123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773774775776777778779780781782783784785786787788789790791792793794795796797798799800801802803804805806807808809810811812813814815816817818819820821822823824825826827828829830831832833834835836837838839840841842843844845846847848849850851852853854855856857858859860861862863864865866867868869870871872873874875876877878879880881882883884885886887888889890891892893894895896897898899900901902903904905906907908909910911912913914915916917918919920921922923924925926927928929930931932933934935936937938939940941942943944945946947948949950951952953954955956957958959960961962963964965966967968969970971972973974975976977978979980981982983984985986987988989990991992993994995996997998999100010011002100310041005100610071008100910101011101210131014101510161017101810191020102110221023102410251026102710281029103010311032103310341035103610371038103910401041104210431044104510461047104810491050105110521053105410551056105710581059106010611062106310641065106610671068106910701071107210731074107510761077107810791080108110821083108410851086108710881089109010911092109310941095109610971098109911001101110211031104110511061107110811091110111111121113111411151116111711181119112011211122112311241125112611271128112911301131113211331134113511361137113811391140114111421143114411451146114711481149115011511152115311541155115611571158115911601161116211631164116511661167116811691170117111721173117411751176117711781179118011811182118311841185118611871188118911901191119211931194119511961197119811991200120112021203120412051206120712081209121012111212121312141215121612171218121912201221122212231224122512261227122812291230123112321233123412351236123712381239124012411242124312441245124612471248124912501251125212531254125512561257125812591260126112621263126412651266126712681269127012711272127312741275127612771278127912801281128212831284128512861287128812891290129112921293129412951296129712981299130013011302130313041305130613071308130913101311131213131314131513161317131813191320132113221323132413251326132713281329133013311332133313341335133613371338133913401341134213431344134513461347134813491350135113521353135413551356135713581359136013611362136313641365136613671368136913701371137213731374137513761377137813791380138113821383138413851386138713881389139013911392139313941395139613971398139914001401140214031404140514061407140814091410141114121413141414151416141714181419142014211422142314241425142614271428142914301431143214331434143514361437143814391440144114421443144414451446144714481449145014511452145314541455145614571458145914601461146214631464146514661467146814691470147114721473147414751476147714781479148014811482148314841485148614871488148914901491149214931494149514961497149814991500150115021503150415051506150715081509151015111512151315141515151615171518151915201521152215231524152515261527152815291530153115321533153415351536153715381539154015411542154315441545154615471548154915501551155215531554155515561557155815591560156115621563156415651566156715681569157015711572157315741575157615771578157915801581158215831584158515861587158815891590159115921593159415951596159715981599160016011602160316041605160616071608160916101611161216131614161516161617161816191620162116221623162416251626162716281629163016311632163316341635163616371638163916401641164216431644164516461647164816491650165116521653165416551656165716581659166016611662166316641665166616671668166916701671167216731674167516761677167816791680168116821683168416851686168716881689169016911692169316941695169616971698169917001701170217031704170517061707170817091710171117121713171417151716171717181719172017211722172317241725172617271728172917301731173217331734173517361737173817391740174117421743174417451746174717481749175017511752175317541755175617571758175917601761176217631764176517661767176817691770177117721773177417751776177717781779178017811782178317841785178617871788178917901791179217931794179517961797179817991800180118021803180418051806180718081809181018111812181318141815181618171818181918201821182218231824182518261827182818291830183118321833183418351836183718381839184018411842184318441845184618471848184918501851185218531854185518561857185818591860186118621863186418651866186718681869187018711872187318741875187618771878187918801881188218831884188518861887188818891890189118921893189418951896189718981899190019011902190319041905190619071908190919101911191219131914191519161917191819191920192119221923192419251926192719281929193019311932193319341935193619371938193919401941194219431944194519461947194819491950195119521953195419551956195719581959196019611962196319641965196619671968196919701971197219731974197519761977197819791980198119821983198419851986198719881989199019911992199319941995199619971998199920002001200220032004200520062007200820092010201120122013201420152016201720182019202020212022202320242025202620272028202920302031203220332034203520362037203820392040204120422043204420452046204720482049205020512052205320542055205620572058205920602061206220632064206520662067206820692070207120722073207420752076207720782079208020812082208320842085208620872088208920902091209220932094209520962097209820992100210121022103210421052106210721082109211021112112211321142115211621172118211921202121212221232124212521262127212821292130213121322133213421352136213721382139214021412142214321442145214621472148214921502151215221532154215521562157215821592160216121622163216421652166216721682169217021712172217321742175217621772178217921802181218221832184218521862187218821892190219121922193219421952196219721982199220022012202220322042205220622072208220922102211221222132214221522162217221822192220222122222223222422252226222722282229223022312232223322342235223622372238223922402241224222432244224522462247224822492250225122522253225422552256225722582259226022612262226322642265226622672268226922702271227222732274227522762277227822792280228122822283228422852286228722882289229022912292229322942295229622972298229923002301230223032304230523062307230823092310231123122313231423152316231723182319232023212322232323242325232623272328232923302331233223332334233523362337233823392340234123422343234423452346234723482349235023512352235323542355235623572358235923602361236223632364236523662367236823692370237123722373237423752376237723782379238023812382238323842385238623872388238923902391239223932394239523962397239823992400240124022403240424052406240724082409241024112412241324142415241624172418241924202421242224232424242524262427242824292430243124322433243424352436243724382439244024412442244324442445244624472448244924502451245224532454245524562457245824592460246124622463246424652466246724682469247024712472247324742475247624772478247924802481248224832484248524862487248824892490249124922493249424952496249724982499250025012502250325042505250625072508250925102511251225132514251525162517251825192520252125222523252425252526252725282529253025312532253325342535253625372538253925402541254225432544254525462547254825492550255125522553255425552556255725582559256025612562256325642565256625672568256925702571257225732574257525762577257825792580258125822583258425852586258725882589259025912592259325942595259625972598259926002601260226032604260526062607260826092610261126122613261426152616261726182619262026212622262326242625262626272628262926302631263226332634263526362637263826392640264126422643264426452646264726482649265026512652265326542655265626572658265926602661266226632664266526662667266826692670267126722673267426752676267726782679268026812682268326842685268626872688268926902691269226932694269526962697269826992700270127022703270427052706270727082709271027112712271327142715271627172718271927202721272227232724272527262727272827292730273127322733273427352736273727382739274027412742274327442745274627472748274927502751275227532754275527562757275827592760276127622763276427652766276727682769277027712772277327742775277627772778277927802781278227832784278527862787278827892790279127922793279427952796279727982799280028012802280328042805280628072808280928102811281228132814281528162817281828192820282128222823282428252826282728282829283028312832283328342835283628372838283928402841284228432844284528462847284828492850285128522853285428552856285728582859286028612862286328642865286628672868286928702871287228732874287528762877287828792880288128822883288428852886288728882889289028912892289328942895289628972898289929002901290229032904290529062907290829092910291129122913291429152916291729182919292029212922292329242925292629272928292929302931293229332934293529362937293829392940294129422943294429452946294729482949295029512952295329542955295629572958295929602961296229632964296529662967296829692970297129722973297429752976297729782979298029812982298329842985298629872988298929902991299229932994299529962997299829993000300130023003300430053006300730083009301030113012301330143015301630173018301930203021302230233024302530263027302830293030303130323033303430353036303730383039304030413042304330443045304630473048304930503051305230533054305530563057305830593060306130623063306430653066306730683069307030713072307330743075307630773078307930803081308230833084308530863087308830893090309130923093309430953096309730983099310031013102310331043105310631073108310931103111311231133114311531163117311831193120312131223123312431253126312731283129313031313132313331343135313631373138313931403141314231433144314531463147314831493150315131523153315431553156315731583159316031613162316331643165316631673168316931703171317231733174317531763177317831793180318131823183318431853186318731883189319031913192319331943195319631973198319932003201320232033204320532063207320832093210321132123213321432153216321732183219322032213222322332243225322632273228322932303231323232333234323532363237323832393240324132423243324432453246324732483249325032513252325332543255325632573258325932603261326232633264326532663267326832693270327132723273327432753276327732783279328032813282328332843285328632873288328932903291329232933294329532963297329832993300330133023303330433053306330733083309331033113312331333143315331633173318331933203321332233233324332533263327332833293330333133323333333433353336333733383339334033413342334333443345334633473348334933503351335233533354335533563357335833593360336133623363336433653366336733683369337033713372337333743375337633773378337933803381338233833384338533863387338833893390339133923393339433953396339733983399340034013402340334043405340634073408340934103411341234133414341534163417341834193420342134223423342434253426342734283429343034313432343334343435343634373438343934403441344234433444344534463447344834493450345134523453345434553456345734583459346034613462346334643465346634673468346934703471347234733474347534763477347834793480348134823483348434853486348734883489349034913492349334943495349634973498349935003501350235033504350535063507350835093510351135123513351435153516351735183519352035213522352335243525352635273528352935303531353235333534353535363537353835393540354135423543354435453546354735483549355035513552355335543555355635573558355935603561356235633564356535663567356835693570357135723573357435753576357735783579358035813582358335843585358635873588358935903591359235933594359535963597359835993600360136023603360436053606360736083609361036113612361336143615361636173618361936203621362236233624362536263627362836293630363136323633363436353636363736383639364036413642364336443645364636473648364936503651365236533654365536563657365836593660366136623663366436653666366736683669367036713672367336743675367636773678367936803681368236833684368536863687368836893690369136923693369436953696369736983699370037013702370337043705370637073708370937103711371237133714371537163717371837193720372137223723372437253726372737283729373037313732373337343735373637373738373937403741374237433744374537463747374837493750375137523753375437553756375737583759376037613762376337643765376637673768376937703771377237733774377537763777377837793780378137823783378437853786378737883789379037913792379337943795379637973798379938003801380238033804380538063807380838093810381138123813381438153816381738183819382038213822382338243825382638273828382938303831383238333834383538363837383838393840384138423843384438453846384738483849385038513852385338543855385638573858385938603861386238633864386538663867386838693870387138723873387438753876387738783879388038813882388338843885388638873888388938903891389238933894389538963897389838993900390139023903390439053906390739083909391039113912391339143915391639173918391939203921392239233924392539263927392839293930393139323933393439353936393739383939394039413942394339443945394639473948394939503951395239533954395539563957395839593960396139623963396439653966396739683969397039713972397339743975397639773978397939803981398239833984398539863987398839893990399139923993399439953996399739983999400040014002400340044005400640074008400940104011401240134014401540164017401840194020402140224023402440254026402740284029403040314032403340344035403640374038403940404041404240434044404540464047404840494050405140524053405440554056405740584059406040614062406340644065406640674068406940704071407240734074407540764077407840794080408140824083408440854086408740884089409040914092409340944095409640974098409941004101410241034104410541064107410841094110411141124113411441154116411741184119412041214122412341244125412641274128412941304131413241334134413541364137413841394140414141424143414441454146414741484149415041514152415341544155415641574158415941604161416241634164416541664167416841694170417141724173417441754176417741784179418041814182418341844185418641874188418941904191419241934194419541964197419841994200420142024203420442054206420742084209421042114212421342144215421642174218421942204221422242234224422542264227422842294230423142324233423442354236423742384239424042414242424342444245424642474248424942504251425242534254425542564257425842594260426142624263426442654266426742684269427042714272427342744275427642774278427942804281428242834284428542864287428842894290429142924293429442954296429742984299430043014302430343044305430643074308430943104311431243134314431543164317431843194320432143224323432443254326432743284329433043314332433343344335433643374338433943404341434243434344434543464347434843494350435143524353435443554356435743584359436043614362436343644365436643674368436943704371437243734374437543764377437843794380438143824383438443854386438743884389439043914392439343944395439643974398439944004401440244034404440544064407440844094410441144124413441444154416441744184419442044214422442344244425442644274428442944304431443244334434443544364437443844394440444144424443444444454446444744484449445044514452445344544455445644574458445944604461446244634464446544664467446844694470447144724473447444754476447744784479448044814482448344844485448644874488448944904491449244934494449544964497449844994500450145024503450445054506450745084509451045114512451345144515451645174518451945204521452245234524452545264527452845294530453145324533453445354536453745384539454045414542454345444545454645474548454945504551455245534554455545564557455845594560456145624563456445654566456745684569457045714572457345744575457645774578457945804581458245834584458545864587458845894590459145924593459445954596459745984599460046014602460346044605460646074608460946104611461246134614461546164617461846194620462146224623462446254626462746284629463046314632463346344635463646374638463946404641464246434644464546464647464846494650465146524653465446554656465746584659466046614662466346644665466646674668466946704671467246734674467546764677467846794680468146824683468446854686468746884689469046914692469346944695469646974698469947004701470247034704470547064707470847094710471147124713471447154716471747184719472047214722472347244725472647274728472947304731473247334734473547364737473847394740474147424743474447454746474747484749475047514752475347544755475647574758475947604761476247634764476547664767476847694770477147724773477447754776477747784779478047814782478347844785478647874788478947904791479247934794479547964797479847994800480148024803480448054806480748084809481048114812481348144815481648174818481948204821482248234824482548264827482848294830483148324833483448354836483748384839484048414842484348444845484648474848484948504851485248534854485548564857485848594860486148624863486448654866486748684869487048714872487348744875487648774878487948804881488248834884488548864887488848894890489148924893489448954896489748984899490049014902490349044905490649074908490949104911491249134914491549164917491849194920492149224923492449254926492749284929493049314932493349344935493649374938493949404941494249434944494549464947494849494950495149524953495449554956495749584959496049614962496349644965496649674968496949704971497249734974497549764977497849794980498149824983498449854986498749884989499049914992499349944995499649974998499950005001500250035004500550065007500850095010501150125013501450155016501750185019502050215022502350245025502650275028502950305031503250335034503550365037503850395040504150425043504450455046504750485049505050515052505350545055505650575058505950605061506250635064506550665067506850695070507150725073507450755076507750785079508050815082508350845085508650875088508950905091509250935094509550965097509850995100510151025103510451055106510751085109511051115112511351145115511651175118511951205121512251235124512551265127512851295130513151325133513451355136513751385139514051415142514351445145514651475148514951505151515251535154515551565157515851595160516151625163516451655166516751685169517051715172517351745175517651775178517951805181518251835184518551865187518851895190519151925193519451955196519751985199520052015202520352045205520652075208520952105211521252135214521552165217521852195220522152225223522452255226522752285229523052315232523352345235523652375238523952405241524252435244524552465247524852495250525152525253525452555256525752585259526052615262526352645265526652675268526952705271527252735274527552765277527852795280528152825283528452855286528752885289529052915292529352945295529652975298529953005301530253035304530553065307530853095310531153125313531453155316531753185319532053215322532353245325532653275328532953305331533253335334533553365337533853395340534153425343534453455346534753485349535053515352535353545355535653575358535953605361536253635364536553665367536853695370537153725373537453755376537753785379538053815382538353845385538653875388538953905391539253935394539553965397539853995400540154025403540454055406540754085409541054115412541354145415541654175418541954205421542254235424542554265427542854295430543154325433543454355436543754385439544054415442544354445445544654475448544954505451545254535454545554565457545854595460546154625463546454655466546754685469547054715472547354745475547654775478547954805481548254835484548554865487548854895490549154925493549454955496549754985499550055015502550355045505550655075508550955105511551255135514551555165517551855195520552155225523552455255526552755285529553055315532553355345535553655375538553955405541554255435544554555465547554855495550555155525553555455555556555755585559556055615562556355645565556655675568556955705571557255735574557555765577557855795580558155825583558455855586558755885589559055915592559355945595559655975598559956005601560256035604560556065607560856095610561156125613561456155616561756185619562056215622562356245625562656275628562956305631563256335634563556365637563856395640564156425643564456455646564756485649565056515652565356545655565656575658565956605661566256635664566556665667566856695670567156725673567456755676567756785679568056815682568356845685568656875688568956905691569256935694569556965697569856995700570157025703570457055706570757085709571057115712571357145715571657175718571957205721572257235724572557265727572857295730573157325733573457355736573757385739574057415742574357445745574657475748574957505751575257535754575557565757575857595760576157625763576457655766576757685769577057715772577357745775577657775778577957805781578257835784578557865787578857895790579157925793579457955796579757985799580058015802580358045805580658075808580958105811581258135814581558165817581858195820582158225823582458255826582758285829583058315832583358345835583658375838583958405841584258435844584558465847584858495850585158525853585458555856585758585859586058615862586358645865586658675868586958705871587258735874587558765877587858795880588158825883588458855886588758885889589058915892589358945895589658975898589959005901590259035904590559065907590859095910591159125913591459155916591759185919592059215922592359245925592659275928592959305931593259335934593559365937593859395940594159425943594459455946594759485949595059515952595359545955595659575958595959605961596259635964596559665967596859695970597159725973597459755976597759785979598059815982598359845985598659875988598959905991599259935994599559965997599859996000600160026003600460056006600760086009601060116012601360146015601660176018601960206021602260236024602560266027602860296030603160326033603460356036603760386039604060416042604360446045604660476048604960506051605260536054605560566057605860596060606160626063606460656066606760686069607060716072607360746075607660776078607960806081608260836084608560866087608860896090609160926093609460956096609760986099610061016102610361046105610661076108610961106111611261136114611561166117611861196120612161226123612461256126612761286129613061316132613361346135613661376138613961406141614261436144614561466147614861496150615161526153615461556156615761586159616061616162616361646165616661676168616961706171617261736174617561766177617861796180618161826183618461856186618761886189619061916192619361946195619661976198619962006201620262036204620562066207620862096210621162126213621462156216621762186219622062216222622362246225622662276228622962306231623262336234623562366237623862396240624162426243624462456246624762486249625062516252625362546255625662576258625962606261626262636264626562666267626862696270627162726273627462756276627762786279628062816282628362846285628662876288628962906291629262936294629562966297629862996300630163026303630463056306630763086309631063116312631363146315631663176318631963206321632263236324632563266327632863296330633163326333633463356336633763386339634063416342634363446345634663476348634963506351635263536354635563566357635863596360636163626363636463656366636763686369637063716372637363746375637663776378637963806381638263836384638563866387638863896390639163926393639463956396639763986399640064016402640364046405640664076408640964106411641264136414641564166417641864196420642164226423642464256426642764286429643064316432643364346435643664376438643964406441644264436444644564466447644864496450645164526453645464556456645764586459646064616462646364646465646664676468646964706471647264736474647564766477647864796480648164826483648464856486648764886489649064916492649364946495649664976498649965006501650265036504650565066507650865096510651165126513651465156516651765186519652065216522652365246525652665276528652965306531653265336534653565366537653865396540654165426543654465456546654765486549655065516552655365546555655665576558655965606561656265636564656565666567656865696570657165726573657465756576657765786579658065816582658365846585658665876588658965906591659265936594659565966597659865996600660166026603660466056606660766086609661066116612661366146615661666176618661966206621662266236624662566266627662866296630663166326633663466356636663766386639664066416642664366446645664666476648664966506651665266536654665566566657665866596660666166626663666466656666666766686669667066716672667366746675667666776678667966806681668266836684668566866687668866896690669166926693669466956696669766986699670067016702670367046705670667076708670967106711671267136714671567166717671867196720672167226723672467256726672767286729673067316732673367346735673667376738673967406741674267436744674567466747674867496750675167526753675467556756675767586759676067616762676367646765676667676768676967706771677267736774677567766777677867796780678167826783678467856786678767886789679067916792679367946795679667976798679968006801680268036804680568066807680868096810681168126813681468156816681768186819682068216822682368246825682668276828682968306831683268336834683568366837683868396840684168426843684468456846684768486849685068516852685368546855685668576858685968606861686268636864686568666867686868696870687168726873687468756876687768786879688068816882688368846885688668876888688968906891689268936894689568966897689868996900690169026903690469056906690769086909691069116912691369146915691669176918691969206921692269236924692569266927692869296930693169326933693469356936693769386939694069416942694369446945694669476948694969506951695269536954695569566957695869596960696169626963696469656966696769686969697069716972697369746975697669776978697969806981698269836984698569866987698869896990699169926993699469956996699769986999700070017002700370047005700670077008700970107011701270137014701570167017701870197020702170227023702470257026702770287029703070317032703370347035703670377038703970407041704270437044704570467047704870497050705170527053705470557056705770587059706070617062706370647065706670677068706970707071707270737074707570767077707870797080708170827083708470857086708770887089709070917092709370947095709670977098709971007101710271037104710571067107710871097110711171127113711471157116711771187119712071217122712371247125712671277128712971307131713271337134713571367137713871397140714171427143714471457146714771487149715071517152715371547155715671577158715971607161716271637164716571667167716871697170717171727173717471757176717771787179718071817182718371847185718671877188718971907191719271937194719571967197719871997200720172027203720472057206720772087209721072117212721372147215721672177218721972207221722272237224722572267227722872297230723172327233723472357236723772387239724072417242724372447245724672477248724972507251725272537254725572567257725872597260726172627263726472657266726772687269727072717272727372747275727672777278727972807281728272837284728572867287728872897290729172927293729472957296729772987299730073017302730373047305730673077308730973107311731273137314731573167317731873197320732173227323732473257326732773287329733073317332733373347335733673377338733973407341734273437344734573467347734873497350735173527353735473557356735773587359736073617362736373647365736673677368736973707371737273737374737573767377737873797380738173827383738473857386738773887389739073917392739373947395739673977398739974007401740274037404740574067407740874097410741174127413741474157416741774187419742074217422742374247425742674277428742974307431743274337434743574367437743874397440744174427443744474457446744774487449745074517452745374547455745674577458745974607461746274637464746574667467746874697470747174727473747474757476747774787479748074817482748374847485748674877488748974907491749274937494749574967497749874997500750175027503750475057506750775087509751075117512751375147515751675177518751975207521752275237524752575267527752875297530753175327533753475357536753775387539754075417542754375447545754675477548754975507551755275537554755575567557755875597560756175627563756475657566756775687569757075717572757375747575757675777578757975807581758275837584758575867587758875897590759175927593759475957596759775987599760076017602760376047605760676077608760976107611761276137614761576167617761876197620762176227623762476257626762776287629763076317632763376347635763676377638763976407641764276437644764576467647764876497650765176527653765476557656765776587659766076617662766376647665766676677668766976707671767276737674767576767677767876797680768176827683768476857686768776887689769076917692769376947695769676977698769977007701770277037704770577067707770877097710771177127713771477157716771777187719772077217722772377247725772677277728772977307731773277337734773577367737773877397740774177427743774477457746774777487749775077517752775377547755775677577758775977607761776277637764776577667767776877697770777177727773777477757776777777787779778077817782778377847785778677877788778977907791779277937794779577967797779877997800780178027803780478057806780778087809781078117812781378147815781678177818781978207821782278237824782578267827782878297830783178327833783478357836783778387839784078417842784378447845784678477848784978507851785278537854785578567857785878597860786178627863786478657866786778687869787078717872787378747875787678777878787978807881788278837884788578867887788878897890789178927893789478957896789778987899790079017902790379047905790679077908790979107911791279137914791579167917791879197920792179227923792479257926792779287929793079317932793379347935793679377938793979407941794279437944794579467947794879497950795179527953795479557956795779587959796079617962796379647965796679677968796979707971797279737974797579767977797879797980798179827983798479857986798779887989799079917992799379947995799679977998799980008001800280038004800580068007800880098010801180128013801480158016801780188019802080218022802380248025802680278028802980308031803280338034803580368037803880398040804180428043804480458046804780488049805080518052805380548055805680578058805980608061806280638064806580668067806880698070807180728073807480758076807780788079808080818082808380848085808680878088808980908091809280938094809580968097809880998100810181028103810481058106810781088109811081118112811381148115811681178118811981208121812281238124812581268127812881298130813181328133813481358136813781388139814081418142814381448145814681478148814981508151815281538154815581568157815881598160816181628163816481658166816781688169817081718172817381748175817681778178817981808181818281838184818581868187818881898190819181928193819481958196819781988199820082018202820382048205820682078208820982108211821282138214821582168217821882198220822182228223822482258226822782288229823082318232823382348235823682378238823982408241824282438244824582468247824882498250825182528253825482558256825782588259826082618262826382648265826682678268826982708271827282738274827582768277827882798280828182828283828482858286828782888289829082918292829382948295829682978298829983008301830283038304830583068307830883098310831183128313831483158316831783188319832083218322832383248325832683278328832983308331833283338334833583368337833883398340834183428343834483458346834783488349835083518352835383548355835683578358835983608361836283638364836583668367836883698370837183728373837483758376837783788379838083818382838383848385838683878388838983908391839283938394839583968397839883998400840184028403840484058406840784088409841084118412841384148415841684178418841984208421842284238424842584268427842884298430843184328433843484358436843784388439844084418442844384448445844684478448844984508451845284538454845584568457845884598460846184628463846484658466846784688469847084718472847384748475847684778478847984808481848284838484848584868487848884898490849184928493849484958496849784988499850085018502850385048505850685078508850985108511851285138514851585168517851885198520852185228523852485258526852785288529853085318532853385348535853685378538853985408541854285438544854585468547854885498550855185528553855485558556855785588559856085618562856385648565856685678568856985708571857285738574857585768577857885798580858185828583858485858586858785888589859085918592859385948595859685978598859986008601860286038604860586068607860886098610861186128613861486158616861786188619862086218622862386248625862686278628862986308631863286338634863586368637863886398640864186428643864486458646864786488649865086518652865386548655865686578658865986608661866286638664866586668667866886698670867186728673867486758676867786788679868086818682868386848685868686878688868986908691869286938694869586968697869886998700870187028703870487058706870787088709871087118712871387148715871687178718871987208721872287238724872587268727872887298730873187328733873487358736873787388739874087418742874387448745874687478748874987508751875287538754875587568757875887598760876187628763876487658766876787688769877087718772877387748775877687778778877987808781878287838784878587868787878887898790879187928793879487958796879787988799880088018802880388048805880688078808880988108811881288138814881588168817881888198820882188228823882488258826882788288829883088318832883388348835883688378838883988408841884288438844884588468847884888498850885188528853885488558856885788588859886088618862886388648865886688678868886988708871887288738874887588768877887888798880888188828883888488858886888788888889889088918892889388948895889688978898889989008901890289038904890589068907890889098910891189128913891489158916891789188919892089218922892389248925892689278928892989308931893289338934893589368937893889398940894189428943894489458946894789488949895089518952895389548955895689578958895989608961896289638964896589668967896889698970897189728973897489758976897789788979898089818982898389848985898689878988898989908991899289938994899589968997899889999000900190029003900490059006900790089009901090119012901390149015901690179018901990209021902290239024902590269027902890299030903190329033903490359036903790389039904090419042904390449045904690479048904990509051905290539054905590569057905890599060906190629063906490659066906790689069907090719072907390749075907690779078907990809081908290839084908590869087908890899090909190929093909490959096909790989099910091019102910391049105910691079108910991109111911291139114911591169117911891199120912191229123912491259126912791289129913091319132913391349135913691379138913991409141914291439144914591469147914891499150915191529153915491559156915791589159916091619162916391649165916691679168916991709171917291739174917591769177917891799180918191829183918491859186918791889189919091919192919391949195919691979198919992009201920292039204920592069207920892099210921192129213921492159216921792189219922092219222922392249225922692279228922992309231923292339234923592369237923892399240924192429243924492459246924792489249925092519252925392549255925692579258925992609261926292639264926592669267926892699270927192729273927492759276927792789279928092819282928392849285928692879288928992909291929292939294929592969297929892999300930193029303930493059306930793089309931093119312931393149315931693179318931993209321932293239324932593269327932893299330933193329333933493359336933793389339934093419342934393449345934693479348934993509351935293539354935593569357935893599360936193629363936493659366936793689369937093719372937393749375937693779378937993809381938293839384938593869387938893899390939193929393939493959396939793989399940094019402940394049405940694079408940994109411941294139414941594169417941894199420942194229423942494259426942794289429943094319432943394349435943694379438943994409441944294439444944594469447944894499450945194529453945494559456945794589459946094619462946394649465946694679468946994709471947294739474947594769477947894799480948194829483948494859486948794889489949094919492949394949495949694979498949995009501950295039504950595069507950895099510951195129513951495159516951795189519952095219522952395249525952695279528952995309531953295339534953595369537953895399540954195429543954495459546954795489549955095519552955395549555955695579558955995609561956295639564956595669567956895699570957195729573957495759576957795789579958095819582958395849585958695879588958995909591959295939594959595969597959895999600960196029603960496059606960796089609961096119612961396149615961696179618961996209621962296239624962596269627962896299630963196329633963496359636963796389639964096419642964396449645964696479648964996509651965296539654965596569657965896599660966196629663966496659666966796689669967096719672967396749675967696779678967996809681968296839684968596869687968896899690969196929693969496959696969796989699970097019702970397049705970697079708970997109711971297139714971597169717971897199720972197229723972497259726972797289729973097319732973397349735973697379738973997409741974297439744974597469747974897499750975197529753975497559756975797589759976097619762976397649765976697679768976997709771977297739774977597769777977897799780978197829783978497859786978797889789979097919792979397949795979697979798979998009801980298039804980598069807980898099810981198129813981498159816981798189819982098219822982398249825982698279828982998309831983298339834983598369837983898399840984198429843984498459846984798489849985098519852985398549855985698579858985998609861986298639864986598669867986898699870987198729873987498759876987798789879988098819882988398849885988698879888988998909891989298939894989598969897989898999900990199029903990499059906990799089909991099119912991399149915991699179918991999209921992299239924992599269927992899299930993199329933993499359936993799389939994099419942994399449945994699479948994999509951995299539954995599569957995899599960996199629963996499659966996799689969997099719972997399749975997699779978997999809981998299839984998599869987998899899990999199929993999499959996999799989999100001000110002100031000410005100061000710008100091001010011100121001310014100151001610017100181001910020100211002210023100241002510026100271002810029100301003110032100331003410035100361003710038100391004010041100421004310044100451004610047100481004910050100511005210053100541005510056100571005810059100601006110062100631006410065100661006710068100691007010071100721007310074100751007610077100781007910080100811008210083100841008510086100871008810089100901009110092100931009410095100961009710098100991010010101101021010310104101051010610107101081010910110101111011210113101141011510116101171011810119101201012110122101231012410125101261012710128101291013010131101321013310134101351013610137101381013910140101411014210143101441014510146101471014810149101501015110152101531015410155101561015710158101591016010161101621016310164101651016610167101681016910170101711017210173101741017510176101771017810179101801018110182101831018410185101861018710188101891019010191101921019310194101951019610197101981019910200102011020210203102041020510206102071020810209102101021110212102131021410215102161021710218102191022010221102221022310224102251022610227102281022910230102311023210233102341023510236102371023810239102401024110242102431024410245102461024710248102491025010251102521025310254102551025610257102581025910260102611026210263102641026510266102671026810269102701027110272102731027410275102761027710278102791028010281102821028310284102851028610287102881028910290102911029210293102941029510296102971029810299103001030110302103031030410305103061030710308103091031010311103121031310314103151031610317103181031910320103211032210323103241032510326103271032810329103301033110332103331033410335103361033710338103391034010341103421034310344103451034610347103481034910350103511035210353103541035510356103571035810359103601036110362103631036410365103661036710368103691037010371103721037310374103751037610377103781037910380103811038210383103841038510386103871038810389103901039110392103931039410395103961039710398103991040010401104021040310404104051040610407104081040910410104111041210413104141041510416104171041810419104201042110422104231042410425104261042710428104291043010431104321043310434104351043610437104381043910440104411044210443104441044510446104471044810449104501045110452104531045410455104561045710458104591046010461104621046310464104651046610467104681046910470104711047210473104741047510476104771047810479104801048110482104831048410485104861048710488104891049010491104921049310494104951049610497104981049910500105011050210503105041050510506105071050810509105101051110512105131051410515105161051710518105191052010521105221052310524105251052610527105281052910530105311053210533105341053510536105371053810539105401054110542105431054410545105461054710548105491055010551105521055310554105551055610557105581055910560105611056210563105641056510566105671056810569105701057110572105731057410575105761057710578105791058010581105821058310584105851058610587105881058910590105911059210593// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (C) 2007 Oracle.  All rights reserved.
 */

#include <linux/kernel.h>
#include <linux/bio.h>
#include <linux/buffer_head.h>
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/pagemap.h>
#include <linux/highmem.h>
#include <linux/time.h>
#include <linux/init.h>
#include <linux/string.h>
#include <linux/backing-dev.h>
#include <linux/writeback.h>
#include <linux/compat.h>
#include <linux/xattr.h>
#include <linux/posix_acl.h>
#include <linux/falloc.h>
#include <linux/slab.h>
#include <linux/ratelimit.h>
#include <linux/btrfs.h>
#include <linux/blkdev.h>
#include <linux/posix_acl_xattr.h>
#include <linux/uio.h>
#include <linux/magic.h>
#include <linux/iversion.h>
#include <asm/unaligned.h>
#include "ctree.h"
#include "disk-io.h"
#include "transaction.h"
#include "btrfs_inode.h"
#include "print-tree.h"
#include "ordered-data.h"
#include "xattr.h"
#include "tree-log.h"
#include "volumes.h"
#include "compression.h"
#include "locking.h"
#include "free-space-cache.h"
#include "inode-map.h"
#include "backref.h"
#include "props.h"
#include "qgroup.h"
#include "dedupe.h"

struct btrfs_iget_args {
	struct btrfs_key *location;
	struct btrfs_root *root;
};

struct btrfs_dio_data {
	u64 reserve;
	u64 unsubmitted_oe_range_start;
	u64 unsubmitted_oe_range_end;
	int overwrite;
};

static const struct inode_operations btrfs_dir_inode_operations;
static const struct inode_operations btrfs_symlink_inode_operations;
static const struct inode_operations btrfs_dir_ro_inode_operations;
static const struct inode_operations btrfs_special_inode_operations;
static const struct inode_operations btrfs_file_inode_operations;
static const struct address_space_operations btrfs_aops;
static const struct file_operations btrfs_dir_file_operations;
static const struct extent_io_ops btrfs_extent_io_ops;

static struct kmem_cache *btrfs_inode_cachep;
struct kmem_cache *btrfs_trans_handle_cachep;
struct kmem_cache *btrfs_path_cachep;
struct kmem_cache *btrfs_free_space_cachep;

#define S_SHIFT 12
static const unsigned char btrfs_type_by_mode[S_IFMT >> S_SHIFT] = {
	[S_IFREG >> S_SHIFT]	= BTRFS_FT_REG_FILE,
	[S_IFDIR >> S_SHIFT]	= BTRFS_FT_DIR,
	[S_IFCHR >> S_SHIFT]	= BTRFS_FT_CHRDEV,
	[S_IFBLK >> S_SHIFT]	= BTRFS_FT_BLKDEV,
	[S_IFIFO >> S_SHIFT]	= BTRFS_FT_FIFO,
	[S_IFSOCK >> S_SHIFT]	= BTRFS_FT_SOCK,
	[S_IFLNK >> S_SHIFT]	= BTRFS_FT_SYMLINK,
};

static int btrfs_setsize(struct inode *inode, struct iattr *attr);
static int btrfs_truncate(struct inode *inode, bool skip_writeback);
static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent);
static noinline int cow_file_range(struct inode *inode,
				   struct page *locked_page,
				   u64 start, u64 end, u64 delalloc_end,
				   int *page_started, unsigned long *nr_written,
				   int unlock, struct btrfs_dedupe_hash *hash);
static struct extent_map *create_io_em(struct inode *inode, u64 start, u64 len,
				       u64 orig_start, u64 block_start,
				       u64 block_len, u64 orig_block_len,
				       u64 ram_bytes, int compress_type,
				       int type);

static void __endio_write_update_ordered(struct inode *inode,
					 const u64 offset, const u64 bytes,
					 const bool uptodate);

/*
 * Cleanup all submitted ordered extents in specified range to handle errors
 * from the fill_dellaloc() callback.
 *
 * NOTE: caller must ensure that when an error happens, it can not call
 * extent_clear_unlock_delalloc() to clear both the bits EXTENT_DO_ACCOUNTING
 * and EXTENT_DELALLOC simultaneously, because that causes the reserved metadata
 * to be released, which we want to happen only when finishing the ordered
 * extent (btrfs_finish_ordered_io()). Also note that the caller of the
 * fill_delalloc() callback already does proper cleanup for the first page of
 * the range, that is, it invokes the callback writepage_end_io_hook() for the
 * range of the first page.
 */
static inline void btrfs_cleanup_ordered_extents(struct inode *inode,
						 const u64 offset,
						 const u64 bytes)
{
	unsigned long index = offset >> PAGE_SHIFT;
	unsigned long end_index = (offset + bytes - 1) >> PAGE_SHIFT;
	struct page *page;

	while (index <= end_index) {
		page = find_get_page(inode->i_mapping, index);
		index++;
		if (!page)
			continue;
		ClearPagePrivate2(page);
		put_page(page);
	}
	return __endio_write_update_ordered(inode, offset + PAGE_SIZE,
					    bytes - PAGE_SIZE, false);
}

static int btrfs_dirty_inode(struct inode *inode);

#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
void btrfs_test_inode_set_ops(struct inode *inode)
{
	BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
}
#endif

static int btrfs_init_inode_security(struct btrfs_trans_handle *trans,
				     struct inode *inode,  struct inode *dir,
				     const struct qstr *qstr)
{
	int err;

	err = btrfs_init_acl(trans, inode, dir);
	if (!err)
		err = btrfs_xattr_security_init(trans, inode, dir, qstr);
	return err;
}

/*
 * this does all the hard work for inserting an inline extent into
 * the btree.  The caller should have done a btrfs_drop_extents so that
 * no overlapping inline items exist in the btree
 */
static int insert_inline_extent(struct btrfs_trans_handle *trans,
				struct btrfs_path *path, int extent_inserted,
				struct btrfs_root *root, struct inode *inode,
				u64 start, size_t size, size_t compressed_size,
				int compress_type,
				struct page **compressed_pages)
{
	struct extent_buffer *leaf;
	struct page *page = NULL;
	char *kaddr;
	unsigned long ptr;
	struct btrfs_file_extent_item *ei;
	int ret;
	size_t cur_size = size;
	unsigned long offset;

	if (compressed_size && compressed_pages)
		cur_size = compressed_size;

	inode_add_bytes(inode, size);

	if (!extent_inserted) {
		struct btrfs_key key;
		size_t datasize;

		key.objectid = btrfs_ino(BTRFS_I(inode));
		key.offset = start;
		key.type = BTRFS_EXTENT_DATA_KEY;

		datasize = btrfs_file_extent_calc_inline_size(cur_size);
		path->leave_spinning = 1;
		ret = btrfs_insert_empty_item(trans, root, path, &key,
					      datasize);
		if (ret)
			goto fail;
	}
	leaf = path->nodes[0];
	ei = btrfs_item_ptr(leaf, path->slots[0],
			    struct btrfs_file_extent_item);
	btrfs_set_file_extent_generation(leaf, ei, trans->transid);
	btrfs_set_file_extent_type(leaf, ei, BTRFS_FILE_EXTENT_INLINE);
	btrfs_set_file_extent_encryption(leaf, ei, 0);
	btrfs_set_file_extent_other_encoding(leaf, ei, 0);
	btrfs_set_file_extent_ram_bytes(leaf, ei, size);
	ptr = btrfs_file_extent_inline_start(ei);

	if (compress_type != BTRFS_COMPRESS_NONE) {
		struct page *cpage;
		int i = 0;
		while (compressed_size > 0) {
			cpage = compressed_pages[i];
			cur_size = min_t(unsigned long, compressed_size,
				       PAGE_SIZE);

			kaddr = kmap_atomic(cpage);
			write_extent_buffer(leaf, kaddr, ptr, cur_size);
			kunmap_atomic(kaddr);

			i++;
			ptr += cur_size;
			compressed_size -= cur_size;
		}
		btrfs_set_file_extent_compression(leaf, ei,
						  compress_type);
	} else {
		page = find_get_page(inode->i_mapping,
				     start >> PAGE_SHIFT);
		btrfs_set_file_extent_compression(leaf, ei, 0);
		kaddr = kmap_atomic(page);
		offset = start & (PAGE_SIZE - 1);
		write_extent_buffer(leaf, kaddr + offset, ptr, size);
		kunmap_atomic(kaddr);
		put_page(page);
	}
	btrfs_mark_buffer_dirty(leaf);
	btrfs_release_path(path);

	/*
	 * we're an inline extent, so nobody can
	 * extend the file past i_size without locking
	 * a page we already have locked.
	 *
	 * We must do any isize and inode updates
	 * before we unlock the pages.  Otherwise we
	 * could end up racing with unlink.
	 */
	BTRFS_I(inode)->disk_i_size = inode->i_size;
	ret = btrfs_update_inode(trans, root, inode);

fail:
	return ret;
}


/*
 * conditionally insert an inline extent into the file.  This
 * does the checks required to make sure the data is small enough
 * to fit as an inline extent.
 */
static noinline int cow_file_range_inline(struct inode *inode, u64 start,
					  u64 end, size_t compressed_size,
					  int compress_type,
					  struct page **compressed_pages)
{
	struct btrfs_root *root = BTRFS_I(inode)->root;
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct btrfs_trans_handle *trans;
	u64 isize = i_size_read(inode);
	u64 actual_end = min(end + 1, isize);
	u64 inline_len = actual_end - start;
	u64 aligned_end = ALIGN(end, fs_info->sectorsize);
	u64 data_len = inline_len;
	int ret;
	struct btrfs_path *path;
	int extent_inserted = 0;
	u32 extent_item_size;

	if (compressed_size)
		data_len = compressed_size;

	if (start > 0 ||
	    actual_end > fs_info->sectorsize ||
	    data_len > BTRFS_MAX_INLINE_DATA_SIZE(fs_info) ||
	    (!compressed_size &&
	    (actual_end & (fs_info->sectorsize - 1)) == 0) ||
	    end + 1 < isize ||
	    data_len > fs_info->max_inline) {
		return 1;
	}

	path = btrfs_alloc_path();
	if (!path)
		return -ENOMEM;

	trans = btrfs_join_transaction(root);
	if (IS_ERR(trans)) {
		btrfs_free_path(path);
		return PTR_ERR(trans);
	}
	trans->block_rsv = &BTRFS_I(inode)->block_rsv;

	if (compressed_size && compressed_pages)
		extent_item_size = btrfs_file_extent_calc_inline_size(
		   compressed_size);
	else
		extent_item_size = btrfs_file_extent_calc_inline_size(
		    inline_len);

	ret = __btrfs_drop_extents(trans, root, inode, path,
				   start, aligned_end, NULL,
				   1, 1, extent_item_size, &extent_inserted);
	if (ret) {
		btrfs_abort_transaction(trans, ret);
		goto out;
	}

	if (isize > actual_end)
		inline_len = min_t(u64, isize, actual_end);
	ret = insert_inline_extent(trans, path, extent_inserted,
				   root, inode, start,
				   inline_len, compressed_size,
				   compress_type, compressed_pages);
	if (ret && ret != -ENOSPC) {
		btrfs_abort_transaction(trans, ret);
		goto out;
	} else if (ret == -ENOSPC) {
		ret = 1;
		goto out;
	}

	set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &BTRFS_I(inode)->runtime_flags);
	btrfs_drop_extent_cache(BTRFS_I(inode), start, aligned_end - 1, 0);
out:
	/*
	 * Don't forget to free the reserved space, as for inlined extent
	 * it won't count as data extent, free them directly here.
	 * And at reserve time, it's always aligned to page size, so
	 * just free one page here.
	 */
	btrfs_qgroup_free_data(inode, NULL, 0, PAGE_SIZE);
	btrfs_free_path(path);
	btrfs_end_transaction(trans);
	return ret;
}

struct async_extent {
	u64 start;
	u64 ram_size;
	u64 compressed_size;
	struct page **pages;
	unsigned long nr_pages;
	int compress_type;
	struct list_head list;
};

struct async_cow {
	struct inode *inode;
	struct btrfs_root *root;
	struct page *locked_page;
	u64 start;
	u64 end;
	unsigned int write_flags;
	struct list_head extents;
	struct btrfs_work work;
};

static noinline int add_async_extent(struct async_cow *cow,
				     u64 start, u64 ram_size,
				     u64 compressed_size,
				     struct page **pages,
				     unsigned long nr_pages,
				     int compress_type)
{
	struct async_extent *async_extent;

	async_extent = kmalloc(sizeof(*async_extent), GFP_NOFS);
	BUG_ON(!async_extent); /* -ENOMEM */
	async_extent->start = start;
	async_extent->ram_size = ram_size;
	async_extent->compressed_size = compressed_size;
	async_extent->pages = pages;
	async_extent->nr_pages = nr_pages;
	async_extent->compress_type = compress_type;
	list_add_tail(&async_extent->list, &cow->extents);
	return 0;
}

static inline int inode_need_compress(struct inode *inode, u64 start, u64 end)
{
	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);

	/* force compress */
	if (btrfs_test_opt(fs_info, FORCE_COMPRESS))
		return 1;
	/* defrag ioctl */
	if (BTRFS_I(inode)->defrag_compress)
		return 1;
	/* bad compression ratios */
	if (BTRFS_I(inode)->flags & BTRFS_INODE_NOCOMPRESS)
		return 0;
	if (btrfs_test_opt(fs_info, COMPRESS) ||
	    BTRFS_I(inode)->flags & BTRFS_INODE_COMPRESS ||
	    BTRFS_I(inode)->prop_compress)
		return btrfs_compress_heuristic(inode, start, end);
	return 0;
}

static inline void inode_should_defrag(struct btrfs_inode *inode,
		u64 start, u64 end, u64 num_bytes, u64 small_write)
{
	/* If this is a small write inside eof, kick off a defrag */
	if (num_bytes < small_write &&
	    (start > 0 || end + 1 < inode->disk_i_size))
		btrfs_add_inode_defrag(NULL, inode);
}

/*
 * we create compressed extents in two phases.  The first
 * phase compresses a range of pages that have already been
 * locked (both pages and state bits are locked).
 *
 * This is done inside an ordered work queue, and the compression
 * is spread across many cpus.  The actual IO submission is step
 * two, and the ordered work queue takes care of making sure that
 * happens in the same order things were put onto the queue by
 * writepages and friends.
 *
 * If this code finds it can't get good compression, it puts an
 * entry onto the work queue to write the uncompressed bytes.  This
 * makes sure that both compressed inodes and uncompressed inodes
 * are written in the same order that the flusher thread sent them
 * down.
 */
static noinline void compress_file_range(struct inode *inode,
					struct page *locked_page,
					u64 start, u64 end,
					struct async_cow *async_cow,
					int *num_added)
{
	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
	u64 blocksize = fs_info->sectorsize;
	u64 actual_end;
	u64 isize = i_size_read(inode);
	int ret = 0;
	struct page **pages = NULL;
	unsigned long nr_pages;
	unsigned long total_compressed = 0;
	unsigned long total_in = 0;
	int i;
	int will_compress;
	int compress_type = fs_info->compress_type;
	int redirty = 0;

	inode_should_defrag(BTRFS_I(inode), start, end, end - start + 1,
			SZ_16K);

	actual_end = min_t(u64, isize, end + 1);
again:
	will_compress = 0;
	nr_pages = (end >> PAGE_SHIFT) - (start >> PAGE_SHIFT) + 1;
	BUILD_BUG_ON((BTRFS_MAX_COMPRESSED % PAGE_SIZE) != 0);
	nr_pages = min_t(unsigned long, nr_pages,
			BTRFS_MAX_COMPRESSED / PAGE_SIZE);

	/*
	 * we don't want to send crud past the end of i_size through
	 * compression, that's just a waste of CPU time.  So, if the
	 * end of the file is before the start of our current
	 * requested range of bytes, we bail out to the uncompressed
	 * cleanup code that can deal with all of this.
	 *
	 * It isn't really the fastest way to fix things, but this is a
	 * very uncommon corner.
	 */
	if (actual_end <= start)
		goto cleanup_and_bail_uncompressed;

	total_compressed = actual_end - start;

	/*
	 * skip compression for a small file range(<=blocksize) that
	 * isn't an inline extent, since it doesn't save disk space at all.
	 */
	if (total_compressed <= blocksize &&
	   (start > 0 || end + 1 < BTRFS_I(inode)->disk_i_size))
		goto cleanup_and_bail_uncompressed;

	total_compressed = min_t(unsigned long, total_compressed,
			BTRFS_MAX_UNCOMPRESSED);
	total_in = 0;
	ret = 0;

	/*
	 * we do compression for mount -o compress and when the
	 * inode has not been flagged as nocompress.  This flag can
	 * change at any time if we discover bad compression ratios.
	 */
	if (inode_need_compress(inode, start, end)) {
		WARN_ON(pages);
		pages = kcalloc(nr_pages, sizeof(struct page *), GFP_NOFS);
		if (!pages) {
			/* just bail out to the uncompressed code */
			nr_pages = 0;
			goto cont;
		}

		if (BTRFS_I(inode)->defrag_compress)
			compress_type = BTRFS_I(inode)->defrag_compress;
		else if (BTRFS_I(inode)->prop_compress)
			compress_type = BTRFS_I(inode)->prop_compress;

		/*
		 * we need to call clear_page_dirty_for_io on each
		 * page in the range.  Otherwise applications with the file
		 * mmap'd can wander in and change the page contents while
		 * we are compressing them.
		 *
		 * If the compression fails for any reason, we set the pages
		 * dirty again later on.
		 *
		 * Note that the remaining part is redirtied, the start pointer
		 * has moved, the end is the original one.
		 */
		if (!redirty) {
			extent_range_clear_dirty_for_io(inode, start, end);
			redirty = 1;
		}

		/* Compression level is applied here and only here */
		ret = btrfs_compress_pages(
			compress_type | (fs_info->compress_level << 4),
					   inode->i_mapping, start,
					   pages,
					   &nr_pages,
					   &total_in,
					   &total_compressed);

		if (!ret) {
			unsigned long offset = total_compressed &
				(PAGE_SIZE - 1);
			struct page *page = pages[nr_pages - 1];
			char *kaddr;

			/* zero the tail end of the last page, we might be
			 * sending it down to disk
			 */
			if (offset) {
				kaddr = kmap_atomic(page);
				memset(kaddr + offset, 0,
				       PAGE_SIZE - offset);
				kunmap_atomic(kaddr);
			}
			will_compress = 1;
		}
	}
cont:
	if (start == 0) {
		/* lets try to make an inline extent */
		if (ret || total_in < actual_end) {
			/* we didn't compress the entire range, try
			 * to make an uncompressed inline extent.
			 */
			ret = cow_file_range_inline(inode, start, end, 0,
						    BTRFS_COMPRESS_NONE, NULL);
		} else {
			/* try making a compressed inline extent */
			ret = cow_file_range_inline(inode, start, end,
						    total_compressed,
						    compress_type, pages);
		}
		if (ret <= 0) {
			unsigned long clear_flags = EXTENT_DELALLOC |
				EXTENT_DELALLOC_NEW | EXTENT_DEFRAG |
				EXTENT_DO_ACCOUNTING;
			unsigned long page_error_op;

			page_error_op = ret < 0 ? PAGE_SET_ERROR : 0;

			/*
			 * inline extent creation worked or returned error,
			 * we don't need to create any more async work items.
			 * Unlock and free up our temp pages.
			 *
			 * We use DO_ACCOUNTING here because we need the
			 * delalloc_release_metadata to be done _after_ we drop
			 * our outstanding extent for clearing delalloc for this
			 * range.
			 */
			extent_clear_unlock_delalloc(inode, start, end, end,
						     NULL, clear_flags,
						     PAGE_UNLOCK |
						     PAGE_CLEAR_DIRTY |
						     PAGE_SET_WRITEBACK |
						     page_error_op |
						     PAGE_END_WRITEBACK);
			goto free_pages_out;
		}
	}

	if (will_compress) {
		/*
		 * we aren't doing an inline extent round the compressed size
		 * up to a block size boundary so the allocator does sane
		 * things
		 */
		total_compressed = ALIGN(total_compressed, blocksize);

		/*
		 * one last check to make sure the compression is really a
		 * win, compare the page count read with the blocks on disk,
		 * compression must free at least one sector size
		 */
		total_in = ALIGN(total_in, PAGE_SIZE);
		if (total_compressed + blocksize <= total_in) {
			*num_added += 1;

			/*
			 * The async work queues will take care of doing actual
			 * allocation on disk for these compressed pages, and
			 * will submit them to the elevator.
			 */
			add_async_extent(async_cow, start, total_in,
					total_compressed, pages, nr_pages,
					compress_type);

			if (start + total_in < end) {
				start += total_in;
				pages = NULL;
				cond_resched();
				goto again;
			}
			return;
		}
	}
	if (pages) {
		/*
		 * the compression code ran but failed to make things smaller,
		 * free any pages it allocated and our page pointer array
		 */
		for (i = 0; i < nr_pages; i++) {
			WARN_ON(pages[i]->mapping);
			put_page(pages[i]);
		}
		kfree(pages);
		pages = NULL;
		total_compressed = 0;
		nr_pages = 0;

		/* flag the file so we don't compress in the future */
		if (!btrfs_test_opt(fs_info, FORCE_COMPRESS) &&
		    !(BTRFS_I(inode)->prop_compress)) {
			BTRFS_I(inode)->flags |= BTRFS_INODE_NOCOMPRESS;
		}
	}
cleanup_and_bail_uncompressed:
	/*
	 * No compression, but we still need to write the pages in the file
	 * we've been given so far.  redirty the locked page if it corresponds
	 * to our extent and set things up for the async work queue to run
	 * cow_file_range to do the normal delalloc dance.
	 */
	if (page_offset(locked_page) >= start &&
	    page_offset(locked_page) <= end)
		__set_page_dirty_nobuffers(locked_page);
		/* unlocked later on in the async handlers */

	if (redirty)
		extent_range_redirty_for_io(inode, start, end);
	add_async_extent(async_cow, start, end - start + 1, 0, NULL, 0,
			 BTRFS_COMPRESS_NONE);
	*num_added += 1;

	return;

free_pages_out:
	for (i = 0; i < nr_pages; i++) {
		WARN_ON(pages[i]->mapping);
		put_page(pages[i]);
	}
	kfree(pages);
}

static void free_async_extent_pages(struct async_extent *async_extent)
{
	int i;

	if (!async_extent->pages)
		return;

	for (i = 0; i < async_extent->nr_pages; i++) {
		WARN_ON(async_extent->pages[i]->mapping);
		put_page(async_extent->pages[i]);
	}
	kfree(async_extent->pages);
	async_extent->nr_pages = 0;
	async_extent->pages = NULL;
}

/*
 * phase two of compressed writeback.  This is the ordered portion
 * of the code, which only gets called in the order the work was
 * queued.  We walk all the async extents created by compress_file_range
 * and send them down to the disk.
 */
static noinline void submit_compressed_extents(struct inode *inode,
					      struct async_cow *async_cow)
{
	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
	struct async_extent *async_extent;
	u64 alloc_hint = 0;
	struct btrfs_key ins;
	struct extent_map *em;
	struct btrfs_root *root = BTRFS_I(inode)->root;
	struct extent_io_tree *io_tree;
	int ret = 0;

again:
	while (!list_empty(&async_cow->extents)) {
		async_extent = list_entry(async_cow->extents.next,
					  struct async_extent, list);
		list_del(&async_extent->list);

		io_tree = &BTRFS_I(inode)->io_tree;

retry:
		/* did the compression code fall back to uncompressed IO? */
		if (!async_extent->pages) {
			int page_started = 0;
			unsigned long nr_written = 0;

			lock_extent(io_tree, async_extent->start,
					 async_extent->start +
					 async_extent->ram_size - 1);

			/* allocate blocks */
			ret = cow_file_range(inode, async_cow->locked_page,
					     async_extent->start,
					     async_extent->start +
					     async_extent->ram_size - 1,
					     async_extent->start +
					     async_extent->ram_size - 1,
					     &page_started, &nr_written, 0,
					     NULL);

			/* JDM XXX */

			/*
			 * if page_started, cow_file_range inserted an
			 * inline extent and took care of all the unlocking
			 * and IO for us.  Otherwise, we need to submit
			 * all those pages down to the drive.
			 */
			if (!page_started && !ret)
				extent_write_locked_range(inode,
						  async_extent->start,
						  async_extent->start +
						  async_extent->ram_size - 1,
						  WB_SYNC_ALL);
			else if (ret)
				unlock_page(async_cow->locked_page);
			kfree(async_extent);
			cond_resched();
			continue;
		}

		lock_extent(io_tree, async_extent->start,
			    async_extent->start + async_extent->ram_size - 1);

		ret = btrfs_reserve_extent(root, async_extent->ram_size,
					   async_extent->compressed_size,
					   async_extent->compressed_size,
					   0, alloc_hint, &ins, 1, 1);
		if (ret) {
			free_async_extent_pages(async_extent);

			if (ret == -ENOSPC) {
				unlock_extent(io_tree, async_extent->start,
					      async_extent->start +
					      async_extent->ram_size - 1);

				/*
				 * we need to redirty the pages if we decide to
				 * fallback to uncompressed IO, otherwise we
				 * will not submit these pages down to lower
				 * layers.
				 */
				extent_range_redirty_for_io(inode,
						async_extent->start,
						async_extent->start +
						async_extent->ram_size - 1);

				goto retry;
			}
			goto out_free;
		}
		/*
		 * here we're doing allocation and writeback of the
		 * compressed pages
		 */
		em = create_io_em(inode, async_extent->start,
				  async_extent->ram_size, /* len */
				  async_extent->start, /* orig_start */
				  ins.objectid, /* block_start */
				  ins.offset, /* block_len */
				  ins.offset, /* orig_block_len */
				  async_extent->ram_size, /* ram_bytes */
				  async_extent->compress_type,
				  BTRFS_ORDERED_COMPRESSED);
		if (IS_ERR(em))
			/* ret value is not necessary due to void function */
			goto out_free_reserve;
		free_extent_map(em);

		ret = btrfs_add_ordered_extent_compress(inode,
						async_extent->start,
						ins.objectid,
						async_extent->ram_size,
						ins.offset,
						BTRFS_ORDERED_COMPRESSED,
						async_extent->compress_type);
		if (ret) {
			btrfs_drop_extent_cache(BTRFS_I(inode),
						async_extent->start,
						async_extent->start +
						async_extent->ram_size - 1, 0);
			goto out_free_reserve;
		}
		btrfs_dec_block_group_reservations(fs_info, ins.objectid);

		/*
		 * clear dirty, set writeback and unlock the pages.
		 */
		extent_clear_unlock_delalloc(inode, async_extent->start,
				async_extent->start +
				async_extent->ram_size - 1,
				async_extent->start +
				async_extent->ram_size - 1,
				NULL, EXTENT_LOCKED | EXTENT_DELALLOC,
				PAGE_UNLOCK | PAGE_CLEAR_DIRTY |
				PAGE_SET_WRITEBACK);
		if (btrfs_submit_compressed_write(inode,
				    async_extent->start,
				    async_extent->ram_size,
				    ins.objectid,
				    ins.offset, async_extent->pages,
				    async_extent->nr_pages,
				    async_cow->write_flags)) {
			struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree;
			struct page *p = async_extent->pages[0];
			const u64 start = async_extent->start;
			const u64 end = start + async_extent->ram_size - 1;

			p->mapping = inode->i_mapping;
			tree->ops->writepage_end_io_hook(p, start, end,
							 NULL, 0);
			p->mapping = NULL;
			extent_clear_unlock_delalloc(inode, start, end, end,
						     NULL, 0,
						     PAGE_END_WRITEBACK |
						     PAGE_SET_ERROR);
			free_async_extent_pages(async_extent);
		}
		alloc_hint = ins.objectid + ins.offset;
		kfree(async_extent);
		cond_resched();
	}
	return;
out_free_reserve:
	btrfs_dec_block_group_reservations(fs_info, ins.objectid);
	btrfs_free_reserved_extent(fs_info, ins.objectid, ins.offset, 1);
out_free:
	extent_clear_unlock_delalloc(inode, async_extent->start,
				     async_extent->start +
				     async_extent->ram_size - 1,
				     async_extent->start +
				     async_extent->ram_size - 1,
				     NULL, EXTENT_LOCKED | EXTENT_DELALLOC |
				     EXTENT_DELALLOC_NEW |
				     EXTENT_DEFRAG | EXTENT_DO_ACCOUNTING,
				     PAGE_UNLOCK | PAGE_CLEAR_DIRTY |
				     PAGE_SET_WRITEBACK | PAGE_END_WRITEBACK |
				     PAGE_SET_ERROR);
	free_async_extent_pages(async_extent);
	kfree(async_extent);
	goto again;
}

static u64 get_extent_allocation_hint(struct inode *inode, u64 start,
				      u64 num_bytes)
{
	struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
	struct extent_map *em;
	u64 alloc_hint = 0;

	read_lock(&em_tree->lock);
	em = search_extent_mapping(em_tree, start, num_bytes);
	if (em) {
		/*
		 * if block start isn't an actual block number then find the
		 * first block in this inode and use that as a hint.  If that
		 * block is also bogus then just don't worry about it.
		 */
		if (em->block_start >= EXTENT_MAP_LAST_BYTE) {
			free_extent_map(em);
			em = search_extent_mapping(em_tree, 0, 0);
			if (em && em->block_start < EXTENT_MAP_LAST_BYTE)
				alloc_hint = em->block_start;
			if (em)
				free_extent_map(em);
		} else {
			alloc_hint = em->block_start;
			free_extent_map(em);
		}
	}
	read_unlock(&em_tree->lock);

	return alloc_hint;
}

/*
 * when extent_io.c finds a delayed allocation range in the file,
 * the call backs end up in this code.  The basic idea is to
 * allocate extents on disk for the range, and create ordered data structs
 * in ram to track those extents.
 *
 * locked_page is the page that writepage had locked already.  We use
 * it to make sure we don't do extra locks or unlocks.
 *
 * *page_started is set to one if we unlock locked_page and do everything
 * required to start IO on it.  It may be clean and already done with
 * IO when we return.
 */
static noinline int cow_file_range(struct inode *inode,
				   struct page *locked_page,
				   u64 start, u64 end, u64 delalloc_end,
				   int *page_started, unsigned long *nr_written,
				   int unlock, struct btrfs_dedupe_hash *hash)
{
	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
	struct btrfs_root *root = BTRFS_I(inode)->root;
	u64 alloc_hint = 0;
	u64 num_bytes;
	unsigned long ram_size;
	u64 cur_alloc_size = 0;
	u64 blocksize = fs_info->sectorsize;
	struct btrfs_key ins;
	struct extent_map *em;
	unsigned clear_bits;
	unsigned long page_ops;
	bool extent_reserved = false;
	int ret = 0;

	if (btrfs_is_free_space_inode(BTRFS_I(inode))) {
		WARN_ON_ONCE(1);
		ret = -EINVAL;
		goto out_unlock;
	}

	num_bytes = ALIGN(end - start + 1, blocksize);
	num_bytes = max(blocksize,  num_bytes);
	ASSERT(num_bytes <= btrfs_super_total_bytes(fs_info->super_copy));

	inode_should_defrag(BTRFS_I(inode), start, end, num_bytes, SZ_64K);

	if (start == 0) {
		/* lets try to make an inline extent */
		ret = cow_file_range_inline(inode, start, end, 0,
					    BTRFS_COMPRESS_NONE, NULL);
		if (ret == 0) {
			/*
			 * We use DO_ACCOUNTING here because we need the
			 * delalloc_release_metadata to be run _after_ we drop
			 * our outstanding extent for clearing delalloc for this
			 * range.
			 */
			extent_clear_unlock_delalloc(inode, start, end,
				     delalloc_end, NULL,
				     EXTENT_LOCKED | EXTENT_DELALLOC |
				     EXTENT_DELALLOC_NEW | EXTENT_DEFRAG |
				     EXTENT_DO_ACCOUNTING, PAGE_UNLOCK |
				     PAGE_CLEAR_DIRTY | PAGE_SET_WRITEBACK |
				     PAGE_END_WRITEBACK);
			*nr_written = *nr_written +
			     (end - start + PAGE_SIZE) / PAGE_SIZE;
			*page_started = 1;
			goto out;
		} else if (ret < 0) {
			goto out_unlock;
		}
	}

	alloc_hint = get_extent_allocation_hint(inode, start, num_bytes);
	btrfs_drop_extent_cache(BTRFS_I(inode), start,
			start + num_bytes - 1, 0);

	while (num_bytes > 0) {
		cur_alloc_size = num_bytes;
		ret = btrfs_reserve_extent(root, cur_alloc_size, cur_alloc_size,
					   fs_info->sectorsize, 0, alloc_hint,
					   &ins, 1, 1);
		if (ret < 0)
			goto out_unlock;
		cur_alloc_size = ins.offset;
		extent_reserved = true;

		ram_size = ins.offset;
		em = create_io_em(inode, start, ins.offset, /* len */
				  start, /* orig_start */
				  ins.objectid, /* block_start */
				  ins.offset, /* block_len */
				  ins.offset, /* orig_block_len */
				  ram_size, /* ram_bytes */
				  BTRFS_COMPRESS_NONE, /* compress_type */
				  BTRFS_ORDERED_REGULAR /* type */);
		if (IS_ERR(em)) {
			ret = PTR_ERR(em);
			goto out_reserve;
		}
		free_extent_map(em);

		ret = btrfs_add_ordered_extent(inode, start, ins.objectid,
					       ram_size, cur_alloc_size, 0);
		if (ret)
			goto out_drop_extent_cache;

		if (root->root_key.objectid ==
		    BTRFS_DATA_RELOC_TREE_OBJECTID) {
			ret = btrfs_reloc_clone_csums(inode, start,
						      cur_alloc_size);
			/*
			 * Only drop cache here, and process as normal.
			 *
			 * We must not allow extent_clear_unlock_delalloc()
			 * at out_unlock label to free meta of this ordered
			 * extent, as its meta should be freed by
			 * btrfs_finish_ordered_io().
			 *
			 * So we must continue until @start is increased to
			 * skip current ordered extent.
			 */
			if (ret)
				btrfs_drop_extent_cache(BTRFS_I(inode), start,
						start + ram_size - 1, 0);
		}

		btrfs_dec_block_group_reservations(fs_info, ins.objectid);

		/* we're not doing compressed IO, don't unlock the first
		 * page (which the caller expects to stay locked), don't
		 * clear any dirty bits and don't set any writeback bits
		 *
		 * Do set the Private2 bit so we know this page was properly
		 * setup for writepage
		 */
		page_ops = unlock ? PAGE_UNLOCK : 0;
		page_ops |= PAGE_SET_PRIVATE2;

		extent_clear_unlock_delalloc(inode, start,
					     start + ram_size - 1,
					     delalloc_end, locked_page,
					     EXTENT_LOCKED | EXTENT_DELALLOC,
					     page_ops);
		if (num_bytes < cur_alloc_size)
			num_bytes = 0;
		else
			num_bytes -= cur_alloc_size;
		alloc_hint = ins.objectid + ins.offset;
		start += cur_alloc_size;
		extent_reserved = false;

		/*
		 * btrfs_reloc_clone_csums() error, since start is increased
		 * extent_clear_unlock_delalloc() at out_unlock label won't
		 * free metadata of current ordered extent, we're OK to exit.
		 */
		if (ret)
			goto out_unlock;
	}
out:
	return ret;

out_drop_extent_cache:
	btrfs_drop_extent_cache(BTRFS_I(inode), start, start + ram_size - 1, 0);
out_reserve:
	btrfs_dec_block_group_reservations(fs_info, ins.objectid);
	btrfs_free_reserved_extent(fs_info, ins.objectid, ins.offset, 1);
out_unlock:
	clear_bits = EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_DELALLOC_NEW |
		EXTENT_DEFRAG | EXTENT_CLEAR_META_RESV;
	page_ops = PAGE_UNLOCK | PAGE_CLEAR_DIRTY | PAGE_SET_WRITEBACK |
		PAGE_END_WRITEBACK;
	/*
	 * If we reserved an extent for our delalloc range (or a subrange) and
	 * failed to create the respective ordered extent, then it means that
	 * when we reserved the extent we decremented the extent's size from
	 * the data space_info's bytes_may_use counter and incremented the
	 * space_info's bytes_reserved counter by the same amount. We must make
	 * sure extent_clear_unlock_delalloc() does not try to decrement again
	 * the data space_info's bytes_may_use counter, therefore we do not pass
	 * it the flag EXTENT_CLEAR_DATA_RESV.
	 */
	if (extent_reserved) {
		extent_clear_unlock_delalloc(inode, start,
					     start + cur_alloc_size,
					     start + cur_alloc_size,
					     locked_page,
					     clear_bits,
					     page_ops);
		start += cur_alloc_size;
		if (start >= end)
			goto out;
	}
	extent_clear_unlock_delalloc(inode, start, end, delalloc_end,
				     locked_page,
				     clear_bits | EXTENT_CLEAR_DATA_RESV,
				     page_ops);
	goto out;
}

/*
 * work queue call back to started compression on a file and pages
 */
static noinline void async_cow_start(struct btrfs_work *work)
{
	struct async_cow *async_cow;
	int num_added = 0;
	async_cow = container_of(work, struct async_cow, work);

	compress_file_range(async_cow->inode, async_cow->locked_page,
			    async_cow->start, async_cow->end, async_cow,
			    &num_added);
	if (num_added == 0) {
		btrfs_add_delayed_iput(async_cow->inode);
		async_cow->inode = NULL;
	}
}

/*
 * work queue call back to submit previously compressed pages
 */
static noinline void async_cow_submit(struct btrfs_work *work)
{
	struct btrfs_fs_info *fs_info;
	struct async_cow *async_cow;
	struct btrfs_root *root;
	unsigned long nr_pages;

	async_cow = container_of(work, struct async_cow, work);

	root = async_cow->root;
	fs_info = root->fs_info;
	nr_pages = (async_cow->end - async_cow->start + PAGE_SIZE) >>
		PAGE_SHIFT;

	/* atomic_sub_return implies a barrier */
	if (atomic_sub_return(nr_pages, &fs_info->async_delalloc_pages) <
	    5 * SZ_1M)
		cond_wake_up_nomb(&fs_info->async_submit_wait);

	if (async_cow->inode)
		submit_compressed_extents(async_cow->inode, async_cow);
}

static noinline void async_cow_free(struct btrfs_work *work)
{
	struct async_cow *async_cow;
	async_cow = container_of(work, struct async_cow, work);
	if (async_cow->inode)
		btrfs_add_delayed_iput(async_cow->inode);
	kfree(async_cow);
}

static int cow_file_range_async(struct inode *inode, struct page *locked_page,
				u64 start, u64 end, int *page_started,
				unsigned long *nr_written,
				unsigned int write_flags)
{
	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
	struct async_cow *async_cow;
	struct btrfs_root *root = BTRFS_I(inode)->root;
	unsigned long nr_pages;
	u64 cur_end;

	clear_extent_bit(&BTRFS_I(inode)->io_tree, start, end, EXTENT_LOCKED,
			 1, 0, NULL);
	while (start < end) {
		async_cow = kmalloc(sizeof(*async_cow), GFP_NOFS);
		BUG_ON(!async_cow); /* -ENOMEM */
		async_cow->inode = igrab(inode);
		async_cow->root = root;
		async_cow->locked_page = locked_page;
		async_cow->start = start;
		async_cow->write_flags = write_flags;

		if (BTRFS_I(inode)->flags & BTRFS_INODE_NOCOMPRESS &&
		    !btrfs_test_opt(fs_info, FORCE_COMPRESS))
			cur_end = end;
		else
			cur_end = min(end, start + SZ_512K - 1);

		async_cow->end = cur_end;
		INIT_LIST_HEAD(&async_cow->extents);

		btrfs_init_work(&async_cow->work,
				btrfs_delalloc_helper,
				async_cow_start, async_cow_submit,
				async_cow_free);

		nr_pages = (cur_end - start + PAGE_SIZE) >>
			PAGE_SHIFT;
		atomic_add(nr_pages, &fs_info->async_delalloc_pages);

		btrfs_queue_work(fs_info->delalloc_workers, &async_cow->work);

		*nr_written += nr_pages;
		start = cur_end + 1;
	}
	*page_started = 1;
	return 0;
}

static noinline int csum_exist_in_range(struct btrfs_fs_info *fs_info,
					u64 bytenr, u64 num_bytes)
{
	int ret;
	struct btrfs_ordered_sum *sums;
	LIST_HEAD(list);

	ret = btrfs_lookup_csums_range(fs_info->csum_root, bytenr,
				       bytenr + num_bytes - 1, &list, 0);
	if (ret == 0 && list_empty(&list))
		return 0;

	while (!list_empty(&list)) {
		sums = list_entry(list.next, struct btrfs_ordered_sum, list);
		list_del(&sums->list);
		kfree(sums);
	}
	if (ret < 0)
		return ret;
	return 1;
}

/*
 * when nowcow writeback call back.  This checks for snapshots or COW copies
 * of the extents that exist in the file, and COWs the file as required.
 *
 * If no cow copies or snapshots exist, we write directly to the existing
 * blocks on disk
 */
static noinline int run_delalloc_nocow(struct inode *inode,
				       struct page *locked_page,
			      u64 start, u64 end, int *page_started, int force,
			      unsigned long *nr_written)
{
	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
	struct btrfs_root *root = BTRFS_I(inode)->root;
	struct extent_buffer *leaf;
	struct btrfs_path *path;
	struct btrfs_file_extent_item *fi;
	struct btrfs_key found_key;
	struct extent_map *em;
	u64 cow_start;
	u64 cur_offset;
	u64 extent_end;
	u64 extent_offset;
	u64 disk_bytenr;
	u64 num_bytes;
	u64 disk_num_bytes;
	u64 ram_bytes;
	int extent_type;
	int ret;
	int type;
	int nocow;
	int check_prev = 1;
	bool nolock;
	u64 ino = btrfs_ino(BTRFS_I(inode));

	path = btrfs_alloc_path();
	if (!path) {
		extent_clear_unlock_delalloc(inode, start, end, end,
					     locked_page,
					     EXTENT_LOCKED | EXTENT_DELALLOC |
					     EXTENT_DO_ACCOUNTING |
					     EXTENT_DEFRAG, PAGE_UNLOCK |
					     PAGE_CLEAR_DIRTY |
					     PAGE_SET_WRITEBACK |
					     PAGE_END_WRITEBACK);
		return -ENOMEM;
	}

	nolock = btrfs_is_free_space_inode(BTRFS_I(inode));

	cow_start = (u64)-1;
	cur_offset = start;
	while (1) {
		ret = btrfs_lookup_file_extent(NULL, root, path, ino,
					       cur_offset, 0);
		if (ret < 0)
			goto error;
		if (ret > 0 && path->slots[0] > 0 && check_prev) {
			leaf = path->nodes[0];
			btrfs_item_key_to_cpu(leaf, &found_key,
					      path->slots[0] - 1);
			if (found_key.objectid == ino &&
			    found_key.type == BTRFS_EXTENT_DATA_KEY)
				path->slots[0]--;
		}
		check_prev = 0;
next_slot:
		leaf = path->nodes[0];
		if (path->slots[0] >= btrfs_header_nritems(leaf)) {
			ret = btrfs_next_leaf(root, path);
			if (ret < 0) {
				if (cow_start != (u64)-1)
					cur_offset = cow_start;
				goto error;
			}
			if (ret > 0)
				break;
			leaf = path->nodes[0];
		}

		nocow = 0;
		disk_bytenr = 0;
		num_bytes = 0;
		btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);

		if (found_key.objectid > ino)
			break;
		if (WARN_ON_ONCE(found_key.objectid < ino) ||
		    found_key.type < BTRFS_EXTENT_DATA_KEY) {
			path->slots[0]++;
			goto next_slot;
		}
		if (found_key.type > BTRFS_EXTENT_DATA_KEY ||
		    found_key.offset > end)
			break;

		if (found_key.offset > cur_offset) {
			extent_end = found_key.offset;
			extent_type = 0;
			goto out_check;
		}

		fi = btrfs_item_ptr(leaf, path->slots[0],
				    struct btrfs_file_extent_item);
		extent_type = btrfs_file_extent_type(leaf, fi);

		ram_bytes = btrfs_file_extent_ram_bytes(leaf, fi);
		if (extent_type == BTRFS_FILE_EXTENT_REG ||
		    extent_type == BTRFS_FILE_EXTENT_PREALLOC) {
			disk_bytenr = btrfs_file_extent_disk_bytenr(leaf, fi);
			extent_offset = btrfs_file_extent_offset(leaf, fi);
			extent_end = found_key.offset +
				btrfs_file_extent_num_bytes(leaf, fi);
			disk_num_bytes =
				btrfs_file_extent_disk_num_bytes(leaf, fi);
			if (extent_end <= start) {
				path->slots[0]++;
				goto next_slot;
			}
			if (disk_bytenr == 0)
				goto out_check;
			if (btrfs_file_extent_compression(leaf, fi) ||
			    btrfs_file_extent_encryption(leaf, fi) ||
			    btrfs_file_extent_other_encoding(leaf, fi))
				goto out_check;
			/*
			 * Do the same check as in btrfs_cross_ref_exist but
			 * without the unnecessary search.
			 */
			if (btrfs_file_extent_generation(leaf, fi) <=
			    btrfs_root_last_snapshot(&root->root_item))
				goto out_check;
			if (extent_type == BTRFS_FILE_EXTENT_REG && !force)
				goto out_check;
			if (btrfs_extent_readonly(fs_info, disk_bytenr))
				goto out_check;
			ret = btrfs_cross_ref_exist(root, ino,
						    found_key.offset -
						    extent_offset, disk_bytenr);
			if (ret) {
				/*
				 * ret could be -EIO if the above fails to read
				 * metadata.
				 */
				if (ret < 0) {
					if (cow_start != (u64)-1)
						cur_offset = cow_start;
					goto error;
				}

				WARN_ON_ONCE(nolock);
				goto out_check;
			}
			disk_bytenr += extent_offset;
			disk_bytenr += cur_offset - found_key.offset;
			num_bytes = min(end + 1, extent_end) - cur_offset;
			/*
			 * if there are pending snapshots for this root,
			 * we fall into common COW way.
			 */
			if (!nolock && atomic_read(&root->snapshot_force_cow))
				goto out_check;
			/*
			 * force cow if csum exists in the range.
			 * this ensure that csum for a given extent are
			 * either valid or do not exist.
			 */
			ret = csum_exist_in_range(fs_info, disk_bytenr,
						  num_bytes);
			if (ret) {
				/*
				 * ret could be -EIO if the above fails to read
				 * metadata.
				 */
				if (ret < 0) {
					if (cow_start != (u64)-1)
						cur_offset = cow_start;
					goto error;
				}
				WARN_ON_ONCE(nolock);
				goto out_check;
			}
			if (!btrfs_inc_nocow_writers(fs_info, disk_bytenr))
				goto out_check;
			nocow = 1;
		} else if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
			extent_end = found_key.offset +
				btrfs_file_extent_ram_bytes(leaf, fi);
			extent_end = ALIGN(extent_end,
					   fs_info->sectorsize);
		} else {
			BUG_ON(1);
		}
out_check:
		if (extent_end <= start) {
			path->slots[0]++;
			if (nocow)
				btrfs_dec_nocow_writers(fs_info, disk_bytenr);
			goto next_slot;
		}
		if (!nocow) {
			if (cow_start == (u64)-1)
				cow_start = cur_offset;
			cur_offset = extent_end;
			if (cur_offset > end)
				break;
			path->slots[0]++;
			goto next_slot;
		}

		btrfs_release_path(path);
		if (cow_start != (u64)-1) {
			ret = cow_file_range(inode, locked_page,
					     cow_start, found_key.offset - 1,
					     end, page_started, nr_written, 1,
					     NULL);
			if (ret) {
				if (nocow)
					btrfs_dec_nocow_writers(fs_info,
								disk_bytenr);
				goto error;
			}
			cow_start = (u64)-1;
		}

		if (extent_type == BTRFS_FILE_EXTENT_PREALLOC) {
			u64 orig_start = found_key.offset - extent_offset;

			em = create_io_em(inode, cur_offset, num_bytes,
					  orig_start,
					  disk_bytenr, /* block_start */
					  num_bytes, /* block_len */
					  disk_num_bytes, /* orig_block_len */
					  ram_bytes, BTRFS_COMPRESS_NONE,
					  BTRFS_ORDERED_PREALLOC);
			if (IS_ERR(em)) {
				if (nocow)
					btrfs_dec_nocow_writers(fs_info,
								disk_bytenr);
				ret = PTR_ERR(em);
				goto error;
			}
			free_extent_map(em);
		}

		if (extent_type == BTRFS_FILE_EXTENT_PREALLOC) {
			type = BTRFS_ORDERED_PREALLOC;
		} else {
			type = BTRFS_ORDERED_NOCOW;
		}

		ret = btrfs_add_ordered_extent(inode, cur_offset, disk_bytenr,
					       num_bytes, num_bytes, type);
		if (nocow)
			btrfs_dec_nocow_writers(fs_info, disk_bytenr);
		BUG_ON(ret); /* -ENOMEM */

		if (root->root_key.objectid ==
		    BTRFS_DATA_RELOC_TREE_OBJECTID)
			/*
			 * Error handled later, as we must prevent
			 * extent_clear_unlock_delalloc() in error handler
			 * from freeing metadata of created ordered extent.
			 */
			ret = btrfs_reloc_clone_csums(inode, cur_offset,
						      num_bytes);

		extent_clear_unlock_delalloc(inode, cur_offset,
					     cur_offset + num_bytes - 1, end,
					     locked_page, EXTENT_LOCKED |
					     EXTENT_DELALLOC |
					     EXTENT_CLEAR_DATA_RESV,
					     PAGE_UNLOCK | PAGE_SET_PRIVATE2);

		cur_offset = extent_end;

		/*
		 * btrfs_reloc_clone_csums() error, now we're OK to call error
		 * handler, as metadata for created ordered extent will only
		 * be freed by btrfs_finish_ordered_io().
		 */
		if (ret)
			goto error;
		if (cur_offset > end)
			break;
	}
	btrfs_release_path(path);

	if (cur_offset <= end && cow_start == (u64)-1)
		cow_start = cur_offset;

	if (cow_start != (u64)-1) {
		cur_offset = end;
		ret = cow_file_range(inode, locked_page, cow_start, end, end,
				     page_started, nr_written, 1, NULL);
		if (ret)
			goto error;
	}

error:
	if (ret && cur_offset < end)
		extent_clear_unlock_delalloc(inode, cur_offset, end, end,
					     locked_page, EXTENT_LOCKED |
					     EXTENT_DELALLOC | EXTENT_DEFRAG |
					     EXTENT_DO_ACCOUNTING, PAGE_UNLOCK |
					     PAGE_CLEAR_DIRTY |
					     PAGE_SET_WRITEBACK |
					     PAGE_END_WRITEBACK);
	btrfs_free_path(path);
	return ret;
}

static inline int need_force_cow(struct inode *inode, u64 start, u64 end)
{

	if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW) &&
	    !(BTRFS_I(inode)->flags & BTRFS_INODE_PREALLOC))
		return 0;

	/*
	 * @defrag_bytes is a hint value, no spinlock held here,
	 * if is not zero, it means the file is defragging.
	 * Force cow if given extent needs to be defragged.
	 */
	if (BTRFS_I(inode)->defrag_bytes &&
	    test_range_bit(&BTRFS_I(inode)->io_tree, start, end,
			   EXTENT_DEFRAG, 0, NULL))
		return 1;

	return 0;
}

/*
 * extent_io.c call back to do delayed allocation processing
 */
static int run_delalloc_range(void *private_data, struct page *locked_page,
			      u64 start, u64 end, int *page_started,
			      unsigned long *nr_written,
			      struct writeback_control *wbc)
{
	struct inode *inode = private_data;
	int ret;
	int force_cow = need_force_cow(inode, start, end);
	unsigned int write_flags = wbc_to_write_flags(wbc);

	if (BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW && !force_cow) {
		ret = run_delalloc_nocow(inode, locked_page, start, end,
					 page_started, 1, nr_written);
	} else if (BTRFS_I(inode)->flags & BTRFS_INODE_PREALLOC && !force_cow) {
		ret = run_delalloc_nocow(inode, locked_page, start, end,
					 page_started, 0, nr_written);
	} else if (!inode_need_compress(inode, start, end)) {
		ret = cow_file_range(inode, locked_page, start, end, end,
				      page_started, nr_written, 1, NULL);
	} else {
		set_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
			&BTRFS_I(inode)->runtime_flags);
		ret = cow_file_range_async(inode, locked_page, start, end,
					   page_started, nr_written,
					   write_flags);
	}
	if (ret)
		btrfs_cleanup_ordered_extents(inode, start, end - start + 1);
	return ret;
}

static void btrfs_split_extent_hook(void *private_data,
				    struct extent_state *orig, u64 split)
{
	struct inode *inode = private_data;
	u64 size;

	/* not delalloc, ignore it */
	if (!(orig->state & EXTENT_DELALLOC))
		return;

	size = orig->end - orig->start + 1;
	if (size > BTRFS_MAX_EXTENT_SIZE) {
		u32 num_extents;
		u64 new_size;

		/*
		 * See the explanation in btrfs_merge_extent_hook, the same
		 * applies here, just in reverse.
		 */
		new_size = orig->end - split + 1;
		num_extents = count_max_extents(new_size);
		new_size = split - orig->start;
		num_extents += count_max_extents(new_size);
		if (count_max_extents(size) >= num_extents)
			return;
	}

	spin_lock(&BTRFS_I(inode)->lock);
	btrfs_mod_outstanding_extents(BTRFS_I(inode), 1);
	spin_unlock(&BTRFS_I(inode)->lock);
}

/*
 * extent_io.c merge_extent_hook, used to track merged delayed allocation
 * extents so we can keep track of new extents that are just merged onto old
 * extents, such as when we are doing sequential writes, so we can properly
 * account for the metadata space we'll need.
 */
static void btrfs_merge_extent_hook(void *private_data,
				    struct extent_state *new,
				    struct extent_state *other)
{
	struct inode *inode = private_data;
	u64 new_size, old_size;
	u32 num_extents;

	/* not delalloc, ignore it */
	if (!(other->state & EXTENT_DELALLOC))
		return;

	if (new->start > other->start)
		new_size = new->end - other->start + 1;
	else
		new_size = other->end - new->start + 1;

	/* we're not bigger than the max, unreserve the space and go */
	if (new_size <= BTRFS_MAX_EXTENT_SIZE) {
		spin_lock(&BTRFS_I(inode)->lock);
		btrfs_mod_outstanding_extents(BTRFS_I(inode), -1);
		spin_unlock(&BTRFS_I(inode)->lock);
		return;
	}

	/*
	 * We have to add up either side to figure out how many extents were
	 * accounted for before we merged into one big extent.  If the number of
	 * extents we accounted for is <= the amount we need for the new range
	 * then we can return, otherwise drop.  Think of it like this
	 *
	 * [ 4k][MAX_SIZE]
	 *
	 * So we've grown the extent by a MAX_SIZE extent, this would mean we
	 * need 2 outstanding extents, on one side we have 1 and the other side
	 * we have 1 so they are == and we can return.  But in this case
	 *
	 * [MAX_SIZE+4k][MAX_SIZE+4k]
	 *
	 * Each range on their own accounts for 2 extents, but merged together
	 * they are only 3 extents worth of accounting, so we need to drop in
	 * this case.
	 */
	old_size = other->end - other->start + 1;
	num_extents = count_max_extents(old_size);
	old_size = new->end - new->start + 1;
	num_extents += count_max_extents(old_size);
	if (count_max_extents(new_size) >= num_extents)
		return;

	spin_lock(&BTRFS_I(inode)->lock);
	btrfs_mod_outstanding_extents(BTRFS_I(inode), -1);
	spin_unlock(&BTRFS_I(inode)->lock);
}

static void btrfs_add_delalloc_inodes(struct btrfs_root *root,
				      struct inode *inode)
{
	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);

	spin_lock(&root->delalloc_lock);
	if (list_empty(&BTRFS_I(inode)->delalloc_inodes)) {
		list_add_tail(&BTRFS_I(inode)->delalloc_inodes,
			      &root->delalloc_inodes);
		set_bit(BTRFS_INODE_IN_DELALLOC_LIST,
			&BTRFS_I(inode)->runtime_flags);
		root->nr_delalloc_inodes++;
		if (root->nr_delalloc_inodes == 1) {
			spin_lock(&fs_info->delalloc_root_lock);
			BUG_ON(!list_empty(&root->delalloc_root));
			list_add_tail(&root->delalloc_root,
				      &fs_info->delalloc_roots);
			spin_unlock(&fs_info->delalloc_root_lock);
		}
	}
	spin_unlock(&root->delalloc_lock);
}


void __btrfs_del_delalloc_inode(struct btrfs_root *root,
				struct btrfs_inode *inode)
{
	struct btrfs_fs_info *fs_info = root->fs_info;

	if (!list_empty(&inode->delalloc_inodes)) {
		list_del_init(&inode->delalloc_inodes);
		clear_bit(BTRFS_INODE_IN_DELALLOC_LIST,
			  &inode->runtime_flags);
		root->nr_delalloc_inodes--;
		if (!root->nr_delalloc_inodes) {
			ASSERT(list_empty(&root->delalloc_inodes));
			spin_lock(&fs_info->delalloc_root_lock);
			BUG_ON(list_empty(&root->delalloc_root));
			list_del_init(&root->delalloc_root);
			spin_unlock(&fs_info->delalloc_root_lock);
		}
	}
}

static void btrfs_del_delalloc_inode(struct btrfs_root *root,
				     struct btrfs_inode *inode)
{
	spin_lock(&root->delalloc_lock);
	__btrfs_del_delalloc_inode(root, inode);
	spin_unlock(&root->delalloc_lock);
}

/*
 * extent_io.c set_bit_hook, used to track delayed allocation
 * bytes in this file, and to maintain the list of inodes that
 * have pending delalloc work to be done.
 */
static void btrfs_set_bit_hook(void *private_data,
			       struct extent_state *state, unsigned *bits)
{
	struct inode *inode = private_data;

	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);

	if ((*bits & EXTENT_DEFRAG) && !(*bits & EXTENT_DELALLOC))
		WARN_ON(1);
	/*
	 * set_bit and clear bit hooks normally require _irqsave/restore
	 * but in this case, we are only testing for the DELALLOC
	 * bit, which is only set or cleared with irqs on
	 */
	if (!(state->state & EXTENT_DELALLOC) && (*bits & EXTENT_DELALLOC)) {
		struct btrfs_root *root = BTRFS_I(inode)->root;
		u64 len = state->end + 1 - state->start;
		u32 num_extents = count_max_extents(len);
		bool do_list = !btrfs_is_free_space_inode(BTRFS_I(inode));

		spin_lock(&BTRFS_I(inode)->lock);
		btrfs_mod_outstanding_extents(BTRFS_I(inode), num_extents);
		spin_unlock(&BTRFS_I(inode)->lock);

		/* For sanity tests */
		if (btrfs_is_testing(fs_info))
			return;

		percpu_counter_add_batch(&fs_info->delalloc_bytes, len,
					 fs_info->delalloc_batch);
		spin_lock(&BTRFS_I(inode)->lock);
		BTRFS_I(inode)->delalloc_bytes += len;
		if (*bits & EXTENT_DEFRAG)
			BTRFS_I(inode)->defrag_bytes += len;
		if (do_list && !test_bit(BTRFS_INODE_IN_DELALLOC_LIST,
					 &BTRFS_I(inode)->runtime_flags))
			btrfs_add_delalloc_inodes(root, inode);
		spin_unlock(&BTRFS_I(inode)->lock);
	}

	if (!(state->state & EXTENT_DELALLOC_NEW) &&
	    (*bits & EXTENT_DELALLOC_NEW)) {
		spin_lock(&BTRFS_I(inode)->lock);
		BTRFS_I(inode)->new_delalloc_bytes += state->end + 1 -
			state->start;
		spin_unlock(&BTRFS_I(inode)->lock);
	}
}

/*
 * extent_io.c clear_bit_hook, see set_bit_hook for why
 */
static void btrfs_clear_bit_hook(void *private_data,
				 struct extent_state *state,
				 unsigned *bits)
{
	struct btrfs_inode *inode = BTRFS_I((struct inode *)private_data);
	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
	u64 len = state->end + 1 - state->start;
	u32 num_extents = count_max_extents(len);

	if ((state->state & EXTENT_DEFRAG) && (*bits & EXTENT_DEFRAG)) {
		spin_lock(&inode->lock);
		inode->defrag_bytes -= len;
		spin_unlock(&inode->lock);
	}

	/*
	 * set_bit and clear bit hooks normally require _irqsave/restore
	 * but in this case, we are only testing for the DELALLOC
	 * bit, which is only set or cleared with irqs on
	 */
	if ((state->state & EXTENT_DELALLOC) && (*bits & EXTENT_DELALLOC)) {
		struct btrfs_root *root = inode->root;
		bool do_list = !btrfs_is_free_space_inode(inode);

		spin_lock(&inode->lock);
		btrfs_mod_outstanding_extents(inode, -num_extents);
		spin_unlock(&inode->lock);

		/*
		 * We don't reserve metadata space for space cache inodes so we
		 * don't need to call dellalloc_release_metadata if there is an
		 * error.
		 */
		if (*bits & EXTENT_CLEAR_META_RESV &&
		    root != fs_info->tree_root)
			btrfs_delalloc_release_metadata(inode, len, false);

		/* For sanity tests. */
		if (btrfs_is_testing(fs_info))
			return;

		if (root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID &&
		    do_list && !(state->state & EXTENT_NORESERVE) &&
		    (*bits & EXTENT_CLEAR_DATA_RESV))
			btrfs_free_reserved_data_space_noquota(
					&inode->vfs_inode,
					state->start, len);

		percpu_counter_add_batch(&fs_info->delalloc_bytes, -len,
					 fs_info->delalloc_batch);
		spin_lock(&inode->lock);
		inode->delalloc_bytes -= len;
		if (do_list && inode->delalloc_bytes == 0 &&
		    test_bit(BTRFS_INODE_IN_DELALLOC_LIST,
					&inode->runtime_flags))
			btrfs_del_delalloc_inode(root, inode);
		spin_unlock(&inode->lock);
	}

	if ((state->state & EXTENT_DELALLOC_NEW) &&
	    (*bits & EXTENT_DELALLOC_NEW)) {
		spin_lock(&inode->lock);
		ASSERT(inode->new_delalloc_bytes >= len);
		inode->new_delalloc_bytes -= len;
		spin_unlock(&inode->lock);
	}
}

/*
 * Merge bio hook, this must check the chunk tree to make sure we don't create
 * bios that span stripes or chunks
 *
 * return 1 if page cannot be merged to bio
 * return 0 if page can be merged to bio
 * return error otherwise
 */
int btrfs_merge_bio_hook(struct page *page, unsigned long offset,
			 size_t size, struct bio *bio,
			 unsigned long bio_flags)
{
	struct inode *inode = page->mapping->host;
	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
	u64 logical = (u64)bio->bi_iter.bi_sector << 9;
	u64 length = 0;
	u64 map_length;
	int ret;

	if (bio_flags & EXTENT_BIO_COMPRESSED)
		return 0;

	length = bio->bi_iter.bi_size;
	map_length = length;
	ret = btrfs_map_block(fs_info, btrfs_op(bio), logical, &map_length,
			      NULL, 0);
	if (ret < 0)
		return ret;
	if (map_length < length + size)
		return 1;
	return 0;
}

/*
 * in order to insert checksums into the metadata in large chunks,
 * we wait until bio submission time.   All the pages in the bio are
 * checksummed and sums are attached onto the ordered extent record.
 *
 * At IO completion time the cums attached on the ordered extent record
 * are inserted into the btree
 */
static blk_status_t btrfs_submit_bio_start(void *private_data, struct bio *bio,
				    u64 bio_offset)
{
	struct inode *inode = private_data;
	blk_status_t ret = 0;

	ret = btrfs_csum_one_bio(inode, bio, 0, 0);
	BUG_ON(ret); /* -ENOMEM */
	return 0;
}

/*
 * in order to insert checksums into the metadata in large chunks,
 * we wait until bio submission time.   All the pages in the bio are
 * checksummed and sums are attached onto the ordered extent record.
 *
 * At IO completion time the cums attached on the ordered extent record
 * are inserted into the btree
 */
blk_status_t btrfs_submit_bio_done(void *private_data, struct bio *bio,
			  int mirror_num)
{
	struct inode *inode = private_data;
	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
	blk_status_t ret;

	ret = btrfs_map_bio(fs_info, bio, mirror_num, 1);
	if (ret) {
		bio->bi_status = ret;
		bio_endio(bio);
	}
	return ret;
}

/*
 * extent_io.c submission hook. This does the right thing for csum calculation
 * on write, or reading the csums from the tree before a read.
 *
 * Rules about async/sync submit,
 * a) read:				sync submit
 *
 * b) write without checksum:		sync submit
 *
 * c) write with checksum:
 *    c-1) if bio is issued by fsync:	sync submit
 *         (sync_writers != 0)
 *
 *    c-2) if root is reloc root:	sync submit
 *         (only in case of buffered IO)
 *
 *    c-3) otherwise:			async submit
 */
static blk_status_t btrfs_submit_bio_hook(void *private_data, struct bio *bio,
				 int mirror_num, unsigned long bio_flags,
				 u64 bio_offset)
{
	struct inode *inode = private_data;
	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
	struct btrfs_root *root = BTRFS_I(inode)->root;
	enum btrfs_wq_endio_type metadata = BTRFS_WQ_ENDIO_DATA;
	blk_status_t ret = 0;
	int skip_sum;
	int async = !atomic_read(&BTRFS_I(inode)->sync_writers);

	skip_sum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM;

	if (btrfs_is_free_space_inode(BTRFS_I(inode)))
		metadata = BTRFS_WQ_ENDIO_FREE_SPACE;

	if (bio_op(bio) != REQ_OP_WRITE) {
		ret = btrfs_bio_wq_end_io(fs_info, bio, metadata);
		if (ret)
			goto out;

		if (bio_flags & EXTENT_BIO_COMPRESSED) {
			ret = btrfs_submit_compressed_read(inode, bio,
							   mirror_num,
							   bio_flags);
			goto out;
		} else if (!skip_sum) {
			ret = btrfs_lookup_bio_sums(inode, bio, NULL);
			if (ret)
				goto out;
		}
		goto mapit;
	} else if (async && !skip_sum) {
		/* csum items have already been cloned */
		if (root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID)
			goto mapit;
		/* we're doing a write, do the async checksumming */
		ret = btrfs_wq_submit_bio(fs_info, bio, mirror_num, bio_flags,
					  bio_offset, inode,
					  btrfs_submit_bio_start);
		goto out;
	} else if (!skip_sum) {
		ret = btrfs_csum_one_bio(inode, bio, 0, 0);
		if (ret)
			goto out;
	}

mapit:
	ret = btrfs_map_bio(fs_info, bio, mirror_num, 0);

out:
	if (ret) {
		bio->bi_status = ret;
		bio_endio(bio);
	}
	return ret;
}

/*
 * given a list of ordered sums record them in the inode.  This happens
 * at IO completion time based on sums calculated at bio submission time.
 */
static noinline int add_pending_csums(struct btrfs_trans_handle *trans,
			     struct inode *inode, struct list_head *list)
{
	struct btrfs_ordered_sum *sum;
	int ret;

	list_for_each_entry(sum, list, list) {
		trans->adding_csums = true;
		ret = btrfs_csum_file_blocks(trans,
		       BTRFS_I(inode)->root->fs_info->csum_root, sum);
		trans->adding_csums = false;
		if (ret)
			return ret;
	}
	return 0;
}

int btrfs_set_extent_delalloc(struct inode *inode, u64 start, u64 end,
			      unsigned int extra_bits,
			      struct extent_state **cached_state, int dedupe)
{
	WARN_ON((end & (PAGE_SIZE - 1)) == 0);
	return set_extent_delalloc(&BTRFS_I(inode)->io_tree, start, end,
				   extra_bits, cached_state);
}

/* see btrfs_writepage_start_hook for details on why this is required */
struct btrfs_writepage_fixup {
	struct page *page;
	struct btrfs_work work;
};

static void btrfs_writepage_fixup_worker(struct btrfs_work *work)
{
	struct btrfs_writepage_fixup *fixup;
	struct btrfs_ordered_extent *ordered;
	struct extent_state *cached_state = NULL;
	struct extent_changeset *data_reserved = NULL;
	struct page *page;
	struct inode *inode;
	u64 page_start;
	u64 page_end;
	int ret;

	fixup = container_of(work, struct btrfs_writepage_fixup, work);
	page = fixup->page;
again:
	lock_page(page);
	if (!page->mapping || !PageDirty(page) || !PageChecked(page)) {
		ClearPageChecked(page);
		goto out_page;
	}

	inode = page->mapping->host;
	page_start = page_offset(page);
	page_end = page_offset(page) + PAGE_SIZE - 1;

	lock_extent_bits(&BTRFS_I(inode)->io_tree, page_start, page_end,
			 &cached_state);

	/* already ordered? We're done */
	if (PagePrivate2(page))
		goto out;

	ordered = btrfs_lookup_ordered_range(BTRFS_I(inode), page_start,
					PAGE_SIZE);
	if (ordered) {
		unlock_extent_cached(&BTRFS_I(inode)->io_tree, page_start,
				     page_end, &cached_state);
		unlock_page(page);
		btrfs_start_ordered_extent(inode, ordered, 1);
		btrfs_put_ordered_extent(ordered);
		goto again;
	}

	ret = btrfs_delalloc_reserve_space(inode, &data_reserved, page_start,
					   PAGE_SIZE);
	if (ret) {
		mapping_set_error(page->mapping, ret);
		end_extent_writepage(page, ret, page_start, page_end);
		ClearPageChecked(page);
		goto out;
	 }

	ret = btrfs_set_extent_delalloc(inode, page_start, page_end, 0,
					&cached_state, 0);
	if (ret) {
		mapping_set_error(page->mapping, ret);
		end_extent_writepage(page, ret, page_start, page_end);
		ClearPageChecked(page);
		goto out;
	}

	ClearPageChecked(page);
	set_page_dirty(page);
	btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE, false);
out:
	unlock_extent_cached(&BTRFS_I(inode)->io_tree, page_start, page_end,
			     &cached_state);
out_page:
	unlock_page(page);
	put_page(page);
	kfree(fixup);
	extent_changeset_free(data_reserved);
}

/*
 * There are a few paths in the higher layers of the kernel that directly
 * set the page dirty bit without asking the filesystem if it is a
 * good idea.  This causes problems because we want to make sure COW
 * properly happens and the data=ordered rules are followed.
 *
 * In our case any range that doesn't have the ORDERED bit set
 * hasn't been properly setup for IO.  We kick off an async process
 * to fix it up.  The async helper will wait for ordered extents, set
 * the delalloc bit and make it safe to write the page.
 */
static int btrfs_writepage_start_hook(struct page *page, u64 start, u64 end)
{
	struct inode *inode = page->mapping->host;
	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
	struct btrfs_writepage_fixup *fixup;

	/* this page is properly in the ordered list */
	if (TestClearPagePrivate2(page))
		return 0;

	if (PageChecked(page))
		return -EAGAIN;

	fixup = kzalloc(sizeof(*fixup), GFP_NOFS);
	if (!fixup)
		return -EAGAIN;

	SetPageChecked(page);
	get_page(page);
	btrfs_init_work(&fixup->work, btrfs_fixup_helper,
			btrfs_writepage_fixup_worker, NULL, NULL);
	fixup->page = page;
	btrfs_queue_work(fs_info->fixup_workers, &fixup->work);
	return -EBUSY;
}

static int insert_reserved_file_extent(struct btrfs_trans_handle *trans,
				       struct inode *inode, u64 file_pos,
				       u64 disk_bytenr, u64 disk_num_bytes,
				       u64 num_bytes, u64 ram_bytes,
				       u8 compression, u8 encryption,
				       u16 other_encoding, int extent_type)
{
	struct btrfs_root *root = BTRFS_I(inode)->root;
	struct btrfs_file_extent_item *fi;
	struct btrfs_path *path;
	struct extent_buffer *leaf;
	struct btrfs_key ins;
	u64 qg_released;
	int extent_inserted = 0;
	int ret;

	path = btrfs_alloc_path();
	if (!path)
		return -ENOMEM;

	/*
	 * we may be replacing one extent in the tree with another.
	 * The new extent is pinned in the extent map, and we don't want
	 * to drop it from the cache until it is completely in the btree.
	 *
	 * So, tell btrfs_drop_extents to leave this extent in the cache.
	 * the caller is expected to unpin it and allow it to be merged
	 * with the others.
	 */
	ret = __btrfs_drop_extents(trans, root, inode, path, file_pos,
				   file_pos + num_bytes, NULL, 0,
				   1, sizeof(*fi), &extent_inserted);
	if (ret)
		goto out;

	if (!extent_inserted) {
		ins.objectid = btrfs_ino(BTRFS_I(inode));
		ins.offset = file_pos;
		ins.type = BTRFS_EXTENT_DATA_KEY;

		path->leave_spinning = 1;
		ret = btrfs_insert_empty_item(trans, root, path, &ins,
					      sizeof(*fi));
		if (ret)
			goto out;
	}
	leaf = path->nodes[0];
	fi = btrfs_item_ptr(leaf, path->slots[0],
			    struct btrfs_file_extent_item);
	btrfs_set_file_extent_generation(leaf, fi, trans->transid);
	btrfs_set_file_extent_type(leaf, fi, extent_type);
	btrfs_set_file_extent_disk_bytenr(leaf, fi, disk_bytenr);
	btrfs_set_file_extent_disk_num_bytes(leaf, fi, disk_num_bytes);
	btrfs_set_file_extent_offset(leaf, fi, 0);
	btrfs_set_file_extent_num_bytes(leaf, fi, num_bytes);
	btrfs_set_file_extent_ram_bytes(leaf, fi, ram_bytes);
	btrfs_set_file_extent_compression(leaf, fi, compression);
	btrfs_set_file_extent_encryption(leaf, fi, encryption);
	btrfs_set_file_extent_other_encoding(leaf, fi, other_encoding);

	btrfs_mark_buffer_dirty(leaf);
	btrfs_release_path(path);

	inode_add_bytes(inode, num_bytes);

	ins.objectid = disk_bytenr;
	ins.offset = disk_num_bytes;
	ins.type = BTRFS_EXTENT_ITEM_KEY;

	/*
	 * Release the reserved range from inode dirty range map, as it is
	 * already moved into delayed_ref_head
	 */
	ret = btrfs_qgroup_release_data(inode, file_pos, ram_bytes);
	if (ret < 0)
		goto out;
	qg_released = ret;
	ret = btrfs_alloc_reserved_file_extent(trans, root,
					       btrfs_ino(BTRFS_I(inode)),
					       file_pos, qg_released, &ins);
out:
	btrfs_free_path(path);

	return ret;
}

/* snapshot-aware defrag */
struct sa_defrag_extent_backref {
	struct rb_node node;
	struct old_sa_defrag_extent *old;
	u64 root_id;
	u64 inum;
	u64 file_pos;
	u64 extent_offset;
	u64 num_bytes;
	u64 generation;
};

struct old_sa_defrag_extent {
	struct list_head list;
	struct new_sa_defrag_extent *new;

	u64 extent_offset;
	u64 bytenr;
	u64 offset;
	u64 len;
	int count;
};

struct new_sa_defrag_extent {
	struct rb_root root;
	struct list_head head;
	struct btrfs_path *path;
	struct inode *inode;
	u64 file_pos;
	u64 len;
	u64 bytenr;
	u64 disk_len;
	u8 compress_type;
};

static int backref_comp(struct sa_defrag_extent_backref *b1,
			struct sa_defrag_extent_backref *b2)
{
	if (b1->root_id < b2->root_id)
		return -1;
	else if (b1->root_id > b2->root_id)
		return 1;

	if (b1->inum < b2->inum)
		return -1;
	else if (b1->inum > b2->inum)
		return 1;

	if (b1->file_pos < b2->file_pos)
		return -1;
	else if (b1->file_pos > b2->file_pos)
		return 1;

	/*
	 * [------------------------------] ===> (a range of space)
	 *     |<--->|   |<---->| =============> (fs/file tree A)
	 * |<---------------------------->| ===> (fs/file tree B)
	 *
	 * A range of space can refer to two file extents in one tree while
	 * refer to only one file extent in another tree.
	 *
	 * So we may process a disk offset more than one time(two extents in A)
	 * and locate at the same extent(one extent in B), then insert two same
	 * backrefs(both refer to the extent in B).
	 */
	return 0;
}

static void backref_insert(struct rb_root *root,
			   struct sa_defrag_extent_backref *backref)
{
	struct rb_node **p = &root->rb_node;
	struct rb_node *parent = NULL;
	struct sa_defrag_extent_backref *entry;
	int ret;

	while (*p) {
		parent = *p;
		entry = rb_entry(parent, struct sa_defrag_extent_backref, node);

		ret = backref_comp(backref, entry);
		if (ret < 0)
			p = &(*p)->rb_left;
		else
			p = &(*p)->rb_right;
	}

	rb_link_node(&backref->node, parent, p);
	rb_insert_color(&backref->node, root);
}

/*
 * Note the backref might has changed, and in this case we just return 0.
 */
static noinline int record_one_backref(u64 inum, u64 offset, u64 root_id,
				       void *ctx)
{
	struct btrfs_file_extent_item *extent;
	struct old_sa_defrag_extent *old = ctx;
	struct new_sa_defrag_extent *new = old->new;
	struct btrfs_path *path = new->path;
	struct btrfs_key key;
	struct btrfs_root *root;
	struct sa_defrag_extent_backref *backref;
	struct extent_buffer *leaf;
	struct inode *inode = new->inode;
	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
	int slot;
	int ret;
	u64 extent_offset;
	u64 num_bytes;

	if (BTRFS_I(inode)->root->root_key.objectid == root_id &&
	    inum == btrfs_ino(BTRFS_I(inode)))
		return 0;

	key.objectid = root_id;
	key.type = BTRFS_ROOT_ITEM_KEY;
	key.offset = (u64)-1;

	root = btrfs_read_fs_root_no_name(fs_info, &key);
	if (IS_ERR(root)) {
		if (PTR_ERR(root) == -ENOENT)
			return 0;
		WARN_ON(1);
		btrfs_debug(fs_info, "inum=%llu, offset=%llu, root_id=%llu",
			 inum, offset, root_id);
		return PTR_ERR(root);
	}

	key.objectid = inum;
	key.type = BTRFS_EXTENT_DATA_KEY;
	if (offset > (u64)-1 << 32)
		key.offset = 0;
	else
		key.offset = offset;

	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
	if (WARN_ON(ret < 0))
		return ret;
	ret = 0;

	while (1) {
		cond_resched();

		leaf = path->nodes[0];
		slot = path->slots[0];

		if (slot >= btrfs_header_nritems(leaf)) {
			ret = btrfs_next_leaf(root, path);
			if (ret < 0) {
				goto out;
			} else if (ret > 0) {
				ret = 0;
				goto out;
			}
			continue;
		}

		path->slots[0]++;

		btrfs_item_key_to_cpu(leaf, &key, slot);

		if (key.objectid > inum)
			goto out;

		if (key.objectid < inum || key.type != BTRFS_EXTENT_DATA_KEY)
			continue;

		extent = btrfs_item_ptr(leaf, slot,
					struct btrfs_file_extent_item);

		if (btrfs_file_extent_disk_bytenr(leaf, extent) != old->bytenr)
			continue;

		/*
		 * 'offset' refers to the exact key.offset,
		 * NOT the 'offset' field in btrfs_extent_data_ref, ie.
		 * (key.offset - extent_offset).
		 */
		if (key.offset != offset)
			continue;

		extent_offset = btrfs_file_extent_offset(leaf, extent);
		num_bytes = btrfs_file_extent_num_bytes(leaf, extent);

		if (extent_offset >= old->extent_offset + old->offset +
		    old->len || extent_offset + num_bytes <=
		    old->extent_offset + old->offset)
			continue;
		break;
	}

	backref = kmalloc(sizeof(*backref), GFP_NOFS);
	if (!backref) {
		ret = -ENOENT;
		goto out;
	}

	backref->root_id = root_id;
	backref->inum = inum;
	backref->file_pos = offset;
	backref->num_bytes = num_bytes;
	backref->extent_offset = extent_offset;
	backref->generation = btrfs_file_extent_generation(leaf, extent);
	backref->old = old;
	backref_insert(&new->root, backref);
	old->count++;
out:
	btrfs_release_path(path);
	WARN_ON(ret);
	return ret;
}

static noinline bool record_extent_backrefs(struct btrfs_path *path,
				   struct new_sa_defrag_extent *new)
{
	struct btrfs_fs_info *fs_info = btrfs_sb(new->inode->i_sb);
	struct old_sa_defrag_extent *old, *tmp;
	int ret;

	new->path = path;

	list_for_each_entry_safe(old, tmp, &new->head, list) {
		ret = iterate_inodes_from_logical(old->bytenr +
						  old->extent_offset, fs_info,
						  path, record_one_backref,
						  old, false);
		if (ret < 0 && ret != -ENOENT)
			return false;

		/* no backref to be processed for this extent */
		if (!old->count) {
			list_del(&old->list);
			kfree(old);
		}
	}

	if (list_empty(&new->head))
		return false;

	return true;
}

static int relink_is_mergable(struct extent_buffer *leaf,
			      struct btrfs_file_extent_item *fi,
			      struct new_sa_defrag_extent *new)
{
	if (btrfs_file_extent_disk_bytenr(leaf, fi) != new->bytenr)
		return 0;

	if (btrfs_file_extent_type(leaf, fi) != BTRFS_FILE_EXTENT_REG)
		return 0;

	if (btrfs_file_extent_compression(leaf, fi) != new->compress_type)
		return 0;

	if (btrfs_file_extent_encryption(leaf, fi) ||
	    btrfs_file_extent_other_encoding(leaf, fi))
		return 0;

	return 1;
}

/*
 * Note the backref might has changed, and in this case we just return 0.
 */
static noinline int relink_extent_backref(struct btrfs_path *path,
				 struct sa_defrag_extent_backref *prev,
				 struct sa_defrag_extent_backref *backref)
{
	struct btrfs_file_extent_item *extent;
	struct btrfs_file_extent_item *item;
	struct btrfs_ordered_extent *ordered;
	struct btrfs_trans_handle *trans;
	struct btrfs_root *root;
	struct btrfs_key key;
	struct extent_buffer *leaf;
	struct old_sa_defrag_extent *old = backref->old;
	struct new_sa_defrag_extent *new = old->new;
	struct btrfs_fs_info *fs_info = btrfs_sb(new->inode->i_sb);
	struct inode *inode;
	struct extent_state *cached = NULL;
	int ret = 0;
	u64 start;
	u64 len;
	u64 lock_start;
	u64 lock_end;
	bool merge = false;
	int index;

	if (prev && prev->root_id == backref->root_id &&
	    prev->inum == backref->inum &&
	    prev->file_pos + prev->num_bytes == backref->file_pos)
		merge = true;

	/* step 1: get root */
	key.objectid = backref->root_id;
	key.type = BTRFS_ROOT_ITEM_KEY;
	key.offset = (u64)-1;

	index = srcu_read_lock(&fs_info->subvol_srcu);

	root = btrfs_read_fs_root_no_name(fs_info, &key);
	if (IS_ERR(root)) {
		srcu_read_unlock(&fs_info->subvol_srcu, index);
		if (PTR_ERR(root) == -ENOENT)
			return 0;
		return PTR_ERR(root);
	}

	if (btrfs_root_readonly(root)) {
		srcu_read_unlock(&fs_info->subvol_srcu, index);
		return 0;
	}

	/* step 2: get inode */
	key.objectid = backref->inum;
	key.type = BTRFS_INODE_ITEM_KEY;
	key.offset = 0;

	inode = btrfs_iget(fs_info->sb, &key, root, NULL);
	if (IS_ERR(inode)) {
		srcu_read_unlock(&fs_info->subvol_srcu, index);
		return 0;
	}

	srcu_read_unlock(&fs_info->subvol_srcu, index);

	/* step 3: relink backref */
	lock_start = backref->file_pos;
	lock_end = backref->file_pos + backref->num_bytes - 1;
	lock_extent_bits(&BTRFS_I(inode)->io_tree, lock_start, lock_end,
			 &cached);

	ordered = btrfs_lookup_first_ordered_extent(inode, lock_end);
	if (ordered) {
		btrfs_put_ordered_extent(ordered);
		goto out_unlock;
	}

	trans = btrfs_join_transaction(root);
	if (IS_ERR(trans)) {
		ret = PTR_ERR(trans);
		goto out_unlock;
	}

	key.objectid = backref->inum;
	key.type = BTRFS_EXTENT_DATA_KEY;
	key.offset = backref->file_pos;

	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
	if (ret < 0) {
		goto out_free_path;
	} else if (ret > 0) {
		ret = 0;
		goto out_free_path;
	}

	extent = btrfs_item_ptr(path->nodes[0], path->slots[0],
				struct btrfs_file_extent_item);

	if (btrfs_file_extent_generation(path->nodes[0], extent) !=
	    backref->generation)
		goto out_free_path;

	btrfs_release_path(path);

	start = backref->file_pos;
	if (backref->extent_offset < old->extent_offset + old->offset)
		start += old->extent_offset + old->offset -
			 backref->extent_offset;

	len = min(backref->extent_offset + backref->num_bytes,
		  old->extent_offset + old->offset + old->len);
	len -= max(backref->extent_offset, old->extent_offset + old->offset);

	ret = btrfs_drop_extents(trans, root, inode, start,
				 start + len, 1);
	if (ret)
		goto out_free_path;
again:
	key.objectid = btrfs_ino(BTRFS_I(inode));
	key.type = BTRFS_EXTENT_DATA_KEY;
	key.offset = start;

	path->leave_spinning = 1;
	if (merge) {
		struct btrfs_file_extent_item *fi;
		u64 extent_len;
		struct btrfs_key found_key;

		ret = btrfs_search_slot(trans, root, &key, path, 0, 1);
		if (ret < 0)
			goto out_free_path;

		path->slots[0]--;
		leaf = path->nodes[0];
		btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);

		fi = btrfs_item_ptr(leaf, path->slots[0],
				    struct btrfs_file_extent_item);
		extent_len = btrfs_file_extent_num_bytes(leaf, fi);

		if (extent_len + found_key.offset == start &&
		    relink_is_mergable(leaf, fi, new)) {
			btrfs_set_file_extent_num_bytes(leaf, fi,
							extent_len + len);
			btrfs_mark_buffer_dirty(leaf);
			inode_add_bytes(inode, len);

			ret = 1;
			goto out_free_path;
		} else {
			merge = false;
			btrfs_release_path(path);
			goto again;
		}
	}

	ret = btrfs_insert_empty_item(trans, root, path, &key,
					sizeof(*extent));
	if (ret) {
		btrfs_abort_transaction(trans, ret);
		goto out_free_path;
	}

	leaf = path->nodes[0];
	item = btrfs_item_ptr(leaf, path->slots[0],
				struct btrfs_file_extent_item);
	btrfs_set_file_extent_disk_bytenr(leaf, item, new->bytenr);
	btrfs_set_file_extent_disk_num_bytes(leaf, item, new->disk_len);
	btrfs_set_file_extent_offset(leaf, item, start - new->file_pos);
	btrfs_set_file_extent_num_bytes(leaf, item, len);
	btrfs_set_file_extent_ram_bytes(leaf, item, new->len);
	btrfs_set_file_extent_generation(leaf, item, trans->transid);
	btrfs_set_file_extent_type(leaf, item, BTRFS_FILE_EXTENT_REG);
	btrfs_set_file_extent_compression(leaf, item, new->compress_type);
	btrfs_set_file_extent_encryption(leaf, item, 0);
	btrfs_set_file_extent_other_encoding(leaf, item, 0);

	btrfs_mark_buffer_dirty(leaf);
	inode_add_bytes(inode, len);
	btrfs_release_path(path);

	ret = btrfs_inc_extent_ref(trans, root, new->bytenr,
			new->disk_len, 0,
			backref->root_id, backref->inum,
			new->file_pos);	/* start - extent_offset */
	if (ret) {
		btrfs_abort_transaction(trans, ret);
		goto out_free_path;
	}

	ret = 1;
out_free_path:
	btrfs_release_path(path);
	path->leave_spinning = 0;
	btrfs_end_transaction(trans);
out_unlock:
	unlock_extent_cached(&BTRFS_I(inode)->io_tree, lock_start, lock_end,
			     &cached);
	iput(inode);
	return ret;
}

static void free_sa_defrag_extent(struct new_sa_defrag_extent *new)
{
	struct old_sa_defrag_extent *old, *tmp;

	if (!new)
		return;

	list_for_each_entry_safe(old, tmp, &new->head, list) {
		kfree(old);
	}
	kfree(new);
}

static void relink_file_extents(struct new_sa_defrag_extent *new)
{
	struct btrfs_fs_info *fs_info = btrfs_sb(new->inode->i_sb);
	struct btrfs_path *path;
	struct sa_defrag_extent_backref *backref;
	struct sa_defrag_extent_backref *prev = NULL;
	struct rb_node *node;
	int ret;

	path = btrfs_alloc_path();
	if (!path)
		return;

	if (!record_extent_backrefs(path, new)) {
		btrfs_free_path(path);
		goto out;
	}
	btrfs_release_path(path);

	while (1) {
		node = rb_first(&new->root);
		if (!node)
			break;
		rb_erase(node, &new->root);

		backref = rb_entry(node, struct sa_defrag_extent_backref, node);

		ret = relink_extent_backref(path, prev, backref);
		WARN_ON(ret < 0);

		kfree(prev);

		if (ret == 1)
			prev = backref;
		else
			prev = NULL;
		cond_resched();
	}
	kfree(prev);

	btrfs_free_path(path);
out:
	free_sa_defrag_extent(new);

	atomic_dec(&fs_info->defrag_running);
	wake_up(&fs_info->transaction_wait);
}

static struct new_sa_defrag_extent *
record_old_file_extents(struct inode *inode,
			struct btrfs_ordered_extent *ordered)
{
	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
	struct btrfs_root *root = BTRFS_I(inode)->root;
	struct btrfs_path *path;
	struct btrfs_key key;
	struct old_sa_defrag_extent *old;
	struct new_sa_defrag_extent *new;
	int ret;

	new = kmalloc(sizeof(*new), GFP_NOFS);
	if (!new)
		return NULL;

	new->inode = inode;
	new->file_pos = ordered->file_offset;
	new->len = ordered->len;
	new->bytenr = ordered->start;
	new->disk_len = ordered->disk_len;
	new->compress_type = ordered->compress_type;
	new->root = RB_ROOT;
	INIT_LIST_HEAD(&new->head);

	path = btrfs_alloc_path();
	if (!path)
		goto out_kfree;

	key.objectid = btrfs_ino(BTRFS_I(inode));
	key.type = BTRFS_EXTENT_DATA_KEY;
	key.offset = new->file_pos;

	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
	if (ret < 0)
		goto out_free_path;
	if (ret > 0 && path->slots[0] > 0)
		path->slots[0]--;

	/* find out all the old extents for the file range */
	while (1) {
		struct btrfs_file_extent_item *extent;
		struct extent_buffer *l;
		int slot;
		u64 num_bytes;
		u64 offset;
		u64 end;
		u64 disk_bytenr;
		u64 extent_offset;

		l = path->nodes[0];
		slot = path->slots[0];

		if (slot >= btrfs_header_nritems(l)) {
			ret = btrfs_next_leaf(root, path);
			if (ret < 0)
				goto out_free_path;
			else if (ret > 0)
				break;
			continue;
		}

		btrfs_item_key_to_cpu(l, &key, slot);

		if (key.objectid != btrfs_ino(BTRFS_I(inode)))
			break;
		if (key.type != BTRFS_EXTENT_DATA_KEY)
			break;
		if (key.offset >= new->file_pos + new->len)
			break;

		extent = btrfs_item_ptr(l, slot, struct btrfs_file_extent_item);

		num_bytes = btrfs_file_extent_num_bytes(l, extent);
		if (key.offset + num_bytes < new->file_pos)
			goto next;

		disk_bytenr = btrfs_file_extent_disk_bytenr(l, extent);
		if (!disk_bytenr)
			goto next;

		extent_offset = btrfs_file_extent_offset(l, extent);

		old = kmalloc(sizeof(*old), GFP_NOFS);
		if (!old)
			goto out_free_path;

		offset = max(new->file_pos, key.offset);
		end = min(new->file_pos + new->len, key.offset + num_bytes);

		old->bytenr = disk_bytenr;
		old->extent_offset = extent_offset;
		old->offset = offset - key.offset;
		old->len = end - offset;
		old->new = new;
		old->count = 0;
		list_add_tail(&old->list, &new->head);
next:
		path->slots[0]++;
		cond_resched();
	}

	btrfs_free_path(path);
	atomic_inc(&fs_info->defrag_running);

	return new;

out_free_path:
	btrfs_free_path(path);
out_kfree:
	free_sa_defrag_extent(new);
	return NULL;
}

static void btrfs_release_delalloc_bytes(struct btrfs_fs_info *fs_info,
					 u64 start, u64 len)
{
	struct btrfs_block_group_cache *cache;

	cache = btrfs_lookup_block_group(fs_info, start);
	ASSERT(cache);

	spin_lock(&cache->lock);
	cache->delalloc_bytes -= len;
	spin_unlock(&cache->lock);

	btrfs_put_block_group(cache);
}

/* as ordered data IO finishes, this gets called so we can finish
 * an ordered extent if the range of bytes in the file it covers are
 * fully written.
 */
static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
{
	struct inode *inode = ordered_extent->inode;
	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
	struct btrfs_root *root = BTRFS_I(inode)->root;
	struct btrfs_trans_handle *trans = NULL;
	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
	struct extent_state *cached_state = NULL;
	struct new_sa_defrag_extent *new = NULL;
	int compress_type = 0;
	int ret = 0;
	u64 logical_len = ordered_extent->len;
	bool nolock;
	bool truncated = false;
	bool range_locked = false;
	bool clear_new_delalloc_bytes = false;
	bool clear_reserved_extent = true;

	if (!test_bit(BTRFS_ORDERED_NOCOW, &ordered_extent->flags) &&
	    !test_bit(BTRFS_ORDERED_PREALLOC, &ordered_extent->flags) &&
	    !test_bit(BTRFS_ORDERED_DIRECT, &ordered_extent->flags))
		clear_new_delalloc_bytes = true;

	nolock = btrfs_is_free_space_inode(BTRFS_I(inode));

	if (test_bit(BTRFS_ORDERED_IOERR, &ordered_extent->flags)) {
		ret = -EIO;
		goto out;
	}

	btrfs_free_io_failure_record(BTRFS_I(inode),
			ordered_extent->file_offset,
			ordered_extent->file_offset +
			ordered_extent->len - 1);

	if (test_bit(BTRFS_ORDERED_TRUNCATED, &ordered_extent->flags)) {
		truncated = true;
		logical_len = ordered_extent->truncated_len;
		/* Truncated the entire extent, don't bother adding */
		if (!logical_len)
			goto out;
	}

	if (test_bit(BTRFS_ORDERED_NOCOW, &ordered_extent->flags)) {
		BUG_ON(!list_empty(&ordered_extent->list)); /* Logic error */

		/*
		 * For mwrite(mmap + memset to write) case, we still reserve
		 * space for NOCOW range.
		 * As NOCOW won't cause a new delayed ref, just free the space
		 */
		btrfs_qgroup_free_data(inode, NULL, ordered_extent->file_offset,
				       ordered_extent->len);
		btrfs_ordered_update_i_size(inode, 0, ordered_extent);
		if (nolock)
			trans = btrfs_join_transaction_nolock(root);
		else
			trans = btrfs_join_transaction(root);
		if (IS_ERR(trans)) {
			ret = PTR_ERR(trans);
			trans = NULL;
			goto out;
		}
		trans->block_rsv = &BTRFS_I(inode)->block_rsv;
		ret = btrfs_update_inode_fallback(trans, root, inode);
		if (ret) /* -ENOMEM or corruption */
			btrfs_abort_transaction(trans, ret);
		goto out;
	}

	range_locked = true;
	lock_extent_bits(io_tree, ordered_extent->file_offset,
			 ordered_extent->file_offset + ordered_extent->len - 1,
			 &cached_state);

	ret = test_range_bit(io_tree, ordered_extent->file_offset,
			ordered_extent->file_offset + ordered_extent->len - 1,
			EXTENT_DEFRAG, 0, cached_state);
	if (ret) {
		u64 last_snapshot = btrfs_root_last_snapshot(&root->root_item);
		if (0 && last_snapshot >= BTRFS_I(inode)->generation)
			/* the inode is shared */
			new = record_old_file_extents(inode, ordered_extent);

		clear_extent_bit(io_tree, ordered_extent->file_offset,
			ordered_extent->file_offset + ordered_extent->len - 1,
			EXTENT_DEFRAG, 0, 0, &cached_state);
	}

	if (nolock)
		trans = btrfs_join_transaction_nolock(root);
	else
		trans = btrfs_join_transaction(root);
	if (IS_ERR(trans)) {
		ret = PTR_ERR(trans);
		trans = NULL;
		goto out;
	}

	trans->block_rsv = &BTRFS_I(inode)->block_rsv;

	if (test_bit(BTRFS_ORDERED_COMPRESSED, &ordered_extent->flags))
		compress_type = ordered_extent->compress_type;
	if (test_bit(BTRFS_ORDERED_PREALLOC, &ordered_extent->flags)) {
		BUG_ON(compress_type);
		btrfs_qgroup_free_data(inode, NULL, ordered_extent->file_offset,
				       ordered_extent->len);
		ret = btrfs_mark_extent_written(trans, BTRFS_I(inode),
						ordered_extent->file_offset,
						ordered_extent->file_offset +
						logical_len);
	} else {
		BUG_ON(root == fs_info->tree_root);
		ret = insert_reserved_file_extent(trans, inode,
						ordered_extent->file_offset,
						ordered_extent->start,
						ordered_extent->disk_len,
						logical_len, logical_len,
						compress_type, 0, 0,
						BTRFS_FILE_EXTENT_REG);
		if (!ret) {
			clear_reserved_extent = false;
			btrfs_release_delalloc_bytes(fs_info,
						     ordered_extent->start,
						     ordered_extent->disk_len);
		}
	}
	unpin_extent_cache(&BTRFS_I(inode)->extent_tree,
			   ordered_extent->file_offset, ordered_extent->len,
			   trans->transid);
	if (ret < 0) {
		btrfs_abort_transaction(trans, ret);
		goto out;
	}

	ret = add_pending_csums(trans, inode, &ordered_extent->list);
	if (ret) {
		btrfs_abort_transaction(trans, ret);
		goto out;
	}

	btrfs_ordered_update_i_size(inode, 0, ordered_extent);
	ret = btrfs_update_inode_fallback(trans, root, inode);
	if (ret) { /* -ENOMEM or corruption */
		btrfs_abort_transaction(trans, ret);
		goto out;
	}
	ret = 0;
out:
	if (range_locked || clear_new_delalloc_bytes) {
		unsigned int clear_bits = 0;

		if (range_locked)
			clear_bits |= EXTENT_LOCKED;
		if (clear_new_delalloc_bytes)
			clear_bits |= EXTENT_DELALLOC_NEW;
		clear_extent_bit(&BTRFS_I(inode)->io_tree,
				 ordered_extent->file_offset,
				 ordered_extent->file_offset +
				 ordered_extent->len - 1,
				 clear_bits,
				 (clear_bits & EXTENT_LOCKED) ? 1 : 0,
				 0, &cached_state);
	}

	if (trans)
		btrfs_end_transaction(trans);

	if (ret || truncated) {
		u64 start, end;

		if (truncated)
			start = ordered_extent->file_offset + logical_len;
		else
			start = ordered_extent->file_offset;
		end = ordered_extent->file_offset + ordered_extent->len - 1;
		clear_extent_uptodate(io_tree, start, end, NULL);

		/* Drop the cache for the part of the extent we didn't write. */
		btrfs_drop_extent_cache(BTRFS_I(inode), start, end, 0);

		/*
		 * If the ordered extent had an IOERR or something else went
		 * wrong we need to return the space for this ordered extent
		 * back to the allocator.  We only free the extent in the
		 * truncated case if we didn't write out the extent at all.
		 *
		 * If we made it past insert_reserved_file_extent before we
		 * errored out then we don't need to do this as the accounting
		 * has already been done.
		 */
		if ((ret || !logical_len) &&
		    clear_reserved_extent &&
		    !test_bit(BTRFS_ORDERED_NOCOW, &ordered_extent->flags) &&
		    !test_bit(BTRFS_ORDERED_PREALLOC, &ordered_extent->flags))
			btrfs_free_reserved_extent(fs_info,
						   ordered_extent->start,
						   ordered_extent->disk_len, 1);
	}


	/*
	 * This needs to be done to make sure anybody waiting knows we are done
	 * updating everything for this ordered extent.
	 */
	btrfs_remove_ordered_extent(inode, ordered_extent);

	/* for snapshot-aware defrag */
	if (new) {
		if (ret) {
			free_sa_defrag_extent(new);
			atomic_dec(&fs_info->defrag_running);
		} else {
			relink_file_extents(new);
		}
	}

	/* once for us */
	btrfs_put_ordered_extent(ordered_extent);
	/* once for the tree */
	btrfs_put_ordered_extent(ordered_extent);

	/* Try to release some metadata so we don't get an OOM but don't wait */
	btrfs_btree_balance_dirty_nodelay(fs_info);

	return ret;
}

static void finish_ordered_fn(struct btrfs_work *work)
{
	struct btrfs_ordered_extent *ordered_extent;
	ordered_extent = container_of(work, struct btrfs_ordered_extent, work);
	btrfs_finish_ordered_io(ordered_extent);
}

static void btrfs_writepage_end_io_hook(struct page *page, u64 start, u64 end,
				struct extent_state *state, int uptodate)
{
	struct inode *inode = page->mapping->host;
	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
	struct btrfs_ordered_extent *ordered_extent = NULL;
	struct btrfs_workqueue *wq;
	btrfs_work_func_t func;

	trace_btrfs_writepage_end_io_hook(page, start, end, uptodate);

	ClearPagePrivate2(page);
	if (!btrfs_dec_test_ordered_pending(inode, &ordered_extent, start,
					    end - start + 1, uptodate))
		return;

	if (btrfs_is_free_space_inode(BTRFS_I(inode))) {
		wq = fs_info->endio_freespace_worker;
		func = btrfs_freespace_write_helper;
	} else {
		wq = fs_info->endio_write_workers;
		func = btrfs_endio_write_helper;
	}

	btrfs_init_work(&ordered_extent->work, func, finish_ordered_fn, NULL,
			NULL);
	btrfs_queue_work(wq, &ordered_extent->work);
}

static int __readpage_endio_check(struct inode *inode,
				  struct btrfs_io_bio *io_bio,
				  int icsum, struct page *page,
				  int pgoff, u64 start, size_t len)
{
	char *kaddr;
	u32 csum_expected;
	u32 csum = ~(u32)0;

	csum_expected = *(((u32 *)io_bio->csum) + icsum);

	kaddr = kmap_atomic(page);
	csum = btrfs_csum_data(kaddr + pgoff, csum,  len);
	btrfs_csum_final(csum, (u8 *)&csum);
	if (csum != csum_expected)
		goto zeroit;

	kunmap_atomic(kaddr);
	return 0;
zeroit:
	btrfs_print_data_csum_error(BTRFS_I(inode), start, csum, csum_expected,
				    io_bio->mirror_num);
	memset(kaddr + pgoff, 1, len);
	flush_dcache_page(page);
	kunmap_atomic(kaddr);
	return -EIO;
}

/*
 * when reads are done, we need to check csums to verify the data is correct
 * if there's a match, we allow the bio to finish.  If not, the code in
 * extent_io.c will try to find good copies for us.
 */
static int btrfs_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
				      u64 phy_offset, struct page *page,
				      u64 start, u64 end, int mirror)
{
	size_t offset = start - page_offset(page);
	struct inode *inode = page->mapping->host;
	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
	struct btrfs_root *root = BTRFS_I(inode)->root;

	if (PageChecked(page)) {
		ClearPageChecked(page);
		return 0;
	}

	if (BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)
		return 0;

	if (root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID &&
	    test_range_bit(io_tree, start, end, EXTENT_NODATASUM, 1, NULL)) {
		clear_extent_bits(io_tree, start, end, EXTENT_NODATASUM);
		return 0;
	}

	phy_offset >>= inode->i_sb->s_blocksize_bits;
	return __readpage_endio_check(inode, io_bio, phy_offset, page, offset,
				      start, (size_t)(end - start + 1));
}

/*
 * btrfs_add_delayed_iput - perform a delayed iput on @inode
 *
 * @inode: The inode we want to perform iput on
 *
 * This function uses the generic vfs_inode::i_count to track whether we should
 * just decrement it (in case it's > 1) or if this is the last iput then link
 * the inode to the delayed iput machinery. Delayed iputs are processed at
 * transaction commit time/superblock commit/cleaner kthread.
 */
void btrfs_add_delayed_iput(struct inode *inode)
{
	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
	struct btrfs_inode *binode = BTRFS_I(inode);

	if (atomic_add_unless(&inode->i_count, -1, 1))
		return;

	spin_lock(&fs_info->delayed_iput_lock);
	ASSERT(list_empty(&binode->delayed_iput));
	list_add_tail(&binode->delayed_iput, &fs_info->delayed_iputs);
	spin_unlock(&fs_info->delayed_iput_lock);
}

void btrfs_run_delayed_iputs(struct btrfs_fs_info *fs_info)
{

	spin_lock(&fs_info->delayed_iput_lock);
	while (!list_empty(&fs_info->delayed_iputs)) {
		struct btrfs_inode *inode;

		inode = list_first_entry(&fs_info->delayed_iputs,
				struct btrfs_inode, delayed_iput);
		list_del_init(&inode->delayed_iput);
		spin_unlock(&fs_info->delayed_iput_lock);
		iput(&inode->vfs_inode);
		spin_lock(&fs_info->delayed_iput_lock);
	}
	spin_unlock(&fs_info->delayed_iput_lock);
}

/*
 * This creates an orphan entry for the given inode in case something goes wrong
 * in the middle of an unlink.
 */
int btrfs_orphan_add(struct btrfs_trans_handle *trans,
		     struct btrfs_inode *inode)
{
	int ret;

	ret = btrfs_insert_orphan_item(trans, inode->root, btrfs_ino(inode));
	if (ret && ret != -EEXIST) {
		btrfs_abort_transaction(trans, ret);
		return ret;
	}

	return 0;
}

/*
 * We have done the delete so we can go ahead and remove the orphan item for
 * this particular inode.
 */
static int btrfs_orphan_del(struct btrfs_trans_handle *trans,
			    struct btrfs_inode *inode)
{
	return btrfs_del_orphan_item(trans, inode->root, btrfs_ino(inode));
}

/*
 * this cleans up any orphans that may be left on the list from the last use
 * of this root.
 */
int btrfs_orphan_cleanup(struct btrfs_root *root)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct btrfs_path *path;
	struct extent_buffer *leaf;
	struct btrfs_key key, found_key;
	struct btrfs_trans_handle *trans;
	struct inode *inode;
	u64 last_objectid = 0;
	int ret = 0, nr_unlink = 0;

	if (cmpxchg(&root->orphan_cleanup_state, 0, ORPHAN_CLEANUP_STARTED))
		return 0;

	path = btrfs_alloc_path();
	if (!path) {
		ret = -ENOMEM;
		goto out;
	}
	path->reada = READA_BACK;

	key.objectid = BTRFS_ORPHAN_OBJECTID;
	key.type = BTRFS_ORPHAN_ITEM_KEY;
	key.offset = (u64)-1;

	while (1) {
		ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
		if (ret < 0)
			goto out;

		/*
		 * if ret == 0 means we found what we were searching for, which
		 * is weird, but possible, so only screw with path if we didn't
		 * find the key and see if we have stuff that matches
		 */
		if (ret > 0) {
			ret = 0;
			if (path->slots[0] == 0)
				break;
			path->slots[0]--;
		}

		/* pull out the item */
		leaf = path->nodes[0];
		btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);

		/* make sure the item matches what we want */
		if (found_key.objectid != BTRFS_ORPHAN_OBJECTID)
			break;
		if (found_key.type != BTRFS_ORPHAN_ITEM_KEY)
			break;

		/* release the path since we're done with it */
		btrfs_release_path(path);

		/*
		 * this is where we are basically btrfs_lookup, without the
		 * crossing root thing.  we store the inode number in the
		 * offset of the orphan item.
		 */

		if (found_key.offset == last_objectid) {
			btrfs_err(fs_info,
				  "Error removing orphan entry, stopping orphan cleanup");
			ret = -EINVAL;
			goto out;
		}

		last_objectid = found_key.offset;

		found_key.objectid = found_key.offset;
		found_key.type = BTRFS_INODE_ITEM_KEY;
		found_key.offset = 0;
		inode = btrfs_iget(fs_info->sb, &found_key, root, NULL);
		ret = PTR_ERR_OR_ZERO(inode);
		if (ret && ret != -ENOENT)
			goto out;

		if (ret == -ENOENT && root == fs_info->tree_root) {
			struct btrfs_root *dead_root;
			struct btrfs_fs_info *fs_info = root->fs_info;
			int is_dead_root = 0;

			/*
			 * this is an orphan in the tree root. Currently these
			 * could come from 2 sources:
			 *  a) a snapshot deletion in progress
			 *  b) a free space cache inode
			 * We need to distinguish those two, as the snapshot
			 * orphan must not get deleted.
			 * find_dead_roots already ran before us, so if this
			 * is a snapshot deletion, we should find the root
			 * in the dead_roots list
			 */
			spin_lock(&fs_info->trans_lock);
			list_for_each_entry(dead_root, &fs_info->dead_roots,
					    root_list) {
				if (dead_root->root_key.objectid ==
				    found_key.objectid) {
					is_dead_root = 1;
					break;
				}
			}
			spin_unlock(&fs_info->trans_lock);
			if (is_dead_root) {
				/* prevent this orphan from being found again */
				key.offset = found_key.objectid - 1;
				continue;
			}

		}

		/*
		 * If we have an inode with links, there are a couple of
		 * possibilities. Old kernels (before v3.12) used to create an
		 * orphan item for truncate indicating that there were possibly
		 * extent items past i_size that needed to be deleted. In v3.12,
		 * truncate was changed to update i_size in sync with the extent
		 * items, but the (useless) orphan item was still created. Since
		 * v4.18, we don't create the orphan item for truncate at all.
		 *
		 * So, this item could mean that we need to do a truncate, but
		 * only if this filesystem was last used on a pre-v3.12 kernel
		 * and was not cleanly unmounted. The odds of that are quite
		 * slim, and it's a pain to do the truncate now, so just delete
		 * the orphan item.
		 *
		 * It's also possible that this orphan item was supposed to be
		 * deleted but wasn't. The inode number may have been reused,
		 * but either way, we can delete the orphan item.
		 */
		if (ret == -ENOENT || inode->i_nlink) {
			if (!ret)
				iput(inode);
			trans = btrfs_start_transaction(root, 1);
			if (IS_ERR(trans)) {
				ret = PTR_ERR(trans);
				goto out;
			}
			btrfs_debug(fs_info, "auto deleting %Lu",
				    found_key.objectid);
			ret = btrfs_del_orphan_item(trans, root,
						    found_key.objectid);
			btrfs_end_transaction(trans);
			if (ret)
				goto out;
			continue;
		}

		nr_unlink++;

		/* this will do delete_inode and everything for us */
		iput(inode);
	}
	/* release the path since we're done with it */
	btrfs_release_path(path);

	root->orphan_cleanup_state = ORPHAN_CLEANUP_DONE;

	if (test_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &root->state)) {
		trans = btrfs_join_transaction(root);
		if (!IS_ERR(trans))
			btrfs_end_transaction(trans);
	}

	if (nr_unlink)
		btrfs_debug(fs_info, "unlinked %d orphans", nr_unlink);

out:
	if (ret)
		btrfs_err(fs_info, "could not do orphan cleanup %d", ret);
	btrfs_free_path(path);
	return ret;
}

/*
 * very simple check to peek ahead in the leaf looking for xattrs.  If we
 * don't find any xattrs, we know there can't be any acls.
 *
 * slot is the slot the inode is in, objectid is the objectid of the inode
 */
static noinline int acls_after_inode_item(struct extent_buffer *leaf,
					  int slot, u64 objectid,
					  int *first_xattr_slot)
{
	u32 nritems = btrfs_header_nritems(leaf);
	struct btrfs_key found_key;
	static u64 xattr_access = 0;
	static u64 xattr_default = 0;
	int scanned = 0;

	if (!xattr_access) {
		xattr_access = btrfs_name_hash(XATTR_NAME_POSIX_ACL_ACCESS,
					strlen(XATTR_NAME_POSIX_ACL_ACCESS));
		xattr_default = btrfs_name_hash(XATTR_NAME_POSIX_ACL_DEFAULT,
					strlen(XATTR_NAME_POSIX_ACL_DEFAULT));
	}

	slot++;
	*first_xattr_slot = -1;
	while (slot < nritems) {
		btrfs_item_key_to_cpu(leaf, &found_key, slot);

		/* we found a different objectid, there must not be acls */
		if (found_key.objectid != objectid)
			return 0;

		/* we found an xattr, assume we've got an acl */
		if (found_key.type == BTRFS_XATTR_ITEM_KEY) {
			if (*first_xattr_slot == -1)
				*first_xattr_slot = slot;
			if (found_key.offset == xattr_access ||
			    found_key.offset == xattr_default)
				return 1;
		}

		/*
		 * we found a key greater than an xattr key, there can't
		 * be any acls later on
		 */
		if (found_key.type > BTRFS_XATTR_ITEM_KEY)
			return 0;

		slot++;
		scanned++;

		/*
		 * it goes inode, inode backrefs, xattrs, extents,
		 * so if there are a ton of hard links to an inode there can
		 * be a lot of backrefs.  Don't waste time searching too hard,
		 * this is just an optimization
		 */
		if (scanned >= 8)
			break;
	}
	/* we hit the end of the leaf before we found an xattr or
	 * something larger than an xattr.  We have to assume the inode
	 * has acls
	 */
	if (*first_xattr_slot == -1)
		*first_xattr_slot = slot;
	return 1;
}

/*
 * read an inode from the btree into the in-memory inode
 */
static int btrfs_read_locked_inode(struct inode *inode,
				   struct btrfs_path *in_path)
{
	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
	struct btrfs_path *path = in_path;
	struct extent_buffer *leaf;
	struct btrfs_inode_item *inode_item;
	struct btrfs_root *root = BTRFS_I(inode)->root;
	struct btrfs_key location;
	unsigned long ptr;
	int maybe_acls;
	u32 rdev;
	int ret;
	bool filled = false;
	int first_xattr_slot;

	ret = btrfs_fill_inode(inode, &rdev);
	if (!ret)
		filled = true;

	if (!path) {
		path = btrfs_alloc_path();
		if (!path)
			return -ENOMEM;
	}

	memcpy(&location, &BTRFS_I(inode)->location, sizeof(location));

	ret = btrfs_lookup_inode(NULL, root, path, &location, 0);
	if (ret) {
		if (path != in_path)
			btrfs_free_path(path);
		return ret;
	}

	leaf = path->nodes[0];

	if (filled)
		goto cache_index;

	inode_item = btrfs_item_ptr(leaf, path->slots[0],
				    struct btrfs_inode_item);
	inode->i_mode = btrfs_inode_mode(leaf, inode_item);
	set_nlink(inode, btrfs_inode_nlink(leaf, inode_item));
	i_uid_write(inode, btrfs_inode_uid(leaf, inode_item));
	i_gid_write(inode, btrfs_inode_gid(leaf, inode_item));
	btrfs_i_size_write(BTRFS_I(inode), btrfs_inode_size(leaf, inode_item));

	inode->i_atime.tv_sec = btrfs_timespec_sec(leaf, &inode_item->atime);
	inode->i_atime.tv_nsec = btrfs_timespec_nsec(leaf, &inode_item->atime);

	inode->i_mtime.tv_sec = btrfs_timespec_sec(leaf, &inode_item->mtime);
	inode->i_mtime.tv_nsec = btrfs_timespec_nsec(leaf, &inode_item->mtime);

	inode->i_ctime.tv_sec = btrfs_timespec_sec(leaf, &inode_item->ctime);
	inode->i_ctime.tv_nsec = btrfs_timespec_nsec(leaf, &inode_item->ctime);

	BTRFS_I(inode)->i_otime.tv_sec =
		btrfs_timespec_sec(leaf, &inode_item->otime);
	BTRFS_I(inode)->i_otime.tv_nsec =
		btrfs_timespec_nsec(leaf, &inode_item->otime);

	inode_set_bytes(inode, btrfs_inode_nbytes(leaf, inode_item));
	BTRFS_I(inode)->generation = btrfs_inode_generation(leaf, inode_item);
	BTRFS_I(inode)->last_trans = btrfs_inode_transid(leaf, inode_item);

	inode_set_iversion_queried(inode,
				   btrfs_inode_sequence(leaf, inode_item));
	inode->i_generation = BTRFS_I(inode)->generation;
	inode->i_rdev = 0;
	rdev = btrfs_inode_rdev(leaf, inode_item);

	BTRFS_I(inode)->index_cnt = (u64)-1;
	BTRFS_I(inode)->flags = btrfs_inode_flags(leaf, inode_item);

cache_index:
	/*
	 * If we were modified in the current generation and evicted from memory
	 * and then re-read we need to do a full sync since we don't have any
	 * idea about which extents were modified before we were evicted from
	 * cache.
	 *
	 * This is required for both inode re-read from disk and delayed inode
	 * in delayed_nodes_tree.
	 */
	if (BTRFS_I(inode)->last_trans == fs_info->generation)
		set_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
			&BTRFS_I(inode)->runtime_flags);

	/*
	 * We don't persist the id of the transaction where an unlink operation
	 * against the inode was last made. So here we assume the inode might
	 * have been evicted, and therefore the exact value of last_unlink_trans
	 * lost, and set it to last_trans to avoid metadata inconsistencies
	 * between the inode and its parent if the inode is fsync'ed and the log
	 * replayed. For example, in the scenario:
	 *
	 * touch mydir/foo
	 * ln mydir/foo mydir/bar
	 * sync
	 * unlink mydir/bar
	 * echo 2 > /proc/sys/vm/drop_caches   # evicts inode
	 * xfs_io -c fsync mydir/foo
	 * <power failure>
	 * mount fs, triggers fsync log replay
	 *
	 * We must make sure that when we fsync our inode foo we also log its
	 * parent inode, otherwise after log replay the parent still has the
	 * dentry with the "bar" name but our inode foo has a link count of 1
	 * and doesn't have an inode ref with the name "bar" anymore.
	 *
	 * Setting last_unlink_trans to last_trans is a pessimistic approach,
	 * but it guarantees correctness at the expense of occasional full
	 * transaction commits on fsync if our inode is a directory, or if our
	 * inode is not a directory, logging its parent unnecessarily.
	 */
	BTRFS_I(inode)->last_unlink_trans = BTRFS_I(inode)->last_trans;

	path->slots[0]++;
	if (inode->i_nlink != 1 ||
	    path->slots[0] >= btrfs_header_nritems(leaf))
		goto cache_acl;

	btrfs_item_key_to_cpu(leaf, &location, path->slots[0]);
	if (location.objectid != btrfs_ino(BTRFS_I(inode)))
		goto cache_acl;

	ptr = btrfs_item_ptr_offset(leaf, path->slots[0]);
	if (location.type == BTRFS_INODE_REF_KEY) {
		struct btrfs_inode_ref *ref;

		ref = (struct btrfs_inode_ref *)ptr;
		BTRFS_I(inode)->dir_index = btrfs_inode_ref_index(leaf, ref);
	} else if (location.type == BTRFS_INODE_EXTREF_KEY) {
		struct btrfs_inode_extref *extref;

		extref = (struct btrfs_inode_extref *)ptr;
		BTRFS_I(inode)->dir_index = btrfs_inode_extref_index(leaf,
								     extref);
	}
cache_acl:
	/*
	 * try to precache a NULL acl entry for files that don't have
	 * any xattrs or acls
	 */
	maybe_acls = acls_after_inode_item(leaf, path->slots[0],
			btrfs_ino(BTRFS_I(inode)), &first_xattr_slot);
	if (first_xattr_slot != -1) {
		path->slots[0] = first_xattr_slot;
		ret = btrfs_load_inode_props(inode, path);
		if (ret)
			btrfs_err(fs_info,
				  "error loading props for ino %llu (root %llu): %d",
				  btrfs_ino(BTRFS_I(inode)),
				  root->root_key.objectid, ret);
	}
	if (path != in_path)
		btrfs_free_path(path);

	if (!maybe_acls)
		cache_no_acl(inode);

	switch (inode->i_mode & S_IFMT) {
	case S_IFREG:
		inode->i_mapping->a_ops = &btrfs_aops;
		BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
		inode->i_fop = &btrfs_file_operations;
		inode->i_op = &btrfs_file_inode_operations;
		break;
	case S_IFDIR:
		inode->i_fop = &btrfs_dir_file_operations;
		inode->i_op = &btrfs_dir_inode_operations;
		break;
	case S_IFLNK:
		inode->i_op = &btrfs_symlink_inode_operations;
		inode_nohighmem(inode);
		inode->i_mapping->a_ops = &btrfs_aops;
		break;
	default:
		inode->i_op = &btrfs_special_inode_operations;
		init_special_inode(inode, inode->i_mode, rdev);
		break;
	}

	btrfs_sync_inode_flags_to_i_flags(inode);
	return 0;
}

/*
 * given a leaf and an inode, copy the inode fields into the leaf
 */
static void fill_inode_item(struct btrfs_trans_handle *trans,
			    struct extent_buffer *leaf,
			    struct btrfs_inode_item *item,
			    struct inode *inode)
{
	struct btrfs_map_token token;

	btrfs_init_map_token(&token);

	btrfs_set_token_inode_uid(leaf, item, i_uid_read(inode), &token);
	btrfs_set_token_inode_gid(leaf, item, i_gid_read(inode), &token);
	btrfs_set_token_inode_size(leaf, item, BTRFS_I(inode)->disk_i_size,
				   &token);
	btrfs_set_token_inode_mode(leaf, item, inode->i_mode, &token);
	btrfs_set_token_inode_nlink(leaf, item, inode->i_nlink, &token);

	btrfs_set_token_timespec_sec(leaf, &item->atime,
				     inode->i_atime.tv_sec, &token);
	btrfs_set_token_timespec_nsec(leaf, &item->atime,
				      inode->i_atime.tv_nsec, &token);

	btrfs_set_token_timespec_sec(leaf, &item->mtime,
				     inode->i_mtime.tv_sec, &token);
	btrfs_set_token_timespec_nsec(leaf, &item->mtime,
				      inode->i_mtime.tv_nsec, &token);

	btrfs_set_token_timespec_sec(leaf, &item->ctime,
				     inode->i_ctime.tv_sec, &token);
	btrfs_set_token_timespec_nsec(leaf, &item->ctime,
				      inode->i_ctime.tv_nsec, &token);

	btrfs_set_token_timespec_sec(leaf, &item->otime,
				     BTRFS_I(inode)->i_otime.tv_sec, &token);
	btrfs_set_token_timespec_nsec(leaf, &item->otime,
				      BTRFS_I(inode)->i_otime.tv_nsec, &token);

	btrfs_set_token_inode_nbytes(leaf, item, inode_get_bytes(inode),
				     &token);
	btrfs_set_token_inode_generation(leaf, item, BTRFS_I(inode)->generation,
					 &token);
	btrfs_set_token_inode_sequence(leaf, item, inode_peek_iversion(inode),
				       &token);
	btrfs_set_token_inode_transid(leaf, item, trans->transid, &token);
	btrfs_set_token_inode_rdev(leaf, item, inode->i_rdev, &token);
	btrfs_set_token_inode_flags(leaf, item, BTRFS_I(inode)->flags, &token);
	btrfs_set_token_inode_block_group(leaf, item, 0, &token);
}

/*
 * copy everything in the in-memory inode into the btree.
 */
static noinline int btrfs_update_inode_item(struct btrfs_trans_handle *trans,
				struct btrfs_root *root, struct inode *inode)
{
	struct btrfs_inode_item *inode_item;
	struct btrfs_path *path;
	struct extent_buffer *leaf;
	int ret;

	path = btrfs_alloc_path();
	if (!path)
		return -ENOMEM;

	path->leave_spinning = 1;
	ret = btrfs_lookup_inode(trans, root, path, &BTRFS_I(inode)->location,
				 1);
	if (ret) {
		if (ret > 0)
			ret = -ENOENT;
		goto failed;
	}

	leaf = path->nodes[0];
	inode_item = btrfs_item_ptr(leaf, path->slots[0],
				    struct btrfs_inode_item);

	fill_inode_item(trans, leaf, inode_item, inode);
	btrfs_mark_buffer_dirty(leaf);
	btrfs_set_inode_last_trans(trans, inode);
	ret = 0;
failed:
	btrfs_free_path(path);
	return ret;
}

/*
 * copy everything in the in-memory inode into the btree.
 */
noinline int btrfs_update_inode(struct btrfs_trans_handle *trans,
				struct btrfs_root *root, struct inode *inode)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	int ret;

	/*
	 * If the inode is a free space inode, we can deadlock during commit
	 * if we put it into the delayed code.
	 *
	 * The data relocation inode should also be directly updated
	 * without delay
	 */
	if (!btrfs_is_free_space_inode(BTRFS_I(inode))
	    && root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID
	    && !test_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags)) {
		btrfs_update_root_times(trans, root);

		ret = btrfs_delayed_update_inode(trans, root, inode);
		if (!ret)
			btrfs_set_inode_last_trans(trans, inode);
		return ret;
	}

	return btrfs_update_inode_item(trans, root, inode);
}

noinline int btrfs_update_inode_fallback(struct btrfs_trans_handle *trans,
					 struct btrfs_root *root,
					 struct inode *inode)
{
	int ret;

	ret = btrfs_update_inode(trans, root, inode);
	if (ret == -ENOSPC)
		return btrfs_update_inode_item(trans, root, inode);
	return ret;
}

/*
 * unlink helper that gets used here in inode.c and in the tree logging
 * recovery code.  It remove a link in a directory with a given name, and
 * also drops the back refs in the inode to the directory
 */
static int __btrfs_unlink_inode(struct btrfs_trans_handle *trans,
				struct btrfs_root *root,
				struct btrfs_inode *dir,
				struct btrfs_inode *inode,
				const char *name, int name_len)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct btrfs_path *path;
	int ret = 0;
	struct extent_buffer *leaf;
	struct btrfs_dir_item *di;
	struct btrfs_key key;
	u64 index;
	u64 ino = btrfs_ino(inode);
	u64 dir_ino = btrfs_ino(dir);

	path = btrfs_alloc_path();
	if (!path) {
		ret = -ENOMEM;
		goto out;
	}

	path->leave_spinning = 1;
	di = btrfs_lookup_dir_item(trans, root, path, dir_ino,
				    name, name_len, -1);
	if (IS_ERR_OR_NULL(di)) {
		ret = di ? PTR_ERR(di) : -ENOENT;
		goto err;
	}
	leaf = path->nodes[0];
	btrfs_dir_item_key_to_cpu(leaf, di, &key);
	ret = btrfs_delete_one_dir_name(trans, root, path, di);
	if (ret)
		goto err;
	btrfs_release_path(path);

	/*
	 * If we don't have dir index, we have to get it by looking up
	 * the inode ref, since we get the inode ref, remove it directly,
	 * it is unnecessary to do delayed deletion.
	 *
	 * But if we have dir index, needn't search inode ref to get it.
	 * Since the inode ref is close to the inode item, it is better
	 * that we delay to delete it, and just do this deletion when
	 * we update the inode item.
	 */
	if (inode->dir_index) {
		ret = btrfs_delayed_delete_inode_ref(inode);
		if (!ret) {
			index = inode->dir_index;
			goto skip_backref;
		}
	}

	ret = btrfs_del_inode_ref(trans, root, name, name_len, ino,
				  dir_ino, &index);
	if (ret) {
		btrfs_info(fs_info,
			"failed to delete reference to %.*s, inode %llu parent %llu",
			name_len, name, ino, dir_ino);
		btrfs_abort_transaction(trans, ret);
		goto err;
	}
skip_backref:
	ret = btrfs_delete_delayed_dir_index(trans, dir, index);
	if (ret) {
		btrfs_abort_transaction(trans, ret);
		goto err;
	}

	ret = btrfs_del_inode_ref_in_log(trans, root, name, name_len, inode,
			dir_ino);
	if (ret != 0 && ret != -ENOENT) {
		btrfs_abort_transaction(trans, ret);
		goto err;
	}

	ret = btrfs_del_dir_entries_in_log(trans, root, name, name_len, dir,
			index);
	if (ret == -ENOENT)
		ret = 0;
	else if (ret)
		btrfs_abort_transaction(trans, ret);
err:
	btrfs_free_path(path);
	if (ret)
		goto out;

	btrfs_i_size_write(dir, dir->vfs_inode.i_size - name_len * 2);
	inode_inc_iversion(&inode->vfs_inode);
	inode_inc_iversion(&dir->vfs_inode);
	inode->vfs_inode.i_ctime = dir->vfs_inode.i_mtime =
		dir->vfs_inode.i_ctime = current_time(&inode->vfs_inode);
	ret = btrfs_update_inode(trans, root, &dir->vfs_inode);
out:
	return ret;
}

int btrfs_unlink_inode(struct btrfs_trans_handle *trans,
		       struct btrfs_root *root,
		       struct btrfs_inode *dir, struct btrfs_inode *inode,
		       const char *name, int name_len)
{
	int ret;
	ret = __btrfs_unlink_inode(trans, root, dir, inode, name, name_len);
	if (!ret) {
		drop_nlink(&inode->vfs_inode);
		ret = btrfs_update_inode(trans, root, &inode->vfs_inode);
	}
	return ret;
}

/*
 * helper to start transaction for unlink and rmdir.
 *
 * unlink and rmdir are special in btrfs, they do not always free space, so
 * if we cannot make our reservations the normal way try and see if there is
 * plenty of slack room in the global reserve to migrate, otherwise we cannot
 * allow the unlink to occur.
 */
static struct btrfs_trans_handle *__unlink_start_trans(struct inode *dir)
{
	struct btrfs_root *root = BTRFS_I(dir)->root;

	/*
	 * 1 for the possible orphan item
	 * 1 for the dir item
	 * 1 for the dir index
	 * 1 for the inode ref
	 * 1 for the inode
	 */
	return btrfs_start_transaction_fallback_global_rsv(root, 5, 5);
}

static int btrfs_unlink(struct inode *dir, struct dentry *dentry)
{
	struct btrfs_root *root = BTRFS_I(dir)->root;
	struct btrfs_trans_handle *trans;
	struct inode *inode = d_inode(dentry);
	int ret;

	trans = __unlink_start_trans(dir);
	if (IS_ERR(trans))
		return PTR_ERR(trans);

	btrfs_record_unlink_dir(trans, BTRFS_I(dir), BTRFS_I(d_inode(dentry)),
			0);

	ret = btrfs_unlink_inode(trans, root, BTRFS_I(dir),
			BTRFS_I(d_inode(dentry)), dentry->d_name.name,
			dentry->d_name.len);
	if (ret)
		goto out;

	if (inode->i_nlink == 0) {
		ret = btrfs_orphan_add(trans, BTRFS_I(inode));
		if (ret)
			goto out;
	}

out:
	btrfs_end_transaction(trans);
	btrfs_btree_balance_dirty(root->fs_info);
	return ret;
}

static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
			       struct inode *dir, u64 objectid,
			       const char *name, int name_len)
{
	struct btrfs_root *root = BTRFS_I(dir)->root;
	struct btrfs_path *path;
	struct extent_buffer *leaf;
	struct btrfs_dir_item *di;
	struct btrfs_key key;
	u64 index;
	int ret;
	u64 dir_ino = btrfs_ino(BTRFS_I(dir));

	path = btrfs_alloc_path();
	if (!path)
		return -ENOMEM;

	di = btrfs_lookup_dir_item(trans, root, path, dir_ino,
				   name, name_len, -1);
	if (IS_ERR_OR_NULL(di)) {
		ret = di ? PTR_ERR(di) : -ENOENT;
		goto out;
	}

	leaf = path->nodes[0];
	btrfs_dir_item_key_to_cpu(leaf, di, &key);
	WARN_ON(key.type != BTRFS_ROOT_ITEM_KEY || key.objectid != objectid);
	ret = btrfs_delete_one_dir_name(trans, root, path, di);
	if (ret) {
		btrfs_abort_transaction(trans, ret);
		goto out;
	}
	btrfs_release_path(path);

	ret = btrfs_del_root_ref(trans, objectid, root->root_key.objectid,
				 dir_ino, &index, name, name_len);
	if (ret < 0) {
		if (ret != -ENOENT) {
			btrfs_abort_transaction(trans, ret);
			goto out;
		}
		di = btrfs_search_dir_index_item(root, path, dir_ino,
						 name, name_len);
		if (IS_ERR_OR_NULL(di)) {
			if (!di)
				ret = -ENOENT;
			else
				ret = PTR_ERR(di);
			btrfs_abort_transaction(trans, ret);
			goto out;
		}

		leaf = path->nodes[0];
		btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
		index = key.offset;
	}
	btrfs_release_path(path);

	ret = btrfs_delete_delayed_dir_index(trans, BTRFS_I(dir), index);
	if (ret) {
		btrfs_abort_transaction(trans, ret);
		goto out;
	}

	btrfs_i_size_write(BTRFS_I(dir), dir->i_size - name_len * 2);
	inode_inc_iversion(dir);
	dir->i_mtime = dir->i_ctime = current_time(dir);
	ret = btrfs_update_inode_fallback(trans, root, dir);
	if (ret)
		btrfs_abort_transaction(trans, ret);
out:
	btrfs_free_path(path);
	return ret;
}

/*
 * Helper to check if the subvolume references other subvolumes or if it's
 * default.
 */
static noinline int may_destroy_subvol(struct btrfs_root *root)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct btrfs_path *path;
	struct btrfs_dir_item *di;
	struct btrfs_key key;
	u64 dir_id;
	int ret;

	path = btrfs_alloc_path();
	if (!path)
		return -ENOMEM;

	/* Make sure this root isn't set as the default subvol */
	dir_id = btrfs_super_root_dir(fs_info->super_copy);
	di = btrfs_lookup_dir_item(NULL, fs_info->tree_root, path,
				   dir_id, "default", 7, 0);
	if (di && !IS_ERR(di)) {
		btrfs_dir_item_key_to_cpu(path->nodes[0], di, &key);
		if (key.objectid == root->root_key.objectid) {
			ret = -EPERM;
			btrfs_err(fs_info,
				  "deleting default subvolume %llu is not allowed",
				  key.objectid);
			goto out;
		}
		btrfs_release_path(path);
	}

	key.objectid = root->root_key.objectid;
	key.type = BTRFS_ROOT_REF_KEY;
	key.offset = (u64)-1;

	ret = btrfs_search_slot(NULL, fs_info->tree_root, &key, path, 0, 0);
	if (ret < 0)
		goto out;
	BUG_ON(ret == 0);

	ret = 0;
	if (path->slots[0] > 0) {
		path->slots[0]--;
		btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
		if (key.objectid == root->root_key.objectid &&
		    key.type == BTRFS_ROOT_REF_KEY)
			ret = -ENOTEMPTY;
	}
out:
	btrfs_free_path(path);
	return ret;
}

/* Delete all dentries for inodes belonging to the root */
static void btrfs_prune_dentries(struct btrfs_root *root)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct rb_node *node;
	struct rb_node *prev;
	struct btrfs_inode *entry;
	struct inode *inode;
	u64 objectid = 0;

	if (!test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state))
		WARN_ON(btrfs_root_refs(&root->root_item) != 0);

	spin_lock(&root->inode_lock);
again:
	node = root->inode_tree.rb_node;
	prev = NULL;
	while (node) {
		prev = node;
		entry = rb_entry(node, struct btrfs_inode, rb_node);

		if (objectid < btrfs_ino(entry))
			node = node->rb_left;
		else if (objectid > btrfs_ino(entry))
			node = node->rb_right;
		else
			break;
	}
	if (!node) {
		while (prev) {
			entry = rb_entry(prev, struct btrfs_inode, rb_node);
			if (objectid <= btrfs_ino(entry)) {
				node = prev;
				break;
			}
			prev = rb_next(prev);
		}
	}
	while (node) {
		entry = rb_entry(node, struct btrfs_inode, rb_node);
		objectid = btrfs_ino(entry) + 1;
		inode = igrab(&entry->vfs_inode);
		if (inode) {
			spin_unlock(&root->inode_lock);
			if (atomic_read(&inode->i_count) > 1)
				d_prune_aliases(inode);
			/*
			 * btrfs_drop_inode will have it removed from the inode
			 * cache when its usage count hits zero.
			 */
			iput(inode);
			cond_resched();
			spin_lock(&root->inode_lock);
			goto again;
		}

		if (cond_resched_lock(&root->inode_lock))
			goto again;

		node = rb_next(node);
	}
	spin_unlock(&root->inode_lock);
}

int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry)
{
	struct btrfs_fs_info *fs_info = btrfs_sb(dentry->d_sb);
	struct btrfs_root *root = BTRFS_I(dir)->root;
	struct inode *inode = d_inode(dentry);
	struct btrfs_root *dest = BTRFS_I(inode)->root;
	struct btrfs_trans_handle *trans;
	struct btrfs_block_rsv block_rsv;
	u64 root_flags;
	int ret;
	int err;

	/*
	 * Don't allow to delete a subvolume with send in progress. This is
	 * inside the inode lock so the error handling that has to drop the bit
	 * again is not run concurrently.
	 */
	spin_lock(&dest->root_item_lock);
	if (dest->send_in_progress) {
		spin_unlock(&dest->root_item_lock);
		btrfs_warn(fs_info,
			   "attempt to delete subvolume %llu during send",
			   dest->root_key.objectid);
		return -EPERM;
	}
	root_flags = btrfs_root_flags(&dest->root_item);
	btrfs_set_root_flags(&dest->root_item,
			     root_flags | BTRFS_ROOT_SUBVOL_DEAD);
	spin_unlock(&dest->root_item_lock);

	down_write(&fs_info->subvol_sem);

	err = may_destroy_subvol(dest);
	if (err)
		goto out_up_write;

	btrfs_init_block_rsv(&block_rsv, BTRFS_BLOCK_RSV_TEMP);
	/*
	 * One for dir inode,
	 * two for dir entries,
	 * two for root ref/backref.
	 */
	err = btrfs_subvolume_reserve_metadata(root, &block_rsv, 5, true);
	if (err)
		goto out_up_write;

	trans = btrfs_start_transaction(root, 0);
	if (IS_ERR(trans)) {
		err = PTR_ERR(trans);
		goto out_release;
	}
	trans->block_rsv = &block_rsv;
	trans->bytes_reserved = block_rsv.size;

	btrfs_record_snapshot_destroy(trans, BTRFS_I(dir));

	ret = btrfs_unlink_subvol(trans, dir, dest->root_key.objectid,
				  dentry->d_name.name, dentry->d_name.len);
	if (ret) {
		err = ret;
		btrfs_abort_transaction(trans, ret);
		goto out_end_trans;
	}

	btrfs_record_root_in_trans(trans, dest);

	memset(&dest->root_item.drop_progress, 0,
		sizeof(dest->root_item.drop_progress));
	dest->root_item.drop_level = 0;
	btrfs_set_root_refs(&dest->root_item, 0);

	if (!test_and_set_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &dest->state)) {
		ret = btrfs_insert_orphan_item(trans,
					fs_info->tree_root,
					dest->root_key.objectid);
		if (ret) {
			btrfs_abort_transaction(trans, ret);
			err = ret;
			goto out_end_trans;
		}
	}

	ret = btrfs_uuid_tree_remove(trans, dest->root_item.uuid,
				  BTRFS_UUID_KEY_SUBVOL,
				  dest->root_key.objectid);
	if (ret && ret != -ENOENT) {
		btrfs_abort_transaction(trans, ret);
		err = ret;
		goto out_end_trans;
	}
	if (!btrfs_is_empty_uuid(dest->root_item.received_uuid)) {
		ret = btrfs_uuid_tree_remove(trans,
					  dest->root_item.received_uuid,
					  BTRFS_UUID_KEY_RECEIVED_SUBVOL,
					  dest->root_key.objectid);
		if (ret && ret != -ENOENT) {
			btrfs_abort_transaction(trans, ret);
			err = ret;
			goto out_end_trans;
		}
	}

out_end_trans:
	trans->block_rsv = NULL;
	trans->bytes_reserved = 0;
	ret = btrfs_end_transaction(trans);
	if (ret && !err)
		err = ret;
	inode->i_flags |= S_DEAD;
out_release:
	btrfs_subvolume_release_metadata(fs_info, &block_rsv);
out_up_write:
	up_write(&fs_info->subvol_sem);
	if (err) {
		spin_lock(&dest->root_item_lock);
		root_flags = btrfs_root_flags(&dest->root_item);
		btrfs_set_root_flags(&dest->root_item,
				root_flags & ~BTRFS_ROOT_SUBVOL_DEAD);
		spin_unlock(&dest->root_item_lock);
	} else {
		d_invalidate(dentry);
		btrfs_prune_dentries(dest);
		ASSERT(dest->send_in_progress == 0);

		/* the last ref */
		if (dest->ino_cache_inode) {
			iput(dest->ino_cache_inode);
			dest->ino_cache_inode = NULL;
		}
	}

	return err;
}

static int btrfs_rmdir(struct inode *dir, struct dentry *dentry)
{
	struct inode *inode = d_inode(dentry);
	int err = 0;
	struct btrfs_root *root = BTRFS_I(dir)->root;
	struct btrfs_trans_handle *trans;
	u64 last_unlink_trans;

	if (inode->i_size > BTRFS_EMPTY_DIR_SIZE)
		return -ENOTEMPTY;
	if (btrfs_ino(BTRFS_I(inode)) == BTRFS_FIRST_FREE_OBJECTID)
		return btrfs_delete_subvolume(dir, dentry);

	trans = __unlink_start_trans(dir);
	if (IS_ERR(trans))
		return PTR_ERR(trans);

	if (unlikely(btrfs_ino(BTRFS_I(inode)) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)) {
		err = btrfs_unlink_subvol(trans, dir,
					  BTRFS_I(inode)->location.objectid,
					  dentry->d_name.name,
					  dentry->d_name.len);
		goto out;
	}

	err = btrfs_orphan_add(trans, BTRFS_I(inode));
	if (err)
		goto out;

	last_unlink_trans = BTRFS_I(inode)->last_unlink_trans;

	/* now the directory is empty */
	err = btrfs_unlink_inode(trans, root, BTRFS_I(dir),
			BTRFS_I(d_inode(dentry)), dentry->d_name.name,
			dentry->d_name.len);
	if (!err) {
		btrfs_i_size_write(BTRFS_I(inode), 0);
		/*
		 * Propagate the last_unlink_trans value of the deleted dir to
		 * its parent directory. This is to prevent an unrecoverable
		 * log tree in the case we do something like this:
		 * 1) create dir foo
		 * 2) create snapshot under dir foo
		 * 3) delete the snapshot
		 * 4) rmdir foo
		 * 5) mkdir foo
		 * 6) fsync foo or some file inside foo
		 */
		if (last_unlink_trans >= trans->transid)
			BTRFS_I(dir)->last_unlink_trans = last_unlink_trans;
	}
out:
	btrfs_end_transaction(trans);
	btrfs_btree_balance_dirty(root->fs_info);

	return err;
}

static int truncate_space_check(struct btrfs_trans_handle *trans,
				struct btrfs_root *root,
				u64 bytes_deleted)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	int ret;

	/*
	 * This is only used to apply pressure to the enospc system, we don't
	 * intend to use this reservation at all.
	 */
	bytes_deleted = btrfs_csum_bytes_to_leaves(fs_info, bytes_deleted);
	bytes_deleted *= fs_info->nodesize;
	ret = btrfs_block_rsv_add(root, &fs_info->trans_block_rsv,
				  bytes_deleted, BTRFS_RESERVE_NO_FLUSH);
	if (!ret) {
		trace_btrfs_space_reservation(fs_info, "transaction",
					      trans->transid,
					      bytes_deleted, 1);
		trans->bytes_reserved += bytes_deleted;
	}
	return ret;

}

/*
 * Return this if we need to call truncate_block for the last bit of the
 * truncate.
 */
#define NEED_TRUNCATE_BLOCK 1

/*
 * this can truncate away extent items, csum items and directory items.
 * It starts at a high offset and removes keys until it can't find
 * any higher than new_size
 *
 * csum items that cross the new i_size are truncated to the new size
 * as well.
 *
 * min_type is the minimum key type to truncate down to.  If set to 0, this
 * will kill all the items on this inode, including the INODE_ITEM_KEY.
 */
int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
			       struct btrfs_root *root,
			       struct inode *inode,
			       u64 new_size, u32 min_type)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct btrfs_path *path;
	struct extent_buffer *leaf;
	struct btrfs_file_extent_item *fi;
	struct btrfs_key key;
	struct btrfs_key found_key;
	u64 extent_start = 0;
	u64 extent_num_bytes = 0;
	u64 extent_offset = 0;
	u64 item_end = 0;
	u64 last_size = new_size;
	u32 found_type = (u8)-1;
	int found_extent;
	int del_item;
	int pending_del_nr = 0;
	int pending_del_slot = 0;
	int extent_type = -1;
	int ret;
	u64 ino = btrfs_ino(BTRFS_I(inode));
	u64 bytes_deleted = 0;
	bool be_nice = false;
	bool should_throttle = false;
	bool should_end = false;

	BUG_ON(new_size > 0 && min_type != BTRFS_EXTENT_DATA_KEY);

	/*
	 * for non-free space inodes and ref cows, we want to back off from
	 * time to time
	 */
	if (!btrfs_is_free_space_inode(BTRFS_I(inode)) &&
	    test_bit(BTRFS_ROOT_REF_COWS, &root->state))
		be_nice = true;

	path = btrfs_alloc_path();
	if (!path)
		return -ENOMEM;
	path->reada = READA_BACK;

	/*
	 * We want to drop from the next block forward in case this new size is
	 * not block aligned since we will be keeping the last block of the
	 * extent just the way it is.
	 */
	if (test_bit(BTRFS_ROOT_REF_COWS, &root->state) ||
	    root == fs_info->tree_root)
		btrfs_drop_extent_cache(BTRFS_I(inode), ALIGN(new_size,
					fs_info->sectorsize),
					(u64)-1, 0);

	/*
	 * This function is also used to drop the items in the log tree before
	 * we relog the inode, so if root != BTRFS_I(inode)->root, it means
	 * it is used to drop the loged items. So we shouldn't kill the delayed
	 * items.
	 */
	if (min_type == 0 && root == BTRFS_I(inode)->root)
		btrfs_kill_delayed_inode_items(BTRFS_I(inode));

	key.objectid = ino;
	key.offset = (u64)-1;
	key.type = (u8)-1;

search_again:
	/*
	 * with a 16K leaf size and 128MB extents, you can actually queue
	 * up a huge file in a single leaf.  Most of the time that
	 * bytes_deleted is > 0, it will be huge by the time we get here
	 */
	if (be_nice && bytes_deleted > SZ_32M &&
	    btrfs_should_end_transaction(trans)) {
		ret = -EAGAIN;
		goto out;
	}

	path->leave_spinning = 1;
	ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
	if (ret < 0)
		goto out;

	if (ret > 0) {
		ret = 0;
		/* there are no items in the tree for us to truncate, we're
		 * done
		 */
		if (path->slots[0] == 0)
			goto out;
		path->slots[0]--;
	}

	while (1) {
		fi = NULL;
		leaf = path->nodes[0];
		btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
		found_type = found_key.type;

		if (found_key.objectid != ino)
			break;

		if (found_type < min_type)
			break;

		item_end = found_key.offset;
		if (found_type == BTRFS_EXTENT_DATA_KEY) {
			fi = btrfs_item_ptr(leaf, path->slots[0],
					    struct btrfs_file_extent_item);
			extent_type = btrfs_file_extent_type(leaf, fi);
			if (extent_type != BTRFS_FILE_EXTENT_INLINE) {
				item_end +=
				    btrfs_file_extent_num_bytes(leaf, fi);

				trace_btrfs_truncate_show_fi_regular(
					BTRFS_I(inode), leaf, fi,
					found_key.offset);
			} else if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
				item_end += btrfs_file_extent_ram_bytes(leaf,
									fi);

				trace_btrfs_truncate_show_fi_inline(
					BTRFS_I(inode), leaf, fi, path->slots[0],
					found_key.offset);
			}
			item_end--;
		}
		if (found_type > min_type) {
			del_item = 1;
		} else {
			if (item_end < new_size)
				break;
			if (found_key.offset >= new_size)
				del_item = 1;
			else
				del_item = 0;
		}
		found_extent = 0;
		/* FIXME, shrink the extent if the ref count is only 1 */
		if (found_type != BTRFS_EXTENT_DATA_KEY)
			goto delete;

		if (extent_type != BTRFS_FILE_EXTENT_INLINE) {
			u64 num_dec;
			extent_start = btrfs_file_extent_disk_bytenr(leaf, fi);
			if (!del_item) {
				u64 orig_num_bytes =
					btrfs_file_extent_num_bytes(leaf, fi);
				extent_num_bytes = ALIGN(new_size -
						found_key.offset,
						fs_info->sectorsize);
				btrfs_set_file_extent_num_bytes(leaf, fi,
							 extent_num_bytes);
				num_dec = (orig_num_bytes -
					   extent_num_bytes);
				if (test_bit(BTRFS_ROOT_REF_COWS,
					     &root->state) &&
				    extent_start != 0)
					inode_sub_bytes(inode, num_dec);
				btrfs_mark_buffer_dirty(leaf);
			} else {
				extent_num_bytes =
					btrfs_file_extent_disk_num_bytes(leaf,
									 fi);
				extent_offset = found_key.offset -
					btrfs_file_extent_offset(leaf, fi);

				/* FIXME blocksize != 4096 */
				num_dec = btrfs_file_extent_num_bytes(leaf, fi);
				if (extent_start != 0) {
					found_extent = 1;
					if (test_bit(BTRFS_ROOT_REF_COWS,
						     &root->state))
						inode_sub_bytes(inode, num_dec);
				}
			}
		} else if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
			/*
			 * we can't truncate inline items that have had
			 * special encodings
			 */
			if (!del_item &&
			    btrfs_file_extent_encryption(leaf, fi) == 0 &&
			    btrfs_file_extent_other_encoding(leaf, fi) == 0 &&
			    btrfs_file_extent_compression(leaf, fi) == 0) {
				u32 size = (u32)(new_size - found_key.offset);

				btrfs_set_file_extent_ram_bytes(leaf, fi, size);
				size = btrfs_file_extent_calc_inline_size(size);
				btrfs_truncate_item(root->fs_info, path, size, 1);
			} else if (!del_item) {
				/*
				 * We have to bail so the last_size is set to
				 * just before this extent.
				 */
				ret = NEED_TRUNCATE_BLOCK;
				break;
			}

			if (test_bit(BTRFS_ROOT_REF_COWS, &root->state))
				inode_sub_bytes(inode, item_end + 1 - new_size);
		}
delete:
		if (del_item)
			last_size = found_key.offset;
		else
			last_size = new_size;
		if (del_item) {
			if (!pending_del_nr) {
				/* no pending yet, add ourselves */
				pending_del_slot = path->slots[0];
				pending_del_nr = 1;
			} else if (pending_del_nr &&
				   path->slots[0] + 1 == pending_del_slot) {
				/* hop on the pending chunk */
				pending_del_nr++;
				pending_del_slot = path->slots[0];
			} else {
				BUG();
			}
		} else {
			break;
		}
		should_throttle = false;

		if (found_extent &&
		    (test_bit(BTRFS_ROOT_REF_COWS, &root->state) ||
		     root == fs_info->tree_root)) {
			btrfs_set_path_blocking(path);
			bytes_deleted += extent_num_bytes;
			ret = btrfs_free_extent(trans, root, extent_start,
						extent_num_bytes, 0,
						btrfs_header_owner(leaf),
						ino, extent_offset);
			if (ret) {
				btrfs_abort_transaction(trans, ret);
				break;
			}
			if (btrfs_should_throttle_delayed_refs(trans))
				btrfs_async_run_delayed_refs(fs_info,
					trans->delayed_ref_updates * 2,
					trans->transid, 0);
			if (be_nice) {
				if (truncate_space_check(trans, root,
							 extent_num_bytes)) {
					should_end = true;
				}
				if (btrfs_should_throttle_delayed_refs(trans))
					should_throttle = true;
			}
		}

		if (found_type == BTRFS_INODE_ITEM_KEY)
			break;

		if (path->slots[0] == 0 ||
		    path->slots[0] != pending_del_slot ||
		    should_throttle || should_end) {
			if (pending_del_nr) {
				ret = btrfs_del_items(trans, root, path,
						pending_del_slot,
						pending_del_nr);
				if (ret) {
					btrfs_abort_transaction(trans, ret);
					break;
				}
				pending_del_nr = 0;
			}
			btrfs_release_path(path);
			if (should_throttle) {
				unsigned long updates = trans->delayed_ref_updates;
				if (updates) {
					trans->delayed_ref_updates = 0;
					ret = btrfs_run_delayed_refs(trans,
								   updates * 2);
					if (ret)
						break;
				}
			}
			/*
			 * if we failed to refill our space rsv, bail out
			 * and let the transaction restart
			 */
			if (should_end) {
				ret = -EAGAIN;
				break;
			}
			goto search_again;
		} else {
			path->slots[0]--;
		}
	}
out:
	if (ret >= 0 && pending_del_nr) {
		int err;

		err = btrfs_del_items(trans, root, path, pending_del_slot,
				      pending_del_nr);
		if (err) {
			btrfs_abort_transaction(trans, err);
			ret = err;
		}
	}
	if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) {
		ASSERT(last_size >= new_size);
		if (!ret && last_size > new_size)
			last_size = new_size;
		btrfs_ordered_update_i_size(inode, last_size, NULL);
	}

	btrfs_free_path(path);

	if (be_nice && bytes_deleted > SZ_32M && (ret >= 0 || ret == -EAGAIN)) {
		unsigned long updates = trans->delayed_ref_updates;
		int err;

		if (updates) {
			trans->delayed_ref_updates = 0;
			err = btrfs_run_delayed_refs(trans, updates * 2);
			if (err)
				ret = err;
		}
	}
	return ret;
}

/*
 * btrfs_truncate_block - read, zero a chunk and write a block
 * @inode - inode that we're zeroing
 * @from - the offset to start zeroing
 * @len - the length to zero, 0 to zero the entire range respective to the
 *	offset
 * @front - zero up to the offset instead of from the offset on
 *
 * This will find the block for the "from" offset and cow the block and zero the
 * part we want to zero.  This is used with truncate and hole punching.
 */
int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len,
			int front)
{
	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
	struct address_space *mapping = inode->i_mapping;
	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
	struct btrfs_ordered_extent *ordered;
	struct extent_state *cached_state = NULL;
	struct extent_changeset *data_reserved = NULL;
	char *kaddr;
	u32 blocksize = fs_info->sectorsize;
	pgoff_t index = from >> PAGE_SHIFT;
	unsigned offset = from & (blocksize - 1);
	struct page *page;
	gfp_t mask = btrfs_alloc_write_mask(mapping);
	int ret = 0;
	u64 block_start;
	u64 block_end;

	if (IS_ALIGNED(offset, blocksize) &&
	    (!len || IS_ALIGNED(len, blocksize)))
		goto out;

	block_start = round_down(from, blocksize);
	block_end = block_start + blocksize - 1;

	ret = btrfs_delalloc_reserve_space(inode, &data_reserved,
					   block_start, blocksize);
	if (ret)
		goto out;

again:
	page = find_or_create_page(mapping, index, mask);
	if (!page) {
		btrfs_delalloc_release_space(inode, data_reserved,
					     block_start, blocksize, true);
		btrfs_delalloc_release_extents(BTRFS_I(inode), blocksize, true);
		ret = -ENOMEM;
		goto out;
	}

	if (!PageUptodate(page)) {
		ret = btrfs_readpage(NULL, page);
		lock_page(page);
		if (page->mapping != mapping) {
			unlock_page(page);
			put_page(page);
			goto again;
		}
		if (!PageUptodate(page)) {
			ret = -EIO;
			goto out_unlock;
		}
	}
	wait_on_page_writeback(page);

	lock_extent_bits(io_tree, block_start, block_end, &cached_state);
	set_page_extent_mapped(page);

	ordered = btrfs_lookup_ordered_extent(inode, block_start);
	if (ordered) {
		unlock_extent_cached(io_tree, block_start, block_end,
				     &cached_state);
		unlock_page(page);
		put_page(page);
		btrfs_start_ordered_extent(inode, ordered, 1);
		btrfs_put_ordered_extent(ordered);
		goto again;
	}

	clear_extent_bit(&BTRFS_I(inode)->io_tree, block_start, block_end,
			  EXTENT_DIRTY | EXTENT_DELALLOC |
			  EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG,
			  0, 0, &cached_state);

	ret = btrfs_set_extent_delalloc(inode, block_start, block_end, 0,
					&cached_state, 0);
	if (ret) {
		unlock_extent_cached(io_tree, block_start, block_end,
				     &cached_state);
		goto out_unlock;
	}

	if (offset != blocksize) {
		if (!len)
			len = blocksize - offset;
		kaddr = kmap(page);
		if (front)
			memset(kaddr + (block_start - page_offset(page)),
				0, offset);
		else
			memset(kaddr + (block_start - page_offset(page)) +  offset,
				0, len);
		flush_dcache_page(page);
		kunmap(page);
	}
	ClearPageChecked(page);
	set_page_dirty(page);
	unlock_extent_cached(io_tree, block_start, block_end, &cached_state);

out_unlock:
	if (ret)
		btrfs_delalloc_release_space(inode, data_reserved, block_start,
					     blocksize, true);
	btrfs_delalloc_release_extents(BTRFS_I(inode), blocksize, (ret != 0));
	unlock_page(page);
	put_page(page);
out:
	extent_changeset_free(data_reserved);
	return ret;
}

static int maybe_insert_hole(struct btrfs_root *root, struct inode *inode,
			     u64 offset, u64 len)
{
	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
	struct btrfs_trans_handle *trans;
	int ret;

	/*
	 * Still need to make sure the inode looks like it's been updated so
	 * that any holes get logged if we fsync.
	 */
	if (btrfs_fs_incompat(fs_info, NO_HOLES)) {
		BTRFS_I(inode)->last_trans = fs_info->generation;
		BTRFS_I(inode)->last_sub_trans = root->log_transid;
		BTRFS_I(inode)->last_log_commit = root->last_log_commit;
		return 0;
	}

	/*
	 * 1 - for the one we're dropping
	 * 1 - for the one we're adding
	 * 1 - for updating the inode.
	 */
	trans = btrfs_start_transaction(root, 3);
	if (IS_ERR(trans))
		return PTR_ERR(trans);

	ret = btrfs_drop_extents(trans, root, inode, offset, offset + len, 1);
	if (ret) {
		btrfs_abort_transaction(trans, ret);
		btrfs_end_transaction(trans);
		return ret;
	}

	ret = btrfs_insert_file_extent(trans, root, btrfs_ino(BTRFS_I(inode)),
			offset, 0, 0, len, 0, len, 0, 0, 0);
	if (ret)
		btrfs_abort_transaction(trans, ret);
	else
		btrfs_update_inode(trans, root, inode);
	btrfs_end_transaction(trans);
	return ret;
}

/*
 * This function puts in dummy file extents for the area we're creating a hole
 * for.  So if we are truncating this file to a larger size we need to insert
 * these file extents so that btrfs_get_extent will return a EXTENT_MAP_HOLE for
 * the range between oldsize and size
 */
int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
{
	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
	struct btrfs_root *root = BTRFS_I(inode)->root;
	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
	struct extent_map *em = NULL;
	struct extent_state *cached_state = NULL;
	struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
	u64 hole_start = ALIGN(oldsize, fs_info->sectorsize);
	u64 block_end = ALIGN(size, fs_info->sectorsize);
	u64 last_byte;
	u64 cur_offset;
	u64 hole_size;
	int err = 0;

	/*
	 * If our size started in the middle of a block we need to zero out the
	 * rest of the block before we expand the i_size, otherwise we could
	 * expose stale data.
	 */
	err = btrfs_truncate_block(inode, oldsize, 0, 0);
	if (err)
		return err;

	if (size <= hole_start)
		return 0;

	while (1) {
		struct btrfs_ordered_extent *ordered;

		lock_extent_bits(io_tree, hole_start, block_end - 1,
				 &cached_state);
		ordered = btrfs_lookup_ordered_range(BTRFS_I(inode), hole_start,
						     block_end - hole_start);
		if (!ordered)
			break;
		unlock_extent_cached(io_tree, hole_start, block_end - 1,
				     &cached_state);
		btrfs_start_ordered_extent(inode, ordered, 1);
		btrfs_put_ordered_extent(ordered);
	}

	cur_offset = hole_start;
	while (1) {
		em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, cur_offset,
				block_end - cur_offset, 0);
		if (IS_ERR(em)) {
			err = PTR_ERR(em);
			em = NULL;
			break;
		}
		last_byte = min(extent_map_end(em), block_end);
		last_byte = ALIGN(last_byte, fs_info->sectorsize);
		if (!test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) {
			struct extent_map *hole_em;
			hole_size = last_byte - cur_offset;

			err = maybe_insert_hole(root, inode, cur_offset,
						hole_size);
			if (err)
				break;
			btrfs_drop_extent_cache(BTRFS_I(inode), cur_offset,
						cur_offset + hole_size - 1, 0);
			hole_em = alloc_extent_map();
			if (!hole_em) {
				set_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
					&BTRFS_I(inode)->runtime_flags);
				goto next;
			}
			hole_em->start = cur_offset;
			hole_em->len = hole_size;
			hole_em->orig_start = cur_offset;

			hole_em->block_start = EXTENT_MAP_HOLE;
			hole_em->block_len = 0;
			hole_em->orig_block_len = 0;
			hole_em->ram_bytes = hole_size;
			hole_em->bdev = fs_info->fs_devices->latest_bdev;
			hole_em->compress_type = BTRFS_COMPRESS_NONE;
			hole_em->generation = fs_info->generation;

			while (1) {
				write_lock(&em_tree->lock);
				err = add_extent_mapping(em_tree, hole_em, 1);
				write_unlock(&em_tree->lock);
				if (err != -EEXIST)
					break;
				btrfs_drop_extent_cache(BTRFS_I(inode),
							cur_offset,
							cur_offset +
							hole_size - 1, 0);
			}
			free_extent_map(hole_em);
		}
next:
		free_extent_map(em);
		em = NULL;
		cur_offset = last_byte;
		if (cur_offset >= block_end)
			break;
	}
	free_extent_map(em);
	unlock_extent_cached(io_tree, hole_start, block_end - 1, &cached_state);
	return err;
}

static int btrfs_setsize(struct inode *inode, struct iattr *attr)
{
	struct btrfs_root *root = BTRFS_I(inode)->root;
	struct btrfs_trans_handle *trans;
	loff_t oldsize = i_size_read(inode);
	loff_t newsize = attr->ia_size;
	int mask = attr->ia_valid;
	int ret;

	/*
	 * The regular truncate() case without ATTR_CTIME and ATTR_MTIME is a
	 * special case where we need to update the times despite not having
	 * these flags set.  For all other operations the VFS set these flags
	 * explicitly if it wants a timestamp update.
	 */
	if (newsize != oldsize) {
		inode_inc_iversion(inode);
		if (!(mask & (ATTR_CTIME | ATTR_MTIME)))
			inode->i_ctime = inode->i_mtime =
				current_time(inode);
	}

	if (newsize > oldsize) {
		/*
		 * Don't do an expanding truncate while snapshotting is ongoing.
		 * This is to ensure the snapshot captures a fully consistent
		 * state of this file - if the snapshot captures this expanding
		 * truncation, it must capture all writes that happened before
		 * this truncation.
		 */
		btrfs_wait_for_snapshot_creation(root);
		ret = btrfs_cont_expand(inode, oldsize, newsize);
		if (ret) {
			btrfs_end_write_no_snapshotting(root);
			return ret;
		}

		trans = btrfs_start_transaction(root, 1);
		if (IS_ERR(trans)) {
			btrfs_end_write_no_snapshotting(root);
			return PTR_ERR(trans);
		}

		i_size_write(inode, newsize);
		btrfs_ordered_update_i_size(inode, i_size_read(inode), NULL);
		pagecache_isize_extended(inode, oldsize, newsize);
		ret = btrfs_update_inode(trans, root, inode);
		btrfs_end_write_no_snapshotting(root);
		btrfs_end_transaction(trans);
	} else {

		/*
		 * We're truncating a file that used to have good data down to
		 * zero. Make sure it gets into the ordered flush list so that
		 * any new writes get down to disk quickly.
		 */
		if (newsize == 0)
			set_bit(BTRFS_INODE_ORDERED_DATA_CLOSE,
				&BTRFS_I(inode)->runtime_flags);

		truncate_setsize(inode, newsize);

		/* Disable nonlocked read DIO to avoid the end less truncate */
		btrfs_inode_block_unlocked_dio(BTRFS_I(inode));
		inode_dio_wait(inode);
		btrfs_inode_resume_unlocked_dio(BTRFS_I(inode));

		ret = btrfs_truncate(inode, newsize == oldsize);
		if (ret && inode->i_nlink) {
			int err;

			/*
			 * Truncate failed, so fix up the in-memory size. We
			 * adjusted disk_i_size down as we removed extents, so
			 * wait for disk_i_size to be stable and then update the
			 * in-memory size to match.
			 */
			err = btrfs_wait_ordered_range(inode, 0, (u64)-1);
			if (err)
				return err;
			i_size_write(inode, BTRFS_I(inode)->disk_i_size);
		}
	}

	return ret;
}

static int btrfs_setattr(struct dentry *dentry, struct iattr *attr)
{
	struct inode *inode = d_inode(dentry);
	struct btrfs_root *root = BTRFS_I(inode)->root;
	int err;

	if (btrfs_root_readonly(root))
		return -EROFS;

	err = setattr_prepare(dentry, attr);
	if (err)
		return err;

	if (S_ISREG(inode->i_mode) && (attr->ia_valid & ATTR_SIZE)) {
		err = btrfs_setsize(inode, attr);
		if (err)
			return err;
	}

	if (attr->ia_valid) {
		setattr_copy(inode, attr);
		inode_inc_iversion(inode);
		err = btrfs_dirty_inode(inode);

		if (!err && attr->ia_valid & ATTR_MODE)
			err = posix_acl_chmod(inode, inode->i_mode);
	}

	return err;
}

/*
 * While truncating the inode pages during eviction, we get the VFS calling
 * btrfs_invalidatepage() against each page of the inode. This is slow because
 * the calls to btrfs_invalidatepage() result in a huge amount of calls to
 * lock_extent_bits() and clear_extent_bit(), which keep merging and splitting
 * extent_state structures over and over, wasting lots of time.
 *
 * Therefore if the inode is being evicted, let btrfs_invalidatepage() skip all
 * those expensive operations on a per page basis and do only the ordered io
 * finishing, while we release here the extent_map and extent_state structures,
 * without the excessive merging and splitting.
 */
static void evict_inode_truncate_pages(struct inode *inode)
{
	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
	struct extent_map_tree *map_tree = &BTRFS_I(inode)->extent_tree;
	struct rb_node *node;

	ASSERT(inode->i_state & I_FREEING);
	truncate_inode_pages_final(&inode->i_data);

	write_lock(&map_tree->lock);
	while (!RB_EMPTY_ROOT(&map_tree->map.rb_root)) {
		struct extent_map *em;

		node = rb_first_cached(&map_tree->map);
		em = rb_entry(node, struct extent_map, rb_node);
		clear_bit(EXTENT_FLAG_PINNED, &em->flags);
		clear_bit(EXTENT_FLAG_LOGGING, &em->flags);
		remove_extent_mapping(map_tree, em);
		free_extent_map(em);
		if (need_resched()) {
			write_unlock(&map_tree->lock);
			cond_resched();
			write_lock(&map_tree->lock);
		}
	}
	write_unlock(&map_tree->lock);

	/*
	 * Keep looping until we have no more ranges in the io tree.
	 * We can have ongoing bios started by readpages (called from readahead)
	 * that have their endio callback (extent_io.c:end_bio_extent_readpage)
	 * still in progress (unlocked the pages in the bio but did not yet
	 * unlocked the ranges in the io tree). Therefore this means some
	 * ranges can still be locked and eviction started because before
	 * submitting those bios, which are executed by a separate task (work
	 * queue kthread), inode references (inode->i_count) were not taken
	 * (which would be dropped in the end io callback of each bio).
	 * Therefore here we effectively end up waiting for those bios and
	 * anyone else holding locked ranges without having bumped the inode's
	 * reference count - if we don't do it, when they access the inode's
	 * io_tree to unlock a range it may be too late, leading to an
	 * use-after-free issue.
	 */
	spin_lock(&io_tree->lock);
	while (!RB_EMPTY_ROOT(&io_tree->state)) {
		struct extent_state *state;
		struct extent_state *cached_state = NULL;
		u64 start;
		u64 end;
		unsigned state_flags;

		node = rb_first(&io_tree->state);
		state = rb_entry(node, struct extent_state, rb_node);
		start = state->start;
		end = state->end;
		state_flags = state->state;
		spin_unlock(&io_tree->lock);

		lock_extent_bits(io_tree, start, end, &cached_state);

		/*
		 * If still has DELALLOC flag, the extent didn't reach disk,
		 * and its reserved space won't be freed by delayed_ref.
		 * So we need to free its reserved space here.
		 * (Refer to comment in btrfs_invalidatepage, case 2)
		 *
		 * Note, end is the bytenr of last byte, so we need + 1 here.
		 */
		if (state_flags & EXTENT_DELALLOC)
			btrfs_qgroup_free_data(inode, NULL, start, end - start + 1);

		clear_extent_bit(io_tree, start, end,
				 EXTENT_LOCKED | EXTENT_DIRTY |
				 EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING |
				 EXTENT_DEFRAG, 1, 1, &cached_state);

		cond_resched();
		spin_lock(&io_tree->lock);
	}
	spin_unlock(&io_tree->lock);
}

static struct btrfs_trans_handle *evict_refill_and_join(struct btrfs_root *root,
							struct btrfs_block_rsv *rsv)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv;
	int failures = 0;

	for (;;) {
		struct btrfs_trans_handle *trans;
		int ret;

		ret = btrfs_block_rsv_refill(root, rsv, rsv->size,
					     BTRFS_RESERVE_FLUSH_LIMIT);

		if (ret && ++failures > 2) {
			btrfs_warn(fs_info,
				   "could not allocate space for a delete; will truncate on mount");
			return ERR_PTR(-ENOSPC);
		}

		trans = btrfs_join_transaction(root);
		if (IS_ERR(trans) || !ret)
			return trans;

		/*
		 * Try to steal from the global reserve if there is space for
		 * it.
		 */
		if (!btrfs_check_space_for_delayed_refs(trans) &&
		    !btrfs_block_rsv_migrate(global_rsv, rsv, rsv->size, false))
			return trans;

		/* If not, commit and try again. */
		ret = btrfs_commit_transaction(trans);
		if (ret)
			return ERR_PTR(ret);
	}
}

void btrfs_evict_inode(struct inode *inode)
{
	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
	struct btrfs_trans_handle *trans;
	struct btrfs_root *root = BTRFS_I(inode)->root;
	struct btrfs_block_rsv *rsv;
	int ret;

	trace_btrfs_inode_evict(inode);

	if (!root) {
		clear_inode(inode);
		return;
	}

	evict_inode_truncate_pages(inode);

	if (inode->i_nlink &&
	    ((btrfs_root_refs(&root->root_item) != 0 &&
	      root->root_key.objectid != BTRFS_ROOT_TREE_OBJECTID) ||
	     btrfs_is_free_space_inode(BTRFS_I(inode))))
		goto no_delete;

	if (is_bad_inode(inode))
		goto no_delete;

	btrfs_free_io_failure_record(BTRFS_I(inode), 0, (u64)-1);

	if (test_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags))
		goto no_delete;

	if (inode->i_nlink > 0) {
		BUG_ON(btrfs_root_refs(&root->root_item) != 0 &&
		       root->root_key.objectid != BTRFS_ROOT_TREE_OBJECTID);
		goto no_delete;
	}

	ret = btrfs_commit_inode_delayed_inode(BTRFS_I(inode));
	if (ret)
		goto no_delete;

	rsv = btrfs_alloc_block_rsv(fs_info, BTRFS_BLOCK_RSV_TEMP);
	if (!rsv)
		goto no_delete;
	rsv->size = btrfs_calc_trunc_metadata_size(fs_info, 1);
	rsv->failfast = 1;

	btrfs_i_size_write(BTRFS_I(inode), 0);

	while (1) {
		trans = evict_refill_and_join(root, rsv);
		if (IS_ERR(trans))
			goto free_rsv;

		trans->block_rsv = rsv;

		ret = btrfs_truncate_inode_items(trans, root, inode, 0, 0);
		trans->block_rsv = &fs_info->trans_block_rsv;
		btrfs_end_transaction(trans);
		btrfs_btree_balance_dirty(fs_info);
		if (ret && ret != -ENOSPC && ret != -EAGAIN)
			goto free_rsv;
		else if (!ret)
			break;
	}

	/*
	 * Errors here aren't a big deal, it just means we leave orphan items in
	 * the tree. They will be cleaned up on the next mount. If the inode
	 * number gets reused, cleanup deletes the orphan item without doing
	 * anything, and unlink reuses the existing orphan item.
	 *
	 * If it turns out that we are dropping too many of these, we might want
	 * to add a mechanism for retrying these after a commit.
	 */
	trans = evict_refill_and_join(root, rsv);
	if (!IS_ERR(trans)) {
		trans->block_rsv = rsv;
		btrfs_orphan_del(trans, BTRFS_I(inode));
		trans->block_rsv = &fs_info->trans_block_rsv;
		btrfs_end_transaction(trans);
	}

	if (!(root == fs_info->tree_root ||
	      root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID))
		btrfs_return_ino(root, btrfs_ino(BTRFS_I(inode)));

free_rsv:
	btrfs_free_block_rsv(fs_info, rsv);
no_delete:
	/*
	 * If we didn't successfully delete, the orphan item will still be in
	 * the tree and we'll retry on the next mount. Again, we might also want
	 * to retry these periodically in the future.
	 */
	btrfs_remove_delayed_node(BTRFS_I(inode));
	clear_inode(inode);
}

/*
 * this returns the key found in the dir entry in the location pointer.
 * If no dir entries were found, returns -ENOENT.
 * If found a corrupted location in dir entry, returns -EUCLEAN.
 */
static int btrfs_inode_by_name(struct inode *dir, struct dentry *dentry,
			       struct btrfs_key *location)
{
	const char *name = dentry->d_name.name;
	int namelen = dentry->d_name.len;
	struct btrfs_dir_item *di;
	struct btrfs_path *path;
	struct btrfs_root *root = BTRFS_I(dir)->root;
	int ret = 0;

	path = btrfs_alloc_path();
	if (!path)
		return -ENOMEM;

	di = btrfs_lookup_dir_item(NULL, root, path, btrfs_ino(BTRFS_I(dir)),
			name, namelen, 0);
	if (IS_ERR_OR_NULL(di)) {
		ret = di ? PTR_ERR(di) : -ENOENT;
		goto out;
	}

	btrfs_dir_item_key_to_cpu(path->nodes[0], di, location);
	if (location->type != BTRFS_INODE_ITEM_KEY &&
	    location->type != BTRFS_ROOT_ITEM_KEY) {
		ret = -EUCLEAN;
		btrfs_warn(root->fs_info,
"%s gets something invalid in DIR_ITEM (name %s, directory ino %llu, location(%llu %u %llu))",
			   __func__, name, btrfs_ino(BTRFS_I(dir)),
			   location->objectid, location->type, location->offset);
	}
out:
	btrfs_free_path(path);
	return ret;
}

/*
 * when we hit a tree root in a directory, the btrfs part of the inode
 * needs to be changed to reflect the root directory of the tree root.  This
 * is kind of like crossing a mount point.
 */
static int fixup_tree_root_location(struct btrfs_fs_info *fs_info,
				    struct inode *dir,
				    struct dentry *dentry,
				    struct btrfs_key *location,
				    struct btrfs_root **sub_root)
{
	struct btrfs_path *path;
	struct btrfs_root *new_root;
	struct btrfs_root_ref *ref;
	struct extent_buffer *leaf;
	struct btrfs_key key;
	int ret;
	int err = 0;

	path = btrfs_alloc_path();
	if (!path) {
		err = -ENOMEM;
		goto out;
	}

	err = -ENOENT;
	key.objectid = BTRFS_I(dir)->root->root_key.objectid;
	key.type = BTRFS_ROOT_REF_KEY;
	key.offset = location->objectid;

	ret = btrfs_search_slot(NULL, fs_info->tree_root, &key, path, 0, 0);
	if (ret) {
		if (ret < 0)
			err = ret;
		goto out;
	}

	leaf = path->nodes[0];
	ref = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_root_ref);
	if (btrfs_root_ref_dirid(leaf, ref) != btrfs_ino(BTRFS_I(dir)) ||
	    btrfs_root_ref_name_len(leaf, ref) != dentry->d_name.len)
		goto out;

	ret = memcmp_extent_buffer(leaf, dentry->d_name.name,
				   (unsigned long)(ref + 1),
				   dentry->d_name.len);
	if (ret)
		goto out;

	btrfs_release_path(path);

	new_root = btrfs_read_fs_root_no_name(fs_info, location);
	if (IS_ERR(new_root)) {
		err = PTR_ERR(new_root);
		goto out;
	}

	*sub_root = new_root;
	location->objectid = btrfs_root_dirid(&new_root->root_item);
	location->type = BTRFS_INODE_ITEM_KEY;
	location->offset = 0;
	err = 0;
out:
	btrfs_free_path(path);
	return err;
}

static void inode_tree_add(struct inode *inode)
{
	struct btrfs_root *root = BTRFS_I(inode)->root;
	struct btrfs_inode *entry;
	struct rb_node **p;
	struct rb_node *parent;
	struct rb_node *new = &BTRFS_I(inode)->rb_node;
	u64 ino = btrfs_ino(BTRFS_I(inode));

	if (inode_unhashed(inode))
		return;
	parent = NULL;
	spin_lock(&root->inode_lock);
	p = &root->inode_tree.rb_node;
	while (*p) {
		parent = *p;
		entry = rb_entry(parent, struct btrfs_inode, rb_node);

		if (ino < btrfs_ino(entry))
			p = &parent->rb_left;
		else