12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394959697989910010110210310410510610710810911011111211311411511611711811912012112212312412512612712812913013113213313413513613713813914014114214314414514614714814915015115215315415515615715815916016116216316416516616716816917017117217317417517617717817918018118218318418518618718818919019119219319419519619719819920020120220320420520620720820921021121221321421521621721821922022122222322422522622722822923023123223323423523623723823924024124224324424524624724824925025125225325425525625725825926026126226326426526626726826927027127227327427527627727827928028128228328428528628728828929029129229329429529629729829930030130230330430530630730830931031131231331431531631731831932032132232332432532632732832933033133233333433533633733833934034134234334434534634734834935035135235335435535635735835936036136236336436536636736836937037137237337437537637737837938038138238338438538638738838939039139239339439539639739839940040140240340440540640740840941041141241341441541641741841942042142242342442542642742842943043143243343443543643743843944044144244344444544644744844945045145245345445545645745845946046146246346446546646746846947047147247347447547647747847948048148248348448548648748848949049149249349449549649749849950050150250350450550650750850951051151251351451551651751851952052152252352452552652752852953053153253353453553653753853954054154254354454554654754854955055155255355455555655755855956056156256356456556656756856957057157257357457557657757857958058158258358458558658758858959059159259359459559659759859960060160260360460560660760860961061161261361461561661761861962062162262362462562662762862963063163263363463563663763863964064164264364464564664764864965065165265365465565665765865966066166266366466566666766866967067167267367467567667767867968068168268368468568668768868969069169269369469569669769869970070170270370470570670770870971071171271371471571671771871972072172272372472572672772872973073173273373473573673773873974074174274374474574674774874975075175275375475575675775875976076176276376476576676776876977077177277377477577677777877978078178278378478578678778878979079179279379479579679779879980080180280380480580680780880981081181281381481581681781881982082182282382482582682782882983083183283383483583683783883984084184284384484584684784884985085185285385485585685785885986086186286386486586686786886987087187287387487587687787887988088188288388488588688788888989089189289389489589689789889990090190290390490590690790890991091191291391491591691791891992092192292392492592692792892993093193293393493593693793893994094194294394494594694794894995095195295395495595695795895996096196296396496596696796896997097197297397497597697797897998098198298398498598698798898999099199299399499599699799899910001001100210031004100510061007100810091010101110121013101410151016101710181019102010211022102310241025102610271028102910301031103210331034103510361037103810391040104110421043104410451046104710481049105010511052105310541055105610571058105910601061106210631064106510661067106810691070107110721073107410751076107710781079108010811082108310841085108610871088108910901091109210931094109510961097109810991100110111021103110411051106110711081109111011111112111311141115111611171118111911201121112211231124112511261127112811291130113111321133113411351136113711381139114011411142114311441145114611471148114911501151115211531154115511561157115811591160116111621163116411651166116711681169117011711172117311741175117611771178117911801181118211831184118511861187118811891190119111921193119411951196119711981199120012011202120312041205120612071208120912101211121212131214121512161217121812191220122112221223122412251226122712281229123012311232123312341235123612371238123912401241124212431244124512461247124812491250125112521253125412551256125712581259126012611262126312641265126612671268126912701271127212731274127512761277127812791280128112821283128412851286128712881289129012911292129312941295129612971298129913001301130213031304130513061307130813091310131113121313131413151316131713181319132013211322132313241325132613271328132913301331133213331334133513361337133813391340134113421343134413451346134713481349135013511352135313541355135613571358135913601361136213631364136513661367136813691370137113721373137413751376137713781379138013811382138313841385138613871388138913901391139213931394139513961397139813991400140114021403140414051406140714081409141014111412141314141415141614171418141914201421142214231424142514261427142814291430143114321433143414351436143714381439144014411442144314441445144614471448144914501451145214531454145514561457145814591460146114621463146414651466146714681469147014711472147314741475147614771478147914801481148214831484148514861487148814891490149114921493149414951496149714981499150015011502150315041505150615071508150915101511151215131514151515161517151815191520152115221523152415251526152715281529153015311532153315341535153615371538153915401541154215431544154515461547154815491550155115521553155415551556155715581559156015611562156315641565156615671568156915701571157215731574157515761577157815791580158115821583158415851586158715881589159015911592159315941595159615971598159916001601160216031604160516061607160816091610161116121613161416151616161716181619162016211622162316241625162616271628162916301631163216331634163516361637163816391640164116421643164416451646164716481649165016511652165316541655165616571658165916601661166216631664166516661667166816691670167116721673167416751676167716781679168016811682168316841685168616871688168916901691169216931694169516961697169816991700170117021703170417051706170717081709171017111712171317141715171617171718171917201721172217231724172517261727172817291730173117321733173417351736173717381739174017411742174317441745174617471748174917501751175217531754175517561757175817591760176117621763176417651766176717681769177017711772177317741775177617771778177917801781178217831784178517861787178817891790179117921793179417951796179717981799180018011802180318041805180618071808180918101811181218131814181518161817181818191820182118221823182418251826182718281829183018311832183318341835183618371838183918401841184218431844184518461847184818491850185118521853185418551856185718581859186018611862186318641865186618671868186918701871187218731874187518761877187818791880188118821883188418851886188718881889189018911892189318941895189618971898189919001901190219031904190519061907190819091910191119121913191419151916191719181919192019211922192319241925192619271928192919301931193219331934193519361937193819391940194119421943194419451946194719481949195019511952195319541955195619571958195919601961196219631964196519661967196819691970197119721973197419751976197719781979198019811982198319841985198619871988198919901991199219931994199519961997199819992000200120022003200420052006200720082009201020112012201320142015201620172018201920202021202220232024202520262027202820292030203120322033203420352036203720382039204020412042204320442045204620472048204920502051205220532054205520562057205820592060206120622063206420652066206720682069207020712072207320742075207620772078207920802081208220832084208520862087208820892090209120922093209420952096209720982099210021012102210321042105210621072108210921102111211221132114211521162117211821192120212121222123212421252126212721282129213021312132213321342135213621372138213921402141214221432144214521462147214821492150215121522153215421552156215721582159216021612162216321642165216621672168216921702171217221732174217521762177217821792180218121822183218421852186218721882189219021912192219321942195219621972198219922002201220222032204220522062207220822092210221122122213221422152216221722182219222022212222222322242225222622272228222922302231223222332234223522362237223822392240224122422243224422452246224722482249225022512252225322542255225622572258225922602261226222632264226522662267226822692270227122722273227422752276227722782279228022812282228322842285228622872288228922902291229222932294229522962297229822992300230123022303230423052306230723082309231023112312231323142315231623172318231923202321232223232324232523262327232823292330233123322333233423352336233723382339234023412342234323442345234623472348234923502351235223532354235523562357235823592360236123622363236423652366236723682369237023712372237323742375237623772378237923802381238223832384238523862387238823892390239123922393239423952396239723982399240024012402240324042405240624072408240924102411241224132414241524162417241824192420242124222423242424252426242724282429243024312432243324342435243624372438243924402441244224432444244524462447244824492450245124522453245424552456245724582459246024612462246324642465246624672468246924702471247224732474247524762477247824792480248124822483248424852486248724882489249024912492249324942495249624972498249925002501250225032504250525062507250825092510251125122513251425152516251725182519252025212522252325242525252625272528252925302531253225332534253525362537253825392540254125422543254425452546254725482549255025512552255325542555255625572558255925602561256225632564256525662567256825692570257125722573257425752576257725782579258025812582258325842585258625872588258925902591259225932594259525962597259825992600260126022603260426052606260726082609261026112612261326142615261626172618261926202621262226232624262526262627262826292630263126322633263426352636263726382639264026412642264326442645264626472648264926502651265226532654265526562657265826592660266126622663266426652666266726682669267026712672267326742675267626772678267926802681268226832684268526862687268826892690269126922693269426952696269726982699270027012702270327042705270627072708270927102711271227132714271527162717271827192720272127222723272427252726272727282729273027312732273327342735273627372738273927402741274227432744274527462747274827492750275127522753275427552756275727582759276027612762276327642765276627672768276927702771277227732774277527762777277827792780278127822783278427852786278727882789279027912792279327942795279627972798279928002801280228032804280528062807280828092810281128122813281428152816281728182819282028212822282328242825282628272828282928302831283228332834283528362837283828392840284128422843284428452846284728482849285028512852285328542855285628572858285928602861286228632864286528662867286828692870287128722873287428752876287728782879288028812882288328842885288628872888288928902891289228932894289528962897289828992900290129022903290429052906290729082909291029112912291329142915291629172918291929202921292229232924292529262927292829292930293129322933293429352936293729382939294029412942294329442945294629472948294929502951295229532954295529562957295829592960296129622963296429652966296729682969297029712972297329742975297629772978297929802981298229832984298529862987298829892990299129922993299429952996299729982999300030013002300330043005300630073008300930103011301230133014301530163017301830193020302130223023302430253026302730283029303030313032303330343035303630373038303930403041304230433044304530463047304830493050305130523053305430553056305730583059306030613062306330643065306630673068306930703071307230733074307530763077307830793080308130823083308430853086308730883089309030913092309330943095309630973098309931003101310231033104310531063107310831093110311131123113311431153116311731183119312031213122312331243125312631273128312931303131313231333134313531363137313831393140314131423143314431453146314731483149315031513152315331543155315631573158315931603161316231633164316531663167316831693170317131723173317431753176317731783179318031813182318331843185318631873188318931903191319231933194319531963197319831993200320132023203320432053206320732083209321032113212321332143215321632173218321932203221322232233224322532263227322832293230323132323233323432353236323732383239324032413242324332443245324632473248324932503251325232533254325532563257325832593260326132623263326432653266326732683269327032713272327332743275327632773278327932803281328232833284328532863287328832893290329132923293329432953296329732983299330033013302330333043305330633073308330933103311331233133314331533163317331833193320332133223323332433253326332733283329333033313332333333343335333633373338333933403341334233433344334533463347334833493350335133523353335433553356335733583359336033613362336333643365336633673368336933703371337233733374337533763377337833793380338133823383338433853386338733883389339033913392339333943395339633973398339934003401340234033404340534063407340834093410341134123413341434153416341734183419342034213422342334243425342634273428342934303431343234333434343534363437343834393440344134423443344434453446344734483449345034513452345334543455345634573458345934603461346234633464346534663467346834693470347134723473347434753476347734783479348034813482348334843485348634873488348934903491349234933494349534963497349834993500350135023503350435053506350735083509351035113512351335143515351635173518351935203521352235233524352535263527352835293530353135323533353435353536353735383539354035413542354335443545354635473548354935503551355235533554355535563557355835593560356135623563356435653566356735683569357035713572357335743575357635773578357935803581358235833584358535863587358835893590359135923593359435953596359735983599360036013602360336043605360636073608360936103611361236133614361536163617361836193620362136223623362436253626362736283629363036313632363336343635363636373638363936403641364236433644364536463647364836493650365136523653365436553656365736583659366036613662366336643665366636673668366936703671367236733674367536763677367836793680368136823683368436853686368736883689369036913692369336943695369636973698369937003701370237033704370537063707370837093710371137123713371437153716371737183719372037213722372337243725372637273728372937303731373237333734373537363737373837393740374137423743374437453746374737483749375037513752375337543755375637573758375937603761376237633764376537663767376837693770377137723773377437753776377737783779378037813782378337843785378637873788378937903791379237933794379537963797379837993800380138023803380438053806380738083809381038113812381338143815381638173818381938203821382238233824382538263827382838293830383138323833383438353836383738383839384038413842384338443845384638473848384938503851385238533854385538563857385838593860386138623863386438653866386738683869387038713872387338743875387638773878387938803881388238833884388538863887388838893890389138923893389438953896389738983899390039013902390339043905390639073908390939103911391239133914391539163917391839193920392139223923392439253926392739283929393039313932393339343935393639373938393939403941394239433944394539463947394839493950395139523953395439553956395739583959396039613962396339643965396639673968396939703971397239733974397539763977397839793980398139823983398439853986398739883989399039913992399339943995399639973998399940004001400240034004400540064007400840094010401140124013401440154016401740184019402040214022402340244025402640274028402940304031403240334034403540364037403840394040404140424043404440454046404740484049405040514052405340544055405640574058405940604061406240634064406540664067406840694070407140724073407440754076407740784079408040814082408340844085408640874088408940904091409240934094409540964097409840994100410141024103410441054106410741084109411041114112411341144115411641174118411941204121412241234124412541264127412841294130413141324133413441354136413741384139414041414142414341444145414641474148414941504151415241534154415541564157415841594160416141624163416441654166416741684169417041714172417341744175417641774178417941804181418241834184418541864187418841894190419141924193419441954196419741984199420042014202420342044205420642074208420942104211421242134214421542164217421842194220422142224223422442254226422742284229423042314232423342344235423642374238423942404241424242434244424542464247424842494250425142524253425442554256425742584259426042614262426342644265426642674268426942704271427242734274427542764277427842794280428142824283428442854286428742884289429042914292429342944295429642974298429943004301430243034304430543064307430843094310431143124313431443154316431743184319432043214322432343244325432643274328432943304331433243334334433543364337433843394340434143424343434443454346434743484349435043514352435343544355435643574358435943604361436243634364436543664367436843694370437143724373437443754376437743784379438043814382438343844385438643874388438943904391439243934394439543964397439843994400440144024403440444054406440744084409441044114412441344144415441644174418441944204421442244234424442544264427442844294430443144324433443444354436443744384439444044414442444344444445444644474448444944504451445244534454445544564457445844594460446144624463446444654466446744684469447044714472447344744475447644774478447944804481448244834484448544864487448844894490449144924493449444954496449744984499450045014502450345044505450645074508450945104511451245134514451545164517451845194520452145224523452445254526452745284529453045314532453345344535453645374538453945404541454245434544454545464547454845494550455145524553455445554556455745584559456045614562456345644565456645674568456945704571457245734574457545764577457845794580458145824583458445854586458745884589459045914592459345944595459645974598459946004601460246034604460546064607460846094610461146124613461446154616461746184619462046214622462346244625462646274628462946304631463246334634463546364637463846394640464146424643464446454646464746484649465046514652465346544655465646574658465946604661466246634664466546664667466846694670467146724673467446754676467746784679468046814682468346844685468646874688468946904691469246934694469546964697469846994700470147024703470447054706470747084709471047114712471347144715471647174718471947204721472247234724472547264727472847294730473147324733473447354736473747384739474047414742474347444745474647474748474947504751475247534754475547564757475847594760476147624763476447654766476747684769477047714772477347744775477647774778477947804781478247834784478547864787478847894790479147924793479447954796479747984799480048014802480348044805480648074808480948104811481248134814481548164817481848194820482148224823482448254826482748284829483048314832483348344835483648374838483948404841484248434844484548464847484848494850485148524853485448554856485748584859486048614862486348644865486648674868486948704871487248734874487548764877487848794880488148824883488448854886488748884889489048914892489348944895489648974898489949004901490249034904490549064907490849094910491149124913491449154916491749184919492049214922492349244925492649274928492949304931493249334934493549364937493849394940494149424943494449454946494749484949495049514952495349544955495649574958495949604961496249634964496549664967496849694970497149724973497449754976497749784979498049814982498349844985498649874988498949904991499249934994499549964997499849995000500150025003500450055006500750085009501050115012501350145015501650175018501950205021502250235024502550265027502850295030503150325033503450355036503750385039504050415042504350445045504650475048504950505051505250535054505550565057505850595060506150625063506450655066506750685069507050715072507350745075507650775078507950805081508250835084508550865087508850895090509150925093509450955096509750985099510051015102510351045105510651075108510951105111511251135114511551165117511851195120512151225123512451255126512751285129513051315132513351345135513651375138513951405141514251435144514551465147514851495150515151525153515451555156515751585159516051615162516351645165516651675168516951705171517251735174517551765177517851795180518151825183518451855186518751885189519051915192519351945195519651975198519952005201520252035204520552065207520852095210521152125213521452155216521752185219522052215222522352245225522652275228522952305231523252335234523552365237523852395240524152425243524452455246524752485249525052515252525352545255525652575258525952605261526252635264526552665267526852695270527152725273527452755276527752785279528052815282528352845285528652875288528952905291529252935294529552965297529852995300530153025303530453055306530753085309531053115312531353145315531653175318531953205321532253235324532553265327532853295330533153325333533453355336533753385339534053415342534353445345534653475348534953505351535253535354535553565357535853595360536153625363536453655366536753685369537053715372537353745375537653775378537953805381538253835384538553865387538853895390539153925393539453955396539753985399540054015402540354045405540654075408540954105411541254135414541554165417541854195420542154225423542454255426542754285429543054315432543354345435543654375438543954405441544254435444544554465447544854495450545154525453545454555456545754585459546054615462546354645465546654675468546954705471547254735474547554765477547854795480548154825483548454855486548754885489549054915492549354945495549654975498549955005501550255035504550555065507550855095510551155125513551455155516551755185519552055215522552355245525552655275528552955305531553255335534553555365537553855395540554155425543554455455546554755485549555055515552555355545555555655575558555955605561556255635564556555665567556855695570557155725573557455755576557755785579558055815582558355845585558655875588558955905591559255935594559555965597559855995600560156025603560456055606560756085609561056115612561356145615561656175618561956205621562256235624562556265627562856295630563156325633563456355636563756385639564056415642564356445645564656475648564956505651565256535654565556565657565856595660566156625663566456655666566756685669567056715672567356745675567656775678567956805681568256835684568556865687568856895690569156925693569456955696569756985699570057015702570357045705570657075708570957105711571257135714571557165717571857195720572157225723572457255726572757285729573057315732573357345735573657375738573957405741574257435744574557465747574857495750575157525753575457555756575757585759576057615762576357645765576657675768576957705771577257735774577557765777577857795780578157825783578457855786578757885789579057915792579357945795579657975798579958005801580258035804580558065807580858095810581158125813581458155816581758185819582058215822582358245825582658275828582958305831583258335834583558365837583858395840584158425843584458455846584758485849585058515852585358545855585658575858585958605861586258635864586558665867586858695870587158725873587458755876587758785879588058815882588358845885588658875888588958905891589258935894589558965897589858995900590159025903590459055906590759085909591059115912591359145915591659175918591959205921592259235924592559265927592859295930593159325933593459355936593759385939594059415942594359445945594659475948594959505951595259535954595559565957595859595960596159625963596459655966596759685969597059715972597359745975597659775978597959805981598259835984598559865987598859895990599159925993599459955996599759985999600060016002600360046005600660076008600960106011601260136014601560166017601860196020602160226023602460256026602760286029603060316032603360346035603660376038603960406041604260436044604560466047604860496050605160526053605460556056605760586059606060616062606360646065606660676068606960706071607260736074607560766077607860796080608160826083608460856086608760886089609060916092609360946095609660976098609961006101610261036104610561066107610861096110611161126113611461156116611761186119612061216122612361246125612661276128612961306131613261336134613561366137613861396140614161426143614461456146614761486149615061516152615361546155615661576158615961606161616261636164616561666167616861696170617161726173617461756176617761786179618061816182618361846185618661876188618961906191619261936194619561966197619861996200620162026203620462056206620762086209621062116212621362146215621662176218621962206221622262236224622562266227622862296230623162326233623462356236623762386239624062416242624362446245624662476248624962506251625262536254625562566257625862596260626162626263626462656266626762686269627062716272627362746275627662776278627962806281628262836284628562866287628862896290629162926293629462956296629762986299630063016302630363046305630663076308630963106311631263136314631563166317631863196320632163226323632463256326632763286329633063316332633363346335633663376338633963406341634263436344634563466347634863496350635163526353635463556356635763586359636063616362636363646365636663676368636963706371637263736374637563766377637863796380638163826383638463856386638763886389639063916392639363946395639663976398639964006401640264036404640564066407640864096410641164126413641464156416641764186419642064216422642364246425642664276428642964306431643264336434643564366437643864396440644164426443644464456446644764486449645064516452645364546455645664576458645964606461646264636464646564666467646864696470647164726473647464756476647764786479648064816482648364846485648664876488648964906491649264936494649564966497649864996500650165026503650465056506650765086509651065116512651365146515651665176518651965206521652265236524652565266527652865296530653165326533653465356536653765386539654065416542654365446545654665476548654965506551655265536554655565566557655865596560656165626563656465656566656765686569657065716572657365746575657665776578657965806581658265836584658565866587658865896590659165926593659465956596659765986599660066016602660366046605660666076608660966106611661266136614661566166617661866196620662166226623662466256626662766286629663066316632663366346635663666376638663966406641664266436644664566466647664866496650665166526653665466556656665766586659666066616662666366646665666666676668666966706671667266736674667566766677667866796680668166826683668466856686668766886689669066916692669366946695669666976698669967006701670267036704670567066707670867096710671167126713671467156716671767186719672067216722672367246725672667276728672967306731673267336734673567366737673867396740674167426743674467456746674767486749675067516752675367546755675667576758675967606761676267636764676567666767676867696770677167726773677467756776677767786779678067816782678367846785678667876788678967906791679267936794679567966797679867996800680168026803680468056806680768086809681068116812681368146815681668176818681968206821682268236824682568266827682868296830683168326833683468356836683768386839684068416842684368446845684668476848684968506851685268536854685568566857685868596860686168626863686468656866686768686869687068716872687368746875687668776878687968806881688268836884688568866887688868896890689168926893689468956896689768986899690069016902690369046905690669076908690969106911691269136914691569166917691869196920692169226923692469256926692769286929693069316932693369346935693669376938693969406941694269436944694569466947694869496950695169526953695469556956695769586959696069616962696369646965696669676968696969706971697269736974697569766977697869796980698169826983698469856986698769886989699069916992699369946995699669976998699970007001700270037004700570067007700870097010701170127013701470157016701770187019702070217022702370247025702670277028702970307031703270337034703570367037703870397040704170427043704470457046704770487049705070517052705370547055705670577058705970607061706270637064706570667067706870697070707170727073707470757076707770787079708070817082708370847085708670877088708970907091709270937094709570967097709870997100710171027103710471057106710771087109711071117112711371147115711671177118711971207121712271237124712571267127712871297130713171327133713471357136713771387139714071417142714371447145714671477148714971507151715271537154715571567157715871597160716171627163716471657166716771687169717071717172717371747175717671777178717971807181718271837184718571867187718871897190719171927193719471957196719771987199720072017202720372047205720672077208720972107211721272137214721572167217721872197220722172227223722472257226722772287229723072317232723372347235723672377238723972407241724272437244724572467247724872497250725172527253725472557256725772587259726072617262726372647265726672677268726972707271727272737274727572767277727872797280728172827283728472857286728772887289729072917292729372947295729672977298729973007301730273037304730573067307730873097310731173127313731473157316731773187319732073217322732373247325732673277328732973307331733273337334733573367337733873397340734173427343734473457346734773487349735073517352735373547355735673577358735973607361736273637364736573667367736873697370737173727373737473757376737773787379738073817382738373847385738673877388738973907391739273937394739573967397739873997400740174027403740474057406740774087409741074117412741374147415741674177418741974207421742274237424742574267427742874297430743174327433743474357436743774387439744074417442744374447445744674477448744974507451745274537454745574567457745874597460746174627463746474657466746774687469747074717472747374747475747674777478747974807481748274837484748574867487748874897490749174927493749474957496749774987499750075017502750375047505750675077508750975107511751275137514751575167517751875197520752175227523752475257526752775287529753075317532753375347535753675377538753975407541754275437544754575467547754875497550755175527553755475557556755775587559756075617562756375647565756675677568756975707571757275737574757575767577757875797580758175827583758475857586758775887589759075917592759375947595759675977598759976007601760276037604760576067607760876097610 |
- // SPDX-License-Identifier: GPL-2.0
- /*
- * Copyright (C) 2012 Alexander Block. All rights reserved.
- */
- #include <linux/bsearch.h>
- #include <linux/fs.h>
- #include <linux/file.h>
- #include <linux/sort.h>
- #include <linux/mount.h>
- #include <linux/xattr.h>
- #include <linux/posix_acl_xattr.h>
- #include <linux/radix-tree.h>
- #include <linux/vmalloc.h>
- #include <linux/string.h>
- #include <linux/compat.h>
- #include <linux/crc32c.h>
- #include "send.h"
- #include "backref.h"
- #include "locking.h"
- #include "disk-io.h"
- #include "btrfs_inode.h"
- #include "transaction.h"
- #include "compression.h"
- #include "xattr.h"
- /*
- * Maximum number of references an extent can have in order for us to attempt to
- * issue clone operations instead of write operations. This currently exists to
- * avoid hitting limitations of the backreference walking code (taking a lot of
- * time and using too much memory for extents with large number of references).
- */
- #define SEND_MAX_EXTENT_REFS 64
- /*
- * A fs_path is a helper to dynamically build path names with unknown size.
- * It reallocates the internal buffer on demand.
- * It allows fast adding of path elements on the right side (normal path) and
- * fast adding to the left side (reversed path). A reversed path can also be
- * unreversed if needed.
- */
- struct fs_path {
- union {
- struct {
- char *start;
- char *end;
- char *buf;
- unsigned short buf_len:15;
- unsigned short reversed:1;
- char inline_buf[];
- };
- /*
- * Average path length does not exceed 200 bytes, we'll have
- * better packing in the slab and higher chance to satisfy
- * a allocation later during send.
- */
- char pad[256];
- };
- };
- #define FS_PATH_INLINE_SIZE \
- (sizeof(struct fs_path) - offsetof(struct fs_path, inline_buf))
- /* reused for each extent */
- struct clone_root {
- struct btrfs_root *root;
- u64 ino;
- u64 offset;
- u64 found_refs;
- };
- #define SEND_CTX_MAX_NAME_CACHE_SIZE 128
- #define SEND_CTX_NAME_CACHE_CLEAN_SIZE (SEND_CTX_MAX_NAME_CACHE_SIZE * 2)
- struct send_ctx {
- struct file *send_filp;
- loff_t send_off;
- char *send_buf;
- u32 send_size;
- u32 send_max_size;
- u64 total_send_size;
- u64 cmd_send_size[BTRFS_SEND_C_MAX + 1];
- u64 flags; /* 'flags' member of btrfs_ioctl_send_args is u64 */
- struct btrfs_root *send_root;
- struct btrfs_root *parent_root;
- struct clone_root *clone_roots;
- int clone_roots_cnt;
- /* current state of the compare_tree call */
- struct btrfs_path *left_path;
- struct btrfs_path *right_path;
- struct btrfs_key *cmp_key;
- /*
- * infos of the currently processed inode. In case of deleted inodes,
- * these are the values from the deleted inode.
- */
- u64 cur_ino;
- u64 cur_inode_gen;
- int cur_inode_new;
- int cur_inode_new_gen;
- int cur_inode_deleted;
- u64 cur_inode_size;
- u64 cur_inode_mode;
- u64 cur_inode_rdev;
- u64 cur_inode_last_extent;
- u64 cur_inode_next_write_offset;
- bool ignore_cur_inode;
- u64 send_progress;
- struct list_head new_refs;
- struct list_head deleted_refs;
- struct radix_tree_root name_cache;
- struct list_head name_cache_list;
- int name_cache_size;
- struct file_ra_state ra;
- char *read_buf;
- /*
- * We process inodes by their increasing order, so if before an
- * incremental send we reverse the parent/child relationship of
- * directories such that a directory with a lower inode number was
- * the parent of a directory with a higher inode number, and the one
- * becoming the new parent got renamed too, we can't rename/move the
- * directory with lower inode number when we finish processing it - we
- * must process the directory with higher inode number first, then
- * rename/move it and then rename/move the directory with lower inode
- * number. Example follows.
- *
- * Tree state when the first send was performed:
- *
- * .
- * |-- a (ino 257)
- * |-- b (ino 258)
- * |
- * |
- * |-- c (ino 259)
- * | |-- d (ino 260)
- * |
- * |-- c2 (ino 261)
- *
- * Tree state when the second (incremental) send is performed:
- *
- * .
- * |-- a (ino 257)
- * |-- b (ino 258)
- * |-- c2 (ino 261)
- * |-- d2 (ino 260)
- * |-- cc (ino 259)
- *
- * The sequence of steps that lead to the second state was:
- *
- * mv /a/b/c/d /a/b/c2/d2
- * mv /a/b/c /a/b/c2/d2/cc
- *
- * "c" has lower inode number, but we can't move it (2nd mv operation)
- * before we move "d", which has higher inode number.
- *
- * So we just memorize which move/rename operations must be performed
- * later when their respective parent is processed and moved/renamed.
- */
- /* Indexed by parent directory inode number. */
- struct rb_root pending_dir_moves;
- /*
- * Reverse index, indexed by the inode number of a directory that
- * is waiting for the move/rename of its immediate parent before its
- * own move/rename can be performed.
- */
- struct rb_root waiting_dir_moves;
- /*
- * A directory that is going to be rm'ed might have a child directory
- * which is in the pending directory moves index above. In this case,
- * the directory can only be removed after the move/rename of its child
- * is performed. Example:
- *
- * Parent snapshot:
- *
- * . (ino 256)
- * |-- a/ (ino 257)
- * |-- b/ (ino 258)
- * |-- c/ (ino 259)
- * | |-- x/ (ino 260)
- * |
- * |-- y/ (ino 261)
- *
- * Send snapshot:
- *
- * . (ino 256)
- * |-- a/ (ino 257)
- * |-- b/ (ino 258)
- * |-- YY/ (ino 261)
- * |-- x/ (ino 260)
- *
- * Sequence of steps that lead to the send snapshot:
- * rm -f /a/b/c/foo.txt
- * mv /a/b/y /a/b/YY
- * mv /a/b/c/x /a/b/YY
- * rmdir /a/b/c
- *
- * When the child is processed, its move/rename is delayed until its
- * parent is processed (as explained above), but all other operations
- * like update utimes, chown, chgrp, etc, are performed and the paths
- * that it uses for those operations must use the orphanized name of
- * its parent (the directory we're going to rm later), so we need to
- * memorize that name.
- *
- * Indexed by the inode number of the directory to be deleted.
- */
- struct rb_root orphan_dirs;
- };
- struct pending_dir_move {
- struct rb_node node;
- struct list_head list;
- u64 parent_ino;
- u64 ino;
- u64 gen;
- struct list_head update_refs;
- };
- struct waiting_dir_move {
- struct rb_node node;
- u64 ino;
- /*
- * There might be some directory that could not be removed because it
- * was waiting for this directory inode to be moved first. Therefore
- * after this directory is moved, we can try to rmdir the ino rmdir_ino.
- */
- u64 rmdir_ino;
- u64 rmdir_gen;
- bool orphanized;
- };
- struct orphan_dir_info {
- struct rb_node node;
- u64 ino;
- u64 gen;
- u64 last_dir_index_offset;
- };
- struct name_cache_entry {
- struct list_head list;
- /*
- * radix_tree has only 32bit entries but we need to handle 64bit inums.
- * We use the lower 32bit of the 64bit inum to store it in the tree. If
- * more then one inum would fall into the same entry, we use radix_list
- * to store the additional entries. radix_list is also used to store
- * entries where two entries have the same inum but different
- * generations.
- */
- struct list_head radix_list;
- u64 ino;
- u64 gen;
- u64 parent_ino;
- u64 parent_gen;
- int ret;
- int need_later_update;
- int name_len;
- char name[];
- };
- #define ADVANCE 1
- #define ADVANCE_ONLY_NEXT -1
- enum btrfs_compare_tree_result {
- BTRFS_COMPARE_TREE_NEW,
- BTRFS_COMPARE_TREE_DELETED,
- BTRFS_COMPARE_TREE_CHANGED,
- BTRFS_COMPARE_TREE_SAME,
- };
- typedef int (*btrfs_changed_cb_t)(struct btrfs_path *left_path,
- struct btrfs_path *right_path,
- struct btrfs_key *key,
- enum btrfs_compare_tree_result result,
- void *ctx);
- __cold
- static void inconsistent_snapshot_error(struct send_ctx *sctx,
- enum btrfs_compare_tree_result result,
- const char *what)
- {
- const char *result_string;
- switch (result) {
- case BTRFS_COMPARE_TREE_NEW:
- result_string = "new";
- break;
- case BTRFS_COMPARE_TREE_DELETED:
- result_string = "deleted";
- break;
- case BTRFS_COMPARE_TREE_CHANGED:
- result_string = "updated";
- break;
- case BTRFS_COMPARE_TREE_SAME:
- ASSERT(0);
- result_string = "unchanged";
- break;
- default:
- ASSERT(0);
- result_string = "unexpected";
- }
- btrfs_err(sctx->send_root->fs_info,
- "Send: inconsistent snapshot, found %s %s for inode %llu without updated inode item, send root is %llu, parent root is %llu",
- result_string, what, sctx->cmp_key->objectid,
- sctx->send_root->root_key.objectid,
- (sctx->parent_root ?
- sctx->parent_root->root_key.objectid : 0));
- }
- static int is_waiting_for_move(struct send_ctx *sctx, u64 ino);
- static struct waiting_dir_move *
- get_waiting_dir_move(struct send_ctx *sctx, u64 ino);
- static int is_waiting_for_rm(struct send_ctx *sctx, u64 dir_ino, u64 gen);
- static int need_send_hole(struct send_ctx *sctx)
- {
- return (sctx->parent_root && !sctx->cur_inode_new &&
- !sctx->cur_inode_new_gen && !sctx->cur_inode_deleted &&
- S_ISREG(sctx->cur_inode_mode));
- }
- static void fs_path_reset(struct fs_path *p)
- {
- if (p->reversed) {
- p->start = p->buf + p->buf_len - 1;
- p->end = p->start;
- *p->start = 0;
- } else {
- p->start = p->buf;
- p->end = p->start;
- *p->start = 0;
- }
- }
- static struct fs_path *fs_path_alloc(void)
- {
- struct fs_path *p;
- p = kmalloc(sizeof(*p), GFP_KERNEL);
- if (!p)
- return NULL;
- p->reversed = 0;
- p->buf = p->inline_buf;
- p->buf_len = FS_PATH_INLINE_SIZE;
- fs_path_reset(p);
- return p;
- }
- static struct fs_path *fs_path_alloc_reversed(void)
- {
- struct fs_path *p;
- p = fs_path_alloc();
- if (!p)
- return NULL;
- p->reversed = 1;
- fs_path_reset(p);
- return p;
- }
- static void fs_path_free(struct fs_path *p)
- {
- if (!p)
- return;
- if (p->buf != p->inline_buf)
- kfree(p->buf);
- kfree(p);
- }
- static int fs_path_len(struct fs_path *p)
- {
- return p->end - p->start;
- }
- static int fs_path_ensure_buf(struct fs_path *p, int len)
- {
- char *tmp_buf;
- int path_len;
- int old_buf_len;
- len++;
- if (p->buf_len >= len)
- return 0;
- if (len > PATH_MAX) {
- WARN_ON(1);
- return -ENOMEM;
- }
- path_len = p->end - p->start;
- old_buf_len = p->buf_len;
- /*
- * First time the inline_buf does not suffice
- */
- if (p->buf == p->inline_buf) {
- tmp_buf = kmalloc(len, GFP_KERNEL);
- if (tmp_buf)
- memcpy(tmp_buf, p->buf, old_buf_len);
- } else {
- tmp_buf = krealloc(p->buf, len, GFP_KERNEL);
- }
- if (!tmp_buf)
- return -ENOMEM;
- p->buf = tmp_buf;
- /*
- * The real size of the buffer is bigger, this will let the fast path
- * happen most of the time
- */
- p->buf_len = ksize(p->buf);
- if (p->reversed) {
- tmp_buf = p->buf + old_buf_len - path_len - 1;
- p->end = p->buf + p->buf_len - 1;
- p->start = p->end - path_len;
- memmove(p->start, tmp_buf, path_len + 1);
- } else {
- p->start = p->buf;
- p->end = p->start + path_len;
- }
- return 0;
- }
- static int fs_path_prepare_for_add(struct fs_path *p, int name_len,
- char **prepared)
- {
- int ret;
- int new_len;
- new_len = p->end - p->start + name_len;
- if (p->start != p->end)
- new_len++;
- ret = fs_path_ensure_buf(p, new_len);
- if (ret < 0)
- goto out;
- if (p->reversed) {
- if (p->start != p->end)
- *--p->start = '/';
- p->start -= name_len;
- *prepared = p->start;
- } else {
- if (p->start != p->end)
- *p->end++ = '/';
- *prepared = p->end;
- p->end += name_len;
- *p->end = 0;
- }
- out:
- return ret;
- }
- static int fs_path_add(struct fs_path *p, const char *name, int name_len)
- {
- int ret;
- char *prepared;
- ret = fs_path_prepare_for_add(p, name_len, &prepared);
- if (ret < 0)
- goto out;
- memcpy(prepared, name, name_len);
- out:
- return ret;
- }
- static int fs_path_add_path(struct fs_path *p, struct fs_path *p2)
- {
- int ret;
- char *prepared;
- ret = fs_path_prepare_for_add(p, p2->end - p2->start, &prepared);
- if (ret < 0)
- goto out;
- memcpy(prepared, p2->start, p2->end - p2->start);
- out:
- return ret;
- }
- static int fs_path_add_from_extent_buffer(struct fs_path *p,
- struct extent_buffer *eb,
- unsigned long off, int len)
- {
- int ret;
- char *prepared;
- ret = fs_path_prepare_for_add(p, len, &prepared);
- if (ret < 0)
- goto out;
- read_extent_buffer(eb, prepared, off, len);
- out:
- return ret;
- }
- static int fs_path_copy(struct fs_path *p, struct fs_path *from)
- {
- int ret;
- p->reversed = from->reversed;
- fs_path_reset(p);
- ret = fs_path_add_path(p, from);
- return ret;
- }
- static void fs_path_unreverse(struct fs_path *p)
- {
- char *tmp;
- int len;
- if (!p->reversed)
- return;
- tmp = p->start;
- len = p->end - p->start;
- p->start = p->buf;
- p->end = p->start + len;
- memmove(p->start, tmp, len + 1);
- p->reversed = 0;
- }
- static struct btrfs_path *alloc_path_for_send(void)
- {
- struct btrfs_path *path;
- path = btrfs_alloc_path();
- if (!path)
- return NULL;
- path->search_commit_root = 1;
- path->skip_locking = 1;
- path->need_commit_sem = 1;
- return path;
- }
- static int write_buf(struct file *filp, const void *buf, u32 len, loff_t *off)
- {
- int ret;
- u32 pos = 0;
- while (pos < len) {
- ret = kernel_write(filp, buf + pos, len - pos, off);
- /* TODO handle that correctly */
- /*if (ret == -ERESTARTSYS) {
- continue;
- }*/
- if (ret < 0)
- return ret;
- if (ret == 0) {
- return -EIO;
- }
- pos += ret;
- }
- return 0;
- }
- static int tlv_put(struct send_ctx *sctx, u16 attr, const void *data, int len)
- {
- struct btrfs_tlv_header *hdr;
- int total_len = sizeof(*hdr) + len;
- int left = sctx->send_max_size - sctx->send_size;
- if (unlikely(left < total_len))
- return -EOVERFLOW;
- hdr = (struct btrfs_tlv_header *) (sctx->send_buf + sctx->send_size);
- hdr->tlv_type = cpu_to_le16(attr);
- hdr->tlv_len = cpu_to_le16(len);
- memcpy(hdr + 1, data, len);
- sctx->send_size += total_len;
- return 0;
- }
- #define TLV_PUT_DEFINE_INT(bits) \
- static int tlv_put_u##bits(struct send_ctx *sctx, \
- u##bits attr, u##bits value) \
- { \
- __le##bits __tmp = cpu_to_le##bits(value); \
- return tlv_put(sctx, attr, &__tmp, sizeof(__tmp)); \
- }
- TLV_PUT_DEFINE_INT(64)
- static int tlv_put_string(struct send_ctx *sctx, u16 attr,
- const char *str, int len)
- {
- if (len == -1)
- len = strlen(str);
- return tlv_put(sctx, attr, str, len);
- }
- static int tlv_put_uuid(struct send_ctx *sctx, u16 attr,
- const u8 *uuid)
- {
- return tlv_put(sctx, attr, uuid, BTRFS_UUID_SIZE);
- }
- static int tlv_put_btrfs_timespec(struct send_ctx *sctx, u16 attr,
- struct extent_buffer *eb,
- struct btrfs_timespec *ts)
- {
- struct btrfs_timespec bts;
- read_extent_buffer(eb, &bts, (unsigned long)ts, sizeof(bts));
- return tlv_put(sctx, attr, &bts, sizeof(bts));
- }
- #define TLV_PUT(sctx, attrtype, data, attrlen) \
- do { \
- ret = tlv_put(sctx, attrtype, data, attrlen); \
- if (ret < 0) \
- goto tlv_put_failure; \
- } while (0)
- #define TLV_PUT_INT(sctx, attrtype, bits, value) \
- do { \
- ret = tlv_put_u##bits(sctx, attrtype, value); \
- if (ret < 0) \
- goto tlv_put_failure; \
- } while (0)
- #define TLV_PUT_U8(sctx, attrtype, data) TLV_PUT_INT(sctx, attrtype, 8, data)
- #define TLV_PUT_U16(sctx, attrtype, data) TLV_PUT_INT(sctx, attrtype, 16, data)
- #define TLV_PUT_U32(sctx, attrtype, data) TLV_PUT_INT(sctx, attrtype, 32, data)
- #define TLV_PUT_U64(sctx, attrtype, data) TLV_PUT_INT(sctx, attrtype, 64, data)
- #define TLV_PUT_STRING(sctx, attrtype, str, len) \
- do { \
- ret = tlv_put_string(sctx, attrtype, str, len); \
- if (ret < 0) \
- goto tlv_put_failure; \
- } while (0)
- #define TLV_PUT_PATH(sctx, attrtype, p) \
- do { \
- ret = tlv_put_string(sctx, attrtype, p->start, \
- p->end - p->start); \
- if (ret < 0) \
- goto tlv_put_failure; \
- } while(0)
- #define TLV_PUT_UUID(sctx, attrtype, uuid) \
- do { \
- ret = tlv_put_uuid(sctx, attrtype, uuid); \
- if (ret < 0) \
- goto tlv_put_failure; \
- } while (0)
- #define TLV_PUT_BTRFS_TIMESPEC(sctx, attrtype, eb, ts) \
- do { \
- ret = tlv_put_btrfs_timespec(sctx, attrtype, eb, ts); \
- if (ret < 0) \
- goto tlv_put_failure; \
- } while (0)
- static int send_header(struct send_ctx *sctx)
- {
- struct btrfs_stream_header hdr;
- strcpy(hdr.magic, BTRFS_SEND_STREAM_MAGIC);
- hdr.version = cpu_to_le32(BTRFS_SEND_STREAM_VERSION);
- return write_buf(sctx->send_filp, &hdr, sizeof(hdr),
- &sctx->send_off);
- }
- /*
- * For each command/item we want to send to userspace, we call this function.
- */
- static int begin_cmd(struct send_ctx *sctx, int cmd)
- {
- struct btrfs_cmd_header *hdr;
- if (WARN_ON(!sctx->send_buf))
- return -EINVAL;
- BUG_ON(sctx->send_size);
- sctx->send_size += sizeof(*hdr);
- hdr = (struct btrfs_cmd_header *)sctx->send_buf;
- hdr->cmd = cpu_to_le16(cmd);
- return 0;
- }
- static int send_cmd(struct send_ctx *sctx)
- {
- int ret;
- struct btrfs_cmd_header *hdr;
- u32 crc;
- hdr = (struct btrfs_cmd_header *)sctx->send_buf;
- hdr->len = cpu_to_le32(sctx->send_size - sizeof(*hdr));
- hdr->crc = 0;
- crc = btrfs_crc32c(0, (unsigned char *)sctx->send_buf, sctx->send_size);
- hdr->crc = cpu_to_le32(crc);
- ret = write_buf(sctx->send_filp, sctx->send_buf, sctx->send_size,
- &sctx->send_off);
- sctx->total_send_size += sctx->send_size;
- sctx->cmd_send_size[le16_to_cpu(hdr->cmd)] += sctx->send_size;
- sctx->send_size = 0;
- return ret;
- }
- /*
- * Sends a move instruction to user space
- */
- static int send_rename(struct send_ctx *sctx,
- struct fs_path *from, struct fs_path *to)
- {
- struct btrfs_fs_info *fs_info = sctx->send_root->fs_info;
- int ret;
- btrfs_debug(fs_info, "send_rename %s -> %s", from->start, to->start);
- ret = begin_cmd(sctx, BTRFS_SEND_C_RENAME);
- if (ret < 0)
- goto out;
- TLV_PUT_PATH(sctx, BTRFS_SEND_A_PATH, from);
- TLV_PUT_PATH(sctx, BTRFS_SEND_A_PATH_TO, to);
- ret = send_cmd(sctx);
- tlv_put_failure:
- out:
- return ret;
- }
- /*
- * Sends a link instruction to user space
- */
- static int send_link(struct send_ctx *sctx,
- struct fs_path *path, struct fs_path *lnk)
- {
- struct btrfs_fs_info *fs_info = sctx->send_root->fs_info;
- int ret;
- btrfs_debug(fs_info, "send_link %s -> %s", path->start, lnk->start);
- ret = begin_cmd(sctx, BTRFS_SEND_C_LINK);
- if (ret < 0)
- goto out;
- TLV_PUT_PATH(sctx, BTRFS_SEND_A_PATH, path);
- TLV_PUT_PATH(sctx, BTRFS_SEND_A_PATH_LINK, lnk);
- ret = send_cmd(sctx);
- tlv_put_failure:
- out:
- return ret;
- }
- /*
- * Sends an unlink instruction to user space
- */
- static int send_unlink(struct send_ctx *sctx, struct fs_path *path)
- {
- struct btrfs_fs_info *fs_info = sctx->send_root->fs_info;
- int ret;
- btrfs_debug(fs_info, "send_unlink %s", path->start);
- ret = begin_cmd(sctx, BTRFS_SEND_C_UNLINK);
- if (ret < 0)
- goto out;
- TLV_PUT_PATH(sctx, BTRFS_SEND_A_PATH, path);
- ret = send_cmd(sctx);
- tlv_put_failure:
- out:
- return ret;
- }
- /*
- * Sends a rmdir instruction to user space
- */
- static int send_rmdir(struct send_ctx *sctx, struct fs_path *path)
- {
- struct btrfs_fs_info *fs_info = sctx->send_root->fs_info;
- int ret;
- btrfs_debug(fs_info, "send_rmdir %s", path->start);
- ret = begin_cmd(sctx, BTRFS_SEND_C_RMDIR);
- if (ret < 0)
- goto out;
- TLV_PUT_PATH(sctx, BTRFS_SEND_A_PATH, path);
- ret = send_cmd(sctx);
- tlv_put_failure:
- out:
- return ret;
- }
- /*
- * Helper function to retrieve some fields from an inode item.
- */
- static int __get_inode_info(struct btrfs_root *root, struct btrfs_path *path,
- u64 ino, u64 *size, u64 *gen, u64 *mode, u64 *uid,
- u64 *gid, u64 *rdev)
- {
- int ret;
- struct btrfs_inode_item *ii;
- struct btrfs_key key;
- key.objectid = ino;
- key.type = BTRFS_INODE_ITEM_KEY;
- key.offset = 0;
- ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
- if (ret) {
- if (ret > 0)
- ret = -ENOENT;
- return ret;
- }
- ii = btrfs_item_ptr(path->nodes[0], path->slots[0],
- struct btrfs_inode_item);
- if (size)
- *size = btrfs_inode_size(path->nodes[0], ii);
- if (gen)
- *gen = btrfs_inode_generation(path->nodes[0], ii);
- if (mode)
- *mode = btrfs_inode_mode(path->nodes[0], ii);
- if (uid)
- *uid = btrfs_inode_uid(path->nodes[0], ii);
- if (gid)
- *gid = btrfs_inode_gid(path->nodes[0], ii);
- if (rdev)
- *rdev = btrfs_inode_rdev(path->nodes[0], ii);
- return ret;
- }
- static int get_inode_info(struct btrfs_root *root,
- u64 ino, u64 *size, u64 *gen,
- u64 *mode, u64 *uid, u64 *gid,
- u64 *rdev)
- {
- struct btrfs_path *path;
- int ret;
- path = alloc_path_for_send();
- if (!path)
- return -ENOMEM;
- ret = __get_inode_info(root, path, ino, size, gen, mode, uid, gid,
- rdev);
- btrfs_free_path(path);
- return ret;
- }
- typedef int (*iterate_inode_ref_t)(int num, u64 dir, int index,
- struct fs_path *p,
- void *ctx);
- /*
- * Helper function to iterate the entries in ONE btrfs_inode_ref or
- * btrfs_inode_extref.
- * The iterate callback may return a non zero value to stop iteration. This can
- * be a negative value for error codes or 1 to simply stop it.
- *
- * path must point to the INODE_REF or INODE_EXTREF when called.
- */
- static int iterate_inode_ref(struct btrfs_root *root, struct btrfs_path *path,
- struct btrfs_key *found_key, int resolve,
- iterate_inode_ref_t iterate, void *ctx)
- {
- struct extent_buffer *eb = path->nodes[0];
- struct btrfs_item *item;
- struct btrfs_inode_ref *iref;
- struct btrfs_inode_extref *extref;
- struct btrfs_path *tmp_path;
- struct fs_path *p;
- u32 cur = 0;
- u32 total;
- int slot = path->slots[0];
- u32 name_len;
- char *start;
- int ret = 0;
- int num = 0;
- int index;
- u64 dir;
- unsigned long name_off;
- unsigned long elem_size;
- unsigned long ptr;
- p = fs_path_alloc_reversed();
- if (!p)
- return -ENOMEM;
- tmp_path = alloc_path_for_send();
- if (!tmp_path) {
- fs_path_free(p);
- return -ENOMEM;
- }
- if (found_key->type == BTRFS_INODE_REF_KEY) {
- ptr = (unsigned long)btrfs_item_ptr(eb, slot,
- struct btrfs_inode_ref);
- item = btrfs_item_nr(slot);
- total = btrfs_item_size(eb, item);
- elem_size = sizeof(*iref);
- } else {
- ptr = btrfs_item_ptr_offset(eb, slot);
- total = btrfs_item_size_nr(eb, slot);
- elem_size = sizeof(*extref);
- }
- while (cur < total) {
- fs_path_reset(p);
- if (found_key->type == BTRFS_INODE_REF_KEY) {
- iref = (struct btrfs_inode_ref *)(ptr + cur);
- name_len = btrfs_inode_ref_name_len(eb, iref);
- name_off = (unsigned long)(iref + 1);
- index = btrfs_inode_ref_index(eb, iref);
- dir = found_key->offset;
- } else {
- extref = (struct btrfs_inode_extref *)(ptr + cur);
- name_len = btrfs_inode_extref_name_len(eb, extref);
- name_off = (unsigned long)&extref->name;
- index = btrfs_inode_extref_index(eb, extref);
- dir = btrfs_inode_extref_parent(eb, extref);
- }
- if (resolve) {
- start = btrfs_ref_to_path(root, tmp_path, name_len,
- name_off, eb, dir,
- p->buf, p->buf_len);
- if (IS_ERR(start)) {
- ret = PTR_ERR(start);
- goto out;
- }
- if (start < p->buf) {
- /* overflow , try again with larger buffer */
- ret = fs_path_ensure_buf(p,
- p->buf_len + p->buf - start);
- if (ret < 0)
- goto out;
- start = btrfs_ref_to_path(root, tmp_path,
- name_len, name_off,
- eb, dir,
- p->buf, p->buf_len);
- if (IS_ERR(start)) {
- ret = PTR_ERR(start);
- goto out;
- }
- BUG_ON(start < p->buf);
- }
- p->start = start;
- } else {
- ret = fs_path_add_from_extent_buffer(p, eb, name_off,
- name_len);
- if (ret < 0)
- goto out;
- }
- cur += elem_size + name_len;
- ret = iterate(num, dir, index, p, ctx);
- if (ret)
- goto out;
- num++;
- }
- out:
- btrfs_free_path(tmp_path);
- fs_path_free(p);
- return ret;
- }
- typedef int (*iterate_dir_item_t)(int num, struct btrfs_key *di_key,
- const char *name, int name_len,
- const char *data, int data_len,
- u8 type, void *ctx);
- /*
- * Helper function to iterate the entries in ONE btrfs_dir_item.
- * The iterate callback may return a non zero value to stop iteration. This can
- * be a negative value for error codes or 1 to simply stop it.
- *
- * path must point to the dir item when called.
- */
- static int iterate_dir_item(struct btrfs_root *root, struct btrfs_path *path,
- iterate_dir_item_t iterate, void *ctx)
- {
- int ret = 0;
- struct extent_buffer *eb;
- struct btrfs_item *item;
- struct btrfs_dir_item *di;
- struct btrfs_key di_key;
- char *buf = NULL;
- int buf_len;
- u32 name_len;
- u32 data_len;
- u32 cur;
- u32 len;
- u32 total;
- int slot;
- int num;
- u8 type;
- /*
- * Start with a small buffer (1 page). If later we end up needing more
- * space, which can happen for xattrs on a fs with a leaf size greater
- * then the page size, attempt to increase the buffer. Typically xattr
- * values are small.
- */
- buf_len = PATH_MAX;
- buf = kmalloc(buf_len, GFP_KERNEL);
- if (!buf) {
- ret = -ENOMEM;
- goto out;
- }
- eb = path->nodes[0];
- slot = path->slots[0];
- item = btrfs_item_nr(slot);
- di = btrfs_item_ptr(eb, slot, struct btrfs_dir_item);
- cur = 0;
- len = 0;
- total = btrfs_item_size(eb, item);
- num = 0;
- while (cur < total) {
- name_len = btrfs_dir_name_len(eb, di);
- data_len = btrfs_dir_data_len(eb, di);
- type = btrfs_dir_type(eb, di);
- btrfs_dir_item_key_to_cpu(eb, di, &di_key);
- if (type == BTRFS_FT_XATTR) {
- if (name_len > XATTR_NAME_MAX) {
- ret = -ENAMETOOLONG;
- goto out;
- }
- if (name_len + data_len >
- BTRFS_MAX_XATTR_SIZE(root->fs_info)) {
- ret = -E2BIG;
- goto out;
- }
- } else {
- /*
- * Path too long
- */
- if (name_len + data_len > PATH_MAX) {
- ret = -ENAMETOOLONG;
- goto out;
- }
- }
- if (name_len + data_len > buf_len) {
- buf_len = name_len + data_len;
- if (is_vmalloc_addr(buf)) {
- vfree(buf);
- buf = NULL;
- } else {
- char *tmp = krealloc(buf, buf_len,
- GFP_KERNEL | __GFP_NOWARN);
- if (!tmp)
- kfree(buf);
- buf = tmp;
- }
- if (!buf) {
- buf = kvmalloc(buf_len, GFP_KERNEL);
- if (!buf) {
- ret = -ENOMEM;
- goto out;
- }
- }
- }
- read_extent_buffer(eb, buf, (unsigned long)(di + 1),
- name_len + data_len);
- len = sizeof(*di) + name_len + data_len;
- di = (struct btrfs_dir_item *)((char *)di + len);
- cur += len;
- ret = iterate(num, &di_key, buf, name_len, buf + name_len,
- data_len, type, ctx);
- if (ret < 0)
- goto out;
- if (ret) {
- ret = 0;
- goto out;
- }
- num++;
- }
- out:
- kvfree(buf);
- return ret;
- }
- static int __copy_first_ref(int num, u64 dir, int index,
- struct fs_path *p, void *ctx)
- {
- int ret;
- struct fs_path *pt = ctx;
- ret = fs_path_copy(pt, p);
- if (ret < 0)
- return ret;
- /* we want the first only */
- return 1;
- }
- /*
- * Retrieve the first path of an inode. If an inode has more then one
- * ref/hardlink, this is ignored.
- */
- static int get_inode_path(struct btrfs_root *root,
- u64 ino, struct fs_path *path)
- {
- int ret;
- struct btrfs_key key, found_key;
- struct btrfs_path *p;
- p = alloc_path_for_send();
- if (!p)
- return -ENOMEM;
- fs_path_reset(path);
- key.objectid = ino;
- key.type = BTRFS_INODE_REF_KEY;
- key.offset = 0;
- ret = btrfs_search_slot_for_read(root, &key, p, 1, 0);
- if (ret < 0)
- goto out;
- if (ret) {
- ret = 1;
- goto out;
- }
- btrfs_item_key_to_cpu(p->nodes[0], &found_key, p->slots[0]);
- if (found_key.objectid != ino ||
- (found_key.type != BTRFS_INODE_REF_KEY &&
- found_key.type != BTRFS_INODE_EXTREF_KEY)) {
- ret = -ENOENT;
- goto out;
- }
- ret = iterate_inode_ref(root, p, &found_key, 1,
- __copy_first_ref, path);
- if (ret < 0)
- goto out;
- ret = 0;
- out:
- btrfs_free_path(p);
- return ret;
- }
- struct backref_ctx {
- struct send_ctx *sctx;
- /* number of total found references */
- u64 found;
- /*
- * used for clones found in send_root. clones found behind cur_objectid
- * and cur_offset are not considered as allowed clones.
- */
- u64 cur_objectid;
- u64 cur_offset;
- /* may be truncated in case it's the last extent in a file */
- u64 extent_len;
- /* data offset in the file extent item */
- u64 data_offset;
- /* Just to check for bugs in backref resolving */
- int found_itself;
- };
- static int __clone_root_cmp_bsearch(const void *key, const void *elt)
- {
- u64 root = (u64)(uintptr_t)key;
- struct clone_root *cr = (struct clone_root *)elt;
- if (root < cr->root->root_key.objectid)
- return -1;
- if (root > cr->root->root_key.objectid)
- return 1;
- return 0;
- }
- static int __clone_root_cmp_sort(const void *e1, const void *e2)
- {
- struct clone_root *cr1 = (struct clone_root *)e1;
- struct clone_root *cr2 = (struct clone_root *)e2;
- if (cr1->root->root_key.objectid < cr2->root->root_key.objectid)
- return -1;
- if (cr1->root->root_key.objectid > cr2->root->root_key.objectid)
- return 1;
- return 0;
- }
- /*
- * Called for every backref that is found for the current extent.
- * Results are collected in sctx->clone_roots->ino/offset/found_refs
- */
- static int __iterate_backrefs(u64 ino, u64 offset, u64 root, void *ctx_)
- {
- struct backref_ctx *bctx = ctx_;
- struct clone_root *found;
- /* First check if the root is in the list of accepted clone sources */
- found = bsearch((void *)(uintptr_t)root, bctx->sctx->clone_roots,
- bctx->sctx->clone_roots_cnt,
- sizeof(struct clone_root),
- __clone_root_cmp_bsearch);
- if (!found)
- return 0;
- if (found->root == bctx->sctx->send_root &&
- ino == bctx->cur_objectid &&
- offset == bctx->cur_offset) {
- bctx->found_itself = 1;
- }
- /*
- * Make sure we don't consider clones from send_root that are
- * behind the current inode/offset.
- */
- if (found->root == bctx->sctx->send_root) {
- /*
- * If the source inode was not yet processed we can't issue a
- * clone operation, as the source extent does not exist yet at
- * the destination of the stream.
- */
- if (ino > bctx->cur_objectid)
- return 0;
- /*
- * We clone from the inode currently being sent as long as the
- * source extent is already processed, otherwise we could try
- * to clone from an extent that does not exist yet at the
- * destination of the stream.
- */
- if (ino == bctx->cur_objectid &&
- offset + bctx->extent_len >
- bctx->sctx->cur_inode_next_write_offset)
- return 0;
- }
- bctx->found++;
- found->found_refs++;
- if (ino < found->ino) {
- found->ino = ino;
- found->offset = offset;
- } else if (found->ino == ino) {
- /*
- * same extent found more then once in the same file.
- */
- if (found->offset > offset + bctx->extent_len)
- found->offset = offset;
- }
- return 0;
- }
- /*
- * Given an inode, offset and extent item, it finds a good clone for a clone
- * instruction. Returns -ENOENT when none could be found. The function makes
- * sure that the returned clone is usable at the point where sending is at the
- * moment. This means, that no clones are accepted which lie behind the current
- * inode+offset.
- *
- * path must point to the extent item when called.
- */
- static int find_extent_clone(struct send_ctx *sctx,
- struct btrfs_path *path,
- u64 ino, u64 data_offset,
- u64 ino_size,
- struct clone_root **found)
- {
- struct btrfs_fs_info *fs_info = sctx->send_root->fs_info;
- int ret;
- int extent_type;
- u64 logical;
- u64 disk_byte;
- u64 num_bytes;
- u64 extent_item_pos;
- u64 flags = 0;
- struct btrfs_file_extent_item *fi;
- struct extent_buffer *eb = path->nodes[0];
- struct backref_ctx *backref_ctx = NULL;
- struct clone_root *cur_clone_root;
- struct btrfs_key found_key;
- struct btrfs_path *tmp_path;
- struct btrfs_extent_item *ei;
- int compressed;
- u32 i;
- tmp_path = alloc_path_for_send();
- if (!tmp_path)
- return -ENOMEM;
- /* We only use this path under the commit sem */
- tmp_path->need_commit_sem = 0;
- backref_ctx = kmalloc(sizeof(*backref_ctx), GFP_KERNEL);
- if (!backref_ctx) {
- ret = -ENOMEM;
- goto out;
- }
- if (data_offset >= ino_size) {
- /*
- * There may be extents that lie behind the file's size.
- * I at least had this in combination with snapshotting while
- * writing large files.
- */
- ret = 0;
- goto out;
- }
- fi = btrfs_item_ptr(eb, path->slots[0],
- struct btrfs_file_extent_item);
- extent_type = btrfs_file_extent_type(eb, fi);
- if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
- ret = -ENOENT;
- goto out;
- }
- compressed = btrfs_file_extent_compression(eb, fi);
- num_bytes = btrfs_file_extent_num_bytes(eb, fi);
- disk_byte = btrfs_file_extent_disk_bytenr(eb, fi);
- if (disk_byte == 0) {
- ret = -ENOENT;
- goto out;
- }
- logical = disk_byte + btrfs_file_extent_offset(eb, fi);
- down_read(&fs_info->commit_root_sem);
- ret = extent_from_logical(fs_info, disk_byte, tmp_path,
- &found_key, &flags);
- up_read(&fs_info->commit_root_sem);
- if (ret < 0)
- goto out;
- if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) {
- ret = -EIO;
- goto out;
- }
- ei = btrfs_item_ptr(tmp_path->nodes[0], tmp_path->slots[0],
- struct btrfs_extent_item);
- /*
- * Backreference walking (iterate_extent_inodes() below) is currently
- * too expensive when an extent has a large number of references, both
- * in time spent and used memory. So for now just fallback to write
- * operations instead of clone operations when an extent has more than
- * a certain amount of references.
- */
- if (btrfs_extent_refs(tmp_path->nodes[0], ei) > SEND_MAX_EXTENT_REFS) {
- ret = -ENOENT;
- goto out;
- }
- btrfs_release_path(tmp_path);
- /*
- * Setup the clone roots.
- */
- for (i = 0; i < sctx->clone_roots_cnt; i++) {
- cur_clone_root = sctx->clone_roots + i;
- cur_clone_root->ino = (u64)-1;
- cur_clone_root->offset = 0;
- cur_clone_root->found_refs = 0;
- }
- backref_ctx->sctx = sctx;
- backref_ctx->found = 0;
- backref_ctx->cur_objectid = ino;
- backref_ctx->cur_offset = data_offset;
- backref_ctx->found_itself = 0;
- backref_ctx->extent_len = num_bytes;
- /*
- * For non-compressed extents iterate_extent_inodes() gives us extent
- * offsets that already take into account the data offset, but not for
- * compressed extents, since the offset is logical and not relative to
- * the physical extent locations. We must take this into account to
- * avoid sending clone offsets that go beyond the source file's size,
- * which would result in the clone ioctl failing with -EINVAL on the
- * receiving end.
- */
- if (compressed == BTRFS_COMPRESS_NONE)
- backref_ctx->data_offset = 0;
- else
- backref_ctx->data_offset = btrfs_file_extent_offset(eb, fi);
- /*
- * The last extent of a file may be too large due to page alignment.
- * We need to adjust extent_len in this case so that the checks in
- * __iterate_backrefs work.
- */
- if (data_offset + num_bytes >= ino_size)
- backref_ctx->extent_len = ino_size - data_offset;
- /*
- * Now collect all backrefs.
- */
- if (compressed == BTRFS_COMPRESS_NONE)
- extent_item_pos = logical - found_key.objectid;
- else
- extent_item_pos = 0;
- ret = iterate_extent_inodes(fs_info, found_key.objectid,
- extent_item_pos, 1, __iterate_backrefs,
- backref_ctx, false);
- if (ret < 0)
- goto out;
- if (!backref_ctx->found_itself) {
- /* found a bug in backref code? */
- ret = -EIO;
- btrfs_err(fs_info,
- "did not find backref in send_root. inode=%llu, offset=%llu, disk_byte=%llu found extent=%llu",
- ino, data_offset, disk_byte, found_key.objectid);
- goto out;
- }
- btrfs_debug(fs_info,
- "find_extent_clone: data_offset=%llu, ino=%llu, num_bytes=%llu, logical=%llu",
- data_offset, ino, num_bytes, logical);
- if (!backref_ctx->found)
- btrfs_debug(fs_info, "no clones found");
- cur_clone_root = NULL;
- for (i = 0; i < sctx->clone_roots_cnt; i++) {
- if (sctx->clone_roots[i].found_refs) {
- if (!cur_clone_root)
- cur_clone_root = sctx->clone_roots + i;
- else if (sctx->clone_roots[i].root == sctx->send_root)
- /* prefer clones from send_root over others */
- cur_clone_root = sctx->clone_roots + i;
- }
- }
- if (cur_clone_root) {
- *found = cur_clone_root;
- ret = 0;
- } else {
- ret = -ENOENT;
- }
- out:
- btrfs_free_path(tmp_path);
- kfree(backref_ctx);
- return ret;
- }
- static int read_symlink(struct btrfs_root *root,
- u64 ino,
- struct fs_path *dest)
- {
- int ret;
- struct btrfs_path *path;
- struct btrfs_key key;
- struct btrfs_file_extent_item *ei;
- u8 type;
- u8 compression;
- unsigned long off;
- int len;
- path = alloc_path_for_send();
- if (!path)
- return -ENOMEM;
- key.objectid = ino;
- key.type = BTRFS_EXTENT_DATA_KEY;
- key.offset = 0;
- ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
- if (ret < 0)
- goto out;
- if (ret) {
- /*
- * An empty symlink inode. Can happen in rare error paths when
- * creating a symlink (transaction committed before the inode
- * eviction handler removed the symlink inode items and a crash
- * happened in between or the subvol was snapshoted in between).
- * Print an informative message to dmesg/syslog so that the user
- * can delete the symlink.
- */
- btrfs_err(root->fs_info,
- "Found empty symlink inode %llu at root %llu",
- ino, root->root_key.objectid);
- ret = -EIO;
- goto out;
- }
- ei = btrfs_item_ptr(path->nodes[0], path->slots[0],
- struct btrfs_file_extent_item);
- type = btrfs_file_extent_type(path->nodes[0], ei);
- compression = btrfs_file_extent_compression(path->nodes[0], ei);
- BUG_ON(type != BTRFS_FILE_EXTENT_INLINE);
- BUG_ON(compression);
- off = btrfs_file_extent_inline_start(ei);
- len = btrfs_file_extent_ram_bytes(path->nodes[0], ei);
- ret = fs_path_add_from_extent_buffer(dest, path->nodes[0], off, len);
- out:
- btrfs_free_path(path);
- return ret;
- }
- /*
- * Helper function to generate a file name that is unique in the root of
- * send_root and parent_root. This is used to generate names for orphan inodes.
- */
- static int gen_unique_name(struct send_ctx *sctx,
- u64 ino, u64 gen,
- struct fs_path *dest)
- {
- int ret = 0;
- struct btrfs_path *path;
- struct btrfs_dir_item *di;
- char tmp[64];
- int len;
- u64 idx = 0;
- path = alloc_path_for_send();
- if (!path)
- return -ENOMEM;
- while (1) {
- len = snprintf(tmp, sizeof(tmp), "o%llu-%llu-%llu",
- ino, gen, idx);
- ASSERT(len < sizeof(tmp));
- di = btrfs_lookup_dir_item(NULL, sctx->send_root,
- path, BTRFS_FIRST_FREE_OBJECTID,
- tmp, strlen(tmp), 0);
- btrfs_release_path(path);
- if (IS_ERR(di)) {
- ret = PTR_ERR(di);
- goto out;
- }
- if (di) {
- /* not unique, try again */
- idx++;
- continue;
- }
- if (!sctx->parent_root) {
- /* unique */
- ret = 0;
- break;
- }
- di = btrfs_lookup_dir_item(NULL, sctx->parent_root,
- path, BTRFS_FIRST_FREE_OBJECTID,
- tmp, strlen(tmp), 0);
- btrfs_release_path(path);
- if (IS_ERR(di)) {
- ret = PTR_ERR(di);
- goto out;
- }
- if (di) {
- /* not unique, try again */
- idx++;
- continue;
- }
- /* unique */
- break;
- }
- ret = fs_path_add(dest, tmp, strlen(tmp));
- out:
- btrfs_free_path(path);
- return ret;
- }
- enum inode_state {
- inode_state_no_change,
- inode_state_will_create,
- inode_state_did_create,
- inode_state_will_delete,
- inode_state_did_delete,
- };
- static int get_cur_inode_state(struct send_ctx *sctx, u64 ino, u64 gen)
- {
- int ret;
- int left_ret;
- int right_ret;
- u64 left_gen;
- u64 right_gen;
- ret = get_inode_info(sctx->send_root, ino, NULL, &left_gen, NULL, NULL,
- NULL, NULL);
- if (ret < 0 && ret != -ENOENT)
- goto out;
- left_ret = ret;
- if (!sctx->parent_root) {
- right_ret = -ENOENT;
- } else {
- ret = get_inode_info(sctx->parent_root, ino, NULL, &right_gen,
- NULL, NULL, NULL, NULL);
- if (ret < 0 && ret != -ENOENT)
- goto out;
- right_ret = ret;
- }
- if (!left_ret && !right_ret) {
- if (left_gen == gen && right_gen == gen) {
- ret = inode_state_no_change;
- } else if (left_gen == gen) {
- if (ino < sctx->send_progress)
- ret = inode_state_did_create;
- else
- ret = inode_state_will_create;
- } else if (right_gen == gen) {
- if (ino < sctx->send_progress)
- ret = inode_state_did_delete;
- else
- ret = inode_state_will_delete;
- } else {
- ret = -ENOENT;
- }
- } else if (!left_ret) {
- if (left_gen == gen) {
- if (ino < sctx->send_progress)
- ret = inode_state_did_create;
- else
- ret = inode_state_will_create;
- } else {
- ret = -ENOENT;
- }
- } else if (!right_ret) {
- if (right_gen == gen) {
- if (ino < sctx->send_progress)
- ret = inode_state_did_delete;
- else
- ret = inode_state_will_delete;
- } else {
- ret = -ENOENT;
- }
- } else {
- ret = -ENOENT;
- }
- out:
- return ret;
- }
- static int is_inode_existent(struct send_ctx *sctx, u64 ino, u64 gen)
- {
- int ret;
- if (ino == BTRFS_FIRST_FREE_OBJECTID)
- return 1;
- ret = get_cur_inode_state(sctx, ino, gen);
- if (ret < 0)
- goto out;
- if (ret == inode_state_no_change ||
- ret == inode_state_did_create ||
- ret == inode_state_will_delete)
- ret = 1;
- else
- ret = 0;
- out:
- return ret;
- }
- /*
- * Helper function to lookup a dir item in a dir.
- */
- static int lookup_dir_item_inode(struct btrfs_root *root,
- u64 dir, const char *name, int name_len,
- u64 *found_inode,
- u8 *found_type)
- {
- int ret = 0;
- struct btrfs_dir_item *di;
- struct btrfs_key key;
- struct btrfs_path *path;
- path = alloc_path_for_send();
- if (!path)
- return -ENOMEM;
- di = btrfs_lookup_dir_item(NULL, root, path,
- dir, name, name_len, 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, &key);
- if (key.type == BTRFS_ROOT_ITEM_KEY) {
- ret = -ENOENT;
- goto out;
- }
- *found_inode = key.objectid;
- *found_type = btrfs_dir_type(path->nodes[0], di);
- out:
- btrfs_free_path(path);
- return ret;
- }
- /*
- * Looks up the first btrfs_inode_ref of a given ino. It returns the parent dir,
- * generation of the parent dir and the name of the dir entry.
- */
- static int get_first_ref(struct btrfs_root *root, u64 ino,
- u64 *dir, u64 *dir_gen, struct fs_path *name)
- {
- int ret;
- struct btrfs_key key;
- struct btrfs_key found_key;
- struct btrfs_path *path;
- int len;
- u64 parent_dir;
- path = alloc_path_for_send();
- if (!path)
- return -ENOMEM;
- key.objectid = ino;
- key.type = BTRFS_INODE_REF_KEY;
- key.offset = 0;
- ret = btrfs_search_slot_for_read(root, &key, path, 1, 0);
- if (ret < 0)
- goto out;
- if (!ret)
- btrfs_item_key_to_cpu(path->nodes[0], &found_key,
- path->slots[0]);
- if (ret || found_key.objectid != ino ||
- (found_key.type != BTRFS_INODE_REF_KEY &&
- found_key.type != BTRFS_INODE_EXTREF_KEY)) {
- ret = -ENOENT;
- goto out;
- }
- if (found_key.type == BTRFS_INODE_REF_KEY) {
- struct btrfs_inode_ref *iref;
- iref = btrfs_item_ptr(path->nodes[0], path->slots[0],
- struct btrfs_inode_ref);
- len = btrfs_inode_ref_name_len(path->nodes[0], iref);
- ret = fs_path_add_from_extent_buffer(name, path->nodes[0],
- (unsigned long)(iref + 1),
- len);
- parent_dir = found_key.offset;
- } else {
- struct btrfs_inode_extref *extref;
- extref = btrfs_item_ptr(path->nodes[0], path->slots[0],
- struct btrfs_inode_extref);
- len = btrfs_inode_extref_name_len(path->nodes[0], extref);
- ret = fs_path_add_from_extent_buffer(name, path->nodes[0],
- (unsigned long)&extref->name, len);
- parent_dir = btrfs_inode_extref_parent(path->nodes[0], extref);
- }
- if (ret < 0)
- goto out;
- btrfs_release_path(path);
- if (dir_gen) {
- ret = get_inode_info(root, parent_dir, NULL, dir_gen, NULL,
- NULL, NULL, NULL);
- if (ret < 0)
- goto out;
- }
- *dir = parent_dir;
- out:
- btrfs_free_path(path);
- return ret;
- }
- static int is_first_ref(struct btrfs_root *root,
- u64 ino, u64 dir,
- const char *name, int name_len)
- {
- int ret;
- struct fs_path *tmp_name;
- u64 tmp_dir;
- tmp_name = fs_path_alloc();
- if (!tmp_name)
- return -ENOMEM;
- ret = get_first_ref(root, ino, &tmp_dir, NULL, tmp_name);
- if (ret < 0)
- goto out;
- if (dir != tmp_dir || name_len != fs_path_len(tmp_name)) {
- ret = 0;
- goto out;
- }
- ret = !memcmp(tmp_name->start, name, name_len);
- out:
- fs_path_free(tmp_name);
- return ret;
- }
- /*
- * Used by process_recorded_refs to determine if a new ref would overwrite an
- * already existing ref. In case it detects an overwrite, it returns the
- * inode/gen in who_ino/who_gen.
- * When an overwrite is detected, process_recorded_refs does proper orphanizing
- * to make sure later references to the overwritten inode are possible.
- * Orphanizing is however only required for the first ref of an inode.
- * process_recorded_refs does an additional is_first_ref check to see if
- * orphanizing is really required.
- */
- static int will_overwrite_ref(struct send_ctx *sctx, u64 dir, u64 dir_gen,
- const char *name, int name_len,
- u64 *who_ino, u64 *who_gen, u64 *who_mode)
- {
- int ret = 0;
- u64 gen;
- u64 other_inode = 0;
- u8 other_type = 0;
- if (!sctx->parent_root)
- goto out;
- ret = is_inode_existent(sctx, dir, dir_gen);
- if (ret <= 0)
- goto out;
- /*
- * If we have a parent root we need to verify that the parent dir was
- * not deleted and then re-created, if it was then we have no overwrite
- * and we can just unlink this entry.
- */
- if (sctx->parent_root && dir != BTRFS_FIRST_FREE_OBJECTID) {
- ret = get_inode_info(sctx->parent_root, dir, NULL, &gen, NULL,
- NULL, NULL, NULL);
- if (ret < 0 && ret != -ENOENT)
- goto out;
- if (ret) {
- ret = 0;
- goto out;
- }
- if (gen != dir_gen)
- goto out;
- }
- ret = lookup_dir_item_inode(sctx->parent_root, dir, name, name_len,
- &other_inode, &other_type);
- if (ret < 0 && ret != -ENOENT)
- goto out;
- if (ret) {
- ret = 0;
- goto out;
- }
- /*
- * Check if the overwritten ref was already processed. If yes, the ref
- * was already unlinked/moved, so we can safely assume that we will not
- * overwrite anything at this point in time.
- */
- if (other_inode > sctx->send_progress ||
- is_waiting_for_move(sctx, other_inode)) {
- ret = get_inode_info(sctx->parent_root, other_inode, NULL,
- who_gen, who_mode, NULL, NULL, NULL);
- if (ret < 0)
- goto out;
- ret = 1;
- *who_ino = other_inode;
- } else {
- ret = 0;
- }
- out:
- return ret;
- }
- /*
- * Checks if the ref was overwritten by an already processed inode. This is
- * used by __get_cur_name_and_parent to find out if the ref was orphanized and
- * thus the orphan name needs be used.
- * process_recorded_refs also uses it to avoid unlinking of refs that were
- * overwritten.
- */
- static int did_overwrite_ref(struct send_ctx *sctx,
- u64 dir, u64 dir_gen,
- u64 ino, u64 ino_gen,
- const char *name, int name_len)
- {
- int ret = 0;
- u64 gen;
- u64 ow_inode;
- u8 other_type;
- if (!sctx->parent_root)
- goto out;
- ret = is_inode_existent(sctx, dir, dir_gen);
- if (ret <= 0)
- goto out;
- if (dir != BTRFS_FIRST_FREE_OBJECTID) {
- ret = get_inode_info(sctx->send_root, dir, NULL, &gen, NULL,
- NULL, NULL, NULL);
- if (ret < 0 && ret != -ENOENT)
- goto out;
- if (ret) {
- ret = 0;
- goto out;
- }
- if (gen != dir_gen)
- goto out;
- }
- /* check if the ref was overwritten by another ref */
- ret = lookup_dir_item_inode(sctx->send_root, dir, name, name_len,
- &ow_inode, &other_type);
- if (ret < 0 && ret != -ENOENT)
- goto out;
- if (ret) {
- /* was never and will never be overwritten */
- ret = 0;
- goto out;
- }
- ret = get_inode_info(sctx->send_root, ow_inode, NULL, &gen, NULL, NULL,
- NULL, NULL);
- if (ret < 0)
- goto out;
- if (ow_inode == ino && gen == ino_gen) {
- ret = 0;
- goto out;
- }
- /*
- * We know that it is or will be overwritten. Check this now.
- * The current inode being processed might have been the one that caused
- * inode 'ino' to be orphanized, therefore check if ow_inode matches
- * the current inode being processed.
- */
- if ((ow_inode < sctx->send_progress) ||
- (ino != sctx->cur_ino && ow_inode == sctx->cur_ino &&
- gen == sctx->cur_inode_gen))
- ret = 1;
- else
- ret = 0;
- out:
- return ret;
- }
- /*
- * Same as did_overwrite_ref, but also checks if it is the first ref of an inode
- * that got overwritten. This is used by process_recorded_refs to determine
- * if it has to use the path as returned by get_cur_path or the orphan name.
- */
- static int did_overwrite_first_ref(struct send_ctx *sctx, u64 ino, u64 gen)
- {
- int ret = 0;
- struct fs_path *name = NULL;
- u64 dir;
- u64 dir_gen;
- if (!sctx->parent_root)
- goto out;
- name = fs_path_alloc();
- if (!name)
- return -ENOMEM;
- ret = get_first_ref(sctx->parent_root, ino, &dir, &dir_gen, name);
- if (ret < 0)
- goto out;
- ret = did_overwrite_ref(sctx, dir, dir_gen, ino, gen,
- name->start, fs_path_len(name));
- out:
- fs_path_free(name);
- return ret;
- }
- /*
- * Insert a name cache entry. On 32bit kernels the radix tree index is 32bit,
- * so we need to do some special handling in case we have clashes. This function
- * takes care of this with the help of name_cache_entry::radix_list.
- * In case of error, nce is kfreed.
- */
- static int name_cache_insert(struct send_ctx *sctx,
- struct name_cache_entry *nce)
- {
- int ret = 0;
- struct list_head *nce_head;
- nce_head = radix_tree_lookup(&sctx->name_cache,
- (unsigned long)nce->ino);
- if (!nce_head) {
- nce_head = kmalloc(sizeof(*nce_head), GFP_KERNEL);
- if (!nce_head) {
- kfree(nce);
- return -ENOMEM;
- }
- INIT_LIST_HEAD(nce_head);
- ret = radix_tree_insert(&sctx->name_cache, nce->ino, nce_head);
- if (ret < 0) {
- kfree(nce_head);
- kfree(nce);
- return ret;
- }
- }
- list_add_tail(&nce->radix_list, nce_head);
- list_add_tail(&nce->list, &sctx->name_cache_list);
- sctx->name_cache_size++;
- return ret;
- }
- static void name_cache_delete(struct send_ctx *sctx,
- struct name_cache_entry *nce)
- {
- struct list_head *nce_head;
- nce_head = radix_tree_lookup(&sctx->name_cache,
- (unsigned long)nce->ino);
- if (!nce_head) {
- btrfs_err(sctx->send_root->fs_info,
- "name_cache_delete lookup failed ino %llu cache size %d, leaking memory",
- nce->ino, sctx->name_cache_size);
- }
- list_del(&nce->radix_list);
- list_del(&nce->list);
- sctx->name_cache_size--;
- /*
- * We may not get to the final release of nce_head if the lookup fails
- */
- if (nce_head && list_empty(nce_head)) {
- radix_tree_delete(&sctx->name_cache, (unsigned long)nce->ino);
- kfree(nce_head);
- }
- }
- static struct name_cache_entry *name_cache_search(struct send_ctx *sctx,
- u64 ino, u64 gen)
- {
- struct list_head *nce_head;
- struct name_cache_entry *cur;
- nce_head = radix_tree_lookup(&sctx->name_cache, (unsigned long)ino);
- if (!nce_head)
- return NULL;
- list_for_each_entry(cur, nce_head, radix_list) {
- if (cur->ino == ino && cur->gen == gen)
- return cur;
- }
- return NULL;
- }
- /*
- * Removes the entry from the list and adds it back to the end. This marks the
- * entry as recently used so that name_cache_clean_unused does not remove it.
- */
- static void name_cache_used(struct send_ctx *sctx, struct name_cache_entry *nce)
- {
- list_del(&nce->list);
- list_add_tail(&nce->list, &sctx->name_cache_list);
- }
- /*
- * Remove some entries from the beginning of name_cache_list.
- */
- static void name_cache_clean_unused(struct send_ctx *sctx)
- {
- struct name_cache_entry *nce;
- if (sctx->name_cache_size < SEND_CTX_NAME_CACHE_CLEAN_SIZE)
- return;
- while (sctx->name_cache_size > SEND_CTX_MAX_NAME_CACHE_SIZE) {
- nce = list_entry(sctx->name_cache_list.next,
- struct name_cache_entry, list);
- name_cache_delete(sctx, nce);
- kfree(nce);
- }
- }
- static void name_cache_free(struct send_ctx *sctx)
- {
- struct name_cache_entry *nce;
- while (!list_empty(&sctx->name_cache_list)) {
- nce = list_entry(sctx->name_cache_list.next,
- struct name_cache_entry, list);
- name_cache_delete(sctx, nce);
- kfree(nce);
- }
- }
- /*
- * Used by get_cur_path for each ref up to the root.
- * Returns 0 if it succeeded.
- * Returns 1 if the inode is not existent or got overwritten. In that case, the
- * name is an orphan name. This instructs get_cur_path to stop iterating. If 1
- * is returned, parent_ino/parent_gen are not guaranteed to be valid.
- * Returns <0 in case of error.
- */
- static int __get_cur_name_and_parent(struct send_ctx *sctx,
- u64 ino, u64 gen,
- u64 *parent_ino,
- u64 *parent_gen,
- struct fs_path *dest)
- {
- int ret;
- int nce_ret;
- struct name_cache_entry *nce = NULL;
- /*
- * First check if we already did a call to this function with the same
- * ino/gen. If yes, check if the cache entry is still up-to-date. If yes
- * return the cached result.
- */
- nce = name_cache_search(sctx, ino, gen);
- if (nce) {
- if (ino < sctx->send_progress && nce->need_later_update) {
- name_cache_delete(sctx, nce);
- kfree(nce);
- nce = NULL;
- } else {
- name_cache_used(sctx, nce);
- *parent_ino = nce->parent_ino;
- *parent_gen = nce->parent_gen;
- ret = fs_path_add(dest, nce->name, nce->name_len);
- if (ret < 0)
- goto out;
- ret = nce->ret;
- goto out;
- }
- }
- /*
- * If the inode is not existent yet, add the orphan name and return 1.
- * This should only happen for the parent dir that we determine in
- * __record_new_ref
- */
- ret = is_inode_existent(sctx, ino, gen);
- if (ret < 0)
- goto out;
- if (!ret) {
- ret = gen_unique_name(sctx, ino, gen, dest);
- if (ret < 0)
- goto out;
- ret = 1;
- goto out_cache;
- }
- /*
- * Depending on whether the inode was already processed or not, use
- * send_root or parent_root for ref lookup.
- */
- if (ino < sctx->send_progress)
- ret = get_first_ref(sctx->send_root, ino,
- parent_ino, parent_gen, dest);
- else
- ret = get_first_ref(sctx->parent_root, ino,
- parent_ino, parent_gen, dest);
- if (ret < 0)
- goto out;
- /*
- * Check if the ref was overwritten by an inode's ref that was processed
- * earlier. If yes, treat as orphan and return 1.
- */
- ret = did_overwrite_ref(sctx, *parent_ino, *parent_gen, ino, gen,
- dest->start, dest->end - dest->start);
- if (ret < 0)
- goto out;
- if (ret) {
- fs_path_reset(dest);
- ret = gen_unique_name(sctx, ino, gen, dest);
- if (ret < 0)
- goto out;
- ret = 1;
- }
- out_cache:
- /*
- * Store the result of the lookup in the name cache.
- */
- nce = kmalloc(sizeof(*nce) + fs_path_len(dest) + 1, GFP_KERNEL);
- if (!nce) {
- ret = -ENOMEM;
- goto out;
- }
- nce->ino = ino;
- nce->gen = gen;
- nce->parent_ino = *parent_ino;
- nce->parent_gen = *parent_gen;
- nce->name_len = fs_path_len(dest);
- nce->ret = ret;
- strcpy(nce->name, dest->start);
- if (ino < sctx->send_progress)
- nce->need_later_update = 0;
- else
- nce->need_later_update = 1;
- nce_ret = name_cache_insert(sctx, nce);
- if (nce_ret < 0)
- ret = nce_ret;
- name_cache_clean_unused(sctx);
- out:
- return ret;
- }
- /*
- * Magic happens here. This function returns the first ref to an inode as it
- * would look like while receiving the stream at this point in time.
- * We walk the path up to the root. For every inode in between, we check if it
- * was already processed/sent. If yes, we continue with the parent as found
- * in send_root. If not, we continue with the parent as found in parent_root.
- * If we encounter an inode that was deleted at this point in time, we use the
- * inodes "orphan" name instead of the real name and stop. Same with new inodes
- * that were not created yet and overwritten inodes/refs.
- *
- * When do we have orphan inodes:
- * 1. When an inode is freshly created and thus no valid refs are available yet
- * 2. When a directory lost all it's refs (deleted) but still has dir items
- * inside which were not processed yet (pending for move/delete). If anyone
- * tried to get the path to the dir items, it would get a path inside that
- * orphan directory.
- * 3. When an inode is moved around or gets new links, it may overwrite the ref
- * of an unprocessed inode. If in that case the first ref would be
- * overwritten, the overwritten inode gets "orphanized". Later when we
- * process this overwritten inode, it is restored at a new place by moving
- * the orphan inode.
- *
- * sctx->send_progress tells this function at which point in time receiving
- * would be.
- */
- static int get_cur_path(struct send_ctx *sctx, u64 ino, u64 gen,
- struct fs_path *dest)
- {
- int ret = 0;
- struct fs_path *name = NULL;
- u64 parent_inode = 0;
- u64 parent_gen = 0;
- int stop = 0;
- name = fs_path_alloc();
- if (!name) {
- ret = -ENOMEM;
- goto out;
- }
- dest->reversed = 1;
- fs_path_reset(dest);
- while (!stop && ino != BTRFS_FIRST_FREE_OBJECTID) {
- struct waiting_dir_move *wdm;
- fs_path_reset(name);
- if (is_waiting_for_rm(sctx, ino, gen)) {
- ret = gen_unique_name(sctx, ino, gen, name);
- if (ret < 0)
- goto out;
- ret = fs_path_add_path(dest, name);
- break;
- }
- wdm = get_waiting_dir_move(sctx, ino);
- if (wdm && wdm->orphanized) {
- ret = gen_unique_name(sctx, ino, gen, name);
- stop = 1;
- } else if (wdm) {
- ret = get_first_ref(sctx->parent_root, ino,
- &parent_inode, &parent_gen, name);
- } else {
- ret = __get_cur_name_and_parent(sctx, ino, gen,
- &parent_inode,
- &parent_gen, name);
- if (ret)
- stop = 1;
- }
- if (ret < 0)
- goto out;
- ret = fs_path_add_path(dest, name);
- if (ret < 0)
- goto out;
- ino = parent_inode;
- gen = parent_gen;
- }
- out:
- fs_path_free(name);
- if (!ret)
- fs_path_unreverse(dest);
- return ret;
- }
- /*
- * Sends a BTRFS_SEND_C_SUBVOL command/item to userspace
- */
- static int send_subvol_begin(struct send_ctx *sctx)
- {
- int ret;
- struct btrfs_root *send_root = sctx->send_root;
- struct btrfs_root *parent_root = sctx->parent_root;
- struct btrfs_path *path;
- struct btrfs_key key;
- struct btrfs_root_ref *ref;
- struct extent_buffer *leaf;
- char *name = NULL;
- int namelen;
- path = btrfs_alloc_path();
- if (!path)
- return -ENOMEM;
- name = kmalloc(BTRFS_PATH_NAME_MAX, GFP_KERNEL);
- if (!name) {
- btrfs_free_path(path);
- return -ENOMEM;
- }
- key.objectid = send_root->root_key.objectid;
- key.type = BTRFS_ROOT_BACKREF_KEY;
- key.offset = 0;
- ret = btrfs_search_slot_for_read(send_root->fs_info->tree_root,
- &key, path, 1, 0);
- if (ret < 0)
- goto out;
- if (ret) {
- ret = -ENOENT;
- goto out;
- }
- leaf = path->nodes[0];
- btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
- if (key.type != BTRFS_ROOT_BACKREF_KEY ||
- key.objectid != send_root->root_key.objectid) {
- ret = -ENOENT;
- goto out;
- }
- ref = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_root_ref);
- namelen = btrfs_root_ref_name_len(leaf, ref);
- read_extent_buffer(leaf, name, (unsigned long)(ref + 1), namelen);
- btrfs_release_path(path);
- if (parent_root) {
- ret = begin_cmd(sctx, BTRFS_SEND_C_SNAPSHOT);
- if (ret < 0)
- goto out;
- } else {
- ret = begin_cmd(sctx, BTRFS_SEND_C_SUBVOL);
- if (ret < 0)
- goto out;
- }
- TLV_PUT_STRING(sctx, BTRFS_SEND_A_PATH, name, namelen);
- if (!btrfs_is_empty_uuid(sctx->send_root->root_item.received_uuid))
- TLV_PUT_UUID(sctx, BTRFS_SEND_A_UUID,
- sctx->send_root->root_item.received_uuid);
- else
- TLV_PUT_UUID(sctx, BTRFS_SEND_A_UUID,
- sctx->send_root->root_item.uuid);
- TLV_PUT_U64(sctx, BTRFS_SEND_A_CTRANSID,
- le64_to_cpu(sctx->send_root->root_item.ctransid));
- if (parent_root) {
- if (!btrfs_is_empty_uuid(parent_root->root_item.received_uuid))
- TLV_PUT_UUID(sctx, BTRFS_SEND_A_CLONE_UUID,
- parent_root->root_item.received_uuid);
- else
- TLV_PUT_UUID(sctx, BTRFS_SEND_A_CLONE_UUID,
- parent_root->root_item.uuid);
- TLV_PUT_U64(sctx, BTRFS_SEND_A_CLONE_CTRANSID,
- le64_to_cpu(sctx->parent_root->root_item.ctransid));
- }
- ret = send_cmd(sctx);
- tlv_put_failure:
- out:
- btrfs_free_path(path);
- kfree(name);
- return ret;
- }
- static int send_truncate(struct send_ctx *sctx, u64 ino, u64 gen, u64 size)
- {
- struct btrfs_fs_info *fs_info = sctx->send_root->fs_info;
- int ret = 0;
- struct fs_path *p;
- btrfs_debug(fs_info, "send_truncate %llu size=%llu", ino, size);
- p = fs_path_alloc();
- if (!p)
- return -ENOMEM;
- ret = begin_cmd(sctx, BTRFS_SEND_C_TRUNCATE);
- if (ret < 0)
- goto out;
- ret = get_cur_path(sctx, ino, gen, p);
- if (ret < 0)
- goto out;
- TLV_PUT_PATH(sctx, BTRFS_SEND_A_PATH, p);
- TLV_PUT_U64(sctx, BTRFS_SEND_A_SIZE, size);
- ret = send_cmd(sctx);
- tlv_put_failure:
- out:
- fs_path_free(p);
- return ret;
- }
- static int send_chmod(struct send_ctx *sctx, u64 ino, u64 gen, u64 mode)
- {
- struct btrfs_fs_info *fs_info = sctx->send_root->fs_info;
- int ret = 0;
- struct fs_path *p;
- btrfs_debug(fs_info, "send_chmod %llu mode=%llu", ino, mode);
- p = fs_path_alloc();
- if (!p)
- return -ENOMEM;
- ret = begin_cmd(sctx, BTRFS_SEND_C_CHMOD);
- if (ret < 0)
- goto out;
- ret = get_cur_path(sctx, ino, gen, p);
- if (ret < 0)
- goto out;
- TLV_PUT_PATH(sctx, BTRFS_SEND_A_PATH, p);
- TLV_PUT_U64(sctx, BTRFS_SEND_A_MODE, mode & 07777);
- ret = send_cmd(sctx);
- tlv_put_failure:
- out:
- fs_path_free(p);
- return ret;
- }
- static int send_chown(struct send_ctx *sctx, u64 ino, u64 gen, u64 uid, u64 gid)
- {
- struct btrfs_fs_info *fs_info = sctx->send_root->fs_info;
- int ret = 0;
- struct fs_path *p;
- btrfs_debug(fs_info, "send_chown %llu uid=%llu, gid=%llu",
- ino, uid, gid);
- p = fs_path_alloc();
- if (!p)
- return -ENOMEM;
- ret = begin_cmd(sctx, BTRFS_SEND_C_CHOWN);
- if (ret < 0)
- goto out;
- ret = get_cur_path(sctx, ino, gen, p);
- if (ret < 0)
- goto out;
- TLV_PUT_PATH(sctx, BTRFS_SEND_A_PATH, p);
- TLV_PUT_U64(sctx, BTRFS_SEND_A_UID, uid);
- TLV_PUT_U64(sctx, BTRFS_SEND_A_GID, gid);
- ret = send_cmd(sctx);
- tlv_put_failure:
- out:
- fs_path_free(p);
- return ret;
- }
- static int send_utimes(struct send_ctx *sctx, u64 ino, u64 gen)
- {
- struct btrfs_fs_info *fs_info = sctx->send_root->fs_info;
- int ret = 0;
- struct fs_path *p = NULL;
- struct btrfs_inode_item *ii;
- struct btrfs_path *path = NULL;
- struct extent_buffer *eb;
- struct btrfs_key key;
- int slot;
- btrfs_debug(fs_info, "send_utimes %llu", ino);
- p = fs_path_alloc();
- if (!p)
- return -ENOMEM;
- path = alloc_path_for_send();
- if (!path) {
- ret = -ENOMEM;
- goto out;
- }
- key.objectid = ino;
- key.type = BTRFS_INODE_ITEM_KEY;
- key.offset = 0;
- ret = btrfs_search_slot(NULL, sctx->send_root, &key, path, 0, 0);
- if (ret > 0)
- ret = -ENOENT;
- if (ret < 0)
- goto out;
- eb = path->nodes[0];
- slot = path->slots[0];
- ii = btrfs_item_ptr(eb, slot, struct btrfs_inode_item);
- ret = begin_cmd(sctx, BTRFS_SEND_C_UTIMES);
- if (ret < 0)
- goto out;
- ret = get_cur_path(sctx, ino, gen, p);
- if (ret < 0)
- goto out;
- TLV_PUT_PATH(sctx, BTRFS_SEND_A_PATH, p);
- TLV_PUT_BTRFS_TIMESPEC(sctx, BTRFS_SEND_A_ATIME, eb, &ii->atime);
- TLV_PUT_BTRFS_TIMESPEC(sctx, BTRFS_SEND_A_MTIME, eb, &ii->mtime);
- TLV_PUT_BTRFS_TIMESPEC(sctx, BTRFS_SEND_A_CTIME, eb, &ii->ctime);
- /* TODO Add otime support when the otime patches get into upstream */
- ret = send_cmd(sctx);
- tlv_put_failure:
- out:
- fs_path_free(p);
- btrfs_free_path(path);
- return ret;
- }
- /*
- * Sends a BTRFS_SEND_C_MKXXX or SYMLINK command to user space. We don't have
- * a valid path yet because we did not process the refs yet. So, the inode
- * is created as orphan.
- */
- static int send_create_inode(struct send_ctx *sctx, u64 ino)
- {
- struct btrfs_fs_info *fs_info = sctx->send_root->fs_info;
- int ret = 0;
- struct fs_path *p;
- int cmd;
- u64 gen;
- u64 mode;
- u64 rdev;
- btrfs_debug(fs_info, "send_create_inode %llu", ino);
- p = fs_path_alloc();
- if (!p)
- return -ENOMEM;
- if (ino != sctx->cur_ino) {
- ret = get_inode_info(sctx->send_root, ino, NULL, &gen, &mode,
- NULL, NULL, &rdev);
- if (ret < 0)
- goto out;
- } else {
- gen = sctx->cur_inode_gen;
- mode = sctx->cur_inode_mode;
- rdev = sctx->cur_inode_rdev;
- }
- if (S_ISREG(mode)) {
- cmd = BTRFS_SEND_C_MKFILE;
- } else if (S_ISDIR(mode)) {
- cmd = BTRFS_SEND_C_MKDIR;
- } else if (S_ISLNK(mode)) {
- cmd = BTRFS_SEND_C_SYMLINK;
- } else if (S_ISCHR(mode) || S_ISBLK(mode)) {
- cmd = BTRFS_SEND_C_MKNOD;
- } else if (S_ISFIFO(mode)) {
- cmd = BTRFS_SEND_C_MKFIFO;
- } else if (S_ISSOCK(mode)) {
- cmd = BTRFS_SEND_C_MKSOCK;
- } else {
- btrfs_warn(sctx->send_root->fs_info, "unexpected inode type %o",
- (int)(mode & S_IFMT));
- ret = -EOPNOTSUPP;
- goto out;
- }
- ret = begin_cmd(sctx, cmd);
- if (ret < 0)
- goto out;
- ret = gen_unique_name(sctx, ino, gen, p);
- if (ret < 0)
- goto out;
- TLV_PUT_PATH(sctx, BTRFS_SEND_A_PATH, p);
- TLV_PUT_U64(sctx, BTRFS_SEND_A_INO, ino);
- if (S_ISLNK(mode)) {
- fs_path_reset(p);
- ret = read_symlink(sctx->send_root, ino, p);
- if (ret < 0)
- goto out;
- TLV_PUT_PATH(sctx, BTRFS_SEND_A_PATH_LINK, p);
- } else if (S_ISCHR(mode) || S_ISBLK(mode) ||
- S_ISFIFO(mode) || S_ISSOCK(mode)) {
- TLV_PUT_U64(sctx, BTRFS_SEND_A_RDEV, new_encode_dev(rdev));
- TLV_PUT_U64(sctx, BTRFS_SEND_A_MODE, mode);
- }
- ret = send_cmd(sctx);
- if (ret < 0)
- goto out;
- tlv_put_failure:
- out:
- fs_path_free(p);
- return ret;
- }
- /*
- * We need some special handling for inodes that get processed before the parent
- * directory got created. See process_recorded_refs for details.
- * This function does the check if we already created the dir out of order.
- */
- static int did_create_dir(struct send_ctx *sctx, u64 dir)
- {
- int ret = 0;
- struct btrfs_path *path = NULL;
- struct btrfs_key key;
- struct btrfs_key found_key;
- struct btrfs_key di_key;
- struct extent_buffer *eb;
- struct btrfs_dir_item *di;
- int slot;
- path = alloc_path_for_send();
- if (!path) {
- ret = -ENOMEM;
- goto out;
- }
- key.objectid = dir;
- key.type = BTRFS_DIR_INDEX_KEY;
- key.offset = 0;
- ret = btrfs_search_slot(NULL, sctx->send_root, &key, path, 0, 0);
- if (ret < 0)
- goto out;
- while (1) {
- eb = path->nodes[0];
- slot = path->slots[0];
- if (slot >= btrfs_header_nritems(eb)) {
- ret = btrfs_next_leaf(sctx->send_root, path);
- if (ret < 0) {
- goto out;
- } else if (ret > 0) {
- ret = 0;
- break;
- }
- continue;
- }
- btrfs_item_key_to_cpu(eb, &found_key, slot);
- if (found_key.objectid != key.objectid ||
- found_key.type != key.type) {
- ret = 0;
- goto out;
- }
- di = btrfs_item_ptr(eb, slot, struct btrfs_dir_item);
- btrfs_dir_item_key_to_cpu(eb, di, &di_key);
- if (di_key.type != BTRFS_ROOT_ITEM_KEY &&
- di_key.objectid < sctx->send_progress) {
- ret = 1;
- goto out;
- }
- path->slots[0]++;
- }
- out:
- btrfs_free_path(path);
- return ret;
- }
- /*
- * Only creates the inode if it is:
- * 1. Not a directory
- * 2. Or a directory which was not created already due to out of order
- * directories. See did_create_dir and process_recorded_refs for details.
- */
- static int send_create_inode_if_needed(struct send_ctx *sctx)
- {
- int ret;
- if (S_ISDIR(sctx->cur_inode_mode)) {
- ret = did_create_dir(sctx, sctx->cur_ino);
- if (ret < 0)
- goto out;
- if (ret) {
- ret = 0;
- goto out;
- }
- }
- ret = send_create_inode(sctx, sctx->cur_ino);
- if (ret < 0)
- goto out;
- out:
- return ret;
- }
- struct recorded_ref {
- struct list_head list;
- char *name;
- struct fs_path *full_path;
- u64 dir;
- u64 dir_gen;
- int name_len;
- };
- static void set_ref_path(struct recorded_ref *ref, struct fs_path *path)
- {
- ref->full_path = path;
- ref->name = (char *)kbasename(ref->full_path->start);
- ref->name_len = ref->full_path->end - ref->name;
- }
- /*
- * We need to process new refs before deleted refs, but compare_tree gives us
- * everything mixed. So we first record all refs and later process them.
- * This function is a helper to record one ref.
- */
- static int __record_ref(struct list_head *head, u64 dir,
- u64 dir_gen, struct fs_path *path)
- {
- struct recorded_ref *ref;
- ref = kmalloc(sizeof(*ref), GFP_KERNEL);
- if (!ref)
- return -ENOMEM;
- ref->dir = dir;
- ref->dir_gen = dir_gen;
- set_ref_path(ref, path);
- list_add_tail(&ref->list, head);
- return 0;
- }
- static int dup_ref(struct recorded_ref *ref, struct list_head *list)
- {
- struct recorded_ref *new;
- new = kmalloc(sizeof(*ref), GFP_KERNEL);
- if (!new)
- return -ENOMEM;
- new->dir = ref->dir;
- new->dir_gen = ref->dir_gen;
- new->full_path = NULL;
- INIT_LIST_HEAD(&new->list);
- list_add_tail(&new->list, list);
- return 0;
- }
- static void __free_recorded_refs(struct list_head *head)
- {
- struct recorded_ref *cur;
- while (!list_empty(head)) {
- cur = list_entry(head->next, struct recorded_ref, list);
- fs_path_free(cur->full_path);
- list_del(&cur->list);
- kfree(cur);
- }
- }
- static void free_recorded_refs(struct send_ctx *sctx)
- {
- __free_recorded_refs(&sctx->new_refs);
- __free_recorded_refs(&sctx->deleted_refs);
- }
- /*
- * Renames/moves a file/dir to its orphan name. Used when the first
- * ref of an unprocessed inode gets overwritten and for all non empty
- * directories.
- */
- static int orphanize_inode(struct send_ctx *sctx, u64 ino, u64 gen,
- struct fs_path *path)
- {
- int ret;
- struct fs_path *orphan;
- orphan = fs_path_alloc();
- if (!orphan)
- return -ENOMEM;
- ret = gen_unique_name(sctx, ino, gen, orphan);
- if (ret < 0)
- goto out;
- ret = send_rename(sctx, path, orphan);
- out:
- fs_path_free(orphan);
- return ret;
- }
- static struct orphan_dir_info *add_orphan_dir_info(struct send_ctx *sctx,
- u64 dir_ino, u64 dir_gen)
- {
- struct rb_node **p = &sctx->orphan_dirs.rb_node;
- struct rb_node *parent = NULL;
- struct orphan_dir_info *entry, *odi;
- while (*p) {
- parent = *p;
- entry = rb_entry(parent, struct orphan_dir_info, node);
- if (dir_ino < entry->ino)
- p = &(*p)->rb_left;
- else if (dir_ino > entry->ino)
- p = &(*p)->rb_right;
- else if (dir_gen < entry->gen)
- p = &(*p)->rb_left;
- else if (dir_gen > entry->gen)
- p = &(*p)->rb_right;
- else
- return entry;
- }
- odi = kmalloc(sizeof(*odi), GFP_KERNEL);
- if (!odi)
- return ERR_PTR(-ENOMEM);
- odi->ino = dir_ino;
- odi->gen = dir_gen;
- odi->last_dir_index_offset = 0;
- rb_link_node(&odi->node, parent, p);
- rb_insert_color(&odi->node, &sctx->orphan_dirs);
- return odi;
- }
- static struct orphan_dir_info *get_orphan_dir_info(struct send_ctx *sctx,
- u64 dir_ino, u64 gen)
- {
- struct rb_node *n = sctx->orphan_dirs.rb_node;
- struct orphan_dir_info *entry;
- while (n) {
- entry = rb_entry(n, struct orphan_dir_info, node);
- if (dir_ino < entry->ino)
- n = n->rb_left;
- else if (dir_ino > entry->ino)
- n = n->rb_right;
- else if (gen < entry->gen)
- n = n->rb_left;
- else if (gen > entry->gen)
- n = n->rb_right;
- else
- return entry;
- }
- return NULL;
- }
- static int is_waiting_for_rm(struct send_ctx *sctx, u64 dir_ino, u64 gen)
- {
- struct orphan_dir_info *odi = get_orphan_dir_info(sctx, dir_ino, gen);
- return odi != NULL;
- }
- static void free_orphan_dir_info(struct send_ctx *sctx,
- struct orphan_dir_info *odi)
- {
- if (!odi)
- return;
- rb_erase(&odi->node, &sctx->orphan_dirs);
- kfree(odi);
- }
- /*
- * Returns 1 if a directory can be removed at this point in time.
- * We check this by iterating all dir items and checking if the inode behind
- * the dir item was already processed.
- */
- static int can_rmdir(struct send_ctx *sctx, u64 dir, u64 dir_gen,
- u64 send_progress)
- {
- int ret = 0;
- struct btrfs_root *root = sctx->parent_root;
- struct btrfs_path *path;
- struct btrfs_key key;
- struct btrfs_key found_key;
- struct btrfs_key loc;
- struct btrfs_dir_item *di;
- struct orphan_dir_info *odi = NULL;
- /*
- * Don't try to rmdir the top/root subvolume dir.
- */
- if (dir == BTRFS_FIRST_FREE_OBJECTID)
- return 0;
- path = alloc_path_for_send();
- if (!path)
- return -ENOMEM;
- key.objectid = dir;
- key.type = BTRFS_DIR_INDEX_KEY;
- key.offset = 0;
- odi = get_orphan_dir_info(sctx, dir, dir_gen);
- if (odi)
- key.offset = odi->last_dir_index_offset;
- ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
- if (ret < 0)
- goto out;
- while (1) {
- struct waiting_dir_move *dm;
- if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) {
- ret = btrfs_next_leaf(root, path);
- if (ret < 0)
- goto out;
- else if (ret > 0)
- break;
- continue;
- }
- btrfs_item_key_to_cpu(path->nodes[0], &found_key,
- path->slots[0]);
- if (found_key.objectid != key.objectid ||
- found_key.type != key.type)
- break;
- di = btrfs_item_ptr(path->nodes[0], path->slots[0],
- struct btrfs_dir_item);
- btrfs_dir_item_key_to_cpu(path->nodes[0], di, &loc);
- dm = get_waiting_dir_move(sctx, loc.objectid);
- if (dm) {
- odi = add_orphan_dir_info(sctx, dir, dir_gen);
- if (IS_ERR(odi)) {
- ret = PTR_ERR(odi);
- goto out;
- }
- odi->gen = dir_gen;
- odi->last_dir_index_offset = found_key.offset;
- dm->rmdir_ino = dir;
- dm->rmdir_gen = dir_gen;
- ret = 0;
- goto out;
- }
- if (loc.objectid > send_progress) {
- odi = add_orphan_dir_info(sctx, dir, dir_gen);
- if (IS_ERR(odi)) {
- ret = PTR_ERR(odi);
- goto out;
- }
- odi->gen = dir_gen;
- odi->last_dir_index_offset = found_key.offset;
- ret = 0;
- goto out;
- }
- path->slots[0]++;
- }
- free_orphan_dir_info(sctx, odi);
- ret = 1;
- out:
- btrfs_free_path(path);
- return ret;
- }
- static int is_waiting_for_move(struct send_ctx *sctx, u64 ino)
- {
- struct waiting_dir_move *entry = get_waiting_dir_move(sctx, ino);
- return entry != NULL;
- }
- static int add_waiting_dir_move(struct send_ctx *sctx, u64 ino, bool orphanized)
- {
- struct rb_node **p = &sctx->waiting_dir_moves.rb_node;
- struct rb_node *parent = NULL;
- struct waiting_dir_move *entry, *dm;
- dm = kmalloc(sizeof(*dm), GFP_KERNEL);
- if (!dm)
- return -ENOMEM;
- dm->ino = ino;
- dm->rmdir_ino = 0;
- dm->rmdir_gen = 0;
- dm->orphanized = orphanized;
- while (*p) {
- parent = *p;
- entry = rb_entry(parent, struct waiting_dir_move, node);
- if (ino < entry->ino) {
- p = &(*p)->rb_left;
- } else if (ino > entry->ino) {
- p = &(*p)->rb_right;
- } else {
- kfree(dm);
- return -EEXIST;
- }
- }
- rb_link_node(&dm->node, parent, p);
- rb_insert_color(&dm->node, &sctx->waiting_dir_moves);
- return 0;
- }
- static struct waiting_dir_move *
- get_waiting_dir_move(struct send_ctx *sctx, u64 ino)
- {
- struct rb_node *n = sctx->waiting_dir_moves.rb_node;
- struct waiting_dir_move *entry;
- while (n) {
- entry = rb_entry(n, struct waiting_dir_move, node);
- if (ino < entry->ino)
- n = n->rb_left;
- else if (ino > entry->ino)
- n = n->rb_right;
- else
- return entry;
- }
- return NULL;
- }
- static void free_waiting_dir_move(struct send_ctx *sctx,
- struct waiting_dir_move *dm)
- {
- if (!dm)
- return;
- rb_erase(&dm->node, &sctx->waiting_dir_moves);
- kfree(dm);
- }
- static int add_pending_dir_move(struct send_ctx *sctx,
- u64 ino,
- u64 ino_gen,
- u64 parent_ino,
- struct list_head *new_refs,
- struct list_head *deleted_refs,
- const bool is_orphan)
- {
- struct rb_node **p = &sctx->pending_dir_moves.rb_node;
- struct rb_node *parent = NULL;
- struct pending_dir_move *entry = NULL, *pm;
- struct recorded_ref *cur;
- int exists = 0;
- int ret;
- pm = kmalloc(sizeof(*pm), GFP_KERNEL);
- if (!pm)
- return -ENOMEM;
- pm->parent_ino = parent_ino;
- pm->ino = ino;
- pm->gen = ino_gen;
- INIT_LIST_HEAD(&pm->list);
- INIT_LIST_HEAD(&pm->update_refs);
- RB_CLEAR_NODE(&pm->node);
- while (*p) {
- parent = *p;
- entry = rb_entry(parent, struct pending_dir_move, node);
- if (parent_ino < entry->parent_ino) {
- p = &(*p)->rb_left;
- } else if (parent_ino > entry->parent_ino) {
- p = &(*p)->rb_right;
- } else {
- exists = 1;
- break;
- }
- }
- list_for_each_entry(cur, deleted_refs, list) {
- ret = dup_ref(cur, &pm->update_refs);
- if (ret < 0)
- goto out;
- }
- list_for_each_entry(cur, new_refs, list) {
- ret = dup_ref(cur, &pm->update_refs);
- if (ret < 0)
- goto out;
- }
- ret = add_waiting_dir_move(sctx, pm->ino, is_orphan);
- if (ret)
- goto out;
- if (exists) {
- list_add_tail(&pm->list, &entry->list);
- } else {
- rb_link_node(&pm->node, parent, p);
- rb_insert_color(&pm->node, &sctx->pending_dir_moves);
- }
- ret = 0;
- out:
- if (ret) {
- __free_recorded_refs(&pm->update_refs);
- kfree(pm);
- }
- return ret;
- }
- static struct pending_dir_move *get_pending_dir_moves(struct send_ctx *sctx,
- u64 parent_ino)
- {
- struct rb_node *n = sctx->pending_dir_moves.rb_node;
- struct pending_dir_move *entry;
- while (n) {
- entry = rb_entry(n, struct pending_dir_move, node);
- if (parent_ino < entry->parent_ino)
- n = n->rb_left;
- else if (parent_ino > entry->parent_ino)
- n = n->rb_right;
- else
- return entry;
- }
- return NULL;
- }
- static int path_loop(struct send_ctx *sctx, struct fs_path *name,
- u64 ino, u64 gen, u64 *ancestor_ino)
- {
- int ret = 0;
- u64 parent_inode = 0;
- u64 parent_gen = 0;
- u64 start_ino = ino;
- *ancestor_ino = 0;
- while (ino != BTRFS_FIRST_FREE_OBJECTID) {
- fs_path_reset(name);
- if (is_waiting_for_rm(sctx, ino, gen))
- break;
- if (is_waiting_for_move(sctx, ino)) {
- if (*ancestor_ino == 0)
- *ancestor_ino = ino;
- ret = get_first_ref(sctx->parent_root, ino,
- &parent_inode, &parent_gen, name);
- } else {
- ret = __get_cur_name_and_parent(sctx, ino, gen,
- &parent_inode,
- &parent_gen, name);
- if (ret > 0) {
- ret = 0;
- break;
- }
- }
- if (ret < 0)
- break;
- if (parent_inode == start_ino) {
- ret = 1;
- if (*ancestor_ino == 0)
- *ancestor_ino = ino;
- break;
- }
- ino = parent_inode;
- gen = parent_gen;
- }
- return ret;
- }
- static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm)
- {
- struct fs_path *from_path = NULL;
- struct fs_path *to_path = NULL;
- struct fs_path *name = NULL;
- u64 orig_progress = sctx->send_progress;
- struct recorded_ref *cur;
- u64 parent_ino, parent_gen;
- struct waiting_dir_move *dm = NULL;
- u64 rmdir_ino = 0;
- u64 rmdir_gen;
- u64 ancestor;
- bool is_orphan;
- int ret;
- name = fs_path_alloc();
- from_path = fs_path_alloc();
- if (!name || !from_path) {
- ret = -ENOMEM;
- goto out;
- }
- dm = get_waiting_dir_move(sctx, pm->ino);
- ASSERT(dm);
- rmdir_ino = dm->rmdir_ino;
- rmdir_gen = dm->rmdir_gen;
- is_orphan = dm->orphanized;
- free_waiting_dir_move(sctx, dm);
- if (is_orphan) {
- ret = gen_unique_name(sctx, pm->ino,
- pm->gen, from_path);
- } else {
- ret = get_first_ref(sctx->parent_root, pm->ino,
- &parent_ino, &parent_gen, name);
- if (ret < 0)
- goto out;
- ret = get_cur_path(sctx, parent_ino, parent_gen,
- from_path);
- if (ret < 0)
- goto out;
- ret = fs_path_add_path(from_path, name);
- }
- if (ret < 0)
- goto out;
- sctx->send_progress = sctx->cur_ino + 1;
- ret = path_loop(sctx, name, pm->ino, pm->gen, &ancestor);
- if (ret < 0)
- goto out;
- if (ret) {
- LIST_HEAD(deleted_refs);
- ASSERT(ancestor > BTRFS_FIRST_FREE_OBJECTID);
- ret = add_pending_dir_move(sctx, pm->ino, pm->gen, ancestor,
- &pm->update_refs, &deleted_refs,
- is_orphan);
- if (ret < 0)
- goto out;
- if (rmdir_ino) {
- dm = get_waiting_dir_move(sctx, pm->ino);
- ASSERT(dm);
- dm->rmdir_ino = rmdir_ino;
- dm->rmdir_gen = rmdir_gen;
- }
- goto out;
- }
- fs_path_reset(name);
- to_path = name;
- name = NULL;
- ret = get_cur_path(sctx, pm->ino, pm->gen, to_path);
- if (ret < 0)
- goto out;
- ret = send_rename(sctx, from_path, to_path);
- if (ret < 0)
- goto out;
- if (rmdir_ino) {
- struct orphan_dir_info *odi;
- u64 gen;
- odi = get_orphan_dir_info(sctx, rmdir_ino, rmdir_gen);
- if (!odi) {
- /* already deleted */
- goto finish;
- }
- gen = odi->gen;
- ret = can_rmdir(sctx, rmdir_ino, gen, sctx->cur_ino);
- if (ret < 0)
- goto out;
- if (!ret)
- goto finish;
- name = fs_path_alloc();
- if (!name) {
- ret = -ENOMEM;
- goto out;
- }
- ret = get_cur_path(sctx, rmdir_ino, gen, name);
- if (ret < 0)
- goto out;
- ret = send_rmdir(sctx, name);
- if (ret < 0)
- goto out;
- }
- finish:
- ret = send_utimes(sctx, pm->ino, pm->gen);
- if (ret < 0)
- goto out;
- /*
- * After rename/move, need to update the utimes of both new parent(s)
- * and old parent(s).
- */
- list_for_each_entry(cur, &pm->update_refs, list) {
- /*
- * The parent inode might have been deleted in the send snapshot
- */
- ret = get_inode_info(sctx->send_root, cur->dir, NULL,
- NULL, NULL, NULL, NULL, NULL);
- if (ret == -ENOENT) {
- ret = 0;
- continue;
- }
- if (ret < 0)
- goto out;
- ret = send_utimes(sctx, cur->dir, cur->dir_gen);
- if (ret < 0)
- goto out;
- }
- out:
- fs_path_free(name);
- fs_path_free(from_path);
- fs_path_free(to_path);
- sctx->send_progress = orig_progress;
- return ret;
- }
- static void free_pending_move(struct send_ctx *sctx, struct pending_dir_move *m)
- {
- if (!list_empty(&m->list))
- list_del(&m->list);
- if (!RB_EMPTY_NODE(&m->node))
- rb_erase(&m->node, &sctx->pending_dir_moves);
- __free_recorded_refs(&m->update_refs);
- kfree(m);
- }
- static void tail_append_pending_moves(struct send_ctx *sctx,
- struct pending_dir_move *moves,
- struct list_head *stack)
- {
- if (list_empty(&moves->list)) {
- list_add_tail(&moves->list, stack);
- } else {
- LIST_HEAD(list);
- list_splice_init(&moves->list, &list);
- list_add_tail(&moves->list, stack);
- list_splice_tail(&list, stack);
- }
- if (!RB_EMPTY_NODE(&moves->node)) {
- rb_erase(&moves->node, &sctx->pending_dir_moves);
- RB_CLEAR_NODE(&moves->node);
- }
- }
- static int apply_children_dir_moves(struct send_ctx *sctx)
- {
- struct pending_dir_move *pm;
- struct list_head stack;
- u64 parent_ino = sctx->cur_ino;
- int ret = 0;
- pm = get_pending_dir_moves(sctx, parent_ino);
- if (!pm)
- return 0;
- INIT_LIST_HEAD(&stack);
- tail_append_pending_moves(sctx, pm, &stack);
- while (!list_empty(&stack)) {
- pm = list_first_entry(&stack, struct pending_dir_move, list);
- parent_ino = pm->ino;
- ret = apply_dir_move(sctx, pm);
- free_pending_move(sctx, pm);
- if (ret)
- goto out;
- pm = get_pending_dir_moves(sctx, parent_ino);
- if (pm)
- tail_append_pending_moves(sctx, pm, &stack);
- }
- return 0;
- out:
- while (!list_empty(&stack)) {
- pm = list_first_entry(&stack, struct pending_dir_move, list);
- free_pending_move(sctx, pm);
- }
- return ret;
- }
- /*
- * We might need to delay a directory rename even when no ancestor directory
- * (in the send root) with a higher inode number than ours (sctx->cur_ino) was
- * renamed. This happens when we rename a directory to the old name (the name
- * in the parent root) of some other unrelated directory that got its rename
- * delayed due to some ancestor with higher number that got renamed.
- *
- * Example:
- *
- * Parent snapshot:
- * . (ino 256)
- * |---- a/ (ino 257)
- * | |---- file (ino 260)
- * |
- * |---- b/ (ino 258)
- * |---- c/ (ino 259)
- *
- * Send snapshot:
- * . (ino 256)
- * |---- a/ (ino 258)
- * |---- x/ (ino 259)
- * |---- y/ (ino 257)
- * |----- file (ino 260)
- *
- * Here we can not rename 258 from 'b' to 'a' without the rename of inode 257
- * from 'a' to 'x/y' happening first, which in turn depends on the rename of
- * inode 259 from 'c' to 'x'. So the order of rename commands the send stream
- * must issue is:
- *
- * 1 - rename 259 from 'c' to 'x'
- * 2 - rename 257 from 'a' to 'x/y'
- * 3 - rename 258 from 'b' to 'a'
- *
- * Returns 1 if the rename of sctx->cur_ino needs to be delayed, 0 if it can
- * be done right away and < 0 on error.
- */
- static int wait_for_dest_dir_move(struct send_ctx *sctx,
- struct recorded_ref *parent_ref,
- const bool is_orphan)
- {
- struct btrfs_fs_info *fs_info = sctx->parent_root->fs_info;
- struct btrfs_path *path;
- struct btrfs_key key;
- struct btrfs_key di_key;
- struct btrfs_dir_item *di;
- u64 left_gen;
- u64 right_gen;
- int ret = 0;
- struct waiting_dir_move *wdm;
- if (RB_EMPTY_ROOT(&sctx->waiting_dir_moves))
- return 0;
- path = alloc_path_for_send();
- if (!path)
- return -ENOMEM;
- key.objectid = parent_ref->dir;
- key.type = BTRFS_DIR_ITEM_KEY;
- key.offset = btrfs_name_hash(parent_ref->name, parent_ref->name_len);
- ret = btrfs_search_slot(NULL, sctx->parent_root, &key, path, 0, 0);
- if (ret < 0) {
- goto out;
- } else if (ret > 0) {
- ret = 0;
- goto out;
- }
- di = btrfs_match_dir_item_name(fs_info, path, parent_ref->name,
- parent_ref->name_len);
- if (!di) {
- ret = 0;
- goto out;
- }
- /*
- * di_key.objectid has the number of the inode that has a dentry in the
- * parent directory with the same name that sctx->cur_ino is being
- * renamed to. We need to check if that inode is in the send root as
- * well and if it is currently marked as an inode with a pending rename,
- * if it is, we need to delay the rename of sctx->cur_ino as well, so
- * that it happens after that other inode is renamed.
- */
- btrfs_dir_item_key_to_cpu(path->nodes[0], di, &di_key);
- if (di_key.type != BTRFS_INODE_ITEM_KEY) {
- ret = 0;
- goto out;
- }
- ret = get_inode_info(sctx->parent_root, di_key.objectid, NULL,
- &left_gen, NULL, NULL, NULL, NULL);
- if (ret < 0)
- goto out;
- ret = get_inode_info(sctx->send_root, di_key.objectid, NULL,
- &right_gen, NULL, NULL, NULL, NULL);
- if (ret < 0) {
- if (ret == -ENOENT)
- ret = 0;
- goto out;
- }
- /* Different inode, no need to delay the rename of sctx->cur_ino */
- if (right_gen != left_gen) {
- ret = 0;
- goto out;
- }
- wdm = get_waiting_dir_move(sctx, di_key.objectid);
- if (wdm && !wdm->orphanized) {
- ret = add_pending_dir_move(sctx,
- sctx->cur_ino,
- sctx->cur_inode_gen,
- di_key.objectid,
- &sctx->new_refs,
- &sctx->deleted_refs,
- is_orphan);
- if (!ret)
- ret = 1;
- }
- out:
- btrfs_free_path(path);
- return ret;
- }
- /*
- * Check if inode ino2, or any of its ancestors, is inode ino1.
- * Return 1 if true, 0 if false and < 0 on error.
- */
- static int check_ino_in_path(struct btrfs_root *root,
- const u64 ino1,
- const u64 ino1_gen,
- const u64 ino2,
- const u64 ino2_gen,
- struct fs_path *fs_path)
- {
- u64 ino = ino2;
- if (ino1 == ino2)
- return ino1_gen == ino2_gen;
- while (ino > BTRFS_FIRST_FREE_OBJECTID) {
- u64 parent;
- u64 parent_gen;
- int ret;
- fs_path_reset(fs_path);
- ret = get_first_ref(root, ino, &parent, &parent_gen, fs_path);
- if (ret < 0)
- return ret;
- if (parent == ino1)
- return parent_gen == ino1_gen;
- ino = parent;
- }
- return 0;
- }
- /*
- * Check if ino ino1 is an ancestor of inode ino2 in the given root for any
- * possible path (in case ino2 is not a directory and has multiple hard links).
- * Return 1 if true, 0 if false and < 0 on error.
- */
- static int is_ancestor(struct btrfs_root *root,
- const u64 ino1,
- const u64 ino1_gen,
- const u64 ino2,
- struct fs_path *fs_path)
- {
- bool free_fs_path = false;
- int ret = 0;
- struct btrfs_path *path = NULL;
- struct btrfs_key key;
- if (!fs_path) {
- fs_path = fs_path_alloc();
- if (!fs_path)
- return -ENOMEM;
- free_fs_path = true;
- }
- path = alloc_path_for_send();
- if (!path) {
- ret = -ENOMEM;
- goto out;
- }
- key.objectid = ino2;
- key.type = BTRFS_INODE_REF_KEY;
- key.offset = 0;
- ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
- if (ret < 0)
- goto out;
- while (true) {
- struct extent_buffer *leaf = path->nodes[0];
- int slot = path->slots[0];
- u32 cur_offset = 0;
- u32 item_size;
- if (slot >= btrfs_header_nritems(leaf)) {
- ret = btrfs_next_leaf(root, path);
- if (ret < 0)
- goto out;
- if (ret > 0)
- break;
- continue;
- }
- btrfs_item_key_to_cpu(leaf, &key, slot);
- if (key.objectid != ino2)
- break;
- if (key.type != BTRFS_INODE_REF_KEY &&
- key.type != BTRFS_INODE_EXTREF_KEY)
- break;
- item_size = btrfs_item_size_nr(leaf, slot);
- while (cur_offset < item_size) {
- u64 parent;
- u64 parent_gen;
- if (key.type == BTRFS_INODE_EXTREF_KEY) {
- unsigned long ptr;
- struct btrfs_inode_extref *extref;
- ptr = btrfs_item_ptr_offset(leaf, slot);
- extref = (struct btrfs_inode_extref *)
- (ptr + cur_offset);
- parent = btrfs_inode_extref_parent(leaf,
- extref);
- cur_offset += sizeof(*extref);
- cur_offset += btrfs_inode_extref_name_len(leaf,
- extref);
- } else {
- parent = key.offset;
- cur_offset = item_size;
- }
- ret = get_inode_info(root, parent, NULL, &parent_gen,
- NULL, NULL, NULL, NULL);
- if (ret < 0)
- goto out;
- ret = check_ino_in_path(root, ino1, ino1_gen,
- parent, parent_gen, fs_path);
- if (ret)
- goto out;
- }
- path->slots[0]++;
- }
- ret = 0;
- out:
- btrfs_free_path(path);
- if (free_fs_path)
- fs_path_free(fs_path);
- return ret;
- }
- static int wait_for_parent_move(struct send_ctx *sctx,
- struct recorded_ref *parent_ref,
- const bool is_orphan)
- {
- int ret = 0;
- u64 ino = parent_ref->dir;
- u64 ino_gen = parent_ref->dir_gen;
- u64 parent_ino_before, parent_ino_after;
- struct fs_path *path_before = NULL;
- struct fs_path *path_after = NULL;
- int len1, len2;
- path_after = fs_path_alloc();
- path_before = fs_path_alloc();
- if (!path_after || !path_before) {
- ret = -ENOMEM;
- goto out;
- }
- /*
- * Our current directory inode may not yet be renamed/moved because some
- * ancestor (immediate or not) has to be renamed/moved first. So find if
- * such ancestor exists and make sure our own rename/move happens after
- * that ancestor is processed to avoid path build infinite loops (done
- * at get_cur_path()).
- */
- while (ino > BTRFS_FIRST_FREE_OBJECTID) {
- u64 parent_ino_after_gen;
- if (is_waiting_for_move(sctx, ino)) {
- /*
- * If the current inode is an ancestor of ino in the
- * parent root, we need to delay the rename of the
- * current inode, otherwise don't delayed the rename
- * because we can end up with a circular dependency
- * of renames, resulting in some directories never
- * getting the respective rename operations issued in
- * the send stream or getting into infinite path build
- * loops.
- */
- ret = is_ancestor(sctx->parent_root,
- sctx->cur_ino, sctx->cur_inode_gen,
- ino, path_before);
- if (ret)
- break;
- }
- fs_path_reset(path_before);
- fs_path_reset(path_after);
- ret = get_first_ref(sctx->send_root, ino, &parent_ino_after,
- &parent_ino_after_gen, path_after);
- if (ret < 0)
- goto out;
- ret = get_first_ref(sctx->parent_root, ino, &parent_ino_before,
- NULL, path_before);
- if (ret < 0 && ret != -ENOENT) {
- goto out;
- } else if (ret == -ENOENT) {
- ret = 0;
- break;
- }
- len1 = fs_path_len(path_before);
- len2 = fs_path_len(path_after);
- if (ino > sctx->cur_ino &&
- (parent_ino_before != parent_ino_after || len1 != len2 ||
- memcmp(path_before->start, path_after->start, len1))) {
- u64 parent_ino_gen;
- ret = get_inode_info(sctx->parent_root, ino, NULL,
- &parent_ino_gen, NULL, NULL, NULL,
- NULL);
- if (ret < 0)
- goto out;
- if (ino_gen == parent_ino_gen) {
- ret = 1;
- break;
- }
- }
- ino = parent_ino_after;
- ino_gen = parent_ino_after_gen;
- }
- out:
- fs_path_free(path_before);
- fs_path_free(path_after);
- if (ret == 1) {
- ret = add_pending_dir_move(sctx,
- sctx->cur_ino,
- sctx->cur_inode_gen,
- ino,
- &sctx->new_refs,
- &sctx->deleted_refs,
- is_orphan);
- if (!ret)
- ret = 1;
- }
- return ret;
- }
- static int update_ref_path(struct send_ctx *sctx, struct recorded_ref *ref)
- {
- int ret;
- struct fs_path *new_path;
- /*
- * Our reference's name member points to its full_path member string, so
- * we use here a new path.
- */
- new_path = fs_path_alloc();
- if (!new_path)
- return -ENOMEM;
- ret = get_cur_path(sctx, ref->dir, ref->dir_gen, new_path);
- if (ret < 0) {
- fs_path_free(new_path);
- return ret;
- }
- ret = fs_path_add(new_path, ref->name, ref->name_len);
- if (ret < 0) {
- fs_path_free(new_path);
- return ret;
- }
- fs_path_free(ref->full_path);
- set_ref_path(ref, new_path);
- return 0;
- }
- /*
- * When processing the new references for an inode we may orphanize an existing
- * directory inode because its old name conflicts with one of the new references
- * of the current inode. Later, when processing another new reference of our
- * inode, we might need to orphanize another inode, but the path we have in the
- * reference reflects the pre-orphanization name of the directory we previously
- * orphanized. For example:
- *
- * parent snapshot looks like:
- *
- * . (ino 256)
- * |----- f1 (ino 257)
- * |----- f2 (ino 258)
- * |----- d1/ (ino 259)
- * |----- d2/ (ino 260)
- *
- * send snapshot looks like:
- *
- * . (ino 256)
- * |----- d1 (ino 258)
- * |----- f2/ (ino 259)
- * |----- f2_link/ (ino 260)
- * | |----- f1 (ino 257)
- * |
- * |----- d2 (ino 258)
- *
- * When processing inode 257 we compute the name for inode 259 as "d1", and we
- * cache it in the name cache. Later when we start processing inode 258, when
- * collecting all its new references we set a full path of "d1/d2" for its new
- * reference with name "d2". When we start processing the new references we
- * start by processing the new reference with name "d1", and this results in
- * orphanizing inode 259, since its old reference causes a conflict. Then we
- * move on the next new reference, with name "d2", and we find out we must
- * orphanize inode 260, as its old reference conflicts with ours - but for the
- * orphanization we use a source path corresponding to the path we stored in the
- * new reference, which is "d1/d2" and not "o259-6-0/d2" - this makes the
- * receiver fail since the path component "d1/" no longer exists, it was renamed
- * to "o259-6-0/" when processing the previous new reference. So in this case we
- * must recompute the path in the new reference and use it for the new
- * orphanization operation.
- */
- static int refresh_ref_path(struct send_ctx *sctx, struct recorded_ref *ref)
- {
- char *name;
- int ret;
- name = kmemdup(ref->name, ref->name_len, GFP_KERNEL);
- if (!name)
- return -ENOMEM;
- fs_path_reset(ref->full_path);
- ret = get_cur_path(sctx, ref->dir, ref->dir_gen, ref->full_path);
- if (ret < 0)
- goto out;
- ret = fs_path_add(ref->full_path, name, ref->name_len);
- if (ret < 0)
- goto out;
- /* Update the reference's base name pointer. */
- set_ref_path(ref, ref->full_path);
- out:
- kfree(name);
- return ret;
- }
- /*
- * This does all the move/link/unlink/rmdir magic.
- */
- static int process_recorded_refs(struct send_ctx *sctx, int *pending_move)
- {
- struct btrfs_fs_info *fs_info = sctx->send_root->fs_info;
- int ret = 0;
- struct recorded_ref *cur;
- struct recorded_ref *cur2;
- struct list_head check_dirs;
- struct fs_path *valid_path = NULL;
- u64 ow_inode = 0;
- u64 ow_gen;
- u64 ow_mode;
- int did_overwrite = 0;
- int is_orphan = 0;
- u64 last_dir_ino_rm = 0;
- bool can_rename = true;
- bool orphanized_dir = false;
- bool orphanized_ancestor = false;
- btrfs_debug(fs_info, "process_recorded_refs %llu", sctx->cur_ino);
- /*
- * This should never happen as the root dir always has the same ref
- * which is always '..'
- */
- BUG_ON(sctx->cur_ino <= BTRFS_FIRST_FREE_OBJECTID);
- INIT_LIST_HEAD(&check_dirs);
- valid_path = fs_path_alloc();
- if (!valid_path) {
- ret = -ENOMEM;
- goto out;
- }
- /*
- * First, check if the first ref of the current inode was overwritten
- * before. If yes, we know that the current inode was already orphanized
- * and thus use the orphan name. If not, we can use get_cur_path to
- * get the path of the first ref as it would like while receiving at
- * this point in time.
- * New inodes are always orphan at the beginning, so force to use the
- * orphan name in this case.
- * The first ref is stored in valid_path and will be updated if it
- * gets moved around.
- */
- if (!sctx->cur_inode_new) {
- ret = did_overwrite_first_ref(sctx, sctx->cur_ino,
- sctx->cur_inode_gen);
- if (ret < 0)
- goto out;
- if (ret)
- did_overwrite = 1;
- }
- if (sctx->cur_inode_new || did_overwrite) {
- ret = gen_unique_name(sctx, sctx->cur_ino,
- sctx->cur_inode_gen, valid_path);
- if (ret < 0)
- goto out;
- is_orphan = 1;
- } else {
- ret = get_cur_path(sctx, sctx->cur_ino, sctx->cur_inode_gen,
- valid_path);
- if (ret < 0)
- goto out;
- }
- /*
- * Before doing any rename and link operations, do a first pass on the
- * new references to orphanize any unprocessed inodes that may have a
- * reference that conflicts with one of the new references of the current
- * inode. This needs to happen first because a new reference may conflict
- * with the old reference of a parent directory, so we must make sure
- * that the path used for link and rename commands don't use an
- * orphanized name when an ancestor was not yet orphanized.
- *
- * Example:
- *
- * Parent snapshot:
- *
- * . (ino 256)
- * |----- testdir/ (ino 259)
- * | |----- a (ino 257)
- * |
- * |----- b (ino 258)
- *
- * Send snapshot:
- *
- * . (ino 256)
- * |----- testdir_2/ (ino 259)
- * | |----- a (ino 260)
- * |
- * |----- testdir (ino 257)
- * |----- b (ino 257)
- * |----- b2 (ino 258)
- *
- * Processing the new reference for inode 257 with name "b" may happen
- * before processing the new reference with name "testdir". If so, we
- * must make sure that by the time we send a link command to create the
- * hard link "b", inode 259 was already orphanized, since the generated
- * path in "valid_path" already contains the orphanized name for 259.
- * We are processing inode 257, so only later when processing 259 we do
- * the rename operation to change its temporary (orphanized) name to
- * "testdir_2".
- */
- list_for_each_entry(cur, &sctx->new_refs, list) {
- ret = get_cur_inode_state(sctx, cur->dir, cur->dir_gen);
- if (ret < 0)
- goto out;
- if (ret == inode_state_will_create)
- continue;
- /*
- * Check if this new ref would overwrite the first ref of another
- * unprocessed inode. If yes, orphanize the overwritten inode.
- * If we find an overwritten ref that is not the first ref,
- * simply unlink it.
- */
- ret = will_overwrite_ref(sctx, cur->dir, cur->dir_gen,
- cur->name, cur->name_len,
- &ow_inode, &ow_gen, &ow_mode);
- if (ret < 0)
- goto out;
- if (ret) {
- ret = is_first_ref(sctx->parent_root,
- ow_inode, cur->dir, cur->name,
- cur->name_len);
- if (ret < 0)
- goto out;
- if (ret) {
- struct name_cache_entry *nce;
- struct waiting_dir_move *wdm;
- if (orphanized_dir) {
- ret = refresh_ref_path(sctx, cur);
- if (ret < 0)
- goto out;
- }
- ret = orphanize_inode(sctx, ow_inode, ow_gen,
- cur->full_path);
- if (ret < 0)
- goto out;
- if (S_ISDIR(ow_mode))
- orphanized_dir = true;
- /*
- * If ow_inode has its rename operation delayed
- * make sure that its orphanized name is used in
- * the source path when performing its rename
- * operation.
- */
- if (is_waiting_for_move(sctx, ow_inode)) {
- wdm = get_waiting_dir_move(sctx,
- ow_inode);
- ASSERT(wdm);
- wdm->orphanized = true;
- }
- /*
- * Make sure we clear our orphanized inode's
- * name from the name cache. This is because the
- * inode ow_inode might be an ancestor of some
- * other inode that will be orphanized as well
- * later and has an inode number greater than
- * sctx->send_progress. We need to prevent
- * future name lookups from using the old name
- * and get instead the orphan name.
- */
- nce = name_cache_search(sctx, ow_inode, ow_gen);
- if (nce) {
- name_cache_delete(sctx, nce);
- kfree(nce);
- }
- /*
- * ow_inode might currently be an ancestor of
- * cur_ino, therefore compute valid_path (the
- * current path of cur_ino) again because it
- * might contain the pre-orphanization name of
- * ow_inode, which is no longer valid.
- */
- ret = is_ancestor(sctx->parent_root,
- ow_inode, ow_gen,
- sctx->cur_ino, NULL);
- if (ret > 0) {
- orphanized_ancestor = true;
- fs_path_reset(valid_path);
- ret = get_cur_path(sctx, sctx->cur_ino,
- sctx->cur_inode_gen,
- valid_path);
- }
- if (ret < 0)
- goto out;
- } else {
- /*
- * If we previously orphanized a directory that
- * collided with a new reference that we already
- * processed, recompute the current path because
- * that directory may be part of the path.
- */
- if (orphanized_dir) {
- ret = refresh_ref_path(sctx, cur);
- if (ret < 0)
- goto out;
- }
- ret = send_unlink(sctx, cur->full_path);
- if (ret < 0)
- goto out;
- }
- }
- }
- list_for_each_entry(cur, &sctx->new_refs, list) {
- /*
- * We may have refs where the parent directory does not exist
- * yet. This happens if the parent directories inum is higher
- * than the current inum. To handle this case, we create the
- * parent directory out of order. But we need to check if this
- * did already happen before due to other refs in the same dir.
- */
- ret = get_cur_inode_state(sctx, cur->dir, cur->dir_gen);
- if (ret < 0)
- goto out;
- if (ret == inode_state_will_create) {
- ret = 0;
- /*
- * First check if any of the current inodes refs did
- * already create the dir.
- */
- list_for_each_entry(cur2, &sctx->new_refs, list) {
- if (cur == cur2)
- break;
- if (cur2->dir == cur->dir) {
- ret = 1;
- break;
- }
- }
- /*
- * If that did not happen, check if a previous inode
- * did already create the dir.
- */
- if (!ret)
- ret = did_create_dir(sctx, cur->dir);
- if (ret < 0)
- goto out;
- if (!ret) {
- ret = send_create_inode(sctx, cur->dir);
- if (ret < 0)
- goto out;
- }
- }
- if (S_ISDIR(sctx->cur_inode_mode) && sctx->parent_root) {
- ret = wait_for_dest_dir_move(sctx, cur, is_orphan);
- if (ret < 0)
- goto out;
- if (ret == 1) {
- can_rename = false;
- *pending_move = 1;
- }
- }
- if (S_ISDIR(sctx->cur_inode_mode) && sctx->parent_root &&
- can_rename) {
- ret = wait_for_parent_move(sctx, cur, is_orphan);
- if (ret < 0)
- goto out;
- if (ret == 1) {
- can_rename = false;
- *pending_move = 1;
- }
- }
- /*
- * link/move the ref to the new place. If we have an orphan
- * inode, move it and update valid_path. If not, link or move
- * it depending on the inode mode.
- */
- if (is_orphan && can_rename) {
- ret = send_rename(sctx, valid_path, cur->full_path);
- if (ret < 0)
- goto out;
- is_orphan = 0;
- ret = fs_path_copy(valid_path, cur->full_path);
- if (ret < 0)
- goto out;
- } else if (can_rename) {
- if (S_ISDIR(sctx->cur_inode_mode)) {
- /*
- * Dirs can't be linked, so move it. For moved
- * dirs, we always have one new and one deleted
- * ref. The deleted ref is ignored later.
- */
- ret = send_rename(sctx, valid_path,
- cur->full_path);
- if (!ret)
- ret = fs_path_copy(valid_path,
- cur->full_path);
- if (ret < 0)
- goto out;
- } else {
- /*
- * We might have previously orphanized an inode
- * which is an ancestor of our current inode,
- * so our reference's full path, which was
- * computed before any such orphanizations, must
- * be updated.
- */
- if (orphanized_dir) {
- ret = update_ref_path(sctx, cur);
- if (ret < 0)
- goto out;
- }
- ret = send_link(sctx, cur->full_path,
- valid_path);
- if (ret < 0)
- goto out;
- }
- }
- ret = dup_ref(cur, &check_dirs);
- if (ret < 0)
- goto out;
- }
- if (S_ISDIR(sctx->cur_inode_mode) && sctx->cur_inode_deleted) {
- /*
- * Check if we can already rmdir the directory. If not,
- * orphanize it. For every dir item inside that gets deleted
- * later, we do this check again and rmdir it then if possible.
- * See the use of check_dirs for more details.
- */
- ret = can_rmdir(sctx, sctx->cur_ino, sctx->cur_inode_gen,
- sctx->cur_ino);
- if (ret < 0)
- goto out;
- if (ret) {
- ret = send_rmdir(sctx, valid_path);
- if (ret < 0)
- goto out;
- } else if (!is_orphan) {
- ret = orphanize_inode(sctx, sctx->cur_ino,
- sctx->cur_inode_gen, valid_path);
- if (ret < 0)
- goto out;
- is_orphan = 1;
- }
- list_for_each_entry(cur, &sctx->deleted_refs, list) {
- ret = dup_ref(cur, &check_dirs);
- if (ret < 0)
- goto out;
- }
- } else if (S_ISDIR(sctx->cur_inode_mode) &&
- !list_empty(&sctx->deleted_refs)) {
- /*
- * We have a moved dir. Add the old parent to check_dirs
- */
- cur = list_entry(sctx->deleted_refs.next, struct recorded_ref,
- list);
- ret = dup_ref(cur, &check_dirs);
- if (ret < 0)
- goto out;
- } else if (!S_ISDIR(sctx->cur_inode_mode)) {
- /*
- * We have a non dir inode. Go through all deleted refs and
- * unlink them if they were not already overwritten by other
- * inodes.
- */
- list_for_each_entry(cur, &sctx->deleted_refs, list) {
- ret = did_overwrite_ref(sctx, cur->dir, cur->dir_gen,
- sctx->cur_ino, sctx->cur_inode_gen,
- cur->name, cur->name_len);
- if (ret < 0)
- goto out;
- if (!ret) {
- /*
- * If we orphanized any ancestor before, we need
- * to recompute the full path for deleted names,
- * since any such path was computed before we
- * processed any references and orphanized any
- * ancestor inode.
- */
- if (orphanized_ancestor) {
- ret = update_ref_path(sctx, cur);
- if (ret < 0)
- goto out;
- }
- ret = send_unlink(sctx, cur->full_path);
- if (ret < 0)
- goto out;
- }
- ret = dup_ref(cur, &check_dirs);
- if (ret < 0)
- goto out;
- }
- /*
- * If the inode is still orphan, unlink the orphan. This may
- * happen when a previous inode did overwrite the first ref
- * of this inode and no new refs were added for the current
- * inode. Unlinking does not mean that the inode is deleted in
- * all cases. There may still be links to this inode in other
- * places.
- */
- if (is_orphan) {
- ret = send_unlink(sctx, valid_path);
- if (ret < 0)
- goto out;
- }
- }
- /*
- * We did collect all parent dirs where cur_inode was once located. We
- * now go through all these dirs and check if they are pending for
- * deletion and if it's finally possible to perform the rmdir now.
- * We also update the inode stats of the parent dirs here.
- */
- list_for_each_entry(cur, &check_dirs, list) {
- /*
- * In case we had refs into dirs that were not processed yet,
- * we don't need to do the utime and rmdir logic for these dirs.
- * The dir will be processed later.
- */
- if (cur->dir > sctx->cur_ino)
- continue;
- ret = get_cur_inode_state(sctx, cur->dir, cur->dir_gen);
- if (ret < 0)
- goto out;
- if (ret == inode_state_did_create ||
- ret == inode_state_no_change) {
- /* TODO delayed utimes */
- ret = send_utimes(sctx, cur->dir, cur->dir_gen);
- if (ret < 0)
- goto out;
- } else if (ret == inode_state_did_delete &&
- cur->dir != last_dir_ino_rm) {
- ret = can_rmdir(sctx, cur->dir, cur->dir_gen,
- sctx->cur_ino);
- if (ret < 0)
- goto out;
- if (ret) {
- ret = get_cur_path(sctx, cur->dir,
- cur->dir_gen, valid_path);
- if (ret < 0)
- goto out;
- ret = send_rmdir(sctx, valid_path);
- if (ret < 0)
- goto out;
- last_dir_ino_rm = cur->dir;
- }
- }
- }
- ret = 0;
- out:
- __free_recorded_refs(&check_dirs);
- free_recorded_refs(sctx);
- fs_path_free(valid_path);
- return ret;
- }
- static int record_ref(struct btrfs_root *root, u64 dir, struct fs_path *name,
- void *ctx, struct list_head *refs)
- {
- int ret = 0;
- struct send_ctx *sctx = ctx;
- struct fs_path *p;
- u64 gen;
- p = fs_path_alloc();
- if (!p)
- return -ENOMEM;
- ret = get_inode_info(root, dir, NULL, &gen, NULL, NULL,
- NULL, NULL);
- if (ret < 0)
- goto out;
- ret = get_cur_path(sctx, dir, gen, p);
- if (ret < 0)
- goto out;
- ret = fs_path_add_path(p, name);
- if (ret < 0)
- goto out;
- ret = __record_ref(refs, dir, gen, p);
- out:
- if (ret)
- fs_path_free(p);
- return ret;
- }
- static int __record_new_ref(int num, u64 dir, int index,
- struct fs_path *name,
- void *ctx)
- {
- struct send_ctx *sctx = ctx;
- return record_ref(sctx->send_root, dir, name, ctx, &sctx->new_refs);
- }
- static int __record_deleted_ref(int num, u64 dir, int index,
- struct fs_path *name,
- void *ctx)
- {
- struct send_ctx *sctx = ctx;
- return record_ref(sctx->parent_root, dir, name, ctx,
- &sctx->deleted_refs);
- }
- static int record_new_ref(struct send_ctx *sctx)
- {
- int ret;
- ret = iterate_inode_ref(sctx->send_root, sctx->left_path,
- sctx->cmp_key, 0, __record_new_ref, sctx);
- if (ret < 0)
- goto out;
- ret = 0;
- out:
- return ret;
- }
- static int record_deleted_ref(struct send_ctx *sctx)
- {
- int ret;
- ret = iterate_inode_ref(sctx->parent_root, sctx->right_path,
- sctx->cmp_key, 0, __record_deleted_ref, sctx);
- if (ret < 0)
- goto out;
- ret = 0;
- out:
- return ret;
- }
- struct find_ref_ctx {
- u64 dir;
- u64 dir_gen;
- struct btrfs_root *root;
- struct fs_path *name;
- int found_idx;
- };
- static int __find_iref(int num, u64 dir, int index,
- struct fs_path *name,
- void *ctx_)
- {
- struct find_ref_ctx *ctx = ctx_;
- u64 dir_gen;
- int ret;
- if (dir == ctx->dir && fs_path_len(name) == fs_path_len(ctx->name) &&
- strncmp(name->start, ctx->name->start, fs_path_len(name)) == 0) {
- /*
- * To avoid doing extra lookups we'll only do this if everything
- * else matches.
- */
- ret = get_inode_info(ctx->root, dir, NULL, &dir_gen, NULL,
- NULL, NULL, NULL);
- if (ret)
- return ret;
- if (dir_gen != ctx->dir_gen)
- return 0;
- ctx->found_idx = num;
- return 1;
- }
- return 0;
- }
- static int find_iref(struct btrfs_root *root,
- struct btrfs_path *path,
- struct btrfs_key *key,
- u64 dir, u64 dir_gen, struct fs_path *name)
- {
- int ret;
- struct find_ref_ctx ctx;
- ctx.dir = dir;
- ctx.name = name;
- ctx.dir_gen = dir_gen;
- ctx.found_idx = -1;
- ctx.root = root;
- ret = iterate_inode_ref(root, path, key, 0, __find_iref, &ctx);
- if (ret < 0)
- return ret;
- if (ctx.found_idx == -1)
- return -ENOENT;
- return ctx.found_idx;
- }
- static int __record_changed_new_ref(int num, u64 dir, int index,
- struct fs_path *name,
- void *ctx)
- {
- u64 dir_gen;
- int ret;
- struct send_ctx *sctx = ctx;
- ret = get_inode_info(sctx->send_root, dir, NULL, &dir_gen, NULL,
- NULL, NULL, NULL);
- if (ret)
- return ret;
- ret = find_iref(sctx->parent_root, sctx->right_path,
- sctx->cmp_key, dir, dir_gen, name);
- if (ret == -ENOENT)
- ret = __record_new_ref(num, dir, index, name, sctx);
- else if (ret > 0)
- ret = 0;
- return ret;
- }
- static int __record_changed_deleted_ref(int num, u64 dir, int index,
- struct fs_path *name,
- void *ctx)
- {
- u64 dir_gen;
- int ret;
- struct send_ctx *sctx = ctx;
- ret = get_inode_info(sctx->parent_root, dir, NULL, &dir_gen, NULL,
- NULL, NULL, NULL);
- if (ret)
- return ret;
- ret = find_iref(sctx->send_root, sctx->left_path, sctx->cmp_key,
- dir, dir_gen, name);
- if (ret == -ENOENT)
- ret = __record_deleted_ref(num, dir, index, name, sctx);
- else if (ret > 0)
- ret = 0;
- return ret;
- }
- static int record_changed_ref(struct send_ctx *sctx)
- {
- int ret = 0;
- ret = iterate_inode_ref(sctx->send_root, sctx->left_path,
- sctx->cmp_key, 0, __record_changed_new_ref, sctx);
- if (ret < 0)
- goto out;
- ret = iterate_inode_ref(sctx->parent_root, sctx->right_path,
- sctx->cmp_key, 0, __record_changed_deleted_ref, sctx);
- if (ret < 0)
- goto out;
- ret = 0;
- out:
- return ret;
- }
- /*
- * Record and process all refs at once. Needed when an inode changes the
- * generation number, which means that it was deleted and recreated.
- */
- static int process_all_refs(struct send_ctx *sctx,
- enum btrfs_compare_tree_result cmd)
- {
- int ret;
- struct btrfs_root *root;
- struct btrfs_path *path;
- struct btrfs_key key;
- struct btrfs_key found_key;
- struct extent_buffer *eb;
- int slot;
- iterate_inode_ref_t cb;
- int pending_move = 0;
- path = alloc_path_for_send();
- if (!path)
- return -ENOMEM;
- if (cmd == BTRFS_COMPARE_TREE_NEW) {
- root = sctx->send_root;
- cb = __record_new_ref;
- } else if (cmd == BTRFS_COMPARE_TREE_DELETED) {
- root = sctx->parent_root;
- cb = __record_deleted_ref;
- } else {
- btrfs_err(sctx->send_root->fs_info,
- "Wrong command %d in process_all_refs", cmd);
- ret = -EINVAL;
- goto out;
- }
- key.objectid = sctx->cmp_key->objectid;
- key.type = BTRFS_INODE_REF_KEY;
- key.offset = 0;
- ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
- if (ret < 0)
- goto out;
- while (1) {
- eb = path->nodes[0];
- slot = path->slots[0];
- if (slot >= btrfs_header_nritems(eb)) {
- ret = btrfs_next_leaf(root, path);
- if (ret < 0)
- goto out;
- else if (ret > 0)
- break;
- continue;
- }
- btrfs_item_key_to_cpu(eb, &found_key, slot);
- if (found_key.objectid != key.objectid ||
- (found_key.type != BTRFS_INODE_REF_KEY &&
- found_key.type != BTRFS_INODE_EXTREF_KEY))
- break;
- ret = iterate_inode_ref(root, path, &found_key, 0, cb, sctx);
- if (ret < 0)
- goto out;
- path->slots[0]++;
- }
- btrfs_release_path(path);
- /*
- * We don't actually care about pending_move as we are simply
- * re-creating this inode and will be rename'ing it into place once we
- * rename the parent directory.
- */
- ret = process_recorded_refs(sctx, &pending_move);
- out:
- btrfs_free_path(path);
- return ret;
- }
- static int send_set_xattr(struct send_ctx *sctx,
- struct fs_path *path,
- const char *name, int name_len,
- const char *data, int data_len)
- {
- int ret = 0;
- ret = begin_cmd(sctx, BTRFS_SEND_C_SET_XATTR);
- if (ret < 0)
- goto out;
- TLV_PUT_PATH(sctx, BTRFS_SEND_A_PATH, path);
- TLV_PUT_STRING(sctx, BTRFS_SEND_A_XATTR_NAME, name, name_len);
- TLV_PUT(sctx, BTRFS_SEND_A_XATTR_DATA, data, data_len);
- ret = send_cmd(sctx);
- tlv_put_failure:
- out:
- return ret;
- }
- static int send_remove_xattr(struct send_ctx *sctx,
- struct fs_path *path,
- const char *name, int name_len)
- {
- int ret = 0;
- ret = begin_cmd(sctx, BTRFS_SEND_C_REMOVE_XATTR);
- if (ret < 0)
- goto out;
- TLV_PUT_PATH(sctx, BTRFS_SEND_A_PATH, path);
- TLV_PUT_STRING(sctx, BTRFS_SEND_A_XATTR_NAME, name, name_len);
- ret = send_cmd(sctx);
- tlv_put_failure:
- out:
- return ret;
- }
- static int __process_new_xattr(int num, struct btrfs_key *di_key,
- const char *name, int name_len,
- const char *data, int data_len,
- u8 type, void *ctx)
- {
- int ret;
- struct send_ctx *sctx = ctx;
- struct fs_path *p;
- struct posix_acl_xattr_header dummy_acl;
- /* Capabilities are emitted by finish_inode_if_needed */
- if (!strncmp(name, XATTR_NAME_CAPS, name_len))
- return 0;
- p = fs_path_alloc();
- if (!p)
- return -ENOMEM;
- /*
- * This hack is needed because empty acls are stored as zero byte
- * data in xattrs. Problem with that is, that receiving these zero byte
- * acls will fail later. To fix this, we send a dummy acl list that
- * only contains the version number and no entries.
- */
- if (!strncmp(name, XATTR_NAME_POSIX_ACL_ACCESS, name_len) ||
- !strncmp(name, XATTR_NAME_POSIX_ACL_DEFAULT, name_len)) {
- if (data_len == 0) {
- dummy_acl.a_version =
- cpu_to_le32(POSIX_ACL_XATTR_VERSION);
- data = (char *)&dummy_acl;
- data_len = sizeof(dummy_acl);
- }
- }
- ret = get_cur_path(sctx, sctx->cur_ino, sctx->cur_inode_gen, p);
- if (ret < 0)
- goto out;
- ret = send_set_xattr(sctx, p, name, name_len, data, data_len);
- out:
- fs_path_free(p);
- return ret;
- }
- static int __process_deleted_xattr(int num, struct btrfs_key *di_key,
- const char *name, int name_len,
- const char *data, int data_len,
- u8 type, void *ctx)
- {
- int ret;
- struct send_ctx *sctx = ctx;
- struct fs_path *p;
- p = fs_path_alloc();
- if (!p)
- return -ENOMEM;
- ret = get_cur_path(sctx, sctx->cur_ino, sctx->cur_inode_gen, p);
- if (ret < 0)
- goto out;
- ret = send_remove_xattr(sctx, p, name, name_len);
- out:
- fs_path_free(p);
- return ret;
- }
- static int process_new_xattr(struct send_ctx *sctx)
- {
- int ret = 0;
- ret = iterate_dir_item(sctx->send_root, sctx->left_path,
- __process_new_xattr, sctx);
- return ret;
- }
- static int process_deleted_xattr(struct send_ctx *sctx)
- {
- return iterate_dir_item(sctx->parent_root, sctx->right_path,
- __process_deleted_xattr, sctx);
- }
- struct find_xattr_ctx {
- const char *name;
- int name_len;
- int found_idx;
- char *found_data;
- int found_data_len;
- };
- static int __find_xattr(int num, struct btrfs_key *di_key,
- const char *name, int name_len,
- const char *data, int data_len,
- u8 type, void *vctx)
- {
- struct find_xattr_ctx *ctx = vctx;
- if (name_len == ctx->name_len &&
- strncmp(name, ctx->name, name_len) == 0) {
- ctx->found_idx = num;
- ctx->found_data_len = data_len;
- ctx->found_data = kmemdup(data, data_len, GFP_KERNEL);
- if (!ctx->found_data)
- return -ENOMEM;
- return 1;
- }
- return 0;
- }
- static int find_xattr(struct btrfs_root *root,
- struct btrfs_path *path,
- struct btrfs_key *key,
- const char *name, int name_len,
- char **data, int *data_len)
- {
- int ret;
- struct find_xattr_ctx ctx;
- ctx.name = name;
- ctx.name_len = name_len;
- ctx.found_idx = -1;
- ctx.found_data = NULL;
- ctx.found_data_len = 0;
- ret = iterate_dir_item(root, path, __find_xattr, &ctx);
- if (ret < 0)
- return ret;
- if (ctx.found_idx == -1)
- return -ENOENT;
- if (data) {
- *data = ctx.found_data;
- *data_len = ctx.found_data_len;
- } else {
- kfree(ctx.found_data);
- }
- return ctx.found_idx;
- }
- static int __process_changed_new_xattr(int num, struct btrfs_key *di_key,
- const char *name, int name_len,
- const char *data, int data_len,
- u8 type, void *ctx)
- {
- int ret;
- struct send_ctx *sctx = ctx;
- char *found_data = NULL;
- int found_data_len = 0;
- ret = find_xattr(sctx->parent_root, sctx->right_path,
- sctx->cmp_key, name, name_len, &found_data,
- &found_data_len);
- if (ret == -ENOENT) {
- ret = __process_new_xattr(num, di_key, name, name_len, data,
- data_len, type, ctx);
- } else if (ret >= 0) {
- if (data_len != found_data_len ||
- memcmp(data, found_data, data_len)) {
- ret = __process_new_xattr(num, di_key, name, name_len,
- data, data_len, type, ctx);
- } else {
- ret = 0;
- }
- }
- kfree(found_data);
- return ret;
- }
- static int __process_changed_deleted_xattr(int num, struct btrfs_key *di_key,
- const char *name, int name_len,
- const char *data, int data_len,
- u8 type, void *ctx)
- {
- int ret;
- struct send_ctx *sctx = ctx;
- ret = find_xattr(sctx->send_root, sctx->left_path, sctx->cmp_key,
- name, name_len, NULL, NULL);
- if (ret == -ENOENT)
- ret = __process_deleted_xattr(num, di_key, name, name_len, data,
- data_len, type, ctx);
- else if (ret >= 0)
- ret = 0;
- return ret;
- }
- static int process_changed_xattr(struct send_ctx *sctx)
- {
- int ret = 0;
- ret = iterate_dir_item(sctx->send_root, sctx->left_path,
- __process_changed_new_xattr, sctx);
- if (ret < 0)
- goto out;
- ret = iterate_dir_item(sctx->parent_root, sctx->right_path,
- __process_changed_deleted_xattr, sctx);
- out:
- return ret;
- }
- static int process_all_new_xattrs(struct send_ctx *sctx)
- {
- int ret;
- struct btrfs_root *root;
- struct btrfs_path *path;
- struct btrfs_key key;
- struct btrfs_key found_key;
- struct extent_buffer *eb;
- int slot;
- path = alloc_path_for_send();
- if (!path)
- return -ENOMEM;
- root = sctx->send_root;
- key.objectid = sctx->cmp_key->objectid;
- key.type = BTRFS_XATTR_ITEM_KEY;
- key.offset = 0;
- ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
- if (ret < 0)
- goto out;
- while (1) {
- eb = path->nodes[0];
- slot = path->slots[0];
- if (slot >= btrfs_header_nritems(eb)) {
- ret = btrfs_next_leaf(root, path);
- if (ret < 0) {
- goto out;
- } else if (ret > 0) {
- ret = 0;
- break;
- }
- continue;
- }
- btrfs_item_key_to_cpu(eb, &found_key, slot);
- if (found_key.objectid != key.objectid ||
- found_key.type != key.type) {
- ret = 0;
- goto out;
- }
- ret = iterate_dir_item(root, path, __process_new_xattr, sctx);
- if (ret < 0)
- goto out;
- path->slots[0]++;
- }
- out:
- btrfs_free_path(path);
- return ret;
- }
- static ssize_t fill_read_buf(struct send_ctx *sctx, u64 offset, u32 len)
- {
- struct btrfs_root *root = sctx->send_root;
- struct btrfs_fs_info *fs_info = root->fs_info;
- struct inode *inode;
- struct page *page;
- char *addr;
- struct btrfs_key key;
- pgoff_t index = offset >> PAGE_SHIFT;
- pgoff_t last_index;
- unsigned pg_offset = offset_in_page(offset);
- ssize_t ret = 0;
- key.objectid = sctx->cur_ino;
- key.type = BTRFS_INODE_ITEM_KEY;
- key.offset = 0;
- inode = btrfs_iget(fs_info->sb, &key, root, NULL);
- if (IS_ERR(inode))
- return PTR_ERR(inode);
- if (offset + len > i_size_read(inode)) {
- if (offset > i_size_read(inode))
- len = 0;
- else
- len = offset - i_size_read(inode);
- }
- if (len == 0)
- goto out;
- last_index = (offset + len - 1) >> PAGE_SHIFT;
- /* initial readahead */
- memset(&sctx->ra, 0, sizeof(struct file_ra_state));
- file_ra_state_init(&sctx->ra, inode->i_mapping);
- while (index <= last_index) {
- unsigned cur_len = min_t(unsigned, len,
- PAGE_SIZE - pg_offset);
- page = find_lock_page(inode->i_mapping, index);
- if (!page) {
- page_cache_sync_readahead(inode->i_mapping, &sctx->ra,
- NULL, index, last_index + 1 - index);
- page = find_or_create_page(inode->i_mapping, index,
- GFP_KERNEL);
- if (!page) {
- ret = -ENOMEM;
- break;
- }
- }
- if (PageReadahead(page)) {
- page_cache_async_readahead(inode->i_mapping, &sctx->ra,
- NULL, page, index, last_index + 1 - index);
- }
- if (!PageUptodate(page)) {
- btrfs_readpage(NULL, page);
- lock_page(page);
- if (!PageUptodate(page)) {
- unlock_page(page);
- put_page(page);
- ret = -EIO;
- break;
- }
- }
- addr = kmap(page);
- memcpy(sctx->read_buf + ret, addr + pg_offset, cur_len);
- kunmap(page);
- unlock_page(page);
- put_page(page);
- index++;
- pg_offset = 0;
- len -= cur_len;
- ret += cur_len;
- }
- out:
- iput(inode);
- return ret;
- }
- /*
- * Read some bytes from the current inode/file and send a write command to
- * user space.
- */
- static int send_write(struct send_ctx *sctx, u64 offset, u32 len)
- {
- struct btrfs_fs_info *fs_info = sctx->send_root->fs_info;
- int ret = 0;
- struct fs_path *p;
- ssize_t num_read = 0;
- p = fs_path_alloc();
- if (!p)
- return -ENOMEM;
- btrfs_debug(fs_info, "send_write offset=%llu, len=%d", offset, len);
- num_read = fill_read_buf(sctx, offset, len);
- if (num_read <= 0) {
- if (num_read < 0)
- ret = num_read;
- goto out;
- }
- ret = begin_cmd(sctx, BTRFS_SEND_C_WRITE);
- if (ret < 0)
- goto out;
- ret = get_cur_path(sctx, sctx->cur_ino, sctx->cur_inode_gen, p);
- if (ret < 0)
- goto out;
- TLV_PUT_PATH(sctx, BTRFS_SEND_A_PATH, p);
- TLV_PUT_U64(sctx, BTRFS_SEND_A_FILE_OFFSET, offset);
- TLV_PUT(sctx, BTRFS_SEND_A_DATA, sctx->read_buf, num_read);
- ret = send_cmd(sctx);
- tlv_put_failure:
- out:
- fs_path_free(p);
- if (ret < 0)
- return ret;
- return num_read;
- }
- /*
- * Send a clone command to user space.
- */
- static int send_clone(struct send_ctx *sctx,
- u64 offset, u32 len,
- struct clone_root *clone_root)
- {
- int ret = 0;
- struct fs_path *p;
- u64 gen;
- btrfs_debug(sctx->send_root->fs_info,
- "send_clone offset=%llu, len=%d, clone_root=%llu, clone_inode=%llu, clone_offset=%llu",
- offset, len, clone_root->root->root_key.objectid,
- clone_root->ino, clone_root->offset);
- p = fs_path_alloc();
- if (!p)
- return -ENOMEM;
- ret = begin_cmd(sctx, BTRFS_SEND_C_CLONE);
- if (ret < 0)
- goto out;
- ret = get_cur_path(sctx, sctx->cur_ino, sctx->cur_inode_gen, p);
- if (ret < 0)
- goto out;
- TLV_PUT_U64(sctx, BTRFS_SEND_A_FILE_OFFSET, offset);
- TLV_PUT_U64(sctx, BTRFS_SEND_A_CLONE_LEN, len);
- TLV_PUT_PATH(sctx, BTRFS_SEND_A_PATH, p);
- if (clone_root->root == sctx->send_root) {
- ret = get_inode_info(sctx->send_root, clone_root->ino, NULL,
- &gen, NULL, NULL, NULL, NULL);
- if (ret < 0)
- goto out;
- ret = get_cur_path(sctx, clone_root->ino, gen, p);
- } else {
- ret = get_inode_path(clone_root->root, clone_root->ino, p);
- }
- if (ret < 0)
- goto out;
- /*
- * If the parent we're using has a received_uuid set then use that as
- * our clone source as that is what we will look for when doing a
- * receive.
- *
- * This covers the case that we create a snapshot off of a received
- * subvolume and then use that as the parent and try to receive on a
- * different host.
- */
- if (!btrfs_is_empty_uuid(clone_root->root->root_item.received_uuid))
- TLV_PUT_UUID(sctx, BTRFS_SEND_A_CLONE_UUID,
- clone_root->root->root_item.received_uuid);
- else
- TLV_PUT_UUID(sctx, BTRFS_SEND_A_CLONE_UUID,
- clone_root->root->root_item.uuid);
- TLV_PUT_U64(sctx, BTRFS_SEND_A_CLONE_CTRANSID,
- le64_to_cpu(clone_root->root->root_item.ctransid));
- TLV_PUT_PATH(sctx, BTRFS_SEND_A_CLONE_PATH, p);
- TLV_PUT_U64(sctx, BTRFS_SEND_A_CLONE_OFFSET,
- clone_root->offset);
- ret = send_cmd(sctx);
- tlv_put_failure:
- out:
- fs_path_free(p);
- return ret;
- }
- /*
- * Send an update extent command to user space.
- */
- static int send_update_extent(struct send_ctx *sctx,
- u64 offset, u32 len)
- {
- int ret = 0;
- struct fs_path *p;
- p = fs_path_alloc();
- if (!p)
- return -ENOMEM;
- ret = begin_cmd(sctx, BTRFS_SEND_C_UPDATE_EXTENT);
- if (ret < 0)
- goto out;
- ret = get_cur_path(sctx, sctx->cur_ino, sctx->cur_inode_gen, p);
- if (ret < 0)
- goto out;
- TLV_PUT_PATH(sctx, BTRFS_SEND_A_PATH, p);
- TLV_PUT_U64(sctx, BTRFS_SEND_A_FILE_OFFSET, offset);
- TLV_PUT_U64(sctx, BTRFS_SEND_A_SIZE, len);
- ret = send_cmd(sctx);
- tlv_put_failure:
- out:
- fs_path_free(p);
- return ret;
- }
- static int send_hole(struct send_ctx *sctx, u64 end)
- {
- struct fs_path *p = NULL;
- u64 offset = sctx->cur_inode_last_extent;
- u64 len;
- int ret = 0;
- /*
- * A hole that starts at EOF or beyond it. Since we do not yet support
- * fallocate (for extent preallocation and hole punching), sending a
- * write of zeroes starting at EOF or beyond would later require issuing
- * a truncate operation which would undo the write and achieve nothing.
- */
- if (offset >= sctx->cur_inode_size)
- return 0;
- /*
- * Don't go beyond the inode's i_size due to prealloc extents that start
- * after the i_size.
- */
- end = min_t(u64, end, sctx->cur_inode_size);
- if (sctx->flags & BTRFS_SEND_FLAG_NO_FILE_DATA)
- return send_update_extent(sctx, offset, end - offset);
- p = fs_path_alloc();
- if (!p)
- return -ENOMEM;
- ret = get_cur_path(sctx, sctx->cur_ino, sctx->cur_inode_gen, p);
- if (ret < 0)
- goto tlv_put_failure;
- memset(sctx->read_buf, 0, BTRFS_SEND_READ_SIZE);
- while (offset < end) {
- len = min_t(u64, end - offset, BTRFS_SEND_READ_SIZE);
- ret = begin_cmd(sctx, BTRFS_SEND_C_WRITE);
- if (ret < 0)
- break;
- TLV_PUT_PATH(sctx, BTRFS_SEND_A_PATH, p);
- TLV_PUT_U64(sctx, BTRFS_SEND_A_FILE_OFFSET, offset);
- TLV_PUT(sctx, BTRFS_SEND_A_DATA, sctx->read_buf, len);
- ret = send_cmd(sctx);
- if (ret < 0)
- break;
- offset += len;
- }
- sctx->cur_inode_next_write_offset = offset;
- tlv_put_failure:
- fs_path_free(p);
- return ret;
- }
- static int send_extent_data(struct send_ctx *sctx,
- const u64 offset,
- const u64 len)
- {
- u64 sent = 0;
- if (sctx->flags & BTRFS_SEND_FLAG_NO_FILE_DATA)
- return send_update_extent(sctx, offset, len);
- while (sent < len) {
- u64 size = len - sent;
- int ret;
- if (size > BTRFS_SEND_READ_SIZE)
- size = BTRFS_SEND_READ_SIZE;
- ret = send_write(sctx, offset + sent, size);
- if (ret < 0)
- return ret;
- if (!ret)
- break;
- sent += ret;
- }
- return 0;
- }
- /*
- * Search for a capability xattr related to sctx->cur_ino. If the capability is
- * found, call send_set_xattr function to emit it.
- *
- * Return 0 if there isn't a capability, or when the capability was emitted
- * successfully, or < 0 if an error occurred.
- */
- static int send_capabilities(struct send_ctx *sctx)
- {
- struct fs_path *fspath = NULL;
- struct btrfs_path *path;
- struct btrfs_dir_item *di;
- struct extent_buffer *leaf;
- unsigned long data_ptr;
- char *buf = NULL;
- int buf_len;
- int ret = 0;
- path = alloc_path_for_send();
- if (!path)
- return -ENOMEM;
- di = btrfs_lookup_xattr(NULL, sctx->send_root, path, sctx->cur_ino,
- XATTR_NAME_CAPS, strlen(XATTR_NAME_CAPS), 0);
- if (!di) {
- /* There is no xattr for this inode */
- goto out;
- } else if (IS_ERR(di)) {
- ret = PTR_ERR(di);
- goto out;
- }
- leaf = path->nodes[0];
- buf_len = btrfs_dir_data_len(leaf, di);
- fspath = fs_path_alloc();
- buf = kmalloc(buf_len, GFP_KERNEL);
- if (!fspath || !buf) {
- ret = -ENOMEM;
- goto out;
- }
- ret = get_cur_path(sctx, sctx->cur_ino, sctx->cur_inode_gen, fspath);
- if (ret < 0)
- goto out;
- data_ptr = (unsigned long)(di + 1) + btrfs_dir_name_len(leaf, di);
- read_extent_buffer(leaf, buf, data_ptr, buf_len);
- ret = send_set_xattr(sctx, fspath, XATTR_NAME_CAPS,
- strlen(XATTR_NAME_CAPS), buf, buf_len);
- out:
- kfree(buf);
- fs_path_free(fspath);
- btrfs_free_path(path);
- return ret;
- }
- static int clone_range(struct send_ctx *sctx,
- struct clone_root *clone_root,
- const u64 disk_byte,
- u64 data_offset,
- u64 offset,
- u64 len)
- {
- struct btrfs_path *path;
- struct btrfs_key key;
- int ret;
- u64 clone_src_i_size = 0;
- /*
- * Prevent cloning from a zero offset with a length matching the sector
- * size because in some scenarios this will make the receiver fail.
- *
- * For example, if in the source filesystem the extent at offset 0
- * has a length of sectorsize and it was written using direct IO, then
- * it can never be an inline extent (even if compression is enabled).
- * Then this extent can be cloned in the original filesystem to a non
- * zero file offset, but it may not be possible to clone in the
- * destination filesystem because it can be inlined due to compression
- * on the destination filesystem (as the receiver's write operations are
- * always done using buffered IO). The same happens when the original
- * filesystem does not have compression enabled but the destination
- * filesystem has.
- */
- if (clone_root->offset == 0 &&
- len == sctx->send_root->fs_info->sectorsize)
- return send_extent_data(sctx, offset, len);
- path = alloc_path_for_send();
- if (!path)
- return -ENOMEM;
- /*
- * There are inodes that have extents that lie behind its i_size. Don't
- * accept clones from these extents.
- */
- ret = __get_inode_info(clone_root->root, path, clone_root->ino,
- &clone_src_i_size, NULL, NULL, NULL, NULL, NULL);
- btrfs_release_path(path);
- if (ret < 0)
- goto out;
- /*
- * We can't send a clone operation for the entire range if we find
- * extent items in the respective range in the source file that
- * refer to different extents or if we find holes.
- * So check for that and do a mix of clone and regular write/copy
- * operations if needed.
- *
- * Example:
- *
- * mkfs.btrfs -f /dev/sda
- * mount /dev/sda /mnt
- * xfs_io -f -c "pwrite -S 0xaa 0K 100K" /mnt/foo
- * cp --reflink=always /mnt/foo /mnt/bar
- * xfs_io -c "pwrite -S 0xbb 50K 50K" /mnt/foo
- * btrfs subvolume snapshot -r /mnt /mnt/snap
- *
- * If when we send the snapshot and we are processing file bar (which
- * has a higher inode number than foo) we blindly send a clone operation
- * for the [0, 100K[ range from foo to bar, the receiver ends up getting
- * a file bar that matches the content of file foo - iow, doesn't match
- * the content from bar in the original filesystem.
- */
- key.objectid = clone_root->ino;
- key.type = BTRFS_EXTENT_DATA_KEY;
- key.offset = clone_root->offset;
- ret = btrfs_search_slot(NULL, clone_root->root, &key, path, 0, 0);
- if (ret < 0)
- goto out;
- if (ret > 0 && path->slots[0] > 0) {
- btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0] - 1);
- if (key.objectid == clone_root->ino &&
- key.type == BTRFS_EXTENT_DATA_KEY)
- path->slots[0]--;
- }
- while (true) {
- struct extent_buffer *leaf = path->nodes[0];
- int slot = path->slots[0];
- struct btrfs_file_extent_item *ei;
- u8 type;
- u64 ext_len;
- u64 clone_len;
- u64 clone_data_offset;
- if (slot >= btrfs_header_nritems(leaf)) {
- ret = btrfs_next_leaf(clone_root->root, path);
- if (ret < 0)
- goto out;
- else if (ret > 0)
- break;
- continue;
- }
- btrfs_item_key_to_cpu(leaf, &key, slot);
- /*
- * We might have an implicit trailing hole (NO_HOLES feature
- * enabled). We deal with it after leaving this loop.
- */
- if (key.objectid != clone_root->ino ||
- key.type != BTRFS_EXTENT_DATA_KEY)
- break;
- ei = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item);
- type = btrfs_file_extent_type(leaf, ei);
- if (type == BTRFS_FILE_EXTENT_INLINE) {
- ext_len = btrfs_file_extent_ram_bytes(leaf, ei);
- ext_len = PAGE_ALIGN(ext_len);
- } else {
- ext_len = btrfs_file_extent_num_bytes(leaf, ei);
- }
- if (key.offset + ext_len <= clone_root->offset)
- goto next;
- if (key.offset > clone_root->offset) {
- /* Implicit hole, NO_HOLES feature enabled. */
- u64 hole_len = key.offset - clone_root->offset;
- if (hole_len > len)
- hole_len = len;
- ret = send_extent_data(sctx, offset, hole_len);
- if (ret < 0)
- goto out;
- len -= hole_len;
- if (len == 0)
- break;
- offset += hole_len;
- clone_root->offset += hole_len;
- data_offset += hole_len;
- }
- if (key.offset >= clone_root->offset + len)
- break;
- if (key.offset >= clone_src_i_size)
- break;
- if (key.offset + ext_len > clone_src_i_size)
- ext_len = clone_src_i_size - key.offset;
- clone_data_offset = btrfs_file_extent_offset(leaf, ei);
- if (btrfs_file_extent_disk_bytenr(leaf, ei) == disk_byte) {
- clone_root->offset = key.offset;
- if (clone_data_offset < data_offset &&
- clone_data_offset + ext_len > data_offset) {
- u64 extent_offset;
- extent_offset = data_offset - clone_data_offset;
- ext_len -= extent_offset;
- clone_data_offset += extent_offset;
- clone_root->offset += extent_offset;
- }
- }
- clone_len = min_t(u64, ext_len, len);
- if (btrfs_file_extent_disk_bytenr(leaf, ei) == disk_byte &&
- clone_data_offset == data_offset) {
- const u64 src_end = clone_root->offset + clone_len;
- const u64 sectorsize = SZ_64K;
- /*
- * We can't clone the last block, when its size is not
- * sector size aligned, into the middle of a file. If we
- * do so, the receiver will get a failure (-EINVAL) when
- * trying to clone or will silently corrupt the data in
- * the destination file if it's on a kernel without the
- * fix introduced by commit ac765f83f1397646
- * ("Btrfs: fix data corruption due to cloning of eof
- * block).
- *
- * So issue a clone of the aligned down range plus a
- * regular write for the eof block, if we hit that case.
- *
- * Also, we use the maximum possible sector size, 64K,
- * because we don't know what's the sector size of the
- * filesystem that receives the stream, so we have to
- * assume the largest possible sector size.
- */
- if (src_end == clone_src_i_size &&
- !IS_ALIGNED(src_end, sectorsize) &&
- offset + clone_len < sctx->cur_inode_size) {
- u64 slen;
- slen = ALIGN_DOWN(src_end - clone_root->offset,
- sectorsize);
- if (slen > 0) {
- ret = send_clone(sctx, offset, slen,
- clone_root);
- if (ret < 0)
- goto out;
- }
- ret = send_extent_data(sctx, offset + slen,
- clone_len - slen);
- } else {
- ret = send_clone(sctx, offset, clone_len,
- clone_root);
- }
- } else {
- ret = send_extent_data(sctx, offset, clone_len);
- }
- if (ret < 0)
- goto out;
- len -= clone_len;
- if (len == 0)
- break;
- offset += clone_len;
- clone_root->offset += clone_len;
- /*
- * If we are cloning from the file we are currently processing,
- * and using the send root as the clone root, we must stop once
- * the current clone offset reaches the current eof of the file
- * at the receiver, otherwise we would issue an invalid clone
- * operation (source range going beyond eof) and cause the
- * receiver to fail. So if we reach the current eof, bail out
- * and fallback to a regular write.
- */
- if (clone_root->root == sctx->send_root &&
- clone_root->ino == sctx->cur_ino &&
- clone_root->offset >= sctx->cur_inode_next_write_offset)
- break;
- data_offset += clone_len;
- next:
- path->slots[0]++;
- }
- if (len > 0)
- ret = send_extent_data(sctx, offset, len);
- else
- ret = 0;
- out:
- btrfs_free_path(path);
- return ret;
- }
- static int send_write_or_clone(struct send_ctx *sctx,
- struct btrfs_path *path,
- struct btrfs_key *key,
- struct clone_root *clone_root)
- {
- int ret = 0;
- struct btrfs_file_extent_item *ei;
- u64 offset = key->offset;
- u64 len;
- u8 type;
- u64 bs = sctx->send_root->fs_info->sb->s_blocksize;
- ei = btrfs_item_ptr(path->nodes[0], path->slots[0],
- struct btrfs_file_extent_item);
- type = btrfs_file_extent_type(path->nodes[0], ei);
- if (type == BTRFS_FILE_EXTENT_INLINE) {
- len = btrfs_file_extent_ram_bytes(path->nodes[0], ei);
- /*
- * it is possible the inline item won't cover the whole page,
- * but there may be items after this page. Make
- * sure to send the whole thing
- */
- len = PAGE_ALIGN(len);
- } else {
- len = btrfs_file_extent_num_bytes(path->nodes[0], ei);
- }
- if (offset >= sctx->cur_inode_size) {
- ret = 0;
- goto out;
- }
- if (offset + len > sctx->cur_inode_size)
- len = sctx->cur_inode_size - offset;
- if (len == 0) {
- ret = 0;
- goto out;
- }
- if (clone_root && IS_ALIGNED(offset + len, bs)) {
- u64 disk_byte;
- u64 data_offset;
- disk_byte = btrfs_file_extent_disk_bytenr(path->nodes[0], ei);
- data_offset = btrfs_file_extent_offset(path->nodes[0], ei);
- ret = clone_range(sctx, clone_root, disk_byte, data_offset,
- offset, len);
- } else {
- ret = send_extent_data(sctx, offset, len);
- }
- sctx->cur_inode_next_write_offset = offset + len;
- out:
- return ret;
- }
- static int is_extent_unchanged(struct send_ctx *sctx,
- struct btrfs_path *left_path,
- struct btrfs_key *ekey)
- {
- int ret = 0;
- struct btrfs_key key;
- struct btrfs_path *path = NULL;
- struct extent_buffer *eb;
- int slot;
- struct btrfs_key found_key;
- struct btrfs_file_extent_item *ei;
- u64 left_disknr;
- u64 right_disknr;
- u64 left_offset;
- u64 right_offset;
- u64 left_offset_fixed;
- u64 left_len;
- u64 right_len;
- u64 left_gen;
- u64 right_gen;
- u8 left_type;
- u8 right_type;
- path = alloc_path_for_send();
- if (!path)
- return -ENOMEM;
- eb = left_path->nodes[0];
- slot = left_path->slots[0];
- ei = btrfs_item_ptr(eb, slot, struct btrfs_file_extent_item);
- left_type = btrfs_file_extent_type(eb, ei);
- if (left_type != BTRFS_FILE_EXTENT_REG) {
- ret = 0;
- goto out;
- }
- left_disknr = btrfs_file_extent_disk_bytenr(eb, ei);
- left_len = btrfs_file_extent_num_bytes(eb, ei);
- left_offset = btrfs_file_extent_offset(eb, ei);
- left_gen = btrfs_file_extent_generation(eb, ei);
- /*
- * Following comments will refer to these graphics. L is the left
- * extents which we are checking at the moment. 1-8 are the right
- * extents that we iterate.
- *
- * |-----L-----|
- * |-1-|-2a-|-3-|-4-|-5-|-6-|
- *
- * |-----L-----|
- * |--1--|-2b-|...(same as above)
- *
- * Alternative situation. Happens on files where extents got split.
- * |-----L-----|
- * |-----------7-----------|-6-|
- *
- * Alternative situation. Happens on files which got larger.
- * |-----L-----|
- * |-8-|
- * Nothing follows after 8.
- */
- key.objectid = ekey->objectid;
- key.type = BTRFS_EXTENT_DATA_KEY;
- key.offset = ekey->offset;
- ret = btrfs_search_slot_for_read(sctx->parent_root, &key, path, 0, 0);
- if (ret < 0)
- goto out;
- if (ret) {
- ret = 0;
- goto out;
- }
- /*
- * Handle special case where the right side has no extents at all.
- */
- eb = path->nodes[0];
- slot = path->slots[0];
- btrfs_item_key_to_cpu(eb, &found_key, slot);
- if (found_key.objectid != key.objectid ||
- found_key.type != key.type) {
- /* If we're a hole then just pretend nothing changed */
- ret = (left_disknr) ? 0 : 1;
- goto out;
- }
- /*
- * We're now on 2a, 2b or 7.
- */
- key = found_key;
- while (key.offset < ekey->offset + left_len) {
- ei = btrfs_item_ptr(eb, slot, struct btrfs_file_extent_item);
- right_type = btrfs_file_extent_type(eb, ei);
- if (right_type != BTRFS_FILE_EXTENT_REG &&
- right_type != BTRFS_FILE_EXTENT_INLINE) {
- ret = 0;
- goto out;
- }
- if (right_type == BTRFS_FILE_EXTENT_INLINE) {
- right_len = btrfs_file_extent_ram_bytes(eb, ei);
- right_len = PAGE_ALIGN(right_len);
- } else {
- right_len = btrfs_file_extent_num_bytes(eb, ei);
- }
- /*
- * Are we at extent 8? If yes, we know the extent is changed.
- * This may only happen on the first iteration.
- */
- if (found_key.offset + right_len <= ekey->offset) {
- /* If we're a hole just pretend nothing changed */
- ret = (left_disknr) ? 0 : 1;
- goto out;
- }
- /*
- * We just wanted to see if when we have an inline extent, what
- * follows it is a regular extent (wanted to check the above
- * condition for inline extents too). This should normally not
- * happen but it's possible for example when we have an inline
- * compressed extent representing data with a size matching
- * the page size (currently the same as sector size).
- */
- if (right_type == BTRFS_FILE_EXTENT_INLINE) {
- ret = 0;
- goto out;
- }
- right_disknr = btrfs_file_extent_disk_bytenr(eb, ei);
- right_offset = btrfs_file_extent_offset(eb, ei);
- right_gen = btrfs_file_extent_generation(eb, ei);
- left_offset_fixed = left_offset;
- if (key.offset < ekey->offset) {
- /* Fix the right offset for 2a and 7. */
- right_offset += ekey->offset - key.offset;
- } else {
- /* Fix the left offset for all behind 2a and 2b */
- left_offset_fixed += key.offset - ekey->offset;
- }
- /*
- * Check if we have the same extent.
- */
- if (left_disknr != right_disknr ||
- left_offset_fixed != right_offset ||
- left_gen != right_gen) {
- ret = 0;
- goto out;
- }
- /*
- * Go to the next extent.
- */
- ret = btrfs_next_item(sctx->parent_root, path);
- if (ret < 0)
- goto out;
- if (!ret) {
- eb = path->nodes[0];
- slot = path->slots[0];
- btrfs_item_key_to_cpu(eb, &found_key, slot);
- }
- if (ret || found_key.objectid != key.objectid ||
- found_key.type != key.type) {
- key.offset += right_len;
- break;
- }
- if (found_key.offset != key.offset + right_len) {
- ret = 0;
- goto out;
- }
- key = found_key;
- }
- /*
- * We're now behind the left extent (treat as unchanged) or at the end
- * of the right side (treat as changed).
- */
- if (key.offset >= ekey->offset + left_len)
- ret = 1;
- else
- ret = 0;
- out:
- btrfs_free_path(path);
- return ret;
- }
- static int get_last_extent(struct send_ctx *sctx, u64 offset)
- {
- struct btrfs_path *path;
- struct btrfs_root *root = sctx->send_root;
- struct btrfs_file_extent_item *fi;
- struct btrfs_key key;
- u64 extent_end;
- u8 type;
- int ret;
- path = alloc_path_for_send();
- if (!path)
- return -ENOMEM;
- sctx->cur_inode_last_extent = 0;
- key.objectid = sctx->cur_ino;
- key.type = BTRFS_EXTENT_DATA_KEY;
- key.offset = offset;
- ret = btrfs_search_slot_for_read(root, &key, path, 0, 1);
- if (ret < 0)
- goto out;
- ret = 0;
- btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
- if (key.objectid != sctx->cur_ino || key.type != BTRFS_EXTENT_DATA_KEY)
- goto out;
- fi = btrfs_item_ptr(path->nodes[0], path->slots[0],
- struct btrfs_file_extent_item);
- type = btrfs_file_extent_type(path->nodes[0], fi);
- if (type == BTRFS_FILE_EXTENT_INLINE) {
- u64 size = btrfs_file_extent_ram_bytes(path->nodes[0], fi);
- extent_end = ALIGN(key.offset + size,
- sctx->send_root->fs_info->sectorsize);
- } else {
- extent_end = key.offset +
- btrfs_file_extent_num_bytes(path->nodes[0], fi);
- }
- sctx->cur_inode_last_extent = extent_end;
- out:
- btrfs_free_path(path);
- return ret;
- }
- static int range_is_hole_in_parent(struct send_ctx *sctx,
- const u64 start,
- const u64 end)
- {
- struct btrfs_path *path;
- struct btrfs_key key;
- struct btrfs_root *root = sctx->parent_root;
- u64 search_start = start;
- int ret;
- path = alloc_path_for_send();
- if (!path)
- return -ENOMEM;
- key.objectid = sctx->cur_ino;
- key.type = BTRFS_EXTENT_DATA_KEY;
- key.offset = search_start;
- ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
- if (ret < 0)
- goto out;
- if (ret > 0 && path->slots[0] > 0)
- path->slots[0]--;
- while (search_start < end) {
- struct extent_buffer *leaf = path->nodes[0];
- int slot = path->slots[0];
- struct btrfs_file_extent_item *fi;
- u64 extent_end;
- if (slot >= btrfs_header_nritems(leaf)) {
- ret = btrfs_next_leaf(root, path);
- if (ret < 0)
- goto out;
- else if (ret > 0)
- break;
- continue;
- }
- btrfs_item_key_to_cpu(leaf, &key, slot);
- if (key.objectid < sctx->cur_ino ||
- key.type < BTRFS_EXTENT_DATA_KEY)
- goto next;
- if (key.objectid > sctx->cur_ino ||
- key.type > BTRFS_EXTENT_DATA_KEY ||
- key.offset >= end)
- break;
- fi = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item);
- if (btrfs_file_extent_type(leaf, fi) ==
- BTRFS_FILE_EXTENT_INLINE) {
- u64 size = btrfs_file_extent_ram_bytes(leaf, fi);
- extent_end = ALIGN(key.offset + size,
- root->fs_info->sectorsize);
- } else {
- extent_end = key.offset +
- btrfs_file_extent_num_bytes(leaf, fi);
- }
- if (extent_end <= start)
- goto next;
- if (btrfs_file_extent_disk_bytenr(leaf, fi) == 0) {
- search_start = extent_end;
- goto next;
- }
- ret = 0;
- goto out;
- next:
- path->slots[0]++;
- }
- ret = 1;
- out:
- btrfs_free_path(path);
- return ret;
- }
- static int maybe_send_hole(struct send_ctx *sctx, struct btrfs_path *path,
- struct btrfs_key *key)
- {
- struct btrfs_file_extent_item *fi;
- u64 extent_end;
- u8 type;
- int ret = 0;
- if (sctx->cur_ino != key->objectid || !need_send_hole(sctx))
- return 0;
- if (sctx->cur_inode_last_extent == (u64)-1) {
- ret = get_last_extent(sctx, key->offset - 1);
- if (ret)
- return ret;
- }
- fi = btrfs_item_ptr(path->nodes[0], path->slots[0],
- struct btrfs_file_extent_item);
- type = btrfs_file_extent_type(path->nodes[0], fi);
- if (type == BTRFS_FILE_EXTENT_INLINE) {
- u64 size = btrfs_file_extent_ram_bytes(path->nodes[0], fi);
- extent_end = ALIGN(key->offset + size,
- sctx->send_root->fs_info->sectorsize);
- } else {
- extent_end = key->offset +
- btrfs_file_extent_num_bytes(path->nodes[0], fi);
- }
- if (path->slots[0] == 0 &&
- sctx->cur_inode_last_extent < key->offset) {
- /*
- * We might have skipped entire leafs that contained only
- * file extent items for our current inode. These leafs have
- * a generation number smaller (older) than the one in the
- * current leaf and the leaf our last extent came from, and
- * are located between these 2 leafs.
- */
- ret = get_last_extent(sctx, key->offset - 1);
- if (ret)
- return ret;
- }
- if (sctx->cur_inode_last_extent < key->offset) {
- ret = range_is_hole_in_parent(sctx,
- sctx->cur_inode_last_extent,
- key->offset);
- if (ret < 0)
- return ret;
- else if (ret == 0)
- ret = send_hole(sctx, key->offset);
- else
- ret = 0;
- }
- sctx->cur_inode_last_extent = extent_end;
- return ret;
- }
- static int process_extent(struct send_ctx *sctx,
- struct btrfs_path *path,
- struct btrfs_key *key)
- {
- struct clone_root *found_clone = NULL;
- int ret = 0;
- if (S_ISLNK(sctx->cur_inode_mode))
- return 0;
- if (sctx->parent_root && !sctx->cur_inode_new) {
- ret = is_extent_unchanged(sctx, path, key);
- if (ret < 0)
- goto out;
- if (ret) {
- ret = 0;
- goto out_hole;
- }
- } else {
- struct btrfs_file_extent_item *ei;
- u8 type;
- ei = btrfs_item_ptr(path->nodes[0], path->slots[0],
- struct btrfs_file_extent_item);
- type = btrfs_file_extent_type(path->nodes[0], ei);
- if (type == BTRFS_FILE_EXTENT_PREALLOC ||
- type == BTRFS_FILE_EXTENT_REG) {
- /*
- * The send spec does not have a prealloc command yet,
- * so just leave a hole for prealloc'ed extents until
- * we have enough commands queued up to justify rev'ing
- * the send spec.
- */
- if (type == BTRFS_FILE_EXTENT_PREALLOC) {
- ret = 0;
- goto out;
- }
- /* Have a hole, just skip it. */
- if (btrfs_file_extent_disk_bytenr(path->nodes[0], ei) == 0) {
- ret = 0;
- goto out;
- }
- }
- }
- ret = find_extent_clone(sctx, path, key->objectid, key->offset,
- sctx->cur_inode_size, &found_clone);
- if (ret != -ENOENT && ret < 0)
- goto out;
- ret = send_write_or_clone(sctx, path, key, found_clone);
- if (ret)
- goto out;
- out_hole:
- ret = maybe_send_hole(sctx, path, key);
- out:
- return ret;
- }
- static int process_all_extents(struct send_ctx *sctx)
- {
- int ret;
- struct btrfs_root *root;
- struct btrfs_path *path;
- struct btrfs_key key;
- struct btrfs_key found_key;
- struct extent_buffer *eb;
- int slot;
- root = sctx->send_root;
- path = alloc_path_for_send();
- if (!path)
- return -ENOMEM;
- key.objectid = sctx->cmp_key->objectid;
- key.type = BTRFS_EXTENT_DATA_KEY;
- key.offset = 0;
- ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
- if (ret < 0)
- goto out;
- while (1) {
- eb = path->nodes[0];
- slot = path->slots[0];
- if (slot >= btrfs_header_nritems(eb)) {
- ret = btrfs_next_leaf(root, path);
- if (ret < 0) {
- goto out;
- } else if (ret > 0) {
- ret = 0;
- break;
- }
- continue;
- }
- btrfs_item_key_to_cpu(eb, &found_key, slot);
- if (found_key.objectid != key.objectid ||
- found_key.type != key.type) {
- ret = 0;
- goto out;
- }
- ret = process_extent(sctx, path, &found_key);
- if (ret < 0)
- goto out;
- path->slots[0]++;
- }
- out:
- btrfs_free_path(path);
- return ret;
- }
- static int process_recorded_refs_if_needed(struct send_ctx *sctx, int at_end,
- int *pending_move,
- int *refs_processed)
- {
- int ret = 0;
- if (sctx->cur_ino == 0)
- goto out;
- if (!at_end && sctx->cur_ino == sctx->cmp_key->objectid &&
- sctx->cmp_key->type <= BTRFS_INODE_EXTREF_KEY)
- goto out;
- if (list_empty(&sctx->new_refs) && list_empty(&sctx->deleted_refs))
- goto out;
- ret = process_recorded_refs(sctx, pending_move);
- if (ret < 0)
- goto out;
- *refs_processed = 1;
- out:
- return ret;
- }
- static int finish_inode_if_needed(struct send_ctx *sctx, int at_end)
- {
- int ret = 0;
- u64 left_mode;
- u64 left_uid;
- u64 left_gid;
- u64 right_mode;
- u64 right_uid;
- u64 right_gid;
- int need_chmod = 0;
- int need_chown = 0;
- int need_truncate = 1;
- int pending_move = 0;
- int refs_processed = 0;
- if (sctx->ignore_cur_inode)
- return 0;
- ret = process_recorded_refs_if_needed(sctx, at_end, &pending_move,
- &refs_processed);
- if (ret < 0)
- goto out;
- /*
- * We have processed the refs and thus need to advance send_progress.
- * Now, calls to get_cur_xxx will take the updated refs of the current
- * inode into account.
- *
- * On the other hand, if our current inode is a directory and couldn't
- * be moved/renamed because its parent was renamed/moved too and it has
- * a higher inode number, we can only move/rename our current inode
- * after we moved/renamed its parent. Therefore in this case operate on
- * the old path (pre move/rename) of our current inode, and the
- * move/rename will be performed later.
- */
- if (refs_processed && !pending_move)
- sctx->send_progress = sctx->cur_ino + 1;
- if (sctx->cur_ino == 0 || sctx->cur_inode_deleted)
- goto out;
- if (!at_end && sctx->cmp_key->objectid == sctx->cur_ino)
- goto out;
- ret = get_inode_info(sctx->send_root, sctx->cur_ino, NULL, NULL,
- &left_mode, &left_uid, &left_gid, NULL);
- if (ret < 0)
- goto out;
- if (!sctx->parent_root || sctx->cur_inode_new) {
- need_chown = 1;
- if (!S_ISLNK(sctx->cur_inode_mode))
- need_chmod = 1;
- if (sctx->cur_inode_next_write_offset == sctx->cur_inode_size)
- need_truncate = 0;
- } else {
- u64 old_size;
- ret = get_inode_info(sctx->parent_root, sctx->cur_ino,
- &old_size, NULL, &right_mode, &right_uid,
- &right_gid, NULL);
- if (ret < 0)
- goto out;
- if (left_uid != right_uid || left_gid != right_gid)
- need_chown = 1;
- if (!S_ISLNK(sctx->cur_inode_mode) && left_mode != right_mode)
- need_chmod = 1;
- if ((old_size == sctx->cur_inode_size) ||
- (sctx->cur_inode_size > old_size &&
- sctx->cur_inode_next_write_offset == sctx->cur_inode_size))
- need_truncate = 0;
- }
- if (S_ISREG(sctx->cur_inode_mode)) {
- if (need_send_hole(sctx)) {
- if (sctx->cur_inode_last_extent == (u64)-1 ||
- sctx->cur_inode_last_extent <
- sctx->cur_inode_size) {
- ret = get_last_extent(sctx, (u64)-1);
- if (ret)
- goto out;
- }
- if (sctx->cur_inode_last_extent <
- sctx->cur_inode_size) {
- ret = send_hole(sctx, sctx->cur_inode_size);
- if (ret)
- goto out;
- }
- }
- if (need_truncate) {
- ret = send_truncate(sctx, sctx->cur_ino,
- sctx->cur_inode_gen,
- sctx->cur_inode_size);
- if (ret < 0)
- goto out;
- }
- }
- if (need_chown) {
- ret = send_chown(sctx, sctx->cur_ino, sctx->cur_inode_gen,
- left_uid, left_gid);
- if (ret < 0)
- goto out;
- }
- if (need_chmod) {
- ret = send_chmod(sctx, sctx->cur_ino, sctx->cur_inode_gen,
- left_mode);
- if (ret < 0)
- goto out;
- }
- ret = send_capabilities(sctx);
- if (ret < 0)
- goto out;
- /*
- * If other directory inodes depended on our current directory
- * inode's move/rename, now do their move/rename operations.
- */
- if (!is_waiting_for_move(sctx, sctx->cur_ino)) {
- ret = apply_children_dir_moves(sctx);
- if (ret)
- goto out;
- /*
- * Need to send that every time, no matter if it actually
- * changed between the two trees as we have done changes to
- * the inode before. If our inode is a directory and it's
- * waiting to be moved/renamed, we will send its utimes when
- * it's moved/renamed, therefore we don't need to do it here.
- */
- sctx->send_progress = sctx->cur_ino + 1;
- ret = send_utimes(sctx, sctx->cur_ino, sctx->cur_inode_gen);
- if (ret < 0)
- goto out;
- }
- out:
- return ret;
- }
- struct parent_paths_ctx {
- struct list_head *refs;
- struct send_ctx *sctx;
- };
- static int record_parent_ref(int num, u64 dir, int index, struct fs_path *name,
- void *ctx)
- {
- struct parent_paths_ctx *ppctx = ctx;
- return record_ref(ppctx->sctx->parent_root, dir, name, ppctx->sctx,
- ppctx->refs);
- }
- /*
- * Issue unlink operations for all paths of the current inode found in the
- * parent snapshot.
- */
- static int btrfs_unlink_all_paths(struct send_ctx *sctx)
- {
- LIST_HEAD(deleted_refs);
- struct btrfs_path *path;
- struct btrfs_key key;
- struct parent_paths_ctx ctx;
- int ret;
- path = alloc_path_for_send();
- if (!path)
- return -ENOMEM;
- key.objectid = sctx->cur_ino;
- key.type = BTRFS_INODE_REF_KEY;
- key.offset = 0;
- ret = btrfs_search_slot(NULL, sctx->parent_root, &key, path, 0, 0);
- if (ret < 0)
- goto out;
- ctx.refs = &deleted_refs;
- ctx.sctx = sctx;
- while (true) {
- struct extent_buffer *eb = path->nodes[0];
- int slot = path->slots[0];
- if (slot >= btrfs_header_nritems(eb)) {
- ret = btrfs_next_leaf(sctx->parent_root, path);
- if (ret < 0)
- goto out;
- else if (ret > 0)
- break;
- continue;
- }
- btrfs_item_key_to_cpu(eb, &key, slot);
- if (key.objectid != sctx->cur_ino)
- break;
- if (key.type != BTRFS_INODE_REF_KEY &&
- key.type != BTRFS_INODE_EXTREF_KEY)
- break;
- ret = iterate_inode_ref(sctx->parent_root, path, &key, 1,
- record_parent_ref, &ctx);
- if (ret < 0)
- goto out;
- path->slots[0]++;
- }
- while (!list_empty(&deleted_refs)) {
- struct recorded_ref *ref;
- ref = list_first_entry(&deleted_refs, struct recorded_ref, list);
- ret = send_unlink(sctx, ref->full_path);
- if (ret < 0)
- goto out;
- fs_path_free(ref->full_path);
- list_del(&ref->list);
- kfree(ref);
- }
- ret = 0;
- out:
- btrfs_free_path(path);
- if (ret)
- __free_recorded_refs(&deleted_refs);
- return ret;
- }
- static int changed_inode(struct send_ctx *sctx,
- enum btrfs_compare_tree_result result)
- {
- int ret = 0;
- struct btrfs_key *key = sctx->cmp_key;
- struct btrfs_inode_item *left_ii = NULL;
- struct btrfs_inode_item *right_ii = NULL;
- u64 left_gen = 0;
- u64 right_gen = 0;
- sctx->cur_ino = key->objectid;
- sctx->cur_inode_new_gen = 0;
- sctx->cur_inode_last_extent = (u64)-1;
- sctx->cur_inode_next_write_offset = 0;
- sctx->ignore_cur_inode = false;
- /*
- * Set send_progress to current inode. This will tell all get_cur_xxx
- * functions that the current inode's refs are not updated yet. Later,
- * when process_recorded_refs is finished, it is set to cur_ino + 1.
- */
- sctx->send_progress = sctx->cur_ino;
- if (result == BTRFS_COMPARE_TREE_NEW ||
- result == BTRFS_COMPARE_TREE_CHANGED) {
- left_ii = btrfs_item_ptr(sctx->left_path->nodes[0],
- sctx->left_path->slots[0],
- struct btrfs_inode_item);
- left_gen = btrfs_inode_generation(sctx->left_path->nodes[0],
- left_ii);
- } else {
- right_ii = btrfs_item_ptr(sctx->right_path->nodes[0],
- sctx->right_path->slots[0],
- struct btrfs_inode_item);
- right_gen = btrfs_inode_generation(sctx->right_path->nodes[0],
- right_ii);
- }
- if (result == BTRFS_COMPARE_TREE_CHANGED) {
- right_ii = btrfs_item_ptr(sctx->right_path->nodes[0],
- sctx->right_path->slots[0],
- struct btrfs_inode_item);
- right_gen = btrfs_inode_generation(sctx->right_path->nodes[0],
- right_ii);
- /*
- * The cur_ino = root dir case is special here. We can't treat
- * the inode as deleted+reused because it would generate a
- * stream that tries to delete/mkdir the root dir.
- */
- if (left_gen != right_gen &&
- sctx->cur_ino != BTRFS_FIRST_FREE_OBJECTID)
- sctx->cur_inode_new_gen = 1;
- }
- /*
- * Normally we do not find inodes with a link count of zero (orphans)
- * because the most common case is to create a snapshot and use it
- * for a send operation. However other less common use cases involve
- * using a subvolume and send it after turning it to RO mode just
- * after deleting all hard links of a file while holding an open
- * file descriptor against it or turning a RO snapshot into RW mode,
- * keep an open file descriptor against a file, delete it and then
- * turn the snapshot back to RO mode before using it for a send
- * operation. So if we find such cases, ignore the inode and all its
- * items completely if it's a new inode, or if it's a changed inode
- * make sure all its previous paths (from the parent snapshot) are all
- * unlinked and all other the inode items are ignored.
- */
- if (result == BTRFS_COMPARE_TREE_NEW ||
- result == BTRFS_COMPARE_TREE_CHANGED) {
- u32 nlinks;
- nlinks = btrfs_inode_nlink(sctx->left_path->nodes[0], left_ii);
- if (nlinks == 0) {
- sctx->ignore_cur_inode = true;
- if (result == BTRFS_COMPARE_TREE_CHANGED)
- ret = btrfs_unlink_all_paths(sctx);
- goto out;
- }
- }
- if (result == BTRFS_COMPARE_TREE_NEW) {
- sctx->cur_inode_gen = left_gen;
- sctx->cur_inode_new = 1;
- sctx->cur_inode_deleted = 0;
- sctx->cur_inode_size = btrfs_inode_size(
- sctx->left_path->nodes[0], left_ii);
- sctx->cur_inode_mode = btrfs_inode_mode(
- sctx->left_path->nodes[0], left_ii);
- sctx->cur_inode_rdev = btrfs_inode_rdev(
- sctx->left_path->nodes[0], left_ii);
- if (sctx->cur_ino != BTRFS_FIRST_FREE_OBJECTID)
- ret = send_create_inode_if_needed(sctx);
- } else if (result == BTRFS_COMPARE_TREE_DELETED) {
- sctx->cur_inode_gen = right_gen;
- sctx->cur_inode_new = 0;
- sctx->cur_inode_deleted = 1;
- sctx->cur_inode_size = btrfs_inode_size(
- sctx->right_path->nodes[0], right_ii);
- sctx->cur_inode_mode = btrfs_inode_mode(
- sctx->right_path->nodes[0], right_ii);
- } else if (result == BTRFS_COMPARE_TREE_CHANGED) {
- /*
- * We need to do some special handling in case the inode was
- * reported as changed with a changed generation number. This
- * means that the original inode was deleted and new inode
- * reused the same inum. So we have to treat the old inode as
- * deleted and the new one as new.
- */
- if (sctx->cur_inode_new_gen) {
- /*
- * First, process the inode as if it was deleted.
- */
- sctx->cur_inode_gen = right_gen;
- sctx->cur_inode_new = 0;
- sctx->cur_inode_deleted = 1;
- sctx->cur_inode_size = btrfs_inode_size(
- sctx->right_path->nodes[0], right_ii);
- sctx->cur_inode_mode = btrfs_inode_mode(
- sctx->right_path->nodes[0], right_ii);
- ret = process_all_refs(sctx,
- BTRFS_COMPARE_TREE_DELETED);
- if (ret < 0)
- goto out;
- /*
- * Now process the inode as if it was new.
- */
- sctx->cur_inode_gen = left_gen;
- sctx->cur_inode_new = 1;
- sctx->cur_inode_deleted = 0;
- sctx->cur_inode_size = btrfs_inode_size(
- sctx->left_path->nodes[0], left_ii);
- sctx->cur_inode_mode = btrfs_inode_mode(
- sctx->left_path->nodes[0], left_ii);
- sctx->cur_inode_rdev = btrfs_inode_rdev(
- sctx->left_path->nodes[0], left_ii);
- ret = send_create_inode_if_needed(sctx);
- if (ret < 0)
- goto out;
- ret = process_all_refs(sctx, BTRFS_COMPARE_TREE_NEW);
- if (ret < 0)
- goto out;
- /*
- * Advance send_progress now as we did not get into
- * process_recorded_refs_if_needed in the new_gen case.
- */
- sctx->send_progress = sctx->cur_ino + 1;
- /*
- * Now process all extents and xattrs of the inode as if
- * they were all new.
- */
- ret = process_all_extents(sctx);
- if (ret < 0)
- goto out;
- ret = process_all_new_xattrs(sctx);
- if (ret < 0)
- goto out;
- } else {
- sctx->cur_inode_gen = left_gen;
- sctx->cur_inode_new = 0;
- sctx->cur_inode_new_gen = 0;
- sctx->cur_inode_deleted = 0;
- sctx->cur_inode_size = btrfs_inode_size(
- sctx->left_path->nodes[0], left_ii);
- sctx->cur_inode_mode = btrfs_inode_mode(
- sctx->left_path->nodes[0], left_ii);
- }
- }
- out:
- return ret;
- }
- /*
- * We have to process new refs before deleted refs, but compare_trees gives us
- * the new and deleted refs mixed. To fix this, we record the new/deleted refs
- * first and later process them in process_recorded_refs.
- * For the cur_inode_new_gen case, we skip recording completely because
- * changed_inode did already initiate processing of refs. The reason for this is
- * that in this case, compare_tree actually compares the refs of 2 different
- * inodes. To fix this, process_all_refs is used in changed_inode to handle all
- * refs of the right tree as deleted and all refs of the left tree as new.
- */
- static int changed_ref(struct send_ctx *sctx,
- enum btrfs_compare_tree_result result)
- {
- int ret = 0;
- if (sctx->cur_ino != sctx->cmp_key->objectid) {
- inconsistent_snapshot_error(sctx, result, "reference");
- return -EIO;
- }
- if (!sctx->cur_inode_new_gen &&
- sctx->cur_ino != BTRFS_FIRST_FREE_OBJECTID) {
- if (result == BTRFS_COMPARE_TREE_NEW)
- ret = record_new_ref(sctx);
- else if (result == BTRFS_COMPARE_TREE_DELETED)
- ret = record_deleted_ref(sctx);
- else if (result == BTRFS_COMPARE_TREE_CHANGED)
- ret = record_changed_ref(sctx);
- }
- return ret;
- }
- /*
- * Process new/deleted/changed xattrs. We skip processing in the
- * cur_inode_new_gen case because changed_inode did already initiate processing
- * of xattrs. The reason is the same as in changed_ref
- */
- static int changed_xattr(struct send_ctx *sctx,
- enum btrfs_compare_tree_result result)
- {
- int ret = 0;
- if (sctx->cur_ino != sctx->cmp_key->objectid) {
- inconsistent_snapshot_error(sctx, result, "xattr");
- return -EIO;
- }
- if (!sctx->cur_inode_new_gen && !sctx->cur_inode_deleted) {
- if (result == BTRFS_COMPARE_TREE_NEW)
- ret = process_new_xattr(sctx);
- else if (result == BTRFS_COMPARE_TREE_DELETED)
- ret = process_deleted_xattr(sctx);
- else if (result == BTRFS_COMPARE_TREE_CHANGED)
- ret = process_changed_xattr(sctx);
- }
- return ret;
- }
- /*
- * Process new/deleted/changed extents. We skip processing in the
- * cur_inode_new_gen case because changed_inode did already initiate processing
- * of extents. The reason is the same as in changed_ref
- */
- static int changed_extent(struct send_ctx *sctx,
- enum btrfs_compare_tree_result result)
- {
- int ret = 0;
- /*
- * We have found an extent item that changed without the inode item
- * having changed. This can happen either after relocation (where the
- * disk_bytenr of an extent item is replaced at
- * relocation.c:replace_file_extents()) or after deduplication into a
- * file in both the parent and send snapshots (where an extent item can
- * get modified or replaced with a new one). Note that deduplication
- * updates the inode item, but it only changes the iversion (sequence
- * field in the inode item) of the inode, so if a file is deduplicated
- * the same amount of times in both the parent and send snapshots, its
- * iversion becames the same in both snapshots, whence the inode item is
- * the same on both snapshots.
- */
- if (sctx->cur_ino != sctx->cmp_key->objectid)
- return 0;
- if (!sctx->cur_inode_new_gen && !sctx->cur_inode_deleted) {
- if (result != BTRFS_COMPARE_TREE_DELETED)
- ret = process_extent(sctx, sctx->left_path,
- sctx->cmp_key);
- }
- return ret;
- }
- static int dir_changed(struct send_ctx *sctx, u64 dir)
- {
- u64 orig_gen, new_gen;
- int ret;
- ret = get_inode_info(sctx->send_root, dir, NULL, &new_gen, NULL, NULL,
- NULL, NULL);
- if (ret)
- return ret;
- ret = get_inode_info(sctx->parent_root, dir, NULL, &orig_gen, NULL,
- NULL, NULL, NULL);
- if (ret)
- return ret;
- return (orig_gen != new_gen) ? 1 : 0;
- }
- static int compare_refs(struct send_ctx *sctx, struct btrfs_path *path,
- struct btrfs_key *key)
- {
- struct btrfs_inode_extref *extref;
- struct extent_buffer *leaf;
- u64 dirid = 0, last_dirid = 0;
- unsigned long ptr;
- u32 item_size;
- u32 cur_offset = 0;
- int ref_name_len;
- int ret = 0;
- /* Easy case, just check this one dirid */
- if (key->type == BTRFS_INODE_REF_KEY) {
- dirid = key->offset;
- ret = dir_changed(sctx, dirid);
- goto out;
- }
- leaf = path->nodes[0];
- item_size = btrfs_item_size_nr(leaf, path->slots[0]);
- ptr = btrfs_item_ptr_offset(leaf, path->slots[0]);
- while (cur_offset < item_size) {
- extref = (struct btrfs_inode_extref *)(ptr +
- cur_offset);
- dirid = btrfs_inode_extref_parent(leaf, extref);
- ref_name_len = btrfs_inode_extref_name_len(leaf, extref);
- cur_offset += ref_name_len + sizeof(*extref);
- if (dirid == last_dirid)
- continue;
- ret = dir_changed(sctx, dirid);
- if (ret)
- break;
- last_dirid = dirid;
- }
- out:
- return ret;
- }
- /*
- * Updates compare related fields in sctx and simply forwards to the actual
- * changed_xxx functions.
- */
- static int changed_cb(struct btrfs_path *left_path,
- struct btrfs_path *right_path,
- struct btrfs_key *key,
- enum btrfs_compare_tree_result result,
- void *ctx)
- {
- int ret = 0;
- struct send_ctx *sctx = ctx;
- if (result == BTRFS_COMPARE_TREE_SAME) {
- if (key->type == BTRFS_INODE_REF_KEY ||
- key->type == BTRFS_INODE_EXTREF_KEY) {
- ret = compare_refs(sctx, left_path, key);
- if (!ret)
- return 0;
- if (ret < 0)
- return ret;
- } else if (key->type == BTRFS_EXTENT_DATA_KEY) {
- return maybe_send_hole(sctx, left_path, key);
- } else {
- return 0;
- }
- result = BTRFS_COMPARE_TREE_CHANGED;
- ret = 0;
- }
- sctx->left_path = left_path;
- sctx->right_path = right_path;
- sctx->cmp_key = key;
- ret = finish_inode_if_needed(sctx, 0);
- if (ret < 0)
- goto out;
- /* Ignore non-FS objects */
- if (key->objectid == BTRFS_FREE_INO_OBJECTID ||
- key->objectid == BTRFS_FREE_SPACE_OBJECTID)
- goto out;
- if (key->type == BTRFS_INODE_ITEM_KEY) {
- ret = changed_inode(sctx, result);
- } else if (!sctx->ignore_cur_inode) {
- if (key->type == BTRFS_INODE_REF_KEY ||
- key->type == BTRFS_INODE_EXTREF_KEY)
- ret = changed_ref(sctx, result);
- else if (key->type == BTRFS_XATTR_ITEM_KEY)
- ret = changed_xattr(sctx, result);
- else if (key->type == BTRFS_EXTENT_DATA_KEY)
- ret = changed_extent(sctx, result);
- }
- out:
- return ret;
- }
- static int full_send_tree(struct send_ctx *sctx)
- {
- int ret;
- struct btrfs_root *send_root = sctx->send_root;
- struct btrfs_key key;
- struct btrfs_path *path;
- struct extent_buffer *eb;
- int slot;
- path = alloc_path_for_send();
- if (!path)
- return -ENOMEM;
- key.objectid = BTRFS_FIRST_FREE_OBJECTID;
- key.type = BTRFS_INODE_ITEM_KEY;
- key.offset = 0;
- ret = btrfs_search_slot_for_read(send_root, &key, path, 1, 0);
- if (ret < 0)
- goto out;
- if (ret)
- goto out_finish;
- while (1) {
- eb = path->nodes[0];
- slot = path->slots[0];
- btrfs_item_key_to_cpu(eb, &key, slot);
- ret = changed_cb(path, NULL, &key,
- BTRFS_COMPARE_TREE_NEW, sctx);
- if (ret < 0)
- goto out;
- ret = btrfs_next_item(send_root, path);
- if (ret < 0)
- goto out;
- if (ret) {
- ret = 0;
- break;
- }
- }
- out_finish:
- ret = finish_inode_if_needed(sctx, 1);
- out:
- btrfs_free_path(path);
- return ret;
- }
- static int tree_move_down(struct btrfs_path *path, int *level)
- {
- struct extent_buffer *eb;
- BUG_ON(*level == 0);
- eb = btrfs_read_node_slot(path->nodes[*level], path->slots[*level]);
- if (IS_ERR(eb))
- return PTR_ERR(eb);
- path->nodes[*level - 1] = eb;
- path->slots[*level - 1] = 0;
- (*level)--;
- return 0;
- }
- static int tree_move_next_or_upnext(struct btrfs_path *path,
- int *level, int root_level)
- {
- int ret = 0;
- int nritems;
- nritems = btrfs_header_nritems(path->nodes[*level]);
- path->slots[*level]++;
- while (path->slots[*level] >= nritems) {
- if (*level == root_level)
- return -1;
- /* move upnext */
- path->slots[*level] = 0;
- free_extent_buffer(path->nodes[*level]);
- path->nodes[*level] = NULL;
- (*level)++;
- path->slots[*level]++;
- nritems = btrfs_header_nritems(path->nodes[*level]);
- ret = 1;
- }
- return ret;
- }
- /*
- * Returns 1 if it had to move up and next. 0 is returned if it moved only next
- * or down.
- */
- static int tree_advance(struct btrfs_path *path,
- int *level, int root_level,
- int allow_down,
- struct btrfs_key *key)
- {
- int ret;
- if (*level == 0 || !allow_down) {
- ret = tree_move_next_or_upnext(path, level, root_level);
- } else {
- ret = tree_move_down(path, level);
- }
- if (ret >= 0) {
- if (*level == 0)
- btrfs_item_key_to_cpu(path->nodes[*level], key,
- path->slots[*level]);
- else
- btrfs_node_key_to_cpu(path->nodes[*level], key,
- path->slots[*level]);
- }
- return ret;
- }
- static int tree_compare_item(struct btrfs_path *left_path,
- struct btrfs_path *right_path,
- char *tmp_buf)
- {
- int cmp;
- int len1, len2;
- unsigned long off1, off2;
- len1 = btrfs_item_size_nr(left_path->nodes[0], left_path->slots[0]);
- len2 = btrfs_item_size_nr(right_path->nodes[0], right_path->slots[0]);
- if (len1 != len2)
- return 1;
- off1 = btrfs_item_ptr_offset(left_path->nodes[0], left_path->slots[0]);
- off2 = btrfs_item_ptr_offset(right_path->nodes[0],
- right_path->slots[0]);
- read_extent_buffer(left_path->nodes[0], tmp_buf, off1, len1);
- cmp = memcmp_extent_buffer(right_path->nodes[0], tmp_buf, off2, len1);
- if (cmp)
- return 1;
- return 0;
- }
- /*
- * This function compares two trees and calls the provided callback for
- * every changed/new/deleted item it finds.
- * If shared tree blocks are encountered, whole subtrees are skipped, making
- * the compare pretty fast on snapshotted subvolumes.
- *
- * This currently works on commit roots only. As commit roots are read only,
- * we don't do any locking. The commit roots are protected with transactions.
- * Transactions are ended and rejoined when a commit is tried in between.
- *
- * This function checks for modifications done to the trees while comparing.
- * If it detects a change, it aborts immediately.
- */
- static int btrfs_compare_trees(struct btrfs_root *left_root,
- struct btrfs_root *right_root,
- btrfs_changed_cb_t changed_cb, void *ctx)
- {
- struct btrfs_fs_info *fs_info = left_root->fs_info;
- int ret;
- int cmp;
- struct btrfs_path *left_path = NULL;
- struct btrfs_path *right_path = NULL;
- struct btrfs_key left_key;
- struct btrfs_key right_key;
- char *tmp_buf = NULL;
- int left_root_level;
- int right_root_level;
- int left_level;
- int right_level;
- int left_end_reached;
- int right_end_reached;
- int advance_left;
- int advance_right;
- u64 left_blockptr;
- u64 right_blockptr;
- u64 left_gen;
- u64 right_gen;
- left_path = btrfs_alloc_path();
- if (!left_path) {
- ret = -ENOMEM;
- goto out;
- }
- right_path = btrfs_alloc_path();
- if (!right_path) {
- ret = -ENOMEM;
- goto out;
- }
- tmp_buf = kvmalloc(fs_info->nodesize, GFP_KERNEL);
- if (!tmp_buf) {
- ret = -ENOMEM;
- goto out;
- }
- left_path->search_commit_root = 1;
- left_path->skip_locking = 1;
- right_path->search_commit_root = 1;
- right_path->skip_locking = 1;
- /*
- * Strategy: Go to the first items of both trees. Then do
- *
- * If both trees are at level 0
- * Compare keys of current items
- * If left < right treat left item as new, advance left tree
- * and repeat
- * If left > right treat right item as deleted, advance right tree
- * and repeat
- * If left == right do deep compare of items, treat as changed if
- * needed, advance both trees and repeat
- * If both trees are at the same level but not at level 0
- * Compare keys of current nodes/leafs
- * If left < right advance left tree and repeat
- * If left > right advance right tree and repeat
- * If left == right compare blockptrs of the next nodes/leafs
- * If they match advance both trees but stay at the same level
- * and repeat
- * If they don't match advance both trees while allowing to go
- * deeper and repeat
- * If tree levels are different
- * Advance the tree that needs it and repeat
- *
- * Advancing a tree means:
- * If we are at level 0, try to go to the next slot. If that's not
- * possible, go one level up and repeat. Stop when we found a level
- * where we could go to the next slot. We may at this point be on a
- * node or a leaf.
- *
- * If we are not at level 0 and not on shared tree blocks, go one
- * level deeper.
- *
- * If we are not at level 0 and on shared tree blocks, go one slot to
- * the right if possible or go up and right.
- */
- down_read(&fs_info->commit_root_sem);
- left_level = btrfs_header_level(left_root->commit_root);
- left_root_level = left_level;
- left_path->nodes[left_level] =
- btrfs_clone_extent_buffer(left_root->commit_root);
- if (!left_path->nodes[left_level]) {
- up_read(&fs_info->commit_root_sem);
- ret = -ENOMEM;
- goto out;
- }
- right_level = btrfs_header_level(right_root->commit_root);
- right_root_level = right_level;
- right_path->nodes[right_level] =
- btrfs_clone_extent_buffer(right_root->commit_root);
- if (!right_path->nodes[right_level]) {
- up_read(&fs_info->commit_root_sem);
- ret = -ENOMEM;
- goto out;
- }
- up_read(&fs_info->commit_root_sem);
- if (left_level == 0)
- btrfs_item_key_to_cpu(left_path->nodes[left_level],
- &left_key, left_path->slots[left_level]);
- else
- btrfs_node_key_to_cpu(left_path->nodes[left_level],
- &left_key, left_path->slots[left_level]);
- if (right_level == 0)
- btrfs_item_key_to_cpu(right_path->nodes[right_level],
- &right_key, right_path->slots[right_level]);
- else
- btrfs_node_key_to_cpu(right_path->nodes[right_level],
- &right_key, right_path->slots[right_level]);
- left_end_reached = right_end_reached = 0;
- advance_left = advance_right = 0;
- while (1) {
- cond_resched();
- if (advance_left && !left_end_reached) {
- ret = tree_advance(left_path, &left_level,
- left_root_level,
- advance_left != ADVANCE_ONLY_NEXT,
- &left_key);
- if (ret == -1)
- left_end_reached = ADVANCE;
- else if (ret < 0)
- goto out;
- advance_left = 0;
- }
- if (advance_right && !right_end_reached) {
- ret = tree_advance(right_path, &right_level,
- right_root_level,
- advance_right != ADVANCE_ONLY_NEXT,
- &right_key);
- if (ret == -1)
- right_end_reached = ADVANCE;
- else if (ret < 0)
- goto out;
- advance_right = 0;
- }
- if (left_end_reached && right_end_reached) {
- ret = 0;
- goto out;
- } else if (left_end_reached) {
- if (right_level == 0) {
- ret = changed_cb(left_path, right_path,
- &right_key,
- BTRFS_COMPARE_TREE_DELETED,
- ctx);
- if (ret < 0)
- goto out;
- }
- advance_right = ADVANCE;
- continue;
- } else if (right_end_reached) {
- if (left_level == 0) {
- ret = changed_cb(left_path, right_path,
- &left_key,
- BTRFS_COMPARE_TREE_NEW,
- ctx);
- if (ret < 0)
- goto out;
- }
- advance_left = ADVANCE;
- continue;
- }
- if (left_level == 0 && right_level == 0) {
- cmp = btrfs_comp_cpu_keys(&left_key, &right_key);
- if (cmp < 0) {
- ret = changed_cb(left_path, right_path,
- &left_key,
- BTRFS_COMPARE_TREE_NEW,
- ctx);
- if (ret < 0)
- goto out;
- advance_left = ADVANCE;
- } else if (cmp > 0) {
- ret = changed_cb(left_path, right_path,
- &right_key,
- BTRFS_COMPARE_TREE_DELETED,
- ctx);
- if (ret < 0)
- goto out;
- advance_right = ADVANCE;
- } else {
- enum btrfs_compare_tree_result result;
- WARN_ON(!extent_buffer_uptodate(left_path->nodes[0]));
- ret = tree_compare_item(left_path, right_path,
- tmp_buf);
- if (ret)
- result = BTRFS_COMPARE_TREE_CHANGED;
- else
- result = BTRFS_COMPARE_TREE_SAME;
- ret = changed_cb(left_path, right_path,
- &left_key, result, ctx);
- if (ret < 0)
- goto out;
- advance_left = ADVANCE;
- advance_right = ADVANCE;
- }
- } else if (left_level == right_level) {
- cmp = btrfs_comp_cpu_keys(&left_key, &right_key);
- if (cmp < 0) {
- advance_left = ADVANCE;
- } else if (cmp > 0) {
- advance_right = ADVANCE;
- } else {
- left_blockptr = btrfs_node_blockptr(
- left_path->nodes[left_level],
- left_path->slots[left_level]);
- right_blockptr = btrfs_node_blockptr(
- right_path->nodes[right_level],
- right_path->slots[right_level]);
- left_gen = btrfs_node_ptr_generation(
- left_path->nodes[left_level],
- left_path->slots[left_level]);
- right_gen = btrfs_node_ptr_generation(
- right_path->nodes[right_level],
- right_path->slots[right_level]);
- if (left_blockptr == right_blockptr &&
- left_gen == right_gen) {
- /*
- * As we're on a shared block, don't
- * allow to go deeper.
- */
- advance_left = ADVANCE_ONLY_NEXT;
- advance_right = ADVANCE_ONLY_NEXT;
- } else {
- advance_left = ADVANCE;
- advance_right = ADVANCE;
- }
- }
- } else if (left_level < right_level) {
- advance_right = ADVANCE;
- } else {
- advance_left = ADVANCE;
- }
- }
- out:
- btrfs_free_path(left_path);
- btrfs_free_path(right_path);
- kvfree(tmp_buf);
- return ret;
- }
- static int send_subvol(struct send_ctx *sctx)
- {
- int ret;
- if (!(sctx->flags & BTRFS_SEND_FLAG_OMIT_STREAM_HEADER)) {
- ret = send_header(sctx);
- if (ret < 0)
- goto out;
- }
- ret = send_subvol_begin(sctx);
- if (ret < 0)
- goto out;
- if (sctx->parent_root) {
- ret = btrfs_compare_trees(sctx->send_root, sctx->parent_root,
- changed_cb, sctx);
- if (ret < 0)
- goto out;
- ret = finish_inode_if_needed(sctx, 1);
- if (ret < 0)
- goto out;
- } else {
- ret = full_send_tree(sctx);
- if (ret < 0)
- goto out;
- }
- out:
- free_recorded_refs(sctx);
- return ret;
- }
- /*
- * If orphan cleanup did remove any orphans from a root, it means the tree
- * was modified and therefore the commit root is not the same as the current
- * root anymore. This is a problem, because send uses the commit root and
- * therefore can see inode items that don't exist in the current root anymore,
- * and for example make calls to btrfs_iget, which will do tree lookups based
- * on the current root and not on the commit root. Those lookups will fail,
- * returning a -ESTALE error, and making send fail with that error. So make
- * sure a send does not see any orphans we have just removed, and that it will
- * see the same inodes regardless of whether a transaction commit happened
- * before it started (meaning that the commit root will be the same as the
- * current root) or not.
- */
- static int ensure_commit_roots_uptodate(struct send_ctx *sctx)
- {
- int i;
- struct btrfs_trans_handle *trans = NULL;
- again:
- if (sctx->parent_root &&
- sctx->parent_root->node != sctx->parent_root->commit_root)
- goto commit_trans;
- for (i = 0; i < sctx->clone_roots_cnt; i++)
- if (sctx->clone_roots[i].root->node !=
- sctx->clone_roots[i].root->commit_root)
- goto commit_trans;
- if (trans)
- return btrfs_end_transaction(trans);
- return 0;
- commit_trans:
- /* Use any root, all fs roots will get their commit roots updated. */
- if (!trans) {
- trans = btrfs_join_transaction(sctx->send_root);
- if (IS_ERR(trans))
- return PTR_ERR(trans);
- goto again;
- }
- return btrfs_commit_transaction(trans);
- }
- /*
- * Make sure any existing dellaloc is flushed for any root used by a send
- * operation so that we do not miss any data and we do not race with writeback
- * finishing and changing a tree while send is using the tree. This could
- * happen if a subvolume is in RW mode, has delalloc, is turned to RO mode and
- * a send operation then uses the subvolume.
- * After flushing delalloc ensure_commit_roots_uptodate() must be called.
- */
- static int flush_delalloc_roots(struct send_ctx *sctx)
- {
- struct btrfs_root *root = sctx->parent_root;
- int ret;
- int i;
- if (root) {
- ret = btrfs_start_delalloc_snapshot(root);
- if (ret)
- return ret;
- btrfs_wait_ordered_extents(root, U64_MAX, 0, U64_MAX);
- }
- for (i = 0; i < sctx->clone_roots_cnt; i++) {
- root = sctx->clone_roots[i].root;
- ret = btrfs_start_delalloc_snapshot(root);
- if (ret)
- return ret;
- btrfs_wait_ordered_extents(root, U64_MAX, 0, U64_MAX);
- }
- return 0;
- }
- static void btrfs_root_dec_send_in_progress(struct btrfs_root* root)
- {
- spin_lock(&root->root_item_lock);
- root->send_in_progress--;
- /*
- * Not much left to do, we don't know why it's unbalanced and
- * can't blindly reset it to 0.
- */
- if (root->send_in_progress < 0)
- btrfs_err(root->fs_info,
- "send_in_progress unbalanced %d root %llu",
- root->send_in_progress, root->root_key.objectid);
- spin_unlock(&root->root_item_lock);
- }
- static void dedupe_in_progress_warn(const struct btrfs_root *root)
- {
- btrfs_warn_rl(root->fs_info,
- "cannot use root %llu for send while deduplications on it are in progress (%d in progress)",
- root->root_key.objectid, root->dedupe_in_progress);
- }
- long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg)
- {
- int ret = 0;
- struct btrfs_root *send_root = BTRFS_I(file_inode(mnt_file))->root;
- struct btrfs_fs_info *fs_info = send_root->fs_info;
- struct btrfs_root *clone_root;
- struct btrfs_key key;
- struct send_ctx *sctx = NULL;
- u32 i;
- u64 *clone_sources_tmp = NULL;
- int clone_sources_to_rollback = 0;
- unsigned alloc_size;
- int sort_clone_roots = 0;
- int index;
- if (!capable(CAP_SYS_ADMIN))
- return -EPERM;
- /*
- * The subvolume must remain read-only during send, protect against
- * making it RW. This also protects against deletion.
- */
- spin_lock(&send_root->root_item_lock);
- if (btrfs_root_readonly(send_root) && send_root->dedupe_in_progress) {
- dedupe_in_progress_warn(send_root);
- spin_unlock(&send_root->root_item_lock);
- return -EAGAIN;
- }
- send_root->send_in_progress++;
- spin_unlock(&send_root->root_item_lock);
- /*
- * Userspace tools do the checks and warn the user if it's
- * not RO.
- */
- if (!btrfs_root_readonly(send_root)) {
- ret = -EPERM;
- goto out;
- }
- /*
- * Check that we don't overflow at later allocations, we request
- * clone_sources_count + 1 items, and compare to unsigned long inside
- * access_ok.
- */
- if (arg->clone_sources_count >
- ULONG_MAX / sizeof(struct clone_root) - 1) {
- ret = -EINVAL;
- goto out;
- }
- if (!access_ok(arg->clone_sources,
- sizeof(*arg->clone_sources) *
- arg->clone_sources_count)) {
- ret = -EFAULT;
- goto out;
- }
- if (arg->flags & ~BTRFS_SEND_FLAG_MASK) {
- ret = -EINVAL;
- goto out;
- }
- sctx = kzalloc(sizeof(struct send_ctx), GFP_KERNEL);
- if (!sctx) {
- ret = -ENOMEM;
- goto out;
- }
- INIT_LIST_HEAD(&sctx->new_refs);
- INIT_LIST_HEAD(&sctx->deleted_refs);
- INIT_RADIX_TREE(&sctx->name_cache, GFP_KERNEL);
- INIT_LIST_HEAD(&sctx->name_cache_list);
- sctx->flags = arg->flags;
- sctx->send_filp = fget(arg->send_fd);
- if (!sctx->send_filp) {
- ret = -EBADF;
- goto out;
- }
- sctx->send_root = send_root;
- /*
- * Unlikely but possible, if the subvolume is marked for deletion but
- * is slow to remove the directory entry, send can still be started
- */
- if (btrfs_root_dead(sctx->send_root)) {
- ret = -EPERM;
- goto out;
- }
- sctx->clone_roots_cnt = arg->clone_sources_count;
- sctx->send_max_size = BTRFS_SEND_BUF_SIZE;
- sctx->send_buf = kvmalloc(sctx->send_max_size, GFP_KERNEL);
- if (!sctx->send_buf) {
- ret = -ENOMEM;
- goto out;
- }
- sctx->read_buf = kvmalloc(BTRFS_SEND_READ_SIZE, GFP_KERNEL);
- if (!sctx->read_buf) {
- ret = -ENOMEM;
- goto out;
- }
- sctx->pending_dir_moves = RB_ROOT;
- sctx->waiting_dir_moves = RB_ROOT;
- sctx->orphan_dirs = RB_ROOT;
- alloc_size = sizeof(struct clone_root) * (arg->clone_sources_count + 1);
- sctx->clone_roots = kvzalloc(alloc_size, GFP_KERNEL);
- if (!sctx->clone_roots) {
- ret = -ENOMEM;
- goto out;
- }
- alloc_size = arg->clone_sources_count * sizeof(*arg->clone_sources);
- if (arg->clone_sources_count) {
- clone_sources_tmp = kvmalloc(alloc_size, GFP_KERNEL);
- if (!clone_sources_tmp) {
- ret = -ENOMEM;
- goto out;
- }
- ret = copy_from_user(clone_sources_tmp, arg->clone_sources,
- alloc_size);
- if (ret) {
- ret = -EFAULT;
- goto out;
- }
- for (i = 0; i < arg->clone_sources_count; i++) {
- key.objectid = clone_sources_tmp[i];
- key.type = BTRFS_ROOT_ITEM_KEY;
- key.offset = (u64)-1;
- index = srcu_read_lock(&fs_info->subvol_srcu);
- clone_root = btrfs_read_fs_root_no_name(fs_info, &key);
- if (IS_ERR(clone_root)) {
- srcu_read_unlock(&fs_info->subvol_srcu, index);
- ret = PTR_ERR(clone_root);
- goto out;
- }
- spin_lock(&clone_root->root_item_lock);
- if (!btrfs_root_readonly(clone_root) ||
- btrfs_root_dead(clone_root)) {
- spin_unlock(&clone_root->root_item_lock);
- srcu_read_unlock(&fs_info->subvol_srcu, index);
- ret = -EPERM;
- goto out;
- }
- if (clone_root->dedupe_in_progress) {
- dedupe_in_progress_warn(clone_root);
- spin_unlock(&clone_root->root_item_lock);
- srcu_read_unlock(&fs_info->subvol_srcu, index);
- ret = -EAGAIN;
- goto out;
- }
- clone_root->send_in_progress++;
- spin_unlock(&clone_root->root_item_lock);
- srcu_read_unlock(&fs_info->subvol_srcu, index);
- sctx->clone_roots[i].root = clone_root;
- clone_sources_to_rollback = i + 1;
- }
- kvfree(clone_sources_tmp);
- clone_sources_tmp = NULL;
- }
- if (arg->parent_root) {
- key.objectid = arg->parent_root;
- key.type = BTRFS_ROOT_ITEM_KEY;
- key.offset = (u64)-1;
- index = srcu_read_lock(&fs_info->subvol_srcu);
- sctx->parent_root = btrfs_read_fs_root_no_name(fs_info, &key);
- if (IS_ERR(sctx->parent_root)) {
- srcu_read_unlock(&fs_info->subvol_srcu, index);
- ret = PTR_ERR(sctx->parent_root);
- goto out;
- }
- spin_lock(&sctx->parent_root->root_item_lock);
- sctx->parent_root->send_in_progress++;
- if (!btrfs_root_readonly(sctx->parent_root) ||
- btrfs_root_dead(sctx->parent_root)) {
- spin_unlock(&sctx->parent_root->root_item_lock);
- srcu_read_unlock(&fs_info->subvol_srcu, index);
- ret = -EPERM;
- goto out;
- }
- if (sctx->parent_root->dedupe_in_progress) {
- dedupe_in_progress_warn(sctx->parent_root);
- spin_unlock(&sctx->parent_root->root_item_lock);
- srcu_read_unlock(&fs_info->subvol_srcu, index);
- ret = -EAGAIN;
- goto out;
- }
- spin_unlock(&sctx->parent_root->root_item_lock);
- srcu_read_unlock(&fs_info->subvol_srcu, index);
- }
- /*
- * Clones from send_root are allowed, but only if the clone source
- * is behind the current send position. This is checked while searching
- * for possible clone sources.
- */
- sctx->clone_roots[sctx->clone_roots_cnt++].root = sctx->send_root;
- /* We do a bsearch later */
- sort(sctx->clone_roots, sctx->clone_roots_cnt,
- sizeof(*sctx->clone_roots), __clone_root_cmp_sort,
- NULL);
- sort_clone_roots = 1;
- ret = flush_delalloc_roots(sctx);
- if (ret)
- goto out;
- ret = ensure_commit_roots_uptodate(sctx);
- if (ret)
- goto out;
- mutex_lock(&fs_info->balance_mutex);
- if (test_bit(BTRFS_FS_BALANCE_RUNNING, &fs_info->flags)) {
- mutex_unlock(&fs_info->balance_mutex);
- btrfs_warn_rl(fs_info,
- "cannot run send because a balance operation is in progress");
- ret = -EAGAIN;
- goto out;
- }
- fs_info->send_in_progress++;
- mutex_unlock(&fs_info->balance_mutex);
- current->journal_info = BTRFS_SEND_TRANS_STUB;
- ret = send_subvol(sctx);
- current->journal_info = NULL;
- mutex_lock(&fs_info->balance_mutex);
- fs_info->send_in_progress--;
- mutex_unlock(&fs_info->balance_mutex);
- if (ret < 0)
- goto out;
- if (!(sctx->flags & BTRFS_SEND_FLAG_OMIT_END_CMD)) {
- ret = begin_cmd(sctx, BTRFS_SEND_C_END);
- if (ret < 0)
- goto out;
- ret = send_cmd(sctx);
- if (ret < 0)
- goto out;
- }
- out:
- WARN_ON(sctx && !ret && !RB_EMPTY_ROOT(&sctx->pending_dir_moves));
- while (sctx && !RB_EMPTY_ROOT(&sctx->pending_dir_moves)) {
- struct rb_node *n;
- struct pending_dir_move *pm;
- n = rb_first(&sctx->pending_dir_moves);
- pm = rb_entry(n, struct pending_dir_move, node);
- while (!list_empty(&pm->list)) {
- struct pending_dir_move *pm2;
- pm2 = list_first_entry(&pm->list,
- struct pending_dir_move, list);
- free_pending_move(sctx, pm2);
- }
- free_pending_move(sctx, pm);
- }
- WARN_ON(sctx && !ret && !RB_EMPTY_ROOT(&sctx->waiting_dir_moves));
- while (sctx && !RB_EMPTY_ROOT(&sctx->waiting_dir_moves)) {
- struct rb_node *n;
- struct waiting_dir_move *dm;
- n = rb_first(&sctx->waiting_dir_moves);
- dm = rb_entry(n, struct waiting_dir_move, node);
- rb_erase(&dm->node, &sctx->waiting_dir_moves);
- kfree(dm);
- }
- WARN_ON(sctx && !ret && !RB_EMPTY_ROOT(&sctx->orphan_dirs));
- while (sctx && !RB_EMPTY_ROOT(&sctx->orphan_dirs)) {
- struct rb_node *n;
- struct orphan_dir_info *odi;
- n = rb_first(&sctx->orphan_dirs);
- odi = rb_entry(n, struct orphan_dir_info, node);
- free_orphan_dir_info(sctx, odi);
- }
- if (sort_clone_roots) {
- for (i = 0; i < sctx->clone_roots_cnt; i++)
- btrfs_root_dec_send_in_progress(
- sctx->clone_roots[i].root);
- } else {
- for (i = 0; sctx && i < clone_sources_to_rollback; i++)
- btrfs_root_dec_send_in_progress(
- sctx->clone_roots[i].root);
- btrfs_root_dec_send_in_progress(send_root);
- }
- if (sctx && !IS_ERR_OR_NULL(sctx->parent_root))
- btrfs_root_dec_send_in_progress(sctx->parent_root);
- kvfree(clone_sources_tmp);
- if (sctx) {
- if (sctx->send_filp)
- fput(sctx->send_filp);
- kvfree(sctx->clone_roots);
- kvfree(sctx->send_buf);
- kvfree(sctx->read_buf);
- name_cache_free(sctx);
- kfree(sctx);
- }
- return ret;
- }
|