12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394959697989910010110210310410510610710810911011111211311411511611711811912012112212312412512612712812913013113213313413513613713813914014114214314414514614714814915015115215315415515615715815916016116216316416516616716816917017117217317417517617717817918018118218318418518618718818919019119219319419519619719819920020120220320420520620720820921021121221321421521621721821922022122222322422522622722822923023123223323423523623723823924024124224324424524624724824925025125225325425525625725825926026126226326426526626726826927027127227327427527627727827928028128228328428528628728828929029129229329429529629729829930030130230330430530630730830931031131231331431531631731831932032132232332432532632732832933033133233333433533633733833934034134234334434534634734834935035135235335435535635735835936036136236336436536636736836937037137237337437537637737837938038138238338438538638738838939039139239339439539639739839940040140240340440540640740840941041141241341441541641741841942042142242342442542642742842943043143243343443543643743843944044144244344444544644744844945045145245345445545645745845946046146246346446546646746846947047147247347447547647747847948048148248348448548648748848949049149249349449549649749849950050150250350450550650750850951051151251351451551651751851952052152252352452552652752852953053153253353453553653753853954054154254354454554654754854955055155255355455555655755855956056156256356456556656756856957057157257357457557657757857958058158258358458558658758858959059159259359459559659759859960060160260360460560660760860961061161261361461561661761861962062162262362462562662762862963063163263363463563663763863964064164264364464564664764864965065165265365465565665765865966066166266366466566666766866967067167267367467567667767867968068168268368468568668768868969069169269369469569669769869970070170270370470570670770870971071171271371471571671771871972072172272372472572672772872973073173273373473573673773873974074174274374474574674774874975075175275375475575675775875976076176276376476576676776876977077177277377477577677777877978078178278378478578678778878979079179279379479579679779879980080180280380480580680780880981081181281381481581681781881982082182282382482582682782882983083183283383483583683783883984084184284384484584684784884985085185285385485585685785885986086186286386486586686786886987087187287387487587687787887988088188288388488588688788888989089189289389489589689789889990090190290390490590690790890991091191291391491591691791891992092192292392492592692792892993093193293393493593693793893994094194294394494594694794894995095195295395495595695795895996096196296396496596696796896997097197297397497597697797897998098198298398498598698798898999099199299399499599699799899910001001100210031004100510061007100810091010101110121013101410151016101710181019102010211022102310241025102610271028102910301031103210331034103510361037103810391040104110421043104410451046104710481049105010511052105310541055105610571058105910601061106210631064106510661067106810691070107110721073107410751076107710781079108010811082108310841085108610871088108910901091109210931094109510961097109810991100110111021103110411051106110711081109111011111112111311141115111611171118111911201121112211231124112511261127112811291130113111321133113411351136113711381139114011411142114311441145114611471148114911501151115211531154115511561157115811591160116111621163116411651166116711681169117011711172117311741175117611771178117911801181118211831184118511861187118811891190119111921193119411951196119711981199120012011202120312041205120612071208120912101211121212131214121512161217121812191220122112221223122412251226122712281229123012311232123312341235123612371238123912401241124212431244124512461247124812491250125112521253125412551256125712581259126012611262126312641265126612671268126912701271127212731274127512761277127812791280128112821283128412851286128712881289129012911292129312941295129612971298129913001301130213031304130513061307130813091310131113121313131413151316131713181319132013211322132313241325132613271328132913301331133213331334133513361337133813391340134113421343134413451346134713481349135013511352135313541355135613571358135913601361136213631364136513661367136813691370137113721373137413751376137713781379138013811382138313841385138613871388138913901391139213931394139513961397139813991400140114021403140414051406140714081409141014111412141314141415141614171418141914201421142214231424142514261427142814291430143114321433143414351436143714381439144014411442144314441445144614471448144914501451145214531454145514561457145814591460146114621463146414651466146714681469147014711472147314741475147614771478147914801481148214831484148514861487148814891490149114921493149414951496149714981499150015011502150315041505150615071508150915101511151215131514151515161517151815191520152115221523152415251526152715281529153015311532153315341535153615371538153915401541154215431544154515461547154815491550155115521553155415551556155715581559156015611562156315641565156615671568156915701571157215731574157515761577157815791580158115821583158415851586158715881589159015911592159315941595159615971598159916001601160216031604160516061607160816091610161116121613161416151616161716181619162016211622162316241625162616271628162916301631163216331634163516361637163816391640164116421643164416451646164716481649165016511652165316541655165616571658165916601661166216631664166516661667166816691670167116721673167416751676167716781679168016811682168316841685168616871688168916901691169216931694169516961697169816991700170117021703170417051706170717081709171017111712171317141715171617171718171917201721172217231724172517261727172817291730173117321733173417351736173717381739174017411742174317441745174617471748174917501751175217531754175517561757175817591760176117621763176417651766176717681769177017711772177317741775177617771778177917801781178217831784178517861787178817891790179117921793179417951796179717981799180018011802180318041805180618071808180918101811181218131814181518161817181818191820182118221823182418251826182718281829183018311832183318341835183618371838183918401841184218431844184518461847184818491850185118521853185418551856185718581859186018611862186318641865186618671868186918701871187218731874187518761877187818791880188118821883188418851886188718881889189018911892189318941895189618971898189919001901190219031904190519061907190819091910191119121913191419151916191719181919192019211922192319241925192619271928192919301931193219331934193519361937193819391940194119421943194419451946194719481949195019511952195319541955195619571958195919601961196219631964196519661967196819691970197119721973197419751976197719781979198019811982198319841985198619871988198919901991199219931994199519961997199819992000200120022003200420052006200720082009201020112012201320142015201620172018201920202021202220232024202520262027202820292030203120322033203420352036203720382039204020412042204320442045204620472048204920502051205220532054205520562057205820592060206120622063206420652066206720682069207020712072207320742075207620772078207920802081208220832084208520862087208820892090209120922093209420952096209720982099210021012102210321042105210621072108210921102111211221132114211521162117211821192120212121222123212421252126212721282129213021312132213321342135213621372138213921402141214221432144214521462147214821492150215121522153215421552156215721582159216021612162216321642165216621672168216921702171217221732174217521762177217821792180218121822183218421852186218721882189219021912192219321942195219621972198219922002201220222032204220522062207220822092210221122122213221422152216221722182219222022212222222322242225222622272228222922302231223222332234223522362237223822392240224122422243224422452246224722482249225022512252225322542255225622572258225922602261226222632264226522662267226822692270227122722273227422752276227722782279228022812282228322842285228622872288228922902291229222932294229522962297229822992300230123022303230423052306230723082309231023112312231323142315231623172318231923202321232223232324232523262327232823292330233123322333233423352336233723382339234023412342234323442345234623472348234923502351235223532354235523562357235823592360236123622363236423652366236723682369237023712372237323742375237623772378237923802381238223832384238523862387238823892390239123922393239423952396239723982399240024012402240324042405240624072408240924102411241224132414241524162417241824192420242124222423242424252426242724282429243024312432243324342435243624372438243924402441244224432444244524462447244824492450245124522453245424552456245724582459246024612462246324642465246624672468246924702471247224732474247524762477247824792480248124822483248424852486248724882489249024912492249324942495249624972498249925002501250225032504250525062507250825092510251125122513251425152516251725182519252025212522252325242525252625272528252925302531253225332534253525362537253825392540254125422543254425452546254725482549255025512552255325542555255625572558255925602561256225632564256525662567256825692570257125722573257425752576257725782579258025812582258325842585258625872588258925902591259225932594259525962597259825992600260126022603260426052606260726082609261026112612261326142615261626172618261926202621262226232624262526262627262826292630263126322633263426352636263726382639264026412642264326442645264626472648264926502651265226532654265526562657265826592660266126622663266426652666266726682669267026712672267326742675267626772678267926802681268226832684268526862687268826892690269126922693269426952696269726982699270027012702270327042705270627072708270927102711271227132714271527162717271827192720272127222723272427252726272727282729273027312732273327342735273627372738273927402741274227432744274527462747274827492750275127522753275427552756275727582759276027612762276327642765276627672768276927702771277227732774277527762777277827792780278127822783278427852786278727882789279027912792279327942795279627972798279928002801280228032804280528062807280828092810281128122813281428152816281728182819282028212822282328242825282628272828282928302831283228332834283528362837283828392840284128422843284428452846284728482849285028512852285328542855285628572858285928602861286228632864286528662867286828692870287128722873287428752876287728782879288028812882288328842885288628872888288928902891289228932894289528962897289828992900290129022903290429052906290729082909291029112912291329142915291629172918291929202921292229232924292529262927292829292930293129322933293429352936293729382939294029412942294329442945294629472948294929502951295229532954295529562957295829592960296129622963296429652966296729682969297029712972297329742975297629772978297929802981298229832984298529862987298829892990299129922993299429952996299729982999300030013002300330043005300630073008300930103011301230133014301530163017301830193020302130223023302430253026302730283029303030313032303330343035303630373038303930403041304230433044304530463047304830493050305130523053305430553056305730583059306030613062306330643065306630673068306930703071307230733074307530763077307830793080308130823083308430853086308730883089309030913092309330943095309630973098309931003101310231033104310531063107310831093110311131123113311431153116311731183119312031213122312331243125312631273128312931303131313231333134313531363137313831393140314131423143314431453146314731483149315031513152315331543155315631573158315931603161316231633164316531663167316831693170317131723173317431753176317731783179318031813182318331843185318631873188318931903191319231933194319531963197319831993200320132023203320432053206320732083209321032113212321332143215321632173218321932203221322232233224322532263227322832293230323132323233323432353236323732383239324032413242324332443245324632473248324932503251325232533254325532563257325832593260326132623263326432653266326732683269327032713272327332743275327632773278327932803281328232833284328532863287328832893290329132923293329432953296329732983299330033013302330333043305330633073308330933103311331233133314331533163317331833193320332133223323332433253326332733283329333033313332333333343335333633373338333933403341334233433344334533463347334833493350335133523353335433553356335733583359336033613362336333643365336633673368336933703371337233733374337533763377337833793380338133823383338433853386338733883389339033913392339333943395339633973398339934003401340234033404340534063407340834093410341134123413341434153416341734183419342034213422342334243425342634273428342934303431343234333434343534363437343834393440344134423443344434453446344734483449345034513452345334543455345634573458345934603461346234633464346534663467346834693470347134723473347434753476347734783479348034813482348334843485348634873488348934903491349234933494349534963497349834993500350135023503350435053506350735083509351035113512351335143515351635173518351935203521352235233524352535263527352835293530353135323533353435353536353735383539354035413542354335443545354635473548354935503551355235533554355535563557355835593560356135623563356435653566356735683569357035713572357335743575357635773578357935803581358235833584358535863587358835893590359135923593359435953596359735983599360036013602360336043605360636073608360936103611361236133614361536163617361836193620362136223623362436253626362736283629363036313632363336343635363636373638363936403641364236433644364536463647364836493650365136523653365436553656365736583659366036613662366336643665366636673668366936703671367236733674367536763677367836793680368136823683368436853686368736883689369036913692369336943695369636973698369937003701370237033704370537063707370837093710371137123713371437153716371737183719372037213722372337243725372637273728372937303731373237333734373537363737373837393740374137423743374437453746374737483749375037513752375337543755375637573758375937603761376237633764376537663767376837693770377137723773377437753776377737783779378037813782378337843785378637873788378937903791379237933794379537963797379837993800380138023803380438053806380738083809381038113812381338143815381638173818381938203821382238233824382538263827382838293830383138323833383438353836383738383839384038413842384338443845384638473848384938503851385238533854385538563857385838593860386138623863386438653866386738683869387038713872387338743875387638773878387938803881388238833884388538863887388838893890389138923893389438953896389738983899390039013902390339043905390639073908390939103911391239133914391539163917391839193920392139223923392439253926392739283929393039313932393339343935393639373938393939403941394239433944394539463947394839493950395139523953395439553956395739583959396039613962396339643965396639673968396939703971397239733974397539763977397839793980398139823983398439853986398739883989399039913992399339943995399639973998399940004001400240034004400540064007400840094010401140124013401440154016401740184019402040214022402340244025402640274028402940304031403240334034403540364037403840394040404140424043404440454046404740484049405040514052405340544055405640574058405940604061406240634064406540664067406840694070407140724073407440754076407740784079408040814082408340844085408640874088408940904091409240934094409540964097409840994100410141024103410441054106410741084109411041114112411341144115411641174118411941204121412241234124412541264127412841294130413141324133413441354136413741384139414041414142414341444145414641474148414941504151415241534154415541564157415841594160416141624163416441654166416741684169417041714172417341744175417641774178417941804181418241834184418541864187418841894190419141924193419441954196419741984199420042014202420342044205420642074208420942104211421242134214421542164217421842194220422142224223422442254226422742284229423042314232423342344235423642374238423942404241424242434244424542464247424842494250425142524253425442554256425742584259426042614262426342644265426642674268426942704271427242734274427542764277427842794280428142824283428442854286428742884289429042914292429342944295429642974298429943004301430243034304430543064307430843094310431143124313431443154316431743184319432043214322432343244325432643274328432943304331433243334334433543364337433843394340434143424343434443454346434743484349435043514352435343544355435643574358435943604361436243634364436543664367436843694370437143724373437443754376437743784379438043814382438343844385438643874388438943904391439243934394439543964397439843994400440144024403440444054406440744084409441044114412441344144415441644174418441944204421442244234424442544264427442844294430443144324433443444354436443744384439444044414442444344444445444644474448444944504451445244534454445544564457445844594460446144624463446444654466446744684469447044714472447344744475447644774478447944804481448244834484448544864487448844894490449144924493449444954496449744984499450045014502450345044505450645074508450945104511451245134514451545164517451845194520452145224523452445254526452745284529453045314532453345344535453645374538453945404541454245434544454545464547454845494550455145524553455445554556455745584559456045614562456345644565456645674568456945704571457245734574457545764577457845794580458145824583458445854586458745884589459045914592459345944595459645974598459946004601460246034604460546064607460846094610461146124613461446154616461746184619462046214622462346244625462646274628462946304631463246334634463546364637463846394640464146424643464446454646464746484649465046514652465346544655465646574658465946604661466246634664466546664667466846694670467146724673467446754676467746784679468046814682468346844685468646874688468946904691469246934694469546964697469846994700470147024703470447054706470747084709471047114712471347144715471647174718471947204721472247234724472547264727472847294730473147324733473447354736473747384739474047414742474347444745474647474748474947504751475247534754475547564757475847594760476147624763476447654766476747684769477047714772477347744775477647774778477947804781478247834784478547864787478847894790479147924793479447954796479747984799480048014802480348044805480648074808480948104811481248134814481548164817481848194820482148224823482448254826482748284829483048314832483348344835483648374838483948404841484248434844484548464847484848494850485148524853485448554856485748584859486048614862486348644865486648674868486948704871487248734874487548764877487848794880488148824883488448854886488748884889489048914892489348944895489648974898489949004901490249034904490549064907490849094910491149124913491449154916491749184919492049214922492349244925492649274928492949304931493249334934493549364937493849394940494149424943494449454946494749484949495049514952495349544955495649574958495949604961496249634964496549664967496849694970497149724973497449754976497749784979498049814982498349844985498649874988498949904991499249934994499549964997499849995000500150025003500450055006500750085009501050115012501350145015501650175018501950205021502250235024502550265027502850295030503150325033503450355036503750385039504050415042504350445045504650475048504950505051505250535054505550565057505850595060506150625063506450655066506750685069507050715072507350745075507650775078507950805081508250835084508550865087508850895090509150925093509450955096509750985099510051015102510351045105510651075108510951105111511251135114511551165117511851195120512151225123512451255126512751285129513051315132513351345135513651375138513951405141514251435144514551465147514851495150515151525153515451555156515751585159516051615162516351645165516651675168516951705171517251735174517551765177517851795180518151825183518451855186518751885189519051915192519351945195519651975198519952005201520252035204520552065207520852095210521152125213521452155216521752185219522052215222522352245225522652275228522952305231523252335234523552365237523852395240524152425243524452455246524752485249525052515252525352545255525652575258525952605261526252635264526552665267526852695270527152725273527452755276527752785279528052815282528352845285528652875288528952905291529252935294529552965297529852995300530153025303530453055306530753085309531053115312531353145315531653175318531953205321532253235324532553265327532853295330533153325333533453355336533753385339534053415342534353445345534653475348534953505351535253535354535553565357535853595360536153625363536453655366536753685369537053715372537353745375537653775378537953805381538253835384538553865387538853895390539153925393539453955396539753985399540054015402540354045405540654075408540954105411541254135414541554165417541854195420542154225423542454255426542754285429543054315432543354345435543654375438543954405441544254435444544554465447544854495450545154525453545454555456545754585459546054615462546354645465546654675468546954705471547254735474547554765477547854795480548154825483548454855486548754885489549054915492549354945495549654975498549955005501550255035504550555065507550855095510551155125513551455155516551755185519552055215522552355245525552655275528552955305531553255335534553555365537553855395540554155425543554455455546554755485549555055515552555355545555555655575558555955605561556255635564556555665567556855695570557155725573557455755576557755785579558055815582558355845585558655875588558955905591559255935594559555965597559855995600560156025603560456055606560756085609561056115612561356145615561656175618561956205621562256235624562556265627562856295630563156325633563456355636563756385639564056415642564356445645564656475648564956505651565256535654565556565657565856595660566156625663566456655666566756685669567056715672567356745675567656775678567956805681568256835684568556865687568856895690569156925693569456955696569756985699570057015702570357045705570657075708570957105711571257135714571557165717571857195720572157225723572457255726572757285729573057315732573357345735573657375738573957405741574257435744574557465747574857495750575157525753575457555756575757585759576057615762576357645765576657675768576957705771577257735774577557765777577857795780578157825783578457855786578757885789579057915792579357945795579657975798579958005801580258035804580558065807580858095810581158125813581458155816581758185819582058215822582358245825582658275828582958305831583258335834583558365837583858395840584158425843584458455846584758485849585058515852585358545855585658575858585958605861586258635864586558665867586858695870587158725873587458755876587758785879588058815882588358845885588658875888588958905891589258935894589558965897589858995900590159025903590459055906590759085909591059115912591359145915591659175918591959205921592259235924592559265927592859295930593159325933593459355936593759385939594059415942594359445945594659475948594959505951595259535954595559565957595859595960596159625963596459655966596759685969597059715972597359745975597659775978597959805981598259835984598559865987598859895990599159925993599459955996599759985999600060016002600360046005600660076008600960106011601260136014601560166017601860196020602160226023602460256026602760286029603060316032603360346035603660376038603960406041604260436044604560466047604860496050605160526053605460556056605760586059606060616062606360646065606660676068606960706071607260736074607560766077607860796080608160826083608460856086608760886089609060916092609360946095609660976098609961006101610261036104610561066107610861096110611161126113611461156116611761186119612061216122612361246125612661276128612961306131613261336134613561366137613861396140614161426143614461456146614761486149615061516152615361546155615661576158615961606161616261636164616561666167616861696170617161726173617461756176617761786179618061816182618361846185618661876188618961906191619261936194619561966197619861996200620162026203620462056206620762086209621062116212621362146215621662176218621962206221622262236224622562266227622862296230623162326233623462356236623762386239624062416242624362446245624662476248624962506251625262536254625562566257625862596260626162626263626462656266626762686269627062716272627362746275627662776278627962806281628262836284628562866287628862896290629162926293629462956296629762986299630063016302630363046305630663076308630963106311631263136314631563166317631863196320632163226323632463256326632763286329633063316332633363346335633663376338633963406341634263436344634563466347634863496350635163526353635463556356635763586359636063616362636363646365636663676368636963706371637263736374637563766377637863796380638163826383638463856386638763886389639063916392639363946395639663976398639964006401640264036404640564066407640864096410641164126413641464156416641764186419642064216422642364246425642664276428642964306431643264336434643564366437643864396440644164426443644464456446644764486449645064516452645364546455645664576458645964606461646264636464646564666467646864696470647164726473647464756476647764786479648064816482648364846485648664876488648964906491649264936494649564966497// SPDX-License-Identifier: GPL-2.0
/*
 * INET		An implementation of the TCP/IP protocol suite for the LINUX
 *		operating system.  INET is implemented using the  BSD Socket
 *		interface as the means of communication with the user level.
 *
 *		Implementation of the Transmission Control Protocol(TCP).
 *
 * Authors:	Ross Biro
 *		Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
 *		Mark Evans, <evansmp@uhura.aston.ac.uk>
 *		Corey Minyard <wf-rch!minyard@relay.EU.net>
 *		Florian La Roche, <flla@stud.uni-sb.de>
 *		Charles Hedrick, <hedrick@klinzhai.rutgers.edu>
 *		Linus Torvalds, <torvalds@cs.helsinki.fi>
 *		Alan Cox, <gw4pts@gw4pts.ampr.org>
 *		Matthew Dillon, <dillon@apollo.west.oic.com>
 *		Arnt Gulbrandsen, <agulbra@nvg.unit.no>
 *		Jorge Cwik, <jorge@laser.satlink.net>
 */

/*
 * Changes:
 *		Pedro Roque	:	Fast Retransmit/Recovery.
 *					Two receive queues.
 *					Retransmit queue handled by TCP.
 *					Better retransmit timer handling.
 *					New congestion avoidance.
 *					Header prediction.
 *					Variable renaming.
 *
 *		Eric		:	Fast Retransmit.
 *		Randy Scott	:	MSS option defines.
 *		Eric Schenk	:	Fixes to slow start algorithm.
 *		Eric Schenk	:	Yet another double ACK bug.
 *		Eric Schenk	:	Delayed ACK bug fixes.
 *		Eric Schenk	:	Floyd style fast retrans war avoidance.
 *		David S. Miller	:	Don't allow zero congestion window.
 *		Eric Schenk	:	Fix retransmitter so that it sends
 *					next packet on ack of previous packet.
 *		Andi Kleen	:	Moved open_request checking here
 *					and process RSTs for open_requests.
 *		Andi Kleen	:	Better prune_queue, and other fixes.
 *		Andrey Savochkin:	Fix RTT measurements in the presence of
 *					timestamps.
 *		Andrey Savochkin:	Check sequence numbers correctly when
 *					removing SACKs due to in sequence incoming
 *					data segments.
 *		Andi Kleen:		Make sure we never ack data there is not
 *					enough room for. Also make this condition
 *					a fatal error if it might still happen.
 *		Andi Kleen:		Add tcp_measure_rcv_mss to make
 *					connections with MSS<min(MTU,ann. MSS)
 *					work without delayed acks.
 *		Andi Kleen:		Process packets with PSH set in the
 *					fast path.
 *		J Hadi Salim:		ECN support
 *	 	Andrei Gurtov,
 *		Pasi Sarolahti,
 *		Panu Kuhlberg:		Experimental audit of TCP (re)transmission
 *					engine. Lots of bugs are found.
 *		Pasi Sarolahti:		F-RTO for dealing with spurious RTOs
 */

#define pr_fmt(fmt) "TCP: " fmt

#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/sysctl.h>
#include <linux/kernel.h>
#include <linux/prefetch.h>
#include <net/dst.h>
#include <net/tcp.h>
#include <net/inet_common.h>
#include <linux/ipsec.h>
#include <asm/unaligned.h>
#include <linux/errqueue.h>
#include <trace/events/tcp.h>
#include <linux/static_key.h>

int sysctl_tcp_max_orphans __read_mostly = NR_FILE;

#define FLAG_DATA		0x01 /* Incoming frame contained data.		*/
#define FLAG_WIN_UPDATE		0x02 /* Incoming ACK was a window update.	*/
#define FLAG_DATA_ACKED		0x04 /* This ACK acknowledged new data.		*/
#define FLAG_RETRANS_DATA_ACKED	0x08 /* "" "" some of which was retransmitted.	*/
#define FLAG_SYN_ACKED		0x10 /* This ACK acknowledged SYN.		*/
#define FLAG_DATA_SACKED	0x20 /* New SACK.				*/
#define FLAG_ECE		0x40 /* ECE in this ACK				*/
#define FLAG_LOST_RETRANS	0x80 /* This ACK marks some retransmission lost */
#define FLAG_SLOWPATH		0x100 /* Do not skip RFC checks for window update.*/
#define FLAG_ORIG_SACK_ACKED	0x200 /* Never retransmitted data are (s)acked	*/
#define FLAG_SND_UNA_ADVANCED	0x400 /* Snd_una was changed (!= FLAG_DATA_ACKED) */
#define FLAG_DSACKING_ACK	0x800 /* SACK blocks contained D-SACK info */
#define FLAG_SET_XMIT_TIMER	0x1000 /* Set TLP or RTO timer */
#define FLAG_SACK_RENEGING	0x2000 /* snd_una advanced to a sacked seq */
#define FLAG_UPDATE_TS_RECENT	0x4000 /* tcp_replace_ts_recent() */
#define FLAG_NO_CHALLENGE_ACK	0x8000 /* do not call tcp_send_challenge_ack()	*/
#define FLAG_ACK_MAYBE_DELAYED	0x10000 /* Likely a delayed ACK */

#define FLAG_ACKED		(FLAG_DATA_ACKED|FLAG_SYN_ACKED)
#define FLAG_NOT_DUP		(FLAG_DATA|FLAG_WIN_UPDATE|FLAG_ACKED)
#define FLAG_CA_ALERT		(FLAG_DATA_SACKED|FLAG_ECE|FLAG_DSACKING_ACK)
#define FLAG_FORWARD_PROGRESS	(FLAG_ACKED|FLAG_DATA_SACKED)

#define TCP_REMNANT (TCP_FLAG_FIN|TCP_FLAG_URG|TCP_FLAG_SYN|TCP_FLAG_PSH)
#define TCP_HP_BITS (~(TCP_RESERVED_BITS|TCP_FLAG_PSH))

#define REXMIT_NONE	0 /* no loss recovery to do */
#define REXMIT_LOST	1 /* retransmit packets marked lost */
#define REXMIT_NEW	2 /* FRTO-style transmit of unsent/new packets */

#if IS_ENABLED(CONFIG_TLS_DEVICE)
static DEFINE_STATIC_KEY_FALSE(clean_acked_data_enabled);

void clean_acked_data_enable(struct inet_connection_sock *icsk,
			     void (*cad)(struct sock *sk, u32 ack_seq))
{
	icsk->icsk_clean_acked = cad;
	static_branch_inc(&clean_acked_data_enabled);
}
EXPORT_SYMBOL_GPL(clean_acked_data_enable);

void clean_acked_data_disable(struct inet_connection_sock *icsk)
{
	static_branch_dec(&clean_acked_data_enabled);
	icsk->icsk_clean_acked = NULL;
}
EXPORT_SYMBOL_GPL(clean_acked_data_disable);
#endif

static void tcp_gro_dev_warn(struct sock *sk, const struct sk_buff *skb,
			     unsigned int len)
{
	static bool __once __read_mostly;

	if (!__once) {
		struct net_device *dev;

		__once = true;

		rcu_read_lock();
		dev = dev_get_by_index_rcu(sock_net(sk), skb->skb_iif);
		if (!dev || len >= dev->mtu)
			pr_warn("%s: Driver has suspect GRO implementation, TCP performance may be compromised.\n",
				dev ? dev->name : "Unknown driver");
		rcu_read_unlock();
	}
}

/* Adapt the MSS value used to make delayed ack decision to the
 * real world.
 */
static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb)
{
	struct inet_connection_sock *icsk = inet_csk(sk);
	const unsigned int lss = icsk->icsk_ack.last_seg_size;
	unsigned int len;

	icsk->icsk_ack.last_seg_size = 0;

	/* skb->len may jitter because of SACKs, even if peer
	 * sends good full-sized frames.
	 */
	len = skb_shinfo(skb)->gso_size ? : skb->len;
	if (len >= icsk->icsk_ack.rcv_mss) {
		icsk->icsk_ack.rcv_mss = min_t(unsigned int, len,
					       tcp_sk(sk)->advmss);
		/* Account for possibly-removed options */
		if (unlikely(len > icsk->icsk_ack.rcv_mss +
				   MAX_TCP_OPTION_SPACE))
			tcp_gro_dev_warn(sk, skb, len);
	} else {
		/* Otherwise, we make more careful check taking into account,
		 * that SACKs block is variable.
		 *
		 * "len" is invariant segment length, including TCP header.
		 */
		len += skb->data - skb_transport_header(skb);
		if (len >= TCP_MSS_DEFAULT + sizeof(struct tcphdr) ||
		    /* If PSH is not set, packet should be
		     * full sized, provided peer TCP is not badly broken.
		     * This observation (if it is correct 8)) allows
		     * to handle super-low mtu links fairly.
		     */
		    (len >= TCP_MIN_MSS + sizeof(struct tcphdr) &&
		     !(tcp_flag_word(tcp_hdr(skb)) & TCP_REMNANT))) {
			/* Subtract also invariant (if peer is RFC compliant),
			 * tcp header plus fixed timestamp option length.
			 * Resulting "len" is MSS free of SACK jitter.
			 */
			len -= tcp_sk(sk)->tcp_header_len;
			icsk->icsk_ack.last_seg_size = len;
			if (len == lss) {
				icsk->icsk_ack.rcv_mss = len;
				return;
			}
		}
		if (icsk->icsk_ack.pending & ICSK_ACK_PUSHED)
			icsk->icsk_ack.pending |= ICSK_ACK_PUSHED2;
		icsk->icsk_ack.pending |= ICSK_ACK_PUSHED;
	}
}

static void tcp_incr_quickack(struct sock *sk, unsigned int max_quickacks)
{
	struct inet_connection_sock *icsk = inet_csk(sk);
	unsigned int quickacks = tcp_sk(sk)->rcv_wnd / (2 * icsk->icsk_ack.rcv_mss);

	if (quickacks == 0)
		quickacks = 2;
	quickacks = min(quickacks, max_quickacks);
	if (quickacks > icsk->icsk_ack.quick)
		icsk->icsk_ack.quick = quickacks;
}

void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks)
{
	struct inet_connection_sock *icsk = inet_csk(sk);

	tcp_incr_quickack(sk, max_quickacks);
	icsk->icsk_ack.pingpong = 0;
	icsk->icsk_ack.ato = TCP_ATO_MIN;
}
EXPORT_SYMBOL(tcp_enter_quickack_mode);

/* Send ACKs quickly, if "quick" count is not exhausted
 * and the session is not interactive.
 */

static bool tcp_in_quickack_mode(struct sock *sk)
{
	const struct inet_connection_sock *icsk = inet_csk(sk);
	const struct dst_entry *dst = __sk_dst_get(sk);

	return (dst && dst_metric(dst, RTAX_QUICKACK)) ||
		(icsk->icsk_ack.quick && !icsk->icsk_ack.pingpong);
}

static void tcp_ecn_queue_cwr(struct tcp_sock *tp)
{
	if (tp->ecn_flags & TCP_ECN_OK)
		tp->ecn_flags |= TCP_ECN_QUEUE_CWR;
}

static void tcp_ecn_accept_cwr(struct tcp_sock *tp, const struct sk_buff *skb)
{
	if (tcp_hdr(skb)->cwr) {
		tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;

		/* If the sender is telling us it has entered CWR, then its
		 * cwnd may be very low (even just 1 packet), so we should ACK
		 * immediately.
		 */
		tcp_enter_quickack_mode((struct sock *)tp, 2);
	}
}

static void tcp_ecn_withdraw_cwr(struct tcp_sock *tp)
{
	tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
}

static void __tcp_ecn_check_ce(struct sock *sk, const struct sk_buff *skb)
{
	struct tcp_sock *tp = tcp_sk(sk);

	switch (TCP_SKB_CB(skb)->ip_dsfield & INET_ECN_MASK) {
	case INET_ECN_NOT_ECT:
		/* Funny extension: if ECT is not set on a segment,
		 * and we already seen ECT on a previous segment,
		 * it is probably a retransmit.
		 */
		if (tp->ecn_flags & TCP_ECN_SEEN)
			tcp_enter_quickack_mode(sk, 2);
		break;
	case INET_ECN_CE:
		if (tcp_ca_needs_ecn(sk))
			tcp_ca_event(sk, CA_EVENT_ECN_IS_CE);

		if (!(tp->ecn_flags & TCP_ECN_DEMAND_CWR)) {
			/* Better not delay acks, sender can have a very low cwnd */
			tcp_enter_quickack_mode(sk, 2);
			tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
		}
		tp->ecn_flags |= TCP_ECN_SEEN;
		break;
	default:
		if (tcp_ca_needs_ecn(sk))
			tcp_ca_event(sk, CA_EVENT_ECN_NO_CE);
		tp->ecn_flags |= TCP_ECN_SEEN;
		break;
	}
}

static void tcp_ecn_check_ce(struct sock *sk, const struct sk_buff *skb)
{
	if (tcp_sk(sk)->ecn_flags & TCP_ECN_OK)
		__tcp_ecn_check_ce(sk, skb);
}

static void tcp_ecn_rcv_synack(struct tcp_sock *tp, const struct tcphdr *th)
{
	if ((tp->ecn_flags & TCP_ECN_OK) && (!th->ece || th->cwr))
		tp->ecn_flags &= ~TCP_ECN_OK;
}

static void tcp_ecn_rcv_syn(struct tcp_sock *tp, const struct tcphdr *th)
{
	if ((tp->ecn_flags & TCP_ECN_OK) && (!th->ece || !th->cwr))
		tp->ecn_flags &= ~TCP_ECN_OK;
}

static bool tcp_ecn_rcv_ecn_echo(const struct tcp_sock *tp, const struct tcphdr *th)
{
	if (th->ece && !th->syn && (tp->ecn_flags & TCP_ECN_OK))
		return true;
	return false;
}

/* Buffer size and advertised window tuning.
 *
 * 1. Tuning sk->sk_sndbuf, when connection enters established state.
 */

static void tcp_sndbuf_expand(struct sock *sk)
{
	const struct tcp_sock *tp = tcp_sk(sk);
	const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops;
	int sndmem, per_mss;
	u32 nr_segs;

	/* Worst case is non GSO/TSO : each frame consumes one skb
	 * and skb->head is kmalloced using power of two area of memory
	 */
	per_mss = max_t(u32, tp->rx_opt.mss_clamp, tp->mss_cache) +
		  MAX_TCP_HEADER +
		  SKB_DATA_ALIGN(sizeof(struct skb_shared_info));

	per_mss = roundup_pow_of_two(per_mss) +
		  SKB_DATA_ALIGN(sizeof(struct sk_buff));

	nr_segs = max_t(u32, TCP_INIT_CWND, tp->snd_cwnd);
	nr_segs = max_t(u32, nr_segs, tp->reordering + 1);

	/* Fast Recovery (RFC 5681 3.2) :
	 * Cubic needs 1.7 factor, rounded to 2 to include
	 * extra cushion (application might react slowly to EPOLLOUT)
	 */
	sndmem = ca_ops->sndbuf_expand ? ca_ops->sndbuf_expand(sk) : 2;
	sndmem *= nr_segs * per_mss;

	if (sk->sk_sndbuf < sndmem)
		sk->sk_sndbuf = min(sndmem, sock_net(sk)->ipv4.sysctl_tcp_wmem[2]);
}

/* 2. Tuning advertised window (window_clamp, rcv_ssthresh)
 *
 * All tcp_full_space() is split to two parts: "network" buffer, allocated
 * forward and advertised in receiver window (tp->rcv_wnd) and
 * "application buffer", required to isolate scheduling/application
 * latencies from network.
 * window_clamp is maximal advertised window. It can be less than
 * tcp_full_space(), in this case tcp_full_space() - window_clamp
 * is reserved for "application" buffer. The less window_clamp is
 * the smoother our behaviour from viewpoint of network, but the lower
 * throughput and the higher sensitivity of the connection to losses. 8)
 *
 * rcv_ssthresh is more strict window_clamp used at "slow start"
 * phase to predict further behaviour of this connection.
 * It is used for two goals:
 * - to enforce header prediction at sender, even when application
 *   requires some significant "application buffer". It is check #1.
 * - to prevent pruning of receive queue because of misprediction
 *   of receiver window. Check #2.
 *
 * The scheme does not work when sender sends good segments opening
 * window and then starts to feed us spaghetti. But it should work
 * in common situations. Otherwise, we have to rely on queue collapsing.
 */

/* Slow part of check#2. */
static int __tcp_grow_window(const struct sock *sk, const struct sk_buff *skb)
{
	struct tcp_sock *tp = tcp_sk(sk);
	/* Optimize this! */
	int truesize = tcp_win_from_space(sk, skb->truesize) >> 1;
	int window = tcp_win_from_space(sk, sock_net(sk)->ipv4.sysctl_tcp_rmem[2]) >> 1;

	while (tp->rcv_ssthresh <= window) {
		if (truesize <= skb->len)
			return 2 * inet_csk(sk)->icsk_ack.rcv_mss;

		truesize >>= 1;
		window >>= 1;
	}
	return 0;
}

static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb)
{
	struct tcp_sock *tp = tcp_sk(sk);

	/* Check #1 */
	if (tp->rcv_ssthresh < tp->window_clamp &&
	    (int)tp->rcv_ssthresh < tcp_space(sk) &&
	    !tcp_under_memory_pressure(sk)) {
		int incr;

		/* Check #2. Increase window, if skb with such overhead
		 * will fit to rcvbuf in future.
		 */
		if (tcp_win_from_space(sk, skb->truesize) <= skb->len)
			incr = 2 * tp->advmss;
		else
			incr = __tcp_grow_window(sk, skb);

		if (incr) {
			incr = max_t(int, incr, 2 * skb->len);
			tp->rcv_ssthresh = min(tp->rcv_ssthresh + incr,
					       tp->window_clamp);
			inet_csk(sk)->icsk_ack.quick |= 1;
		}
	}
}

/* 3. Tuning rcvbuf, when connection enters established state. */
static void tcp_fixup_rcvbuf(struct sock *sk)
{
	u32 mss = tcp_sk(sk)->advmss;
	int rcvmem;

	rcvmem = 2 * SKB_TRUESIZE(mss + MAX_TCP_HEADER) *
		 tcp_default_init_rwnd(mss);

	/* Dynamic Right Sizing (DRS) has 2 to 3 RTT latency
	 * Allow enough cushion so that sender is not limited by our window
	 */
	if (sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf)
		rcvmem <<= 2;

	if (sk->sk_rcvbuf < rcvmem)
		sk->sk_rcvbuf = min(rcvmem, sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
}

/* 4. Try to fixup all. It is made immediately after connection enters
 *    established state.
 */
void tcp_init_buffer_space(struct sock *sk)
{
	int tcp_app_win = sock_net(sk)->ipv4.sysctl_tcp_app_win;
	struct tcp_sock *tp = tcp_sk(sk);
	int maxwin;

	if (!(sk->sk_userlocks & SOCK_RCVBUF_LOCK))
		tcp_fixup_rcvbuf(sk);
	if (!(sk->sk_userlocks & SOCK_SNDBUF_LOCK))
		tcp_sndbuf_expand(sk);

	tp->rcvq_space.space = tp->rcv_wnd;
	tcp_mstamp_refresh(tp);
	tp->rcvq_space.time = tp->tcp_mstamp;
	tp->rcvq_space.seq = tp->copied_seq;

	maxwin = tcp_full_space(sk);

	if (tp->window_clamp >= maxwin) {
		tp->window_clamp = maxwin;

		if (tcp_app_win && maxwin > 4 * tp->advmss)
			tp->window_clamp = max(maxwin -
					       (maxwin >> tcp_app_win),
					       4 * tp->advmss);
	}

	/* Force reservation of one segment. */
	if (tcp_app_win &&
	    tp->window_clamp > 2 * tp->advmss &&
	    tp->window_clamp + tp->advmss > maxwin)
		tp->window_clamp = max(2 * tp->advmss, maxwin - tp->advmss);

	tp->rcv_ssthresh = min(tp->rcv_ssthresh, tp->window_clamp);
	tp->snd_cwnd_stamp = tcp_jiffies32;
}

/* 5. Recalculate window clamp after socket hit its memory bounds. */
static void tcp_clamp_window(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct inet_connection_sock *icsk = inet_csk(sk);
	struct net *net = sock_net(sk);

	icsk->icsk_ack.quick = 0;

	if (sk->sk_rcvbuf < net->ipv4.sysctl_tcp_rmem[2] &&
	    !(sk->sk_userlocks & SOCK_RCVBUF_LOCK) &&
	    !tcp_under_memory_pressure(sk) &&
	    sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)) {
		sk->sk_rcvbuf = min(atomic_read(&sk->sk_rmem_alloc),
				    net->ipv4.sysctl_tcp_rmem[2]);
	}
	if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf)
		tp->rcv_ssthresh = min(tp->window_clamp, 2U * tp->advmss);
}

/* Initialize RCV_MSS value.
 * RCV_MSS is an our guess about MSS used by the peer.
 * We haven't any direct information about the MSS.
 * It's better to underestimate the RCV_MSS rather than overestimate.
 * Overestimations make us ACKing less frequently than needed.
 * Underestimations are more easy to detect and fix by tcp_measure_rcv_mss().
 */
void tcp_initialize_rcv_mss(struct sock *sk)
{
	const struct tcp_sock *tp = tcp_sk(sk);
	unsigned int hint = min_t(unsigned int, tp->advmss, tp->mss_cache);

	hint = min(hint, tp->rcv_wnd / 2);
	hint = min(hint, TCP_MSS_DEFAULT);
	hint = max(hint, TCP_MIN_MSS);

	inet_csk(sk)->icsk_ack.rcv_mss = hint;
}
EXPORT_SYMBOL(tcp_initialize_rcv_mss);

/* Receiver "autotuning" code.
 *
 * The algorithm for RTT estimation w/o timestamps is based on
 * Dynamic Right-Sizing (DRS) by Wu Feng and Mike Fisk of LANL.
 * <http://public.lanl.gov/radiant/pubs.html#DRS>
 *
 * More detail on this code can be found at
 * <http://staff.psc.edu/jheffner/>,
 * though this reference is out of date.  A new paper
 * is pending.
 */
static void tcp_rcv_rtt_update(struct tcp_sock *tp, u32 sample, int win_dep)
{
	u32 new_sample = tp->rcv_rtt_est.rtt_us;
	long m = sample;

	if (new_sample != 0) {
		/* If we sample in larger samples in the non-timestamp
		 * case, we could grossly overestimate the RTT especially
		 * with chatty applications or bulk transfer apps which
		 * are stalled on filesystem I/O.
		 *
		 * Also, since we are only going for a minimum in the
		 * non-timestamp case, we do not smooth things out
		 * else with timestamps disabled convergence takes too
		 * long.
		 */
		if (!win_dep) {
			m -= (new_sample >> 3);
			new_sample += m;
		} else {
			m <<= 3;
			if (m < new_sample)
				new_sample = m;
		}
	} else {
		/* No previous measure. */
		new_sample = m << 3;
	}

	tp->rcv_rtt_est.rtt_us = new_sample;
}

static inline void tcp_rcv_rtt_measure(struct tcp_sock *tp)
{
	u32 delta_us;

	if (tp->rcv_rtt_est.time == 0)
		goto new_measure;
	if (before(tp->rcv_nxt, tp->rcv_rtt_est.seq))
		return;
	delta_us = tcp_stamp_us_delta(tp->tcp_mstamp, tp->rcv_rtt_est.time);
	if (!delta_us)
		delta_us = 1;
	tcp_rcv_rtt_update(tp, delta_us, 1);

new_measure:
	tp->rcv_rtt_est.seq = tp->rcv_nxt + tp->rcv_wnd;
	tp->rcv_rtt_est.time = tp->tcp_mstamp;
}

static inline void tcp_rcv_rtt_measure_ts(struct sock *sk,
					  const struct sk_buff *skb)
{
	struct tcp_sock *tp = tcp_sk(sk);

	if (tp->rx_opt.rcv_tsecr &&
	    (TCP_SKB_CB(skb)->end_seq -
	     TCP_SKB_CB(skb)->seq >= inet_csk(sk)->icsk_ack.rcv_mss)) {
		u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr;
		u32 delta_us;

		if (!delta)
			delta = 1;
		delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ);
		tcp_rcv_rtt_update(tp, delta_us, 0);
	}
}

/*
 * This function should be called every time data is copied to user space.
 * It calculates the appropriate TCP receive buffer space.
 */
void tcp_rcv_space_adjust(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);
	u32 copied;
	int time;

	trace_tcp_rcv_space_adjust(sk);

	tcp_mstamp_refresh(tp);
	time = tcp_stamp_us_delta(tp->tcp_mstamp, tp->rcvq_space.time);
	if (time < (tp->rcv_rtt_est.rtt_us >> 3) || tp->rcv_rtt_est.rtt_us == 0)
		return;

	/* Number of bytes copied to user in last RTT */
	copied = tp->copied_seq - tp->rcvq_space.seq;
	if (copied <= tp->rcvq_space.space)
		goto new_measure;

	/* A bit of theory :
	 * copied = bytes received in previous RTT, our base window
	 * To cope with packet losses, we need a 2x factor
	 * To cope with slow start, and sender growing its cwin by 100 %
	 * every RTT, we need a 4x factor, because the ACK we are sending
	 * now is for the next RTT, not the current one :
	 * <prev RTT . ><current RTT .. ><next RTT .... >
	 */

	if (sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf &&
	    !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
		int rcvmem, rcvbuf;
		u64 rcvwin, grow;

		/* minimal window to cope with packet losses, assuming
		 * steady state. Add some cushion because of small variations.
		 */
		rcvwin = ((u64)copied << 1) + 16 * tp->advmss;

		/* Accommodate for sender rate increase (eg. slow start) */
		grow = rcvwin * (copied - tp->rcvq_space.space);
		do_div(grow, tp->rcvq_space.space);
		rcvwin += (grow << 1);

		rcvmem = SKB_TRUESIZE(tp->advmss + MAX_TCP_HEADER);
		while (tcp_win_from_space(sk, rcvmem) < tp->advmss)
			rcvmem += 128;

		do_div(rcvwin, tp->advmss);
		rcvbuf = min_t(u64, rcvwin * rcvmem,
			       sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
		if (rcvbuf > sk->sk_rcvbuf) {
			sk->sk_rcvbuf = rcvbuf;

			/* Make the window clamp follow along.  */
			tp->window_clamp = tcp_win_from_space(sk, rcvbuf);
		}
	}
	tp->rcvq_space.space = copied;

new_measure:
	tp->rcvq_space.seq = tp->copied_seq;
	tp->rcvq_space.time = tp->tcp_mstamp;
}

/* There is something which you must keep in mind when you analyze the
 * behavior of the tp->ato delayed ack timeout interval.  When a
 * connection starts up, we want to ack as quickly as possible.  The
 * problem is that "good" TCP's do slow start at the beginning of data
 * transmission.  The means that until we send the first few ACK's the
 * sender will sit on his end and only queue most of his data, because
 * he can only send snd_cwnd unacked packets at any given time.  For
 * each ACK we send, he increments snd_cwnd and transmits more of his
 * queue.  -DaveM
 */
static void tcp_event_data_recv(struct sock *sk, struct sk_buff *skb)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct inet_connection_sock *icsk = inet_csk(sk);
	u32 now;

	inet_csk_schedule_ack(sk);

	tcp_measure_rcv_mss(sk, skb);

	tcp_rcv_rtt_measure(tp);

	now = tcp_jiffies32;

	if (!icsk->icsk_ack.ato) {
		/* The _first_ data packet received, initialize
		 * delayed ACK engine.
		 */
		tcp_incr_quickack(sk, TCP_MAX_QUICKACKS);
		icsk->icsk_ack.ato = TCP_ATO_MIN;
	} else {
		int m = now - icsk->icsk_ack.lrcvtime;

		if (m <= TCP_ATO_MIN / 2) {
			/* The fastest case is the first. */
			icsk->icsk_ack.ato = (icsk->icsk_ack.ato >> 1) + TCP_ATO_MIN / 2;
		} else if (m < icsk->icsk_ack.ato) {
			icsk->icsk_ack.ato = (icsk->icsk_ack.ato >> 1) + m;
			if (icsk->icsk_ack.ato > icsk->icsk_rto)
				icsk->icsk_ack.ato = icsk->icsk_rto;
		} else if (m > icsk->icsk_rto) {
			/* Too long gap. Apparently sender failed to
			 * restart window, so that we send ACKs quickly.
			 */
			tcp_incr_quickack(sk, TCP_MAX_QUICKACKS);
			sk_mem_reclaim(sk);
		}
	}
	icsk->icsk_ack.lrcvtime = now;

	tcp_ecn_check_ce(sk, skb);

	if (skb->len >= 128)
		tcp_grow_window(sk, skb);
}

/* Called to compute a smoothed rtt estimate. The data fed to this
 * routine either comes from timestamps, or from segments that were
 * known _not_ to have been retransmitted [see Karn/Partridge
 * Proceedings SIGCOMM 87]. The algorithm is from the SIGCOMM 88
 * piece by Van Jacobson.
 * NOTE: the next three routines used to be one big routine.
 * To save cycles in the RFC 1323 implementation it was better to break
 * it up into three procedures. -- erics
 */
static void tcp_rtt_estimator(struct sock *sk, long mrtt_us)
{
	struct tcp_sock *tp = tcp_sk(sk);
	long m = mrtt_us; /* RTT */
	u32 srtt = tp->srtt_us;

	/*	The following amusing code comes from Jacobson's
	 *	article in SIGCOMM '88.  Note that rtt and mdev
	 *	are scaled versions of rtt and mean deviation.
	 *	This is designed to be as fast as possible
	 *	m stands for "measurement".
	 *
	 *	On a 1990 paper the rto value is changed to:
	 *	RTO = rtt + 4 * mdev
	 *
	 * Funny. This algorithm seems to be very broken.
	 * These formulae increase RTO, when it should be decreased, increase
	 * too slowly, when it should be increased quickly, decrease too quickly
	 * etc. I guess in BSD RTO takes ONE value, so that it is absolutely
	 * does not matter how to _calculate_ it. Seems, it was trap
	 * that VJ failed to avoid. 8)
	 */
	if (srtt != 0) {
		m -= (srtt >> 3);	/* m is now error in rtt est */
		srtt += m;		/* rtt = 7/8 rtt + 1/8 new */
		if (m < 0) {
			m = -m;		/* m is now abs(error) */
			m -= (tp->mdev_us >> 2);   /* similar update on mdev */
			/* This is similar to one of Eifel findings.
			 * Eifel blocks mdev updates when rtt decreases.
			 * This solution is a bit different: we use finer gain
			 * for mdev in this case (alpha*beta).
			 * Like Eifel it also prevents growth of rto,
			 * but also it limits too fast rto decreases,
			 * happening in pure Eifel.
			 */
			if (m > 0)
				m >>= 3;
		} else {
			m -= (tp->mdev_us >> 2);   /* similar update on mdev */
		}
		tp->mdev_us += m;		/* mdev = 3/4 mdev + 1/4 new */
		if (tp->mdev_us > tp->mdev_max_us) {
			tp->mdev_max_us = tp->mdev_us;
			if (tp->mdev_max_us > tp->rttvar_us)
				tp->rttvar_us = tp->mdev_max_us;
		}
		if (after(tp->snd_una, tp->rtt_seq)) {
			if (tp->mdev_max_us < tp->rttvar_us)
				tp->rttvar_us -= (tp->rttvar_us - tp->mdev_max_us) >> 2;
			tp->rtt_seq = tp->snd_nxt;
			tp->mdev_max_us = tcp_rto_min_us(sk);
		}
	} else {
		/* no previous measure. */
		srtt = m << 3;		/* take the measured time to be rtt */
		tp->mdev_us = m << 1;	/* make sure rto = 3*rtt */
		tp->rttvar_us = max(tp->mdev_us, tcp_rto_min_us(sk));
		tp->mdev_max_us = tp->rttvar_us;
		tp->rtt_seq = tp->snd_nxt;
	}
	tp->srtt_us = max(1U, srtt);
}

static void tcp_update_pacing_rate(struct sock *sk)
{
	const struct tcp_sock *tp = tcp_sk(sk);
	u64 rate;

	/* set sk_pacing_rate to 200 % of current rate (mss * cwnd / srtt) */
	rate = (u64)tp->mss_cache * ((USEC_PER_SEC / 100) << 3);

	/* current rate is (cwnd * mss) / srtt
	 * In Slow Start [1], set sk_pacing_rate to 200 % the current rate.
	 * In Congestion Avoidance phase, set it to 120 % the current rate.
	 *
	 * [1] : Normal Slow Start condition is (tp->snd_cwnd < tp->snd_ssthresh)
	 *	 If snd_cwnd >= (tp->snd_ssthresh / 2), we are approaching
	 *	 end of slow start and should slow down.
	 */
	if (tp->snd_cwnd < tp->snd_ssthresh / 2)
		rate *= sock_net(sk)->ipv4.sysctl_tcp_pacing_ss_ratio;
	else
		rate *= sock_net(sk)->ipv4.sysctl_tcp_pacing_ca_ratio;

	rate *= max(tp->snd_cwnd, tp->packets_out);

	if (likely(tp->srtt_us))
		do_div(rate, tp->srtt_us);

	/* WRITE_ONCE() is needed because sch_fq fetches sk_pacing_rate
	 * without any lock. We want to make sure compiler wont store
	 * intermediate values in this location.
	 */
	WRITE_ONCE(sk->sk_pacing_rate, min_t(u64, rate,
					     sk->sk_max_pacing_rate));
}

/* Calculate rto without backoff.  This is the second half of Van Jacobson's
 * routine referred to above.
 */
static void tcp_set_rto(struct sock *sk)
{
	const struct tcp_sock *tp = tcp_sk(sk);
	/* Old crap is replaced with new one. 8)
	 *
	 * More seriously:
	 * 1. If rtt variance happened to be less 50msec, it is hallucination.
	 *    It cannot be less due to utterly erratic ACK generation made
	 *    at least by solaris and freebsd. "Erratic ACKs" has _nothing_
	 *    to do with delayed acks, because at cwnd>2 true delack timeout
	 *    is invisible. Actually, Linux-2.4 also generates erratic
	 *    ACKs in some circumstances.
	 */
	inet_csk(sk)->icsk_rto = __tcp_set_rto(tp);

	/* 2. Fixups made earlier cannot be right.
	 *    If we do not estimate RTO correctly without them,
	 *    all the algo is pure shit and should be replaced
	 *    with correct one. It is exactly, which we pretend to do.
	 */

	/* NOTE: clamping at TCP_RTO_MIN is not required, current algo
	 * guarantees that rto is higher.
	 */
	tcp_bound_rto(sk);
}

__u32 tcp_init_cwnd(const struct tcp_sock *tp, const struct dst_entry *dst)
{
	__u32 cwnd = (dst ? dst_metric(dst, RTAX_INITCWND) : 0);

	if (!cwnd)
		cwnd = TCP_INIT_CWND;
	return min_t(__u32, cwnd, tp->snd_cwnd_clamp);
}

/* Take a notice that peer is sending D-SACKs */
static void tcp_dsack_seen(struct tcp_sock *tp)
{
	tp->rx_opt.sack_ok |= TCP_DSACK_SEEN;
	tp->rack.dsack_seen = 1;
}

/* It's reordering when higher sequence was delivered (i.e. sacked) before
 * some lower never-retransmitted sequence ("low_seq"). The maximum reordering
 * distance is approximated in full-mss packet distance ("reordering").
 */
static void tcp_check_sack_reordering(struct sock *sk, const u32 low_seq,
				      const int ts)
{
	struct tcp_sock *tp = tcp_sk(sk);
	const u32 mss = tp->mss_cache;
	u32 fack, metric;

	fack = tcp_highest_sack_seq(tp);
	if (!before(low_seq, fack))
		return;

	metric = fack - low_seq;
	if ((metric > tp->reordering * mss) && mss) {
#if FASTRETRANS_DEBUG > 1
		pr_debug("Disorder%d %d %u f%u s%u rr%d\n",
			 tp->rx_opt.sack_ok, inet_csk(sk)->icsk_ca_state,
			 tp->reordering,
			 0,
			 tp->sacked_out,
			 tp->undo_marker ? tp->undo_retrans : 0);
#endif
		tp->reordering = min_t(u32, (metric + mss - 1) / mss,
				       sock_net(sk)->ipv4.sysctl_tcp_max_reordering);
	}

	tp->rack.reord = 1;
	/* This exciting event is worth to be remembered. 8) */
	NET_INC_STATS(sock_net(sk),
		      ts ? LINUX_MIB_TCPTSREORDER : LINUX_MIB_TCPSACKREORDER);
}

/* This must be called before lost_out is incremented */
static void tcp_verify_retransmit_hint(struct tcp_sock *tp, struct sk_buff *skb)
{
	if (!tp->retransmit_skb_hint ||
	    before(TCP_SKB_CB(skb)->seq,
		   TCP_SKB_CB(tp->retransmit_skb_hint)->seq))
		tp->retransmit_skb_hint = skb;
}

/* Sum the number of packets on the wire we have marked as lost.
 * There are two cases we care about here:
 * a) Packet hasn't been marked lost (nor retransmitted),
 *    and this is the first loss.
 * b) Packet has been marked both lost and retransmitted,
 *    and this means we think it was lost again.
 */
static void tcp_sum_lost(struct tcp_sock *tp, struct sk_buff *skb)
{
	__u8 sacked = TCP_SKB_CB(skb)->sacked;

	if (!(sacked & TCPCB_LOST) ||
	    ((sacked & TCPCB_LOST) && (sacked & TCPCB_SACKED_RETRANS)))
		tp->lost += tcp_skb_pcount(skb);
}

static void tcp_skb_mark_lost(struct tcp_sock *tp, struct sk_buff *skb)
{
	if (!(TCP_SKB_CB(skb)->sacked & (TCPCB_LOST|TCPCB_SACKED_ACKED))) {
		tcp_verify_retransmit_hint(tp, skb);

		tp->lost_out += tcp_skb_pcount(skb);
		tcp_sum_lost(tp, skb);
		TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
	}
}

void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, struct sk_buff *skb)
{
	tcp_verify_retransmit_hint(tp, skb);

	tcp_sum_lost(tp, skb);
	if (!(TCP_SKB_CB(skb)->sacked & (TCPCB_LOST|TCPCB_SACKED_ACKED))) {
		tp->lost_out += tcp_skb_pcount(skb);
		TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
	}
}

/* This procedure tags the retransmission queue when SACKs arrive.
 *
 * We have three tag bits: SACKED(S), RETRANS(R) and LOST(L).
 * Packets in queue with these bits set are counted in variables
 * sacked_out, retrans_out and lost_out, correspondingly.
 *
 * Valid combinations are:
 * Tag  InFlight	Description
 * 0	1		- orig segment is in flight.
 * S	0		- nothing flies, orig reached receiver.
 * L	0		- nothing flies, orig lost by net.
 * R	2		- both orig and retransmit are in flight.
 * L|R	1		- orig is lost, retransmit is in flight.
 * S|R  1		- orig reached receiver, retrans is still in flight.
 * (L|S|R is logically valid, it could occur when L|R is sacked,
 *  but it is equivalent to plain S and code short-curcuits it to S.
 *  L|S is logically invalid, it would mean -1 packet in flight 8))
 *
 * These 6 states form finite state machine, controlled by the following events:
 * 1. New ACK (+SACK) arrives. (tcp_sacktag_write_queue())
 * 2. Retransmission. (tcp_retransmit_skb(), tcp_xmit_retransmit_queue())
 * 3. Loss detection event of two flavors:
 *	A. Scoreboard estimator decided the packet is lost.
 *	   A'. Reno "three dupacks" marks head of queue lost.
 *	B. SACK arrives sacking SND.NXT at the moment, when the
 *	   segment was retransmitted.
 * 4. D-SACK added new rule: D-SACK changes any tag to S.
 *
 * It is pleasant to note, that state diagram turns out to be commutative,
 * so that we are allowed not to be bothered by order of our actions,
 * when multiple events arrive simultaneously. (see the function below).
 *
 * Reordering detection.
 * --------------------
 * Reordering metric is maximal distance, which a packet can be displaced
 * in packet stream. With SACKs we can estimate it:
 *
 * 1. SACK fills old hole and the corresponding segment was not
 *    ever retransmitted -> reordering. Alas, we cannot use it
 *    when segment was retransmitted.
 * 2. The last flaw is solved with D-SACK. D-SACK arrives
 *    for retransmitted and already SACKed segment -> reordering..
 * Both of these heuristics are not used in Loss state, when we cannot
 * account for retransmits accurately.
 *
 * SACK block validation.
 * ----------------------
 *
 * SACK block range validation checks that the received SACK block fits to
 * the expected sequence limits, i.e., it is between SND.UNA and SND.NXT.
 * Note that SND.UNA is not included to the range though being valid because
 * it means that the receiver is rather inconsistent with itself reporting
 * SACK reneging when it should advance SND.UNA. Such SACK block this is
 * perfectly valid, however, in light of RFC2018 which explicitly states
 * that "SACK block MUST reflect the newest segment.  Even if the newest
 * segment is going to be discarded ...", not that it looks very clever
 * in case of head skb. Due to potentional receiver driven attacks, we
 * choose to avoid immediate execution of a walk in write queue due to
 * reneging and defer head skb's loss recovery to standard loss recovery
 * procedure that will eventually trigger (nothing forbids us doing this).
 *
 * Implements also blockage to start_seq wrap-around. Problem lies in the
 * fact that though start_seq (s) is before end_seq (i.e., not reversed),
 * there's no guarantee that it will be before snd_nxt (n). The problem
 * happens when start_seq resides between end_seq wrap (e_w) and snd_nxt
 * wrap (s_w):
 *
 *         <- outs wnd ->                          <- wrapzone ->
 *         u     e      n                         u_w   e_w  s n_w
 *         |     |      |                          |     |   |  |
 * |<------------+------+----- TCP seqno space --------------+---------->|
 * ...-- <2^31 ->|                                           |<--------...
 * ...---- >2^31 ------>|                                    |<--------...
 *
 * Current code wouldn't be vulnerable but it's better still to discard such
 * crazy SACK blocks. Doing this check for start_seq alone closes somewhat
 * similar case (end_seq after snd_nxt wrap) as earlier reversed check in
 * snd_nxt wrap -> snd_una region will then become "well defined", i.e.,
 * equal to the ideal case (infinite seqno space without wrap caused issues).
 *
 * With D-SACK the lower bound is extended to cover sequence space below
 * SND.UNA down to undo_marker, which is the last point of interest. Yet
 * again, D-SACK block must not to go across snd_una (for the same reason as
 * for the normal SACK blocks, explained above). But there all simplicity
 * ends, TCP might receive valid D-SACKs below that. As long as they reside
 * fully below undo_marker they do not affect behavior in anyway and can
 * therefore be safely ignored. In rare cases (which are more or less
 * theoretical ones), the D-SACK will nicely cross that boundary due to skb
 * fragmentation and packet reordering past skb's retransmission. To consider
 * them correctly, the acceptable range must be extended even more though
 * the exact amount is rather hard to quantify. However, tp->max_window can
 * be used as an exaggerated estimate.
 */
static bool tcp_is_sackblock_valid(struct tcp_sock *tp, bool is_dsack,
				   u32 start_seq, u32 end_seq)
{
	/* Too far in future, or reversed (interpretation is ambiguous) */
	if (after(end_seq, tp->snd_nxt) || !before(start_seq, end_seq))
		return false;

	/* Nasty start_seq wrap-around check (see comments above) */
	if (!before(start_seq, tp->snd_nxt))
		return false;

	/* In outstanding window? ...This is valid exit for D-SACKs too.
	 * start_seq == snd_una is non-sensical (see comments above)
	 */
	if (after(start_seq, tp->snd_una))
		return true;

	if (!is_dsack || !tp->undo_marker)
		return false;

	/* ...Then it's D-SACK, and must reside below snd_una completely */
	if (after(end_seq, tp->snd_una))
		return false;

	if (!before(start_seq, tp->undo_marker))
		return true;

	/* Too old */
	if (!after(end_seq, tp->undo_marker))
		return false;

	/* Undo_marker boundary crossing (overestimates a lot). Known already:
	 *   start_seq < undo_marker and end_seq >= undo_marker.
	 */
	return !before(start_seq, end_seq - tp->max_window);
}

static bool tcp_check_dsack(struct sock *sk, const struct sk_buff *ack_skb,
			    struct tcp_sack_block_wire *sp, int num_sacks,
			    u32 prior_snd_una)
{
	struct tcp_sock *tp = tcp_sk(sk);
	u32 start_seq_0 = get_unaligned_be32(&sp[0].start_seq);
	u32 end_seq_0 = get_unaligned_be32(&sp[0].end_seq);
	bool dup_sack = false;

	if (before(start_seq_0, TCP_SKB_CB(ack_skb)->ack_seq)) {
		dup_sack = true;
		tcp_dsack_seen(tp);
		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPDSACKRECV);
	} else if (num_sacks > 1) {
		u32 end_seq_1 = get_unaligned_be32(&sp[1].end_seq);
		u32 start_seq_1 = get_unaligned_be32(&sp[1].start_seq);

		if (!after(end_seq_0, end_seq_1) &&
		    !before(start_seq_0, start_seq_1)) {
			dup_sack = true;
			tcp_dsack_seen(tp);
			NET_INC_STATS(sock_net(sk),
					LINUX_MIB_TCPDSACKOFORECV);
		}
	}

	/* D-SACK for already forgotten data... Do dumb counting. */
	if (dup_sack && tp->undo_marker && tp->undo_retrans > 0 &&
	    !after(end_seq_0, prior_snd_una) &&
	    after(end_seq_0, tp->undo_marker))
		tp->undo_retrans--;

	return dup_sack;
}

struct tcp_sacktag_state {
	u32	reord;
	/* Timestamps for earliest and latest never-retransmitted segment
	 * that was SACKed. RTO needs the earliest RTT to stay conservative,
	 * but congestion control should still get an accurate delay signal.
	 */
	u64	first_sackt;
	u64	last_sackt;
	struct rate_sample *rate;
	int	flag;
	unsigned int mss_now;
};

/* Check if skb is fully within the SACK block. In presence of GSO skbs,
 * the incoming SACK may not exactly match but we can find smaller MSS
 * aligned portion of it that matches. Therefore we might need to fragment
 * which may fail and creates some hassle (caller must handle error case
 * returns).
 *
 * FIXME: this could be merged to shift decision code
 */
static int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb,
				  u32 start_seq, u32 end_seq)
{
	int err;
	bool in_sack;
	unsigned int pkt_len;
	unsigned int mss;

	in_sack = !after(start_seq, TCP_SKB_CB(skb)->seq) &&
		  !before(end_seq, TCP_SKB_CB(skb)->end_seq);

	if (tcp_skb_pcount(skb) > 1 && !in_sack &&
	    after(TCP_SKB_CB(skb)->end_seq, start_seq)) {
		mss = tcp_skb_mss(skb);
		in_sack = !after(start_seq, TCP_SKB_CB(skb)->seq);

		if (!in_sack) {
			pkt_len = start_seq - TCP_SKB_CB(skb)->seq;
			if (pkt_len < mss)
				pkt_len = mss;
		} else {
			pkt_len = end_seq - TCP_SKB_CB(skb)->seq;
			if (pkt_len < mss)
				return -EINVAL;
		}

		/* Round if necessary so that SACKs cover only full MSSes
		 * and/or the remaining small portion (if present)
		 */
		if (pkt_len > mss) {
			unsigned int new_len = (pkt_len / mss) * mss;
			if (!in_sack && new_len < pkt_len)
				new_len += mss;
			pkt_len = new_len;
		}

		if (pkt_len >= skb->len && !in_sack)
			return 0;

		err = tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb,
				   pkt_len, mss, GFP_ATOMIC);
		if (err < 0)
			return err;
	}

	return in_sack;
}

/* Mark the given newly-SACKed range as such, adjusting counters and hints. */
static u8 tcp_sacktag_one(struct sock *sk,
			  struct tcp_sacktag_state *state, u8 sacked,
			  u32 start_seq, u32 end_seq,
			  int dup_sack, int pcount,
			  u64 xmit_time)
{
	struct tcp_sock *tp = tcp_sk(sk);

	/* Account D-SACK for retransmitted packet. */
	if (dup_sack && (sacked & TCPCB_RETRANS)) {
		if (tp->undo_marker && tp->undo_retrans > 0 &&
		    after(end_seq, tp->undo_marker))
			tp->undo_retrans--;
		if ((sacked & TCPCB_SACKED_ACKED) &&
		    before(start_seq, state->reord))
				state->reord = start_seq;
	}

	/* Nothing to do; acked frame is about to be dropped (was ACKed). */
	if (!after(end_seq, tp->snd_una))
		return sacked;

	if (!(sacked & TCPCB_SACKED_ACKED)) {
		tcp_rack_advance(tp, sacked, end_seq, xmit_time);

		if (sacked & TCPCB_SACKED_RETRANS) {
			/* If the segment is not tagged as lost,
			 * we do not clear RETRANS, believing
			 * that retransmission is still in flight.
			 */
			if (sacked & TCPCB_LOST) {
				sacked &= ~(TCPCB_LOST|TCPCB_SACKED_RETRANS);
				tp->lost_out -= pcount;
				tp->retrans_out -= pcount;
			}
		} else {
			if (!(sacked & TCPCB_RETRANS)) {
				/* New sack for not retransmitted frame,
				 * which was in hole. It is reordering.
				 */
				if (before(start_seq,
					   tcp_highest_sack_seq(tp)) &&
				    before(start_seq, state->reord))
					state->reord = start_seq;

				if (!after(end_seq, tp->high_seq))
					state->flag |= FLAG_ORIG_SACK_ACKED;
				if (state->first_sackt == 0)
					state->first_sackt = xmit_time;
				state->last_sackt = xmit_time;
			}

			if (sacked & TCPCB_LOST) {
				sacked &= ~TCPCB_LOST;
				tp->lost_out -= pcount;
			}
		}

		sacked |= TCPCB_SACKED_ACKED;
		state->flag |= FLAG_DATA_SACKED;
		tp->sacked_out += pcount;
		tp->delivered += pcount;  /* Out-of-order packets delivered */

		/* Lost marker hint past SACKed? Tweak RFC3517 cnt */
		if (tp->lost_skb_hint &&
		    before(start_seq, TCP_SKB_CB(tp->lost_skb_hint)->seq))
			tp->lost_cnt_hint += pcount;
	}

	/* D-SACK. We can detect redundant retransmission in S|R and plain R
	 * frames and clear it. undo_retrans is decreased above, L|R frames
	 * are accounted above as well.
	 */
	if (dup_sack && (sacked & TCPCB_SACKED_RETRANS)) {
		sacked &= ~TCPCB_SACKED_RETRANS;
		tp->retrans_out -= pcount;
	}

	return sacked;
}

/* Shift newly-SACKed bytes from this skb to the immediately previous
 * already-SACKed sk_buff. Mark the newly-SACKed bytes as such.
 */
static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *prev,
			    struct sk_buff *skb,
			    struct tcp_sacktag_state *state,
			    unsigned int pcount, int shifted, int mss,
			    bool dup_sack)
{
	struct tcp_sock *tp = tcp_sk(sk);
	u32 start_seq = TCP_SKB_CB(skb)->seq;	/* start of newly-SACKed */
	u32 end_seq = start_seq + shifted;	/* end of newly-SACKed */

	BUG_ON(!pcount);

	/* Adjust counters and hints for the newly sacked sequence
	 * range but discard the return value since prev is already
	 * marked. We must tag the range first because the seq
	 * advancement below implicitly advances
	 * tcp_highest_sack_seq() when skb is highest_sack.
	 */
	tcp_sacktag_one(sk, state, TCP_SKB_CB(skb)->sacked,
			start_seq, end_seq, dup_sack, pcount,
			skb->skb_mstamp);
	tcp_rate_skb_delivered(sk, skb, state->rate);

	if (skb == tp->lost_skb_hint)
		tp->lost_cnt_hint += pcount;

	TCP_SKB_CB(prev)->end_seq += shifted;
	TCP_SKB_CB(skb)->seq += shifted;

	tcp_skb_pcount_add(prev, pcount);
	BUG_ON(tcp_skb_pcount(skb) < pcount);
	tcp_skb_pcount_add(skb, -pcount);

	/* When we're adding to gso_segs == 1, gso_size will be zero,
	 * in theory this shouldn't be necessary but as long as DSACK
	 * code can come after this skb later on it's better to keep
	 * setting gso_size to something.
	 */
	if (!TCP_SKB_CB(prev)->tcp_gso_size)
		TCP_SKB_CB(prev)->tcp_gso_size = mss;

	/* CHECKME: To clear or not to clear? Mimics normal skb currently */
	if (tcp_skb_pcount(skb) <= 1)
		TCP_SKB_CB(skb)->tcp_gso_size = 0;

	/* Difference in this won't matter, both ACKed by the same cumul. ACK */
	TCP_SKB_CB(prev)->sacked |= (TCP_SKB_CB(skb)->sacked & TCPCB_EVER_RETRANS);

	if (skb->len > 0) {
		BUG_ON(!tcp_skb_pcount(skb));
		NET_INC_STATS(sock_net(sk), LINUX_MIB_SACKSHIFTED);
		return false;
	}

	/* Whole SKB was eaten :-) */

	if (skb == tp->retransmit_skb_hint)
		tp->retransmit_skb_hint = prev;
	if (skb == tp->lost_skb_hint) {
		tp->lost_skb_hint = prev;
		tp->lost_cnt_hint -= tcp_skb_pcount(prev);
	}

	TCP_SKB_CB(prev)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags;
	TCP_SKB_CB(prev)->eor = TCP_SKB_CB(skb)->eor;
	if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
		TCP_SKB_CB(prev)->end_seq++;

	if (skb == tcp_highest_sack(sk))
		tcp_advance_highest_sack(sk, skb);

	tcp_skb_collapse_tstamp(prev, skb);
	if (unlikely(TCP_SKB_CB(prev)->tx.delivered_mstamp))
		TCP_SKB_CB(prev)->tx.delivered_mstamp = 0;

	tcp_rtx_queue_unlink_and_free(skb, sk);

	NET_INC_STATS(sock_net(sk), LINUX_MIB_SACKMERGED);

	return true;
}

/* I wish gso_size would have a bit more sane initialization than
 * something-or-zero which complicates things
 */
static int tcp_skb_seglen(const struct sk_buff *skb)
{
	return tcp_skb_pcount(skb) == 1 ? skb->len : tcp_skb_mss(skb);
}

/* Shifting pages past head area doesn't work */
static int skb_can_shift(const struct sk_buff *skb)
{
	return !skb_headlen(skb) && skb_is_nonlinear(skb);
}

/* Try collapsing SACK blocks spanning across multiple skbs to a single
 * skb.
 */
static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb,
					  struct tcp_sacktag_state *state,
					  u32 start_seq, u32 end_seq,
					  bool dup_sack)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct sk_buff *prev;
	int mss;
	int pcount = 0;
	int len;
	int in_sack;

	/* Normally R but no L won't result in plain S */
	if (!dup_sack &&
	    (TCP_SKB_CB(skb)->sacked & (TCPCB_LOST|TCPCB_SACKED_RETRANS)) == TCPCB_SACKED_RETRANS)
		goto fallback;
	if (!skb_can_shift(skb))
		goto fallback;
	/* This frame is about to be dropped (was ACKed). */
	if (!after(TCP_SKB_CB(skb)->end_seq, tp->snd_una))
		goto fallback;

	/* Can only happen with delayed DSACK + discard craziness */
	prev = skb_rb_prev(skb);
	if (!prev)
		goto fallback;

	if ((TCP_SKB_CB(prev)->sacked & TCPCB_TAGBITS) != TCPCB_SACKED_ACKED)
		goto fallback;

	if (!tcp_skb_can_collapse_to(prev))
		goto fallback;

	in_sack = !after(start_seq, TCP_SKB_CB(skb)->seq) &&
		  !before(end_seq, TCP_SKB_CB(skb)->end_seq);

	if (in_sack) {
		len = skb->len;
		pcount = tcp_skb_pcount(skb);
		mss = tcp_skb_seglen(skb);

		/* TODO: Fix DSACKs to not fragment already SACKed and we can
		 * drop this restriction as unnecessary
		 */
		if (mss != tcp_skb_seglen(prev))
			goto fallback;
	} else {
		if (!after(TCP_SKB_CB(skb)->end_seq, start_seq))
			goto noop;
		/* CHECKME: This is non-MSS split case only?, this will
		 * cause skipped skbs due to advancing loop btw, original
		 * has that feature too
		 */
		if (tcp_skb_pcount(skb) <= 1)
			goto noop;

		in_sack = !after(start_seq, TCP_SKB_CB(skb)->seq);
		if (!in_sack) {
			/* TODO: head merge to next could be attempted here
			 * if (!after(TCP_SKB_CB(skb)->end_seq, end_seq)),
			 * though it might not be worth of the additional hassle
			 *
			 * ...we can probably just fallback to what was done
			 * previously. We could try merging non-SACKed ones
			 * as well but it probably isn't going to buy off
			 * because later SACKs might again split them, and
			 * it would make skb timestamp tracking considerably
			 * harder problem.
			 */
			goto fallback;
		}

		len = end_seq - TCP_SKB_CB(skb)->seq;
		BUG_ON(len < 0);
		BUG_ON(len > skb->len);

		/* MSS boundaries should be honoured or else pcount will
		 * severely break even though it makes things bit trickier.
		 * Optimize common case to avoid most of the divides
		 */
		mss = tcp_skb_mss(skb);

		/* TODO: Fix DSACKs to not fragment already SACKed and we can
		 * drop this restriction as unnecessary
		 */
		if (mss != tcp_skb_seglen(prev))
			goto fallback;

		if (len == mss) {
			pcount = 1;
		} else if (len < mss) {
			goto noop;
		} else {
			pcount = len / mss;
			len = pcount * mss;
		}
	}

	/* tcp_sacktag_one() won't SACK-tag ranges below snd_una */
	if (!after(TCP_SKB_CB(skb)->seq + len, tp->snd_una))
		goto fallback;

	if (!skb_shift(prev, skb, len))
		goto fallback;
	if (!tcp_shifted_skb(sk, prev, skb, state, pcount, len, mss, dup_sack))
		goto out;

	/* Hole filled allows collapsing with the next as well, this is very
	 * useful when hole on every nth skb pattern happens
	 */
	skb = skb_rb_next(prev);
	if (!skb)
		goto out;

	if (!skb_can_shift(skb) ||
	    ((TCP_SKB_CB(skb)->sacked & TCPCB_TAGBITS) != TCPCB_SACKED_ACKED) ||
	    (mss != tcp_skb_seglen(skb)))
		goto out;

	len = skb->len;
	if (skb_shift(prev, skb, len)) {
		pcount += tcp_skb_pcount(skb);
		tcp_shifted_skb(sk, prev, skb, state, tcp_skb_pcount(skb),
				len, mss, 0);
	}

out:
	return prev;

noop:
	return skb;

fallback:
	NET_INC_STATS(sock_net(sk), LINUX_MIB_SACKSHIFTFALLBACK);
	return NULL;
}

static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk,
					struct tcp_sack_block *next_dup,
					struct tcp_sacktag_state *state,
					u32 start_seq, u32 end_seq,
					bool dup_sack_in)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct sk_buff *tmp;

	skb_rbtree_walk_from(skb) {
		int in_sack = 0;
		bool dup_sack = dup_sack_in;

		/* queue is in-order => we can short-circuit the walk early */
		if (!before(TCP_SKB_CB(skb)->seq, end_seq))
			break;

		if (next_dup  &&
		    before(TCP_SKB_CB(skb)->seq, next_dup->end_seq)) {
			in_sack = tcp_match_skb_to_sack(sk, skb,
							next_dup->start_seq,
							next_dup->end_seq);
			if (in_sack > 0)
				dup_sack = true;
		}

		/* skb reference here is a bit tricky to get right, since
		 * shifting can eat and free both this skb and the next,
		 * so not even _safe variant of the loop is enough.
		 */
		if (in_sack <= 0) {
			tmp = tcp_shift_skb_data(sk, skb, state,
						 start_seq, end_seq, dup_sack);
			if (tmp) {
				if (tmp != skb) {
					skb = tmp;
					continue;
				}

				in_sack = 0;
			} else {
				in_sack = tcp_match_skb_to_sack(sk, skb,
								start_seq,
								end_seq);
			}
		}

		if (unlikely(in_sack < 0))
			break;

		if (in_sack) {
			TCP_SKB_CB(skb)->sacked =
				tcp_sacktag_one(sk,
						state,
						TCP_SKB_CB(skb)->sacked,
						TCP_SKB_CB(skb)->seq,
						TCP_SKB_CB(skb)->end_seq,
						dup_sack,
						tcp_skb_pcount(skb),
						skb->skb_mstamp);
			tcp_rate_skb_delivered(sk, skb, state->rate);
			if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)
				list_del_init(&skb->tcp_tsorted_anchor);

			if (!before(TCP_SKB_CB(skb)->seq,
				    tcp_highest_sack_seq(tp)))
				tcp_advance_highest_sack(sk, skb);
		}
	}
	return skb;
}

static struct sk_buff *tcp_sacktag_bsearch(struct sock *sk,
					   struct tcp_sacktag_state *state,
					   u32 seq)
{
	struct rb_node *parent, **p = &sk->tcp_rtx_queue.rb_node;
	struct sk_buff *skb;

	while (*p) {
		parent = *p;
		skb = rb_to_skb(parent);
		if (before(seq, TCP_SKB_CB(skb)->seq)) {
			p = &parent->rb_left;
			continue;
		}
		if (!before(seq, TCP_SKB_CB(skb)->end_seq)) {
			p = &parent->rb_right;
			continue;
		}
		return skb;
	}
	return NULL;
}

static struct sk_buff *tcp_sacktag_skip(struct sk_buff *skb, struct sock *sk,
					struct tcp_sacktag_state *state,
					u32 skip_to_seq)
{
	if (skb && after(TCP_SKB_CB(skb)->seq, skip_to_seq))
		return skb;

	return tcp_sacktag_bsearch(sk, state, skip_to_seq);
}

static struct sk_buff *tcp_maybe_skipping_dsack(struct sk_buff *skb,
						struct sock *sk,
						struct tcp_sack_block *next_dup,
						struct tcp_sacktag_state *state,
						u32 skip_to_seq)
{
	if (!next_dup)
		return skb;

	if (before(next_dup->start_seq, skip_to_seq)) {
		skb = tcp_sacktag_skip(skb, sk, state, next_dup->start_seq);
		skb = tcp_sacktag_walk(skb, sk, NULL, state,
				       next_dup->start_seq, next_dup->end_seq,
				       1);
	}

	return skb;
}

static int tcp_sack_cache_ok(const struct tcp_sock *tp, const struct tcp_sack_block *cache)
{
	return cache < tp->recv_sack_cache + ARRAY_SIZE(tp->recv_sack_cache);
}

static int
tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb,
			u32 prior_snd_una, struct tcp_sacktag_state *state)
{
	struct tcp_sock *tp = tcp_sk(sk);
	const unsigned char *ptr = (skb_transport_header(ack_skb) +
				    TCP_SKB_CB(ack_skb)->sacked);
	struct tcp_sack_block_wire *sp_wire = (struct tcp_sack_block_wire *)(ptr+2);
	struct tcp_sack_block sp[TCP_NUM_SACKS];
	struct tcp_sack_block *cache;
	struct sk_buff *skb;
	int num_sacks = min(TCP_NUM_SACKS, (ptr[1] - TCPOLEN_SACK_BASE) >> 3);
	int used_sacks;
	bool found_dup_sack = false;
	int i, j;
	int first_sack_index;

	state->flag = 0;
	state->reord = tp->snd_nxt;

	if (!tp->sacked_out)
		tcp_highest_sack_reset(sk);

	found_dup_sack = tcp_check_dsack(sk, ack_skb, sp_wire,
					 num_sacks, prior_snd_una);
	if (found_dup_sack) {
		state->flag |= FLAG_DSACKING_ACK;
		tp->delivered++; /* A spurious retransmission is delivered */
	}

	/* Eliminate too old ACKs, but take into
	 * account more or less fresh ones, they can
	 * contain valid SACK info.
	 */
	if (before(TCP_SKB_CB(ack_skb)->ack_seq, prior_snd_una - tp->max_window))
		return 0;

	if (!tp->packets_out)
		goto out;

	used_sacks = 0;
	first_sack_index = 0;
	for (i = 0; i < num_sacks; i++) {
		bool dup_sack = !i && found_dup_sack;

		sp[used_sacks].start_seq = get_unaligned_be32(&sp_wire[i].start_seq);
		sp[used_sacks].end_seq = get_unaligned_be32(&sp_wire[i].end_seq);

		if (!tcp_is_sackblock_valid(tp, dup_sack,
					    sp[used_sacks].start_seq,
					    sp[used_sacks].end_seq)) {
			int mib_idx;

			if (dup_sack) {
				if (!tp->undo_marker)
					mib_idx = LINUX_MIB_TCPDSACKIGNOREDNOUNDO;
				else
					mib_idx = LINUX_MIB_TCPDSACKIGNOREDOLD;
			} else {
				/* Don't count olds caused by ACK reordering */
				if ((TCP_SKB_CB(ack_skb)->ack_seq != tp->snd_una) &&
				    !after(sp[used_sacks].end_seq, tp->snd_una))
					continue;
				mib_idx = LINUX_MIB_TCPSACKDISCARD;
			}

			NET_INC_STATS(sock_net(sk), mib_idx);
			if (i == 0)
				first_sack_index = -1;
			continue;
		}

		/* Ignore very old stuff early */
		if (!after(sp[used_sacks].end_seq, prior_snd_una))
			continue;

		used_sacks++;
	}

	/* order SACK blocks to allow in order walk of the retrans queue */
	for (i = used_sacks - 1; i > 0; i--) {
		for (j = 0; j < i; j++) {
			if (after(sp[j].start_seq, sp[j + 1].start_seq)) {
				swap(sp[j], sp[j + 1]);

				/* Track where the first SACK block goes to */
				if (j == first_sack_index)
					first_sack_index = j + 1;
			}
		}
	}

	state->mss_now = tcp_current_mss(sk);
	skb = NULL;
	i = 0;

	if (!tp->sacked_out) {
		/* It's already past, so skip checking against it */
		cache = tp->recv_sack_cache + ARRAY_SIZE(tp->recv_sack_cache);
	} else {
		cache = tp->recv_sack_cache;
		/* Skip empty blocks in at head of the cache */
		while (tcp_sack_cache_ok(tp, cache) && !cache->start_seq &&
		       !cache->end_seq)
			cache++;
	}

	while (i < used_sacks) {
		u32 start_seq = sp[i].start_seq;
		u32 end_seq = sp[i].end_seq;
		bool dup_sack = (found_dup_sack && (i == first_sack_index));
		struct tcp_sack_block *next_dup = NULL;

		if (found_dup_sack && ((i + 1) == first_sack_index))
			next_dup = &sp[i + 1];

		/* Skip too early cached blocks */
		while (tcp_sack_cache_ok(tp, cache) &&
		       !before(start_seq, cache->end_seq))
			cache++;

		/* Can skip some work by looking recv_sack_cache? */
		if (tcp_sack_cache_ok(tp, cache) && !dup_sack &&
		    after(end_seq, cache->start_seq)) {

			/* Head todo? */
			if (before(start_seq, cache->start_seq)) {
				skb = tcp_sacktag_skip(skb, sk, state,
						       start_seq);
				skb = tcp_sacktag_walk(skb, sk, next_dup,
						       state,
						       start_seq,
						       cache->start_seq,
						       dup_sack);
			}

			/* Rest of the block already fully processed? */
			if (!after(end_seq, cache->end_seq))
				goto advance_sp;

			skb = tcp_maybe_skipping_dsack(skb, sk, next_dup,
						       state,
						       cache->end_seq);

			/* ...tail remains todo... */
			if (tcp_highest_sack_seq(tp) == cache->end_seq) {
				/* ...but better entrypoint exists! */
				skb = tcp_highest_sack(sk);
				if (!skb)
					break;
				cache++;
				goto walk;
			}

			skb = tcp_sacktag_skip(skb, sk, state, cache->end_seq);
			/* Check overlap against next cached too (past this one already) */
			cache++;
			continue;
		}

		if (!before(start_seq, tcp_highest_sack_seq(tp))) {
			skb = tcp_highest_sack(sk);
			if (!skb)
				break;
		}
		skb = tcp_sacktag_skip(skb, sk, state, start_seq);

walk:
		skb = tcp_sacktag_walk(skb, sk, next_dup, state,
				       start_seq, end_seq, dup_sack);

advance_sp:
		i++;
	}

	/* Clear the head of the cache sack blocks so we can skip it next time */
	for (i = 0; i < ARRAY_SIZE(tp->recv_sack_cache) - used_sacks; i++) {
		tp->recv_sack_cache[i].start_seq = 0;
		tp->recv_sack_cache[i].end_seq = 0;
	}
	for (j = 0; j < used_sacks; j++)
		tp->recv_sack_cache[i++] = sp[j];

	if (inet_csk(sk)->icsk_ca_state != TCP_CA_Loss || tp->undo_marker)
		tcp_check_sack_reordering(sk, state->reord, 0);

	tcp_verify_left_out(tp);
out:

#if FASTRETRANS_DEBUG > 0
	WARN_ON((int)tp->sacked_out < 0);
	WARN_ON((int)tp->lost_out < 0);
	WARN_ON((int)tp->retrans_out < 0);
	WARN_ON((int)tcp_packets_in_flight(tp) < 0);
#endif
	return state->flag;
}

/* Limits sacked_out so that sum with lost_out isn't ever larger than
 * packets_out. Returns false if sacked_out adjustement wasn't necessary.
 */
static bool tcp_limit_reno_sacked(struct tcp_sock *tp)
{
	u32 holes;

	holes = max(tp->lost_out, 1U);
	holes = min(holes, tp->packets_out);

	if ((tp->sacked_out + holes) > tp->packets_out) {
		tp->sacked_out = tp->packets_out - holes;
		return true;
	}
	return false;
}

/* If we receive more dupacks than we expected counting segments
 * in assumption of absent reordering, interpret this as reordering.
 * The only another reason could be bug in receiver TCP.
 */
static void tcp_check_reno_reordering(struct sock *sk, const int addend)
{
	struct tcp_sock *tp = tcp_sk(sk);

	if (!tcp_limit_reno_sacked(tp))
		return;

	tp->reordering = min_t(u32, tp->packets_out + addend,
			       sock_net(sk)->ipv4.sysctl_tcp_max_reordering);
	NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRENOREORDER);
}

/* Emulate SACKs for SACKless connection: account for a new dupack. */

static void tcp_add_reno_sack(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);
	u32 prior_sacked = tp->sacked_out;

	tp->sacked_out++;
	tcp_check_reno_reordering(sk, 0);
	if (tp->sacked_out > prior_sacked)
		tp->delivered++; /* Some out-of-order packet is delivered */
	tcp_verify_left_out(tp);
}

/* Account for ACK, ACKing some data in Reno Recovery phase. */

static void tcp_remove_reno_sacks(struct sock *sk, int acked)
{
	struct tcp_sock *tp = tcp_sk(sk);

	if (acked > 0) {
		/* One ACK acked hole. The rest eat duplicate ACKs. */
		tp->delivered += max_t(int, acked - tp->sacked_out, 1);
		if (acked - 1 >= tp->sacked_out)
			tp->sacked_out = 0;
		else
			tp->sacked_out -= acked - 1;
	}
	tcp_check_reno_reordering(sk, acked);
	tcp_verify_left_out(tp);
}

static inline void tcp_reset_reno_sack(struct tcp_sock *tp)
{
	tp->sacked_out = 0;
}

void tcp_clear_retrans(struct tcp_sock *tp)
{
	tp->retrans_out = 0;
	tp->lost_out = 0;
	tp->undo_marker = 0;
	tp->undo_retrans = -1;
	tp->sacked_out = 0;
}

static inline void tcp_init_undo(struct tcp_sock *tp)
{
	tp->undo_marker = tp->snd_una;
	/* Retransmission still in flight may cause DSACKs later. */
	tp->undo_retrans = tp->retrans_out ? : -1;
}

static bool tcp_is_rack(const struct sock *sk)
{
	return sock_net(sk)->ipv4.sysctl_tcp_recovery & TCP_RACK_LOSS_DETECTION;
}

/* If we detect SACK reneging, forget all SACK information
 * and reset tags completely, otherwise preserve SACKs. If receiver
 * dropped its ofo queue, we will know this due to reneging detection.
 */
static void tcp_timeout_mark_lost(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct sk_buff *skb, *head;
	bool is_reneg;			/* is receiver reneging on SACKs? */

	head = tcp_rtx_queue_head(sk);
	is_reneg = head && (TCP_SKB_CB(head)->sacked & TCPCB_SACKED_ACKED);
	if (is_reneg) {
		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSACKRENEGING);
		tp->sacked_out = 0;
		/* Mark SACK reneging until we recover from this loss event. */
		tp->is_sack_reneg = 1;
	} else if (tcp_is_reno(tp)) {
		tcp_reset_reno_sack(tp);
	}

	skb = head;
	skb_rbtree_walk_from(skb) {
		if (is_reneg)
			TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_ACKED;
		else if (tcp_is_rack(sk) && skb != head &&
			 tcp_rack_skb_timeout(tp, skb, 0) > 0)
			continue; /* Don't mark recently sent ones lost yet */
		tcp_mark_skb_lost(sk, skb);
	}
	tcp_verify_left_out(tp);
	tcp_clear_all_retrans_hints(tp);
}

/* Enter Loss state. */
void tcp_enter_loss(struct sock *sk)
{
	const struct inet_connection_sock *icsk = inet_csk(sk);
	struct tcp_sock *tp = tcp_sk(sk);
	struct net *net = sock_net(sk);
	bool new_recovery = icsk->icsk_ca_state < TCP_CA_Recovery;

	tcp_timeout_mark_lost(sk);

	/* Reduce ssthresh if it has not yet been made inside this window. */
	if (icsk->icsk_ca_state <= TCP_CA_Disorder ||
	    !after(tp->high_seq, tp->snd_una) ||
	    (icsk->icsk_ca_state == TCP_CA_Loss && !icsk->icsk_retransmits)) {
		tp->prior_ssthresh = tcp_current_ssthresh(sk);
		tp->prior_cwnd = tp->snd_cwnd;
		tp->snd_ssthresh = icsk->icsk_ca_ops->ssthresh(sk);
		tcp_ca_event(sk, CA_EVENT_LOSS);
		tcp_init_undo(tp);
	}
	tp->snd_cwnd	   = tcp_packets_in_flight(tp) + 1;
	tp->snd_cwnd_cnt   = 0;
	tp->snd_cwnd_stamp = tcp_jiffies32;

	/* Timeout in disordered state after receiving substantial DUPACKs
	 * suggests that the degree of reordering is over-estimated.
	 */
	if (icsk->icsk_ca_state <= TCP_CA_Disorder &&
	    tp->sacked_out >= net->ipv4.sysctl_tcp_reordering)
		tp->reordering = min_t(unsigned int, tp->reordering,
				       net->ipv4.sysctl_tcp_reordering);
	tcp_set_ca_state(sk, TCP_CA_Loss);
	tp->high_seq = tp->snd_nxt;
	tcp_ecn_queue_cwr(tp);

	/* F-RTO RFC5682 sec 3.1 step 1: retransmit SND.UNA if no previous
	 * loss recovery is underway except recurring timeout(s) on
	 * the same SND.UNA (sec 3.2). Disable F-RTO on path MTU probing
	 */
	tp->frto = net->ipv4.sysctl_tcp_frto &&
		   (new_recovery || icsk->icsk_retransmits) &&
		   !inet_csk(sk)->icsk_mtup.probe_size;
}

/* If ACK arrived pointing to a remembered SACK, it means that our
 * remembered SACKs do not reflect real state of receiver i.e.
 * receiver _host_ is heavily congested (or buggy).
 *
 * To avoid big spurious retransmission bursts due to transient SACK
 * scoreboard oddities that look like reneging, we give the receiver a
 * little time (max(RTT/2, 10ms)) to send us some more ACKs that will
 * restore sanity to the SACK scoreboard. If the apparent reneging
 * persists until this RTO then we'll clear the SACK scoreboard.
 */
static bool tcp_check_sack_reneging(struct sock *sk, int flag)
{
	if (flag & FLAG_SACK_RENEGING) {
		struct tcp_sock *tp = tcp_sk(sk);
		unsigned long delay = max(usecs_to_jiffies(tp->srtt_us >> 4),
					  msecs_to_jiffies(10));

		inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
					  delay, TCP_RTO_MAX);
		return true;
	}
	return false;
}

/* Heurestics to calculate number of duplicate ACKs. There's no dupACKs
 * counter when SACK is enabled (without SACK, sacked_out is used for
 * that purpose).
 *
 * With reordering, holes may still be in flight, so RFC3517 recovery
 * uses pure sacked_out (total number of SACKed segments) even though
 * it violates the RFC that uses duplicate ACKs, often these are equal
 * but when e.g. out-of-window ACKs or packet duplication occurs,
 * they differ. Since neither occurs due to loss, TCP should really
 * ignore them.
 */
static inline int tcp_dupack_heuristics(const struct tcp_sock *tp)
{
	return tp->sacked_out + 1;
}

/* Linux NewReno/SACK/ECN state machine.
 * --------------------------------------
 *
 * "Open"	Normal state, no dubious events, fast path.
 * "Disorder"   In all the respects it is "Open",
 *		but requires a bit more attention. It is entered when
 *		we see some SACKs or dupacks. It is split of "Open"
 *		mainly to move some processing from fast path to slow one.
 * "CWR"	CWND was reduced due to some Congestion Notification event.
 *		It can be ECN, ICMP source quench, local device congestion.
 * "Recovery"	CWND was reduced, we are fast-retransmitting.
 * "Loss"	CWND was reduced due to RTO timeout or SACK reneging.
 *
 * tcp_fastretrans_alert() is entered:
 * - each incoming ACK, if state is not "Open"
 * - when arrived ACK is unusual, namely:
 *	* SACK
 *	* Duplicate ACK.
 *	* ECN ECE.
 *
 * Counting packets in flight is pretty simple.
 *
 *	in_flight = packets_out - left_out + retrans_out
 *
 *	packets_out is SND.NXT-SND.UNA counted in packets.
 *
 *	retrans_out is number of retransmitted segments.
 *
 *	left_out is number of segments left network, but not ACKed yet.
 *
 *		left_out = sacked_out + lost_out
 *
 *     sacked_out: Packets, which arrived to receiver out of order
 *		   and hence not ACKed. With SACKs this number is simply
 *		   amount of SACKed data. Even without SACKs
 *		   it is easy to give pretty reliable estimate of this number,
 *		   counting duplicate ACKs.
 *
 *       lost_out: Packets lost by network. TCP has no explicit
 *		   "loss notification" feedback from network (for now).
 *		   It means that this number can be only _guessed_.
 *		   Actually, it is the heuristics to predict lossage that
 *		   distinguishes different algorithms.
 *
 *	F.e. after RTO, when all the queue is considered as lost,
 *	lost_out = packets_out and in_flight = retrans_out.
 *
 *		Essentially, we have now a few algorithms detecting
 *		lost packets.
 *
 *		If the receiver supports SACK:
 *
 *		RFC6675/3517: It is the conventional algorithm. A packet is
 *		considered lost if the number of higher sequence packets
 *		SACKed is greater than or equal the DUPACK thoreshold
 *		(reordering). This is implemented in tcp_mark_head_lost and
 *		tcp_update_scoreboard.
 *
 *		RACK (draft-ietf-tcpm-rack-01): it is a newer algorithm
 *		(2017-) that checks timing instead of counting DUPACKs.
 *		Essentially a packet is considered lost if it's not S/ACKed
 *		after RTT + reordering_window, where both metrics are
 *		dynamically measured and adjusted. This is implemented in
 *		tcp_rack_mark_lost.
 *
 *		If the receiver does not support SACK:
 *
 *		NewReno (RFC6582): in Recovery we assume that one segment
 *		is lost (classic Reno). While we are in Recovery and
 *		a partial ACK arrives, we assume that one more packet
 *		is lost (NewReno). This heuristics are the same in NewReno
 *		and SACK.
 *
 * Really tricky (and requiring careful tuning) part of algorithm
 * is hidden in functions tcp_time_to_recover() and tcp_xmit_retransmit_queue().
 * The first determines the moment _when_ we should reduce CWND and,
 * hence, slow down forward transmission. In fact, it determines the moment
 * when we decide that hole is caused by loss, rather than by a reorder.
 *
 * tcp_xmit_retransmit_queue() decides, _what_ we should retransmit to fill
 * holes, caused by lost packets.
 *
 * And the most logically complicated part of algorithm is undo
 * heuristics. We detect false retransmits due to both too early
 * fast retransmit (reordering) and underestimated RTO, analyzing
 * timestamps and D-SACKs. When we detect that some segments were
 * retransmitted by mistake and CWND reduction was wrong, we undo
 * window reduction and abort recovery phase. This logic is hidden
 * inside several functions named tcp_try_undo_<something>.
 */

/* This function decides, when we should leave Disordered state
 * and enter Recovery phase, reducing congestion window.
 *
 * Main question: may we further continue forward transmission
 * with the same cwnd?
 */
static bool tcp_time_to_recover(struct sock *sk, int flag)
{
	struct tcp_sock *tp = tcp_sk(sk);

	/* Trick#1: The loss is proven. */
	if (tp->lost_out)
		return true;

	/* Not-A-Trick#2 : Classic rule... */
	if (!tcp_is_rack(sk) && tcp_dupack_heuristics(tp) > tp->reordering)
		return true;

	return false;
}

/* Detect loss in event "A" above by marking head of queue up as lost.
 * For non-SACK(Reno) senders, the first "packets" number of segments
 * are considered lost. For RFC3517 SACK, a segment is considered lost if it
 * has at least tp->reordering SACKed seqments above it; "packets" refers to
 * the maximum SACKed segments to pass before reaching this limit.
 */
static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct sk_buff *skb;
	int cnt, oldcnt, lost;
	unsigned int mss;
	/* Use SACK to deduce losses of new sequences sent during recovery */
	const u32 loss_high = tcp_is_sack(tp) ?  tp->snd_nxt : tp->high_seq;

	WARN_ON(packets > tp->packets_out);
	skb = tp->lost_skb_hint;
	if (skb) {
		/* Head already handled? */
		if (mark_head && after(TCP_SKB_CB(skb)->seq, tp->snd_una))
			return;
		cnt = tp->lost_cnt_hint;
	} else {
		skb = tcp_rtx_queue_head(sk);
		cnt = 0;
	}

	skb_rbtree_walk_from(skb) {
		/* TODO: do this better */
		/* this is not the most efficient way to do this... */
		tp->lost_skb_hint = skb;
		tp->lost_cnt_hint = cnt;

		if (after(TCP_SKB_CB(skb)->end_seq, loss_high))
			break;

		oldcnt = cnt;
		if (tcp_is_reno(tp) ||
		    (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED))
			cnt += tcp_skb_pcount(skb);

		if (cnt > packets) {
			if (tcp_is_sack(tp) ||
			    (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) ||
			    (oldcnt >= packets))
				break;

			mss = tcp_skb_mss(skb);
			/* If needed, chop off the prefix to mark as lost. */
			lost = (packets - oldcnt) * mss;
			if (lost < skb->len &&
			    tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb,
					 lost, mss, GFP_ATOMIC) < 0)
				break;
			cnt = packets;
		}

		tcp_skb_mark_lost(tp, skb);

		if (mark_head)
			break;
	}
	tcp_verify_left_out(tp);
}

/* Account newly detected lost packet(s) */

static void tcp_update_scoreboard(struct sock *sk, int fast_rexmit)
{
	struct tcp_sock *tp = tcp_sk(sk);

	if (tcp_is_sack(tp)) {
		int sacked_upto = tp->sacked_out - tp->reordering;
		if (sacked_upto >= 0)
			tcp_mark_head_lost(sk, sacked_upto, 0);
		else if (fast_rexmit)
			tcp_mark_head_lost(sk, 1, 1);
	}
}

static bool tcp_tsopt_ecr_before(const struct tcp_sock *tp, u32 when)
{
	return tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr &&
	       before(tp->rx_opt.rcv_tsecr, when);
}

/* skb is spurious retransmitted if the returned timestamp echo
 * reply is prior to the skb transmission time
 */
static bool tcp_skb_spurious_retrans(const struct tcp_sock *tp,
				     const struct sk_buff *skb)
{
	return (TCP_SKB_CB(skb)->sacked & TCPCB_RETRANS) &&
	       tcp_tsopt_ecr_before(tp, tcp_skb_timestamp(skb));
}

/* Nothing was retransmitted or returned timestamp is less
 * than timestamp of the first retransmission.
 */
static inline bool tcp_packet_delayed(const struct tcp_sock *tp)
{
	return !tp->retrans_stamp ||
	       tcp_tsopt_ecr_before(tp, tp->retrans_stamp);
}

/* Undo procedures. */

/* We can clear retrans_stamp when there are no retransmissions in the
 * window. It would seem that it is trivially available for us in
 * tp->retrans_out, however, that kind of assumptions doesn't consider
 * what will happen if errors occur when sending retransmission for the
 * second time. ...It could the that such segment has only
 * TCPCB_EVER_RETRANS set at the present time. It seems that checking
 * the head skb is enough except for some reneging corner cases that
 * are not worth the effort.
 *
 * Main reason for all this complexity is the fact that connection dying
 * time now depends on the validity of the retrans_stamp, in particular,
 * that successive retransmissions of a segment must not advance
 * retrans_stamp under any conditions.
 */
static bool tcp_any_retrans_done(const struct sock *sk)
{
	const struct tcp_sock *tp = tcp_sk(sk);
	struct sk_buff *skb;

	if (tp->retrans_out)
		return true;

	skb = tcp_rtx_queue_head(sk);
	if (unlikely(skb && TCP_SKB_CB(skb)->sacked & TCPCB_EVER_RETRANS))
		return true;

	return false;
}

static void DBGUNDO(struct sock *sk, const char *msg)
{
#if FASTRETRANS_DEBUG > 1
	struct tcp_sock *tp = tcp_sk(sk);
	struct inet_sock *inet = inet_sk(sk);

	if (sk->sk_family == AF_INET) {
		pr_debug("Undo %s %pI4/%u c%u l%u ss%u/%u p%u\n",
			 msg,
			 &inet->inet_daddr, ntohs(inet->inet_dport),
			 tp->snd_cwnd, tcp_left_out(tp),
			 tp->snd_ssthresh, tp->prior_ssthresh,
			 tp->packets_out);
	}
#if IS_ENABLED(CONFIG_IPV6)
	else if (sk->sk_family == AF_INET6) {
		pr_debug("Undo %s %pI6/%u c%u l%u ss%u/%u p%u\n",
			 msg,
			 &sk->sk_v6_daddr, ntohs(inet->inet_dport),
			 tp->snd_cwnd, tcp_left_out(tp),
			 tp->snd_ssthresh, tp->prior_ssthresh,
			 tp->packets_out);
	}
#endif
#endif
}

static void tcp_undo_cwnd_reduction(struct sock *sk, bool unmark_loss)
{
	struct tcp_sock *tp = tcp_sk(sk);

	if (unmark_loss) {
		struct sk_buff *skb;

		skb_rbtree_walk(skb, &sk->tcp_rtx_queue) {
			TCP_SKB_CB(skb)->sacked &= ~TCPCB_LOST;
		}
		tp->lost_out = 0;
		tcp_clear_all_retrans_hints(tp);
	}

	if (tp->prior_ssthresh) {
		const struct inet_connection_sock *icsk = inet_csk(sk);

		tp->snd_cwnd = icsk->icsk_ca_ops->undo_cwnd(sk);

		if (tp->prior_ssthresh > tp->snd_ssthresh) {
			tp->snd_ssthresh = tp->prior_ssthresh;
			tcp_ecn_withdraw_cwr(tp);
		}
	}
	tp->snd_cwnd_stamp = tcp_jiffies32;
	tp->undo_marker = 0;
	tp->rack.advanced = 1; /* Force RACK to re-exam losses */
}

static inline bool tcp_may_undo(const struct tcp_sock *tp)
{
	return tp->undo_marker && (!tp->undo_retrans || tcp_packet_delayed(tp));
}

/* People celebrate: "We love our President!" */
static bool tcp_try_undo_recovery(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);

	if (tcp_may_undo(tp)) {
		int mib_idx;

		/* Happy end! We did not retransmit anything
		 * or our original transmission succeeded.
		 */
		DBGUNDO(sk, inet_csk(sk)->icsk_ca_state == TCP_CA_Loss ? "loss" : "retrans");
		tcp_undo_cwnd_reduction(sk, false);
		if (inet_csk(sk)->icsk_ca_state == TCP_CA_Loss)
			mib_idx = LINUX_MIB_TCPLOSSUNDO;
		else
			mib_idx = LINUX_MIB_TCPFULLUNDO;

		NET_INC_STATS(sock_net(sk), mib_idx);
	} else if (tp->rack.reo_wnd_persist) {
		tp->rack.reo_wnd_persist--;
	}
	if (tp->snd_una == tp->high_seq && tcp_is_reno(tp)) {
		/* Hold old state until something *above* high_seq
		 * is ACKed. For Reno it is MUST to prevent false
		 * fast retransmits (RFC2582). SACK TCP is safe. */
		if (!tcp_any_retrans_done(sk))
			tp->retrans_stamp = 0;
		return true;
	}
	tcp_set_ca_state(sk, TCP_CA_Open);
	tp->is_sack_reneg = 0;
	return false;
}

/* Try to undo cwnd reduction, because D-SACKs acked all retransmitted data */
static bool tcp_try_undo_dsack(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);

	if (tp->undo_marker && !tp->undo_retrans) {
		tp->rack.reo_wnd_persist = min(TCP_RACK_RECOVERY_THRESH,
					       tp->rack.reo_wnd_persist + 1);
		DBGUNDO(sk, "D-SACK");
		tcp_undo_cwnd_reduction(sk, false);
		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPDSACKUNDO);
		return true;
	}
	return false;
}

/* Undo during loss recovery after partial ACK or using F-RTO. */
static bool tcp_try_undo_loss(struct sock *sk, bool frto_undo)
{
	struct tcp_sock *tp = tcp_sk(sk);

	if (frto_undo || tcp_may_undo(tp)) {
		tcp_undo_cwnd_reduction(sk, true);

		DBGUNDO(sk, "partial loss");
		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPLOSSUNDO);
		if (frto_undo)
			NET_INC_STATS(sock_net(sk),
					LINUX_MIB_TCPSPURIOUSRTOS);
		inet_csk(sk)->icsk_retransmits = 0;
		if (frto_undo || tcp_is_sack(tp)) {
			tcp_set_ca_state(sk, TCP_CA_Open);
			tp->is_sack_reneg = 0;
		}
		return true;
	}
	return false;
}

/* The cwnd reduction in CWR and Recovery uses the PRR algorithm in RFC 6937.
 * It computes the number of packets to send (sndcnt) based on packets newly
 * delivered:
 *   1) If the packets in flight is larger than ssthresh, PRR spreads the
 *	cwnd reductions across a full RTT.
 *   2) Otherwise PRR uses packet conservation to send as much as delivered.
 *      But when the retransmits are acked without further losses, PRR
 *      slow starts cwnd up to ssthresh to speed up the recovery.
 */
static void tcp_init_cwnd_reduction(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);

	tp->high_seq = tp->snd_nxt;
	tp->tlp_high_seq = 0;
	tp->snd_cwnd_cnt = 0;
	tp->prior_cwnd = tp->snd_cwnd;
	tp->prr_delivered = 0;
	tp->prr_out = 0;
	tp->snd_ssthresh = inet_csk(sk)->icsk_ca_ops->ssthresh(sk);
	tcp_ecn_queue_cwr(tp);
}

void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked, int flag)
{
	struct tcp_sock *tp = tcp_sk(sk);
	int sndcnt = 0;
	int delta = tp->snd_ssthresh - tcp_packets_in_flight(tp);

	if (newly_acked_sacked <= 0 || WARN_ON_ONCE(!tp->prior_cwnd))
		return;

	tp->prr_delivered += newly_acked_sacked;
	if (delta < 0) {
		u64 dividend = (u64)tp->snd_ssthresh * tp->prr_delivered +
			       tp->prior_cwnd - 1;
		sndcnt = div_u64(dividend, tp->prior_cwnd) - tp->prr_out;
	} else if ((flag & FLAG_RETRANS_DATA_ACKED) &&
		   !(flag & FLAG_LOST_RETRANS)) {
		sndcnt = min_t(int, delta,
			       max_t(int, tp->prr_delivered - tp->prr_out,
				     newly_acked_sacked) + 1);
	} else {
		sndcnt = min(delta, newly_acked_sacked);
	}
	/* Force a fast retransmit upon entering fast recovery */
	sndcnt = max(sndcnt, (tp->prr_out ? 0 : 1));
	tp->snd_cwnd = tcp_packets_in_flight(tp) + sndcnt;
}

static inline void tcp_end_cwnd_reduction(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);

	if (inet_csk(sk)->icsk_ca_ops->cong_control)
		return;

	/* Reset cwnd to ssthresh in CWR or Recovery (unless it's undone) */
	if (tp->snd_ssthresh < TCP_INFINITE_SSTHRESH &&
	    (inet_csk(sk)->icsk_ca_state == TCP_CA_CWR || tp->undo_marker)) {
		tp->snd_cwnd = tp->snd_ssthresh;
		tp->snd_cwnd_stamp = tcp_jiffies32;
	}
	tcp_ca_event(sk, CA_EVENT_COMPLETE_CWR);
}

/* Enter CWR state. Disable cwnd undo since congestion is proven with ECN */
void tcp_enter_cwr(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);

	tp->prior_ssthresh = 0;
	if (inet_csk(sk)->icsk_ca_state < TCP_CA_CWR) {
		tp->undo_marker = 0;
		tcp_init_cwnd_reduction(sk);
		tcp_set_ca_state(sk, TCP_CA_CWR);
	}
}
EXPORT_SYMBOL(tcp_enter_cwr);

static void tcp_try_keep_open(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);
	int state = TCP_CA_Open;

	if (tcp_left_out(tp) || tcp_any_retrans_done(sk))
		state = TCP_CA_Disorder;

	if (inet_csk(sk)->icsk_ca_state != state) {
		tcp_set_ca_state(sk, state);
		tp->high_seq = tp->snd_nxt;
	}
}

static void tcp_try_to_open(struct sock *sk, int flag)
{
	struct tcp_sock *tp = tcp_sk(sk);

	tcp_verify_left_out(tp);

	if (!tcp_any_retrans_done(sk))
		tp->retrans_stamp = 0;

	if (flag & FLAG_ECE)
		tcp_enter_cwr(sk);

	if (inet_csk(sk)->icsk_ca_state != TCP_CA_CWR) {
		tcp_try_keep_open(sk);
	}
}

static void tcp_mtup_probe_failed(struct sock *sk)
{
	struct inet_connection_sock *icsk = inet_csk(sk);

	icsk->icsk_mtup.search_high = icsk->icsk_mtup.probe_size - 1;
	icsk->icsk_mtup.probe_size = 0;
	NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMTUPFAIL);
}

static void tcp_mtup_probe_success(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct inet_connection_sock *icsk = inet_csk(sk);

	/* FIXME: breaks with very large cwnd */
	tp->prior_ssthresh = tcp_current_ssthresh(sk);
	tp->snd_cwnd = tp->snd_cwnd *
		       tcp_mss_to_mtu(sk, tp->mss_cache) /
		       icsk->icsk_mtup.probe_size;
	tp->snd_cwnd_cnt = 0;
	tp->snd_cwnd_stamp = tcp_jiffies32;
	tp->snd_ssthresh = tcp_current_ssthresh(sk);

	icsk->icsk_mtup.search_low = icsk->icsk_mtup.probe_size;
	icsk->icsk_mtup.probe_size = 0;
	tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
	NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMTUPSUCCESS);
}

/* Do a simple retransmit without using the backoff mechanisms in
 * tcp_timer. This is used for path mtu discovery.
 * The socket is already locked here.
 */
void tcp_simple_retransmit(struct sock *sk)
{
	const struct inet_connection_sock *icsk = inet_csk(sk);
	struct tcp_sock *tp = tcp_sk(sk);
	struct sk_buff *skb;
	unsigned int mss = tcp_current_mss(sk);

	skb_rbtree_walk(skb, &sk->tcp_rtx_queue) {
		if (tcp_skb_seglen(skb) > mss &&
		    !(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) {
			if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) {
				TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS;
				tp->retrans_out -= tcp_skb_pcount(skb);
			}
			tcp_skb_mark_lost_uncond_verify(tp, skb);
		}
	}

	tcp_clear_retrans_hints_partial(tp);

	if (!tp->lost_out)
		return;

	if (tcp_is_reno(tp))
		tcp_limit_reno_sacked(tp);

	tcp_verify_left_out(tp);

	/* Don't muck with the congestion window here.
	 * Reason is that we do not increase amount of _data_
	 * in network, but units changed and effective
	 * cwnd/ssthresh really reduced now.
	 */
	if (icsk->icsk_ca_state != TCP_CA_Loss) {
		tp->high_seq = tp->snd_nxt;
		tp->snd_ssthresh = tcp_current_ssthresh(sk);
		tp->prior_ssthresh = 0;
		tp->undo_marker = 0;
		tcp_set_ca_state(sk, TCP_CA_Loss);
	}
	tcp_xmit_retransmit_queue(sk);
}
EXPORT_SYMBOL(tcp_simple_retransmit);

void tcp_enter_recovery(struct sock *sk, bool ece_ack)
{
	struct tcp_sock *tp = tcp_sk(sk);
	int mib_idx;

	if (tcp_is_reno(tp))
		mib_idx = LINUX_MIB_TCPRENORECOVERY;
	else
		mib_idx = LINUX_MIB_TCPSACKRECOVERY;

	NET_INC_STATS(sock_net(sk), mib_idx);

	tp->prior_ssthresh = 0;
	tcp_init_undo(tp);

	if (!tcp_in_cwnd_reduction(sk)) {
		if (!ece_ack)
			tp->prior_ssthresh = tcp_current_ssthresh(sk);
		tcp_init_cwnd_reduction(sk);
	}
	tcp_set_ca_state(sk, TCP_CA_Recovery);
}

/* Process an ACK in CA_Loss state. Move to CA_Open if lost data are
 * recovered or spurious. Otherwise retransmits more on partial ACKs.
 */
static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack,
			     int *rexmit)
{
	struct tcp_sock *tp = tcp_sk(sk);
	bool recovered = !before(tp->snd_una, tp->high_seq);

	if ((flag & FLAG_SND_UNA_ADVANCED) &&
	    tcp_try_undo_loss(sk, false))
		return;

	if (tp->frto) { /* F-RTO RFC5682 sec 3.1 (sack enhanced version). */
		/* Step 3.b. A timeout is spurious if not all data are
		 * lost, i.e., never-retransmitted data are (s)acked.
		 */
		if ((flag & FLAG_ORIG_SACK_ACKED) &&
		    tcp_try_undo_loss(sk, true))
			return;

		if (after(tp->snd_nxt, tp->high_seq)) {
			if (flag & FLAG_DATA_SACKED || is_dupack)
				tp->frto = 0; /* Step 3.a. loss was real */
		} else if (flag & FLAG_SND_UNA_ADVANCED && !recovered) {
			tp->high_seq = tp->snd_nxt;
			/* Step 2.b. Try send new data (but deferred until cwnd
			 * is updated in tcp_ack()). Otherwise fall back to
			 * the conventional recovery.
			 */
			if (!tcp_write_queue_empty(sk) &&
			    after(tcp_wnd_end(tp), tp->snd_nxt)) {
				*rexmit = REXMIT_NEW;
				return;
			}
			tp->frto = 0;
		}
	}

	if (recovered) {
		/* F-RTO RFC5682 sec 3.1 step 2.a and 1st part of step 3.a */
		tcp_try_undo_recovery(sk);
		return;
	}
	if (tcp_is_reno(tp)) {
		/* A Reno DUPACK means new data in F-RTO step 2.b above are
		 * delivered. Lower inflight to clock out (re)tranmissions.
		 */
		if (after(tp->snd_nxt, tp->high_seq) && is_dupack)
			tcp_add_reno_sack(sk);
		else if (flag & FLAG_SND_UNA_ADVANCED)
			tcp_reset_reno_sack(tp);
	}
	*rexmit = REXMIT_LOST;
}

/* Undo during fast recovery after partial ACK. */
static bool tcp_try_undo_partial(struct sock *sk, u32 prior_snd_una)
{
	struct tcp_sock *tp = tcp_sk(sk);

	if (tp->undo_marker && tcp_packet_delayed(tp)) {
		/* Plain luck! Hole if filled with delayed
		 * packet, rather than with a retransmit. Check reordering.
		 */
		tcp_check_sack_reordering(sk, prior_snd_una, 1);

		/* We are getting evidence that the reordering degree is higher
		 * than we realized. If there are no retransmits out then we
		 * can undo. Otherwise we clock out new packets but do not
		 * mark more packets lost or retransmit more.
		 */
		if (tp->retrans_out)
			return true;

		if (!tcp_any_retrans_done(sk))
			tp->retrans_stamp = 0;

		DBGUNDO(sk, "partial recovery");
		tcp_undo_cwnd_reduction(sk, true);
		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPPARTIALUNDO);
		tcp_try_keep_open(sk);
		return true;
	}
	return false;
}

static void tcp_identify_packet_loss(struct sock *sk, int *ack_flag)
{
	struct tcp_sock *tp = tcp_sk(sk);

	if (tcp_rtx_queue_empty(sk))
		return;

	if (unlikely(tcp_is_reno(tp))) {
		tcp_newreno_mark_lost(sk, *ack_flag & FLAG_SND_UNA_ADVANCED);
	} else if (tcp_is_rack(sk)) {
		u32 prior_retrans = tp->retrans_out;

		tcp_rack_mark_lost(sk);
		if (prior_retrans > tp->retrans_out)
			*ack_flag |= FLAG_LOST_RETRANS;
	}
}

static bool tcp_force_fast_retransmit(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);

	return after(tcp_highest_sack_seq(tp),
		     tp->snd_una + tp->reordering * tp->mss_cache);
}

/* Process an event, which can update packets-in-flight not trivially.
 * Main goal of this function is to calculate new estimate for left_out,
 * taking into account both packets sitting in receiver's buffer and
 * packets lost by network.
 *
 * Besides that it updates the congestion state when packet loss or ECN
 * is detected. But it does not reduce the cwnd, it is done by the
 * congestion control later.
 *
 * It does _not_ decide what to send, it is made in function
 * tcp_xmit_retransmit_queue().
 */
static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una,
				  bool is_dupack, int *ack_flag, int *rexmit)
{
	struct inet_connection_sock *icsk = inet_csk(sk);
	struct tcp_sock *tp = tcp_sk(sk);
	int fast_rexmit = 0, flag = *ack_flag;
	bool do_lost = is_dupack || ((flag & FLAG_DATA_SACKED) &&
				     tcp_force_fast_retransmit(sk));

	if (!tp->packets_out && tp->sacked_out)
		tp->sacked_out = 0;

	/* Now state machine starts.
	 * A. ECE, hence prohibit cwnd undoing, the reduction is required. */
	if (flag & FLAG_ECE)
		tp->prior_ssthresh = 0;

	/* B. In all the states check for reneging SACKs. */
	if (tcp_check_sack_reneging(sk, flag))
		return;

	/* C. Check consistency of the current state. */
	tcp_verify_left_out(tp);

	/* D. Check state exit conditions. State can be terminated
	 *    when high_seq is ACKed. */
	if (icsk->icsk_ca_state == TCP_CA_Open) {
		WARN_ON(tp->retrans_out != 0);
		tp->retrans_stamp = 0;
	} else if (!before(tp->snd_una, tp->high_seq)) {
		switch (icsk->icsk_ca_state) {
		case TCP_CA_CWR:
			/* CWR is to be held something *above* high_seq
			 * is ACKed for CWR bit to reach receiver. */
			if (tp->snd_una != tp->high_seq) {
				tcp_end_cwnd_reduction(sk);
				tcp_set_ca_state(sk, TCP_CA_Open);
			}
			break;

		case TCP_CA_Recovery:
			if (tcp_is_reno(tp))
				tcp_reset_reno_sack(tp);
			if (tcp_try_undo_recovery(sk))
				return;
			tcp_end_cwnd_reduction(sk);
			break;
		}
	}

	/* E. Process state. */
	switch (icsk->icsk_ca_state) {
	case TCP_CA_Recovery:
		if (!(flag & FLAG_SND_UNA_ADVANCED)) {
			if (tcp_is_reno(tp) && is_dupack)
				tcp_add_reno_sack(sk);
		} else {
			if (tcp_try_undo_partial(sk, prior_snd_una))
				return;
			/* Partial ACK arrived. Force fast retransmit. */
			do_lost = tcp_is_reno(tp) ||
				  tcp_force_fast_retransmit(sk);
		}
		if (tcp_try_undo_dsack(sk)) {
			tcp_try_keep_open(sk);
			return;
		}
		tcp_identify_packet_loss(sk, ack_flag);
		break;
	case TCP_CA_Loss:
		tcp_process_loss(sk, flag, is_dupack, rexmit);
		tcp_identify_packet_loss(sk, ack_flag);
		if (!(icsk->icsk_ca_state == TCP_CA_Open ||
		      (*ack_flag & FLAG_LOST_RETRANS)))
			return;
		/* Change state if cwnd is undone or retransmits are lost */
		/* fall through */
	default:
		if (tcp_is_reno(tp)) {
			if (flag & FLAG_SND_UNA_ADVANCED)
				tcp_reset_reno_sack(tp);
			if (is_dupack)
				tcp_add_reno_sack(sk);
		}

		if (icsk->icsk_ca_state <= TCP_CA_Disorder)
			tcp_try_undo_dsack(sk);

		tcp_identify_packet_loss(sk, ack_flag);
		if (!tcp_time_to_recover(sk, flag)) {
			tcp_try_to_open(sk, flag);
			return;
		}

		/* MTU probe failure: don't reduce cwnd */
		if (icsk->icsk_ca_state < TCP_CA_CWR &&
		    icsk->icsk_mtup.probe_size &&
		    tp->snd_una == tp->mtu_probe.probe_seq_start) {
			tcp_mtup_probe_failed(sk);
			/* Restores the reduction we did in tcp_mtup_probe() */
			tp->snd_cwnd++;
			tcp_simple_retransmit(sk);
			return;
		}

		/* Otherwise enter Recovery state */
		tcp_enter_recovery(sk, (flag & FLAG_ECE));
		fast_rexmit = 1;
	}

	if (!tcp_is_rack(sk) && do_lost)
		tcp_update_scoreboard(sk, fast_rexmit);
	*rexmit = REXMIT_LOST;
}

static void tcp_update_rtt_min(struct sock *sk, u32 rtt_us, const int flag)
{
	u32 wlen = sock_net(sk)->ipv4.sysctl_tcp_min_rtt_wlen * HZ;
	struct tcp_sock *tp = tcp_sk(sk);

	if ((flag & FLAG_ACK_MAYBE_DELAYED) && rtt_us > tcp_min_rtt(tp)) {
		/* If the remote keeps returning delayed ACKs, eventually
		 * the min filter would pick it up and overestimate the
		 * prop. delay when it expires. Skip suspected delayed ACKs.
		 */
		return;
	}
	minmax_running_min(&tp->rtt_min, wlen, tcp_jiffies32,
			   rtt_us ? : jiffies_to_usecs(1));
}

static bool tcp_ack_update_rtt(struct sock *sk, const int flag,
			       long seq_rtt_us, long sack_rtt_us,
			       long ca_rtt_us, struct rate_sample *rs)
{
	const struct tcp_sock *tp = tcp_sk(sk);

	/* Prefer RTT measured from ACK's timing to TS-ECR. This is because
	 * broken middle-boxes or peers may corrupt TS-ECR fields. But
	 * Karn's algorithm forbids taking RTT if some retransmitted data
	 * is acked (RFC6298).
	 */
	if (seq_rtt_us < 0)
		seq_rtt_us = sack_rtt_us;

	/* RTTM Rule: A TSecr value received in a segment is used to
	 * update the averaged RTT measurement only if the segment
	 * acknowledges some new data, i.e., only if it advances the
	 * left edge of the send window.
	 * See draft-ietf-tcplw-high-performance-00, section 3.3.
	 */
	if (seq_rtt_us < 0 && tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr &&
	    flag & FLAG_ACKED) {
		u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr;
		u32 delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ);

		seq_rtt_us = ca_rtt_us = delta_us;
	}
	rs->rtt_us = ca_rtt_us; /* RTT of last (S)ACKed packet (or -1) */
	if (seq_rtt_us < 0)
		return false;

	/* ca_rtt_us >= 0 is counting on the invariant that ca_rtt_us is
	 * always taken together with ACK, SACK, or TS-opts. Any negative
	 * values will be skipped with the seq_rtt_us < 0 check above.
	 */
	tcp_update_rtt_min(sk, ca_rtt_us, flag);
	tcp_rtt_estimator(sk, seq_rtt_us);
	tcp_set_rto(sk);

	/* RFC6298: only reset backoff on valid RTT measurement. */
	inet_csk(sk)->icsk_backoff = 0;
	return true;
}

/* Compute time elapsed between (last) SYNACK and the ACK completing 3WHS. */
void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req)
{
	struct rate_sample rs;
	long rtt_us = -1L;

	if (req && !req->num_retrans && tcp_rsk(req)->snt_synack)
		rtt_us = tcp_stamp_us_delta(tcp_clock_us(), tcp_rsk(req)->snt_synack);

	tcp_ack_update_rtt(sk, FLAG_SYN_ACKED, rtt_us, -1L, rtt_us, &rs);
}


static void tcp_cong_avoid(struct sock *sk, u32 ack, u32 acked)
{
	const struct inet_connection_sock *icsk = inet_csk(sk);

	icsk->icsk_ca_ops->cong_avoid(sk, ack, acked);
	tcp_sk(sk)->snd_cwnd_stamp = tcp_jiffies32;
}

/* Restart timer after forward progress on connection.
 * RFC2988 recommends to restart timer to now+rto.
 */
void tcp_rearm_rto(struct sock *sk)
{
	const struct inet_connection_sock *icsk = inet_csk(sk);
	struct tcp_sock *tp = tcp_sk(sk);

	/* If the retrans timer is currently being used by Fast Open
	 * for SYN-ACK retrans purpose, stay put.
	 */
	if (tp->fastopen_rsk)
		return;

	if (!tp->packets_out) {
		inet_csk_clear_xmit_timer(sk, ICSK_TIME_RETRANS);
	} else {
		u32 rto = inet_csk(sk)->icsk_rto;
		/* Offset the time elapsed after installing regular RTO */
		if (icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT ||
		    icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
			s64 delta_us = tcp_rto_delta_us(sk);
			/* delta_us may not be positive if the socket is locked
			 * when the retrans timer fires and is rescheduled.
			 */
			rto = usecs_to_jiffies(max_t(int, delta_us, 1));
		}
		inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, rto,
					  TCP_RTO_MAX);
	}
}

/* Try to schedule a loss probe; if that doesn't work, then schedule an RTO. */
static void tcp_set_xmit_timer(struct sock *sk)
{
	if (!tcp_schedule_loss_probe(sk, true))
		tcp_rearm_rto(sk);
}

/* If we get here, the whole TSO packet has not been acked. */
static u32 tcp_tso_acked(struct sock *sk, struct sk_buff *skb)
{
	struct tcp_sock *tp = tcp_sk(sk);
	u32 packets_acked;

	BUG_ON(!after(TCP_SKB_CB(skb)->end_seq, tp->snd_una));

	packets_acked = tcp_skb_pcount(skb);
	if (tcp_trim_head(sk, skb, tp->snd_una - TCP_SKB_CB(skb)->seq))
		return 0;
	packets_acked -= tcp_skb_pcount(skb);

	if (packets_acked) {
		BUG_ON(tcp_skb_pcount(skb) == 0);
		BUG_ON(!before(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq));
	}

	return packets_acked;
}

static void tcp_ack_tstamp(struct sock *sk, struct sk_buff *skb,
			   u32 prior_snd_una)
{
	const struct skb_shared_info *shinfo;

	/* Avoid cache line misses to get skb_shinfo() and shinfo->tx_flags */
	if (likely(!TCP_SKB_CB(skb)->txstamp_ack))
		return;

	shinfo = skb_shinfo(skb);
	if (!before(shinfo->tskey, prior_snd_una) &&
	    before(shinfo->tskey, tcp_sk(sk)->snd_una)) {
		tcp_skb_tsorted_save(skb) {
			__skb_tstamp_tx(skb, NULL, sk, SCM_TSTAMP_ACK);
		} tcp_skb_tsorted_restore(skb);
	}
}

/* Remove acknowledged frames from the retransmission queue. If our packet
 * is before the ack sequence we can discard it as it's confirmed to have
 * arrived at the other end.
 */
static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack,
			       u32 prior_snd_una,
			       struct tcp_sacktag_state *sack)
{
	const struct inet_connection_sock *icsk = inet_csk(sk);
	u64 first_ackt, last_ackt;
	struct tcp_sock *tp = tcp_sk(sk);
	u32 prior_sacked = tp->sacked_out;
	u32 reord = tp->snd_nxt; /* lowest acked un-retx un-sacked seq */
	struct sk_buff *skb, *next;
	bool fully_acked = true;
	long sack_rtt_us = -1L;
	long seq_rtt_us = -1L;
	long ca_rtt_us = -1L;
	u32 pkts_acked = 0;
	u32 last_in_flight = 0;
	bool rtt_update;
	int flag = 0;

	first_ackt = 0;

	for (skb = skb_rb_first(&sk->tcp_rtx_queue); skb; skb = next) {
		struct tcp_skb_cb *scb = TCP_SKB_CB(skb);
		const u32 start_seq = scb->seq;
		u8 sacked = scb->sacked;
		u32 acked_pcount;

		tcp_ack_tstamp(sk, skb, prior_snd_una);

		/* Determine how many packets and what bytes were acked, tso and else */
		if (after(scb->end_seq, tp->snd_una)) {
			if (tcp_skb_pcount(skb) == 1 ||
			    !after(tp->snd_una, scb->seq))
				break;

			acked_pcount = tcp_tso_acked(sk, skb);
			if (!acked_pcount)
				break;
			fully_acked = false;
		} else {
			acked_pcount = tcp_skb_pcount(skb);
		}

		if (unlikely(sacked & TCPCB_RETRANS)) {
			if (sacked & TCPCB_SACKED_RETRANS)
				tp->retrans_out -= acked_pcount;
			flag |= FLAG_RETRANS_DATA_ACKED;
		} else if (!(sacked & TCPCB_SACKED_ACKED)) {
			last_ackt = skb->skb_mstamp;
			WARN_ON_ONCE(last_ackt == 0);
			if (!first_ackt)
				first_ackt = last_ackt;

			last_in_flight = TCP_SKB_CB(skb)->tx.in_flight;
			if (before(start_seq, reord))
				reord = start_seq;
			if (!after(scb->end_seq, tp->high_seq))
				flag |= FLAG_ORIG_SACK_ACKED;
		}

		if (sacked & TCPCB_SACKED_ACKED) {
			tp->sacked_out -= acked_pcount;
		} else if (tcp_is_sack(tp)) {
			tp->delivered += acked_pcount;
			if (!tcp_skb_spurious_retrans(tp, skb))
				tcp_rack_advance(tp, sacked, scb->end_seq,
						 skb->skb_mstamp);
		}
		if (sacked & TCPCB_LOST)
			tp->lost_out -= acked_pcount;

		tp->packets_out -= acked_pcount;
		pkts_acked += acked_pcount;
		tcp_rate_skb_delivered(sk, skb, sack->rate);

		/* Initial outgoing SYN's get put onto the write_queue
		 * just like anything else we transmit.  It is not
		 * true data, and if we misinform our callers that
		 * this ACK acks real data, we will erroneously exit
		 * connection startup slow start one packet too
		 * quickly.  This is severely frowned upon behavior.
		 */
		if (likely(!(scb->tcp_flags & TCPHDR_SYN))) {
			flag |= FLAG_DATA_ACKED;
		} else {
			flag |= FLAG_SYN_ACKED;
			tp->retrans_stamp = 0;
		}

		if (!fully_acked)
			break;

		next = skb_rb_next(skb);
		if (unlikely(skb == tp->retransmit_skb_hint))
			tp->retransmit_skb_hint = NULL;
		if (unlikely(skb == tp->lost_skb_hint))
			tp->lost_skb_hint = NULL;
		tcp_rtx_queue_unlink_and_free(skb, sk);
	}

	if (!skb)
		tcp_chrono_stop(sk, TCP_CHRONO_BUSY);

	if (likely(between(tp->snd_up, prior_snd_una, tp->snd_una)))
		tp->snd_up = tp->snd_una;

	if (skb && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED))
		flag |= FLAG_SACK_RENEGING;

	if (likely(first_ackt) && !(flag & FLAG_RETRANS_DATA_ACKED)) {
		seq_rtt_us = tcp_stamp_us_delta(tp->tcp_mstamp, first_ackt);
		ca_rtt_us = tcp_stamp_us_delta(tp->tcp_mstamp, last_ackt);

		if (pkts_acked == 1 && last_in_flight < tp->mss_cache &&
		    last_in_flight && !prior_sacked && fully_acked &&
		    sack->rate->prior_delivered + 1 == tp->delivered &&
		    !(flag & (FLAG_CA_ALERT | FLAG_SYN_ACKED))) {
			/* Conservatively mark a delayed ACK. It's typically
			 * from a lone runt packet over the round trip to
			 * a receiver w/o out-of-order or CE events.
			 */
			flag |= FLAG_ACK_MAYBE_DELAYED;
		}
	}
	if (sack->first_sackt) {
		sack_rtt_us = tcp_stamp_us_delta(tp->tcp_mstamp, sack->first_sackt);
		ca_rtt_us = tcp_stamp_us_delta(tp->tcp_mstamp, sack->last_sackt);
	}
	rtt_update = tcp_ack_update_rtt(sk, flag, seq_rtt_us, sack_rtt_us,
					ca_rtt_us, sack->rate);

	if (flag & FLAG_ACKED) {
		flag |= FLAG_SET_XMIT_TIMER;  /* set TLP or RTO timer */
		if (unlikely(icsk->icsk_mtup.probe_size &&
			     !after(tp->mtu_probe.probe_seq_end, tp->snd_una))) {
			tcp_mtup_probe_success(sk);
		}

		if (tcp_is_reno(tp)) {
			tcp_remove_reno_sacks(sk, pkts_acked);

			/* If any of the cumulatively ACKed segments was
			 * retransmitted, non-SACK case cannot confirm that
			 * progress was due to original transmission due to
			 * lack of TCPCB_SACKED_ACKED bits even if some of
			 * the packets may have been never retransmitted.
			 */
			if (flag & FLAG_RETRANS_DATA_ACKED)
				flag &= ~FLAG_ORIG_SACK_ACKED;
		} else {
			int delta;

			/* Non-retransmitted hole got filled? That's reordering */
			if (before(reord, prior_fack))
				tcp_check_sack_reordering(sk, reord, 0);

			delta = prior_sacked - tp->sacked_out;
			tp->lost_cnt_hint -= min(tp->lost_cnt_hint, delta);
		}
	} else if (skb && rtt_update && sack_rtt_us >= 0 &&
		   sack_rtt_us > tcp_stamp_us_delta(tp->tcp_mstamp, skb->skb_mstamp)) {
		/* Do not re-arm RTO if the sack RTT is measured from data sent
		 * after when the head was last (re)transmitted. Otherwise the
		 * timeout may continue to extend in loss recovery.
		 */
		flag |= FLAG_SET_XMIT_TIMER;  /* set TLP or RTO timer */
	}

	if (icsk->icsk_ca_ops->pkts_acked) {
		struct ack_sample sample = { .pkts_acked = pkts_acked,
					     .rtt_us = sack->rate->rtt_us,
					     .in_flight = last_in_flight };

		icsk->icsk_ca_ops->pkts_acked(sk, &sample);
	}

#if FASTRETRANS_DEBUG > 0
	WARN_ON((int)tp->sacked_out < 0);
	WARN_ON((int)tp->lost_out < 0);
	WARN_ON((int)tp->retrans_out < 0);
	if (!tp->packets_out && tcp_is_sack(tp)) {
		icsk = inet_csk(sk);
		if (tp->lost_out) {
			pr_debug("Leak l=%u %d\n",
				 tp->lost_out, icsk->icsk_ca_state);
			tp->lost_out = 0;
		}
		if (tp->sacked_out) {
			pr_debug("Leak s=%u %d\n",
				 tp->sacked_out, icsk->icsk_ca_state);
			tp->sacked_out = 0;
		}
		if (tp->retrans_out) {
			pr_debug("Leak r=%u %d\n",
				 tp->retrans_out, icsk->icsk_ca_state);
			tp->retrans_out = 0;
		}
	}
#endif
	return flag;
}

static void tcp_ack_probe(struct sock *sk)
{
	struct inet_connection_sock *icsk = inet_csk(sk);
	struct sk_buff *head = tcp_send_head(sk);
	const struct tcp_sock *tp = tcp_sk(sk);

	/* Was it a usable window open? */
	if (!head)
		return;
	if (!after(TCP_SKB_CB(head)->end_seq, tcp_wnd_end(tp))) {
		icsk->icsk_backoff = 0;
		inet_csk_clear_xmit_timer(sk, ICSK_TIME_PROBE0);
		/* Socket must be waked up by subsequent tcp_data_snd_check().
		 * This function is not for random using!
		 */
	} else {
		unsigned long when = tcp_probe0_when(sk, TCP_RTO_MAX);

		inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0,
					  when, TCP_RTO_MAX);
	}
}

static inline bool tcp_ack_is_dubious(const struct sock *sk, const int flag)
{
	return !(flag & FLAG_NOT_DUP) || (flag & FLAG_CA_ALERT) ||
		inet_csk(sk)->icsk_ca_state != TCP_CA_Open;
}

/* Decide wheather to run the increase function of congestion control. */
static inline bool tcp_may_raise_cwnd(const struct sock *sk, const int flag)
{
	/* If reordering is high then always grow cwnd whenever data is
	 * delivered regardless of its ordering. Otherwise stay conservative
	 * and only grow cwnd on in-order delivery (RFC5681). A stretched ACK w/
	 * new SACK or ECE mark may first advance cwnd here and later reduce
	 * cwnd in tcp_fastretrans_alert() based on more states.
	 */
	if (tcp_sk(sk)->reordering > sock_net(sk)->ipv4.sysctl_tcp_reordering)
		return flag & FLAG_FORWARD_PROGRESS;

	return flag & FLAG_DATA_ACKED;
}

/* The "ultimate" congestion control function that aims to replace the rigid
 * cwnd increase and decrease control (tcp_cong_avoid,tcp_*cwnd_reduction).
 * It's called toward the end of processing an ACK with precise rate
 * information. All transmission or retransmission are delayed afterwards.
 */
static void tcp_cong_control(struct sock *sk, u32 ack, u32 acked_sacked,
			     int flag, const struct rate_sample *rs)
{
	const struct inet_connection_sock *icsk = inet_csk(sk);

	if (icsk->icsk_ca_ops->cong_control) {
		icsk->icsk_ca_ops->cong_control(sk, rs);
		return;
	}

	if (tcp_in_cwnd_reduction(sk)) {
		/* Reduce cwnd if state mandates */
		tcp_cwnd_reduction(sk, acked_sacked, flag);
	} else if (tcp_may_raise_cwnd(sk, flag)) {
		/* Advance cwnd if state allows */
		tcp_cong_avoid(sk, ack, acked_sacked);
	}
	tcp_update_pacing_rate(sk);
}

/* Check that window update is acceptable.
 * The function assumes that snd_una<=ack<=snd_next.
 */
static inline bool tcp_may_update_window(const struct tcp_sock *tp,
					const u32 ack, const u32 ack_seq,
					const u32 nwin)
{
	return	after(ack, tp->snd_una) ||
		after(ack_seq, tp->snd_wl1) ||
		(ack_seq == tp->snd_wl1 && nwin > tp->snd_wnd);
}

/* If we update tp->snd_una, also update tp->bytes_acked */
static void tcp_snd_una_update(struct tcp_sock *tp, u32 ack)
{
	u32 delta = ack - tp->snd_una;

	sock_owned_by_me((struct sock *)tp);
	tp->bytes_acked += delta;
	tp->snd_una = ack;
}

/* If we update tp->rcv_nxt, also update tp->bytes_received */
static void tcp_rcv_nxt_update(struct tcp_sock *tp, u32 seq)
{
	u32 delta = seq - tp->rcv_nxt;

	sock_owned_by_me((struct sock *)tp);
	tp->bytes_received += delta;
	tp->rcv_nxt = seq;
}

/* Update our send window.
 *
 * Window update algorithm, described in RFC793/RFC1122 (used in linux-2.2
 * and in FreeBSD. NetBSD's one is even worse.) is wrong.
 */
static int tcp_ack_update_window(struct sock *sk, const struct sk_buff *skb, u32 ack,
				 u32 ack_seq)
{
	struct tcp_sock *tp = tcp_sk(sk);
	int flag = 0;
	u32 nwin = ntohs(tcp_hdr(skb)->window);

	if (likely(!tcp_hdr(skb)->syn))
		nwin <<= tp->rx_opt.snd_wscale;

	if (tcp_may_update_window(tp, ack, ack_seq, nwin)) {
		flag |= FLAG_WIN_UPDATE;
		tcp_update_wl(tp, ack_seq);

		if (tp->snd_wnd != nwin) {
			tp->snd_wnd = nwin;

			/* Note, it is the only place, where
			 * fast path is recovered for sending TCP.
			 */
			tp->pred_flags = 0;
			tcp_fast_path_check(sk);

			if (!tcp_write_queue_empty(sk))
				tcp_slow_start_after_idle_check(sk);

			if (nwin > tp->max_window) {
				tp->max_window = nwin;
				tcp_sync_mss(sk, inet_csk(sk)->icsk_pmtu_cookie);
			}
		}
	}

	tcp_snd_una_update(tp, ack);

	return flag;
}

static bool __tcp_oow_rate_limited(struct net *net, int mib_idx,
				   u32 *last_oow_ack_time)
{
	if (*last_oow_ack_time) {
		s32 elapsed = (s32)(tcp_jiffies32 - *last_oow_ack_time);

		if (0 <= elapsed && elapsed < net->ipv4.sysctl_tcp_invalid_ratelimit) {
			NET_INC_STATS(net, mib_idx);
			return true;	/* rate-limited: don't send yet! */
		}
	}

	*last_oow_ack_time = tcp_jiffies32;

	return false;	/* not rate-limited: go ahead, send dupack now! */
}

/* Return true if we're currently rate-limiting out-of-window ACKs and
 * thus shouldn't send a dupack right now. We rate-limit dupacks in
 * response to out-of-window SYNs or ACKs to mitigate ACK loops or DoS
 * attacks that send repeated SYNs or ACKs for the same connection. To
 * do this, we do not send a duplicate SYNACK or ACK if the remote
 * endpoint is sending out-of-window SYNs or pure ACKs at a high rate.
 */
bool tcp_oow_rate_limited(struct net *net, const struct sk_buff *skb,
			  int mib_idx, u32 *last_oow_ack_time)
{
	/* Data packets without SYNs are not likely part of an ACK loop. */
	if ((TCP_SKB_CB(skb)->seq != TCP_SKB_CB(skb)->end_seq) &&
	    !tcp_hdr(skb)->syn)
		return false;

	return __tcp_oow_rate_limited(net, mib_idx, last_oow_ack_time);
}

/* RFC 5961 7 [ACK Throttling] */
static void tcp_send_challenge_ack(struct sock *sk, const struct sk_buff *skb)
{
	/* unprotected vars, we dont care of overwrites */
	static u32 challenge_timestamp;
	static unsigned int challenge_count;
	struct tcp_sock *tp = tcp_sk(sk);
	struct net *net = sock_net(sk);
	u32 count, now;

	/* First check our per-socket dupack rate limit. */
	if (__tcp_oow_rate_limited(net,
				   LINUX_MIB_TCPACKSKIPPEDCHALLENGE,
				   &tp->last_oow_ack_time))
		return;

	/* Then check host-wide RFC 5961 rate limit. */
	now = jiffies / HZ;
	if (now != challenge_timestamp) {
		u32 ack_limit = net->ipv4.sysctl_tcp_challenge_ack_limit;
		u32 half = (ack_limit + 1) >> 1;

		challenge_timestamp = now;
		WRITE_ONCE(challenge_count, half + prandom_u32_max(ack_limit));
	}
	count = READ_ONCE(challenge_count);
	if (count > 0) {
		WRITE_ONCE(challenge_count, count - 1);
		NET_INC_STATS(net, LINUX_MIB_TCPCHALLENGEACK);
		tcp_send_ack(sk);
	}
}

static void tcp_store_ts_recent(struct tcp_sock *tp)
{
	tp->rx_opt.ts_recent = tp->rx_opt.rcv_tsval;
	tp->rx_opt.ts_recent_stamp = get_seconds();
}

static void tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq)
{
	if (tp->rx_opt.saw_tstamp && !after(seq, tp->rcv_wup)) {
		/* PAWS bug workaround wrt. ACK frames, the PAWS discard
		 * extra check below makes sure this can only happen
		 * for pure ACK frames.  -DaveM
		 *
		 * Not only, also it occurs for expired timestamps.
		 */

		if (tcp_paws_check(&tp->rx_opt, 0))
			tcp_store_ts_recent(tp);
	}
}

/* This routine deals with acks during a TLP episode.
 * We mark the end of a TLP episode on receiving TLP dupack or when
 * ack is after tlp_high_seq.
 * Ref: loss detection algorithm in draft-dukkipati-tcpm-tcp-loss-probe.
 */
static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag)
{
	struct tcp_sock *tp = tcp_sk(sk);

	if (before(ack, tp->tlp_high_seq))
		return;

	if (flag & FLAG_DSACKING_ACK) {
		/* This DSACK means original and TLP probe arrived; no loss */
		tp->tlp_high_seq = 0;
	} else if (after(ack, tp->tlp_high_seq)) {
		/* ACK advances: there was a loss, so reduce cwnd. Reset
		 * tlp_high_seq in tcp_init_cwnd_reduction()
		 */
		tcp_init_cwnd_reduction(sk);
		tcp_set_ca_state(sk, TCP_CA_CWR);
		tcp_end_cwnd_reduction(sk);
		tcp_try_keep_open(sk);
		NET_INC_STATS(sock_net(sk),
				LINUX_MIB_TCPLOSSPROBERECOVERY);
	} else if (!(flag & (FLAG_SND_UNA_ADVANCED |
			     FLAG_NOT_DUP | FLAG_DATA_SACKED))) {
		/* Pure dupack: original and TLP probe arrived; no loss */
		tp->tlp_high_seq = 0;
	}
}

static inline void tcp_in_ack_event(struct sock *sk, u32 flags)
{
	const struct inet_connection_sock *icsk = inet_csk(sk);

	if (icsk->icsk_ca_ops->in_ack_event)
		icsk->icsk_ca_ops->in_ack_event(sk, flags);
}

/* Congestion control has updated the cwnd already. So if we're in
 * loss recovery then now we do any new sends (for FRTO) or
 * retransmits (for CA_Loss or CA_recovery) that make sense.
 */
static void tcp_xmit_recovery(struct sock *sk, int rexmit)
{
	struct tcp_sock *tp = tcp_sk(sk);

	if (rexmit == REXMIT_NONE)
		return;

	if (unlikely(rexmit == 2)) {
		__tcp_push_pending_frames(sk, tcp_current_mss(sk),
					  TCP_NAGLE_OFF);
		if (after(tp->snd_nxt, tp->high_seq))
			return;
		tp->frto = 0;
	}
	tcp_xmit_retransmit_queue(sk);
}

/* Returns the number of packets newly acked or sacked by the current ACK */
static u32 tcp_newly_delivered(struct sock *sk, u32 prior_delivered, int flag)
{
	const struct net *net = sock_net(sk);
	struct tcp_sock *tp = tcp_sk(sk);
	u32 delivered;

	delivered = tp->delivered - prior_delivered;
	NET_ADD_STATS(net, LINUX_MIB_TCPDELIVERED, delivered);
	if (flag & FLAG_ECE) {
		tp->delivered_ce += delivered;
		NET_ADD_STATS(net, LINUX_MIB_TCPDELIVEREDCE, delivered);
	}
	return delivered;
}

/* This routine deals with incoming acks, but not outgoing ones. */
static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
{
	struct inet_connection_sock *icsk = inet_csk(sk);
	struct tcp_sock *tp = tcp_sk(sk);
	struct tcp_sacktag_state sack_state;
	struct rate_sample rs = { .prior_delivered = 0 };
	u32 prior_snd_una = tp->snd_una;
	bool is_sack_reneg = tp->is_sack_reneg;
	u32 ack_seq = TCP_SKB_CB(skb)->seq;
	u32 ack = TCP_SKB_CB(skb)->ack_seq;
	bool is_dupack = false;
	int prior_packets = tp->packets_out;
	u32 delivered = tp->delivered;
	u32 lost = tp->lost;
	int rexmit = REXMIT_NONE; /* Flag to (re)transmit to recover losses */
	u32 prior_fack;

	sack_state.first_sackt = 0;
	sack_state.rate = &rs;

	/* We very likely will need to access rtx queue. */
	prefetch(sk->tcp_rtx_queue.rb_node);

	/* If the ack is older than previous acks
	 * then we can probably ignore it.
	 */
	if (before(ack, prior_snd_una)) {
		/* RFC 5961 5.2 [Blind Data Injection Attack].[Mitigation] */
		if (before(ack, prior_snd_una - tp->max_window)) {
			if (!(flag & FLAG_NO_CHALLENGE_ACK))
				tcp_send_challenge_ack(sk, skb);
			return -1;
		}
		goto old_ack;
	}

	/* If the ack includes data we haven't sent yet, discard
	 * this segment (RFC793 Section 3.9).
	 */
	if (after(ack, tp->snd_nxt))
		goto invalid_ack;

	if (after(ack, prior_snd_una)) {
		flag |= FLAG_SND_UNA_ADVANCED;
		icsk->icsk_retransmits = 0;

#if IS_ENABLED(CONFIG_TLS_DEVICE)
		if (static_branch_unlikely(&clean_acked_data_enabled))
			if (icsk->icsk_clean_acked)
				icsk->icsk_clean_acked(sk, ack);
#endif
	}

	prior_fack = tcp_is_sack(tp) ? tcp_highest_sack_seq(tp) : tp->snd_una;
	rs.prior_in_flight = tcp_packets_in_flight(tp);

	/* ts_recent update must be made after we are sure that the packet
	 * is in window.
	 */
	if (flag & FLAG_UPDATE_TS_RECENT)
		tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq);

	if (!(flag & FLAG_SLOWPATH) && after(ack, prior_snd_una)) {
		/* Window is constant, pure forward advance.
		 * No more checks are required.
		 * Note, we use the fact that SND.UNA>=SND.WL2.
		 */
		tcp_update_wl(tp, ack_seq);
		tcp_snd_una_update(tp, ack);
		flag |= FLAG_WIN_UPDATE;

		tcp_in_ack_event(sk, CA_ACK_WIN_UPDATE);

		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPHPACKS);
	} else {
		u32 ack_ev_flags = CA_ACK_SLOWPATH;

		if (ack_seq != TCP_SKB_CB(skb)->end_seq)
			flag |= FLAG_DATA;
		else
			NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPPUREACKS);

		flag |= tcp_ack_update_window(sk, skb, ack, ack_seq);

		if (TCP_SKB_CB(skb)->sacked)
			flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una,
							&sack_state);

		if (tcp_ecn_rcv_ecn_echo(tp, tcp_hdr(skb))) {
			flag |= FLAG_ECE;
			ack_ev_flags |= CA_ACK_ECE;
		}

		if (flag & FLAG_WIN_UPDATE)
			ack_ev_flags |= CA_ACK_WIN_UPDATE;

		tcp_in_ack_event(sk, ack_ev_flags);
	}

	/* We passed data and got it acked, remove any soft error
	 * log. Something worked...
	 */
	sk->sk_err_soft = 0;
	icsk->icsk_probes_out = 0;
	tp->rcv_tstamp = tcp_jiffies32;
	if (!prior_packets)
		goto no_queue;

	/* See if we can take anything off of the retransmit queue. */
	flag |= tcp_clean_rtx_queue(sk, prior_fack, prior_snd_una, &sack_state);

	tcp_rack_update_reo_wnd(sk, &rs);

	if (tp->tlp_high_seq)
		tcp_process_tlp_ack(sk, ack, flag);
	/* If needed, reset TLP/RTO timer; RACK may later override this. */
	if (flag & FLAG_SET_XMIT_TIMER)
		tcp_set_xmit_timer(sk);

	if (tcp_ack_is_dubious(sk, flag)) {
		is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP));
		tcp_fastretrans_alert(sk, prior_snd_una, is_dupack, &flag,
				      &rexmit);
	}

	if ((flag & FLAG_FORWARD_PROGRESS) || !(flag & FLAG_NOT_DUP))
		sk_dst_confirm(sk);

	delivered = tcp_newly_delivered(sk, delivered, flag);
	lost = tp->lost - lost;			/* freshly marked lost */
	rs.is_ack_delayed = !!(flag & FLAG_ACK_MAYBE_DELAYED);
	tcp_rate_gen(sk, delivered, lost, is_sack_reneg, sack_state.rate);
	tcp_cong_control(sk, ack, delivered, flag, sack_state.rate);
	tcp_xmit_recovery(sk, rexmit);
	return 1;

no_queue:
	/* If data was DSACKed, see if we can undo a cwnd reduction. */
	if (flag & FLAG_DSACKING_ACK) {
		tcp_fastretrans_alert(sk, prior_snd_una, is_dupack, &flag,
				      &rexmit);
		tcp_newly_delivered(sk, delivered, flag);
	}
	/* If this ack opens up a zero window, clear backoff.  It was
	 * being used to time the probes, and is probably far higher than
	 * it needs to be for normal retransmission.
	 */
	tcp_ack_probe(sk);

	if (tp->tlp_high_seq)
		tcp_process_tlp_ack(sk, ack, flag);
	return 1;

invalid_ack:
	SOCK_DEBUG(sk, "Ack %u after %u:%u\n", ack, tp->snd_una, tp->snd_nxt);
	return -1;

old_ack:
	/* If data was SACKed, tag it and see if we should send more data.
	 * If data was DSACKed, see if we can undo a cwnd reduction.
	 */
	if (TCP_SKB_CB(skb)->sacked) {
		flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una,
						&sack_state);
		tcp_fastretrans_alert(sk, prior_snd_una, is_dupack, &flag,
				      &rexmit);
		tcp_newly_delivered(sk, delivered, flag);
		tcp_xmit_recovery(sk, rexmit);
	}

	SOCK_DEBUG(sk, "Ack %u before %u:%u\n", ack, tp->snd_una, tp->snd_nxt);
	return 0;
}

static void tcp_parse_fastopen_option(int len, const unsigned char *cookie,
				      bool syn, struct tcp_fastopen_cookie *foc,
				      bool exp_opt)
{
	/* Valid only in SYN or SYN-ACK with an even length.  */
	if (!foc || !syn || len < 0 || (len & 1))
		return;

	if (len >= TCP_FASTOPEN_COOKIE_MIN &&
	    len <= TCP_FASTOPEN_COOKIE_MAX)
		memcpy(foc->val, cookie, len);
	else if (len != 0)
		len = -1;
	foc->len = len;
	foc->exp = exp_opt;
}

static void smc_parse_options(const struct tcphdr *th,
			      struct tcp_options_received *opt_rx,
			      const unsigned char *ptr,
			      int opsize)
{
#if IS_ENABLED(CONFIG_SMC)
	if (static_branch_unlikely(&tcp_have_smc)) {
		if (th->syn && !(opsize & 1) &&
		    opsize >= TCPOLEN_EXP_SMC_BASE &&
		    get_unaligned_be32(ptr) == TCPOPT_SMC_MAGIC)
			opt_rx->smc_ok = 1;
	}
#endif
}

/* Look for tcp options. Normally only called on SYN and SYNACK packets.
 * But, this can also be called on packets in the established flow when
 * the fast version below fails.
 */
void tcp_parse_options(const struct net *net,
		       const struct sk_buff *skb,
		       struct tcp_options_received *opt_rx, int estab,
		       struct tcp_fastopen_cookie *foc)
{
	const unsigned char *ptr;
	const struct tcphdr *th = tcp_hdr(skb);
	int length = (th->doff * 4) - sizeof(struct tcphdr);

	ptr = (const unsigned char *)(th + 1);
	opt_rx->saw_tstamp = 0;

	while (length > 0) {
		int opcode = *ptr++;
		int opsize;

		switch (opcode) {
		case TCPOPT_EOL:
			return;
		case TCPOPT_NOP:	/* Ref: RFC 793 section 3.1 */
			length--;
			continue;
		default:
			opsize = *ptr++;
			if (opsize < 2) /* "silly options" */
				return;
			if (opsize > length)
				return;	/* don't parse partial options */
			switch (opcode) {
			case TCPOPT_MSS:
				if (opsize == TCPOLEN_MSS && th->syn && !estab) {
					u16 in_mss = get_unaligned_be16(ptr);
					if (in_mss) {
						if (opt_rx->user_mss &&
						    opt_rx->user_mss < in_mss)
							in_mss = opt_rx->user_mss;
						opt_rx->mss_clamp = in_mss;
					}
				}
				break;
			case TCPOPT_WINDOW:
				if (opsize == TCPOLEN_WINDOW && th->syn &&
				    !estab && net->ipv4.sysctl_tcp_window_scaling) {
					__u8 snd_wscale = *(__u8 *)ptr;
					opt_rx->wscale_ok = 1;
					if (snd_wscale > TCP_MAX_WSCALE) {
						net_info_ratelimited("%s: Illegal window scaling value %d > %u received\n",
								     __func__,
								     snd_wscale,
								     TCP_MAX_WSCALE);
						snd_wscale = TCP_MAX_WSCALE;
					}
					opt_rx->snd_wscale = snd_wscale;
				}
				break;
			case TCPOPT_TIMESTAMP:
				if ((opsize == TCPOLEN_TIMESTAMP) &&
				    ((estab && opt_rx->tstamp_ok) ||
				     (!estab && net->ipv4.sysctl_tcp_timestamps))) {
					opt_rx->saw_tstamp = 1;
					opt_rx->rcv_tsval = get_unaligned_be32(ptr);
					opt_rx->rcv_tsecr = get_unaligned_be32(ptr + 4);
				}
				break;
			case TCPOPT_SACK_PERM:
				if (opsize == TCPOLEN_SACK_PERM && th->syn &&
				    !estab && net->ipv4.sysctl_tcp_sack) {
					opt_rx->sack_ok = TCP_SACK_SEEN;
					tcp_sack_reset(opt_rx);
				}
				break;

			case TCPOPT_SACK:
				if ((opsize >= (TCPOLEN_SACK_BASE + TCPOLEN_SACK_PERBLOCK)) &&
				   !((opsize - TCPOLEN_SACK_BASE) % TCPOLEN_SACK_PERBLOCK) &&
				   opt_rx->sack_ok) {
					TCP_SKB_CB(skb)->sacked = (ptr - 2) - (unsigned char *)th;
				}
				break;
#ifdef CONFIG_TCP_MD5SIG
			case TCPOPT_MD5SIG:
				/*
				 * The MD5 Hash has already been
				 * checked (see tcp_v{4,6}_do_rcv()).
				 */
				break;
#endif
			case TCPOPT_FASTOPEN:
				tcp_parse_fastopen_option(
					opsize - TCPOLEN_FASTOPEN_BASE,
					ptr, th->syn, foc, false);
				break;

			case TCPOPT_EXP:
				/* Fast Open option shares code 254 using a
				 * 16 bits magic number.
				 */
				if (opsize >= TCPOLEN_EXP_FASTOPEN_BASE &&
				    get_unaligned_be16(ptr) ==
				    TCPOPT_FASTOPEN_MAGIC)
					tcp_parse_fastopen_option(opsize -
						TCPOLEN_EXP_FASTOPEN_BASE,
						ptr + 2, th->syn, foc, true);
				else
					smc_parse_options(th, opt_rx, ptr,
							  opsize);
				break;

			}
			ptr += opsize-2;
			length -= opsize;
		}
	}
}
EXPORT_SYMBOL(tcp_parse_options);

static bool tcp_parse_aligned_timestamp(struct tcp_sock *tp, const struct tcphdr *th)
{
	const __be32 *ptr = (const __be32 *)(th + 1);

	if (*ptr == htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16)
			  | (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP)) {
		tp->rx_opt.saw_tstamp = 1;
		++ptr;
		tp->rx_opt.rcv_tsval = ntohl(*ptr);
		++ptr;
		if (*ptr)
			tp->rx_opt.rcv_tsecr = ntohl(*ptr) - tp->tsoffset;
		else
			tp->rx_opt.rcv_tsecr = 0;
		return true;
	}
	return false;
}

/* Fast parse options. This hopes to only see timestamps.
 * If it is wrong it falls back on tcp_parse_options().
 */
static bool tcp_fast_parse_options(const struct net *net,
				   const struct sk_buff *skb,
				   const struct tcphdr *th, struct tcp_sock *tp)
{
	/* In the spirit of fast parsing, compare doff directly to constant
	 * values.  Because equality is used, short doff can be ignored here.
	 */
	if (th->doff == (sizeof(*th) / 4)) {
		tp->rx_opt.saw_tstamp = 0;
		return false;
	} else if (tp->rx_opt.tstamp_ok &&
		   th->doff == ((sizeof(*th) + TCPOLEN_TSTAMP_ALIGNED) / 4)) {
		if (tcp_parse_aligned_timestamp(tp, th))
			return true;
	}

	tcp_parse_options(net, skb, &tp->rx_opt, 1, NULL);
	if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr)
		tp->rx_opt.rcv_tsecr -= tp->tsoffset;

	return true;
}

#ifdef CONFIG_TCP_MD5SIG
/*
 * Parse MD5 Signature option
 */
const u8 *tcp_parse_md5sig_option(const struct tcphdr *th)
{
	int length = (th->doff << 2) - sizeof(*th);
	const u8 *ptr = (const u8 *)(th + 1);

	/* If not enough data remaining, we can short cut */
	while (length >= TCPOLEN_MD5SIG) {
		int opcode = *ptr++;
		int opsize;

		switch (opcode) {
		case TCPOPT_EOL:
			return NULL;
		case TCPOPT_NOP:
			length--;
			continue;
		default:
			opsize = *ptr++;
			if (opsize < 2 || opsize > length)
				return NULL;
			if (opcode == TCPOPT_MD5SIG)
				return opsize == TCPOLEN_MD5SIG ? ptr : NULL;
		}
		ptr += opsize - 2;
		length -= opsize;
	}
	return NULL;
}
EXPORT_SYMBOL(tcp_parse_md5sig_option);
#endif

/* Sorry, PAWS as specified is broken wrt. pure-ACKs -DaveM
 *
 * It is not fatal. If this ACK does _not_ change critical state (seqs, window)
 * it can pass through stack. So, the following predicate verifies that
 * this segment is not used for anything but congestion avoidance or
 * fast retransmit. Moreover, we even are able to eliminate most of such
 * second order effects, if we apply some small "replay" window (~RTO)
 * to timestamp space.
 *
 * All these measures still do not guarantee that we reject wrapped ACKs
 * on networks with high bandwidth, when sequence space is recycled fastly,
 * but it guarantees that such events will be very rare and do not affect
 * connection seriously. This doesn't look nice, but alas, PAWS is really
 * buggy extension.
 *
 * [ Later note. Even worse! It is buggy for segments _with_ data. RFC
 * states that events when retransmit arrives after original data are rare.
 * It is a blatant lie. VJ forgot about fast retransmit! 8)8) It is
 * the biggest problem on large power networks even with minor reordering.
 * OK, let's give it small replay window. If peer clock is even 1hz, it is safe
 * up to bandwidth of 18Gigabit/sec. 8) ]
 */

static int tcp_disordered_ack(const struct sock *sk, const struct sk_buff *skb)
{
	const struct tcp_sock *tp = tcp_sk(sk);
	const struct tcphdr *th = tcp_hdr(skb);
	u32 seq = TCP_SKB_CB(skb)->seq;
	u32 ack = TCP_SKB_CB(skb)->ack_seq;

	return (/* 1. Pure ACK with correct sequence number. */
		(th->ack && seq == TCP_SKB_CB(skb)->end_seq && seq == tp->rcv_nxt) &&

		/* 2. ... and duplicate ACK. */
		ack == tp->snd_una &&

		/* 3. ... and does not update window. */
		!tcp_may_update_window(tp, ack, seq, ntohs(th->window) << tp->rx_opt.snd_wscale) &&

		/* 4. ... and sits in replay window. */
		(s32)(tp->rx_opt.ts_recent - tp->rx_opt.rcv_tsval) <= (inet_csk(sk)->icsk_rto * 1024) / HZ);
}

static inline bool tcp_paws_discard(const struct sock *sk,
				   const struct sk_buff *skb)
{
	const struct tcp_sock *tp = tcp_sk(sk);

	return !tcp_paws_check(&tp->rx_opt, TCP_PAWS_WINDOW) &&
	       !tcp_disordered_ack(sk, skb);
}

/* Check segment sequence number for validity.
 *
 * Segment controls are considered valid, if the segment
 * fits to the window after truncation to the window. Acceptability
 * of data (and SYN, FIN, of course) is checked separately.
 * See tcp_data_queue(), for example.
 *
 * Also, controls (RST is main one) are accepted using RCV.WUP instead
 * of RCV.NXT. Peer still did not advance his SND.UNA when we
 * delayed ACK, so that hisSND.UNA<=ourRCV.WUP.
 * (borrowed from freebsd)
 */

static inline bool tcp_sequence(const struct tcp_sock *tp, u32 seq, u32 end_seq)
{
	return	!before(end_seq, tp->rcv_wup) &&
		!after(seq, tp->rcv_nxt + tcp_receive_window(tp));
}

/* When we get a reset we do this. */
void tcp_reset(struct sock *sk)
{
	trace_tcp_receive_reset(sk);

	/* We want the right error as BSD sees it (and indeed as we do). */
	switch (sk->sk_state) {
	case TCP_SYN_SENT:
		sk->sk_err = ECONNREFUSED;
		break;
	case TCP_CLOSE_WAIT:
		sk->sk_err = EPIPE;
		break;
	case TCP_CLOSE:
		return;
	default:
		sk->sk_err = ECONNRESET;
	}
	/* This barrier is coupled with smp_rmb() in tcp_poll() */
	smp_wmb();

	tcp_write_queue_purge(sk);
	tcp_done(sk);

	if (!sock_flag(sk, SOCK_DEAD))
		sk->sk_error_report(sk);
}

/*
 * 	Process the FIN bit. This now behaves as it is supposed to work
 *	and the FIN takes effect when it is validly part of sequence
 *	space. Not before when we get holes.
 *
 *	If we are ESTABLISHED, a received fin moves us to CLOSE-WAIT
 *	(and thence onto LAST-ACK and finally, CLOSE, we never enter
 *	TIME-WAIT)
 *
 *	If we are in FINWAIT-1, a received FIN indicates simultaneous
 *	close and we go into CLOSING (and later onto TIME-WAIT)
 *
 *	If we are in FINWAIT-2, a received FIN moves us to TIME-WAIT.
 */
void tcp_fin(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);

	inet_csk_schedule_ack(sk);

	sk->sk_shutdown |= RCV_SHUTDOWN;
	sock_set_flag(sk, SOCK_DONE);

	switch (sk->sk_state) {
	case TCP_SYN_RECV:
	case TCP_ESTABLISHED:
		/* Move to CLOSE_WAIT */
		tcp_set_state(sk, TCP_CLOSE_WAIT);
		inet_csk(sk)->icsk_ack.pingpong = 1;
		break;

	case TCP_CLOSE_WAIT:
	case TCP_CLOSING:
		/* Received a retransmission of the FIN, do
		 * nothing.
		 */
		break;
	case TCP_LAST_ACK:
		/* RFC793: Remain in the LAST-ACK state. */
		break;

	case TCP_FIN_WAIT1:
		/* This case occurs when a simultaneous close
		 * happens, we must ack the received FIN and
		 * enter the CLOSING state.
		 */
		tcp_send_ack(sk);
		tcp_set_state(sk, TCP_CLOSING);
		break;
	case TCP_FIN_WAIT2:
		/* Received a FIN -- send ACK and enter TIME_WAIT. */
		tcp_send_ack(sk);
		tcp_time_wait(sk, TCP_TIME_WAIT, 0);
		break;
	default:
		/* Only TCP_LISTEN and TCP_CLOSE are left, in these
		 * cases we should never reach this piece of code.
		 */
		pr_err("%s: Impossible, sk->sk_state=%d\n",
		       __func__, sk->sk_state);
		break;
	}

	/* It _is_ possible, that we have something out-of-order _after_ FIN.
	 * Probably, we should reset in this case. For now drop them.
	 */
	skb_rbtree_purge(&tp->out_of_order_queue);
	if (tcp_is_sack(tp))
		tcp_sack_reset(&tp->rx_opt);
	sk_mem_reclaim(sk);

	if (!sock_flag(sk, SOCK_DEAD)) {
		sk->sk_state_change(sk);

		/* Do not send POLL_HUP for half duplex close. */
		if (sk->sk_shutdown == SHUTDOWN_MASK ||
		    sk->sk_state == TCP_CLOSE)
			sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_HUP);
		else
			sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN);
	}
}

static inline bool tcp_sack_extend(struct tcp_sack_block *sp, u32 seq,
				  u32 end_seq)
{
	if (!after(seq, sp->end_seq) && !after(sp->start_seq, end_seq)) {
		if (before(seq, sp->start_seq))
			sp->start_seq = seq;
		if (after(end_seq, sp->end_seq))
			sp->end_seq = end_seq;
		return true;
	}
	return false;
}

static void tcp_dsack_set(struct sock *sk, u32 seq, u32 end_seq)
{
	struct tcp_sock *tp = tcp_sk(sk);

	if (tcp_is_sack(tp) && sock_net(sk)->ipv4.sysctl_tcp_dsack) {
		int mib_idx;

		if (before(seq, tp->rcv_nxt))
			mib_idx = LINUX_MIB_TCPDSACKOLDSENT;
		else
			mib_idx = LINUX_MIB_TCPDSACKOFOSENT;

		NET_INC_STATS(sock_net(sk), mib_idx);

		tp->rx_opt.dsack = 1;
		tp->duplicate_sack[0].start_seq = seq;
		tp->duplicate_sack[0].end_seq = end_seq;
	}
}

static void tcp_dsack_extend(struct sock *sk, u32 seq, u32 end_seq)
{
	struct tcp_sock *tp = tcp_sk(sk);

	if (!tp->rx_opt.dsack)
		tcp_dsack_set(sk, seq, end_seq);
	else
		tcp_sack_extend(tp->duplicate_sack, seq, end_seq);
}

static void tcp_send_dupack(struct sock *sk, const struct sk_buff *skb)
{
	struct tcp_sock *tp = tcp_sk(sk);

	if (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq &&
	    before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) {
		NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOST);
		tcp_enter_quickack_mode(sk, TCP_MAX_QUICKACKS);

		if (tcp_is_sack(tp) && sock_net(sk)->ipv4.sysctl_tcp_dsack) {
			u32 end_seq = TCP_SKB_CB(skb)->end_seq;

			if (after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt))
				end_seq = tp->rcv_nxt;
			tcp_dsack_set(sk, TCP_SKB_CB(skb)->seq, end_seq);
		}
	}

	tcp_send_ack(sk);
}

/* These routines update the SACK block as out-of-order packets arrive or
 * in-order packets close up the sequence space.
 */
static void tcp_sack_maybe_coalesce(struct tcp_sock *tp)
{
	int this_sack;
	struct tcp_sack_block *sp = &tp->selective_acks[0];
	struct tcp_sack_block *swalk = sp + 1;

	/* See if the recent change to the first SACK eats into
	 * or hits the sequence space of other SACK blocks, if so coalesce.
	 */
	for (this_sack = 1; this_sack < tp->rx_opt.num_sacks;) {
		if (tcp_sack_extend(sp, swalk->start_seq, swalk->end_seq)) {
			int i;

			/* Zap SWALK, by moving every further SACK up by one slot.
			 * Decrease num_sacks.
			 */
			tp->rx_opt.num_sacks--;
			for (i = this_sack; i < tp->rx_opt.num_sacks; i++)
				sp[i] = sp[i + 1];
			continue;
		}
		this_sack++, swalk++;
	}
}

static void tcp_sack_new_ofo_skb(struct sock *sk, u32 seq, u32 end_seq)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct tcp_sack_block *sp = &tp->selective_acks[0];
	int cur_sacks = tp->rx_opt.num_sacks;
	int this_sack;

	if (!cur_sacks)
		goto new_sack;

	for (this_sack = 0; this_sack < cur_sacks; this_sack++, sp++) {
		if (tcp_sack_extend(sp, seq, end_seq)) {
			/* Rotate this_sack to the first one. */
			for (; this_sack > 0; this_sack--, sp--)
				swap(*sp, *(sp - 1));
			if (cur_sacks > 1)
				tcp_sack_maybe_coalesce(tp);
			return;
		}
	}

	/* Could not find an adjacent existing SACK, build a new one,
	 * put it at the front, and shift everyone else down.  We
	 * always know there is at least one SACK present already here.
	 *
	 * If the sack array is full, forget about the last one.
	 */
	if (this_sack >= TCP_NUM_SACKS) {
		if (tp->compressed_ack)
			tcp_send_ack(sk);
		this_sack--;
		tp->rx_opt.num_sacks--;
		sp--;
	}
	for (; this_sack > 0; this_sack--, sp--)
		*sp = *(sp - 1);

new_sack:
	/* Build the new head SACK, and we're done. */
	sp->start_seq = seq;
	sp->end_seq = end_seq;
	tp->rx_opt.num_sacks++;
}

/* RCV.NXT advances, some SACKs should be eaten. */

static void tcp_sack_remove(struct tcp_sock *tp)
{
	struct tcp_sack_block *sp = &tp->selective_acks[0];
	int num_sacks = tp->rx_opt.num_sacks;
	int this_sack;

	/* Empty ofo queue, hence, all the SACKs are eaten. Clear. */
	if (RB_EMPTY_ROOT(&tp->out_of_order_queue)) {
		tp->rx_opt.num_sacks = 0;
		return;
	}

	for (this_sack = 0; this_sack < num_sacks;) {
		/* Check if the start of the sack is covered by RCV.NXT. */
		if (!before(tp->rcv_nxt, sp->start_seq)) {
			int i;

			/* RCV.NXT must cover all the block! */
			WARN_ON(before(tp->rcv_nxt, sp->end_seq));

			/* Zap this SACK, by moving forward any other SACKS. */
			for (i = this_sack+1; i < num_sacks; i++)
				tp->selective_acks[i-1] = tp->selective_acks[i];
			num_sacks--;
			continue;
		}
		this_sack++;
		sp++;
	}
	tp->rx_opt.num_sacks = num_sacks;
}

/**
 * tcp_try_coalesce - try to merge skb to prior one
 * @sk: socket
 * @dest: destination queue
 * @to: prior buffer
 * @from: buffer to add in queue
 * @fragstolen: pointer to boolean
 *
 * Before queueing skb @from after @to, try to merge them
 * to reduce overall memory use and queue lengths, if cost is small.
 * Packets in ofo or receive queues can stay a long time.
 * Better try to coalesce them right now to avoid future collapses.
 * Returns true if caller should free @from instead of queueing it
 */
static bool tcp_try_coalesce(struct sock *sk,
			     struct sk_buff *to,
			     struct sk_buff *from,
			     bool *fragstolen)
{
	int delta;

	*fragstolen = false;

	/* Its possible this segment overlaps with prior segment in queue */
	if (TCP_SKB_CB(from)->seq != TCP_SKB_CB(to)->end_seq)
		return false;

	if (!skb_try_coalesce(to, from, fragstolen, &delta))
		return false;

	atomic_add(delta, &sk->sk_rmem_alloc);
	sk_mem_charge(sk, delta);
	NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRCVCOALESCE);
	TCP_SKB_CB(to)->end_seq = TCP_SKB_CB(from)->end_seq;
	TCP_SKB_CB(to)->ack_seq = TCP_SKB_CB(from)->ack_seq;
	TCP_SKB_CB(to)->tcp_flags |= TCP_SKB_CB(from)->tcp_flags;

	if (TCP_SKB_CB(from)->has_rxtstamp) {
		TCP_SKB_CB(to)->has_rxtstamp = true;
		to->tstamp = from->tstamp;
	}

	return true;
}

static bool tcp_ooo_try_coalesce(struct sock *sk,
			     struct sk_buff *to,
			     struct sk_buff *from,
			     bool *fragstolen)
{
	bool res = tcp_try_coalesce(sk, to, from, fragstolen);

	/* In case tcp_drop() is called later, update to->gso_segs */
	if (res) {
		u32 gso_segs = max_t(u16, 1, skb_shinfo(to)->gso_segs) +
			       max_t(u16, 1, skb_shinfo(from)->gso_segs);

		skb_shinfo(to)->gso_segs = min_t(u32, gso_segs, 0xFFFF);
	}
	return res;
}

static void tcp_drop(struct sock *sk, struct sk_buff *skb)
{
	sk_drops_add(sk, skb);
	__kfree_skb(skb);
}

/* This one checks to see if we can put data from the
 * out_of_order queue into the receive_queue.
 */
static void tcp_ofo_queue(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);
	__u32 dsack_high = tp->rcv_nxt;
	bool fin, fragstolen, eaten;
	struct sk_buff *skb, *tail;
	struct rb_node *p;

	p = rb_first(&tp->out_of_order_queue);
	while (p) {
		skb = rb_to_skb(p);
		if (after(TCP_SKB_CB(skb)->seq, tp->rcv_nxt))
			break;

		if (before(TCP_SKB_CB(skb)->seq, dsack_high)) {
			__u32 dsack = dsack_high;
			if (before(TCP_SKB_CB(skb)->end_seq, dsack_high))
				dsack_high = TCP_SKB_CB(skb)->end_seq;
			tcp_dsack_extend(sk, TCP_SKB_CB(skb)->seq, dsack);
		}
		p = rb_next(p);
		rb_erase(&skb->rbnode, &tp->out_of_order_queue);

		if (unlikely(!after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt))) {
			SOCK_DEBUG(sk, "ofo packet was already received\n");
			tcp_drop(sk, skb);
			continue;
		}
		SOCK_DEBUG(sk, "ofo requeuing : rcv_next %X seq %X - %X\n",
			   tp->rcv_nxt, TCP_SKB_CB(skb)->seq,
			   TCP_SKB_CB(skb)->end_seq);

		tail = skb_peek_tail(&sk->sk_receive_queue);
		eaten = tail && tcp_try_coalesce(sk, tail, skb, &fragstolen);
		tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq);
		fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN;
		if (!eaten)
			__skb_queue_tail(&sk->sk_receive_queue, skb);
		else
			kfree_skb_partial(skb, fragstolen);

		if (unlikely(fin)) {
			tcp_fin(sk);
			/* tcp_fin() purges tp->out_of_order_queue,
			 * so we must end this loop right now.
			 */
			break;
		}
	}
}

static bool tcp_prune_ofo_queue(struct sock *sk);
static int tcp_prune_queue(struct sock *sk);

static int tcp_try_rmem_schedule(struct sock *sk, struct sk_buff *skb,
				 unsigned int size)
{
	if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf ||
	    !sk_rmem_schedule(sk, skb, size)) {

		if (tcp_prune_queue(sk) < 0)
			return -1;

		while (!sk_rmem_schedule(sk, skb, size)) {
			if (!tcp_prune_ofo_queue(sk))
				return -1;
		}
	}
	return 0;
}

static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct rb_node **p, *parent;
	struct sk_buff *skb1;
	u32 seq, end_seq;
	bool fragstolen;

	tcp_ecn_check_ce(sk, skb);

	if (unlikely(tcp_try_rmem_schedule(sk, skb, skb->truesize))) {
		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFODROP);
		tcp_drop(sk, skb);
		return;
	}

	/* Disable header prediction. */
	tp->pred_flags = 0;
	inet_csk_schedule_ack(sk);

	NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFOQUEUE);
	seq = TCP_SKB_CB(skb)->seq;
	end_seq = TCP_SKB_CB(skb)->end_seq;
	SOCK_DEBUG(sk, "out of order segment: rcv_next %X seq %X - %X\n",
		   tp->rcv_nxt, seq, end_seq);

	p = &tp->out_of_order_queue.rb_node;
	if (RB_EMPTY_ROOT(&tp->out_of_order_queue)) {
		/* Initial out of order segment, build 1 SACK. */
		if (tcp_is_sack(tp)) {
			tp->rx_opt.num_sacks = 1;
			tp->selective_acks[0].start_seq = seq;
			tp->selective_acks[0].end_seq = end_seq;
		}
		rb_link_node(&skb->rbnode, NULL, p);
		rb_insert_color(&skb->rbnode, &tp->out_of_order_queue);
		tp->ooo_last_skb = skb;
		goto end;
	}

	/* In the typical case, we are adding an skb to the end of the list.
	 * Use of ooo_last_skb avoids the O(Log(N)) rbtree lookup.
	 */
	if (tcp_ooo_try_coalesce(sk, tp->ooo_last_skb,
				 skb, &fragstolen)) {
coalesce_done:
		tcp_grow_window(sk, skb);
		kfree_skb_partial(skb, fragstolen);
		skb = NULL;
		goto add_sack;
	}
	/* Can avoid an rbtree lookup if we are adding skb after ooo_last_skb */
	if (!before(seq, TCP_SKB_CB(tp->ooo_last_skb)->end_seq)) {
		parent = &tp->ooo_last_skb->rbnode;
		p = &parent->rb_right;
		goto insert;
	}

	/* Find place to insert this segment. Handle overlaps on the way. */
	parent = NULL;
	while (*p) {
		parent = *p;
		skb1 = rb_to_skb(parent);
		if (before(seq, TCP_SKB_CB(skb1)->seq)) {
			p = &parent->rb_left;
			continue;
		}
		if (before(seq, TCP_SKB_CB(skb1)->end_seq)) {
			if (!after(end_seq, TCP_SKB_CB(skb1)->end_seq)) {
				/* All the bits are present. Drop. */
				NET_INC_STATS(sock_net(sk),
					      LINUX_MIB_TCPOFOMERGE);
				tcp_drop(sk, skb);
				skb = NULL;
				tcp_dsack_set(sk, seq, end_seq);
				goto add_sack;
			}
			if (after(seq, TCP_SKB_CB(skb1)->seq)) {
				/* Partial overlap. */
				tcp_dsack_set(sk, seq, TCP_SKB_CB(skb1)->end_seq);
			} else {
				/* skb's seq == skb1's seq and skb covers skb1.
				 * Replace skb1 with skb.
				 */
				rb_replace_node(&skb1->rbnode, &skb->rbnode,
						&tp->out_of_order_queue);
				tcp_dsack_extend(sk,
						 TCP_SKB_CB(skb1)->seq,
						 TCP_SKB_CB(skb1)->end_seq);
				NET_INC_STATS(sock_net(sk),
					      LINUX_MIB_TCPOFOMERGE);
				tcp_drop(sk, skb1);
				goto merge_right;
			}
		} else if (tcp_ooo_try_coalesce(sk, skb1,
						skb, &fragstolen)) {
			goto coalesce_done;
		}
		p = &parent->rb_right;
	}
insert:
	/* Insert segment into RB tree. */
	rb_link_node(&skb->rbnode, parent, p);
	rb_insert_color(&skb->rbnode, &tp->out_of_order_queue);

merge_right:
	/* Remove other segments covered by skb. */
	while ((skb1 = skb_rb_next(skb)) != NULL) {
		if (!after(end_seq, TCP_SKB_CB(skb1)->seq))
			break;
		if (before(end_seq, TCP_SKB_CB(skb1)->end_seq)) {
			tcp_dsack_extend(sk, TCP_SKB_CB(skb1)->seq,
					 end_seq);
			break;
		}
		rb_erase(&skb1->rbnode, &tp->out_of_order_queue);
		tcp_dsack_extend(sk, TCP_SKB_CB(skb1)->seq,
				 TCP_SKB_CB(skb1)->end_seq);
		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFOMERGE);
		tcp_drop(sk, skb1);
	}
	/* If there is no skb after us, we are the last_skb ! */
	if (!skb1)
		tp->ooo_last_skb = skb;

add_sack:
	if (tcp_is_sack(tp))
		tcp_sack_new_ofo_skb(sk, seq, end_seq);
end:
	if (skb) {
		tcp_grow_window(sk, skb);
		skb_condense(skb);
		skb_set_owner_r(skb, sk);
	}
}

static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, int hdrlen,
		  bool *fragstolen)
{
	int eaten;
	struct sk_buff *tail = skb_peek_tail(&sk->sk_receive_queue);

	__skb_pull(skb, hdrlen);
	eaten = (tail &&
		 tcp_try_coalesce(sk, tail,
				  skb, fragstolen)) ? 1 : 0;
	tcp_rcv_nxt_update(tcp_sk(sk), TCP_SKB_CB(skb)->end_seq);
	if (!eaten) {
		__skb_queue_tail(&sk->sk_receive_queue, skb);
		skb_set_owner_r(skb, sk);
	}
	return eaten;
}

int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size)
{
	struct sk_buff *skb;
	int err = -ENOMEM;
	int data_len = 0;
	bool fragstolen;

	if (size == 0)
		return 0;

	if (size > PAGE_SIZE) {
		int npages = min_t(size_t, size >> PAGE_SHIFT, MAX_SKB_FRAGS);

		data_len = npages << PAGE_SHIFT;
		size = data_len + (size & ~PAGE_MASK);
	}
	skb = alloc_skb_with_frags(size - data_len, data_len,
				   PAGE_ALLOC_COSTLY_ORDER,
				   &err, sk->sk_allocation);
	if (!skb)
		goto err;

	skb_put(skb, size - data_len);
	skb->data_len = data_len;
	skb->len = size;

	if (tcp_try_rmem_schedule(sk, skb, skb->truesize))
		goto err_free;

	err = skb_copy_datagram_from_iter(skb, 0, &msg->msg_iter, size);
	if (err)
		goto err_free;

	TCP_SKB_CB(skb)->seq = tcp_sk(sk)->rcv_nxt;
	TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(skb)->seq + size;
	TCP_SKB_CB(skb)->ack_seq = tcp_sk(sk)->snd_una - 1;

	if (tcp_queue_rcv(sk, skb, 0, &fragstolen)) {
		WARN_ON_ONCE(fragstolen); /* should not happen */
		__kfree_skb(skb);
	}
	return size;

err_free:
	kfree_skb(skb);
err:
	return err;

}

void tcp_data_ready(struct sock *sk)
{
	const struct tcp_sock *tp = tcp_sk(sk);
	int avail = tp->rcv_nxt - tp->copied_seq;

	if (avail < sk->sk_rcvlowat && !sock_flag(sk, SOCK_DONE))
		return;

	sk->sk_data_ready(sk);
}

static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
{
	struct tcp_sock *tp = tcp_sk(sk);
	bool fragstolen;
	int eaten;

	if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) {
		__kfree_skb(skb);
		return;
	}
	skb_dst_drop(skb);
	__skb_pull(skb, tcp_hdr(skb)->doff * 4);

	tcp_ecn_accept_cwr(tp, skb);

	tp->rx_opt.dsack = 0;

	/*  Queue data for delivery to the user.
	 *  Packets in sequence go to the receive queue.
	 *  Out of sequence packets to the out_of_order_queue.
	 */
	if (TCP_SKB_CB(skb)->seq == tp->rcv_nxt) {
		if (tcp_receive_window(tp) == 0)
			goto out_of_window;

		/* Ok. In sequence. In window. */
queue_and_out:
		if (skb_queue_len(&sk->sk_receive_queue) == 0)
			sk_forced_mem_schedule(sk, skb->truesize);
		else if (tcp_try_rmem_schedule(sk, skb, skb->truesize))
			goto drop;

		eaten = tcp_queue_rcv(sk, skb, 0, &fragstolen);
		tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq);
		if (skb->len)
			tcp_event_data_recv(sk, skb);
		if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
			tcp_fin(sk);

		if (!RB_EMPTY_ROOT(&tp->out_of_order_queue)) {
			tcp_ofo_queue(sk);

			/* RFC2581. 4.2. SHOULD send immediate ACK, when
			 * gap in queue is filled.
			 */
			if (RB_EMPTY_ROOT(&tp->out_of_order_queue))
				inet_csk(sk)->icsk_ack.pingpong = 0;
		}

		if (tp->rx_opt.num_sacks)
			tcp_sack_remove(tp);

		tcp_fast_path_check(sk);

		if (eaten > 0)
			kfree_skb_partial(skb, fragstolen);
		if (!sock_flag(sk, SOCK_DEAD))
			tcp_data_ready(sk);
		return;
	}

	if (!after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt)) {
		/* A retransmit, 2nd most common case.  Force an immediate ack. */
		NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOST);
		tcp_dsack_set(sk, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq);

out_of_window:
		tcp_enter_quickack_mode(sk, TCP_MAX_QUICKACKS);
		inet_csk_schedule_ack(sk);
drop:
		tcp_drop(sk, skb);
		return;
	}

	/* Out of window. F.e. zero window probe. */
	if (!before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt + tcp_receive_window(tp)))
		goto out_of_window;

	if (before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) {
		/* Partial packet, seq < rcv_next < end_seq */
		SOCK_DEBUG(sk, "partial packet: rcv_next %X seq %X - %X\n",
			   tp->rcv_nxt, TCP_SKB_CB(skb)->seq,
			   TCP_SKB_CB(skb)->end_seq);

		tcp_dsack_set(sk, TCP_SKB_CB(skb)->seq, tp->rcv_nxt);

		/* If window is closed, drop tail of packet. But after
		 * remembering D-SACK for its head made in previous line.
		 */
		if (!tcp_receive_window(tp))
			goto out_of_window;
		goto queue_and_out;
	}

	tcp_data_queue_ofo(sk, skb);
}

static struct sk_buff *tcp_skb_next(struct sk_buff *skb, struct sk_buff_head *list)
{
	if (list)
		return !skb_queue_is_last(list, skb) ? skb->next : NULL;

	return skb_rb_next(skb);
}

static struct sk_buff *tcp_collapse_one(struct sock *sk, struct sk_buff *skb,
					struct sk_buff_head *list,
					struct rb_root *root)
{
	struct sk_buff *next = tcp_skb_next(skb, list);

	if (list)
		__skb_unlink(skb, list);
	else
		rb_erase(&skb->rbnode, root);

	__kfree_skb(skb);
	NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRCVCOLLAPSED);

	return next;
}

/* Insert skb into rb tree, ordered by TCP_SKB_CB(skb)->seq */
void tcp_rbtree_insert(struct rb_root *root, struct sk_buff *skb)
{
	struct rb_node **p = &root->rb_node;
	struct rb_node *parent = NULL;
	struct sk_buff *skb1;

	while (*p) {
		parent = *p;
		skb1 = rb_to_skb(parent);
		if (before(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb1)->seq))
			p = &parent->rb_left;
		else
			p = &parent->rb_right;
	}
	rb_link_node(&skb->rbnode, parent, p);
	rb_insert_color(&skb->rbnode, root);
}

/* Collapse contiguous sequence of skbs head..tail with
 * sequence numbers start..end.
 *
 * If tail is NULL, this means until the end of the queue.
 *
 * Segments with FIN/SYN are not collapsed (only because this
 * simplifies code)
 */
static void
tcp_collapse(struct sock *sk, struct sk_buff_head *list, struct rb_root *root,
	     struct sk_buff *head, struct sk_buff *tail, u32 start, u32 end)
{
	struct sk_buff *skb = head, *n;
	struct sk_buff_head tmp;
	bool end_of_skbs;

	/* First, check that queue is collapsible and find
	 * the point where collapsing can be useful.
	 */
restart:
	for (end_of_skbs = true; skb != NULL && skb != tail; skb = n) {
		n = tcp_skb_next(skb, list);

		/* No new bits? It is possible on ofo queue. */
		if (!before(start, TCP_SKB_CB(skb)->end_seq)) {
			skb = tcp_collapse_one(sk, skb, list, root);
			if (!skb)
				break;
			goto restart;
		}

		/* The first skb to collapse is:
		 * - not SYN/FIN and
		 * - bloated or contains data before "start" or
		 *   overlaps to the next one.
		 */
		if (!(TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)) &&
		    (tcp_win_from_space(sk, skb->truesize) > skb->len ||
		     before(TCP_SKB_CB(skb)->seq, start))) {
			end_of_skbs = false;
			break;
		}

		if (n && n != tail &&
		    TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(n)->seq) {
			end_of_skbs = false;
			break;
		}

		/* Decided to skip this, advance start seq. */
		start = TCP_SKB_CB(skb)->end_seq;
	}
	if (end_of_skbs ||
	    (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)))
		return;

	__skb_queue_head_init(&tmp);

	while (before(start, end)) {
		int copy = min_t(int, SKB_MAX_ORDER(0, 0), end - start);
		struct sk_buff *nskb;

		nskb = alloc_skb(copy, GFP_ATOMIC);
		if (!nskb)
			break;

		memcpy(nskb->cb, skb->cb, sizeof(skb->cb));
		TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(nskb)->end_seq = start;
		if (list)
			__skb_queue_before(list, skb, nskb);
		else
			__skb_queue_tail(&tmp, nskb); /* defer rbtree insertion */
		skb_set_owner_r(nskb, sk);

		/* Copy data, releasing collapsed skbs. */
		while (copy > 0) {
			int offset = start - TCP_SKB_CB(skb)->seq;
			int size = TCP_SKB_CB(skb)->end_seq - start;

			BUG_ON(offset < 0);
			if (size > 0) {
				size = min(copy, size);
				if (skb_copy_bits(skb, offset, skb_put(nskb, size), size))
					BUG();
				TCP_SKB_CB(nskb)->end_seq += size;
				copy -= size;
				start += size;
			}
			if (!before(start, TCP_SKB_CB(skb)->end_seq)) {
				skb = tcp_collapse_one(sk, skb, list, root);
				if (!skb ||
				    skb == tail ||
				    (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)))
					goto end;
			}
		}
	}
end:
	skb_queue_walk_safe(&tmp, skb, n)
		tcp_rbtree_insert(root, skb);
}

/* Collapse ofo queue. Algorithm: select contiguous sequence of skbs
 * and tcp_collapse() them until all the queue is collapsed.
 */
static void tcp_collapse_ofo_queue(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);
	u32 range_truesize, sum_tiny = 0;
	struct sk_buff *skb, *head;
	u32 start, end;

	skb = skb_rb_first(&tp->out_of_order_queue);
new_range:
	if (!skb) {
		tp->ooo_last_skb = skb_rb_last(&tp->out_of_order_queue);
		return;
	}
	start = TCP_SKB_CB(skb)->seq;
	end = TCP_SKB_CB(skb)->end_seq;
	range_truesize = skb->truesize;

	for (head = skb;;) {
		skb = skb_rb_next(skb);

		/* Range is terminated when we see a gap or when
		 * we are at the queue end.
		 */
		if (!skb ||
		    after(TCP_SKB_CB(skb)->seq, end) ||
		    before(TCP_SKB_CB(skb)->end_seq, start)) {
			/* Do not attempt collapsing tiny skbs */
			if (range_truesize != head->truesize ||
			    end - start >= SKB_WITH_OVERHEAD(SK_MEM_QUANTUM)) {
				tcp_collapse(sk, NULL, &tp->out_of_order_queue,
					     head, skb, start, end);
			} else {
				sum_tiny += range_truesize;
				if (sum_tiny > sk->sk_rcvbuf >> 3)
					return;
			}
			goto new_range;
		}

		range_truesize += skb->truesize;
		if (unlikely(before(TCP_SKB_CB(skb)->seq, start)))
			start = TCP_SKB_CB(skb)->seq;
		if (after(TCP_SKB_CB(skb)->end_seq, end))
			end = TCP_SKB_CB(skb)->end_seq;
	}
}

/*
 * Clean the out-of-order queue to make room.
 * We drop high sequences packets to :
 * 1) Let a chance for holes to be filled.
 * 2) not add too big latencies if thousands of packets sit there.
 *    (But if application shrinks SO_RCVBUF, we could still end up
 *     freeing whole queue here)
 * 3) Drop at least 12.5 % of sk_rcvbuf to avoid malicious attacks.
 *
 * Return true if queue has shrunk.
 */
static bool tcp_prune_ofo_queue(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct rb_node *node, *prev;
	int goal;

	if (RB_EMPTY_ROOT(&tp->out_of_order_queue))
		return false;

	NET_INC_STATS(sock_net(sk), LINUX_MIB_OFOPRUNED);
	goal = sk->sk_rcvbuf >> 3;
	node = &tp->ooo_last_skb->rbnode;
	do {
		prev = rb_prev(node);
		rb_erase(node, &tp->out_of_order_queue);
		goal -= rb_to_skb(node)->truesize;
		tcp_drop(sk, rb_to_skb(node));
		if (!prev || goal <= 0) {
			sk_mem_reclaim(sk);
			if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf &&
			    !tcp_under_memory_pressure(sk))
				break;
			goal = sk->sk_rcvbuf >> 3;
		}
		node = prev;
	} while (node);
	tp->ooo_last_skb = rb_to_skb(prev);

	/* Reset SACK state.  A conforming SACK implementation will
	 * do the same at a timeout based retransmit.  When a connection
	 * is in a sad state like this, we care only about integrity
	 * of the connection not performance.
	 */
	if (tp->rx_opt.sack_ok)
		tcp_sack_reset(&tp->rx_opt);
	return true;
}

/* Reduce allocated memory if we can, trying to get
 * the socket within its memory limits again.
 *
 * Return less than zero if we should start dropping frames
 * until the socket owning process reads some of the data
 * to stabilize the situation.
 */
static int tcp_prune_queue(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);

	SOCK_DEBUG(sk, "prune_queue: c=%x\n", tp->copied_seq);

	NET_INC_STATS(sock_net(sk), LINUX_MIB_PRUNECALLED);

	if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf)
		tcp_clamp_window(sk);
	else if (tcp_under_memory_pressure(sk))
		tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss);

	if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf)
		return 0;

	tcp_collapse_ofo_queue(sk);
	if (!skb_queue_empty(&sk->sk_receive_queue))
		tcp_collapse(sk, &sk->sk_receive_queue, NULL,
			     skb_peek(&sk->sk_receive_queue),
			     NULL,
			     tp->copied_seq, tp->rcv_nxt);
	sk_mem_reclaim(sk);

	if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf)
		return 0;

	/* Collapsing did not help, destructive actions follow.
	 * This must not ever occur. */

	tcp_prune_ofo_queue(sk);

	if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf)
		return 0;

	/* If we are really being abused, tell the caller to silently
	 * drop receive data on the floor.  It will get retransmitted
	 * and hopefully then we'll have sufficient space.
	 */
	NET_INC_STATS(sock_net(sk), LINUX_MIB_RCVPRUNED);

	/* Massive buffer overcommit. */
	tp->pred_flags = 0;
	return -1;
}

static bool tcp_should_expand_sndbuf(const struct sock *sk)
{
	const struct tcp_sock *tp = tcp_sk(sk);

	/* If the user specified a specific send buffer setting, do
	 * not modify it.
	 */
	if (sk->sk_userlocks & SOCK_SNDBUF_LOCK)
		return false;

	/* If we are under global TCP memory pressure, do not expand.  */
	if (tcp_under_memory_pressure(sk))
		return false;

	/* If we are under soft global TCP memory pressure, do not expand.  */
	if (sk_memory_allocated(sk) >= sk_prot_mem_limits(sk, 0))
		return false;

	/* If we filled the congestion window, do not expand.  */
	if (tcp_packets_in_flight(tp) >= tp->snd_cwnd)
		return false;

	return true;
}

/* When incoming ACK allowed to free some skb from write_queue,
 * we remember this event in flag SOCK_QUEUE_SHRUNK and wake up socket
 * on the exit from tcp input handler.
 *
 * PROBLEM: sndbuf expansion does not work well with largesend.
 */
static void tcp_new_space(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);

	if (tcp_should_expand_sndbuf(sk)) {
		tcp_sndbuf_expand(sk);
		tp->snd_cwnd_stamp = tcp_jiffies32;
	}

	sk->sk_write_space(sk);
}

static void tcp_check_space(struct sock *sk)
{
	if (sock_flag(sk, SOCK_QUEUE_SHRUNK)) {
		sock_reset_flag(sk, SOCK_QUEUE_SHRUNK);
		/* pairs with tcp_poll() */
		smp_mb();
		if (sk->sk_socket &&
		    test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) {
			tcp_new_space(sk);
			if (!test_bit(SOCK_NOSPACE, &sk->sk_socket->flags))
				tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED);
		}
	}
}

static inline void tcp_data_snd_check(struct sock *sk)
{
	tcp_push_pending_frames(sk);
	tcp_check_space(sk);
}

/*
 * Check if sending an ack is needed.
 */
static void __tcp_ack_snd_check(struct sock *sk, int ofo_possible)
{
	struct tcp_sock *tp = tcp_sk(sk);
	unsigned long rtt, delay;

	    /* More than one full frame received... */
	if (((tp->rcv_nxt - tp->rcv_wup) > inet_csk(sk)->icsk_ack.rcv_mss &&
	     /* ... and right edge of window advances far enough.
	      * (tcp_recvmsg() will send ACK otherwise).
	      * If application uses SO_RCVLOWAT, we want send ack now if
	      * we have not received enough bytes to satisfy the condition.
	      */
	    (tp->rcv_nxt - tp->copied_seq < sk->sk_rcvlowat ||
	     __tcp_select_window(sk) >= tp->rcv_wnd)) ||
	    /* We ACK each frame or... */
	    tcp_in_quickack_mode(sk)) {
send_now:
		tcp_send_ack(sk);
		return;
	}

	if (!ofo_possible || RB_EMPTY_ROOT(&tp->out_of_order_queue)) {
		tcp_send_delayed_ack(sk);
		return;
	}

	if (!tcp_is_sack(tp) ||
	    tp->compressed_ack >= sock_net(sk)->ipv4.sysctl_tcp_comp_sack_nr)
		goto send_now;
	tp->compressed_ack++;

	if (hrtimer_is_queued(&tp->compressed_ack_timer))
		return;

	/* compress ack timer : 5 % of rtt, but no more than tcp_comp_sack_delay_ns */

	rtt = tp->rcv_rtt_est.rtt_us;
	if (tp->srtt_us && tp->srtt_us < rtt)
		rtt = tp->srtt_us;

	delay = min_t(unsigned long, sock_net(sk)->ipv4.sysctl_tcp_comp_sack_delay_ns,
		      rtt * (NSEC_PER_USEC >> 3)/20);
	sock_hold(sk);
	hrtimer_start(&tp->compressed_ack_timer, ns_to_ktime(delay),
		      HRTIMER_MODE_REL_PINNED_SOFT);
}

static inline void tcp_ack_snd_check(struct sock *sk)
{
	if (!inet_csk_ack_scheduled(sk)) {
		/* We sent a data segment already. */
		return;
	}
	__tcp_ack_snd_check(sk, 1);
}

/*
 *	This routine is only called when we have urgent data
 *	signaled. Its the 'slow' part of tcp_urg. It could be
 *	moved inline now as tcp_urg is only called from one
 *	place. We handle URGent data wrong. We have to - as
 *	BSD still doesn't use the correction from RFC961.
 *	For 1003.1g we should support a new option TCP_STDURG to permit
 *	either form (or just set the sysctl tcp_stdurg).
 */

static void tcp_check_urg(struct sock *sk, const struct tcphdr *th)
{
	struct tcp_sock *tp = tcp_sk(sk);
	u32 ptr = ntohs(th->urg_ptr);

	if (ptr && !sock_net(sk)->ipv4.sysctl_tcp_stdurg)
		ptr--;
	ptr += ntohl(th->seq);

	/* Ignore urgent data that we've already seen and read. */
	if (after(tp->copied_seq, ptr))
		return;

	/* Do not replay urg ptr.
	 *
	 * NOTE: interesting situation not covered by specs.
	 * Misbehaving sender may send urg ptr, pointing to segment,
	 * which we already have in ofo queue. We are not able to fetch
	 * such data and will stay in TCP_URG_NOTYET until will be eaten
	 * by recvmsg(). Seems, we are not obliged to handle such wicked
	 * situations. But it is worth to think about possibility of some
	 * DoSes using some hypothetical application level deadlock.
	 */
	if (before(ptr, tp->rcv_nxt))
		return;

	/* Do we already have a newer (or duplicate) urgent pointer? */
	if (tp->urg_data && !after(ptr, tp->urg_seq))
		return;

	/* Tell the world about our new urgent pointer. */
	sk_send_sigurg(sk);

	/* We may be adding urgent data when the last byte read was
	 * urgent. To do this requires some care. We cannot just ignore
	 * tp->copied_seq since we would read the last urgent byte again
	 * as data, nor can we alter copied_seq until this data arrives
	 * or we break the semantics of SIOCATMARK (and thus sockatmark())
	 *
	 * NOTE. Double Dutch. Rendering to plain English: author of comment
	 * above did something sort of 	send("A", MSG_OOB); send("B", MSG_OOB);
	 * and expect that both A and B disappear from stream. This is _wrong_.
	 * Though this happens in BSD with high probability, this is occasional.
	 * Any application relying on this is buggy. Note also, that fix "works"
	 * only in this artificial test. Insert some normal data between A and B and we will
	 * decline of BSD again. Verdict: it is better to remove to trap
	 * buggy users.
	 */
	if (tp->urg_seq == tp->copied_seq && tp->urg_data &&
	    !sock_flag(sk, SOCK_URGINLINE) && tp->copied_seq != tp->rcv_nxt) {
		struct sk_buff *skb = skb_peek(&sk->sk_receive_queue);
		tp->copied_seq++;
		if (skb && !before(tp->copied_seq, TCP_SKB_CB(skb)->end_seq)) {
			__skb_unlink(skb, &sk->sk_receive_queue);
			__kfree_skb(skb);
		}
	}

	tp->urg_data = TCP_URG_NOTYET;
	tp->urg_seq = ptr;

	/* Disable header prediction. */
	tp->pred_flags = 0;
}

/* This is the 'fast' part of urgent handling. */
static void tcp_urg(struct sock *sk, struct sk_buff *skb, const struct tcphdr *th)
{
	struct tcp_sock *tp = tcp_sk(sk);

	/* Check if we get a new urgent pointer - normally not. */
	if (th->urg)
		tcp_check_urg(sk, th);

	/* Do we wait for any urgent data? - normally not... */
	if (tp->urg_data == TCP_URG_NOTYET) {
		u32 ptr = tp->urg_seq - ntohl(th->seq) + (th->doff * 4) -
			  th->syn;

		/* Is the urgent pointer pointing into this packet? */
		if (ptr < skb->len) {
			u8 tmp;
			if (skb_copy_bits(skb, ptr, &tmp, 1))
				BUG();
			tp->urg_data = TCP_URG_VALID | tmp;
			if (!sock_flag(sk, SOCK_DEAD))
				sk->sk_data_ready(sk);
		}
	}
}

/* Accept RST for rcv_nxt - 1 after a FIN.
 * When tcp connections are abruptly terminated from Mac OSX (via ^C), a
 * FIN is sent followed by a RST packet. The RST is sent with the same
 * sequence number as the FIN, and thus according to RFC 5961 a challenge
 * ACK should be sent. However, Mac OSX rate limits replies to challenge
 * ACKs on the closed socket. In addition middleboxes can drop either the
 * challenge ACK or a subsequent RST.
 */
static bool tcp_reset_check(const struct sock *sk, const struct sk_buff *skb)
{
	struct tcp_sock *tp = tcp_sk(sk);

	return unlikely(TCP_SKB_CB(skb)->seq == (tp->rcv_nxt - 1) &&
			(1 << sk->sk_state) & (TCPF_CLOSE_WAIT | TCPF_LAST_ACK |
					       TCPF_CLOSING));
}

/* Does PAWS and seqno based validation of an incoming segment, flags will
 * play significant role here.
 */
static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
				  const struct tcphdr *th, int syn_inerr)
{
	struct tcp_sock *tp = tcp_sk(sk);
	bool rst_seq_match = false;

	/* RFC1323: H1. Apply PAWS check first. */
	if (tcp_fast_parse_options(sock_net(sk), skb, th, tp) &&
	    tp->rx_opt.saw_tstamp &&
	    tcp_paws_discard(sk, skb)) {
		if (!th->rst) {
			NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED);
			if (!tcp_oow_rate_limited(sock_net(sk), skb,
						  LINUX_MIB_TCPACKSKIPPEDPAWS,
						  &tp->last_oow_ack_time))
				tcp_send_dupack(sk, skb);
			goto discard;
		}
		/* Reset is accepted even if it did not pass PAWS. */
	}

	/* Step 1: check sequence number */
	if (!tcp_sequence(tp, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq)) {
		/* RFC793, page 37: "In all states except SYN-SENT, all reset
		 * (RST) segments are validated by checking their SEQ-fields."
		 * And page 69: "If an incoming segment is not acceptable,
		 * an acknowledgment should be sent in reply (unless the RST
		 * bit is set, if so drop the segment and return)".
		 */
		if (!th->rst) {
			if (th->syn)
				goto syn_challenge;
			if (!tcp_oow_rate_limited(sock_net(sk), skb,
						  LINUX_MIB_TCPACKSKIPPEDSEQ,
						  &tp->last_oow_ack_time))
				tcp_send_dupack(sk, skb);
		} else if (tcp_reset_check(sk, skb)) {
			tcp_reset(sk);
		}
		goto discard;
	}

	/* Step 2: check RST bit */
	if (th->rst) {
		/* RFC 5961 3.2 (extend to match against (RCV.NXT - 1) after a
		 * FIN and SACK too if available):
		 * If seq num matches RCV.NXT or (RCV.NXT - 1) after a FIN, or
		 * the right-most SACK block,
		 * then
		 *     RESET the connection
		 * else
		 *     Send a challenge ACK
		 */
		if (TCP_SKB_CB(skb)->seq == tp->rcv_nxt ||
		    tcp_reset_check(sk, skb)) {
			rst_seq_match = true;
		} else if (tcp_is_sack(tp) && tp->rx_opt.num_sacks > 0) {
			struct tcp_sack_block *sp = &tp->selective_acks[0];
			int max_sack = sp[0].end_seq;
			int this_sack;

			for (this_sack = 1; this_sack < tp->rx_opt.num_sacks;
			     ++this_sack) {
				max_sack = after(sp[this_sack].end_seq,
						 max_sack) ?
					sp[this_sack].end_seq : max_sack;
			}

			if (TCP_SKB_CB(skb)->seq == max_sack)
				rst_seq_match = true;
		}

		if (rst_seq_match)
			tcp_reset(sk);
		else {
			/* Disable TFO if RST is out-of-order
			 * and no data has been received
			 * for current active TFO socket
			 */
			if (tp->syn_fastopen && !tp->data_segs_in &&
			    sk->sk_state == TCP_ESTABLISHED)
				tcp_fastopen_active_disable(sk);
			tcp_send_challenge_ack(sk, skb);
		}
		goto discard;
	}

	/* step 3: check security and precedence [ignored] */

	/* step 4: Check for a SYN
	 * RFC 5961 4.2 : Send a challenge ack
	 */
	if (th->syn) {
syn_challenge:
		if (syn_inerr)
			TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS);
		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNCHALLENGE);
		tcp_send_challenge_ack(sk, skb);
		goto discard;
	}

	return true;

discard:
	tcp_drop(sk, skb);
	return false;
}

/*
 *	TCP receive function for the ESTABLISHED state.
 *
 *	It is split into a fast path and a slow path. The fast path is
 * 	disabled when:
 *	- A zero window was announced from us - zero window probing
 *        is only handled properly in the slow path.
 *	- Out of order segments arrived.
 *	- Urgent data is expected.
 *	- There is no buffer space left
 *	- Unexpected TCP flags/window values/header lengths are received
 *	  (detected by checking the TCP header against pred_flags)
 *	- Data is sent in both directions. Fast path only supports pure senders
 *	  or pure receivers (this means either the sequence number or the ack
 *	  value must stay constant)
 *	- Unexpected TCP option.
 *
 *	When these conditions are not satisfied it drops into a standard
 *	receive procedure patterned after RFC793 to handle all cases.
 *	The first three cases are guaranteed by proper pred_flags setting,
 *	the rest is checked inline. Fast processing is turned on in
 *	tcp_data_queue when everything is OK.
 */
void tcp_rcv_established(struct sock *sk, struct sk_buff *skb)
{
	const struct tcphdr *th = (const struct tcphdr *)skb->data;
	struct tcp_sock *tp = tcp_sk(sk);
	unsigned int len = skb->len;

	/* TCP congestion window tracking */
	trace_tcp_probe(sk, skb);

	tcp_mstamp_refresh(tp);
	if (unlikely(!sk->sk_rx_dst))
		inet_csk(sk)->icsk_af_ops->sk_rx_dst_set(sk, skb);
	/*
	 *	Header prediction.
	 *	The code loosely follows the one in the famous
	 *	"30 instruction TCP receive" Van Jacobson mail.
	 *
	 *	Van's trick is to deposit buffers into socket queue
	 *	on a device interrupt, to call tcp_recv function
	 *	on the receive process context and checksum and copy
	 *	the buffer to user space. smart...
	 *
	 *	Our current scheme is not silly either but we take the
	 *	extra cost of the net_bh soft interrupt processing...
	 *	We do checksum and copy also but from device to kernel.
	 */

	tp->rx_opt.saw_tstamp = 0;

	/*	pred_flags is 0xS?10 << 16 + snd_wnd
	 *	if header_prediction is to be made
	 *	'S' will always be tp->tcp_header_len >> 2
	 *	'?' will be 0 for the fast path, otherwise pred_flags is 0 to
	 *  turn it off	(when there are holes in the receive
	 *	 space for instance)
	 *	PSH flag is ignored.
	 */

	if ((tcp_flag_word(th) & TCP_HP_BITS) == tp->pred_flags &&
	    TCP_SKB_CB(skb)->seq == tp->rcv_nxt &&
	    !after(TCP_SKB_CB(skb)->ack_seq, tp->snd_nxt)) {
		int tcp_header_len = tp->tcp_header_len;

		/* Timestamp header prediction: tcp_header_len
		 * is automatically equal to th->doff*4 due to pred_flags
		 * match.
		 */

		/* Check timestamp */
		if (tcp_header_len == sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED) {
			/* No? Slow path! */
			if (!tcp_parse_aligned_timestamp(tp, th))
				goto slow_path;

			/* If PAWS failed, check it more carefully in slow path */
			if ((s32)(tp->rx_opt.rcv_tsval - tp->rx_opt.ts_recent) < 0)
				goto slow_path;

			/* DO NOT update ts_recent here, if checksum fails
			 * and timestamp was corrupted part, it will result
			 * in a hung connection since we will drop all
			 * future packets due to the PAWS test.
			 */
		}

		if (len <= tcp_header_len) {
			/* Bulk data transfer: sender */
			if (len == tcp_header_len) {
				/* Predicted packet is in window by definition.
				 * seq == rcv_nxt and rcv_wup <= rcv_nxt.
				 * Hence, check seq<=rcv_wup reduces to:
				 */
				if (tcp_header_len ==
				    (sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED) &&
				    tp->rcv_nxt == tp->rcv_wup)
					tcp_store_ts_recent(tp);

				/* We know that such packets are checksummed
				 * on entry.
				 */
				tcp_ack(sk, skb, 0);
				__kfree_skb(skb);
				tcp_data_snd_check(sk);
				return;
			} else { /* Header too small */
				TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS);
				goto discard;
			}
		} else {
			int eaten = 0;
			bool fragstolen = false;

			if (tcp_checksum_complete(skb))
				goto csum_error;

			if ((int)skb->truesize > sk->sk_forward_alloc)
				goto step5;

			/* Predicted packet is in window by definition.
			 * seq == rcv_nxt and rcv_wup <= rcv_nxt.
			 * Hence, check seq<=rcv_wup reduces to:
			 */
			if (tcp_header_len ==
			    (sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED) &&
			    tp->rcv_nxt == tp->rcv_wup)
				tcp_store_ts_recent(tp);

			tcp_rcv_rtt_measure_ts(sk, skb);