320732173227323732473257326732773287329733073317332733373347335733673377338733973407341734273437344734573467347734873497350735173527353735473557356735773587359736073617362736373647365736673677368736973707371737273737374737573767377737873797380738173827383738473857386738773887389739073917392739373947395739673977398/*
*  Copyright (c) 2001 The Regents of the University of Michigan.
*  All rights reserved.
*
*  Kendrick Smith <kmsmith@umich.edu>
*  Andy Adamson <kandros@umich.edu>
*
*  Redistribution and use in source and binary forms, with or without
*  modification, are permitted provided that the following conditions
*  are met:
*
*  1. Redistributions of source code must retain the above copyright
*     notice, this list of conditions and the following disclaimer.
*  2. Redistributions in binary form must reproduce the above copyright
*     notice, this list of conditions and the following disclaimer in the
*     documentation and/or other materials provided with the distribution.
*  3. Neither the name of the University nor the names of its
*     contributors may be used to endorse or promote products derived
*     from this software without specific prior written permission.
*
*  THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
*  WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
*  MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
*  DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
*  FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
*  CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
*  SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
*  BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
*  LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
*  NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
*  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*
*/

#include <linux/file.h>
#include <linux/fs.h>
#include <linux/slab.h>
#include <linux/namei.h>
#include <linux/swap.h>
#include <linux/pagemap.h>
#include <linux/ratelimit.h>
#include <linux/sunrpc/svcauth_gss.h>
#include <linux/sunrpc/addr.h>
#include <linux/jhash.h>
#include "xdr4.h"
#include "xdr4cb.h"
#include "vfs.h"
#include "current_stateid.h"

#include "netns.h"
#include "pnfs.h"

#define NFSDDBG_FACILITY                NFSDDBG_PROC

#define all_ones {{~0,~0},~0}
static const stateid_t one_stateid = {
	.si_generation = ~0,
	.si_opaque = all_ones,
};
static const stateid_t zero_stateid = {
	/* all fields zero */
};
static const stateid_t currentstateid = {
	.si_generation = 1,
};
static const stateid_t close_stateid = {
	.si_generation = 0xffffffffU,
};

static u64 current_sessionid = 1;

#define ZERO_STATEID(stateid) (!memcmp((stateid), &zero_stateid, sizeof(stateid_t)))
#define ONE_STATEID(stateid)  (!memcmp((stateid), &one_stateid, sizeof(stateid_t)))
#define CURRENT_STATEID(stateid) (!memcmp((stateid), &currentstateid, sizeof(stateid_t)))
#define CLOSE_STATEID(stateid)  (!memcmp((stateid), &close_stateid, sizeof(stateid_t)))

/* forward declarations */
static bool check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner);
static void nfs4_free_ol_stateid(struct nfs4_stid *stid);

/* Locking: */

/*
 * Currently used for the del_recall_lru and file hash table.  In an
 * effort to decrease the scope of the client_mutex, this spinlock may
 * eventually cover more:
 */
static DEFINE_SPINLOCK(state_lock);

enum nfsd4_st_mutex_lock_subclass {
	OPEN_STATEID_MUTEX = 0,
	LOCK_STATEID_MUTEX = 1,
};

/*
 * A waitqueue for all in-progress 4.0 CLOSE operations that are waiting for
 * the refcount on the open stateid to drop.
 */
static DECLARE_WAIT_QUEUE_HEAD(close_wq);

static struct kmem_cache *client_slab;
static struct kmem_cache *openowner_slab;
static struct kmem_cache *lockowner_slab;
static struct kmem_cache *file_slab;
static struct kmem_cache *stateid_slab;
static struct kmem_cache *deleg_slab;
static struct kmem_cache *odstate_slab;

static void free_session(struct nfsd4_session *);

static const struct nfsd4_callback_ops nfsd4_cb_recall_ops;
static const struct nfsd4_callback_ops nfsd4_cb_notify_lock_ops;

static bool is_session_dead(struct nfsd4_session *ses)
{
	return ses->se_flags & NFS4_SESSION_DEAD;
}

static __be32 mark_session_dead_locked(struct nfsd4_session *ses, int ref_held_by_me)
{
	if (atomic_read(&ses->se_ref) > ref_held_by_me)
		return nfserr_jukebox;
	ses->se_flags |= NFS4_SESSION_DEAD;
	return nfs_ok;
}

static bool is_client_expired(struct nfs4_client *clp)
{
	return clp->cl_time == 0;
}

static __be32 get_client_locked(struct nfs4_client *clp)
{
	struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);

	lockdep_assert_held(&nn->client_lock);

	if (is_client_expired(clp))
		return nfserr_expired;
	atomic_inc(&clp->cl_refcount);
	return nfs_ok;
}

/* must be called under the client_lock */
static inline void
renew_client_locked(struct nfs4_client *clp)
{
	struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);

	if (is_client_expired(clp)) {
		WARN_ON(1);
		printk("%s: client (clientid %08x/%08x) already expired\n",
			__func__,
			clp->cl_clientid.cl_boot,
			clp->cl_clientid.cl_id);
		return;
	}

	dprintk("renewing client (clientid %08x/%08x)\n",
			clp->cl_clientid.cl_boot,
			clp->cl_clientid.cl_id);
	list_move_tail(&clp->cl_lru, &nn->client_lru);
	clp->cl_time = get_seconds();
}

static void put_client_renew_locked(struct nfs4_client *clp)
{
	struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);

	lockdep_assert_held(&nn->client_lock);

	if (!atomic_dec_and_test(&clp->cl_refcount))
		return;
	if (!is_client_expired(clp))
		renew_client_locked(clp);
}

static void put_client_renew(struct nfs4_client *clp)
{
	struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);

	if (!atomic_dec_and_lock(&clp->cl_refcount, &nn->client_lock))
		return;
	if (!is_client_expired(clp))
		renew_client_locked(clp);
	spin_unlock(&nn->client_lock);
}

static __be32 nfsd4_get_session_locked(struct nfsd4_session *ses)
{
	__be32 status;

	if (is_session_dead(ses))
		return nfserr_badsession;
	status = get_client_locked(ses->se_client);
	if (status)
		return status;
	atomic_inc(&ses->se_ref);
	return nfs_ok;
}

static void nfsd4_put_session_locked(struct nfsd4_session *ses)
{
	struct nfs4_client *clp = ses->se_client;
	struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);

	lockdep_assert_held(&nn->client_lock);

	if (atomic_dec_and_test(&ses->se_ref) && is_session_dead(ses))
		free_session(ses);
	put_client_renew_locked(clp);
}

static void nfsd4_put_session(struct nfsd4_session *ses)
{
	struct nfs4_client *clp = ses->se_client;
	struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);

	spin_lock(&nn->client_lock);
	nfsd4_put_session_locked(ses);
	spin_unlock(&nn->client_lock);
}

static struct nfsd4_blocked_lock *
find_blocked_lock(struct nfs4_lockowner *lo, struct knfsd_fh *fh,
			struct nfsd_net *nn)
{
	struct nfsd4_blocked_lock *cur, *found = NULL;

	spin_lock(&nn->blocked_locks_lock);
	list_for_each_entry(cur, &lo->lo_blocked, nbl_list) {
		if (fh_match(fh, &cur->nbl_fh)) {
			list_del_init(&cur->nbl_list);
			list_del_init(&cur->nbl_lru);
			found = cur;
			break;
		}
	}
	spin_unlock(&nn->blocked_locks_lock);
	if (found)
		posix_unblock_lock(&found->nbl_lock);
	return found;
}

static struct nfsd4_blocked_lock *
find_or_allocate_block(struct nfs4_lockowner *lo, struct knfsd_fh *fh,
			struct nfsd_net *nn)
{
	struct nfsd4_blocked_lock *nbl;

	nbl = find_blocked_lock(lo, fh, nn);
	if (!nbl) {
		nbl= kmalloc(sizeof(*nbl), GFP_KERNEL);
		if (nbl) {
			fh_copy_shallow(&nbl->nbl_fh, fh);
			locks_init_lock(&nbl->nbl_lock);
			nfsd4_init_cb(&nbl->nbl_cb, lo->lo_owner.so_client,
					&nfsd4_cb_notify_lock_ops,
					NFSPROC4_CLNT_CB_NOTIFY_LOCK);
		}
	}
	return nbl;
}

static void
free_blocked_lock(struct nfsd4_blocked_lock *nbl)
{
	locks_release_private(&nbl->nbl_lock);
	kfree(nbl);
}

static void
remove_blocked_locks(struct nfs4_lockowner *lo)
{
	struct nfs4_client *clp = lo->lo_owner.so_client;
	struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
	struct nfsd4_blocked_lock *nbl;
	LIST_HEAD(reaplist);

	/* Dequeue all blocked locks */
	spin_lock(&nn->blocked_locks_lock);
	while (!list_empty(&lo->lo_blocked)) {
		nbl = list_first_entry(&lo->lo_blocked,
					struct nfsd4_blocked_lock,
					nbl_list);
		list_del_init(&nbl->nbl_list);
		list_move(&nbl->nbl_lru, &reaplist);
	}
	spin_unlock(&nn->blocked_locks_lock);

	/* Now free them */
	while (!list_empty(&reaplist)) {
		nbl = list_first_entry(&reaplist, struct nfsd4_blocked_lock,
					nbl_lru);
		list_del_init(&nbl->nbl_lru);
		posix_unblock_lock(&nbl->nbl_lock);
		free_blocked_lock(nbl);
	}
}

static int
nfsd4_cb_notify_lock_done(struct nfsd4_callback *cb, struct rpc_task *task)
{
	/*
	 * Since this is just an optimization, we don't try very hard if it
	 * turns out not to succeed. We'll requeue it on NFS4ERR_DELAY, and
	 * just quit trying on anything else.
	 */
	switch (task->tk_status) {
	case -NFS4ERR_DELAY:
		rpc_delay(task, 1 * HZ);
		return 0;
	default:
		return 1;
	}
}

static void
nfsd4_cb_notify_lock_release(struct nfsd4_callback *cb)
{
	struct nfsd4_blocked_lock	*nbl = container_of(cb,
						struct nfsd4_blocked_lock, nbl_cb);

	free_blocked_lock(nbl);
}

static const struct nfsd4_callback_ops nfsd4_cb_notify_lock_ops = {
	.done		= nfsd4_cb_notify_lock_done,
	.release	= nfsd4_cb_notify_lock_release,
};

static inline struct nfs4_stateowner *
nfs4_get_stateowner(struct nfs4_stateowner *sop)
{
	atomic_inc(&sop->so_count);
	return sop;
}

static int
same_owner_str(struct nfs4_stateowner *sop, struct xdr_netobj *owner)
{
	return (sop->so_owner.len == owner->len) &&
		0 == memcmp(sop->so_owner.data, owner->data, owner->len);
}

static struct nfs4_openowner *
find_openstateowner_str_locked(unsigned int hashval, struct nfsd4_open *open,
			struct nfs4_client *clp)
{
	struct nfs4_stateowner *so;

	lockdep_assert_held(&clp->cl_lock);

	list_for_each_entry(so, &clp->cl_ownerstr_hashtbl[hashval],
			    so_strhash) {
		if (!so->so_is_open_owner)
			continue;
		if (same_owner_str(so, &open->op_owner))
			return openowner(nfs4_get_stateowner(so));
	}
	return NULL;
}

static struct nfs4_openowner *
find_openstateowner_str(unsigned int hashval, struct nfsd4_open *open,
			struct nfs4_client *clp)
{
	struct nfs4_openowner *oo;

	spin_lock(&clp->cl_lock);
	oo = find_openstateowner_str_locked(hashval, open, clp);
	spin_unlock(&clp->cl_lock);
	return oo;
}

static inline u32
opaque_hashval(const void *ptr, int nbytes)
{
	unsigned char *cptr = (unsigned char *) ptr;

	u32 x = 0;
	while (nbytes--) {
		x *= 37;
		x += *cptr++;
	}
	return x;
}

static void nfsd4_free_file_rcu(struct rcu_head *rcu)
{
	struct nfs4_file *fp = container_of(rcu, struct nfs4_file, fi_rcu);

	kmem_cache_free(file_slab, fp);
}

void
put_nfs4_file(struct nfs4_file *fi)
{
	might_lock(&state_lock);

	if (refcount_dec_and_lock(&fi->fi_ref, &state_lock)) {
		hlist_del_rcu(&fi->fi_hash);
		spin_unlock(&state_lock);
		WARN_ON_ONCE(!list_empty(&fi->fi_clnt_odstate));
		WARN_ON_ONCE(!list_empty(&fi->fi_delegations));
		call_rcu(&fi->fi_rcu, nfsd4_free_file_rcu);
	}
}

static struct file *
__nfs4_get_fd(struct nfs4_file *f, int oflag)
{
	if (f->fi_fds[oflag])
		return get_file(f->fi_fds[oflag]);
	return NULL;
}

static struct file *
find_writeable_file_locked(struct nfs4_file *f)
{
	struct file *ret;

	lockdep_assert_held(&f->fi_lock);

	ret = __nfs4_get_fd(f, O_WRONLY);
	if (!ret)
		ret = __nfs4_get_fd(f, O_RDWR);
	return ret;
}

static struct file *
find_writeable_file(struct nfs4_file *f)
{
	struct file *ret;

	spin_lock(&f->fi_lock);
	ret = find_writeable_file_locked(f);
	spin_unlock(&f->fi_lock);

	return ret;
}

static struct file *find_readable_file_locked(struct nfs4_file *f)
{
	struct file *ret;

	lockdep_assert_held(&f->fi_lock);

	ret = __nfs4_get_fd(f, O_RDONLY);
	if (!ret)
		ret = __nfs4_get_fd(f, O_RDWR);
	return ret;
}

static struct file *
find_readable_file(struct nfs4_file *f)
{
	struct file *ret;

	spin_lock(&f->fi_lock);
	ret = find_readable_file_locked(f);
	spin_unlock(&f->fi_lock);

	return ret;
}

struct file *
find_any_file(struct nfs4_file *f)
{
	struct file *ret;

	spin_lock(&f->fi_lock);
	ret = __nfs4_get_fd(f, O_RDWR);
	if (!ret) {
		ret = __nfs4_get_fd(f, O_WRONLY);
		if (!ret)
			ret = __nfs4_get_fd(f, O_RDONLY);
	}
	spin_unlock(&f->fi_lock);
	return ret;
}

static atomic_long_t num_delegations;
unsigned long max_delegations;

/*
 * Open owner state (share locks)
 */

/* hash tables for lock and open owners */
#define OWNER_HASH_BITS              8
#define OWNER_HASH_SIZE             (1 << OWNER_HASH_BITS)
#define OWNER_HASH_MASK             (OWNER_HASH_SIZE - 1)

static unsigned int ownerstr_hashval(struct xdr_netobj *ownername)
{
	unsigned int ret;

	ret = opaque_hashval(ownername->data, ownername->len);
	return ret & OWNER_HASH_MASK;
}

/* hash table for nfs4_file */
#define FILE_HASH_BITS                   8
#define FILE_HASH_SIZE                  (1 << FILE_HASH_BITS)

static unsigned int nfsd_fh_hashval(struct knfsd_fh *fh)
{
	return jhash2(fh->fh_base.fh_pad, XDR_QUADLEN(fh->fh_size), 0);
}

static unsigned int file_hashval(struct knfsd_fh *fh)
{
	return nfsd_fh_hashval(fh) & (FILE_HASH_SIZE - 1);
}

static struct hlist_head file_hashtbl[FILE_HASH_SIZE];

static void
__nfs4_file_get_access(struct nfs4_file *fp, u32 access)
{
	lockdep_assert_held(&fp->fi_lock);

	if (access & NFS4_SHARE_ACCESS_WRITE)
		atomic_inc(&fp->fi_access[O_WRONLY]);
	if (access & NFS4_SHARE_ACCESS_READ)
		atomic_inc(&fp->fi_access[O_RDONLY]);
}

static __be32
nfs4_file_get_access(struct nfs4_file *fp, u32 access)
{
	lockdep_assert_held(&fp->fi_lock);

	/* Does this access mode make sense? */
	if (access & ~NFS4_SHARE_ACCESS_BOTH)
		return nfserr_inval;

	/* Does it conflict with a deny mode already set? */
	if ((access & fp->fi_share_deny) != 0)
		return nfserr_share_denied;

	__nfs4_file_get_access(fp, access);
	return nfs_ok;
}

static __be32 nfs4_file_check_deny(struct nfs4_file *fp, u32 deny)
{
	/* Common case is that there is no deny mode. */
	if (deny) {
		/* Does this deny mode make sense? */
		if (deny & ~NFS4_SHARE_DENY_BOTH)
			return nfserr_inval;

		if ((deny & NFS4_SHARE_DENY_READ) &&
		    atomic_read(&fp->fi_access[O_RDONLY]))
			return nfserr_share_denied;

		if ((deny & NFS4_SHARE_DENY_WRITE) &&
		    atomic_read(&fp->fi_access[O_WRONLY]))
			return nfserr_share_denied;
	}
	return nfs_ok;
}

static void __nfs4_file_put_access(struct nfs4_file *fp, int oflag)
{
	might_lock(&fp->fi_lock);

	if (atomic_dec_and_lock(&fp->fi_access[oflag], &fp->fi_lock)) {
		struct file *f1 = NULL;
		struct file *f2 = NULL;

		swap(f1, fp->fi_fds[oflag]);
		if (atomic_read(&fp->fi_access[1 - oflag]) == 0)
			swap(f2, fp->fi_fds[O_RDWR]);
		spin_unlock(&fp->fi_lock);
		if (f1)
			fput(f1);
		if (f2)
			fput(f2);
	}
}

static void nfs4_file_put_access(struct nfs4_file *fp, u32 access)
{
	WARN_ON_ONCE(access & ~NFS4_SHARE_ACCESS_BOTH);

	if (access & NFS4_SHARE_ACCESS_WRITE)
		__nfs4_file_put_access(fp, O_WRONLY);
	if (access & NFS4_SHARE_ACCESS_READ)
		__nfs4_file_put_access(fp, O_RDONLY);
}

/*
 * Allocate a new open/delegation state counter. This is needed for
 * pNFS for proper return on close semantics.
 *
 * Note that we only allocate it for pNFS-enabled exports, otherwise
 * all pointers to struct nfs4_clnt_odstate are always NULL.
 */
static struct nfs4_clnt_odstate *
alloc_clnt_odstate(struct nfs4_client *clp)
{
	struct nfs4_clnt_odstate *co;

	co = kmem_cache_zalloc(odstate_slab, GFP_KERNEL);
	if (co) {
		co->co_client = clp;
		refcount_set(&co->co_odcount, 1);
	}
	return co;
}

static void
hash_clnt_odstate_locked(struct nfs4_clnt_odstate *co)
{
	struct nfs4_file *fp = co->co_file;

	lockdep_assert_held(&fp->fi_lock);
	list_add(&co->co_perfile, &fp->fi_clnt_odstate);
}

static inline void
get_clnt_odstate(struct nfs4_clnt_odstate *co)
{
	if (co)
		refcount_inc(&co->co_odcount);
}

static void
put_clnt_odstate(struct nfs4_clnt_odstate *co)
{
	struct nfs4_file *fp;

	if (!co)
		return;

	fp = co->co_file;
	if (refcount_dec_and_lock(&co->co_odcount, &fp->fi_lock)) {
		list_del(&co->co_perfile);
		spin_unlock(&fp->fi_lock);

		nfsd4_return_all_file_layouts(co->co_client, fp);
		kmem_cache_free(odstate_slab, co);
	}
}

static struct nfs4_clnt_odstate *
find_or_hash_clnt_odstate(struct nfs4_file *fp, struct nfs4_clnt_odstate *new)
{
	struct nfs4_clnt_odstate *co;
	struct nfs4_client *cl;

	if (!new)
		return NULL;

	cl = new->co_client;

	spin_lock(&fp->fi_lock);
	list_for_each_entry(co, &fp->fi_clnt_odstate, co_perfile) {
		if (co->co_client == cl) {
			get_clnt_odstate(co);
			goto out;
		}
	}
	co = new;
	co->co_file = fp;
	hash_clnt_odstate_locked(new);
out:
	spin_unlock(&fp->fi_lock);
	return co;
}

struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct kmem_cache *slab,
				  void (*sc_free)(struct nfs4_stid *))
{
	struct nfs4_stid *stid;
	int new_id;

	stid = kmem_cache_zalloc(slab, GFP_KERNEL);
	if (!stid)
		return NULL;

	idr_preload(GFP_KERNEL);
	spin_lock(&cl->cl_lock);
	new_id = idr_alloc_cyclic(&cl->cl_stateids, stid, 0, 0, GFP_NOWAIT);
	spin_unlock(&cl->cl_lock);
	idr_preload_end();
	if (new_id < 0)
		goto out_free;

	stid->sc_free = sc_free;
	stid->sc_client = cl;
	stid->sc_stateid.si_opaque.so_id = new_id;
	stid->sc_stateid.si_opaque.so_clid = cl->cl_clientid;
	/* Will be incremented before return to client: */
	refcount_set(&stid->sc_count, 1);
	spin_lock_init(&stid->sc_lock);

	/*
	 * It shouldn't be a problem to reuse an opaque stateid value.
	 * I don't think it is for 4.1.  But with 4.0 I worry that, for
	 * example, a stray write retransmission could be accepted by
	 * the server when it should have been rejected.  Therefore,
	 * adopt a trick from the sctp code to attempt to maximize the
	 * amount of time until an id is reused, by ensuring they always
	 * "increase" (mod INT_MAX):
	 */
	return stid;
out_free:
	kmem_cache_free(slab, stid);
	return NULL;
}

static struct nfs4_ol_stateid * nfs4_alloc_open_stateid(struct nfs4_client *clp)
{
	struct nfs4_stid *stid;

	stid = nfs4_alloc_stid(clp, stateid_slab, nfs4_free_ol_stateid);
	if (!stid)
		return NULL;

	return openlockstateid(stid);
}

static void nfs4_free_deleg(struct nfs4_stid *stid)
{
	kmem_cache_free(deleg_slab, stid);
	atomic_long_dec(&num_delegations);
}

/*
 * When we recall a delegation, we should be careful not to hand it
 * out again straight away.
 * To ensure this we keep a pair of bloom filters ('new' and 'old')
 * in which the filehandles of recalled delegations are "stored".
 * If a filehandle appear in either filter, a delegation is blocked.
 * When a delegation is recalled, the filehandle is stored in the "new"
 * filter.
 * Every 30 seconds we swap the filters and clear the "new" one,
 * unless both are empty of course.
 *
 * Each filter is 256 bits.  We hash the filehandle to 32bit and use the
 * low 3 bytes as hash-table indices.
 *
 * 'blocked_delegations_lock', which is always taken in block_delegations(),
 * is used to manage concurrent access.  Testing does not need the lock
 * except when swapping the two filters.
 */
static DEFINE_SPINLOCK(blocked_delegations_lock);
static struct bloom_pair {
	int	entries, old_entries;
	time_t	swap_time;
	int	new; /* index into 'set' */
	DECLARE_BITMAP(set[2], 256);
} blocked_delegations;

static int delegation_blocked(struct knfsd_fh *fh)
{
	u32 hash;
	struct bloom_pair *bd = &blocked_delegations;

	if (bd->entries == 0)
		return 0;
	if (seconds_since_boot() - bd->swap_time > 30) {
		spin_lock(&blocked_delegations_lock);
		if (seconds_since_boot() - bd->swap_time > 30) {
			bd->entries -= bd->old_entries;
			bd->old_entries = bd->entries;
			memset(bd->set[bd->new], 0,
			       sizeof(bd->set[0]));
			bd->new = 1-bd->new;
			bd->swap_time = seconds_since_boot();
		}
		spin_unlock(&blocked_delegations_lock);
	}
	hash = jhash(&fh->fh_base, fh->fh_size, 0);
	if (test_bit(hash&255, bd->set[0]) &&
	    test_bit((hash>>8)&255, bd->set[0]) &&
	    test_bit((hash>>16)&255, bd->set[0]))
		return 1;

	if (test_bit(hash&255, bd->set[1]) &&
	    test_bit((hash>>8)&255, bd->set[1]) &&
	    test_bit((hash>>16)&255, bd->set[1]))
		return 1;

	return 0;
}

static void block_delegations(struct knfsd_fh *fh)
{
	u32 hash;
	struct bloom_pair *bd = &blocked_delegations;

	hash = jhash(&fh->fh_base, fh->fh_size, 0);

	spin_lock(&blocked_delegations_lock);
	__set_bit(hash&255, bd->set[bd->new]);
	__set_bit((hash>>8)&255, bd->set[bd->new]);
	__set_bit((hash>>16)&255, bd->set[bd->new]);
	if (bd->entries == 0)
		bd->swap_time = seconds_since_boot();
	bd->entries += 1;
	spin_unlock(&blocked_delegations_lock);
}

static struct nfs4_delegation *
alloc_init_deleg(struct nfs4_client *clp, struct nfs4_file *fp,
		 struct svc_fh *current_fh,
		 struct nfs4_clnt_odstate *odstate)
{
	struct nfs4_delegation *dp;
	long n;

	dprintk("NFSD alloc_init_deleg\n");
	n = atomic_long_inc_return(&num_delegations);
	if (n < 0 || n > max_delegations)
		goto out_dec;
	if (delegation_blocked(&current_fh->fh_handle))
		goto out_dec;
	dp = delegstateid(nfs4_alloc_stid(clp, deleg_slab, nfs4_free_deleg));
	if (dp == NULL)
		goto out_dec;

	/*
	 * delegation seqid's are never incremented.  The 4.1 special
	 * meaning of seqid 0 isn't meaningful, really, but let's avoid
	 * 0 anyway just for consistency and use 1:
	 */
	dp->dl_stid.sc_stateid.si_generation = 1;
	INIT_LIST_HEAD(&dp->dl_perfile);
	INIT_LIST_HEAD(&dp->dl_perclnt);
	INIT_LIST_HEAD(&dp->dl_recall_lru);
	dp->dl_clnt_odstate = odstate;
	get_clnt_odstate(odstate);
	dp->dl_type = NFS4_OPEN_DELEGATE_READ;
	dp->dl_retries = 1;
	nfsd4_init_cb(&dp->dl_recall, dp->dl_stid.sc_client,
		      &nfsd4_cb_recall_ops, NFSPROC4_CLNT_CB_RECALL);
	get_nfs4_file(fp);
	dp->dl_stid.sc_file = fp;
	return dp;
out_dec:
	atomic_long_dec(&num_delegations);
	return NULL;
}

void
nfs4_put_stid(struct nfs4_stid *s)
{
	struct nfs4_file *fp = s->sc_file;
	struct nfs4_client *clp = s->sc_client;

	might_lock(&clp->cl_lock);

	if (!refcount_dec_and_lock(&s->sc_count, &clp->cl_lock)) {
		wake_up_all(&close_wq);
		return;
	}
	idr_remove(&clp->cl_stateids, s->sc_stateid.si_opaque.so_id);
	spin_unlock(&clp->cl_lock);
	s->sc_free(s);
	if (fp)
		put_nfs4_file(fp);
}

void
nfs4_inc_and_copy_stateid(stateid_t *dst, struct nfs4_stid *stid)
{
	stateid_t *src = &stid->sc_stateid;

	spin_lock(&stid->sc_lock);
	if (unlikely(++src->si_generation == 0))
		src->si_generation = 1;
	memcpy(dst, src, sizeof(*dst));
	spin_unlock(&stid->sc_lock);
}

static void put_deleg_file(struct nfs4_file *fp)
{
	struct file *filp = NULL;

	spin_lock(&fp->fi_lock);
	if (--fp->fi_delegees == 0)
		swap(filp, fp->fi_deleg_file);
	spin_unlock(&fp->fi_lock);

	if (filp)
		fput(filp);
}

static void nfs4_unlock_deleg_lease(struct nfs4_delegation *dp)
{
	struct nfs4_file *fp = dp->dl_stid.sc_file;
	struct file *filp = fp->fi_deleg_file;

	WARN_ON_ONCE(!fp->fi_delegees);

	vfs_setlease(filp, F_UNLCK, NULL, (void **)&dp);
	put_deleg_file(fp);
}

static void destroy_unhashed_deleg(struct nfs4_delegation *dp)
{
	put_clnt_odstate(dp->dl_clnt_odstate);
	nfs4_unlock_deleg_lease(dp);
	nfs4_put_stid(&dp->dl_stid);
}

void nfs4_unhash_stid(struct nfs4_stid *s)
{
	s->sc_type = 0;
}

/**
 * nfs4_delegation_exists - Discover if this delegation already exists
 * @clp:     a pointer to the nfs4_client we're granting a delegation to
 * @fp:      a pointer to the nfs4_file we're granting a delegation on
 *
 * Return:
 *      On success: true iff an existing delegation is found
 */

static bool
nfs4_delegation_exists(struct nfs4_client *clp, struct nfs4_file *fp)
{
	struct nfs4_delegation *searchdp = NULL;
	struct nfs4_client *searchclp = NULL;

	lockdep_assert_held(&state_lock);
	lockdep_assert_held(&fp->fi_lock);

	list_for_each_entry(searchdp, &fp->fi_delegations, dl_perfile) {
		searchclp = searchdp->dl_stid.sc_client;
		if (clp == searchclp) {
			return true;
		}
	}
	return false;
}

/**
 * hash_delegation_locked - Add a delegation to the appropriate lists
 * @dp:     a pointer to the nfs4_delegation we are adding.
 * @fp:     a pointer to the nfs4_file we're granting a delegation on
 *
 * Return:
 *      On success: NULL if the delegation was successfully hashed.
 *
 *      On error: -EAGAIN if one was previously granted to this
 *                 nfs4_client for this nfs4_file. Delegation is not hashed.
 *
 */

static int
hash_delegation_locked(struct nfs4_delegation *dp, struct nfs4_file *fp)
{
	struct nfs4_client *clp = dp->dl_stid.sc_client;

	lockdep_assert_held(&state_lock);
	lockdep_assert_held(&fp->fi_lock);

	if (nfs4_delegation_exists(clp, fp))
		return -EAGAIN;
	refcount_inc(&dp->dl_stid.sc_count);
	dp->dl_stid.sc_type = NFS4_DELEG_STID;
	list_add(&dp->dl_perfile, &fp->fi_delegations);
	list_add(&dp->dl_perclnt, &clp->cl_delegations);
	return 0;
}

static bool
unhash_delegation_locked(struct nfs4_delegation *dp)
{
	struct nfs4_file *fp = dp->dl_stid.sc_file;

	lockdep_assert_held(&state_lock);

	if (list_empty(&dp->dl_perfile))
		return false;

	dp->dl_stid.sc_type = NFS4_CLOSED_DELEG_STID;
	/* Ensure that deleg break won't try to requeue it */
	++dp->dl_time;
	spin_lock(&fp->fi_lock);
	list_del_init(&dp->dl_perclnt);
	list_del_init(&dp->dl_recall_lru);
	list_del_init(&dp->dl_perfile);
	spin_unlock(&fp->fi_lock);
	return true;
}

static void destroy_delegation(struct nfs4_delegation *dp)
{
	bool unhashed;

	spin_lock(&state_lock);
	unhashed = unhash_delegation_locked(dp);
	spin_unlock(&state_lock);
	if (unhashed)
		destroy_unhashed_deleg(dp);
}

static void revoke_delegation(struct nfs4_delegation *dp)
{
	struct nfs4_client *clp = dp->dl_stid.sc_client;

	WARN_ON(!list_empty(&dp->dl_recall_lru));

	if (clp->cl_minorversion) {
		dp->dl_stid.sc_type = NFS4_REVOKED_DELEG_STID;
		refcount_inc(&dp->dl_stid.sc_count);
		spin_lock(&clp->cl_lock);
		list_add(&dp->dl_recall_lru, &clp->cl_revoked);
		spin_unlock(&clp->cl_lock);
	}
	destroy_unhashed_deleg(dp);
}

/* 
 * SETCLIENTID state 
 */

static unsigned int clientid_hashval(u32 id)
{
	return id & CLIENT_HASH_MASK;
}

static unsigned int clientstr_hashval(const char *name)
{
	return opaque_hashval(name, 8) & CLIENT_HASH_MASK;
}

/*
 * We store the NONE, READ, WRITE, and BOTH bits separately in the
 * st_{access,deny}_bmap field of the stateid, in order to track not
 * only what share bits are currently in force, but also what
 * combinations of share bits previous opens have used.  This allows us
 * to enforce the recommendation of rfc 3530 14.2.19 that the server
 * return an error if the client attempt to downgrade to a combination
 * of share bits not explicable by closing some of its previous opens.
 *
 * XXX: This enforcement is actually incomplete, since we don't keep
 * track of access/deny bit combinations; so, e.g., we allow:
 *
 *	OPEN allow read, deny write
 *	OPEN allow both, deny none
 *	DOWNGRADE allow read, deny none
 *
 * which we should reject.
 */
static unsigned int
bmap_to_share_mode(unsigned long bmap) {
	int i;
	unsigned int access = 0;

	for (i = 1; i < 4; i++) {
		if (test_bit(i, &bmap))
			access |= i;
	}
	return access;
}

/* set share access for a given stateid */
static inline void
set_access(u32 access, struct nfs4_ol_stateid *stp)
{
	unsigned char mask = 1 << access;

	WARN_ON_ONCE(access > NFS4_SHARE_ACCESS_BOTH);
	stp->st_access_bmap |= mask;
}

/* clear share access for a given stateid */
static inline void
clear_access(u32 access, struct nfs4_ol_stateid *stp)
{
	unsigned char mask = 1 << access;

	WARN_ON_ONCE(access > NFS4_SHARE_ACCESS_BOTH);
	stp->st_access_bmap &= ~mask;
}

/* test whether a given stateid has access */
static inline bool
test_access(u32 access, struct nfs4_ol_stateid *stp)
{
	unsigned char mask = 1 << access;

	return (bool)(stp->st_access_bmap & mask);
}

/* set share deny for a given stateid */
static inline void
set_deny(u32 deny, struct nfs4_ol_stateid *stp)
{
	unsigned char mask = 1 << deny;

	WARN_ON_ONCE(deny > NFS4_SHARE_DENY_BOTH);
	stp->st_deny_bmap |= mask;
}

/* clear share deny for a given stateid */
static inline void
clear_deny(u32 deny, struct nfs4_ol_stateid *stp)
{
	unsigned char mask = 1 << deny;

	WARN_ON_ONCE(deny > NFS4_SHARE_DENY_BOTH);
	stp->st_deny_bmap &= ~mask;
}

/* test whether a given stateid is denying specific access */
static inline bool
test_deny(u32 deny, struct nfs4_ol_stateid *stp)
{
	unsigned char mask = 1 << deny;

	return (bool)(stp->st_deny_bmap & mask);
}

static int nfs4_access_to_omode(u32 access)
{
	switch (access & NFS4_SHARE_ACCESS_BOTH) {
	case NFS4_SHARE_ACCESS_READ:
		return O_RDONLY;
	case NFS4_SHARE_ACCESS_WRITE:
		return O_WRONLY;
	case NFS4_SHARE_ACCESS_BOTH:
		return O_RDWR;
	}
	WARN_ON_ONCE(1);
	return O_RDONLY;
}

/*
 * A stateid that had a deny mode associated with it is being released
 * or downgraded. Recalculate the deny mode on the file.
 */
static void
recalculate_deny_mode(struct nfs4_file *fp)
{
	struct nfs4_ol_stateid *stp;

	spin_lock(&fp->fi_lock);
	fp->fi_share_deny = 0;
	list_for_each_entry(stp, &fp->fi_stateids, st_perfile)
		fp->fi_share_deny |= bmap_to_share_mode(stp->st_deny_bmap);
	spin_unlock(&fp->fi_lock);
}

static void
reset_union_bmap_deny(u32 deny, struct nfs4_ol_stateid *stp)
{
	int i;
	bool change = false;

	for (i = 1; i < 4; i++) {
		if ((i & deny) != i) {
			change = true;
			clear_deny(i, stp);
		}
	}

	/* Recalculate per-file deny mode if there was a change */
	if (change)
		recalculate_deny_mode(stp->st_stid.sc_file);
}

/* release all access and file references for a given stateid */
static void
release_all_access(struct nfs4_ol_stateid *stp)
{
	int i;
	struct nfs4_file *fp = stp->st_stid.sc_file;

	if (fp && stp->st_deny_bmap != 0)
		recalculate_deny_mode(fp);

	for (i = 1; i < 4; i++) {
		if (test_access(i, stp))
			nfs4_file_put_access(stp->st_stid.sc_file, i);
		clear_access(i, stp);
	}
}

static inline void nfs4_free_stateowner(struct nfs4_stateowner *sop)
{
	kfree(sop->so_owner.data);
	sop->so_ops->so_free(sop);
}

static void nfs4_put_stateowner(struct nfs4_stateowner *sop)
{
	struct nfs4_client *clp = sop->so_client;

	might_lock(&clp->cl_lock);

	if (!atomic_dec_and_lock(&sop->so_count, &clp->cl_lock))
		return;
	sop->so_ops->so_unhash(sop);
	spin_unlock(&clp->cl_lock);
	nfs4_free_stateowner(sop);
}

static bool unhash_ol_stateid(struct nfs4_ol_stateid *stp)
{
	struct nfs4_file *fp = stp->st_stid.sc_file;

	lockdep_assert_held(&stp->st_stateowner->so_client->cl_lock);

	if (list_empty(&stp->st_perfile))
		return false;

	spin_lock(&fp->fi_lock);
	list_del_init(&stp->st_perfile);
	spin_unlock(&fp->fi_lock);
	list_del(&stp->st_perstateowner);
	return true;
}

static void nfs4_free_ol_stateid(struct nfs4_stid *stid)
{
	struct nfs4_ol_stateid *stp = openlockstateid(stid);

	put_clnt_odstate(stp->st_clnt_odstate);
	release_all_access(stp);
	if (stp->st_stateowner)
		nfs4_put_stateowner(stp->st_stateowner);
	kmem_cache_free(stateid_slab, stid);
}

static void nfs4_free_lock_stateid(struct nfs4_stid *stid)
{
	struct nfs4_ol_stateid *stp = openlockstateid(stid);
	struct nfs4_lockowner *lo = lockowner(stp->st_stateowner);
	struct file *file;

	file = find_any_file(stp->st_stid.sc_file);
	if (file)
		filp_close(file, (fl_owner_t)lo);
	nfs4_free_ol_stateid(stid);
}

/*
 * Put the persistent reference to an already unhashed generic stateid, while
 * holding the cl_lock. If it's the last reference, then put it onto the
 * reaplist for later destruction.
 */
static void put_ol_stateid_locked(struct nfs4_ol_stateid *stp,
				       struct list_head *reaplist)
{
	struct nfs4_stid *s = &stp->st_stid;
	struct nfs4_client *clp = s->sc_client;

	lockdep_assert_held(&clp->cl_lock);

	WARN_ON_ONCE(!list_empty(&stp->st_locks));

	if (!refcount_dec_and_test(&s->sc_count)) {
		wake_up_all(&close_wq);
		return;
	}

	idr_remove(&clp->cl_stateids, s->sc_stateid.si_opaque.so_id);
	list_add(&stp->st_locks, reaplist);
}

static bool unhash_lock_stateid(struct nfs4_ol_stateid *stp)
{
	lockdep_assert_held(&stp->st_stid.sc_client->cl_lock);

	list_del_init(&stp->st_locks);
	nfs4_unhash_stid(&stp->st_stid);
	return unhash_ol_stateid(stp);
}

static void release_lock_stateid(struct nfs4_ol_stateid *stp)
{
	struct nfs4_client *clp = stp->st_stid.sc_client;
	bool unhashed;

	spin_lock(&clp->cl_lock);
	unhashed = unhash_lock_stateid(stp);
	spin_unlock(&clp->cl_lock);
	if (unhashed)
		nfs4_put_stid(&stp->st_stid);
}

static void unhash_lockowner_locked(struct nfs4_lockowner *lo)
{
	struct nfs4_client *clp = lo->lo_owner.so_client;

	lockdep_assert_held(&clp->cl_lock);

	list_del_init(&lo->lo_owner.so_strhash);
}

/*
 * Free a list of generic stateids that were collected earlier after being
 * fully unhashed.
 */
static void
free_ol_stateid_reaplist(struct list_head *reaplist)
{
	struct nfs4_ol_stateid *stp;
	struct nfs4_file *fp;

	might_sleep();

	while (!list_empty(reaplist)) {
		stp = list_first_entry(reaplist, struct nfs4_ol_stateid,
				       st_locks);
		list_del(&stp->st_locks);
		fp = stp->st_stid.sc_file;
		stp->st_stid.sc_free(&stp->st_stid);
		if (fp)
			put_nfs4_file(fp);
	}
}

static void release_open_stateid_locks(struct nfs4_ol_stateid *open_stp,
				       struct list_head *reaplist)
{
	struct nfs4_ol_stateid *stp;

	lockdep_assert_held(&open_stp->st_stid.sc_client->cl_lock);

	while (!list_empty(&open_stp->st_locks)) {
		stp = list_entry(open_stp->st_locks.next,
				struct nfs4_ol_stateid, st_locks);
		WARN_ON(!unhash_lock_stateid(stp));
		put_ol_stateid_locked(stp, reaplist);
	}
}

static bool unhash_open_stateid(struct nfs4_ol_stateid *stp,
				struct list_head *reaplist)
{
	bool unhashed;

	lockdep_assert_held(&stp->st_stid.sc_client->cl_lock);

	unhashed = unhash_ol_stateid(stp);
	release_open_stateid_locks(stp, reaplist);
	return unhashed;
}

static void release_open_stateid(struct nfs4_ol_stateid *stp)
{
	LIST_HEAD(reaplist);

	spin_lock(&stp->st_stid.sc_client->cl_lock);
	if (unhash_open_stateid(stp, &reaplist))
		put_ol_stateid_locked(stp, &reaplist);
	spin_unlock(&stp->st_stid.sc_client->cl_lock);
	free_ol_stateid_reaplist(&reaplist);
}

static void unhash_openowner_locked(struct nfs4_openowner *oo)
{
	struct nfs4_client *clp = oo->oo_owner.so_client;

	lockdep_assert_held(&clp->cl_lock);

	list_del_init(&oo->oo_owner.so_strhash);
	list_del_init(&oo->oo_perclient);
}

static void release_last_closed_stateid(struct nfs4_openowner *oo)
{
	struct nfsd_net *nn = net_generic(oo->oo_owner.so_client->net,
					  nfsd_net_id);
	struct nfs4_ol_stateid *s;

	spin_lock(&nn->client_lock);
	s = oo->oo_last_closed_stid;
	if (s) {
		list_del_init(&oo->oo_close_lru);
		oo->oo_last_closed_stid = NULL;
	}
	spin_unlock(&nn->client_lock);
	if (s)
		nfs4_put_stid(&s->st_stid);
}

static void release_openowner(struct nfs4_openowner *oo)
{
	struct nfs4_ol_stateid *stp;
	struct nfs4_client *clp = oo->oo_owner.so_client;
	struct list_head reaplist;

	INIT_LIST_HEAD(&reaplist);

	spin_lock(&clp->cl_lock);
	unhash_openowner_locked(oo);
	while (!list_empty(&oo->oo_owner.so_stateids)) {
		stp = list_first_entry(&oo->oo_owner.so_stateids,
				struct nfs4_ol_stateid, st_perstateowner);
		if (unhash_open_stateid(stp, &reaplist))
			put_ol_stateid_locked(stp, &reaplist);
	}
	spin_unlock(&clp->cl_lock);
	free_ol_stateid_reaplist(&reaplist);
	release_last_closed_stateid(oo);
	nfs4_put_stateowner(&oo->oo_owner);
}

static inline int
hash_sessionid(struct nfs4_sessionid *sessionid)
{
	struct nfsd4_sessionid *sid = (struct nfsd4_sessionid *)sessionid;

	return sid->sequence % SESSION_HASH_SIZE;
}

#ifdef CONFIG_SUNRPC_DEBUG
static inline void
dump_sessionid(const char *fn, struct nfs4_sessionid *sessionid)
{
	u32 *ptr = (u32 *)(&sessionid->data[0]);
	dprintk("%s: %u:%u:%u:%u\n", fn, ptr[0], ptr[1], ptr[2], ptr[3]);
}
#else
static inline void
dump_sessionid(const char *fn, struct nfs4_sessionid *sessionid)
{
}
#endif

/*
 * Bump the seqid on cstate->replay_owner, and clear replay_owner if it
 * won't be used for replay.
 */
void nfsd4_bump_seqid(struct nfsd4_compound_state *cstate, __be32 nfserr)
{
	struct nfs4_stateowner *so = cstate->replay_owner;

	if (nfserr == nfserr_replay_me)
		return;

	if (!seqid_mutating_err(ntohl(nfserr))) {
		nfsd4_cstate_clear_replay(cstate);
		return;
	}
	if (!so)
		return;
	if (so->so_is_open_owner)
		release_last_closed_stateid(openowner(so));
	so->so_seqid++;
	return;
}

static void
gen_sessionid(struct nfsd4_session *ses)
{
	struct nfs4_client *clp = ses->se_client;
	struct nfsd4_sessionid *sid;

	sid = (struct nfsd4_sessionid *)ses->se_sessionid.data;
	sid->clientid = clp->cl_clientid;
	sid->sequence = current_sessionid++;
	sid->reserved = 0;
}

/*
 * The protocol defines ca_maxresponssize_cached to include the size of
 * the rpc header, but all we need to cache is the data starting after
 * the end of the initial SEQUENCE operation--the rest we regenerate
 * each time.  Therefore we can advertise a ca_maxresponssize_cached
 * value that is the number of bytes in our cache plus a few additional
 * bytes.  In order to stay on the safe side, and not promise more than
 * we can cache, those additional bytes must be the minimum possible: 24
 * bytes of rpc header (xid through accept state, with AUTH_NULL
 * verifier), 12 for the compound header (with zero-length tag), and 44
 * for the SEQUENCE op response:
 */
#define NFSD_MIN_HDR_SEQ_SZ  (24 + 12 + 44)

static void
free_session_slots(struct nfsd4_session *ses)
{
	int i;

	for (i = 0; i < ses->se_fchannel.maxreqs; i++) {
		free_svc_cred(&ses->se_slots[i]->sl_cred);
		kfree(ses->se_slots[i]);
	}
}

/*
 * We don't actually need to cache the rpc and session headers, so we
 * can allocate a little less for each slot:
 */
static inline u32 slot_bytes(struct nfsd4_channel_attrs *ca)
{
	u32 size;

	if (ca->maxresp_cached < NFSD_MIN_HDR_SEQ_SZ)
		size = 0;
	else
		size = ca->maxresp_cached - NFSD_MIN_HDR_SEQ_SZ;
	return size + sizeof(struct nfsd4_slot);
}

/*
 * XXX: If we run out of reserved DRC memory we could (up to a point)
 * re-negotiate active sessions and reduce their slot usage to make
 * room for new connections. For now we just fail the create session.
 */
static u32 nfsd4_get_drc_mem(struct nfsd4_channel_attrs *ca)
{
	u32 slotsize = slot_bytes(ca);
	u32 num = ca->maxreqs;
	int avail;

	spin_lock(&nfsd_drc_lock);
	avail = min((unsigned long)NFSD_MAX_MEM_PER_SESSION,
		    nfsd_drc_max_mem - nfsd_drc_mem_used);
	/*
	 * Never use more than a third of the remaining memory,
	 * unless it's the only way to give this client a slot:
	 */
	avail = clamp_t(int, avail, slotsize, avail/3);
	num = min_t(int, num, avail / slotsize);
	nfsd_drc_mem_used += num * slotsize;
	spin_unlock(&nfsd_drc_lock);

	return num;
}

static void nfsd4_put_drc_mem(struct nfsd4_channel_attrs *ca)
{
	int slotsize = slot_bytes(ca);

	spin_lock(&nfsd_drc_lock);
	nfsd_drc_mem_used -= slotsize * ca->maxreqs;
	spin_unlock(&nfsd_drc_lock);
}

static struct nfsd4_session *alloc_session(struct nfsd4_channel_attrs *fattrs,
					   struct nfsd4_channel_attrs *battrs)
{
	int numslots = fattrs->maxreqs;
	int slotsize = slot_bytes(fattrs);
	struct nfsd4_session *new;
	int mem, i;

	BUILD_BUG_ON(NFSD_MAX_SLOTS_PER_SESSION * sizeof(struct nfsd4_slot *)
			+ sizeof(struct nfsd4_session) > PAGE_SIZE);
	mem = numslots * sizeof(struct nfsd4_slot *);

	new = kzalloc(sizeof(*new) + mem, GFP_KERNEL);
	if (!new)
		return NULL;
	/* allocate each struct nfsd4_slot and data cache in one piece */
	for (i = 0; i < numslots; i++) {
		new->se_slots[i] = kzalloc(slotsize, GFP_KERNEL);
		if (!new->se_slots[i])
			goto out_free;
	}

	memcpy(&new->se_fchannel, fattrs, sizeof(struct nfsd4_channel_attrs));
	memcpy(&new->se_bchannel, battrs, sizeof(struct nfsd4_channel_attrs));

	return new;
out_free:
	while (i--)
		kfree(new->se_slots[i]);
	kfree(new);
	return NULL;
}

static void free_conn(struct nfsd4_conn *c)
{
	svc_xprt_put(c->cn_xprt);
	kfree(c);
}

static void nfsd4_conn_lost(struct svc_xpt_user *u)
{
	struct nfsd4_conn *c = container_of(u, struct nfsd4_conn, cn_xpt_user);
	struct nfs4_client *clp = c->cn_session->se_client;

	spin_lock(&clp->cl_lock);
	if (!list_empty(&c->cn_persession)) {
		list_del(&c->cn_persession);
		free_conn(c);
	}
	nfsd4_probe_callback(clp);
	spin_unlock(&clp->cl_lock);
}

static struct nfsd4_conn *alloc_conn(struct svc_rqst *rqstp, u32 flags)
{
	struct nfsd4_conn *conn;

	conn = kmalloc(sizeof(struct nfsd4_conn), GFP_KERNEL);
	if (!conn)
		return NULL;
	svc_xprt_get(rqstp->rq_xprt);
	conn->cn_xprt = rqstp->rq_xprt;
	conn->cn_flags = flags;
	INIT_LIST_HEAD(&conn->cn_xpt_user.list);
	return conn;
}

static void __nfsd4_hash_conn(struct nfsd4_conn *conn, struct nfsd4_session *ses)
{
	conn->cn_session = ses;
	list_add(&conn->cn_persession, &ses->se_conns);
}

static void nfsd4_hash_conn(struct nfsd4_conn *conn, struct nfsd4_session *ses)
{
	struct nfs4_client *clp = ses->se_client;

	spin_lock(&clp->cl_lock);
	__nfsd4_hash_conn(conn, ses);
	spin_unlock(&clp->cl_lock);
}

static int nfsd4_register_conn(struct nfsd4_conn *conn)
{
	conn->cn_xpt_user.callback = nfsd4_conn_lost;
	return register_xpt_user(conn->cn_xprt, &conn->cn_xpt_user);
}

static void nfsd4_init_conn(struct svc_rqst *rqstp, struct nfsd4_conn *conn, struct nfsd4_session *ses)
{
	int ret;

	nfsd4_hash_conn(conn, ses);
	ret = nfsd4_register_conn(conn);
	if (ret)
		/* oops; xprt is already down: */
		nfsd4_conn_lost(&conn->cn_xpt_user);
	/* We may have gained or lost a callback channel: */
	nfsd4_probe_callback_sync(ses->se_client);
}

static struct nfsd4_conn *alloc_conn_from_crses(struct svc_rqst *rqstp, struct nfsd4_create_session *cses)
{
	u32 dir = NFS4_CDFC4_FORE;

	if (cses->flags & SESSION4_BACK_CHAN)
		dir |= NFS4_CDFC4_BACK;
	return alloc_conn(rqstp, dir);
}

/* must be called under client_lock */
static void nfsd4_del_conns(struct nfsd4_session *s)
{
	struct nfs4_client *clp = s->se_client;
	struct nfsd4_conn *c;

	spin_lock(&clp->cl_lock);
	while (!list_empty(&s->se_conns)) {
		c = list_first_entry(&s->se_conns, struct nfsd4_conn, cn_persession);
		list_del_init(&c->cn_persession);
		spin_unlock(&clp->cl_lock);

		unregister_xpt_user(c->cn_xprt, &c->cn_xpt_user);
		free_conn(c);

		spin_lock(&clp->cl_lock);
	}
	spin_unlock(&clp->cl_lock);
}

static void __free_session(struct nfsd4_session *ses)
{
	free_session_slots(ses);
	kfree(ses);
}

static void free_session(struct nfsd4_session *ses)
{
	nfsd4_del_conns(ses);
	nfsd4_put_drc_mem(&ses->se_fchannel);
	__free_session(ses);
}

static void init_session(struct svc_rqst *rqstp, struct nfsd4_session *new, struct nfs4_client *clp, struct nfsd4_create_session *cses)
{
	int idx;
	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);

	new->se_client = clp;
	gen_sessionid(new);

	INIT_LIST_HEAD(&new->se_conns);

	new->se_cb_seq_nr = 1;
	new->se_flags = cses->flags;
	new->se_cb_prog = cses->callback_prog;
	new->se_cb_sec = cses->cb_sec;
	atomic_set(&new->se_ref, 0);
	idx = hash_sessionid(&new->se_sessionid);
	list_add(&new->se_hash, &nn->sessionid_hashtbl[idx]);
	spin_lock(&clp->cl_lock);
	list_add(&new->se_perclnt, &clp->cl_sessions);
	spin_unlock(&clp->cl_lock);

	{
		struct sockaddr *sa = svc_addr(rqstp);
		/*
		 * This is a little silly; with sessions there's no real
		 * use for the callback address.  Use the peer address
		 * as a reasonable default for now, but consider fixing
		 * the rpc client not to require an address in the
		 * future:
		 */
		rpc_copy_addr((struct sockaddr *)&clp->cl_cb_conn.cb_addr, sa);
		clp->cl_cb_conn.cb_addrlen = svc_addr_len(sa);
	}
}

/* caller must hold client_lock */
static struct nfsd4_session *
__find_in_sessionid_hashtbl(struct nfs4_sessionid *sessionid, struct net *net)
{
	struct nfsd4_session *elem;
	int idx;
	struct nfsd_net *nn = net_generic(net, nfsd_net_id);

	lockdep_assert_held(&nn->client_lock);

	dump_sessionid(__func__, sessionid);
	idx = hash_sessionid(sessionid);
	/* Search in the appropriate list */
	list_for_each_entry(elem, &nn->sessionid_hashtbl[idx], se_hash) {
		if (!memcmp(elem->se_sessionid.data, sessionid->data,
			    NFS4_MAX_SESSIONID_LEN)) {
			return elem;
		}
	}

	dprintk("%s: session not found\n", __func__);
	return NULL;
}

static struct nfsd4_session *
find_in_sessionid_hashtbl(struct nfs4_sessionid *sessionid, struct net *net,
		__be32 *ret)
{
	struct nfsd4_session *session;
	__be32 status = nfserr_badsession;

	session = __find_in_sessionid_hashtbl(sessionid, net);
	if (!session)
		goto out;
	status = nfsd4_get_session_locked(session);
	if (status)
		session = NULL;
out:
	*ret = status;
	return session;
}

/* caller must hold client_lock */
static void
unhash_session(struct nfsd4_session *ses)
{
	struct nfs4_client *clp = ses->se_client;
	struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);

	lockdep_assert_held(&nn->client_lock);

	list_del(&ses->se_hash);
	spin_lock(&ses->se_client->cl_lock);
	list_del(&ses->se_perclnt);
	spin_unlock(&ses->se_client->cl_lock);
}

/* SETCLIENTID and SETCLIENTID_CONFIRM Helper functions */
static int
STALE_CLIENTID(clientid_t *clid, struct nfsd_net *nn)
{
	/*
	 * We're assuming the clid was not given out from a boot
	 * precisely 2^32 (about 136 years) before this one.  That seems
	 * a safe assumption:
	 */
	if (clid->cl_boot == (u32)nn->boot_time)
		return 0;
	dprintk("NFSD stale clientid (%08x/%08x) boot_time %08lx\n",
		clid->cl_boot, clid->cl_id, nn->boot_time);
	return 1;
}

/* 
 * XXX Should we use a slab cache ?
 * This type of memory management is somewhat inefficient, but we use it
 * anyway since SETCLIENTID is not a common operation.
 */
static struct nfs4_client *alloc_client(struct xdr_netobj name)
{
	struct nfs4_client *clp;
	int i;

	clp = kmem_cache_zalloc(client_slab, GFP_KERNEL);
	if (clp == NULL)
		return NULL;
	clp->cl_name.data = kmemdup(name.data, name.len, GFP_KERNEL);
	if (clp->cl_name.data == NULL)
		goto err_no_name;
	clp->cl_ownerstr_hashtbl = kmalloc_array(OWNER_HASH_SIZE,
						 sizeof(struct list_head),
						 GFP_KERNEL);
	if (!clp->cl_ownerstr_hashtbl)
		goto err_no_hashtbl;
	for (i = 0; i < OWNER_HASH_SIZE; i++)
		INIT_LIST_HEAD(&clp->cl_ownerstr_hashtbl[i]);
	clp->cl_name.len = name.len;
	INIT_LIST_HEAD(&clp->cl_sessions);
	idr_init(&clp->cl_stateids);
	atomic_set(&clp->cl_refcount, 0);
	clp->cl_cb_state = NFSD4_CB_UNKNOWN;
	INIT_LIST_HEAD(&clp->cl_idhash);
	INIT_LIST_HEAD(&clp->cl_openowners);
	INIT_LIST_HEAD(&clp->cl_delegations);
	INIT_LIST_HEAD(&clp->cl_lru);
	INIT_LIST_HEAD(&clp->cl_revoked);
#ifdef CONFIG_NFSD_PNFS
	INIT_LIST_HEAD(&clp->cl_lo_states);
#endif
	spin_lock_init(&clp->cl_lock);
	rpc_init_wait_queue(&clp->cl_cb_waitq, "Backchannel slot table");
	return clp;
err_no_hashtbl:
	kfree(clp->cl_name.data);
err_no_name:
	kmem_cache_free(client_slab, clp);
	return NULL;
}

static void
free_client(struct nfs4_client *clp)
{
	while (!list_empty(&clp->cl_sessions)) {
		struct nfsd4_session *ses;
		ses = list_entry(clp->cl_sessions.next, struct nfsd4_session,
				se_perclnt);
		list_del(&ses->se_perclnt);
		WARN_ON_ONCE(atomic_read(&ses->se_ref));
		free_session(ses);
	}
	rpc_destroy_wait_queue(&clp->cl_cb_waitq);
	free_svc_cred(&clp->cl_cred);
	kfree(clp->cl_ownerstr_hashtbl);
	kfree(clp->cl_name.data);
	idr_destroy(&clp->cl_stateids);
	kmem_cache_free(client_slab, clp);
}

/* must be called under the client_lock */
static void
unhash_client_locked(struct nfs4_client *clp)
{
	struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
	struct nfsd4_session *ses;

	lockdep_assert_held(&nn->client_lock);

	/* Mark the client as expired! */
	clp->cl_time = 0;
	/* Make it invisible */
	if (!list_empty(&clp->cl_idhash)) {
		list_del_init(&clp->cl_idhash);
		if (test_bit(NFSD4_CLIENT_CONFIRMED, &clp->cl_flags))
			rb_erase(&clp->cl_namenode, &nn->conf_name_tree);
		else
			rb_erase(&clp->cl_namenode, &nn->unconf_name_tree);
	}
	list_del_init(&clp->cl_lru);
	spin_lock(&clp->cl_lock);
	list_for_each_entry(ses, &clp->cl_sessions, se_perclnt)
		list_del_init(&ses->se_hash);
	spin_unlock(&clp->cl_lock);
}

static void
unhash_client(struct nfs4_client *clp)
{
	struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);

	spin_lock(&nn->client_lock);
	unhash_client_locked(clp);
	spin_unlock(&nn->client_lock);
}

static __be32 mark_client_expired_locked(struct nfs4_client *clp)
{
	if (atomic_read(&clp->cl_refcount))
		return nfserr_jukebox;
	unhash_client_locked(clp);
	return nfs_ok;
}

static void
__destroy_client(struct nfs4_client *clp)
{
	int i;
	struct nfs4_openowner *oo;
	struct nfs4_delegation *dp;
	struct list_head reaplist;

	INIT_LIST_HEAD(&reaplist);
	spin_lock(&state_lock);
	while (!list_empty(&clp->cl_delegations)) {
		dp = list_entry(clp->cl_delegations.next, struct nfs4_delegation, dl_perclnt);
		WARN_ON(!unhash_delegation_locked(dp));
		list_add(&dp->dl_recall_lru, &reaplist);
	}
	spin_unlock(&state_lock);
	while (!list_empty(&reaplist)) {
		dp = list_entry(reaplist.next, struct nfs4_delegation, dl_recall_lru);
		list_del_init(&dp->dl_recall_lru);
		destroy_unhashed_deleg(dp);
	}
	while (!list_empty(&clp->cl_revoked)) {
		dp = list_entry(clp->cl_revoked.next, struct nfs4_delegation, dl_recall_lru);
		list_del_init(&dp->dl_recall_lru);
		nfs4_put_stid(&dp->dl_stid);
	}
	while (!list_empty(&clp->cl_openowners)) {
		oo = list_entry(clp->cl_openowners.next, struct nfs4_openowner, oo_perclient);
		nfs4_get_stateowner(&oo->oo_owner);
		release_openowner(oo);
	}
	for (i = 0; i < OWNER_HASH_SIZE; i++) {
		struct nfs4_stateowner *so, *tmp;

		list_for_each_entry_safe(so, tmp, &clp->cl_ownerstr_hashtbl[i],
					 so_strhash) {
			/* Should be no openowners at this point */
			WARN_ON_ONCE(so->so_is_open_owner);
			remove_blocked_locks(lockowner(so));
		}
	}
	nfsd4_return_all_client_layouts(clp);
	nfsd4_shutdown_callback(clp);
	if (clp->cl_cb_conn.cb_xprt)
		svc_xprt_put(clp->cl_cb_conn.cb_xprt);
	free_client(clp);
}

static void
destroy_client(struct nfs4_client *clp)
{
	unhash_client(clp);
	__destroy_client(clp);
}

static void expire_client(struct nfs4_client *clp)
{
	unhash_client(clp);
	nfsd4_client_record_remove(clp);
	__destroy_client(clp);
}

static void copy_verf(struct nfs4_client *target, nfs4_verifier *source)
{
	memcpy(target->cl_verifier.data, source->data,
			sizeof(target->cl_verifier.data));
}

static void copy_clid(struct nfs4_client *target, struct nfs4_client *source)
{
	target->cl_clientid.cl_boot = source->cl_clientid.cl_boot; 
	target->cl_clientid.cl_id = source->cl_clientid.cl_id; 
}

static int copy_cred(struct svc_cred *target, struct svc_cred *source)
{
	target->cr_principal = kstrdup(source->cr_principal, GFP_KERNEL);
	target->cr_raw_principal = kstrdup(source->cr_raw_principal,
								GFP_KERNEL);
	target->cr_targ_princ = kstrdup(source->cr_targ_princ, GFP_KERNEL);
	if ((source->cr_principal && !target->cr_principal) ||
	    (source->cr_raw_principal && !target->cr_raw_principal) ||
	    (source->cr_targ_princ && !target->cr_targ_princ))
		return -ENOMEM;

	target->cr_flavor = source->cr_flavor;
	target->cr_uid = source->cr_uid;
	target->cr_gid = source->cr_gid;
	target->cr_group_info = source->cr_group_info;
	get_group_info(target->cr_group_info);
	target->cr_gss_mech = source->cr_gss_mech;
	if (source->cr_gss_mech)
		gss_mech_get(source->cr_gss_mech);
	return 0;
}

static int
compare_blob(const struct xdr_netobj *o1, const struct xdr_netobj *o2)
{
	if (o1->len < o2->len)
		return -1;
	if (o1->len > o2->len)
		return 1;
	return memcmp(o1->data, o2->data, o1->len);
}

static int same_name(const char *n1, const char *n2)
{
	return 0 == memcmp(n1, n2, HEXDIR_LEN);
}

static int
same_verf(nfs4_verifier *v1, nfs4_verifier *v2)
{
	return 0 == memcmp(v1->data, v2->data, sizeof(v1->data));
}

static int
same_clid(clientid_t *cl1, clientid_t *cl2)
{
	return (cl1->cl_boot == cl2->cl_boot) && (cl1->cl_id == cl2->cl_id);
}

static bool groups_equal(struct group_info *g1, struct group_info *g2)
{
	int i;

	if (g1->ngroups != g2->ngroups)
		return false;
	for (i=0; i<g1->ngroups; i++)
		if (!gid_eq(g1->gid[i], g2->gid[i]))
			return false;
	return true;
}

/*
 * RFC 3530 language requires clid_inuse be returned when the
 * "principal" associated with a requests differs from that previously
 * used.  We use uid, gid's, and gss principal string as our best
 * approximation.  We also don't want to allow non-gss use of a client
 * established using gss: in theory cr_principal should catch that
 * change, but in practice cr_principal can be null even in the gss case
 * since gssd doesn't always pass down a principal string.
 */
static bool is_gss_cred(struct svc_cred *cr)
{
	/* Is cr_flavor one of the gss "pseudoflavors"?: */
	return (cr->cr_flavor > RPC_AUTH_MAXFLAVOR);
}


static bool
same_creds(struct svc_cred *cr1, struct svc_cred *cr2)
{
	if ((is_gss_cred(cr1) != is_gss_cred(cr2))
		|| (!uid_eq(cr1->cr_uid, cr2->cr_uid))
		|| (!gid_eq(cr1->cr_gid, cr2->cr_gid))
		|| !groups_equal(cr1->cr_group_info, cr2->cr_group_info))
		return false;
	/* XXX: check that cr_targ_princ fields match ? */
	if (cr1->cr_principal == cr2->cr_principal)
		return true;
	if (!cr1->cr_principal || !cr2->cr_principal)
		return false;
	return 0 == strcmp(cr1->cr_principal, cr2->cr_principal);
}

static bool svc_rqst_integrity_protected(struct svc_rqst *rqstp)
{
	struct svc_cred *cr = &rqstp->rq_cred;
	u32 service;

	if (!cr->cr_gss_mech)
		return false;
	service = gss_pseudoflavor_to_service(cr->cr_gss_mech, cr->cr_flavor);
	return service == RPC_GSS_SVC_INTEGRITY ||
	       service == RPC_GSS_SVC_PRIVACY;
}

bool nfsd4_mach_creds_match(struct nfs4_client *cl, struct svc_rqst *rqstp)
{
	struct svc_cred *cr = &rqstp->rq_cred;

	if (!cl->cl_mach_cred)
		return true;
	if (cl->cl_cred.cr_gss_mech != cr->cr_gss_mech)
		return false;
	if (!svc_rqst_integrity_protected(rqstp))
		return false;
	if (cl->cl_cred.cr_raw_principal)
		return 0 == strcmp(cl->cl_cred.cr_raw_principal,
						cr->cr_raw_principal);
	if (!cr->cr_principal)
		return false;
	return 0 == strcmp(cl->cl_cred.cr_principal, cr->cr_principal);
}

static void gen_confirm(struct nfs4_client *clp, struct nfsd_net *nn)
{
	__be32 verf[2];

	/*
	 * This is opaque to client, so no need to byte-swap. Use
	 * __force to keep sparse happy
	 */
	verf[0] = (__force __be32)get_seconds();
	verf[1] = (__force __be32)nn->clverifier_counter++;
	memcpy(clp->cl_confirm.data, verf, sizeof(clp->cl_confirm.data));
}

static void gen_clid(struct nfs4_client *clp, struct nfsd_net *nn)
{
	clp->cl_clientid.cl_boot = nn->boot_time;
	clp->cl_clientid.cl_id = nn->clientid_counter++;
	gen_confirm(clp, nn);
}

static struct nfs4_stid *
find_stateid_locked(struct nfs4_client *cl, stateid_t *t)
{
	struct nfs4_stid *ret;

	ret = idr_find(&cl->cl_stateids, t->si_opaque.so_id);
	if (!ret || !ret->sc_type)
		return NULL;
	return ret;
}

static struct nfs4_stid *
find_stateid_by_type(struct nfs4_client *cl, stateid_t *t, char typemask)
{
	struct nfs4_stid *s;

	spin_lock(&cl->cl_lock);
	s = find_stateid_locked(cl, t);
	if (s != NULL) {
		if (typemask & s->sc_type)
			refcount_inc(&s->sc_count);
		else
			s = NULL;
	}
	spin_unlock(&cl->cl_lock);
	return s;
}

static struct nfs4_client *create_client(struct xdr_netobj name,
		struct svc_rqst *rqstp, nfs4_verifier *verf)
{
	struct nfs4_client *clp;
	struct sockaddr *sa = svc_addr(rqstp);
	int ret;
	struct net *net = SVC_NET(rqstp);

	clp = alloc_client(name);
	if (clp == NULL)
		return NULL;

	ret = copy_cred(&clp->cl_cred, &rqstp->rq_cred);
	if (ret) {
		free_client(clp);
		return NULL;
	}
	nfsd4_init_cb(&clp->cl_cb_null, clp, NULL, NFSPROC4_CLNT_CB_NULL);
	clp->cl_time = get_seconds();
	clear_bit(0, &clp->cl_cb_slot_busy);
	copy_verf(clp, verf);
	rpc_copy_addr((struct sockaddr *) &clp->cl_addr, sa);
	clp->cl_cb_session = NULL;
	clp->net = net;
	return clp;
}

static void
add_clp_to_name_tree(struct nfs4_client *new_clp, struct rb_root *root)
{
	struct rb_node **new = &(root->rb_node), *parent = NULL;
	struct nfs4_client *clp;

	while (*new) {
		clp = rb_entry(*new, struct nfs4_client, cl_namenode);
		parent = *new;

		if (compare_blob(&clp->cl_name, &new_clp->cl_name) > 0)
			new = &((*new)->rb_left);
		else
			new = &((*new)->rb_right);
	}

	rb_link_node(&new_clp->cl_namenode, parent, new);
	rb_insert_color(&new_clp->cl_namenode, root);
}

static struct nfs4_client *
find_clp_in_name_tree(struct xdr_netobj *name, struct rb_root *root)
{
	int cmp;
	struct rb_node *node = root->rb_node;
	struct nfs4_client *clp;

	while (node) {
		clp = rb_entry(node, struct nfs4_client, cl_namenode);
		cmp = compare_blob(&clp->cl_name, name);
		if (cmp > 0)
			node = node->rb_left;
		else if (cmp < 0)
			node = node->rb_right;
		else
			return clp;
	}
	return NULL;
}

static void
add_to_unconfirmed(struct nfs4_client *clp)
{
	unsigned int idhashval;
	struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);

	lockdep_assert_held(&nn->client_lock);

	clear_bit(NFSD4_CLIENT_CONFIRMED, &clp->cl_flags);
	add_clp_to_name_tree(clp, &nn->unconf_name_tree);
	idhashval = clientid_hashval(clp->cl_clientid.cl_id);
	list_add(&clp->cl_idhash, &nn->unconf_id_hashtbl[idhashval]);
	renew_client_locked(clp);
}

static void
move_to_confirmed(struct nfs4_client *clp)
{
	unsigned int idhashval = clientid_hashval(clp->cl_clientid.cl_id);
	struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);

	lockdep_assert_held(&nn->client_lock);

	dprintk("NFSD: move_to_confirm nfs4_client %p\n", clp);
	list_move(&clp->cl_idhash, &nn->conf_id_hashtbl[idhashval]);
	rb_erase(&clp->cl_namenode, &nn->unconf_name_tree);
	add_clp_to_name_tree(clp, &nn->conf_name_tree);
	set_bit(NFSD4_CLIENT_CONFIRMED, &clp->cl_flags);
	renew_client_locked(clp);
}

static struct nfs4_client *
find_client_in_id_table(struct list_head *tbl, clientid_t *clid, bool sessions)
{
	struct nfs4_client *clp;
	unsigned int idhashval = clientid_hashval(clid->cl_id);

	list_for_each_entry(clp, &tbl[idhashval], cl_idhash) {
		if (same_clid(&clp->cl_clientid, clid)) {
			if ((bool)clp->cl_minorversion != sessions)
				return NULL;
			renew_client_locked(clp);
			return clp;
		}
	}
	return NULL;
}

static struct nfs4_client *
find_confirmed_client(clientid_t *clid, bool sessions, struct nfsd_net *nn)
{
	struct list_head *tbl = nn->conf_id_hashtbl;

	lockdep_assert_held(&nn->client_lock);
	return find_client_in_id_table(tbl, clid, sessions);
}

static struct nfs4_client *
find_unconfirmed_client(clientid_t *clid, bool sessions, struct nfsd_net *nn)
{
	struct list_head *tbl = nn->unconf_id_hashtbl;

	lockdep_assert_held(&nn->client_lock);
	return find_client_in_id_table(tbl, clid, sessions);
}

static bool clp_used_exchangeid(struct nfs4_client *clp)
{
	return clp->cl_exchange_flags != 0;
} 

static struct nfs4_client *
find_confirmed_client_by_name(struct xdr_netobj *name, struct nfsd_net *nn)
{
	lockdep_assert_held(&nn->client_lock);
	return find_clp_in_name_tree(name, &nn->conf_name_tree);
}

static struct nfs4_client *
find_unconfirmed_client_by_name(struct xdr_netobj *name, struct nfsd_net *nn)
{
	lockdep_assert_held(&nn->client_lock);
	return find_clp_in_name_tree(name, &nn->unconf_name_tree);
}

static void
gen_callback(struct nfs4_client *clp, struct nfsd4_setclientid *se, struct svc_rqst *rqstp)
{
	struct nfs4_cb_conn *conn = &clp->cl_cb_conn;
	struct sockaddr	*sa = svc_addr(rqstp);
	u32 scopeid = rpc_get_scope_id(sa);
	unsigned short expected_family;

	/* Currently, we only support tcp and tcp6 for the callback channel */
	if (se->se_callback_netid_len == 3 &&
	    !memcmp(se->se_callback_netid_val, "tcp", 3))
		expected_family = AF_INET;
	else if (se->se_callback_netid_len == 4 &&
		 !memcmp(se->se_callback_netid_val, "tcp6", 4))
		expected_family = AF_INET6;
	else
		goto out_err;

	conn->cb_addrlen = rpc_uaddr2sockaddr(clp->net, se->se_callback_addr_val,
					    se->se_callback_addr_len,
					    (struct sockaddr *)&conn->cb_addr,
					    sizeof(conn->cb_addr));

	if (!conn->cb_addrlen || conn->cb_addr.ss_family != expected_family)
		goto out_err;

	if (conn->cb_addr.ss_family == AF_INET6)
		((struct sockaddr_in6 *)&conn->cb_addr)->sin6_scope_id = scopeid;

	conn->cb_prog = se->se_callback_prog;
	conn->cb_ident = se->se_callback_ident;
	memcpy(&conn->cb_saddr, &rqstp->rq_daddr, rqstp->rq_daddrlen);
	return;
out_err:
	conn->cb_addr.ss_family = AF_UNSPEC;
	conn->cb_addrlen = 0;
	dprintk("NFSD: this client (clientid %08x/%08x) "
		"will not receive delegations\n",
		clp->cl_clientid.cl_boot, clp->cl_clientid.cl_id);

	return;
}

/*
 * Cache a reply. nfsd4_check_resp_size() has bounded the cache size.
 */
static void
nfsd4_store_cache_entry(struct nfsd4_compoundres *resp)
{
	struct xdr_buf *buf = resp->xdr.buf;
	struct nfsd4_slot *slot = resp->cstate.slot;
	unsigned int base;

	dprintk("--> %s slot %p\n", __func__, slot);

	slot->sl_flags |= NFSD4_SLOT_INITIALIZED;
	slot->sl_opcnt = resp->opcnt;
	slot->sl_status = resp->cstate.status;
	free_svc_cred(&slot->sl_cred);
	copy_cred(&slot->sl_cred, &resp->rqstp->rq_cred);

	if (!nfsd4_cache_this(resp)) {
		slot->sl_flags &= ~NFSD4_SLOT_CACHED;
		return;
	}
	slot->sl_flags |= NFSD4_SLOT_CACHED;

	base = resp->cstate.data_offset;
	slot->sl_datalen = buf->len - base;
	if (read_bytes_from_xdr_buf(buf, base, slot->sl_data, slot->sl_datalen))
		WARN(1, "%s: sessions DRC could not cache compound\n",
		     __func__);
	return;
}

/*
 * Encode the replay sequence operation from the slot values.
 * If cachethis is FALSE encode the uncached rep error on the next
 * operation which sets resp->p and increments resp->opcnt for
 * nfs4svc_encode_compoundres.
 *
 */
static __be32
nfsd4_enc_sequence_replay(struct nfsd4_compoundargs *args,
			  struct nfsd4_compoundres *resp)
{
	struct nfsd4_op *op;
	struct nfsd4_slot *slot = resp->cstate.slot;

	/* Encode the replayed sequence operation */
	op = &args->ops[resp->opcnt - 1];
	nfsd4_encode_operation(resp, op);

	if (slot->sl_flags & NFSD4_SLOT_CACHED)
		return op->status;
	if (args->opcnt == 1) {
		/*
		 * The original operation wasn't a solo sequence--we
		 * always cache those--so this retry must not match the
		 * original:
		 */
		op->status = nfserr_seq_false_retry;
	} else {
		op = &args->ops[resp->opcnt++];
		op->status = nfserr_retry_uncached_rep;
		nfsd4_encode_operation(resp, op);
	}
	return op->status;
}

/*
 * The sequence operation is not cached because we can use the slot and
 * session values.
 */
static __be32
nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp,
			 struct nfsd4_sequence *seq)
{
	struct nfsd4_slot *slot = resp->cstate.slot;
	struct xdr_stream *xdr = &resp->xdr;
	__be32 *p;
	__be32 status;

	dprintk("--> %s slot %p\n", __func__, slot);

	status = nfsd4_enc_sequence_replay(resp->rqstp->rq_argp, resp);
	if (status)
		return status;

	p = xdr_reserve_space(xdr, slot->sl_datalen);
	if (!p) {
		WARN_ON_ONCE(1);
		return nfserr_serverfault;
	}
	xdr_encode_opaque_fixed(p, slot->sl_data, slot->sl_datalen);
	xdr_commit_encode(xdr);

	resp->opcnt = slot->sl_opcnt;
	return slot->sl_status;
}

/*
 * Set the exchange_id flags returned by the server.
 */
static void
nfsd4_set_ex_flags(struct nfs4_client *new, struct nfsd4_exchange_id *clid)
{
#ifdef CONFIG_NFSD_PNFS
	new->cl_exchange_flags |= EXCHGID4_FLAG_USE_PNFS_MDS;
#else
	new->cl_exchange_flags |= EXCHGID4_FLAG_USE_NON_PNFS;
#endif

	/* Referrals are supported, Migration is not. */
	new->cl_exchange_flags |= EXCHGID4_FLAG_SUPP_MOVED_REFER;

	/* set the wire flags to return to client. */
	clid->flags = new->cl_exchange_flags;
}

static bool client_has_openowners(struct nfs4_client *clp)
{
	struct nfs4_openowner *oo;

	list_for_each_entry(oo, &clp->cl_openowners, oo_perclient) {
		if (!list_empty(&oo->oo_owner.so_stateids))
			return true;
	}
	return false;
}

static bool client_has_state(struct nfs4_client *clp)
{
	return client_has_openowners(clp)
#ifdef CONFIG_NFSD_PNFS
		|| !list_empty(&clp->cl_lo_states)
#endif
		|| !list_empty(&clp->cl_delegations)
		|| !list_empty(&clp->cl_sessions);
}

__be32
nfsd4_exchange_id(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
		union nfsd4_op_u *u)
{
	struct nfsd4_exchange_id *exid = &u->exchange_id;
	struct nfs4_client *conf, *new;
	struct nfs4_client *unconf = NULL;
	__be32 status;
	char			addr_str[INET6_ADDRSTRLEN];
	nfs4_verifier		verf = exid->verifier;
	struct sockaddr		*sa = svc_addr(rqstp);
	bool	update = exid->flags & EXCHGID4_FLAG_UPD_CONFIRMED_REC_A;
	struct nfsd_net		*nn = net_generic(SVC_NET(rqstp), nfsd_net_id);

	rpc_ntop(sa, addr_str, sizeof(addr_str));
	dprintk("%s rqstp=%p exid=%p clname.len=%u clname.data=%p "
		"ip_addr=%s flags %x, spa_how %d\n",
		__func__, rqstp, exid, exid->clname.len, exid->clname.data,
		addr_str, exid->flags, exid->spa_how);

	if (exid->flags & ~EXCHGID4_FLAG_MASK_A)
		return nfserr_inval;

	new = create_client(exid->clname, rqstp, &verf);
	if (new == NULL)
		return nfserr_jukebox;

	switch (exid->spa_how) {
	case SP4_MACH_CRED:
		exid->spo_must_enforce[0] = 0;
		exid->spo_must_enforce[1] = (
			1 << (OP_BIND_CONN_TO_SESSION - 32) |
			1 << (OP_EXCHANGE_ID - 32) |
			1 << (OP_CREATE_SESSION - 32) |
			1 << (OP_DESTROY_SESSION - 32) |
			1 << (OP_DESTROY_CLIENTID - 32));

		exid->spo_must_allow[0] &= (1 << (OP_CLOSE) |
					1 << (OP_OPEN_DOWNGRADE) |
					1 << (OP_LOCKU) |
					1 << (OP_DELEGRETURN));

		exid->spo_must_allow[1] &= (
					1 << (OP_TEST_STATEID - 32) |
					1 << (OP_FREE_STATEID - 32));
		if (!svc_rqst_integrity_protected(rqstp)) {
			status = nfserr_inval;
			goto out_nolock;
		}
		/*
		 * Sometimes userspace doesn't give us a principal.
		 * Which is a bug, really.  Anyway, we can't enforce
		 * MACH_CRED in that case, better to give up now:
		 */
		if (!new->cl_cred.cr_principal &&
					!new->cl_cred.cr_raw_principal) {
			status = nfserr_serverfault;
			goto out_nolock;
		}
		new->cl_mach_cred = true;
	case SP4_NONE:
		break;
	default:				/* checked by xdr code */
		WARN_ON_ONCE(1);
	case SP4_SSV:
		status = nfserr_encr_alg_unsupp;
		goto out_nolock;
	}

	/* Cases below refer to rfc 5661 section 18.35.4: */
	spin_lock(&nn->client_lock);
	conf = find_confirmed_client_by_name(&exid->clname, nn);
	if (conf) {
		bool creds_match = same_creds(&conf->cl_cred, &rqstp->rq_cred);
		bool verfs_match = same_verf(&verf, &conf->cl_verifier);

		if (update) {
			if (!clp_used_exchangeid(conf)) { /* buggy client */
				status = nfserr_inval;
				goto out;
			}
			if (!nfsd4_mach_creds_match(conf, rqstp)) {
				status = nfserr_wrong_cred;
				goto out;
			}
			if (!creds_match) { /* case 9 */
				status = nfserr_perm;
				goto out;
			}
			if (!verfs_match) { /* case 8 */
				status = nfserr_not_same;
				goto out;
			}
			/* case 6 */
			exid->flags |= EXCHGID4_FLAG_CONFIRMED_R;
			goto out_copy;
		}
		if (!creds_match) { /* case 3 */
			if (client_has_state(conf)) {
				status = nfserr_clid_inuse;
				goto out;
			}
			goto out_new;
		}
		if (verfs_match) { /* case 2 */
			conf->cl_exchange_flags |= EXCHGID4_FLAG_CONFIRMED_R;
			goto out_copy;
		}
		/* case 5, client reboot */
		conf = NULL;
		goto out_new;
	}

	if (update) { /* case 7 */
		status = nfserr_noent;
		goto out;
	}

	unconf  = find_unconfirmed_client_by_name(&exid->clname, nn);
	if (unconf) /* case 4, possible retry or client restart */
		unhash_client_locked(unconf);

	/* case 1 (normal case) */
out_new:
	if (conf) {
		status = mark_client_expired_locked(conf);
		if (status)
			goto out;
	}
	new->cl_minorversion = cstate->minorversion;
	new->cl_spo_must_allow.u.words[0] = exid->spo_must_allow[0];
	new->cl_spo_must_allow.u.words[1] = exid->spo_must_allow[1];

	gen_clid(new, nn);
	add_to_unconfirmed(new);
	swap(new, conf);
out_copy:
	exid->clientid.cl_boot = conf->cl_clientid.cl_boot;
	exid->clientid.cl_id = conf->cl_clientid.cl_id;

	exid->seqid = conf->cl_cs_slot.sl_seqid + 1;
	nfsd4_set_ex_flags(conf, exid);

	dprintk("nfsd4_exchange_id seqid %d flags %x\n",
		conf->cl_cs_slot.sl_seqid, conf->cl_exchange_flags);
	status = nfs_ok;

out:
	spin_unlock(&nn->client_lock);
out_nolock:
	if (new)
		expire_client(new);
	if (unconf)
		expire_client(unconf);
	return status;
}

static __be32
check_slot_seqid(u32 seqid, u32 slot_seqid, int slot_inuse)
{
	dprintk("%s enter. seqid %d slot_seqid %d\n", __func__, seqid,
		slot_seqid);

	/* The slot is in use, and no response has been sent. */
	if (slot_inuse) {
		if (seqid == slot_seqid)
			return nfserr_jukebox;
		else
			return nfserr_seq_misordered;
	}
	/* Note unsigned 32-bit arithmetic handles wraparound: */
	if (likely(seqid == slot_seqid + 1))
		return nfs_ok;
	if (seqid == slot_seqid)
		return nfserr_replay_cache;
	return nfserr_seq_misordered;
}

/*
 * Cache the create session result into the create session single DRC
 * slot cache by saving the xdr structure. sl_seqid has been set.
 * Do this for solo or embedded create session operations.
 */
static void
nfsd4_cache_create_session(struct nfsd4_create_session *cr_ses,
			   struct nfsd4_clid_slot *slot, __be32 nfserr)
{
	slot->sl_status = nfserr;
	memcpy(&slot->sl_cr_ses, cr_ses, sizeof(*cr_ses));
}

static __be32
nfsd4_replay_create_session(struct nfsd4_create_session *cr_ses,
			    struct nfsd4_clid_slot *slot)
{
	memcpy(cr_ses, &slot->sl_cr_ses, sizeof(*cr_ses));
	return slot->sl_status;
}

#define NFSD_MIN_REQ_HDR_SEQ_SZ	((\
			2 * 2 + /* credential,verifier: AUTH_NULL, length 0 */ \
			1 +	/* MIN tag is length with zero, only length */ \
			3 +	/* version, opcount, opcode */ \
			XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + \
				/* seqid, slotID, slotID, cache */ \
			4 ) * sizeof(__be32))

#define NFSD_MIN_RESP_HDR_SEQ_SZ ((\
			2 +	/* verifier: AUTH_NULL, length 0 */\
			1 +	/* status */ \
			1 +	/* MIN tag is length with zero, only length */ \
			3 +	/* opcount, opcode, opstatus*/ \
			XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + \
				/* seqid, slotID, slotID, slotID, status */ \
			5 ) * sizeof(__be32))

static __be32 check_forechannel_attrs(struct nfsd4_channel_attrs *ca, struct nfsd_net *nn)
{
	u32 maxrpc = nn->nfsd_serv->sv_max_mesg;

	if (ca->maxreq_sz < NFSD_MIN_REQ_HDR_SEQ_SZ)
		return nfserr_toosmall;
	if (ca->maxresp_sz < NFSD_MIN_RESP_HDR_SEQ_SZ)
		return nfserr_toosmall;
	ca->headerpadsz = 0;
	ca->maxreq_sz = min_t(u32, ca->maxreq_sz, maxrpc);
	ca->maxresp_sz = min_t(u32, ca->maxresp_sz, maxrpc);
	ca->maxops = min_t(u32, ca->maxops, NFSD_MAX_OPS_PER_COMPOUND);
	ca->maxresp_cached = min_t(u32, ca->maxresp_cached,
			NFSD_SLOT_CACHE_SIZE + NFSD_MIN_HDR_SEQ_SZ);
	ca->maxreqs = min_t(u32, ca->maxreqs, NFSD_MAX_SLOTS_PER_SESSION);
	/*
	 * Note decreasing slot size below client's request may make it
	 * difficult for client to function correctly, whereas
	 * decreasing the number of slots will (just?) affect
	 * performance.  When short on memory we therefore prefer to
	 * decrease number of slots instead of their size.  Clients that
	 * request larger slots than they need will get poor results:
	 */
	ca->maxreqs = nfsd4_get_drc_mem(ca);
	if (!ca->maxreqs)
		return nfserr_jukebox;

	return nfs_ok;
}

/*
 * Server's NFSv4.1 backchannel support is AUTH_SYS-only for now.
 * These are based on similar macros in linux/sunrpc/msg_prot.h .
 */
#define RPC_MAX_HEADER_WITH_AUTH_SYS \
	(RPC_CALLHDRSIZE + 2 * (2 + UNX_CALLSLACK))

#define RPC_MAX_REPHEADER_WITH_AUTH_SYS \
	(RPC_REPHDRSIZE + (2 + NUL_REPLYSLACK))

#define NFSD_CB_MAX_REQ_SZ	((NFS4_enc_cb_recall_sz + \
				 RPC_MAX_HEADER_WITH_AUTH_SYS) * sizeof(__be32))
#define NFSD_CB_MAX_RESP_SZ	((NFS4_dec_cb_recall_sz + \
				 RPC_MAX_REPHEADER_WITH_AUTH_SYS) * \
				 sizeof(__be32))

static __be32 check_backchannel_attrs(struct nfsd4_channel_attrs *ca)
{
	ca->headerpadsz = 0;

	if (ca->maxreq_sz < NFSD_CB_MAX_REQ_SZ)
		return nfserr_toosmall;
	if (ca->maxresp_sz < NFSD_CB_MAX_RESP_SZ)
		return nfserr_toosmall;
	ca->maxresp_cached = 0;
	if (ca->maxops < 2)
		return nfserr_toosmall;

	return nfs_ok;
}

static __be32 nfsd4_check_cb_sec(struct nfsd4_cb_sec *cbs)
{
	switch (cbs->flavor) {
	case RPC_AUTH_NULL:
	case RPC_AUTH_UNIX:
		return nfs_ok;
	default:
		/*
		 * GSS case: the spec doesn't allow us to return this
		 * error.  But it also doesn't allow us not to support
		 * GSS.
		 * I'd rather this fail hard than return some error the
		 * client might think it can already handle:
		 */
		return nfserr_encr_alg_unsupp;
	}
}

__be32
nfsd4_create_session(struct svc_rqst *rqstp,
		struct nfsd4_compound_state *cstate, union nfsd4_op_u *u)
{
	struct nfsd4_create_session *cr_ses = &u->create_session;
	struct sockaddr *sa = svc_addr(rqstp);
	struct nfs4_client *conf, *unconf;
	struct nfs4_client *old = NULL;
	struct nfsd4_session *new;
	struct nfsd4_conn *conn;
	struct nfsd4_clid_slot *cs_slot = NULL;
	__be32 status = 0;
	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);

	if (cr_ses->flags & ~SESSION4_FLAG_MASK_A)
		return nfserr_inval;
	status = nfsd4_check_cb_sec(&cr_ses->cb_sec);
	if (status)
		return status;
	status = check_forechannel_attrs(&cr_ses->fore_channel, nn);
	if (status)
		return status;
	status = check_backchannel_attrs(&cr_ses->back_channel);
	if (status)
		goto out_release_drc_mem;
	status = nfserr_jukebox;
	new = alloc_session(&cr_ses->fore_channel, &cr_ses->back_channel);
	if (!new)
		goto out_release_drc_mem;
	conn = alloc_conn_from_crses(rqstp, cr_ses);
	if (!conn)
		goto out_free_session;

	spin_lock(&nn->client_lock);
	unconf = find_unconfirmed_client(&cr_ses->clientid, true, nn);
	conf = find_confirmed_client(&cr_ses->clientid, true, nn);
	WARN_ON_ONCE(conf && unconf);

	if (conf) {
		status = nfserr_wrong_cred;
		if (!nfsd4_mach_creds_match(conf, rqstp))
			goto out_free_conn;
		cs_slot = &conf->cl_cs_slot;
		status = check_slot_seqid(cr_ses->seqid, cs_slot->sl_seqid, 0);
		if (status) {
			if (status == nfserr_replay_cache)
				status = nfsd4_replay_create_session(cr_ses, cs_slot);
			goto out_free_conn;
		}
	} else if (unconf) {
		if (!same_creds(&unconf->cl_cred, &rqstp->rq_cred) ||
		    !rpc_cmp_addr(sa, (struct sockaddr *) &unconf->cl_addr)) {
			status = nfserr_clid_inuse;
			goto out_free_conn;
		}
		status = nfserr_wrong_cred;
		if (!nfsd4_mach_creds_match(unconf, rqstp))
			goto out_free_conn;
		cs_slot = &unconf->cl_cs_slot;
		status = check_slot_seqid(cr_ses->seqid, cs_slot->sl_seqid, 0);
		if (status) {
			/* an unconfirmed replay returns misordered */
			status = nfserr_seq_misordered;
			goto out_free_conn;
		}
		old = find_confirmed_client_by_name(&unconf->cl_name, nn);
		if (old) {
			status = mark_client_expired_locked(old);
			if (status) {
				old = NULL;
				goto out_free_conn;
			}
		}
		move_to_confirmed(unconf);
		conf = unconf;
	} else {
		status = nfserr_stale_clientid;
		goto out_free_conn;
	}
	status = nfs_ok;
	/* Persistent sessions are not supported */
	cr_ses->flags &= ~SESSION4_PERSIST;
	/* Upshifting from TCP to RDMA is not supported */
	cr_ses->flags &= ~SESSION4_RDMA;

	init_session(rqstp, new, conf, cr_ses);
	nfsd4_get_session_locked(new);

	memcpy(cr_ses->sessionid.data, new->se_sessionid.data,
	       NFS4_MAX_SESSIONID_LEN);
	cs_slot->sl_seqid++;
	cr_ses->seqid = cs_slot->sl_seqid;

	/* cache solo and embedded create sessions under the client_lock */
	nfsd4_cache_create_session(cr_ses, cs_slot, status);
	spin_unlock(&nn->client_lock);
	/* init connection and backchannel */
	nfsd4_init_conn(rqstp, conn, new);
	nfsd4_put_session(new);
	if (old)
		expire_client(old);
	return status;
out_free_conn:
	spin_unlock(&nn->client_lock);
	free_conn(conn);
	if (old)
		expire_client(old);
out_free_session:
	__free_session(new);
out_release_drc_mem:
	nfsd4_put_drc_mem(&cr_ses->fore_channel);
	return status;
}

static __be32 nfsd4_map_bcts_dir(u32 *dir)
{
	switch (*dir) {
	case NFS4_CDFC4_FORE:
	case NFS4_CDFC4_BACK:
		return nfs_ok;
	case NFS4_CDFC4_FORE_OR_BOTH:
	case NFS4_CDFC4_BACK_OR_BOTH:
		*dir = NFS4_CDFC4_BOTH;
		return nfs_ok;
	};
	return nfserr_inval;
}

__be32 nfsd4_backchannel_ctl(struct svc_rqst *rqstp,
		struct nfsd4_compound_state *cstate,
		union nfsd4_op_u *u)
{
	struct nfsd4_backchannel_ctl *bc = &u->backchannel_ctl;
	struct nfsd4_session *session = cstate->session;
	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
	__be32 status;

	status = nfsd4_check_cb_sec(&bc->bc_cb_sec);
	if (status)
		return status;
	spin_lock(&nn->client_lock);
	session->se_cb_prog = bc->bc_cb_program;
	session->se_cb_sec = bc->bc_cb_sec;
	spin_unlock(&nn->client_lock);

	nfsd4_probe_callback(session->se_client);

	return nfs_ok;
}

__be32 nfsd4_bind_conn_to_session(struct svc_rqst *rqstp,
		     struct nfsd4_compound_state *cstate,
		     union nfsd4_op_u *u)
{
	struct nfsd4_bind_conn_to_session *bcts = &u->bind_conn_to_session;
	__be32 status;
	struct nfsd4_conn *conn;
	struct nfsd4_session *session;
	struct net *net = SVC_NET(rqstp);
	struct nfsd_net *nn = net_generic(net, nfsd_net_id);

	if (!nfsd4_last_compound_op(rqstp))
		return nfserr_not_only_op;
	spin_lock(&nn->client_lock);
	session = find_in_sessionid_hashtbl(&bcts->sessionid, net, &status);
	spin_unlock(&nn->client_lock);
	if (!session)
		goto out_no_session;
	status = nfserr_wrong_cred;
	if (!nfsd4_mach_creds_match(session->se_client, rqstp))
		goto out;
	status = nfsd4_map_bcts_dir(&bcts->dir);
	if (status)
		goto out;
	conn = alloc_conn(rqstp, bcts->dir);
	status = nfserr_jukebox;
	if (!conn)
		goto out;
	nfsd4_init_conn(rqstp, conn, session);
	status = nfs_ok;
out:
	nfsd4_put_session(session);
out_no_session:
	return status;
}

static bool nfsd4_compound_in_session(struct nfsd4_compound_state *cstate, struct nfs4_sessionid *sid)
{
	if (!cstate->session)
		return false;
	return !memcmp(sid, &cstate->session->se_sessionid, sizeof(*sid));
}

__be32
nfsd4_destroy_session(struct svc_rqst *r, struct nfsd4_compound_state *cstate,
		union nfsd4_op_u *u)
{
	struct nfs4_sessionid *sessionid = &u->destroy_session.sessionid;
	struct nfsd4_session *ses;
	__be32 status;
	int ref_held_by_me = 0;
	struct net *net = SVC_NET(r);
	struct nfsd_net *nn = net_generic(net, nfsd_net_id);

	status = nfserr_not_only_op;
	if (nfsd4_compound_in_session(cstate, sessionid)) {
		if (!nfsd4_last_compound_op(r))
			goto out;
		ref_held_by_me++;
	}
	dump_sessionid(__func__, sessionid);
	spin_lock(&nn->client_lock);
	ses = find_in_sessionid_hashtbl(sessionid, net, &status);
	if (!ses)
		goto out_client_lock;
	status = nfserr_wrong_cred;
	if (!nfsd4_mach_creds_match(ses->se_client, r))
		goto out_put_session;
	status = mark_session_dead_locked(ses, 1 + ref_held_by_me);
	if (status)
		goto out_put_session;
	unhash_session(ses);
	spin_unlock(&nn->client_lock);

	nfsd4_probe_callback_sync(ses->se_client);

	spin_lock(&nn->client_lock);
	status = nfs_ok;
out_put_session:
	nfsd4_put_session_locked(ses);
out_client_lock:
	spin_unlock(&nn->client_lock);
out:
	return status;
}

static struct nfsd4_conn *__nfsd4_find_conn(struct svc_xprt *xpt, struct nfsd4_session *s)
{
	struct nfsd4_conn *c;

	list_for_each_entry(c, &s->se_conns, cn_persession) {
		if (c->cn_xprt == xpt) {
			return c;
		}
	}
	return NULL;
}

static __be32 nfsd4_sequence_check_conn(struct nfsd4_conn *new, struct nfsd4_session *ses)
{
	struct nfs4_client *clp = ses->se_client;
	struct nfsd4_conn *c;
	__be32 status = nfs_ok;
	int ret;

	spin_lock(&clp->cl_lock);
	c = __nfsd4_find_conn(new->cn_xprt, ses);
	if (c)
		goto out_free;
	status = nfserr_conn_not_bound_to_session;
	if (clp->cl_mach_cred)
		goto out_free;
	__nfsd4_hash_conn(new, ses);
	spin_unlock(&clp->cl_lock);
	ret = nfsd4_register_conn(new);
	if (ret)
		/* oops; xprt is already down: */
		nfsd4_conn_lost(&new->cn_xpt_user);
	return nfs_ok;
out_free:
	spin_unlock(&clp->cl_lock);
	free_conn(new);
	return status;
}

static bool nfsd4_session_too_many_ops(struct svc_rqst *rqstp, struct nfsd4_session *session)
{
	struct nfsd4_compoundargs *args = rqstp->rq_argp;

	return args->opcnt > session->se_fchannel.maxops;
}

static bool nfsd4_request_too_big(struct svc_rqst *rqstp,
				  struct nfsd4_session *session)
{
	struct xdr_buf *xb = &rqstp->rq_arg;

	return xb->len > session->se_fchannel.maxreq_sz;
}

static bool replay_matches_cache(struct svc_rqst *rqstp,
		 struct nfsd4_sequence *seq, struct nfsd4_slot *slot)
{
	struct nfsd4_compoundargs *argp = rqstp->rq_argp;

	if ((bool)(slot->sl_flags & NFSD4_SLOT_CACHETHIS) !=
	    (bool)seq->cachethis)
		return false;
	/*
	 * If there's an error than the reply can have fewer ops than
	 * the call.  But if we cached a reply with *more* ops than the
	 * call you're sending us now, then this new call is clearly not
	 * really a replay of the old one:
	 */
	if (slot->sl_opcnt < argp->opcnt)
		return false;
	/* This is the only check explicitly called by spec: */
	if (!same_creds(&rqstp->rq_cred, &slot->sl_cred))
		return false;
	/*
	 * There may be more comparisons we could actually do, but the
	 * spec doesn't require us to catch every case where the calls
	 * don't match (that would require caching the call as well as
	 * the reply), so we don't bother.
	 */
	return true;
}

__be32
nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
		union nfsd4_op_u *u)
{
	struct nfsd4_sequence *seq = &u->sequence;
	struct nfsd4_compoundres *resp = rqstp->rq_resp;
	struct xdr_stream *xdr = &resp->xdr;
	struct nfsd4_session *session;
	struct nfs4_client *clp;
	struct nfsd4_slot *slot;
	struct nfsd4_conn *conn;
	__be32 status;
	int buflen;
	struct net *net = SVC_NET(rqstp);
	struct nfsd_net *nn = net_generic(net, nfsd_net_id);

	if (resp->opcnt != 1)
		return nfserr_sequence_pos;

	/*
	 * Will be either used or freed by nfsd4_sequence_check_conn
	 * below.
	 */
	conn = alloc_conn(rqstp, NFS4_CDFC4_FORE);
	if (!conn)
		return nfserr_jukebox;

	spin_lock(&nn->client_lock);
	session = find_in_sessionid_hashtbl(&seq->sessionid, net, &status);
	if (!session)
		goto out_no_session;
	clp = session->se_client;

	status = nfserr_too_many_ops;
	if (nfsd4_session_too_many_ops(rqstp, session))
		goto out_put_session;

	status = nfserr_req_too_big;
	if (nfsd4_request_too_big(rqstp, session))
		goto out_put_session;

	status = nfserr_badslot;
	if (seq->slotid >= session->se_fchannel.maxreqs)
		goto out_put_session;

	slot = session->se_slots[seq->slotid];
	dprintk("%s: slotid %d\n", __func__, seq->slotid);

	/* We do not negotiate the number of slots yet, so set the
	 * maxslots to the session maxreqs which is used to encode
	 * sr_highest_slotid and the sr_target_slot id to maxslots */
	seq->maxslots = session->se_fchannel.maxreqs;

	status = check_slot_seqid(seq->seqid, slot->sl_seqid,
					slot->sl_flags & NFSD4_SLOT_INUSE);
	if (status == nfserr_replay_cache) {
		status = nfserr_seq_misordered;
		if (!(slot->sl_flags & NFSD4_SLOT_INITIALIZED))
			goto out_put_session;
		status = nfserr_seq_false_retry;
		if (!replay_matches_cache(rqstp, seq, slot))
			goto out_put_session;
		cstate->slot = slot;
		cstate->session = session;
		cstate->clp = clp;
		/* Return the cached reply status and set cstate->status
		 * for nfsd4_proc_compound processing */
		status = nfsd4_replay_cache_entry(resp, seq);
		cstate->status = nfserr_replay_cache;
		goto out;
	}
	if (status)
		goto out_put_session;

	status = nfsd4_sequence_check_conn(conn, session);
	conn = NULL;
	if (status)
		goto out_put_session;

	buflen = (seq->cachethis) ?
			session->se_fchannel.maxresp_cached :
			session->se_fchannel.maxresp_sz;
	status = (seq->cachethis) ? nfserr_rep_too_big_to_cache :
				    nfserr_rep_too_big;
	if (xdr_restrict_buflen(xdr, buflen - rqstp->rq_auth_slack))
		goto out_put_session;
	svc_reserve(rqstp, buflen);

	status = nfs_ok;
	/* Success! bump slot seqid */
	slot->sl_seqid = seq->seqid;
	slot->sl_flags |= NFSD4_SLOT_INUSE;
	if (seq->cachethis)
		slot->sl_flags |= NFSD4_SLOT_CACHETHIS;
	else
		slot->sl_flags &= ~NFSD4_SLOT_CACHETHIS;

	cstate->slot = slot;
	cstate->session = session;
	cstate->clp = clp;

out:
	switch (clp->cl_cb_state) {
	case NFSD4_CB_DOWN:
		seq->status_flags = SEQ4_STATUS_CB_PATH_DOWN;
		break;
	case NFSD4_CB_FAULT:
		seq->status_flags = SEQ4_STATUS_BACKCHANNEL_FAULT;
		break;
	default:
		seq->status_flags = 0;
	}
	if (!list_empty(&clp->cl_revoked))
		seq->status_flags |= SEQ4_STATUS_RECALLABLE_STATE_REVOKED;
out_no_session:
	if (conn)
		free_conn(conn);
	spin_unlock(&nn->client_lock);
	return status;
out_put_session:
	nfsd4_put_session_locked(session);
	goto out_no_session;
}

void
nfsd4_sequence_done(struct nfsd4_compoundres *resp)
{
	struct nfsd4_compound_state *cs = &resp->cstate;

	if (nfsd4_has_session(cs)) {
		if (cs->status != nfserr_replay_cache) {
			nfsd4_store_cache_entry(resp);
			cs->slot->sl_flags &= ~NFSD4_SLOT_INUSE;
		}
		/* Drop session reference that was taken in nfsd4_sequence() */
		nfsd4_put_session(cs->session);
	} else if (cs->clp)
		put_client_renew(cs->clp);
}

__be32
nfsd4_destroy_clientid(struct svc_rqst *rqstp,
		struct nfsd4_compound_state *cstate,
		union nfsd4_op_u *u)
{
	struct nfsd4_destroy_clientid *dc = &u->destroy_clientid;
	struct nfs4_client *conf, *unconf;
	struct nfs4_client *clp = NULL;
	__be32 status = 0;
	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);

	spin_lock(&nn->client_lock);
	unconf = find_unconfirmed_client(&dc->clientid, true, nn);
	conf = find_confirmed_client(&dc->clientid, true, nn);
	WARN_ON_ONCE(conf && unconf);

	if (conf) {
		if (client_has_state(conf)) {
			status = nfserr_clientid_busy;
			goto out;
		}
		status = mark_client_expired_locked(conf);
		if (status)
			goto out;
		clp = conf;
	} else if (unconf)
		clp = unconf;
	else {
		status = nfserr_stale_clientid;
		goto out;
	}
	if (!nfsd4_mach_creds_match(clp, rqstp)) {
		clp = NULL;
		status = nfserr_wrong_cred;
		goto out;
	}
	unhash_client_locked(clp);
out:
	spin_unlock(&nn->client_lock);
	if (clp)
		expire_client(clp);
	return status;
}

__be32
nfsd4_reclaim_complete(struct svc_rqst *rqstp,
		struct nfsd4_compound_state *cstate, union nfsd4_op_u *u)
{
	struct nfsd4_reclaim_complete *rc = &u->reclaim_complete;
	__be32 status = 0;

	if (rc->rca_one_fs) {
		if (!cstate->current_fh.fh_dentry)
			return nfserr_nofilehandle;
		/*
		 * We don't take advantage of the rca_one_fs case.
		 * That's OK, it's optional, we can safely ignore it.
		 */
		return nfs_ok;
	}

	status = nfserr_complete_already;
	if (test_and_set_bit(NFSD4_CLIENT_RECLAIM_COMPLETE,
			     &cstate->session->se_client->cl_flags))
		goto out;

	status = nfserr_stale_clientid;
	if (is_client_expired(cstate->session->se_client))
		/*
		 * The following error isn't really legal.
		 * But we only get here if the client just explicitly
		 * destroyed the client.  Surely it no longer cares what
		 * error it gets back on an operation for the dead
		 * client.
		 */
		goto out;

	status = nfs_ok;
	nfsd4_client_record_create(cstate->session->se_client);
out:
	return status;
}

__be32
nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
		  union nfsd4_op_u *u)
{
	struct nfsd4_setclientid *setclid = &u->setclientid;
	struct xdr_netobj 	clname = setclid->se_name;
	nfs4_verifier		clverifier = setclid->se_verf;
	struct nfs4_client	*conf, *new;
	struct nfs4_client	*unconf = NULL;
	__be32 			status;
	struct nfsd_net		*nn = net_generic(SVC_NET(rqstp), nfsd_net_id);

	new = create_client(clname, rqstp, &clverifier);
	if (new == NULL)
		return nfserr_jukebox;
	/* Cases below refer to rfc 3530 section 14.2.33: */
	spin_lock(&nn->client_lock);
	conf = find_confirmed_client_by_name(&clname, nn);
	if (conf && client_has_state(conf)) {
		/* case 0: */
		status = nfserr_clid_inuse;
		if (clp_used_exchangeid(conf))
			goto out;
		if (!same_creds(&conf->cl_cred, &rqstp->rq_cred)) {
			char addr_str[INET6_ADDRSTRLEN];
			rpc_ntop((struct sockaddr *) &conf->cl_addr, addr_str,
				 sizeof(addr_str));
			dprintk("NFSD: setclientid: string in use by client "
				"at %s\n", addr_str);
			goto out;
		}
	}
	unconf = find_unconfirmed_client_by_name(&clname, nn);
	if (unconf)
		unhash_client_locked(unconf);
	if (conf && same_verf(&conf->cl_verifier, &clverifier)) {
		/* case 1: probable callback update */
		copy_clid(new, conf);
		gen_confirm(new, nn);
	} else /* case 4 (new client) or cases 2, 3 (client reboot): */
		gen_clid(new, nn);
	new->cl_minorversion = 0;
	gen_callback(new, setclid, rqstp);
	add_to_unconfirmed(new);
	setclid->se_clientid.cl_boot = new->cl_clientid.cl_boot;
	setclid->se_clientid.cl_id = new->cl_clientid.cl_id;
	memcpy(setclid->se_confirm.data, new->cl_confirm.data, sizeof(setclid->se_confirm.data));
	new = NULL;
	status = nfs_ok;
out:
	spin_unlock(&nn->client_lock);
	if (new)
		free_client(new);
	if (unconf)
		expire_client(unconf);
	return status;
}


__be32
nfsd4_setclientid_confirm(struct svc_rqst *rqstp,
			struct nfsd4_compound_state *cstate,
			union nfsd4_op_u *u)
{
	struct nfsd4_setclientid_confirm *setclientid_confirm =
			&u->setclientid_confirm;
	struct nfs4_client *conf, *unconf;
	struct nfs4_client *old = NULL;
	nfs4_verifier confirm = setclientid_confirm->sc_confirm; 
	clientid_t * clid = &setclientid_confirm->sc_clientid;
	__be32 status;
	struct nfsd_net	*nn = net_generic(SVC_NET(rqstp), nfsd_net_id);

	if (STALE_CLIENTID(clid, nn))
		return nfserr_stale_clientid;

	spin_lock(&nn->client_lock);
	conf = find_confirmed_client(clid, false, nn);
	unconf = find_unconfirmed_client(clid, false, nn);
	/*
	 * We try hard to give out unique clientid's, so if we get an
	 * attempt to confirm the same clientid with a different cred,
	 * the client may be buggy; this should never happen.
	 *
	 * Nevertheless, RFC 7530 recommends INUSE for this case:
	 */
	status = nfserr_clid_inuse;
	if (unconf && !same_creds(&unconf->cl_cred, &rqstp->rq_cred))
		goto out;
	if (conf && !same_creds(&conf->cl_cred, &rqstp->rq_cred))
		goto out;
	/* cases below refer to rfc 3530 section 14.2.34: */
	if (!unconf || !same_verf(&confirm, &unconf->cl_confirm)) {
		if (conf && same_verf(&confirm, &conf->cl_confirm)) {
			/* case 2: probable retransmit */
			status = nfs_ok;
		} else /* case 4: client hasn't noticed we rebooted yet? */
			status = nfserr_stale_clientid;
		goto out;
	}
	status = nfs_ok;
	if (conf) { /* case 1: callback update */
		old = unconf;
		unhash_client_locked(old);
		nfsd4_change_callback(conf, &unconf->cl_cb_conn);
	} else { /* case 3: normal case; new or rebooted client */
		old = find_confirmed_client_by_name(&unconf->cl_name, nn);
		if (old) {
			status = nfserr_clid_inuse;
			if (client_has_state(old)
					&& !same_creds(&unconf->cl_cred,
							&old->cl_cred))
				goto out;
			status = mark_client_expired_locked(old);
			if (status) {
				old = NULL;
				goto out;
			}
		}
		move_to_confirmed(unconf);
		conf = unconf;
	}
	get_client_locked(conf);
	spin_unlock(&nn->client_lock);
	nfsd4_probe_callback(conf);
	spin_lock(&nn->client_lock);
	put_client_renew_locked(conf);
out:
	spin_unlock(&nn->client_lock);
	if (old)
		expire_client(old);
	return status;
}

static struct nfs4_file *nfsd4_alloc_file(void)
{
	return kmem_cache_alloc(file_slab, GFP_KERNEL);
}

/* OPEN Share state helper functions */
static void nfsd4_init_file(struct knfsd_fh *fh, unsigned int hashval,
				struct nfs4_file *fp)
{
	lockdep_assert_held(&state_lock);

	refcount_set(&fp->fi_ref, 1);
	spin_lock_init(&fp->fi_lock);
	INIT_LIST_HEAD(&fp->fi_stateids);
	INIT_LIST_HEAD(&fp->fi_delegations);
	INIT_LIST_HEAD(&fp->fi_clnt_odstate);
	fh_copy_shallow(&fp->fi_fhandle, fh);
	fp->fi_deleg_file = NULL;
	fp->fi_had_conflict = false;
	fp->fi_share_deny = 0;
	memset(fp->fi_fds, 0, sizeof(fp->fi_fds));
	memset(fp->fi_access, 0, sizeof(fp->fi_access));
#ifdef CONFIG_NFSD_PNFS
	INIT_LIST_HEAD(&fp->fi_lo_states);
	atomic_set(&fp->fi_lo_recalls, 0);
#endif
	hlist_add_head_rcu(&fp->fi_hash, &file_hashtbl[hashval]);
}

void
nfsd4_free_slabs(void)
{
	kmem_cache_destroy(client_slab);
	kmem_cache_destroy(openowner_slab);
	kmem_cache_destroy(lockowner_slab);
	kmem_cache_destroy(file_slab);
	kmem_cache_destroy(stateid_slab);
	kmem_cache_destroy(deleg_slab);
	kmem_cache_destroy(odstate_slab);
}

int
nfsd4_init_slabs(void)
{
	client_slab = kmem_cache_create("nfsd4_clients",
			sizeof(struct nfs4_client), 0, 0, NULL);
	if (client_slab == NULL)
		goto out;
	openowner_slab = kmem_cache_create("nfsd4_openowners",
			sizeof(struct nfs4_openowner), 0, 0, NULL);
	if (openowner_slab == NULL)
		goto out_free_client_slab;
	lockowner_slab = kmem_cache_create("nfsd4_lockowners",
			sizeof(struct nfs4_lockowner), 0, 0, NULL);
	if (lockowner_slab == NULL)
		goto out_free_openowner_slab;
	file_slab = kmem_cache_create("nfsd4_files",
			sizeof(struct nfs4_file), 0, 0, NULL);
	if (file_slab == NULL)
		goto out_free_lockowner_slab;
	stateid_slab = kmem_cache_create("nfsd4_stateids",
			sizeof(struct nfs4_ol_stateid), 0, 0, NULL);
	if (stateid_slab == NULL)
		goto out_free_file_slab;
	deleg_slab = kmem_cache_create("nfsd4_delegations",
			sizeof(struct nfs4_delegation), 0, 0, NULL);
	if (deleg_slab == NULL)
		goto out_free_stateid_slab;
	odstate_slab = kmem_cache_create("nfsd4_odstate",
			sizeof(struct nfs4_clnt_odstate), 0, 0, NULL);
	if (odstate_slab == NULL)
		goto out_free_deleg_slab;
	return 0;

out_free_deleg_slab:
	kmem_cache_destroy(deleg_slab);
out_free_stateid_slab:
	kmem_cache_destroy(stateid_slab);
out_free_file_slab:
	kmem_cache_destroy(file_slab);
out_free_lockowner_slab:
	kmem_cache_destroy(lockowner_slab);
out_free_openowner_slab:
	kmem_cache_destroy(openowner_slab);
out_free_client_slab:
	kmem_cache_destroy(client_slab);
out:
	dprintk("nfsd4: out of memory while initializing nfsv4\n");
	return -ENOMEM;
}

static void init_nfs4_replay(struct nfs4_replay *rp)
{
	rp->rp_status = nfserr_serverfault;
	rp->rp_buflen = 0;
	rp->rp_buf = rp->rp_ibuf;
	mutex_init(&rp->rp_mutex);
}

static void nfsd4_cstate_assign_replay(struct nfsd4_compound_state *cstate,
		struct nfs4_stateowner *so)
{
	if (!nfsd4_has_session(cstate)) {
		mutex_lock(&so->so_replay.rp_mutex);
		cstate->replay_owner = nfs4_get_stateowner(so);
	}
}

void nfsd4_cstate_clear_replay(struct nfsd4_compound_state *cstate)
{
	struct nfs4_stateowner *so = cstate->replay_owner;

	if (so != NULL) {
		cstate->replay_owner = NULL;
		mutex_unlock(&so->so_replay.rp_mutex);
		nfs4_put_stateowner(so);
	}
}

static inline void *alloc_stateowner(struct kmem_cache *slab, struct xdr_netobj *owner, struct nfs4_client *clp)
{
	struct nfs4_stateowner *sop;

	sop = kmem_cache_alloc(slab, GFP_KERNEL);
	if (!sop)
		return NULL;

	sop->so_owner.data = kmemdup(owner->data, owner->len, GFP_KERNEL);
	if (!sop->so_owner.data) {
		kmem_cache_free(slab, sop);
		return NULL;
	}
	sop->so_owner.len = owner->len;

	INIT_LIST_HEAD(&sop->so_stateids);
	sop->so_client = clp;
	init_nfs4_replay(&sop->so_replay);
	atomic_set(&sop->so_count, 1);
	return sop;
}

static void hash_openowner(struct nfs4_openowner *oo, struct nfs4_client *clp, unsigned int strhashval)
{
	lockdep_assert_held(&clp->cl_lock);

	list_add(&oo->oo_owner.so_strhash,
		 &clp->cl_ownerstr_hashtbl[strhashval]);
	list_add(&oo->oo_perclient, &clp->cl_openowners);
}

static void nfs4_unhash_openowner(struct nfs4_stateowner *so)
{
	unhash_openowner_locked(openowner(so));
}

static void nfs4_free_openowner(struct nfs4_stateowner *so)
{
	struct nfs4_openowner *oo = openowner(so);

	kmem_cache_free(openowner_slab, oo);
}

static const struct nfs4_stateowner_operations openowner_ops = {
	.so_unhash =	nfs4_unhash_openowner,
	.so_free =	nfs4_free_openowner,
};

static struct nfs4_ol_stateid *
nfsd4_find_existing_open(struct nfs4_file *fp, struct nfsd4_open *open)
{
	struct nfs4_ol_stateid *local, *ret = NULL;
	struct nfs4_openowner *oo = open->op_openowner;

	lockdep_assert_held(&fp->fi_lock);

	list_for_each_entry(local, &fp->fi_stateids, st_perfile) {
		/* ignore lock owners */
		if (local->st_stateowner->so_is_open_owner == 0)
			continue;
		if (local->st_stateowner != &oo->oo_owner)
			continue;
		if (local->st_stid.sc_type == NFS4_OPEN_STID) {
			ret = local;
			refcount_inc(&ret->st_stid.sc_count);
			break;
		}
	}
	return ret;
}

static __be32
nfsd4_verify_open_stid(struct nfs4_stid *s)
{
	__be32 ret = nfs_ok;

	switch (s->sc_type) {
	default:
		break;
	case 0:
	case NFS4_CLOSED_STID:
	case NFS4_CLOSED_DELEG_STID:
		ret = nfserr_bad_stateid;
		break;
	case NFS4_REVOKED_DELEG_STID:
		ret = nfserr_deleg_revoked;
	}
	return ret;
}

/* Lock the stateid st_mutex, and deal with races with CLOSE */
static __be32
nfsd4_lock_ol_stateid(struct nfs4_ol_stateid *stp)
{
	__be32 ret;

	mutex_lock_nested(&stp->st_mutex, LOCK_STATEID_MUTEX);
	ret = nfsd4_verify_open_stid(&stp->st_stid);
	if (ret != nfs_ok)
		mutex_unlock(&stp->st_mutex);
	return ret;
}

static struct nfs4_ol_stateid *
nfsd4_find_and_lock_existing_open(struct nfs4_file *fp, struct nfsd4_open *open)
{
	struct nfs4_ol_stateid *stp;
	for (;;) {
		spin_lock(&fp->fi_lock);
		stp = nfsd4_find_existing_open(fp, open);
		spin_unlock(&fp->fi_lock);
		if (!stp || nfsd4_lock_ol_stateid(stp) == nfs_ok)
			break;
		nfs4_put_stid(&stp->st_stid);
	}
	return stp;
}

static struct nfs4_openowner *
alloc_init_open_stateowner(unsigned int strhashval, struct nfsd4_open *open,
			   struct nfsd4_compound_state *cstate)
{
	struct nfs4_client *clp = cstate->clp;
	struct nfs4_openowner *oo, *ret;

	oo = alloc_stateowner(openowner_slab, &open->op_owner, clp);
	if (!oo)
		return NULL;
	oo->oo_owner.so_ops = &openowner_ops;
	oo->oo_owner.so_is_open_owner = 1;
	oo->oo_owner.so_seqid = open->op_seqid;
	oo->oo_flags = 0;
	if (nfsd4_has_session(cstate))
		oo->oo_flags |= NFS4_OO_CONFIRMED;
	oo->oo_time = 0;
	oo->oo_last_closed_stid = NULL;
	INIT_LIST_HEAD(&oo->oo_close_lru);
	spin_lock(&clp->cl_lock);
	ret = find_openstateowner_str_locked(strhashval, open, clp);
	if (ret == NULL) {
		hash_openowner(oo, clp, strhashval);
		ret = oo;
	} else
		nfs4_free_stateowner(&oo->oo_owner);

	spin_unlock(&clp->cl_lock);
	return ret;
}

static struct nfs4_ol_stateid *
init_open_stateid(struct nfs4_file *fp, struct nfsd4_open *open)
{

	struct nfs4_openowner *oo = open->op_openowner;
	struct nfs4_ol_stateid *retstp = NULL;
	struct nfs4_ol_stateid *stp;

	stp = open->op_stp;
	/* We are moving these outside of the spinlocks to avoid the warnings */
	mutex_init(&stp->st_mutex);
	mutex_lock_nested(&stp->st_mutex, OPEN_STATEID_MUTEX);

retry:
	spin_lock(&oo->oo_owner.so_client->cl_lock);
	spin_lock(&fp->fi_lock);

	retstp = nfsd4_find_existing_open(fp, open);
	if (retstp)
		goto out_unlock;

	open->op_stp = NULL;
	refcount_inc(&stp->st_stid.sc_count);
	stp->st_stid.sc_type = NFS4_OPEN_STID;
	INIT_LIST_HEAD(&stp->st_locks);
	stp->st_stateowner = nfs4_get_stateowner(&oo->oo_owner);
	get_nfs4_file(fp);
	stp->st_stid.sc_file = fp;
	stp->st_access_bmap = 0;
	stp->st_deny_bmap = 0;
	stp->st_openstp = NULL;
	list_add(&stp->st_perstateowner, &oo->oo_owner.so_stateids);
	list_add(&stp->st_perfile, &fp->fi_stateids);

out_unlock:
	spin_unlock(&fp->fi_lock);
	spin_unlock(&oo->oo_owner.so_client->cl_lock);
	if (retstp) {
		/* Handle races with CLOSE */
		if (nfsd4_lock_ol_stateid(retstp) != nfs_ok) {
			nfs4_put_stid(&retstp->st_stid);
			goto retry;
		}
		/* To keep mutex tracking happy */
		mutex_unlock(&stp->st_mutex);
		stp = retstp;
	}
	return stp;
}

/*
 * In the 4.0 case we need to keep the owners around a little while to handle
 * CLOSE replay. We still do need to release any file access that is held by
 * them before returning however.
 */
static void
move_to_close_lru(struct nfs4_ol_stateid *s, struct net *net)
{
	struct nfs4_ol_stateid *last;
	struct nfs4_openowner *oo = openowner(s->st_stateowner);
	struct nfsd_net *nn = net_generic(s->st_stid.sc_client->net,
						nfsd_net_id);

	dprintk("NFSD: move_to_close_lru nfs4_openowner %p\n", oo);

	/*
	 * We know that we hold one reference via nfsd4_close, and another
	 * "persistent" reference for the client. If the refcount is higher
	 * than 2, then there are still calls in progress that are using this
	 * stateid. We can't put the sc_file reference until they are finished.
	 * Wait for the refcount to drop to 2. Since it has been unhashed,
	 * there should be no danger of the refcount going back up again at
	 * this point.
	 */
	wait_event(close_wq, refcount_read(&s->st_stid.sc_count) == 2);

	release_all_access(s);
	if (s->st_stid.sc_file) {
		put_nfs4_file(s->st_stid.sc_file);
		s->st_stid.sc_file = NULL;
	}

	spin_lock(&nn->client_lock);
	last = oo->oo_last_closed_stid;
	oo->oo_last_closed_stid = s;
	list_move_tail(&oo->oo_close_lru, &nn->close_lru);
	oo->oo_time = get_seconds();
	spin_unlock(&nn->client_lock);
	if (last)
		nfs4_put_stid(&last->st_stid);
}

/* search file_hashtbl[] for file */
static struct nfs4_file *
find_file_locked(struct knfsd_fh *fh, unsigned int hashval)
{
	struct nfs4_file *fp;

	hlist_for_each_entry_rcu(fp, &file_hashtbl[hashval], fi_hash) {
		if (fh_match(&fp->fi_fhandle, fh)) {
			if (refcount_inc_not_zero(&fp->fi_ref))
				return fp;
		}
	}
	return NULL;
}

struct nfs4_file *
find_file(struct knfsd_fh *fh)
{
	struct nfs4_file *fp;
	unsigned int hashval = file_hashval(fh);

	rcu_read_lock();
	fp = find_file_locked(fh, hashval);
	rcu_read_unlock();
	return fp;
}

static struct nfs4_file *
find_or_add_file(struct nfs4_file *new, struct knfsd_fh *fh)
{
	struct nfs4_file *fp;
	unsigned int hashval = file_hashval(fh);

	rcu_read_lock();
	fp = find_file_locked(fh, hashval);
	rcu_read_unlock();
	if (fp)
		return fp;

	spin_lock(&state_lock);
	fp = find_file_locked(fh, hashval);
	if (likely(fp == NULL)) {
		nfsd4_init_file(fh, hashval, new);
		fp = new;
	}
	spin_unlock(&state_lock);

	return fp;
}

/*
 * Called to check deny when READ with all zero stateid or
 * WRITE with all zero or all one stateid
 */
static __be32
nfs4_share_conflict(struct svc_fh *current_fh, unsigned int deny_type)
{
	struct nfs4_file *fp;
	__be32 ret = nfs_ok;

	fp = find_file(&current_fh->fh_handle);
	if (!fp)
		return ret;
	/* Check for conflicting share reservations */
	spin_lock(&fp->fi_lock);
	if (fp->fi_share_deny & deny_type)
		ret = nfserr_locked;
	spin_unlock(&fp->fi_lock);
	put_nfs4_file(fp);
	return ret;
}

static void nfsd4_cb_recall_prepare(struct nfsd4_callback *cb)
{
	struct nfs4_delegation *dp = cb_to_delegation(cb);
	struct nfsd_net *nn = net_generic(dp->dl_stid.sc_client->net,
					  nfsd_net_id);

	block_delegations(&dp->dl_stid.sc_file->fi_fhandle);

	/*
	 * We can't do this in nfsd_break_deleg_cb because it is
	 * already holding inode->i_lock.
	 *
	 * If the dl_time != 0, then we know that it has already been
	 * queued for a lease break. Don't queue it again.
	 */
	spin_lock(&state_lock);
	if (dp->dl_time == 0) {
		dp->dl_time = get_seconds();
		list_add_tail(&dp->dl_recall_lru, &nn->del_recall_lru);
	}
	spin_unlock(&state_lock);
}

static int nfsd4_cb_recall_done(struct nfsd4_callback *cb,
		struct rpc_task *task)
{
	struct nfs4_delegation *dp = cb_to_delegation(cb);

	if (dp->dl_stid.sc_type == NFS4_CLOSED_DELEG_STID)
	        return 1;

	switch (task->tk_status) {
	case 0:
		return 1;
	case -EBADHANDLE:
	case -NFS4ERR_BAD_STATEID:
		/*
		 * Race: client probably got cb_recall before open reply
		 * granting delegation.
		 */
		if (dp->dl_retries--) {
			rpc_delay(task, 2 * HZ);
			return 0;
		}
		/*FALLTHRU*/
	default:
		return -1;
	}
}

static void nfsd4_cb_recall_release(struct nfsd4_callback *cb)
{
	struct nfs4_delegation *dp = cb_to_delegation(cb);

	nfs4_put_stid(&dp->dl_stid);
}

static const struct nfsd4_callback_ops nfsd4_cb_recall_ops = {
	.prepare	= nfsd4_cb_recall_prepare,
	.done		= nfsd4_cb_recall_done,
	.release	= nfsd4_cb_recall_release,
};

static void nfsd_break_one_deleg(struct nfs4_delegation *dp)
{
	/*
	 * We're assuming the state code never drops its reference
	 * without first removing the lease.  Since we're in this lease
	 * callback (and since the lease code is serialized by the
	 * i_lock) we know the server hasn't removed the lease yet, and
	 * we know it's safe to take a reference.
	 */
	refcount_inc(&dp->dl_stid.sc_count);
	nfsd4_run_cb(&dp->dl_recall);
}

/* Called from break_lease() with i_lock held. */
static bool
nfsd_break_deleg_cb(struct file_lock *fl)
{
	bool ret = false;
	struct nfs4_delegation *dp = (struct nfs4_delegation *)fl->fl_owner;
	struct nfs4_file *fp = dp->dl_stid.sc_file;

	/*
	 * We don't want the locks code to timeout the lease for us;
	 * we'll remove it ourself if a delegation isn't returned
	 * in time:
	 */
	fl->fl_break_time = 0;

	spin_lock(&fp->fi_lock);
	fp->fi_had_conflict = true;
	nfsd_break_one_deleg(dp);
	spin_unlock(&fp->fi_lock);
	return ret;
}

static int
nfsd_change_deleg_cb(struct file_lock *onlist, int arg,
		     struct list_head *dispose)
{
	if (arg & F_UNLCK)
		return lease_modify(onlist, arg, dispose);
	else
		return -EAGAIN;
}

static const struct lock_manager_operations nfsd_lease_mng_ops = {
	.lm_break = nfsd_break_deleg_cb,
	.lm_change = nfsd_change_deleg_cb,
};

static __be32 nfsd4_check_seqid(struct nfsd4_compound_state *cstate, struct nfs4_stateowner *so, u32 seqid)
{
	if (nfsd4_has_session(cstate))
		return nfs_ok;
	if (seqid == so->so_seqid - 1)
		return nfserr_replay_me;
	if (seqid == so->so_seqid)
		return nfs_ok;
	return nfserr_bad_seqid;
}

static __be32 lookup_clientid(clientid_t *clid,
		struct nfsd4_compound_state *cstate,
		struct nfsd_net *nn)
{
	struct nfs4_client *found;

	if (cstate->clp) {
		found = cstate->clp;
		if (!same_clid(&found->cl_clientid, clid))
			return nfserr_stale_clientid;
		return nfs_ok;
	}

	if (STALE_CLIENTID(clid, nn))
		return nfserr_stale_clientid;

	/*
	 * For v4.1+ we get the client in the SEQUENCE op. If we don't have one
	 * cached already then we know this is for is for v4.0 and "sessions"
	 * will be false.
	 */
	WARN_ON_ONCE(cstate->session);
	spin_lock(&nn->client_lock);
	found = find_confirmed_client(clid, false, nn);
	if (!found) {
		spin_unlock(&nn->client_lock);
		return nfserr_expired;
	}
	atomic_inc(&found->cl_refcount);
	spin_unlock(&nn->client_lock);

	/* Cache the nfs4_client in cstate! */
	cstate->clp = found;
	return nfs_ok;
}

__be32
nfsd4_process_open1(struct nfsd4_compound_state *cstate,
		    struct nfsd4_open *open, struct nfsd_net *nn)
{
	clientid_t *clientid = &open->op_clientid;
	struct nfs4_client *clp = NULL;
	unsigned int strhashval;
	struct nfs4_openowner *oo = NULL;
	__be32 status;

	if (STALE_CLIENTID(&open->op_clientid, nn))
		return nfserr_stale_clientid;
	/*
	 * In case we need it later, after we've already created the
	 * file and don't want to risk a further failure:
	 */
	open->op_file = nfsd4_alloc_file();
	if (open->op_file == NULL)
		return nfserr_jukebox;

	status = lookup_clientid(clientid, cstate, nn);
	if (status)
		return status;
	clp = cstate->clp;

	strhashval = ownerstr_hashval(&open->op_owner);
	oo = find_openstateowner_str(strhashval, open, clp);
	open->op_openowner = oo;
	if (!oo) {
		goto new_owner;
	}
	if (!(oo->oo_flags & NFS4_OO_CONFIRMED)) {
		/* Replace unconfirmed owners without checking for replay. */
		release_openowner(oo);
		open->op_openowner = NULL;
		goto new_owner;
	}
	status = nfsd4_check_seqid(cstate, &oo->oo_owner, open->op_seqid);
	if (status)
		return status;
	goto alloc_stateid;
new_owner:
	oo = alloc_init_open_stateowner(strhashval, open, cstate);
	if (oo == NULL)
		return nfserr_jukebox;
	open->op_openowner = oo;
alloc_stateid:
	open->op_stp = nfs4_alloc_open_stateid(clp);
	if (!open->op_stp)
		return nfserr_jukebox;

	if (nfsd4_has_session(cstate) &&
	    (cstate->current_fh.fh_export->ex_flags & NFSEXP_PNFS)) {
		open->op_odstate = alloc_clnt_odstate(clp);
		if (!open->op_odstate)
			return nfserr_jukebox;
	}

	return nfs_ok;
}

static inline __be32
nfs4_check_delegmode(struct nfs4_delegation *dp, int flags)
{
	if ((flags & WR_STATE) && (dp->dl_type == NFS4_OPEN_DELEGATE_READ))
		return nfserr_openmode;
	else
		return nfs_ok;
}

static int share_access_to_flags(u32 share_access)
{
	return share_access == NFS4_SHARE_ACCESS_READ ? RD_STATE : WR_STATE;
}

static struct nfs4_delegation *find_deleg_stateid(struct nfs4_client *cl, stateid_t *s)
{
	struct nfs4_stid *ret;

	ret = find_stateid_by_type(cl, s,
				NFS4_DELEG_STID|NFS4_REVOKED_DELEG_STID);
	if (!ret)
		return NULL;
	return delegstateid(ret);
}

static bool nfsd4_is_deleg_cur(struct nfsd4_open *open)
{
	return open->op_claim_type == NFS4_OPEN_CLAIM_DELEGATE_CUR ||
	       open->op_claim_type == NFS4_OPEN_CLAIM_DELEG_CUR_FH;
}

static __be32
nfs4_check_deleg(struct nfs4_client *cl, struct nfsd4_open *open,
		struct nfs4_delegation **dp)
{
	int flags;
	__be32 status = nfserr_bad_stateid;
	struct nfs4_delegation *deleg;

	deleg = find_deleg_stateid(cl, &open->op_delegate_stateid);
	if (deleg == NULL)
		goto out;
	if (deleg->dl_stid.sc_type == NFS4_REVOKED_DELEG_STID) {
		nfs4_put_stid(&deleg->dl_stid);
		if (cl->cl_minorversion)
			status = nfserr_deleg_revoked;
		goto out;
	}
	flags = share_access_to_flags(open->op_share_access);
	status = nfs4_check_delegmode(deleg, flags);
	if (status) {
		nfs4_put_stid(&deleg->dl_stid);
		goto out;
	}
	*dp = deleg;
out:
	if (!nfsd4_is_deleg_cur(open))
		return nfs_ok;
	if (status)
		return status;
	open->op_openowner->oo_flags |= NFS4_OO_CONFIRMED;
	return nfs_ok;
}

static inline int nfs4_access_to_access(u32 nfs4_access)
{
	int flags = 0;

	if (nfs4_access & NFS4_SHARE_ACCESS_READ)
		flags |= NFSD_MAY_READ;
	if (nfs4_access & NFS4_SHARE_ACCESS_WRITE)
		flags |= NFSD_MAY_WRITE;
	return flags;
}

static inline __be32
nfsd4_truncate(struct svc_rqst *rqstp, struct svc_fh *fh,
		struct nfsd4_open *open)
{
	struct iattr iattr = {
		.ia_valid = ATTR_SIZE,
		.ia_size = 0,
	};
	if (!open->op_truncate)
		return 0;
	if (!(open->op_share_access & NFS4_SHARE_ACCESS_WRITE))
		return nfserr_inval;
	return nfsd_setattr(rqstp, fh, &iattr, 0, (time_t)0);
}

static __be32 nfs4_get_vfs_file(struct svc_rqst *rqstp, struct nfs4_file *fp,
		struct svc_fh *cur_fh, struct nfs4_ol_stateid *stp,
		struct nfsd4_open *open)
{
	struct file *filp = NULL;
	__be32 status;
	int oflag = nfs4_access_to_omode(open->op_share_access);
	int access = nfs4_access_to_access(open->op_share_access);
	unsigned char old_access_bmap, old_deny_bmap;

	spin_lock(&fp->fi_lock);

	/*
	 * Are we trying to set a deny mode that would conflict with
	 * current access?
	 */
	status = nfs4_file_check_deny(fp, open->op_share_deny);
	if (status != nfs_ok) {
		spin_unlock(&fp->fi_lock);
		goto out;
	}

	/* set access to the file */
	status = nfs4_file_get_access(fp, open->op_share_access);
	if (status != nfs_ok) {
		spin_unlock(&fp->fi_lock);
		goto out;
	}

	/* Set access bits in stateid */
	old_access_bmap = stp->st_access_bmap;
	set_access(open->op_share_access, stp);

	/* Set new deny mask */
	old_deny_bmap = stp->st_deny_bmap;
	set_deny(open->op_share_deny, stp);
	fp->fi_share_deny |= (open->op_share_deny & NFS4_SHARE_DENY_BOTH);

	if (!fp->fi_fds[oflag]) {
		spin_unlock(&fp->fi_lock);
		status = nfsd_open(rqstp, cur_fh, S_IFREG, access, &filp);
		if (status)
			goto out_put_access;
		spin_lock(&fp->fi_lock);
		if (!fp->fi_fds[oflag]) {
			fp->fi_fds[oflag] = filp;
			filp = NULL;
		}
	}
	spin_unlock(&fp->fi_lock);
	if (filp)
		fput(filp);

	status = nfsd4_truncate(rqstp, cur_fh, open);
	if (status)
		goto out_put_access;
out:
	return status;
out_put_access:
	stp->st_access_bmap = old_access_bmap;
	nfs4_file_put_access(fp, open->op_share_access);
	reset_union_bmap_deny(bmap_to_share_mode(old_deny_bmap), stp);
	goto out;
}

static __be32
nfs4_upgrade_open(struct svc_rqst *rqstp, struct nfs4_file *fp, struct svc_fh *cur_fh, struct nfs4_ol_stateid *stp, struct nfsd4_open *open)
{
	__be32 status;
	unsigned char old_deny_bmap = stp->st_deny_bmap;

	if (!test_access(open->op_share_access, stp))
		return nfs4_get_vfs_file(rqstp, fp, cur_fh, stp, open);

	/* test and set deny mode */
	spin_lock(&fp->fi_lock);
	status = nfs4_file_check_deny(fp, open->op_share_deny);
	if (status == nfs_ok) {
		set_deny(open->op_share_deny, stp);
		fp->fi_share_deny |=
				(open->op_share_deny & NFS4_SHARE_DENY_BOTH);
	}
	spin_unlock(&fp->fi_lock);

	if (status != nfs_ok)
		return status;

	status = nfsd4_truncate(rqstp, cur_fh, open);
	if (status != nfs_ok)
		reset_union_bmap_deny(old_deny_bmap, stp);
	return status;
}

/* Should we give out recallable state?: */
static bool nfsd4_cb_channel_good(struct nfs4_client *clp)
{
	if (clp->cl_cb_state == NFSD4_CB_UP)
		return true;
	/*
	 * In the sessions case, since we don't have to establish a
	 * separate connection for callbacks, we assume it's OK
	 * until we hear otherwise:
	 */
	return clp->cl_minorversion && clp->cl_cb_state == NFSD4_CB_UNKNOWN;
}

static struct file_lock *nfs4_alloc_init_lease(struct nfs4_delegation *dp,
						int flag)
{
	struct file_lock *fl;

	fl = locks_alloc_lock();
	if (!fl)
		return NULL;
	fl->fl_lmops = &nfsd_lease_mng_ops;
	fl->fl_flags = FL_DELEG;
	fl->fl_type = flag == NFS4_OPEN_DELEGATE_READ? F_RDLCK: F_WRLCK;
	fl->fl_end = OFFSET_MAX;
	fl->fl_owner = (fl_owner_t)dp;
	fl->fl_pid = current->tgid;
	fl->fl_file = dp->dl_stid.sc_file->fi_deleg_file;
	return fl;
}

static struct nfs4_delegation *
nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh,
		    struct nfs4_file *fp, struct nfs4_clnt_odstate *odstate)
{
	int status = 0;
	struct nfs4_delegation *dp;
	struct file *filp;
	struct file_lock *fl;

	/*
	 * The fi_had_conflict and nfs_get_existing_delegation checks
	 * here are just optimizations; we'll need to recheck them at
	 * the end:
	 */
	if (fp->fi_had_conflict)
		return ERR_PTR(-EAGAIN);

	filp = find_readable_file(fp);
	if (!filp) {
		/* We should always have a readable file here */
		WARN_ON_ONCE(1);
		return ERR_PTR(-EBADF);
	}
	spin_lock(&state_lock);
	spin_lock(&fp->fi_lock);
	if (nfs4_delegation_exists(clp, fp))
		status = -EAGAIN;
	else if (!fp->fi_deleg_file) {
		fp->fi_deleg_file = filp;
		/* increment early to prevent fi_deleg_file from being
		 * cleared */
		fp->fi_delegees = 1;
		filp = NULL;
	} else
		fp->fi_delegees++;
	spin_unlock(&fp->fi_lock);
	spin_unlock(&state_lock);
	if (filp)
		fput(filp);
	if (status)
		return ERR_PTR(status);

	status = -ENOMEM;
	dp = alloc_init_deleg(clp, fp, fh, odstate);
	if (!dp)
		goto out_delegees;

	fl = nfs4_alloc_init_lease(dp, NFS4_OPEN_DELEGATE_READ);
	if (!fl)
		goto out_stid;

	status = vfs_setlease(fp->fi_deleg_file, fl->fl_type, &fl, NULL);
	if (fl)
		locks_free_lock(fl);
	if (status)
		goto out_clnt_odstate;

	spin_lock(&state_lock);
	spin_lock(&fp->fi_lock);
	if (fp->fi_had_conflict)
		status = -EAGAIN;
	else
		status = hash_delegation_locked(dp, fp);
	spin_unlock(&fp->fi_lock);
	spin_unlock(&state_lock);

	if (status)
		goto out_unlock;

	return dp;
out_unlock:
	vfs_setlease(fp->fi_deleg_file, F_UNLCK, NULL, (void **)&dp);
out_clnt_odstate:
	put_clnt_odstate(dp->dl_clnt_odstate);
out_stid:
	nfs4_put_stid(&dp->dl_stid);
out_delegees:
	put_deleg_file(fp);
	return ERR_PTR(status);
}

static void nfsd4_open_deleg_none_ext(struct nfsd4_open *open, int status)
{
	open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE_EXT;
	if (status == -EAGAIN)
		open->op_why_no_deleg = WND4_CONTENTION;
	else {
		open->op_why_no_deleg = WND4_RESOURCE;
		switch (open->op_deleg_want) {
		case NFS4_SHARE_WANT_READ_DELEG:
		case NFS4_SHARE_WANT_WRITE_DELEG:
		case NFS4_SHARE_WANT_ANY_DELEG:
			break;
		case NFS4_SHARE_WANT_CANCEL:
			open->op_why_no_deleg = WND4_CANCELLED;
			break;
		case NFS4_SHARE_WANT_NO_DELEG:
			WARN_ON_ONCE(1);
		}
	}
}

/*
 * Attempt to hand out a delegation.
 *
 * Note we don't support write delegations, and won't until the vfs has
 * proper support for them.
 */
static void
nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open,
			struct nfs4_ol_stateid *stp)
{
	struct nfs4_delegation *dp;
	struct nfs4_openowner *oo = openowner(stp->st_stateowner);
	struct nfs4_client *clp = stp->st_stid.sc_client;
	int cb_up;
	int status = 0;

	cb_up = nfsd4_cb_channel_good(oo->oo_owner.so_client);
	open->op_recall = 0;
	switch (open->op_claim_type) {
		case NFS4_OPEN_CLAIM_PREVIOUS:
			if (!cb_up)
				open->op_recall = 1;
			if (open->op_delegate_type != NFS4_OPEN_DELEGATE_READ)
				goto out_no_deleg;
			break;
		case NFS4_OPEN_CLAIM_NULL:
		case NFS4_OPEN_CLAIM_FH:
			/*
			 * Let's not give out any delegations till everyone's
			 * had the chance to reclaim theirs, *and* until
			 * NLM locks have all been reclaimed:
			 */
			if (locks_in_grace(clp->net))
				goto out_no_deleg;
			if (!cb_up || !(oo->oo_flags & NFS4_OO_CONFIRMED))
				goto out_no_deleg;
			/*
			 * Also, if the file was opened for write or
			 * create, there's a good chance the client's
			 * about to write to it, resulting in an
			 * immediate recall (since we don't support
			 * write delegations):
			 */
			if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE)
				goto out_no_deleg;
			if (open->op_create == NFS4_OPEN_CREATE)
				goto out_no_deleg;
			break;
		default:
			goto out_no_deleg;
	}
	dp = nfs4_set_delegation(clp, fh, stp->st_stid.sc_file, stp->st_clnt_odstate);
	if (IS_ERR(dp))
		goto out_no_deleg;

	memcpy(&open->op_delegate_stateid, &dp->dl_stid.sc_stateid, sizeof(dp->dl_stid.sc_stateid));

	dprintk("NFSD: delegation stateid=" STATEID_FMT "\n",
		STATEID_VAL(&dp->dl_stid.sc_stateid));
	open->op_delegate_type = NFS4_OPEN_DELEGATE_READ;
	nfs4_put_stid(&dp->dl_stid);
	return;
out_no_deleg:
	open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE;
	if (open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS &&
	    open->op_delegate_type != NFS4_OPEN_DELEGATE_NONE) {
		dprintk("NFSD: WARNING: refusing delegation reclaim\n");
		open->op_recall = 1;
	}

	/* 4.1 client asking for a delegation? */
	if (open->op_deleg_want)
		nfsd4_open_deleg_none_ext(open, status);
	return;
}

static void nfsd4_deleg_xgrade_none_ext(struct nfsd4_open *open,
					struct nfs4_delegation *dp)
{
	if (open->op_deleg_want == NFS4_SHARE_WANT_READ_DELEG &&
	    dp->dl_type == NFS4_OPEN_DELEGATE_WRITE) {
		open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE_EXT;
		open->op_why_no_deleg = WND4_NOT_SUPP_DOWNGRADE;
	} else if (open->op_deleg_want == NFS4_SHARE_WANT_WRITE_DELEG &&
		   dp->dl_type == NFS4_OPEN_DELEGATE_WRITE) {
		open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE_EXT;
		open->op_why_no_deleg = WND4_NOT_SUPP_UPGRADE;
	}
	/* Otherwise the client must be confused wanting a delegation
	 * it already has, therefore we don't return
	 * NFS4_OPEN_DELEGATE_NONE_EXT and reason.
	 */
}

__be32
nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_open *open)
{
	struct nfsd4_compoundres *resp = rqstp->rq_resp;
	struct nfs4_client *cl = open->op_openowner->oo_owner.so_client;
	struct nfs4_file *fp = NULL;
	struct nfs4_ol_stateid *stp = NULL;
	struct nfs4_delegation *dp = NULL;
	__be32 status;
	bool new_stp = false;

	/*
	 * Lookup file; if found, lookup stateid and check open request,
	 * and check for delegations in the process of being recalled.
	 * If not found, create the nfs4_file struct
	 */
	fp = find_or_add_file(open->op_file, &current_fh->fh_handle);
	if (fp != open->op_file) {
		status = nfs4_check_deleg(cl, open, &dp);
		if (status)
			goto out;
		stp = nfsd4_find_and_lock_existing_open(fp, open);
	} else {
		open->op_file = NULL;
		status = nfserr_bad_stateid;
		if (nfsd4_is_deleg_cur(open))
			goto out;
	}

	if (!stp) {
		stp = init_open_stateid(fp, open);
		if (!open->op_stp)
			new_stp = true;
	}

	/*
	 * OPEN the file, or upgrade an existing OPEN.
	 * If truncate fails, the OPEN fails.
	 *
	 * stp is already locked.
	 */
	if (!new_stp) {
		/* Stateid was found, this is an OPEN upgrade */
		status = nfs4_upgrade_open(rqstp, fp, current_fh, stp, open);
		if (status) {
			mutex_unlock(&stp->st_mutex);
			goto out;
		}
	} else {
		status = nfs4_get_vfs_file(rqstp, fp, current_fh, stp, open);
		if (status) {
			stp->st_stid.sc_type = NFS4_CLOSED_STID;
			release_open_stateid(stp);
			mutex_unlock(&stp->st_mutex);
			goto out;
		}

		stp->st_clnt_odstate = find_or_hash_clnt_odstate(fp,
							open->op_odstate);
		if (stp->st_clnt_odstate == open->op_odstate)
			open->op_odstate = NULL;
	}

	nfs4_inc_and_copy_stateid(&open->op_stateid, &stp->st_stid);
	mutex_unlock(&stp->st_mutex);

	if (nfsd4_has_session(&resp->cstate)) {
		if (open->op_deleg_want & NFS4_SHARE_WANT_NO_DELEG) {
			open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE_EXT;
			open->op_why_no_deleg = WND4_NOT_WANTED;
			goto nodeleg;
		}
	}

	/*
	* Attempt to hand out a delegation. No error return, because the
	* OPEN succeeds even if we fail.
	*/
	nfs4_open_delegation(current_fh, open, stp);
nodeleg:
	status = nfs_ok;

	dprintk("%s: stateid=" STATEID_FMT "\n", __func__,
		STATEID_VAL(&stp->st_stid.sc_stateid));
out:
	/* 4.1 client trying to upgrade/downgrade delegation? */
	if (open->op_delegate_type == NFS4_OPEN_DELEGATE_NONE && dp &&
	    open->op_deleg_want)
		nfsd4_deleg_xgrade_none_ext(open, dp);

	if (fp)
		put_nfs4_file(fp);
	if (status == 0 && open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS)
		open->op_openowner->oo_flags |= NFS4_OO_CONFIRMED;
	/*
	* To finish the open response, we just need to set the rflags.
	*/
	open->op_rflags = NFS4_OPEN_RESULT_LOCKTYPE_POSIX;
	if (nfsd4_has_session(&resp->cstate))
		open->op_rflags |= NFS4_OPEN_RESULT_MAY_NOTIFY_LOCK;
	else if (!(open->op_openowner->oo_flags & NFS4_OO_CONFIRMED))
		open->op_rflags |= NFS4_OPEN_RESULT_CONFIRM;

	if (dp)
		nfs4_put_stid(&dp->dl_stid);
	if (stp)
		nfs4_put_stid(&stp->st_stid);

	return status;
}

void nfsd4_cleanup_open_state(struct nfsd4_compound_state *cstate,
			      struct nfsd4_open *open)
{
	if (open->op_openowner) {
		struct nfs4_stateowner *so = &open->op_openowner->oo_owner;

		nfsd4_cstate_assign_replay(cstate, so);
		nfs4_put_stateowner(so);
	}
	if (open->op_file)
		kmem_cache_free(file_slab, open->op_file);
	if (open->op_stp)
		nfs4_put_stid(&open->op_stp->st_stid);
	if (open->op_odstate)
		kmem_cache_free(odstate_slab, open->op_odstate);
}

__be32
nfsd4_renew(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
	    union nfsd4_op_u *u)
{
	clientid_t *clid = &u->renew;
	struct nfs4_client *clp;
	__be32 status;
	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);

	dprintk("process_renew(%08x/%08x): starting\n", 
			clid->cl_boot, clid->cl_id);
	status = lookup_clientid(clid, cstate, nn);
	if (status)
		goto out;
	clp = cstate->clp;
	status = nfserr_cb_path_down;
	if (!list_empty(&clp->cl_delegations)
			&& clp->cl_cb_state != NFSD4_CB_UP)
		goto out;
	status = nfs_ok;
out:
	return status;
}

void
nfsd4_end_grace(struct nfsd_net *nn)
{
	/* do nothing if grace period already ended */
	if (nn->grace_ended)
		return;

	dprintk("NFSD: end of grace period\n");
	nn->grace_ended = true;
	/*
	 * If the server goes down again right now, an NFSv4
	 * client will still be allowed to reclaim after it comes back up,
	 * even if it hasn't yet had a chance to reclaim state this time.
	 *
	 */
	nfsd4_record_grace_done(nn);
	/*
	 * At this point, NFSv4 clients can still reclaim.  But if the
	 * server crashes, any that have not yet reclaimed will be out
	 * of luck on the next boot.
	 *
	 * (NFSv4.1+ clients are considered to have reclaimed once they
	 * call RECLAIM_COMPLETE.  NFSv4.0 clients are considered to
	 * have reclaimed after their first OPEN.)
	 */
	locks_end_grace(&nn->nfsd4_manager);
	/*
	 * At this point, and once lockd and/or any other containers
	 * exit their grace period, further reclaims will fail and
	 * regular locking can resume.
	 */
}

/*
 * If we've waited a lease period but there are still clients trying to
 * reclaim, wait a little longer to give them a chance to finish.
 */
static bool clients_still_reclaiming(struct nfsd_net *nn)
{
	unsigned long now = get_seconds();
	unsigned long double_grace_period_end = nn->boot_time +
						2 * nn->nfsd4_lease;

	if (!nn->somebody_reclaimed)
		return false;
	nn->somebody_reclaimed = false;
	/*
	 * If we've given them *two* lease times to reclaim, and they're
	 * still not done, give up:
	 */
	if (time_after(now, double_grace_period_end))
		return false;
	return true;
}

static time_t
nfs4_laundromat(struct nfsd_net *nn)
{
	struct nfs4_client *clp;
	struct nfs4_openowner *oo;
	struct nfs4_delegation *dp;
	struct nfs4_ol_stateid *stp;
	struct nfsd4_blocked_lock *nbl;
	struct list_head *pos, *next, reaplist;
	time_t cutoff = get_seconds() - nn->nfsd4_lease;
	time_t t, new_timeo = nn->nfsd4_lease;

	dprintk("NFSD: laundromat service - starting\n");

	if (clients_still_reclaiming(nn)) {
		new_timeo = 0;
		goto out;
	}
	nfsd4_end_grace(nn);
	INIT_LIST_HEAD(&reaplist);
	spin_lock(&nn->client_lock);
	list_for_each_safe(pos, next, &nn->client_lru) {
		clp = list_entry(pos, struct nfs4_client, cl_lru);
		if (time_after((unsigned long)clp->cl_time, (unsigned long)cutoff)) {
			t = clp->cl_time - cutoff;
			new_timeo = min(new_timeo, t);
			break;
		}
		if (mark_client_expired_locked(clp)) {
			dprintk("NFSD: client in use (clientid %08x)\n",
				clp->cl_clientid.cl_id);
			continue;
		}
		list_add(&clp->cl_lru, &reaplist);
	}
	spin_unlock(&nn->client_lock);
	list_for_each_safe(pos, next, &reaplist) {
		clp = list_entry(pos, struct nfs4_client, cl_lru);
		dprintk("NFSD: purging unused client (clientid %08x)\n",
			clp->cl_clientid.cl_id);
		list_del_init(&clp->cl_lru);
		expire_client(clp);
	}
	spin_lock(&state_lock);
	list_for_each_safe(pos, next, &nn->del_recall_lru) {
		dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru);
		if (time_after((unsigned long)dp->dl_time, (unsigned long)cutoff)) {
			t = dp->dl_time - cutoff;
			new_timeo = min(new_timeo, t);
			break;
		}
		WARN_ON(!unhash_delegation_locked(dp));
		list_add(&dp->dl_recall_lru, &reaplist);
	}
	spin_unlock(&state_lock);
	while (!list_empty(&reaplist)) {
		dp = list_first_entry(&reaplist, struct nfs4_delegation,
					dl_recall_lru);
		list_del_init(&dp->dl_recall_lru);
		revoke_delegation(dp);
	}

	spin_lock(&nn->client_lock);
	while (!list_empty(&nn->close_lru)) {
		oo = list_first_entry(&nn->close_lru, struct nfs4_openowner,
					oo_close_lru);
		if (time_after((unsigned long)oo->oo_time,
			       (unsigned long)cutoff)) {
			t = oo->oo_time - cutoff;
			new_timeo = min(new_timeo, t);
			break;
		}
		list_del_init(&oo->oo_close_lru);
		stp = oo->oo_last_closed_stid;
		oo->oo_last_closed_stid = NULL;
		spin_unlock(&nn->client_lock);
		nfs4_put_stid(&stp->st_stid);
		spin_lock(&nn->client_lock);
	}
	spin_unlock(&nn->client_lock);

	/*
	 * It's possible for a client to try and acquire an already held lock
	 * that is being held for a long time, and then lose interest in it.
	 * So, we clean out any un-revisited request after a lease period
	 * under the assumption that the client is no longer interested.
	 *
	 * RFC5661, sec. 9.6 states that the client must not rely on getting
	 * notifications and must continue to poll for locks, even when the
	 * server supports them. Thus this shouldn't lead to clients blocking
	 * indefinitely once the lock does become free.
	 */
	BUG_ON(!list_empty(&reaplist));
	spin_lock(&nn->blocked_locks_lock);
	while (!list_empty(&nn->blocked_locks_lru)) {
		nbl = list_first_entry(&nn->blocked_locks_lru,
					struct nfsd4_blocked_lock, nbl_lru);
		if (time_after((unsigned long)nbl->nbl_time,
			       (unsigned long)cutoff)) {
			t = nbl->nbl_time - cutoff;
			new_timeo = min(new_timeo, t);
			break;
		}
		list_move(&nbl->nbl_lru, &reaplist);
		list_del_init(&nbl->nbl_list);
	}
	spin_unlock(&nn->blocked_locks_lock);

	while (!list_empty(&reaplist)) {
		nbl = list_first_entry(&reaplist,
					struct nfsd4_blocked_lock, nbl_lru);
		list_del_init(&nbl->nbl_lru);
		posix_unblock_lock(&nbl->nbl_lock);
		free_blocked_lock(nbl);
	}
out:
	new_timeo = max_t(time_t, new_timeo, NFSD_LAUNDROMAT_MINTIMEOUT);
	return new_timeo;
}

static struct workqueue_struct *laundry_wq;
static void laundromat_main(struct work_struct *);

static void
laundromat_main(struct work_struct *laundry)
{
	time_t t;
	struct delayed_work *dwork = to_delayed_work(laundry);
	struct nfsd_net *nn = container_of(dwork, struct nfsd_net,
					   laundromat_work);

	t = nfs4_laundromat(nn);
	dprintk("NFSD: laundromat_main - sleeping for %ld seconds\n", t);
	queue_delayed_work(laundry_wq, &nn->laundromat_work, t*HZ);
}

static inline __be32 nfs4_check_fh(struct svc_fh *fhp, struct nfs4_stid *stp)
{
	if (!fh_match(&fhp->fh_handle, &stp->sc_file->fi_fhandle))
		return nfserr_bad_stateid;
	return nfs_ok;
}

static inline int
access_permit_read(struct nfs4_ol_stateid *stp)
{
	return test_access(NFS4_SHARE_ACCESS_READ, stp) ||
		test_access(NFS4_SHARE_ACCESS_BOTH, stp) ||
		test_access(NFS4_SHARE_ACCESS_WRITE, stp);
}

static inline int
access_permit_write(struct nfs4_ol_stateid *stp)
{
	return test_access(NFS4_SHARE_ACCESS_WRITE, stp) ||
		test_access(NFS4_SHARE_ACCESS_BOTH, stp);
}

static
__be32 nfs4_check_openmode(struct nfs4_ol_stateid *stp, int flags)
{
        __be32 status = nfserr_openmode;

	/* For lock stateid's, we test the parent open, not the lock: */
	if (stp->st_openstp)
		stp = stp->st_openstp;
	if ((flags & WR_STATE) && !access_permit_write(stp))
                goto out;
	if ((flags & RD_STATE) && !access_permit_read(stp))
                goto out;
	status = nfs_ok;
out:
	return status;
}

static inline __be32
check_special_stateids(struct net *net, svc_fh *current_fh, stateid_t *stateid, int flags)
{
	if (ONE_STATEID(stateid) && (flags & RD_STATE))
		return nfs_ok;
	else if (opens_in_grace(net)) {
		/* Answer in remaining cases depends on existence of
		 * conflicting state; so we must wait out the grace period. */
		return nfserr_grace;
	} else if (flags & WR_STATE)
		return nfs4_share_conflict(current_fh,
				NFS4_SHARE_DENY_WRITE);
	else /* (flags & RD_STATE) && ZERO_STATEID(stateid) */
		return nfs4_share_conflict(current_fh,
				NFS4_SHARE_DENY_READ);
}

/*
 * Allow READ/WRITE during grace period on recovered state only for files
 * that are not able to provide mandatory locking.
 */
static inline int
grace_disallows_io(struct net *net, struct inode *inode)
{
	return opens_in_grace(net) && mandatory_lock(inode);
}

static __be32 check_stateid_generation(stateid_t *in, stateid_t *ref, bool has_session)
{
	/*
	 * When sessions are used the stateid generation number is ignored
	 * when it is zero.
	 */
	if (has_session && in->si_generation == 0)
		return nfs_ok;

	if (in->si_generation == ref->si_generation)
		return nfs_ok;

	/* If the client sends us a stateid from the future, it's buggy: */
	if (nfsd4_stateid_generation_after(in, ref))
		return nfserr_bad_stateid;
	/*
	 * However, we could see a stateid from the past, even from a
	 * non-buggy client.  For example, if the client sends a lock
	 * while some IO is outstanding, the lock may bump si_generation
	 * while the IO is still in flight.  The client could avoid that
	 * situation by waiting for responses on all the IO requests,
	 * but better performance may result in retrying IO that
	 * receives an old_stateid error if requests are rarely
	 * reordered in flight:
	 */
	return nfserr_old_stateid;
}

static __be32 nfsd4_stid_check_stateid_generation(stateid_t *in, struct nfs4_stid *s, bool has_session)
{
	__be32 ret;

	spin_lock(&s->sc_lock);
	ret = nfsd4_verify_open_stid(s);
	if (ret == nfs_ok)
		ret = check_stateid_generation(in, &s->sc_stateid, has_session);
	spin_unlock(&s->sc_lock);
	return ret;
}

static __be32 nfsd4_check_openowner_confirmed(struct nfs4_ol_stateid *ols)
{
	if (ols->st_stateowner->so_is_open_owner &&
	    !(openowner(ols->st_stateowner)->oo_flags & NFS4_OO_CONFIRMED))
		return nfserr_bad_stateid;
	return nfs_ok;
}

static __be32 nfsd4_validate_stateid(struct nfs4_client *cl, stateid_t *stateid)
{
	struct nfs4_stid *s;
	__be32 status = nfserr_bad_stateid;

	if (ZERO_STATEID(stateid) || ONE_STATEID(stateid) ||
		CLOSE_STATEID(stateid))
		return status;
	/* Client debugging aid. */
	if (!same_clid(&stateid->si_opaque.so_clid, &cl->cl_clientid)) {
		char addr_str[INET6_ADDRSTRLEN];
		rpc_ntop((struct sockaddr *)&cl->cl_addr, addr_str,
				 sizeof(addr_str));
		pr_warn_ratelimited("NFSD: client %s testing state ID "
					"with incorrect client ID\n", addr_str);
		return status;
	}
	spin_lock(&cl->cl_lock);
	s = find_stateid_locked(cl, stateid);
	if (!s)
		goto out_unlock;
	status = nfsd4_stid_check_stateid_generation(stateid, s, 1);
	if (status)
		goto out_unlock;
	switch (s->sc_type) {
	case NFS4_DELEG_STID:
		status = nfs_ok;
		break;
	case NFS4_REVOKED_DELEG_STID:
		status = nfserr_deleg_revoked;
		break;
	case NFS4_OPEN_STID:
	case NFS4_LOCK_STID:
		status = nfsd4_check_openowner_confirmed(openlockstateid(s));
		break;
	default:
		printk("unknown stateid type %x\n", s->sc_type);
		/* Fallthrough */
	case NFS4_CLOSED_STID:
	case NFS4_CLOSED_DELEG_STID:
		status = nfserr_bad_stateid;
	}
out_unlock:
	spin_unlock(&cl->cl_lock);
	return status;
}

__be32
nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate,
		     stateid_t *stateid, unsigned char typemask,
		     struct nfs4_stid **s, struct nfsd_net *nn)
{
	__be32 status;
	bool return_revoked = false;

	/*
	 *  only return revoked delegations if explicitly asked.
	 *  otherwise we report revoked or bad_stateid status.
	 */
	if (typemask & NFS4_REVOKED_DELEG_STID)
		return_revoked = true;
	else if (typemask & NFS4_DELEG_STID)
		typemask |= NFS4_REVOKED_DELEG_STID;

	if (ZERO_STATEID(stateid) || ONE_STATEID(stateid) ||
		CLOSE_STATEID(stateid))
		return nfserr_bad_stateid;
	status = lookup_clientid(&stateid->si_opaque.so_clid, cstate, nn);
	if (status == nfserr_stale_clientid) {
		if (cstate->session)
			return nfserr_bad_stateid;
		return nfserr_stale_stateid;
	}
	if (status)
		return status;
	*s = find_stateid_by_type(cstate->clp, stateid, typemask);
	if (!*s)
		return nfserr_bad_stateid;
	if (((*s)->sc_type == NFS4_REVOKED_DELEG_STID) && !return_revoked) {
		nfs4_put_stid(*s);
		if (cstate->minorversion)
			return nfserr_deleg_revoked;
		return nfserr_bad_stateid;
	}
	return nfs_ok;
}

static struct file *
nfs4_find_file(struct nfs4_stid *s, int flags)
{
	if (!s)
		return NULL;

	switch (s->sc_type) {
	case NFS4_DELEG_STID:
		if (WARN_ON_ONCE(!s->sc_file->fi_deleg_file))
			return NULL;
		return get_file(s->sc_file->fi_deleg_file);
	case NFS4_OPEN_STID:
	case NFS4_LOCK_STID:
		if (flags & RD_STATE)
			return find_readable_file(s->sc_file);
		else
			return find_writeable_file(s->sc_file);
		break;
	}

	return NULL;
}

static __be32
nfs4_check_olstateid(struct svc_fh *fhp, struct nfs4_ol_stateid *ols, int flags)
{
	__be32 status;

	status = nfsd4_check_openowner_confirmed(ols);
	if (status)
		return status;
	return nfs4_check_openmode(ols, flags);
}

static __be32
nfs4_check_file(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfs4_stid *s,
		struct file **filpp, bool *tmp_file, int flags)
{
	int acc = (flags & RD_STATE) ? NFSD_MAY_READ : NFSD_MAY_WRITE;
	struct file *file;
	__be32 status;

	file = nfs4_find_file(s, flags);
	if (file) {
		status = nfsd_permission(rqstp, fhp->fh_export, fhp->fh_dentry,
				acc | NFSD_MAY_OWNER_OVERRIDE);
		if (status) {
			fput(file);
			return status;
		}

		*filpp = file;
	} else {
		status = nfsd_open(rqstp, fhp, S_IFREG, acc, filpp);
		if (status)
			return status;

		if (tmp_file)
			*tmp_file = true;
	}

	return 0;
}

/*
 * Checks for stateid operations
 */
__be32
nfs4_preprocess_stateid_op(struct svc_rqst *rqstp,
		struct nfsd4_compound_state *cstate, struct svc_fh *fhp,
		stateid_t *stateid, int flags, struct file **filpp, bool *tmp_file)
{
	struct inode *ino = d_inode(fhp->fh_dentry);
	struct net *net = SVC_NET(rqstp);
	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
	struct nfs4_stid *s = NULL;
	__be32 status;

	if (filpp)
		*filpp = NULL;
	if (tmp_file)
		*tmp_file = false;

	if (grace_disallows_io(net, ino))
		return nfserr_grace;

	if (ZERO_STATEID(stateid) || ONE_STATEID(stateid)) {
		status = check_special_stateids(net, fhp, stateid, flags);
		goto done;
	}

	status = nfsd4_lookup_stateid(cstate, stateid,
				NFS4_DELEG_STID|NFS4_OPEN_STID|NFS4_LOCK_STID,
				&s, nn);
	if (status)
		return status;
	status = nfsd4_stid_check_stateid_generation(stateid, s,
			nfsd4_has_session(cstate));
	if (status)
		goto out;

	switch (s->sc_type) {
	case NFS4_DELEG_STID:
		status = nfs4_check_delegmode(delegstateid(s), flags);
		break;
	case NFS4_OPEN_STID:
	case NFS4_LOCK_STID:
		status = nfs4_check_olstateid(fhp, openlockstateid(s), flags);
		break;
	default:
		status = nfserr_bad_stateid;
		break;
	}
	if (status)
		goto out;
	status = nfs4_check_fh(fhp, s);

done:
	if (!status && filpp)
		status = nfs4_check_file(rqstp, fhp, s, filpp, tmp_file, flags);
out:
	if (s)
		nfs4_put_stid(s);
	return status;
}

/*
 * Test if the stateid is valid
 */
__be32
nfsd4_test_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
		   union nfsd4_op_u *u)
{
	struct nfsd4_test_stateid *test_stateid = &u->test_stateid;
	struct nfsd4_test_stateid_id *stateid;
	struct nfs4_client *cl = cstate->session->se_client;

	list_for_each_entry(stateid, &test_stateid->ts_stateid_list, ts_id_list)
		stateid->ts_id_status =
			nfsd4_validate_stateid(cl, &stateid->ts_id_stateid);

	return nfs_ok;
}

static __be32
nfsd4_free_lock_stateid(stateid_t *stateid, struct nfs4_stid *s)
{
	struct nfs4_ol_stateid *stp = openlockstateid(s);
	__be32 ret;

	ret = nfsd4_lock_ol_stateid(stp);
	if (ret)
		goto out_put_stid;

	ret = check_stateid_generation(stateid, &s->sc_stateid, 1);
	if (ret)
		goto out;

	ret = nfserr_locks_held;
	if (check_for_locks(stp->st_stid.sc_file,
			    lockowner(stp->st_stateowner)))
		goto out;

	release_lock_stateid(stp);
	ret = nfs_ok;

out:
	mutex_unlock(&stp->st_mutex);
out_put_stid:
	nfs4_put_stid(s);
	return ret;
}

__be32
nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
		   union nfsd4_op_u *u)
{
	struct nfsd4_free_stateid *free_stateid = &u->free_stateid;
	stateid_t *stateid = &free_stateid->fr_stateid;
	struct nfs4_stid *s;
	struct nfs4_delegation *dp;
	struct nfs4_client *cl = cstate->session->se_client;
	__be32 ret = nfserr_bad_stateid;

	spin_lock(&cl->cl_lock);
	s = find_stateid_locked(cl, stateid);
	if (!s)
		goto out_unlock;
	spin_lock(&s->sc_lock);
	switch (s->sc_type) {
	case NFS4_DELEG_STID:
		ret = nfserr_locks_held;
		break;
	case NFS4_OPEN_STID:
		ret = check_stateid_generation(stateid, &s->sc_stateid, 1);
		if (ret)
			break;
		ret = nfserr_locks_held;
		break;
	case NFS4_LOCK_STID:
		spin_unlock(&s->sc_lock);
		refcount_inc(&s->sc_count);
		spin_unlock(&cl->cl_lock);
		ret = nfsd4_free_lock_stateid(stateid, s);
		goto out;
	case NFS4_REVOKED_DELEG_STID:
		spin_unlock(&s->sc_lock);
		dp = delegstateid(s);
		list_del_init(&dp->dl_recall_lru);
		spin_unlock(&cl->cl_lock);
		nfs4_put_stid(s);
		ret = nfs_ok;
		goto out;
	/* Default falls through and returns nfserr_bad_stateid */
	}
	spin_unlock(&s->sc_lock);
out_unlock:
	spin_unlock(&cl->cl_lock);
out:
	return ret;
}

static inline int
setlkflg (int type)
{
	return (type == NFS4_READW_LT || type == NFS4_READ_LT) ?
		RD_STATE : WR_STATE;
}

static __be32 nfs4_seqid_op_checks(struct nfsd4_compound_state *cstate, stateid_t *stateid, u32 seqid, struct nfs4_ol_stateid *stp)
{
	struct svc_fh *current_fh = &cstate->current_fh;
	struct nfs4_stateowner *sop = stp->st_stateowner;
	__be32 status;

	status = nfsd4_check_seqid(cstate, sop, seqid);
	if (status)
		return status;
	status = nfsd4_lock_ol_stateid(stp);
	if (status != nfs_ok)
		return status;
	status = check_stateid_generation(stateid, &stp->st_stid.sc_stateid, nfsd4_has_session(cstate));
	if (status == nfs_ok)
		status = nfs4_check_fh(current_fh, &stp->st_stid);
	if (status != nfs_ok)
		mutex_unlock(&stp->st_mutex);
	return status;
}

/* 
 * Checks for sequence id mutating operations. 
 */
static __be32
nfs4_preprocess_seqid_op(struct nfsd4_compound_state *cstate, u32 seqid,
			 stateid_t *stateid, char typemask,
			 struct nfs4_ol_stateid **stpp,
			 struct nfsd_net *nn)
{
	__be32 status;
	struct nfs4_stid *s;
	struct nfs4_ol_stateid *stp = NULL;

	dprintk("NFSD: %s: seqid=%d stateid = " STATEID_FMT "\n", __func__,
		seqid, STATEID_VAL(stateid));

	*stpp = NULL;
	status = nfsd4_lookup_stateid(cstate, stateid, typemask, &s, nn);
	if (status)
		return status;
	stp = openlockstateid(s);
	nfsd4_cstate_assign_replay(cstate, stp->st_stateowner);

	status = nfs4_seqid_op_checks(cstate, stateid, seqid, stp);
	if (!status)
		*stpp = stp;
	else
		nfs4_put_stid(&stp->st_stid);
	return status;
}

static __be32 nfs4_preprocess_confirmed_seqid_op(struct nfsd4_compound_state *cstate, u32 seqid,
						 stateid_t *stateid, struct nfs4_ol_stateid **stpp, struct nfsd_net *nn)
{
	__be32 status;
	struct nfs4_openowner *oo;
	struct nfs4_ol_stateid *stp;

	status = nfs4_preprocess_seqid_op(cstate, seqid, stateid,
						NFS4_OPEN_STID, &stp, nn);
	if (status)
		return status;
	oo = openowner(stp->st_stateowner);
	if (!(oo->oo_flags & NFS4_OO_CONFIRMED)) {
		mutex_unlock(&stp->st_mutex);
		nfs4_put_stid(&stp->st_stid);
		return nfserr_bad_stateid;
	}
	*stpp = stp;
	return nfs_ok;
}

__be32
nfsd4_open_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
		   union nfsd4_op_u *u)
{
	struct nfsd4_open_confirm *oc = &u->open_confirm;
	__be32 status;
	struct nfs4_openowner *oo;
	struct nfs4_ol_stateid *stp;
	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);

	dprintk("NFSD: nfsd4_open_confirm on file %pd\n",
			cstate->current_fh.fh_dentry);

	status = fh_verify(rqstp, &cstate->current_fh, S_IFREG, 0);
	if (status)
		return status;

	status = nfs4_preprocess_seqid_op(cstate,
					oc->oc_seqid, &oc->oc_req_stateid,
					NFS4_OPEN_STID, &stp, nn);
	if (status)
		goto out;
	oo = openowner(stp->st_stateowner);
	status = nfserr_bad_stateid;
	if (oo->oo_flags & NFS4_OO_CONFIRMED) {
		mutex_unlock(&stp->st_mutex);
		goto put_stateid;
	}
	oo->oo_flags |= NFS4_OO_CONFIRMED;
	nfs4_inc_and_copy_stateid(&oc->oc_resp_stateid, &stp->st_stid);
	mutex_unlock(&stp->st_mutex);
	dprintk("NFSD: %s: success, seqid=%d stateid=" STATEID_FMT "\n",
		__func__, oc->oc_seqid, STATEID_VAL(&stp->st_stid.sc_stateid));

	nfsd4_client_record_create(oo->oo_owner.so_client);
	status = nfs_ok;
put_stateid:
	nfs4_put_stid(&stp->st_stid);
out:
	nfsd4_bump_seqid(cstate, status);
	return status;
}

static inline void nfs4_stateid_downgrade_bit(struct nfs4_ol_stateid *stp, u32 access)
{
	if (!test_access(access, stp))
		return;
	nfs4_file_put_access(stp->st_stid.sc_file, access);
	clear_access(access, stp);
}

static inline void nfs4_stateid_downgrade(struct nfs4_ol_stateid *stp, u32 to_access)
{
	switch (to_access) {
	case NFS4_SHARE_ACCESS_READ:
		nfs4_stateid_downgrade_bit(stp, NFS4_SHARE_ACCESS_WRITE);
		nfs4_stateid_downgrade_bit(stp, NFS4_SHARE_ACCESS_BOTH);
		break;
	case NFS4_SHARE_ACCESS_WRITE:
		nfs4_stateid_downgrade_bit(stp, NFS4_SHARE_ACCESS_READ);
		nfs4_stateid_downgrade_bit(stp, NFS4_SHARE_ACCESS_BOTH);
		break;
	case NFS4_SHARE_ACCESS_BOTH:
		break;
	default:
		WARN_ON_ONCE(1);
	}
}

__be32
nfsd4_open_downgrade(struct svc_rqst *rqstp,
		     struct nfsd4_compound_state *cstate, union nfsd4_op_u *u)
{
	struct nfsd4_open_downgrade *od = &u->open_downgrade;
	__be32 status;
	struct nfs4_ol_stateid *stp;
	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);

	dprintk("NFSD: nfsd4_open_downgrade on file %pd\n", 
			cstate->current_fh.fh_dentry);

	/* We don't yet support WANT bits: */
	if (od->od_deleg_want)
		dprintk("NFSD: %s: od_deleg_want=0x%x ignored\n", __func__,
			od->od_deleg_want);

	status = nfs4_preprocess_confirmed_seqid_op(cstate, od->od_seqid,
					&od->od_stateid, &stp, nn);
	if (status)
		goto out; 
	status = nfserr_inval;
	if (!test_access(od->od_share_access, stp)) {
		dprintk("NFSD: access not a subset of current bitmap: 0x%hhx, input access=%08x\n",
			stp->st_access_bmap, od->od_share_access);
		goto put_stateid;
	}
	if (!test_deny(od->od_share_deny, stp)) {
		dprintk("NFSD: deny not a subset of current bitmap: 0x%hhx, input deny=%08x\n",
			stp->st_deny_bmap, od->od_share_deny);
		goto put_stateid;
	}
	nfs4_stateid_downgrade(stp, od->od_share_access);
	reset_union_bmap_deny(od->od_share_deny, stp);
	nfs4_inc_and_copy_stateid(&od->od_stateid, &stp->st_stid);
	status = nfs_ok;
put_stateid:
	mutex_unlock(&stp->st_mutex);
	nfs4_put_stid(&stp->st_stid);
out:
	nfsd4_bump_seqid(cstate, status);
	return status;
}

static void nfsd4_close_open_stateid(struct nfs4_ol_stateid *s)
{
	struct nfs4_client *clp = s->st_stid.sc_client;
	bool unhashed;
	LIST_HEAD(reaplist);

	spin_lock(&clp->cl_lock);
	unhashed = unhash_open_stateid(s, &reaplist);

	if (clp->cl_minorversion) {
		if (unhashed)
			put_ol_stateid_locked(s, &reaplist);
		spin_unlock(&clp->cl_lock);
		free_ol_stateid_reaplist(&reaplist);
	} else {
		spin_unlock(&clp->cl_lock);
		free_ol_stateid_reaplist(&reaplist);
		if (unhashed)
			move_to_close_lru(s, clp->net);
	}
}

/*
 * nfs4_unlock_state() called after encode
 */
__be32
nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
		union nfsd4_op_u *u)
{
	struct nfsd4_close *close = &u->close;
	__be32 status;
	struct nfs4_ol_stateid *stp;
	struct net *net = SVC_NET(rqstp);
	struct nfsd_net *nn = net_generic(net, nfsd_net_id);

	dprintk("NFSD: nfsd4_close on file %pd\n", 
			cstate->current_fh.fh_dentry);

	status = nfs4_preprocess_seqid_op(cstate, close->cl_seqid,
					&close->cl_stateid,
					NFS4_OPEN_STID|NFS4_CLOSED_STID,
					&stp, nn);
	nfsd4_bump_seqid(cstate, status);
	if (status)
		goto out; 

	stp->st_stid.sc_type = NFS4_CLOSED_STID;

	/*
	 * Technically we don't _really_ have to increment or copy it, since
	 * it should just be gone after this operation and we clobber the
	 * copied value below, but we continue to do so here just to ensure
	 * that racing ops see that there was a state change.
	 */
	nfs4_inc_and_copy_stateid(&close->cl_stateid, &stp->st_stid);

	nfsd4_close_open_stateid(stp);
	mutex_unlock(&stp->st_mutex);

	/* v4.1+ suggests that we send a special stateid in here, since the
	 * clients should just ignore this anyway. Since this is not useful
	 * for v4.0 clients either, we set it to the special close_stateid
	 * universally.
	 *
	 * See RFC5661 section 18.2.4, and RFC7530 section 16.2.5
	 */
	memcpy(&close->cl_stateid, &close_stateid, sizeof(close->cl_stateid));

	/* put reference from nfs4_preprocess_seqid_op */
	nfs4_put_stid(&stp->st_stid);
out:
	return status;
}

__be32
nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
		  union nfsd4_op_u *u)
{
	struct nfsd4_delegreturn *dr = &u->delegreturn;
	struct nfs4_delegation *dp;
	stateid_t *stateid = &dr->dr_stateid;
	struct nfs4_stid *s;
	__be32 status;
	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);

	if ((status = fh_verify(rqstp, &cstate->current_fh, S_IFREG, 0)))
		return status;

	status = nfsd4_lookup_stateid(cstate, stateid, NFS4_DELEG_STID, &s, nn);
	if (status)
		goto out;
	dp = delegstateid(s);
	status = nfsd4_stid_check_stateid_generation(stateid, &dp->dl_stid, nfsd4_has_session(