| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773774775776777778779780781782783784785786787788789790791792793794795796797798799800801802803804805806807808809810811812813814815816817818819820821822823824825826827828829830831832833834835836837838839840841842843844845846847848849850851852853854855856857858859860861862863864865866867868869870871872873874875876877878879880881882883884885886887888889890891892893894895896897898899900901902903904905906907908909910911912913914915916917918919920921922923924925926927928929930931932933934935936937938939940941942943944945946947948949950951952953954955956957958959960961962963964965966967968969970971972973974975976977978979980981982983984985986987988989990991992993994995996997998999100010011002100310041005100610071008100910101011101210131014101510161017101810191020102110221023102410251026102710281029103010311032103310341035103610371038103910401041104210431044104510461047104810491050105110521053105410551056105710581059106010611062106310641065106610671068106910701071107210731074107510761077107810791080108110821083108410851086108710881089109010911092109310941095109610971098109911001101110211031104110511061107110811091110111111121113111411151116111711181119112011211122112311241125112611271128112911301131113211331134113511361137113811391140114111421143114411451146114711481149115011511152115311541155115611571158115911601161116211631164116511661167116811691170117111721173117411751176117711781179118011811182118311841185118611871188118911901191119211931194119511961197119811991200120112021203120412051206120712081209121012111212121312141215121612171218121912201221122212231224122512261227122812291230123112321233123412351236123712381239124012411242124312441245124612471248124912501251125212531254125512561257125812591260126112621263126412651266126712681269127012711272127312741275127612771278127912801281128212831284128512861287128812891290129112921293129412951296129712981299130013011302130313041305130613071308130913101311131213131314131513161317131813191320132113221323132413251326132713281329133013311332133313341335133613371338133913401341134213431344134513461347134813491350135113521353135413551356135713581359136013611362136313641365136613671368136913701371137213731374137513761377137813791380138113821383138413851386138713881389139013911392139313941395139613971398139914001401140214031404140514061407140814091410141114121413141414151416141714181419142014211422142314241425142614271428142914301431143214331434143514361437143814391440144114421443144414451446144714481449145014511452145314541455145614571458145914601461146214631464146514661467146814691470147114721473147414751476147714781479148014811482148314841485148614871488148914901491149214931494149514961497149814991500150115021503150415051506150715081509151015111512151315141515151615171518151915201521152215231524152515261527152815291530153115321533153415351536153715381539154015411542154315441545154615471548154915501551155215531554155515561557155815591560156115621563156415651566156715681569157015711572157315741575157615771578157915801581158215831584158515861587158815891590159115921593159415951596159715981599160016011602160316041605160616071608160916101611161216131614161516161617161816191620162116221623162416251626162716281629163016311632163316341635163616371638163916401641164216431644164516461647164816491650165116521653165416551656165716581659166016611662166316641665166616671668166916701671167216731674167516761677167816791680168116821683168416851686168716881689169016911692169316941695169616971698169917001701170217031704170517061707170817091710171117121713171417151716171717181719172017211722172317241725172617271728172917301731173217331734173517361737173817391740174117421743174417451746174717481749175017511752175317541755175617571758175917601761176217631764176517661767176817691770177117721773177417751776177717781779178017811782178317841785178617871788178917901791179217931794179517961797179817991800180118021803180418051806180718081809181018111812181318141815181618171818181918201821182218231824182518261827182818291830183118321833183418351836183718381839184018411842184318441845184618471848184918501851185218531854185518561857185818591860186118621863186418651866186718681869187018711872187318741875187618771878187918801881188218831884188518861887188818891890189118921893189418951896189718981899190019011902190319041905190619071908190919101911191219131914191519161917191819191920192119221923192419251926192719281929193019311932193319341935193619371938193919401941194219431944194519461947194819491950195119521953195419551956195719581959196019611962196319641965196619671968196919701971197219731974197519761977197819791980198119821983198419851986198719881989199019911992199319941995199619971998199920002001200220032004200520062007200820092010201120122013201420152016201720182019202020212022202320242025202620272028202920302031203220332034203520362037203820392040204120422043204420452046204720482049205020512052205320542055205620572058205920602061206220632064206520662067206820692070207120722073207420752076207720782079208020812082208320842085208620872088208920902091209220932094209520962097209820992100210121022103210421052106210721082109211021112112211321142115211621172118211921202121212221232124212521262127212821292130213121322133213421352136213721382139214021412142214321442145214621472148214921502151215221532154215521562157215821592160216121622163216421652166216721682169217021712172217321742175217621772178217921802181218221832184218521862187218821892190219121922193219421952196219721982199220022012202220322042205220622072208220922102211221222132214221522162217221822192220222122222223222422252226222722282229223022312232223322342235223622372238223922402241224222432244224522462247224822492250225122522253225422552256225722582259226022612262226322642265226622672268226922702271227222732274227522762277227822792280228122822283228422852286228722882289229022912292229322942295229622972298229923002301230223032304230523062307230823092310231123122313231423152316231723182319232023212322232323242325232623272328232923302331233223332334233523362337233823392340234123422343234423452346234723482349235023512352235323542355235623572358235923602361236223632364236523662367236823692370237123722373237423752376237723782379238023812382238323842385238623872388238923902391239223932394239523962397239823992400240124022403240424052406240724082409241024112412241324142415241624172418241924202421242224232424242524262427242824292430243124322433243424352436243724382439244024412442244324442445244624472448244924502451245224532454245524562457245824592460246124622463246424652466246724682469247024712472247324742475247624772478247924802481248224832484248524862487248824892490249124922493249424952496249724982499250025012502250325042505250625072508250925102511251225132514251525162517251825192520252125222523252425252526252725282529253025312532253325342535253625372538253925402541254225432544254525462547254825492550255125522553255425552556255725582559256025612562256325642565256625672568256925702571257225732574257525762577257825792580258125822583258425852586258725882589259025912592259325942595259625972598259926002601260226032604260526062607260826092610261126122613261426152616261726182619262026212622262326242625262626272628262926302631263226332634263526362637263826392640264126422643264426452646264726482649265026512652265326542655265626572658265926602661266226632664266526662667266826692670267126722673267426752676267726782679268026812682268326842685268626872688268926902691269226932694269526962697269826992700270127022703270427052706270727082709271027112712271327142715271627172718271927202721272227232724272527262727272827292730273127322733273427352736273727382739274027412742274327442745274627472748274927502751275227532754275527562757275827592760276127622763276427652766276727682769277027712772277327742775277627772778277927802781278227832784278527862787278827892790279127922793279427952796279727982799280028012802280328042805280628072808280928102811281228132814281528162817281828192820282128222823282428252826282728282829283028312832283328342835283628372838283928402841284228432844284528462847284828492850285128522853285428552856285728582859286028612862286328642865286628672868286928702871287228732874287528762877287828792880288128822883288428852886288728882889289028912892289328942895289628972898289929002901290229032904290529062907290829092910291129122913291429152916291729182919292029212922292329242925292629272928292929302931293229332934293529362937293829392940294129422943294429452946294729482949295029512952295329542955295629572958295929602961296229632964296529662967296829692970297129722973297429752976297729782979298029812982298329842985298629872988298929902991299229932994299529962997299829993000300130023003300430053006300730083009301030113012301330143015301630173018301930203021302230233024302530263027302830293030303130323033303430353036303730383039304030413042304330443045304630473048304930503051305230533054305530563057305830593060306130623063306430653066306730683069307030713072307330743075307630773078307930803081308230833084308530863087308830893090309130923093309430953096309730983099310031013102310331043105310631073108310931103111311231133114311531163117311831193120312131223123312431253126312731283129313031313132313331343135313631373138313931403141314231433144314531463147314831493150315131523153315431553156315731583159316031613162316331643165316631673168316931703171317231733174317531763177317831793180318131823183318431853186318731883189319031913192319331943195319631973198319932003201320232033204320532063207320832093210321132123213321432153216321732183219322032213222322332243225322632273228322932303231323232333234323532363237323832393240324132423243324432453246324732483249325032513252325332543255325632573258325932603261326232633264326532663267326832693270327132723273327432753276327732783279328032813282328332843285328632873288328932903291329232933294329532963297329832993300330133023303330433053306330733083309331033113312331333143315331633173318331933203321332233233324332533263327332833293330333133323333333433353336333733383339334033413342334333443345334633473348334933503351335233533354335533563357335833593360336133623363336433653366336733683369337033713372337333743375337633773378337933803381338233833384338533863387338833893390339133923393339433953396339733983399340034013402340334043405340634073408340934103411341234133414341534163417341834193420342134223423342434253426342734283429343034313432343334343435343634373438343934403441344234433444344534463447344834493450345134523453345434553456345734583459346034613462346334643465346634673468346934703471347234733474347534763477347834793480348134823483348434853486348734883489349034913492349334943495349634973498349935003501350235033504350535063507350835093510351135123513351435153516351735183519352035213522352335243525352635273528352935303531353235333534353535363537353835393540354135423543354435453546354735483549355035513552355335543555355635573558355935603561356235633564356535663567356835693570357135723573357435753576357735783579358035813582358335843585358635873588358935903591359235933594359535963597359835993600360136023603360436053606360736083609361036113612361336143615361636173618361936203621362236233624362536263627362836293630363136323633363436353636363736383639364036413642364336443645364636473648364936503651365236533654365536563657365836593660366136623663366436653666366736683669367036713672367336743675367636773678367936803681368236833684368536863687368836893690369136923693369436953696369736983699370037013702370337043705370637073708370937103711371237133714371537163717371837193720372137223723372437253726372737283729373037313732373337343735373637373738373937403741374237433744374537463747374837493750375137523753375437553756375737583759376037613762376337643765376637673768376937703771377237733774377537763777377837793780378137823783378437853786378737883789379037913792379337943795379637973798379938003801380238033804380538063807380838093810381138123813381438153816381738183819382038213822382338243825382638273828382938303831383238333834383538363837383838393840384138423843384438453846384738483849385038513852385338543855385638573858385938603861386238633864386538663867386838693870387138723873387438753876387738783879388038813882388338843885388638873888388938903891389238933894389538963897389838993900390139023903390439053906390739083909391039113912391339143915391639173918391939203921392239233924392539263927392839293930393139323933393439353936393739383939394039413942394339443945394639473948394939503951395239533954395539563957395839593960396139623963396439653966396739683969397039713972397339743975397639773978397939803981398239833984398539863987398839893990399139923993399439953996399739983999400040014002400340044005400640074008400940104011401240134014401540164017401840194020402140224023402440254026402740284029403040314032403340344035403640374038403940404041404240434044404540464047404840494050405140524053405440554056405740584059406040614062406340644065406640674068406940704071407240734074407540764077407840794080408140824083408440854086408740884089409040914092409340944095409640974098409941004101410241034104410541064107410841094110411141124113411441154116411741184119412041214122412341244125412641274128412941304131413241334134413541364137413841394140414141424143414441454146414741484149415041514152415341544155415641574158415941604161416241634164416541664167416841694170417141724173417441754176417741784179418041814182418341844185418641874188418941904191419241934194419541964197419841994200420142024203420442054206420742084209421042114212421342144215421642174218421942204221422242234224422542264227422842294230423142324233423442354236423742384239424042414242424342444245424642474248424942504251425242534254425542564257425842594260426142624263426442654266426742684269427042714272427342744275427642774278427942804281428242834284428542864287428842894290429142924293429442954296429742984299430043014302430343044305430643074308430943104311431243134314431543164317431843194320432143224323432443254326432743284329433043314332433343344335433643374338433943404341434243434344434543464347434843494350435143524353435443554356435743584359436043614362436343644365436643674368436943704371437243734374437543764377437843794380438143824383438443854386438743884389439043914392439343944395439643974398439944004401440244034404440544064407440844094410441144124413441444154416441744184419442044214422442344244425442644274428442944304431443244334434443544364437443844394440444144424443444444454446444744484449445044514452445344544455445644574458445944604461446244634464446544664467446844694470447144724473447444754476447744784479448044814482448344844485448644874488448944904491449244934494449544964497449844994500450145024503450445054506450745084509451045114512451345144515451645174518451945204521452245234524452545264527452845294530453145324533453445354536453745384539454045414542454345444545454645474548454945504551455245534554455545564557455845594560456145624563456445654566456745684569457045714572457345744575457645774578457945804581458245834584458545864587458845894590459145924593459445954596459745984599460046014602460346044605460646074608460946104611461246134614461546164617461846194620462146224623462446254626462746284629463046314632463346344635463646374638463946404641464246434644464546464647464846494650465146524653465446554656465746584659466046614662466346644665466646674668466946704671467246734674467546764677467846794680468146824683468446854686468746884689469046914692469346944695469646974698469947004701470247034704470547064707470847094710471147124713471447154716471747184719472047214722472347244725472647274728472947304731473247334734473547364737473847394740474147424743474447454746474747484749475047514752475347544755475647574758475947604761476247634764476547664767476847694770477147724773477447754776477747784779478047814782478347844785478647874788478947904791479247934794479547964797479847994800480148024803480448054806480748084809481048114812481348144815481648174818481948204821482248234824482548264827482848294830483148324833483448354836483748384839484048414842484348444845484648474848484948504851485248534854485548564857485848594860486148624863486448654866486748684869487048714872487348744875487648774878487948804881488248834884488548864887488848894890489148924893489448954896489748984899490049014902490349044905490649074908490949104911491249134914491549164917491849194920492149224923492449254926492749284929493049314932493349344935493649374938493949404941494249434944494549464947494849494950495149524953495449554956495749584959496049614962496349644965496649674968496949704971497249734974497549764977497849794980498149824983498449854986498749884989499049914992499349944995499649974998499950005001500250035004500550065007500850095010501150125013501450155016501750185019502050215022502350245025502650275028502950305031503250335034503550365037503850395040504150425043504450455046504750485049505050515052505350545055505650575058505950605061506250635064506550665067506850695070507150725073507450755076507750785079508050815082508350845085508650875088508950905091509250935094509550965097509850995100510151025103510451055106510751085109511051115112511351145115511651175118511951205121512251235124512551265127512851295130513151325133513451355136513751385139514051415142514351445145514651475148514951505151515251535154515551565157515851595160516151625163516451655166516751685169517051715172517351745175517651775178517951805181518251835184518551865187518851895190519151925193519451955196519751985199520052015202520352045205520652075208520952105211521252135214521552165217521852195220522152225223522452255226522752285229523052315232523352345235523652375238523952405241524252435244524552465247524852495250525152525253525452555256525752585259526052615262526352645265526652675268526952705271527252735274527552765277527852795280528152825283528452855286528752885289529052915292529352945295529652975298529953005301530253035304530553065307530853095310531153125313531453155316531753185319532053215322532353245325532653275328532953305331533253335334533553365337533853395340534153425343534453455346534753485349535053515352535353545355535653575358535953605361536253635364536553665367536853695370537153725373537453755376537753785379538053815382538353845385538653875388538953905391539253935394539553965397539853995400540154025403540454055406540754085409541054115412541354145415541654175418541954205421542254235424542554265427542854295430543154325433543454355436543754385439544054415442544354445445544654475448544954505451545254535454545554565457545854595460546154625463546454655466546754685469547054715472547354745475547654775478547954805481548254835484548554865487548854895490549154925493549454955496549754985499550055015502550355045505550655075508550955105511551255135514551555165517551855195520552155225523552455255526552755285529553055315532553355345535553655375538553955405541554255435544554555465547554855495550555155525553555455555556555755585559556055615562556355645565556655675568556955705571557255735574557555765577557855795580558155825583558455855586558755885589559055915592559355945595559655975598559956005601560256035604560556065607560856095610561156125613561456155616561756185619562056215622562356245625562656275628562956305631563256335634563556365637563856395640564156425643564456455646564756485649565056515652565356545655565656575658565956605661566256635664566556665667566856695670567156725673567456755676567756785679568056815682568356845685568656875688568956905691569256935694569556965697569856995700570157025703570457055706570757085709571057115712571357145715571657175718571957205721572257235724572557265727572857295730573157325733573457355736573757385739574057415742574357445745574657475748574957505751575257535754575557565757575857595760576157625763576457655766576757685769577057715772577357745775577657775778577957805781578257835784578557865787578857895790579157925793579457955796579757985799580058015802580358045805580658075808580958105811581258135814581558165817581858195820582158225823582458255826582758285829583058315832583358345835583658375838583958405841584258435844584558465847584858495850585158525853585458555856585758585859586058615862586358645865586658675868586958705871587258735874587558765877587858795880588158825883588458855886588758885889589058915892589358945895589658975898589959005901590259035904590559065907590859095910591159125913591459155916591759185919592059215922592359245925592659275928592959305931593259335934593559365937593859395940594159425943594459455946594759485949595059515952595359545955595659575958595959605961596259635964596559665967596859695970597159725973597459755976597759785979598059815982598359845985598659875988598959905991599259935994599559965997599859996000600160026003600460056006600760086009601060116012601360146015601660176018601960206021602260236024602560266027602860296030603160326033603460356036603760386039604060416042604360446045604660476048604960506051605260536054605560566057605860596060606160626063606460656066606760686069607060716072607360746075607660776078607960806081608260836084608560866087608860896090609160926093609460956096609760986099610061016102610361046105610661076108610961106111611261136114611561166117611861196120612161226123612461256126612761286129613061316132613361346135613661376138613961406141614261436144614561466147614861496150615161526153615461556156615761586159616061616162616361646165616661676168616961706171617261736174617561766177617861796180618161826183618461856186618761886189619061916192619361946195619661976198619962006201620262036204620562066207620862096210621162126213621462156216621762186219622062216222622362246225622662276228622962306231623262336234623562366237623862396240624162426243624462456246624762486249625062516252625362546255625662576258625962606261626262636264626562666267626862696270627162726273627462756276627762786279628062816282628362846285628662876288628962906291629262936294629562966297629862996300630163026303630463056306630763086309631063116312631363146315631663176318631963206321632263236324632563266327632863296330633163326333633463356336633763386339634063416342634363446345634663476348634963506351635263536354635563566357635863596360636163626363636463656366636763686369637063716372637363746375637663776378637963806381638263836384638563866387638863896390639163926393639463956396639763986399640064016402640364046405640664076408640964106411641264136414641564166417641864196420642164226423642464256426642764286429643064316432643364346435643664376438643964406441644264436444644564466447644864496450645164526453645464556456645764586459646064616462646364646465646664676468646964706471647264736474647564766477647864796480648164826483648464856486648764886489649064916492649364946495649664976498649965006501650265036504650565066507650865096510651165126513651465156516651765186519652065216522652365246525652665276528652965306531653265336534653565366537653865396540654165426543654465456546654765486549655065516552655365546555655665576558655965606561656265636564656565666567656865696570657165726573657465756576657765786579658065816582658365846585658665876588658965906591659265936594659565966597659865996600660166026603660466056606660766086609661066116612661366146615661666176618661966206621662266236624662566266627662866296630663166326633663466356636663766386639664066416642664366446645664666476648664966506651665266536654665566566657665866596660666166626663666466656666666766686669667066716672667366746675667666776678667966806681668266836684668566866687668866896690669166926693669466956696669766986699670067016702670367046705670667076708670967106711671267136714671567166717671867196720672167226723672467256726672767286729673067316732673367346735673667376738673967406741674267436744674567466747674867496750675167526753675467556756675767586759676067616762676367646765676667676768676967706771677267736774677567766777677867796780678167826783678467856786678767886789679067916792679367946795679667976798679968006801680268036804680568066807680868096810681168126813681468156816681768186819682068216822682368246825682668276828682968306831683268336834683568366837683868396840684168426843684468456846684768486849685068516852685368546855685668576858685968606861686268636864686568666867686868696870687168726873687468756876687768786879688068816882688368846885688668876888688968906891689268936894689568966897689868996900690169026903690469056906690769086909691069116912691369146915691669176918691969206921692269236924692569266927692869296930693169326933693469356936693769386939694069416942694369446945694669476948694969506951695269536954695569566957695869596960696169626963696469656966696769686969697069716972697369746975697669776978697969806981698269836984698569866987698869896990699169926993699469956996699769986999700070017002700370047005700670077008700970107011701270137014701570167017701870197020702170227023702470257026702770287029703070317032703370347035703670377038703970407041704270437044704570467047704870497050705170527053705470557056705770587059706070617062706370647065706670677068706970707071707270737074707570767077707870797080708170827083708470857086708770887089709070917092709370947095709670977098709971007101710271037104710571067107710871097110711171127113711471157116711771187119712071217122712371247125712671277128712971307131713271337134713571367137713871397140714171427143714471457146714771487149715071517152715371547155715671577158715971607161716271637164716571667167716871697170717171727173717471757176717771787179718071817182718371847185718671877188718971907191719271937194719571967197719871997200720172027203720472057206720772087209721072117212721372147215721672177218721972207221722272237224722572267227722872297230723172327233723472357236723772387239724072417242724372447245724672477248724972507251725272537254725572567257725872597260726172627263726472657266726772687269727072717272727372747275727672777278727972807281728272837284728572867287728872897290729172927293729472957296729772987299730073017302730373047305730673077308730973107311731273137314731573167317731873197320732173227323732473257326732773287329733073317332733373347335733673377338733973407341734273437344734573467347734873497350735173527353735473557356735773587359736073617362736373647365736673677368736973707371737273737374737573767377737873797380738173827383738473857386738773887389739073917392739373947395739673977398739974007401740274037404740574067407740874097410741174127413741474157416741774187419742074217422742374247425742674277428742974307431743274337434743574367437743874397440744174427443744474457446744774487449745074517452745374547455745674577458745974607461746274637464746574667467746874697470747174727473747474757476747774787479748074817482748374847485748674877488748974907491749274937494749574967497749874997500750175027503750475057506750775087509751075117512751375147515751675177518751975207521752275237524752575267527752875297530753175327533753475357536753775387539754075417542754375447545754675477548754975507551755275537554755575567557755875597560756175627563756475657566756775687569757075717572757375747575757675777578757975807581758275837584758575867587758875897590759175927593759475957596759775987599760076017602760376047605760676077608760976107611761276137614761576167617761876197620762176227623762476257626762776287629763076317632763376347635763676377638763976407641764276437644764576467647764876497650765176527653765476557656765776587659766076617662766376647665766676677668766976707671767276737674767576767677767876797680768176827683768476857686768776887689769076917692769376947695769676977698769977007701770277037704770577067707770877097710771177127713771477157716771777187719772077217722772377247725772677277728772977307731773277337734773577367737773877397740774177427743774477457746774777487749775077517752775377547755775677577758775977607761776277637764776577667767776877697770777177727773777477757776777777787779778077817782778377847785778677877788778977907791779277937794779577967797779877997800780178027803780478057806780778087809781078117812781378147815781678177818781978207821782278237824782578267827782878297830783178327833783478357836783778387839784078417842784378447845784678477848784978507851785278537854785578567857785878597860786178627863786478657866786778687869787078717872787378747875787678777878787978807881788278837884788578867887788878897890789178927893789478957896789778987899790079017902790379047905790679077908790979107911791279137914791579167917791879197920792179227923792479257926792779287929793079317932793379347935793679377938793979407941794279437944794579467947794879497950795179527953795479557956795779587959796079617962796379647965796679677968796979707971797279737974797579767977797879797980798179827983798479857986798779887989799079917992799379947995799679977998799980008001800280038004800580068007800880098010801180128013801480158016801780188019802080218022802380248025802680278028802980308031803280338034803580368037803880398040804180428043804480458046804780488049805080518052805380548055805680578058805980608061806280638064806580668067806880698070807180728073807480758076807780788079808080818082808380848085808680878088808980908091809280938094809580968097809880998100810181028103810481058106810781088109811081118112811381148115811681178118811981208121812281238124812581268127812881298130813181328133813481358136813781388139814081418142814381448145814681478148814981508151815281538154815581568157815881598160816181628163816481658166816781688169817081718172817381748175817681778178817981808181818281838184818581868187818881898190819181928193819481958196819781988199820082018202820382048205820682078208820982108211821282138214821582168217821882198220822182228223822482258226822782288229823082318232823382348235823682378238823982408241824282438244824582468247824882498250825182528253825482558256825782588259826082618262826382648265826682678268826982708271827282738274827582768277827882798280828182828283828482858286828782888289829082918292829382948295829682978298829983008301830283038304830583068307830883098310831183128313831483158316831783188319832083218322832383248325832683278328832983308331833283338334833583368337833883398340834183428343834483458346834783488349835083518352835383548355835683578358835983608361836283638364836583668367836883698370837183728373837483758376837783788379838083818382838383848385838683878388838983908391839283938394839583968397839883998400840184028403840484058406840784088409841084118412841384148415841684178418841984208421842284238424842584268427842884298430843184328433843484358436843784388439844084418442844384448445844684478448844984508451845284538454845584568457845884598460846184628463846484658466846784688469847084718472847384748475847684778478847984808481848284838484848584868487848884898490849184928493849484958496849784988499850085018502850385048505850685078508850985108511851285138514851585168517851885198520852185228523852485258526852785288529853085318532853385348535853685378538853985408541854285438544854585468547854885498550855185528553855485558556855785588559856085618562856385648565856685678568856985708571857285738574857585768577857885798580858185828583858485858586858785888589859085918592859385948595859685978598859986008601860286038604860586068607860886098610861186128613861486158616861786188619862086218622862386248625862686278628862986308631863286338634863586368637863886398640864186428643864486458646864786488649865086518652865386548655865686578658865986608661866286638664866586668667866886698670867186728673867486758676867786788679868086818682868386848685868686878688868986908691869286938694869586968697869886998700870187028703870487058706870787088709871087118712871387148715871687178718871987208721872287238724872587268727872887298730873187328733873487358736873787388739874087418742874387448745874687478748874987508751875287538754875587568757875887598760876187628763876487658766876787688769877087718772877387748775877687778778877987808781878287838784878587868787878887898790879187928793879487958796879787988799880088018802880388048805880688078808880988108811881288138814881588168817881888198820882188228823882488258826882788288829883088318832883388348835883688378838883988408841884288438844884588468847884888498850885188528853885488558856885788588859886088618862886388648865886688678868886988708871887288738874887588768877887888798880888188828883888488858886888788888889889088918892889388948895889688978898889989008901890289038904890589068907890889098910891189128913891489158916891789188919892089218922892389248925892689278928892989308931893289338934893589368937893889398940894189428943894489458946894789488949895089518952895389548955895689578958895989608961896289638964896589668967896889698970897189728973897489758976897789788979898089818982898389848985898689878988898989908991899289938994899589968997899889999000900190029003900490059006900790089009901090119012901390149015901690179018901990209021902290239024902590269027902890299030903190329033903490359036903790389039904090419042904390449045904690479048904990509051905290539054905590569057905890599060906190629063906490659066906790689069907090719072907390749075907690779078907990809081908290839084908590869087908890899090909190929093909490959096909790989099910091019102910391049105910691079108910991109111911291139114911591169117911891199120912191229123912491259126912791289129913091319132913391349135913691379138913991409141914291439144914591469147914891499150915191529153915491559156915791589159916091619162916391649165916691679168916991709171917291739174917591769177917891799180918191829183918491859186918791889189919091919192919391949195919691979198919992009201920292039204920592069207920892099210921192129213921492159216921792189219922092219222922392249225922692279228922992309231923292339234923592369237923892399240924192429243924492459246924792489249925092519252925392549255925692579258925992609261926292639264926592669267926892699270927192729273927492759276927792789279928092819282928392849285928692879288928992909291929292939294929592969297929892999300930193029303930493059306930793089309931093119312931393149315931693179318931993209321932293239324932593269327932893299330933193329333933493359336933793389339934093419342934393449345934693479348934993509351935293539354935593569357935893599360936193629363936493659366936793689369937093719372937393749375937693779378937993809381938293839384938593869387938893899390939193929393939493959396939793989399940094019402940394049405940694079408940994109411941294139414941594169417941894199420942194229423942494259426942794289429943094319432943394349435943694379438943994409441944294439444944594469447944894499450945194529453945494559456945794589459946094619462946394649465946694679468946994709471947294739474947594769477947894799480948194829483948494859486948794889489949094919492949394949495949694979498949995009501950295039504950595069507950895099510951195129513951495159516951795189519952095219522952395249525952695279528952995309531953295339534953595369537953895399540954195429543954495459546954795489549955095519552955395549555955695579558955995609561956295639564956595669567956895699570957195729573957495759576957795789579958095819582958395849585958695879588958995909591959295939594959595969597959895999600960196029603960496059606960796089609961096119612961396149615961696179618961996209621962296239624962596269627962896299630963196329633963496359636963796389639964096419642964396449645964696479648964996509651965296539654965596569657965896599660966196629663966496659666966796689669967096719672967396749675967696779678967996809681968296839684968596869687968896899690969196929693969496959696969796989699970097019702970397049705970697079708970997109711971297139714971597169717971897199720972197229723972497259726972797289729973097319732973397349735973697379738973997409741974297439744974597469747974897499750975197529753975497559756975797589759976097619762976397649765976697679768976997709771977297739774977597769777977897799780978197829783978497859786978797889789979097919792979397949795979697979798979998009801980298039804980598069807980898099810981198129813981498159816981798189819982098219822982398249825982698279828982998309831983298339834983598369837983898399840984198429843984498459846984798489849985098519852985398549855985698579858985998609861986298639864986598669867986898699870987198729873987498759876987798789879988098819882988398849885988698879888988998909891989298939894989598969897989898999900990199029903990499059906990799089909991099119912991399149915991699179918991999209921992299239924992599269927992899299930993199329933993499359936993799389939994099419942994399449945994699479948994999509951995299539954995599569957995899599960996199629963996499659966996799689969997099719972997399749975997699779978997999809981998299839984998599869987998899899990999199929993999499959996999799989999100001000110002100031000410005100061000710008100091001010011100121001310014100151001610017100181001910020100211002210023100241002510026100271002810029100301003110032100331003410035100361003710038100391004010041100421004310044100451004610047100481004910050100511005210053100541005510056100571005810059100601006110062100631006410065100661006710068100691007010071100721007310074100751007610077100781007910080100811008210083100841008510086100871008810089100901009110092100931009410095100961009710098100991010010101101021010310104101051010610107101081010910110101111011210113101141011510116101171011810119101201012110122101231012410125101261012710128101291013010131101321013310134101351013610137101381013910140101411014210143101441014510146101471014810149101501015110152101531015410155101561015710158101591016010161101621016310164101651016610167101681016910170101711017210173101741017510176101771017810179101801018110182101831018410185101861018710188101891019010191101921019310194101951019610197101981019910200102011020210203102041020510206102071020810209102101021110212102131021410215102161021710218102191022010221102221022310224102251022610227102281022910230102311023210233102341023510236102371023810239102401024110242102431024410245102461024710248102491025010251102521025310254102551025610257102581025910260102611026210263102641026510266102671026810269102701027110272102731027410275102761027710278102791028010281102821028310284102851028610287102881028910290102911029210293102941029510296102971029810299103001030110302103031030410305103061030710308103091031010311103121031310314103151031610317103181031910320103211032210323103241032510326103271032810329103301033110332103331033410335103361033710338103391034010341103421034310344103451034610347103481034910350103511035210353103541035510356103571035810359103601036110362103631036410365103661036710368103691037010371103721037310374103751037610377103781037910380103811038210383103841038510386103871038810389103901039110392103931039410395103961039710398103991040010401104021040310404104051040610407104081040910410104111041210413104141041510416104171041810419104201042110422104231042410425104261042710428104291043010431104321043310434104351043610437104381043910440104411044210443104441044510446104471044810449104501045110452104531045410455104561045710458104591046010461104621046310464104651046610467104681046910470104711047210473104741047510476104771047810479104801048110482104831048410485104861048710488104891049010491104921049310494104951049610497104981049910500105011050210503105041050510506105071050810509105101051110512105131051410515105161051710518105191052010521105221052310524105251052610527105281052910530105311053210533105341053510536105371053810539105401054110542105431054410545105461054710548105491055010551105521055310554105551055610557105581055910560105611056210563105641056510566105671056810569105701057110572105731057410575105761057710578105791058010581105821058310584105851058610587105881058910590105911059210593105941059510596105971059810599106001060110602106031060410605106061060710608106091061010611106121061310614106151061610617106181061910620106211062210623106241062510626106271062810629106301063110632106331063410635106361063710638106391064010641106421064310644106451064610647106481064910650106511065210653106541065510656106571065810659106601066110662106631066410665106661066710668106691067010671106721067310674106751067610677106781067910680106811068210683106841068510686106871068810689106901069110692106931069410695106961069710698106991070010701107021070310704107051070610707107081070910710107111071210713107141071510716107171071810719107201072110722107231072410725107261072710728107291073010731107321073310734107351073610737107381073910740107411074210743107441074510746107471074810749107501075110752107531075410755107561075710758107591076010761107621076310764107651076610767107681076910770107711077210773107741077510776107771077810779107801078110782107831078410785107861078710788107891079010791107921079310794107951079610797107981079910800108011080210803108041080510806108071080810809108101081110812108131081410815108161081710818108191082010821108221082310824108251082610827108281082910830108311083210833108341083510836108371083810839108401084110842108431084410845108461084710848108491085010851108521085310854108551085610857108581085910860108611086210863108641086510866108671086810869108701087110872108731087410875108761087710878108791088010881108821088310884108851088610887108881088910890108911089210893108941089510896108971089810899109001090110902109031090410905109061090710908109091091010911109121091310914109151091610917109181091910920109211092210923109241092510926109271092810929109301093110932109331093410935109361093710938109391094010941109421094310944109451094610947109481094910950109511095210953109541095510956109571095810959109601096110962109631096410965109661096710968109691097010971109721097310974109751097610977109781097910980109811098210983109841098510986109871098810989109901099110992109931099410995109961099710998109991100011001110021100311004110051100611007110081100911010110111101211013110141101511016110171101811019110201102111022110231102411025110261102711028110291103011031110321103311034110351103611037110381103911040110411104211043110441104511046110471104811049110501105111052110531105411055110561105711058110591106011061110621106311064110651106611067110681106911070110711107211073110741107511076110771107811079110801108111082110831108411085110861108711088110891109011091110921109311094110951109611097110981109911100111011110211103111041110511106111071110811109111101111111112111131111411115111161111711118111191112011121111221112311124111251112611127111281112911130111311113211133111341113511136111371113811139111401114111142111431114411145111461114711148111491115011151111521115311154111551115611157111581115911160111611116211163111641116511166111671116811169111701117111172111731117411175111761117711178111791118011181111821118311184111851118611187111881118911190111911119211193111941119511196111971119811199112001120111202112031120411205112061120711208112091121011211112121121311214112151121611217112181121911220112211122211223112241122511226112271122811229112301123111232112331123411235112361123711238112391124011241112421124311244112451124611247112481124911250112511125211253112541125511256112571125811259112601126111262112631126411265112661126711268112691127011271112721127311274112751127611277112781127911280112811128211283112841128511286112871128811289112901129111292112931129411295112961129711298112991130011301113021130311304113051130611307113081130911310113111131211313113141131511316113171131811319113201132111322113231132411325113261132711328113291133011331113321133311334113351133611337113381133911340113411134211343113441134511346113471134811349113501135111352113531135411355113561135711358113591136011361113621136311364113651136611367113681136911370113711137211373113741137511376113771137811379113801138111382113831138411385113861138711388113891139011391113921139311394113951139611397113981139911400114011140211403114041140511406114071140811409114101141111412114131141411415114161141711418114191142011421114221142311424114251142611427114281142911430114311143211433114341143511436114371143811439114401144111442114431144411445114461144711448114491145011451114521145311454114551145611457114581145911460114611146211463114641146511466114671146811469114701147111472114731147411475114761147711478114791148011481114821148311484114851148611487114881148911490114911149211493114941149511496114971149811499115001150111502115031150411505115061150711508115091151011511115121151311514115151151611517115181151911520115211152211523115241152511526115271152811529115301153111532115331153411535115361153711538115391154011541115421154311544115451154611547115481154911550115511155211553115541155511556115571155811559115601156111562115631156411565115661156711568115691157011571115721157311574115751157611577115781157911580115811158211583115841158511586115871158811589115901159111592115931159411595115961159711598115991160011601116021160311604116051160611607116081160911610116111161211613116141161511616116171161811619116201162111622116231162411625116261162711628116291163011631116321163311634116351163611637116381163911640116411164211643116441164511646116471164811649116501165111652116531165411655116561165711658116591166011661116621166311664116651166611667116681166911670116711167211673116741167511676116771167811679116801168111682116831168411685116861168711688116891169011691116921169311694116951169611697116981169911700117011170211703117041170511706117071170811709117101171111712117131171411715117161171711718117191172011721117221172311724117251172611727117281172911730117311173211733117341173511736117371173811739117401174111742117431174411745117461174711748117491175011751117521175311754117551175611757117581175911760117611176211763117641176511766117671176811769117701177111772117731177411775117761177711778117791178011781117821178311784117851178611787117881178911790117911179211793117941179511796117971179811799118001180111802118031180411805118061180711808118091181011811118121181311814118151181611817118181181911820118211182211823118241182511826118271182811829118301183111832118331183411835118361183711838118391184011841118421184311844118451184611847118481184911850118511185211853118541185511856118571185811859118601186111862118631186411865118661186711868118691187011871118721187311874118751187611877118781187911880118811188211883118841188511886118871188811889118901189111892118931189411895118961189711898118991190011901119021190311904119051190611907119081190911910119111191211913119141191511916119171191811919119201192111922119231192411925119261192711928119291193011931119321193311934119351193611937119381193911940119411194211943119441194511946119471194811949119501195111952119531195411955119561195711958119591196011961119621196311964119651196611967119681196911970119711197211973119741197511976119771197811979119801198111982119831198411985119861198711988119891199011991119921199311994119951199611997119981199912000120011200212003120041200512006120071200812009120101201112012120131201412015120161201712018120191202012021120221202312024120251202612027120281202912030120311203212033120341203512036120371203812039120401204112042120431204412045120461204712048120491205012051120521205312054120551205612057120581205912060120611206212063120641206512066120671206812069120701207112072120731207412075120761207712078120791208012081120821208312084120851208612087120881208912090120911209212093120941209512096120971209812099121001210112102121031210412105121061210712108121091211012111121121211312114121151211612117121181211912120121211212212123121241212512126121271212812129121301213112132121331213412135121361213712138121391214012141121421214312144121451214612147121481214912150121511215212153121541215512156121571215812159121601216112162121631216412165121661216712168121691217012171121721217312174121751217612177121781217912180121811218212183121841218512186121871218812189121901219112192121931219412195121961219712198121991220012201122021220312204122051220612207122081220912210122111221212213122141221512216122171221812219122201222112222122231222412225122261222712228122291223012231122321223312234122351223612237122381223912240122411224212243122441224512246122471224812249122501225112252122531225412255122561225712258122591226012261122621226312264122651226612267122681226912270122711227212273122741227512276122771227812279122801228112282122831228412285122861228712288122891229012291122921229312294122951229612297122981229912300123011230212303123041230512306123071230812309123101231112312123131231412315123161231712318123191232012321123221232312324123251232612327123281232912330123311233212333123341233512336123371233812339123401234112342123431234412345123461234712348123491235012351123521235312354123551235612357123581235912360123611236212363123641236512366123671236812369123701237112372123731237412375123761237712378123791238012381123821238312384123851238612387123881238912390123911239212393123941239512396123971239812399124001240112402124031240412405124061240712408124091241012411124121241312414124151241612417124181241912420124211242212423124241242512426124271242812429124301243112432124331243412435124361243712438124391244012441124421244312444124451244612447124481244912450124511245212453124541245512456124571245812459124601246112462124631246412465124661246712468124691247012471124721247312474124751247612477124781247912480124811248212483124841248512486124871248812489124901249112492124931249412495124961249712498124991250012501125021250312504125051250612507125081250912510125111251212513125141251512516125171251812519125201252112522125231252412525125261252712528125291253012531125321253312534125351253612537125381253912540125411254212543125441254512546125471254812549125501255112552125531255412555125561255712558125591256012561125621256312564125651256612567125681256912570125711257212573125741257512576125771257812579125801258112582125831258412585125861258712588125891259012591125921259312594125951259612597125981259912600126011260212603126041260512606126071260812609126101261112612126131261412615126161261712618126191262012621126221262312624126251262612627126281262912630126311263212633126341263512636126371263812639126401264112642126431264412645126461264712648126491265012651126521265312654126551265612657126581265912660126611266212663126641266512666126671266812669126701267112672126731267412675126761267712678126791268012681126821268312684126851268612687126881268912690126911269212693126941269512696126971269812699127001270112702127031270412705127061270712708127091271012711127121271312714127151271612717127181271912720127211272212723127241272512726127271272812729127301273112732127331273412735127361273712738127391274012741127421274312744127451274612747127481274912750127511275212753127541275512756127571275812759127601276112762127631276412765127661276712768127691277012771127721277312774127751277612777127781277912780127811278212783127841278512786127871278812789127901279112792127931279412795127961279712798127991280012801128021280312804128051280612807128081280912810128111281212813128141281512816128171281812819128201282112822128231282412825128261282712828128291283012831128321283312834128351283612837128381283912840128411284212843128441284512846128471284812849128501285112852128531285412855128561285712858128591286012861128621286312864128651286612867128681286912870128711287212873128741287512876128771287812879128801288112882128831288412885128861288712888128891289012891128921289312894128951289612897128981289912900129011290212903129041290512906129071290812909129101291112912129131291412915129161291712918129191292012921129221292312924129251292612927129281292912930129311293212933129341293512936129371293812939129401294112942129431294412945129461294712948129491295012951129521295312954129551295612957129581295912960129611296212963129641296512966129671296812969129701297112972129731297412975129761297712978129791298012981129821298312984129851298612987129881298912990129911299212993129941299512996129971299812999130001300113002130031300413005130061300713008130091301013011130121301313014130151301613017130181301913020130211302213023130241302513026130271302813029130301303113032130331303413035130361303713038130391304013041130421304313044130451304613047130481304913050130511305213053130541305513056130571305813059130601306113062130631306413065130661306713068130691307013071130721307313074130751307613077130781307913080130811308213083130841308513086130871308813089130901309113092130931309413095130961309713098130991310013101131021310313104131051310613107131081310913110131111311213113131141311513116131171311813119131201312113122131231312413125131261312713128131291313013131131321313313134131351313613137131381313913140131411314213143131441314513146131471314813149131501315113152131531315413155131561315713158131591316013161131621316313164131651316613167131681316913170131711317213173131741317513176131771317813179131801318113182131831318413185131861318713188131891319013191131921319313194131951319613197131981319913200132011320213203132041320513206132071320813209132101321113212132131321413215132161321713218132191322013221132221322313224132251322613227132281322913230132311323213233132341323513236132371323813239132401324113242132431324413245132461324713248132491325013251132521325313254132551325613257132581325913260132611326213263132641326513266132671326813269132701327113272132731327413275132761327713278132791328013281132821328313284132851328613287132881328913290132911329213293132941329513296132971329813299133001330113302133031330413305133061330713308133091331013311133121331313314133151331613317133181331913320133211332213323133241332513326133271332813329133301333113332133331333413335133361333713338133391334013341133421334313344133451334613347133481334913350133511335213353133541335513356133571335813359133601336113362133631336413365133661336713368133691337013371133721337313374133751337613377133781337913380133811338213383133841338513386133871338813389133901339113392133931339413395133961339713398133991340013401134021340313404134051340613407134081340913410134111341213413134141341513416134171341813419134201342113422134231342413425134261342713428134291343013431134321343313434134351343613437134381343913440134411344213443134441344513446134471344813449134501345113452134531345413455134561345713458134591346013461134621346313464134651346613467134681346913470134711347213473134741347513476134771347813479134801348113482134831348413485134861348713488134891349013491134921349313494134951349613497134981349913500135011350213503135041350513506135071350813509135101351113512135131351413515135161351713518135191352013521135221352313524135251352613527135281352913530135311353213533135341353513536135371353813539135401354113542135431354413545135461354713548135491355013551135521355313554135551355613557135581355913560135611356213563135641356513566135671356813569135701357113572135731357413575135761357713578135791358013581135821358313584135851358613587135881358913590135911359213593135941359513596135971359813599136001360113602136031360413605136061360713608136091361013611136121361313614136151361613617136181361913620136211362213623136241362513626136271362813629136301363113632136331363413635136361363713638136391364013641136421364313644136451364613647136481364913650136511365213653136541365513656136571365813659136601366113662136631366413665136661366713668136691367013671136721367313674136751367613677136781367913680136811368213683136841368513686136871368813689136901369113692136931369413695136961369713698136991370013701137021370313704137051370613707137081370913710137111371213713137141371513716137171371813719137201372113722137231372413725137261372713728137291373013731137321373313734137351373613737137381373913740137411374213743137441374513746137471374813749137501375113752137531375413755137561375713758137591376013761137621376313764137651376613767137681376913770137711377213773137741377513776137771377813779137801378113782137831378413785137861378713788137891379013791137921379313794137951379613797137981379913800138011380213803138041380513806138071380813809138101381113812138131381413815138161381713818138191382013821138221382313824138251382613827138281382913830138311383213833138341383513836138371383813839138401384113842138431384413845138461384713848138491385013851138521385313854138551385613857138581385913860138611386213863138641386513866138671386813869138701387113872138731387413875138761387713878138791388013881138821388313884138851388613887138881388913890138911389213893138941389513896138971389813899139001390113902139031390413905139061390713908139091391013911139121391313914139151391613917139181391913920139211392213923139241392513926139271392813929139301393113932139331393413935139361393713938139391394013941139421394313944139451394613947139481394913950139511395213953139541395513956139571395813959139601396113962139631396413965139661396713968139691397013971139721397313974139751397613977139781397913980139811398213983139841398513986139871398813989139901399113992139931399413995139961399713998139991400014001140021400314004140051400614007140081400914010140111401214013140141401514016140171401814019140201402114022140231402414025140261402714028140291403014031140321403314034140351403614037140381403914040140411404214043140441404514046140471404814049140501405114052140531405414055140561405714058140591406014061140621406314064140651406614067140681406914070140711407214073140741407514076140771407814079140801408114082140831408414085140861408714088140891409014091140921409314094140951409614097140981409914100141011410214103141041410514106141071410814109141101411114112141131411414115141161411714118141191412014121141221412314124141251412614127141281412914130141311413214133141341413514136141371413814139141401414114142141431414414145141461414714148141491415014151141521415314154141551415614157141581415914160141611416214163141641416514166141671416814169141701417114172141731417414175141761417714178141791418014181141821418314184141851418614187141881418914190141911419214193141941419514196141971419814199142001420114202142031420414205142061420714208142091421014211142121421314214142151421614217142181421914220142211422214223142241422514226142271422814229142301423114232142331423414235142361423714238142391424014241142421424314244142451424614247142481424914250142511425214253142541425514256142571425814259142601426114262142631426414265142661426714268142691427014271142721427314274142751427614277142781427914280142811428214283142841428514286142871428814289142901429114292142931429414295142961429714298142991430014301143021430314304143051430614307143081430914310143111431214313143141431514316143171431814319143201432114322143231432414325143261432714328143291433014331143321433314334143351433614337143381433914340143411434214343143441434514346143471434814349143501435114352143531435414355143561435714358143591436014361143621436314364143651436614367143681436914370143711437214373143741437514376143771437814379143801438114382143831438414385143861438714388143891439014391143921439314394143951439614397143981439914400144011440214403144041440514406144071440814409144101441114412144131441414415144161441714418144191442014421144221442314424144251442614427144281442914430144311443214433144341443514436144371443814439144401444114442144431444414445144461444714448144491445014451144521445314454144551445614457144581445914460144611446214463144641446514466144671446814469144701447114472144731447414475144761447714478144791448014481144821448314484144851448614487144881448914490144911449214493144941449514496144971449814499145001450114502145031450414505145061450714508145091451014511145121451314514145151451614517145181451914520145211452214523145241452514526145271452814529145301453114532145331453414535145361453714538145391454014541145421454314544145451454614547145481454914550145511455214553145541455514556145571455814559145601456114562145631456414565145661456714568145691457014571145721457314574145751457614577145781457914580145811458214583145841458514586145871458814589145901459114592145931459414595145961459714598145991460014601146021460314604146051460614607146081460914610146111461214613146141461514616146171461814619146201462114622146231462414625146261462714628146291463014631146321463314634146351463614637146381463914640146411464214643146441464514646146471464814649146501465114652146531465414655146561465714658146591466014661146621466314664146651466614667146681466914670146711467214673146741467514676146771467814679146801468114682146831468414685146861468714688146891469014691146921469314694146951469614697146981469914700147011470214703147041470514706147071470814709147101471114712147131471414715147161471714718147191472014721147221472314724147251472614727147281472914730147311473214733147341473514736147371473814739147401474114742147431474414745147461474714748147491475014751147521475314754147551475614757147581475914760147611476214763147641476514766147671476814769147701477114772147731477414775147761477714778147791478014781147821478314784147851478614787147881478914790147911479214793147941479514796147971479814799148001480114802148031480414805148061480714808148091481014811148121481314814148151481614817148181481914820148211482214823148241482514826148271482814829148301483114832148331483414835148361483714838148391484014841148421484314844148451484614847148481484914850148511485214853148541485514856148571485814859148601486114862148631486414865148661486714868148691487014871148721487314874148751487614877148781487914880148811488214883148841488514886148871488814889148901489114892148931489414895148961489714898148991490014901149021490314904149051490614907149081490914910149111491214913149141491514916149171491814919149201492114922149231492414925149261492714928149291493014931149321493314934149351493614937149381493914940149411494214943149441494514946149471494814949149501495114952149531495414955149561495714958149591496014961149621496314964149651496614967149681496914970149711497214973149741497514976149771497814979149801498114982149831498414985149861498714988149891499014991149921499314994149951499614997149981499915000150011500215003150041500515006150071500815009150101501115012150131501415015150161501715018150191502015021150221502315024150251502615027150281502915030150311503215033150341503515036150371503815039150401504115042150431504415045150461504715048150491505015051150521505315054150551505615057150581505915060150611506215063150641506515066150671506815069150701507115072150731507415075150761507715078150791508015081150821508315084150851508615087150881508915090150911509215093150941509515096150971509815099151001510115102151031510415105151061510715108151091511015111151121511315114151151511615117151181511915120151211512215123151241512515126151271512815129151301513115132151331513415135151361513715138151391514015141151421514315144151451514615147151481514915150151511515215153151541515515156151571515815159151601516115162151631516415165151661516715168151691517015171151721517315174151751517615177151781517915180151811518215183151841518515186151871518815189151901519115192151931519415195151961519715198151991520015201152021520315204152051520615207152081520915210152111521215213152141521515216152171521815219152201522115222152231522415225152261522715228152291523015231152321523315234152351523615237152381523915240152411524215243152441524515246152471524815249152501525115252152531525415255152561525715258152591526015261152621526315264152651526615267152681526915270152711527215273152741527515276152771527815279152801528115282152831528415285152861528715288152891529015291152921529315294152951529615297152981529915300153011530215303153041530515306153071530815309153101531115312153131531415315153161531715318153191532015321153221532315324153251532615327153281532915330153311533215333153341533515336153371533815339153401534115342153431534415345153461534715348153491535015351153521535315354153551535615357153581535915360153611536215363153641536515366153671536815369153701537115372153731537415375153761537715378153791538015381153821538315384153851538615387153881538915390153911539215393153941539515396153971539815399154001540115402154031540415405154061540715408154091541015411154121541315414154151541615417154181541915420154211542215423154241542515426154271542815429154301543115432154331543415435154361543715438154391544015441154421544315444154451544615447154481544915450154511545215453154541545515456154571545815459154601546115462154631546415465154661546715468154691547015471154721547315474154751547615477154781547915480154811548215483154841548515486154871548815489154901549115492154931549415495154961549715498154991550015501155021550315504155051550615507155081550915510155111551215513155141551515516155171551815519155201552115522155231552415525155261552715528155291553015531155321553315534155351553615537155381553915540155411554215543155441554515546155471554815549155501555115552155531555415555155561555715558155591556015561155621556315564155651556615567155681556915570155711557215573155741557515576155771557815579155801558115582155831558415585155861558715588155891559015591155921559315594155951559615597155981559915600156011560215603156041560515606156071560815609156101561115612156131561415615156161561715618156191562015621156221562315624156251562615627156281562915630156311563215633156341563515636156371563815639156401564115642156431564415645156461564715648156491565015651156521565315654156551565615657156581565915660156611566215663156641566515666156671566815669156701567115672156731567415675156761567715678156791568015681156821568315684156851568615687156881568915690156911569215693156941569515696156971569815699157001570115702157031570415705157061570715708157091571015711157121571315714157151571615717157181571915720157211572215723157241572515726157271572815729157301573115732157331573415735157361573715738157391574015741157421574315744157451574615747157481574915750157511575215753157541575515756157571575815759157601576115762157631576415765157661576715768157691577015771157721577315774157751577615777157781577915780157811578215783157841578515786157871578815789157901579115792157931579415795157961579715798157991580015801158021580315804158051580615807158081580915810158111581215813158141581515816158171581815819158201582115822158231582415825158261582715828158291583015831158321583315834158351583615837158381583915840158411584215843158441584515846158471584815849158501585115852158531585415855158561585715858158591586015861158621586315864158651586615867158681586915870158711587215873158741587515876158771587815879158801588115882158831588415885158861588715888158891589015891158921589315894158951589615897158981589915900159011590215903159041590515906159071590815909159101591115912159131591415915159161591715918159191592015921159221592315924159251592615927159281592915930159311593215933159341593515936159371593815939159401594115942159431594415945159461594715948159491595015951159521595315954159551595615957159581595915960159611596215963159641596515966159671596815969159701597115972159731597415975159761597715978159791598015981159821598315984159851598615987159881598915990159911599215993159941599515996159971599815999160001600116002160031600416005160061600716008160091601016011160121601316014160151601616017160181601916020160211602216023160241602516026160271602816029160301603116032160331603416035160361603716038160391604016041160421604316044160451604616047160481604916050160511605216053160541605516056160571605816059160601606116062160631606416065160661606716068160691607016071160721607316074160751607616077160781607916080160811608216083160841608516086160871608816089160901609116092160931609416095160961609716098160991610016101161021610316104161051610616107161081610916110161111611216113161141611516116161171611816119161201612116122161231612416125161261612716128161291613016131161321613316134161351613616137161381613916140161411614216143161441614516146161471614816149161501615116152161531615416155161561615716158161591616016161161621616316164161651616616167161681616916170161711617216173161741617516176161771617816179161801618116182161831618416185161861618716188161891619016191161921619316194161951619616197161981619916200162011620216203162041620516206162071620816209162101621116212162131621416215162161621716218162191622016221162221622316224162251622616227162281622916230162311623216233162341623516236162371623816239162401624116242162431624416245162461624716248162491625016251162521625316254162551625616257162581625916260162611626216263162641626516266162671626816269162701627116272162731627416275162761627716278162791628016281162821628316284162851628616287162881628916290162911629216293162941629516296162971629816299163001630116302163031630416305163061630716308163091631016311163121631316314163151631616317163181631916320163211632216323163241632516326163271632816329163301633116332163331633416335163361633716338163391634016341163421634316344163451634616347163481634916350163511635216353163541635516356163571635816359163601636116362163631636416365163661636716368163691637016371163721637316374163751637616377163781637916380163811638216383163841638516386163871638816389163901639116392163931639416395163961639716398163991640016401164021640316404164051640616407164081640916410164111641216413164141641516416164171641816419164201642116422164231642416425164261642716428164291643016431164321643316434164351643616437164381643916440164411644216443164441644516446164471644816449164501645116452164531645416455164561645716458164591646016461164621646316464164651646616467164681646916470164711647216473164741647516476164771647816479164801648116482164831648416485164861648716488164891649016491164921649316494164951649616497164981649916500165011650216503165041650516506165071650816509165101651116512165131651416515165161651716518165191652016521165221652316524165251652616527165281652916530165311653216533165341653516536165371653816539165401654116542165431654416545165461654716548165491655016551165521655316554165551655616557165581655916560165611656216563165641656516566165671656816569165701657116572165731657416575165761657716578165791658016581165821658316584165851658616587165881658916590165911659216593165941659516596165971659816599166001660116602166031660416605166061660716608166091661016611166121661316614166151661616617166181661916620166211662216623166241662516626166271662816629166301663116632166331663416635166361663716638166391664016641166421664316644166451664616647166481664916650166511665216653166541665516656166571665816659166601666116662166631666416665166661666716668166691667016671166721667316674166751667616677166781667916680166811668216683166841668516686166871668816689166901669116692166931669416695166961669716698166991670016701167021670316704167051670616707167081670916710167111671216713167141671516716167171671816719167201672116722167231672416725167261672716728167291673016731167321673316734167351673616737167381673916740167411674216743167441674516746167471674816749167501675116752167531675416755167561675716758167591676016761167621676316764167651676616767167681676916770167711677216773167741677516776167771677816779167801678116782167831678416785167861678716788167891679016791167921679316794167951679616797167981679916800168011680216803168041680516806168071680816809168101681116812168131681416815168161681716818168191682016821168221682316824168251682616827168281682916830168311683216833168341683516836168371683816839168401684116842168431684416845168461684716848168491685016851168521685316854168551685616857168581685916860168611686216863168641686516866168671686816869168701687116872168731687416875168761687716878168791688016881168821688316884168851688616887168881688916890168911689216893168941689516896168971689816899169001690116902169031690416905169061690716908169091691016911169121691316914169151691616917169181691916920169211692216923169241692516926169271692816929169301693116932169331693416935169361693716938169391694016941169421694316944169451694616947169481694916950169511695216953169541695516956169571695816959169601696116962169631696416965169661696716968169691697016971169721697316974169751697616977169781697916980169811698216983169841698516986169871698816989169901699116992169931699416995169961699716998169991700017001170021700317004170051700617007170081700917010170111701217013170141701517016170171701817019170201702117022170231702417025170261702717028170291703017031170321703317034170351703617037170381703917040170411704217043170441704517046170471704817049170501705117052170531705417055170561705717058170591706017061170621706317064170651706617067170681706917070170711707217073170741707517076170771707817079170801708117082170831708417085170861708717088170891709017091170921709317094170951709617097170981709917100171011710217103171041710517106171071710817109171101711117112171131711417115171161711717118171191712017121171221712317124171251712617127171281712917130171311713217133171341713517136171371713817139171401714117142171431714417145171461714717148171491715017151171521715317154171551715617157171581715917160171611716217163171641716517166171671716817169171701717117172171731717417175171761717717178171791718017181171821718317184171851718617187171881718917190171911719217193171941719517196171971719817199172001720117202172031720417205172061720717208172091721017211172121721317214172151721617217172181721917220172211722217223172241722517226172271722817229172301723117232172331723417235172361723717238172391724017241172421724317244172451724617247172481724917250172511725217253172541725517256172571725817259172601726117262172631726417265172661726717268172691727017271172721727317274172751727617277172781727917280172811728217283172841728517286172871728817289172901729117292172931729417295172961729717298172991730017301173021730317304173051730617307173081730917310173111731217313173141731517316173171731817319173201732117322173231732417325173261732717328173291733017331173321733317334173351733617337173381733917340173411734217343173441734517346173471734817349173501735117352173531735417355173561735717358173591736017361173621736317364173651736617367173681736917370173711737217373173741737517376173771737817379173801738117382173831738417385173861738717388173891739017391173921739317394173951739617397173981739917400174011740217403174041740517406174071740817409174101741117412174131741417415174161741717418174191742017421174221742317424174251742617427174281742917430174311743217433174341743517436174371743817439174401744117442174431744417445174461744717448174491745017451174521745317454174551745617457174581745917460174611746217463174641746517466174671746817469174701747117472174731747417475174761747717478174791748017481174821748317484174851748617487174881748917490174911749217493174941749517496174971749817499175001750117502175031750417505175061750717508175091751017511175121751317514175151751617517175181751917520175211752217523175241752517526175271752817529175301753117532175331753417535175361753717538175391754017541175421754317544175451754617547175481754917550175511755217553175541755517556175571755817559175601756117562175631756417565175661756717568175691757017571175721757317574175751757617577175781757917580175811758217583175841758517586175871758817589175901759117592175931759417595175961759717598175991760017601176021760317604176051760617607176081760917610176111761217613176141761517616176171761817619176201762117622176231762417625176261762717628176291763017631176321763317634176351763617637176381763917640176411764217643176441764517646176471764817649176501765117652176531765417655176561765717658176591766017661176621766317664176651766617667176681766917670176711767217673176741767517676176771767817679176801768117682176831768417685176861768717688176891769017691176921769317694176951769617697176981769917700177011770217703177041770517706177071770817709177101771117712177131771417715177161771717718177191772017721177221772317724177251772617727177281772917730177311773217733177341773517736177371773817739177401774117742177431774417745177461774717748177491775017751177521775317754177551775617757177581775917760177611776217763177641776517766177671776817769177701777117772177731777417775177761777717778177791778017781177821778317784177851778617787177881778917790177911779217793177941779517796177971779817799178001780117802178031780417805178061780717808178091781017811178121781317814178151781617817178181781917820178211782217823178241782517826178271782817829178301783117832178331783417835178361783717838178391784017841178421784317844178451784617847178481784917850178511785217853178541785517856178571785817859178601786117862178631786417865178661786717868178691787017871178721787317874178751787617877178781787917880178811788217883178841788517886178871788817889178901789117892178931789417895178961789717898178991790017901179021790317904179051790617907179081790917910179111791217913179141791517916179171791817919179201792117922179231792417925179261792717928179291793017931179321793317934179351793617937179381793917940179411794217943179441794517946179471794817949179501795117952179531795417955179561795717958179591796017961179621796317964179651796617967179681796917970179711797217973179741797517976179771797817979179801798117982179831798417985179861798717988179891799017991179921799317994179951799617997179981799918000180011800218003180041800518006180071800818009180101801118012180131801418015180161801718018180191802018021180221802318024180251802618027180281802918030180311803218033180341803518036180371803818039180401804118042180431804418045180461804718048180491805018051180521805318054180551805618057180581805918060180611806218063180641806518066180671806818069180701807118072180731807418075180761807718078180791808018081180821808318084180851808618087180881808918090180911809218093180941809518096180971809818099181001810118102181031810418105181061810718108181091811018111181121811318114181151811618117181181811918120181211812218123181241812518126181271812818129181301813118132181331813418135181361813718138181391814018141181421814318144181451814618147181481814918150181511815218153181541815518156181571815818159181601816118162181631816418165181661816718168181691817018171181721817318174181751817618177181781817918180181811818218183181841818518186181871818818189181901819118192181931819418195181961819718198181991820018201182021820318204182051820618207182081820918210182111821218213182141821518216182171821818219182201822118222182231822418225182261822718228182291823018231182321823318234182351823618237182381823918240182411824218243182441824518246182471824818249182501825118252182531825418255182561825718258182591826018261182621826318264182651826618267182681826918270182711827218273182741827518276182771827818279182801828118282182831828418285182861828718288182891829018291182921829318294182951829618297182981829918300183011830218303183041830518306183071830818309183101831118312183131831418315183161831718318183191832018321183221832318324183251832618327183281832918330183311833218333183341833518336183371833818339183401834118342183431834418345183461834718348183491835018351183521835318354183551835618357183581835918360183611836218363183641836518366183671836818369183701837118372183731837418375183761837718378183791838018381183821838318384183851838618387183881838918390183911839218393183941839518396183971839818399184001840118402184031840418405184061840718408184091841018411184121841318414184151841618417184181841918420184211842218423184241842518426184271842818429184301843118432184331843418435184361843718438184391844018441184421844318444184451844618447184481844918450184511845218453184541845518456184571845818459184601846118462184631846418465184661846718468184691847018471184721847318474184751847618477184781847918480184811848218483184841848518486184871848818489184901849118492184931849418495184961849718498184991850018501185021850318504185051850618507185081850918510185111851218513185141851518516185171851818519185201852118522185231852418525185261852718528185291853018531185321853318534185351853618537185381853918540185411854218543185441854518546185471854818549185501855118552185531855418555185561855718558185591856018561185621856318564185651856618567185681856918570185711857218573185741857518576185771857818579185801858118582185831858418585185861858718588185891859018591185921859318594185951859618597185981859918600186011860218603186041860518606186071860818609186101861118612186131861418615186161861718618186191862018621186221862318624186251862618627186281862918630186311863218633186341863518636186371863818639186401864118642186431864418645186461864718648186491865018651186521865318654186551865618657186581865918660186611866218663186641866518666186671866818669186701867118672186731867418675186761867718678186791868018681186821868318684186851868618687186881868918690186911869218693186941869518696186971869818699187001870118702187031870418705187061870718708187091871018711187121871318714187151871618717187181871918720187211872218723187241872518726187271872818729187301873118732187331873418735187361873718738187391874018741187421874318744187451874618747187481874918750187511875218753187541875518756187571875818759187601876118762187631876418765187661876718768187691877018771187721877318774187751877618777187781877918780187811878218783187841878518786187871878818789187901879118792187931879418795187961879718798187991880018801188021880318804188051880618807188081880918810188111881218813188141881518816188171881818819188201882118822188231882418825188261882718828188291883018831188321883318834188351883618837188381883918840188411884218843188441884518846188471884818849188501885118852188531885418855188561885718858188591886018861188621886318864188651886618867188681886918870188711887218873188741887518876188771887818879188801888118882188831888418885188861888718888188891889018891188921889318894188951889618897188981889918900189011890218903189041890518906189071890818909189101891118912189131891418915189161891718918189191892018921189221892318924189251892618927189281892918930189311893218933189341893518936189371893818939189401894118942189431894418945189461894718948189491895018951189521895318954189551895618957189581895918960189611896218963189641896518966189671896818969189701897118972189731897418975189761897718978189791898018981189821898318984189851898618987189881898918990189911899218993189941899518996189971899818999190001900119002190031900419005190061900719008190091901019011190121901319014190151901619017190181901919020190211902219023190241902519026190271902819029190301903119032190331903419035190361903719038190391904019041190421904319044190451904619047190481904919050190511905219053190541905519056190571905819059190601906119062190631906419065190661906719068190691907019071190721907319074190751907619077190781907919080190811908219083190841908519086190871908819089190901909119092190931909419095190961909719098190991910019101191021910319104191051910619107191081910919110191111911219113191141911519116191171911819119191201912119122191231912419125191261912719128191291913019131191321913319134191351913619137191381913919140191411914219143191441914519146191471914819149191501915119152191531915419155191561915719158191591916019161191621916319164191651916619167191681916919170191711917219173191741917519176191771917819179191801918119182191831918419185191861918719188191891919019191191921919319194191951919619197191981919919200192011920219203192041920519206192071920819209192101921119212192131921419215192161921719218192191922019221192221922319224192251922619227192281922919230192311923219233192341923519236192371923819239192401924119242192431924419245192461924719248192491925019251192521925319254192551925619257192581925919260192611926219263192641926519266192671926819269192701927119272192731927419275192761927719278192791928019281192821928319284192851928619287192881928919290192911929219293192941929519296192971929819299193001930119302193031930419305193061930719308193091931019311193121931319314193151931619317193181931919320193211932219323193241932519326193271932819329193301933119332193331933419335193361933719338193391934019341193421934319344193451934619347193481934919350193511935219353193541935519356193571935819359193601936119362193631936419365193661936719368193691937019371193721937319374193751937619377193781937919380193811938219383193841938519386193871938819389193901939119392193931939419395193961939719398193991940019401194021940319404194051940619407194081940919410194111941219413194141941519416194171941819419194201942119422194231942419425194261942719428194291943019431194321943319434194351943619437194381943919440194411944219443194441944519446194471944819449194501945119452194531945419455194561945719458194591946019461194621946319464194651946619467194681946919470194711947219473194741947519476194771947819479194801948119482194831948419485194861948719488194891949019491194921949319494194951949619497194981949919500195011950219503195041950519506195071950819509195101951119512195131951419515195161951719518195191952019521195221952319524195251952619527195281952919530195311953219533195341953519536195371953819539195401954119542195431954419545195461954719548195491955019551195521955319554195551955619557195581955919560195611956219563195641956519566195671956819569195701957119572195731957419575195761957719578195791958019581195821958319584195851958619587195881958919590195911959219593195941959519596195971959819599196001960119602196031960419605196061960719608196091961019611196121961319614196151961619617196181961919620196211962219623196241962519626196271962819629196301963119632196331963419635196361963719638196391964019641196421964319644196451964619647196481964919650196511965219653196541965519656196571965819659196601966119662196631966419665196661966719668196691967019671196721967319674196751967619677196781967919680196811968219683196841968519686196871968819689196901969119692196931969419695196961969719698196991970019701197021970319704197051970619707197081970919710197111971219713197141971519716197171971819719197201972119722197231972419725197261972719728197291973019731197321973319734197351973619737197381973919740197411974219743197441974519746197471974819749197501975119752197531975419755197561975719758197591976019761197621976319764197651976619767197681976919770197711977219773197741977519776197771977819779197801978119782197831978419785197861978719788197891979019791197921979319794197951979619797197981979919800198011980219803198041980519806198071980819809198101981119812198131981419815198161981719818198191982019821198221982319824198251982619827198281982919830198311983219833198341983519836198371983819839198401984119842198431984419845198461984719848198491985019851198521985319854198551985619857198581985919860198611986219863198641986519866198671986819869198701987119872198731987419875198761987719878198791988019881198821988319884198851988619887198881988919890198911989219893198941989519896198971989819899199001990119902199031990419905199061990719908199091991019911199121991319914199151991619917199181991919920199211992219923199241992519926199271992819929199301993119932199331993419935199361993719938199391994019941199421994319944199451994619947199481994919950199511995219953199541995519956199571995819959199601996119962199631996419965199661996719968199691997019971199721997319974199751997619977199781997919980199811998219983199841998519986199871998819989199901999119992199931999419995199961999719998199992000020001200022000320004200052000620007200082000920010200112001220013200142001520016200172001820019200202002120022200232002420025200262002720028200292003020031200322003320034200352003620037200382003920040200412004220043200442004520046200472004820049200502005120052200532005420055200562005720058200592006020061200622006320064200652006620067200682006920070200712007220073200742007520076200772007820079200802008120082200832008420085200862008720088200892009020091200922009320094200952009620097200982009920100201012010220103201042010520106201072010820109201102011120112201132011420115201162011720118201192012020121201222012320124201252012620127201282012920130201312013220133201342013520136201372013820139201402014120142201432014420145201462014720148201492015020151201522015320154201552015620157201582015920160201612016220163201642016520166201672016820169201702017120172201732017420175201762017720178201792018020181201822018320184201852018620187201882018920190201912019220193201942019520196201972019820199202002020120202202032020420205202062020720208202092021020211202122021320214202152021620217202182021920220202212022220223202242022520226202272022820229202302023120232202332023420235202362023720238202392024020241202422024320244202452024620247202482024920250202512025220253202542025520256202572025820259202602026120262202632026420265202662026720268202692027020271202722027320274202752027620277202782027920280202812028220283202842028520286202872028820289202902029120292202932029420295202962029720298202992030020301203022030320304203052030620307203082030920310203112031220313203142031520316203172031820319203202032120322203232032420325203262032720328203292033020331203322033320334203352033620337203382033920340203412034220343203442034520346203472034820349203502035120352203532035420355203562035720358203592036020361203622036320364203652036620367203682036920370203712037220373203742037520376203772037820379203802038120382203832038420385203862038720388203892039020391203922039320394203952039620397203982039920400204012040220403204042040520406204072040820409204102041120412204132041420415204162041720418204192042020421204222042320424204252042620427204282042920430204312043220433204342043520436204372043820439204402044120442204432044420445204462044720448204492045020451204522045320454204552045620457204582045920460204612046220463204642046520466204672046820469204702047120472204732047420475204762047720478204792048020481204822048320484204852048620487204882048920490204912049220493204942049520496204972049820499205002050120502205032050420505205062050720508205092051020511205122051320514205152051620517205182051920520205212052220523205242052520526205272052820529205302053120532205332053420535205362053720538205392054020541205422054320544205452054620547205482054920550205512055220553205542055520556205572055820559205602056120562205632056420565205662056720568205692057020571205722057320574205752057620577205782057920580205812058220583205842058520586205872058820589205902059120592205932059420595205962059720598205992060020601206022060320604206052060620607206082060920610206112061220613206142061520616206172061820619206202062120622206232062420625206262062720628206292063020631206322063320634206352063620637206382063920640206412064220643206442064520646206472064820649206502065120652206532065420655206562065720658206592066020661206622066320664206652066620667206682066920670206712067220673206742067520676206772067820679206802068120682206832068420685206862068720688206892069020691206922069320694206952069620697206982069920700207012070220703207042070520706207072070820709207102071120712207132071420715207162071720718207192072020721207222072320724207252072620727207282072920730207312073220733207342073520736207372073820739207402074120742207432074420745207462074720748207492075020751207522075320754207552075620757207582075920760207612076220763207642076520766207672076820769207702077120772207732077420775207762077720778207792078020781207822078320784207852078620787207882078920790207912079220793207942079520796207972079820799208002080120802208032080420805208062080720808208092081020811208122081320814208152081620817208182081920820208212082220823208242082520826208272082820829208302083120832208332083420835208362083720838208392084020841208422084320844208452084620847208482084920850208512085220853208542085520856208572085820859208602086120862208632086420865208662086720868208692087020871208722087320874208752087620877208782087920880208812088220883208842088520886208872088820889208902089120892208932089420895208962089720898208992090020901209022090320904209052090620907209082090920910209112091220913209142091520916209172091820919209202092120922209232092420925209262092720928209292093020931209322093320934209352093620937209382093920940209412094220943209442094520946209472094820949209502095120952209532095420955209562095720958209592096020961209622096320964209652096620967209682096920970209712097220973209742097520976209772097820979209802098120982209832098420985209862098720988209892099020991209922099320994209952099620997209982099921000210012100221003210042100521006210072100821009210102101121012210132101421015210162101721018210192102021021210222102321024210252102621027210282102921030210312103221033210342103521036210372103821039210402104121042210432104421045210462104721048210492105021051210522105321054210552105621057210582105921060210612106221063210642106521066210672106821069210702107121072210732107421075210762107721078210792108021081210822108321084210852108621087210882108921090210912109221093210942109521096210972109821099211002110121102211032110421105211062110721108211092111021111211122111321114211152111621117211182111921120211212112221123211242112521126211272112821129211302113121132211332113421135211362113721138211392114021141211422114321144211452114621147211482114921150211512115221153211542115521156211572115821159211602116121162211632116421165211662116721168211692117021171211722117321174211752117621177211782117921180211812118221183211842118521186211872118821189211902119121192211932119421195211962119721198211992120021201212022120321204212052120621207212082120921210212112121221213212142121521216212172121821219212202122121222212232122421225212262122721228212292123021231212322123321234212352123621237212382123921240212412124221243212442124521246212472124821249212502125121252212532125421255212562125721258212592126021261212622126321264212652126621267212682126921270212712127221273212742127521276212772127821279212802128121282212832128421285212862128721288212892129021291212922129321294212952129621297212982129921300213012130221303213042130521306213072130821309213102131121312213132131421315213162131721318213192132021321213222132321324213252132621327213282132921330213312133221333213342133521336213372133821339213402134121342213432134421345213462134721348213492135021351213522135321354213552135621357213582135921360213612136221363213642136521366213672136821369213702137121372213732137421375213762137721378213792138021381213822138321384213852138621387213882138921390213912139221393213942139521396213972139821399214002140121402214032140421405214062140721408214092141021411214122141321414214152141621417214182141921420214212142221423214242142521426214272142821429214302143121432214332143421435214362143721438214392144021441214422144321444214452144621447214482144921450214512145221453214542145521456214572145821459214602146121462214632146421465214662146721468214692147021471214722147321474214752147621477214782147921480214812148221483214842148521486214872148821489214902149121492214932149421495214962149721498214992150021501215022150321504215052150621507215082150921510215112151221513215142151521516215172151821519215202152121522215232152421525215262152721528215292153021531215322153321534215352153621537215382153921540215412154221543215442154521546215472154821549215502155121552215532155421555215562155721558215592156021561215622156321564215652156621567215682156921570215712157221573215742157521576215772157821579215802158121582215832158421585215862158721588215892159021591215922159321594215952159621597215982159921600216012160221603216042160521606216072160821609216102161121612216132161421615216162161721618216192162021621216222162321624216252162621627216282162921630216312163221633216342163521636216372163821639216402164121642216432164421645216462164721648216492165021651216522165321654216552165621657216582165921660216612166221663216642166521666216672166821669216702167121672216732167421675216762167721678216792168021681216822168321684216852168621687216882168921690216912169221693216942169521696216972169821699217002170121702217032170421705217062170721708217092171021711217122171321714217152171621717217182171921720217212172221723217242172521726217272172821729217302173121732217332173421735217362173721738217392174021741217422174321744217452174621747217482174921750217512175221753217542175521756217572175821759217602176121762217632176421765217662176721768217692177021771217722177321774217752177621777217782177921780217812178221783217842178521786217872178821789217902179121792217932179421795217962179721798217992180021801218022180321804218052180621807218082180921810218112181221813218142181521816218172181821819218202182121822218232182421825218262182721828218292183021831218322183321834218352183621837218382183921840218412184221843218442184521846218472184821849218502185121852218532185421855218562185721858218592186021861218622186321864218652186621867218682186921870218712187221873218742187521876218772187821879218802188121882218832188421885218862188721888218892189021891218922189321894218952189621897218982189921900219012190221903219042190521906219072190821909219102191121912219132191421915219162191721918219192192021921219222192321924219252192621927219282192921930219312193221933219342193521936219372193821939219402194121942219432194421945219462194721948219492195021951219522195321954219552195621957219582195921960219612196221963219642196521966219672196821969219702197121972219732197421975219762197721978219792198021981219822198321984219852198621987219882198921990219912199221993219942199521996219972199821999220002200122002220032200422005220062200722008220092201022011220122201322014220152201622017220182201922020220212202222023220242202522026220272202822029220302203122032220332203422035220362203722038220392204022041220422204322044220452204622047220482204922050220512205222053220542205522056220572205822059220602206122062220632206422065220662206722068220692207022071220722207322074220752207622077220782207922080220812208222083220842208522086220872208822089220902209122092220932209422095220962209722098220992210022101221022210322104221052210622107221082210922110221112211222113221142211522116221172211822119221202212122122221232212422125221262212722128221292213022131221322213322134221352213622137221382213922140221412214222143221442214522146221472214822149221502215122152221532215422155221562215722158221592216022161221622216322164221652216622167221682216922170221712217222173221742217522176221772217822179221802218122182221832218422185221862218722188221892219022191221922219322194221952219622197221982219922200222012220222203222042220522206222072220822209222102221122212222132221422215222162221722218222192222022221222222222322224222252222622227222282222922230222312223222233222342223522236222372223822239222402224122242222432224422245222462224722248222492225022251222522225322254222552225622257222582225922260222612226222263222642226522266222672226822269222702227122272222732227422275222762227722278222792228022281222822228322284222852228622287222882228922290222912229222293222942229522296222972229822299223002230122302223032230422305223062230722308223092231022311223122231322314223152231622317223182231922320223212232222323223242232522326223272232822329223302233122332223332233422335223362233722338223392234022341223422234322344223452234622347223482234922350223512235222353223542235522356223572235822359223602236122362223632236422365223662236722368223692237022371223722237322374223752237622377223782237922380223812238222383223842238522386223872238822389223902239122392223932239422395223962239722398223992240022401224022240322404224052240622407224082240922410224112241222413224142241522416224172241822419224202242122422224232242422425224262242722428224292243022431224322243322434224352243622437224382243922440224412244222443224442244522446224472244822449224502245122452224532245422455224562245722458224592246022461224622246322464224652246622467224682246922470224712247222473224742247522476224772247822479224802248122482224832248422485224862248722488224892249022491224922249322494224952249622497224982249922500225012250222503225042250522506225072250822509225102251122512225132251422515225162251722518225192252022521225222252322524225252252622527225282252922530225312253222533225342253522536225372253822539225402254122542225432254422545225462254722548225492255022551225522255322554225552255622557225582255922560225612256222563225642256522566225672256822569225702257122572225732257422575225762257722578225792258022581225822258322584225852258622587225882258922590225912259222593225942259522596225972259822599226002260122602226032260422605226062260722608226092261022611226122261322614226152261622617226182261922620226212262222623226242262522626226272262822629226302263122632226332263422635226362263722638226392264022641226422264322644226452264622647226482264922650226512265222653226542265522656226572265822659226602266122662226632266422665226662266722668226692267022671226722267322674226752267622677226782267922680226812268222683226842268522686226872268822689226902269122692226932269422695226962269722698226992270022701227022270322704227052270622707227082270922710227112271222713227142271522716227172271822719227202272122722227232272422725227262272722728227292273022731227322273322734227352273622737227382273922740227412274222743227442274522746227472274822749227502275122752227532275422755227562275722758227592276022761227622276322764227652276622767227682276922770227712277222773227742277522776227772277822779227802278122782227832278422785227862278722788227892279022791227922279322794227952279622797227982279922800228012280222803228042280522806228072280822809228102281122812228132281422815228162281722818228192282022821228222282322824228252282622827228282282922830228312283222833228342283522836228372283822839228402284122842228432284422845228462284722848228492285022851228522285322854228552285622857228582285922860228612286222863228642286522866228672286822869228702287122872228732287422875228762287722878228792288022881228822288322884228852288622887228882288922890228912289222893228942289522896228972289822899229002290122902229032290422905229062290722908229092291022911229122291322914229152291622917229182291922920229212292222923229242292522926229272292822929229302293122932229332293422935229362293722938229392294022941229422294322944229452294622947229482294922950229512295222953229542295522956229572295822959229602296122962229632296422965229662296722968229692297022971229722297322974229752297622977229782297922980229812298222983229842298522986229872298822989229902299122992229932299422995229962299722998229992300023001230022300323004230052300623007230082300923010230112301223013230142301523016230172301823019230202302123022230232302423025230262302723028230292303023031230322303323034230352303623037230382303923040230412304223043230442304523046230472304823049230502305123052230532305423055230562305723058230592306023061230622306323064230652306623067230682306923070230712307223073230742307523076230772307823079230802308123082230832308423085230862308723088230892309023091230922309323094230952309623097230982309923100231012310223103231042310523106231072310823109231102311123112231132311423115231162311723118231192312023121231222312323124231252312623127231282312923130231312313223133231342313523136231372313823139231402314123142231432314423145231462314723148231492315023151231522315323154231552315623157231582315923160231612316223163231642316523166231672316823169231702317123172231732317423175231762317723178231792318023181231822318323184231852318623187231882318923190231912319223193231942319523196231972319823199232002320123202232032320423205232062320723208232092321023211232122321323214232152321623217232182321923220232212322223223232242322523226232272322823229232302323123232232332323423235232362323723238232392324023241232422324323244232452324623247232482324923250232512325223253232542325523256232572325823259232602326123262232632326423265232662326723268232692327023271232722327323274232752327623277232782327923280232812328223283232842328523286232872328823289232902329123292232932329423295232962329723298232992330023301233022330323304233052330623307233082330923310233112331223313233142331523316233172331823319233202332123322233232332423325233262332723328233292333023331233322333323334233352333623337233382333923340233412334223343233442334523346233472334823349233502335123352233532335423355233562335723358233592336023361233622336323364233652336623367233682336923370233712337223373233742337523376233772337823379233802338123382233832338423385233862338723388233892339023391233922339323394233952339623397233982339923400234012340223403234042340523406234072340823409234102341123412234132341423415234162341723418234192342023421234222342323424234252342623427234282342923430234312343223433234342343523436234372343823439234402344123442234432344423445234462344723448234492345023451234522345323454234552345623457234582345923460234612346223463234642346523466234672346823469234702347123472234732347423475234762347723478234792348023481234822348323484234852348623487234882348923490234912349223493234942349523496234972349823499235002350123502235032350423505235062350723508235092351023511235122351323514235152351623517235182351923520235212352223523235242352523526235272352823529235302353123532235332353423535235362353723538235392354023541235422354323544235452354623547235482354923550235512355223553235542355523556235572355823559235602356123562235632356423565235662356723568235692357023571235722357323574235752357623577235782357923580235812358223583235842358523586235872358823589235902359123592235932359423595235962359723598235992360023601236022360323604236052360623607236082360923610236112361223613236142361523616236172361823619236202362123622236232362423625236262362723628236292363023631236322363323634236352363623637236382363923640236412364223643236442364523646236472364823649236502365123652236532365423655236562365723658236592366023661236622366323664236652366623667236682366923670236712367223673236742367523676236772367823679236802368123682236832368423685236862368723688236892369023691236922369323694236952369623697236982369923700237012370223703237042370523706237072370823709237102371123712237132371423715237162371723718237192372023721237222372323724237252372623727237282372923730237312373223733237342373523736237372373823739237402374123742237432374423745237462374723748237492375023751237522375323754237552375623757237582375923760237612376223763237642376523766237672376823769237702377123772237732377423775237762377723778237792378023781237822378323784237852378623787237882378923790237912379223793237942379523796237972379823799238002380123802238032380423805238062380723808238092381023811238122381323814238152381623817238182381923820238212382223823238242382523826238272382823829238302383123832238332383423835238362383723838238392384023841238422384323844238452384623847238482384923850238512385223853238542385523856238572385823859238602386123862238632386423865238662386723868238692387023871238722387323874238752387623877238782387923880238812388223883238842388523886238872388823889238902389123892238932389423895238962389723898238992390023901239022390323904239052390623907239082390923910239112391223913239142391523916239172391823919239202392123922239232392423925239262392723928239292393023931239322393323934239352393623937239382393923940239412394223943239442394523946239472394823949239502395123952239532395423955239562395723958239592396023961239622396323964239652396623967239682396923970239712397223973239742397523976239772397823979239802398123982239832398423985239862398723988239892399023991239922399323994239952399623997239982399924000240012400224003240042400524006240072400824009240102401124012240132401424015240162401724018240192402024021240222402324024240252402624027240282402924030240312403224033240342403524036240372403824039240402404124042240432404424045240462404724048240492405024051240522405324054240552405624057240582405924060240612406224063240642406524066240672406824069240702407124072240732407424075240762407724078240792408024081240822408324084240852408624087240882408924090240912409224093240942409524096240972409824099241002410124102241032410424105241062410724108241092411024111241122411324114241152411624117241182411924120241212412224123241242412524126241272412824129241302413124132241332413424135241362413724138241392414024141241422414324144241452414624147241482414924150241512415224153241542415524156241572415824159241602416124162241632416424165241662416724168241692417024171241722417324174241752417624177241782417924180241812418224183241842418524186241872418824189241902419124192241932419424195241962419724198241992420024201242022420324204242052420624207242082420924210242112421224213242142421524216242172421824219242202422124222242232422424225242262422724228242292423024231242322423324234242352423624237242382423924240242412424224243242442424524246242472424824249242502425124252242532425424255242562425724258242592426024261242622426324264242652426624267242682426924270242712427224273242742427524276242772427824279242802428124282242832428424285242862428724288242892429024291242922429324294242952429624297242982429924300243012430224303243042430524306243072430824309243102431124312243132431424315243162431724318243192432024321243222432324324243252432624327243282432924330243312433224333243342433524336243372433824339243402434124342243432434424345243462434724348243492435024351243522435324354243552435624357243582435924360243612436224363243642436524366243672436824369243702437124372243732437424375243762437724378243792438024381243822438324384243852438624387243882438924390243912439224393243942439524396243972439824399244002440124402244032440424405244062440724408244092441024411244122441324414244152441624417244182441924420244212442224423244242442524426244272442824429244302443124432244332443424435244362443724438244392444024441244422444324444244452444624447244482444924450244512445224453244542445524456244572445824459244602446124462244632446424465244662446724468244692447024471244722447324474244752447624477244782447924480244812448224483244842448524486244872448824489244902449124492244932449424495244962449724498244992450024501245022450324504245052450624507245082450924510245112451224513245142451524516245172451824519245202452124522245232452424525245262452724528245292453024531245322453324534245352453624537245382453924540245412454224543245442454524546245472454824549245502455124552245532455424555245562455724558245592456024561245622456324564245652456624567245682456924570245712457224573245742457524576245772457824579245802458124582245832458424585245862458724588245892459024591245922459324594245952459624597245982459924600246012460224603246042460524606246072460824609246102461124612246132461424615246162461724618246192462024621246222462324624246252462624627246282462924630246312463224633246342463524636246372463824639246402464124642246432464424645246462464724648246492465024651246522465324654246552465624657246582465924660246612466224663246642466524666246672466824669246702467124672246732467424675246762467724678246792468024681246822468324684246852468624687246882468924690246912469224693246942469524696246972469824699247002470124702247032470424705247062470724708247092471024711247122471324714247152471624717247182471924720247212472224723247242472524726247272472824729247302473124732247332473424735247362473724738247392474024741247422474324744247452474624747247482474924750247512475224753247542475524756247572475824759247602476124762247632476424765247662476724768247692477024771247722477324774247752477624777247782477924780247812478224783247842478524786247872478824789247902479124792247932479424795247962479724798247992480024801248022480324804248052480624807248082480924810248112481224813248142481524816248172481824819248202482124822248232482424825248262482724828248292483024831248322483324834248352483624837248382483924840248412484224843248442484524846248472484824849248502485124852248532485424855248562485724858248592486024861248622486324864248652486624867248682486924870248712487224873248742487524876248772487824879248802488124882248832488424885248862488724888248892489024891248922489324894248952489624897248982489924900249012490224903249042490524906249072490824909249102491124912249132491424915249162491724918249192492024921249222492324924249252492624927249282492924930249312493224933249342493524936249372493824939249402494124942249432494424945249462494724948249492495024951249522495324954249552495624957249582495924960249612496224963249642496524966249672496824969249702497124972249732497424975249762497724978249792498024981249822498324984249852498624987249882498924990249912499224993249942499524996249972499824999250002500125002250032500425005250062500725008250092501025011250122501325014250152501625017250182501925020250212502225023250242502525026250272502825029250302503125032250332503425035250362503725038250392504025041250422504325044250452504625047250482504925050250512505225053250542505525056250572505825059250602506125062250632506425065250662506725068250692507025071250722507325074250752507625077250782507925080250812508225083250842508525086250872508825089250902509125092250932509425095250962509725098250992510025101251022510325104251052510625107251082510925110251112511225113251142511525116251172511825119251202512125122251232512425125251262512725128251292513025131251322513325134251352513625137251382513925140251412514225143251442514525146251472514825149251502515125152251532515425155251562515725158251592516025161251622516325164251652516625167251682516925170251712517225173251742517525176251772517825179251802518125182251832518425185251862518725188251892519025191251922519325194251952519625197251982519925200252012520225203252042520525206252072520825209252102521125212252132521425215252162521725218252192522025221252222522325224252252522625227252282522925230252312523225233252342523525236252372523825239252402524125242252432524425245252462524725248252492525025251252522525325254252552525625257252582525925260252612526225263252642526525266252672526825269252702527125272252732527425275252762527725278252792528025281252822528325284252852528625287252882528925290252912529225293252942529525296252972529825299253002530125302253032530425305253062530725308253092531025311253122531325314253152531625317253182531925320253212532225323253242532525326253272532825329253302533125332253332533425335253362533725338253392534025341253422534325344253452534625347253482534925350253512535225353253542535525356253572535825359253602536125362253632536425365253662536725368253692537025371253722537325374253752537625377253782537925380253812538225383253842538525386253872538825389253902539125392253932539425395253962539725398253992540025401254022540325404254052540625407254082540925410254112541225413254142541525416254172541825419254202542125422254232542425425254262542725428254292543025431254322543325434254352543625437254382543925440254412544225443254442544525446254472544825449254502545125452254532545425455254562545725458254592546025461254622546325464254652546625467254682546925470254712547225473254742547525476254772547825479254802548125482254832548425485254862548725488254892549025491254922549325494254952549625497254982549925500255012550225503255042550525506255072550825509255102551125512255132551425515255162551725518255192552025521255222552325524255252552625527255282552925530255312553225533255342553525536255372553825539255402554125542255432554425545255462554725548255492555025551255522555325554255552555625557255582555925560255612556225563255642556525566255672556825569255702557125572255732557425575255762557725578255792558025581255822558325584255852558625587255882558925590255912559225593255942559525596255972559825599256002560125602256032560425605256062560725608256092561025611256122561325614256152561625617256182561925620256212562225623256242562525626256272562825629256302563125632256332563425635256362563725638256392564025641256422564325644256452564625647256482564925650256512565225653256542565525656256572565825659256602566125662256632566425665256662566725668256692567025671256722567325674256752567625677256782567925680256812568225683256842568525686256872568825689256902569125692256932569425695256962569725698256992570025701257022570325704257052570625707257082570925710257112571225713257142571525716257172571825719257202572125722257232572425725257262572725728257292573025731257322573325734257352573625737257382573925740257412574225743257442574525746257472574825749257502575125752257532575425755257562575725758257592576025761257622576325764257652576625767257682576925770257712577225773257742577525776257772577825779257802578125782257832578425785257862578725788257892579025791257922579325794257952579625797257982579925800258012580225803258042580525806258072580825809258102581125812258132581425815258162581725818258192582025821258222582325824258252582625827258282582925830258312583225833258342583525836258372583825839258402584125842258432584425845258462584725848258492585025851258522585325854258552585625857258582585925860258612586225863258642586525866258672586825869258702587125872258732587425875258762587725878258792588025881258822588325884258852588625887258882588925890258912589225893258942589525896258972589825899259002590125902259032590425905259062590725908259092591025911259122591325914259152591625917259182591925920259212592225923259242592525926259272592825929259302593125932259332593425935259362593725938259392594025941259422594325944259452594625947259482594925950259512595225953259542595525956259572595825959259602596125962259632596425965259662596725968259692597025971259722597325974259752597625977259782597925980259812598225983259842598525986259872598825989259902599125992259932599425995259962599725998259992600026001260022600326004260052600626007260082600926010260112601226013260142601526016260172601826019260202602126022260232602426025260262602726028260292603026031260322603326034260352603626037260382603926040260412604226043260442604526046260472604826049260502605126052260532605426055260562605726058260592606026061260622606326064260652606626067260682606926070260712607226073260742607526076260772607826079260802608126082260832608426085260862608726088260892609026091260922609326094260952609626097260982609926100261012610226103261042610526106261072610826109261102611126112261132611426115261162611726118261192612026121261222612326124261252612626127261282612926130261312613226133261342613526136261372613826139261402614126142261432614426145261462614726148261492615026151261522615326154261552615626157261582615926160261612616226163261642616526166261672616826169261702617126172261732617426175261762617726178261792618026181261822618326184261852618626187261882618926190261912619226193261942619526196261972619826199262002620126202262032620426205262062620726208262092621026211262122621326214262152621626217262182621926220262212622226223262242622526226262272622826229262302623126232262332623426235262362623726238262392624026241262422624326244262452624626247262482624926250262512625226253262542625526256262572625826259262602626126262262632626426265262662626726268262692627026271262722627326274262752627626277262782627926280262812628226283262842628526286262872628826289262902629126292262932629426295262962629726298262992630026301263022630326304263052630626307263082630926310263112631226313263142631526316263172631826319263202632126322263232632426325263262632726328263292633026331263322633326334263352633626337263382633926340263412634226343263442634526346263472634826349263502635126352263532635426355263562635726358263592636026361263622636326364263652636626367263682636926370263712637226373263742637526376263772637826379263802638126382263832638426385263862638726388263892639026391263922639326394263952639626397263982639926400264012640226403264042640526406264072640826409264102641126412264132641426415264162641726418264192642026421264222642326424264252642626427264282642926430264312643226433264342643526436264372643826439264402644126442264432644426445264462644726448264492645026451264522645326454264552645626457264582645926460264612646226463264642646526466264672646826469264702647126472264732647426475264762647726478264792648026481264822648326484264852648626487264882648926490264912649226493264942649526496264972649826499265002650126502265032650426505265062650726508265092651026511265122651326514265152651626517265182651926520265212652226523265242652526526265272652826529265302653126532265332653426535265362653726538265392654026541265422654326544265452654626547265482654926550265512655226553265542655526556265572655826559265602656126562265632656426565265662656726568265692657026571265722657326574265752657626577265782657926580265812658226583265842658526586265872658826589265902659126592265932659426595265962659726598265992660026601266022660326604266052660626607266082660926610266112661226613266142661526616266172661826619266202662126622266232662426625266262662726628266292663026631266322663326634266352663626637266382663926640266412664226643266442664526646266472664826649266502665126652266532665426655266562665726658266592666026661266622666326664266652666626667266682666926670266712667226673266742667526676266772667826679266802668126682266832668426685266862668726688266892669026691266922669326694266952669626697266982669926700267012670226703267042670526706267072670826709267102671126712267132671426715267162671726718267192672026721267222672326724267252672626727267282672926730267312673226733267342673526736267372673826739267402674126742267432674426745267462674726748267492675026751267522675326754267552675626757267582675926760267612676226763267642676526766267672676826769267702677126772267732677426775267762677726778267792678026781267822678326784267852678626787267882678926790267912679226793267942679526796267972679826799268002680126802268032680426805268062680726808268092681026811268122681326814268152681626817268182681926820268212682226823268242682526826268272682826829268302683126832268332683426835268362683726838268392684026841268422684326844268452684626847268482684926850268512685226853268542685526856268572685826859268602686126862268632686426865268662686726868268692687026871268722687326874268752687626877268782687926880268812688226883268842688526886268872688826889268902689126892268932689426895268962689726898268992690026901269022690326904269052690626907269082690926910269112691226913269142691526916269172691826919269202692126922269232692426925269262692726928269292693026931269322693326934269352693626937269382693926940269412694226943269442694526946269472694826949269502695126952269532695426955269562695726958269592696026961269622696326964269652696626967269682696926970269712697226973269742697526976269772697826979269802698126982269832698426985269862698726988269892699026991269922699326994269952699626997269982699927000270012700227003270042700527006270072700827009270102701127012270132701427015270162701727018270192702027021270222702327024270252702627027270282702927030270312703227033270342703527036270372703827039270402704127042270432704427045270462704727048270492705027051270522705327054270552705627057270582705927060270612706227063270642706527066270672706827069270702707127072270732707427075270762707727078270792708027081270822708327084270852708627087270882708927090270912709227093270942709527096270972709827099271002710127102271032710427105271062710727108271092711027111271122711327114271152711627117271182711927120271212712227123271242712527126271272712827129271302713127132271332713427135271362713727138271392714027141271422714327144271452714627147271482714927150271512715227153271542715527156271572715827159271602716127162271632716427165271662716727168271692717027171271722717327174271752717627177271782717927180271812718227183271842718527186271872718827189271902719127192271932719427195271962719727198271992720027201272022720327204272052720627207272082720927210272112721227213272142721527216272172721827219272202722127222272232722427225272262722727228272292723027231272322723327234272352723627237272382723927240272412724227243272442724527246272472724827249272502725127252272532725427255272562725727258272592726027261272622726327264272652726627267272682726927270272712727227273272742727527276272772727827279272802728127282272832728427285272862728727288272892729027291272922729327294272952729627297272982729927300273012730227303273042730527306273072730827309273102731127312273132731427315273162731727318273192732027321273222732327324273252732627327273282732927330273312733227333273342733527336273372733827339273402734127342273432734427345273462734727348273492735027351273522735327354273552735627357273582735927360273612736227363273642736527366273672736827369273702737127372273732737427375273762737727378273792738027381273822738327384273852738627387273882738927390273912739227393273942739527396273972739827399274002740127402274032740427405274062740727408274092741027411274122741327414274152741627417274182741927420274212742227423274242742527426274272742827429274302743127432274332743427435274362743727438274392744027441274422744327444274452744627447274482744927450274512745227453274542745527456274572745827459274602746127462274632746427465274662746727468274692747027471274722747327474274752747627477274782747927480274812748227483274842748527486274872748827489274902749127492274932749427495274962749727498274992750027501275022750327504275052750627507275082750927510275112751227513275142751527516275172751827519275202752127522275232752427525275262752727528275292753027531275322753327534275352753627537275382753927540275412754227543275442754527546275472754827549275502755127552275532755427555275562755727558275592756027561275622756327564275652756627567275682756927570275712757227573275742757527576275772757827579275802758127582275832758427585275862758727588275892759027591275922759327594275952759627597275982759927600276012760227603276042760527606276072760827609276102761127612276132761427615276162761727618276192762027621276222762327624276252762627627276282762927630276312763227633276342763527636276372763827639276402764127642276432764427645276462764727648276492765027651276522765327654276552765627657276582765927660276612766227663276642766527666276672766827669276702767127672276732767427675276762767727678276792768027681276822768327684276852768627687276882768927690276912769227693276942769527696276972769827699277002770127702277032770427705277062770727708277092771027711277122771327714277152771627717277182771927720277212772227723277242772527726277272772827729277302773127732277332773427735277362773727738277392774027741277422774327744277452774627747277482774927750277512775227753277542775527756277572775827759277602776127762277632776427765277662776727768277692777027771277722777327774277752777627777277782777927780277812778227783277842778527786277872778827789277902779127792277932779427795277962779727798277992780027801278022780327804278052780627807278082780927810278112781227813278142781527816278172781827819278202782127822278232782427825278262782727828278292783027831278322783327834278352783627837278382783927840278412784227843278442784527846278472784827849278502785127852278532785427855278562785727858278592786027861278622786327864278652786627867278682786927870278712787227873278742787527876278772787827879278802788127882278832788427885278862788727888278892789027891278922789327894278952789627897278982789927900279012790227903279042790527906279072790827909279102791127912279132791427915279162791727918279192792027921279222792327924279252792627927279282792927930279312793227933279342793527936279372793827939279402794127942279432794427945279462794727948279492795027951279522795327954279552795627957279582795927960279612796227963279642796527966279672796827969279702797127972279732797427975279762797727978279792798027981279822798327984279852798627987279882798927990279912799227993279942799527996279972799827999280002800128002280032800428005280062800728008280092801028011280122801328014280152801628017280182801928020280212802228023280242802528026280272802828029280302803128032280332803428035280362803728038280392804028041280422804328044280452804628047280482804928050280512805228053280542805528056280572805828059280602806128062280632806428065280662806728068280692807028071280722807328074280752807628077280782807928080280812808228083280842808528086280872808828089280902809128092280932809428095280962809728098280992810028101281022810328104281052810628107281082810928110281112811228113281142811528116281172811828119281202812128122281232812428125281262812728128281292813028131281322813328134281352813628137281382813928140281412814228143281442814528146281472814828149281502815128152281532815428155281562815728158281592816028161281622816328164281652816628167281682816928170281712817228173281742817528176281772817828179281802818128182281832818428185281862818728188281892819028191281922819328194281952819628197281982819928200282012820228203282042820528206282072820828209282102821128212282132821428215282162821728218282192822028221282222822328224282252822628227282282822928230282312823228233282342823528236282372823828239282402824128242282432824428245282462824728248282492825028251282522825328254282552825628257282582825928260282612826228263282642826528266282672826828269282702827128272282732827428275282762827728278282792828028281282822828328284282852828628287282882828928290282912829228293282942829528296282972829828299283002830128302283032830428305283062830728308283092831028311283122831328314283152831628317283182831928320283212832228323283242832528326283272832828329283302833128332283332833428335283362833728338283392834028341283422834328344283452834628347283482834928350283512835228353283542835528356283572835828359283602836128362283632836428365283662836728368283692837028371283722837328374283752837628377283782837928380283812838228383283842838528386283872838828389283902839128392283932839428395283962839728398283992840028401284022840328404284052840628407284082840928410284112841228413284142841528416284172841828419284202842128422284232842428425284262842728428284292843028431284322843328434284352843628437284382843928440284412844228443284442844528446284472844828449284502845128452284532845428455284562845728458284592846028461284622846328464284652846628467284682846928470284712847228473284742847528476284772847828479284802848128482284832848428485284862848728488284892849028491284922849328494284952849628497284982849928500285012850228503285042850528506285072850828509285102851128512285132851428515285162851728518285192852028521285222852328524285252852628527285282852928530285312853228533285342853528536285372853828539285402854128542285432854428545285462854728548285492855028551285522855328554285552855628557285582855928560285612856228563285642856528566285672856828569285702857128572285732857428575285762857728578285792858028581285822858328584285852858628587285882858928590285912859228593285942859528596285972859828599286002860128602286032860428605286062860728608286092861028611286122861328614286152861628617286182861928620286212862228623286242862528626286272862828629286302863128632286332863428635286362863728638286392864028641286422864328644286452864628647286482864928650286512865228653286542865528656286572865828659286602866128662286632866428665286662866728668286692867028671286722867328674286752867628677286782867928680286812868228683286842868528686286872868828689286902869128692286932869428695286962869728698286992870028701287022870328704287052870628707287082870928710287112871228713287142871528716287172871828719287202872128722287232872428725287262872728728287292873028731287322873328734287352873628737287382873928740287412874228743287442874528746287472874828749287502875128752287532875428755287562875728758287592876028761287622876328764287652876628767287682876928770287712877228773287742877528776287772877828779287802878128782287832878428785287862878728788287892879028791287922879328794287952879628797287982879928800288012880228803288042880528806288072880828809288102881128812288132881428815288162881728818288192882028821288222882328824288252882628827288282882928830288312883228833288342883528836288372883828839288402884128842288432884428845288462884728848288492885028851288522885328854288552885628857288582885928860288612886228863288642886528866288672886828869288702887128872288732887428875288762887728878288792888028881288822888328884288852888628887288882888928890288912889228893288942889528896288972889828899289002890128902289032890428905289062890728908289092891028911289122891328914289152891628917289182891928920289212892228923289242892528926289272892828929289302893128932289332893428935289362893728938289392894028941289422894328944289452894628947289482894928950289512895228953289542895528956289572895828959289602896128962289632896428965289662896728968289692897028971289722897328974289752897628977289782897928980289812898228983289842898528986289872898828989289902899128992289932899428995289962899728998289992900029001290022900329004290052900629007290082900929010290112901229013290142901529016290172901829019290202902129022290232902429025290262902729028290292903029031290322903329034290352903629037290382903929040290412904229043290442904529046290472904829049290502905129052290532905429055290562905729058290592906029061290622906329064290652906629067290682906929070290712907229073290742907529076290772907829079290802908129082290832908429085290862908729088290892909029091290922909329094290952909629097290982909929100291012910229103291042910529106291072910829109291102911129112291132911429115291162911729118291192912029121291222912329124291252912629127291282912929130291312913229133291342913529136291372913829139291402914129142291432914429145291462914729148291492915029151291522915329154291552915629157291582915929160291612916229163291642916529166291672916829169291702917129172291732917429175291762917729178291792918029181291822918329184291852918629187291882918929190291912919229193291942919529196291972919829199292002920129202292032920429205292062920729208292092921029211292122921329214292152921629217292182921929220292212922229223292242922529226292272922829229292302923129232292332923429235292362923729238292392924029241292422924329244292452924629247292482924929250292512925229253292542925529256292572925829259292602926129262292632926429265292662926729268292692927029271292722927329274292752927629277292782927929280292812928229283292842928529286292872928829289292902929129292292932929429295292962929729298292992930029301293022930329304293052930629307293082930929310293112931229313293142931529316293172931829319293202932129322293232932429325293262932729328293292933029331293322933329334293352933629337293382933929340293412934229343293442934529346293472934829349293502935129352293532935429355293562935729358293592936029361293622936329364293652936629367293682936929370293712937229373293742937529376293772937829379293802938129382293832938429385293862938729388293892939029391293922939329394293952939629397293982939929400294012940229403294042940529406294072940829409294102941129412294132941429415294162941729418294192942029421294222942329424294252942629427294282942929430294312943229433294342943529436294372943829439294402944129442294432944429445294462944729448294492945029451294522945329454294552945629457294582945929460294612946229463294642946529466294672946829469294702947129472294732947429475294762947729478294792948029481294822948329484294852948629487294882948929490294912949229493294942949529496294972949829499295002950129502295032950429505295062950729508295092951029511295122951329514295152951629517295182951929520295212952229523295242952529526295272952829529295302953129532295332953429535295362953729538295392954029541295422954329544295452954629547295482954929550295512955229553295542955529556295572955829559295602956129562295632956429565295662956729568295692957029571295722957329574295752957629577295782957929580295812958229583295842958529586295872958829589295902959129592295932959429595295962959729598295992960029601296022960329604296052960629607296082960929610296112961229613296142961529616296172961829619296202962129622296232962429625296262962729628296292963029631296322963329634296352963629637296382963929640296412964229643296442964529646296472964829649296502965129652296532965429655296562965729658296592966029661296622966329664296652966629667296682966929670296712967229673296742967529676296772967829679296802968129682296832968429685296862968729688296892969029691296922969329694296952969629697296982969929700297012970229703297042970529706297072970829709297102971129712297132971429715297162971729718297192972029721297222972329724297252972629727297282972929730297312973229733297342973529736297372973829739297402974129742297432974429745297462974729748297492975029751297522975329754297552975629757297582975929760297612976229763297642976529766297672976829769297702977129772297732977429775297762977729778297792978029781297822978329784297852978629787297882978929790297912979229793297942979529796297972979829799298002980129802298032980429805298062980729808298092981029811298122981329814298152981629817298182981929820298212982229823298242982529826298272982829829298302983129832298332983429835298362983729838298392984029841298422984329844298452984629847298482984929850298512985229853298542985529856298572985829859298602986129862298632986429865298662986729868298692987029871298722987329874298752987629877298782987929880298812988229883298842988529886298872988829889298902989129892298932989429895298962989729898298992990029901299022990329904299052990629907299082990929910299112991229913299142991529916299172991829919299202992129922299232992429925299262992729928299292993029931299322993329934299352993629937299382993929940299412994229943299442994529946299472994829949299502995129952299532995429955299562995729958299592996029961299622996329964299652996629967299682996929970299712997229973299742997529976299772997829979299802998129982299832998429985299862998729988299892999029991299922999329994299952999629997299982999930000300013000230003300043000530006300073000830009300103001130012300133001430015300163001730018300193002030021300223002330024300253002630027300283002930030300313003230033300343003530036300373003830039300403004130042300433004430045300463004730048300493005030051300523005330054300553005630057300583005930060300613006230063300643006530066300673006830069300703007130072300733007430075300763007730078300793008030081300823008330084300853008630087300883008930090300913009230093300943009530096300973009830099301003010130102301033010430105301063010730108301093011030111301123011330114301153011630117301183011930120301213012230123301243012530126301273012830129301303013130132301333013430135301363013730138301393014030141301423014330144301453014630147301483014930150301513015230153301543015530156301573015830159301603016130162301633016430165301663016730168301693017030171301723017330174301753017630177301783017930180301813018230183301843018530186301873018830189301903019130192301933019430195301963019730198301993020030201302023020330204302053020630207302083020930210302113021230213302143021530216302173021830219302203022130222302233022430225302263022730228302293023030231302323023330234302353023630237302383023930240302413024230243302443024530246302473024830249302503025130252302533025430255302563025730258302593026030261302623026330264302653026630267302683026930270302713027230273302743027530276302773027830279302803028130282302833028430285302863028730288302893029030291302923029330294302953029630297302983029930300303013030230303303043030530306303073030830309303103031130312303133031430315303163031730318303193032030321303223032330324303253032630327303283032930330303313033230333303343033530336303373033830339303403034130342303433034430345303463034730348303493035030351303523035330354303553035630357303583035930360303613036230363303643036530366303673036830369303703037130372303733037430375303763037730378303793038030381303823038330384303853038630387303883038930390303913039230393303943039530396303973039830399304003040130402304033040430405304063040730408304093041030411304123041330414304153041630417304183041930420304213042230423304243042530426304273042830429304303043130432304333043430435304363043730438304393044030441304423044330444304453044630447304483044930450304513045230453304543045530456304573045830459304603046130462304633046430465304663046730468304693047030471304723047330474304753047630477304783047930480304813048230483304843048530486304873048830489304903049130492304933049430495304963049730498304993050030501305023050330504305053050630507305083050930510305113051230513305143051530516305173051830519305203052130522305233052430525305263052730528305293053030531305323053330534305353053630537305383053930540305413054230543305443054530546305473054830549305503055130552305533055430555305563055730558305593056030561305623056330564305653056630567305683056930570305713057230573305743057530576305773057830579305803058130582305833058430585305863058730588305893059030591305923059330594305953059630597305983059930600306013060230603306043060530606306073060830609306103061130612306133061430615306163061730618306193062030621306223062330624306253062630627306283062930630306313063230633306343063530636306373063830639306403064130642306433064430645306463064730648306493065030651306523065330654306553065630657306583065930660306613066230663306643066530666306673066830669306703067130672306733067430675306763067730678306793068030681306823068330684306853068630687306883068930690306913069230693306943069530696306973069830699307003070130702307033070430705307063070730708307093071030711307123071330714307153071630717307183071930720307213072230723307243072530726307273072830729307303073130732307333073430735307363073730738307393074030741307423074330744307453074630747307483074930750307513075230753307543075530756307573075830759307603076130762307633076430765307663076730768307693077030771307723077330774307753077630777307783077930780307813078230783307843078530786307873078830789307903079130792307933079430795307963079730798307993080030801308023080330804308053080630807308083080930810308113081230813308143081530816308173081830819308203082130822308233082430825308263082730828308293083030831308323083330834308353083630837308383083930840308413084230843308443084530846308473084830849308503085130852308533085430855308563085730858308593086030861308623086330864308653086630867308683086930870308713087230873308743087530876308773087830879308803088130882308833088430885308863088730888308893089030891308923089330894308953089630897308983089930900309013090230903309043090530906309073090830909309103091130912309133091430915309163091730918309193092030921309223092330924309253092630927309283092930930309313093230933309343093530936309373093830939309403094130942309433094430945309463094730948309493095030951309523095330954309553095630957309583095930960309613096230963309643096530966309673096830969309703097130972309733097430975309763097730978309793098030981309823098330984309853098630987 |
- diff -Nur linux-4.4.28.orig/arch/arm/include/asm/switch_to.h linux-4.4.28/arch/arm/include/asm/switch_to.h
- --- linux-4.4.28.orig/arch/arm/include/asm/switch_to.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/arm/include/asm/switch_to.h 2016-11-01 21:26:56.728210258 +0100
- @@ -3,6 +3,13 @@
-
- #include <linux/thread_info.h>
-
- +#if defined CONFIG_PREEMPT_RT_FULL && defined CONFIG_HIGHMEM
- +void switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p);
- +#else
- +static inline void
- +switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p) { }
- +#endif
- +
- /*
- * For v7 SMP cores running a preemptible kernel we may be pre-empted
- * during a TLB maintenance operation, so execute an inner-shareable dsb
- @@ -25,6 +32,7 @@
- #define switch_to(prev,next,last) \
- do { \
- __complete_pending_tlbi(); \
- + switch_kmaps(prev, next); \
- last = __switch_to(prev,task_thread_info(prev), task_thread_info(next)); \
- } while (0)
-
- diff -Nur linux-4.4.28.orig/arch/arm/include/asm/thread_info.h linux-4.4.28/arch/arm/include/asm/thread_info.h
- --- linux-4.4.28.orig/arch/arm/include/asm/thread_info.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/arm/include/asm/thread_info.h 2016-11-01 21:26:56.748211548 +0100
- @@ -49,6 +49,7 @@
- struct thread_info {
- unsigned long flags; /* low level flags */
- int preempt_count; /* 0 => preemptable, <0 => bug */
- + int preempt_lazy_count; /* 0 => preemptable, <0 => bug */
- mm_segment_t addr_limit; /* address limit */
- struct task_struct *task; /* main task structure */
- __u32 cpu; /* cpu */
- @@ -142,7 +143,8 @@
- #define TIF_SYSCALL_TRACE 4 /* syscall trace active */
- #define TIF_SYSCALL_AUDIT 5 /* syscall auditing active */
- #define TIF_SYSCALL_TRACEPOINT 6 /* syscall tracepoint instrumentation */
- -#define TIF_SECCOMP 7 /* seccomp syscall filtering active */
- +#define TIF_SECCOMP 8 /* seccomp syscall filtering active */
- +#define TIF_NEED_RESCHED_LAZY 7
-
- #define TIF_NOHZ 12 /* in adaptive nohz mode */
- #define TIF_USING_IWMMXT 17
- @@ -152,6 +154,7 @@
- #define _TIF_SIGPENDING (1 << TIF_SIGPENDING)
- #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED)
- #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME)
- +#define _TIF_NEED_RESCHED_LAZY (1 << TIF_NEED_RESCHED_LAZY)
- #define _TIF_UPROBE (1 << TIF_UPROBE)
- #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE)
- #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT)
- @@ -167,7 +170,8 @@
- * Change these and you break ASM code in entry-common.S
- */
- #define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \
- - _TIF_NOTIFY_RESUME | _TIF_UPROBE)
- + _TIF_NOTIFY_RESUME | _TIF_UPROBE | \
- + _TIF_NEED_RESCHED_LAZY)
-
- #endif /* __KERNEL__ */
- #endif /* __ASM_ARM_THREAD_INFO_H */
- diff -Nur linux-4.4.28.orig/arch/arm/Kconfig linux-4.4.28/arch/arm/Kconfig
- --- linux-4.4.28.orig/arch/arm/Kconfig 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/arm/Kconfig 2016-11-01 21:26:56.696208202 +0100
- @@ -33,7 +33,7 @@
- select HARDIRQS_SW_RESEND
- select HAVE_ARCH_AUDITSYSCALL if (AEABI && !OABI_COMPAT)
- select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6
- - select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32
- + select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && !PREEMPT_RT_BASE
- select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32
- select HAVE_ARCH_SECCOMP_FILTER if (AEABI && !OABI_COMPAT)
- select HAVE_ARCH_TRACEHOOK
- @@ -68,6 +68,7 @@
- select HAVE_PERF_EVENTS
- select HAVE_PERF_REGS
- select HAVE_PERF_USER_STACK_DUMP
- + select HAVE_PREEMPT_LAZY
- select HAVE_RCU_TABLE_FREE if (SMP && ARM_LPAE)
- select HAVE_REGS_AND_STACK_ACCESS_API
- select HAVE_SYSCALL_TRACEPOINTS
- diff -Nur linux-4.4.28.orig/arch/arm/kernel/asm-offsets.c linux-4.4.28/arch/arm/kernel/asm-offsets.c
- --- linux-4.4.28.orig/arch/arm/kernel/asm-offsets.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/arm/kernel/asm-offsets.c 2016-11-01 21:26:56.760212322 +0100
- @@ -65,6 +65,7 @@
- BLANK();
- DEFINE(TI_FLAGS, offsetof(struct thread_info, flags));
- DEFINE(TI_PREEMPT, offsetof(struct thread_info, preempt_count));
- + DEFINE(TI_PREEMPT_LAZY, offsetof(struct thread_info, preempt_lazy_count));
- DEFINE(TI_ADDR_LIMIT, offsetof(struct thread_info, addr_limit));
- DEFINE(TI_TASK, offsetof(struct thread_info, task));
- DEFINE(TI_CPU, offsetof(struct thread_info, cpu));
- diff -Nur linux-4.4.28.orig/arch/arm/kernel/entry-armv.S linux-4.4.28/arch/arm/kernel/entry-armv.S
- --- linux-4.4.28.orig/arch/arm/kernel/entry-armv.S 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/arm/kernel/entry-armv.S 2016-11-01 21:26:56.764212578 +0100
- @@ -215,11 +215,18 @@
- #ifdef CONFIG_PREEMPT
- get_thread_info tsk
- ldr r8, [tsk, #TI_PREEMPT] @ get preempt count
- - ldr r0, [tsk, #TI_FLAGS] @ get flags
- teq r8, #0 @ if preempt count != 0
- + bne 1f @ return from exeption
- + ldr r0, [tsk, #TI_FLAGS] @ get flags
- + tst r0, #_TIF_NEED_RESCHED @ if NEED_RESCHED is set
- + blne svc_preempt @ preempt!
- +
- + ldr r8, [tsk, #TI_PREEMPT_LAZY] @ get preempt lazy count
- + teq r8, #0 @ if preempt lazy count != 0
- movne r0, #0 @ force flags to 0
- - tst r0, #_TIF_NEED_RESCHED
- + tst r0, #_TIF_NEED_RESCHED_LAZY
- blne svc_preempt
- +1:
- #endif
-
- svc_exit r5, irq = 1 @ return from exception
- @@ -234,8 +241,14 @@
- 1: bl preempt_schedule_irq @ irq en/disable is done inside
- ldr r0, [tsk, #TI_FLAGS] @ get new tasks TI_FLAGS
- tst r0, #_TIF_NEED_RESCHED
- + bne 1b
- + tst r0, #_TIF_NEED_RESCHED_LAZY
- reteq r8 @ go again
- - b 1b
- + ldr r0, [tsk, #TI_PREEMPT_LAZY] @ get preempt lazy count
- + teq r0, #0 @ if preempt lazy count != 0
- + beq 1b
- + ret r8 @ go again
- +
- #endif
-
- __und_fault:
- diff -Nur linux-4.4.28.orig/arch/arm/kernel/entry-common.S linux-4.4.28/arch/arm/kernel/entry-common.S
- --- linux-4.4.28.orig/arch/arm/kernel/entry-common.S 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/arm/kernel/entry-common.S 2016-11-01 21:26:56.764212578 +0100
- @@ -36,7 +36,9 @@
- UNWIND(.cantunwind )
- disable_irq_notrace @ disable interrupts
- ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing
- - tst r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK
- + tst r1, #((_TIF_SYSCALL_WORK | _TIF_WORK_MASK) & ~_TIF_SECCOMP)
- + bne fast_work_pending
- + tst r1, #_TIF_SECCOMP
- bne fast_work_pending
-
- /* perform architecture specific actions before user return */
- @@ -62,8 +64,11 @@
- str r0, [sp, #S_R0 + S_OFF]! @ save returned r0
- disable_irq_notrace @ disable interrupts
- ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing
- - tst r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK
- + tst r1, #((_TIF_SYSCALL_WORK | _TIF_WORK_MASK) & ~_TIF_SECCOMP)
- + bne do_slower_path
- + tst r1, #_TIF_SECCOMP
- beq no_work_pending
- +do_slower_path:
- UNWIND(.fnend )
- ENDPROC(ret_fast_syscall)
-
- diff -Nur linux-4.4.28.orig/arch/arm/kernel/process.c linux-4.4.28/arch/arm/kernel/process.c
- --- linux-4.4.28.orig/arch/arm/kernel/process.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/arm/kernel/process.c 2016-11-01 21:26:56.772213095 +0100
- @@ -319,6 +319,30 @@
- }
-
- #ifdef CONFIG_MMU
- +/*
- + * CONFIG_SPLIT_PTLOCK_CPUS results in a page->ptl lock. If the lock is not
- + * initialized by pgtable_page_ctor() then a coredump of the vector page will
- + * fail.
- + */
- +static int __init vectors_user_mapping_init_page(void)
- +{
- + struct page *page;
- + unsigned long addr = 0xffff0000;
- + pgd_t *pgd;
- + pud_t *pud;
- + pmd_t *pmd;
- +
- + pgd = pgd_offset_k(addr);
- + pud = pud_offset(pgd, addr);
- + pmd = pmd_offset(pud, addr);
- + page = pmd_page(*(pmd));
- +
- + pgtable_page_ctor(page);
- +
- + return 0;
- +}
- +late_initcall(vectors_user_mapping_init_page);
- +
- #ifdef CONFIG_KUSER_HELPERS
- /*
- * The vectors page is always readable from user space for the
- diff -Nur linux-4.4.28.orig/arch/arm/kernel/signal.c linux-4.4.28/arch/arm/kernel/signal.c
- --- linux-4.4.28.orig/arch/arm/kernel/signal.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/arm/kernel/signal.c 2016-11-01 21:26:56.772213095 +0100
- @@ -572,7 +572,8 @@
- */
- trace_hardirqs_off();
- do {
- - if (likely(thread_flags & _TIF_NEED_RESCHED)) {
- + if (likely(thread_flags & (_TIF_NEED_RESCHED |
- + _TIF_NEED_RESCHED_LAZY))) {
- schedule();
- } else {
- if (unlikely(!user_mode(regs)))
- diff -Nur linux-4.4.28.orig/arch/arm/kernel/smp.c linux-4.4.28/arch/arm/kernel/smp.c
- --- linux-4.4.28.orig/arch/arm/kernel/smp.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/arm/kernel/smp.c 2016-11-01 21:26:56.772213095 +0100
- @@ -230,8 +230,6 @@
- flush_cache_louis();
- local_flush_tlb_all();
-
- - clear_tasks_mm_cpumask(cpu);
- -
- return 0;
- }
-
- @@ -247,6 +245,9 @@
- pr_err("CPU%u: cpu didn't die\n", cpu);
- return;
- }
- +
- + clear_tasks_mm_cpumask(cpu);
- +
- pr_notice("CPU%u: shutdown\n", cpu);
-
- /*
- diff -Nur linux-4.4.28.orig/arch/arm/kernel/unwind.c linux-4.4.28/arch/arm/kernel/unwind.c
- --- linux-4.4.28.orig/arch/arm/kernel/unwind.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/arm/kernel/unwind.c 2016-11-01 21:26:56.776213352 +0100
- @@ -93,7 +93,7 @@
- static const struct unwind_idx *__origin_unwind_idx;
- extern const struct unwind_idx __stop_unwind_idx[];
-
- -static DEFINE_SPINLOCK(unwind_lock);
- +static DEFINE_RAW_SPINLOCK(unwind_lock);
- static LIST_HEAD(unwind_tables);
-
- /* Convert a prel31 symbol to an absolute address */
- @@ -201,7 +201,7 @@
- /* module unwind tables */
- struct unwind_table *table;
-
- - spin_lock_irqsave(&unwind_lock, flags);
- + raw_spin_lock_irqsave(&unwind_lock, flags);
- list_for_each_entry(table, &unwind_tables, list) {
- if (addr >= table->begin_addr &&
- addr < table->end_addr) {
- @@ -213,7 +213,7 @@
- break;
- }
- }
- - spin_unlock_irqrestore(&unwind_lock, flags);
- + raw_spin_unlock_irqrestore(&unwind_lock, flags);
- }
-
- pr_debug("%s: idx = %p\n", __func__, idx);
- @@ -529,9 +529,9 @@
- tab->begin_addr = text_addr;
- tab->end_addr = text_addr + text_size;
-
- - spin_lock_irqsave(&unwind_lock, flags);
- + raw_spin_lock_irqsave(&unwind_lock, flags);
- list_add_tail(&tab->list, &unwind_tables);
- - spin_unlock_irqrestore(&unwind_lock, flags);
- + raw_spin_unlock_irqrestore(&unwind_lock, flags);
-
- return tab;
- }
- @@ -543,9 +543,9 @@
- if (!tab)
- return;
-
- - spin_lock_irqsave(&unwind_lock, flags);
- + raw_spin_lock_irqsave(&unwind_lock, flags);
- list_del(&tab->list);
- - spin_unlock_irqrestore(&unwind_lock, flags);
- + raw_spin_unlock_irqrestore(&unwind_lock, flags);
-
- kfree(tab);
- }
- diff -Nur linux-4.4.28.orig/arch/arm/kvm/arm.c linux-4.4.28/arch/arm/kvm/arm.c
- --- linux-4.4.28.orig/arch/arm/kvm/arm.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/arm/kvm/arm.c 2016-11-01 21:26:56.776213352 +0100
- @@ -496,18 +496,18 @@
- struct kvm_vcpu *vcpu;
-
- kvm_for_each_vcpu(i, vcpu, kvm) {
- - wait_queue_head_t *wq = kvm_arch_vcpu_wq(vcpu);
- + struct swait_queue_head *wq = kvm_arch_vcpu_wq(vcpu);
-
- vcpu->arch.pause = false;
- - wake_up_interruptible(wq);
- + swake_up(wq);
- }
- }
-
- static void vcpu_sleep(struct kvm_vcpu *vcpu)
- {
- - wait_queue_head_t *wq = kvm_arch_vcpu_wq(vcpu);
- + struct swait_queue_head *wq = kvm_arch_vcpu_wq(vcpu);
-
- - wait_event_interruptible(*wq, ((!vcpu->arch.power_off) &&
- + swait_event_interruptible(*wq, ((!vcpu->arch.power_off) &&
- (!vcpu->arch.pause)));
- }
-
- @@ -566,7 +566,7 @@
- * involves poking the GIC, which must be done in a
- * non-preemptible context.
- */
- - preempt_disable();
- + migrate_disable();
- kvm_timer_flush_hwstate(vcpu);
- kvm_vgic_flush_hwstate(vcpu);
-
- @@ -585,7 +585,7 @@
- local_irq_enable();
- kvm_timer_sync_hwstate(vcpu);
- kvm_vgic_sync_hwstate(vcpu);
- - preempt_enable();
- + migrate_enable();
- continue;
- }
-
- @@ -639,7 +639,7 @@
-
- kvm_vgic_sync_hwstate(vcpu);
-
- - preempt_enable();
- + migrate_enable();
-
- ret = handle_exit(vcpu, run, ret);
- }
- diff -Nur linux-4.4.28.orig/arch/arm/kvm/psci.c linux-4.4.28/arch/arm/kvm/psci.c
- --- linux-4.4.28.orig/arch/arm/kvm/psci.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/arm/kvm/psci.c 2016-11-01 21:26:56.780213616 +0100
- @@ -70,7 +70,7 @@
- {
- struct kvm *kvm = source_vcpu->kvm;
- struct kvm_vcpu *vcpu = NULL;
- - wait_queue_head_t *wq;
- + struct swait_queue_head *wq;
- unsigned long cpu_id;
- unsigned long context_id;
- phys_addr_t target_pc;
- @@ -119,7 +119,7 @@
- smp_mb(); /* Make sure the above is visible */
-
- wq = kvm_arch_vcpu_wq(vcpu);
- - wake_up_interruptible(wq);
- + swake_up(wq);
-
- return PSCI_RET_SUCCESS;
- }
- diff -Nur linux-4.4.28.orig/arch/arm/mach-at91/at91rm9200.c linux-4.4.28/arch/arm/mach-at91/at91rm9200.c
- --- linux-4.4.28.orig/arch/arm/mach-at91/at91rm9200.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/arm/mach-at91/at91rm9200.c 2016-11-01 21:26:56.784213869 +0100
- @@ -12,7 +12,6 @@
- #include <linux/of_platform.h>
-
- #include <asm/mach/arch.h>
- -#include <asm/system_misc.h>
-
- #include "generic.h"
- #include "soc.h"
- @@ -33,7 +32,6 @@
-
- of_platform_populate(NULL, of_default_bus_match_table, NULL, soc_dev);
-
- - arm_pm_idle = at91rm9200_idle;
- at91rm9200_pm_init();
- }
-
- diff -Nur linux-4.4.28.orig/arch/arm/mach-at91/at91sam9.c linux-4.4.28/arch/arm/mach-at91/at91sam9.c
- --- linux-4.4.28.orig/arch/arm/mach-at91/at91sam9.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/arm/mach-at91/at91sam9.c 2016-11-01 21:26:56.784213869 +0100
- @@ -62,8 +62,6 @@
- soc_dev = soc_device_to_device(soc);
-
- of_platform_populate(NULL, of_default_bus_match_table, NULL, soc_dev);
- -
- - arm_pm_idle = at91sam9_idle;
- }
-
- static void __init at91sam9_dt_device_init(void)
- diff -Nur linux-4.4.28.orig/arch/arm/mach-at91/generic.h linux-4.4.28/arch/arm/mach-at91/generic.h
- --- linux-4.4.28.orig/arch/arm/mach-at91/generic.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/arm/mach-at91/generic.h 2016-11-01 21:26:56.784213869 +0100
- @@ -11,27 +11,18 @@
- #ifndef _AT91_GENERIC_H
- #define _AT91_GENERIC_H
-
- -#include <linux/of.h>
- -#include <linux/reboot.h>
- -
- - /* Map io */
- -extern void __init at91_map_io(void);
- -extern void __init at91_alt_map_io(void);
- -
- -/* idle */
- -extern void at91rm9200_idle(void);
- -extern void at91sam9_idle(void);
- -
- #ifdef CONFIG_PM
- extern void __init at91rm9200_pm_init(void);
- extern void __init at91sam9260_pm_init(void);
- extern void __init at91sam9g45_pm_init(void);
- extern void __init at91sam9x5_pm_init(void);
- +extern void __init sama5_pm_init(void);
- #else
- static inline void __init at91rm9200_pm_init(void) { }
- static inline void __init at91sam9260_pm_init(void) { }
- static inline void __init at91sam9g45_pm_init(void) { }
- static inline void __init at91sam9x5_pm_init(void) { }
- +static inline void __init sama5_pm_init(void) { }
- #endif
-
- #endif /* _AT91_GENERIC_H */
- diff -Nur linux-4.4.28.orig/arch/arm/mach-at91/Kconfig linux-4.4.28/arch/arm/mach-at91/Kconfig
- --- linux-4.4.28.orig/arch/arm/mach-at91/Kconfig 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/arm/mach-at91/Kconfig 2016-11-01 21:26:56.784213869 +0100
- @@ -99,6 +99,7 @@
- config COMMON_CLK_AT91
- bool
- select COMMON_CLK
- + select MFD_SYSCON
-
- config HAVE_AT91_SMD
- bool
- diff -Nur linux-4.4.28.orig/arch/arm/mach-at91/pm.c linux-4.4.28/arch/arm/mach-at91/pm.c
- --- linux-4.4.28.orig/arch/arm/mach-at91/pm.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/arm/mach-at91/pm.c 2016-11-01 21:26:56.788214125 +0100
- @@ -31,10 +31,13 @@
- #include <asm/mach/irq.h>
- #include <asm/fncpy.h>
- #include <asm/cacheflush.h>
- +#include <asm/system_misc.h>
-
- #include "generic.h"
- #include "pm.h"
-
- +static void __iomem *pmc;
- +
- /*
- * FIXME: this is needed to communicate between the pinctrl driver and
- * the PM implementation in the machine. Possibly part of the PM
- @@ -87,7 +90,7 @@
- unsigned long scsr;
- int i;
-
- - scsr = at91_pmc_read(AT91_PMC_SCSR);
- + scsr = readl(pmc + AT91_PMC_SCSR);
-
- /* USB must not be using PLLB */
- if ((scsr & at91_pm_data.uhp_udp_mask) != 0) {
- @@ -101,8 +104,7 @@
-
- if ((scsr & (AT91_PMC_PCK0 << i)) == 0)
- continue;
- -
- - css = at91_pmc_read(AT91_PMC_PCKR(i)) & AT91_PMC_CSS;
- + css = readl(pmc + AT91_PMC_PCKR(i)) & AT91_PMC_CSS;
- if (css != AT91_PMC_CSS_SLOW) {
- pr_err("AT91: PM - Suspend-to-RAM with PCK%d src %d\n", i, css);
- return 0;
- @@ -145,8 +147,8 @@
- flush_cache_all();
- outer_disable();
-
- - at91_suspend_sram_fn(at91_pmc_base, at91_ramc_base[0],
- - at91_ramc_base[1], pm_data);
- + at91_suspend_sram_fn(pmc, at91_ramc_base[0],
- + at91_ramc_base[1], pm_data);
-
- outer_resume();
- }
- @@ -353,6 +355,21 @@
- at91_pm_set_standby(standby);
- }
-
- +void at91rm9200_idle(void)
- +{
- + /*
- + * Disable the processor clock. The processor will be automatically
- + * re-enabled by an interrupt or by a reset.
- + */
- + writel(AT91_PMC_PCK, pmc + AT91_PMC_SCDR);
- +}
- +
- +void at91sam9_idle(void)
- +{
- + writel(AT91_PMC_PCK, pmc + AT91_PMC_SCDR);
- + cpu_do_idle();
- +}
- +
- static void __init at91_pm_sram_init(void)
- {
- struct gen_pool *sram_pool;
- @@ -399,13 +416,36 @@
- &at91_pm_suspend_in_sram, at91_pm_suspend_in_sram_sz);
- }
-
- -static void __init at91_pm_init(void)
- +static const struct of_device_id atmel_pmc_ids[] __initconst = {
- + { .compatible = "atmel,at91rm9200-pmc" },
- + { .compatible = "atmel,at91sam9260-pmc" },
- + { .compatible = "atmel,at91sam9g45-pmc" },
- + { .compatible = "atmel,at91sam9n12-pmc" },
- + { .compatible = "atmel,at91sam9x5-pmc" },
- + { .compatible = "atmel,sama5d3-pmc" },
- + { .compatible = "atmel,sama5d2-pmc" },
- + { /* sentinel */ },
- +};
- +
- +static void __init at91_pm_init(void (*pm_idle)(void))
- {
- - at91_pm_sram_init();
- + struct device_node *pmc_np;
-
- if (at91_cpuidle_device.dev.platform_data)
- platform_device_register(&at91_cpuidle_device);
-
- + pmc_np = of_find_matching_node(NULL, atmel_pmc_ids);
- + pmc = of_iomap(pmc_np, 0);
- + if (!pmc) {
- + pr_err("AT91: PM not supported, PMC not found\n");
- + return;
- + }
- +
- + if (pm_idle)
- + arm_pm_idle = pm_idle;
- +
- + at91_pm_sram_init();
- +
- if (at91_suspend_sram_fn)
- suspend_set_ops(&at91_pm_ops);
- else
- @@ -424,7 +464,7 @@
- at91_pm_data.uhp_udp_mask = AT91RM9200_PMC_UHP | AT91RM9200_PMC_UDP;
- at91_pm_data.memctrl = AT91_MEMCTRL_MC;
-
- - at91_pm_init();
- + at91_pm_init(at91rm9200_idle);
- }
-
- void __init at91sam9260_pm_init(void)
- @@ -432,7 +472,7 @@
- at91_dt_ramc();
- at91_pm_data.memctrl = AT91_MEMCTRL_SDRAMC;
- at91_pm_data.uhp_udp_mask = AT91SAM926x_PMC_UHP | AT91SAM926x_PMC_UDP;
- - return at91_pm_init();
- + at91_pm_init(at91sam9_idle);
- }
-
- void __init at91sam9g45_pm_init(void)
- @@ -440,7 +480,7 @@
- at91_dt_ramc();
- at91_pm_data.uhp_udp_mask = AT91SAM926x_PMC_UHP;
- at91_pm_data.memctrl = AT91_MEMCTRL_DDRSDR;
- - return at91_pm_init();
- + at91_pm_init(at91sam9_idle);
- }
-
- void __init at91sam9x5_pm_init(void)
- @@ -448,5 +488,13 @@
- at91_dt_ramc();
- at91_pm_data.uhp_udp_mask = AT91SAM926x_PMC_UHP | AT91SAM926x_PMC_UDP;
- at91_pm_data.memctrl = AT91_MEMCTRL_DDRSDR;
- - return at91_pm_init();
- + at91_pm_init(at91sam9_idle);
- +}
- +
- +void __init sama5_pm_init(void)
- +{
- + at91_dt_ramc();
- + at91_pm_data.uhp_udp_mask = AT91SAM926x_PMC_UHP | AT91SAM926x_PMC_UDP;
- + at91_pm_data.memctrl = AT91_MEMCTRL_DDRSDR;
- + at91_pm_init(NULL);
- }
- diff -Nur linux-4.4.28.orig/arch/arm/mach-at91/sama5.c linux-4.4.28/arch/arm/mach-at91/sama5.c
- --- linux-4.4.28.orig/arch/arm/mach-at91/sama5.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/arm/mach-at91/sama5.c 2016-11-01 21:26:56.788214125 +0100
- @@ -51,7 +51,7 @@
- soc_dev = soc_device_to_device(soc);
-
- of_platform_populate(NULL, of_default_bus_match_table, NULL, soc_dev);
- - at91sam9x5_pm_init();
- + sama5_pm_init();
- }
-
- static const char *const sama5_dt_board_compat[] __initconst = {
- diff -Nur linux-4.4.28.orig/arch/arm/mach-exynos/platsmp.c linux-4.4.28/arch/arm/mach-exynos/platsmp.c
- --- linux-4.4.28.orig/arch/arm/mach-exynos/platsmp.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/arm/mach-exynos/platsmp.c 2016-11-01 21:26:56.796214642 +0100
- @@ -230,7 +230,7 @@
- return (void __iomem *)(S5P_VA_SCU);
- }
-
- -static DEFINE_SPINLOCK(boot_lock);
- +static DEFINE_RAW_SPINLOCK(boot_lock);
-
- static void exynos_secondary_init(unsigned int cpu)
- {
- @@ -243,8 +243,8 @@
- /*
- * Synchronise with the boot thread.
- */
- - spin_lock(&boot_lock);
- - spin_unlock(&boot_lock);
- + raw_spin_lock(&boot_lock);
- + raw_spin_unlock(&boot_lock);
- }
-
- int exynos_set_boot_addr(u32 core_id, unsigned long boot_addr)
- @@ -308,7 +308,7 @@
- * Set synchronisation state between this boot processor
- * and the secondary one
- */
- - spin_lock(&boot_lock);
- + raw_spin_lock(&boot_lock);
-
- /*
- * The secondary processor is waiting to be released from
- @@ -335,7 +335,7 @@
-
- if (timeout == 0) {
- printk(KERN_ERR "cpu1 power enable failed");
- - spin_unlock(&boot_lock);
- + raw_spin_unlock(&boot_lock);
- return -ETIMEDOUT;
- }
- }
- @@ -381,7 +381,7 @@
- * calibrations, then wait for it to finish
- */
- fail:
- - spin_unlock(&boot_lock);
- + raw_spin_unlock(&boot_lock);
-
- return pen_release != -1 ? ret : 0;
- }
- diff -Nur linux-4.4.28.orig/arch/arm/mach-hisi/platmcpm.c linux-4.4.28/arch/arm/mach-hisi/platmcpm.c
- --- linux-4.4.28.orig/arch/arm/mach-hisi/platmcpm.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/arm/mach-hisi/platmcpm.c 2016-11-01 21:26:56.800214899 +0100
- @@ -61,7 +61,7 @@
-
- static void __iomem *sysctrl, *fabric;
- static int hip04_cpu_table[HIP04_MAX_CLUSTERS][HIP04_MAX_CPUS_PER_CLUSTER];
- -static DEFINE_SPINLOCK(boot_lock);
- +static DEFINE_RAW_SPINLOCK(boot_lock);
- static u32 fabric_phys_addr;
- /*
- * [0]: bootwrapper physical address
- @@ -113,7 +113,7 @@
- if (cluster >= HIP04_MAX_CLUSTERS || cpu >= HIP04_MAX_CPUS_PER_CLUSTER)
- return -EINVAL;
-
- - spin_lock_irq(&boot_lock);
- + raw_spin_lock_irq(&boot_lock);
-
- if (hip04_cpu_table[cluster][cpu])
- goto out;
- @@ -147,7 +147,7 @@
-
- out:
- hip04_cpu_table[cluster][cpu]++;
- - spin_unlock_irq(&boot_lock);
- + raw_spin_unlock_irq(&boot_lock);
-
- return 0;
- }
- @@ -162,11 +162,11 @@
- cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
- cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
-
- - spin_lock(&boot_lock);
- + raw_spin_lock(&boot_lock);
- hip04_cpu_table[cluster][cpu]--;
- if (hip04_cpu_table[cluster][cpu] == 1) {
- /* A power_up request went ahead of us. */
- - spin_unlock(&boot_lock);
- + raw_spin_unlock(&boot_lock);
- return;
- } else if (hip04_cpu_table[cluster][cpu] > 1) {
- pr_err("Cluster %d CPU%d boots multiple times\n", cluster, cpu);
- @@ -174,7 +174,7 @@
- }
-
- last_man = hip04_cluster_is_down(cluster);
- - spin_unlock(&boot_lock);
- + raw_spin_unlock(&boot_lock);
- if (last_man) {
- /* Since it's Cortex A15, disable L2 prefetching. */
- asm volatile(
- @@ -203,7 +203,7 @@
- cpu >= HIP04_MAX_CPUS_PER_CLUSTER);
-
- count = TIMEOUT_MSEC / POLL_MSEC;
- - spin_lock_irq(&boot_lock);
- + raw_spin_lock_irq(&boot_lock);
- for (tries = 0; tries < count; tries++) {
- if (hip04_cpu_table[cluster][cpu])
- goto err;
- @@ -211,10 +211,10 @@
- data = readl_relaxed(sysctrl + SC_CPU_RESET_STATUS(cluster));
- if (data & CORE_WFI_STATUS(cpu))
- break;
- - spin_unlock_irq(&boot_lock);
- + raw_spin_unlock_irq(&boot_lock);
- /* Wait for clean L2 when the whole cluster is down. */
- msleep(POLL_MSEC);
- - spin_lock_irq(&boot_lock);
- + raw_spin_lock_irq(&boot_lock);
- }
- if (tries >= count)
- goto err;
- @@ -231,10 +231,10 @@
- goto err;
- if (hip04_cluster_is_down(cluster))
- hip04_set_snoop_filter(cluster, 0);
- - spin_unlock_irq(&boot_lock);
- + raw_spin_unlock_irq(&boot_lock);
- return 1;
- err:
- - spin_unlock_irq(&boot_lock);
- + raw_spin_unlock_irq(&boot_lock);
- return 0;
- }
- #endif
- diff -Nur linux-4.4.28.orig/arch/arm/mach-imx/Kconfig linux-4.4.28/arch/arm/mach-imx/Kconfig
- --- linux-4.4.28.orig/arch/arm/mach-imx/Kconfig 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/arm/mach-imx/Kconfig 2016-11-01 21:26:56.804215163 +0100
- @@ -524,7 +524,7 @@
- bool "i.MX6 Quad/DualLite support"
- select ARM_ERRATA_764369 if SMP
- select HAVE_ARM_SCU if SMP
- - select HAVE_ARM_TWD if SMP
- + select HAVE_ARM_TWD
- select PCI_DOMAINS if PCI
- select PINCTRL_IMX6Q
- select SOC_IMX6
- diff -Nur linux-4.4.28.orig/arch/arm/mach-omap2/omap-smp.c linux-4.4.28/arch/arm/mach-omap2/omap-smp.c
- --- linux-4.4.28.orig/arch/arm/mach-omap2/omap-smp.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/arm/mach-omap2/omap-smp.c 2016-11-01 21:26:56.836217219 +0100
- @@ -43,7 +43,7 @@
- /* SCU base address */
- static void __iomem *scu_base;
-
- -static DEFINE_SPINLOCK(boot_lock);
- +static DEFINE_RAW_SPINLOCK(boot_lock);
-
- void __iomem *omap4_get_scu_base(void)
- {
- @@ -74,8 +74,8 @@
- /*
- * Synchronise with the boot thread.
- */
- - spin_lock(&boot_lock);
- - spin_unlock(&boot_lock);
- + raw_spin_lock(&boot_lock);
- + raw_spin_unlock(&boot_lock);
- }
-
- static int omap4_boot_secondary(unsigned int cpu, struct task_struct *idle)
- @@ -89,7 +89,7 @@
- * Set synchronisation state between this boot processor
- * and the secondary one
- */
- - spin_lock(&boot_lock);
- + raw_spin_lock(&boot_lock);
-
- /*
- * Update the AuxCoreBoot0 with boot state for secondary core.
- @@ -166,7 +166,7 @@
- * Now the secondary core is starting up let it run its
- * calibrations, then wait for it to finish
- */
- - spin_unlock(&boot_lock);
- + raw_spin_unlock(&boot_lock);
-
- return 0;
- }
- diff -Nur linux-4.4.28.orig/arch/arm/mach-prima2/platsmp.c linux-4.4.28/arch/arm/mach-prima2/platsmp.c
- --- linux-4.4.28.orig/arch/arm/mach-prima2/platsmp.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/arm/mach-prima2/platsmp.c 2016-11-01 21:26:56.864219031 +0100
- @@ -22,7 +22,7 @@
-
- static void __iomem *clk_base;
-
- -static DEFINE_SPINLOCK(boot_lock);
- +static DEFINE_RAW_SPINLOCK(boot_lock);
-
- static void sirfsoc_secondary_init(unsigned int cpu)
- {
- @@ -36,8 +36,8 @@
- /*
- * Synchronise with the boot thread.
- */
- - spin_lock(&boot_lock);
- - spin_unlock(&boot_lock);
- + raw_spin_lock(&boot_lock);
- + raw_spin_unlock(&boot_lock);
- }
-
- static const struct of_device_id clk_ids[] = {
- @@ -75,7 +75,7 @@
- /* make sure write buffer is drained */
- mb();
-
- - spin_lock(&boot_lock);
- + raw_spin_lock(&boot_lock);
-
- /*
- * The secondary processor is waiting to be released from
- @@ -107,7 +107,7 @@
- * now the secondary core is starting up let it run its
- * calibrations, then wait for it to finish
- */
- - spin_unlock(&boot_lock);
- + raw_spin_unlock(&boot_lock);
-
- return pen_release != -1 ? -ENOSYS : 0;
- }
- diff -Nur linux-4.4.28.orig/arch/arm/mach-qcom/platsmp.c linux-4.4.28/arch/arm/mach-qcom/platsmp.c
- --- linux-4.4.28.orig/arch/arm/mach-qcom/platsmp.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/arm/mach-qcom/platsmp.c 2016-11-01 21:26:56.872219540 +0100
- @@ -46,7 +46,7 @@
-
- extern void secondary_startup_arm(void);
-
- -static DEFINE_SPINLOCK(boot_lock);
- +static DEFINE_RAW_SPINLOCK(boot_lock);
-
- #ifdef CONFIG_HOTPLUG_CPU
- static void qcom_cpu_die(unsigned int cpu)
- @@ -60,8 +60,8 @@
- /*
- * Synchronise with the boot thread.
- */
- - spin_lock(&boot_lock);
- - spin_unlock(&boot_lock);
- + raw_spin_lock(&boot_lock);
- + raw_spin_unlock(&boot_lock);
- }
-
- static int scss_release_secondary(unsigned int cpu)
- @@ -284,7 +284,7 @@
- * set synchronisation state between this boot processor
- * and the secondary one
- */
- - spin_lock(&boot_lock);
- + raw_spin_lock(&boot_lock);
-
- /*
- * Send the secondary CPU a soft interrupt, thereby causing
- @@ -297,7 +297,7 @@
- * now the secondary core is starting up let it run its
- * calibrations, then wait for it to finish
- */
- - spin_unlock(&boot_lock);
- + raw_spin_unlock(&boot_lock);
-
- return ret;
- }
- diff -Nur linux-4.4.28.orig/arch/arm/mach-spear/platsmp.c linux-4.4.28/arch/arm/mach-spear/platsmp.c
- --- linux-4.4.28.orig/arch/arm/mach-spear/platsmp.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/arm/mach-spear/platsmp.c 2016-11-01 21:26:56.896221093 +0100
- @@ -32,7 +32,7 @@
- sync_cache_w(&pen_release);
- }
-
- -static DEFINE_SPINLOCK(boot_lock);
- +static DEFINE_RAW_SPINLOCK(boot_lock);
-
- static void __iomem *scu_base = IOMEM(VA_SCU_BASE);
-
- @@ -47,8 +47,8 @@
- /*
- * Synchronise with the boot thread.
- */
- - spin_lock(&boot_lock);
- - spin_unlock(&boot_lock);
- + raw_spin_lock(&boot_lock);
- + raw_spin_unlock(&boot_lock);
- }
-
- static int spear13xx_boot_secondary(unsigned int cpu, struct task_struct *idle)
- @@ -59,7 +59,7 @@
- * set synchronisation state between this boot processor
- * and the secondary one
- */
- - spin_lock(&boot_lock);
- + raw_spin_lock(&boot_lock);
-
- /*
- * The secondary processor is waiting to be released from
- @@ -84,7 +84,7 @@
- * now the secondary core is starting up let it run its
- * calibrations, then wait for it to finish
- */
- - spin_unlock(&boot_lock);
- + raw_spin_unlock(&boot_lock);
-
- return pen_release != -1 ? -ENOSYS : 0;
- }
- diff -Nur linux-4.4.28.orig/arch/arm/mach-sti/platsmp.c linux-4.4.28/arch/arm/mach-sti/platsmp.c
- --- linux-4.4.28.orig/arch/arm/mach-sti/platsmp.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/arm/mach-sti/platsmp.c 2016-11-01 21:26:56.896221093 +0100
- @@ -35,7 +35,7 @@
- sync_cache_w(&pen_release);
- }
-
- -static DEFINE_SPINLOCK(boot_lock);
- +static DEFINE_RAW_SPINLOCK(boot_lock);
-
- static void sti_secondary_init(unsigned int cpu)
- {
- @@ -48,8 +48,8 @@
- /*
- * Synchronise with the boot thread.
- */
- - spin_lock(&boot_lock);
- - spin_unlock(&boot_lock);
- + raw_spin_lock(&boot_lock);
- + raw_spin_unlock(&boot_lock);
- }
-
- static int sti_boot_secondary(unsigned int cpu, struct task_struct *idle)
- @@ -60,7 +60,7 @@
- * set synchronisation state between this boot processor
- * and the secondary one
- */
- - spin_lock(&boot_lock);
- + raw_spin_lock(&boot_lock);
-
- /*
- * The secondary processor is waiting to be released from
- @@ -91,7 +91,7 @@
- * now the secondary core is starting up let it run its
- * calibrations, then wait for it to finish
- */
- - spin_unlock(&boot_lock);
- + raw_spin_unlock(&boot_lock);
-
- return pen_release != -1 ? -ENOSYS : 0;
- }
- diff -Nur linux-4.4.28.orig/arch/arm/mm/fault.c linux-4.4.28/arch/arm/mm/fault.c
- --- linux-4.4.28.orig/arch/arm/mm/fault.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/arm/mm/fault.c 2016-11-01 21:26:56.900221345 +0100
- @@ -430,6 +430,9 @@
- if (addr < TASK_SIZE)
- return do_page_fault(addr, fsr, regs);
-
- + if (interrupts_enabled(regs))
- + local_irq_enable();
- +
- if (user_mode(regs))
- goto bad_area;
-
- @@ -497,6 +500,9 @@
- static int
- do_sect_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
- {
- + if (interrupts_enabled(regs))
- + local_irq_enable();
- +
- do_bad_area(addr, fsr, regs);
- return 0;
- }
- diff -Nur linux-4.4.28.orig/arch/arm/mm/highmem.c linux-4.4.28/arch/arm/mm/highmem.c
- --- linux-4.4.28.orig/arch/arm/mm/highmem.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/arm/mm/highmem.c 2016-11-01 21:26:56.904221609 +0100
- @@ -34,6 +34,11 @@
- return *ptep;
- }
-
- +static unsigned int fixmap_idx(int type)
- +{
- + return FIX_KMAP_BEGIN + type + KM_TYPE_NR * smp_processor_id();
- +}
- +
- void *kmap(struct page *page)
- {
- might_sleep();
- @@ -54,12 +59,13 @@
-
- void *kmap_atomic(struct page *page)
- {
- + pte_t pte = mk_pte(page, kmap_prot);
- unsigned int idx;
- unsigned long vaddr;
- void *kmap;
- int type;
-
- - preempt_disable();
- + preempt_disable_nort();
- pagefault_disable();
- if (!PageHighMem(page))
- return page_address(page);
- @@ -79,7 +85,7 @@
-
- type = kmap_atomic_idx_push();
-
- - idx = FIX_KMAP_BEGIN + type + KM_TYPE_NR * smp_processor_id();
- + idx = fixmap_idx(type);
- vaddr = __fix_to_virt(idx);
- #ifdef CONFIG_DEBUG_HIGHMEM
- /*
- @@ -93,7 +99,10 @@
- * in place, so the contained TLB flush ensures the TLB is updated
- * with the new mapping.
- */
- - set_fixmap_pte(idx, mk_pte(page, kmap_prot));
- +#ifdef CONFIG_PREEMPT_RT_FULL
- + current->kmap_pte[type] = pte;
- +#endif
- + set_fixmap_pte(idx, pte);
-
- return (void *)vaddr;
- }
- @@ -106,44 +115,75 @@
-
- if (kvaddr >= (void *)FIXADDR_START) {
- type = kmap_atomic_idx();
- - idx = FIX_KMAP_BEGIN + type + KM_TYPE_NR * smp_processor_id();
- + idx = fixmap_idx(type);
-
- if (cache_is_vivt())
- __cpuc_flush_dcache_area((void *)vaddr, PAGE_SIZE);
- +#ifdef CONFIG_PREEMPT_RT_FULL
- + current->kmap_pte[type] = __pte(0);
- +#endif
- #ifdef CONFIG_DEBUG_HIGHMEM
- BUG_ON(vaddr != __fix_to_virt(idx));
- - set_fixmap_pte(idx, __pte(0));
- #else
- (void) idx; /* to kill a warning */
- #endif
- + set_fixmap_pte(idx, __pte(0));
- kmap_atomic_idx_pop();
- } else if (vaddr >= PKMAP_ADDR(0) && vaddr < PKMAP_ADDR(LAST_PKMAP)) {
- /* this address was obtained through kmap_high_get() */
- kunmap_high(pte_page(pkmap_page_table[PKMAP_NR(vaddr)]));
- }
- pagefault_enable();
- - preempt_enable();
- + preempt_enable_nort();
- }
- EXPORT_SYMBOL(__kunmap_atomic);
-
- void *kmap_atomic_pfn(unsigned long pfn)
- {
- + pte_t pte = pfn_pte(pfn, kmap_prot);
- unsigned long vaddr;
- int idx, type;
- struct page *page = pfn_to_page(pfn);
-
- - preempt_disable();
- + preempt_disable_nort();
- pagefault_disable();
- if (!PageHighMem(page))
- return page_address(page);
-
- type = kmap_atomic_idx_push();
- - idx = FIX_KMAP_BEGIN + type + KM_TYPE_NR * smp_processor_id();
- + idx = fixmap_idx(type);
- vaddr = __fix_to_virt(idx);
- #ifdef CONFIG_DEBUG_HIGHMEM
- BUG_ON(!pte_none(get_fixmap_pte(vaddr)));
- #endif
- - set_fixmap_pte(idx, pfn_pte(pfn, kmap_prot));
- +#ifdef CONFIG_PREEMPT_RT_FULL
- + current->kmap_pte[type] = pte;
- +#endif
- + set_fixmap_pte(idx, pte);
-
- return (void *)vaddr;
- }
- +#if defined CONFIG_PREEMPT_RT_FULL
- +void switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p)
- +{
- + int i;
- +
- + /*
- + * Clear @prev's kmap_atomic mappings
- + */
- + for (i = 0; i < prev_p->kmap_idx; i++) {
- + int idx = fixmap_idx(i);
- +
- + set_fixmap_pte(idx, __pte(0));
- + }
- + /*
- + * Restore @next_p's kmap_atomic mappings
- + */
- + for (i = 0; i < next_p->kmap_idx; i++) {
- + int idx = fixmap_idx(i);
- +
- + if (!pte_none(next_p->kmap_pte[i]))
- + set_fixmap_pte(idx, next_p->kmap_pte[i]);
- + }
- +}
- +#endif
- diff -Nur linux-4.4.28.orig/arch/arm/plat-versatile/platsmp.c linux-4.4.28/arch/arm/plat-versatile/platsmp.c
- --- linux-4.4.28.orig/arch/arm/plat-versatile/platsmp.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/arm/plat-versatile/platsmp.c 2016-11-01 21:26:56.936223672 +0100
- @@ -30,7 +30,7 @@
- sync_cache_w(&pen_release);
- }
-
- -static DEFINE_SPINLOCK(boot_lock);
- +static DEFINE_RAW_SPINLOCK(boot_lock);
-
- void versatile_secondary_init(unsigned int cpu)
- {
- @@ -43,8 +43,8 @@
- /*
- * Synchronise with the boot thread.
- */
- - spin_lock(&boot_lock);
- - spin_unlock(&boot_lock);
- + raw_spin_lock(&boot_lock);
- + raw_spin_unlock(&boot_lock);
- }
-
- int versatile_boot_secondary(unsigned int cpu, struct task_struct *idle)
- @@ -55,7 +55,7 @@
- * Set synchronisation state between this boot processor
- * and the secondary one
- */
- - spin_lock(&boot_lock);
- + raw_spin_lock(&boot_lock);
-
- /*
- * This is really belt and braces; we hold unintended secondary
- @@ -85,7 +85,7 @@
- * now the secondary core is starting up let it run its
- * calibrations, then wait for it to finish
- */
- - spin_unlock(&boot_lock);
- + raw_spin_unlock(&boot_lock);
-
- return pen_release != -1 ? -ENOSYS : 0;
- }
- diff -Nur linux-4.4.28.orig/arch/arm64/include/asm/thread_info.h linux-4.4.28/arch/arm64/include/asm/thread_info.h
- --- linux-4.4.28.orig/arch/arm64/include/asm/thread_info.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/arm64/include/asm/thread_info.h 2016-11-01 21:26:56.948224439 +0100
- @@ -49,6 +49,7 @@
- mm_segment_t addr_limit; /* address limit */
- struct task_struct *task; /* main task structure */
- int preempt_count; /* 0 => preemptable, <0 => bug */
- + int preempt_lazy_count; /* 0 => preemptable, <0 => bug */
- int cpu; /* cpu */
- };
-
- @@ -103,6 +104,7 @@
- #define TIF_NEED_RESCHED 1
- #define TIF_NOTIFY_RESUME 2 /* callback before returning to user */
- #define TIF_FOREIGN_FPSTATE 3 /* CPU's FP state is not current's */
- +#define TIF_NEED_RESCHED_LAZY 4
- #define TIF_NOHZ 7
- #define TIF_SYSCALL_TRACE 8
- #define TIF_SYSCALL_AUDIT 9
- @@ -118,6 +120,7 @@
- #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED)
- #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME)
- #define _TIF_FOREIGN_FPSTATE (1 << TIF_FOREIGN_FPSTATE)
- +#define _TIF_NEED_RESCHED_LAZY (1 << TIF_NEED_RESCHED_LAZY)
- #define _TIF_NOHZ (1 << TIF_NOHZ)
- #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE)
- #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT)
- @@ -126,7 +129,8 @@
- #define _TIF_32BIT (1 << TIF_32BIT)
-
- #define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \
- - _TIF_NOTIFY_RESUME | _TIF_FOREIGN_FPSTATE)
- + _TIF_NOTIFY_RESUME | _TIF_FOREIGN_FPSTATE | \
- + _TIF_NEED_RESCHED_LAZY)
-
- #define _TIF_SYSCALL_WORK (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
- _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP | \
- diff -Nur linux-4.4.28.orig/arch/arm64/Kconfig linux-4.4.28/arch/arm64/Kconfig
- --- linux-4.4.28.orig/arch/arm64/Kconfig 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/arm64/Kconfig 2016-11-01 21:26:56.944224187 +0100
- @@ -76,6 +76,7 @@
- select HAVE_PERF_REGS
- select HAVE_PERF_USER_STACK_DUMP
- select HAVE_RCU_TABLE_FREE
- + select HAVE_PREEMPT_LAZY
- select HAVE_SYSCALL_TRACEPOINTS
- select IOMMU_DMA if IOMMU_SUPPORT
- select IRQ_DOMAIN
- @@ -582,7 +583,7 @@
-
- config XEN
- bool "Xen guest support on ARM64"
- - depends on ARM64 && OF
- + depends on ARM64 && OF && !PREEMPT_RT_FULL
- select SWIOTLB_XEN
- help
- Say Y if you want to run Linux in a Virtual Machine on Xen on ARM64.
- diff -Nur linux-4.4.28.orig/arch/arm64/kernel/asm-offsets.c linux-4.4.28/arch/arm64/kernel/asm-offsets.c
- --- linux-4.4.28.orig/arch/arm64/kernel/asm-offsets.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/arm64/kernel/asm-offsets.c 2016-11-01 21:26:56.976226250 +0100
- @@ -35,6 +35,7 @@
- BLANK();
- DEFINE(TI_FLAGS, offsetof(struct thread_info, flags));
- DEFINE(TI_PREEMPT, offsetof(struct thread_info, preempt_count));
- + DEFINE(TI_PREEMPT_LAZY, offsetof(struct thread_info, preempt_lazy_count));
- DEFINE(TI_ADDR_LIMIT, offsetof(struct thread_info, addr_limit));
- DEFINE(TI_TASK, offsetof(struct thread_info, task));
- DEFINE(TI_CPU, offsetof(struct thread_info, cpu));
- diff -Nur linux-4.4.28.orig/arch/arm64/kernel/entry.S linux-4.4.28/arch/arm64/kernel/entry.S
- --- linux-4.4.28.orig/arch/arm64/kernel/entry.S 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/arm64/kernel/entry.S 2016-11-01 21:26:56.976226250 +0100
- @@ -376,11 +376,16 @@
- #ifdef CONFIG_PREEMPT
- get_thread_info tsk
- ldr w24, [tsk, #TI_PREEMPT] // get preempt count
- - cbnz w24, 1f // preempt count != 0
- + cbnz w24, 2f // preempt count != 0
- ldr x0, [tsk, #TI_FLAGS] // get flags
- - tbz x0, #TIF_NEED_RESCHED, 1f // needs rescheduling?
- - bl el1_preempt
- + tbnz x0, #TIF_NEED_RESCHED, 1f // needs rescheduling?
- +
- + ldr w24, [tsk, #TI_PREEMPT_LAZY] // get preempt lazy count
- + cbnz w24, 2f // preempt lazy count != 0
- + tbz x0, #TIF_NEED_RESCHED_LAZY, 2f // needs rescheduling?
- 1:
- + bl el1_preempt
- +2:
- #endif
- #ifdef CONFIG_TRACE_IRQFLAGS
- bl trace_hardirqs_on
- @@ -394,6 +399,7 @@
- 1: bl preempt_schedule_irq // irq en/disable is done inside
- ldr x0, [tsk, #TI_FLAGS] // get new tasks TI_FLAGS
- tbnz x0, #TIF_NEED_RESCHED, 1b // needs rescheduling?
- + tbnz x0, #TIF_NEED_RESCHED_LAZY, 1b // needs rescheduling?
- ret x24
- #endif
-
- @@ -638,6 +644,7 @@
- */
- work_pending:
- tbnz x1, #TIF_NEED_RESCHED, work_resched
- + tbnz x1, #TIF_NEED_RESCHED_LAZY, work_resched
- /* TIF_SIGPENDING, TIF_NOTIFY_RESUME or TIF_FOREIGN_FPSTATE case */
- ldr x2, [sp, #S_PSTATE]
- mov x0, sp // 'regs'
- diff -Nur linux-4.4.28.orig/arch/Kconfig linux-4.4.28/arch/Kconfig
- --- linux-4.4.28.orig/arch/Kconfig 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/Kconfig 2016-11-01 21:26:56.688207681 +0100
- @@ -9,6 +9,7 @@
- tristate "OProfile system profiling"
- depends on PROFILING
- depends on HAVE_OPROFILE
- + depends on !PREEMPT_RT_FULL
- select RING_BUFFER
- select RING_BUFFER_ALLOW_SWAP
- help
- @@ -52,6 +53,7 @@
- config JUMP_LABEL
- bool "Optimize very unlikely/likely branches"
- depends on HAVE_ARCH_JUMP_LABEL
- + depends on (!INTERRUPT_OFF_HIST && !PREEMPT_OFF_HIST && !WAKEUP_LATENCY_HIST && !MISSED_TIMER_OFFSETS_HIST)
- help
- This option enables a transparent branch optimization that
- makes certain almost-always-true or almost-always-false branch
- diff -Nur linux-4.4.28.orig/arch/mips/Kconfig linux-4.4.28/arch/mips/Kconfig
- --- linux-4.4.28.orig/arch/mips/Kconfig 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/mips/Kconfig 2016-11-01 21:26:57.008228310 +0100
- @@ -2410,7 +2410,7 @@
- #
- config HIGHMEM
- bool "High Memory Support"
- - depends on 32BIT && CPU_SUPPORTS_HIGHMEM && SYS_SUPPORTS_HIGHMEM && !CPU_MIPS32_3_5_EVA
- + depends on 32BIT && CPU_SUPPORTS_HIGHMEM && SYS_SUPPORTS_HIGHMEM && !CPU_MIPS32_3_5_EVA && !PREEMPT_RT_FULL
-
- config CPU_SUPPORTS_HIGHMEM
- bool
- diff -Nur linux-4.4.28.orig/arch/mips/kvm/mips.c linux-4.4.28/arch/mips/kvm/mips.c
- --- linux-4.4.28.orig/arch/mips/kvm/mips.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/mips/kvm/mips.c 2016-11-01 21:26:57.044230629 +0100
- @@ -454,8 +454,8 @@
-
- dvcpu->arch.wait = 0;
-
- - if (waitqueue_active(&dvcpu->wq))
- - wake_up_interruptible(&dvcpu->wq);
- + if (swait_active(&dvcpu->wq))
- + swake_up(&dvcpu->wq);
-
- return 0;
- }
- @@ -1183,8 +1183,8 @@
- kvm_mips_callbacks->queue_timer_int(vcpu);
-
- vcpu->arch.wait = 0;
- - if (waitqueue_active(&vcpu->wq))
- - wake_up_interruptible(&vcpu->wq);
- + if (swait_active(&vcpu->wq))
- + swake_up(&vcpu->wq);
- }
-
- /* low level hrtimer wake routine */
- diff -Nur linux-4.4.28.orig/arch/powerpc/include/asm/kvm_host.h linux-4.4.28/arch/powerpc/include/asm/kvm_host.h
- --- linux-4.4.28.orig/arch/powerpc/include/asm/kvm_host.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/powerpc/include/asm/kvm_host.h 2016-11-01 21:26:57.116235270 +0100
- @@ -286,7 +286,7 @@
- struct list_head runnable_threads;
- struct list_head preempt_list;
- spinlock_t lock;
- - wait_queue_head_t wq;
- + struct swait_queue_head wq;
- spinlock_t stoltb_lock; /* protects stolen_tb and preempt_tb */
- u64 stolen_tb;
- u64 preempt_tb;
- @@ -626,7 +626,7 @@
- u8 prodded;
- u32 last_inst;
-
- - wait_queue_head_t *wqp;
- + struct swait_queue_head *wqp;
- struct kvmppc_vcore *vcore;
- int ret;
- int trap;
- diff -Nur linux-4.4.28.orig/arch/powerpc/include/asm/thread_info.h linux-4.4.28/arch/powerpc/include/asm/thread_info.h
- --- linux-4.4.28.orig/arch/powerpc/include/asm/thread_info.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/powerpc/include/asm/thread_info.h 2016-11-01 21:26:57.124235787 +0100
- @@ -42,6 +42,8 @@
- int cpu; /* cpu we're on */
- int preempt_count; /* 0 => preemptable,
- <0 => BUG */
- + int preempt_lazy_count; /* 0 => preemptable,
- + <0 => BUG */
- unsigned long local_flags; /* private flags for thread */
-
- /* low level flags - has atomic operations done on it */
- @@ -82,8 +84,7 @@
- #define TIF_SYSCALL_TRACE 0 /* syscall trace active */
- #define TIF_SIGPENDING 1 /* signal pending */
- #define TIF_NEED_RESCHED 2 /* rescheduling necessary */
- -#define TIF_POLLING_NRFLAG 3 /* true if poll_idle() is polling
- - TIF_NEED_RESCHED */
- +#define TIF_NEED_RESCHED_LAZY 3 /* lazy rescheduling necessary */
- #define TIF_32BIT 4 /* 32 bit binary */
- #define TIF_RESTORE_TM 5 /* need to restore TM FP/VEC/VSX */
- #define TIF_SYSCALL_AUDIT 7 /* syscall auditing active */
- @@ -101,6 +102,8 @@
- #if defined(CONFIG_PPC64)
- #define TIF_ELF2ABI 18 /* function descriptors must die! */
- #endif
- +#define TIF_POLLING_NRFLAG 19 /* true if poll_idle() is polling
- + TIF_NEED_RESCHED */
-
- /* as above, but as bit values */
- #define _TIF_SYSCALL_TRACE (1<<TIF_SYSCALL_TRACE)
- @@ -119,14 +122,16 @@
- #define _TIF_SYSCALL_TRACEPOINT (1<<TIF_SYSCALL_TRACEPOINT)
- #define _TIF_EMULATE_STACK_STORE (1<<TIF_EMULATE_STACK_STORE)
- #define _TIF_NOHZ (1<<TIF_NOHZ)
- +#define _TIF_NEED_RESCHED_LAZY (1<<TIF_NEED_RESCHED_LAZY)
- #define _TIF_SYSCALL_DOTRACE (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
- _TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT | \
- _TIF_NOHZ)
-
- #define _TIF_USER_WORK_MASK (_TIF_SIGPENDING | _TIF_NEED_RESCHED | \
- _TIF_NOTIFY_RESUME | _TIF_UPROBE | \
- - _TIF_RESTORE_TM)
- + _TIF_RESTORE_TM | _TIF_NEED_RESCHED_LAZY)
- #define _TIF_PERSYSCALL_MASK (_TIF_RESTOREALL|_TIF_NOERROR)
- +#define _TIF_NEED_RESCHED_MASK (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY)
-
- /* Bits in local_flags */
- /* Don't move TLF_NAPPING without adjusting the code in entry_32.S */
- diff -Nur linux-4.4.28.orig/arch/powerpc/Kconfig linux-4.4.28/arch/powerpc/Kconfig
- --- linux-4.4.28.orig/arch/powerpc/Kconfig 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/powerpc/Kconfig 2016-11-01 21:26:57.072232440 +0100
- @@ -60,10 +60,11 @@
-
- config RWSEM_GENERIC_SPINLOCK
- bool
- + default y if PREEMPT_RT_FULL
-
- config RWSEM_XCHGADD_ALGORITHM
- bool
- - default y
- + default y if !PREEMPT_RT_FULL
-
- config GENERIC_LOCKBREAK
- bool
- @@ -141,6 +142,7 @@
- select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
- select GENERIC_STRNCPY_FROM_USER
- select GENERIC_STRNLEN_USER
- + select HAVE_PREEMPT_LAZY
- select HAVE_MOD_ARCH_SPECIFIC
- select MODULES_USE_ELF_RELA
- select CLONE_BACKWARDS
- @@ -319,7 +321,7 @@
-
- config HIGHMEM
- bool "High memory support"
- - depends on PPC32
- + depends on PPC32 && !PREEMPT_RT_FULL
-
- source kernel/Kconfig.hz
- source kernel/Kconfig.preempt
- diff -Nur linux-4.4.28.orig/arch/powerpc/kernel/asm-offsets.c linux-4.4.28/arch/powerpc/kernel/asm-offsets.c
- --- linux-4.4.28.orig/arch/powerpc/kernel/asm-offsets.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/powerpc/kernel/asm-offsets.c 2016-11-01 21:26:57.136236560 +0100
- @@ -160,6 +160,7 @@
- DEFINE(TI_FLAGS, offsetof(struct thread_info, flags));
- DEFINE(TI_LOCAL_FLAGS, offsetof(struct thread_info, local_flags));
- DEFINE(TI_PREEMPT, offsetof(struct thread_info, preempt_count));
- + DEFINE(TI_PREEMPT_LAZY, offsetof(struct thread_info, preempt_lazy_count));
- DEFINE(TI_TASK, offsetof(struct thread_info, task));
- DEFINE(TI_CPU, offsetof(struct thread_info, cpu));
-
- diff -Nur linux-4.4.28.orig/arch/powerpc/kernel/entry_32.S linux-4.4.28/arch/powerpc/kernel/entry_32.S
- --- linux-4.4.28.orig/arch/powerpc/kernel/entry_32.S 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/powerpc/kernel/entry_32.S 2016-11-01 21:26:57.144237081 +0100
- @@ -818,7 +818,14 @@
- cmpwi 0,r0,0 /* if non-zero, just restore regs and return */
- bne restore
- andi. r8,r8,_TIF_NEED_RESCHED
- + bne+ 1f
- + lwz r0,TI_PREEMPT_LAZY(r9)
- + cmpwi 0,r0,0 /* if non-zero, just restore regs and return */
- + bne restore
- + lwz r0,TI_FLAGS(r9)
- + andi. r0,r0,_TIF_NEED_RESCHED_LAZY
- beq+ restore
- +1:
- lwz r3,_MSR(r1)
- andi. r0,r3,MSR_EE /* interrupts off? */
- beq restore /* don't schedule if so */
- @@ -829,11 +836,11 @@
- */
- bl trace_hardirqs_off
- #endif
- -1: bl preempt_schedule_irq
- +2: bl preempt_schedule_irq
- CURRENT_THREAD_INFO(r9, r1)
- lwz r3,TI_FLAGS(r9)
- - andi. r0,r3,_TIF_NEED_RESCHED
- - bne- 1b
- + andi. r0,r3,_TIF_NEED_RESCHED_MASK
- + bne- 2b
- #ifdef CONFIG_TRACE_IRQFLAGS
- /* And now, to properly rebalance the above, we tell lockdep they
- * are being turned back on, which will happen when we return
- @@ -1154,7 +1161,7 @@
- #endif /* !(CONFIG_4xx || CONFIG_BOOKE) */
-
- do_work: /* r10 contains MSR_KERNEL here */
- - andi. r0,r9,_TIF_NEED_RESCHED
- + andi. r0,r9,_TIF_NEED_RESCHED_MASK
- beq do_user_signal
-
- do_resched: /* r10 contains MSR_KERNEL here */
- @@ -1175,7 +1182,7 @@
- MTMSRD(r10) /* disable interrupts */
- CURRENT_THREAD_INFO(r9, r1)
- lwz r9,TI_FLAGS(r9)
- - andi. r0,r9,_TIF_NEED_RESCHED
- + andi. r0,r9,_TIF_NEED_RESCHED_MASK
- bne- do_resched
- andi. r0,r9,_TIF_USER_WORK_MASK
- beq restore_user
- diff -Nur linux-4.4.28.orig/arch/powerpc/kernel/entry_64.S linux-4.4.28/arch/powerpc/kernel/entry_64.S
- --- linux-4.4.28.orig/arch/powerpc/kernel/entry_64.S 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/powerpc/kernel/entry_64.S 2016-11-01 21:26:57.144237081 +0100
- @@ -683,7 +683,7 @@
- #else
- beq restore
- #endif
- -1: andi. r0,r4,_TIF_NEED_RESCHED
- +1: andi. r0,r4,_TIF_NEED_RESCHED_MASK
- beq 2f
- bl restore_interrupts
- SCHEDULE_USER
- @@ -745,10 +745,18 @@
-
- #ifdef CONFIG_PREEMPT
- /* Check if we need to preempt */
- + lwz r8,TI_PREEMPT(r9)
- + cmpwi 0,r8,0 /* if non-zero, just restore regs and return */
- + bne restore
- andi. r0,r4,_TIF_NEED_RESCHED
- + bne+ check_count
- +
- + andi. r0,r4,_TIF_NEED_RESCHED_LAZY
- beq+ restore
- + lwz r8,TI_PREEMPT_LAZY(r9)
- +
- /* Check that preempt_count() == 0 and interrupts are enabled */
- - lwz r8,TI_PREEMPT(r9)
- +check_count:
- cmpwi cr1,r8,0
- ld r0,SOFTE(r1)
- cmpdi r0,0
- @@ -765,7 +773,7 @@
- /* Re-test flags and eventually loop */
- CURRENT_THREAD_INFO(r9, r1)
- ld r4,TI_FLAGS(r9)
- - andi. r0,r4,_TIF_NEED_RESCHED
- + andi. r0,r4,_TIF_NEED_RESCHED_MASK
- bne 1b
-
- /*
- diff -Nur linux-4.4.28.orig/arch/powerpc/kernel/irq.c linux-4.4.28/arch/powerpc/kernel/irq.c
- --- linux-4.4.28.orig/arch/powerpc/kernel/irq.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/powerpc/kernel/irq.c 2016-11-01 21:26:57.152237590 +0100
- @@ -614,6 +614,7 @@
- }
- }
-
- +#ifndef CONFIG_PREEMPT_RT_FULL
- void do_softirq_own_stack(void)
- {
- struct thread_info *curtp, *irqtp;
- @@ -631,6 +632,7 @@
- if (irqtp->flags)
- set_bits(irqtp->flags, &curtp->flags);
- }
- +#endif
-
- irq_hw_number_t virq_to_hw(unsigned int virq)
- {
- diff -Nur linux-4.4.28.orig/arch/powerpc/kernel/misc_32.S linux-4.4.28/arch/powerpc/kernel/misc_32.S
- --- linux-4.4.28.orig/arch/powerpc/kernel/misc_32.S 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/powerpc/kernel/misc_32.S 2016-11-01 21:26:57.156237855 +0100
- @@ -40,6 +40,7 @@
- * We store the saved ksp_limit in the unused part
- * of the STACK_FRAME_OVERHEAD
- */
- +#ifndef CONFIG_PREEMPT_RT_FULL
- _GLOBAL(call_do_softirq)
- mflr r0
- stw r0,4(r1)
- @@ -56,6 +57,7 @@
- stw r10,THREAD+KSP_LIMIT(r2)
- mtlr r0
- blr
- +#endif
-
- /*
- * void call_do_irq(struct pt_regs *regs, struct thread_info *irqtp);
- diff -Nur linux-4.4.28.orig/arch/powerpc/kernel/misc_64.S linux-4.4.28/arch/powerpc/kernel/misc_64.S
- --- linux-4.4.28.orig/arch/powerpc/kernel/misc_64.S 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/powerpc/kernel/misc_64.S 2016-11-01 21:26:57.160238107 +0100
- @@ -30,6 +30,7 @@
-
- .text
-
- +#ifndef CONFIG_PREEMPT_RT_FULL
- _GLOBAL(call_do_softirq)
- mflr r0
- std r0,16(r1)
- @@ -40,6 +41,7 @@
- ld r0,16(r1)
- mtlr r0
- blr
- +#endif
-
- _GLOBAL(call_do_irq)
- mflr r0
- diff -Nur linux-4.4.28.orig/arch/powerpc/kvm/book3s_hv.c linux-4.4.28/arch/powerpc/kvm/book3s_hv.c
- --- linux-4.4.28.orig/arch/powerpc/kvm/book3s_hv.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/powerpc/kvm/book3s_hv.c 2016-11-01 21:26:57.184239655 +0100
- @@ -114,11 +114,11 @@
- static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu)
- {
- int cpu;
- - wait_queue_head_t *wqp;
- + struct swait_queue_head *wqp;
-
- wqp = kvm_arch_vcpu_wq(vcpu);
- - if (waitqueue_active(wqp)) {
- - wake_up_interruptible(wqp);
- + if (swait_active(wqp)) {
- + swake_up(wqp);
- ++vcpu->stat.halt_wakeup;
- }
-
- @@ -707,8 +707,8 @@
- tvcpu->arch.prodded = 1;
- smp_mb();
- if (vcpu->arch.ceded) {
- - if (waitqueue_active(&vcpu->wq)) {
- - wake_up_interruptible(&vcpu->wq);
- + if (swait_active(&vcpu->wq)) {
- + swake_up(&vcpu->wq);
- vcpu->stat.halt_wakeup++;
- }
- }
- @@ -1447,7 +1447,7 @@
- INIT_LIST_HEAD(&vcore->runnable_threads);
- spin_lock_init(&vcore->lock);
- spin_lock_init(&vcore->stoltb_lock);
- - init_waitqueue_head(&vcore->wq);
- + init_swait_queue_head(&vcore->wq);
- vcore->preempt_tb = TB_NIL;
- vcore->lpcr = kvm->arch.lpcr;
- vcore->first_vcpuid = core * threads_per_subcore;
- @@ -2519,10 +2519,9 @@
- {
- struct kvm_vcpu *vcpu;
- int do_sleep = 1;
- + DECLARE_SWAITQUEUE(wait);
-
- - DEFINE_WAIT(wait);
- -
- - prepare_to_wait(&vc->wq, &wait, TASK_INTERRUPTIBLE);
- + prepare_to_swait(&vc->wq, &wait, TASK_INTERRUPTIBLE);
-
- /*
- * Check one last time for pending exceptions and ceded state after
- @@ -2536,7 +2535,7 @@
- }
-
- if (!do_sleep) {
- - finish_wait(&vc->wq, &wait);
- + finish_swait(&vc->wq, &wait);
- return;
- }
-
- @@ -2544,7 +2543,7 @@
- trace_kvmppc_vcore_blocked(vc, 0);
- spin_unlock(&vc->lock);
- schedule();
- - finish_wait(&vc->wq, &wait);
- + finish_swait(&vc->wq, &wait);
- spin_lock(&vc->lock);
- vc->vcore_state = VCORE_INACTIVE;
- trace_kvmppc_vcore_blocked(vc, 1);
- @@ -2600,7 +2599,7 @@
- kvmppc_start_thread(vcpu, vc);
- trace_kvm_guest_enter(vcpu);
- } else if (vc->vcore_state == VCORE_SLEEPING) {
- - wake_up(&vc->wq);
- + swake_up(&vc->wq);
- }
-
- }
- diff -Nur linux-4.4.28.orig/arch/powerpc/kvm/Kconfig linux-4.4.28/arch/powerpc/kvm/Kconfig
- --- linux-4.4.28.orig/arch/powerpc/kvm/Kconfig 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/powerpc/kvm/Kconfig 2016-11-01 21:26:57.168238628 +0100
- @@ -172,6 +172,7 @@
- config KVM_MPIC
- bool "KVM in-kernel MPIC emulation"
- depends on KVM && E500
- + depends on !PREEMPT_RT_FULL
- select HAVE_KVM_IRQCHIP
- select HAVE_KVM_IRQFD
- select HAVE_KVM_IRQ_ROUTING
- diff -Nur linux-4.4.28.orig/arch/powerpc/platforms/ps3/device-init.c linux-4.4.28/arch/powerpc/platforms/ps3/device-init.c
- --- linux-4.4.28.orig/arch/powerpc/platforms/ps3/device-init.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/powerpc/platforms/ps3/device-init.c 2016-11-01 21:26:57.192240175 +0100
- @@ -752,7 +752,7 @@
- }
- pr_debug("%s:%u: notification %s issued\n", __func__, __LINE__, op);
-
- - res = wait_event_interruptible(dev->done.wait,
- + res = swait_event_interruptible(dev->done.wait,
- dev->done.done || kthread_should_stop());
- if (kthread_should_stop())
- res = -EINTR;
- diff -Nur linux-4.4.28.orig/arch/s390/include/asm/kvm_host.h linux-4.4.28/arch/s390/include/asm/kvm_host.h
- --- linux-4.4.28.orig/arch/s390/include/asm/kvm_host.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/s390/include/asm/kvm_host.h 2016-11-01 21:26:57.204240949 +0100
- @@ -427,7 +427,7 @@
- struct kvm_s390_local_interrupt {
- spinlock_t lock;
- struct kvm_s390_float_interrupt *float_int;
- - wait_queue_head_t *wq;
- + struct swait_queue_head *wq;
- atomic_t *cpuflags;
- DECLARE_BITMAP(sigp_emerg_pending, KVM_MAX_VCPUS);
- struct kvm_s390_irq_payload irq;
- diff -Nur linux-4.4.28.orig/arch/s390/kvm/interrupt.c linux-4.4.28/arch/s390/kvm/interrupt.c
- --- linux-4.4.28.orig/arch/s390/kvm/interrupt.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/s390/kvm/interrupt.c 2016-11-01 21:26:57.224242231 +0100
- @@ -868,13 +868,13 @@
-
- void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu)
- {
- - if (waitqueue_active(&vcpu->wq)) {
- + if (swait_active(&vcpu->wq)) {
- /*
- * The vcpu gave up the cpu voluntarily, mark it as a good
- * yield-candidate.
- */
- vcpu->preempted = true;
- - wake_up_interruptible(&vcpu->wq);
- + swake_up(&vcpu->wq);
- vcpu->stat.halt_wakeup++;
- }
- }
- diff -Nur linux-4.4.28.orig/arch/sh/kernel/irq.c linux-4.4.28/arch/sh/kernel/irq.c
- --- linux-4.4.28.orig/arch/sh/kernel/irq.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/sh/kernel/irq.c 2016-11-01 21:26:57.284246099 +0100
- @@ -147,6 +147,7 @@
- hardirq_ctx[cpu] = NULL;
- }
-
- +#ifndef CONFIG_PREEMPT_RT_FULL
- void do_softirq_own_stack(void)
- {
- struct thread_info *curctx;
- @@ -174,6 +175,7 @@
- "r5", "r6", "r7", "r8", "r9", "r15", "t", "pr"
- );
- }
- +#endif
- #else
- static inline void handle_one_irq(unsigned int irq)
- {
- diff -Nur linux-4.4.28.orig/arch/sparc/Kconfig linux-4.4.28/arch/sparc/Kconfig
- --- linux-4.4.28.orig/arch/sparc/Kconfig 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/sparc/Kconfig 2016-11-01 21:26:57.460257444 +0100
- @@ -189,12 +189,10 @@
- source kernel/Kconfig.hz
-
- config RWSEM_GENERIC_SPINLOCK
- - bool
- - default y if SPARC32
- + def_bool PREEMPT_RT_FULL
-
- config RWSEM_XCHGADD_ALGORITHM
- - bool
- - default y if SPARC64
- + def_bool !RWSEM_GENERIC_SPINLOCK && !PREEMPT_RT_FULL
-
- config GENERIC_HWEIGHT
- bool
- diff -Nur linux-4.4.28.orig/arch/sparc/kernel/irq_64.c linux-4.4.28/arch/sparc/kernel/irq_64.c
- --- linux-4.4.28.orig/arch/sparc/kernel/irq_64.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/sparc/kernel/irq_64.c 2016-11-01 21:26:57.488259255 +0100
- @@ -854,6 +854,7 @@
- set_irq_regs(old_regs);
- }
-
- +#ifndef CONFIG_PREEMPT_RT_FULL
- void do_softirq_own_stack(void)
- {
- void *orig_sp, *sp = softirq_stack[smp_processor_id()];
- @@ -868,6 +869,7 @@
- __asm__ __volatile__("mov %0, %%sp"
- : : "r" (orig_sp));
- }
- +#endif
-
- #ifdef CONFIG_HOTPLUG_CPU
- void fixup_irqs(void)
- diff -Nur linux-4.4.28.orig/arch/x86/crypto/aesni-intel_glue.c linux-4.4.28/arch/x86/crypto/aesni-intel_glue.c
- --- linux-4.4.28.orig/arch/x86/crypto/aesni-intel_glue.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/x86/crypto/aesni-intel_glue.c 2016-11-01 21:26:57.524261570 +0100
- @@ -383,14 +383,14 @@
- err = blkcipher_walk_virt(desc, &walk);
- desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
-
- - kernel_fpu_begin();
- while ((nbytes = walk.nbytes)) {
- + kernel_fpu_begin();
- aesni_ecb_enc(ctx, walk.dst.virt.addr, walk.src.virt.addr,
- - nbytes & AES_BLOCK_MASK);
- + nbytes & AES_BLOCK_MASK);
- + kernel_fpu_end();
- nbytes &= AES_BLOCK_SIZE - 1;
- err = blkcipher_walk_done(desc, &walk, nbytes);
- }
- - kernel_fpu_end();
-
- return err;
- }
- @@ -407,14 +407,14 @@
- err = blkcipher_walk_virt(desc, &walk);
- desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
-
- - kernel_fpu_begin();
- while ((nbytes = walk.nbytes)) {
- + kernel_fpu_begin();
- aesni_ecb_dec(ctx, walk.dst.virt.addr, walk.src.virt.addr,
- nbytes & AES_BLOCK_MASK);
- + kernel_fpu_end();
- nbytes &= AES_BLOCK_SIZE - 1;
- err = blkcipher_walk_done(desc, &walk, nbytes);
- }
- - kernel_fpu_end();
-
- return err;
- }
- @@ -431,14 +431,14 @@
- err = blkcipher_walk_virt(desc, &walk);
- desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
-
- - kernel_fpu_begin();
- while ((nbytes = walk.nbytes)) {
- + kernel_fpu_begin();
- aesni_cbc_enc(ctx, walk.dst.virt.addr, walk.src.virt.addr,
- nbytes & AES_BLOCK_MASK, walk.iv);
- + kernel_fpu_end();
- nbytes &= AES_BLOCK_SIZE - 1;
- err = blkcipher_walk_done(desc, &walk, nbytes);
- }
- - kernel_fpu_end();
-
- return err;
- }
- @@ -455,14 +455,14 @@
- err = blkcipher_walk_virt(desc, &walk);
- desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
-
- - kernel_fpu_begin();
- while ((nbytes = walk.nbytes)) {
- + kernel_fpu_begin();
- aesni_cbc_dec(ctx, walk.dst.virt.addr, walk.src.virt.addr,
- nbytes & AES_BLOCK_MASK, walk.iv);
- + kernel_fpu_end();
- nbytes &= AES_BLOCK_SIZE - 1;
- err = blkcipher_walk_done(desc, &walk, nbytes);
- }
- - kernel_fpu_end();
-
- return err;
- }
- @@ -514,18 +514,20 @@
- err = blkcipher_walk_virt_block(desc, &walk, AES_BLOCK_SIZE);
- desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
-
- - kernel_fpu_begin();
- while ((nbytes = walk.nbytes) >= AES_BLOCK_SIZE) {
- + kernel_fpu_begin();
- aesni_ctr_enc_tfm(ctx, walk.dst.virt.addr, walk.src.virt.addr,
- nbytes & AES_BLOCK_MASK, walk.iv);
- + kernel_fpu_end();
- nbytes &= AES_BLOCK_SIZE - 1;
- err = blkcipher_walk_done(desc, &walk, nbytes);
- }
- if (walk.nbytes) {
- + kernel_fpu_begin();
- ctr_crypt_final(ctx, &walk);
- + kernel_fpu_end();
- err = blkcipher_walk_done(desc, &walk, 0);
- }
- - kernel_fpu_end();
-
- return err;
- }
- diff -Nur linux-4.4.28.orig/arch/x86/crypto/cast5_avx_glue.c linux-4.4.28/arch/x86/crypto/cast5_avx_glue.c
- --- linux-4.4.28.orig/arch/x86/crypto/cast5_avx_glue.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/x86/crypto/cast5_avx_glue.c 2016-11-01 21:26:57.528261834 +0100
- @@ -59,7 +59,7 @@
- static int ecb_crypt(struct blkcipher_desc *desc, struct blkcipher_walk *walk,
- bool enc)
- {
- - bool fpu_enabled = false;
- + bool fpu_enabled;
- struct cast5_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
- const unsigned int bsize = CAST5_BLOCK_SIZE;
- unsigned int nbytes;
- @@ -75,7 +75,7 @@
- u8 *wsrc = walk->src.virt.addr;
- u8 *wdst = walk->dst.virt.addr;
-
- - fpu_enabled = cast5_fpu_begin(fpu_enabled, nbytes);
- + fpu_enabled = cast5_fpu_begin(false, nbytes);
-
- /* Process multi-block batch */
- if (nbytes >= bsize * CAST5_PARALLEL_BLOCKS) {
- @@ -103,10 +103,9 @@
- } while (nbytes >= bsize);
-
- done:
- + cast5_fpu_end(fpu_enabled);
- err = blkcipher_walk_done(desc, walk, nbytes);
- }
- -
- - cast5_fpu_end(fpu_enabled);
- return err;
- }
-
- @@ -227,7 +226,7 @@
- static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
- struct scatterlist *src, unsigned int nbytes)
- {
- - bool fpu_enabled = false;
- + bool fpu_enabled;
- struct blkcipher_walk walk;
- int err;
-
- @@ -236,12 +235,11 @@
- desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
-
- while ((nbytes = walk.nbytes)) {
- - fpu_enabled = cast5_fpu_begin(fpu_enabled, nbytes);
- + fpu_enabled = cast5_fpu_begin(false, nbytes);
- nbytes = __cbc_decrypt(desc, &walk);
- + cast5_fpu_end(fpu_enabled);
- err = blkcipher_walk_done(desc, &walk, nbytes);
- }
- -
- - cast5_fpu_end(fpu_enabled);
- return err;
- }
-
- @@ -311,7 +309,7 @@
- static int ctr_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
- struct scatterlist *src, unsigned int nbytes)
- {
- - bool fpu_enabled = false;
- + bool fpu_enabled;
- struct blkcipher_walk walk;
- int err;
-
- @@ -320,13 +318,12 @@
- desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
-
- while ((nbytes = walk.nbytes) >= CAST5_BLOCK_SIZE) {
- - fpu_enabled = cast5_fpu_begin(fpu_enabled, nbytes);
- + fpu_enabled = cast5_fpu_begin(false, nbytes);
- nbytes = __ctr_crypt(desc, &walk);
- + cast5_fpu_end(fpu_enabled);
- err = blkcipher_walk_done(desc, &walk, nbytes);
- }
-
- - cast5_fpu_end(fpu_enabled);
- -
- if (walk.nbytes) {
- ctr_crypt_final(desc, &walk);
- err = blkcipher_walk_done(desc, &walk, 0);
- diff -Nur linux-4.4.28.orig/arch/x86/crypto/glue_helper.c linux-4.4.28/arch/x86/crypto/glue_helper.c
- --- linux-4.4.28.orig/arch/x86/crypto/glue_helper.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/x86/crypto/glue_helper.c 2016-11-01 21:26:57.536262350 +0100
- @@ -39,7 +39,7 @@
- void *ctx = crypto_blkcipher_ctx(desc->tfm);
- const unsigned int bsize = 128 / 8;
- unsigned int nbytes, i, func_bytes;
- - bool fpu_enabled = false;
- + bool fpu_enabled;
- int err;
-
- err = blkcipher_walk_virt(desc, walk);
- @@ -49,7 +49,7 @@
- u8 *wdst = walk->dst.virt.addr;
-
- fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit,
- - desc, fpu_enabled, nbytes);
- + desc, false, nbytes);
-
- for (i = 0; i < gctx->num_funcs; i++) {
- func_bytes = bsize * gctx->funcs[i].num_blocks;
- @@ -71,10 +71,10 @@
- }
-
- done:
- + glue_fpu_end(fpu_enabled);
- err = blkcipher_walk_done(desc, walk, nbytes);
- }
-
- - glue_fpu_end(fpu_enabled);
- return err;
- }
-
- @@ -194,7 +194,7 @@
- struct scatterlist *src, unsigned int nbytes)
- {
- const unsigned int bsize = 128 / 8;
- - bool fpu_enabled = false;
- + bool fpu_enabled;
- struct blkcipher_walk walk;
- int err;
-
- @@ -203,12 +203,12 @@
-
- while ((nbytes = walk.nbytes)) {
- fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit,
- - desc, fpu_enabled, nbytes);
- + desc, false, nbytes);
- nbytes = __glue_cbc_decrypt_128bit(gctx, desc, &walk);
- + glue_fpu_end(fpu_enabled);
- err = blkcipher_walk_done(desc, &walk, nbytes);
- }
-
- - glue_fpu_end(fpu_enabled);
- return err;
- }
- EXPORT_SYMBOL_GPL(glue_cbc_decrypt_128bit);
- @@ -277,7 +277,7 @@
- struct scatterlist *src, unsigned int nbytes)
- {
- const unsigned int bsize = 128 / 8;
- - bool fpu_enabled = false;
- + bool fpu_enabled;
- struct blkcipher_walk walk;
- int err;
-
- @@ -286,13 +286,12 @@
-
- while ((nbytes = walk.nbytes) >= bsize) {
- fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit,
- - desc, fpu_enabled, nbytes);
- + desc, false, nbytes);
- nbytes = __glue_ctr_crypt_128bit(gctx, desc, &walk);
- + glue_fpu_end(fpu_enabled);
- err = blkcipher_walk_done(desc, &walk, nbytes);
- }
-
- - glue_fpu_end(fpu_enabled);
- -
- if (walk.nbytes) {
- glue_ctr_crypt_final_128bit(
- gctx->funcs[gctx->num_funcs - 1].fn_u.ctr, desc, &walk);
- @@ -347,7 +346,7 @@
- void *tweak_ctx, void *crypt_ctx)
- {
- const unsigned int bsize = 128 / 8;
- - bool fpu_enabled = false;
- + bool fpu_enabled;
- struct blkcipher_walk walk;
- int err;
-
- @@ -360,21 +359,21 @@
-
- /* set minimum length to bsize, for tweak_fn */
- fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit,
- - desc, fpu_enabled,
- + desc, false,
- nbytes < bsize ? bsize : nbytes);
- -
- /* calculate first value of T */
- tweak_fn(tweak_ctx, walk.iv, walk.iv);
- + glue_fpu_end(fpu_enabled);
-
- while (nbytes) {
- + fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit,
- + desc, false, nbytes);
- nbytes = __glue_xts_crypt_128bit(gctx, crypt_ctx, desc, &walk);
-
- + glue_fpu_end(fpu_enabled);
- err = blkcipher_walk_done(desc, &walk, nbytes);
- nbytes = walk.nbytes;
- }
- -
- - glue_fpu_end(fpu_enabled);
- -
- return err;
- }
- EXPORT_SYMBOL_GPL(glue_xts_crypt_128bit);
- diff -Nur linux-4.4.28.orig/arch/x86/entry/common.c linux-4.4.28/arch/x86/entry/common.c
- --- linux-4.4.28.orig/arch/x86/entry/common.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/x86/entry/common.c 2016-11-01 21:26:57.544262865 +0100
- @@ -220,7 +220,7 @@
-
- #define EXIT_TO_USERMODE_LOOP_FLAGS \
- (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_UPROBE | \
- - _TIF_NEED_RESCHED | _TIF_USER_RETURN_NOTIFY)
- + _TIF_NEED_RESCHED_MASK | _TIF_USER_RETURN_NOTIFY)
-
- static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags)
- {
- @@ -236,9 +236,16 @@
- /* We have work to do. */
- local_irq_enable();
-
- - if (cached_flags & _TIF_NEED_RESCHED)
- + if (cached_flags & _TIF_NEED_RESCHED_MASK)
- schedule();
-
- +#ifdef ARCH_RT_DELAYS_SIGNAL_SEND
- + if (unlikely(current->forced_info.si_signo)) {
- + struct task_struct *t = current;
- + force_sig_info(t->forced_info.si_signo, &t->forced_info, t);
- + t->forced_info.si_signo = 0;
- + }
- +#endif
- if (cached_flags & _TIF_UPROBE)
- uprobe_notify_resume(regs);
-
- diff -Nur linux-4.4.28.orig/arch/x86/entry/entry_32.S linux-4.4.28/arch/x86/entry/entry_32.S
- --- linux-4.4.28.orig/arch/x86/entry/entry_32.S 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/x86/entry/entry_32.S 2016-11-01 21:26:57.548263117 +0100
- @@ -278,8 +278,24 @@
- ENTRY(resume_kernel)
- DISABLE_INTERRUPTS(CLBR_ANY)
- need_resched:
- + # preempt count == 0 + NEED_RS set?
- cmpl $0, PER_CPU_VAR(__preempt_count)
- +#ifndef CONFIG_PREEMPT_LAZY
- jnz restore_all
- +#else
- + jz test_int_off
- +
- + # atleast preempt count == 0 ?
- + cmpl $_PREEMPT_ENABLED,PER_CPU_VAR(__preempt_count)
- + jne restore_all
- +
- + cmpl $0,TI_preempt_lazy_count(%ebp) # non-zero preempt_lazy_count ?
- + jnz restore_all
- +
- + testl $_TIF_NEED_RESCHED_LAZY, TI_flags(%ebp)
- + jz restore_all
- +test_int_off:
- +#endif
- testl $X86_EFLAGS_IF, PT_EFLAGS(%esp) # interrupts off (exception path) ?
- jz restore_all
- call preempt_schedule_irq
- diff -Nur linux-4.4.28.orig/arch/x86/entry/entry_64.S linux-4.4.28/arch/x86/entry/entry_64.S
- --- linux-4.4.28.orig/arch/x86/entry/entry_64.S 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/x86/entry/entry_64.S 2016-11-01 21:26:57.548263117 +0100
- @@ -579,7 +579,23 @@
- bt $9, EFLAGS(%rsp) /* were interrupts off? */
- jnc 1f
- 0: cmpl $0, PER_CPU_VAR(__preempt_count)
- +#ifndef CONFIG_PREEMPT_LAZY
- jnz 1f
- +#else
- + jz do_preempt_schedule_irq
- +
- + # atleast preempt count == 0 ?
- + cmpl $_PREEMPT_ENABLED,PER_CPU_VAR(__preempt_count)
- + jnz 1f
- +
- + GET_THREAD_INFO(%rcx)
- + cmpl $0, TI_preempt_lazy_count(%rcx)
- + jnz 1f
- +
- + bt $TIF_NEED_RESCHED_LAZY,TI_flags(%rcx)
- + jnc 1f
- +do_preempt_schedule_irq:
- +#endif
- call preempt_schedule_irq
- jmp 0b
- 1:
- @@ -867,6 +883,7 @@
- jmp 2b
- .previous
-
- +#ifndef CONFIG_PREEMPT_RT_FULL
- /* Call softirq on interrupt stack. Interrupts are off. */
- ENTRY(do_softirq_own_stack)
- pushq %rbp
- @@ -879,6 +896,7 @@
- decl PER_CPU_VAR(irq_count)
- ret
- END(do_softirq_own_stack)
- +#endif
-
- #ifdef CONFIG_XEN
- idtentry xen_hypervisor_callback xen_do_hypervisor_callback has_error_code=0
- diff -Nur linux-4.4.28.orig/arch/x86/include/asm/preempt.h linux-4.4.28/arch/x86/include/asm/preempt.h
- --- linux-4.4.28.orig/arch/x86/include/asm/preempt.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/x86/include/asm/preempt.h 2016-11-01 21:26:57.556263632 +0100
- @@ -79,17 +79,46 @@
- * a decrement which hits zero means we have no preempt_count and should
- * reschedule.
- */
- -static __always_inline bool __preempt_count_dec_and_test(void)
- +static __always_inline bool ____preempt_count_dec_and_test(void)
- {
- GEN_UNARY_RMWcc("decl", __preempt_count, __percpu_arg(0), "e");
- }
-
- +static __always_inline bool __preempt_count_dec_and_test(void)
- +{
- + if (____preempt_count_dec_and_test())
- + return true;
- +#ifdef CONFIG_PREEMPT_LAZY
- + if (current_thread_info()->preempt_lazy_count)
- + return false;
- + return test_thread_flag(TIF_NEED_RESCHED_LAZY);
- +#else
- + return false;
- +#endif
- +}
- +
- /*
- * Returns true when we need to resched and can (barring IRQ state).
- */
- static __always_inline bool should_resched(int preempt_offset)
- {
- +#ifdef CONFIG_PREEMPT_LAZY
- + u32 tmp;
- +
- + tmp = raw_cpu_read_4(__preempt_count);
- + if (tmp == preempt_offset)
- + return true;
- +
- + /* preempt count == 0 ? */
- + tmp &= ~PREEMPT_NEED_RESCHED;
- + if (tmp)
- + return false;
- + if (current_thread_info()->preempt_lazy_count)
- + return false;
- + return test_thread_flag(TIF_NEED_RESCHED_LAZY);
- +#else
- return unlikely(raw_cpu_read_4(__preempt_count) == preempt_offset);
- +#endif
- }
-
- #ifdef CONFIG_PREEMPT
- diff -Nur linux-4.4.28.orig/arch/x86/include/asm/signal.h linux-4.4.28/arch/x86/include/asm/signal.h
- --- linux-4.4.28.orig/arch/x86/include/asm/signal.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/x86/include/asm/signal.h 2016-11-01 21:26:57.556263632 +0100
- @@ -23,6 +23,19 @@
- unsigned long sig[_NSIG_WORDS];
- } sigset_t;
-
- +/*
- + * Because some traps use the IST stack, we must keep preemption
- + * disabled while calling do_trap(), but do_trap() may call
- + * force_sig_info() which will grab the signal spin_locks for the
- + * task, which in PREEMPT_RT_FULL are mutexes. By defining
- + * ARCH_RT_DELAYS_SIGNAL_SEND the force_sig_info() will set
- + * TIF_NOTIFY_RESUME and set up the signal to be sent on exit of the
- + * trap.
- + */
- +#if defined(CONFIG_PREEMPT_RT_FULL)
- +#define ARCH_RT_DELAYS_SIGNAL_SEND
- +#endif
- +
- #ifndef CONFIG_COMPAT
- typedef sigset_t compat_sigset_t;
- #endif
- diff -Nur linux-4.4.28.orig/arch/x86/include/asm/stackprotector.h linux-4.4.28/arch/x86/include/asm/stackprotector.h
- --- linux-4.4.28.orig/arch/x86/include/asm/stackprotector.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/x86/include/asm/stackprotector.h 2016-11-01 21:26:57.560263897 +0100
- @@ -59,7 +59,7 @@
- */
- static __always_inline void boot_init_stack_canary(void)
- {
- - u64 canary;
- + u64 uninitialized_var(canary);
- u64 tsc;
-
- #ifdef CONFIG_X86_64
- @@ -70,8 +70,15 @@
- * of randomness. The TSC only matters for very early init,
- * there it already has some randomness on most systems. Later
- * on during the bootup the random pool has true entropy too.
- + *
- + * For preempt-rt we need to weaken the randomness a bit, as
- + * we can't call into the random generator from atomic context
- + * due to locking constraints. We just leave canary
- + * uninitialized and use the TSC based randomness on top of it.
- */
- +#ifndef CONFIG_PREEMPT_RT_FULL
- get_random_bytes(&canary, sizeof(canary));
- +#endif
- tsc = rdtsc();
- canary += tsc + (tsc << 32UL);
-
- diff -Nur linux-4.4.28.orig/arch/x86/include/asm/thread_info.h linux-4.4.28/arch/x86/include/asm/thread_info.h
- --- linux-4.4.28.orig/arch/x86/include/asm/thread_info.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/x86/include/asm/thread_info.h 2016-11-01 21:26:57.560263897 +0100
- @@ -58,6 +58,8 @@
- __u32 status; /* thread synchronous flags */
- __u32 cpu; /* current CPU */
- mm_segment_t addr_limit;
- + int preempt_lazy_count; /* 0 => lazy preemptable
- + <0 => BUG */
- unsigned int sig_on_uaccess_error:1;
- unsigned int uaccess_err:1; /* uaccess failed */
- };
- @@ -95,6 +97,7 @@
- #define TIF_SYSCALL_EMU 6 /* syscall emulation active */
- #define TIF_SYSCALL_AUDIT 7 /* syscall auditing active */
- #define TIF_SECCOMP 8 /* secure computing */
- +#define TIF_NEED_RESCHED_LAZY 9 /* lazy rescheduling necessary */
- #define TIF_USER_RETURN_NOTIFY 11 /* notify kernel of userspace return */
- #define TIF_UPROBE 12 /* breakpointed or singlestepping */
- #define TIF_NOTSC 16 /* TSC is not accessible in userland */
- @@ -119,6 +122,7 @@
- #define _TIF_SYSCALL_EMU (1 << TIF_SYSCALL_EMU)
- #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT)
- #define _TIF_SECCOMP (1 << TIF_SECCOMP)
- +#define _TIF_NEED_RESCHED_LAZY (1 << TIF_NEED_RESCHED_LAZY)
- #define _TIF_USER_RETURN_NOTIFY (1 << TIF_USER_RETURN_NOTIFY)
- #define _TIF_UPROBE (1 << TIF_UPROBE)
- #define _TIF_NOTSC (1 << TIF_NOTSC)
- @@ -152,6 +156,8 @@
- #define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY)
- #define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW)
-
- +#define _TIF_NEED_RESCHED_MASK (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY)
- +
- #define STACK_WARN (THREAD_SIZE/8)
-
- /*
- diff -Nur linux-4.4.28.orig/arch/x86/include/asm/uv/uv_bau.h linux-4.4.28/arch/x86/include/asm/uv/uv_bau.h
- --- linux-4.4.28.orig/arch/x86/include/asm/uv/uv_bau.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/x86/include/asm/uv/uv_bau.h 2016-11-01 21:26:57.568264412 +0100
- @@ -615,9 +615,9 @@
- cycles_t send_message;
- cycles_t period_end;
- cycles_t period_time;
- - spinlock_t uvhub_lock;
- - spinlock_t queue_lock;
- - spinlock_t disable_lock;
- + raw_spinlock_t uvhub_lock;
- + raw_spinlock_t queue_lock;
- + raw_spinlock_t disable_lock;
- /* tunables */
- int max_concurr;
- int max_concurr_const;
- @@ -776,15 +776,15 @@
- * to be lowered below the current 'v'. atomic_add_unless can only stop
- * on equal.
- */
- -static inline int atomic_inc_unless_ge(spinlock_t *lock, atomic_t *v, int u)
- +static inline int atomic_inc_unless_ge(raw_spinlock_t *lock, atomic_t *v, int u)
- {
- - spin_lock(lock);
- + raw_spin_lock(lock);
- if (atomic_read(v) >= u) {
- - spin_unlock(lock);
- + raw_spin_unlock(lock);
- return 0;
- }
- atomic_inc(v);
- - spin_unlock(lock);
- + raw_spin_unlock(lock);
- return 1;
- }
-
- diff -Nur linux-4.4.28.orig/arch/x86/include/asm/uv/uv_hub.h linux-4.4.28/arch/x86/include/asm/uv/uv_hub.h
- --- linux-4.4.28.orig/arch/x86/include/asm/uv/uv_hub.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/x86/include/asm/uv/uv_hub.h 2016-11-01 21:26:57.568264412 +0100
- @@ -492,7 +492,7 @@
- unsigned short nr_online_cpus;
- unsigned short pnode;
- short memory_nid;
- - spinlock_t nmi_lock; /* obsolete, see uv_hub_nmi */
- + raw_spinlock_t nmi_lock; /* obsolete, see uv_hub_nmi */
- unsigned long nmi_count; /* obsolete, see uv_hub_nmi */
- };
- extern struct uv_blade_info *uv_blade_info;
- diff -Nur linux-4.4.28.orig/arch/x86/Kconfig linux-4.4.28/arch/x86/Kconfig
- --- linux-4.4.28.orig/arch/x86/Kconfig 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/x86/Kconfig 2016-11-01 21:26:57.508260538 +0100
- @@ -17,6 +17,7 @@
- ### Arch settings
- config X86
- def_bool y
- + select HAVE_PREEMPT_LAZY
- select ACPI_LEGACY_TABLES_LOOKUP if ACPI
- select ACPI_SYSTEM_POWER_STATES_SUPPORT if ACPI
- select ANON_INODES
- @@ -212,8 +213,11 @@
- def_bool y
- depends on ISA_DMA_API
-
- +config RWSEM_GENERIC_SPINLOCK
- + def_bool PREEMPT_RT_FULL
- +
- config RWSEM_XCHGADD_ALGORITHM
- - def_bool y
- + def_bool !RWSEM_GENERIC_SPINLOCK && !PREEMPT_RT_FULL
-
- config GENERIC_CALIBRATE_DELAY
- def_bool y
- @@ -848,7 +852,7 @@
- config MAXSMP
- bool "Enable Maximum number of SMP Processors and NUMA Nodes"
- depends on X86_64 && SMP && DEBUG_KERNEL
- - select CPUMASK_OFFSTACK
- + select CPUMASK_OFFSTACK if !PREEMPT_RT_FULL
- ---help---
- Enable maximum number of CPUS and NUMA Nodes for this architecture.
- If unsure, say N.
- diff -Nur linux-4.4.28.orig/arch/x86/kernel/acpi/boot.c linux-4.4.28/arch/x86/kernel/acpi/boot.c
- --- linux-4.4.28.orig/arch/x86/kernel/acpi/boot.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/x86/kernel/acpi/boot.c 2016-11-01 21:26:57.580265179 +0100
- @@ -87,7 +87,9 @@
- * ->ioapic_mutex
- * ->ioapic_lock
- */
- +#ifdef CONFIG_X86_IO_APIC
- static DEFINE_MUTEX(acpi_ioapic_lock);
- +#endif
-
- /* --------------------------------------------------------------------------
- Boot-time Configuration
- diff -Nur linux-4.4.28.orig/arch/x86/kernel/apic/io_apic.c linux-4.4.28/arch/x86/kernel/apic/io_apic.c
- --- linux-4.4.28.orig/arch/x86/kernel/apic/io_apic.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/x86/kernel/apic/io_apic.c 2016-11-01 21:26:57.600266475 +0100
- @@ -1711,7 +1711,8 @@
- static inline bool ioapic_irqd_mask(struct irq_data *data)
- {
- /* If we are moving the irq we need to mask it */
- - if (unlikely(irqd_is_setaffinity_pending(data))) {
- + if (unlikely(irqd_is_setaffinity_pending(data) &&
- + !irqd_irq_inprogress(data))) {
- mask_ioapic_irq(data);
- return true;
- }
- diff -Nur linux-4.4.28.orig/arch/x86/kernel/apic/x2apic_uv_x.c linux-4.4.28/arch/x86/kernel/apic/x2apic_uv_x.c
- --- linux-4.4.28.orig/arch/x86/kernel/apic/x2apic_uv_x.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/x86/kernel/apic/x2apic_uv_x.c 2016-11-01 21:26:57.612267242 +0100
- @@ -947,7 +947,7 @@
- uv_blade_info[blade].pnode = pnode;
- uv_blade_info[blade].nr_possible_cpus = 0;
- uv_blade_info[blade].nr_online_cpus = 0;
- - spin_lock_init(&uv_blade_info[blade].nmi_lock);
- + raw_spin_lock_init(&uv_blade_info[blade].nmi_lock);
- min_pnode = min(pnode, min_pnode);
- max_pnode = max(pnode, max_pnode);
- blade++;
- diff -Nur linux-4.4.28.orig/arch/x86/kernel/asm-offsets.c linux-4.4.28/arch/x86/kernel/asm-offsets.c
- --- linux-4.4.28.orig/arch/x86/kernel/asm-offsets.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/x86/kernel/asm-offsets.c 2016-11-01 21:26:57.612267242 +0100
- @@ -32,6 +32,7 @@
- OFFSET(TI_flags, thread_info, flags);
- OFFSET(TI_status, thread_info, status);
- OFFSET(TI_addr_limit, thread_info, addr_limit);
- + OFFSET(TI_preempt_lazy_count, thread_info, preempt_lazy_count);
-
- BLANK();
- OFFSET(crypto_tfm_ctx_offset, crypto_tfm, __crt_ctx);
- @@ -89,4 +90,5 @@
-
- BLANK();
- DEFINE(PTREGS_SIZE, sizeof(struct pt_regs));
- + DEFINE(_PREEMPT_ENABLED, PREEMPT_ENABLED);
- }
- diff -Nur linux-4.4.28.orig/arch/x86/kernel/cpu/mcheck/mce.c linux-4.4.28/arch/x86/kernel/cpu/mcheck/mce.c
- --- linux-4.4.28.orig/arch/x86/kernel/cpu/mcheck/mce.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/x86/kernel/cpu/mcheck/mce.c 2016-11-01 21:26:57.624268022 +0100
- @@ -41,6 +41,8 @@
- #include <linux/debugfs.h>
- #include <linux/irq_work.h>
- #include <linux/export.h>
- +#include <linux/jiffies.h>
- +#include <linux/swork.h>
-
- #include <asm/processor.h>
- #include <asm/traps.h>
- @@ -1236,7 +1238,7 @@
- static unsigned long check_interval = INITIAL_CHECK_INTERVAL;
-
- static DEFINE_PER_CPU(unsigned long, mce_next_interval); /* in jiffies */
- -static DEFINE_PER_CPU(struct timer_list, mce_timer);
- +static DEFINE_PER_CPU(struct hrtimer, mce_timer);
-
- static unsigned long mce_adjust_timer_default(unsigned long interval)
- {
- @@ -1245,32 +1247,18 @@
-
- static unsigned long (*mce_adjust_timer)(unsigned long interval) = mce_adjust_timer_default;
-
- -static void __restart_timer(struct timer_list *t, unsigned long interval)
- +static enum hrtimer_restart __restart_timer(struct hrtimer *timer, unsigned long interval)
- {
- - unsigned long when = jiffies + interval;
- - unsigned long flags;
- -
- - local_irq_save(flags);
- -
- - if (timer_pending(t)) {
- - if (time_before(when, t->expires))
- - mod_timer_pinned(t, when);
- - } else {
- - t->expires = round_jiffies(when);
- - add_timer_on(t, smp_processor_id());
- - }
- -
- - local_irq_restore(flags);
- + if (!interval)
- + return HRTIMER_NORESTART;
- + hrtimer_forward_now(timer, ns_to_ktime(jiffies_to_nsecs(interval)));
- + return HRTIMER_RESTART;
- }
-
- -static void mce_timer_fn(unsigned long data)
- +static enum hrtimer_restart mce_timer_fn(struct hrtimer *timer)
- {
- - struct timer_list *t = this_cpu_ptr(&mce_timer);
- - int cpu = smp_processor_id();
- unsigned long iv;
-
- - WARN_ON(cpu != data);
- -
- iv = __this_cpu_read(mce_next_interval);
-
- if (mce_available(this_cpu_ptr(&cpu_info))) {
- @@ -1293,7 +1281,7 @@
-
- done:
- __this_cpu_write(mce_next_interval, iv);
- - __restart_timer(t, iv);
- + return __restart_timer(timer, iv);
- }
-
- /*
- @@ -1301,7 +1289,7 @@
- */
- void mce_timer_kick(unsigned long interval)
- {
- - struct timer_list *t = this_cpu_ptr(&mce_timer);
- + struct hrtimer *t = this_cpu_ptr(&mce_timer);
- unsigned long iv = __this_cpu_read(mce_next_interval);
-
- __restart_timer(t, interval);
- @@ -1316,7 +1304,7 @@
- int cpu;
-
- for_each_online_cpu(cpu)
- - del_timer_sync(&per_cpu(mce_timer, cpu));
- + hrtimer_cancel(&per_cpu(mce_timer, cpu));
- }
-
- static void mce_do_trigger(struct work_struct *work)
- @@ -1326,6 +1314,56 @@
-
- static DECLARE_WORK(mce_trigger_work, mce_do_trigger);
-
- +static void __mce_notify_work(struct swork_event *event)
- +{
- + /* Not more than two messages every minute */
- + static DEFINE_RATELIMIT_STATE(ratelimit, 60*HZ, 2);
- +
- + /* wake processes polling /dev/mcelog */
- + wake_up_interruptible(&mce_chrdev_wait);
- +
- + /*
- + * There is no risk of missing notifications because
- + * work_pending is always cleared before the function is
- + * executed.
- + */
- + if (mce_helper[0] && !work_pending(&mce_trigger_work))
- + schedule_work(&mce_trigger_work);
- +
- + if (__ratelimit(&ratelimit))
- + pr_info(HW_ERR "Machine check events logged\n");
- +}
- +
- +#ifdef CONFIG_PREEMPT_RT_FULL
- +static bool notify_work_ready __read_mostly;
- +static struct swork_event notify_work;
- +
- +static int mce_notify_work_init(void)
- +{
- + int err;
- +
- + err = swork_get();
- + if (err)
- + return err;
- +
- + INIT_SWORK(¬ify_work, __mce_notify_work);
- + notify_work_ready = true;
- + return 0;
- +}
- +
- +static void mce_notify_work(void)
- +{
- + if (notify_work_ready)
- + swork_queue(¬ify_work);
- +}
- +#else
- +static void mce_notify_work(void)
- +{
- + __mce_notify_work(NULL);
- +}
- +static inline int mce_notify_work_init(void) { return 0; }
- +#endif
- +
- /*
- * Notify the user(s) about new machine check events.
- * Can be called from interrupt context, but not from machine check/NMI
- @@ -1333,19 +1371,8 @@
- */
- int mce_notify_irq(void)
- {
- - /* Not more than two messages every minute */
- - static DEFINE_RATELIMIT_STATE(ratelimit, 60*HZ, 2);
- -
- if (test_and_clear_bit(0, &mce_need_notify)) {
- - /* wake processes polling /dev/mcelog */
- - wake_up_interruptible(&mce_chrdev_wait);
- -
- - if (mce_helper[0])
- - schedule_work(&mce_trigger_work);
- -
- - if (__ratelimit(&ratelimit))
- - pr_info(HW_ERR "Machine check events logged\n");
- -
- + mce_notify_work();
- return 1;
- }
- return 0;
- @@ -1639,7 +1666,7 @@
- }
- }
-
- -static void mce_start_timer(unsigned int cpu, struct timer_list *t)
- +static void mce_start_timer(unsigned int cpu, struct hrtimer *t)
- {
- unsigned long iv = check_interval * HZ;
-
- @@ -1648,16 +1675,17 @@
-
- per_cpu(mce_next_interval, cpu) = iv;
-
- - t->expires = round_jiffies(jiffies + iv);
- - add_timer_on(t, cpu);
- + hrtimer_start_range_ns(t, ns_to_ktime(jiffies_to_usecs(iv) * 1000ULL),
- + 0, HRTIMER_MODE_REL_PINNED);
- }
-
- static void __mcheck_cpu_init_timer(void)
- {
- - struct timer_list *t = this_cpu_ptr(&mce_timer);
- + struct hrtimer *t = this_cpu_ptr(&mce_timer);
- unsigned int cpu = smp_processor_id();
-
- - setup_timer(t, mce_timer_fn, cpu);
- + hrtimer_init(t, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
- + t->function = mce_timer_fn;
- mce_start_timer(cpu, t);
- }
-
- @@ -2376,6 +2404,8 @@
- if (!mce_available(raw_cpu_ptr(&cpu_info)))
- return;
-
- + hrtimer_cancel(this_cpu_ptr(&mce_timer));
- +
- if (!(action & CPU_TASKS_FROZEN))
- cmci_clear();
-
- @@ -2398,6 +2428,7 @@
- if (b->init)
- wrmsrl(MSR_IA32_MCx_CTL(i), b->ctl);
- }
- + __mcheck_cpu_init_timer();
- }
-
- /* Get notified when a cpu comes on/off. Be hotplug friendly. */
- @@ -2405,7 +2436,6 @@
- mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
- {
- unsigned int cpu = (unsigned long)hcpu;
- - struct timer_list *t = &per_cpu(mce_timer, cpu);
-
- switch (action & ~CPU_TASKS_FROZEN) {
- case CPU_ONLINE:
- @@ -2425,11 +2455,9 @@
- break;
- case CPU_DOWN_PREPARE:
- smp_call_function_single(cpu, mce_disable_cpu, &action, 1);
- - del_timer_sync(t);
- break;
- case CPU_DOWN_FAILED:
- smp_call_function_single(cpu, mce_reenable_cpu, &action, 1);
- - mce_start_timer(cpu, t);
- break;
- }
-
- @@ -2468,6 +2496,10 @@
- goto err_out;
- }
-
- + err = mce_notify_work_init();
- + if (err)
- + goto err_out;
- +
- if (!zalloc_cpumask_var(&mce_device_initialized, GFP_KERNEL)) {
- err = -ENOMEM;
- goto err_out;
- diff -Nur linux-4.4.28.orig/arch/x86/kernel/cpu/perf_event_intel_rapl.c linux-4.4.28/arch/x86/kernel/cpu/perf_event_intel_rapl.c
- --- linux-4.4.28.orig/arch/x86/kernel/cpu/perf_event_intel_rapl.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/x86/kernel/cpu/perf_event_intel_rapl.c 2016-11-01 21:26:57.636268789 +0100
- @@ -117,7 +117,7 @@
- };
-
- struct rapl_pmu {
- - spinlock_t lock;
- + raw_spinlock_t lock;
- int n_active; /* number of active events */
- struct list_head active_list;
- struct pmu *pmu; /* pointer to rapl_pmu_class */
- @@ -220,13 +220,13 @@
- if (!pmu->n_active)
- return HRTIMER_NORESTART;
-
- - spin_lock_irqsave(&pmu->lock, flags);
- + raw_spin_lock_irqsave(&pmu->lock, flags);
-
- list_for_each_entry(event, &pmu->active_list, active_entry) {
- rapl_event_update(event);
- }
-
- - spin_unlock_irqrestore(&pmu->lock, flags);
- + raw_spin_unlock_irqrestore(&pmu->lock, flags);
-
- hrtimer_forward_now(hrtimer, pmu->timer_interval);
-
- @@ -263,9 +263,9 @@
- struct rapl_pmu *pmu = __this_cpu_read(rapl_pmu);
- unsigned long flags;
-
- - spin_lock_irqsave(&pmu->lock, flags);
- + raw_spin_lock_irqsave(&pmu->lock, flags);
- __rapl_pmu_event_start(pmu, event);
- - spin_unlock_irqrestore(&pmu->lock, flags);
- + raw_spin_unlock_irqrestore(&pmu->lock, flags);
- }
-
- static void rapl_pmu_event_stop(struct perf_event *event, int mode)
- @@ -274,7 +274,7 @@
- struct hw_perf_event *hwc = &event->hw;
- unsigned long flags;
-
- - spin_lock_irqsave(&pmu->lock, flags);
- + raw_spin_lock_irqsave(&pmu->lock, flags);
-
- /* mark event as deactivated and stopped */
- if (!(hwc->state & PERF_HES_STOPPED)) {
- @@ -299,7 +299,7 @@
- hwc->state |= PERF_HES_UPTODATE;
- }
-
- - spin_unlock_irqrestore(&pmu->lock, flags);
- + raw_spin_unlock_irqrestore(&pmu->lock, flags);
- }
-
- static int rapl_pmu_event_add(struct perf_event *event, int mode)
- @@ -308,14 +308,14 @@
- struct hw_perf_event *hwc = &event->hw;
- unsigned long flags;
-
- - spin_lock_irqsave(&pmu->lock, flags);
- + raw_spin_lock_irqsave(&pmu->lock, flags);
-
- hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
-
- if (mode & PERF_EF_START)
- __rapl_pmu_event_start(pmu, event);
-
- - spin_unlock_irqrestore(&pmu->lock, flags);
- + raw_spin_unlock_irqrestore(&pmu->lock, flags);
-
- return 0;
- }
- @@ -603,7 +603,7 @@
- pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu));
- if (!pmu)
- return -1;
- - spin_lock_init(&pmu->lock);
- + raw_spin_lock_init(&pmu->lock);
-
- INIT_LIST_HEAD(&pmu->active_list);
-
- diff -Nur linux-4.4.28.orig/arch/x86/kernel/dumpstack_32.c linux-4.4.28/arch/x86/kernel/dumpstack_32.c
- --- linux-4.4.28.orig/arch/x86/kernel/dumpstack_32.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/x86/kernel/dumpstack_32.c 2016-11-01 21:26:57.648269569 +0100
- @@ -42,7 +42,7 @@
- unsigned long *stack, unsigned long bp,
- const struct stacktrace_ops *ops, void *data)
- {
- - const unsigned cpu = get_cpu();
- + const unsigned cpu = get_cpu_light();
- int graph = 0;
- u32 *prev_esp;
-
- @@ -86,7 +86,7 @@
- break;
- touch_nmi_watchdog();
- }
- - put_cpu();
- + put_cpu_light();
- }
- EXPORT_SYMBOL(dump_trace);
-
- diff -Nur linux-4.4.28.orig/arch/x86/kernel/dumpstack_64.c linux-4.4.28/arch/x86/kernel/dumpstack_64.c
- --- linux-4.4.28.orig/arch/x86/kernel/dumpstack_64.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/x86/kernel/dumpstack_64.c 2016-11-01 21:26:57.648269569 +0100
- @@ -152,7 +152,7 @@
- unsigned long *stack, unsigned long bp,
- const struct stacktrace_ops *ops, void *data)
- {
- - const unsigned cpu = get_cpu();
- + const unsigned cpu = get_cpu_light();
- struct thread_info *tinfo;
- unsigned long *irq_stack = (unsigned long *)per_cpu(irq_stack_ptr, cpu);
- unsigned long dummy;
- @@ -241,7 +241,7 @@
- * This handles the process stack:
- */
- bp = ops->walk_stack(tinfo, stack, bp, ops, data, NULL, &graph);
- - put_cpu();
- + put_cpu_light();
- }
- EXPORT_SYMBOL(dump_trace);
-
- @@ -255,7 +255,7 @@
- int cpu;
- int i;
-
- - preempt_disable();
- + migrate_disable();
- cpu = smp_processor_id();
-
- irq_stack_end = (unsigned long *)(per_cpu(irq_stack_ptr, cpu));
- @@ -291,7 +291,7 @@
- pr_cont(" %016lx", *stack++);
- touch_nmi_watchdog();
- }
- - preempt_enable();
- + migrate_enable();
-
- pr_cont("\n");
- show_trace_log_lvl(task, regs, sp, bp, log_lvl);
- diff -Nur linux-4.4.28.orig/arch/x86/kernel/irq_32.c linux-4.4.28/arch/x86/kernel/irq_32.c
- --- linux-4.4.28.orig/arch/x86/kernel/irq_32.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/x86/kernel/irq_32.c 2016-11-01 21:26:57.652269821 +0100
- @@ -128,6 +128,7 @@
- cpu, per_cpu(hardirq_stack, cpu), per_cpu(softirq_stack, cpu));
- }
-
- +#ifndef CONFIG_PREEMPT_RT_FULL
- void do_softirq_own_stack(void)
- {
- struct thread_info *curstk;
- @@ -146,6 +147,7 @@
-
- call_on_stack(__do_softirq, isp);
- }
- +#endif
-
- bool handle_irq(struct irq_desc *desc, struct pt_regs *regs)
- {
- diff -Nur linux-4.4.28.orig/arch/x86/kernel/kvm.c linux-4.4.28/arch/x86/kernel/kvm.c
- --- linux-4.4.28.orig/arch/x86/kernel/kvm.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/x86/kernel/kvm.c 2016-11-01 21:26:57.652269821 +0100
- @@ -36,6 +36,7 @@
- #include <linux/kprobes.h>
- #include <linux/debugfs.h>
- #include <linux/nmi.h>
- +#include <linux/swait.h>
- #include <asm/timer.h>
- #include <asm/cpu.h>
- #include <asm/traps.h>
- @@ -91,14 +92,14 @@
-
- struct kvm_task_sleep_node {
- struct hlist_node link;
- - wait_queue_head_t wq;
- + struct swait_queue_head wq;
- u32 token;
- int cpu;
- bool halted;
- };
-
- static struct kvm_task_sleep_head {
- - spinlock_t lock;
- + raw_spinlock_t lock;
- struct hlist_head list;
- } async_pf_sleepers[KVM_TASK_SLEEP_HASHSIZE];
-
- @@ -122,17 +123,17 @@
- u32 key = hash_32(token, KVM_TASK_SLEEP_HASHBITS);
- struct kvm_task_sleep_head *b = &async_pf_sleepers[key];
- struct kvm_task_sleep_node n, *e;
- - DEFINE_WAIT(wait);
- + DECLARE_SWAITQUEUE(wait);
-
- rcu_irq_enter();
-
- - spin_lock(&b->lock);
- + raw_spin_lock(&b->lock);
- e = _find_apf_task(b, token);
- if (e) {
- /* dummy entry exist -> wake up was delivered ahead of PF */
- hlist_del(&e->link);
- kfree(e);
- - spin_unlock(&b->lock);
- + raw_spin_unlock(&b->lock);
-
- rcu_irq_exit();
- return;
- @@ -141,13 +142,13 @@
- n.token = token;
- n.cpu = smp_processor_id();
- n.halted = is_idle_task(current) || preempt_count() > 1;
- - init_waitqueue_head(&n.wq);
- + init_swait_queue_head(&n.wq);
- hlist_add_head(&n.link, &b->list);
- - spin_unlock(&b->lock);
- + raw_spin_unlock(&b->lock);
-
- for (;;) {
- if (!n.halted)
- - prepare_to_wait(&n.wq, &wait, TASK_UNINTERRUPTIBLE);
- + prepare_to_swait(&n.wq, &wait, TASK_UNINTERRUPTIBLE);
- if (hlist_unhashed(&n.link))
- break;
-
- @@ -166,7 +167,7 @@
- }
- }
- if (!n.halted)
- - finish_wait(&n.wq, &wait);
- + finish_swait(&n.wq, &wait);
-
- rcu_irq_exit();
- return;
- @@ -178,8 +179,8 @@
- hlist_del_init(&n->link);
- if (n->halted)
- smp_send_reschedule(n->cpu);
- - else if (waitqueue_active(&n->wq))
- - wake_up(&n->wq);
- + else if (swait_active(&n->wq))
- + swake_up(&n->wq);
- }
-
- static void apf_task_wake_all(void)
- @@ -189,14 +190,14 @@
- for (i = 0; i < KVM_TASK_SLEEP_HASHSIZE; i++) {
- struct hlist_node *p, *next;
- struct kvm_task_sleep_head *b = &async_pf_sleepers[i];
- - spin_lock(&b->lock);
- + raw_spin_lock(&b->lock);
- hlist_for_each_safe(p, next, &b->list) {
- struct kvm_task_sleep_node *n =
- hlist_entry(p, typeof(*n), link);
- if (n->cpu == smp_processor_id())
- apf_task_wake_one(n);
- }
- - spin_unlock(&b->lock);
- + raw_spin_unlock(&b->lock);
- }
- }
-
- @@ -212,7 +213,7 @@
- }
-
- again:
- - spin_lock(&b->lock);
- + raw_spin_lock(&b->lock);
- n = _find_apf_task(b, token);
- if (!n) {
- /*
- @@ -225,17 +226,17 @@
- * Allocation failed! Busy wait while other cpu
- * handles async PF.
- */
- - spin_unlock(&b->lock);
- + raw_spin_unlock(&b->lock);
- cpu_relax();
- goto again;
- }
- n->token = token;
- n->cpu = smp_processor_id();
- - init_waitqueue_head(&n->wq);
- + init_swait_queue_head(&n->wq);
- hlist_add_head(&n->link, &b->list);
- } else
- apf_task_wake_one(n);
- - spin_unlock(&b->lock);
- + raw_spin_unlock(&b->lock);
- return;
- }
- EXPORT_SYMBOL_GPL(kvm_async_pf_task_wake);
- @@ -486,7 +487,7 @@
- paravirt_ops_setup();
- register_reboot_notifier(&kvm_pv_reboot_nb);
- for (i = 0; i < KVM_TASK_SLEEP_HASHSIZE; i++)
- - spin_lock_init(&async_pf_sleepers[i].lock);
- + raw_spin_lock_init(&async_pf_sleepers[i].lock);
- if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF))
- x86_init.irqs.trap_init = kvm_apf_trap_init;
-
- diff -Nur linux-4.4.28.orig/arch/x86/kernel/nmi.c linux-4.4.28/arch/x86/kernel/nmi.c
- --- linux-4.4.28.orig/arch/x86/kernel/nmi.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/x86/kernel/nmi.c 2016-11-01 21:26:57.660270336 +0100
- @@ -231,7 +231,7 @@
- #endif
-
- if (panic_on_unrecovered_nmi)
- - panic("NMI: Not continuing");
- + nmi_panic(regs, "NMI: Not continuing");
-
- pr_emerg("Dazed and confused, but trying to continue\n");
-
- @@ -255,8 +255,16 @@
- reason, smp_processor_id());
- show_regs(regs);
-
- - if (panic_on_io_nmi)
- - panic("NMI IOCK error: Not continuing");
- + if (panic_on_io_nmi) {
- + nmi_panic(regs, "NMI IOCK error: Not continuing");
- +
- + /*
- + * If we end up here, it means we have received an NMI while
- + * processing panic(). Simply return without delaying and
- + * re-enabling NMIs.
- + */
- + return;
- + }
-
- /* Re-enable the IOCK line, wait for a few seconds */
- reason = (reason & NMI_REASON_CLEAR_MASK) | NMI_REASON_CLEAR_IOCHK;
- @@ -297,7 +305,7 @@
-
- pr_emerg("Do you have a strange power saving mode enabled?\n");
- if (unknown_nmi_panic || panic_on_unrecovered_nmi)
- - panic("NMI: Not continuing");
- + nmi_panic(regs, "NMI: Not continuing");
-
- pr_emerg("Dazed and confused, but trying to continue\n");
- }
- diff -Nur linux-4.4.28.orig/arch/x86/kernel/process_32.c linux-4.4.28/arch/x86/kernel/process_32.c
- --- linux-4.4.28.orig/arch/x86/kernel/process_32.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/x86/kernel/process_32.c 2016-11-01 21:26:57.664270598 +0100
- @@ -35,6 +35,7 @@
- #include <linux/uaccess.h>
- #include <linux/io.h>
- #include <linux/kdebug.h>
- +#include <linux/highmem.h>
-
- #include <asm/pgtable.h>
- #include <asm/ldt.h>
- @@ -210,6 +211,35 @@
- }
- EXPORT_SYMBOL_GPL(start_thread);
-
- +#ifdef CONFIG_PREEMPT_RT_FULL
- +static void switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p)
- +{
- + int i;
- +
- + /*
- + * Clear @prev's kmap_atomic mappings
- + */
- + for (i = 0; i < prev_p->kmap_idx; i++) {
- + int idx = i + KM_TYPE_NR * smp_processor_id();
- + pte_t *ptep = kmap_pte - idx;
- +
- + kpte_clear_flush(ptep, __fix_to_virt(FIX_KMAP_BEGIN + idx));
- + }
- + /*
- + * Restore @next_p's kmap_atomic mappings
- + */
- + for (i = 0; i < next_p->kmap_idx; i++) {
- + int idx = i + KM_TYPE_NR * smp_processor_id();
- +
- + if (!pte_none(next_p->kmap_pte[i]))
- + set_pte(kmap_pte - idx, next_p->kmap_pte[i]);
- + }
- +}
- +#else
- +static inline void
- +switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p) { }
- +#endif
- +
-
- /*
- * switch_to(x,y) should switch tasks from x to y.
- @@ -286,6 +316,8 @@
- task_thread_info(next_p)->flags & _TIF_WORK_CTXSW_NEXT))
- __switch_to_xtra(prev_p, next_p, tss);
-
- + switch_kmaps(prev_p, next_p);
- +
- /*
- * Leave lazy mode, flushing any hypercalls made here.
- * This must be done before restoring TLS segments so
- diff -Nur linux-4.4.28.orig/arch/x86/kernel/reboot.c linux-4.4.28/arch/x86/kernel/reboot.c
- --- linux-4.4.28.orig/arch/x86/kernel/reboot.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/x86/kernel/reboot.c 2016-11-01 21:26:57.664270598 +0100
- @@ -726,6 +726,7 @@
- static nmi_shootdown_cb shootdown_callback;
-
- static atomic_t waiting_for_crash_ipi;
- +static int crash_ipi_issued;
-
- static int crash_nmi_callback(unsigned int val, struct pt_regs *regs)
- {
- @@ -788,6 +789,9 @@
-
- smp_send_nmi_allbutself();
-
- + /* Kick CPUs looping in NMI context. */
- + WRITE_ONCE(crash_ipi_issued, 1);
- +
- msecs = 1000; /* Wait at most a second for the other cpus to stop */
- while ((atomic_read(&waiting_for_crash_ipi) > 0) && msecs) {
- mdelay(1);
- @@ -796,6 +800,22 @@
-
- /* Leave the nmi callback set */
- }
- +
- +/* Override the weak function in kernel/panic.c */
- +void nmi_panic_self_stop(struct pt_regs *regs)
- +{
- + while (1) {
- + /*
- + * Wait for the crash dumping IPI to be issued, and then
- + * call its callback directly.
- + */
- + if (READ_ONCE(crash_ipi_issued))
- + crash_nmi_callback(0, regs); /* Don't return */
- +
- + cpu_relax();
- + }
- +}
- +
- #else /* !CONFIG_SMP */
- void nmi_shootdown_cpus(nmi_shootdown_cb callback)
- {
- diff -Nur linux-4.4.28.orig/arch/x86/kvm/lapic.c linux-4.4.28/arch/x86/kvm/lapic.c
- --- linux-4.4.28.orig/arch/x86/kvm/lapic.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/x86/kvm/lapic.c 2016-11-01 21:26:57.672271115 +0100
- @@ -1195,7 +1195,7 @@
- static void apic_timer_expired(struct kvm_lapic *apic)
- {
- struct kvm_vcpu *vcpu = apic->vcpu;
- - wait_queue_head_t *q = &vcpu->wq;
- + struct swait_queue_head *q = &vcpu->wq;
- struct kvm_timer *ktimer = &apic->lapic_timer;
-
- if (atomic_read(&apic->lapic_timer.pending))
- @@ -1204,8 +1204,8 @@
- atomic_inc(&apic->lapic_timer.pending);
- kvm_set_pending_timer(vcpu);
-
- - if (waitqueue_active(q))
- - wake_up_interruptible(q);
- + if (swait_active(q))
- + swake_up(q);
-
- if (apic_lvtt_tscdeadline(apic))
- ktimer->expired_tscdeadline = ktimer->tscdeadline;
- @@ -1801,6 +1801,7 @@
- hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC,
- HRTIMER_MODE_ABS);
- apic->lapic_timer.timer.function = apic_timer_fn;
- + apic->lapic_timer.timer.irqsafe = 1;
-
- /*
- * APIC is created enabled. This will prevent kvm_lapic_set_base from
- diff -Nur linux-4.4.28.orig/arch/x86/kvm/x86.c linux-4.4.28/arch/x86/kvm/x86.c
- --- linux-4.4.28.orig/arch/x86/kvm/x86.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/x86/kvm/x86.c 2016-11-01 21:26:57.732274981 +0100
- @@ -5792,6 +5792,13 @@
- goto out;
- }
-
- +#ifdef CONFIG_PREEMPT_RT_FULL
- + if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) {
- + printk(KERN_ERR "RT requires X86_FEATURE_CONSTANT_TSC\n");
- + return -EOPNOTSUPP;
- + }
- +#endif
- +
- r = kvm_mmu_module_init();
- if (r)
- goto out_free_percpu;
- diff -Nur linux-4.4.28.orig/arch/x86/mm/highmem_32.c linux-4.4.28/arch/x86/mm/highmem_32.c
- --- linux-4.4.28.orig/arch/x86/mm/highmem_32.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/x86/mm/highmem_32.c 2016-11-01 21:26:57.740275502 +0100
- @@ -32,10 +32,11 @@
- */
- void *kmap_atomic_prot(struct page *page, pgprot_t prot)
- {
- + pte_t pte = mk_pte(page, prot);
- unsigned long vaddr;
- int idx, type;
-
- - preempt_disable();
- + preempt_disable_nort();
- pagefault_disable();
-
- if (!PageHighMem(page))
- @@ -45,7 +46,10 @@
- idx = type + KM_TYPE_NR*smp_processor_id();
- vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
- BUG_ON(!pte_none(*(kmap_pte-idx)));
- - set_pte(kmap_pte-idx, mk_pte(page, prot));
- +#ifdef CONFIG_PREEMPT_RT_FULL
- + current->kmap_pte[type] = pte;
- +#endif
- + set_pte(kmap_pte-idx, pte);
- arch_flush_lazy_mmu_mode();
-
- return (void *)vaddr;
- @@ -88,6 +92,9 @@
- * is a bad idea also, in case the page changes cacheability
- * attributes or becomes a protected page in a hypervisor.
- */
- +#ifdef CONFIG_PREEMPT_RT_FULL
- + current->kmap_pte[type] = __pte(0);
- +#endif
- kpte_clear_flush(kmap_pte-idx, vaddr);
- kmap_atomic_idx_pop();
- arch_flush_lazy_mmu_mode();
- @@ -100,7 +107,7 @@
- #endif
-
- pagefault_enable();
- - preempt_enable();
- + preempt_enable_nort();
- }
- EXPORT_SYMBOL(__kunmap_atomic);
-
- diff -Nur linux-4.4.28.orig/arch/x86/mm/iomap_32.c linux-4.4.28/arch/x86/mm/iomap_32.c
- --- linux-4.4.28.orig/arch/x86/mm/iomap_32.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/x86/mm/iomap_32.c 2016-11-01 21:26:57.740275502 +0100
- @@ -56,6 +56,7 @@
-
- void *kmap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot)
- {
- + pte_t pte = pfn_pte(pfn, prot);
- unsigned long vaddr;
- int idx, type;
-
- @@ -65,7 +66,12 @@
- type = kmap_atomic_idx_push();
- idx = type + KM_TYPE_NR * smp_processor_id();
- vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
- - set_pte(kmap_pte - idx, pfn_pte(pfn, prot));
- + WARN_ON(!pte_none(*(kmap_pte - idx)));
- +
- +#ifdef CONFIG_PREEMPT_RT_FULL
- + current->kmap_pte[type] = pte;
- +#endif
- + set_pte(kmap_pte - idx, pte);
- arch_flush_lazy_mmu_mode();
-
- return (void *)vaddr;
- @@ -113,6 +119,9 @@
- * is a bad idea also, in case the page changes cacheability
- * attributes or becomes a protected page in a hypervisor.
- */
- +#ifdef CONFIG_PREEMPT_RT_FULL
- + current->kmap_pte[type] = __pte(0);
- +#endif
- kpte_clear_flush(kmap_pte-idx, vaddr);
- kmap_atomic_idx_pop();
- }
- diff -Nur linux-4.4.28.orig/arch/x86/platform/uv/tlb_uv.c linux-4.4.28/arch/x86/platform/uv/tlb_uv.c
- --- linux-4.4.28.orig/arch/x86/platform/uv/tlb_uv.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/x86/platform/uv/tlb_uv.c 2016-11-01 21:26:57.768277302 +0100
- @@ -714,9 +714,9 @@
-
- quiesce_local_uvhub(hmaster);
-
- - spin_lock(&hmaster->queue_lock);
- + raw_spin_lock(&hmaster->queue_lock);
- reset_with_ipi(&bau_desc->distribution, bcp);
- - spin_unlock(&hmaster->queue_lock);
- + raw_spin_unlock(&hmaster->queue_lock);
-
- end_uvhub_quiesce(hmaster);
-
- @@ -736,9 +736,9 @@
-
- quiesce_local_uvhub(hmaster);
-
- - spin_lock(&hmaster->queue_lock);
- + raw_spin_lock(&hmaster->queue_lock);
- reset_with_ipi(&bau_desc->distribution, bcp);
- - spin_unlock(&hmaster->queue_lock);
- + raw_spin_unlock(&hmaster->queue_lock);
-
- end_uvhub_quiesce(hmaster);
-
- @@ -759,7 +759,7 @@
- cycles_t tm1;
-
- hmaster = bcp->uvhub_master;
- - spin_lock(&hmaster->disable_lock);
- + raw_spin_lock(&hmaster->disable_lock);
- if (!bcp->baudisabled) {
- stat->s_bau_disabled++;
- tm1 = get_cycles();
- @@ -772,7 +772,7 @@
- }
- }
- }
- - spin_unlock(&hmaster->disable_lock);
- + raw_spin_unlock(&hmaster->disable_lock);
- }
-
- static void count_max_concurr(int stat, struct bau_control *bcp,
- @@ -835,7 +835,7 @@
- */
- static void uv1_throttle(struct bau_control *hmaster, struct ptc_stats *stat)
- {
- - spinlock_t *lock = &hmaster->uvhub_lock;
- + raw_spinlock_t *lock = &hmaster->uvhub_lock;
- atomic_t *v;
-
- v = &hmaster->active_descriptor_count;
- @@ -968,7 +968,7 @@
- struct bau_control *hmaster;
-
- hmaster = bcp->uvhub_master;
- - spin_lock(&hmaster->disable_lock);
- + raw_spin_lock(&hmaster->disable_lock);
- if (bcp->baudisabled && (get_cycles() >= bcp->set_bau_on_time)) {
- stat->s_bau_reenabled++;
- for_each_present_cpu(tcpu) {
- @@ -980,10 +980,10 @@
- tbcp->period_giveups = 0;
- }
- }
- - spin_unlock(&hmaster->disable_lock);
- + raw_spin_unlock(&hmaster->disable_lock);
- return 0;
- }
- - spin_unlock(&hmaster->disable_lock);
- + raw_spin_unlock(&hmaster->disable_lock);
- return -1;
- }
-
- @@ -1901,9 +1901,9 @@
- bcp->cong_reps = congested_reps;
- bcp->disabled_period = sec_2_cycles(disabled_period);
- bcp->giveup_limit = giveup_limit;
- - spin_lock_init(&bcp->queue_lock);
- - spin_lock_init(&bcp->uvhub_lock);
- - spin_lock_init(&bcp->disable_lock);
- + raw_spin_lock_init(&bcp->queue_lock);
- + raw_spin_lock_init(&bcp->uvhub_lock);
- + raw_spin_lock_init(&bcp->disable_lock);
- }
- }
-
- diff -Nur linux-4.4.28.orig/arch/x86/platform/uv/uv_time.c linux-4.4.28/arch/x86/platform/uv/uv_time.c
- --- linux-4.4.28.orig/arch/x86/platform/uv/uv_time.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/arch/x86/platform/uv/uv_time.c 2016-11-01 21:26:57.768277302 +0100
- @@ -57,7 +57,7 @@
-
- /* There is one of these allocated per node */
- struct uv_rtc_timer_head {
- - spinlock_t lock;
- + raw_spinlock_t lock;
- /* next cpu waiting for timer, local node relative: */
- int next_cpu;
- /* number of cpus on this node: */
- @@ -177,7 +177,7 @@
- uv_rtc_deallocate_timers();
- return -ENOMEM;
- }
- - spin_lock_init(&head->lock);
- + raw_spin_lock_init(&head->lock);
- head->ncpus = uv_blade_nr_possible_cpus(bid);
- head->next_cpu = -1;
- blade_info[bid] = head;
- @@ -231,7 +231,7 @@
- unsigned long flags;
- int next_cpu;
-
- - spin_lock_irqsave(&head->lock, flags);
- + raw_spin_lock_irqsave(&head->lock, flags);
-
- next_cpu = head->next_cpu;
- *t = expires;
- @@ -243,12 +243,12 @@
- if (uv_setup_intr(cpu, expires)) {
- *t = ULLONG_MAX;
- uv_rtc_find_next_timer(head, pnode);
- - spin_unlock_irqrestore(&head->lock, flags);
- + raw_spin_unlock_irqrestore(&head->lock, flags);
- return -ETIME;
- }
- }
-
- - spin_unlock_irqrestore(&head->lock, flags);
- + raw_spin_unlock_irqrestore(&head->lock, flags);
- return 0;
- }
-
- @@ -267,7 +267,7 @@
- unsigned long flags;
- int rc = 0;
-
- - spin_lock_irqsave(&head->lock, flags);
- + raw_spin_lock_irqsave(&head->lock, flags);
-
- if ((head->next_cpu == bcpu && uv_read_rtc(NULL) >= *t) || force)
- rc = 1;
- @@ -279,7 +279,7 @@
- uv_rtc_find_next_timer(head, pnode);
- }
-
- - spin_unlock_irqrestore(&head->lock, flags);
- + raw_spin_unlock_irqrestore(&head->lock, flags);
-
- return rc;
- }
- @@ -299,13 +299,18 @@
- static cycle_t uv_read_rtc(struct clocksource *cs)
- {
- unsigned long offset;
- + cycle_t cycles;
-
- + preempt_disable();
- if (uv_get_min_hub_revision_id() == 1)
- offset = 0;
- else
- offset = (uv_blade_processor_id() * L1_CACHE_BYTES) % PAGE_SIZE;
-
- - return (cycle_t)uv_read_local_mmr(UVH_RTC | offset);
- + cycles = (cycle_t)uv_read_local_mmr(UVH_RTC | offset);
- + preempt_enable();
- +
- + return cycles;
- }
-
- /*
- diff -Nur linux-4.4.28.orig/block/blk-core.c linux-4.4.28/block/blk-core.c
- --- linux-4.4.28.orig/block/blk-core.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/block/blk-core.c 2016-11-01 21:26:57.788278596 +0100
- @@ -125,6 +125,9 @@
-
- INIT_LIST_HEAD(&rq->queuelist);
- INIT_LIST_HEAD(&rq->timeout_list);
- +#ifdef CONFIG_PREEMPT_RT_FULL
- + INIT_WORK(&rq->work, __blk_mq_complete_request_remote_work);
- +#endif
- rq->cpu = -1;
- rq->q = q;
- rq->__sector = (sector_t) -1;
- @@ -233,7 +236,7 @@
- **/
- void blk_start_queue(struct request_queue *q)
- {
- - WARN_ON(!irqs_disabled());
- + WARN_ON_NONRT(!irqs_disabled());
-
- queue_flag_clear(QUEUE_FLAG_STOPPED, q);
- __blk_run_queue(q);
- @@ -659,7 +662,7 @@
- if (!gfpflags_allow_blocking(gfp))
- return -EBUSY;
-
- - ret = wait_event_interruptible(q->mq_freeze_wq,
- + ret = swait_event_interruptible(q->mq_freeze_wq,
- !atomic_read(&q->mq_freeze_depth) ||
- blk_queue_dying(q));
- if (blk_queue_dying(q))
- @@ -679,7 +682,7 @@
- struct request_queue *q =
- container_of(ref, struct request_queue, q_usage_counter);
-
- - wake_up_all(&q->mq_freeze_wq);
- + swake_up_all(&q->mq_freeze_wq);
- }
-
- struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
- @@ -741,7 +744,7 @@
- q->bypass_depth = 1;
- __set_bit(QUEUE_FLAG_BYPASS, &q->queue_flags);
-
- - init_waitqueue_head(&q->mq_freeze_wq);
- + init_swait_queue_head(&q->mq_freeze_wq);
-
- /*
- * Init percpu_ref in atomic mode so that it's faster to shutdown.
- @@ -3200,7 +3203,7 @@
- blk_run_queue_async(q);
- else
- __blk_run_queue(q);
- - spin_unlock(q->queue_lock);
- + spin_unlock_irq(q->queue_lock);
- }
-
- static void flush_plug_callbacks(struct blk_plug *plug, bool from_schedule)
- @@ -3248,7 +3251,6 @@
- void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
- {
- struct request_queue *q;
- - unsigned long flags;
- struct request *rq;
- LIST_HEAD(list);
- unsigned int depth;
- @@ -3268,11 +3270,6 @@
- q = NULL;
- depth = 0;
-
- - /*
- - * Save and disable interrupts here, to avoid doing it for every
- - * queue lock we have to take.
- - */
- - local_irq_save(flags);
- while (!list_empty(&list)) {
- rq = list_entry_rq(list.next);
- list_del_init(&rq->queuelist);
- @@ -3285,7 +3282,7 @@
- queue_unplugged(q, depth, from_schedule);
- q = rq->q;
- depth = 0;
- - spin_lock(q->queue_lock);
- + spin_lock_irq(q->queue_lock);
- }
-
- /*
- @@ -3312,8 +3309,6 @@
- */
- if (q)
- queue_unplugged(q, depth, from_schedule);
- -
- - local_irq_restore(flags);
- }
-
- void blk_finish_plug(struct blk_plug *plug)
- diff -Nur linux-4.4.28.orig/block/blk-ioc.c linux-4.4.28/block/blk-ioc.c
- --- linux-4.4.28.orig/block/blk-ioc.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/block/blk-ioc.c 2016-11-01 21:26:57.800279369 +0100
- @@ -7,6 +7,7 @@
- #include <linux/bio.h>
- #include <linux/blkdev.h>
- #include <linux/slab.h>
- +#include <linux/delay.h>
-
- #include "blk.h"
-
- @@ -109,7 +110,7 @@
- spin_unlock(q->queue_lock);
- } else {
- spin_unlock_irqrestore(&ioc->lock, flags);
- - cpu_relax();
- + cpu_chill();
- spin_lock_irqsave_nested(&ioc->lock, flags, 1);
- }
- }
- @@ -187,7 +188,7 @@
- spin_unlock(icq->q->queue_lock);
- } else {
- spin_unlock_irqrestore(&ioc->lock, flags);
- - cpu_relax();
- + cpu_chill();
- goto retry;
- }
- }
- diff -Nur linux-4.4.28.orig/block/blk-iopoll.c linux-4.4.28/block/blk-iopoll.c
- --- linux-4.4.28.orig/block/blk-iopoll.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/block/blk-iopoll.c 2016-11-01 21:26:57.800279369 +0100
- @@ -35,6 +35,7 @@
- list_add_tail(&iop->list, this_cpu_ptr(&blk_cpu_iopoll));
- __raise_softirq_irqoff(BLOCK_IOPOLL_SOFTIRQ);
- local_irq_restore(flags);
- + preempt_check_resched_rt();
- }
- EXPORT_SYMBOL(blk_iopoll_sched);
-
- @@ -132,6 +133,7 @@
- __raise_softirq_irqoff(BLOCK_IOPOLL_SOFTIRQ);
-
- local_irq_enable();
- + preempt_check_resched_rt();
- }
-
- /**
- @@ -201,6 +203,7 @@
- this_cpu_ptr(&blk_cpu_iopoll));
- __raise_softirq_irqoff(BLOCK_IOPOLL_SOFTIRQ);
- local_irq_enable();
- + preempt_check_resched_rt();
- }
-
- return NOTIFY_OK;
- diff -Nur linux-4.4.28.orig/block/blk-mq.c linux-4.4.28/block/blk-mq.c
- --- linux-4.4.28.orig/block/blk-mq.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/block/blk-mq.c 2016-11-01 21:26:57.812280143 +0100
- @@ -92,7 +92,7 @@
-
- static void blk_mq_freeze_queue_wait(struct request_queue *q)
- {
- - wait_event(q->mq_freeze_wq, percpu_ref_is_zero(&q->q_usage_counter));
- + swait_event(q->mq_freeze_wq, percpu_ref_is_zero(&q->q_usage_counter));
- }
-
- /*
- @@ -130,7 +130,7 @@
- WARN_ON_ONCE(freeze_depth < 0);
- if (!freeze_depth) {
- percpu_ref_reinit(&q->q_usage_counter);
- - wake_up_all(&q->mq_freeze_wq);
- + swake_up_all(&q->mq_freeze_wq);
- }
- }
- EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue);
- @@ -149,7 +149,7 @@
- * dying, we need to ensure that processes currently waiting on
- * the queue are notified as well.
- */
- - wake_up_all(&q->mq_freeze_wq);
- + swake_up_all(&q->mq_freeze_wq);
- }
-
- bool blk_mq_can_queue(struct blk_mq_hw_ctx *hctx)
- @@ -196,6 +196,9 @@
- rq->resid_len = 0;
- rq->sense = NULL;
-
- +#ifdef CONFIG_PREEMPT_RT_FULL
- + INIT_WORK(&rq->work, __blk_mq_complete_request_remote_work);
- +#endif
- INIT_LIST_HEAD(&rq->timeout_list);
- rq->timeout = 0;
-
- @@ -325,6 +328,17 @@
- }
- EXPORT_SYMBOL(blk_mq_end_request);
-
- +#ifdef CONFIG_PREEMPT_RT_FULL
- +
- +void __blk_mq_complete_request_remote_work(struct work_struct *work)
- +{
- + struct request *rq = container_of(work, struct request, work);
- +
- + rq->q->softirq_done_fn(rq);
- +}
- +
- +#else
- +
- static void __blk_mq_complete_request_remote(void *data)
- {
- struct request *rq = data;
- @@ -332,6 +346,8 @@
- rq->q->softirq_done_fn(rq);
- }
-
- +#endif
- +
- static void blk_mq_ipi_complete_request(struct request *rq)
- {
- struct blk_mq_ctx *ctx = rq->mq_ctx;
- @@ -343,19 +359,23 @@
- return;
- }
-
- - cpu = get_cpu();
- + cpu = get_cpu_light();
- if (!test_bit(QUEUE_FLAG_SAME_FORCE, &rq->q->queue_flags))
- shared = cpus_share_cache(cpu, ctx->cpu);
-
- if (cpu != ctx->cpu && !shared && cpu_online(ctx->cpu)) {
- +#ifdef CONFIG_PREEMPT_RT_FULL
- + schedule_work_on(ctx->cpu, &rq->work);
- +#else
- rq->csd.func = __blk_mq_complete_request_remote;
- rq->csd.info = rq;
- rq->csd.flags = 0;
- smp_call_function_single_async(ctx->cpu, &rq->csd);
- +#endif
- } else {
- rq->q->softirq_done_fn(rq);
- }
- - put_cpu();
- + put_cpu_light();
- }
-
- static void __blk_mq_complete_request(struct request *rq)
- @@ -864,14 +884,14 @@
- return;
-
- if (!async) {
- - int cpu = get_cpu();
- + int cpu = get_cpu_light();
- if (cpumask_test_cpu(cpu, hctx->cpumask)) {
- __blk_mq_run_hw_queue(hctx);
- - put_cpu();
- + put_cpu_light();
- return;
- }
-
- - put_cpu();
- + put_cpu_light();
- }
-
- kblockd_schedule_delayed_work_on(blk_mq_hctx_next_cpu(hctx),
- @@ -1619,7 +1639,7 @@
- {
- struct blk_mq_hw_ctx *hctx = data;
-
- - if (action == CPU_DEAD || action == CPU_DEAD_FROZEN)
- + if (action == CPU_POST_DEAD)
- return blk_mq_hctx_cpu_offline(hctx, cpu);
-
- /*
- diff -Nur linux-4.4.28.orig/block/blk-mq-cpu.c linux-4.4.28/block/blk-mq-cpu.c
- --- linux-4.4.28.orig/block/blk-mq-cpu.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/block/blk-mq-cpu.c 2016-11-01 21:26:57.800279369 +0100
- @@ -16,7 +16,7 @@
- #include "blk-mq.h"
-
- static LIST_HEAD(blk_mq_cpu_notify_list);
- -static DEFINE_RAW_SPINLOCK(blk_mq_cpu_notify_lock);
- +static DEFINE_SPINLOCK(blk_mq_cpu_notify_lock);
-
- static int blk_mq_main_cpu_notify(struct notifier_block *self,
- unsigned long action, void *hcpu)
- @@ -25,7 +25,10 @@
- struct blk_mq_cpu_notifier *notify;
- int ret = NOTIFY_OK;
-
- - raw_spin_lock(&blk_mq_cpu_notify_lock);
- + if (action != CPU_POST_DEAD)
- + return NOTIFY_OK;
- +
- + spin_lock(&blk_mq_cpu_notify_lock);
-
- list_for_each_entry(notify, &blk_mq_cpu_notify_list, list) {
- ret = notify->notify(notify->data, action, cpu);
- @@ -33,7 +36,7 @@
- break;
- }
-
- - raw_spin_unlock(&blk_mq_cpu_notify_lock);
- + spin_unlock(&blk_mq_cpu_notify_lock);
- return ret;
- }
-
- @@ -41,16 +44,16 @@
- {
- BUG_ON(!notifier->notify);
-
- - raw_spin_lock(&blk_mq_cpu_notify_lock);
- + spin_lock(&blk_mq_cpu_notify_lock);
- list_add_tail(¬ifier->list, &blk_mq_cpu_notify_list);
- - raw_spin_unlock(&blk_mq_cpu_notify_lock);
- + spin_unlock(&blk_mq_cpu_notify_lock);
- }
-
- void blk_mq_unregister_cpu_notifier(struct blk_mq_cpu_notifier *notifier)
- {
- - raw_spin_lock(&blk_mq_cpu_notify_lock);
- + spin_lock(&blk_mq_cpu_notify_lock);
- list_del(¬ifier->list);
- - raw_spin_unlock(&blk_mq_cpu_notify_lock);
- + spin_unlock(&blk_mq_cpu_notify_lock);
- }
-
- void blk_mq_init_cpu_notifier(struct blk_mq_cpu_notifier *notifier,
- diff -Nur linux-4.4.28.orig/block/blk-mq.h linux-4.4.28/block/blk-mq.h
- --- linux-4.4.28.orig/block/blk-mq.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/block/blk-mq.h 2016-11-01 21:26:57.812280143 +0100
- @@ -74,7 +74,10 @@
- static inline struct blk_mq_ctx *__blk_mq_get_ctx(struct request_queue *q,
- unsigned int cpu)
- {
- - return per_cpu_ptr(q->queue_ctx, cpu);
- + struct blk_mq_ctx *ctx;
- +
- + ctx = per_cpu_ptr(q->queue_ctx, cpu);
- + return ctx;
- }
-
- /*
- @@ -85,12 +88,12 @@
- */
- static inline struct blk_mq_ctx *blk_mq_get_ctx(struct request_queue *q)
- {
- - return __blk_mq_get_ctx(q, get_cpu());
- + return __blk_mq_get_ctx(q, get_cpu_light());
- }
-
- static inline void blk_mq_put_ctx(struct blk_mq_ctx *ctx)
- {
- - put_cpu();
- + put_cpu_light();
- }
-
- struct blk_mq_alloc_data {
- diff -Nur linux-4.4.28.orig/block/blk-softirq.c linux-4.4.28/block/blk-softirq.c
- --- linux-4.4.28.orig/block/blk-softirq.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/block/blk-softirq.c 2016-11-01 21:26:57.812280143 +0100
- @@ -51,6 +51,7 @@
- raise_softirq_irqoff(BLOCK_SOFTIRQ);
-
- local_irq_restore(flags);
- + preempt_check_resched_rt();
- }
-
- /*
- @@ -93,6 +94,7 @@
- this_cpu_ptr(&blk_cpu_done));
- raise_softirq_irqoff(BLOCK_SOFTIRQ);
- local_irq_enable();
- + preempt_check_resched_rt();
- }
-
- return NOTIFY_OK;
- @@ -150,6 +152,7 @@
- goto do_local;
-
- local_irq_restore(flags);
- + preempt_check_resched_rt();
- }
-
- /**
- diff -Nur linux-4.4.28.orig/block/bounce.c linux-4.4.28/block/bounce.c
- --- linux-4.4.28.orig/block/bounce.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/block/bounce.c 2016-11-01 21:26:57.812280143 +0100
- @@ -55,11 +55,11 @@
- unsigned long flags;
- unsigned char *vto;
-
- - local_irq_save(flags);
- + local_irq_save_nort(flags);
- vto = kmap_atomic(to->bv_page);
- memcpy(vto + to->bv_offset, vfrom, to->bv_len);
- kunmap_atomic(vto);
- - local_irq_restore(flags);
- + local_irq_restore_nort(flags);
- }
-
- #else /* CONFIG_HIGHMEM */
- diff -Nur linux-4.4.28.orig/crypto/algapi.c linux-4.4.28/crypto/algapi.c
- --- linux-4.4.28.orig/crypto/algapi.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/crypto/algapi.c 2016-11-01 21:26:57.824280917 +0100
- @@ -719,13 +719,13 @@
-
- int crypto_register_notifier(struct notifier_block *nb)
- {
- - return blocking_notifier_chain_register(&crypto_chain, nb);
- + return srcu_notifier_chain_register(&crypto_chain, nb);
- }
- EXPORT_SYMBOL_GPL(crypto_register_notifier);
-
- int crypto_unregister_notifier(struct notifier_block *nb)
- {
- - return blocking_notifier_chain_unregister(&crypto_chain, nb);
- + return srcu_notifier_chain_unregister(&crypto_chain, nb);
- }
- EXPORT_SYMBOL_GPL(crypto_unregister_notifier);
-
- diff -Nur linux-4.4.28.orig/crypto/api.c linux-4.4.28/crypto/api.c
- --- linux-4.4.28.orig/crypto/api.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/crypto/api.c 2016-11-01 21:26:57.828281169 +0100
- @@ -31,7 +31,7 @@
- DECLARE_RWSEM(crypto_alg_sem);
- EXPORT_SYMBOL_GPL(crypto_alg_sem);
-
- -BLOCKING_NOTIFIER_HEAD(crypto_chain);
- +SRCU_NOTIFIER_HEAD(crypto_chain);
- EXPORT_SYMBOL_GPL(crypto_chain);
-
- static struct crypto_alg *crypto_larval_wait(struct crypto_alg *alg);
- @@ -236,10 +236,10 @@
- {
- int ok;
-
- - ok = blocking_notifier_call_chain(&crypto_chain, val, v);
- + ok = srcu_notifier_call_chain(&crypto_chain, val, v);
- if (ok == NOTIFY_DONE) {
- request_module("cryptomgr");
- - ok = blocking_notifier_call_chain(&crypto_chain, val, v);
- + ok = srcu_notifier_call_chain(&crypto_chain, val, v);
- }
-
- return ok;
- diff -Nur linux-4.4.28.orig/crypto/internal.h linux-4.4.28/crypto/internal.h
- --- linux-4.4.28.orig/crypto/internal.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/crypto/internal.h 2016-11-01 21:26:57.832281426 +0100
- @@ -47,7 +47,7 @@
-
- extern struct list_head crypto_alg_list;
- extern struct rw_semaphore crypto_alg_sem;
- -extern struct blocking_notifier_head crypto_chain;
- +extern struct srcu_notifier_head crypto_chain;
-
- #ifdef CONFIG_PROC_FS
- void __init crypto_init_proc(void);
- @@ -143,7 +143,7 @@
-
- static inline void crypto_notify(unsigned long val, void *v)
- {
- - blocking_notifier_call_chain(&crypto_chain, val, v);
- + srcu_notifier_call_chain(&crypto_chain, val, v);
- }
-
- #endif /* _CRYPTO_INTERNAL_H */
- diff -Nur linux-4.4.28.orig/Documentation/hwlat_detector.txt linux-4.4.28/Documentation/hwlat_detector.txt
- --- linux-4.4.28.orig/Documentation/hwlat_detector.txt 1970-01-01 01:00:00.000000000 +0100
- +++ linux-4.4.28/Documentation/hwlat_detector.txt 2016-11-01 21:26:56.600202005 +0100
- @@ -0,0 +1,64 @@
- +Introduction:
- +-------------
- +
- +The module hwlat_detector is a special purpose kernel module that is used to
- +detect large system latencies induced by the behavior of certain underlying
- +hardware or firmware, independent of Linux itself. The code was developed
- +originally to detect SMIs (System Management Interrupts) on x86 systems,
- +however there is nothing x86 specific about this patchset. It was
- +originally written for use by the "RT" patch since the Real Time
- +kernel is highly latency sensitive.
- +
- +SMIs are usually not serviced by the Linux kernel, which typically does not
- +even know that they are occuring. SMIs are instead are set up by BIOS code
- +and are serviced by BIOS code, usually for "critical" events such as
- +management of thermal sensors and fans. Sometimes though, SMIs are used for
- +other tasks and those tasks can spend an inordinate amount of time in the
- +handler (sometimes measured in milliseconds). Obviously this is a problem if
- +you are trying to keep event service latencies down in the microsecond range.
- +
- +The hardware latency detector works by hogging all of the cpus for configurable
- +amounts of time (by calling stop_machine()), polling the CPU Time Stamp Counter
- +for some period, then looking for gaps in the TSC data. Any gap indicates a
- +time when the polling was interrupted and since the machine is stopped and
- +interrupts turned off the only thing that could do that would be an SMI.
- +
- +Note that the SMI detector should *NEVER* be used in a production environment.
- +It is intended to be run manually to determine if the hardware platform has a
- +problem with long system firmware service routines.
- +
- +Usage:
- +------
- +
- +Loading the module hwlat_detector passing the parameter "enabled=1" (or by
- +setting the "enable" entry in "hwlat_detector" debugfs toggled on) is the only
- +step required to start the hwlat_detector. It is possible to redefine the
- +threshold in microseconds (us) above which latency spikes will be taken
- +into account (parameter "threshold=").
- +
- +Example:
- +
- + # modprobe hwlat_detector enabled=1 threshold=100
- +
- +After the module is loaded, it creates a directory named "hwlat_detector" under
- +the debugfs mountpoint, "/debug/hwlat_detector" for this text. It is necessary
- +to have debugfs mounted, which might be on /sys/debug on your system.
- +
- +The /debug/hwlat_detector interface contains the following files:
- +
- +count - number of latency spikes observed since last reset
- +enable - a global enable/disable toggle (0/1), resets count
- +max - maximum hardware latency actually observed (usecs)
- +sample - a pipe from which to read current raw sample data
- + in the format <timestamp> <latency observed usecs>
- + (can be opened O_NONBLOCK for a single sample)
- +threshold - minimum latency value to be considered (usecs)
- +width - time period to sample with CPUs held (usecs)
- + must be less than the total window size (enforced)
- +window - total period of sampling, width being inside (usecs)
- +
- +By default we will set width to 500,000 and window to 1,000,000, meaning that
- +we will sample every 1,000,000 usecs (1s) for 500,000 usecs (0.5s). If we
- +observe any latencies that exceed the threshold (initially 100 usecs),
- +then we write to a global sample ring buffer of 8K samples, which is
- +consumed by reading from the "sample" (pipe) debugfs file interface.
- diff -Nur linux-4.4.28.orig/Documentation/kernel-parameters.txt linux-4.4.28/Documentation/kernel-parameters.txt
- --- linux-4.4.28.orig/Documentation/kernel-parameters.txt 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/Documentation/kernel-parameters.txt 2016-11-01 21:26:56.640204584 +0100
- @@ -1636,6 +1636,15 @@
- ip= [IP_PNP]
- See Documentation/filesystems/nfs/nfsroot.txt.
-
- + irqaffinity= [SMP] Set the default irq affinity mask
- + Format:
- + <cpu number>,...,<cpu number>
- + or
- + <cpu number>-<cpu number>
- + (must be a positive range in ascending order)
- + or a mixture
- + <cpu number>,...,<cpu number>-<cpu number>
- +
- irqfixup [HW]
- When an interrupt is not handled search all handlers
- for it. Intended to get systems with badly broken
- diff -Nur linux-4.4.28.orig/Documentation/sysrq.txt linux-4.4.28/Documentation/sysrq.txt
- --- linux-4.4.28.orig/Documentation/sysrq.txt 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/Documentation/sysrq.txt 2016-11-01 21:26:56.652205360 +0100
- @@ -59,10 +59,17 @@
- On other - If you know of the key combos for other architectures, please
- let me know so I can add them to this section.
-
- -On all - write a character to /proc/sysrq-trigger. e.g.:
- -
- +On all - write a character to /proc/sysrq-trigger, e.g.:
- echo t > /proc/sysrq-trigger
-
- +On all - Enable network SysRq by writing a cookie to icmp_echo_sysrq, e.g.
- + echo 0x01020304 >/proc/sys/net/ipv4/icmp_echo_sysrq
- + Send an ICMP echo request with this pattern plus the particular
- + SysRq command key. Example:
- + # ping -c1 -s57 -p0102030468
- + will trigger the SysRq-H (help) command.
- +
- +
- * What are the 'command' keys?
- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- 'b' - Will immediately reboot the system without syncing or unmounting
- diff -Nur linux-4.4.28.orig/Documentation/trace/histograms.txt linux-4.4.28/Documentation/trace/histograms.txt
- --- linux-4.4.28.orig/Documentation/trace/histograms.txt 1970-01-01 01:00:00.000000000 +0100
- +++ linux-4.4.28/Documentation/trace/histograms.txt 2016-11-01 21:26:56.672206655 +0100
- @@ -0,0 +1,186 @@
- + Using the Linux Kernel Latency Histograms
- +
- +
- +This document gives a short explanation how to enable, configure and use
- +latency histograms. Latency histograms are primarily relevant in the
- +context of real-time enabled kernels (CONFIG_PREEMPT/CONFIG_PREEMPT_RT)
- +and are used in the quality management of the Linux real-time
- +capabilities.
- +
- +
- +* Purpose of latency histograms
- +
- +A latency histogram continuously accumulates the frequencies of latency
- +data. There are two types of histograms
- +- potential sources of latencies
- +- effective latencies
- +
- +
- +* Potential sources of latencies
- +
- +Potential sources of latencies are code segments where interrupts,
- +preemption or both are disabled (aka critical sections). To create
- +histograms of potential sources of latency, the kernel stores the time
- +stamp at the start of a critical section, determines the time elapsed
- +when the end of the section is reached, and increments the frequency
- +counter of that latency value - irrespective of whether any concurrently
- +running process is affected by latency or not.
- +- Configuration items (in the Kernel hacking/Tracers submenu)
- + CONFIG_INTERRUPT_OFF_LATENCY
- + CONFIG_PREEMPT_OFF_LATENCY
- +
- +
- +* Effective latencies
- +
- +Effective latencies are actually occuring during wakeup of a process. To
- +determine effective latencies, the kernel stores the time stamp when a
- +process is scheduled to be woken up, and determines the duration of the
- +wakeup time shortly before control is passed over to this process. Note
- +that the apparent latency in user space may be somewhat longer, since the
- +process may be interrupted after control is passed over to it but before
- +the execution in user space takes place. Simply measuring the interval
- +between enqueuing and wakeup may also not appropriate in cases when a
- +process is scheduled as a result of a timer expiration. The timer may have
- +missed its deadline, e.g. due to disabled interrupts, but this latency
- +would not be registered. Therefore, the offsets of missed timers are
- +recorded in a separate histogram. If both wakeup latency and missed timer
- +offsets are configured and enabled, a third histogram may be enabled that
- +records the overall latency as a sum of the timer latency, if any, and the
- +wakeup latency. This histogram is called "timerandwakeup".
- +- Configuration items (in the Kernel hacking/Tracers submenu)
- + CONFIG_WAKEUP_LATENCY
- + CONFIG_MISSED_TIMER_OFSETS
- +
- +
- +* Usage
- +
- +The interface to the administration of the latency histograms is located
- +in the debugfs file system. To mount it, either enter
- +
- +mount -t sysfs nodev /sys
- +mount -t debugfs nodev /sys/kernel/debug
- +
- +from shell command line level, or add
- +
- +nodev /sys sysfs defaults 0 0
- +nodev /sys/kernel/debug debugfs defaults 0 0
- +
- +to the file /etc/fstab. All latency histogram related files are then
- +available in the directory /sys/kernel/debug/tracing/latency_hist. A
- +particular histogram type is enabled by writing non-zero to the related
- +variable in the /sys/kernel/debug/tracing/latency_hist/enable directory.
- +Select "preemptirqsoff" for the histograms of potential sources of
- +latencies and "wakeup" for histograms of effective latencies etc. The
- +histogram data - one per CPU - are available in the files
- +
- +/sys/kernel/debug/tracing/latency_hist/preemptoff/CPUx
- +/sys/kernel/debug/tracing/latency_hist/irqsoff/CPUx
- +/sys/kernel/debug/tracing/latency_hist/preemptirqsoff/CPUx
- +/sys/kernel/debug/tracing/latency_hist/wakeup/CPUx
- +/sys/kernel/debug/tracing/latency_hist/wakeup/sharedprio/CPUx
- +/sys/kernel/debug/tracing/latency_hist/missed_timer_offsets/CPUx
- +/sys/kernel/debug/tracing/latency_hist/timerandwakeup/CPUx
- +
- +The histograms are reset by writing non-zero to the file "reset" in a
- +particular latency directory. To reset all latency data, use
- +
- +#!/bin/sh
- +
- +TRACINGDIR=/sys/kernel/debug/tracing
- +HISTDIR=$TRACINGDIR/latency_hist
- +
- +if test -d $HISTDIR
- +then
- + cd $HISTDIR
- + for i in `find . | grep /reset$`
- + do
- + echo 1 >$i
- + done
- +fi
- +
- +
- +* Data format
- +
- +Latency data are stored with a resolution of one microsecond. The
- +maximum latency is 10,240 microseconds. The data are only valid, if the
- +overflow register is empty. Every output line contains the latency in
- +microseconds in the first row and the number of samples in the second
- +row. To display only lines with a positive latency count, use, for
- +example,
- +
- +grep -v " 0$" /sys/kernel/debug/tracing/latency_hist/preemptoff/CPU0
- +
- +#Minimum latency: 0 microseconds.
- +#Average latency: 0 microseconds.
- +#Maximum latency: 25 microseconds.
- +#Total samples: 3104770694
- +#There are 0 samples greater or equal than 10240 microseconds
- +#usecs samples
- + 0 2984486876
- + 1 49843506
- + 2 58219047
- + 3 5348126
- + 4 2187960
- + 5 3388262
- + 6 959289
- + 7 208294
- + 8 40420
- + 9 4485
- + 10 14918
- + 11 18340
- + 12 25052
- + 13 19455
- + 14 5602
- + 15 969
- + 16 47
- + 17 18
- + 18 14
- + 19 1
- + 20 3
- + 21 2
- + 22 5
- + 23 2
- + 25 1
- +
- +
- +* Wakeup latency of a selected process
- +
- +To only collect wakeup latency data of a particular process, write the
- +PID of the requested process to
- +
- +/sys/kernel/debug/tracing/latency_hist/wakeup/pid
- +
- +PIDs are not considered, if this variable is set to 0.
- +
- +
- +* Details of the process with the highest wakeup latency so far
- +
- +Selected data of the process that suffered from the highest wakeup
- +latency that occurred in a particular CPU are available in the file
- +
- +/sys/kernel/debug/tracing/latency_hist/wakeup/max_latency-CPUx.
- +
- +In addition, other relevant system data at the time when the
- +latency occurred are given.
- +
- +The format of the data is (all in one line):
- +<PID> <Priority> <Latency> (<Timeroffset>) <Command> \
- +<- <PID> <Priority> <Command> <Timestamp>
- +
- +The value of <Timeroffset> is only relevant in the combined timer
- +and wakeup latency recording. In the wakeup recording, it is
- +always 0, in the missed_timer_offsets recording, it is the same
- +as <Latency>.
- +
- +When retrospectively searching for the origin of a latency and
- +tracing was not enabled, it may be helpful to know the name and
- +some basic data of the task that (finally) was switching to the
- +late real-tlme task. In addition to the victim's data, also the
- +data of the possible culprit are therefore displayed after the
- +"<-" symbol.
- +
- +Finally, the timestamp of the time when the latency occurred
- +in <seconds>.<microseconds> after the most recent system boot
- +is provided.
- +
- +These data are also reset when the wakeup histogram is reset.
- diff -Nur linux-4.4.28.orig/drivers/acpi/acpica/acglobal.h linux-4.4.28/drivers/acpi/acpica/acglobal.h
- --- linux-4.4.28.orig/drivers/acpi/acpica/acglobal.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/acpi/acpica/acglobal.h 2016-11-01 21:26:57.844282199 +0100
- @@ -116,7 +116,7 @@
- * interrupt level
- */
- ACPI_GLOBAL(acpi_spinlock, acpi_gbl_gpe_lock); /* For GPE data structs and registers */
- -ACPI_GLOBAL(acpi_spinlock, acpi_gbl_hardware_lock); /* For ACPI H/W except GPE registers */
- +ACPI_GLOBAL(acpi_raw_spinlock, acpi_gbl_hardware_lock); /* For ACPI H/W except GPE registers */
- ACPI_GLOBAL(acpi_spinlock, acpi_gbl_reference_count_lock);
-
- /* Mutex for _OSI support */
- diff -Nur linux-4.4.28.orig/drivers/acpi/acpica/hwregs.c linux-4.4.28/drivers/acpi/acpica/hwregs.c
- --- linux-4.4.28.orig/drivers/acpi/acpica/hwregs.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/acpi/acpica/hwregs.c 2016-11-01 21:26:57.852282717 +0100
- @@ -269,14 +269,14 @@
- ACPI_BITMASK_ALL_FIXED_STATUS,
- ACPI_FORMAT_UINT64(acpi_gbl_xpm1a_status.address)));
-
- - lock_flags = acpi_os_acquire_lock(acpi_gbl_hardware_lock);
- + raw_spin_lock_irqsave(acpi_gbl_hardware_lock, lock_flags);
-
- /* Clear the fixed events in PM1 A/B */
-
- status = acpi_hw_register_write(ACPI_REGISTER_PM1_STATUS,
- ACPI_BITMASK_ALL_FIXED_STATUS);
-
- - acpi_os_release_lock(acpi_gbl_hardware_lock, lock_flags);
- + raw_spin_unlock_irqrestore(acpi_gbl_hardware_lock, lock_flags);
-
- if (ACPI_FAILURE(status)) {
- goto exit;
- diff -Nur linux-4.4.28.orig/drivers/acpi/acpica/hwxface.c linux-4.4.28/drivers/acpi/acpica/hwxface.c
- --- linux-4.4.28.orig/drivers/acpi/acpica/hwxface.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/acpi/acpica/hwxface.c 2016-11-01 21:26:57.852282717 +0100
- @@ -374,7 +374,7 @@
- return_ACPI_STATUS(AE_BAD_PARAMETER);
- }
-
- - lock_flags = acpi_os_acquire_lock(acpi_gbl_hardware_lock);
- + raw_spin_lock_irqsave(acpi_gbl_hardware_lock, lock_flags);
-
- /*
- * At this point, we know that the parent register is one of the
- @@ -435,7 +435,7 @@
-
- unlock_and_exit:
-
- - acpi_os_release_lock(acpi_gbl_hardware_lock, lock_flags);
- + raw_spin_unlock_irqrestore(acpi_gbl_hardware_lock, lock_flags);
- return_ACPI_STATUS(status);
- }
-
- diff -Nur linux-4.4.28.orig/drivers/acpi/acpica/utmutex.c linux-4.4.28/drivers/acpi/acpica/utmutex.c
- --- linux-4.4.28.orig/drivers/acpi/acpica/utmutex.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/acpi/acpica/utmutex.c 2016-11-01 21:26:57.864283490 +0100
- @@ -88,7 +88,7 @@
- return_ACPI_STATUS (status);
- }
-
- - status = acpi_os_create_lock (&acpi_gbl_hardware_lock);
- + status = acpi_os_create_raw_lock (&acpi_gbl_hardware_lock);
- if (ACPI_FAILURE (status)) {
- return_ACPI_STATUS (status);
- }
- @@ -156,7 +156,7 @@
- /* Delete the spinlocks */
-
- acpi_os_delete_lock(acpi_gbl_gpe_lock);
- - acpi_os_delete_lock(acpi_gbl_hardware_lock);
- + acpi_os_delete_raw_lock(acpi_gbl_hardware_lock);
- acpi_os_delete_lock(acpi_gbl_reference_count_lock);
-
- /* Delete the reader/writer lock */
- diff -Nur linux-4.4.28.orig/drivers/ata/libata-sff.c linux-4.4.28/drivers/ata/libata-sff.c
- --- linux-4.4.28.orig/drivers/ata/libata-sff.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/ata/libata-sff.c 2016-11-01 21:26:57.884284784 +0100
- @@ -678,9 +678,9 @@
- unsigned long flags;
- unsigned int consumed;
-
- - local_irq_save(flags);
- + local_irq_save_nort(flags);
- consumed = ata_sff_data_xfer32(dev, buf, buflen, rw);
- - local_irq_restore(flags);
- + local_irq_restore_nort(flags);
-
- return consumed;
- }
- @@ -719,7 +719,7 @@
- unsigned long flags;
-
- /* FIXME: use a bounce buffer */
- - local_irq_save(flags);
- + local_irq_save_nort(flags);
- buf = kmap_atomic(page);
-
- /* do the actual data transfer */
- @@ -727,7 +727,7 @@
- do_write);
-
- kunmap_atomic(buf);
- - local_irq_restore(flags);
- + local_irq_restore_nort(flags);
- } else {
- buf = page_address(page);
- ap->ops->sff_data_xfer(qc->dev, buf + offset, qc->sect_size,
- @@ -864,7 +864,7 @@
- unsigned long flags;
-
- /* FIXME: use bounce buffer */
- - local_irq_save(flags);
- + local_irq_save_nort(flags);
- buf = kmap_atomic(page);
-
- /* do the actual data transfer */
- @@ -872,7 +872,7 @@
- count, rw);
-
- kunmap_atomic(buf);
- - local_irq_restore(flags);
- + local_irq_restore_nort(flags);
- } else {
- buf = page_address(page);
- consumed = ap->ops->sff_data_xfer(dev, buf + offset,
- diff -Nur linux-4.4.28.orig/drivers/block/zram/zram_drv.c linux-4.4.28/drivers/block/zram/zram_drv.c
- --- linux-4.4.28.orig/drivers/block/zram/zram_drv.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/block/zram/zram_drv.c 2016-11-01 21:26:57.892285294 +0100
- @@ -520,6 +520,8 @@
- goto out_error;
- }
-
- + zram_meta_init_table_locks(meta, disksize);
- +
- return meta;
-
- out_error:
- @@ -568,12 +570,12 @@
- unsigned long handle;
- size_t size;
-
- - bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
- + zram_lock_table(&meta->table[index]);
- handle = meta->table[index].handle;
- size = zram_get_obj_size(meta, index);
-
- if (!handle || zram_test_flag(meta, index, ZRAM_ZERO)) {
- - bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
- + zram_unlock_table(&meta->table[index]);
- clear_page(mem);
- return 0;
- }
- @@ -584,7 +586,7 @@
- else
- ret = zcomp_decompress(zram->comp, cmem, size, mem);
- zs_unmap_object(meta->mem_pool, handle);
- - bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
- + zram_unlock_table(&meta->table[index]);
-
- /* Should NEVER happen. Return bio error if it does. */
- if (unlikely(ret)) {
- @@ -604,14 +606,14 @@
- struct zram_meta *meta = zram->meta;
- page = bvec->bv_page;
-
- - bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
- + zram_lock_table(&meta->table[index]);
- if (unlikely(!meta->table[index].handle) ||
- zram_test_flag(meta, index, ZRAM_ZERO)) {
- - bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
- + zram_unlock_table(&meta->table[index]);
- handle_zero_page(bvec);
- return 0;
- }
- - bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
- + zram_unlock_table(&meta->table[index]);
-
- if (is_partial_io(bvec))
- /* Use a temporary buffer to decompress the page */
- @@ -689,10 +691,10 @@
- if (user_mem)
- kunmap_atomic(user_mem);
- /* Free memory associated with this sector now. */
- - bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
- + zram_lock_table(&meta->table[index]);
- zram_free_page(zram, index);
- zram_set_flag(meta, index, ZRAM_ZERO);
- - bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
- + zram_unlock_table(&meta->table[index]);
-
- atomic64_inc(&zram->stats.zero_pages);
- ret = 0;
- @@ -752,12 +754,12 @@
- * Free memory associated with this sector
- * before overwriting unused sectors.
- */
- - bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
- + zram_lock_table(&meta->table[index]);
- zram_free_page(zram, index);
-
- meta->table[index].handle = handle;
- zram_set_obj_size(meta, index, clen);
- - bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
- + zram_unlock_table(&meta->table[index]);
-
- /* Update stats */
- atomic64_add(clen, &zram->stats.compr_data_size);
- @@ -800,9 +802,9 @@
- }
-
- while (n >= PAGE_SIZE) {
- - bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
- + zram_lock_table(&meta->table[index]);
- zram_free_page(zram, index);
- - bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
- + zram_unlock_table(&meta->table[index]);
- atomic64_inc(&zram->stats.notify_free);
- index++;
- n -= PAGE_SIZE;
- @@ -928,9 +930,9 @@
- zram = bdev->bd_disk->private_data;
- meta = zram->meta;
-
- - bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
- + zram_lock_table(&meta->table[index]);
- zram_free_page(zram, index);
- - bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
- + zram_unlock_table(&meta->table[index]);
- atomic64_inc(&zram->stats.notify_free);
- }
-
- diff -Nur linux-4.4.28.orig/drivers/block/zram/zram_drv.h linux-4.4.28/drivers/block/zram/zram_drv.h
- --- linux-4.4.28.orig/drivers/block/zram/zram_drv.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/block/zram/zram_drv.h 2016-11-01 21:26:57.892285294 +0100
- @@ -72,6 +72,9 @@
- struct zram_table_entry {
- unsigned long handle;
- unsigned long value;
- +#ifdef CONFIG_PREEMPT_RT_BASE
- + spinlock_t lock;
- +#endif
- };
-
- struct zram_stats {
- @@ -119,4 +122,42 @@
- */
- bool claim; /* Protected by bdev->bd_mutex */
- };
- +
- +#ifndef CONFIG_PREEMPT_RT_BASE
- +static inline void zram_lock_table(struct zram_table_entry *table)
- +{
- + bit_spin_lock(ZRAM_ACCESS, &table->value);
- +}
- +
- +static inline void zram_unlock_table(struct zram_table_entry *table)
- +{
- + bit_spin_unlock(ZRAM_ACCESS, &table->value);
- +}
- +
- +static inline void zram_meta_init_table_locks(struct zram_meta *meta, u64 disksize) { }
- +#else /* CONFIG_PREEMPT_RT_BASE */
- +static inline void zram_lock_table(struct zram_table_entry *table)
- +{
- + spin_lock(&table->lock);
- + __set_bit(ZRAM_ACCESS, &table->value);
- +}
- +
- +static inline void zram_unlock_table(struct zram_table_entry *table)
- +{
- + __clear_bit(ZRAM_ACCESS, &table->value);
- + spin_unlock(&table->lock);
- +}
- +
- +static inline void zram_meta_init_table_locks(struct zram_meta *meta, u64 disksize)
- +{
- + size_t num_pages = disksize >> PAGE_SHIFT;
- + size_t index;
- +
- + for (index = 0; index < num_pages; index++) {
- + spinlock_t *lock = &meta->table[index].lock;
- + spin_lock_init(lock);
- + }
- +}
- +#endif /* CONFIG_PREEMPT_RT_BASE */
- +
- #endif
- diff -Nur linux-4.4.28.orig/drivers/char/random.c linux-4.4.28/drivers/char/random.c
- --- linux-4.4.28.orig/drivers/char/random.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/char/random.c 2016-11-01 21:26:57.900285811 +0100
- @@ -799,8 +799,6 @@
- } sample;
- long delta, delta2, delta3;
-
- - preempt_disable();
- -
- sample.jiffies = jiffies;
- sample.cycles = random_get_entropy();
- sample.num = num;
- @@ -841,7 +839,6 @@
- */
- credit_entropy_bits(r, min_t(int, fls(delta>>1), 11));
- }
- - preempt_enable();
- }
-
- void add_input_randomness(unsigned int type, unsigned int code,
- @@ -894,28 +891,27 @@
- return *(ptr + f->reg_idx++);
- }
-
- -void add_interrupt_randomness(int irq, int irq_flags)
- +void add_interrupt_randomness(int irq, int irq_flags, __u64 ip)
- {
- struct entropy_store *r;
- struct fast_pool *fast_pool = this_cpu_ptr(&irq_randomness);
- - struct pt_regs *regs = get_irq_regs();
- unsigned long now = jiffies;
- cycles_t cycles = random_get_entropy();
- __u32 c_high, j_high;
- - __u64 ip;
- unsigned long seed;
- int credit = 0;
-
- if (cycles == 0)
- - cycles = get_reg(fast_pool, regs);
- + cycles = get_reg(fast_pool, NULL);
- c_high = (sizeof(cycles) > 4) ? cycles >> 32 : 0;
- j_high = (sizeof(now) > 4) ? now >> 32 : 0;
- fast_pool->pool[0] ^= cycles ^ j_high ^ irq;
- fast_pool->pool[1] ^= now ^ c_high;
- - ip = regs ? instruction_pointer(regs) : _RET_IP_;
- + if (!ip)
- + ip = _RET_IP_;
- fast_pool->pool[2] ^= ip;
- fast_pool->pool[3] ^= (sizeof(ip) > 4) ? ip >> 32 :
- - get_reg(fast_pool, regs);
- + get_reg(fast_pool, NULL);
-
- fast_mix(fast_pool);
- add_interrupt_bench(cycles);
- diff -Nur linux-4.4.28.orig/drivers/clk/at91/clk-generated.c linux-4.4.28/drivers/clk/at91/clk-generated.c
- --- linux-4.4.28.orig/drivers/clk/at91/clk-generated.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/clk/at91/clk-generated.c 2016-11-01 21:26:57.916286841 +0100
- @@ -15,8 +15,8 @@
- #include <linux/clkdev.h>
- #include <linux/clk/at91_pmc.h>
- #include <linux/of.h>
- -#include <linux/of_address.h>
- -#include <linux/io.h>
- +#include <linux/mfd/syscon.h>
- +#include <linux/regmap.h>
-
- #include "pmc.h"
-
- @@ -28,8 +28,9 @@
-
- struct clk_generated {
- struct clk_hw hw;
- - struct at91_pmc *pmc;
- + struct regmap *regmap;
- struct clk_range range;
- + spinlock_t *lock;
- u32 id;
- u32 gckdiv;
- u8 parent_id;
- @@ -41,49 +42,52 @@
- static int clk_generated_enable(struct clk_hw *hw)
- {
- struct clk_generated *gck = to_clk_generated(hw);
- - struct at91_pmc *pmc = gck->pmc;
- - u32 tmp;
- + unsigned long flags;
-
- pr_debug("GCLK: %s, gckdiv = %d, parent id = %d\n",
- __func__, gck->gckdiv, gck->parent_id);
-
- - pmc_lock(pmc);
- - pmc_write(pmc, AT91_PMC_PCR, (gck->id & AT91_PMC_PCR_PID_MASK));
- - tmp = pmc_read(pmc, AT91_PMC_PCR) &
- - ~(AT91_PMC_PCR_GCKDIV_MASK | AT91_PMC_PCR_GCKCSS_MASK);
- - pmc_write(pmc, AT91_PMC_PCR, tmp | AT91_PMC_PCR_GCKCSS(gck->parent_id)
- - | AT91_PMC_PCR_CMD
- - | AT91_PMC_PCR_GCKDIV(gck->gckdiv)
- - | AT91_PMC_PCR_GCKEN);
- - pmc_unlock(pmc);
- + spin_lock_irqsave(gck->lock, flags);
- + regmap_write(gck->regmap, AT91_PMC_PCR,
- + (gck->id & AT91_PMC_PCR_PID_MASK));
- + regmap_update_bits(gck->regmap, AT91_PMC_PCR,
- + AT91_PMC_PCR_GCKDIV_MASK | AT91_PMC_PCR_GCKCSS_MASK |
- + AT91_PMC_PCR_CMD | AT91_PMC_PCR_GCKEN,
- + AT91_PMC_PCR_GCKCSS(gck->parent_id) |
- + AT91_PMC_PCR_CMD |
- + AT91_PMC_PCR_GCKDIV(gck->gckdiv) |
- + AT91_PMC_PCR_GCKEN);
- + spin_unlock_irqrestore(gck->lock, flags);
- return 0;
- }
-
- static void clk_generated_disable(struct clk_hw *hw)
- {
- struct clk_generated *gck = to_clk_generated(hw);
- - struct at91_pmc *pmc = gck->pmc;
- - u32 tmp;
- + unsigned long flags;
-
- - pmc_lock(pmc);
- - pmc_write(pmc, AT91_PMC_PCR, (gck->id & AT91_PMC_PCR_PID_MASK));
- - tmp = pmc_read(pmc, AT91_PMC_PCR) & ~AT91_PMC_PCR_GCKEN;
- - pmc_write(pmc, AT91_PMC_PCR, tmp | AT91_PMC_PCR_CMD);
- - pmc_unlock(pmc);
- + spin_lock_irqsave(gck->lock, flags);
- + regmap_write(gck->regmap, AT91_PMC_PCR,
- + (gck->id & AT91_PMC_PCR_PID_MASK));
- + regmap_update_bits(gck->regmap, AT91_PMC_PCR,
- + AT91_PMC_PCR_CMD | AT91_PMC_PCR_GCKEN,
- + AT91_PMC_PCR_CMD);
- + spin_unlock_irqrestore(gck->lock, flags);
- }
-
- static int clk_generated_is_enabled(struct clk_hw *hw)
- {
- struct clk_generated *gck = to_clk_generated(hw);
- - struct at91_pmc *pmc = gck->pmc;
- - int ret;
- + unsigned long flags;
- + unsigned int status;
-
- - pmc_lock(pmc);
- - pmc_write(pmc, AT91_PMC_PCR, (gck->id & AT91_PMC_PCR_PID_MASK));
- - ret = !!(pmc_read(pmc, AT91_PMC_PCR) & AT91_PMC_PCR_GCKEN);
- - pmc_unlock(pmc);
- + spin_lock_irqsave(gck->lock, flags);
- + regmap_write(gck->regmap, AT91_PMC_PCR,
- + (gck->id & AT91_PMC_PCR_PID_MASK));
- + regmap_read(gck->regmap, AT91_PMC_PCR, &status);
- + spin_unlock_irqrestore(gck->lock, flags);
-
- - return ret;
- + return status & AT91_PMC_PCR_GCKEN ? 1 : 0;
- }
-
- static unsigned long
- @@ -214,13 +218,14 @@
- */
- static void clk_generated_startup(struct clk_generated *gck)
- {
- - struct at91_pmc *pmc = gck->pmc;
- u32 tmp;
- + unsigned long flags;
-
- - pmc_lock(pmc);
- - pmc_write(pmc, AT91_PMC_PCR, (gck->id & AT91_PMC_PCR_PID_MASK));
- - tmp = pmc_read(pmc, AT91_PMC_PCR);
- - pmc_unlock(pmc);
- + spin_lock_irqsave(gck->lock, flags);
- + regmap_write(gck->regmap, AT91_PMC_PCR,
- + (gck->id & AT91_PMC_PCR_PID_MASK));
- + regmap_read(gck->regmap, AT91_PMC_PCR, &tmp);
- + spin_unlock_irqrestore(gck->lock, flags);
-
- gck->parent_id = (tmp & AT91_PMC_PCR_GCKCSS_MASK)
- >> AT91_PMC_PCR_GCKCSS_OFFSET;
- @@ -229,8 +234,8 @@
- }
-
- static struct clk * __init
- -at91_clk_register_generated(struct at91_pmc *pmc, const char *name,
- - const char **parent_names, u8 num_parents,
- +at91_clk_register_generated(struct regmap *regmap, spinlock_t *lock, const char
- + *name, const char **parent_names, u8 num_parents,
- u8 id, const struct clk_range *range)
- {
- struct clk_generated *gck;
- @@ -249,7 +254,8 @@
-
- gck->id = id;
- gck->hw.init = &init;
- - gck->pmc = pmc;
- + gck->regmap = regmap;
- + gck->lock = lock;
- gck->range = *range;
-
- clk = clk_register(NULL, &gck->hw);
- @@ -261,8 +267,7 @@
- return clk;
- }
-
- -void __init of_sama5d2_clk_generated_setup(struct device_node *np,
- - struct at91_pmc *pmc)
- +void __init of_sama5d2_clk_generated_setup(struct device_node *np)
- {
- int num;
- u32 id;
- @@ -272,6 +277,7 @@
- const char *parent_names[GENERATED_SOURCE_MAX];
- struct device_node *gcknp;
- struct clk_range range = CLK_RANGE(0, 0);
- + struct regmap *regmap;
-
- num_parents = of_clk_get_parent_count(np);
- if (num_parents <= 0 || num_parents > GENERATED_SOURCE_MAX)
- @@ -283,6 +289,10 @@
- if (!num || num > PERIPHERAL_MAX)
- return;
-
- + regmap = syscon_node_to_regmap(of_get_parent(np));
- + if (IS_ERR(regmap))
- + return;
- +
- for_each_child_of_node(np, gcknp) {
- if (of_property_read_u32(gcknp, "reg", &id))
- continue;
- @@ -296,11 +306,14 @@
- of_at91_get_clk_range(gcknp, "atmel,clk-output-range",
- &range);
-
- - clk = at91_clk_register_generated(pmc, name, parent_names,
- - num_parents, id, &range);
- + clk = at91_clk_register_generated(regmap, &pmc_pcr_lock, name,
- + parent_names, num_parents,
- + id, &range);
- if (IS_ERR(clk))
- continue;
-
- of_clk_add_provider(gcknp, of_clk_src_simple_get, clk);
- }
- }
- +CLK_OF_DECLARE(of_sama5d2_clk_generated_setup, "atmel,sama5d2-clk-generated",
- + of_sama5d2_clk_generated_setup);
- diff -Nur linux-4.4.28.orig/drivers/clk/at91/clk-h32mx.c linux-4.4.28/drivers/clk/at91/clk-h32mx.c
- --- linux-4.4.28.orig/drivers/clk/at91/clk-h32mx.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/clk/at91/clk-h32mx.c 2016-11-01 21:26:57.916286841 +0100
- @@ -15,15 +15,9 @@
- #include <linux/clk-provider.h>
- #include <linux/clkdev.h>
- #include <linux/clk/at91_pmc.h>
- -#include <linux/delay.h>
- #include <linux/of.h>
- -#include <linux/of_address.h>
- -#include <linux/of_irq.h>
- -#include <linux/io.h>
- -#include <linux/interrupt.h>
- -#include <linux/irq.h>
- -#include <linux/sched.h>
- -#include <linux/wait.h>
- +#include <linux/regmap.h>
- +#include <linux/mfd/syscon.h>
-
- #include "pmc.h"
-
- @@ -31,7 +25,7 @@
-
- struct clk_sama5d4_h32mx {
- struct clk_hw hw;
- - struct at91_pmc *pmc;
- + struct regmap *regmap;
- };
-
- #define to_clk_sama5d4_h32mx(hw) container_of(hw, struct clk_sama5d4_h32mx, hw)
- @@ -40,8 +34,10 @@
- unsigned long parent_rate)
- {
- struct clk_sama5d4_h32mx *h32mxclk = to_clk_sama5d4_h32mx(hw);
- + unsigned int mckr;
-
- - if (pmc_read(h32mxclk->pmc, AT91_PMC_MCKR) & AT91_PMC_H32MXDIV)
- + regmap_read(h32mxclk->regmap, AT91_PMC_MCKR, &mckr);
- + if (mckr & AT91_PMC_H32MXDIV)
- return parent_rate / 2;
-
- if (parent_rate > H32MX_MAX_FREQ)
- @@ -70,18 +66,16 @@
- unsigned long parent_rate)
- {
- struct clk_sama5d4_h32mx *h32mxclk = to_clk_sama5d4_h32mx(hw);
- - struct at91_pmc *pmc = h32mxclk->pmc;
- - u32 tmp;
- + u32 mckr = 0;
-
- if (parent_rate != rate && (parent_rate / 2) != rate)
- return -EINVAL;
-
- - pmc_lock(pmc);
- - tmp = pmc_read(pmc, AT91_PMC_MCKR) & ~AT91_PMC_H32MXDIV;
- if ((parent_rate / 2) == rate)
- - tmp |= AT91_PMC_H32MXDIV;
- - pmc_write(pmc, AT91_PMC_MCKR, tmp);
- - pmc_unlock(pmc);
- + mckr = AT91_PMC_H32MXDIV;
- +
- + regmap_update_bits(h32mxclk->regmap, AT91_PMC_MCKR,
- + AT91_PMC_H32MXDIV, mckr);
-
- return 0;
- }
- @@ -92,14 +86,18 @@
- .set_rate = clk_sama5d4_h32mx_set_rate,
- };
-
- -void __init of_sama5d4_clk_h32mx_setup(struct device_node *np,
- - struct at91_pmc *pmc)
- +static void __init of_sama5d4_clk_h32mx_setup(struct device_node *np)
- {
- struct clk_sama5d4_h32mx *h32mxclk;
- struct clk_init_data init;
- const char *parent_name;
- + struct regmap *regmap;
- struct clk *clk;
-
- + regmap = syscon_node_to_regmap(of_get_parent(np));
- + if (IS_ERR(regmap))
- + return;
- +
- h32mxclk = kzalloc(sizeof(*h32mxclk), GFP_KERNEL);
- if (!h32mxclk)
- return;
- @@ -113,7 +111,7 @@
- init.flags = CLK_SET_RATE_GATE;
-
- h32mxclk->hw.init = &init;
- - h32mxclk->pmc = pmc;
- + h32mxclk->regmap = regmap;
-
- clk = clk_register(NULL, &h32mxclk->hw);
- if (IS_ERR(clk)) {
- @@ -123,3 +121,5 @@
-
- of_clk_add_provider(np, of_clk_src_simple_get, clk);
- }
- +CLK_OF_DECLARE(of_sama5d4_clk_h32mx_setup, "atmel,sama5d4-clk-h32mx",
- + of_sama5d4_clk_h32mx_setup);
- diff -Nur linux-4.4.28.orig/drivers/clk/at91/clk-main.c linux-4.4.28/drivers/clk/at91/clk-main.c
- --- linux-4.4.28.orig/drivers/clk/at91/clk-main.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/clk/at91/clk-main.c 2016-11-01 21:26:57.920287105 +0100
- @@ -13,13 +13,8 @@
- #include <linux/clk/at91_pmc.h>
- #include <linux/delay.h>
- #include <linux/of.h>
- -#include <linux/of_address.h>
- -#include <linux/of_irq.h>
- -#include <linux/io.h>
- -#include <linux/interrupt.h>
- -#include <linux/irq.h>
- -#include <linux/sched.h>
- -#include <linux/wait.h>
- +#include <linux/mfd/syscon.h>
- +#include <linux/regmap.h>
-
- #include "pmc.h"
-
- @@ -34,18 +29,14 @@
-
- struct clk_main_osc {
- struct clk_hw hw;
- - struct at91_pmc *pmc;
- - unsigned int irq;
- - wait_queue_head_t wait;
- + struct regmap *regmap;
- };
-
- #define to_clk_main_osc(hw) container_of(hw, struct clk_main_osc, hw)
-
- struct clk_main_rc_osc {
- struct clk_hw hw;
- - struct at91_pmc *pmc;
- - unsigned int irq;
- - wait_queue_head_t wait;
- + struct regmap *regmap;
- unsigned long frequency;
- unsigned long accuracy;
- };
- @@ -54,51 +45,47 @@
-
- struct clk_rm9200_main {
- struct clk_hw hw;
- - struct at91_pmc *pmc;
- + struct regmap *regmap;
- };
-
- #define to_clk_rm9200_main(hw) container_of(hw, struct clk_rm9200_main, hw)
-
- struct clk_sam9x5_main {
- struct clk_hw hw;
- - struct at91_pmc *pmc;
- - unsigned int irq;
- - wait_queue_head_t wait;
- + struct regmap *regmap;
- u8 parent;
- };
-
- #define to_clk_sam9x5_main(hw) container_of(hw, struct clk_sam9x5_main, hw)
-
- -static irqreturn_t clk_main_osc_irq_handler(int irq, void *dev_id)
- +static inline bool clk_main_osc_ready(struct regmap *regmap)
- {
- - struct clk_main_osc *osc = dev_id;
- + unsigned int status;
-
- - wake_up(&osc->wait);
- - disable_irq_nosync(osc->irq);
- + regmap_read(regmap, AT91_PMC_SR, &status);
-
- - return IRQ_HANDLED;
- + return status & AT91_PMC_MOSCS;
- }
-
- static int clk_main_osc_prepare(struct clk_hw *hw)
- {
- struct clk_main_osc *osc = to_clk_main_osc(hw);
- - struct at91_pmc *pmc = osc->pmc;
- + struct regmap *regmap = osc->regmap;
- u32 tmp;
-
- - tmp = pmc_read(pmc, AT91_CKGR_MOR) & ~MOR_KEY_MASK;
- + regmap_read(regmap, AT91_CKGR_MOR, &tmp);
- + tmp &= ~MOR_KEY_MASK;
- +
- if (tmp & AT91_PMC_OSCBYPASS)
- return 0;
-
- if (!(tmp & AT91_PMC_MOSCEN)) {
- tmp |= AT91_PMC_MOSCEN | AT91_PMC_KEY;
- - pmc_write(pmc, AT91_CKGR_MOR, tmp);
- + regmap_write(regmap, AT91_CKGR_MOR, tmp);
- }
-
- - while (!(pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_MOSCS)) {
- - enable_irq(osc->irq);
- - wait_event(osc->wait,
- - pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_MOSCS);
- - }
- + while (!clk_main_osc_ready(regmap))
- + cpu_relax();
-
- return 0;
- }
- @@ -106,9 +93,10 @@
- static void clk_main_osc_unprepare(struct clk_hw *hw)
- {
- struct clk_main_osc *osc = to_clk_main_osc(hw);
- - struct at91_pmc *pmc = osc->pmc;
- - u32 tmp = pmc_read(pmc, AT91_CKGR_MOR);
- + struct regmap *regmap = osc->regmap;
- + u32 tmp;
-
- + regmap_read(regmap, AT91_CKGR_MOR, &tmp);
- if (tmp & AT91_PMC_OSCBYPASS)
- return;
-
- @@ -116,20 +104,22 @@
- return;
-
- tmp &= ~(AT91_PMC_KEY | AT91_PMC_MOSCEN);
- - pmc_write(pmc, AT91_CKGR_MOR, tmp | AT91_PMC_KEY);
- + regmap_write(regmap, AT91_CKGR_MOR, tmp | AT91_PMC_KEY);
- }
-
- static int clk_main_osc_is_prepared(struct clk_hw *hw)
- {
- struct clk_main_osc *osc = to_clk_main_osc(hw);
- - struct at91_pmc *pmc = osc->pmc;
- - u32 tmp = pmc_read(pmc, AT91_CKGR_MOR);
- + struct regmap *regmap = osc->regmap;
- + u32 tmp, status;
-
- + regmap_read(regmap, AT91_CKGR_MOR, &tmp);
- if (tmp & AT91_PMC_OSCBYPASS)
- return 1;
-
- - return !!((pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_MOSCS) &&
- - (pmc_read(pmc, AT91_CKGR_MOR) & AT91_PMC_MOSCEN));
- + regmap_read(regmap, AT91_PMC_SR, &status);
- +
- + return (status & AT91_PMC_MOSCS) && (tmp & AT91_PMC_MOSCEN);
- }
-
- static const struct clk_ops main_osc_ops = {
- @@ -139,18 +129,16 @@
- };
-
- static struct clk * __init
- -at91_clk_register_main_osc(struct at91_pmc *pmc,
- - unsigned int irq,
- +at91_clk_register_main_osc(struct regmap *regmap,
- const char *name,
- const char *parent_name,
- bool bypass)
- {
- - int ret;
- struct clk_main_osc *osc;
- struct clk *clk = NULL;
- struct clk_init_data init;
-
- - if (!pmc || !irq || !name || !parent_name)
- + if (!name || !parent_name)
- return ERR_PTR(-EINVAL);
-
- osc = kzalloc(sizeof(*osc), GFP_KERNEL);
- @@ -164,85 +152,70 @@
- init.flags = CLK_IGNORE_UNUSED;
-
- osc->hw.init = &init;
- - osc->pmc = pmc;
- - osc->irq = irq;
- -
- - init_waitqueue_head(&osc->wait);
- - irq_set_status_flags(osc->irq, IRQ_NOAUTOEN);
- - ret = request_irq(osc->irq, clk_main_osc_irq_handler,
- - IRQF_TRIGGER_HIGH, name, osc);
- - if (ret) {
- - kfree(osc);
- - return ERR_PTR(ret);
- - }
- + osc->regmap = regmap;
-
- if (bypass)
- - pmc_write(pmc, AT91_CKGR_MOR,
- - (pmc_read(pmc, AT91_CKGR_MOR) &
- - ~(MOR_KEY_MASK | AT91_PMC_MOSCEN)) |
- - AT91_PMC_OSCBYPASS | AT91_PMC_KEY);
- + regmap_update_bits(regmap,
- + AT91_CKGR_MOR, MOR_KEY_MASK |
- + AT91_PMC_MOSCEN,
- + AT91_PMC_OSCBYPASS | AT91_PMC_KEY);
-
- clk = clk_register(NULL, &osc->hw);
- - if (IS_ERR(clk)) {
- - free_irq(irq, osc);
- + if (IS_ERR(clk))
- kfree(osc);
- - }
-
- return clk;
- }
-
- -void __init of_at91rm9200_clk_main_osc_setup(struct device_node *np,
- - struct at91_pmc *pmc)
- +static void __init of_at91rm9200_clk_main_osc_setup(struct device_node *np)
- {
- struct clk *clk;
- - unsigned int irq;
- const char *name = np->name;
- const char *parent_name;
- + struct regmap *regmap;
- bool bypass;
-
- of_property_read_string(np, "clock-output-names", &name);
- bypass = of_property_read_bool(np, "atmel,osc-bypass");
- parent_name = of_clk_get_parent_name(np, 0);
-
- - irq = irq_of_parse_and_map(np, 0);
- - if (!irq)
- + regmap = syscon_node_to_regmap(of_get_parent(np));
- + if (IS_ERR(regmap))
- return;
-
- - clk = at91_clk_register_main_osc(pmc, irq, name, parent_name, bypass);
- + clk = at91_clk_register_main_osc(regmap, name, parent_name, bypass);
- if (IS_ERR(clk))
- return;
-
- of_clk_add_provider(np, of_clk_src_simple_get, clk);
- }
- +CLK_OF_DECLARE(at91rm9200_clk_main_osc, "atmel,at91rm9200-clk-main-osc",
- + of_at91rm9200_clk_main_osc_setup);
-
- -static irqreturn_t clk_main_rc_osc_irq_handler(int irq, void *dev_id)
- +static bool clk_main_rc_osc_ready(struct regmap *regmap)
- {
- - struct clk_main_rc_osc *osc = dev_id;
- + unsigned int status;
-
- - wake_up(&osc->wait);
- - disable_irq_nosync(osc->irq);
- + regmap_read(regmap, AT91_PMC_SR, &status);
-
- - return IRQ_HANDLED;
- + return status & AT91_PMC_MOSCRCS;
- }
-
- static int clk_main_rc_osc_prepare(struct clk_hw *hw)
- {
- struct clk_main_rc_osc *osc = to_clk_main_rc_osc(hw);
- - struct at91_pmc *pmc = osc->pmc;
- - u32 tmp;
- + struct regmap *regmap = osc->regmap;
- + unsigned int mor;
-
- - tmp = pmc_read(pmc, AT91_CKGR_MOR) & ~MOR_KEY_MASK;
- + regmap_read(regmap, AT91_CKGR_MOR, &mor);
-
- - if (!(tmp & AT91_PMC_MOSCRCEN)) {
- - tmp |= AT91_PMC_MOSCRCEN | AT91_PMC_KEY;
- - pmc_write(pmc, AT91_CKGR_MOR, tmp);
- - }
- + if (!(mor & AT91_PMC_MOSCRCEN))
- + regmap_update_bits(regmap, AT91_CKGR_MOR,
- + MOR_KEY_MASK | AT91_PMC_MOSCRCEN,
- + AT91_PMC_MOSCRCEN | AT91_PMC_KEY);
-
- - while (!(pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_MOSCRCS)) {
- - enable_irq(osc->irq);
- - wait_event(osc->wait,
- - pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_MOSCRCS);
- - }
- + while (!clk_main_rc_osc_ready(regmap))
- + cpu_relax();
-
- return 0;
- }
- @@ -250,23 +223,28 @@
- static void clk_main_rc_osc_unprepare(struct clk_hw *hw)
- {
- struct clk_main_rc_osc *osc = to_clk_main_rc_osc(hw);
- - struct at91_pmc *pmc = osc->pmc;
- - u32 tmp = pmc_read(pmc, AT91_CKGR_MOR);
- + struct regmap *regmap = osc->regmap;
- + unsigned int mor;
-
- - if (!(tmp & AT91_PMC_MOSCRCEN))
- + regmap_read(regmap, AT91_CKGR_MOR, &mor);
- +
- + if (!(mor & AT91_PMC_MOSCRCEN))
- return;
-
- - tmp &= ~(MOR_KEY_MASK | AT91_PMC_MOSCRCEN);
- - pmc_write(pmc, AT91_CKGR_MOR, tmp | AT91_PMC_KEY);
- + regmap_update_bits(regmap, AT91_CKGR_MOR,
- + MOR_KEY_MASK | AT91_PMC_MOSCRCEN, AT91_PMC_KEY);
- }
-
- static int clk_main_rc_osc_is_prepared(struct clk_hw *hw)
- {
- struct clk_main_rc_osc *osc = to_clk_main_rc_osc(hw);
- - struct at91_pmc *pmc = osc->pmc;
- + struct regmap *regmap = osc->regmap;
- + unsigned int mor, status;
- +
- + regmap_read(regmap, AT91_CKGR_MOR, &mor);
- + regmap_read(regmap, AT91_PMC_SR, &status);
-
- - return !!((pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_MOSCRCS) &&
- - (pmc_read(pmc, AT91_CKGR_MOR) & AT91_PMC_MOSCRCEN));
- + return (mor & AT91_PMC_MOSCRCEN) && (status & AT91_PMC_MOSCRCS);
- }
-
- static unsigned long clk_main_rc_osc_recalc_rate(struct clk_hw *hw,
- @@ -294,17 +272,15 @@
- };
-
- static struct clk * __init
- -at91_clk_register_main_rc_osc(struct at91_pmc *pmc,
- - unsigned int irq,
- +at91_clk_register_main_rc_osc(struct regmap *regmap,
- const char *name,
- u32 frequency, u32 accuracy)
- {
- - int ret;
- struct clk_main_rc_osc *osc;
- struct clk *clk = NULL;
- struct clk_init_data init;
-
- - if (!pmc || !irq || !name || !frequency)
- + if (!name || !frequency)
- return ERR_PTR(-EINVAL);
-
- osc = kzalloc(sizeof(*osc), GFP_KERNEL);
- @@ -318,63 +294,53 @@
- init.flags = CLK_IS_ROOT | CLK_IGNORE_UNUSED;
-
- osc->hw.init = &init;
- - osc->pmc = pmc;
- - osc->irq = irq;
- + osc->regmap = regmap;
- osc->frequency = frequency;
- osc->accuracy = accuracy;
-
- - init_waitqueue_head(&osc->wait);
- - irq_set_status_flags(osc->irq, IRQ_NOAUTOEN);
- - ret = request_irq(osc->irq, clk_main_rc_osc_irq_handler,
- - IRQF_TRIGGER_HIGH, name, osc);
- - if (ret)
- - return ERR_PTR(ret);
- -
- clk = clk_register(NULL, &osc->hw);
- - if (IS_ERR(clk)) {
- - free_irq(irq, osc);
- + if (IS_ERR(clk))
- kfree(osc);
- - }
-
- return clk;
- }
-
- -void __init of_at91sam9x5_clk_main_rc_osc_setup(struct device_node *np,
- - struct at91_pmc *pmc)
- +static void __init of_at91sam9x5_clk_main_rc_osc_setup(struct device_node *np)
- {
- struct clk *clk;
- - unsigned int irq;
- u32 frequency = 0;
- u32 accuracy = 0;
- const char *name = np->name;
- + struct regmap *regmap;
-
- of_property_read_string(np, "clock-output-names", &name);
- of_property_read_u32(np, "clock-frequency", &frequency);
- of_property_read_u32(np, "clock-accuracy", &accuracy);
-
- - irq = irq_of_parse_and_map(np, 0);
- - if (!irq)
- + regmap = syscon_node_to_regmap(of_get_parent(np));
- + if (IS_ERR(regmap))
- return;
-
- - clk = at91_clk_register_main_rc_osc(pmc, irq, name, frequency,
- - accuracy);
- + clk = at91_clk_register_main_rc_osc(regmap, name, frequency, accuracy);
- if (IS_ERR(clk))
- return;
-
- of_clk_add_provider(np, of_clk_src_simple_get, clk);
- }
- +CLK_OF_DECLARE(at91sam9x5_clk_main_rc_osc, "atmel,at91sam9x5-clk-main-rc-osc",
- + of_at91sam9x5_clk_main_rc_osc_setup);
-
-
- -static int clk_main_probe_frequency(struct at91_pmc *pmc)
- +static int clk_main_probe_frequency(struct regmap *regmap)
- {
- unsigned long prep_time, timeout;
- - u32 tmp;
- + unsigned int mcfr;
-
- timeout = jiffies + usecs_to_jiffies(MAINFRDY_TIMEOUT);
- do {
- prep_time = jiffies;
- - tmp = pmc_read(pmc, AT91_CKGR_MCFR);
- - if (tmp & AT91_PMC_MAINRDY)
- + regmap_read(regmap, AT91_CKGR_MCFR, &mcfr);
- + if (mcfr & AT91_PMC_MAINRDY)
- return 0;
- usleep_range(MAINF_LOOP_MIN_WAIT, MAINF_LOOP_MAX_WAIT);
- } while (time_before(prep_time, timeout));
- @@ -382,34 +348,37 @@
- return -ETIMEDOUT;
- }
-
- -static unsigned long clk_main_recalc_rate(struct at91_pmc *pmc,
- +static unsigned long clk_main_recalc_rate(struct regmap *regmap,
- unsigned long parent_rate)
- {
- - u32 tmp;
- + unsigned int mcfr;
-
- if (parent_rate)
- return parent_rate;
-
- pr_warn("Main crystal frequency not set, using approximate value\n");
- - tmp = pmc_read(pmc, AT91_CKGR_MCFR);
- - if (!(tmp & AT91_PMC_MAINRDY))
- + regmap_read(regmap, AT91_CKGR_MCFR, &mcfr);
- + if (!(mcfr & AT91_PMC_MAINRDY))
- return 0;
-
- - return ((tmp & AT91_PMC_MAINF) * SLOW_CLOCK_FREQ) / MAINF_DIV;
- + return ((mcfr & AT91_PMC_MAINF) * SLOW_CLOCK_FREQ) / MAINF_DIV;
- }
-
- static int clk_rm9200_main_prepare(struct clk_hw *hw)
- {
- struct clk_rm9200_main *clkmain = to_clk_rm9200_main(hw);
-
- - return clk_main_probe_frequency(clkmain->pmc);
- + return clk_main_probe_frequency(clkmain->regmap);
- }
-
- static int clk_rm9200_main_is_prepared(struct clk_hw *hw)
- {
- struct clk_rm9200_main *clkmain = to_clk_rm9200_main(hw);
- + unsigned int status;
- +
- + regmap_read(clkmain->regmap, AT91_CKGR_MCFR, &status);
-
- - return !!(pmc_read(clkmain->pmc, AT91_CKGR_MCFR) & AT91_PMC_MAINRDY);
- + return status & AT91_PMC_MAINRDY ? 1 : 0;
- }
-
- static unsigned long clk_rm9200_main_recalc_rate(struct clk_hw *hw,
- @@ -417,7 +386,7 @@
- {
- struct clk_rm9200_main *clkmain = to_clk_rm9200_main(hw);
-
- - return clk_main_recalc_rate(clkmain->pmc, parent_rate);
- + return clk_main_recalc_rate(clkmain->regmap, parent_rate);
- }
-
- static const struct clk_ops rm9200_main_ops = {
- @@ -427,7 +396,7 @@
- };
-
- static struct clk * __init
- -at91_clk_register_rm9200_main(struct at91_pmc *pmc,
- +at91_clk_register_rm9200_main(struct regmap *regmap,
- const char *name,
- const char *parent_name)
- {
- @@ -435,7 +404,7 @@
- struct clk *clk = NULL;
- struct clk_init_data init;
-
- - if (!pmc || !name)
- + if (!name)
- return ERR_PTR(-EINVAL);
-
- if (!parent_name)
- @@ -452,7 +421,7 @@
- init.flags = 0;
-
- clkmain->hw.init = &init;
- - clkmain->pmc = pmc;
- + clkmain->regmap = regmap;
-
- clk = clk_register(NULL, &clkmain->hw);
- if (IS_ERR(clk))
- @@ -461,52 +430,54 @@
- return clk;
- }
-
- -void __init of_at91rm9200_clk_main_setup(struct device_node *np,
- - struct at91_pmc *pmc)
- +static void __init of_at91rm9200_clk_main_setup(struct device_node *np)
- {
- struct clk *clk;
- const char *parent_name;
- const char *name = np->name;
- + struct regmap *regmap;
-
- parent_name = of_clk_get_parent_name(np, 0);
- of_property_read_string(np, "clock-output-names", &name);
-
- - clk = at91_clk_register_rm9200_main(pmc, name, parent_name);
- + regmap = syscon_node_to_regmap(of_get_parent(np));
- + if (IS_ERR(regmap))
- + return;
- +
- + clk = at91_clk_register_rm9200_main(regmap, name, parent_name);
- if (IS_ERR(clk))
- return;
-
- of_clk_add_provider(np, of_clk_src_simple_get, clk);
- }
- +CLK_OF_DECLARE(at91rm9200_clk_main, "atmel,at91rm9200-clk-main",
- + of_at91rm9200_clk_main_setup);
-
- -static irqreturn_t clk_sam9x5_main_irq_handler(int irq, void *dev_id)
- +static inline bool clk_sam9x5_main_ready(struct regmap *regmap)
- {
- - struct clk_sam9x5_main *clkmain = dev_id;
- + unsigned int status;
-
- - wake_up(&clkmain->wait);
- - disable_irq_nosync(clkmain->irq);
- + regmap_read(regmap, AT91_PMC_SR, &status);
-
- - return IRQ_HANDLED;
- + return status & AT91_PMC_MOSCSELS ? 1 : 0;
- }
-
- static int clk_sam9x5_main_prepare(struct clk_hw *hw)
- {
- struct clk_sam9x5_main *clkmain = to_clk_sam9x5_main(hw);
- - struct at91_pmc *pmc = clkmain->pmc;
- + struct regmap *regmap = clkmain->regmap;
-
- - while (!(pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_MOSCSELS)) {
- - enable_irq(clkmain->irq);
- - wait_event(clkmain->wait,
- - pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_MOSCSELS);
- - }
- + while (!clk_sam9x5_main_ready(regmap))
- + cpu_relax();
-
- - return clk_main_probe_frequency(pmc);
- + return clk_main_probe_frequency(regmap);
- }
-
- static int clk_sam9x5_main_is_prepared(struct clk_hw *hw)
- {
- struct clk_sam9x5_main *clkmain = to_clk_sam9x5_main(hw);
-
- - return !!(pmc_read(clkmain->pmc, AT91_PMC_SR) & AT91_PMC_MOSCSELS);
- + return clk_sam9x5_main_ready(clkmain->regmap);
- }
-
- static unsigned long clk_sam9x5_main_recalc_rate(struct clk_hw *hw,
- @@ -514,30 +485,28 @@
- {
- struct clk_sam9x5_main *clkmain = to_clk_sam9x5_main(hw);
-
- - return clk_main_recalc_rate(clkmain->pmc, parent_rate);
- + return clk_main_recalc_rate(clkmain->regmap, parent_rate);
- }
-
- static int clk_sam9x5_main_set_parent(struct clk_hw *hw, u8 index)
- {
- struct clk_sam9x5_main *clkmain = to_clk_sam9x5_main(hw);
- - struct at91_pmc *pmc = clkmain->pmc;
- - u32 tmp;
- + struct regmap *regmap = clkmain->regmap;
- + unsigned int tmp;
-
- if (index > 1)
- return -EINVAL;
-
- - tmp = pmc_read(pmc, AT91_CKGR_MOR) & ~MOR_KEY_MASK;
- + regmap_read(regmap, AT91_CKGR_MOR, &tmp);
- + tmp &= ~MOR_KEY_MASK;
-
- if (index && !(tmp & AT91_PMC_MOSCSEL))
- - pmc_write(pmc, AT91_CKGR_MOR, tmp | AT91_PMC_MOSCSEL);
- + regmap_write(regmap, AT91_CKGR_MOR, tmp | AT91_PMC_MOSCSEL);
- else if (!index && (tmp & AT91_PMC_MOSCSEL))
- - pmc_write(pmc, AT91_CKGR_MOR, tmp & ~AT91_PMC_MOSCSEL);
- + regmap_write(regmap, AT91_CKGR_MOR, tmp & ~AT91_PMC_MOSCSEL);
-
- - while (!(pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_MOSCSELS)) {
- - enable_irq(clkmain->irq);
- - wait_event(clkmain->wait,
- - pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_MOSCSELS);
- - }
- + while (!clk_sam9x5_main_ready(regmap))
- + cpu_relax();
-
- return 0;
- }
- @@ -545,8 +514,11 @@
- static u8 clk_sam9x5_main_get_parent(struct clk_hw *hw)
- {
- struct clk_sam9x5_main *clkmain = to_clk_sam9x5_main(hw);
- + unsigned int status;
- +
- + regmap_read(clkmain->regmap, AT91_CKGR_MOR, &status);
-
- - return !!(pmc_read(clkmain->pmc, AT91_CKGR_MOR) & AT91_PMC_MOSCEN);
- + return status & AT91_PMC_MOSCEN ? 1 : 0;
- }
-
- static const struct clk_ops sam9x5_main_ops = {
- @@ -558,18 +530,17 @@
- };
-
- static struct clk * __init
- -at91_clk_register_sam9x5_main(struct at91_pmc *pmc,
- - unsigned int irq,
- +at91_clk_register_sam9x5_main(struct regmap *regmap,
- const char *name,
- const char **parent_names,
- int num_parents)
- {
- - int ret;
- struct clk_sam9x5_main *clkmain;
- struct clk *clk = NULL;
- struct clk_init_data init;
- + unsigned int status;
-
- - if (!pmc || !irq || !name)
- + if (!name)
- return ERR_PTR(-EINVAL);
-
- if (!parent_names || !num_parents)
- @@ -586,51 +557,42 @@
- init.flags = CLK_SET_PARENT_GATE;
-
- clkmain->hw.init = &init;
- - clkmain->pmc = pmc;
- - clkmain->irq = irq;
- - clkmain->parent = !!(pmc_read(clkmain->pmc, AT91_CKGR_MOR) &
- - AT91_PMC_MOSCEN);
- - init_waitqueue_head(&clkmain->wait);
- - irq_set_status_flags(clkmain->irq, IRQ_NOAUTOEN);
- - ret = request_irq(clkmain->irq, clk_sam9x5_main_irq_handler,
- - IRQF_TRIGGER_HIGH, name, clkmain);
- - if (ret)
- - return ERR_PTR(ret);
- + clkmain->regmap = regmap;
- + regmap_read(clkmain->regmap, AT91_CKGR_MOR, &status);
- + clkmain->parent = status & AT91_PMC_MOSCEN ? 1 : 0;
-
- clk = clk_register(NULL, &clkmain->hw);
- - if (IS_ERR(clk)) {
- - free_irq(clkmain->irq, clkmain);
- + if (IS_ERR(clk))
- kfree(clkmain);
- - }
-
- return clk;
- }
-
- -void __init of_at91sam9x5_clk_main_setup(struct device_node *np,
- - struct at91_pmc *pmc)
- +static void __init of_at91sam9x5_clk_main_setup(struct device_node *np)
- {
- struct clk *clk;
- const char *parent_names[2];
- int num_parents;
- - unsigned int irq;
- const char *name = np->name;
- + struct regmap *regmap;
-
- num_parents = of_clk_get_parent_count(np);
- if (num_parents <= 0 || num_parents > 2)
- return;
-
- of_clk_parent_fill(np, parent_names, num_parents);
- + regmap = syscon_node_to_regmap(of_get_parent(np));
- + if (IS_ERR(regmap))
- + return;
-
- of_property_read_string(np, "clock-output-names", &name);
-
- - irq = irq_of_parse_and_map(np, 0);
- - if (!irq)
- - return;
- -
- - clk = at91_clk_register_sam9x5_main(pmc, irq, name, parent_names,
- + clk = at91_clk_register_sam9x5_main(regmap, name, parent_names,
- num_parents);
- if (IS_ERR(clk))
- return;
-
- of_clk_add_provider(np, of_clk_src_simple_get, clk);
- }
- +CLK_OF_DECLARE(at91sam9x5_clk_main, "atmel,at91sam9x5-clk-main",
- + of_at91sam9x5_clk_main_setup);
- diff -Nur linux-4.4.28.orig/drivers/clk/at91/clk-master.c linux-4.4.28/drivers/clk/at91/clk-master.c
- --- linux-4.4.28.orig/drivers/clk/at91/clk-master.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/clk/at91/clk-master.c 2016-11-01 21:26:57.920287105 +0100
- @@ -12,13 +12,8 @@
- #include <linux/clkdev.h>
- #include <linux/clk/at91_pmc.h>
- #include <linux/of.h>
- -#include <linux/of_address.h>
- -#include <linux/of_irq.h>
- -#include <linux/io.h>
- -#include <linux/wait.h>
- -#include <linux/sched.h>
- -#include <linux/interrupt.h>
- -#include <linux/irq.h>
- +#include <linux/mfd/syscon.h>
- +#include <linux/regmap.h>
-
- #include "pmc.h"
-
- @@ -44,32 +39,26 @@
-
- struct clk_master {
- struct clk_hw hw;
- - struct at91_pmc *pmc;
- - unsigned int irq;
- - wait_queue_head_t wait;
- + struct regmap *regmap;
- const struct clk_master_layout *layout;
- const struct clk_master_characteristics *characteristics;
- };
-
- -static irqreturn_t clk_master_irq_handler(int irq, void *dev_id)
- +static inline bool clk_master_ready(struct regmap *regmap)
- {
- - struct clk_master *master = (struct clk_master *)dev_id;
- + unsigned int status;
-
- - wake_up(&master->wait);
- - disable_irq_nosync(master->irq);
- + regmap_read(regmap, AT91_PMC_SR, &status);
-
- - return IRQ_HANDLED;
- + return status & AT91_PMC_MCKRDY ? 1 : 0;
- }
- +
- static int clk_master_prepare(struct clk_hw *hw)
- {
- struct clk_master *master = to_clk_master(hw);
- - struct at91_pmc *pmc = master->pmc;
-
- - while (!(pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_MCKRDY)) {
- - enable_irq(master->irq);
- - wait_event(master->wait,
- - pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_MCKRDY);
- - }
- + while (!clk_master_ready(master->regmap))
- + cpu_relax();
-
- return 0;
- }
- @@ -78,7 +67,7 @@
- {
- struct clk_master *master = to_clk_master(hw);
-
- - return !!(pmc_read(master->pmc, AT91_PMC_SR) & AT91_PMC_MCKRDY);
- + return clk_master_ready(master->regmap);
- }
-
- static unsigned long clk_master_recalc_rate(struct clk_hw *hw,
- @@ -88,18 +77,16 @@
- u8 div;
- unsigned long rate = parent_rate;
- struct clk_master *master = to_clk_master(hw);
- - struct at91_pmc *pmc = master->pmc;
- const struct clk_master_layout *layout = master->layout;
- const struct clk_master_characteristics *characteristics =
- master->characteristics;
- - u32 tmp;
- + unsigned int mckr;
-
- - pmc_lock(pmc);
- - tmp = pmc_read(pmc, AT91_PMC_MCKR) & layout->mask;
- - pmc_unlock(pmc);
- + regmap_read(master->regmap, AT91_PMC_MCKR, &mckr);
- + mckr &= layout->mask;
-
- - pres = (tmp >> layout->pres_shift) & MASTER_PRES_MASK;
- - div = (tmp >> MASTER_DIV_SHIFT) & MASTER_DIV_MASK;
- + pres = (mckr >> layout->pres_shift) & MASTER_PRES_MASK;
- + div = (mckr >> MASTER_DIV_SHIFT) & MASTER_DIV_MASK;
-
- if (characteristics->have_div3_pres && pres == MASTER_PRES_MAX)
- rate /= 3;
- @@ -119,9 +106,11 @@
- static u8 clk_master_get_parent(struct clk_hw *hw)
- {
- struct clk_master *master = to_clk_master(hw);
- - struct at91_pmc *pmc = master->pmc;
- + unsigned int mckr;
-
- - return pmc_read(pmc, AT91_PMC_MCKR) & AT91_PMC_CSS;
- + regmap_read(master->regmap, AT91_PMC_MCKR, &mckr);
- +
- + return mckr & AT91_PMC_CSS;
- }
-
- static const struct clk_ops master_ops = {
- @@ -132,18 +121,17 @@
- };
-
- static struct clk * __init
- -at91_clk_register_master(struct at91_pmc *pmc, unsigned int irq,
- +at91_clk_register_master(struct regmap *regmap,
- const char *name, int num_parents,
- const char **parent_names,
- const struct clk_master_layout *layout,
- const struct clk_master_characteristics *characteristics)
- {
- - int ret;
- struct clk_master *master;
- struct clk *clk = NULL;
- struct clk_init_data init;
-
- - if (!pmc || !irq || !name || !num_parents || !parent_names)
- + if (!name || !num_parents || !parent_names)
- return ERR_PTR(-EINVAL);
-
- master = kzalloc(sizeof(*master), GFP_KERNEL);
- @@ -159,20 +147,10 @@
- master->hw.init = &init;
- master->layout = layout;
- master->characteristics = characteristics;
- - master->pmc = pmc;
- - master->irq = irq;
- - init_waitqueue_head(&master->wait);
- - irq_set_status_flags(master->irq, IRQ_NOAUTOEN);
- - ret = request_irq(master->irq, clk_master_irq_handler,
- - IRQF_TRIGGER_HIGH, "clk-master", master);
- - if (ret) {
- - kfree(master);
- - return ERR_PTR(ret);
- - }
- + master->regmap = regmap;
-
- clk = clk_register(NULL, &master->hw);
- if (IS_ERR(clk)) {
- - free_irq(master->irq, master);
- kfree(master);
- }
-
- @@ -217,15 +195,15 @@
- }
-
- static void __init
- -of_at91_clk_master_setup(struct device_node *np, struct at91_pmc *pmc,
- +of_at91_clk_master_setup(struct device_node *np,
- const struct clk_master_layout *layout)
- {
- struct clk *clk;
- int num_parents;
- - unsigned int irq;
- const char *parent_names[MASTER_SOURCE_MAX];
- const char *name = np->name;
- struct clk_master_characteristics *characteristics;
- + struct regmap *regmap;
-
- num_parents = of_clk_get_parent_count(np);
- if (num_parents <= 0 || num_parents > MASTER_SOURCE_MAX)
- @@ -239,11 +217,11 @@
- if (!characteristics)
- return;
-
- - irq = irq_of_parse_and_map(np, 0);
- - if (!irq)
- - goto out_free_characteristics;
- + regmap = syscon_node_to_regmap(of_get_parent(np));
- + if (IS_ERR(regmap))
- + return;
-
- - clk = at91_clk_register_master(pmc, irq, name, num_parents,
- + clk = at91_clk_register_master(regmap, name, num_parents,
- parent_names, layout,
- characteristics);
- if (IS_ERR(clk))
- @@ -256,14 +234,16 @@
- kfree(characteristics);
- }
-
- -void __init of_at91rm9200_clk_master_setup(struct device_node *np,
- - struct at91_pmc *pmc)
- +static void __init of_at91rm9200_clk_master_setup(struct device_node *np)
- {
- - of_at91_clk_master_setup(np, pmc, &at91rm9200_master_layout);
- + of_at91_clk_master_setup(np, &at91rm9200_master_layout);
- }
- +CLK_OF_DECLARE(at91rm9200_clk_master, "atmel,at91rm9200-clk-master",
- + of_at91rm9200_clk_master_setup);
-
- -void __init of_at91sam9x5_clk_master_setup(struct device_node *np,
- - struct at91_pmc *pmc)
- +static void __init of_at91sam9x5_clk_master_setup(struct device_node *np)
- {
- - of_at91_clk_master_setup(np, pmc, &at91sam9x5_master_layout);
- + of_at91_clk_master_setup(np, &at91sam9x5_master_layout);
- }
- +CLK_OF_DECLARE(at91sam9x5_clk_master, "atmel,at91sam9x5-clk-master",
- + of_at91sam9x5_clk_master_setup);
- diff -Nur linux-4.4.28.orig/drivers/clk/at91/clk-peripheral.c linux-4.4.28/drivers/clk/at91/clk-peripheral.c
- --- linux-4.4.28.orig/drivers/clk/at91/clk-peripheral.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/clk/at91/clk-peripheral.c 2016-11-01 21:26:57.920287105 +0100
- @@ -12,11 +12,13 @@
- #include <linux/clkdev.h>
- #include <linux/clk/at91_pmc.h>
- #include <linux/of.h>
- -#include <linux/of_address.h>
- -#include <linux/io.h>
- +#include <linux/mfd/syscon.h>
- +#include <linux/regmap.h>
-
- #include "pmc.h"
-
- +DEFINE_SPINLOCK(pmc_pcr_lock);
- +
- #define PERIPHERAL_MAX 64
-
- #define PERIPHERAL_AT91RM9200 0
- @@ -33,7 +35,7 @@
-
- struct clk_peripheral {
- struct clk_hw hw;
- - struct at91_pmc *pmc;
- + struct regmap *regmap;
- u32 id;
- };
-
- @@ -41,8 +43,9 @@
-
- struct clk_sam9x5_peripheral {
- struct clk_hw hw;
- - struct at91_pmc *pmc;
- + struct regmap *regmap;
- struct clk_range range;
- + spinlock_t *lock;
- u32 id;
- u32 div;
- bool auto_div;
- @@ -54,7 +57,6 @@
- static int clk_peripheral_enable(struct clk_hw *hw)
- {
- struct clk_peripheral *periph = to_clk_peripheral(hw);
- - struct at91_pmc *pmc = periph->pmc;
- int offset = AT91_PMC_PCER;
- u32 id = periph->id;
-
- @@ -62,14 +64,14 @@
- return 0;
- if (id > PERIPHERAL_ID_MAX)
- offset = AT91_PMC_PCER1;
- - pmc_write(pmc, offset, PERIPHERAL_MASK(id));
- + regmap_write(periph->regmap, offset, PERIPHERAL_MASK(id));
- +
- return 0;
- }
-
- static void clk_peripheral_disable(struct clk_hw *hw)
- {
- struct clk_peripheral *periph = to_clk_peripheral(hw);
- - struct at91_pmc *pmc = periph->pmc;
- int offset = AT91_PMC_PCDR;
- u32 id = periph->id;
-
- @@ -77,21 +79,23 @@
- return;
- if (id > PERIPHERAL_ID_MAX)
- offset = AT91_PMC_PCDR1;
- - pmc_write(pmc, offset, PERIPHERAL_MASK(id));
- + regmap_write(periph->regmap, offset, PERIPHERAL_MASK(id));
- }
-
- static int clk_peripheral_is_enabled(struct clk_hw *hw)
- {
- struct clk_peripheral *periph = to_clk_peripheral(hw);
- - struct at91_pmc *pmc = periph->pmc;
- int offset = AT91_PMC_PCSR;
- + unsigned int status;
- u32 id = periph->id;
-
- if (id < PERIPHERAL_ID_MIN)
- return 1;
- if (id > PERIPHERAL_ID_MAX)
- offset = AT91_PMC_PCSR1;
- - return !!(pmc_read(pmc, offset) & PERIPHERAL_MASK(id));
- + regmap_read(periph->regmap, offset, &status);
- +
- + return status & PERIPHERAL_MASK(id) ? 1 : 0;
- }
-
- static const struct clk_ops peripheral_ops = {
- @@ -101,14 +105,14 @@
- };
-
- static struct clk * __init
- -at91_clk_register_peripheral(struct at91_pmc *pmc, const char *name,
- +at91_clk_register_peripheral(struct regmap *regmap, const char *name,
- const char *parent_name, u32 id)
- {
- struct clk_peripheral *periph;
- struct clk *clk = NULL;
- struct clk_init_data init;
-
- - if (!pmc || !name || !parent_name || id > PERIPHERAL_ID_MAX)
- + if (!name || !parent_name || id > PERIPHERAL_ID_MAX)
- return ERR_PTR(-EINVAL);
-
- periph = kzalloc(sizeof(*periph), GFP_KERNEL);
- @@ -123,7 +127,7 @@
-
- periph->id = id;
- periph->hw.init = &init;
- - periph->pmc = pmc;
- + periph->regmap = regmap;
-
- clk = clk_register(NULL, &periph->hw);
- if (IS_ERR(clk))
- @@ -160,53 +164,58 @@
- static int clk_sam9x5_peripheral_enable(struct clk_hw *hw)
- {
- struct clk_sam9x5_peripheral *periph = to_clk_sam9x5_peripheral(hw);
- - struct at91_pmc *pmc = periph->pmc;
- - u32 tmp;
- + unsigned long flags;
-
- if (periph->id < PERIPHERAL_ID_MIN)
- return 0;
-
- - pmc_lock(pmc);
- - pmc_write(pmc, AT91_PMC_PCR, (periph->id & AT91_PMC_PCR_PID_MASK));
- - tmp = pmc_read(pmc, AT91_PMC_PCR) & ~AT91_PMC_PCR_DIV_MASK;
- - pmc_write(pmc, AT91_PMC_PCR, tmp | AT91_PMC_PCR_DIV(periph->div)
- - | AT91_PMC_PCR_CMD
- - | AT91_PMC_PCR_EN);
- - pmc_unlock(pmc);
- + spin_lock_irqsave(periph->lock, flags);
- + regmap_write(periph->regmap, AT91_PMC_PCR,
- + (periph->id & AT91_PMC_PCR_PID_MASK));
- + regmap_update_bits(periph->regmap, AT91_PMC_PCR,
- + AT91_PMC_PCR_DIV_MASK | AT91_PMC_PCR_CMD |
- + AT91_PMC_PCR_EN,
- + AT91_PMC_PCR_DIV(periph->div) |
- + AT91_PMC_PCR_CMD |
- + AT91_PMC_PCR_EN);
- + spin_unlock_irqrestore(periph->lock, flags);
- +
- return 0;
- }
-
- static void clk_sam9x5_peripheral_disable(struct clk_hw *hw)
- {
- struct clk_sam9x5_peripheral *periph = to_clk_sam9x5_peripheral(hw);
- - struct at91_pmc *pmc = periph->pmc;
- - u32 tmp;
- + unsigned long flags;
-
- if (periph->id < PERIPHERAL_ID_MIN)
- return;
-
- - pmc_lock(pmc);
- - pmc_write(pmc, AT91_PMC_PCR, (periph->id & AT91_PMC_PCR_PID_MASK));
- - tmp = pmc_read(pmc, AT91_PMC_PCR) & ~AT91_PMC_PCR_EN;
- - pmc_write(pmc, AT91_PMC_PCR, tmp | AT91_PMC_PCR_CMD);
- - pmc_unlock(pmc);
- + spin_lock_irqsave(periph->lock, flags);
- + regmap_write(periph->regmap, AT91_PMC_PCR,
- + (periph->id & AT91_PMC_PCR_PID_MASK));
- + regmap_update_bits(periph->regmap, AT91_PMC_PCR,
- + AT91_PMC_PCR_EN | AT91_PMC_PCR_CMD,
- + AT91_PMC_PCR_CMD);
- + spin_unlock_irqrestore(periph->lock, flags);
- }
-
- static int clk_sam9x5_peripheral_is_enabled(struct clk_hw *hw)
- {
- struct clk_sam9x5_peripheral *periph = to_clk_sam9x5_peripheral(hw);
- - struct at91_pmc *pmc = periph->pmc;
- - int ret;
- + unsigned long flags;
- + unsigned int status;
-
- if (periph->id < PERIPHERAL_ID_MIN)
- return 1;
-
- - pmc_lock(pmc);
- - pmc_write(pmc, AT91_PMC_PCR, (periph->id & AT91_PMC_PCR_PID_MASK));
- - ret = !!(pmc_read(pmc, AT91_PMC_PCR) & AT91_PMC_PCR_EN);
- - pmc_unlock(pmc);
- + spin_lock_irqsave(periph->lock, flags);
- + regmap_write(periph->regmap, AT91_PMC_PCR,
- + (periph->id & AT91_PMC_PCR_PID_MASK));
- + regmap_read(periph->regmap, AT91_PMC_PCR, &status);
- + spin_unlock_irqrestore(periph->lock, flags);
-
- - return ret;
- + return status & AT91_PMC_PCR_EN ? 1 : 0;
- }
-
- static unsigned long
- @@ -214,19 +223,20 @@
- unsigned long parent_rate)
- {
- struct clk_sam9x5_peripheral *periph = to_clk_sam9x5_peripheral(hw);
- - struct at91_pmc *pmc = periph->pmc;
- - u32 tmp;
- + unsigned long flags;
- + unsigned int status;
-
- if (periph->id < PERIPHERAL_ID_MIN)
- return parent_rate;
-
- - pmc_lock(pmc);
- - pmc_write(pmc, AT91_PMC_PCR, (periph->id & AT91_PMC_PCR_PID_MASK));
- - tmp = pmc_read(pmc, AT91_PMC_PCR);
- - pmc_unlock(pmc);
- + spin_lock_irqsave(periph->lock, flags);
- + regmap_write(periph->regmap, AT91_PMC_PCR,
- + (periph->id & AT91_PMC_PCR_PID_MASK));
- + regmap_read(periph->regmap, AT91_PMC_PCR, &status);
- + spin_unlock_irqrestore(periph->lock, flags);
-
- - if (tmp & AT91_PMC_PCR_EN) {
- - periph->div = PERIPHERAL_RSHIFT(tmp);
- + if (status & AT91_PMC_PCR_EN) {
- + periph->div = PERIPHERAL_RSHIFT(status);
- periph->auto_div = false;
- } else {
- clk_sam9x5_peripheral_autodiv(periph);
- @@ -318,15 +328,15 @@
- };
-
- static struct clk * __init
- -at91_clk_register_sam9x5_peripheral(struct at91_pmc *pmc, const char *name,
- - const char *parent_name, u32 id,
- - const struct clk_range *range)
- +at91_clk_register_sam9x5_peripheral(struct regmap *regmap, spinlock_t *lock,
- + const char *name, const char *parent_name,
- + u32 id, const struct clk_range *range)
- {
- struct clk_sam9x5_peripheral *periph;
- struct clk *clk = NULL;
- struct clk_init_data init;
-
- - if (!pmc || !name || !parent_name)
- + if (!name || !parent_name)
- return ERR_PTR(-EINVAL);
-
- periph = kzalloc(sizeof(*periph), GFP_KERNEL);
- @@ -342,7 +352,8 @@
- periph->id = id;
- periph->hw.init = &init;
- periph->div = 0;
- - periph->pmc = pmc;
- + periph->regmap = regmap;
- + periph->lock = lock;
- periph->auto_div = true;
- periph->range = *range;
-
- @@ -356,7 +367,7 @@
- }
-
- static void __init
- -of_at91_clk_periph_setup(struct device_node *np, struct at91_pmc *pmc, u8 type)
- +of_at91_clk_periph_setup(struct device_node *np, u8 type)
- {
- int num;
- u32 id;
- @@ -364,6 +375,7 @@
- const char *parent_name;
- const char *name;
- struct device_node *periphclknp;
- + struct regmap *regmap;
-
- parent_name = of_clk_get_parent_name(np, 0);
- if (!parent_name)
- @@ -373,6 +385,10 @@
- if (!num || num > PERIPHERAL_MAX)
- return;
-
- + regmap = syscon_node_to_regmap(of_get_parent(np));
- + if (IS_ERR(regmap))
- + return;
- +
- for_each_child_of_node(np, periphclknp) {
- if (of_property_read_u32(periphclknp, "reg", &id))
- continue;
- @@ -384,7 +400,7 @@
- name = periphclknp->name;
-
- if (type == PERIPHERAL_AT91RM9200) {
- - clk = at91_clk_register_peripheral(pmc, name,
- + clk = at91_clk_register_peripheral(regmap, name,
- parent_name, id);
- } else {
- struct clk_range range = CLK_RANGE(0, 0);
- @@ -393,7 +409,9 @@
- "atmel,clk-output-range",
- &range);
-
- - clk = at91_clk_register_sam9x5_peripheral(pmc, name,
- + clk = at91_clk_register_sam9x5_peripheral(regmap,
- + &pmc_pcr_lock,
- + name,
- parent_name,
- id, &range);
- }
- @@ -405,14 +423,16 @@
- }
- }
-
- -void __init of_at91rm9200_clk_periph_setup(struct device_node *np,
- - struct at91_pmc *pmc)
- +static void __init of_at91rm9200_clk_periph_setup(struct device_node *np)
- {
- - of_at91_clk_periph_setup(np, pmc, PERIPHERAL_AT91RM9200);
- + of_at91_clk_periph_setup(np, PERIPHERAL_AT91RM9200);
- }
- +CLK_OF_DECLARE(at91rm9200_clk_periph, "atmel,at91rm9200-clk-peripheral",
- + of_at91rm9200_clk_periph_setup);
-
- -void __init of_at91sam9x5_clk_periph_setup(struct device_node *np,
- - struct at91_pmc *pmc)
- +static void __init of_at91sam9x5_clk_periph_setup(struct device_node *np)
- {
- - of_at91_clk_periph_setup(np, pmc, PERIPHERAL_AT91SAM9X5);
- + of_at91_clk_periph_setup(np, PERIPHERAL_AT91SAM9X5);
- }
- +CLK_OF_DECLARE(at91sam9x5_clk_periph, "atmel,at91sam9x5-clk-peripheral",
- + of_at91sam9x5_clk_periph_setup);
- diff -Nur linux-4.4.28.orig/drivers/clk/at91/clk-pll.c linux-4.4.28/drivers/clk/at91/clk-pll.c
- --- linux-4.4.28.orig/drivers/clk/at91/clk-pll.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/clk/at91/clk-pll.c 2016-11-01 21:26:57.924287358 +0100
- @@ -12,14 +12,8 @@
- #include <linux/clkdev.h>
- #include <linux/clk/at91_pmc.h>
- #include <linux/of.h>
- -#include <linux/of_address.h>
- -#include <linux/of_irq.h>
- -#include <linux/io.h>
- -#include <linux/kernel.h>
- -#include <linux/wait.h>
- -#include <linux/sched.h>
- -#include <linux/interrupt.h>
- -#include <linux/irq.h>
- +#include <linux/mfd/syscon.h>
- +#include <linux/regmap.h>
-
- #include "pmc.h"
-
- @@ -58,9 +52,7 @@
-
- struct clk_pll {
- struct clk_hw hw;
- - struct at91_pmc *pmc;
- - unsigned int irq;
- - wait_queue_head_t wait;
- + struct regmap *regmap;
- u8 id;
- u8 div;
- u8 range;
- @@ -69,20 +61,19 @@
- const struct clk_pll_characteristics *characteristics;
- };
-
- -static irqreturn_t clk_pll_irq_handler(int irq, void *dev_id)
- +static inline bool clk_pll_ready(struct regmap *regmap, int id)
- {
- - struct clk_pll *pll = (struct clk_pll *)dev_id;
- + unsigned int status;
-
- - wake_up(&pll->wait);
- - disable_irq_nosync(pll->irq);
- + regmap_read(regmap, AT91_PMC_SR, &status);
-
- - return IRQ_HANDLED;
- + return status & PLL_STATUS_MASK(id) ? 1 : 0;
- }
-
- static int clk_pll_prepare(struct clk_hw *hw)
- {
- struct clk_pll *pll = to_clk_pll(hw);
- - struct at91_pmc *pmc = pll->pmc;
- + struct regmap *regmap = pll->regmap;
- const struct clk_pll_layout *layout = pll->layout;
- const struct clk_pll_characteristics *characteristics =
- pll->characteristics;
- @@ -90,39 +81,34 @@
- u32 mask = PLL_STATUS_MASK(id);
- int offset = PLL_REG(id);
- u8 out = 0;
- - u32 pllr, icpr;
- + unsigned int pllr;
- + unsigned int status;
- u8 div;
- u16 mul;
-
- - pllr = pmc_read(pmc, offset);
- + regmap_read(regmap, offset, &pllr);
- div = PLL_DIV(pllr);
- mul = PLL_MUL(pllr, layout);
-
- - if ((pmc_read(pmc, AT91_PMC_SR) & mask) &&
- + regmap_read(regmap, AT91_PMC_SR, &status);
- + if ((status & mask) &&
- (div == pll->div && mul == pll->mul))
- return 0;
-
- if (characteristics->out)
- out = characteristics->out[pll->range];
- - if (characteristics->icpll) {
- - icpr = pmc_read(pmc, AT91_PMC_PLLICPR) & ~PLL_ICPR_MASK(id);
- - icpr |= (characteristics->icpll[pll->range] <<
- - PLL_ICPR_SHIFT(id));
- - pmc_write(pmc, AT91_PMC_PLLICPR, icpr);
- - }
-
- - pllr &= ~layout->pllr_mask;
- - pllr |= layout->pllr_mask &
- - (pll->div | (PLL_MAX_COUNT << PLL_COUNT_SHIFT) |
- - (out << PLL_OUT_SHIFT) |
- - ((pll->mul & layout->mul_mask) << layout->mul_shift));
- - pmc_write(pmc, offset, pllr);
- -
- - while (!(pmc_read(pmc, AT91_PMC_SR) & mask)) {
- - enable_irq(pll->irq);
- - wait_event(pll->wait,
- - pmc_read(pmc, AT91_PMC_SR) & mask);
- - }
- + if (characteristics->icpll)
- + regmap_update_bits(regmap, AT91_PMC_PLLICPR, PLL_ICPR_MASK(id),
- + characteristics->icpll[pll->range] << PLL_ICPR_SHIFT(id));
- +
- + regmap_update_bits(regmap, offset, layout->pllr_mask,
- + pll->div | (PLL_MAX_COUNT << PLL_COUNT_SHIFT) |
- + (out << PLL_OUT_SHIFT) |
- + ((pll->mul & layout->mul_mask) << layout->mul_shift));
- +
- + while (!clk_pll_ready(regmap, pll->id))
- + cpu_relax();
-
- return 0;
- }
- @@ -130,32 +116,35 @@
- static int clk_pll_is_prepared(struct clk_hw *hw)
- {
- struct clk_pll *pll = to_clk_pll(hw);
- - struct at91_pmc *pmc = pll->pmc;
-
- - return !!(pmc_read(pmc, AT91_PMC_SR) &
- - PLL_STATUS_MASK(pll->id));
- + return clk_pll_ready(pll->regmap, pll->id);
- }
-
- static void clk_pll_unprepare(struct clk_hw *hw)
- {
- struct clk_pll *pll = to_clk_pll(hw);
- - struct at91_pmc *pmc = pll->pmc;
- - const struct clk_pll_layout *layout = pll->layout;
- - int offset = PLL_REG(pll->id);
- - u32 tmp = pmc_read(pmc, offset) & ~(layout->pllr_mask);
- + unsigned int mask = pll->layout->pllr_mask;
-
- - pmc_write(pmc, offset, tmp);
- + regmap_update_bits(pll->regmap, PLL_REG(pll->id), mask, ~mask);
- }
-
- static unsigned long clk_pll_recalc_rate(struct clk_hw *hw,
- unsigned long parent_rate)
- {
- struct clk_pll *pll = to_clk_pll(hw);
- + unsigned int pllr;
- + u16 mul;
- + u8 div;
- +
- + regmap_read(pll->regmap, PLL_REG(pll->id), &pllr);
- +
- + div = PLL_DIV(pllr);
- + mul = PLL_MUL(pllr, pll->layout);
-
- - if (!pll->div || !pll->mul)
- + if (!div || !mul)
- return 0;
-
- - return (parent_rate / pll->div) * (pll->mul + 1);
- + return (parent_rate / div) * (mul + 1);
- }
-
- static long clk_pll_get_best_div_mul(struct clk_pll *pll, unsigned long rate,
- @@ -308,7 +297,7 @@
- };
-
- static struct clk * __init
- -at91_clk_register_pll(struct at91_pmc *pmc, unsigned int irq, const char *name,
- +at91_clk_register_pll(struct regmap *regmap, const char *name,
- const char *parent_name, u8 id,
- const struct clk_pll_layout *layout,
- const struct clk_pll_characteristics *characteristics)
- @@ -316,9 +305,8 @@
- struct clk_pll *pll;
- struct clk *clk = NULL;
- struct clk_init_data init;
- - int ret;
- int offset = PLL_REG(id);
- - u32 tmp;
- + unsigned int pllr;
-
- if (id > PLL_MAX_ID)
- return ERR_PTR(-EINVAL);
- @@ -337,23 +325,13 @@
- pll->hw.init = &init;
- pll->layout = layout;
- pll->characteristics = characteristics;
- - pll->pmc = pmc;
- - pll->irq = irq;
- - tmp = pmc_read(pmc, offset) & layout->pllr_mask;
- - pll->div = PLL_DIV(tmp);
- - pll->mul = PLL_MUL(tmp, layout);
- - init_waitqueue_head(&pll->wait);
- - irq_set_status_flags(pll->irq, IRQ_NOAUTOEN);
- - ret = request_irq(pll->irq, clk_pll_irq_handler, IRQF_TRIGGER_HIGH,
- - id ? "clk-pllb" : "clk-plla", pll);
- - if (ret) {
- - kfree(pll);
- - return ERR_PTR(ret);
- - }
- + pll->regmap = regmap;
- + regmap_read(regmap, offset, &pllr);
- + pll->div = PLL_DIV(pllr);
- + pll->mul = PLL_MUL(pllr, layout);
-
- clk = clk_register(NULL, &pll->hw);
- if (IS_ERR(clk)) {
- - free_irq(pll->irq, pll);
- kfree(pll);
- }
-
- @@ -483,12 +461,12 @@
- }
-
- static void __init
- -of_at91_clk_pll_setup(struct device_node *np, struct at91_pmc *pmc,
- +of_at91_clk_pll_setup(struct device_node *np,
- const struct clk_pll_layout *layout)
- {
- u32 id;
- - unsigned int irq;
- struct clk *clk;
- + struct regmap *regmap;
- const char *parent_name;
- const char *name = np->name;
- struct clk_pll_characteristics *characteristics;
- @@ -500,15 +478,15 @@
-
- of_property_read_string(np, "clock-output-names", &name);
-
- - characteristics = of_at91_clk_pll_get_characteristics(np);
- - if (!characteristics)
- + regmap = syscon_node_to_regmap(of_get_parent(np));
- + if (IS_ERR(regmap))
- return;
-
- - irq = irq_of_parse_and_map(np, 0);
- - if (!irq)
- + characteristics = of_at91_clk_pll_get_characteristics(np);
- + if (!characteristics)
- return;
-
- - clk = at91_clk_register_pll(pmc, irq, name, parent_name, id, layout,
- + clk = at91_clk_register_pll(regmap, name, parent_name, id, layout,
- characteristics);
- if (IS_ERR(clk))
- goto out_free_characteristics;
- @@ -520,26 +498,30 @@
- kfree(characteristics);
- }
-
- -void __init of_at91rm9200_clk_pll_setup(struct device_node *np,
- - struct at91_pmc *pmc)
- +static void __init of_at91rm9200_clk_pll_setup(struct device_node *np)
- {
- - of_at91_clk_pll_setup(np, pmc, &at91rm9200_pll_layout);
- + of_at91_clk_pll_setup(np, &at91rm9200_pll_layout);
- }
- +CLK_OF_DECLARE(at91rm9200_clk_pll, "atmel,at91rm9200-clk-pll",
- + of_at91rm9200_clk_pll_setup);
-
- -void __init of_at91sam9g45_clk_pll_setup(struct device_node *np,
- - struct at91_pmc *pmc)
- +static void __init of_at91sam9g45_clk_pll_setup(struct device_node *np)
- {
- - of_at91_clk_pll_setup(np, pmc, &at91sam9g45_pll_layout);
- + of_at91_clk_pll_setup(np, &at91sam9g45_pll_layout);
- }
- +CLK_OF_DECLARE(at91sam9g45_clk_pll, "atmel,at91sam9g45-clk-pll",
- + of_at91sam9g45_clk_pll_setup);
-
- -void __init of_at91sam9g20_clk_pllb_setup(struct device_node *np,
- - struct at91_pmc *pmc)
- +static void __init of_at91sam9g20_clk_pllb_setup(struct device_node *np)
- {
- - of_at91_clk_pll_setup(np, pmc, &at91sam9g20_pllb_layout);
- + of_at91_clk_pll_setup(np, &at91sam9g20_pllb_layout);
- }
- +CLK_OF_DECLARE(at91sam9g20_clk_pllb, "atmel,at91sam9g20-clk-pllb",
- + of_at91sam9g20_clk_pllb_setup);
-
- -void __init of_sama5d3_clk_pll_setup(struct device_node *np,
- - struct at91_pmc *pmc)
- +static void __init of_sama5d3_clk_pll_setup(struct device_node *np)
- {
- - of_at91_clk_pll_setup(np, pmc, &sama5d3_pll_layout);
- + of_at91_clk_pll_setup(np, &sama5d3_pll_layout);
- }
- +CLK_OF_DECLARE(sama5d3_clk_pll, "atmel,sama5d3-clk-pll",
- + of_sama5d3_clk_pll_setup);
- diff -Nur linux-4.4.28.orig/drivers/clk/at91/clk-plldiv.c linux-4.4.28/drivers/clk/at91/clk-plldiv.c
- --- linux-4.4.28.orig/drivers/clk/at91/clk-plldiv.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/clk/at91/clk-plldiv.c 2016-11-01 21:26:57.924287358 +0100
- @@ -12,8 +12,8 @@
- #include <linux/clkdev.h>
- #include <linux/clk/at91_pmc.h>
- #include <linux/of.h>
- -#include <linux/of_address.h>
- -#include <linux/io.h>
- +#include <linux/mfd/syscon.h>
- +#include <linux/regmap.h>
-
- #include "pmc.h"
-
- @@ -21,16 +21,18 @@
-
- struct clk_plldiv {
- struct clk_hw hw;
- - struct at91_pmc *pmc;
- + struct regmap *regmap;
- };
-
- static unsigned long clk_plldiv_recalc_rate(struct clk_hw *hw,
- unsigned long parent_rate)
- {
- struct clk_plldiv *plldiv = to_clk_plldiv(hw);
- - struct at91_pmc *pmc = plldiv->pmc;
- + unsigned int mckr;
-
- - if (pmc_read(pmc, AT91_PMC_MCKR) & AT91_PMC_PLLADIV2)
- + regmap_read(plldiv->regmap, AT91_PMC_MCKR, &mckr);
- +
- + if (mckr & AT91_PMC_PLLADIV2)
- return parent_rate / 2;
-
- return parent_rate;
- @@ -57,18 +59,12 @@
- unsigned long parent_rate)
- {
- struct clk_plldiv *plldiv = to_clk_plldiv(hw);
- - struct at91_pmc *pmc = plldiv->pmc;
- - u32 tmp;
-
- - if (parent_rate != rate && (parent_rate / 2) != rate)
- + if ((parent_rate != rate) && (parent_rate / 2 != rate))
- return -EINVAL;
-
- - pmc_lock(pmc);
- - tmp = pmc_read(pmc, AT91_PMC_MCKR) & ~AT91_PMC_PLLADIV2;
- - if ((parent_rate / 2) == rate)
- - tmp |= AT91_PMC_PLLADIV2;
- - pmc_write(pmc, AT91_PMC_MCKR, tmp);
- - pmc_unlock(pmc);
- + regmap_update_bits(plldiv->regmap, AT91_PMC_MCKR, AT91_PMC_PLLADIV2,
- + parent_rate != rate ? AT91_PMC_PLLADIV2 : 0);
-
- return 0;
- }
- @@ -80,7 +76,7 @@
- };
-
- static struct clk * __init
- -at91_clk_register_plldiv(struct at91_pmc *pmc, const char *name,
- +at91_clk_register_plldiv(struct regmap *regmap, const char *name,
- const char *parent_name)
- {
- struct clk_plldiv *plldiv;
- @@ -98,7 +94,7 @@
- init.flags = CLK_SET_RATE_GATE;
-
- plldiv->hw.init = &init;
- - plldiv->pmc = pmc;
- + plldiv->regmap = regmap;
-
- clk = clk_register(NULL, &plldiv->hw);
-
- @@ -109,27 +105,27 @@
- }
-
- static void __init
- -of_at91_clk_plldiv_setup(struct device_node *np, struct at91_pmc *pmc)
- +of_at91sam9x5_clk_plldiv_setup(struct device_node *np)
- {
- struct clk *clk;
- const char *parent_name;
- const char *name = np->name;
- + struct regmap *regmap;
-
- parent_name = of_clk_get_parent_name(np, 0);
-
- of_property_read_string(np, "clock-output-names", &name);
-
- - clk = at91_clk_register_plldiv(pmc, name, parent_name);
- + regmap = syscon_node_to_regmap(of_get_parent(np));
- + if (IS_ERR(regmap))
- + return;
-
- + clk = at91_clk_register_plldiv(regmap, name, parent_name);
- if (IS_ERR(clk))
- return;
-
- of_clk_add_provider(np, of_clk_src_simple_get, clk);
- return;
- }
- -
- -void __init of_at91sam9x5_clk_plldiv_setup(struct device_node *np,
- - struct at91_pmc *pmc)
- -{
- - of_at91_clk_plldiv_setup(np, pmc);
- -}
- +CLK_OF_DECLARE(at91sam9x5_clk_plldiv, "atmel,at91sam9x5-clk-plldiv",
- + of_at91sam9x5_clk_plldiv_setup);
- diff -Nur linux-4.4.28.orig/drivers/clk/at91/clk-programmable.c linux-4.4.28/drivers/clk/at91/clk-programmable.c
- --- linux-4.4.28.orig/drivers/clk/at91/clk-programmable.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/clk/at91/clk-programmable.c 2016-11-01 21:26:57.936288132 +0100
- @@ -12,10 +12,8 @@
- #include <linux/clkdev.h>
- #include <linux/clk/at91_pmc.h>
- #include <linux/of.h>
- -#include <linux/of_address.h>
- -#include <linux/io.h>
- -#include <linux/wait.h>
- -#include <linux/sched.h>
- +#include <linux/mfd/syscon.h>
- +#include <linux/regmap.h>
-
- #include "pmc.h"
-
- @@ -24,6 +22,7 @@
-
- #define PROG_STATUS_MASK(id) (1 << ((id) + 8))
- #define PROG_PRES_MASK 0x7
- +#define PROG_PRES(layout, pckr) ((pckr >> layout->pres_shift) & PROG_PRES_MASK)
- #define PROG_MAX_RM9200_CSS 3
-
- struct clk_programmable_layout {
- @@ -34,7 +33,7 @@
-
- struct clk_programmable {
- struct clk_hw hw;
- - struct at91_pmc *pmc;
- + struct regmap *regmap;
- u8 id;
- const struct clk_programmable_layout *layout;
- };
- @@ -44,14 +43,12 @@
- static unsigned long clk_programmable_recalc_rate(struct clk_hw *hw,
- unsigned long parent_rate)
- {
- - u32 pres;
- struct clk_programmable *prog = to_clk_programmable(hw);
- - struct at91_pmc *pmc = prog->pmc;
- - const struct clk_programmable_layout *layout = prog->layout;
- + unsigned int pckr;
- +
- + regmap_read(prog->regmap, AT91_PMC_PCKR(prog->id), &pckr);
-
- - pres = (pmc_read(pmc, AT91_PMC_PCKR(prog->id)) >> layout->pres_shift) &
- - PROG_PRES_MASK;
- - return parent_rate >> pres;
- + return parent_rate >> PROG_PRES(prog->layout, pckr);
- }
-
- static int clk_programmable_determine_rate(struct clk_hw *hw,
- @@ -101,36 +98,36 @@
- {
- struct clk_programmable *prog = to_clk_programmable(hw);
- const struct clk_programmable_layout *layout = prog->layout;
- - struct at91_pmc *pmc = prog->pmc;
- - u32 tmp = pmc_read(pmc, AT91_PMC_PCKR(prog->id)) & ~layout->css_mask;
- + unsigned int mask = layout->css_mask;
- + unsigned int pckr = 0;
-
- if (layout->have_slck_mck)
- - tmp &= AT91_PMC_CSSMCK_MCK;
- + mask |= AT91_PMC_CSSMCK_MCK;
-
- if (index > layout->css_mask) {
- - if (index > PROG_MAX_RM9200_CSS && layout->have_slck_mck) {
- - tmp |= AT91_PMC_CSSMCK_MCK;
- - return 0;
- - } else {
- + if (index > PROG_MAX_RM9200_CSS && !layout->have_slck_mck)
- return -EINVAL;
- - }
- +
- + pckr |= AT91_PMC_CSSMCK_MCK;
- }
-
- - pmc_write(pmc, AT91_PMC_PCKR(prog->id), tmp | index);
- + regmap_update_bits(prog->regmap, AT91_PMC_PCKR(prog->id), mask, pckr);
- +
- return 0;
- }
-
- static u8 clk_programmable_get_parent(struct clk_hw *hw)
- {
- - u32 tmp;
- - u8 ret;
- struct clk_programmable *prog = to_clk_programmable(hw);
- - struct at91_pmc *pmc = prog->pmc;
- const struct clk_programmable_layout *layout = prog->layout;
- + unsigned int pckr;
- + u8 ret;
- +
- + regmap_read(prog->regmap, AT91_PMC_PCKR(prog->id), &pckr);
- +
- + ret = pckr & layout->css_mask;
-
- - tmp = pmc_read(pmc, AT91_PMC_PCKR(prog->id));
- - ret = tmp & layout->css_mask;
- - if (layout->have_slck_mck && (tmp & AT91_PMC_CSSMCK_MCK) && !ret)
- + if (layout->have_slck_mck && (pckr & AT91_PMC_CSSMCK_MCK) && !ret)
- ret = PROG_MAX_RM9200_CSS + 1;
-
- return ret;
- @@ -140,26 +137,27 @@
- unsigned long parent_rate)
- {
- struct clk_programmable *prog = to_clk_programmable(hw);
- - struct at91_pmc *pmc = prog->pmc;
- const struct clk_programmable_layout *layout = prog->layout;
- unsigned long div = parent_rate / rate;
- + unsigned int pckr;
- int shift = 0;
- - u32 tmp = pmc_read(pmc, AT91_PMC_PCKR(prog->id)) &
- - ~(PROG_PRES_MASK << layout->pres_shift);
- +
- + regmap_read(prog->regmap, AT91_PMC_PCKR(prog->id), &pckr);
-
- if (!div)
- return -EINVAL;
-
- shift = fls(div) - 1;
-
- - if (div != (1<<shift))
- + if (div != (1 << shift))
- return -EINVAL;
-
- if (shift >= PROG_PRES_MASK)
- return -EINVAL;
-
- - pmc_write(pmc, AT91_PMC_PCKR(prog->id),
- - tmp | (shift << layout->pres_shift));
- + regmap_update_bits(prog->regmap, AT91_PMC_PCKR(prog->id),
- + PROG_PRES_MASK << layout->pres_shift,
- + shift << layout->pres_shift);
-
- return 0;
- }
- @@ -173,7 +171,7 @@
- };
-
- static struct clk * __init
- -at91_clk_register_programmable(struct at91_pmc *pmc,
- +at91_clk_register_programmable(struct regmap *regmap,
- const char *name, const char **parent_names,
- u8 num_parents, u8 id,
- const struct clk_programmable_layout *layout)
- @@ -198,7 +196,7 @@
- prog->id = id;
- prog->layout = layout;
- prog->hw.init = &init;
- - prog->pmc = pmc;
- + prog->regmap = regmap;
-
- clk = clk_register(NULL, &prog->hw);
- if (IS_ERR(clk))
- @@ -226,7 +224,7 @@
- };
-
- static void __init
- -of_at91_clk_prog_setup(struct device_node *np, struct at91_pmc *pmc,
- +of_at91_clk_prog_setup(struct device_node *np,
- const struct clk_programmable_layout *layout)
- {
- int num;
- @@ -236,6 +234,7 @@
- const char *parent_names[PROG_SOURCE_MAX];
- const char *name;
- struct device_node *progclknp;
- + struct regmap *regmap;
-
- num_parents = of_clk_get_parent_count(np);
- if (num_parents <= 0 || num_parents > PROG_SOURCE_MAX)
- @@ -247,6 +246,10 @@
- if (!num || num > (PROG_ID_MAX + 1))
- return;
-
- + regmap = syscon_node_to_regmap(of_get_parent(np));
- + if (IS_ERR(regmap))
- + return;
- +
- for_each_child_of_node(np, progclknp) {
- if (of_property_read_u32(progclknp, "reg", &id))
- continue;
- @@ -254,7 +257,7 @@
- if (of_property_read_string(np, "clock-output-names", &name))
- name = progclknp->name;
-
- - clk = at91_clk_register_programmable(pmc, name,
- + clk = at91_clk_register_programmable(regmap, name,
- parent_names, num_parents,
- id, layout);
- if (IS_ERR(clk))
- @@ -265,20 +268,23 @@
- }
-
-
- -void __init of_at91rm9200_clk_prog_setup(struct device_node *np,
- - struct at91_pmc *pmc)
- +static void __init of_at91rm9200_clk_prog_setup(struct device_node *np)
- {
- - of_at91_clk_prog_setup(np, pmc, &at91rm9200_programmable_layout);
- + of_at91_clk_prog_setup(np, &at91rm9200_programmable_layout);
- }
- +CLK_OF_DECLARE(at91rm9200_clk_prog, "atmel,at91rm9200-clk-programmable",
- + of_at91rm9200_clk_prog_setup);
-
- -void __init of_at91sam9g45_clk_prog_setup(struct device_node *np,
- - struct at91_pmc *pmc)
- +static void __init of_at91sam9g45_clk_prog_setup(struct device_node *np)
- {
- - of_at91_clk_prog_setup(np, pmc, &at91sam9g45_programmable_layout);
- + of_at91_clk_prog_setup(np, &at91sam9g45_programmable_layout);
- }
- +CLK_OF_DECLARE(at91sam9g45_clk_prog, "atmel,at91sam9g45-clk-programmable",
- + of_at91sam9g45_clk_prog_setup);
-
- -void __init of_at91sam9x5_clk_prog_setup(struct device_node *np,
- - struct at91_pmc *pmc)
- +static void __init of_at91sam9x5_clk_prog_setup(struct device_node *np)
- {
- - of_at91_clk_prog_setup(np, pmc, &at91sam9x5_programmable_layout);
- + of_at91_clk_prog_setup(np, &at91sam9x5_programmable_layout);
- }
- +CLK_OF_DECLARE(at91sam9x5_clk_prog, "atmel,at91sam9x5-clk-programmable",
- + of_at91sam9x5_clk_prog_setup);
- diff -Nur linux-4.4.28.orig/drivers/clk/at91/clk-slow.c linux-4.4.28/drivers/clk/at91/clk-slow.c
- --- linux-4.4.28.orig/drivers/clk/at91/clk-slow.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/clk/at91/clk-slow.c 2016-11-01 21:26:57.940288388 +0100
- @@ -13,17 +13,11 @@
- #include <linux/clk.h>
- #include <linux/clk-provider.h>
- #include <linux/clkdev.h>
- -#include <linux/slab.h>
- #include <linux/clk/at91_pmc.h>
- #include <linux/delay.h>
- #include <linux/of.h>
- -#include <linux/of_address.h>
- -#include <linux/of_irq.h>
- -#include <linux/io.h>
- -#include <linux/interrupt.h>
- -#include <linux/irq.h>
- -#include <linux/sched.h>
- -#include <linux/wait.h>
- +#include <linux/mfd/syscon.h>
- +#include <linux/regmap.h>
-
- #include "pmc.h"
- #include "sckc.h"
- @@ -59,7 +53,7 @@
-
- struct clk_sam9260_slow {
- struct clk_hw hw;
- - struct at91_pmc *pmc;
- + struct regmap *regmap;
- };
-
- #define to_clk_sam9260_slow(hw) container_of(hw, struct clk_sam9260_slow, hw)
- @@ -393,8 +387,11 @@
- static u8 clk_sam9260_slow_get_parent(struct clk_hw *hw)
- {
- struct clk_sam9260_slow *slowck = to_clk_sam9260_slow(hw);
- + unsigned int status;
-
- - return !!(pmc_read(slowck->pmc, AT91_PMC_SR) & AT91_PMC_OSCSEL);
- + regmap_read(slowck->regmap, AT91_PMC_SR, &status);
- +
- + return status & AT91_PMC_OSCSEL ? 1 : 0;
- }
-
- static const struct clk_ops sam9260_slow_ops = {
- @@ -402,7 +399,7 @@
- };
-
- static struct clk * __init
- -at91_clk_register_sam9260_slow(struct at91_pmc *pmc,
- +at91_clk_register_sam9260_slow(struct regmap *regmap,
- const char *name,
- const char **parent_names,
- int num_parents)
- @@ -411,7 +408,7 @@
- struct clk *clk = NULL;
- struct clk_init_data init;
-
- - if (!pmc || !name)
- + if (!name)
- return ERR_PTR(-EINVAL);
-
- if (!parent_names || !num_parents)
- @@ -428,7 +425,7 @@
- init.flags = 0;
-
- slowck->hw.init = &init;
- - slowck->pmc = pmc;
- + slowck->regmap = regmap;
-
- clk = clk_register(NULL, &slowck->hw);
- if (IS_ERR(clk))
- @@ -439,29 +436,34 @@
- return clk;
- }
-
- -void __init of_at91sam9260_clk_slow_setup(struct device_node *np,
- - struct at91_pmc *pmc)
- +static void __init of_at91sam9260_clk_slow_setup(struct device_node *np)
- {
- struct clk *clk;
- const char *parent_names[2];
- int num_parents;
- const char *name = np->name;
- + struct regmap *regmap;
-
- num_parents = of_clk_get_parent_count(np);
- if (num_parents != 2)
- return;
-
- of_clk_parent_fill(np, parent_names, num_parents);
- + regmap = syscon_node_to_regmap(of_get_parent(np));
- + if (IS_ERR(regmap))
- + return;
-
- of_property_read_string(np, "clock-output-names", &name);
-
- - clk = at91_clk_register_sam9260_slow(pmc, name, parent_names,
- + clk = at91_clk_register_sam9260_slow(regmap, name, parent_names,
- num_parents);
- if (IS_ERR(clk))
- return;
-
- of_clk_add_provider(np, of_clk_src_simple_get, clk);
- }
- +CLK_OF_DECLARE(at91sam9260_clk_slow, "atmel,at91sam9260-clk-slow",
- + of_at91sam9260_clk_slow_setup);
-
- /*
- * FIXME: All slow clk users are not properly claiming it (get + prepare +
- diff -Nur linux-4.4.28.orig/drivers/clk/at91/clk-smd.c linux-4.4.28/drivers/clk/at91/clk-smd.c
- --- linux-4.4.28.orig/drivers/clk/at91/clk-smd.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/clk/at91/clk-smd.c 2016-11-01 21:26:57.940288388 +0100
- @@ -12,8 +12,8 @@
- #include <linux/clkdev.h>
- #include <linux/clk/at91_pmc.h>
- #include <linux/of.h>
- -#include <linux/of_address.h>
- -#include <linux/io.h>
- +#include <linux/mfd/syscon.h>
- +#include <linux/regmap.h>
-
- #include "pmc.h"
-
- @@ -24,7 +24,7 @@
-
- struct at91sam9x5_clk_smd {
- struct clk_hw hw;
- - struct at91_pmc *pmc;
- + struct regmap *regmap;
- };
-
- #define to_at91sam9x5_clk_smd(hw) \
- @@ -33,13 +33,13 @@
- static unsigned long at91sam9x5_clk_smd_recalc_rate(struct clk_hw *hw,
- unsigned long parent_rate)
- {
- - u32 tmp;
- - u8 smddiv;
- struct at91sam9x5_clk_smd *smd = to_at91sam9x5_clk_smd(hw);
- - struct at91_pmc *pmc = smd->pmc;
- + unsigned int smdr;
- + u8 smddiv;
- +
- + regmap_read(smd->regmap, AT91_PMC_SMD, &smdr);
- + smddiv = (smdr & AT91_PMC_SMD_DIV) >> SMD_DIV_SHIFT;
-
- - tmp = pmc_read(pmc, AT91_PMC_SMD);
- - smddiv = (tmp & AT91_PMC_SMD_DIV) >> SMD_DIV_SHIFT;
- return parent_rate / (smddiv + 1);
- }
-
- @@ -67,40 +67,38 @@
-
- static int at91sam9x5_clk_smd_set_parent(struct clk_hw *hw, u8 index)
- {
- - u32 tmp;
- struct at91sam9x5_clk_smd *smd = to_at91sam9x5_clk_smd(hw);
- - struct at91_pmc *pmc = smd->pmc;
-
- if (index > 1)
- return -EINVAL;
- - tmp = pmc_read(pmc, AT91_PMC_SMD) & ~AT91_PMC_SMDS;
- - if (index)
- - tmp |= AT91_PMC_SMDS;
- - pmc_write(pmc, AT91_PMC_SMD, tmp);
- +
- + regmap_update_bits(smd->regmap, AT91_PMC_SMD, AT91_PMC_SMDS,
- + index ? AT91_PMC_SMDS : 0);
- +
- return 0;
- }
-
- static u8 at91sam9x5_clk_smd_get_parent(struct clk_hw *hw)
- {
- struct at91sam9x5_clk_smd *smd = to_at91sam9x5_clk_smd(hw);
- - struct at91_pmc *pmc = smd->pmc;
- + unsigned int smdr;
-
- - return pmc_read(pmc, AT91_PMC_SMD) & AT91_PMC_SMDS;
- + regmap_read(smd->regmap, AT91_PMC_SMD, &smdr);
- +
- + return smdr & AT91_PMC_SMDS;
- }
-
- static int at91sam9x5_clk_smd_set_rate(struct clk_hw *hw, unsigned long rate,
- unsigned long parent_rate)
- {
- - u32 tmp;
- struct at91sam9x5_clk_smd *smd = to_at91sam9x5_clk_smd(hw);
- - struct at91_pmc *pmc = smd->pmc;
- unsigned long div = parent_rate / rate;
-
- if (parent_rate % rate || div < 1 || div > (SMD_MAX_DIV + 1))
- return -EINVAL;
- - tmp = pmc_read(pmc, AT91_PMC_SMD) & ~AT91_PMC_SMD_DIV;
- - tmp |= (div - 1) << SMD_DIV_SHIFT;
- - pmc_write(pmc, AT91_PMC_SMD, tmp);
- +
- + regmap_update_bits(smd->regmap, AT91_PMC_SMD, AT91_PMC_SMD_DIV,
- + (div - 1) << SMD_DIV_SHIFT);
-
- return 0;
- }
- @@ -114,7 +112,7 @@
- };
-
- static struct clk * __init
- -at91sam9x5_clk_register_smd(struct at91_pmc *pmc, const char *name,
- +at91sam9x5_clk_register_smd(struct regmap *regmap, const char *name,
- const char **parent_names, u8 num_parents)
- {
- struct at91sam9x5_clk_smd *smd;
- @@ -132,7 +130,7 @@
- init.flags = CLK_SET_RATE_GATE | CLK_SET_PARENT_GATE;
-
- smd->hw.init = &init;
- - smd->pmc = pmc;
- + smd->regmap = regmap;
-
- clk = clk_register(NULL, &smd->hw);
- if (IS_ERR(clk))
- @@ -141,13 +139,13 @@
- return clk;
- }
-
- -void __init of_at91sam9x5_clk_smd_setup(struct device_node *np,
- - struct at91_pmc *pmc)
- +static void __init of_at91sam9x5_clk_smd_setup(struct device_node *np)
- {
- struct clk *clk;
- int num_parents;
- const char *parent_names[SMD_SOURCE_MAX];
- const char *name = np->name;
- + struct regmap *regmap;
-
- num_parents = of_clk_get_parent_count(np);
- if (num_parents <= 0 || num_parents > SMD_SOURCE_MAX)
- @@ -157,10 +155,16 @@
-
- of_property_read_string(np, "clock-output-names", &name);
-
- - clk = at91sam9x5_clk_register_smd(pmc, name, parent_names,
- + regmap = syscon_node_to_regmap(of_get_parent(np));
- + if (IS_ERR(regmap))
- + return;
- +
- + clk = at91sam9x5_clk_register_smd(regmap, name, parent_names,
- num_parents);
- if (IS_ERR(clk))
- return;
-
- of_clk_add_provider(np, of_clk_src_simple_get, clk);
- }
- +CLK_OF_DECLARE(at91sam9x5_clk_smd, "atmel,at91sam9x5-clk-smd",
- + of_at91sam9x5_clk_smd_setup);
- diff -Nur linux-4.4.28.orig/drivers/clk/at91/clk-system.c linux-4.4.28/drivers/clk/at91/clk-system.c
- --- linux-4.4.28.orig/drivers/clk/at91/clk-system.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/clk/at91/clk-system.c 2016-11-01 21:26:57.940288388 +0100
- @@ -12,13 +12,8 @@
- #include <linux/clkdev.h>
- #include <linux/clk/at91_pmc.h>
- #include <linux/of.h>
- -#include <linux/of_address.h>
- -#include <linux/io.h>
- -#include <linux/irq.h>
- -#include <linux/of_irq.h>
- -#include <linux/interrupt.h>
- -#include <linux/wait.h>
- -#include <linux/sched.h>
- +#include <linux/mfd/syscon.h>
- +#include <linux/regmap.h>
-
- #include "pmc.h"
-
- @@ -29,9 +24,7 @@
- #define to_clk_system(hw) container_of(hw, struct clk_system, hw)
- struct clk_system {
- struct clk_hw hw;
- - struct at91_pmc *pmc;
- - unsigned int irq;
- - wait_queue_head_t wait;
- + struct regmap *regmap;
- u8 id;
- };
-
- @@ -39,58 +32,54 @@
- {
- return (id >= 8) && (id <= 15);
- }
- -static irqreturn_t clk_system_irq_handler(int irq, void *dev_id)
- +
- +static inline bool clk_system_ready(struct regmap *regmap, int id)
- {
- - struct clk_system *sys = (struct clk_system *)dev_id;
- + unsigned int status;
-
- - wake_up(&sys->wait);
- - disable_irq_nosync(sys->irq);
- + regmap_read(regmap, AT91_PMC_SR, &status);
-
- - return IRQ_HANDLED;
- + return status & (1 << id) ? 1 : 0;
- }
-
- static int clk_system_prepare(struct clk_hw *hw)
- {
- struct clk_system *sys = to_clk_system(hw);
- - struct at91_pmc *pmc = sys->pmc;
- - u32 mask = 1 << sys->id;
-
- - pmc_write(pmc, AT91_PMC_SCER, mask);
- + regmap_write(sys->regmap, AT91_PMC_SCER, 1 << sys->id);
-
- if (!is_pck(sys->id))
- return 0;
-
- - while (!(pmc_read(pmc, AT91_PMC_SR) & mask)) {
- - if (sys->irq) {
- - enable_irq(sys->irq);
- - wait_event(sys->wait,
- - pmc_read(pmc, AT91_PMC_SR) & mask);
- - } else
- - cpu_relax();
- - }
- + while (!clk_system_ready(sys->regmap, sys->id))
- + cpu_relax();
- +
- return 0;
- }
-
- static void clk_system_unprepare(struct clk_hw *hw)
- {
- struct clk_system *sys = to_clk_system(hw);
- - struct at91_pmc *pmc = sys->pmc;
-
- - pmc_write(pmc, AT91_PMC_SCDR, 1 << sys->id);
- + regmap_write(sys->regmap, AT91_PMC_SCDR, 1 << sys->id);
- }
-
- static int clk_system_is_prepared(struct clk_hw *hw)
- {
- struct clk_system *sys = to_clk_system(hw);
- - struct at91_pmc *pmc = sys->pmc;
- + unsigned int status;
- +
- + regmap_read(sys->regmap, AT91_PMC_SCSR, &status);
-
- - if (!(pmc_read(pmc, AT91_PMC_SCSR) & (1 << sys->id)))
- + if (!(status & (1 << sys->id)))
- return 0;
-
- if (!is_pck(sys->id))
- return 1;
-
- - return !!(pmc_read(pmc, AT91_PMC_SR) & (1 << sys->id));
- + regmap_read(sys->regmap, AT91_PMC_SR, &status);
- +
- + return status & (1 << sys->id) ? 1 : 0;
- }
-
- static const struct clk_ops system_ops = {
- @@ -100,13 +89,12 @@
- };
-
- static struct clk * __init
- -at91_clk_register_system(struct at91_pmc *pmc, const char *name,
- - const char *parent_name, u8 id, int irq)
- +at91_clk_register_system(struct regmap *regmap, const char *name,
- + const char *parent_name, u8 id)
- {
- struct clk_system *sys;
- struct clk *clk = NULL;
- struct clk_init_data init;
- - int ret;
-
- if (!parent_name || id > SYSTEM_MAX_ID)
- return ERR_PTR(-EINVAL);
- @@ -123,44 +111,33 @@
-
- sys->id = id;
- sys->hw.init = &init;
- - sys->pmc = pmc;
- - sys->irq = irq;
- - if (irq) {
- - init_waitqueue_head(&sys->wait);
- - irq_set_status_flags(sys->irq, IRQ_NOAUTOEN);
- - ret = request_irq(sys->irq, clk_system_irq_handler,
- - IRQF_TRIGGER_HIGH, name, sys);
- - if (ret) {
- - kfree(sys);
- - return ERR_PTR(ret);
- - }
- - }
- + sys->regmap = regmap;
-
- clk = clk_register(NULL, &sys->hw);
- - if (IS_ERR(clk)) {
- - if (irq)
- - free_irq(sys->irq, sys);
- + if (IS_ERR(clk))
- kfree(sys);
- - }
-
- return clk;
- }
-
- -static void __init
- -of_at91_clk_sys_setup(struct device_node *np, struct at91_pmc *pmc)
- +static void __init of_at91rm9200_clk_sys_setup(struct device_node *np)
- {
- int num;
- - int irq = 0;
- u32 id;
- struct clk *clk;
- const char *name;
- struct device_node *sysclknp;
- const char *parent_name;
- + struct regmap *regmap;
-
- num = of_get_child_count(np);
- if (num > (SYSTEM_MAX_ID + 1))
- return;
-
- + regmap = syscon_node_to_regmap(of_get_parent(np));
- + if (IS_ERR(regmap))
- + return;
- +
- for_each_child_of_node(np, sysclknp) {
- if (of_property_read_u32(sysclknp, "reg", &id))
- continue;
- @@ -168,21 +145,14 @@
- if (of_property_read_string(np, "clock-output-names", &name))
- name = sysclknp->name;
-
- - if (is_pck(id))
- - irq = irq_of_parse_and_map(sysclknp, 0);
- -
- parent_name = of_clk_get_parent_name(sysclknp, 0);
-
- - clk = at91_clk_register_system(pmc, name, parent_name, id, irq);
- + clk = at91_clk_register_system(regmap, name, parent_name, id);
- if (IS_ERR(clk))
- continue;
-
- of_clk_add_provider(sysclknp, of_clk_src_simple_get, clk);
- }
- }
- -
- -void __init of_at91rm9200_clk_sys_setup(struct device_node *np,
- - struct at91_pmc *pmc)
- -{
- - of_at91_clk_sys_setup(np, pmc);
- -}
- +CLK_OF_DECLARE(at91rm9200_clk_sys, "atmel,at91rm9200-clk-system",
- + of_at91rm9200_clk_sys_setup);
- diff -Nur linux-4.4.28.orig/drivers/clk/at91/clk-usb.c linux-4.4.28/drivers/clk/at91/clk-usb.c
- --- linux-4.4.28.orig/drivers/clk/at91/clk-usb.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/clk/at91/clk-usb.c 2016-11-01 21:26:57.940288388 +0100
- @@ -12,8 +12,8 @@
- #include <linux/clkdev.h>
- #include <linux/clk/at91_pmc.h>
- #include <linux/of.h>
- -#include <linux/of_address.h>
- -#include <linux/io.h>
- +#include <linux/mfd/syscon.h>
- +#include <linux/regmap.h>
-
- #include "pmc.h"
-
- @@ -27,7 +27,7 @@
-
- struct at91sam9x5_clk_usb {
- struct clk_hw hw;
- - struct at91_pmc *pmc;
- + struct regmap *regmap;
- };
-
- #define to_at91sam9x5_clk_usb(hw) \
- @@ -35,7 +35,7 @@
-
- struct at91rm9200_clk_usb {
- struct clk_hw hw;
- - struct at91_pmc *pmc;
- + struct regmap *regmap;
- u32 divisors[4];
- };
-
- @@ -45,13 +45,12 @@
- static unsigned long at91sam9x5_clk_usb_recalc_rate(struct clk_hw *hw,
- unsigned long parent_rate)
- {
- - u32 tmp;
- - u8 usbdiv;
- struct at91sam9x5_clk_usb *usb = to_at91sam9x5_clk_usb(hw);
- - struct at91_pmc *pmc = usb->pmc;
- + unsigned int usbr;
- + u8 usbdiv;
-
- - tmp = pmc_read(pmc, AT91_PMC_USB);
- - usbdiv = (tmp & AT91_PMC_OHCIUSBDIV) >> SAM9X5_USB_DIV_SHIFT;
- + regmap_read(usb->regmap, AT91_PMC_USB, &usbr);
- + usbdiv = (usbr & AT91_PMC_OHCIUSBDIV) >> SAM9X5_USB_DIV_SHIFT;
-
- return DIV_ROUND_CLOSEST(parent_rate, (usbdiv + 1));
- }
- @@ -109,33 +108,31 @@
-
- static int at91sam9x5_clk_usb_set_parent(struct clk_hw *hw, u8 index)
- {
- - u32 tmp;
- struct at91sam9x5_clk_usb *usb = to_at91sam9x5_clk_usb(hw);
- - struct at91_pmc *pmc = usb->pmc;
-
- if (index > 1)
- return -EINVAL;
- - tmp = pmc_read(pmc, AT91_PMC_USB) & ~AT91_PMC_USBS;
- - if (index)
- - tmp |= AT91_PMC_USBS;
- - pmc_write(pmc, AT91_PMC_USB, tmp);
- +
- + regmap_update_bits(usb->regmap, AT91_PMC_USB, AT91_PMC_USBS,
- + index ? AT91_PMC_USBS : 0);
- +
- return 0;
- }
-
- static u8 at91sam9x5_clk_usb_get_parent(struct clk_hw *hw)
- {
- struct at91sam9x5_clk_usb *usb = to_at91sam9x5_clk_usb(hw);
- - struct at91_pmc *pmc = usb->pmc;
- + unsigned int usbr;
-
- - return pmc_read(pmc, AT91_PMC_USB) & AT91_PMC_USBS;
- + regmap_read(usb->regmap, AT91_PMC_USB, &usbr);
- +
- + return usbr & AT91_PMC_USBS;
- }
-
- static int at91sam9x5_clk_usb_set_rate(struct clk_hw *hw, unsigned long rate,
- unsigned long parent_rate)
- {
- - u32 tmp;
- struct at91sam9x5_clk_usb *usb = to_at91sam9x5_clk_usb(hw);
- - struct at91_pmc *pmc = usb->pmc;
- unsigned long div;
-
- if (!rate)
- @@ -145,9 +142,8 @@
- if (div > SAM9X5_USB_MAX_DIV + 1 || !div)
- return -EINVAL;
-
- - tmp = pmc_read(pmc, AT91_PMC_USB) & ~AT91_PMC_OHCIUSBDIV;
- - tmp |= (div - 1) << SAM9X5_USB_DIV_SHIFT;
- - pmc_write(pmc, AT91_PMC_USB, tmp);
- + regmap_update_bits(usb->regmap, AT91_PMC_USB, AT91_PMC_OHCIUSBDIV,
- + (div - 1) << SAM9X5_USB_DIV_SHIFT);
-
- return 0;
- }
- @@ -163,28 +159,28 @@
- static int at91sam9n12_clk_usb_enable(struct clk_hw *hw)
- {
- struct at91sam9x5_clk_usb *usb = to_at91sam9x5_clk_usb(hw);
- - struct at91_pmc *pmc = usb->pmc;
-
- - pmc_write(pmc, AT91_PMC_USB,
- - pmc_read(pmc, AT91_PMC_USB) | AT91_PMC_USBS);
- + regmap_update_bits(usb->regmap, AT91_PMC_USB, AT91_PMC_USBS,
- + AT91_PMC_USBS);
- +
- return 0;
- }
-
- static void at91sam9n12_clk_usb_disable(struct clk_hw *hw)
- {
- struct at91sam9x5_clk_usb *usb = to_at91sam9x5_clk_usb(hw);
- - struct at91_pmc *pmc = usb->pmc;
-
- - pmc_write(pmc, AT91_PMC_USB,
- - pmc_read(pmc, AT91_PMC_USB) & ~AT91_PMC_USBS);
- + regmap_update_bits(usb->regmap, AT91_PMC_USB, AT91_PMC_USBS, 0);
- }
-
- static int at91sam9n12_clk_usb_is_enabled(struct clk_hw *hw)
- {
- struct at91sam9x5_clk_usb *usb = to_at91sam9x5_clk_usb(hw);
- - struct at91_pmc *pmc = usb->pmc;
- + unsigned int usbr;
-
- - return !!(pmc_read(pmc, AT91_PMC_USB) & AT91_PMC_USBS);
- + regmap_read(usb->regmap, AT91_PMC_USB, &usbr);
- +
- + return usbr & AT91_PMC_USBS;
- }
-
- static const struct clk_ops at91sam9n12_usb_ops = {
- @@ -197,7 +193,7 @@
- };
-
- static struct clk * __init
- -at91sam9x5_clk_register_usb(struct at91_pmc *pmc, const char *name,
- +at91sam9x5_clk_register_usb(struct regmap *regmap, const char *name,
- const char **parent_names, u8 num_parents)
- {
- struct at91sam9x5_clk_usb *usb;
- @@ -216,7 +212,7 @@
- CLK_SET_RATE_PARENT;
-
- usb->hw.init = &init;
- - usb->pmc = pmc;
- + usb->regmap = regmap;
-
- clk = clk_register(NULL, &usb->hw);
- if (IS_ERR(clk))
- @@ -226,7 +222,7 @@
- }
-
- static struct clk * __init
- -at91sam9n12_clk_register_usb(struct at91_pmc *pmc, const char *name,
- +at91sam9n12_clk_register_usb(struct regmap *regmap, const char *name,
- const char *parent_name)
- {
- struct at91sam9x5_clk_usb *usb;
- @@ -244,7 +240,7 @@
- init.flags = CLK_SET_RATE_GATE | CLK_SET_RATE_PARENT;
-
- usb->hw.init = &init;
- - usb->pmc = pmc;
- + usb->regmap = regmap;
-
- clk = clk_register(NULL, &usb->hw);
- if (IS_ERR(clk))
- @@ -257,12 +253,12 @@
- unsigned long parent_rate)
- {
- struct at91rm9200_clk_usb *usb = to_at91rm9200_clk_usb(hw);
- - struct at91_pmc *pmc = usb->pmc;
- - u32 tmp;
- + unsigned int pllbr;
- u8 usbdiv;
-
- - tmp = pmc_read(pmc, AT91_CKGR_PLLBR);
- - usbdiv = (tmp & AT91_PMC_USBDIV) >> RM9200_USB_DIV_SHIFT;
- + regmap_read(usb->regmap, AT91_CKGR_PLLBR, &pllbr);
- +
- + usbdiv = (pllbr & AT91_PMC_USBDIV) >> RM9200_USB_DIV_SHIFT;
- if (usb->divisors[usbdiv])
- return parent_rate / usb->divisors[usbdiv];
-
- @@ -310,10 +306,8 @@
- static int at91rm9200_clk_usb_set_rate(struct clk_hw *hw, unsigned long rate,
- unsigned long parent_rate)
- {
- - u32 tmp;
- int i;
- struct at91rm9200_clk_usb *usb = to_at91rm9200_clk_usb(hw);
- - struct at91_pmc *pmc = usb->pmc;
- unsigned long div;
-
- if (!rate)
- @@ -323,10 +317,10 @@
-
- for (i = 0; i < RM9200_USB_DIV_TAB_SIZE; i++) {
- if (usb->divisors[i] == div) {
- - tmp = pmc_read(pmc, AT91_CKGR_PLLBR) &
- - ~AT91_PMC_USBDIV;
- - tmp |= i << RM9200_USB_DIV_SHIFT;
- - pmc_write(pmc, AT91_CKGR_PLLBR, tmp);
- + regmap_update_bits(usb->regmap, AT91_CKGR_PLLBR,
- + AT91_PMC_USBDIV,
- + i << RM9200_USB_DIV_SHIFT);
- +
- return 0;
- }
- }
- @@ -341,7 +335,7 @@
- };
-
- static struct clk * __init
- -at91rm9200_clk_register_usb(struct at91_pmc *pmc, const char *name,
- +at91rm9200_clk_register_usb(struct regmap *regmap, const char *name,
- const char *parent_name, const u32 *divisors)
- {
- struct at91rm9200_clk_usb *usb;
- @@ -359,7 +353,7 @@
- init.flags = CLK_SET_RATE_PARENT;
-
- usb->hw.init = &init;
- - usb->pmc = pmc;
- + usb->regmap = regmap;
- memcpy(usb->divisors, divisors, sizeof(usb->divisors));
-
- clk = clk_register(NULL, &usb->hw);
- @@ -369,13 +363,13 @@
- return clk;
- }
-
- -void __init of_at91sam9x5_clk_usb_setup(struct device_node *np,
- - struct at91_pmc *pmc)
- +static void __init of_at91sam9x5_clk_usb_setup(struct device_node *np)
- {
- struct clk *clk;
- int num_parents;
- const char *parent_names[USB_SOURCE_MAX];
- const char *name = np->name;
- + struct regmap *regmap;
-
- num_parents = of_clk_get_parent_count(np);
- if (num_parents <= 0 || num_parents > USB_SOURCE_MAX)
- @@ -385,19 +379,26 @@
-
- of_property_read_string(np, "clock-output-names", &name);
-
- - clk = at91sam9x5_clk_register_usb(pmc, name, parent_names, num_parents);
- + regmap = syscon_node_to_regmap(of_get_parent(np));
- + if (IS_ERR(regmap))
- + return;
- +
- + clk = at91sam9x5_clk_register_usb(regmap, name, parent_names,
- + num_parents);
- if (IS_ERR(clk))
- return;
-
- of_clk_add_provider(np, of_clk_src_simple_get, clk);
- }
- +CLK_OF_DECLARE(at91sam9x5_clk_usb, "atmel,at91sam9x5-clk-usb",
- + of_at91sam9x5_clk_usb_setup);
-
- -void __init of_at91sam9n12_clk_usb_setup(struct device_node *np,
- - struct at91_pmc *pmc)
- +static void __init of_at91sam9n12_clk_usb_setup(struct device_node *np)
- {
- struct clk *clk;
- const char *parent_name;
- const char *name = np->name;
- + struct regmap *regmap;
-
- parent_name = of_clk_get_parent_name(np, 0);
- if (!parent_name)
- @@ -405,20 +406,26 @@
-
- of_property_read_string(np, "clock-output-names", &name);
-
- - clk = at91sam9n12_clk_register_usb(pmc, name, parent_name);
- + regmap = syscon_node_to_regmap(of_get_parent(np));
- + if (IS_ERR(regmap))
- + return;
- +
- + clk = at91sam9n12_clk_register_usb(regmap, name, parent_name);
- if (IS_ERR(clk))
- return;
-
- of_clk_add_provider(np, of_clk_src_simple_get, clk);
- }
- +CLK_OF_DECLARE(at91sam9n12_clk_usb, "atmel,at91sam9n12-clk-usb",
- + of_at91sam9n12_clk_usb_setup);
-
- -void __init of_at91rm9200_clk_usb_setup(struct device_node *np,
- - struct at91_pmc *pmc)
- +static void __init of_at91rm9200_clk_usb_setup(struct device_node *np)
- {
- struct clk *clk;
- const char *parent_name;
- const char *name = np->name;
- u32 divisors[4] = {0, 0, 0, 0};
- + struct regmap *regmap;
-
- parent_name = of_clk_get_parent_name(np, 0);
- if (!parent_name)
- @@ -430,9 +437,15 @@
-
- of_property_read_string(np, "clock-output-names", &name);
-
- - clk = at91rm9200_clk_register_usb(pmc, name, parent_name, divisors);
- + regmap = syscon_node_to_regmap(of_get_parent(np));
- + if (IS_ERR(regmap))
- + return;
- +
- + clk = at91rm9200_clk_register_usb(regmap, name, parent_name, divisors);
- if (IS_ERR(clk))
- return;
-
- of_clk_add_provider(np, of_clk_src_simple_get, clk);
- }
- +CLK_OF_DECLARE(at91rm9200_clk_usb, "atmel,at91rm9200-clk-usb",
- + of_at91rm9200_clk_usb_setup);
- diff -Nur linux-4.4.28.orig/drivers/clk/at91/clk-utmi.c linux-4.4.28/drivers/clk/at91/clk-utmi.c
- --- linux-4.4.28.orig/drivers/clk/at91/clk-utmi.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/clk/at91/clk-utmi.c 2016-11-01 21:26:57.940288388 +0100
- @@ -11,14 +11,9 @@
- #include <linux/clk-provider.h>
- #include <linux/clkdev.h>
- #include <linux/clk/at91_pmc.h>
- -#include <linux/interrupt.h>
- -#include <linux/irq.h>
- #include <linux/of.h>
- -#include <linux/of_address.h>
- -#include <linux/of_irq.h>
- -#include <linux/io.h>
- -#include <linux/sched.h>
- -#include <linux/wait.h>
- +#include <linux/mfd/syscon.h>
- +#include <linux/regmap.h>
-
- #include "pmc.h"
-
- @@ -26,37 +21,30 @@
-
- struct clk_utmi {
- struct clk_hw hw;
- - struct at91_pmc *pmc;
- - unsigned int irq;
- - wait_queue_head_t wait;
- + struct regmap *regmap;
- };
-
- #define to_clk_utmi(hw) container_of(hw, struct clk_utmi, hw)
-
- -static irqreturn_t clk_utmi_irq_handler(int irq, void *dev_id)
- +static inline bool clk_utmi_ready(struct regmap *regmap)
- {
- - struct clk_utmi *utmi = (struct clk_utmi *)dev_id;
- + unsigned int status;
-
- - wake_up(&utmi->wait);
- - disable_irq_nosync(utmi->irq);
- + regmap_read(regmap, AT91_PMC_SR, &status);
-
- - return IRQ_HANDLED;
- + return status & AT91_PMC_LOCKU;
- }
-
- static int clk_utmi_prepare(struct clk_hw *hw)
- {
- struct clk_utmi *utmi = to_clk_utmi(hw);
- - struct at91_pmc *pmc = utmi->pmc;
- - u32 tmp = pmc_read(pmc, AT91_CKGR_UCKR) | AT91_PMC_UPLLEN |
- - AT91_PMC_UPLLCOUNT | AT91_PMC_BIASEN;
- -
- - pmc_write(pmc, AT91_CKGR_UCKR, tmp);
- -
- - while (!(pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_LOCKU)) {
- - enable_irq(utmi->irq);
- - wait_event(utmi->wait,
- - pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_LOCKU);
- - }
- + unsigned int uckr = AT91_PMC_UPLLEN | AT91_PMC_UPLLCOUNT |
- + AT91_PMC_BIASEN;
- +
- + regmap_update_bits(utmi->regmap, AT91_CKGR_UCKR, uckr, uckr);
- +
- + while (!clk_utmi_ready(utmi->regmap))
- + cpu_relax();
-
- return 0;
- }
- @@ -64,18 +52,15 @@
- static int clk_utmi_is_prepared(struct clk_hw *hw)
- {
- struct clk_utmi *utmi = to_clk_utmi(hw);
- - struct at91_pmc *pmc = utmi->pmc;
-
- - return !!(pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_LOCKU);
- + return clk_utmi_ready(utmi->regmap);
- }
-
- static void clk_utmi_unprepare(struct clk_hw *hw)
- {
- struct clk_utmi *utmi = to_clk_utmi(hw);
- - struct at91_pmc *pmc = utmi->pmc;
- - u32 tmp = pmc_read(pmc, AT91_CKGR_UCKR) & ~AT91_PMC_UPLLEN;
-
- - pmc_write(pmc, AT91_CKGR_UCKR, tmp);
- + regmap_update_bits(utmi->regmap, AT91_CKGR_UCKR, AT91_PMC_UPLLEN, 0);
- }
-
- static unsigned long clk_utmi_recalc_rate(struct clk_hw *hw,
- @@ -93,10 +78,9 @@
- };
-
- static struct clk * __init
- -at91_clk_register_utmi(struct at91_pmc *pmc, unsigned int irq,
- +at91_clk_register_utmi(struct regmap *regmap,
- const char *name, const char *parent_name)
- {
- - int ret;
- struct clk_utmi *utmi;
- struct clk *clk = NULL;
- struct clk_init_data init;
- @@ -112,52 +96,36 @@
- init.flags = CLK_SET_RATE_GATE;
-
- utmi->hw.init = &init;
- - utmi->pmc = pmc;
- - utmi->irq = irq;
- - init_waitqueue_head(&utmi->wait);
- - irq_set_status_flags(utmi->irq, IRQ_NOAUTOEN);
- - ret = request_irq(utmi->irq, clk_utmi_irq_handler,
- - IRQF_TRIGGER_HIGH, "clk-utmi", utmi);
- - if (ret) {
- - kfree(utmi);
- - return ERR_PTR(ret);
- - }
- + utmi->regmap = regmap;
-
- clk = clk_register(NULL, &utmi->hw);
- - if (IS_ERR(clk)) {
- - free_irq(utmi->irq, utmi);
- + if (IS_ERR(clk))
- kfree(utmi);
- - }
-
- return clk;
- }
-
- -static void __init
- -of_at91_clk_utmi_setup(struct device_node *np, struct at91_pmc *pmc)
- +static void __init of_at91sam9x5_clk_utmi_setup(struct device_node *np)
- {
- - unsigned int irq;
- struct clk *clk;
- const char *parent_name;
- const char *name = np->name;
- + struct regmap *regmap;
-
- parent_name = of_clk_get_parent_name(np, 0);
-
- of_property_read_string(np, "clock-output-names", &name);
-
- - irq = irq_of_parse_and_map(np, 0);
- - if (!irq)
- + regmap = syscon_node_to_regmap(of_get_parent(np));
- + if (IS_ERR(regmap))
- return;
-
- - clk = at91_clk_register_utmi(pmc, irq, name, parent_name);
- + clk = at91_clk_register_utmi(regmap, name, parent_name);
- if (IS_ERR(clk))
- return;
-
- of_clk_add_provider(np, of_clk_src_simple_get, clk);
- return;
- }
- -
- -void __init of_at91sam9x5_clk_utmi_setup(struct device_node *np,
- - struct at91_pmc *pmc)
- -{
- - of_at91_clk_utmi_setup(np, pmc);
- -}
- +CLK_OF_DECLARE(at91sam9x5_clk_utmi, "atmel,at91sam9x5-clk-utmi",
- + of_at91sam9x5_clk_utmi_setup);
- diff -Nur linux-4.4.28.orig/drivers/clk/at91/pmc.c linux-4.4.28/drivers/clk/at91/pmc.c
- --- linux-4.4.28.orig/drivers/clk/at91/pmc.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/clk/at91/pmc.c 2016-11-01 21:26:57.940288388 +0100
- @@ -12,36 +12,13 @@
- #include <linux/clkdev.h>
- #include <linux/clk/at91_pmc.h>
- #include <linux/of.h>
- -#include <linux/of_address.h>
- -#include <linux/io.h>
- -#include <linux/interrupt.h>
- -#include <linux/irq.h>
- -#include <linux/irqchip/chained_irq.h>
- -#include <linux/irqdomain.h>
- -#include <linux/of_irq.h>
- +#include <linux/mfd/syscon.h>
- +#include <linux/regmap.h>
-
- #include <asm/proc-fns.h>
-
- #include "pmc.h"
-
- -void __iomem *at91_pmc_base;
- -EXPORT_SYMBOL_GPL(at91_pmc_base);
- -
- -void at91rm9200_idle(void)
- -{
- - /*
- - * Disable the processor clock. The processor will be automatically
- - * re-enabled by an interrupt or by a reset.
- - */
- - at91_pmc_write(AT91_PMC_SCDR, AT91_PMC_PCK);
- -}
- -
- -void at91sam9_idle(void)
- -{
- - at91_pmc_write(AT91_PMC_SCDR, AT91_PMC_PCK);
- - cpu_do_idle();
- -}
- -
- int of_at91_get_clk_range(struct device_node *np, const char *propname,
- struct clk_range *range)
- {
- @@ -64,402 +41,3 @@
- return 0;
- }
- EXPORT_SYMBOL_GPL(of_at91_get_clk_range);
- -
- -static void pmc_irq_mask(struct irq_data *d)
- -{
- - struct at91_pmc *pmc = irq_data_get_irq_chip_data(d);
- -
- - pmc_write(pmc, AT91_PMC_IDR, 1 << d->hwirq);
- -}
- -
- -static void pmc_irq_unmask(struct irq_data *d)
- -{
- - struct at91_pmc *pmc = irq_data_get_irq_chip_data(d);
- -
- - pmc_write(pmc, AT91_PMC_IER, 1 << d->hwirq);
- -}
- -
- -static int pmc_irq_set_type(struct irq_data *d, unsigned type)
- -{
- - if (type != IRQ_TYPE_LEVEL_HIGH) {
- - pr_warn("PMC: type not supported (support only IRQ_TYPE_LEVEL_HIGH type)\n");
- - return -EINVAL;
- - }
- -
- - return 0;
- -}
- -
- -static void pmc_irq_suspend(struct irq_data *d)
- -{
- - struct at91_pmc *pmc = irq_data_get_irq_chip_data(d);
- -
- - pmc->imr = pmc_read(pmc, AT91_PMC_IMR);
- - pmc_write(pmc, AT91_PMC_IDR, pmc->imr);
- -}
- -
- -static void pmc_irq_resume(struct irq_data *d)
- -{
- - struct at91_pmc *pmc = irq_data_get_irq_chip_data(d);
- -
- - pmc_write(pmc, AT91_PMC_IER, pmc->imr);
- -}
- -
- -static struct irq_chip pmc_irq = {
- - .name = "PMC",
- - .irq_disable = pmc_irq_mask,
- - .irq_mask = pmc_irq_mask,
- - .irq_unmask = pmc_irq_unmask,
- - .irq_set_type = pmc_irq_set_type,
- - .irq_suspend = pmc_irq_suspend,
- - .irq_resume = pmc_irq_resume,
- -};
- -
- -static struct lock_class_key pmc_lock_class;
- -
- -static int pmc_irq_map(struct irq_domain *h, unsigned int virq,
- - irq_hw_number_t hw)
- -{
- - struct at91_pmc *pmc = h->host_data;
- -
- - irq_set_lockdep_class(virq, &pmc_lock_class);
- -
- - irq_set_chip_and_handler(virq, &pmc_irq,
- - handle_level_irq);
- - irq_set_chip_data(virq, pmc);
- -
- - return 0;
- -}
- -
- -static int pmc_irq_domain_xlate(struct irq_domain *d,
- - struct device_node *ctrlr,
- - const u32 *intspec, unsigned int intsize,
- - irq_hw_number_t *out_hwirq,
- - unsigned int *out_type)
- -{
- - struct at91_pmc *pmc = d->host_data;
- - const struct at91_pmc_caps *caps = pmc->caps;
- -
- - if (WARN_ON(intsize < 1))
- - return -EINVAL;
- -
- - *out_hwirq = intspec[0];
- -
- - if (!(caps->available_irqs & (1 << *out_hwirq)))
- - return -EINVAL;
- -
- - *out_type = IRQ_TYPE_LEVEL_HIGH;
- -
- - return 0;
- -}
- -
- -static const struct irq_domain_ops pmc_irq_ops = {
- - .map = pmc_irq_map,
- - .xlate = pmc_irq_domain_xlate,
- -};
- -
- -static irqreturn_t pmc_irq_handler(int irq, void *data)
- -{
- - struct at91_pmc *pmc = (struct at91_pmc *)data;
- - unsigned long sr;
- - int n;
- -
- - sr = pmc_read(pmc, AT91_PMC_SR) & pmc_read(pmc, AT91_PMC_IMR);
- - if (!sr)
- - return IRQ_NONE;
- -
- - for_each_set_bit(n, &sr, BITS_PER_LONG)
- - generic_handle_irq(irq_find_mapping(pmc->irqdomain, n));
- -
- - return IRQ_HANDLED;
- -}
- -
- -static const struct at91_pmc_caps at91rm9200_caps = {
- - .available_irqs = AT91_PMC_MOSCS | AT91_PMC_LOCKA | AT91_PMC_LOCKB |
- - AT91_PMC_MCKRDY | AT91_PMC_PCK0RDY |
- - AT91_PMC_PCK1RDY | AT91_PMC_PCK2RDY |
- - AT91_PMC_PCK3RDY,
- -};
- -
- -static const struct at91_pmc_caps at91sam9260_caps = {
- - .available_irqs = AT91_PMC_MOSCS | AT91_PMC_LOCKA | AT91_PMC_LOCKB |
- - AT91_PMC_MCKRDY | AT91_PMC_PCK0RDY |
- - AT91_PMC_PCK1RDY,
- -};
- -
- -static const struct at91_pmc_caps at91sam9g45_caps = {
- - .available_irqs = AT91_PMC_MOSCS | AT91_PMC_LOCKA | AT91_PMC_MCKRDY |
- - AT91_PMC_LOCKU | AT91_PMC_PCK0RDY |
- - AT91_PMC_PCK1RDY,
- -};
- -
- -static const struct at91_pmc_caps at91sam9n12_caps = {
- - .available_irqs = AT91_PMC_MOSCS | AT91_PMC_LOCKA | AT91_PMC_LOCKB |
- - AT91_PMC_MCKRDY | AT91_PMC_PCK0RDY |
- - AT91_PMC_PCK1RDY | AT91_PMC_MOSCSELS |
- - AT91_PMC_MOSCRCS | AT91_PMC_CFDEV,
- -};
- -
- -static const struct at91_pmc_caps at91sam9x5_caps = {
- - .available_irqs = AT91_PMC_MOSCS | AT91_PMC_LOCKA | AT91_PMC_MCKRDY |
- - AT91_PMC_LOCKU | AT91_PMC_PCK0RDY |
- - AT91_PMC_PCK1RDY | AT91_PMC_MOSCSELS |
- - AT91_PMC_MOSCRCS | AT91_PMC_CFDEV,
- -};
- -
- -static const struct at91_pmc_caps sama5d2_caps = {
- - .available_irqs = AT91_PMC_MOSCS | AT91_PMC_LOCKA | AT91_PMC_MCKRDY |
- - AT91_PMC_LOCKU | AT91_PMC_PCK0RDY |
- - AT91_PMC_PCK1RDY | AT91_PMC_PCK2RDY |
- - AT91_PMC_MOSCSELS | AT91_PMC_MOSCRCS |
- - AT91_PMC_CFDEV | AT91_PMC_GCKRDY,
- -};
- -
- -static const struct at91_pmc_caps sama5d3_caps = {
- - .available_irqs = AT91_PMC_MOSCS | AT91_PMC_LOCKA | AT91_PMC_MCKRDY |
- - AT91_PMC_LOCKU | AT91_PMC_PCK0RDY |
- - AT91_PMC_PCK1RDY | AT91_PMC_PCK2RDY |
- - AT91_PMC_MOSCSELS | AT91_PMC_MOSCRCS |
- - AT91_PMC_CFDEV,
- -};
- -
- -static struct at91_pmc *__init at91_pmc_init(struct device_node *np,
- - void __iomem *regbase, int virq,
- - const struct at91_pmc_caps *caps)
- -{
- - struct at91_pmc *pmc;
- -
- - if (!regbase || !virq || !caps)
- - return NULL;
- -
- - at91_pmc_base = regbase;
- -
- - pmc = kzalloc(sizeof(*pmc), GFP_KERNEL);
- - if (!pmc)
- - return NULL;
- -
- - spin_lock_init(&pmc->lock);
- - pmc->regbase = regbase;
- - pmc->virq = virq;
- - pmc->caps = caps;
- -
- - pmc->irqdomain = irq_domain_add_linear(np, 32, &pmc_irq_ops, pmc);
- -
- - if (!pmc->irqdomain)
- - goto out_free_pmc;
- -
- - pmc_write(pmc, AT91_PMC_IDR, 0xffffffff);
- - if (request_irq(pmc->virq, pmc_irq_handler,
- - IRQF_SHARED | IRQF_COND_SUSPEND, "pmc", pmc))
- - goto out_remove_irqdomain;
- -
- - return pmc;
- -
- -out_remove_irqdomain:
- - irq_domain_remove(pmc->irqdomain);
- -out_free_pmc:
- - kfree(pmc);
- -
- - return NULL;
- -}
- -
- -static const struct of_device_id pmc_clk_ids[] __initconst = {
- - /* Slow oscillator */
- - {
- - .compatible = "atmel,at91sam9260-clk-slow",
- - .data = of_at91sam9260_clk_slow_setup,
- - },
- - /* Main clock */
- - {
- - .compatible = "atmel,at91rm9200-clk-main-osc",
- - .data = of_at91rm9200_clk_main_osc_setup,
- - },
- - {
- - .compatible = "atmel,at91sam9x5-clk-main-rc-osc",
- - .data = of_at91sam9x5_clk_main_rc_osc_setup,
- - },
- - {
- - .compatible = "atmel,at91rm9200-clk-main",
- - .data = of_at91rm9200_clk_main_setup,
- - },
- - {
- - .compatible = "atmel,at91sam9x5-clk-main",
- - .data = of_at91sam9x5_clk_main_setup,
- - },
- - /* PLL clocks */
- - {
- - .compatible = "atmel,at91rm9200-clk-pll",
- - .data = of_at91rm9200_clk_pll_setup,
- - },
- - {
- - .compatible = "atmel,at91sam9g45-clk-pll",
- - .data = of_at91sam9g45_clk_pll_setup,
- - },
- - {
- - .compatible = "atmel,at91sam9g20-clk-pllb",
- - .data = of_at91sam9g20_clk_pllb_setup,
- - },
- - {
- - .compatible = "atmel,sama5d3-clk-pll",
- - .data = of_sama5d3_clk_pll_setup,
- - },
- - {
- - .compatible = "atmel,at91sam9x5-clk-plldiv",
- - .data = of_at91sam9x5_clk_plldiv_setup,
- - },
- - /* Master clock */
- - {
- - .compatible = "atmel,at91rm9200-clk-master",
- - .data = of_at91rm9200_clk_master_setup,
- - },
- - {
- - .compatible = "atmel,at91sam9x5-clk-master",
- - .data = of_at91sam9x5_clk_master_setup,
- - },
- - /* System clocks */
- - {
- - .compatible = "atmel,at91rm9200-clk-system",
- - .data = of_at91rm9200_clk_sys_setup,
- - },
- - /* Peripheral clocks */
- - {
- - .compatible = "atmel,at91rm9200-clk-peripheral",
- - .data = of_at91rm9200_clk_periph_setup,
- - },
- - {
- - .compatible = "atmel,at91sam9x5-clk-peripheral",
- - .data = of_at91sam9x5_clk_periph_setup,
- - },
- - /* Programmable clocks */
- - {
- - .compatible = "atmel,at91rm9200-clk-programmable",
- - .data = of_at91rm9200_clk_prog_setup,
- - },
- - {
- - .compatible = "atmel,at91sam9g45-clk-programmable",
- - .data = of_at91sam9g45_clk_prog_setup,
- - },
- - {
- - .compatible = "atmel,at91sam9x5-clk-programmable",
- - .data = of_at91sam9x5_clk_prog_setup,
- - },
- - /* UTMI clock */
- -#if defined(CONFIG_HAVE_AT91_UTMI)
- - {
- - .compatible = "atmel,at91sam9x5-clk-utmi",
- - .data = of_at91sam9x5_clk_utmi_setup,
- - },
- -#endif
- - /* USB clock */
- -#if defined(CONFIG_HAVE_AT91_USB_CLK)
- - {
- - .compatible = "atmel,at91rm9200-clk-usb",
- - .data = of_at91rm9200_clk_usb_setup,
- - },
- - {
- - .compatible = "atmel,at91sam9x5-clk-usb",
- - .data = of_at91sam9x5_clk_usb_setup,
- - },
- - {
- - .compatible = "atmel,at91sam9n12-clk-usb",
- - .data = of_at91sam9n12_clk_usb_setup,
- - },
- -#endif
- - /* SMD clock */
- -#if defined(CONFIG_HAVE_AT91_SMD)
- - {
- - .compatible = "atmel,at91sam9x5-clk-smd",
- - .data = of_at91sam9x5_clk_smd_setup,
- - },
- -#endif
- -#if defined(CONFIG_HAVE_AT91_H32MX)
- - {
- - .compatible = "atmel,sama5d4-clk-h32mx",
- - .data = of_sama5d4_clk_h32mx_setup,
- - },
- -#endif
- -#if defined(CONFIG_HAVE_AT91_GENERATED_CLK)
- - {
- - .compatible = "atmel,sama5d2-clk-generated",
- - .data = of_sama5d2_clk_generated_setup,
- - },
- -#endif
- - { /*sentinel*/ }
- -};
- -
- -static void __init of_at91_pmc_setup(struct device_node *np,
- - const struct at91_pmc_caps *caps)
- -{
- - struct at91_pmc *pmc;
- - struct device_node *childnp;
- - void (*clk_setup)(struct device_node *, struct at91_pmc *);
- - const struct of_device_id *clk_id;
- - void __iomem *regbase = of_iomap(np, 0);
- - int virq;
- -
- - if (!regbase)
- - return;
- -
- - virq = irq_of_parse_and_map(np, 0);
- - if (!virq)
- - return;
- -
- - pmc = at91_pmc_init(np, regbase, virq, caps);
- - if (!pmc)
- - return;
- - for_each_child_of_node(np, childnp) {
- - clk_id = of_match_node(pmc_clk_ids, childnp);
- - if (!clk_id)
- - continue;
- - clk_setup = clk_id->data;
- - clk_setup(childnp, pmc);
- - }
- -}
- -
- -static void __init of_at91rm9200_pmc_setup(struct device_node *np)
- -{
- - of_at91_pmc_setup(np, &at91rm9200_caps);
- -}
- -CLK_OF_DECLARE(at91rm9200_clk_pmc, "atmel,at91rm9200-pmc",
- - of_at91rm9200_pmc_setup);
- -
- -static void __init of_at91sam9260_pmc_setup(struct device_node *np)
- -{
- - of_at91_pmc_setup(np, &at91sam9260_caps);
- -}
- -CLK_OF_DECLARE(at91sam9260_clk_pmc, "atmel,at91sam9260-pmc",
- - of_at91sam9260_pmc_setup);
- -
- -static void __init of_at91sam9g45_pmc_setup(struct device_node *np)
- -{
- - of_at91_pmc_setup(np, &at91sam9g45_caps);
- -}
- -CLK_OF_DECLARE(at91sam9g45_clk_pmc, "atmel,at91sam9g45-pmc",
- - of_at91sam9g45_pmc_setup);
- -
- -static void __init of_at91sam9n12_pmc_setup(struct device_node *np)
- -{
- - of_at91_pmc_setup(np, &at91sam9n12_caps);
- -}
- -CLK_OF_DECLARE(at91sam9n12_clk_pmc, "atmel,at91sam9n12-pmc",
- - of_at91sam9n12_pmc_setup);
- -
- -static void __init of_at91sam9x5_pmc_setup(struct device_node *np)
- -{
- - of_at91_pmc_setup(np, &at91sam9x5_caps);
- -}
- -CLK_OF_DECLARE(at91sam9x5_clk_pmc, "atmel,at91sam9x5-pmc",
- - of_at91sam9x5_pmc_setup);
- -
- -static void __init of_sama5d2_pmc_setup(struct device_node *np)
- -{
- - of_at91_pmc_setup(np, &sama5d2_caps);
- -}
- -CLK_OF_DECLARE(sama5d2_clk_pmc, "atmel,sama5d2-pmc",
- - of_sama5d2_pmc_setup);
- -
- -static void __init of_sama5d3_pmc_setup(struct device_node *np)
- -{
- - of_at91_pmc_setup(np, &sama5d3_caps);
- -}
- -CLK_OF_DECLARE(sama5d3_clk_pmc, "atmel,sama5d3-pmc",
- - of_sama5d3_pmc_setup);
- diff -Nur linux-4.4.28.orig/drivers/clk/at91/pmc.h linux-4.4.28/drivers/clk/at91/pmc.h
- --- linux-4.4.28.orig/drivers/clk/at91/pmc.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/clk/at91/pmc.h 2016-11-01 21:26:57.944288652 +0100
- @@ -14,8 +14,11 @@
-
- #include <linux/io.h>
- #include <linux/irqdomain.h>
- +#include <linux/regmap.h>
- #include <linux/spinlock.h>
-
- +extern spinlock_t pmc_pcr_lock;
- +
- struct clk_range {
- unsigned long min;
- unsigned long max;
- @@ -23,102 +26,7 @@
-
- #define CLK_RANGE(MIN, MAX) {.min = MIN, .max = MAX,}
-
- -struct at91_pmc_caps {
- - u32 available_irqs;
- -};
- -
- -struct at91_pmc {
- - void __iomem *regbase;
- - int virq;
- - spinlock_t lock;
- - const struct at91_pmc_caps *caps;
- - struct irq_domain *irqdomain;
- - u32 imr;
- -};
- -
- -static inline void pmc_lock(struct at91_pmc *pmc)
- -{
- - spin_lock(&pmc->lock);
- -}
- -
- -static inline void pmc_unlock(struct at91_pmc *pmc)
- -{
- - spin_unlock(&pmc->lock);
- -}
- -
- -static inline u32 pmc_read(struct at91_pmc *pmc, int offset)
- -{
- - return readl(pmc->regbase + offset);
- -}
- -
- -static inline void pmc_write(struct at91_pmc *pmc, int offset, u32 value)
- -{
- - writel(value, pmc->regbase + offset);
- -}
- -
- int of_at91_get_clk_range(struct device_node *np, const char *propname,
- struct clk_range *range);
-
- -void of_at91sam9260_clk_slow_setup(struct device_node *np,
- - struct at91_pmc *pmc);
- -
- -void of_at91rm9200_clk_main_osc_setup(struct device_node *np,
- - struct at91_pmc *pmc);
- -void of_at91sam9x5_clk_main_rc_osc_setup(struct device_node *np,
- - struct at91_pmc *pmc);
- -void of_at91rm9200_clk_main_setup(struct device_node *np,
- - struct at91_pmc *pmc);
- -void of_at91sam9x5_clk_main_setup(struct device_node *np,
- - struct at91_pmc *pmc);
- -
- -void of_at91rm9200_clk_pll_setup(struct device_node *np,
- - struct at91_pmc *pmc);
- -void of_at91sam9g45_clk_pll_setup(struct device_node *np,
- - struct at91_pmc *pmc);
- -void of_at91sam9g20_clk_pllb_setup(struct device_node *np,
- - struct at91_pmc *pmc);
- -void of_sama5d3_clk_pll_setup(struct device_node *np,
- - struct at91_pmc *pmc);
- -void of_at91sam9x5_clk_plldiv_setup(struct device_node *np,
- - struct at91_pmc *pmc);
- -
- -void of_at91rm9200_clk_master_setup(struct device_node *np,
- - struct at91_pmc *pmc);
- -void of_at91sam9x5_clk_master_setup(struct device_node *np,
- - struct at91_pmc *pmc);
- -
- -void of_at91rm9200_clk_sys_setup(struct device_node *np,
- - struct at91_pmc *pmc);
- -
- -void of_at91rm9200_clk_periph_setup(struct device_node *np,
- - struct at91_pmc *pmc);
- -void of_at91sam9x5_clk_periph_setup(struct device_node *np,
- - struct at91_pmc *pmc);
- -
- -void of_at91rm9200_clk_prog_setup(struct device_node *np,
- - struct at91_pmc *pmc);
- -void of_at91sam9g45_clk_prog_setup(struct device_node *np,
- - struct at91_pmc *pmc);
- -void of_at91sam9x5_clk_prog_setup(struct device_node *np,
- - struct at91_pmc *pmc);
- -
- -void of_at91sam9x5_clk_utmi_setup(struct device_node *np,
- - struct at91_pmc *pmc);
- -
- -void of_at91rm9200_clk_usb_setup(struct device_node *np,
- - struct at91_pmc *pmc);
- -void of_at91sam9x5_clk_usb_setup(struct device_node *np,
- - struct at91_pmc *pmc);
- -void of_at91sam9n12_clk_usb_setup(struct device_node *np,
- - struct at91_pmc *pmc);
- -
- -void of_at91sam9x5_clk_smd_setup(struct device_node *np,
- - struct at91_pmc *pmc);
- -
- -void of_sama5d4_clk_h32mx_setup(struct device_node *np,
- - struct at91_pmc *pmc);
- -
- -void of_sama5d2_clk_generated_setup(struct device_node *np,
- - struct at91_pmc *pmc);
- -
- #endif /* __PMC_H_ */
- diff -Nur linux-4.4.28.orig/drivers/clocksource/tcb_clksrc.c linux-4.4.28/drivers/clocksource/tcb_clksrc.c
- --- linux-4.4.28.orig/drivers/clocksource/tcb_clksrc.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/clocksource/tcb_clksrc.c 2016-11-01 21:26:57.948288905 +0100
- @@ -23,8 +23,7 @@
- * this 32 bit free-running counter. the second channel is not used.
- *
- * - The third channel may be used to provide a 16-bit clockevent
- - * source, used in either periodic or oneshot mode. This runs
- - * at 32 KiHZ, and can handle delays of up to two seconds.
- + * source, used in either periodic or oneshot mode.
- *
- * A boot clocksource and clockevent source are also currently needed,
- * unless the relevant platforms (ARM/AT91, AVR32/AT32) are changed so
- @@ -74,6 +73,8 @@
- struct tc_clkevt_device {
- struct clock_event_device clkevt;
- struct clk *clk;
- + bool clk_enabled;
- + u32 freq;
- void __iomem *regs;
- };
-
- @@ -82,15 +83,26 @@
- return container_of(clkevt, struct tc_clkevt_device, clkevt);
- }
-
- -/* For now, we always use the 32K clock ... this optimizes for NO_HZ,
- - * because using one of the divided clocks would usually mean the
- - * tick rate can never be less than several dozen Hz (vs 0.5 Hz).
- - *
- - * A divided clock could be good for high resolution timers, since
- - * 30.5 usec resolution can seem "low".
- - */
- static u32 timer_clock;
-
- +static void tc_clk_disable(struct clock_event_device *d)
- +{
- + struct tc_clkevt_device *tcd = to_tc_clkevt(d);
- +
- + clk_disable(tcd->clk);
- + tcd->clk_enabled = false;
- +}
- +
- +static void tc_clk_enable(struct clock_event_device *d)
- +{
- + struct tc_clkevt_device *tcd = to_tc_clkevt(d);
- +
- + if (tcd->clk_enabled)
- + return;
- + clk_enable(tcd->clk);
- + tcd->clk_enabled = true;
- +}
- +
- static int tc_shutdown(struct clock_event_device *d)
- {
- struct tc_clkevt_device *tcd = to_tc_clkevt(d);
- @@ -98,8 +110,14 @@
-
- __raw_writel(0xff, regs + ATMEL_TC_REG(2, IDR));
- __raw_writel(ATMEL_TC_CLKDIS, regs + ATMEL_TC_REG(2, CCR));
- + return 0;
- +}
- +
- +static int tc_shutdown_clk_off(struct clock_event_device *d)
- +{
- + tc_shutdown(d);
- if (!clockevent_state_detached(d))
- - clk_disable(tcd->clk);
- + tc_clk_disable(d);
-
- return 0;
- }
- @@ -112,9 +130,9 @@
- if (clockevent_state_oneshot(d) || clockevent_state_periodic(d))
- tc_shutdown(d);
-
- - clk_enable(tcd->clk);
- + tc_clk_enable(d);
-
- - /* slow clock, count up to RC, then irq and stop */
- + /* count up to RC, then irq and stop */
- __raw_writel(timer_clock | ATMEL_TC_CPCSTOP | ATMEL_TC_WAVE |
- ATMEL_TC_WAVESEL_UP_AUTO, regs + ATMEL_TC_REG(2, CMR));
- __raw_writel(ATMEL_TC_CPCS, regs + ATMEL_TC_REG(2, IER));
- @@ -134,12 +152,12 @@
- /* By not making the gentime core emulate periodic mode on top
- * of oneshot, we get lower overhead and improved accuracy.
- */
- - clk_enable(tcd->clk);
- + tc_clk_enable(d);
-
- - /* slow clock, count up to RC, then irq and restart */
- + /* count up to RC, then irq and restart */
- __raw_writel(timer_clock | ATMEL_TC_WAVE | ATMEL_TC_WAVESEL_UP_AUTO,
- regs + ATMEL_TC_REG(2, CMR));
- - __raw_writel((32768 + HZ / 2) / HZ, tcaddr + ATMEL_TC_REG(2, RC));
- + __raw_writel((tcd->freq + HZ / 2) / HZ, tcaddr + ATMEL_TC_REG(2, RC));
-
- /* Enable clock and interrupts on RC compare */
- __raw_writel(ATMEL_TC_CPCS, regs + ATMEL_TC_REG(2, IER));
- @@ -166,9 +184,13 @@
- .features = CLOCK_EVT_FEAT_PERIODIC |
- CLOCK_EVT_FEAT_ONESHOT,
- /* Should be lower than at91rm9200's system timer */
- +#ifdef CONFIG_ATMEL_TCB_CLKSRC_USE_SLOW_CLOCK
- .rating = 125,
- +#else
- + .rating = 200,
- +#endif
- .set_next_event = tc_next_event,
- - .set_state_shutdown = tc_shutdown,
- + .set_state_shutdown = tc_shutdown_clk_off,
- .set_state_periodic = tc_set_periodic,
- .set_state_oneshot = tc_set_oneshot,
- },
- @@ -188,8 +210,9 @@
- return IRQ_NONE;
- }
-
- -static int __init setup_clkevents(struct atmel_tc *tc, int clk32k_divisor_idx)
- +static int __init setup_clkevents(struct atmel_tc *tc, int divisor_idx)
- {
- + unsigned divisor = atmel_tc_divisors[divisor_idx];
- int ret;
- struct clk *t2_clk = tc->clk[2];
- int irq = tc->irq[2];
- @@ -210,7 +233,11 @@
- clkevt.regs = tc->regs;
- clkevt.clk = t2_clk;
-
- - timer_clock = clk32k_divisor_idx;
- + timer_clock = divisor_idx;
- + if (!divisor)
- + clkevt.freq = 32768;
- + else
- + clkevt.freq = clk_get_rate(t2_clk) / divisor;
-
- clkevt.clkevt.cpumask = cpumask_of(0);
-
- @@ -221,7 +248,7 @@
- return ret;
- }
-
- - clockevents_config_and_register(&clkevt.clkevt, 32768, 1, 0xffff);
- + clockevents_config_and_register(&clkevt.clkevt, clkevt.freq, 1, 0xffff);
-
- return ret;
- }
- @@ -358,7 +385,11 @@
- goto err_disable_t1;
-
- /* channel 2: periodic and oneshot timer support */
- +#ifdef CONFIG_ATMEL_TCB_CLKSRC_USE_SLOW_CLOCK
- ret = setup_clkevents(tc, clk32k_divisor_idx);
- +#else
- + ret = setup_clkevents(tc, best_divisor_idx);
- +#endif
- if (ret)
- goto err_unregister_clksrc;
-
- diff -Nur linux-4.4.28.orig/drivers/clocksource/timer-atmel-pit.c linux-4.4.28/drivers/clocksource/timer-atmel-pit.c
- --- linux-4.4.28.orig/drivers/clocksource/timer-atmel-pit.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/clocksource/timer-atmel-pit.c 2016-11-01 21:26:57.952289162 +0100
- @@ -46,6 +46,7 @@
- u32 cycle;
- u32 cnt;
- unsigned int irq;
- + bool irq_requested;
- struct clk *mck;
- };
-
- @@ -96,15 +97,29 @@
-
- /* disable irq, leaving the clocksource active */
- pit_write(data->base, AT91_PIT_MR, (data->cycle - 1) | AT91_PIT_PITEN);
- + if (data->irq_requested) {
- + free_irq(data->irq, data);
- + data->irq_requested = false;
- + }
- return 0;
- }
-
- +static irqreturn_t at91sam926x_pit_interrupt(int irq, void *dev_id);
- /*
- * Clockevent device: interrupts every 1/HZ (== pit_cycles * MCK/16)
- */
- static int pit_clkevt_set_periodic(struct clock_event_device *dev)
- {
- struct pit_data *data = clkevt_to_pit_data(dev);
- + int ret;
- +
- + ret = request_irq(data->irq, at91sam926x_pit_interrupt,
- + IRQF_SHARED | IRQF_TIMER | IRQF_IRQPOLL,
- + "at91_tick", data);
- + if (ret)
- + panic(pr_fmt("Unable to setup IRQ\n"));
- +
- + data->irq_requested = true;
-
- /* update clocksource counter */
- data->cnt += data->cycle * PIT_PICNT(pit_read(data->base, AT91_PIT_PIVR));
- @@ -181,7 +196,6 @@
- {
- unsigned long pit_rate;
- unsigned bits;
- - int ret;
-
- /*
- * Use our actual MCK to figure out how many MCK/16 ticks per
- @@ -206,13 +220,6 @@
- data->clksrc.flags = CLOCK_SOURCE_IS_CONTINUOUS;
- clocksource_register_hz(&data->clksrc, pit_rate);
-
- - /* Set up irq handler */
- - ret = request_irq(data->irq, at91sam926x_pit_interrupt,
- - IRQF_SHARED | IRQF_TIMER | IRQF_IRQPOLL,
- - "at91_tick", data);
- - if (ret)
- - panic(pr_fmt("Unable to setup IRQ\n"));
- -
- /* Set up and register clockevents */
- data->clkevt.name = "pit";
- data->clkevt.features = CLOCK_EVT_FEAT_PERIODIC;
- diff -Nur linux-4.4.28.orig/drivers/clocksource/timer-atmel-st.c linux-4.4.28/drivers/clocksource/timer-atmel-st.c
- --- linux-4.4.28.orig/drivers/clocksource/timer-atmel-st.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/clocksource/timer-atmel-st.c 2016-11-01 21:26:57.952289162 +0100
- @@ -115,18 +115,29 @@
- last_crtr = read_CRTR();
- }
-
- +static int atmel_st_irq;
- +
- static int clkevt32k_shutdown(struct clock_event_device *evt)
- {
- clkdev32k_disable_and_flush_irq();
- irqmask = 0;
- regmap_write(regmap_st, AT91_ST_IER, irqmask);
- + free_irq(atmel_st_irq, regmap_st);
- return 0;
- }
-
- static int clkevt32k_set_oneshot(struct clock_event_device *dev)
- {
- + int ret;
- +
- clkdev32k_disable_and_flush_irq();
-
- + ret = request_irq(atmel_st_irq, at91rm9200_timer_interrupt,
- + IRQF_SHARED | IRQF_TIMER | IRQF_IRQPOLL,
- + "at91_tick", regmap_st);
- + if (ret)
- + panic(pr_fmt("Unable to setup IRQ\n"));
- +
- /*
- * ALM for oneshot irqs, set by next_event()
- * before 32 seconds have passed.
- @@ -139,8 +150,16 @@
-
- static int clkevt32k_set_periodic(struct clock_event_device *dev)
- {
- + int ret;
- +
- clkdev32k_disable_and_flush_irq();
-
- + ret = request_irq(atmel_st_irq, at91rm9200_timer_interrupt,
- + IRQF_SHARED | IRQF_TIMER | IRQF_IRQPOLL,
- + "at91_tick", regmap_st);
- + if (ret)
- + panic(pr_fmt("Unable to setup IRQ\n"));
- +
- /* PIT for periodic irqs; fixed rate of 1/HZ */
- irqmask = AT91_ST_PITS;
- regmap_write(regmap_st, AT91_ST_PIMR, timer_latch);
- @@ -198,7 +217,7 @@
- {
- struct clk *sclk;
- unsigned int sclk_rate, val;
- - int irq, ret;
- + int ret;
-
- regmap_st = syscon_node_to_regmap(node);
- if (IS_ERR(regmap_st))
- @@ -210,17 +229,10 @@
- regmap_read(regmap_st, AT91_ST_SR, &val);
-
- /* Get the interrupts property */
- - irq = irq_of_parse_and_map(node, 0);
- - if (!irq)
- + atmel_st_irq = irq_of_parse_and_map(node, 0);
- + if (!atmel_st_irq)
- panic(pr_fmt("Unable to get IRQ from DT\n"));
-
- - /* Make IRQs happen for the system timer */
- - ret = request_irq(irq, at91rm9200_timer_interrupt,
- - IRQF_SHARED | IRQF_TIMER | IRQF_IRQPOLL,
- - "at91_tick", regmap_st);
- - if (ret)
- - panic(pr_fmt("Unable to setup IRQ\n"));
- -
- sclk = of_clk_get(node, 0);
- if (IS_ERR(sclk))
- panic(pr_fmt("Unable to get slow clock\n"));
- diff -Nur linux-4.4.28.orig/drivers/cpufreq/Kconfig.x86 linux-4.4.28/drivers/cpufreq/Kconfig.x86
- --- linux-4.4.28.orig/drivers/cpufreq/Kconfig.x86 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/cpufreq/Kconfig.x86 2016-11-01 21:26:57.956289426 +0100
- @@ -123,7 +123,7 @@
-
- config X86_POWERNOW_K8
- tristate "AMD Opteron/Athlon64 PowerNow!"
- - depends on ACPI && ACPI_PROCESSOR && X86_ACPI_CPUFREQ
- + depends on ACPI && ACPI_PROCESSOR && X86_ACPI_CPUFREQ && !PREEMPT_RT_BASE
- help
- This adds the CPUFreq driver for K8/early Opteron/Athlon64 processors.
- Support for K10 and newer processors is now in acpi-cpufreq.
- diff -Nur linux-4.4.28.orig/drivers/cpuidle/coupled.c linux-4.4.28/drivers/cpuidle/coupled.c
- --- linux-4.4.28.orig/drivers/cpuidle/coupled.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/cpuidle/coupled.c 2016-11-01 21:26:57.960289679 +0100
- @@ -119,7 +119,6 @@
-
- #define CPUIDLE_COUPLED_NOT_IDLE (-1)
-
- -static DEFINE_MUTEX(cpuidle_coupled_lock);
- static DEFINE_PER_CPU(struct call_single_data, cpuidle_coupled_poke_cb);
-
- /*
- diff -Nur linux-4.4.28.orig/drivers/gpu/drm/i915/i915_gem_execbuffer.c linux-4.4.28/drivers/gpu/drm/i915/i915_gem_execbuffer.c
- --- linux-4.4.28.orig/drivers/gpu/drm/i915/i915_gem_execbuffer.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/gpu/drm/i915/i915_gem_execbuffer.c 2016-11-01 21:26:57.980290973 +0100
- @@ -1264,7 +1264,9 @@
- if (ret)
- return ret;
-
- +#ifndef CONFIG_PREEMPT_RT_BASE
- trace_i915_gem_ring_dispatch(params->request, params->dispatch_flags);
- +#endif
-
- i915_gem_execbuffer_move_to_active(vmas, params->request);
- i915_gem_execbuffer_retire_commands(params);
- diff -Nur linux-4.4.28.orig/drivers/gpu/drm/i915/i915_gem_shrinker.c linux-4.4.28/drivers/gpu/drm/i915/i915_gem_shrinker.c
- --- linux-4.4.28.orig/drivers/gpu/drm/i915/i915_gem_shrinker.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/gpu/drm/i915/i915_gem_shrinker.c 2016-11-01 21:26:57.984291226 +0100
- @@ -39,7 +39,7 @@
- if (!mutex_is_locked(mutex))
- return false;
-
- -#if defined(CONFIG_DEBUG_MUTEXES) || defined(CONFIG_MUTEX_SPIN_ON_OWNER)
- +#if (defined(CONFIG_DEBUG_MUTEXES) || defined(CONFIG_MUTEX_SPIN_ON_OWNER)) && !defined(CONFIG_PREEMPT_RT_BASE)
- return mutex->owner == task;
- #else
- /* Since UP may be pre-empted, we cannot assume that we own the lock */
- diff -Nur linux-4.4.28.orig/drivers/gpu/drm/i915/i915_irq.c linux-4.4.28/drivers/gpu/drm/i915/i915_irq.c
- --- linux-4.4.28.orig/drivers/gpu/drm/i915/i915_irq.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/gpu/drm/i915/i915_irq.c 2016-11-01 21:26:58.000292256 +0100
- @@ -812,6 +812,7 @@
- spin_lock_irqsave(&dev_priv->uncore.lock, irqflags);
-
- /* preempt_disable_rt() should go right here in PREEMPT_RT patchset. */
- + preempt_disable_rt();
-
- /* Get optional system timestamp before query. */
- if (stime)
- @@ -863,6 +864,7 @@
- *etime = ktime_get();
-
- /* preempt_enable_rt() should go right here in PREEMPT_RT patchset. */
- + preempt_enable_rt();
-
- spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
-
- diff -Nur linux-4.4.28.orig/drivers/gpu/drm/i915/intel_display.c linux-4.4.28/drivers/gpu/drm/i915/intel_display.c
- --- linux-4.4.28.orig/drivers/gpu/drm/i915/intel_display.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/gpu/drm/i915/intel_display.c 2016-11-01 21:26:58.040294841 +0100
- @@ -11400,7 +11400,7 @@
- struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
- struct intel_unpin_work *work;
-
- - WARN_ON(!in_interrupt());
- + WARN_ON_NONRT(!in_interrupt());
-
- if (crtc == NULL)
- return;
- diff -Nur linux-4.4.28.orig/drivers/gpu/drm/i915/intel_sprite.c linux-4.4.28/drivers/gpu/drm/i915/intel_sprite.c
- --- linux-4.4.28.orig/drivers/gpu/drm/i915/intel_sprite.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/gpu/drm/i915/intel_sprite.c 2016-11-01 21:26:58.056295867 +0100
- @@ -38,6 +38,7 @@
- #include "intel_drv.h"
- #include <drm/i915_drm.h>
- #include "i915_drv.h"
- +#include <linux/locallock.h>
-
- static bool
- format_is_yuv(uint32_t format)
- @@ -64,6 +65,8 @@
- 1000 * adjusted_mode->crtc_htotal);
- }
-
- +static DEFINE_LOCAL_IRQ_LOCK(pipe_update_lock);
- +
- /**
- * intel_pipe_update_start() - start update of a set of display registers
- * @crtc: the crtc of which the registers are going to be updated
- @@ -96,7 +99,7 @@
- min = vblank_start - usecs_to_scanlines(adjusted_mode, 100);
- max = vblank_start - 1;
-
- - local_irq_disable();
- + local_lock_irq(pipe_update_lock);
-
- if (min <= 0 || max <= 0)
- return;
- @@ -126,11 +129,11 @@
- break;
- }
-
- - local_irq_enable();
- + local_unlock_irq(pipe_update_lock);
-
- timeout = schedule_timeout(timeout);
-
- - local_irq_disable();
- + local_lock_irq(pipe_update_lock);
- }
-
- finish_wait(wq, &wait);
- @@ -164,7 +167,7 @@
-
- trace_i915_pipe_update_end(crtc, end_vbl_count, scanline_end);
-
- - local_irq_enable();
- + local_unlock_irq(pipe_update_lock);
-
- if (crtc->debug.start_vbl_count &&
- crtc->debug.start_vbl_count != end_vbl_count) {
- diff -Nur linux-4.4.28.orig/drivers/gpu/drm/radeon/radeon_display.c linux-4.4.28/drivers/gpu/drm/radeon/radeon_display.c
- --- linux-4.4.28.orig/drivers/gpu/drm/radeon/radeon_display.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/gpu/drm/radeon/radeon_display.c 2016-11-01 21:26:58.068296641 +0100
- @@ -1862,6 +1862,7 @@
- struct radeon_device *rdev = dev->dev_private;
-
- /* preempt_disable_rt() should go right here in PREEMPT_RT patchset. */
- + preempt_disable_rt();
-
- /* Get optional system timestamp before query. */
- if (stime)
- @@ -1954,6 +1955,7 @@
- *etime = ktime_get();
-
- /* preempt_enable_rt() should go right here in PREEMPT_RT patchset. */
- + preempt_enable_rt();
-
- /* Decode into vertical and horizontal scanout position. */
- *vpos = position & 0x1fff;
- diff -Nur linux-4.4.28.orig/drivers/hv/vmbus_drv.c linux-4.4.28/drivers/hv/vmbus_drv.c
- --- linux-4.4.28.orig/drivers/hv/vmbus_drv.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/hv/vmbus_drv.c 2016-11-01 21:26:58.080297414 +0100
- @@ -820,7 +820,7 @@
- tasklet_schedule(&msg_dpc);
- }
-
- - add_interrupt_randomness(HYPERVISOR_CALLBACK_VECTOR, 0);
- + add_interrupt_randomness(HYPERVISOR_CALLBACK_VECTOR, 0, 0);
- }
-
-
- diff -Nur linux-4.4.28.orig/drivers/i2c/busses/i2c-omap.c linux-4.4.28/drivers/i2c/busses/i2c-omap.c
- --- linux-4.4.28.orig/drivers/i2c/busses/i2c-omap.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/i2c/busses/i2c-omap.c 2016-11-01 21:26:58.088297935 +0100
- @@ -995,15 +995,12 @@
- u16 mask;
- u16 stat;
-
- - spin_lock(&omap->lock);
- - mask = omap_i2c_read_reg(omap, OMAP_I2C_IE_REG);
- stat = omap_i2c_read_reg(omap, OMAP_I2C_STAT_REG);
- + mask = omap_i2c_read_reg(omap, OMAP_I2C_IE_REG);
-
- if (stat & mask)
- ret = IRQ_WAKE_THREAD;
-
- - spin_unlock(&omap->lock);
- -
- return ret;
- }
-
- diff -Nur linux-4.4.28.orig/drivers/ide/alim15x3.c linux-4.4.28/drivers/ide/alim15x3.c
- --- linux-4.4.28.orig/drivers/ide/alim15x3.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/ide/alim15x3.c 2016-11-01 21:26:58.096298444 +0100
- @@ -234,7 +234,7 @@
-
- isa_dev = pci_get_device(PCI_VENDOR_ID_AL, PCI_DEVICE_ID_AL_M1533, NULL);
-
- - local_irq_save(flags);
- + local_irq_save_nort(flags);
-
- if (m5229_revision < 0xC2) {
- /*
- @@ -325,7 +325,7 @@
- }
- pci_dev_put(north);
- pci_dev_put(isa_dev);
- - local_irq_restore(flags);
- + local_irq_restore_nort(flags);
- return 0;
- }
-
- diff -Nur linux-4.4.28.orig/drivers/ide/hpt366.c linux-4.4.28/drivers/ide/hpt366.c
- --- linux-4.4.28.orig/drivers/ide/hpt366.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/ide/hpt366.c 2016-11-01 21:26:58.100298709 +0100
- @@ -1241,7 +1241,7 @@
-
- dma_old = inb(base + 2);
-
- - local_irq_save(flags);
- + local_irq_save_nort(flags);
-
- dma_new = dma_old;
- pci_read_config_byte(dev, hwif->channel ? 0x4b : 0x43, &masterdma);
- @@ -1252,7 +1252,7 @@
- if (dma_new != dma_old)
- outb(dma_new, base + 2);
-
- - local_irq_restore(flags);
- + local_irq_restore_nort(flags);
-
- printk(KERN_INFO " %s: BM-DMA at 0x%04lx-0x%04lx\n",
- hwif->name, base, base + 7);
- diff -Nur linux-4.4.28.orig/drivers/ide/ide-io.c linux-4.4.28/drivers/ide/ide-io.c
- --- linux-4.4.28.orig/drivers/ide/ide-io.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/ide/ide-io.c 2016-11-01 21:26:58.108299218 +0100
- @@ -659,7 +659,7 @@
- /* disable_irq_nosync ?? */
- disable_irq(hwif->irq);
- /* local CPU only, as if we were handling an interrupt */
- - local_irq_disable();
- + local_irq_disable_nort();
- if (hwif->polling) {
- startstop = handler(drive);
- } else if (drive_is_ready(drive)) {
- diff -Nur linux-4.4.28.orig/drivers/ide/ide-iops.c linux-4.4.28/drivers/ide/ide-iops.c
- --- linux-4.4.28.orig/drivers/ide/ide-iops.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/ide/ide-iops.c 2016-11-01 21:26:58.108299218 +0100
- @@ -129,12 +129,12 @@
- if ((stat & ATA_BUSY) == 0)
- break;
-
- - local_irq_restore(flags);
- + local_irq_restore_nort(flags);
- *rstat = stat;
- return -EBUSY;
- }
- }
- - local_irq_restore(flags);
- + local_irq_restore_nort(flags);
- }
- /*
- * Allow status to settle, then read it again.
- diff -Nur linux-4.4.28.orig/drivers/ide/ide-io-std.c linux-4.4.28/drivers/ide/ide-io-std.c
- --- linux-4.4.28.orig/drivers/ide/ide-io-std.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/ide/ide-io-std.c 2016-11-01 21:26:58.104298962 +0100
- @@ -175,7 +175,7 @@
- unsigned long uninitialized_var(flags);
-
- if ((io_32bit & 2) && !mmio) {
- - local_irq_save(flags);
- + local_irq_save_nort(flags);
- ata_vlb_sync(io_ports->nsect_addr);
- }
-
- @@ -186,7 +186,7 @@
- insl(data_addr, buf, words);
-
- if ((io_32bit & 2) && !mmio)
- - local_irq_restore(flags);
- + local_irq_restore_nort(flags);
-
- if (((len + 1) & 3) < 2)
- return;
- @@ -219,7 +219,7 @@
- unsigned long uninitialized_var(flags);
-
- if ((io_32bit & 2) && !mmio) {
- - local_irq_save(flags);
- + local_irq_save_nort(flags);
- ata_vlb_sync(io_ports->nsect_addr);
- }
-
- @@ -230,7 +230,7 @@
- outsl(data_addr, buf, words);
-
- if ((io_32bit & 2) && !mmio)
- - local_irq_restore(flags);
- + local_irq_restore_nort(flags);
-
- if (((len + 1) & 3) < 2)
- return;
- diff -Nur linux-4.4.28.orig/drivers/ide/ide-probe.c linux-4.4.28/drivers/ide/ide-probe.c
- --- linux-4.4.28.orig/drivers/ide/ide-probe.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/ide/ide-probe.c 2016-11-01 21:26:58.116299735 +0100
- @@ -196,10 +196,10 @@
- int bswap = 1;
-
- /* local CPU only; some systems need this */
- - local_irq_save(flags);
- + local_irq_save_nort(flags);
- /* read 512 bytes of id info */
- hwif->tp_ops->input_data(drive, NULL, id, SECTOR_SIZE);
- - local_irq_restore(flags);
- + local_irq_restore_nort(flags);
-
- drive->dev_flags |= IDE_DFLAG_ID_READ;
- #ifdef DEBUG
- diff -Nur linux-4.4.28.orig/drivers/ide/ide-taskfile.c linux-4.4.28/drivers/ide/ide-taskfile.c
- --- linux-4.4.28.orig/drivers/ide/ide-taskfile.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/ide/ide-taskfile.c 2016-11-01 21:26:58.116299735 +0100
- @@ -250,7 +250,7 @@
-
- page_is_high = PageHighMem(page);
- if (page_is_high)
- - local_irq_save(flags);
- + local_irq_save_nort(flags);
-
- buf = kmap_atomic(page) + offset;
-
- @@ -271,7 +271,7 @@
- kunmap_atomic(buf);
-
- if (page_is_high)
- - local_irq_restore(flags);
- + local_irq_restore_nort(flags);
-
- len -= nr_bytes;
- }
- @@ -414,7 +414,7 @@
- }
-
- if ((drive->dev_flags & IDE_DFLAG_UNMASK) == 0)
- - local_irq_disable();
- + local_irq_disable_nort();
-
- ide_set_handler(drive, &task_pio_intr, WAIT_WORSTCASE);
-
- diff -Nur linux-4.4.28.orig/drivers/infiniband/ulp/ipoib/ipoib_multicast.c linux-4.4.28/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
- --- linux-4.4.28.orig/drivers/infiniband/ulp/ipoib/ipoib_multicast.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/infiniband/ulp/ipoib/ipoib_multicast.c 2016-11-01 21:26:58.124300256 +0100
- @@ -857,7 +857,7 @@
-
- ipoib_dbg_mcast(priv, "restarting multicast task\n");
-
- - local_irq_save(flags);
- + local_irq_save_nort(flags);
- netif_addr_lock(dev);
- spin_lock(&priv->lock);
-
- @@ -939,7 +939,7 @@
-
- spin_unlock(&priv->lock);
- netif_addr_unlock(dev);
- - local_irq_restore(flags);
- + local_irq_restore_nort(flags);
-
- /*
- * make sure the in-flight joins have finished before we attempt
- diff -Nur linux-4.4.28.orig/drivers/input/gameport/gameport.c linux-4.4.28/drivers/input/gameport/gameport.c
- --- linux-4.4.28.orig/drivers/input/gameport/gameport.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/input/gameport/gameport.c 2016-11-01 21:26:58.132300765 +0100
- @@ -91,13 +91,13 @@
- tx = ~0;
-
- for (i = 0; i < 50; i++) {
- - local_irq_save(flags);
- + local_irq_save_nort(flags);
- t1 = ktime_get_ns();
- for (t = 0; t < 50; t++)
- gameport_read(gameport);
- t2 = ktime_get_ns();
- t3 = ktime_get_ns();
- - local_irq_restore(flags);
- + local_irq_restore_nort(flags);
- udelay(i * 10);
- t = (t2 - t1) - (t3 - t2);
- if (t < tx)
- @@ -124,12 +124,12 @@
- tx = 1 << 30;
-
- for(i = 0; i < 50; i++) {
- - local_irq_save(flags);
- + local_irq_save_nort(flags);
- GET_TIME(t1);
- for (t = 0; t < 50; t++) gameport_read(gameport);
- GET_TIME(t2);
- GET_TIME(t3);
- - local_irq_restore(flags);
- + local_irq_restore_nort(flags);
- udelay(i * 10);
- if ((t = DELTA(t2,t1) - DELTA(t3,t2)) < tx) tx = t;
- }
- @@ -148,11 +148,11 @@
- tx = 1 << 30;
-
- for(i = 0; i < 50; i++) {
- - local_irq_save(flags);
- + local_irq_save_nort(flags);
- t1 = rdtsc();
- for (t = 0; t < 50; t++) gameport_read(gameport);
- t2 = rdtsc();
- - local_irq_restore(flags);
- + local_irq_restore_nort(flags);
- udelay(i * 10);
- if (t2 - t1 < tx) tx = t2 - t1;
- }
- diff -Nur linux-4.4.28.orig/drivers/iommu/amd_iommu.c linux-4.4.28/drivers/iommu/amd_iommu.c
- --- linux-4.4.28.orig/drivers/iommu/amd_iommu.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/iommu/amd_iommu.c 2016-11-01 21:26:58.156302312 +0100
- @@ -2019,10 +2019,10 @@
- int ret;
-
- /*
- - * Must be called with IRQs disabled. Warn here to detect early
- - * when its not.
- + * Must be called with IRQs disabled on a non RT kernel. Warn here to
- + * detect early when its not.
- */
- - WARN_ON(!irqs_disabled());
- + WARN_ON_NONRT(!irqs_disabled());
-
- /* lock domain */
- spin_lock(&domain->lock);
- @@ -2185,10 +2185,10 @@
- struct protection_domain *domain;
-
- /*
- - * Must be called with IRQs disabled. Warn here to detect early
- - * when its not.
- + * Must be called with IRQs disabled on a non RT kernel. Warn here to
- + * detect early when its not.
- */
- - WARN_ON(!irqs_disabled());
- + WARN_ON_NONRT(!irqs_disabled());
-
- if (WARN_ON(!dev_data->domain))
- return;
- diff -Nur linux-4.4.28.orig/drivers/leds/trigger/Kconfig linux-4.4.28/drivers/leds/trigger/Kconfig
- --- linux-4.4.28.orig/drivers/leds/trigger/Kconfig 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/leds/trigger/Kconfig 2016-11-01 21:26:58.168303087 +0100
- @@ -61,7 +61,7 @@
-
- config LEDS_TRIGGER_CPU
- bool "LED CPU Trigger"
- - depends on LEDS_TRIGGERS
- + depends on LEDS_TRIGGERS && !PREEMPT_RT_BASE
- help
- This allows LEDs to be controlled by active CPUs. This shows
- the active CPUs across an array of LEDs so you can see which
- diff -Nur linux-4.4.28.orig/drivers/md/bcache/Kconfig linux-4.4.28/drivers/md/bcache/Kconfig
- --- linux-4.4.28.orig/drivers/md/bcache/Kconfig 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/md/bcache/Kconfig 2016-11-01 21:26:58.172303343 +0100
- @@ -1,6 +1,7 @@
-
- config BCACHE
- tristate "Block device as cache"
- + depends on !PREEMPT_RT_FULL
- ---help---
- Allows a block device to be used as cache for other devices; uses
- a btree for indexing and the layout is optimized for SSDs.
- diff -Nur linux-4.4.28.orig/drivers/md/dm.c linux-4.4.28/drivers/md/dm.c
- --- linux-4.4.28.orig/drivers/md/dm.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/md/dm.c 2016-11-01 21:26:58.196304892 +0100
- @@ -2127,7 +2127,7 @@
- /* Establish tio->ti before queuing work (map_tio_request) */
- tio->ti = ti;
- queue_kthread_work(&md->kworker, &tio->work);
- - BUG_ON(!irqs_disabled());
- + BUG_ON_NONRT(!irqs_disabled());
- }
-
- goto out;
- diff -Nur linux-4.4.28.orig/drivers/md/raid5.c linux-4.4.28/drivers/md/raid5.c
- --- linux-4.4.28.orig/drivers/md/raid5.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/md/raid5.c 2016-11-01 21:26:58.224306697 +0100
- @@ -1920,8 +1920,9 @@
- struct raid5_percpu *percpu;
- unsigned long cpu;
-
- - cpu = get_cpu();
- + cpu = get_cpu_light();
- percpu = per_cpu_ptr(conf->percpu, cpu);
- + spin_lock(&percpu->lock);
- if (test_bit(STRIPE_OP_BIOFILL, &ops_request)) {
- ops_run_biofill(sh);
- overlap_clear++;
- @@ -1977,7 +1978,8 @@
- if (test_and_clear_bit(R5_Overlap, &dev->flags))
- wake_up(&sh->raid_conf->wait_for_overlap);
- }
- - put_cpu();
- + spin_unlock(&percpu->lock);
- + put_cpu_light();
- }
-
- static struct stripe_head *alloc_stripe(struct kmem_cache *sc, gfp_t gfp)
- @@ -6414,6 +6416,7 @@
- __func__, cpu);
- break;
- }
- + spin_lock_init(&per_cpu_ptr(conf->percpu, cpu)->lock);
- }
- put_online_cpus();
-
- diff -Nur linux-4.4.28.orig/drivers/md/raid5.h linux-4.4.28/drivers/md/raid5.h
- --- linux-4.4.28.orig/drivers/md/raid5.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/md/raid5.h 2016-11-01 21:26:58.236307469 +0100
- @@ -504,6 +504,7 @@
- int recovery_disabled;
- /* per cpu variables */
- struct raid5_percpu {
- + spinlock_t lock; /* Protection for -RT */
- struct page *spare_page; /* Used when checking P/Q in raid6 */
- struct flex_array *scribble; /* space for constructing buffer
- * lists and performing address
- diff -Nur linux-4.4.28.orig/drivers/media/platform/vsp1/vsp1_video.c linux-4.4.28/drivers/media/platform/vsp1/vsp1_video.c
- --- linux-4.4.28.orig/drivers/media/platform/vsp1/vsp1_video.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/media/platform/vsp1/vsp1_video.c 2016-11-01 21:26:58.244307986 +0100
- @@ -520,7 +520,7 @@
- bool stopped;
-
- spin_lock_irqsave(&pipe->irqlock, flags);
- - stopped = pipe->state == VSP1_PIPELINE_STOPPED,
- + stopped = pipe->state == VSP1_PIPELINE_STOPPED;
- spin_unlock_irqrestore(&pipe->irqlock, flags);
-
- return stopped;
- diff -Nur linux-4.4.28.orig/drivers/misc/hwlat_detector.c linux-4.4.28/drivers/misc/hwlat_detector.c
- --- linux-4.4.28.orig/drivers/misc/hwlat_detector.c 1970-01-01 01:00:00.000000000 +0100
- +++ linux-4.4.28/drivers/misc/hwlat_detector.c 2016-11-01 21:26:58.256308759 +0100
- @@ -0,0 +1,1240 @@
- +/*
- + * hwlat_detector.c - A simple Hardware Latency detector.
- + *
- + * Use this module to detect large system latencies induced by the behavior of
- + * certain underlying system hardware or firmware, independent of Linux itself.
- + * The code was developed originally to detect the presence of SMIs on Intel
- + * and AMD systems, although there is no dependency upon x86 herein.
- + *
- + * The classical example usage of this module is in detecting the presence of
- + * SMIs or System Management Interrupts on Intel and AMD systems. An SMI is a
- + * somewhat special form of hardware interrupt spawned from earlier CPU debug
- + * modes in which the (BIOS/EFI/etc.) firmware arranges for the South Bridge
- + * LPC (or other device) to generate a special interrupt under certain
- + * circumstances, for example, upon expiration of a special SMI timer device,
- + * due to certain external thermal readings, on certain I/O address accesses,
- + * and other situations. An SMI hits a special CPU pin, triggers a special
- + * SMI mode (complete with special memory map), and the OS is unaware.
- + *
- + * Although certain hardware-inducing latencies are necessary (for example,
- + * a modern system often requires an SMI handler for correct thermal control
- + * and remote management) they can wreak havoc upon any OS-level performance
- + * guarantees toward low-latency, especially when the OS is not even made
- + * aware of the presence of these interrupts. For this reason, we need a
- + * somewhat brute force mechanism to detect these interrupts. In this case,
- + * we do it by hogging all of the CPU(s) for configurable timer intervals,
- + * sampling the built-in CPU timer, looking for discontiguous readings.
- + *
- + * WARNING: This implementation necessarily introduces latencies. Therefore,
- + * you should NEVER use this module in a production environment
- + * requiring any kind of low-latency performance guarantee(s).
- + *
- + * Copyright (C) 2008-2009 Jon Masters, Red Hat, Inc. <jcm@redhat.com>
- + *
- + * Includes useful feedback from Clark Williams <clark@redhat.com>
- + *
- + * This file is licensed under the terms of the GNU General Public
- + * License version 2. This program is licensed "as is" without any
- + * warranty of any kind, whether express or implied.
- + */
- +
- +#include <linux/module.h>
- +#include <linux/init.h>
- +#include <linux/ring_buffer.h>
- +#include <linux/time.h>
- +#include <linux/hrtimer.h>
- +#include <linux/kthread.h>
- +#include <linux/debugfs.h>
- +#include <linux/seq_file.h>
- +#include <linux/uaccess.h>
- +#include <linux/version.h>
- +#include <linux/delay.h>
- +#include <linux/slab.h>
- +#include <linux/trace_clock.h>
- +
- +#define BUF_SIZE_DEFAULT 262144UL /* 8K*(sizeof(entry)) */
- +#define BUF_FLAGS (RB_FL_OVERWRITE) /* no block on full */
- +#define U64STR_SIZE 22 /* 20 digits max */
- +
- +#define VERSION "1.0.0"
- +#define BANNER "hwlat_detector: "
- +#define DRVNAME "hwlat_detector"
- +#define DEFAULT_SAMPLE_WINDOW 1000000 /* 1s */
- +#define DEFAULT_SAMPLE_WIDTH 500000 /* 0.5s */
- +#define DEFAULT_LAT_THRESHOLD 10 /* 10us */
- +
- +/* Module metadata */
- +
- +MODULE_LICENSE("GPL");
- +MODULE_AUTHOR("Jon Masters <jcm@redhat.com>");
- +MODULE_DESCRIPTION("A simple hardware latency detector");
- +MODULE_VERSION(VERSION);
- +
- +/* Module parameters */
- +
- +static int debug;
- +static int enabled;
- +static int threshold;
- +
- +module_param(debug, int, 0); /* enable debug */
- +module_param(enabled, int, 0); /* enable detector */
- +module_param(threshold, int, 0); /* latency threshold */
- +
- +/* Buffering and sampling */
- +
- +static struct ring_buffer *ring_buffer; /* sample buffer */
- +static DEFINE_MUTEX(ring_buffer_mutex); /* lock changes */
- +static unsigned long buf_size = BUF_SIZE_DEFAULT;
- +static struct task_struct *kthread; /* sampling thread */
- +
- +/* DebugFS filesystem entries */
- +
- +static struct dentry *debug_dir; /* debugfs directory */
- +static struct dentry *debug_max; /* maximum TSC delta */
- +static struct dentry *debug_count; /* total detect count */
- +static struct dentry *debug_sample_width; /* sample width us */
- +static struct dentry *debug_sample_window; /* sample window us */
- +static struct dentry *debug_sample; /* raw samples us */
- +static struct dentry *debug_threshold; /* threshold us */
- +static struct dentry *debug_enable; /* enable/disable */
- +
- +/* Individual samples and global state */
- +
- +struct sample; /* latency sample */
- +struct data; /* Global state */
- +
- +/* Sampling functions */
- +static int __buffer_add_sample(struct sample *sample);
- +static struct sample *buffer_get_sample(struct sample *sample);
- +
- +/* Threading and state */
- +static int kthread_fn(void *unused);
- +static int start_kthread(void);
- +static int stop_kthread(void);
- +static void __reset_stats(void);
- +static int init_stats(void);
- +
- +/* Debugfs interface */
- +static ssize_t simple_data_read(struct file *filp, char __user *ubuf,
- + size_t cnt, loff_t *ppos, const u64 *entry);
- +static ssize_t simple_data_write(struct file *filp, const char __user *ubuf,
- + size_t cnt, loff_t *ppos, u64 *entry);
- +static int debug_sample_fopen(struct inode *inode, struct file *filp);
- +static ssize_t debug_sample_fread(struct file *filp, char __user *ubuf,
- + size_t cnt, loff_t *ppos);
- +static int debug_sample_release(struct inode *inode, struct file *filp);
- +static int debug_enable_fopen(struct inode *inode, struct file *filp);
- +static ssize_t debug_enable_fread(struct file *filp, char __user *ubuf,
- + size_t cnt, loff_t *ppos);
- +static ssize_t debug_enable_fwrite(struct file *file,
- + const char __user *user_buffer,
- + size_t user_size, loff_t *offset);
- +
- +/* Initialization functions */
- +static int init_debugfs(void);
- +static void free_debugfs(void);
- +static int detector_init(void);
- +static void detector_exit(void);
- +
- +/* Individual latency samples are stored here when detected and packed into
- + * the ring_buffer circular buffer, where they are overwritten when
- + * more than buf_size/sizeof(sample) samples are received. */
- +struct sample {
- + u64 seqnum; /* unique sequence */
- + u64 duration; /* ktime delta */
- + u64 outer_duration; /* ktime delta (outer loop) */
- + struct timespec timestamp; /* wall time */
- + unsigned long lost;
- +};
- +
- +/* keep the global state somewhere. */
- +static struct data {
- +
- + struct mutex lock; /* protect changes */
- +
- + u64 count; /* total since reset */
- + u64 max_sample; /* max hardware latency */
- + u64 threshold; /* sample threshold level */
- +
- + u64 sample_window; /* total sampling window (on+off) */
- + u64 sample_width; /* active sampling portion of window */
- +
- + atomic_t sample_open; /* whether the sample file is open */
- +
- + wait_queue_head_t wq; /* waitqeue for new sample values */
- +
- +} data;
- +
- +/**
- + * __buffer_add_sample - add a new latency sample recording to the ring buffer
- + * @sample: The new latency sample value
- + *
- + * This receives a new latency sample and records it in a global ring buffer.
- + * No additional locking is used in this case.
- + */
- +static int __buffer_add_sample(struct sample *sample)
- +{
- + return ring_buffer_write(ring_buffer,
- + sizeof(struct sample), sample);
- +}
- +
- +/**
- + * buffer_get_sample - remove a hardware latency sample from the ring buffer
- + * @sample: Pre-allocated storage for the sample
- + *
- + * This retrieves a hardware latency sample from the global circular buffer
- + */
- +static struct sample *buffer_get_sample(struct sample *sample)
- +{
- + struct ring_buffer_event *e = NULL;
- + struct sample *s = NULL;
- + unsigned int cpu = 0;
- +
- + if (!sample)
- + return NULL;
- +
- + mutex_lock(&ring_buffer_mutex);
- + for_each_online_cpu(cpu) {
- + e = ring_buffer_consume(ring_buffer, cpu, NULL, &sample->lost);
- + if (e)
- + break;
- + }
- +
- + if (e) {
- + s = ring_buffer_event_data(e);
- + memcpy(sample, s, sizeof(struct sample));
- + } else
- + sample = NULL;
- + mutex_unlock(&ring_buffer_mutex);
- +
- + return sample;
- +}
- +
- +#ifndef CONFIG_TRACING
- +#define time_type ktime_t
- +#define time_get() ktime_get()
- +#define time_to_us(x) ktime_to_us(x)
- +#define time_sub(a, b) ktime_sub(a, b)
- +#define init_time(a, b) (a).tv64 = b
- +#define time_u64(a) ((a).tv64)
- +#else
- +#define time_type u64
- +#define time_get() trace_clock_local()
- +#define time_to_us(x) div_u64(x, 1000)
- +#define time_sub(a, b) ((a) - (b))
- +#define init_time(a, b) (a = b)
- +#define time_u64(a) a
- +#endif
- +/**
- + * get_sample - sample the CPU TSC and look for likely hardware latencies
- + *
- + * Used to repeatedly capture the CPU TSC (or similar), looking for potential
- + * hardware-induced latency. Called with interrupts disabled and with
- + * data.lock held.
- + */
- +static int get_sample(void)
- +{
- + time_type start, t1, t2, last_t2;
- + s64 diff, total = 0;
- + u64 sample = 0;
- + u64 outer_sample = 0;
- + int ret = -1;
- +
- + init_time(last_t2, 0);
- + start = time_get(); /* start timestamp */
- +
- + do {
- +
- + t1 = time_get(); /* we'll look for a discontinuity */
- + t2 = time_get();
- +
- + if (time_u64(last_t2)) {
- + /* Check the delta from outer loop (t2 to next t1) */
- + diff = time_to_us(time_sub(t1, last_t2));
- + /* This shouldn't happen */
- + if (diff < 0) {
- + pr_err(BANNER "time running backwards\n");
- + goto out;
- + }
- + if (diff > outer_sample)
- + outer_sample = diff;
- + }
- + last_t2 = t2;
- +
- + total = time_to_us(time_sub(t2, start)); /* sample width */
- +
- + /* This checks the inner loop (t1 to t2) */
- + diff = time_to_us(time_sub(t2, t1)); /* current diff */
- +
- + /* This shouldn't happen */
- + if (diff < 0) {
- + pr_err(BANNER "time running backwards\n");
- + goto out;
- + }
- +
- + if (diff > sample)
- + sample = diff; /* only want highest value */
- +
- + } while (total <= data.sample_width);
- +
- + ret = 0;
- +
- + /* If we exceed the threshold value, we have found a hardware latency */
- + if (sample > data.threshold || outer_sample > data.threshold) {
- + struct sample s;
- +
- + ret = 1;
- +
- + data.count++;
- + s.seqnum = data.count;
- + s.duration = sample;
- + s.outer_duration = outer_sample;
- + s.timestamp = CURRENT_TIME;
- + __buffer_add_sample(&s);
- +
- + /* Keep a running maximum ever recorded hardware latency */
- + if (sample > data.max_sample)
- + data.max_sample = sample;
- + }
- +
- +out:
- + return ret;
- +}
- +
- +/*
- + * kthread_fn - The CPU time sampling/hardware latency detection kernel thread
- + * @unused: A required part of the kthread API.
- + *
- + * Used to periodically sample the CPU TSC via a call to get_sample. We
- + * disable interrupts, which does (intentionally) introduce latency since we
- + * need to ensure nothing else might be running (and thus pre-empting).
- + * Obviously this should never be used in production environments.
- + *
- + * Currently this runs on which ever CPU it was scheduled on, but most
- + * real-worald hardware latency situations occur across several CPUs,
- + * but we might later generalize this if we find there are any actualy
- + * systems with alternate SMI delivery or other hardware latencies.
- + */
- +static int kthread_fn(void *unused)
- +{
- + int ret;
- + u64 interval;
- +
- + while (!kthread_should_stop()) {
- +
- + mutex_lock(&data.lock);
- +
- + local_irq_disable();
- + ret = get_sample();
- + local_irq_enable();
- +
- + if (ret > 0)
- + wake_up(&data.wq); /* wake up reader(s) */
- +
- + interval = data.sample_window - data.sample_width;
- + do_div(interval, USEC_PER_MSEC); /* modifies interval value */
- +
- + mutex_unlock(&data.lock);
- +
- + if (msleep_interruptible(interval))
- + break;
- + }
- +
- + return 0;
- +}
- +
- +/**
- + * start_kthread - Kick off the hardware latency sampling/detector kthread
- + *
- + * This starts a kernel thread that will sit and sample the CPU timestamp
- + * counter (TSC or similar) and look for potential hardware latencies.
- + */
- +static int start_kthread(void)
- +{
- + kthread = kthread_run(kthread_fn, NULL,
- + DRVNAME);
- + if (IS_ERR(kthread)) {
- + pr_err(BANNER "could not start sampling thread\n");
- + enabled = 0;
- + return -ENOMEM;
- + }
- +
- + return 0;
- +}
- +
- +/**
- + * stop_kthread - Inform the hardware latency samping/detector kthread to stop
- + *
- + * This kicks the running hardware latency sampling/detector kernel thread and
- + * tells it to stop sampling now. Use this on unload and at system shutdown.
- + */
- +static int stop_kthread(void)
- +{
- + int ret;
- +
- + ret = kthread_stop(kthread);
- +
- + return ret;
- +}
- +
- +/**
- + * __reset_stats - Reset statistics for the hardware latency detector
- + *
- + * We use data to store various statistics and global state. We call this
- + * function in order to reset those when "enable" is toggled on or off, and
- + * also at initialization. Should be called with data.lock held.
- + */
- +static void __reset_stats(void)
- +{
- + data.count = 0;
- + data.max_sample = 0;
- + ring_buffer_reset(ring_buffer); /* flush out old sample entries */
- +}
- +
- +/**
- + * init_stats - Setup global state statistics for the hardware latency detector
- + *
- + * We use data to store various statistics and global state. We also use
- + * a global ring buffer (ring_buffer) to keep raw samples of detected hardware
- + * induced system latencies. This function initializes these structures and
- + * allocates the global ring buffer also.
- + */
- +static int init_stats(void)
- +{
- + int ret = -ENOMEM;
- +
- + mutex_init(&data.lock);
- + init_waitqueue_head(&data.wq);
- + atomic_set(&data.sample_open, 0);
- +
- + ring_buffer = ring_buffer_alloc(buf_size, BUF_FLAGS);
- +
- + if (WARN(!ring_buffer, KERN_ERR BANNER
- + "failed to allocate ring buffer!\n"))
- + goto out;
- +
- + __reset_stats();
- + data.threshold = threshold ?: DEFAULT_LAT_THRESHOLD; /* threshold us */
- + data.sample_window = DEFAULT_SAMPLE_WINDOW; /* window us */
- + data.sample_width = DEFAULT_SAMPLE_WIDTH; /* width us */
- +
- + ret = 0;
- +
- +out:
- + return ret;
- +
- +}
- +
- +/*
- + * simple_data_read - Wrapper read function for global state debugfs entries
- + * @filp: The active open file structure for the debugfs "file"
- + * @ubuf: The userspace provided buffer to read value into
- + * @cnt: The maximum number of bytes to read
- + * @ppos: The current "file" position
- + * @entry: The entry to read from
- + *
- + * This function provides a generic read implementation for the global state
- + * "data" structure debugfs filesystem entries. It would be nice to use
- + * simple_attr_read directly, but we need to make sure that the data.lock
- + * is held during the actual read.
- + */
- +static ssize_t simple_data_read(struct file *filp, char __user *ubuf,
- + size_t cnt, loff_t *ppos, const u64 *entry)
- +{
- + char buf[U64STR_SIZE];
- + u64 val = 0;
- + int len = 0;
- +
- + memset(buf, 0, sizeof(buf));
- +
- + if (!entry)
- + return -EFAULT;
- +
- + mutex_lock(&data.lock);
- + val = *entry;
- + mutex_unlock(&data.lock);
- +
- + len = snprintf(buf, sizeof(buf), "%llu\n", (unsigned long long)val);
- +
- + return simple_read_from_buffer(ubuf, cnt, ppos, buf, len);
- +
- +}
- +
- +/*
- + * simple_data_write - Wrapper write function for global state debugfs entries
- + * @filp: The active open file structure for the debugfs "file"
- + * @ubuf: The userspace provided buffer to write value from
- + * @cnt: The maximum number of bytes to write
- + * @ppos: The current "file" position
- + * @entry: The entry to write to
- + *
- + * This function provides a generic write implementation for the global state
- + * "data" structure debugfs filesystem entries. It would be nice to use
- + * simple_attr_write directly, but we need to make sure that the data.lock
- + * is held during the actual write.
- + */
- +static ssize_t simple_data_write(struct file *filp, const char __user *ubuf,
- + size_t cnt, loff_t *ppos, u64 *entry)
- +{
- + char buf[U64STR_SIZE];
- + int csize = min(cnt, sizeof(buf));
- + u64 val = 0;
- + int err = 0;
- +
- + memset(buf, '\0', sizeof(buf));
- + if (copy_from_user(buf, ubuf, csize))
- + return -EFAULT;
- +
- + buf[U64STR_SIZE-1] = '\0'; /* just in case */
- + err = kstrtoull(buf, 10, &val);
- + if (err)
- + return -EINVAL;
- +
- + mutex_lock(&data.lock);
- + *entry = val;
- + mutex_unlock(&data.lock);
- +
- + return csize;
- +}
- +
- +/**
- + * debug_count_fopen - Open function for "count" debugfs entry
- + * @inode: The in-kernel inode representation of the debugfs "file"
- + * @filp: The active open file structure for the debugfs "file"
- + *
- + * This function provides an open implementation for the "count" debugfs
- + * interface to the hardware latency detector.
- + */
- +static int debug_count_fopen(struct inode *inode, struct file *filp)
- +{
- + return 0;
- +}
- +
- +/**
- + * debug_count_fread - Read function for "count" debugfs entry
- + * @filp: The active open file structure for the debugfs "file"
- + * @ubuf: The userspace provided buffer to read value into
- + * @cnt: The maximum number of bytes to read
- + * @ppos: The current "file" position
- + *
- + * This function provides a read implementation for the "count" debugfs
- + * interface to the hardware latency detector. Can be used to read the
- + * number of latency readings exceeding the configured threshold since
- + * the detector was last reset (e.g. by writing a zero into "count").
- + */
- +static ssize_t debug_count_fread(struct file *filp, char __user *ubuf,
- + size_t cnt, loff_t *ppos)
- +{
- + return simple_data_read(filp, ubuf, cnt, ppos, &data.count);
- +}
- +
- +/**
- + * debug_count_fwrite - Write function for "count" debugfs entry
- + * @filp: The active open file structure for the debugfs "file"
- + * @ubuf: The user buffer that contains the value to write
- + * @cnt: The maximum number of bytes to write to "file"
- + * @ppos: The current position in the debugfs "file"
- + *
- + * This function provides a write implementation for the "count" debugfs
- + * interface to the hardware latency detector. Can be used to write a
- + * desired value, especially to zero the total count.
- + */
- +static ssize_t debug_count_fwrite(struct file *filp,
- + const char __user *ubuf,
- + size_t cnt,
- + loff_t *ppos)
- +{
- + return simple_data_write(filp, ubuf, cnt, ppos, &data.count);
- +}
- +
- +/**
- + * debug_enable_fopen - Dummy open function for "enable" debugfs interface
- + * @inode: The in-kernel inode representation of the debugfs "file"
- + * @filp: The active open file structure for the debugfs "file"
- + *
- + * This function provides an open implementation for the "enable" debugfs
- + * interface to the hardware latency detector.
- + */
- +static int debug_enable_fopen(struct inode *inode, struct file *filp)
- +{
- + return 0;
- +}
- +
- +/**
- + * debug_enable_fread - Read function for "enable" debugfs interface
- + * @filp: The active open file structure for the debugfs "file"
- + * @ubuf: The userspace provided buffer to read value into
- + * @cnt: The maximum number of bytes to read
- + * @ppos: The current "file" position
- + *
- + * This function provides a read implementation for the "enable" debugfs
- + * interface to the hardware latency detector. Can be used to determine
- + * whether the detector is currently enabled ("0\n" or "1\n" returned).
- + */
- +static ssize_t debug_enable_fread(struct file *filp, char __user *ubuf,
- + size_t cnt, loff_t *ppos)
- +{
- + char buf[4];
- +
- + if ((cnt < sizeof(buf)) || (*ppos))
- + return 0;
- +
- + buf[0] = enabled ? '1' : '0';
- + buf[1] = '\n';
- + buf[2] = '\0';
- + if (copy_to_user(ubuf, buf, strlen(buf)))
- + return -EFAULT;
- + return *ppos = strlen(buf);
- +}
- +
- +/**
- + * debug_enable_fwrite - Write function for "enable" debugfs interface
- + * @filp: The active open file structure for the debugfs "file"
- + * @ubuf: The user buffer that contains the value to write
- + * @cnt: The maximum number of bytes to write to "file"
- + * @ppos: The current position in the debugfs "file"
- + *
- + * This function provides a write implementation for the "enable" debugfs
- + * interface to the hardware latency detector. Can be used to enable or
- + * disable the detector, which will have the side-effect of possibly
- + * also resetting the global stats and kicking off the measuring
- + * kthread (on an enable) or the converse (upon a disable).
- + */
- +static ssize_t debug_enable_fwrite(struct file *filp,
- + const char __user *ubuf,
- + size_t cnt,
- + loff_t *ppos)
- +{
- + char buf[4];
- + int csize = min(cnt, sizeof(buf));
- + long val = 0;
- + int err = 0;
- +
- + memset(buf, '\0', sizeof(buf));
- + if (copy_from_user(buf, ubuf, csize))
- + return -EFAULT;
- +
- + buf[sizeof(buf)-1] = '\0'; /* just in case */
- + err = kstrtoul(buf, 10, &val);
- + if (err)
- + return -EINVAL;
- +
- + if (val) {
- + if (enabled)
- + goto unlock;
- + enabled = 1;
- + __reset_stats();
- + if (start_kthread())
- + return -EFAULT;
- + } else {
- + if (!enabled)
- + goto unlock;
- + enabled = 0;
- + err = stop_kthread();
- + if (err) {
- + pr_err(BANNER "cannot stop kthread\n");
- + return -EFAULT;
- + }
- + wake_up(&data.wq); /* reader(s) should return */
- + }
- +unlock:
- + return csize;
- +}
- +
- +/**
- + * debug_max_fopen - Open function for "max" debugfs entry
- + * @inode: The in-kernel inode representation of the debugfs "file"
- + * @filp: The active open file structure for the debugfs "file"
- + *
- + * This function provides an open implementation for the "max" debugfs
- + * interface to the hardware latency detector.
- + */
- +static int debug_max_fopen(struct inode *inode, struct file *filp)
- +{
- + return 0;
- +}
- +
- +/**
- + * debug_max_fread - Read function for "max" debugfs entry
- + * @filp: The active open file structure for the debugfs "file"
- + * @ubuf: The userspace provided buffer to read value into
- + * @cnt: The maximum number of bytes to read
- + * @ppos: The current "file" position
- + *
- + * This function provides a read implementation for the "max" debugfs
- + * interface to the hardware latency detector. Can be used to determine
- + * the maximum latency value observed since it was last reset.
- + */
- +static ssize_t debug_max_fread(struct file *filp, char __user *ubuf,
- + size_t cnt, loff_t *ppos)
- +{
- + return simple_data_read(filp, ubuf, cnt, ppos, &data.max_sample);
- +}
- +
- +/**
- + * debug_max_fwrite - Write function for "max" debugfs entry
- + * @filp: The active open file structure for the debugfs "file"
- + * @ubuf: The user buffer that contains the value to write
- + * @cnt: The maximum number of bytes to write to "file"
- + * @ppos: The current position in the debugfs "file"
- + *
- + * This function provides a write implementation for the "max" debugfs
- + * interface to the hardware latency detector. Can be used to reset the
- + * maximum or set it to some other desired value - if, then, subsequent
- + * measurements exceed this value, the maximum will be updated.
- + */
- +static ssize_t debug_max_fwrite(struct file *filp,
- + const char __user *ubuf,
- + size_t cnt,
- + loff_t *ppos)
- +{
- + return simple_data_write(filp, ubuf, cnt, ppos, &data.max_sample);
- +}
- +
- +
- +/**
- + * debug_sample_fopen - An open function for "sample" debugfs interface
- + * @inode: The in-kernel inode representation of this debugfs "file"
- + * @filp: The active open file structure for the debugfs "file"
- + *
- + * This function handles opening the "sample" file within the hardware
- + * latency detector debugfs directory interface. This file is used to read
- + * raw samples from the global ring_buffer and allows the user to see a
- + * running latency history. Can be opened blocking or non-blocking,
- + * affecting whether it behaves as a buffer read pipe, or does not.
- + * Implements simple locking to prevent multiple simultaneous use.
- + */
- +static int debug_sample_fopen(struct inode *inode, struct file *filp)
- +{
- + if (!atomic_add_unless(&data.sample_open, 1, 1))
- + return -EBUSY;
- + else
- + return 0;
- +}
- +
- +/**
- + * debug_sample_fread - A read function for "sample" debugfs interface
- + * @filp: The active open file structure for the debugfs "file"
- + * @ubuf: The user buffer that will contain the samples read
- + * @cnt: The maximum bytes to read from the debugfs "file"
- + * @ppos: The current position in the debugfs "file"
- + *
- + * This function handles reading from the "sample" file within the hardware
- + * latency detector debugfs directory interface. This file is used to read
- + * raw samples from the global ring_buffer and allows the user to see a
- + * running latency history. By default this will block pending a new
- + * value written into the sample buffer, unless there are already a
- + * number of value(s) waiting in the buffer, or the sample file was
- + * previously opened in a non-blocking mode of operation.
- + */
- +static ssize_t debug_sample_fread(struct file *filp, char __user *ubuf,
- + size_t cnt, loff_t *ppos)
- +{
- + int len = 0;
- + char buf[64];
- + struct sample *sample = NULL;
- +
- + if (!enabled)
- + return 0;
- +
- + sample = kzalloc(sizeof(struct sample), GFP_KERNEL);
- + if (!sample)
- + return -ENOMEM;
- +
- + while (!buffer_get_sample(sample)) {
- +
- + DEFINE_WAIT(wait);
- +
- + if (filp->f_flags & O_NONBLOCK) {
- + len = -EAGAIN;
- + goto out;
- + }
- +
- + prepare_to_wait(&data.wq, &wait, TASK_INTERRUPTIBLE);
- + schedule();
- + finish_wait(&data.wq, &wait);
- +
- + if (signal_pending(current)) {
- + len = -EINTR;
- + goto out;
- + }
- +
- + if (!enabled) { /* enable was toggled */
- + len = 0;
- + goto out;
- + }
- + }
- +
- + len = snprintf(buf, sizeof(buf), "%010lu.%010lu\t%llu\t%llu\n",
- + sample->timestamp.tv_sec,
- + sample->timestamp.tv_nsec,
- + sample->duration,
- + sample->outer_duration);
- +
- +
- + /* handling partial reads is more trouble than it's worth */
- + if (len > cnt)
- + goto out;
- +
- + if (copy_to_user(ubuf, buf, len))
- + len = -EFAULT;
- +
- +out:
- + kfree(sample);
- + return len;
- +}
- +
- +/**
- + * debug_sample_release - Release function for "sample" debugfs interface
- + * @inode: The in-kernel inode represenation of the debugfs "file"
- + * @filp: The active open file structure for the debugfs "file"
- + *
- + * This function completes the close of the debugfs interface "sample" file.
- + * Frees the sample_open "lock" so that other users may open the interface.
- + */
- +static int debug_sample_release(struct inode *inode, struct file *filp)
- +{
- + atomic_dec(&data.sample_open);
- +
- + return 0;
- +}
- +
- +/**
- + * debug_threshold_fopen - Open function for "threshold" debugfs entry
- + * @inode: The in-kernel inode representation of the debugfs "file"
- + * @filp: The active open file structure for the debugfs "file"
- + *
- + * This function provides an open implementation for the "threshold" debugfs
- + * interface to the hardware latency detector.
- + */
- +static int debug_threshold_fopen(struct inode *inode, struct file *filp)
- +{
- + return 0;
- +}
- +
- +/**
- + * debug_threshold_fread - Read function for "threshold" debugfs entry
- + * @filp: The active open file structure for the debugfs "file"
- + * @ubuf: The userspace provided buffer to read value into
- + * @cnt: The maximum number of bytes to read
- + * @ppos: The current "file" position
- + *
- + * This function provides a read implementation for the "threshold" debugfs
- + * interface to the hardware latency detector. It can be used to determine
- + * the current threshold level at which a latency will be recorded in the
- + * global ring buffer, typically on the order of 10us.
- + */
- +static ssize_t debug_threshold_fread(struct file *filp, char __user *ubuf,
- + size_t cnt, loff_t *ppos)
- +{
- + return simple_data_read(filp, ubuf, cnt, ppos, &data.threshold);
- +}
- +
- +/**
- + * debug_threshold_fwrite - Write function for "threshold" debugfs entry
- + * @filp: The active open file structure for the debugfs "file"
- + * @ubuf: The user buffer that contains the value to write
- + * @cnt: The maximum number of bytes to write to "file"
- + * @ppos: The current position in the debugfs "file"
- + *
- + * This function provides a write implementation for the "threshold" debugfs
- + * interface to the hardware latency detector. It can be used to configure
- + * the threshold level at which any subsequently detected latencies will
- + * be recorded into the global ring buffer.
- + */
- +static ssize_t debug_threshold_fwrite(struct file *filp,
- + const char __user *ubuf,
- + size_t cnt,
- + loff_t *ppos)
- +{
- + int ret;
- +
- + ret = simple_data_write(filp, ubuf, cnt, ppos, &data.threshold);
- +
- + if (enabled)
- + wake_up_process(kthread);
- +
- + return ret;
- +}
- +
- +/**
- + * debug_width_fopen - Open function for "width" debugfs entry
- + * @inode: The in-kernel inode representation of the debugfs "file"
- + * @filp: The active open file structure for the debugfs "file"
- + *
- + * This function provides an open implementation for the "width" debugfs
- + * interface to the hardware latency detector.
- + */
- +static int debug_width_fopen(struct inode *inode, struct file *filp)
- +{
- + return 0;
- +}
- +
- +/**
- + * debug_width_fread - Read function for "width" debugfs entry
- + * @filp: The active open file structure for the debugfs "file"
- + * @ubuf: The userspace provided buffer to read value into
- + * @cnt: The maximum number of bytes to read
- + * @ppos: The current "file" position
- + *
- + * This function provides a read implementation for the "width" debugfs
- + * interface to the hardware latency detector. It can be used to determine
- + * for how many us of the total window us we will actively sample for any
- + * hardware-induced latecy periods. Obviously, it is not possible to
- + * sample constantly and have the system respond to a sample reader, or,
- + * worse, without having the system appear to have gone out to lunch.
- + */
- +static ssize_t debug_width_fread(struct file *filp, char __user *ubuf,
- + size_t cnt, loff_t *ppos)
- +{
- + return simple_data_read(filp, ubuf, cnt, ppos, &data.sample_width);
- +}
- +
- +/**
- + * debug_width_fwrite - Write function for "width" debugfs entry
- + * @filp: The active open file structure for the debugfs "file"
- + * @ubuf: The user buffer that contains the value to write
- + * @cnt: The maximum number of bytes to write to "file"
- + * @ppos: The current position in the debugfs "file"
- + *
- + * This function provides a write implementation for the "width" debugfs
- + * interface to the hardware latency detector. It can be used to configure
- + * for how many us of the total window us we will actively sample for any
- + * hardware-induced latency periods. Obviously, it is not possible to
- + * sample constantly and have the system respond to a sample reader, or,
- + * worse, without having the system appear to have gone out to lunch. It
- + * is enforced that width is less that the total window size.
- + */
- +static ssize_t debug_width_fwrite(struct file *filp,
- + const char __user *ubuf,
- + size_t cnt,
- + loff_t *ppos)
- +{
- + char buf[U64STR_SIZE];
- + int csize = min(cnt, sizeof(buf));
- + u64 val = 0;
- + int err = 0;
- +
- + memset(buf, '\0', sizeof(buf));
- + if (copy_from_user(buf, ubuf, csize))
- + return -EFAULT;
- +
- + buf[U64STR_SIZE-1] = '\0'; /* just in case */
- + err = kstrtoull(buf, 10, &val);
- + if (err)
- + return -EINVAL;
- +
- + mutex_lock(&data.lock);
- + if (val < data.sample_window)
- + data.sample_width = val;
- + else {
- + mutex_unlock(&data.lock);
- + return -EINVAL;
- + }
- + mutex_unlock(&data.lock);
- +
- + if (enabled)
- + wake_up_process(kthread);
- +
- + return csize;
- +}
- +
- +/**
- + * debug_window_fopen - Open function for "window" debugfs entry
- + * @inode: The in-kernel inode representation of the debugfs "file"
- + * @filp: The active open file structure for the debugfs "file"
- + *
- + * This function provides an open implementation for the "window" debugfs
- + * interface to the hardware latency detector. The window is the total time
- + * in us that will be considered one sample period. Conceptually, windows
- + * occur back-to-back and contain a sample width period during which
- + * actual sampling occurs.
- + */
- +static int debug_window_fopen(struct inode *inode, struct file *filp)
- +{
- + return 0;
- +}
- +
- +/**
- + * debug_window_fread - Read function for "window" debugfs entry
- + * @filp: The active open file structure for the debugfs "file"
- + * @ubuf: The userspace provided buffer to read value into
- + * @cnt: The maximum number of bytes to read
- + * @ppos: The current "file" position
- + *
- + * This function provides a read implementation for the "window" debugfs
- + * interface to the hardware latency detector. The window is the total time
- + * in us that will be considered one sample period. Conceptually, windows
- + * occur back-to-back and contain a sample width period during which
- + * actual sampling occurs. Can be used to read the total window size.
- + */
- +static ssize_t debug_window_fread(struct file *filp, char __user *ubuf,
- + size_t cnt, loff_t *ppos)
- +{
- + return simple_data_read(filp, ubuf, cnt, ppos, &data.sample_window);
- +}
- +
- +/**
- + * debug_window_fwrite - Write function for "window" debugfs entry
- + * @filp: The active open file structure for the debugfs "file"
- + * @ubuf: The user buffer that contains the value to write
- + * @cnt: The maximum number of bytes to write to "file"
- + * @ppos: The current position in the debugfs "file"
- + *
- + * This function provides a write implementation for the "window" debufds
- + * interface to the hardware latency detetector. The window is the total time
- + * in us that will be considered one sample period. Conceptually, windows
- + * occur back-to-back and contain a sample width period during which
- + * actual sampling occurs. Can be used to write a new total window size. It
- + * is enfoced that any value written must be greater than the sample width
- + * size, or an error results.
- + */
- +static ssize_t debug_window_fwrite(struct file *filp,
- + const char __user *ubuf,
- + size_t cnt,
- + loff_t *ppos)
- +{
- + char buf[U64STR_SIZE];
- + int csize = min(cnt, sizeof(buf));
- + u64 val = 0;
- + int err = 0;
- +
- + memset(buf, '\0', sizeof(buf));
- + if (copy_from_user(buf, ubuf, csize))
- + return -EFAULT;
- +
- + buf[U64STR_SIZE-1] = '\0'; /* just in case */
- + err = kstrtoull(buf, 10, &val);
- + if (err)
- + return -EINVAL;
- +
- + mutex_lock(&data.lock);
- + if (data.sample_width < val)
- + data.sample_window = val;
- + else {
- + mutex_unlock(&data.lock);
- + return -EINVAL;
- + }
- + mutex_unlock(&data.lock);
- +
- + return csize;
- +}
- +
- +/*
- + * Function pointers for the "count" debugfs file operations
- + */
- +static const struct file_operations count_fops = {
- + .open = debug_count_fopen,
- + .read = debug_count_fread,
- + .write = debug_count_fwrite,
- + .owner = THIS_MODULE,
- +};
- +
- +/*
- + * Function pointers for the "enable" debugfs file operations
- + */
- +static const struct file_operations enable_fops = {
- + .open = debug_enable_fopen,
- + .read = debug_enable_fread,
- + .write = debug_enable_fwrite,
- + .owner = THIS_MODULE,
- +};
- +
- +/*
- + * Function pointers for the "max" debugfs file operations
- + */
- +static const struct file_operations max_fops = {
- + .open = debug_max_fopen,
- + .read = debug_max_fread,
- + .write = debug_max_fwrite,
- + .owner = THIS_MODULE,
- +};
- +
- +/*
- + * Function pointers for the "sample" debugfs file operations
- + */
- +static const struct file_operations sample_fops = {
- + .open = debug_sample_fopen,
- + .read = debug_sample_fread,
- + .release = debug_sample_release,
- + .owner = THIS_MODULE,
- +};
- +
- +/*
- + * Function pointers for the "threshold" debugfs file operations
- + */
- +static const struct file_operations threshold_fops = {
- + .open = debug_threshold_fopen,
- + .read = debug_threshold_fread,
- + .write = debug_threshold_fwrite,
- + .owner = THIS_MODULE,
- +};
- +
- +/*
- + * Function pointers for the "width" debugfs file operations
- + */
- +static const struct file_operations width_fops = {
- + .open = debug_width_fopen,
- + .read = debug_width_fread,
- + .write = debug_width_fwrite,
- + .owner = THIS_MODULE,
- +};
- +
- +/*
- + * Function pointers for the "window" debugfs file operations
- + */
- +static const struct file_operations window_fops = {
- + .open = debug_window_fopen,
- + .read = debug_window_fread,
- + .write = debug_window_fwrite,
- + .owner = THIS_MODULE,
- +};
- +
- +/**
- + * init_debugfs - A function to initialize the debugfs interface files
- + *
- + * This function creates entries in debugfs for "hwlat_detector", including
- + * files to read values from the detector, current samples, and the
- + * maximum sample that has been captured since the hardware latency
- + * dectector was started.
- + */
- +static int init_debugfs(void)
- +{
- + int ret = -ENOMEM;
- +
- + debug_dir = debugfs_create_dir(DRVNAME, NULL);
- + if (!debug_dir)
- + goto err_debug_dir;
- +
- + debug_sample = debugfs_create_file("sample", 0444,
- + debug_dir, NULL,
- + &sample_fops);
- + if (!debug_sample)
- + goto err_sample;
- +
- + debug_count = debugfs_create_file("count", 0444,
- + debug_dir, NULL,
- + &count_fops);
- + if (!debug_count)
- + goto err_count;
- +
- + debug_max = debugfs_create_file("max", 0444,
- + debug_dir, NULL,
- + &max_fops);
- + if (!debug_max)
- + goto err_max;
- +
- + debug_sample_window = debugfs_create_file("window", 0644,
- + debug_dir, NULL,
- + &window_fops);
- + if (!debug_sample_window)
- + goto err_window;
- +
- + debug_sample_width = debugfs_create_file("width", 0644,
- + debug_dir, NULL,
- + &width_fops);
- + if (!debug_sample_width)
- + goto err_width;
- +
- + debug_threshold = debugfs_create_file("threshold", 0644,
- + debug_dir, NULL,
- + &threshold_fops);
- + if (!debug_threshold)
- + goto err_threshold;
- +
- + debug_enable = debugfs_create_file("enable", 0644,
- + debug_dir, &enabled,
- + &enable_fops);
- + if (!debug_enable)
- + goto err_enable;
- +
- + else {
- + ret = 0;
- + goto out;
- + }
- +
- +err_enable:
- + debugfs_remove(debug_threshold);
- +err_threshold:
- + debugfs_remove(debug_sample_width);
- +err_width:
- + debugfs_remove(debug_sample_window);
- +err_window:
- + debugfs_remove(debug_max);
- +err_max:
- + debugfs_remove(debug_count);
- +err_count:
- + debugfs_remove(debug_sample);
- +err_sample:
- + debugfs_remove(debug_dir);
- +err_debug_dir:
- +out:
- + return ret;
- +}
- +
- +/**
- + * free_debugfs - A function to cleanup the debugfs file interface
- + */
- +static void free_debugfs(void)
- +{
- + /* could also use a debugfs_remove_recursive */
- + debugfs_remove(debug_enable);
- + debugfs_remove(debug_threshold);
- + debugfs_remove(debug_sample_width);
- + debugfs_remove(debug_sample_window);
- + debugfs_remove(debug_max);
- + debugfs_remove(debug_count);
- + debugfs_remove(debug_sample);
- + debugfs_remove(debug_dir);
- +}
- +
- +/**
- + * detector_init - Standard module initialization code
- + */
- +static int detector_init(void)
- +{
- + int ret = -ENOMEM;
- +
- + pr_info(BANNER "version %s\n", VERSION);
- +
- + ret = init_stats();
- + if (ret)
- + goto out;
- +
- + ret = init_debugfs();
- + if (ret)
- + goto err_stats;
- +
- + if (enabled)
- + ret = start_kthread();
- +
- + goto out;
- +
- +err_stats:
- + ring_buffer_free(ring_buffer);
- +out:
- + return ret;
- +
- +}
- +
- +/**
- + * detector_exit - Standard module cleanup code
- + */
- +static void detector_exit(void)
- +{
- + int err;
- +
- + if (enabled) {
- + enabled = 0;
- + err = stop_kthread();
- + if (err)
- + pr_err(BANNER "cannot stop kthread\n");
- + }
- +
- + free_debugfs();
- + ring_buffer_free(ring_buffer); /* free up the ring buffer */
- +
- +}
- +
- +module_init(detector_init);
- +module_exit(detector_exit);
- diff -Nur linux-4.4.28.orig/drivers/misc/Kconfig linux-4.4.28/drivers/misc/Kconfig
- --- linux-4.4.28.orig/drivers/misc/Kconfig 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/misc/Kconfig 2016-11-01 21:26:58.256308759 +0100
- @@ -54,6 +54,7 @@
- config ATMEL_TCLIB
- bool "Atmel AT32/AT91 Timer/Counter Library"
- depends on (AVR32 || ARCH_AT91)
- + default y if PREEMPT_RT_FULL
- help
- Select this if you want a library to allocate the Timer/Counter
- blocks found on many Atmel processors. This facilitates using
- @@ -69,8 +70,7 @@
- are combined to make a single 32-bit timer.
-
- When GENERIC_CLOCKEVENTS is defined, the third timer channel
- - may be used as a clock event device supporting oneshot mode
- - (delays of up to two seconds) based on the 32 KiHz clock.
- + may be used as a clock event device supporting oneshot mode.
-
- config ATMEL_TCB_CLKSRC_BLOCK
- int
- @@ -84,6 +84,15 @@
- TC can be used for other purposes, such as PWM generation and
- interval timing.
-
- +config ATMEL_TCB_CLKSRC_USE_SLOW_CLOCK
- + bool "TC Block use 32 KiHz clock"
- + depends on ATMEL_TCB_CLKSRC
- + default y if !PREEMPT_RT_FULL
- + help
- + Select this to use 32 KiHz base clock rate as TC block clock
- + source for clock events.
- +
- +
- config DUMMY_IRQ
- tristate "Dummy IRQ handler"
- default n
- @@ -113,6 +122,35 @@
- for information on the specific driver level and support statement
- for your IBM server.
-
- +config HWLAT_DETECTOR
- + tristate "Testing module to detect hardware-induced latencies"
- + depends on DEBUG_FS
- + depends on RING_BUFFER
- + default m
- + ---help---
- + A simple hardware latency detector. Use this module to detect
- + large latencies introduced by the behavior of the underlying
- + system firmware external to Linux. We do this using periodic
- + use of stop_machine to grab all available CPUs and measure
- + for unexplainable gaps in the CPU timestamp counter(s). By
- + default, the module is not enabled until the "enable" file
- + within the "hwlat_detector" debugfs directory is toggled.
- +
- + This module is often used to detect SMI (System Management
- + Interrupts) on x86 systems, though is not x86 specific. To
- + this end, we default to using a sample window of 1 second,
- + during which we will sample for 0.5 seconds. If an SMI or
- + similar event occurs during that time, it is recorded
- + into an 8K samples global ring buffer until retreived.
- +
- + WARNING: This software should never be enabled (it can be built
- + but should not be turned on after it is loaded) in a production
- + environment where high latencies are a concern since the
- + sampling mechanism actually introduces latencies for
- + regular tasks while the CPU(s) are being held.
- +
- + If unsure, say N
- +
- config PHANTOM
- tristate "Sensable PHANToM (PCI)"
- depends on PCI
- diff -Nur linux-4.4.28.orig/drivers/misc/Makefile linux-4.4.28/drivers/misc/Makefile
- --- linux-4.4.28.orig/drivers/misc/Makefile 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/misc/Makefile 2016-11-01 21:26:58.256308759 +0100
- @@ -39,6 +39,7 @@
- obj-$(CONFIG_HMC6352) += hmc6352.o
- obj-y += eeprom/
- obj-y += cb710/
- +obj-$(CONFIG_HWLAT_DETECTOR) += hwlat_detector.o
- obj-$(CONFIG_SPEAR13XX_PCIE_GADGET) += spear13xx_pcie_gadget.o
- obj-$(CONFIG_VMWARE_BALLOON) += vmw_balloon.o
- obj-$(CONFIG_ARM_CHARLCD) += arm-charlcd.o
- diff -Nur linux-4.4.28.orig/drivers/mmc/host/mmci.c linux-4.4.28/drivers/mmc/host/mmci.c
- --- linux-4.4.28.orig/drivers/mmc/host/mmci.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/mmc/host/mmci.c 2016-11-01 21:26:58.268309533 +0100
- @@ -1155,15 +1155,12 @@
- struct sg_mapping_iter *sg_miter = &host->sg_miter;
- struct variant_data *variant = host->variant;
- void __iomem *base = host->base;
- - unsigned long flags;
- u32 status;
-
- status = readl(base + MMCISTATUS);
-
- dev_dbg(mmc_dev(host->mmc), "irq1 (pio) %08x\n", status);
-
- - local_irq_save(flags);
- -
- do {
- unsigned int remain, len;
- char *buffer;
- @@ -1203,8 +1200,6 @@
-
- sg_miter_stop(sg_miter);
-
- - local_irq_restore(flags);
- -
- /*
- * If we have less than the fifo 'half-full' threshold to transfer,
- * trigger a PIO interrupt as soon as any data is available.
- diff -Nur linux-4.4.28.orig/drivers/net/ethernet/3com/3c59x.c linux-4.4.28/drivers/net/ethernet/3com/3c59x.c
- --- linux-4.4.28.orig/drivers/net/ethernet/3com/3c59x.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/net/ethernet/3com/3c59x.c 2016-11-01 21:26:58.300311601 +0100
- @@ -842,9 +842,9 @@
- {
- struct vortex_private *vp = netdev_priv(dev);
- unsigned long flags;
- - local_irq_save(flags);
- + local_irq_save_nort(flags);
- (vp->full_bus_master_rx ? boomerang_interrupt:vortex_interrupt)(dev->irq,dev);
- - local_irq_restore(flags);
- + local_irq_restore_nort(flags);
- }
- #endif
-
- @@ -1916,12 +1916,12 @@
- * Block interrupts because vortex_interrupt does a bare spin_lock()
- */
- unsigned long flags;
- - local_irq_save(flags);
- + local_irq_save_nort(flags);
- if (vp->full_bus_master_tx)
- boomerang_interrupt(dev->irq, dev);
- else
- vortex_interrupt(dev->irq, dev);
- - local_irq_restore(flags);
- + local_irq_restore_nort(flags);
- }
- }
-
- diff -Nur linux-4.4.28.orig/drivers/net/ethernet/atheros/atl1c/atl1c_main.c linux-4.4.28/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
- --- linux-4.4.28.orig/drivers/net/ethernet/atheros/atl1c/atl1c_main.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/net/ethernet/atheros/atl1c/atl1c_main.c 2016-11-01 21:26:58.324313148 +0100
- @@ -2221,11 +2221,7 @@
- }
-
- tpd_req = atl1c_cal_tpd_req(skb);
- - if (!spin_trylock_irqsave(&adapter->tx_lock, flags)) {
- - if (netif_msg_pktdata(adapter))
- - dev_info(&adapter->pdev->dev, "tx locked\n");
- - return NETDEV_TX_LOCKED;
- - }
- + spin_lock_irqsave(&adapter->tx_lock, flags);
-
- if (atl1c_tpd_avail(adapter, type) < tpd_req) {
- /* no enough descriptor, just stop queue */
- diff -Nur linux-4.4.28.orig/drivers/net/ethernet/atheros/atl1e/atl1e_main.c linux-4.4.28/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
- --- linux-4.4.28.orig/drivers/net/ethernet/atheros/atl1e/atl1e_main.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/net/ethernet/atheros/atl1e/atl1e_main.c 2016-11-01 21:26:58.336313921 +0100
- @@ -1880,8 +1880,7 @@
- return NETDEV_TX_OK;
- }
- tpd_req = atl1e_cal_tdp_req(skb);
- - if (!spin_trylock_irqsave(&adapter->tx_lock, flags))
- - return NETDEV_TX_LOCKED;
- + spin_lock_irqsave(&adapter->tx_lock, flags);
-
- if (atl1e_tpd_avail(adapter) < tpd_req) {
- /* no enough descriptor, just stop queue */
- diff -Nur linux-4.4.28.orig/drivers/net/ethernet/chelsio/cxgb/sge.c linux-4.4.28/drivers/net/ethernet/chelsio/cxgb/sge.c
- --- linux-4.4.28.orig/drivers/net/ethernet/chelsio/cxgb/sge.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/net/ethernet/chelsio/cxgb/sge.c 2016-11-01 21:26:58.348314695 +0100
- @@ -1664,8 +1664,7 @@
- struct cmdQ *q = &sge->cmdQ[qid];
- unsigned int credits, pidx, genbit, count, use_sched_skb = 0;
-
- - if (!spin_trylock(&q->lock))
- - return NETDEV_TX_LOCKED;
- + spin_lock(&q->lock);
-
- reclaim_completed_tx(sge, q);
-
- diff -Nur linux-4.4.28.orig/drivers/net/ethernet/neterion/s2io.c linux-4.4.28/drivers/net/ethernet/neterion/s2io.c
- --- linux-4.4.28.orig/drivers/net/ethernet/neterion/s2io.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/net/ethernet/neterion/s2io.c 2016-11-01 21:26:58.372316242 +0100
- @@ -4084,12 +4084,7 @@
- [skb->priority & (MAX_TX_FIFOS - 1)];
- fifo = &mac_control->fifos[queue];
-
- - if (do_spin_lock)
- - spin_lock_irqsave(&fifo->tx_lock, flags);
- - else {
- - if (unlikely(!spin_trylock_irqsave(&fifo->tx_lock, flags)))
- - return NETDEV_TX_LOCKED;
- - }
- + spin_lock_irqsave(&fifo->tx_lock, flags);
-
- if (sp->config.multiq) {
- if (__netif_subqueue_stopped(dev, fifo->fifo_no)) {
- diff -Nur linux-4.4.28.orig/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c linux-4.4.28/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
- --- linux-4.4.28.orig/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c 2016-11-01 21:26:58.396317789 +0100
- @@ -2137,10 +2137,8 @@
- struct pch_gbe_tx_ring *tx_ring = adapter->tx_ring;
- unsigned long flags;
-
- - if (!spin_trylock_irqsave(&tx_ring->tx_lock, flags)) {
- - /* Collision - tell upper layer to requeue */
- - return NETDEV_TX_LOCKED;
- - }
- + spin_lock_irqsave(&tx_ring->tx_lock, flags);
- +
- if (unlikely(!PCH_GBE_DESC_UNUSED(tx_ring))) {
- netif_stop_queue(netdev);
- spin_unlock_irqrestore(&tx_ring->tx_lock, flags);
- diff -Nur linux-4.4.28.orig/drivers/net/ethernet/realtek/8139too.c linux-4.4.28/drivers/net/ethernet/realtek/8139too.c
- --- linux-4.4.28.orig/drivers/net/ethernet/realtek/8139too.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/net/ethernet/realtek/8139too.c 2016-11-01 21:26:58.416319072 +0100
- @@ -2229,7 +2229,7 @@
- struct rtl8139_private *tp = netdev_priv(dev);
- const int irq = tp->pci_dev->irq;
-
- - disable_irq(irq);
- + disable_irq_nosync(irq);
- rtl8139_interrupt(irq, dev);
- enable_irq(irq);
- }
- diff -Nur linux-4.4.28.orig/drivers/net/ethernet/tehuti/tehuti.c linux-4.4.28/drivers/net/ethernet/tehuti/tehuti.c
- --- linux-4.4.28.orig/drivers/net/ethernet/tehuti/tehuti.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/net/ethernet/tehuti/tehuti.c 2016-11-01 21:26:58.436320363 +0100
- @@ -1629,13 +1629,8 @@
- unsigned long flags;
-
- ENTER;
- - local_irq_save(flags);
- - if (!spin_trylock(&priv->tx_lock)) {
- - local_irq_restore(flags);
- - DBG("%s[%s]: TX locked, returning NETDEV_TX_LOCKED\n",
- - BDX_DRV_NAME, ndev->name);
- - return NETDEV_TX_LOCKED;
- - }
- +
- + spin_lock_irqsave(&priv->tx_lock, flags);
-
- /* build tx descriptor */
- BDX_ASSERT(f->m.wptr >= f->m.memsz); /* started with valid wptr */
- diff -Nur linux-4.4.28.orig/drivers/net/rionet.c linux-4.4.28/drivers/net/rionet.c
- --- linux-4.4.28.orig/drivers/net/rionet.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/net/rionet.c 2016-11-01 21:26:58.448321136 +0100
- @@ -174,11 +174,7 @@
- unsigned long flags;
- int add_num = 1;
-
- - local_irq_save(flags);
- - if (!spin_trylock(&rnet->tx_lock)) {
- - local_irq_restore(flags);
- - return NETDEV_TX_LOCKED;
- - }
- + spin_lock_irqsave(&rnet->tx_lock, flags);
-
- if (is_multicast_ether_addr(eth->h_dest))
- add_num = nets[rnet->mport->id].nact;
- diff -Nur linux-4.4.28.orig/drivers/net/wireless/orinoco/orinoco_usb.c linux-4.4.28/drivers/net/wireless/orinoco/orinoco_usb.c
- --- linux-4.4.28.orig/drivers/net/wireless/orinoco/orinoco_usb.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/net/wireless/orinoco/orinoco_usb.c 2016-11-01 21:26:58.460321910 +0100
- @@ -697,7 +697,7 @@
- while (!ctx->done.done && msecs--)
- udelay(1000);
- } else {
- - wait_event_interruptible(ctx->done.wait,
- + swait_event_interruptible(ctx->done.wait,
- ctx->done.done);
- }
- break;
- diff -Nur linux-4.4.28.orig/drivers/pci/access.c linux-4.4.28/drivers/pci/access.c
- --- linux-4.4.28.orig/drivers/pci/access.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/pci/access.c 2016-11-01 21:26:58.472322683 +0100
- @@ -561,7 +561,7 @@
- WARN_ON(!dev->block_cfg_access);
-
- dev->block_cfg_access = 0;
- - wake_up_all(&pci_cfg_wait);
- + wake_up_all_locked(&pci_cfg_wait);
- raw_spin_unlock_irqrestore(&pci_lock, flags);
- }
- EXPORT_SYMBOL_GPL(pci_cfg_access_unlock);
- diff -Nur linux-4.4.28.orig/drivers/scsi/fcoe/fcoe.c linux-4.4.28/drivers/scsi/fcoe/fcoe.c
- --- linux-4.4.28.orig/drivers/scsi/fcoe/fcoe.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/scsi/fcoe/fcoe.c 2016-11-01 21:26:58.496324231 +0100
- @@ -1286,7 +1286,7 @@
- struct sk_buff *skb;
- #ifdef CONFIG_SMP
- struct fcoe_percpu_s *p0;
- - unsigned targ_cpu = get_cpu();
- + unsigned targ_cpu = get_cpu_light();
- #endif /* CONFIG_SMP */
-
- FCOE_DBG("Destroying receive thread for CPU %d\n", cpu);
- @@ -1342,7 +1342,7 @@
- kfree_skb(skb);
- spin_unlock_bh(&p->fcoe_rx_list.lock);
- }
- - put_cpu();
- + put_cpu_light();
- #else
- /*
- * This a non-SMP scenario where the singular Rx thread is
- @@ -1566,11 +1566,11 @@
- static int fcoe_alloc_paged_crc_eof(struct sk_buff *skb, int tlen)
- {
- struct fcoe_percpu_s *fps;
- - int rc;
- + int rc, cpu = get_cpu_light();
-
- - fps = &get_cpu_var(fcoe_percpu);
- + fps = &per_cpu(fcoe_percpu, cpu);
- rc = fcoe_get_paged_crc_eof(skb, tlen, fps);
- - put_cpu_var(fcoe_percpu);
- + put_cpu_light();
-
- return rc;
- }
- @@ -1766,11 +1766,11 @@
- return 0;
- }
-
- - stats = per_cpu_ptr(lport->stats, get_cpu());
- + stats = per_cpu_ptr(lport->stats, get_cpu_light());
- stats->InvalidCRCCount++;
- if (stats->InvalidCRCCount < 5)
- printk(KERN_WARNING "fcoe: dropping frame with CRC error\n");
- - put_cpu();
- + put_cpu_light();
- return -EINVAL;
- }
-
- @@ -1814,7 +1814,7 @@
- */
- hp = (struct fcoe_hdr *) skb_network_header(skb);
-
- - stats = per_cpu_ptr(lport->stats, get_cpu());
- + stats = per_cpu_ptr(lport->stats, get_cpu_light());
- if (unlikely(FC_FCOE_DECAPS_VER(hp) != FC_FCOE_VER)) {
- if (stats->ErrorFrames < 5)
- printk(KERN_WARNING "fcoe: FCoE version "
- @@ -1846,13 +1846,13 @@
- goto drop;
-
- if (!fcoe_filter_frames(lport, fp)) {
- - put_cpu();
- + put_cpu_light();
- fc_exch_recv(lport, fp);
- return;
- }
- drop:
- stats->ErrorFrames++;
- - put_cpu();
- + put_cpu_light();
- kfree_skb(skb);
- }
-
- diff -Nur linux-4.4.28.orig/drivers/scsi/fcoe/fcoe_ctlr.c linux-4.4.28/drivers/scsi/fcoe/fcoe_ctlr.c
- --- linux-4.4.28.orig/drivers/scsi/fcoe/fcoe_ctlr.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/scsi/fcoe/fcoe_ctlr.c 2016-11-01 21:26:58.516325525 +0100
- @@ -831,7 +831,7 @@
-
- INIT_LIST_HEAD(&del_list);
-
- - stats = per_cpu_ptr(fip->lp->stats, get_cpu());
- + stats = per_cpu_ptr(fip->lp->stats, get_cpu_light());
-
- list_for_each_entry_safe(fcf, next, &fip->fcfs, list) {
- deadline = fcf->time + fcf->fka_period + fcf->fka_period / 2;
- @@ -867,7 +867,7 @@
- sel_time = fcf->time;
- }
- }
- - put_cpu();
- + put_cpu_light();
-
- list_for_each_entry_safe(fcf, next, &del_list, list) {
- /* Removes fcf from current list */
- diff -Nur linux-4.4.28.orig/drivers/scsi/libfc/fc_exch.c linux-4.4.28/drivers/scsi/libfc/fc_exch.c
- --- linux-4.4.28.orig/drivers/scsi/libfc/fc_exch.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/scsi/libfc/fc_exch.c 2016-11-01 21:26:58.536326808 +0100
- @@ -814,10 +814,10 @@
- }
- memset(ep, 0, sizeof(*ep));
-
- - cpu = get_cpu();
- + cpu = get_cpu_light();
- pool = per_cpu_ptr(mp->pool, cpu);
- spin_lock_bh(&pool->lock);
- - put_cpu();
- + put_cpu_light();
-
- /* peek cache of free slot */
- if (pool->left != FC_XID_UNKNOWN) {
- diff -Nur linux-4.4.28.orig/drivers/scsi/libsas/sas_ata.c linux-4.4.28/drivers/scsi/libsas/sas_ata.c
- --- linux-4.4.28.orig/drivers/scsi/libsas/sas_ata.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/scsi/libsas/sas_ata.c 2016-11-01 21:26:58.548327581 +0100
- @@ -190,7 +190,7 @@
- /* TODO: audit callers to ensure they are ready for qc_issue to
- * unconditionally re-enable interrupts
- */
- - local_irq_save(flags);
- + local_irq_save_nort(flags);
- spin_unlock(ap->lock);
-
- /* If the device fell off, no sense in issuing commands */
- @@ -255,7 +255,7 @@
-
- out:
- spin_lock(ap->lock);
- - local_irq_restore(flags);
- + local_irq_restore_nort(flags);
- return ret;
- }
-
- diff -Nur linux-4.4.28.orig/drivers/scsi/qla2xxx/qla_inline.h linux-4.4.28/drivers/scsi/qla2xxx/qla_inline.h
- --- linux-4.4.28.orig/drivers/scsi/qla2xxx/qla_inline.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/scsi/qla2xxx/qla_inline.h 2016-11-01 21:26:58.560328355 +0100
- @@ -59,12 +59,12 @@
- {
- unsigned long flags;
- struct qla_hw_data *ha = rsp->hw;
- - local_irq_save(flags);
- + local_irq_save_nort(flags);
- if (IS_P3P_TYPE(ha))
- qla82xx_poll(0, rsp);
- else
- ha->isp_ops->intr_handler(0, rsp);
- - local_irq_restore(flags);
- + local_irq_restore_nort(flags);
- }
-
- static inline uint8_t *
- diff -Nur linux-4.4.28.orig/drivers/thermal/x86_pkg_temp_thermal.c linux-4.4.28/drivers/thermal/x86_pkg_temp_thermal.c
- --- linux-4.4.28.orig/drivers/thermal/x86_pkg_temp_thermal.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/thermal/x86_pkg_temp_thermal.c 2016-11-01 21:26:58.572329128 +0100
- @@ -29,6 +29,7 @@
- #include <linux/pm.h>
- #include <linux/thermal.h>
- #include <linux/debugfs.h>
- +#include <linux/swork.h>
- #include <asm/cpu_device_id.h>
- #include <asm/mce.h>
-
- @@ -352,7 +353,7 @@
- }
- }
-
- -static int pkg_temp_thermal_platform_thermal_notify(__u64 msr_val)
- +static void platform_thermal_notify_work(struct swork_event *event)
- {
- unsigned long flags;
- int cpu = smp_processor_id();
- @@ -369,7 +370,7 @@
- pkg_work_scheduled[phy_id]) {
- disable_pkg_thres_interrupt();
- spin_unlock_irqrestore(&pkg_work_lock, flags);
- - return -EINVAL;
- + return;
- }
- pkg_work_scheduled[phy_id] = 1;
- spin_unlock_irqrestore(&pkg_work_lock, flags);
- @@ -378,9 +379,48 @@
- schedule_delayed_work_on(cpu,
- &per_cpu(pkg_temp_thermal_threshold_work, cpu),
- msecs_to_jiffies(notify_delay_ms));
- +}
- +
- +#ifdef CONFIG_PREEMPT_RT_FULL
- +static struct swork_event notify_work;
- +
- +static int thermal_notify_work_init(void)
- +{
- + int err;
- +
- + err = swork_get();
- + if (err)
- + return err;
- +
- + INIT_SWORK(¬ify_work, platform_thermal_notify_work);
- return 0;
- }
-
- +static void thermal_notify_work_cleanup(void)
- +{
- + swork_put();
- +}
- +
- +static int pkg_temp_thermal_platform_thermal_notify(__u64 msr_val)
- +{
- + swork_queue(¬ify_work);
- + return 0;
- +}
- +
- +#else /* !CONFIG_PREEMPT_RT_FULL */
- +
- +static int thermal_notify_work_init(void) { return 0; }
- +
- +static void thermal_notify_work_cleanup(void) { }
- +
- +static int pkg_temp_thermal_platform_thermal_notify(__u64 msr_val)
- +{
- + platform_thermal_notify_work(NULL);
- +
- + return 0;
- +}
- +#endif /* CONFIG_PREEMPT_RT_FULL */
- +
- static int find_siblings_cpu(int cpu)
- {
- int i;
- @@ -584,6 +624,9 @@
- if (!x86_match_cpu(pkg_temp_thermal_ids))
- return -ENODEV;
-
- + if (!thermal_notify_work_init())
- + return -ENODEV;
- +
- spin_lock_init(&pkg_work_lock);
- platform_thermal_package_notify =
- pkg_temp_thermal_platform_thermal_notify;
- @@ -608,7 +651,7 @@
- kfree(pkg_work_scheduled);
- platform_thermal_package_notify = NULL;
- platform_thermal_package_rate_control = NULL;
- -
- + thermal_notify_work_cleanup();
- return -ENODEV;
- }
-
- @@ -633,6 +676,7 @@
- mutex_unlock(&phy_dev_list_mutex);
- platform_thermal_package_notify = NULL;
- platform_thermal_package_rate_control = NULL;
- + thermal_notify_work_cleanup();
- for_each_online_cpu(i)
- cancel_delayed_work_sync(
- &per_cpu(pkg_temp_thermal_threshold_work, i));
- diff -Nur linux-4.4.28.orig/drivers/tty/serial/8250/8250_core.c linux-4.4.28/drivers/tty/serial/8250/8250_core.c
- --- linux-4.4.28.orig/drivers/tty/serial/8250/8250_core.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/tty/serial/8250/8250_core.c 2016-11-01 21:26:58.576329393 +0100
- @@ -58,7 +58,16 @@
-
- static unsigned int skip_txen_test; /* force skip of txen test at init time */
-
- -#define PASS_LIMIT 512
- +/*
- + * On -rt we can have a more delays, and legitimately
- + * so - so don't drop work spuriously and spam the
- + * syslog:
- + */
- +#ifdef CONFIG_PREEMPT_RT_FULL
- +# define PASS_LIMIT 1000000
- +#else
- +# define PASS_LIMIT 512
- +#endif
-
- #include <asm/serial.h>
- /*
- diff -Nur linux-4.4.28.orig/drivers/tty/serial/8250/8250_port.c linux-4.4.28/drivers/tty/serial/8250/8250_port.c
- --- linux-4.4.28.orig/drivers/tty/serial/8250/8250_port.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/tty/serial/8250/8250_port.c 2016-11-01 21:26:58.596330676 +0100
- @@ -35,6 +35,7 @@
- #include <linux/nmi.h>
- #include <linux/mutex.h>
- #include <linux/slab.h>
- +#include <linux/kdb.h>
- #include <linux/uaccess.h>
- #include <linux/pm_runtime.h>
-
- @@ -2843,9 +2844,9 @@
-
- serial8250_rpm_get(up);
-
- - if (port->sysrq)
- + if (port->sysrq || oops_in_progress)
- locked = 0;
- - else if (oops_in_progress)
- + else if (in_kdb_printk())
- locked = spin_trylock_irqsave(&port->lock, flags);
- else
- spin_lock_irqsave(&port->lock, flags);
- diff -Nur linux-4.4.28.orig/drivers/tty/serial/amba-pl011.c linux-4.4.28/drivers/tty/serial/amba-pl011.c
- --- linux-4.4.28.orig/drivers/tty/serial/amba-pl011.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/tty/serial/amba-pl011.c 2016-11-01 21:26:58.608331449 +0100
- @@ -2067,13 +2067,19 @@
-
- clk_enable(uap->clk);
-
- - local_irq_save(flags);
- + /*
- + * local_irq_save(flags);
- + *
- + * This local_irq_save() is nonsense. If we come in via sysrq
- + * handling then interrupts are already disabled. Aside of
- + * that the port.sysrq check is racy on SMP regardless.
- + */
- if (uap->port.sysrq)
- locked = 0;
- else if (oops_in_progress)
- - locked = spin_trylock(&uap->port.lock);
- + locked = spin_trylock_irqsave(&uap->port.lock, flags);
- else
- - spin_lock(&uap->port.lock);
- + spin_lock_irqsave(&uap->port.lock, flags);
-
- /*
- * First save the CR then disable the interrupts
- @@ -2098,8 +2104,7 @@
- writew(old_cr, uap->port.membase + UART011_CR);
-
- if (locked)
- - spin_unlock(&uap->port.lock);
- - local_irq_restore(flags);
- + spin_unlock_irqrestore(&uap->port.lock, flags);
-
- clk_disable(uap->clk);
- }
- diff -Nur linux-4.4.28.orig/drivers/tty/serial/omap-serial.c linux-4.4.28/drivers/tty/serial/omap-serial.c
- --- linux-4.4.28.orig/drivers/tty/serial/omap-serial.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/tty/serial/omap-serial.c 2016-11-01 21:26:58.620332223 +0100
- @@ -1257,13 +1257,10 @@
-
- pm_runtime_get_sync(up->dev);
-
- - local_irq_save(flags);
- - if (up->port.sysrq)
- - locked = 0;
- - else if (oops_in_progress)
- - locked = spin_trylock(&up->port.lock);
- + if (up->port.sysrq || oops_in_progress)
- + locked = spin_trylock_irqsave(&up->port.lock, flags);
- else
- - spin_lock(&up->port.lock);
- + spin_lock_irqsave(&up->port.lock, flags);
-
- /*
- * First save the IER then disable the interrupts
- @@ -1292,8 +1289,7 @@
- pm_runtime_mark_last_busy(up->dev);
- pm_runtime_put_autosuspend(up->dev);
- if (locked)
- - spin_unlock(&up->port.lock);
- - local_irq_restore(flags);
- + spin_unlock_irqrestore(&up->port.lock, flags);
- }
-
- static int __init
- diff -Nur linux-4.4.28.orig/drivers/tty/serial/sc16is7xx.c linux-4.4.28/drivers/tty/serial/sc16is7xx.c
- --- linux-4.4.28.orig/drivers/tty/serial/sc16is7xx.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/tty/serial/sc16is7xx.c 2016-11-01 21:26:58.628332740 +0100
- @@ -1230,7 +1230,7 @@
-
- /* Setup interrupt */
- ret = devm_request_irq(dev, irq, sc16is7xx_irq,
- - IRQF_ONESHOT | flags, dev_name(dev), s);
- + flags, dev_name(dev), s);
- if (!ret)
- return 0;
-
- diff -Nur linux-4.4.28.orig/drivers/usb/core/hcd.c linux-4.4.28/drivers/usb/core/hcd.c
- --- linux-4.4.28.orig/drivers/usb/core/hcd.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/usb/core/hcd.c 2016-11-01 21:26:58.648334034 +0100
- @@ -1735,9 +1735,9 @@
- * and no one may trigger the above deadlock situation when
- * running complete() in tasklet.
- */
- - local_irq_save(flags);
- + local_irq_save_nort(flags);
- urb->complete(urb);
- - local_irq_restore(flags);
- + local_irq_restore_nort(flags);
-
- usb_anchor_resume_wakeups(anchor);
- atomic_dec(&urb->use_count);
- diff -Nur linux-4.4.28.orig/drivers/usb/gadget/function/f_fs.c linux-4.4.28/drivers/usb/gadget/function/f_fs.c
- --- linux-4.4.28.orig/drivers/usb/gadget/function/f_fs.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/usb/gadget/function/f_fs.c 2016-11-01 21:26:58.680336091 +0100
- @@ -1404,7 +1404,7 @@
- pr_info("%s(): freeing\n", __func__);
- ffs_data_clear(ffs);
- BUG_ON(waitqueue_active(&ffs->ev.waitq) ||
- - waitqueue_active(&ffs->ep0req_completion.wait));
- + swait_active(&ffs->ep0req_completion.wait));
- kfree(ffs->dev_name);
- kfree(ffs);
- }
- diff -Nur linux-4.4.28.orig/drivers/usb/gadget/legacy/inode.c linux-4.4.28/drivers/usb/gadget/legacy/inode.c
- --- linux-4.4.28.orig/drivers/usb/gadget/legacy/inode.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/usb/gadget/legacy/inode.c 2016-11-01 21:26:58.692336864 +0100
- @@ -345,7 +345,7 @@
- spin_unlock_irq (&epdata->dev->lock);
-
- if (likely (value == 0)) {
- - value = wait_event_interruptible (done.wait, done.done);
- + value = swait_event_interruptible (done.wait, done.done);
- if (value != 0) {
- spin_lock_irq (&epdata->dev->lock);
- if (likely (epdata->ep != NULL)) {
- @@ -354,7 +354,7 @@
- usb_ep_dequeue (epdata->ep, epdata->req);
- spin_unlock_irq (&epdata->dev->lock);
-
- - wait_event (done.wait, done.done);
- + swait_event (done.wait, done.done);
- if (epdata->status == -ECONNRESET)
- epdata->status = -EINTR;
- } else {
- diff -Nur linux-4.4.28.orig/drivers/usb/gadget/udc/atmel_usba_udc.c linux-4.4.28/drivers/usb/gadget/udc/atmel_usba_udc.c
- --- linux-4.4.28.orig/drivers/usb/gadget/udc/atmel_usba_udc.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/usb/gadget/udc/atmel_usba_udc.c 2016-11-01 21:26:58.704337638 +0100
- @@ -17,7 +17,9 @@
- #include <linux/device.h>
- #include <linux/dma-mapping.h>
- #include <linux/list.h>
- +#include <linux/mfd/syscon.h>
- #include <linux/platform_device.h>
- +#include <linux/regmap.h>
- #include <linux/usb/ch9.h>
- #include <linux/usb/gadget.h>
- #include <linux/usb/atmel_usba_udc.h>
- @@ -1888,20 +1890,15 @@
- #ifdef CONFIG_OF
- static void at91sam9rl_toggle_bias(struct usba_udc *udc, int is_on)
- {
- - unsigned int uckr = at91_pmc_read(AT91_CKGR_UCKR);
- -
- - if (is_on)
- - at91_pmc_write(AT91_CKGR_UCKR, uckr | AT91_PMC_BIASEN);
- - else
- - at91_pmc_write(AT91_CKGR_UCKR, uckr & ~(AT91_PMC_BIASEN));
- + regmap_update_bits(udc->pmc, AT91_CKGR_UCKR, AT91_PMC_BIASEN,
- + is_on ? AT91_PMC_BIASEN : 0);
- }
-
- static void at91sam9g45_pulse_bias(struct usba_udc *udc)
- {
- - unsigned int uckr = at91_pmc_read(AT91_CKGR_UCKR);
- -
- - at91_pmc_write(AT91_CKGR_UCKR, uckr & ~(AT91_PMC_BIASEN));
- - at91_pmc_write(AT91_CKGR_UCKR, uckr | AT91_PMC_BIASEN);
- + regmap_update_bits(udc->pmc, AT91_CKGR_UCKR, AT91_PMC_BIASEN, 0);
- + regmap_update_bits(udc->pmc, AT91_CKGR_UCKR, AT91_PMC_BIASEN,
- + AT91_PMC_BIASEN);
- }
-
- static const struct usba_udc_errata at91sam9rl_errata = {
- @@ -1938,6 +1935,9 @@
- return ERR_PTR(-EINVAL);
-
- udc->errata = match->data;
- + udc->pmc = syscon_regmap_lookup_by_compatible("atmel,at91sam9g45-pmc");
- + if (udc->errata && IS_ERR(udc->pmc))
- + return ERR_CAST(udc->pmc);
-
- udc->num_ep = 0;
-
- diff -Nur linux-4.4.28.orig/drivers/usb/gadget/udc/atmel_usba_udc.h linux-4.4.28/drivers/usb/gadget/udc/atmel_usba_udc.h
- --- linux-4.4.28.orig/drivers/usb/gadget/udc/atmel_usba_udc.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/drivers/usb/gadget/udc/atmel_usba_udc.h 2016-11-01 21:26:58.704337638 +0100
- @@ -354,6 +354,8 @@
- struct dentry *debugfs_root;
- struct dentry *debugfs_regs;
- #endif
- +
- + struct regmap *pmc;
- };
-
- static inline struct usba_ep *to_usba_ep(struct usb_ep *ep)
- diff -Nur linux-4.4.28.orig/fs/aio.c linux-4.4.28/fs/aio.c
- --- linux-4.4.28.orig/fs/aio.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/fs/aio.c 2016-11-01 21:26:58.716338411 +0100
- @@ -40,6 +40,7 @@
- #include <linux/ramfs.h>
- #include <linux/percpu-refcount.h>
- #include <linux/mount.h>
- +#include <linux/swork.h>
-
- #include <asm/kmap_types.h>
- #include <asm/uaccess.h>
- @@ -115,7 +116,7 @@
- struct page **ring_pages;
- long nr_pages;
-
- - struct work_struct free_work;
- + struct swork_event free_work;
-
- /*
- * signals when all in-flight requests are done
- @@ -258,6 +259,7 @@
- .mount = aio_mount,
- .kill_sb = kill_anon_super,
- };
- + BUG_ON(swork_get());
- aio_mnt = kern_mount(&aio_fs);
- if (IS_ERR(aio_mnt))
- panic("Failed to create aio fs mount.");
- @@ -573,9 +575,9 @@
- return cancel(&kiocb->common);
- }
-
- -static void free_ioctx(struct work_struct *work)
- +static void free_ioctx(struct swork_event *sev)
- {
- - struct kioctx *ctx = container_of(work, struct kioctx, free_work);
- + struct kioctx *ctx = container_of(sev, struct kioctx, free_work);
-
- pr_debug("freeing %p\n", ctx);
-
- @@ -594,8 +596,8 @@
- if (ctx->rq_wait && atomic_dec_and_test(&ctx->rq_wait->count))
- complete(&ctx->rq_wait->comp);
-
- - INIT_WORK(&ctx->free_work, free_ioctx);
- - schedule_work(&ctx->free_work);
- + INIT_SWORK(&ctx->free_work, free_ioctx);
- + swork_queue(&ctx->free_work);
- }
-
- /*
- @@ -603,9 +605,9 @@
- * and ctx->users has dropped to 0, so we know no more kiocbs can be submitted -
- * now it's safe to cancel any that need to be.
- */
- -static void free_ioctx_users(struct percpu_ref *ref)
- +static void free_ioctx_users_work(struct swork_event *sev)
- {
- - struct kioctx *ctx = container_of(ref, struct kioctx, users);
- + struct kioctx *ctx = container_of(sev, struct kioctx, free_work);
- struct aio_kiocb *req;
-
- spin_lock_irq(&ctx->ctx_lock);
- @@ -624,6 +626,14 @@
- percpu_ref_put(&ctx->reqs);
- }
-
- +static void free_ioctx_users(struct percpu_ref *ref)
- +{
- + struct kioctx *ctx = container_of(ref, struct kioctx, users);
- +
- + INIT_SWORK(&ctx->free_work, free_ioctx_users_work);
- + swork_queue(&ctx->free_work);
- +}
- +
- static int ioctx_add_table(struct kioctx *ctx, struct mm_struct *mm)
- {
- unsigned i, new_nr;
- diff -Nur linux-4.4.28.orig/fs/autofs4/autofs_i.h linux-4.4.28/fs/autofs4/autofs_i.h
- --- linux-4.4.28.orig/fs/autofs4/autofs_i.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/fs/autofs4/autofs_i.h 2016-11-01 21:26:58.716338411 +0100
- @@ -34,6 +34,7 @@
- #include <linux/sched.h>
- #include <linux/mount.h>
- #include <linux/namei.h>
- +#include <linux/delay.h>
- #include <asm/current.h>
- #include <asm/uaccess.h>
-
- diff -Nur linux-4.4.28.orig/fs/autofs4/expire.c linux-4.4.28/fs/autofs4/expire.c
- --- linux-4.4.28.orig/fs/autofs4/expire.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/fs/autofs4/expire.c 2016-11-01 21:26:58.716338411 +0100
- @@ -150,7 +150,7 @@
- parent = p->d_parent;
- if (!spin_trylock(&parent->d_lock)) {
- spin_unlock(&p->d_lock);
- - cpu_relax();
- + cpu_chill();
- goto relock;
- }
- spin_unlock(&p->d_lock);
- diff -Nur linux-4.4.28.orig/fs/buffer.c linux-4.4.28/fs/buffer.c
- --- linux-4.4.28.orig/fs/buffer.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/fs/buffer.c 2016-11-01 21:26:58.716338411 +0100
- @@ -305,8 +305,7 @@
- * decide that the page is now completely done.
- */
- first = page_buffers(page);
- - local_irq_save(flags);
- - bit_spin_lock(BH_Uptodate_Lock, &first->b_state);
- + flags = bh_uptodate_lock_irqsave(first);
- clear_buffer_async_read(bh);
- unlock_buffer(bh);
- tmp = bh;
- @@ -319,8 +318,7 @@
- }
- tmp = tmp->b_this_page;
- } while (tmp != bh);
- - bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
- - local_irq_restore(flags);
- + bh_uptodate_unlock_irqrestore(first, flags);
-
- /*
- * If none of the buffers had errors and they are all
- @@ -332,9 +330,7 @@
- return;
-
- still_busy:
- - bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
- - local_irq_restore(flags);
- - return;
- + bh_uptodate_unlock_irqrestore(first, flags);
- }
-
- /*
- @@ -362,8 +358,7 @@
- }
-
- first = page_buffers(page);
- - local_irq_save(flags);
- - bit_spin_lock(BH_Uptodate_Lock, &first->b_state);
- + flags = bh_uptodate_lock_irqsave(first);
-
- clear_buffer_async_write(bh);
- unlock_buffer(bh);
- @@ -375,15 +370,12 @@
- }
- tmp = tmp->b_this_page;
- }
- - bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
- - local_irq_restore(flags);
- + bh_uptodate_unlock_irqrestore(first, flags);
- end_page_writeback(page);
- return;
-
- still_busy:
- - bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
- - local_irq_restore(flags);
- - return;
- + bh_uptodate_unlock_irqrestore(first, flags);
- }
- EXPORT_SYMBOL(end_buffer_async_write);
-
- @@ -3325,6 +3317,7 @@
- struct buffer_head *ret = kmem_cache_zalloc(bh_cachep, gfp_flags);
- if (ret) {
- INIT_LIST_HEAD(&ret->b_assoc_buffers);
- + buffer_head_init_locks(ret);
- preempt_disable();
- __this_cpu_inc(bh_accounting.nr);
- recalc_bh_state();
- diff -Nur linux-4.4.28.orig/fs/dcache.c linux-4.4.28/fs/dcache.c
- --- linux-4.4.28.orig/fs/dcache.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/fs/dcache.c 2016-11-01 21:26:58.720338675 +0100
- @@ -19,6 +19,7 @@
- #include <linux/mm.h>
- #include <linux/fs.h>
- #include <linux/fsnotify.h>
- +#include <linux/delay.h>
- #include <linux/slab.h>
- #include <linux/init.h>
- #include <linux/hash.h>
- @@ -747,6 +748,8 @@
- */
- void dput(struct dentry *dentry)
- {
- + struct dentry *parent;
- +
- if (unlikely(!dentry))
- return;
-
- @@ -783,9 +786,18 @@
- return;
-
- kill_it:
- - dentry = dentry_kill(dentry);
- - if (dentry) {
- - cond_resched();
- + parent = dentry_kill(dentry);
- + if (parent) {
- + int r;
- +
- + if (parent == dentry) {
- + /* the task with the highest priority won't schedule */
- + r = cond_resched();
- + if (!r)
- + cpu_chill();
- + } else {
- + dentry = parent;
- + }
- goto repeat;
- }
- }
- @@ -2394,7 +2406,7 @@
- if (dentry->d_lockref.count == 1) {
- if (!spin_trylock(&inode->i_lock)) {
- spin_unlock(&dentry->d_lock);
- - cpu_relax();
- + cpu_chill();
- goto again;
- }
- dentry->d_flags &= ~DCACHE_CANT_MOUNT;
- diff -Nur linux-4.4.28.orig/fs/eventpoll.c linux-4.4.28/fs/eventpoll.c
- --- linux-4.4.28.orig/fs/eventpoll.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/fs/eventpoll.c 2016-11-01 21:26:58.720338675 +0100
- @@ -505,12 +505,12 @@
- */
- static void ep_poll_safewake(wait_queue_head_t *wq)
- {
- - int this_cpu = get_cpu();
- + int this_cpu = get_cpu_light();
-
- ep_call_nested(&poll_safewake_ncalls, EP_MAX_NESTS,
- ep_poll_wakeup_proc, NULL, wq, (void *) (long) this_cpu);
-
- - put_cpu();
- + put_cpu_light();
- }
-
- static void ep_remove_wait_queue(struct eppoll_entry *pwq)
- diff -Nur linux-4.4.28.orig/fs/exec.c linux-4.4.28/fs/exec.c
- --- linux-4.4.28.orig/fs/exec.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/fs/exec.c 2016-11-01 21:26:58.720338675 +0100
- @@ -865,12 +865,14 @@
- }
- }
- task_lock(tsk);
- + preempt_disable_rt();
- active_mm = tsk->active_mm;
- tsk->mm = mm;
- tsk->active_mm = mm;
- activate_mm(active_mm, mm);
- tsk->mm->vmacache_seqnum = 0;
- vmacache_flush(tsk);
- + preempt_enable_rt();
- task_unlock(tsk);
- if (old_mm) {
- up_read(&old_mm->mmap_sem);
- diff -Nur linux-4.4.28.orig/fs/f2fs/f2fs.h linux-4.4.28/fs/f2fs/f2fs.h
- --- linux-4.4.28.orig/fs/f2fs/f2fs.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/fs/f2fs/f2fs.h 2016-11-01 21:26:58.720338675 +0100
- @@ -24,7 +24,6 @@
-
- #ifdef CONFIG_F2FS_CHECK_FS
- #define f2fs_bug_on(sbi, condition) BUG_ON(condition)
- -#define f2fs_down_write(x, y) down_write_nest_lock(x, y)
- #else
- #define f2fs_bug_on(sbi, condition) \
- do { \
- @@ -33,7 +32,6 @@
- set_sbi_flag(sbi, SBI_NEED_FSCK); \
- } \
- } while (0)
- -#define f2fs_down_write(x, y) down_write(x)
- #endif
-
- /*
- @@ -959,7 +957,7 @@
-
- static inline void f2fs_lock_all(struct f2fs_sb_info *sbi)
- {
- - f2fs_down_write(&sbi->cp_rwsem, &sbi->cp_mutex);
- + down_write(&sbi->cp_rwsem);
- }
-
- static inline void f2fs_unlock_all(struct f2fs_sb_info *sbi)
- diff -Nur linux-4.4.28.orig/fs/jbd2/checkpoint.c linux-4.4.28/fs/jbd2/checkpoint.c
- --- linux-4.4.28.orig/fs/jbd2/checkpoint.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/fs/jbd2/checkpoint.c 2016-11-01 21:26:58.720338675 +0100
- @@ -116,6 +116,8 @@
- nblocks = jbd2_space_needed(journal);
- while (jbd2_log_space_left(journal) < nblocks) {
- write_unlock(&journal->j_state_lock);
- + if (current->plug)
- + io_schedule();
- mutex_lock(&journal->j_checkpoint_mutex);
-
- /*
- diff -Nur linux-4.4.28.orig/fs/namespace.c linux-4.4.28/fs/namespace.c
- --- linux-4.4.28.orig/fs/namespace.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/fs/namespace.c 2016-11-01 21:26:58.724338928 +0100
- @@ -14,6 +14,7 @@
- #include <linux/mnt_namespace.h>
- #include <linux/user_namespace.h>
- #include <linux/namei.h>
- +#include <linux/delay.h>
- #include <linux/security.h>
- #include <linux/idr.h>
- #include <linux/init.h> /* init_rootfs */
- @@ -353,8 +354,11 @@
- * incremented count after it has set MNT_WRITE_HOLD.
- */
- smp_mb();
- - while (ACCESS_ONCE(mnt->mnt.mnt_flags) & MNT_WRITE_HOLD)
- - cpu_relax();
- + while (ACCESS_ONCE(mnt->mnt.mnt_flags) & MNT_WRITE_HOLD) {
- + preempt_enable();
- + cpu_chill();
- + preempt_disable();
- + }
- /*
- * After the slowpath clears MNT_WRITE_HOLD, mnt_is_readonly will
- * be set to match its requirements. So we must not load that until
- diff -Nur linux-4.4.28.orig/fs/ntfs/aops.c linux-4.4.28/fs/ntfs/aops.c
- --- linux-4.4.28.orig/fs/ntfs/aops.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/fs/ntfs/aops.c 2016-11-01 21:26:58.724338928 +0100
- @@ -107,8 +107,7 @@
- "0x%llx.", (unsigned long long)bh->b_blocknr);
- }
- first = page_buffers(page);
- - local_irq_save(flags);
- - bit_spin_lock(BH_Uptodate_Lock, &first->b_state);
- + flags = bh_uptodate_lock_irqsave(first);
- clear_buffer_async_read(bh);
- unlock_buffer(bh);
- tmp = bh;
- @@ -123,8 +122,7 @@
- }
- tmp = tmp->b_this_page;
- } while (tmp != bh);
- - bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
- - local_irq_restore(flags);
- + bh_uptodate_unlock_irqrestore(first, flags);
- /*
- * If none of the buffers had errors then we can set the page uptodate,
- * but we first have to perform the post read mst fixups, if the
- @@ -145,13 +143,13 @@
- recs = PAGE_CACHE_SIZE / rec_size;
- /* Should have been verified before we got here... */
- BUG_ON(!recs);
- - local_irq_save(flags);
- + local_irq_save_nort(flags);
- kaddr = kmap_atomic(page);
- for (i = 0; i < recs; i++)
- post_read_mst_fixup((NTFS_RECORD*)(kaddr +
- i * rec_size), rec_size);
- kunmap_atomic(kaddr);
- - local_irq_restore(flags);
- + local_irq_restore_nort(flags);
- flush_dcache_page(page);
- if (likely(page_uptodate && !PageError(page)))
- SetPageUptodate(page);
- @@ -159,9 +157,7 @@
- unlock_page(page);
- return;
- still_busy:
- - bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
- - local_irq_restore(flags);
- - return;
- + bh_uptodate_unlock_irqrestore(first, flags);
- }
-
- /**
- diff -Nur linux-4.4.28.orig/fs/timerfd.c linux-4.4.28/fs/timerfd.c
- --- linux-4.4.28.orig/fs/timerfd.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/fs/timerfd.c 2016-11-01 21:26:58.724338928 +0100
- @@ -450,7 +450,10 @@
- break;
- }
- spin_unlock_irq(&ctx->wqh.lock);
- - cpu_relax();
- + if (isalarm(ctx))
- + hrtimer_wait_for_timer(&ctx->t.alarm.timer);
- + else
- + hrtimer_wait_for_timer(&ctx->t.tmr);
- }
-
- /*
- diff -Nur linux-4.4.28.orig/include/acpi/platform/aclinux.h linux-4.4.28/include/acpi/platform/aclinux.h
- --- linux-4.4.28.orig/include/acpi/platform/aclinux.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/acpi/platform/aclinux.h 2016-11-01 21:26:58.724338928 +0100
- @@ -127,6 +127,7 @@
-
- #define acpi_cache_t struct kmem_cache
- #define acpi_spinlock spinlock_t *
- +#define acpi_raw_spinlock raw_spinlock_t *
- #define acpi_cpu_flags unsigned long
-
- /* Use native linux version of acpi_os_allocate_zeroed */
- @@ -145,6 +146,20 @@
- #define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_get_thread_id
- #define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_create_lock
-
- +#define acpi_os_create_raw_lock(__handle) \
- +({ \
- + raw_spinlock_t *lock = ACPI_ALLOCATE(sizeof(*lock)); \
- + \
- + if (lock) { \
- + *(__handle) = lock; \
- + raw_spin_lock_init(*(__handle)); \
- + } \
- + lock ? AE_OK : AE_NO_MEMORY; \
- + })
- +
- +#define acpi_os_delete_raw_lock(__handle) kfree(__handle)
- +
- +
- /*
- * OSL interfaces used by debugger/disassembler
- */
- diff -Nur linux-4.4.28.orig/include/asm-generic/bug.h linux-4.4.28/include/asm-generic/bug.h
- --- linux-4.4.28.orig/include/asm-generic/bug.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/asm-generic/bug.h 2016-11-01 21:26:58.724338928 +0100
- @@ -206,6 +206,20 @@
- # define WARN_ON_SMP(x) ({0;})
- #endif
-
- +#ifdef CONFIG_PREEMPT_RT_BASE
- +# define BUG_ON_RT(c) BUG_ON(c)
- +# define BUG_ON_NONRT(c) do { } while (0)
- +# define WARN_ON_RT(condition) WARN_ON(condition)
- +# define WARN_ON_NONRT(condition) do { } while (0)
- +# define WARN_ON_ONCE_NONRT(condition) do { } while (0)
- +#else
- +# define BUG_ON_RT(c) do { } while (0)
- +# define BUG_ON_NONRT(c) BUG_ON(c)
- +# define WARN_ON_RT(condition) do { } while (0)
- +# define WARN_ON_NONRT(condition) WARN_ON(condition)
- +# define WARN_ON_ONCE_NONRT(condition) WARN_ON_ONCE(condition)
- +#endif
- +
- #endif /* __ASSEMBLY__ */
-
- #endif
- diff -Nur linux-4.4.28.orig/include/asm-generic/preempt.h linux-4.4.28/include/asm-generic/preempt.h
- --- linux-4.4.28.orig/include/asm-generic/preempt.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/asm-generic/preempt.h 2016-11-01 21:26:58.724338928 +0100
- @@ -7,10 +7,10 @@
-
- static __always_inline int preempt_count(void)
- {
- - return current_thread_info()->preempt_count;
- + return READ_ONCE(current_thread_info()->preempt_count);
- }
-
- -static __always_inline int *preempt_count_ptr(void)
- +static __always_inline volatile int *preempt_count_ptr(void)
- {
- return ¤t_thread_info()->preempt_count;
- }
- diff -Nur linux-4.4.28.orig/include/linux/blkdev.h linux-4.4.28/include/linux/blkdev.h
- --- linux-4.4.28.orig/include/linux/blkdev.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/blkdev.h 2016-11-01 21:26:58.724338928 +0100
- @@ -89,6 +89,7 @@
- struct list_head queuelist;
- union {
- struct call_single_data csd;
- + struct work_struct work;
- unsigned long fifo_time;
- };
-
- @@ -455,7 +456,7 @@
- struct throtl_data *td;
- #endif
- struct rcu_head rcu_head;
- - wait_queue_head_t mq_freeze_wq;
- + struct swait_queue_head mq_freeze_wq;
- struct percpu_ref q_usage_counter;
- struct list_head all_q_node;
-
- diff -Nur linux-4.4.28.orig/include/linux/blk-mq.h linux-4.4.28/include/linux/blk-mq.h
- --- linux-4.4.28.orig/include/linux/blk-mq.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/blk-mq.h 2016-11-01 21:26:58.724338928 +0100
- @@ -212,6 +212,7 @@
-
- struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *, const int ctx_index);
- struct blk_mq_hw_ctx *blk_mq_alloc_single_hw_queue(struct blk_mq_tag_set *, unsigned int, int);
- +void __blk_mq_complete_request_remote_work(struct work_struct *work);
-
- int blk_mq_request_started(struct request *rq);
- void blk_mq_start_request(struct request *rq);
- diff -Nur linux-4.4.28.orig/include/linux/bottom_half.h linux-4.4.28/include/linux/bottom_half.h
- --- linux-4.4.28.orig/include/linux/bottom_half.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/bottom_half.h 2016-11-01 21:26:58.724338928 +0100
- @@ -3,6 +3,39 @@
-
- #include <linux/preempt.h>
-
- +#ifdef CONFIG_PREEMPT_RT_FULL
- +
- +extern void __local_bh_disable(void);
- +extern void _local_bh_enable(void);
- +extern void __local_bh_enable(void);
- +
- +static inline void local_bh_disable(void)
- +{
- + __local_bh_disable();
- +}
- +
- +static inline void __local_bh_disable_ip(unsigned long ip, unsigned int cnt)
- +{
- + __local_bh_disable();
- +}
- +
- +static inline void local_bh_enable(void)
- +{
- + __local_bh_enable();
- +}
- +
- +static inline void __local_bh_enable_ip(unsigned long ip, unsigned int cnt)
- +{
- + __local_bh_enable();
- +}
- +
- +static inline void local_bh_enable_ip(unsigned long ip)
- +{
- + __local_bh_enable();
- +}
- +
- +#else
- +
- #ifdef CONFIG_TRACE_IRQFLAGS
- extern void __local_bh_disable_ip(unsigned long ip, unsigned int cnt);
- #else
- @@ -30,5 +63,6 @@
- {
- __local_bh_enable_ip(_THIS_IP_, SOFTIRQ_DISABLE_OFFSET);
- }
- +#endif
-
- #endif /* _LINUX_BH_H */
- diff -Nur linux-4.4.28.orig/include/linux/buffer_head.h linux-4.4.28/include/linux/buffer_head.h
- --- linux-4.4.28.orig/include/linux/buffer_head.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/buffer_head.h 2016-11-01 21:26:58.724338928 +0100
- @@ -75,8 +75,50 @@
- struct address_space *b_assoc_map; /* mapping this buffer is
- associated with */
- atomic_t b_count; /* users using this buffer_head */
- +#ifdef CONFIG_PREEMPT_RT_BASE
- + spinlock_t b_uptodate_lock;
- +#if IS_ENABLED(CONFIG_JBD2)
- + spinlock_t b_state_lock;
- + spinlock_t b_journal_head_lock;
- +#endif
- +#endif
- };
-
- +static inline unsigned long bh_uptodate_lock_irqsave(struct buffer_head *bh)
- +{
- + unsigned long flags;
- +
- +#ifndef CONFIG_PREEMPT_RT_BASE
- + local_irq_save(flags);
- + bit_spin_lock(BH_Uptodate_Lock, &bh->b_state);
- +#else
- + spin_lock_irqsave(&bh->b_uptodate_lock, flags);
- +#endif
- + return flags;
- +}
- +
- +static inline void
- +bh_uptodate_unlock_irqrestore(struct buffer_head *bh, unsigned long flags)
- +{
- +#ifndef CONFIG_PREEMPT_RT_BASE
- + bit_spin_unlock(BH_Uptodate_Lock, &bh->b_state);
- + local_irq_restore(flags);
- +#else
- + spin_unlock_irqrestore(&bh->b_uptodate_lock, flags);
- +#endif
- +}
- +
- +static inline void buffer_head_init_locks(struct buffer_head *bh)
- +{
- +#ifdef CONFIG_PREEMPT_RT_BASE
- + spin_lock_init(&bh->b_uptodate_lock);
- +#if IS_ENABLED(CONFIG_JBD2)
- + spin_lock_init(&bh->b_state_lock);
- + spin_lock_init(&bh->b_journal_head_lock);
- +#endif
- +#endif
- +}
- +
- /*
- * macro tricks to expand the set_buffer_foo(), clear_buffer_foo()
- * and buffer_foo() functions.
- diff -Nur linux-4.4.28.orig/include/linux/cgroup-defs.h linux-4.4.28/include/linux/cgroup-defs.h
- --- linux-4.4.28.orig/include/linux/cgroup-defs.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/cgroup-defs.h 2016-11-01 21:26:58.728339185 +0100
- @@ -16,6 +16,7 @@
- #include <linux/percpu-refcount.h>
- #include <linux/percpu-rwsem.h>
- #include <linux/workqueue.h>
- +#include <linux/swork.h>
-
- #ifdef CONFIG_CGROUPS
-
- @@ -142,6 +143,7 @@
- /* percpu_ref killing and RCU release */
- struct rcu_head rcu_head;
- struct work_struct destroy_work;
- + struct swork_event destroy_swork;
- };
-
- /*
- diff -Nur linux-4.4.28.orig/include/linux/clk/at91_pmc.h linux-4.4.28/include/linux/clk/at91_pmc.h
- --- linux-4.4.28.orig/include/linux/clk/at91_pmc.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/clk/at91_pmc.h 2016-11-01 21:26:58.728339185 +0100
- @@ -16,18 +16,6 @@
- #ifndef AT91_PMC_H
- #define AT91_PMC_H
-
- -#ifndef __ASSEMBLY__
- -extern void __iomem *at91_pmc_base;
- -
- -#define at91_pmc_read(field) \
- - readl_relaxed(at91_pmc_base + field)
- -
- -#define at91_pmc_write(field, value) \
- - writel_relaxed(value, at91_pmc_base + field)
- -#else
- -.extern at91_pmc_base
- -#endif
- -
- #define AT91_PMC_SCER 0x00 /* System Clock Enable Register */
- #define AT91_PMC_SCDR 0x04 /* System Clock Disable Register */
-
- diff -Nur linux-4.4.28.orig/include/linux/completion.h linux-4.4.28/include/linux/completion.h
- --- linux-4.4.28.orig/include/linux/completion.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/completion.h 2016-11-01 21:26:58.728339185 +0100
- @@ -7,8 +7,7 @@
- * Atomic wait-for-completion handler data structures.
- * See kernel/sched/completion.c for details.
- */
- -
- -#include <linux/wait.h>
- +#include <linux/swait.h>
-
- /*
- * struct completion - structure used to maintain state for a "completion"
- @@ -24,11 +23,11 @@
- */
- struct completion {
- unsigned int done;
- - wait_queue_head_t wait;
- + struct swait_queue_head wait;
- };
-
- #define COMPLETION_INITIALIZER(work) \
- - { 0, __WAIT_QUEUE_HEAD_INITIALIZER((work).wait) }
- + { 0, __SWAIT_QUEUE_HEAD_INITIALIZER((work).wait) }
-
- #define COMPLETION_INITIALIZER_ONSTACK(work) \
- ({ init_completion(&work); work; })
- @@ -73,7 +72,7 @@
- static inline void init_completion(struct completion *x)
- {
- x->done = 0;
- - init_waitqueue_head(&x->wait);
- + init_swait_queue_head(&x->wait);
- }
-
- /**
- diff -Nur linux-4.4.28.orig/include/linux/cpu.h linux-4.4.28/include/linux/cpu.h
- --- linux-4.4.28.orig/include/linux/cpu.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/cpu.h 2016-11-01 21:26:58.728339185 +0100
- @@ -231,6 +231,8 @@
- extern void put_online_cpus(void);
- extern void cpu_hotplug_disable(void);
- extern void cpu_hotplug_enable(void);
- +extern void pin_current_cpu(void);
- +extern void unpin_current_cpu(void);
- #define hotcpu_notifier(fn, pri) cpu_notifier(fn, pri)
- #define __hotcpu_notifier(fn, pri) __cpu_notifier(fn, pri)
- #define register_hotcpu_notifier(nb) register_cpu_notifier(nb)
- @@ -248,6 +250,8 @@
- #define put_online_cpus() do { } while (0)
- #define cpu_hotplug_disable() do { } while (0)
- #define cpu_hotplug_enable() do { } while (0)
- +static inline void pin_current_cpu(void) { }
- +static inline void unpin_current_cpu(void) { }
- #define hotcpu_notifier(fn, pri) do { (void)(fn); } while (0)
- #define __hotcpu_notifier(fn, pri) do { (void)(fn); } while (0)
- /* These aren't inline functions due to a GCC bug. */
- diff -Nur linux-4.4.28.orig/include/linux/delay.h linux-4.4.28/include/linux/delay.h
- --- linux-4.4.28.orig/include/linux/delay.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/delay.h 2016-11-01 21:26:58.728339185 +0100
- @@ -52,4 +52,10 @@
- msleep(seconds * 1000);
- }
-
- +#ifdef CONFIG_PREEMPT_RT_FULL
- +extern void cpu_chill(void);
- +#else
- +# define cpu_chill() cpu_relax()
- +#endif
- +
- #endif /* defined(_LINUX_DELAY_H) */
- diff -Nur linux-4.4.28.orig/include/linux/ftrace.h linux-4.4.28/include/linux/ftrace.h
- --- linux-4.4.28.orig/include/linux/ftrace.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/ftrace.h 2016-11-01 21:26:58.728339185 +0100
- @@ -694,6 +694,18 @@
- #define CALLER_ADDR5 ((unsigned long)ftrace_return_address(5))
- #define CALLER_ADDR6 ((unsigned long)ftrace_return_address(6))
-
- +static inline unsigned long get_lock_parent_ip(void)
- +{
- + unsigned long addr = CALLER_ADDR0;
- +
- + if (!in_lock_functions(addr))
- + return addr;
- + addr = CALLER_ADDR1;
- + if (!in_lock_functions(addr))
- + return addr;
- + return CALLER_ADDR2;
- +}
- +
- #ifdef CONFIG_IRQSOFF_TRACER
- extern void time_hardirqs_on(unsigned long a0, unsigned long a1);
- extern void time_hardirqs_off(unsigned long a0, unsigned long a1);
- diff -Nur linux-4.4.28.orig/include/linux/highmem.h linux-4.4.28/include/linux/highmem.h
- --- linux-4.4.28.orig/include/linux/highmem.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/highmem.h 2016-11-01 21:26:58.728339185 +0100
- @@ -7,6 +7,7 @@
- #include <linux/mm.h>
- #include <linux/uaccess.h>
- #include <linux/hardirq.h>
- +#include <linux/sched.h>
-
- #include <asm/cacheflush.h>
-
- @@ -65,7 +66,7 @@
-
- static inline void *kmap_atomic(struct page *page)
- {
- - preempt_disable();
- + preempt_disable_nort();
- pagefault_disable();
- return page_address(page);
- }
- @@ -74,7 +75,7 @@
- static inline void __kunmap_atomic(void *addr)
- {
- pagefault_enable();
- - preempt_enable();
- + preempt_enable_nort();
- }
-
- #define kmap_atomic_pfn(pfn) kmap_atomic(pfn_to_page(pfn))
- @@ -86,32 +87,51 @@
-
- #if defined(CONFIG_HIGHMEM) || defined(CONFIG_X86_32)
-
- +#ifndef CONFIG_PREEMPT_RT_FULL
- DECLARE_PER_CPU(int, __kmap_atomic_idx);
- +#endif
-
- static inline int kmap_atomic_idx_push(void)
- {
- +#ifndef CONFIG_PREEMPT_RT_FULL
- int idx = __this_cpu_inc_return(__kmap_atomic_idx) - 1;
-
- -#ifdef CONFIG_DEBUG_HIGHMEM
- +# ifdef CONFIG_DEBUG_HIGHMEM
- WARN_ON_ONCE(in_irq() && !irqs_disabled());
- BUG_ON(idx >= KM_TYPE_NR);
- -#endif
- +# endif
- return idx;
- +#else
- + current->kmap_idx++;
- + BUG_ON(current->kmap_idx > KM_TYPE_NR);
- + return current->kmap_idx - 1;
- +#endif
- }
-
- static inline int kmap_atomic_idx(void)
- {
- +#ifndef CONFIG_PREEMPT_RT_FULL
- return __this_cpu_read(__kmap_atomic_idx) - 1;
- +#else
- + return current->kmap_idx - 1;
- +#endif
- }
-
- static inline void kmap_atomic_idx_pop(void)
- {
- -#ifdef CONFIG_DEBUG_HIGHMEM
- +#ifndef CONFIG_PREEMPT_RT_FULL
- +# ifdef CONFIG_DEBUG_HIGHMEM
- int idx = __this_cpu_dec_return(__kmap_atomic_idx);
-
- BUG_ON(idx < 0);
- -#else
- +# else
- __this_cpu_dec(__kmap_atomic_idx);
- +# endif
- +#else
- + current->kmap_idx--;
- +# ifdef CONFIG_DEBUG_HIGHMEM
- + BUG_ON(current->kmap_idx < 0);
- +# endif
- #endif
- }
-
- diff -Nur linux-4.4.28.orig/include/linux/hrtimer.h linux-4.4.28/include/linux/hrtimer.h
- --- linux-4.4.28.orig/include/linux/hrtimer.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/hrtimer.h 2016-11-01 21:26:58.728339185 +0100
- @@ -87,6 +87,9 @@
- * @function: timer expiry callback function
- * @base: pointer to the timer base (per cpu and per clock)
- * @state: state information (See bit values above)
- + * @cb_entry: list entry to defer timers from hardirq context
- + * @irqsafe: timer can run in hardirq context
- + * @praecox: timer expiry time if expired at the time of programming
- * @is_rel: Set if the timer was armed relative
- * @start_pid: timer statistics field to store the pid of the task which
- * started the timer
- @@ -103,6 +106,11 @@
- enum hrtimer_restart (*function)(struct hrtimer *);
- struct hrtimer_clock_base *base;
- u8 state;
- + struct list_head cb_entry;
- + int irqsafe;
- +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
- + ktime_t praecox;
- +#endif
- u8 is_rel;
- #ifdef CONFIG_TIMER_STATS
- int start_pid;
- @@ -123,11 +131,7 @@
- struct task_struct *task;
- };
-
- -#ifdef CONFIG_64BIT
- # define HRTIMER_CLOCK_BASE_ALIGN 64
- -#else
- -# define HRTIMER_CLOCK_BASE_ALIGN 32
- -#endif
-
- /**
- * struct hrtimer_clock_base - the timer base for a specific clock
- @@ -136,6 +140,7 @@
- * timer to a base on another cpu.
- * @clockid: clock id for per_cpu support
- * @active: red black tree root node for the active timers
- + * @expired: list head for deferred timers.
- * @get_time: function to retrieve the current time of the clock
- * @offset: offset of this clock to the monotonic base
- */
- @@ -144,6 +149,7 @@
- int index;
- clockid_t clockid;
- struct timerqueue_head active;
- + struct list_head expired;
- ktime_t (*get_time)(void);
- ktime_t offset;
- } __attribute__((__aligned__(HRTIMER_CLOCK_BASE_ALIGN)));
- @@ -187,6 +193,7 @@
- raw_spinlock_t lock;
- seqcount_t seq;
- struct hrtimer *running;
- + struct hrtimer *running_soft;
- unsigned int cpu;
- unsigned int active_bases;
- unsigned int clock_was_set_seq;
- @@ -203,6 +210,9 @@
- unsigned int nr_hangs;
- unsigned int max_hang_time;
- #endif
- +#ifdef CONFIG_PREEMPT_RT_BASE
- + wait_queue_head_t wait;
- +#endif
- struct hrtimer_clock_base clock_base[HRTIMER_MAX_CLOCK_BASES];
- } ____cacheline_aligned;
-
- @@ -412,6 +422,13 @@
- hrtimer_start_expires(timer, HRTIMER_MODE_ABS);
- }
-
- +/* Softirq preemption could deadlock timer removal */
- +#ifdef CONFIG_PREEMPT_RT_BASE
- + extern void hrtimer_wait_for_timer(const struct hrtimer *timer);
- +#else
- +# define hrtimer_wait_for_timer(timer) do { cpu_relax(); } while (0)
- +#endif
- +
- /* Query timers: */
- extern ktime_t __hrtimer_get_remaining(const struct hrtimer *timer, bool adjust);
-
- @@ -436,7 +453,7 @@
- * Helper function to check, whether the timer is running the callback
- * function
- */
- -static inline int hrtimer_callback_running(struct hrtimer *timer)
- +static inline int hrtimer_callback_running(const struct hrtimer *timer)
- {
- return timer->base->cpu_base->running == timer;
- }
- diff -Nur linux-4.4.28.orig/include/linux/idr.h linux-4.4.28/include/linux/idr.h
- --- linux-4.4.28.orig/include/linux/idr.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/idr.h 2016-11-01 21:26:58.728339185 +0100
- @@ -95,10 +95,14 @@
- * Each idr_preload() should be matched with an invocation of this
- * function. See idr_preload() for details.
- */
- +#ifdef CONFIG_PREEMPT_RT_FULL
- +void idr_preload_end(void);
- +#else
- static inline void idr_preload_end(void)
- {
- preempt_enable();
- }
- +#endif
-
- /**
- * idr_find - return pointer for given id
- diff -Nur linux-4.4.28.orig/include/linux/init_task.h linux-4.4.28/include/linux/init_task.h
- --- linux-4.4.28.orig/include/linux/init_task.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/init_task.h 2016-11-01 21:26:58.728339185 +0100
- @@ -148,9 +148,15 @@
- # define INIT_PERF_EVENTS(tsk)
- #endif
-
- +#ifdef CONFIG_PREEMPT_RT_BASE
- +# define INIT_TIMER_LIST .posix_timer_list = NULL,
- +#else
- +# define INIT_TIMER_LIST
- +#endif
- +
- #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
- # define INIT_VTIME(tsk) \
- - .vtime_seqlock = __SEQLOCK_UNLOCKED(tsk.vtime_seqlock), \
- + .vtime_seqcount = SEQCNT_ZERO(tsk.vtime_seqcount), \
- .vtime_snap = 0, \
- .vtime_snap_whence = VTIME_SYS,
- #else
- @@ -239,6 +245,7 @@
- .cpu_timers = INIT_CPU_TIMERS(tsk.cpu_timers), \
- .pi_lock = __RAW_SPIN_LOCK_UNLOCKED(tsk.pi_lock), \
- .timer_slack_ns = 50000, /* 50 usec default slack */ \
- + INIT_TIMER_LIST \
- .pids = { \
- [PIDTYPE_PID] = INIT_PID_LINK(PIDTYPE_PID), \
- [PIDTYPE_PGID] = INIT_PID_LINK(PIDTYPE_PGID), \
- diff -Nur linux-4.4.28.orig/include/linux/interrupt.h linux-4.4.28/include/linux/interrupt.h
- --- linux-4.4.28.orig/include/linux/interrupt.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/interrupt.h 2016-11-01 21:26:58.728339185 +0100
- @@ -61,6 +61,7 @@
- * interrupt handler after suspending interrupts. For system
- * wakeup devices users need to implement wakeup detection in
- * their interrupt handlers.
- + * IRQF_NO_SOFTIRQ_CALL - Do not process softirqs in the irq thread context (RT)
- */
- #define IRQF_SHARED 0x00000080
- #define IRQF_PROBE_SHARED 0x00000100
- @@ -74,6 +75,7 @@
- #define IRQF_NO_THREAD 0x00010000
- #define IRQF_EARLY_RESUME 0x00020000
- #define IRQF_COND_SUSPEND 0x00040000
- +#define IRQF_NO_SOFTIRQ_CALL 0x00080000
-
- #define IRQF_TIMER (__IRQF_TIMER | IRQF_NO_SUSPEND | IRQF_NO_THREAD)
-
- @@ -186,7 +188,7 @@
- #ifdef CONFIG_LOCKDEP
- # define local_irq_enable_in_hardirq() do { } while (0)
- #else
- -# define local_irq_enable_in_hardirq() local_irq_enable()
- +# define local_irq_enable_in_hardirq() local_irq_enable_nort()
- #endif
-
- extern void disable_irq_nosync(unsigned int irq);
- @@ -206,6 +208,7 @@
- * @irq: Interrupt to which notification applies
- * @kref: Reference count, for internal use
- * @work: Work item, for internal use
- + * @list: List item for deferred callbacks
- * @notify: Function to be called on change. This will be
- * called in process context.
- * @release: Function to be called on release. This will be
- @@ -217,6 +220,7 @@
- unsigned int irq;
- struct kref kref;
- struct work_struct work;
- + struct list_head list;
- void (*notify)(struct irq_affinity_notify *, const cpumask_t *mask);
- void (*release)(struct kref *ref);
- };
- @@ -379,9 +383,13 @@
- bool state);
-
- #ifdef CONFIG_IRQ_FORCED_THREADING
- +# ifndef CONFIG_PREEMPT_RT_BASE
- extern bool force_irqthreads;
- +# else
- +# define force_irqthreads (true)
- +# endif
- #else
- -#define force_irqthreads (0)
- +#define force_irqthreads (false)
- #endif
-
- #ifndef __ARCH_SET_SOFTIRQ_PENDING
- @@ -438,9 +446,10 @@
- void (*action)(struct softirq_action *);
- };
-
- +#ifndef CONFIG_PREEMPT_RT_FULL
- asmlinkage void do_softirq(void);
- asmlinkage void __do_softirq(void);
- -
- +static inline void thread_do_softirq(void) { do_softirq(); }
- #ifdef __ARCH_HAS_DO_SOFTIRQ
- void do_softirq_own_stack(void);
- #else
- @@ -449,13 +458,25 @@
- __do_softirq();
- }
- #endif
- +#else
- +extern void thread_do_softirq(void);
- +#endif
-
- extern void open_softirq(int nr, void (*action)(struct softirq_action *));
- extern void softirq_init(void);
- extern void __raise_softirq_irqoff(unsigned int nr);
- +#ifdef CONFIG_PREEMPT_RT_FULL
- +extern void __raise_softirq_irqoff_ksoft(unsigned int nr);
- +#else
- +static inline void __raise_softirq_irqoff_ksoft(unsigned int nr)
- +{
- + __raise_softirq_irqoff(nr);
- +}
- +#endif
-
- extern void raise_softirq_irqoff(unsigned int nr);
- extern void raise_softirq(unsigned int nr);
- +extern void softirq_check_pending_idle(void);
-
- DECLARE_PER_CPU(struct task_struct *, ksoftirqd);
-
- @@ -477,8 +498,9 @@
- to be executed on some cpu at least once after this.
- * If the tasklet is already scheduled, but its execution is still not
- started, it will be executed only once.
- - * If this tasklet is already running on another CPU (or schedule is called
- - from tasklet itself), it is rescheduled for later.
- + * If this tasklet is already running on another CPU, it is rescheduled
- + for later.
- + * Schedule must not be called from the tasklet itself (a lockup occurs)
- * Tasklet is strictly serialized wrt itself, but not
- wrt another tasklets. If client needs some intertask synchronization,
- he makes it with spinlocks.
- @@ -503,27 +525,36 @@
- enum
- {
- TASKLET_STATE_SCHED, /* Tasklet is scheduled for execution */
- - TASKLET_STATE_RUN /* Tasklet is running (SMP only) */
- + TASKLET_STATE_RUN, /* Tasklet is running (SMP only) */
- + TASKLET_STATE_PENDING /* Tasklet is pending */
- };
-
- -#ifdef CONFIG_SMP
- +#define TASKLET_STATEF_SCHED (1 << TASKLET_STATE_SCHED)
- +#define TASKLET_STATEF_RUN (1 << TASKLET_STATE_RUN)
- +#define TASKLET_STATEF_PENDING (1 << TASKLET_STATE_PENDING)
- +
- +#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL)
- static inline int tasklet_trylock(struct tasklet_struct *t)
- {
- return !test_and_set_bit(TASKLET_STATE_RUN, &(t)->state);
- }
-
- +static inline int tasklet_tryunlock(struct tasklet_struct *t)
- +{
- + return cmpxchg(&t->state, TASKLET_STATEF_RUN, 0) == TASKLET_STATEF_RUN;
- +}
- +
- static inline void tasklet_unlock(struct tasklet_struct *t)
- {
- smp_mb__before_atomic();
- clear_bit(TASKLET_STATE_RUN, &(t)->state);
- }
-
- -static inline void tasklet_unlock_wait(struct tasklet_struct *t)
- -{
- - while (test_bit(TASKLET_STATE_RUN, &(t)->state)) { barrier(); }
- -}
- +extern void tasklet_unlock_wait(struct tasklet_struct *t);
- +
- #else
- #define tasklet_trylock(t) 1
- +#define tasklet_tryunlock(t) 1
- #define tasklet_unlock_wait(t) do { } while (0)
- #define tasklet_unlock(t) do { } while (0)
- #endif
- @@ -572,12 +603,7 @@
- smp_mb();
- }
-
- -static inline void tasklet_enable(struct tasklet_struct *t)
- -{
- - smp_mb__before_atomic();
- - atomic_dec(&t->count);
- -}
- -
- +extern void tasklet_enable(struct tasklet_struct *t);
- extern void tasklet_kill(struct tasklet_struct *t);
- extern void tasklet_kill_immediate(struct tasklet_struct *t, unsigned int cpu);
- extern void tasklet_init(struct tasklet_struct *t,
- @@ -608,6 +634,12 @@
- tasklet_kill(&ttimer->tasklet);
- }
-
- +#ifdef CONFIG_PREEMPT_RT_FULL
- +extern void softirq_early_init(void);
- +#else
- +static inline void softirq_early_init(void) { }
- +#endif
- +
- /*
- * Autoprobing for irqs:
- *
- diff -Nur linux-4.4.28.orig/include/linux/irqdesc.h linux-4.4.28/include/linux/irqdesc.h
- --- linux-4.4.28.orig/include/linux/irqdesc.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/irqdesc.h 2016-11-01 21:26:58.732339449 +0100
- @@ -61,6 +61,7 @@
- unsigned int irqs_unhandled;
- atomic_t threads_handled;
- int threads_handled_last;
- + u64 random_ip;
- raw_spinlock_t lock;
- struct cpumask *percpu_enabled;
- #ifdef CONFIG_SMP
- diff -Nur linux-4.4.28.orig/include/linux/irqflags.h linux-4.4.28/include/linux/irqflags.h
- --- linux-4.4.28.orig/include/linux/irqflags.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/irqflags.h 2016-11-01 21:26:58.732339449 +0100
- @@ -25,8 +25,6 @@
- # define trace_softirqs_enabled(p) ((p)->softirqs_enabled)
- # define trace_hardirq_enter() do { current->hardirq_context++; } while (0)
- # define trace_hardirq_exit() do { current->hardirq_context--; } while (0)
- -# define lockdep_softirq_enter() do { current->softirq_context++; } while (0)
- -# define lockdep_softirq_exit() do { current->softirq_context--; } while (0)
- # define INIT_TRACE_IRQFLAGS .softirqs_enabled = 1,
- #else
- # define trace_hardirqs_on() do { } while (0)
- @@ -39,9 +37,15 @@
- # define trace_softirqs_enabled(p) 0
- # define trace_hardirq_enter() do { } while (0)
- # define trace_hardirq_exit() do { } while (0)
- +# define INIT_TRACE_IRQFLAGS
- +#endif
- +
- +#if defined(CONFIG_TRACE_IRQFLAGS) && !defined(CONFIG_PREEMPT_RT_FULL)
- +# define lockdep_softirq_enter() do { current->softirq_context++; } while (0)
- +# define lockdep_softirq_exit() do { current->softirq_context--; } while (0)
- +#else
- # define lockdep_softirq_enter() do { } while (0)
- # define lockdep_softirq_exit() do { } while (0)
- -# define INIT_TRACE_IRQFLAGS
- #endif
-
- #if defined(CONFIG_IRQSOFF_TRACER) || \
- @@ -148,4 +152,23 @@
-
- #define irqs_disabled_flags(flags) raw_irqs_disabled_flags(flags)
-
- +/*
- + * local_irq* variants depending on RT/!RT
- + */
- +#ifdef CONFIG_PREEMPT_RT_FULL
- +# define local_irq_disable_nort() do { } while (0)
- +# define local_irq_enable_nort() do { } while (0)
- +# define local_irq_save_nort(flags) local_save_flags(flags)
- +# define local_irq_restore_nort(flags) (void)(flags)
- +# define local_irq_disable_rt() local_irq_disable()
- +# define local_irq_enable_rt() local_irq_enable()
- +#else
- +# define local_irq_disable_nort() local_irq_disable()
- +# define local_irq_enable_nort() local_irq_enable()
- +# define local_irq_save_nort(flags) local_irq_save(flags)
- +# define local_irq_restore_nort(flags) local_irq_restore(flags)
- +# define local_irq_disable_rt() do { } while (0)
- +# define local_irq_enable_rt() do { } while (0)
- +#endif
- +
- #endif
- diff -Nur linux-4.4.28.orig/include/linux/irq.h linux-4.4.28/include/linux/irq.h
- --- linux-4.4.28.orig/include/linux/irq.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/irq.h 2016-11-01 21:26:58.728339185 +0100
- @@ -72,6 +72,7 @@
- * IRQ_IS_POLLED - Always polled by another interrupt. Exclude
- * it from the spurious interrupt detection
- * mechanism and from core side polling.
- + * IRQ_NO_SOFTIRQ_CALL - No softirq processing in the irq thread context (RT)
- * IRQ_DISABLE_UNLAZY - Disable lazy irq disable
- */
- enum {
- @@ -99,13 +100,14 @@
- IRQ_PER_CPU_DEVID = (1 << 17),
- IRQ_IS_POLLED = (1 << 18),
- IRQ_DISABLE_UNLAZY = (1 << 19),
- + IRQ_NO_SOFTIRQ_CALL = (1 << 20),
- };
-
- #define IRQF_MODIFY_MASK \
- (IRQ_TYPE_SENSE_MASK | IRQ_NOPROBE | IRQ_NOREQUEST | \
- IRQ_NOAUTOEN | IRQ_MOVE_PCNTXT | IRQ_LEVEL | IRQ_NO_BALANCING | \
- IRQ_PER_CPU | IRQ_NESTED_THREAD | IRQ_NOTHREAD | IRQ_PER_CPU_DEVID | \
- - IRQ_IS_POLLED | IRQ_DISABLE_UNLAZY)
- + IRQ_IS_POLLED | IRQ_DISABLE_UNLAZY | IRQ_NO_SOFTIRQ_CALL)
-
- #define IRQ_NO_BALANCING_MASK (IRQ_PER_CPU | IRQ_NO_BALANCING)
-
- diff -Nur linux-4.4.28.orig/include/linux/irq_work.h linux-4.4.28/include/linux/irq_work.h
- --- linux-4.4.28.orig/include/linux/irq_work.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/irq_work.h 2016-11-01 21:26:58.728339185 +0100
- @@ -16,6 +16,7 @@
- #define IRQ_WORK_BUSY 2UL
- #define IRQ_WORK_FLAGS 3UL
- #define IRQ_WORK_LAZY 4UL /* Doesn't want IPI, wait for tick */
- +#define IRQ_WORK_HARD_IRQ 8UL /* Run hard IRQ context, even on RT */
-
- struct irq_work {
- unsigned long flags;
- @@ -51,4 +52,10 @@
- static inline void irq_work_run(void) { }
- #endif
-
- +#if defined(CONFIG_IRQ_WORK) && defined(CONFIG_PREEMPT_RT_FULL)
- +void irq_work_tick_soft(void);
- +#else
- +static inline void irq_work_tick_soft(void) { }
- +#endif
- +
- #endif /* _LINUX_IRQ_WORK_H */
- diff -Nur linux-4.4.28.orig/include/linux/jbd2.h linux-4.4.28/include/linux/jbd2.h
- --- linux-4.4.28.orig/include/linux/jbd2.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/jbd2.h 2016-11-01 21:26:58.732339449 +0100
- @@ -352,32 +352,56 @@
-
- static inline void jbd_lock_bh_state(struct buffer_head *bh)
- {
- +#ifndef CONFIG_PREEMPT_RT_BASE
- bit_spin_lock(BH_State, &bh->b_state);
- +#else
- + spin_lock(&bh->b_state_lock);
- +#endif
- }
-
- static inline int jbd_trylock_bh_state(struct buffer_head *bh)
- {
- +#ifndef CONFIG_PREEMPT_RT_BASE
- return bit_spin_trylock(BH_State, &bh->b_state);
- +#else
- + return spin_trylock(&bh->b_state_lock);
- +#endif
- }
-
- static inline int jbd_is_locked_bh_state(struct buffer_head *bh)
- {
- +#ifndef CONFIG_PREEMPT_RT_BASE
- return bit_spin_is_locked(BH_State, &bh->b_state);
- +#else
- + return spin_is_locked(&bh->b_state_lock);
- +#endif
- }
-
- static inline void jbd_unlock_bh_state(struct buffer_head *bh)
- {
- +#ifndef CONFIG_PREEMPT_RT_BASE
- bit_spin_unlock(BH_State, &bh->b_state);
- +#else
- + spin_unlock(&bh->b_state_lock);
- +#endif
- }
-
- static inline void jbd_lock_bh_journal_head(struct buffer_head *bh)
- {
- +#ifndef CONFIG_PREEMPT_RT_BASE
- bit_spin_lock(BH_JournalHead, &bh->b_state);
- +#else
- + spin_lock(&bh->b_journal_head_lock);
- +#endif
- }
-
- static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh)
- {
- +#ifndef CONFIG_PREEMPT_RT_BASE
- bit_spin_unlock(BH_JournalHead, &bh->b_state);
- +#else
- + spin_unlock(&bh->b_journal_head_lock);
- +#endif
- }
-
- #define J_ASSERT(assert) BUG_ON(!(assert))
- diff -Nur linux-4.4.28.orig/include/linux/kdb.h linux-4.4.28/include/linux/kdb.h
- --- linux-4.4.28.orig/include/linux/kdb.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/kdb.h 2016-11-01 21:26:58.732339449 +0100
- @@ -167,6 +167,7 @@
- extern __printf(1, 2) int kdb_printf(const char *, ...);
- typedef __printf(1, 2) int (*kdb_printf_t)(const char *, ...);
-
- +#define in_kdb_printk() (kdb_trap_printk)
- extern void kdb_init(int level);
-
- /* Access to kdb specific polling devices */
- @@ -201,6 +202,7 @@
- extern int kdb_unregister(char *);
- #else /* ! CONFIG_KGDB_KDB */
- static inline __printf(1, 2) int kdb_printf(const char *fmt, ...) { return 0; }
- +#define in_kdb_printk() (0)
- static inline void kdb_init(int level) {}
- static inline int kdb_register(char *cmd, kdb_func_t func, char *usage,
- char *help, short minlen) { return 0; }
- diff -Nur linux-4.4.28.orig/include/linux/kernel.h linux-4.4.28/include/linux/kernel.h
- --- linux-4.4.28.orig/include/linux/kernel.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/kernel.h 2016-11-01 21:26:58.732339449 +0100
- @@ -188,6 +188,9 @@
- */
- # define might_sleep() \
- do { __might_sleep(__FILE__, __LINE__, 0); might_resched(); } while (0)
- +
- +# define might_sleep_no_state_check() \
- + do { ___might_sleep(__FILE__, __LINE__, 0); might_resched(); } while (0)
- # define sched_annotate_sleep() (current->task_state_change = 0)
- #else
- static inline void ___might_sleep(const char *file, int line,
- @@ -195,6 +198,7 @@
- static inline void __might_sleep(const char *file, int line,
- int preempt_offset) { }
- # define might_sleep() do { might_resched(); } while (0)
- +# define might_sleep_no_state_check() do { might_resched(); } while (0)
- # define sched_annotate_sleep() do { } while (0)
- #endif
-
- @@ -255,6 +259,7 @@
- __printf(1, 2)
- void panic(const char *fmt, ...)
- __noreturn __cold;
- +void nmi_panic(struct pt_regs *regs, const char *msg);
- extern void oops_enter(void);
- extern void oops_exit(void);
- void print_oops_end_marker(void);
- @@ -448,6 +453,14 @@
- extern bool crash_kexec_post_notifiers;
-
- /*
- + * panic_cpu is used for synchronizing panic() and crash_kexec() execution. It
- + * holds a CPU number which is executing panic() currently. A value of
- + * PANIC_CPU_INVALID means no CPU has entered panic() or crash_kexec().
- + */
- +extern atomic_t panic_cpu;
- +#define PANIC_CPU_INVALID -1
- +
- +/*
- * Only to be used by arch init code. If the user over-wrote the default
- * CONFIG_PANIC_TIMEOUT, honor it.
- */
- @@ -475,6 +488,7 @@
- SYSTEM_HALT,
- SYSTEM_POWER_OFF,
- SYSTEM_RESTART,
- + SYSTEM_SUSPEND,
- } system_state;
-
- #define TAINT_PROPRIETARY_MODULE 0
- diff -Nur linux-4.4.28.orig/include/linux/kvm_host.h linux-4.4.28/include/linux/kvm_host.h
- --- linux-4.4.28.orig/include/linux/kvm_host.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/kvm_host.h 2016-11-01 21:26:58.732339449 +0100
- @@ -25,6 +25,7 @@
- #include <linux/irqflags.h>
- #include <linux/context_tracking.h>
- #include <linux/irqbypass.h>
- +#include <linux/swait.h>
- #include <asm/signal.h>
-
- #include <linux/kvm.h>
- @@ -243,7 +244,7 @@
- int fpu_active;
- int guest_fpu_loaded, guest_xcr0_loaded;
- unsigned char fpu_counter;
- - wait_queue_head_t wq;
- + struct swait_queue_head wq;
- struct pid *pid;
- int sigset_active;
- sigset_t sigset;
- @@ -794,7 +795,7 @@
- }
- #endif
-
- -static inline wait_queue_head_t *kvm_arch_vcpu_wq(struct kvm_vcpu *vcpu)
- +static inline struct swait_queue_head *kvm_arch_vcpu_wq(struct kvm_vcpu *vcpu)
- {
- #ifdef __KVM_HAVE_ARCH_WQP
- return vcpu->arch.wqp;
- diff -Nur linux-4.4.28.orig/include/linux/lglock.h linux-4.4.28/include/linux/lglock.h
- --- linux-4.4.28.orig/include/linux/lglock.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/lglock.h 2016-11-01 21:26:58.732339449 +0100
- @@ -34,13 +34,30 @@
- #endif
-
- struct lglock {
- +#ifdef CONFIG_PREEMPT_RT_FULL
- + struct rt_mutex __percpu *lock;
- +#else
- arch_spinlock_t __percpu *lock;
- +#endif
- #ifdef CONFIG_DEBUG_LOCK_ALLOC
- struct lock_class_key lock_key;
- struct lockdep_map lock_dep_map;
- #endif
- };
-
- +#ifdef CONFIG_PREEMPT_RT_FULL
- +# define DEFINE_LGLOCK(name) \
- + static DEFINE_PER_CPU(struct rt_mutex, name ## _lock) \
- + = __RT_MUTEX_INITIALIZER( name ## _lock); \
- + struct lglock name = { .lock = &name ## _lock }
- +
- +# define DEFINE_STATIC_LGLOCK(name) \
- + static DEFINE_PER_CPU(struct rt_mutex, name ## _lock) \
- + = __RT_MUTEX_INITIALIZER( name ## _lock); \
- + static struct lglock name = { .lock = &name ## _lock }
- +
- +#else
- +
- #define DEFINE_LGLOCK(name) \
- static DEFINE_PER_CPU(arch_spinlock_t, name ## _lock) \
- = __ARCH_SPIN_LOCK_UNLOCKED; \
- @@ -50,6 +67,7 @@
- static DEFINE_PER_CPU(arch_spinlock_t, name ## _lock) \
- = __ARCH_SPIN_LOCK_UNLOCKED; \
- static struct lglock name = { .lock = &name ## _lock }
- +#endif
-
- void lg_lock_init(struct lglock *lg, char *name);
-
- @@ -64,6 +82,12 @@
- void lg_global_lock(struct lglock *lg);
- void lg_global_unlock(struct lglock *lg);
-
- +#ifndef CONFIG_PREEMPT_RT_FULL
- +#define lg_global_trylock_relax(name) lg_global_lock(name)
- +#else
- +void lg_global_trylock_relax(struct lglock *lg);
- +#endif
- +
- #else
- /* When !CONFIG_SMP, map lglock to spinlock */
- #define lglock spinlock
- diff -Nur linux-4.4.28.orig/include/linux/list_bl.h linux-4.4.28/include/linux/list_bl.h
- --- linux-4.4.28.orig/include/linux/list_bl.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/list_bl.h 2016-11-01 21:26:58.732339449 +0100
- @@ -2,6 +2,7 @@
- #define _LINUX_LIST_BL_H
-
- #include <linux/list.h>
- +#include <linux/spinlock.h>
- #include <linux/bit_spinlock.h>
-
- /*
- @@ -32,13 +33,24 @@
-
- struct hlist_bl_head {
- struct hlist_bl_node *first;
- +#ifdef CONFIG_PREEMPT_RT_BASE
- + raw_spinlock_t lock;
- +#endif
- };
-
- struct hlist_bl_node {
- struct hlist_bl_node *next, **pprev;
- };
- -#define INIT_HLIST_BL_HEAD(ptr) \
- - ((ptr)->first = NULL)
- +
- +#ifdef CONFIG_PREEMPT_RT_BASE
- +#define INIT_HLIST_BL_HEAD(h) \
- +do { \
- + (h)->first = NULL; \
- + raw_spin_lock_init(&(h)->lock); \
- +} while (0)
- +#else
- +#define INIT_HLIST_BL_HEAD(h) (h)->first = NULL
- +#endif
-
- static inline void INIT_HLIST_BL_NODE(struct hlist_bl_node *h)
- {
- @@ -118,12 +130,26 @@
-
- static inline void hlist_bl_lock(struct hlist_bl_head *b)
- {
- +#ifndef CONFIG_PREEMPT_RT_BASE
- bit_spin_lock(0, (unsigned long *)b);
- +#else
- + raw_spin_lock(&b->lock);
- +#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK)
- + __set_bit(0, (unsigned long *)b);
- +#endif
- +#endif
- }
-
- static inline void hlist_bl_unlock(struct hlist_bl_head *b)
- {
- +#ifndef CONFIG_PREEMPT_RT_BASE
- __bit_spin_unlock(0, (unsigned long *)b);
- +#else
- +#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK)
- + __clear_bit(0, (unsigned long *)b);
- +#endif
- + raw_spin_unlock(&b->lock);
- +#endif
- }
-
- static inline bool hlist_bl_is_locked(struct hlist_bl_head *b)
- diff -Nur linux-4.4.28.orig/include/linux/locallock.h linux-4.4.28/include/linux/locallock.h
- --- linux-4.4.28.orig/include/linux/locallock.h 1970-01-01 01:00:00.000000000 +0100
- +++ linux-4.4.28/include/linux/locallock.h 2016-11-01 21:26:58.732339449 +0100
- @@ -0,0 +1,276 @@
- +#ifndef _LINUX_LOCALLOCK_H
- +#define _LINUX_LOCALLOCK_H
- +
- +#include <linux/percpu.h>
- +#include <linux/spinlock.h>
- +
- +#ifdef CONFIG_PREEMPT_RT_BASE
- +
- +#ifdef CONFIG_DEBUG_SPINLOCK
- +# define LL_WARN(cond) WARN_ON(cond)
- +#else
- +# define LL_WARN(cond) do { } while (0)
- +#endif
- +
- +/*
- + * per cpu lock based substitute for local_irq_*()
- + */
- +struct local_irq_lock {
- + spinlock_t lock;
- + struct task_struct *owner;
- + int nestcnt;
- + unsigned long flags;
- +};
- +
- +#define DEFINE_LOCAL_IRQ_LOCK(lvar) \
- + DEFINE_PER_CPU(struct local_irq_lock, lvar) = { \
- + .lock = __SPIN_LOCK_UNLOCKED((lvar).lock) }
- +
- +#define DECLARE_LOCAL_IRQ_LOCK(lvar) \
- + DECLARE_PER_CPU(struct local_irq_lock, lvar)
- +
- +#define local_irq_lock_init(lvar) \
- + do { \
- + int __cpu; \
- + for_each_possible_cpu(__cpu) \
- + spin_lock_init(&per_cpu(lvar, __cpu).lock); \
- + } while (0)
- +
- +/*
- + * spin_lock|trylock|unlock_local flavour that does not migrate disable
- + * used for __local_lock|trylock|unlock where get_local_var/put_local_var
- + * already takes care of the migrate_disable/enable
- + * for CONFIG_PREEMPT_BASE map to the normal spin_* calls.
- + */
- +#ifdef CONFIG_PREEMPT_RT_FULL
- +# define spin_lock_local(lock) rt_spin_lock__no_mg(lock)
- +# define spin_trylock_local(lock) rt_spin_trylock__no_mg(lock)
- +# define spin_unlock_local(lock) rt_spin_unlock__no_mg(lock)
- +#else
- +# define spin_lock_local(lock) spin_lock(lock)
- +# define spin_trylock_local(lock) spin_trylock(lock)
- +# define spin_unlock_local(lock) spin_unlock(lock)
- +#endif
- +
- +static inline void __local_lock(struct local_irq_lock *lv)
- +{
- + if (lv->owner != current) {
- + spin_lock_local(&lv->lock);
- + LL_WARN(lv->owner);
- + LL_WARN(lv->nestcnt);
- + lv->owner = current;
- + }
- + lv->nestcnt++;
- +}
- +
- +#define local_lock(lvar) \
- + do { __local_lock(&get_local_var(lvar)); } while (0)
- +
- +#define local_lock_on(lvar, cpu) \
- + do { __local_lock(&per_cpu(lvar, cpu)); } while (0)
- +
- +static inline int __local_trylock(struct local_irq_lock *lv)
- +{
- + if (lv->owner != current && spin_trylock_local(&lv->lock)) {
- + LL_WARN(lv->owner);
- + LL_WARN(lv->nestcnt);
- + lv->owner = current;
- + lv->nestcnt = 1;
- + return 1;
- + }
- + return 0;
- +}
- +
- +#define local_trylock(lvar) \
- + ({ \
- + int __locked; \
- + __locked = __local_trylock(&get_local_var(lvar)); \
- + if (!__locked) \
- + put_local_var(lvar); \
- + __locked; \
- + })
- +
- +static inline void __local_unlock(struct local_irq_lock *lv)
- +{
- + LL_WARN(lv->nestcnt == 0);
- + LL_WARN(lv->owner != current);
- + if (--lv->nestcnt)
- + return;
- +
- + lv->owner = NULL;
- + spin_unlock_local(&lv->lock);
- +}
- +
- +#define local_unlock(lvar) \
- + do { \
- + __local_unlock(this_cpu_ptr(&lvar)); \
- + put_local_var(lvar); \
- + } while (0)
- +
- +#define local_unlock_on(lvar, cpu) \
- + do { __local_unlock(&per_cpu(lvar, cpu)); } while (0)
- +
- +static inline void __local_lock_irq(struct local_irq_lock *lv)
- +{
- + spin_lock_irqsave(&lv->lock, lv->flags);
- + LL_WARN(lv->owner);
- + LL_WARN(lv->nestcnt);
- + lv->owner = current;
- + lv->nestcnt = 1;
- +}
- +
- +#define local_lock_irq(lvar) \
- + do { __local_lock_irq(&get_local_var(lvar)); } while (0)
- +
- +#define local_lock_irq_on(lvar, cpu) \
- + do { __local_lock_irq(&per_cpu(lvar, cpu)); } while (0)
- +
- +static inline void __local_unlock_irq(struct local_irq_lock *lv)
- +{
- + LL_WARN(!lv->nestcnt);
- + LL_WARN(lv->owner != current);
- + lv->owner = NULL;
- + lv->nestcnt = 0;
- + spin_unlock_irq(&lv->lock);
- +}
- +
- +#define local_unlock_irq(lvar) \
- + do { \
- + __local_unlock_irq(this_cpu_ptr(&lvar)); \
- + put_local_var(lvar); \
- + } while (0)
- +
- +#define local_unlock_irq_on(lvar, cpu) \
- + do { \
- + __local_unlock_irq(&per_cpu(lvar, cpu)); \
- + } while (0)
- +
- +static inline int __local_lock_irqsave(struct local_irq_lock *lv)
- +{
- + if (lv->owner != current) {
- + __local_lock_irq(lv);
- + return 0;
- + } else {
- + lv->nestcnt++;
- + return 1;
- + }
- +}
- +
- +#define local_lock_irqsave(lvar, _flags) \
- + do { \
- + if (__local_lock_irqsave(&get_local_var(lvar))) \
- + put_local_var(lvar); \
- + _flags = __this_cpu_read(lvar.flags); \
- + } while (0)
- +
- +#define local_lock_irqsave_on(lvar, _flags, cpu) \
- + do { \
- + __local_lock_irqsave(&per_cpu(lvar, cpu)); \
- + _flags = per_cpu(lvar, cpu).flags; \
- + } while (0)
- +
- +static inline int __local_unlock_irqrestore(struct local_irq_lock *lv,
- + unsigned long flags)
- +{
- + LL_WARN(!lv->nestcnt);
- + LL_WARN(lv->owner != current);
- + if (--lv->nestcnt)
- + return 0;
- +
- + lv->owner = NULL;
- + spin_unlock_irqrestore(&lv->lock, lv->flags);
- + return 1;
- +}
- +
- +#define local_unlock_irqrestore(lvar, flags) \
- + do { \
- + if (__local_unlock_irqrestore(this_cpu_ptr(&lvar), flags)) \
- + put_local_var(lvar); \
- + } while (0)
- +
- +#define local_unlock_irqrestore_on(lvar, flags, cpu) \
- + do { \
- + __local_unlock_irqrestore(&per_cpu(lvar, cpu), flags); \
- + } while (0)
- +
- +#define local_spin_trylock_irq(lvar, lock) \
- + ({ \
- + int __locked; \
- + local_lock_irq(lvar); \
- + __locked = spin_trylock(lock); \
- + if (!__locked) \
- + local_unlock_irq(lvar); \
- + __locked; \
- + })
- +
- +#define local_spin_lock_irq(lvar, lock) \
- + do { \
- + local_lock_irq(lvar); \
- + spin_lock(lock); \
- + } while (0)
- +
- +#define local_spin_unlock_irq(lvar, lock) \
- + do { \
- + spin_unlock(lock); \
- + local_unlock_irq(lvar); \
- + } while (0)
- +
- +#define local_spin_lock_irqsave(lvar, lock, flags) \
- + do { \
- + local_lock_irqsave(lvar, flags); \
- + spin_lock(lock); \
- + } while (0)
- +
- +#define local_spin_unlock_irqrestore(lvar, lock, flags) \
- + do { \
- + spin_unlock(lock); \
- + local_unlock_irqrestore(lvar, flags); \
- + } while (0)
- +
- +#define get_locked_var(lvar, var) \
- + (*({ \
- + local_lock(lvar); \
- + this_cpu_ptr(&var); \
- + }))
- +
- +#define put_locked_var(lvar, var) local_unlock(lvar);
- +
- +#define local_lock_cpu(lvar) \
- + ({ \
- + local_lock(lvar); \
- + smp_processor_id(); \
- + })
- +
- +#define local_unlock_cpu(lvar) local_unlock(lvar)
- +
- +#else /* PREEMPT_RT_BASE */
- +
- +#define DEFINE_LOCAL_IRQ_LOCK(lvar) __typeof__(const int) lvar
- +#define DECLARE_LOCAL_IRQ_LOCK(lvar) extern __typeof__(const int) lvar
- +
- +static inline void local_irq_lock_init(int lvar) { }
- +
- +#define local_lock(lvar) preempt_disable()
- +#define local_unlock(lvar) preempt_enable()
- +#define local_lock_irq(lvar) local_irq_disable()
- +#define local_unlock_irq(lvar) local_irq_enable()
- +#define local_lock_irqsave(lvar, flags) local_irq_save(flags)
- +#define local_unlock_irqrestore(lvar, flags) local_irq_restore(flags)
- +
- +#define local_spin_trylock_irq(lvar, lock) spin_trylock_irq(lock)
- +#define local_spin_lock_irq(lvar, lock) spin_lock_irq(lock)
- +#define local_spin_unlock_irq(lvar, lock) spin_unlock_irq(lock)
- +#define local_spin_lock_irqsave(lvar, lock, flags) \
- + spin_lock_irqsave(lock, flags)
- +#define local_spin_unlock_irqrestore(lvar, lock, flags) \
- + spin_unlock_irqrestore(lock, flags)
- +
- +#define get_locked_var(lvar, var) get_cpu_var(var)
- +#define put_locked_var(lvar, var) put_cpu_var(var)
- +
- +#define local_lock_cpu(lvar) get_cpu()
- +#define local_unlock_cpu(lvar) put_cpu()
- +
- +#endif
- +
- +#endif
- diff -Nur linux-4.4.28.orig/include/linux/mm_types.h linux-4.4.28/include/linux/mm_types.h
- --- linux-4.4.28.orig/include/linux/mm_types.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/mm_types.h 2016-11-01 21:26:58.732339449 +0100
- @@ -11,6 +11,7 @@
- #include <linux/completion.h>
- #include <linux/cpumask.h>
- #include <linux/uprobes.h>
- +#include <linux/rcupdate.h>
- #include <linux/page-flags-layout.h>
- #include <asm/page.h>
- #include <asm/mmu.h>
- @@ -504,6 +505,9 @@
- bool tlb_flush_pending;
- #endif
- struct uprobes_state uprobes_state;
- +#ifdef CONFIG_PREEMPT_RT_BASE
- + struct rcu_head delayed_drop;
- +#endif
- #ifdef CONFIG_X86_INTEL_MPX
- /* address of the bounds directory */
- void __user *bd_addr;
- diff -Nur linux-4.4.28.orig/include/linux/mutex.h linux-4.4.28/include/linux/mutex.h
- --- linux-4.4.28.orig/include/linux/mutex.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/mutex.h 2016-11-01 21:26:58.732339449 +0100
- @@ -19,6 +19,17 @@
- #include <asm/processor.h>
- #include <linux/osq_lock.h>
-
- +#ifdef CONFIG_DEBUG_LOCK_ALLOC
- +# define __DEP_MAP_MUTEX_INITIALIZER(lockname) \
- + , .dep_map = { .name = #lockname }
- +#else
- +# define __DEP_MAP_MUTEX_INITIALIZER(lockname)
- +#endif
- +
- +#ifdef CONFIG_PREEMPT_RT_FULL
- +# include <linux/mutex_rt.h>
- +#else
- +
- /*
- * Simple, straightforward mutexes with strict semantics:
- *
- @@ -99,13 +110,6 @@
- static inline void mutex_destroy(struct mutex *lock) {}
- #endif
-
- -#ifdef CONFIG_DEBUG_LOCK_ALLOC
- -# define __DEP_MAP_MUTEX_INITIALIZER(lockname) \
- - , .dep_map = { .name = #lockname }
- -#else
- -# define __DEP_MAP_MUTEX_INITIALIZER(lockname)
- -#endif
- -
- #define __MUTEX_INITIALIZER(lockname) \
- { .count = ATOMIC_INIT(1) \
- , .wait_lock = __SPIN_LOCK_UNLOCKED(lockname.wait_lock) \
- @@ -173,6 +177,8 @@
- extern int mutex_trylock(struct mutex *lock);
- extern void mutex_unlock(struct mutex *lock);
-
- +#endif /* !PREEMPT_RT_FULL */
- +
- extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock);
-
- #endif /* __LINUX_MUTEX_H */
- diff -Nur linux-4.4.28.orig/include/linux/mutex_rt.h linux-4.4.28/include/linux/mutex_rt.h
- --- linux-4.4.28.orig/include/linux/mutex_rt.h 1970-01-01 01:00:00.000000000 +0100
- +++ linux-4.4.28/include/linux/mutex_rt.h 2016-11-01 21:26:58.732339449 +0100
- @@ -0,0 +1,84 @@
- +#ifndef __LINUX_MUTEX_RT_H
- +#define __LINUX_MUTEX_RT_H
- +
- +#ifndef __LINUX_MUTEX_H
- +#error "Please include mutex.h"
- +#endif
- +
- +#include <linux/rtmutex.h>
- +
- +/* FIXME: Just for __lockfunc */
- +#include <linux/spinlock.h>
- +
- +struct mutex {
- + struct rt_mutex lock;
- +#ifdef CONFIG_DEBUG_LOCK_ALLOC
- + struct lockdep_map dep_map;
- +#endif
- +};
- +
- +#define __MUTEX_INITIALIZER(mutexname) \
- + { \
- + .lock = __RT_MUTEX_INITIALIZER(mutexname.lock) \
- + __DEP_MAP_MUTEX_INITIALIZER(mutexname) \
- + }
- +
- +#define DEFINE_MUTEX(mutexname) \
- + struct mutex mutexname = __MUTEX_INITIALIZER(mutexname)
- +
- +extern void __mutex_do_init(struct mutex *lock, const char *name, struct lock_class_key *key);
- +extern void __lockfunc _mutex_lock(struct mutex *lock);
- +extern int __lockfunc _mutex_lock_interruptible(struct mutex *lock);
- +extern int __lockfunc _mutex_lock_killable(struct mutex *lock);
- +extern void __lockfunc _mutex_lock_nested(struct mutex *lock, int subclass);
- +extern void __lockfunc _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest_lock);
- +extern int __lockfunc _mutex_lock_interruptible_nested(struct mutex *lock, int subclass);
- +extern int __lockfunc _mutex_lock_killable_nested(struct mutex *lock, int subclass);
- +extern int __lockfunc _mutex_trylock(struct mutex *lock);
- +extern void __lockfunc _mutex_unlock(struct mutex *lock);
- +
- +#define mutex_is_locked(l) rt_mutex_is_locked(&(l)->lock)
- +#define mutex_lock(l) _mutex_lock(l)
- +#define mutex_lock_interruptible(l) _mutex_lock_interruptible(l)
- +#define mutex_lock_killable(l) _mutex_lock_killable(l)
- +#define mutex_trylock(l) _mutex_trylock(l)
- +#define mutex_unlock(l) _mutex_unlock(l)
- +#define mutex_destroy(l) rt_mutex_destroy(&(l)->lock)
- +
- +#ifdef CONFIG_DEBUG_LOCK_ALLOC
- +# define mutex_lock_nested(l, s) _mutex_lock_nested(l, s)
- +# define mutex_lock_interruptible_nested(l, s) \
- + _mutex_lock_interruptible_nested(l, s)
- +# define mutex_lock_killable_nested(l, s) \
- + _mutex_lock_killable_nested(l, s)
- +
- +# define mutex_lock_nest_lock(lock, nest_lock) \
- +do { \
- + typecheck(struct lockdep_map *, &(nest_lock)->dep_map); \
- + _mutex_lock_nest_lock(lock, &(nest_lock)->dep_map); \
- +} while (0)
- +
- +#else
- +# define mutex_lock_nested(l, s) _mutex_lock(l)
- +# define mutex_lock_interruptible_nested(l, s) \
- + _mutex_lock_interruptible(l)
- +# define mutex_lock_killable_nested(l, s) \
- + _mutex_lock_killable(l)
- +# define mutex_lock_nest_lock(lock, nest_lock) mutex_lock(lock)
- +#endif
- +
- +# define mutex_init(mutex) \
- +do { \
- + static struct lock_class_key __key; \
- + \
- + rt_mutex_init(&(mutex)->lock); \
- + __mutex_do_init((mutex), #mutex, &__key); \
- +} while (0)
- +
- +# define __mutex_init(mutex, name, key) \
- +do { \
- + rt_mutex_init(&(mutex)->lock); \
- + __mutex_do_init((mutex), name, key); \
- +} while (0)
- +
- +#endif
- diff -Nur linux-4.4.28.orig/include/linux/netdevice.h linux-4.4.28/include/linux/netdevice.h
- --- linux-4.4.28.orig/include/linux/netdevice.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/netdevice.h 2016-11-01 21:26:58.736339702 +0100
- @@ -2248,11 +2248,20 @@
- void synchronize_net(void);
- int init_dummy_netdev(struct net_device *dev);
-
- +#ifdef CONFIG_PREEMPT_RT_FULL
- +static inline int dev_recursion_level(void)
- +{
- + return current->xmit_recursion;
- +}
- +
- +#else
- +
- DECLARE_PER_CPU(int, xmit_recursion);
- static inline int dev_recursion_level(void)
- {
- return this_cpu_read(xmit_recursion);
- }
- +#endif
-
- struct net_device *dev_get_by_index(struct net *net, int ifindex);
- struct net_device *__dev_get_by_index(struct net *net, int ifindex);
- @@ -2563,6 +2572,7 @@
- unsigned int dropped;
- struct sk_buff_head input_pkt_queue;
- struct napi_struct backlog;
- + struct sk_buff_head tofree_queue;
-
- };
-
- diff -Nur linux-4.4.28.orig/include/linux/netfilter/x_tables.h linux-4.4.28/include/linux/netfilter/x_tables.h
- --- linux-4.4.28.orig/include/linux/netfilter/x_tables.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/netfilter/x_tables.h 2016-11-01 21:26:58.736339702 +0100
- @@ -4,6 +4,7 @@
-
- #include <linux/netdevice.h>
- #include <linux/static_key.h>
- +#include <linux/locallock.h>
- #include <uapi/linux/netfilter/x_tables.h>
-
- /**
- @@ -289,6 +290,8 @@
- */
- DECLARE_PER_CPU(seqcount_t, xt_recseq);
-
- +DECLARE_LOCAL_IRQ_LOCK(xt_write_lock);
- +
- /* xt_tee_enabled - true if x_tables needs to handle reentrancy
- *
- * Enabled if current ip(6)tables ruleset has at least one -j TEE rule.
- @@ -309,6 +312,9 @@
- {
- unsigned int addend;
-
- + /* RT protection */
- + local_lock(xt_write_lock);
- +
- /*
- * Low order bit of sequence is set if we already
- * called xt_write_recseq_begin().
- @@ -339,6 +345,7 @@
- /* this is kind of a write_seqcount_end(), but addend is 0 or 1 */
- smp_wmb();
- __this_cpu_add(xt_recseq.sequence, addend);
- + local_unlock(xt_write_lock);
- }
-
- /*
- diff -Nur linux-4.4.28.orig/include/linux/notifier.h linux-4.4.28/include/linux/notifier.h
- --- linux-4.4.28.orig/include/linux/notifier.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/notifier.h 2016-11-01 21:26:58.736339702 +0100
- @@ -6,7 +6,7 @@
- *
- * Alan Cox <Alan.Cox@linux.org>
- */
- -
- +
- #ifndef _LINUX_NOTIFIER_H
- #define _LINUX_NOTIFIER_H
- #include <linux/errno.h>
- @@ -42,9 +42,7 @@
- * in srcu_notifier_call_chain(): no cache bounces and no memory barriers.
- * As compensation, srcu_notifier_chain_unregister() is rather expensive.
- * SRCU notifier chains should be used when the chain will be called very
- - * often but notifier_blocks will seldom be removed. Also, SRCU notifier
- - * chains are slightly more difficult to use because they require special
- - * runtime initialization.
- + * often but notifier_blocks will seldom be removed.
- */
-
- typedef int (*notifier_fn_t)(struct notifier_block *nb,
- @@ -88,7 +86,7 @@
- (name)->head = NULL; \
- } while (0)
-
- -/* srcu_notifier_heads must be initialized and cleaned up dynamically */
- +/* srcu_notifier_heads must be cleaned up dynamically */
- extern void srcu_init_notifier_head(struct srcu_notifier_head *nh);
- #define srcu_cleanup_notifier_head(name) \
- cleanup_srcu_struct(&(name)->srcu);
- @@ -101,7 +99,13 @@
- .head = NULL }
- #define RAW_NOTIFIER_INIT(name) { \
- .head = NULL }
- -/* srcu_notifier_heads cannot be initialized statically */
- +
- +#define SRCU_NOTIFIER_INIT(name, pcpu) \
- + { \
- + .mutex = __MUTEX_INITIALIZER(name.mutex), \
- + .head = NULL, \
- + .srcu = __SRCU_STRUCT_INIT(name.srcu, pcpu), \
- + }
-
- #define ATOMIC_NOTIFIER_HEAD(name) \
- struct atomic_notifier_head name = \
- @@ -113,6 +117,18 @@
- struct raw_notifier_head name = \
- RAW_NOTIFIER_INIT(name)
-
- +#define _SRCU_NOTIFIER_HEAD(name, mod) \
- + static DEFINE_PER_CPU(struct srcu_struct_array, \
- + name##_head_srcu_array); \
- + mod struct srcu_notifier_head name = \
- + SRCU_NOTIFIER_INIT(name, name##_head_srcu_array)
- +
- +#define SRCU_NOTIFIER_HEAD(name) \
- + _SRCU_NOTIFIER_HEAD(name, )
- +
- +#define SRCU_NOTIFIER_HEAD_STATIC(name) \
- + _SRCU_NOTIFIER_HEAD(name, static)
- +
- #ifdef __KERNEL__
-
- extern int atomic_notifier_chain_register(struct atomic_notifier_head *nh,
- @@ -182,12 +198,12 @@
-
- /*
- * Declared notifiers so far. I can imagine quite a few more chains
- - * over time (eg laptop power reset chains, reboot chain (to clean
- + * over time (eg laptop power reset chains, reboot chain (to clean
- * device units up), device [un]mount chain, module load/unload chain,
- - * low memory chain, screenblank chain (for plug in modular screenblankers)
- + * low memory chain, screenblank chain (for plug in modular screenblankers)
- * VC switch chains (for loadable kernel svgalib VC switch helpers) etc...
- */
- -
- +
- /* CPU notfiers are defined in include/linux/cpu.h. */
-
- /* netdevice notifiers are defined in include/linux/netdevice.h */
- diff -Nur linux-4.4.28.orig/include/linux/percpu.h linux-4.4.28/include/linux/percpu.h
- --- linux-4.4.28.orig/include/linux/percpu.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/percpu.h 2016-11-01 21:26:58.736339702 +0100
- @@ -24,6 +24,35 @@
- PERCPU_MODULE_RESERVE)
- #endif
-
- +#ifdef CONFIG_PREEMPT_RT_FULL
- +
- +#define get_local_var(var) (*({ \
- + migrate_disable(); \
- + this_cpu_ptr(&var); }))
- +
- +#define put_local_var(var) do { \
- + (void)&(var); \
- + migrate_enable(); \
- +} while (0)
- +
- +# define get_local_ptr(var) ({ \
- + migrate_disable(); \
- + this_cpu_ptr(var); })
- +
- +# define put_local_ptr(var) do { \
- + (void)(var); \
- + migrate_enable(); \
- +} while (0)
- +
- +#else
- +
- +#define get_local_var(var) get_cpu_var(var)
- +#define put_local_var(var) put_cpu_var(var)
- +#define get_local_ptr(var) get_cpu_ptr(var)
- +#define put_local_ptr(var) put_cpu_ptr(var)
- +
- +#endif
- +
- /* minimum unit size, also is the maximum supported allocation size */
- #define PCPU_MIN_UNIT_SIZE PFN_ALIGN(32 << 10)
-
- diff -Nur linux-4.4.28.orig/include/linux/pid.h linux-4.4.28/include/linux/pid.h
- --- linux-4.4.28.orig/include/linux/pid.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/pid.h 2016-11-01 21:26:58.736339702 +0100
- @@ -2,6 +2,7 @@
- #define _LINUX_PID_H
-
- #include <linux/rcupdate.h>
- +#include <linux/atomic.h>
-
- enum pid_type
- {
- diff -Nur linux-4.4.28.orig/include/linux/preempt.h linux-4.4.28/include/linux/preempt.h
- --- linux-4.4.28.orig/include/linux/preempt.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/preempt.h 2016-11-01 21:26:58.736339702 +0100
- @@ -50,7 +50,11 @@
- #define HARDIRQ_OFFSET (1UL << HARDIRQ_SHIFT)
- #define NMI_OFFSET (1UL << NMI_SHIFT)
-
- -#define SOFTIRQ_DISABLE_OFFSET (2 * SOFTIRQ_OFFSET)
- +#ifndef CONFIG_PREEMPT_RT_FULL
- +# define SOFTIRQ_DISABLE_OFFSET (2 * SOFTIRQ_OFFSET)
- +#else
- +# define SOFTIRQ_DISABLE_OFFSET (0)
- +#endif
-
- /* We use the MSB mostly because its available */
- #define PREEMPT_NEED_RESCHED 0x80000000
- @@ -59,9 +63,15 @@
- #include <asm/preempt.h>
-
- #define hardirq_count() (preempt_count() & HARDIRQ_MASK)
- -#define softirq_count() (preempt_count() & SOFTIRQ_MASK)
- #define irq_count() (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_MASK \
- | NMI_MASK))
- +#ifndef CONFIG_PREEMPT_RT_FULL
- +# define softirq_count() (preempt_count() & SOFTIRQ_MASK)
- +# define in_serving_softirq() (softirq_count() & SOFTIRQ_OFFSET)
- +#else
- +# define softirq_count() (0UL)
- +extern int in_serving_softirq(void);
- +#endif
-
- /*
- * Are we doing bottom half or hardware interrupt processing?
- @@ -72,7 +82,6 @@
- #define in_irq() (hardirq_count())
- #define in_softirq() (softirq_count())
- #define in_interrupt() (irq_count())
- -#define in_serving_softirq() (softirq_count() & SOFTIRQ_OFFSET)
-
- /*
- * Are we in NMI context?
- @@ -91,7 +100,11 @@
- /*
- * The preempt_count offset after spin_lock()
- */
- +#if !defined(CONFIG_PREEMPT_RT_FULL)
- #define PREEMPT_LOCK_OFFSET PREEMPT_DISABLE_OFFSET
- +#else
- +#define PREEMPT_LOCK_OFFSET 0
- +#endif
-
- /*
- * The preempt_count offset needed for things like:
- @@ -140,6 +153,20 @@
- #define preempt_count_inc() preempt_count_add(1)
- #define preempt_count_dec() preempt_count_sub(1)
-
- +#ifdef CONFIG_PREEMPT_LAZY
- +#define add_preempt_lazy_count(val) do { preempt_lazy_count() += (val); } while (0)
- +#define sub_preempt_lazy_count(val) do { preempt_lazy_count() -= (val); } while (0)
- +#define inc_preempt_lazy_count() add_preempt_lazy_count(1)
- +#define dec_preempt_lazy_count() sub_preempt_lazy_count(1)
- +#define preempt_lazy_count() (current_thread_info()->preempt_lazy_count)
- +#else
- +#define add_preempt_lazy_count(val) do { } while (0)
- +#define sub_preempt_lazy_count(val) do { } while (0)
- +#define inc_preempt_lazy_count() do { } while (0)
- +#define dec_preempt_lazy_count() do { } while (0)
- +#define preempt_lazy_count() (0)
- +#endif
- +
- #ifdef CONFIG_PREEMPT_COUNT
-
- #define preempt_disable() \
- @@ -148,13 +175,25 @@
- barrier(); \
- } while (0)
-
- +#define preempt_lazy_disable() \
- +do { \
- + inc_preempt_lazy_count(); \
- + barrier(); \
- +} while (0)
- +
- #define sched_preempt_enable_no_resched() \
- do { \
- barrier(); \
- preempt_count_dec(); \
- } while (0)
-
- -#define preempt_enable_no_resched() sched_preempt_enable_no_resched()
- +#ifdef CONFIG_PREEMPT_RT_BASE
- +# define preempt_enable_no_resched() sched_preempt_enable_no_resched()
- +# define preempt_check_resched_rt() preempt_check_resched()
- +#else
- +# define preempt_enable_no_resched() preempt_enable()
- +# define preempt_check_resched_rt() barrier();
- +#endif
-
- #define preemptible() (preempt_count() == 0 && !irqs_disabled())
-
- @@ -179,6 +218,13 @@
- __preempt_schedule(); \
- } while (0)
-
- +#define preempt_lazy_enable() \
- +do { \
- + dec_preempt_lazy_count(); \
- + barrier(); \
- + preempt_check_resched(); \
- +} while (0)
- +
- #else /* !CONFIG_PREEMPT */
- #define preempt_enable() \
- do { \
- @@ -224,6 +270,7 @@
- #define preempt_disable_notrace() barrier()
- #define preempt_enable_no_resched_notrace() barrier()
- #define preempt_enable_notrace() barrier()
- +#define preempt_check_resched_rt() barrier()
- #define preemptible() 0
-
- #endif /* CONFIG_PREEMPT_COUNT */
- @@ -244,10 +291,31 @@
- } while (0)
- #define preempt_fold_need_resched() \
- do { \
- - if (tif_need_resched()) \
- + if (tif_need_resched_now()) \
- set_preempt_need_resched(); \
- } while (0)
-
- +#ifdef CONFIG_PREEMPT_RT_FULL
- +# define preempt_disable_rt() preempt_disable()
- +# define preempt_enable_rt() preempt_enable()
- +# define preempt_disable_nort() barrier()
- +# define preempt_enable_nort() barrier()
- +# ifdef CONFIG_SMP
- + extern void migrate_disable(void);
- + extern void migrate_enable(void);
- +# else /* CONFIG_SMP */
- +# define migrate_disable() barrier()
- +# define migrate_enable() barrier()
- +# endif /* CONFIG_SMP */
- +#else
- +# define preempt_disable_rt() barrier()
- +# define preempt_enable_rt() barrier()
- +# define preempt_disable_nort() preempt_disable()
- +# define preempt_enable_nort() preempt_enable()
- +# define migrate_disable() preempt_disable()
- +# define migrate_enable() preempt_enable()
- +#endif
- +
- #ifdef CONFIG_PREEMPT_NOTIFIERS
-
- struct preempt_notifier;
- diff -Nur linux-4.4.28.orig/include/linux/printk.h linux-4.4.28/include/linux/printk.h
- --- linux-4.4.28.orig/include/linux/printk.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/printk.h 2016-11-01 21:26:58.736339702 +0100
- @@ -117,9 +117,11 @@
- #ifdef CONFIG_EARLY_PRINTK
- extern asmlinkage __printf(1, 2)
- void early_printk(const char *fmt, ...);
- +extern void printk_kill(void);
- #else
- static inline __printf(1, 2) __cold
- void early_printk(const char *s, ...) { }
- +static inline void printk_kill(void) { }
- #endif
-
- typedef __printf(1, 0) int (*printk_func_t)(const char *fmt, va_list args);
- diff -Nur linux-4.4.28.orig/include/linux/radix-tree.h linux-4.4.28/include/linux/radix-tree.h
- --- linux-4.4.28.orig/include/linux/radix-tree.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/radix-tree.h 2016-11-01 21:26:58.736339702 +0100
- @@ -277,8 +277,13 @@
- unsigned int radix_tree_gang_lookup_slot(struct radix_tree_root *root,
- void ***results, unsigned long *indices,
- unsigned long first_index, unsigned int max_items);
- +#ifndef CONFIG_PREEMPT_RT_FULL
- int radix_tree_preload(gfp_t gfp_mask);
- int radix_tree_maybe_preload(gfp_t gfp_mask);
- +#else
- +static inline int radix_tree_preload(gfp_t gm) { return 0; }
- +static inline int radix_tree_maybe_preload(gfp_t gfp_mask) { return 0; }
- +#endif
- void radix_tree_init(void);
- void *radix_tree_tag_set(struct radix_tree_root *root,
- unsigned long index, unsigned int tag);
- @@ -303,7 +308,7 @@
-
- static inline void radix_tree_preload_end(void)
- {
- - preempt_enable();
- + preempt_enable_nort();
- }
-
- /**
- diff -Nur linux-4.4.28.orig/include/linux/random.h linux-4.4.28/include/linux/random.h
- --- linux-4.4.28.orig/include/linux/random.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/random.h 2016-11-01 21:26:58.736339702 +0100
- @@ -20,7 +20,7 @@
- extern void add_device_randomness(const void *, unsigned int);
- extern void add_input_randomness(unsigned int type, unsigned int code,
- unsigned int value);
- -extern void add_interrupt_randomness(int irq, int irq_flags);
- +extern void add_interrupt_randomness(int irq, int irq_flags, __u64 ip);
-
- extern void get_random_bytes(void *buf, int nbytes);
- extern int add_random_ready_callback(struct random_ready_callback *rdy);
- diff -Nur linux-4.4.28.orig/include/linux/rbtree.h linux-4.4.28/include/linux/rbtree.h
- --- linux-4.4.28.orig/include/linux/rbtree.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/rbtree.h 2016-11-01 21:26:58.736339702 +0100
- @@ -31,7 +31,6 @@
-
- #include <linux/kernel.h>
- #include <linux/stddef.h>
- -#include <linux/rcupdate.h>
-
- struct rb_node {
- unsigned long __rb_parent_color;
- @@ -86,14 +85,8 @@
- *rb_link = node;
- }
-
- -static inline void rb_link_node_rcu(struct rb_node *node, struct rb_node *parent,
- - struct rb_node **rb_link)
- -{
- - node->__rb_parent_color = (unsigned long)parent;
- - node->rb_left = node->rb_right = NULL;
- -
- - rcu_assign_pointer(*rb_link, node);
- -}
- +void rb_link_node_rcu(struct rb_node *node, struct rb_node *parent,
- + struct rb_node **rb_link);
-
- #define rb_entry_safe(ptr, type, member) \
- ({ typeof(ptr) ____ptr = (ptr); \
- diff -Nur linux-4.4.28.orig/include/linux/rcupdate.h linux-4.4.28/include/linux/rcupdate.h
- --- linux-4.4.28.orig/include/linux/rcupdate.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/rcupdate.h 2016-11-01 21:26:58.740339958 +0100
- @@ -169,6 +169,9 @@
-
- #endif /* #else #ifdef CONFIG_PREEMPT_RCU */
-
- +#ifdef CONFIG_PREEMPT_RT_FULL
- +#define call_rcu_bh call_rcu
- +#else
- /**
- * call_rcu_bh() - Queue an RCU for invocation after a quicker grace period.
- * @head: structure to be used for queueing the RCU updates.
- @@ -192,6 +195,7 @@
- */
- void call_rcu_bh(struct rcu_head *head,
- rcu_callback_t func);
- +#endif
-
- /**
- * call_rcu_sched() - Queue an RCU for invocation after sched grace period.
- @@ -292,6 +296,11 @@
- * types of kernel builds, the rcu_read_lock() nesting depth is unknowable.
- */
- #define rcu_preempt_depth() (current->rcu_read_lock_nesting)
- +#ifndef CONFIG_PREEMPT_RT_FULL
- +#define sched_rcu_preempt_depth() rcu_preempt_depth()
- +#else
- +static inline int sched_rcu_preempt_depth(void) { return 0; }
- +#endif
-
- #else /* #ifdef CONFIG_PREEMPT_RCU */
-
- @@ -317,6 +326,8 @@
- return 0;
- }
-
- +#define sched_rcu_preempt_depth() rcu_preempt_depth()
- +
- #endif /* #else #ifdef CONFIG_PREEMPT_RCU */
-
- /* Internal to kernel */
- @@ -489,7 +500,14 @@
- int debug_lockdep_rcu_enabled(void);
-
- int rcu_read_lock_held(void);
- +#ifdef CONFIG_PREEMPT_RT_FULL
- +static inline int rcu_read_lock_bh_held(void)
- +{
- + return rcu_read_lock_held();
- +}
- +#else
- int rcu_read_lock_bh_held(void);
- +#endif
-
- /**
- * rcu_read_lock_sched_held() - might we be in RCU-sched read-side critical section?
- @@ -937,10 +955,14 @@
- static inline void rcu_read_lock_bh(void)
- {
- local_bh_disable();
- +#ifdef CONFIG_PREEMPT_RT_FULL
- + rcu_read_lock();
- +#else
- __acquire(RCU_BH);
- rcu_lock_acquire(&rcu_bh_lock_map);
- RCU_LOCKDEP_WARN(!rcu_is_watching(),
- "rcu_read_lock_bh() used illegally while idle");
- +#endif
- }
-
- /*
- @@ -950,10 +972,14 @@
- */
- static inline void rcu_read_unlock_bh(void)
- {
- +#ifdef CONFIG_PREEMPT_RT_FULL
- + rcu_read_unlock();
- +#else
- RCU_LOCKDEP_WARN(!rcu_is_watching(),
- "rcu_read_unlock_bh() used illegally while idle");
- rcu_lock_release(&rcu_bh_lock_map);
- __release(RCU_BH);
- +#endif
- local_bh_enable();
- }
-
- diff -Nur linux-4.4.28.orig/include/linux/rcutree.h linux-4.4.28/include/linux/rcutree.h
- --- linux-4.4.28.orig/include/linux/rcutree.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/rcutree.h 2016-11-01 21:26:58.740339958 +0100
- @@ -44,7 +44,11 @@
- rcu_note_context_switch();
- }
-
- +#ifdef CONFIG_PREEMPT_RT_FULL
- +# define synchronize_rcu_bh synchronize_rcu
- +#else
- void synchronize_rcu_bh(void);
- +#endif
- void synchronize_sched_expedited(void);
- void synchronize_rcu_expedited(void);
-
- @@ -72,7 +76,11 @@
- }
-
- void rcu_barrier(void);
- +#ifdef CONFIG_PREEMPT_RT_FULL
- +# define rcu_barrier_bh rcu_barrier
- +#else
- void rcu_barrier_bh(void);
- +#endif
- void rcu_barrier_sched(void);
- unsigned long get_state_synchronize_rcu(void);
- void cond_synchronize_rcu(unsigned long oldstate);
- @@ -85,12 +93,10 @@
- unsigned long rcu_batches_started_bh(void);
- unsigned long rcu_batches_started_sched(void);
- unsigned long rcu_batches_completed(void);
- -unsigned long rcu_batches_completed_bh(void);
- unsigned long rcu_batches_completed_sched(void);
- void show_rcu_gp_kthreads(void);
-
- void rcu_force_quiescent_state(void);
- -void rcu_bh_force_quiescent_state(void);
- void rcu_sched_force_quiescent_state(void);
-
- void rcu_idle_enter(void);
- @@ -105,6 +111,14 @@
-
- bool rcu_is_watching(void);
-
- +#ifndef CONFIG_PREEMPT_RT_FULL
- +void rcu_bh_force_quiescent_state(void);
- +unsigned long rcu_batches_completed_bh(void);
- +#else
- +# define rcu_bh_force_quiescent_state rcu_force_quiescent_state
- +# define rcu_batches_completed_bh rcu_batches_completed
- +#endif
- +
- void rcu_all_qs(void);
-
- #endif /* __LINUX_RCUTREE_H */
- diff -Nur linux-4.4.28.orig/include/linux/rtmutex.h linux-4.4.28/include/linux/rtmutex.h
- --- linux-4.4.28.orig/include/linux/rtmutex.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/rtmutex.h 2016-11-01 21:26:58.740339958 +0100
- @@ -13,11 +13,15 @@
- #define __LINUX_RT_MUTEX_H
-
- #include <linux/linkage.h>
- +#include <linux/spinlock_types_raw.h>
- #include <linux/rbtree.h>
- -#include <linux/spinlock_types.h>
-
- extern int max_lock_depth; /* for sysctl */
-
- +#ifdef CONFIG_DEBUG_MUTEXES
- +#include <linux/debug_locks.h>
- +#endif
- +
- /**
- * The rt_mutex structure
- *
- @@ -31,8 +35,8 @@
- struct rb_root waiters;
- struct rb_node *waiters_leftmost;
- struct task_struct *owner;
- -#ifdef CONFIG_DEBUG_RT_MUTEXES
- int save_state;
- +#ifdef CONFIG_DEBUG_RT_MUTEXES
- const char *name, *file;
- int line;
- void *magic;
- @@ -55,22 +59,33 @@
- # define rt_mutex_debug_check_no_locks_held(task) do { } while (0)
- #endif
-
- +# define rt_mutex_init(mutex) \
- + do { \
- + raw_spin_lock_init(&(mutex)->wait_lock); \
- + __rt_mutex_init(mutex, #mutex); \
- + } while (0)
- +
- #ifdef CONFIG_DEBUG_RT_MUTEXES
- # define __DEBUG_RT_MUTEX_INITIALIZER(mutexname) \
- , .name = #mutexname, .file = __FILE__, .line = __LINE__
- -# define rt_mutex_init(mutex) __rt_mutex_init(mutex, __func__)
- extern void rt_mutex_debug_task_free(struct task_struct *tsk);
- #else
- # define __DEBUG_RT_MUTEX_INITIALIZER(mutexname)
- -# define rt_mutex_init(mutex) __rt_mutex_init(mutex, NULL)
- # define rt_mutex_debug_task_free(t) do { } while (0)
- #endif
-
- -#define __RT_MUTEX_INITIALIZER(mutexname) \
- - { .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(mutexname.wait_lock) \
- +#define __RT_MUTEX_INITIALIZER_PLAIN(mutexname) \
- + .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(mutexname.wait_lock) \
- , .waiters = RB_ROOT \
- , .owner = NULL \
- - __DEBUG_RT_MUTEX_INITIALIZER(mutexname)}
- + __DEBUG_RT_MUTEX_INITIALIZER(mutexname)
- +
- +#define __RT_MUTEX_INITIALIZER(mutexname) \
- + { __RT_MUTEX_INITIALIZER_PLAIN(mutexname) }
- +
- +#define __RT_MUTEX_INITIALIZER_SAVE_STATE(mutexname) \
- + { __RT_MUTEX_INITIALIZER_PLAIN(mutexname) \
- + , .save_state = 1 }
-
- #define DEFINE_RT_MUTEX(mutexname) \
- struct rt_mutex mutexname = __RT_MUTEX_INITIALIZER(mutexname)
- @@ -91,6 +106,7 @@
-
- extern void rt_mutex_lock(struct rt_mutex *lock);
- extern int rt_mutex_lock_interruptible(struct rt_mutex *lock);
- +extern int rt_mutex_lock_killable(struct rt_mutex *lock);
- extern int rt_mutex_timed_lock(struct rt_mutex *lock,
- struct hrtimer_sleeper *timeout);
-
- diff -Nur linux-4.4.28.orig/include/linux/rwlock_rt.h linux-4.4.28/include/linux/rwlock_rt.h
- --- linux-4.4.28.orig/include/linux/rwlock_rt.h 1970-01-01 01:00:00.000000000 +0100
- +++ linux-4.4.28/include/linux/rwlock_rt.h 2016-11-01 21:26:58.740339958 +0100
- @@ -0,0 +1,99 @@
- +#ifndef __LINUX_RWLOCK_RT_H
- +#define __LINUX_RWLOCK_RT_H
- +
- +#ifndef __LINUX_SPINLOCK_H
- +#error Do not include directly. Use spinlock.h
- +#endif
- +
- +#define rwlock_init(rwl) \
- +do { \
- + static struct lock_class_key __key; \
- + \
- + rt_mutex_init(&(rwl)->lock); \
- + __rt_rwlock_init(rwl, #rwl, &__key); \
- +} while (0)
- +
- +extern void __lockfunc rt_write_lock(rwlock_t *rwlock);
- +extern void __lockfunc rt_read_lock(rwlock_t *rwlock);
- +extern int __lockfunc rt_write_trylock(rwlock_t *rwlock);
- +extern int __lockfunc rt_write_trylock_irqsave(rwlock_t *trylock, unsigned long *flags);
- +extern int __lockfunc rt_read_trylock(rwlock_t *rwlock);
- +extern void __lockfunc rt_write_unlock(rwlock_t *rwlock);
- +extern void __lockfunc rt_read_unlock(rwlock_t *rwlock);
- +extern unsigned long __lockfunc rt_write_lock_irqsave(rwlock_t *rwlock);
- +extern unsigned long __lockfunc rt_read_lock_irqsave(rwlock_t *rwlock);
- +extern void __rt_rwlock_init(rwlock_t *rwlock, char *name, struct lock_class_key *key);
- +
- +#define read_trylock(lock) __cond_lock(lock, rt_read_trylock(lock))
- +#define write_trylock(lock) __cond_lock(lock, rt_write_trylock(lock))
- +
- +#define write_trylock_irqsave(lock, flags) \
- + __cond_lock(lock, rt_write_trylock_irqsave(lock, &flags))
- +
- +#define read_lock_irqsave(lock, flags) \
- + do { \
- + typecheck(unsigned long, flags); \
- + flags = rt_read_lock_irqsave(lock); \
- + } while (0)
- +
- +#define write_lock_irqsave(lock, flags) \
- + do { \
- + typecheck(unsigned long, flags); \
- + flags = rt_write_lock_irqsave(lock); \
- + } while (0)
- +
- +#define read_lock(lock) rt_read_lock(lock)
- +
- +#define read_lock_bh(lock) \
- + do { \
- + local_bh_disable(); \
- + rt_read_lock(lock); \
- + } while (0)
- +
- +#define read_lock_irq(lock) read_lock(lock)
- +
- +#define write_lock(lock) rt_write_lock(lock)
- +
- +#define write_lock_bh(lock) \
- + do { \
- + local_bh_disable(); \
- + rt_write_lock(lock); \
- + } while (0)
- +
- +#define write_lock_irq(lock) write_lock(lock)
- +
- +#define read_unlock(lock) rt_read_unlock(lock)
- +
- +#define read_unlock_bh(lock) \
- + do { \
- + rt_read_unlock(lock); \
- + local_bh_enable(); \
- + } while (0)
- +
- +#define read_unlock_irq(lock) read_unlock(lock)
- +
- +#define write_unlock(lock) rt_write_unlock(lock)
- +
- +#define write_unlock_bh(lock) \
- + do { \
- + rt_write_unlock(lock); \
- + local_bh_enable(); \
- + } while (0)
- +
- +#define write_unlock_irq(lock) write_unlock(lock)
- +
- +#define read_unlock_irqrestore(lock, flags) \
- + do { \
- + typecheck(unsigned long, flags); \
- + (void) flags; \
- + rt_read_unlock(lock); \
- + } while (0)
- +
- +#define write_unlock_irqrestore(lock, flags) \
- + do { \
- + typecheck(unsigned long, flags); \
- + (void) flags; \
- + rt_write_unlock(lock); \
- + } while (0)
- +
- +#endif
- diff -Nur linux-4.4.28.orig/include/linux/rwlock_types.h linux-4.4.28/include/linux/rwlock_types.h
- --- linux-4.4.28.orig/include/linux/rwlock_types.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/rwlock_types.h 2016-11-01 21:26:58.740339958 +0100
- @@ -1,6 +1,10 @@
- #ifndef __LINUX_RWLOCK_TYPES_H
- #define __LINUX_RWLOCK_TYPES_H
-
- +#if !defined(__LINUX_SPINLOCK_TYPES_H)
- +# error "Do not include directly, include spinlock_types.h"
- +#endif
- +
- /*
- * include/linux/rwlock_types.h - generic rwlock type definitions
- * and initializers
- @@ -43,6 +47,7 @@
- RW_DEP_MAP_INIT(lockname) }
- #endif
-
- -#define DEFINE_RWLOCK(x) rwlock_t x = __RW_LOCK_UNLOCKED(x)
- +#define DEFINE_RWLOCK(name) \
- + rwlock_t name __cacheline_aligned_in_smp = __RW_LOCK_UNLOCKED(name)
-
- #endif /* __LINUX_RWLOCK_TYPES_H */
- diff -Nur linux-4.4.28.orig/include/linux/rwlock_types_rt.h linux-4.4.28/include/linux/rwlock_types_rt.h
- --- linux-4.4.28.orig/include/linux/rwlock_types_rt.h 1970-01-01 01:00:00.000000000 +0100
- +++ linux-4.4.28/include/linux/rwlock_types_rt.h 2016-11-01 21:26:58.740339958 +0100
- @@ -0,0 +1,33 @@
- +#ifndef __LINUX_RWLOCK_TYPES_RT_H
- +#define __LINUX_RWLOCK_TYPES_RT_H
- +
- +#ifndef __LINUX_SPINLOCK_TYPES_H
- +#error "Do not include directly. Include spinlock_types.h instead"
- +#endif
- +
- +/*
- + * rwlocks - rtmutex which allows single reader recursion
- + */
- +typedef struct {
- + struct rt_mutex lock;
- + int read_depth;
- + unsigned int break_lock;
- +#ifdef CONFIG_DEBUG_LOCK_ALLOC
- + struct lockdep_map dep_map;
- +#endif
- +} rwlock_t;
- +
- +#ifdef CONFIG_DEBUG_LOCK_ALLOC
- +# define RW_DEP_MAP_INIT(lockname) .dep_map = { .name = #lockname }
- +#else
- +# define RW_DEP_MAP_INIT(lockname)
- +#endif
- +
- +#define __RW_LOCK_UNLOCKED(name) \
- + { .lock = __RT_MUTEX_INITIALIZER_SAVE_STATE(name.lock), \
- + RW_DEP_MAP_INIT(name) }
- +
- +#define DEFINE_RWLOCK(name) \
- + rwlock_t name __cacheline_aligned_in_smp = __RW_LOCK_UNLOCKED(name)
- +
- +#endif
- diff -Nur linux-4.4.28.orig/include/linux/rwsem.h linux-4.4.28/include/linux/rwsem.h
- --- linux-4.4.28.orig/include/linux/rwsem.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/rwsem.h 2016-11-01 21:26:58.740339958 +0100
- @@ -18,6 +18,10 @@
- #include <linux/osq_lock.h>
- #endif
-
- +#ifdef CONFIG_PREEMPT_RT_FULL
- +#include <linux/rwsem_rt.h>
- +#else /* PREEMPT_RT_FULL */
- +
- struct rw_semaphore;
-
- #ifdef CONFIG_RWSEM_GENERIC_SPINLOCK
- @@ -177,4 +181,6 @@
- # define up_read_non_owner(sem) up_read(sem)
- #endif
-
- +#endif /* !PREEMPT_RT_FULL */
- +
- #endif /* _LINUX_RWSEM_H */
- diff -Nur linux-4.4.28.orig/include/linux/rwsem_rt.h linux-4.4.28/include/linux/rwsem_rt.h
- --- linux-4.4.28.orig/include/linux/rwsem_rt.h 1970-01-01 01:00:00.000000000 +0100
- +++ linux-4.4.28/include/linux/rwsem_rt.h 2016-11-01 21:26:58.740339958 +0100
- @@ -0,0 +1,152 @@
- +#ifndef _LINUX_RWSEM_RT_H
- +#define _LINUX_RWSEM_RT_H
- +
- +#ifndef _LINUX_RWSEM_H
- +#error "Include rwsem.h"
- +#endif
- +
- +/*
- + * RW-semaphores are a spinlock plus a reader-depth count.
- + *
- + * Note that the semantics are different from the usual
- + * Linux rw-sems, in PREEMPT_RT mode we do not allow
- + * multiple readers to hold the lock at once, we only allow
- + * a read-lock owner to read-lock recursively. This is
- + * better for latency, makes the implementation inherently
- + * fair and makes it simpler as well.
- + */
- +
- +#include <linux/rtmutex.h>
- +
- +struct rw_semaphore {
- + struct rt_mutex lock;
- + int read_depth;
- +#ifdef CONFIG_DEBUG_LOCK_ALLOC
- + struct lockdep_map dep_map;
- +#endif
- +};
- +
- +#define __RWSEM_INITIALIZER(name) \
- + { .lock = __RT_MUTEX_INITIALIZER(name.lock), \
- + RW_DEP_MAP_INIT(name) }
- +
- +#define DECLARE_RWSEM(lockname) \
- + struct rw_semaphore lockname = __RWSEM_INITIALIZER(lockname)
- +
- +extern void __rt_rwsem_init(struct rw_semaphore *rwsem, const char *name,
- + struct lock_class_key *key);
- +
- +#define __rt_init_rwsem(sem, name, key) \
- + do { \
- + rt_mutex_init(&(sem)->lock); \
- + __rt_rwsem_init((sem), (name), (key));\
- + } while (0)
- +
- +#define __init_rwsem(sem, name, key) __rt_init_rwsem(sem, name, key)
- +
- +# define rt_init_rwsem(sem) \
- +do { \
- + static struct lock_class_key __key; \
- + \
- + __rt_init_rwsem((sem), #sem, &__key); \
- +} while (0)
- +
- +extern void rt_down_write(struct rw_semaphore *rwsem);
- +extern void rt_down_read_nested(struct rw_semaphore *rwsem, int subclass);
- +extern void rt_down_write_nested(struct rw_semaphore *rwsem, int subclass);
- +extern void rt_down_write_nested_lock(struct rw_semaphore *rwsem,
- + struct lockdep_map *nest);
- +extern void rt__down_read(struct rw_semaphore *rwsem);
- +extern void rt_down_read(struct rw_semaphore *rwsem);
- +extern int rt_down_write_trylock(struct rw_semaphore *rwsem);
- +extern int rt__down_read_trylock(struct rw_semaphore *rwsem);
- +extern int rt_down_read_trylock(struct rw_semaphore *rwsem);
- +extern void __rt_up_read(struct rw_semaphore *rwsem);
- +extern void rt_up_read(struct rw_semaphore *rwsem);
- +extern void rt_up_write(struct rw_semaphore *rwsem);
- +extern void rt_downgrade_write(struct rw_semaphore *rwsem);
- +
- +#define init_rwsem(sem) rt_init_rwsem(sem)
- +#define rwsem_is_locked(s) rt_mutex_is_locked(&(s)->lock)
- +
- +static inline int rwsem_is_contended(struct rw_semaphore *sem)
- +{
- + /* rt_mutex_has_waiters() */
- + return !RB_EMPTY_ROOT(&sem->lock.waiters);
- +}
- +
- +static inline void __down_read(struct rw_semaphore *sem)
- +{
- + rt__down_read(sem);
- +}
- +
- +static inline void down_read(struct rw_semaphore *sem)
- +{
- + rt_down_read(sem);
- +}
- +
- +static inline int __down_read_trylock(struct rw_semaphore *sem)
- +{
- + return rt__down_read_trylock(sem);
- +}
- +
- +static inline int down_read_trylock(struct rw_semaphore *sem)
- +{
- + return rt_down_read_trylock(sem);
- +}
- +
- +static inline void down_write(struct rw_semaphore *sem)
- +{
- + rt_down_write(sem);
- +}
- +
- +static inline int down_write_trylock(struct rw_semaphore *sem)
- +{
- + return rt_down_write_trylock(sem);
- +}
- +
- +static inline void __up_read(struct rw_semaphore *sem)
- +{
- + __rt_up_read(sem);
- +}
- +
- +static inline void up_read(struct rw_semaphore *sem)
- +{
- + rt_up_read(sem);
- +}
- +
- +static inline void up_write(struct rw_semaphore *sem)
- +{
- + rt_up_write(sem);
- +}
- +
- +static inline void downgrade_write(struct rw_semaphore *sem)
- +{
- + rt_downgrade_write(sem);
- +}
- +
- +static inline void down_read_nested(struct rw_semaphore *sem, int subclass)
- +{
- + return rt_down_read_nested(sem, subclass);
- +}
- +
- +static inline void down_write_nested(struct rw_semaphore *sem, int subclass)
- +{
- + rt_down_write_nested(sem, subclass);
- +}
- +#ifdef CONFIG_DEBUG_LOCK_ALLOC
- +static inline void down_write_nest_lock(struct rw_semaphore *sem,
- + struct rw_semaphore *nest_lock)
- +{
- + rt_down_write_nested_lock(sem, &nest_lock->dep_map);
- +}
- +
- +#else
- +
- +static inline void down_write_nest_lock(struct rw_semaphore *sem,
- + struct rw_semaphore *nest_lock)
- +{
- + rt_down_write_nested_lock(sem, NULL);
- +}
- +#endif
- +#endif
- diff -Nur linux-4.4.28.orig/include/linux/sched.h linux-4.4.28/include/linux/sched.h
- --- linux-4.4.28.orig/include/linux/sched.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/sched.h 2016-11-01 21:26:58.740339958 +0100
- @@ -26,6 +26,7 @@
- #include <linux/nodemask.h>
- #include <linux/mm_types.h>
- #include <linux/preempt.h>
- +#include <asm/kmap_types.h>
-
- #include <asm/page.h>
- #include <asm/ptrace.h>
- @@ -182,8 +183,6 @@
- static inline void update_cpu_load_nohz(void) { }
- #endif
-
- -extern unsigned long get_parent_ip(unsigned long addr);
- -
- extern void dump_cpu_task(int cpu);
-
- struct seq_file;
- @@ -242,10 +241,7 @@
- TASK_UNINTERRUPTIBLE | __TASK_STOPPED | \
- __TASK_TRACED | EXIT_ZOMBIE | EXIT_DEAD)
-
- -#define task_is_traced(task) ((task->state & __TASK_TRACED) != 0)
- #define task_is_stopped(task) ((task->state & __TASK_STOPPED) != 0)
- -#define task_is_stopped_or_traced(task) \
- - ((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0)
- #define task_contributes_to_load(task) \
- ((task->state & TASK_UNINTERRUPTIBLE) != 0 && \
- (task->flags & PF_FROZEN) == 0 && \
- @@ -311,6 +307,11 @@
-
- #endif
-
- +#define __set_current_state_no_track(state_value) \
- + do { current->state = (state_value); } while (0)
- +#define set_current_state_no_track(state_value) \
- + set_mb(current->state, (state_value))
- +
- /* Task command name length */
- #define TASK_COMM_LEN 16
-
- @@ -970,8 +971,18 @@
- struct wake_q_head name = { WAKE_Q_TAIL, &name.first }
-
- extern void wake_q_add(struct wake_q_head *head,
- - struct task_struct *task);
- -extern void wake_up_q(struct wake_q_head *head);
- + struct task_struct *task);
- +extern void __wake_up_q(struct wake_q_head *head, bool sleeper);
- +
- +static inline void wake_up_q(struct wake_q_head *head)
- +{
- + __wake_up_q(head, false);
- +}
- +
- +static inline void wake_up_q_sleeper(struct wake_q_head *head)
- +{
- + __wake_up_q(head, true);
- +}
-
- /*
- * sched-domains (multiprocessor balancing) declarations:
- @@ -1379,6 +1390,7 @@
-
- struct task_struct {
- volatile long state; /* -1 unrunnable, 0 runnable, >0 stopped */
- + volatile long saved_state; /* saved state for "spinlock sleepers" */
- void *stack;
- atomic_t usage;
- unsigned int flags; /* per process flags, defined below */
- @@ -1415,6 +1427,12 @@
- #endif
-
- unsigned int policy;
- +#ifdef CONFIG_PREEMPT_RT_FULL
- + int migrate_disable;
- +# ifdef CONFIG_SCHED_DEBUG
- + int migrate_disable_atomic;
- +# endif
- +#endif
- int nr_cpus_allowed;
- cpumask_t cpus_allowed;
-
- @@ -1522,11 +1540,14 @@
- cputime_t gtime;
- struct prev_cputime prev_cputime;
- #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
- - seqlock_t vtime_seqlock;
- + seqcount_t vtime_seqcount;
- unsigned long long vtime_snap;
- enum {
- - VTIME_SLEEPING = 0,
- + /* Task is sleeping or running in a CPU with VTIME inactive */
- + VTIME_INACTIVE = 0,
- + /* Task runs in userspace in a CPU with VTIME active */
- VTIME_USER,
- + /* Task runs in kernelspace in a CPU with VTIME active */
- VTIME_SYS,
- } vtime_snap_whence;
- #endif
- @@ -1538,6 +1559,9 @@
-
- struct task_cputime cputime_expires;
- struct list_head cpu_timers[3];
- +#ifdef CONFIG_PREEMPT_RT_BASE
- + struct task_struct *posix_timer_list;
- +#endif
-
- /* process credentials */
- const struct cred __rcu *real_cred; /* objective and real subjective task
- @@ -1568,10 +1592,15 @@
- /* signal handlers */
- struct signal_struct *signal;
- struct sighand_struct *sighand;
- + struct sigqueue *sigqueue_cache;
-
- sigset_t blocked, real_blocked;
- sigset_t saved_sigmask; /* restored if set_restore_sigmask() was used */
- struct sigpending pending;
- +#ifdef CONFIG_PREEMPT_RT_FULL
- + /* TODO: move me into ->restart_block ? */
- + struct siginfo forced_info;
- +#endif
-
- unsigned long sas_ss_sp;
- size_t sas_ss_size;
- @@ -1795,6 +1824,12 @@
- unsigned long trace;
- /* bitmask and counter of trace recursion */
- unsigned long trace_recursion;
- +#ifdef CONFIG_WAKEUP_LATENCY_HIST
- + u64 preempt_timestamp_hist;
- +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
- + long timer_offset;
- +#endif
- +#endif
- #endif /* CONFIG_TRACING */
- #ifdef CONFIG_MEMCG
- struct mem_cgroup *memcg_in_oom;
- @@ -1811,9 +1846,23 @@
- unsigned int sequential_io;
- unsigned int sequential_io_avg;
- #endif
- +#ifdef CONFIG_PREEMPT_RT_BASE
- + struct rcu_head put_rcu;
- + int softirq_nestcnt;
- + unsigned int softirqs_raised;
- +#endif
- +#ifdef CONFIG_PREEMPT_RT_FULL
- +# if defined CONFIG_HIGHMEM || defined CONFIG_X86_32
- + int kmap_idx;
- + pte_t kmap_pte[KM_TYPE_NR];
- +# endif
- +#endif
- #ifdef CONFIG_DEBUG_ATOMIC_SLEEP
- unsigned long task_state_change;
- #endif
- +#ifdef CONFIG_PREEMPT_RT_FULL
- + int xmit_recursion;
- +#endif
- int pagefault_disabled;
- /* CPU-specific state of this task */
- struct thread_struct thread;
- @@ -1831,9 +1880,6 @@
- # define arch_task_struct_size (sizeof(struct task_struct))
- #endif
-
- -/* Future-safe accessor for struct task_struct's cpus_allowed. */
- -#define tsk_cpus_allowed(tsk) (&(tsk)->cpus_allowed)
- -
- #define TNF_MIGRATED 0x01
- #define TNF_NO_GROUP 0x02
- #define TNF_SHARED 0x04
- @@ -2023,6 +2069,15 @@
- extern void free_task(struct task_struct *tsk);
- #define get_task_struct(tsk) do { atomic_inc(&(tsk)->usage); } while(0)
-
- +#ifdef CONFIG_PREEMPT_RT_BASE
- +extern void __put_task_struct_cb(struct rcu_head *rhp);
- +
- +static inline void put_task_struct(struct task_struct *t)
- +{
- + if (atomic_dec_and_test(&t->usage))
- + call_rcu(&t->put_rcu, __put_task_struct_cb);
- +}
- +#else
- extern void __put_task_struct(struct task_struct *t);
-
- static inline void put_task_struct(struct task_struct *t)
- @@ -2030,6 +2085,7 @@
- if (atomic_dec_and_test(&t->usage))
- __put_task_struct(t);
- }
- +#endif
-
- #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
- extern void task_cputime(struct task_struct *t,
- @@ -2068,6 +2124,7 @@
- /*
- * Per process flags
- */
- +#define PF_IN_SOFTIRQ 0x00000001 /* Task is serving softirq */
- #define PF_EXITING 0x00000004 /* getting shut down */
- #define PF_EXITPIDONE 0x00000008 /* pi exit done on shut down */
- #define PF_VCPU 0x00000010 /* I'm a virtual CPU */
- @@ -2232,6 +2289,10 @@
-
- extern int set_cpus_allowed_ptr(struct task_struct *p,
- const struct cpumask *new_mask);
- +int migrate_me(void);
- +void tell_sched_cpu_down_begin(int cpu);
- +void tell_sched_cpu_down_done(int cpu);
- +
- #else
- static inline void do_set_cpus_allowed(struct task_struct *p,
- const struct cpumask *new_mask)
- @@ -2244,6 +2305,9 @@
- return -EINVAL;
- return 0;
- }
- +static inline int migrate_me(void) { return 0; }
- +static inline void tell_sched_cpu_down_begin(int cpu) { }
- +static inline void tell_sched_cpu_down_done(int cpu) { }
- #endif
-
- #ifdef CONFIG_NO_HZ_COMMON
- @@ -2453,6 +2517,7 @@
-
- extern int wake_up_state(struct task_struct *tsk, unsigned int state);
- extern int wake_up_process(struct task_struct *tsk);
- +extern int wake_up_lock_sleeper(struct task_struct * tsk);
- extern void wake_up_new_task(struct task_struct *tsk);
- #ifdef CONFIG_SMP
- extern void kick_process(struct task_struct *tsk);
- @@ -2576,12 +2641,24 @@
-
- /* mmdrop drops the mm and the page tables */
- extern void __mmdrop(struct mm_struct *);
- +
- static inline void mmdrop(struct mm_struct * mm)
- {
- if (unlikely(atomic_dec_and_test(&mm->mm_count)))
- __mmdrop(mm);
- }
-
- +#ifdef CONFIG_PREEMPT_RT_BASE
- +extern void __mmdrop_delayed(struct rcu_head *rhp);
- +static inline void mmdrop_delayed(struct mm_struct *mm)
- +{
- + if (atomic_dec_and_test(&mm->mm_count))
- + call_rcu(&mm->delayed_drop, __mmdrop_delayed);
- +}
- +#else
- +# define mmdrop_delayed(mm) mmdrop(mm)
- +#endif
- +
- /* mmput gets rid of the mappings and all user-space */
- extern void mmput(struct mm_struct *);
- /* Grab a reference to a task's mm, if it is not already going away */
- @@ -2891,6 +2968,43 @@
- return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED));
- }
-
- +#ifdef CONFIG_PREEMPT_LAZY
- +static inline void set_tsk_need_resched_lazy(struct task_struct *tsk)
- +{
- + set_tsk_thread_flag(tsk,TIF_NEED_RESCHED_LAZY);
- +}
- +
- +static inline void clear_tsk_need_resched_lazy(struct task_struct *tsk)
- +{
- + clear_tsk_thread_flag(tsk,TIF_NEED_RESCHED_LAZY);
- +}
- +
- +static inline int test_tsk_need_resched_lazy(struct task_struct *tsk)
- +{
- + return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED_LAZY));
- +}
- +
- +static inline int need_resched_lazy(void)
- +{
- + return test_thread_flag(TIF_NEED_RESCHED_LAZY);
- +}
- +
- +static inline int need_resched_now(void)
- +{
- + return test_thread_flag(TIF_NEED_RESCHED);
- +}
- +
- +#else
- +static inline void clear_tsk_need_resched_lazy(struct task_struct *tsk) { }
- +static inline int need_resched_lazy(void) { return 0; }
- +
- +static inline int need_resched_now(void)
- +{
- + return test_thread_flag(TIF_NEED_RESCHED);
- +}
- +
- +#endif
- +
- static inline int restart_syscall(void)
- {
- set_tsk_thread_flag(current, TIF_SIGPENDING);
- @@ -2922,6 +3036,51 @@
- return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p);
- }
-
- +static inline bool __task_is_stopped_or_traced(struct task_struct *task)
- +{
- + if (task->state & (__TASK_STOPPED | __TASK_TRACED))
- + return true;
- +#ifdef CONFIG_PREEMPT_RT_FULL
- + if (task->saved_state & (__TASK_STOPPED | __TASK_TRACED))
- + return true;
- +#endif
- + return false;
- +}
- +
- +static inline bool task_is_stopped_or_traced(struct task_struct *task)
- +{
- + bool traced_stopped;
- +
- +#ifdef CONFIG_PREEMPT_RT_FULL
- + unsigned long flags;
- +
- + raw_spin_lock_irqsave(&task->pi_lock, flags);
- + traced_stopped = __task_is_stopped_or_traced(task);
- + raw_spin_unlock_irqrestore(&task->pi_lock, flags);
- +#else
- + traced_stopped = __task_is_stopped_or_traced(task);
- +#endif
- + return traced_stopped;
- +}
- +
- +static inline bool task_is_traced(struct task_struct *task)
- +{
- + bool traced = false;
- +
- + if (task->state & __TASK_TRACED)
- + return true;
- +#ifdef CONFIG_PREEMPT_RT_FULL
- + /* in case the task is sleeping on tasklist_lock */
- + raw_spin_lock_irq(&task->pi_lock);
- + if (task->state & __TASK_TRACED)
- + traced = true;
- + else if (task->saved_state & __TASK_TRACED)
- + traced = true;
- + raw_spin_unlock_irq(&task->pi_lock);
- +#endif
- + return traced;
- +}
- +
- /*
- * cond_resched() and cond_resched_lock(): latency reduction via
- * explicit rescheduling in places that are safe. The return
- @@ -2943,12 +3102,16 @@
- __cond_resched_lock(lock); \
- })
-
- +#ifndef CONFIG_PREEMPT_RT_FULL
- extern int __cond_resched_softirq(void);
-
- #define cond_resched_softirq() ({ \
- ___might_sleep(__FILE__, __LINE__, SOFTIRQ_DISABLE_OFFSET); \
- __cond_resched_softirq(); \
- })
- +#else
- +# define cond_resched_softirq() cond_resched()
- +#endif
-
- static inline void cond_resched_rcu(void)
- {
- @@ -3110,6 +3273,31 @@
-
- #endif /* CONFIG_SMP */
-
- +static inline int __migrate_disabled(struct task_struct *p)
- +{
- +#ifdef CONFIG_PREEMPT_RT_FULL
- + return p->migrate_disable;
- +#else
- + return 0;
- +#endif
- +}
- +
- +/* Future-safe accessor for struct task_struct's cpus_allowed. */
- +static inline const struct cpumask *tsk_cpus_allowed(struct task_struct *p)
- +{
- + if (__migrate_disabled(p))
- + return cpumask_of(task_cpu(p));
- +
- + return &p->cpus_allowed;
- +}
- +
- +static inline int tsk_nr_cpus_allowed(struct task_struct *p)
- +{
- + if (__migrate_disabled(p))
- + return 1;
- + return p->nr_cpus_allowed;
- +}
- +
- extern long sched_setaffinity(pid_t pid, const struct cpumask *new_mask);
- extern long sched_getaffinity(pid_t pid, struct cpumask *mask);
-
- diff -Nur linux-4.4.28.orig/include/linux/seqlock.h linux-4.4.28/include/linux/seqlock.h
- --- linux-4.4.28.orig/include/linux/seqlock.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/seqlock.h 2016-11-01 21:26:58.744340223 +0100
- @@ -220,20 +220,30 @@
- return __read_seqcount_retry(s, start);
- }
-
- -
- -
- -static inline void raw_write_seqcount_begin(seqcount_t *s)
- +static inline void __raw_write_seqcount_begin(seqcount_t *s)
- {
- s->sequence++;
- smp_wmb();
- }
-
- -static inline void raw_write_seqcount_end(seqcount_t *s)
- +static inline void raw_write_seqcount_begin(seqcount_t *s)
- +{
- + preempt_disable_rt();
- + __raw_write_seqcount_begin(s);
- +}
- +
- +static inline void __raw_write_seqcount_end(seqcount_t *s)
- {
- smp_wmb();
- s->sequence++;
- }
-
- +static inline void raw_write_seqcount_end(seqcount_t *s)
- +{
- + __raw_write_seqcount_end(s);
- + preempt_enable_rt();
- +}
- +
- /**
- * raw_write_seqcount_barrier - do a seq write barrier
- * @s: pointer to seqcount_t
- @@ -425,10 +435,32 @@
- /*
- * Read side functions for starting and finalizing a read side section.
- */
- +#ifndef CONFIG_PREEMPT_RT_FULL
- static inline unsigned read_seqbegin(const seqlock_t *sl)
- {
- return read_seqcount_begin(&sl->seqcount);
- }
- +#else
- +/*
- + * Starvation safe read side for RT
- + */
- +static inline unsigned read_seqbegin(seqlock_t *sl)
- +{
- + unsigned ret;
- +
- +repeat:
- + ret = ACCESS_ONCE(sl->seqcount.sequence);
- + if (unlikely(ret & 1)) {
- + /*
- + * Take the lock and let the writer proceed (i.e. evtl
- + * boost it), otherwise we could loop here forever.
- + */
- + spin_unlock_wait(&sl->lock);
- + goto repeat;
- + }
- + return ret;
- +}
- +#endif
-
- static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start)
- {
- @@ -443,36 +475,36 @@
- static inline void write_seqlock(seqlock_t *sl)
- {
- spin_lock(&sl->lock);
- - write_seqcount_begin(&sl->seqcount);
- + __raw_write_seqcount_begin(&sl->seqcount);
- }
-
- static inline void write_sequnlock(seqlock_t *sl)
- {
- - write_seqcount_end(&sl->seqcount);
- + __raw_write_seqcount_end(&sl->seqcount);
- spin_unlock(&sl->lock);
- }
-
- static inline void write_seqlock_bh(seqlock_t *sl)
- {
- spin_lock_bh(&sl->lock);
- - write_seqcount_begin(&sl->seqcount);
- + __raw_write_seqcount_begin(&sl->seqcount);
- }
-
- static inline void write_sequnlock_bh(seqlock_t *sl)
- {
- - write_seqcount_end(&sl->seqcount);
- + __raw_write_seqcount_end(&sl->seqcount);
- spin_unlock_bh(&sl->lock);
- }
-
- static inline void write_seqlock_irq(seqlock_t *sl)
- {
- spin_lock_irq(&sl->lock);
- - write_seqcount_begin(&sl->seqcount);
- + __raw_write_seqcount_begin(&sl->seqcount);
- }
-
- static inline void write_sequnlock_irq(seqlock_t *sl)
- {
- - write_seqcount_end(&sl->seqcount);
- + __raw_write_seqcount_end(&sl->seqcount);
- spin_unlock_irq(&sl->lock);
- }
-
- @@ -481,7 +513,7 @@
- unsigned long flags;
-
- spin_lock_irqsave(&sl->lock, flags);
- - write_seqcount_begin(&sl->seqcount);
- + __raw_write_seqcount_begin(&sl->seqcount);
- return flags;
- }
-
- @@ -491,7 +523,7 @@
- static inline void
- write_sequnlock_irqrestore(seqlock_t *sl, unsigned long flags)
- {
- - write_seqcount_end(&sl->seqcount);
- + __raw_write_seqcount_end(&sl->seqcount);
- spin_unlock_irqrestore(&sl->lock, flags);
- }
-
- diff -Nur linux-4.4.28.orig/include/linux/signal.h linux-4.4.28/include/linux/signal.h
- --- linux-4.4.28.orig/include/linux/signal.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/signal.h 2016-11-01 21:26:58.744340223 +0100
- @@ -233,6 +233,7 @@
- }
-
- extern void flush_sigqueue(struct sigpending *queue);
- +extern void flush_task_sigqueue(struct task_struct *tsk);
-
- /* Test if 'sig' is valid signal. Use this instead of testing _NSIG directly */
- static inline int valid_signal(unsigned long sig)
- diff -Nur linux-4.4.28.orig/include/linux/skbuff.h linux-4.4.28/include/linux/skbuff.h
- --- linux-4.4.28.orig/include/linux/skbuff.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/skbuff.h 2016-11-01 21:26:58.744340223 +0100
- @@ -203,6 +203,7 @@
-
- __u32 qlen;
- spinlock_t lock;
- + raw_spinlock_t raw_lock;
- };
-
- struct sk_buff;
- @@ -1465,6 +1466,12 @@
- __skb_queue_head_init(list);
- }
-
- +static inline void skb_queue_head_init_raw(struct sk_buff_head *list)
- +{
- + raw_spin_lock_init(&list->raw_lock);
- + __skb_queue_head_init(list);
- +}
- +
- static inline void skb_queue_head_init_class(struct sk_buff_head *list,
- struct lock_class_key *class)
- {
- diff -Nur linux-4.4.28.orig/include/linux/smp.h linux-4.4.28/include/linux/smp.h
- --- linux-4.4.28.orig/include/linux/smp.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/smp.h 2016-11-01 21:26:58.744340223 +0100
- @@ -185,6 +185,9 @@
- #define get_cpu() ({ preempt_disable(); smp_processor_id(); })
- #define put_cpu() preempt_enable()
-
- +#define get_cpu_light() ({ migrate_disable(); smp_processor_id(); })
- +#define put_cpu_light() migrate_enable()
- +
- /*
- * Callback to arch code if there's nosmp or maxcpus=0 on the
- * boot command line:
- diff -Nur linux-4.4.28.orig/include/linux/spinlock_api_smp.h linux-4.4.28/include/linux/spinlock_api_smp.h
- --- linux-4.4.28.orig/include/linux/spinlock_api_smp.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/spinlock_api_smp.h 2016-11-01 21:26:58.744340223 +0100
- @@ -189,6 +189,8 @@
- return 0;
- }
-
- -#include <linux/rwlock_api_smp.h>
- +#ifndef CONFIG_PREEMPT_RT_FULL
- +# include <linux/rwlock_api_smp.h>
- +#endif
-
- #endif /* __LINUX_SPINLOCK_API_SMP_H */
- diff -Nur linux-4.4.28.orig/include/linux/spinlock.h linux-4.4.28/include/linux/spinlock.h
- --- linux-4.4.28.orig/include/linux/spinlock.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/spinlock.h 2016-11-01 21:26:58.744340223 +0100
- @@ -271,7 +271,11 @@
- #define raw_spin_can_lock(lock) (!raw_spin_is_locked(lock))
-
- /* Include rwlock functions */
- -#include <linux/rwlock.h>
- +#ifdef CONFIG_PREEMPT_RT_FULL
- +# include <linux/rwlock_rt.h>
- +#else
- +# include <linux/rwlock.h>
- +#endif
-
- /*
- * Pull the _spin_*()/_read_*()/_write_*() functions/declarations:
- @@ -282,6 +286,10 @@
- # include <linux/spinlock_api_up.h>
- #endif
-
- +#ifdef CONFIG_PREEMPT_RT_FULL
- +# include <linux/spinlock_rt.h>
- +#else /* PREEMPT_RT_FULL */
- +
- /*
- * Map the spin_lock functions to the raw variants for PREEMPT_RT=n
- */
- @@ -347,6 +355,12 @@
- raw_spin_unlock(&lock->rlock);
- }
-
- +static __always_inline int spin_unlock_no_deboost(spinlock_t *lock)
- +{
- + raw_spin_unlock(&lock->rlock);
- + return 0;
- +}
- +
- static __always_inline void spin_unlock_bh(spinlock_t *lock)
- {
- raw_spin_unlock_bh(&lock->rlock);
- @@ -416,4 +430,6 @@
- #define atomic_dec_and_lock(atomic, lock) \
- __cond_lock(lock, _atomic_dec_and_lock(atomic, lock))
-
- +#endif /* !PREEMPT_RT_FULL */
- +
- #endif /* __LINUX_SPINLOCK_H */
- diff -Nur linux-4.4.28.orig/include/linux/spinlock_rt.h linux-4.4.28/include/linux/spinlock_rt.h
- --- linux-4.4.28.orig/include/linux/spinlock_rt.h 1970-01-01 01:00:00.000000000 +0100
- +++ linux-4.4.28/include/linux/spinlock_rt.h 2016-11-01 21:26:58.744340223 +0100
- @@ -0,0 +1,165 @@
- +#ifndef __LINUX_SPINLOCK_RT_H
- +#define __LINUX_SPINLOCK_RT_H
- +
- +#ifndef __LINUX_SPINLOCK_H
- +#error Do not include directly. Use spinlock.h
- +#endif
- +
- +#include <linux/bug.h>
- +
- +extern void
- +__rt_spin_lock_init(spinlock_t *lock, char *name, struct lock_class_key *key);
- +
- +#define spin_lock_init(slock) \
- +do { \
- + static struct lock_class_key __key; \
- + \
- + rt_mutex_init(&(slock)->lock); \
- + __rt_spin_lock_init(slock, #slock, &__key); \
- +} while (0)
- +
- +void __lockfunc rt_spin_lock__no_mg(spinlock_t *lock);
- +void __lockfunc rt_spin_unlock__no_mg(spinlock_t *lock);
- +int __lockfunc rt_spin_trylock__no_mg(spinlock_t *lock);
- +
- +extern void __lockfunc rt_spin_lock(spinlock_t *lock);
- +extern unsigned long __lockfunc rt_spin_lock_trace_flags(spinlock_t *lock);
- +extern void __lockfunc rt_spin_lock_nested(spinlock_t *lock, int subclass);
- +extern void __lockfunc rt_spin_unlock(spinlock_t *lock);
- +extern int __lockfunc rt_spin_unlock_no_deboost(spinlock_t *lock);
- +extern void __lockfunc rt_spin_unlock_wait(spinlock_t *lock);
- +extern int __lockfunc rt_spin_trylock_irqsave(spinlock_t *lock, unsigned long *flags);
- +extern int __lockfunc rt_spin_trylock_bh(spinlock_t *lock);
- +extern int __lockfunc rt_spin_trylock(spinlock_t *lock);
- +extern int atomic_dec_and_spin_lock(atomic_t *atomic, spinlock_t *lock);
- +
- +/*
- + * lockdep-less calls, for derived types like rwlock:
- + * (for trylock they can use rt_mutex_trylock() directly.
- + */
- +extern void __lockfunc __rt_spin_lock__no_mg(struct rt_mutex *lock);
- +extern void __lockfunc __rt_spin_lock(struct rt_mutex *lock);
- +extern void __lockfunc __rt_spin_unlock(struct rt_mutex *lock);
- +extern int __lockfunc __rt_spin_trylock(struct rt_mutex *lock);
- +
- +#define spin_lock(lock) rt_spin_lock(lock)
- +
- +#define spin_lock_bh(lock) \
- + do { \
- + local_bh_disable(); \
- + rt_spin_lock(lock); \
- + } while (0)
- +
- +#define spin_lock_irq(lock) spin_lock(lock)
- +
- +#define spin_do_trylock(lock) __cond_lock(lock, rt_spin_trylock(lock))
- +
- +#define spin_trylock(lock) \
- +({ \
- + int __locked; \
- + __locked = spin_do_trylock(lock); \
- + __locked; \
- +})
- +
- +#ifdef CONFIG_LOCKDEP
- +# define spin_lock_nested(lock, subclass) \
- + do { \
- + rt_spin_lock_nested(lock, subclass); \
- + } while (0)
- +
- +#define spin_lock_bh_nested(lock, subclass) \
- + do { \
- + local_bh_disable(); \
- + rt_spin_lock_nested(lock, subclass); \
- + } while (0)
- +
- +# define spin_lock_irqsave_nested(lock, flags, subclass) \
- + do { \
- + typecheck(unsigned long, flags); \
- + flags = 0; \
- + rt_spin_lock_nested(lock, subclass); \
- + } while (0)
- +#else
- +# define spin_lock_nested(lock, subclass) spin_lock(lock)
- +# define spin_lock_bh_nested(lock, subclass) spin_lock_bh(lock)
- +
- +# define spin_lock_irqsave_nested(lock, flags, subclass) \
- + do { \
- + typecheck(unsigned long, flags); \
- + flags = 0; \
- + spin_lock(lock); \
- + } while (0)
- +#endif
- +
- +#define spin_lock_irqsave(lock, flags) \
- + do { \
- + typecheck(unsigned long, flags); \
- + flags = 0; \
- + spin_lock(lock); \
- + } while (0)
- +
- +static inline unsigned long spin_lock_trace_flags(spinlock_t *lock)
- +{
- + unsigned long flags = 0;
- +#ifdef CONFIG_TRACE_IRQFLAGS
- + flags = rt_spin_lock_trace_flags(lock);
- +#else
- + spin_lock(lock); /* lock_local */
- +#endif
- + return flags;
- +}
- +
- +/* FIXME: we need rt_spin_lock_nest_lock */
- +#define spin_lock_nest_lock(lock, nest_lock) spin_lock_nested(lock, 0)
- +
- +#define spin_unlock(lock) rt_spin_unlock(lock)
- +#define spin_unlock_no_deboost(lock) rt_spin_unlock_no_deboost(lock)
- +
- +#define spin_unlock_bh(lock) \
- + do { \
- + rt_spin_unlock(lock); \
- + local_bh_enable(); \
- + } while (0)
- +
- +#define spin_unlock_irq(lock) spin_unlock(lock)
- +
- +#define spin_unlock_irqrestore(lock, flags) \
- + do { \
- + typecheck(unsigned long, flags); \
- + (void) flags; \
- + spin_unlock(lock); \
- + } while (0)
- +
- +#define spin_trylock_bh(lock) __cond_lock(lock, rt_spin_trylock_bh(lock))
- +#define spin_trylock_irq(lock) spin_trylock(lock)
- +
- +#define spin_trylock_irqsave(lock, flags) \
- + rt_spin_trylock_irqsave(lock, &(flags))
- +
- +#define spin_unlock_wait(lock) rt_spin_unlock_wait(lock)
- +
- +#ifdef CONFIG_GENERIC_LOCKBREAK
- +# define spin_is_contended(lock) ((lock)->break_lock)
- +#else
- +# define spin_is_contended(lock) (((void)(lock), 0))
- +#endif
- +
- +static inline int spin_can_lock(spinlock_t *lock)
- +{
- + return !rt_mutex_is_locked(&lock->lock);
- +}
- +
- +static inline int spin_is_locked(spinlock_t *lock)
- +{
- + return rt_mutex_is_locked(&lock->lock);
- +}
- +
- +static inline void assert_spin_locked(spinlock_t *lock)
- +{
- + BUG_ON(!spin_is_locked(lock));
- +}
- +
- +#define atomic_dec_and_lock(atomic, lock) \
- + atomic_dec_and_spin_lock(atomic, lock)
- +
- +#endif
- diff -Nur linux-4.4.28.orig/include/linux/spinlock_types.h linux-4.4.28/include/linux/spinlock_types.h
- --- linux-4.4.28.orig/include/linux/spinlock_types.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/spinlock_types.h 2016-11-01 21:26:58.744340223 +0100
- @@ -9,80 +9,15 @@
- * Released under the General Public License (GPL).
- */
-
- -#if defined(CONFIG_SMP)
- -# include <asm/spinlock_types.h>
- -#else
- -# include <linux/spinlock_types_up.h>
- -#endif
- -
- -#include <linux/lockdep.h>
- -
- -typedef struct raw_spinlock {
- - arch_spinlock_t raw_lock;
- -#ifdef CONFIG_GENERIC_LOCKBREAK
- - unsigned int break_lock;
- -#endif
- -#ifdef CONFIG_DEBUG_SPINLOCK
- - unsigned int magic, owner_cpu;
- - void *owner;
- -#endif
- -#ifdef CONFIG_DEBUG_LOCK_ALLOC
- - struct lockdep_map dep_map;
- -#endif
- -} raw_spinlock_t;
- -
- -#define SPINLOCK_MAGIC 0xdead4ead
- -
- -#define SPINLOCK_OWNER_INIT ((void *)-1L)
- -
- -#ifdef CONFIG_DEBUG_LOCK_ALLOC
- -# define SPIN_DEP_MAP_INIT(lockname) .dep_map = { .name = #lockname }
- -#else
- -# define SPIN_DEP_MAP_INIT(lockname)
- -#endif
- +#include <linux/spinlock_types_raw.h>
-
- -#ifdef CONFIG_DEBUG_SPINLOCK
- -# define SPIN_DEBUG_INIT(lockname) \
- - .magic = SPINLOCK_MAGIC, \
- - .owner_cpu = -1, \
- - .owner = SPINLOCK_OWNER_INIT,
- +#ifndef CONFIG_PREEMPT_RT_FULL
- +# include <linux/spinlock_types_nort.h>
- +# include <linux/rwlock_types.h>
- #else
- -# define SPIN_DEBUG_INIT(lockname)
- +# include <linux/rtmutex.h>
- +# include <linux/spinlock_types_rt.h>
- +# include <linux/rwlock_types_rt.h>
- #endif
-
- -#define __RAW_SPIN_LOCK_INITIALIZER(lockname) \
- - { \
- - .raw_lock = __ARCH_SPIN_LOCK_UNLOCKED, \
- - SPIN_DEBUG_INIT(lockname) \
- - SPIN_DEP_MAP_INIT(lockname) }
- -
- -#define __RAW_SPIN_LOCK_UNLOCKED(lockname) \
- - (raw_spinlock_t) __RAW_SPIN_LOCK_INITIALIZER(lockname)
- -
- -#define DEFINE_RAW_SPINLOCK(x) raw_spinlock_t x = __RAW_SPIN_LOCK_UNLOCKED(x)
- -
- -typedef struct spinlock {
- - union {
- - struct raw_spinlock rlock;
- -
- -#ifdef CONFIG_DEBUG_LOCK_ALLOC
- -# define LOCK_PADSIZE (offsetof(struct raw_spinlock, dep_map))
- - struct {
- - u8 __padding[LOCK_PADSIZE];
- - struct lockdep_map dep_map;
- - };
- -#endif
- - };
- -} spinlock_t;
- -
- -#define __SPIN_LOCK_INITIALIZER(lockname) \
- - { { .rlock = __RAW_SPIN_LOCK_INITIALIZER(lockname) } }
- -
- -#define __SPIN_LOCK_UNLOCKED(lockname) \
- - (spinlock_t ) __SPIN_LOCK_INITIALIZER(lockname)
- -
- -#define DEFINE_SPINLOCK(x) spinlock_t x = __SPIN_LOCK_UNLOCKED(x)
- -
- -#include <linux/rwlock_types.h>
- -
- #endif /* __LINUX_SPINLOCK_TYPES_H */
- diff -Nur linux-4.4.28.orig/include/linux/spinlock_types_nort.h linux-4.4.28/include/linux/spinlock_types_nort.h
- --- linux-4.4.28.orig/include/linux/spinlock_types_nort.h 1970-01-01 01:00:00.000000000 +0100
- +++ linux-4.4.28/include/linux/spinlock_types_nort.h 2016-11-01 21:26:58.744340223 +0100
- @@ -0,0 +1,33 @@
- +#ifndef __LINUX_SPINLOCK_TYPES_NORT_H
- +#define __LINUX_SPINLOCK_TYPES_NORT_H
- +
- +#ifndef __LINUX_SPINLOCK_TYPES_H
- +#error "Do not include directly. Include spinlock_types.h instead"
- +#endif
- +
- +/*
- + * The non RT version maps spinlocks to raw_spinlocks
- + */
- +typedef struct spinlock {
- + union {
- + struct raw_spinlock rlock;
- +
- +#ifdef CONFIG_DEBUG_LOCK_ALLOC
- +# define LOCK_PADSIZE (offsetof(struct raw_spinlock, dep_map))
- + struct {
- + u8 __padding[LOCK_PADSIZE];
- + struct lockdep_map dep_map;
- + };
- +#endif
- + };
- +} spinlock_t;
- +
- +#define __SPIN_LOCK_INITIALIZER(lockname) \
- + { { .rlock = __RAW_SPIN_LOCK_INITIALIZER(lockname) } }
- +
- +#define __SPIN_LOCK_UNLOCKED(lockname) \
- + (spinlock_t ) __SPIN_LOCK_INITIALIZER(lockname)
- +
- +#define DEFINE_SPINLOCK(x) spinlock_t x = __SPIN_LOCK_UNLOCKED(x)
- +
- +#endif
- diff -Nur linux-4.4.28.orig/include/linux/spinlock_types_raw.h linux-4.4.28/include/linux/spinlock_types_raw.h
- --- linux-4.4.28.orig/include/linux/spinlock_types_raw.h 1970-01-01 01:00:00.000000000 +0100
- +++ linux-4.4.28/include/linux/spinlock_types_raw.h 2016-11-01 21:26:58.744340223 +0100
- @@ -0,0 +1,56 @@
- +#ifndef __LINUX_SPINLOCK_TYPES_RAW_H
- +#define __LINUX_SPINLOCK_TYPES_RAW_H
- +
- +#if defined(CONFIG_SMP)
- +# include <asm/spinlock_types.h>
- +#else
- +# include <linux/spinlock_types_up.h>
- +#endif
- +
- +#include <linux/lockdep.h>
- +
- +typedef struct raw_spinlock {
- + arch_spinlock_t raw_lock;
- +#ifdef CONFIG_GENERIC_LOCKBREAK
- + unsigned int break_lock;
- +#endif
- +#ifdef CONFIG_DEBUG_SPINLOCK
- + unsigned int magic, owner_cpu;
- + void *owner;
- +#endif
- +#ifdef CONFIG_DEBUG_LOCK_ALLOC
- + struct lockdep_map dep_map;
- +#endif
- +} raw_spinlock_t;
- +
- +#define SPINLOCK_MAGIC 0xdead4ead
- +
- +#define SPINLOCK_OWNER_INIT ((void *)-1L)
- +
- +#ifdef CONFIG_DEBUG_LOCK_ALLOC
- +# define SPIN_DEP_MAP_INIT(lockname) .dep_map = { .name = #lockname }
- +#else
- +# define SPIN_DEP_MAP_INIT(lockname)
- +#endif
- +
- +#ifdef CONFIG_DEBUG_SPINLOCK
- +# define SPIN_DEBUG_INIT(lockname) \
- + .magic = SPINLOCK_MAGIC, \
- + .owner_cpu = -1, \
- + .owner = SPINLOCK_OWNER_INIT,
- +#else
- +# define SPIN_DEBUG_INIT(lockname)
- +#endif
- +
- +#define __RAW_SPIN_LOCK_INITIALIZER(lockname) \
- + { \
- + .raw_lock = __ARCH_SPIN_LOCK_UNLOCKED, \
- + SPIN_DEBUG_INIT(lockname) \
- + SPIN_DEP_MAP_INIT(lockname) }
- +
- +#define __RAW_SPIN_LOCK_UNLOCKED(lockname) \
- + (raw_spinlock_t) __RAW_SPIN_LOCK_INITIALIZER(lockname)
- +
- +#define DEFINE_RAW_SPINLOCK(x) raw_spinlock_t x = __RAW_SPIN_LOCK_UNLOCKED(x)
- +
- +#endif
- diff -Nur linux-4.4.28.orig/include/linux/spinlock_types_rt.h linux-4.4.28/include/linux/spinlock_types_rt.h
- --- linux-4.4.28.orig/include/linux/spinlock_types_rt.h 1970-01-01 01:00:00.000000000 +0100
- +++ linux-4.4.28/include/linux/spinlock_types_rt.h 2016-11-01 21:26:58.744340223 +0100
- @@ -0,0 +1,51 @@
- +#ifndef __LINUX_SPINLOCK_TYPES_RT_H
- +#define __LINUX_SPINLOCK_TYPES_RT_H
- +
- +#ifndef __LINUX_SPINLOCK_TYPES_H
- +#error "Do not include directly. Include spinlock_types.h instead"
- +#endif
- +
- +#include <linux/cache.h>
- +
- +/*
- + * PREEMPT_RT: spinlocks - an RT mutex plus lock-break field:
- + */
- +typedef struct spinlock {
- + struct rt_mutex lock;
- + unsigned int break_lock;
- +#ifdef CONFIG_DEBUG_LOCK_ALLOC
- + struct lockdep_map dep_map;
- +#endif
- +} spinlock_t;
- +
- +#ifdef CONFIG_DEBUG_RT_MUTEXES
- +# define __RT_SPIN_INITIALIZER(name) \
- + { \
- + .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock), \
- + .save_state = 1, \
- + .file = __FILE__, \
- + .line = __LINE__ , \
- + }
- +#else
- +# define __RT_SPIN_INITIALIZER(name) \
- + { \
- + .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock), \
- + .save_state = 1, \
- + }
- +#endif
- +
- +/*
- +.wait_list = PLIST_HEAD_INIT_RAW((name).lock.wait_list, (name).lock.wait_lock)
- +*/
- +
- +#define __SPIN_LOCK_UNLOCKED(name) \
- + { .lock = __RT_SPIN_INITIALIZER(name.lock), \
- + SPIN_DEP_MAP_INIT(name) }
- +
- +#define __DEFINE_SPINLOCK(name) \
- + spinlock_t name = __SPIN_LOCK_UNLOCKED(name)
- +
- +#define DEFINE_SPINLOCK(name) \
- + spinlock_t name __cacheline_aligned_in_smp = __SPIN_LOCK_UNLOCKED(name)
- +
- +#endif
- diff -Nur linux-4.4.28.orig/include/linux/srcu.h linux-4.4.28/include/linux/srcu.h
- --- linux-4.4.28.orig/include/linux/srcu.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/srcu.h 2016-11-01 21:26:58.744340223 +0100
- @@ -84,10 +84,10 @@
-
- void process_srcu(struct work_struct *work);
-
- -#define __SRCU_STRUCT_INIT(name) \
- +#define __SRCU_STRUCT_INIT(name, pcpu_name) \
- { \
- .completed = -300, \
- - .per_cpu_ref = &name##_srcu_array, \
- + .per_cpu_ref = &pcpu_name, \
- .queue_lock = __SPIN_LOCK_UNLOCKED(name.queue_lock), \
- .running = false, \
- .batch_queue = RCU_BATCH_INIT(name.batch_queue), \
- @@ -104,7 +104,7 @@
- */
- #define __DEFINE_SRCU(name, is_static) \
- static DEFINE_PER_CPU(struct srcu_struct_array, name##_srcu_array);\
- - is_static struct srcu_struct name = __SRCU_STRUCT_INIT(name)
- + is_static struct srcu_struct name = __SRCU_STRUCT_INIT(name, name##_srcu_array)
- #define DEFINE_SRCU(name) __DEFINE_SRCU(name, /* not static */)
- #define DEFINE_STATIC_SRCU(name) __DEFINE_SRCU(name, static)
-
- diff -Nur linux-4.4.28.orig/include/linux/suspend.h linux-4.4.28/include/linux/suspend.h
- --- linux-4.4.28.orig/include/linux/suspend.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/suspend.h 2016-11-01 21:26:58.748340476 +0100
- @@ -194,6 +194,12 @@
- void (*end)(void);
- };
-
- +#if defined(CONFIG_SUSPEND) || defined(CONFIG_HIBERNATION)
- +extern bool pm_in_action;
- +#else
- +# define pm_in_action false
- +#endif
- +
- #ifdef CONFIG_SUSPEND
- /**
- * suspend_set_ops - set platform dependent suspend operations
- diff -Nur linux-4.4.28.orig/include/linux/swait.h linux-4.4.28/include/linux/swait.h
- --- linux-4.4.28.orig/include/linux/swait.h 1970-01-01 01:00:00.000000000 +0100
- +++ linux-4.4.28/include/linux/swait.h 2016-11-01 21:26:58.748340476 +0100
- @@ -0,0 +1,173 @@
- +#ifndef _LINUX_SWAIT_H
- +#define _LINUX_SWAIT_H
- +
- +#include <linux/list.h>
- +#include <linux/stddef.h>
- +#include <linux/spinlock.h>
- +#include <asm/current.h>
- +
- +/*
- + * Simple wait queues
- + *
- + * While these are very similar to the other/complex wait queues (wait.h) the
- + * most important difference is that the simple waitqueue allows for
- + * deterministic behaviour -- IOW it has strictly bounded IRQ and lock hold
- + * times.
- + *
- + * In order to make this so, we had to drop a fair number of features of the
- + * other waitqueue code; notably:
- + *
- + * - mixing INTERRUPTIBLE and UNINTERRUPTIBLE sleeps on the same waitqueue;
- + * all wakeups are TASK_NORMAL in order to avoid O(n) lookups for the right
- + * sleeper state.
- + *
- + * - the exclusive mode; because this requires preserving the list order
- + * and this is hard.
- + *
- + * - custom wake functions; because you cannot give any guarantees about
- + * random code.
- + *
- + * As a side effect of this; the data structures are slimmer.
- + *
- + * One would recommend using this wait queue where possible.
- + */
- +
- +struct task_struct;
- +
- +struct swait_queue_head {
- + raw_spinlock_t lock;
- + struct list_head task_list;
- +};
- +
- +struct swait_queue {
- + struct task_struct *task;
- + struct list_head task_list;
- +};
- +
- +#define __SWAITQUEUE_INITIALIZER(name) { \
- + .task = current, \
- + .task_list = LIST_HEAD_INIT((name).task_list), \
- +}
- +
- +#define DECLARE_SWAITQUEUE(name) \
- + struct swait_queue name = __SWAITQUEUE_INITIALIZER(name)
- +
- +#define __SWAIT_QUEUE_HEAD_INITIALIZER(name) { \
- + .lock = __RAW_SPIN_LOCK_UNLOCKED(name.lock), \
- + .task_list = LIST_HEAD_INIT((name).task_list), \
- +}
- +
- +#define DECLARE_SWAIT_QUEUE_HEAD(name) \
- + struct swait_queue_head name = __SWAIT_QUEUE_HEAD_INITIALIZER(name)
- +
- +extern void __init_swait_queue_head(struct swait_queue_head *q, const char *name,
- + struct lock_class_key *key);
- +
- +#define init_swait_queue_head(q) \
- + do { \
- + static struct lock_class_key __key; \
- + __init_swait_queue_head((q), #q, &__key); \
- + } while (0)
- +
- +#ifdef CONFIG_LOCKDEP
- +# define __SWAIT_QUEUE_HEAD_INIT_ONSTACK(name) \
- + ({ init_swait_queue_head(&name); name; })
- +# define DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(name) \
- + struct swait_queue_head name = __SWAIT_QUEUE_HEAD_INIT_ONSTACK(name)
- +#else
- +# define DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(name) \
- + DECLARE_SWAIT_QUEUE_HEAD(name)
- +#endif
- +
- +static inline int swait_active(struct swait_queue_head *q)
- +{
- + return !list_empty(&q->task_list);
- +}
- +
- +extern void swake_up(struct swait_queue_head *q);
- +extern void swake_up_all(struct swait_queue_head *q);
- +extern void swake_up_locked(struct swait_queue_head *q);
- +extern void swake_up_all_locked(struct swait_queue_head *q);
- +
- +extern void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait);
- +extern void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int state);
- +extern long prepare_to_swait_event(struct swait_queue_head *q, struct swait_queue *wait, int state);
- +
- +extern void __finish_swait(struct swait_queue_head *q, struct swait_queue *wait);
- +extern void finish_swait(struct swait_queue_head *q, struct swait_queue *wait);
- +
- +/* as per ___wait_event() but for swait, therefore "exclusive == 0" */
- +#define ___swait_event(wq, condition, state, ret, cmd) \
- +({ \
- + struct swait_queue __wait; \
- + long __ret = ret; \
- + \
- + INIT_LIST_HEAD(&__wait.task_list); \
- + for (;;) { \
- + long __int = prepare_to_swait_event(&wq, &__wait, state);\
- + \
- + if (condition) \
- + break; \
- + \
- + if (___wait_is_interruptible(state) && __int) { \
- + __ret = __int; \
- + break; \
- + } \
- + \
- + cmd; \
- + } \
- + finish_swait(&wq, &__wait); \
- + __ret; \
- +})
- +
- +#define __swait_event(wq, condition) \
- + (void)___swait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0, \
- + schedule())
- +
- +#define swait_event(wq, condition) \
- +do { \
- + if (condition) \
- + break; \
- + __swait_event(wq, condition); \
- +} while (0)
- +
- +#define __swait_event_timeout(wq, condition, timeout) \
- + ___swait_event(wq, ___wait_cond_timeout(condition), \
- + TASK_UNINTERRUPTIBLE, timeout, \
- + __ret = schedule_timeout(__ret))
- +
- +#define swait_event_timeout(wq, condition, timeout) \
- +({ \
- + long __ret = timeout; \
- + if (!___wait_cond_timeout(condition)) \
- + __ret = __swait_event_timeout(wq, condition, timeout); \
- + __ret; \
- +})
- +
- +#define __swait_event_interruptible(wq, condition) \
- + ___swait_event(wq, condition, TASK_INTERRUPTIBLE, 0, \
- + schedule())
- +
- +#define swait_event_interruptible(wq, condition) \
- +({ \
- + int __ret = 0; \
- + if (!(condition)) \
- + __ret = __swait_event_interruptible(wq, condition); \
- + __ret; \
- +})
- +
- +#define __swait_event_interruptible_timeout(wq, condition, timeout) \
- + ___swait_event(wq, ___wait_cond_timeout(condition), \
- + TASK_INTERRUPTIBLE, timeout, \
- + __ret = schedule_timeout(__ret))
- +
- +#define swait_event_interruptible_timeout(wq, condition, timeout) \
- +({ \
- + long __ret = timeout; \
- + if (!___wait_cond_timeout(condition)) \
- + __ret = __swait_event_interruptible_timeout(wq, \
- + condition, timeout); \
- + __ret; \
- +})
- +
- +#endif /* _LINUX_SWAIT_H */
- diff -Nur linux-4.4.28.orig/include/linux/swap.h linux-4.4.28/include/linux/swap.h
- --- linux-4.4.28.orig/include/linux/swap.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/swap.h 2016-11-01 21:26:58.748340476 +0100
- @@ -11,6 +11,7 @@
- #include <linux/fs.h>
- #include <linux/atomic.h>
- #include <linux/page-flags.h>
- +#include <linux/locallock.h>
- #include <asm/page.h>
-
- struct notifier_block;
- @@ -252,7 +253,8 @@
- void *workingset_eviction(struct address_space *mapping, struct page *page);
- bool workingset_refault(void *shadow);
- void workingset_activation(struct page *page);
- -extern struct list_lru workingset_shadow_nodes;
- +extern struct list_lru __workingset_shadow_nodes;
- +DECLARE_LOCAL_IRQ_LOCK(workingset_shadow_lock);
-
- static inline unsigned int workingset_node_pages(struct radix_tree_node *node)
- {
- @@ -298,6 +300,7 @@
-
-
- /* linux/mm/swap.c */
- +DECLARE_LOCAL_IRQ_LOCK(swapvec_lock);
- extern void lru_cache_add(struct page *);
- extern void lru_cache_add_anon(struct page *page);
- extern void lru_cache_add_file(struct page *page);
- diff -Nur linux-4.4.28.orig/include/linux/swork.h linux-4.4.28/include/linux/swork.h
- --- linux-4.4.28.orig/include/linux/swork.h 1970-01-01 01:00:00.000000000 +0100
- +++ linux-4.4.28/include/linux/swork.h 2016-11-01 21:26:58.748340476 +0100
- @@ -0,0 +1,24 @@
- +#ifndef _LINUX_SWORK_H
- +#define _LINUX_SWORK_H
- +
- +#include <linux/list.h>
- +
- +struct swork_event {
- + struct list_head item;
- + unsigned long flags;
- + void (*func)(struct swork_event *);
- +};
- +
- +static inline void INIT_SWORK(struct swork_event *event,
- + void (*func)(struct swork_event *))
- +{
- + event->flags = 0;
- + event->func = func;
- +}
- +
- +bool swork_queue(struct swork_event *sev);
- +
- +int swork_get(void);
- +void swork_put(void);
- +
- +#endif /* _LINUX_SWORK_H */
- diff -Nur linux-4.4.28.orig/include/linux/thread_info.h linux-4.4.28/include/linux/thread_info.h
- --- linux-4.4.28.orig/include/linux/thread_info.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/thread_info.h 2016-11-01 21:26:58.748340476 +0100
- @@ -102,7 +102,17 @@
- #define test_thread_flag(flag) \
- test_ti_thread_flag(current_thread_info(), flag)
-
- -#define tif_need_resched() test_thread_flag(TIF_NEED_RESCHED)
- +#ifdef CONFIG_PREEMPT_LAZY
- +#define tif_need_resched() (test_thread_flag(TIF_NEED_RESCHED) || \
- + test_thread_flag(TIF_NEED_RESCHED_LAZY))
- +#define tif_need_resched_now() (test_thread_flag(TIF_NEED_RESCHED))
- +#define tif_need_resched_lazy() test_thread_flag(TIF_NEED_RESCHED_LAZY))
- +
- +#else
- +#define tif_need_resched() test_thread_flag(TIF_NEED_RESCHED)
- +#define tif_need_resched_now() test_thread_flag(TIF_NEED_RESCHED)
- +#define tif_need_resched_lazy() 0
- +#endif
-
- #if defined TIF_RESTORE_SIGMASK && !defined HAVE_SET_RESTORE_SIGMASK
- /*
- diff -Nur linux-4.4.28.orig/include/linux/timer.h linux-4.4.28/include/linux/timer.h
- --- linux-4.4.28.orig/include/linux/timer.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/timer.h 2016-11-01 21:26:58.748340476 +0100
- @@ -225,7 +225,7 @@
-
- extern int try_to_del_timer_sync(struct timer_list *timer);
-
- -#ifdef CONFIG_SMP
- +#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL)
- extern int del_timer_sync(struct timer_list *timer);
- #else
- # define del_timer_sync(t) del_timer(t)
- diff -Nur linux-4.4.28.orig/include/linux/trace_events.h linux-4.4.28/include/linux/trace_events.h
- --- linux-4.4.28.orig/include/linux/trace_events.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/trace_events.h 2016-11-01 21:26:58.748340476 +0100
- @@ -66,6 +66,9 @@
- unsigned char flags;
- unsigned char preempt_count;
- int pid;
- + unsigned short migrate_disable;
- + unsigned short padding;
- + unsigned char preempt_lazy_count;
- };
-
- #define TRACE_EVENT_TYPE_MAX \
- diff -Nur linux-4.4.28.orig/include/linux/uaccess.h linux-4.4.28/include/linux/uaccess.h
- --- linux-4.4.28.orig/include/linux/uaccess.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/uaccess.h 2016-11-01 21:26:58.748340476 +0100
- @@ -24,6 +24,7 @@
- */
- static inline void pagefault_disable(void)
- {
- + migrate_disable();
- pagefault_disabled_inc();
- /*
- * make sure to have issued the store before a pagefault
- @@ -40,6 +41,7 @@
- */
- barrier();
- pagefault_disabled_dec();
- + migrate_enable();
- }
-
- /*
- diff -Nur linux-4.4.28.orig/include/linux/uprobes.h linux-4.4.28/include/linux/uprobes.h
- --- linux-4.4.28.orig/include/linux/uprobes.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/uprobes.h 2016-11-01 21:26:58.748340476 +0100
- @@ -27,6 +27,7 @@
- #include <linux/errno.h>
- #include <linux/rbtree.h>
- #include <linux/types.h>
- +#include <linux/wait.h>
-
- struct vm_area_struct;
- struct mm_struct;
- diff -Nur linux-4.4.28.orig/include/linux/vmstat.h linux-4.4.28/include/linux/vmstat.h
- --- linux-4.4.28.orig/include/linux/vmstat.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/vmstat.h 2016-11-01 21:26:58.748340476 +0100
- @@ -33,7 +33,9 @@
- */
- static inline void __count_vm_event(enum vm_event_item item)
- {
- + preempt_disable_rt();
- raw_cpu_inc(vm_event_states.event[item]);
- + preempt_enable_rt();
- }
-
- static inline void count_vm_event(enum vm_event_item item)
- @@ -43,7 +45,9 @@
-
- static inline void __count_vm_events(enum vm_event_item item, long delta)
- {
- + preempt_disable_rt();
- raw_cpu_add(vm_event_states.event[item], delta);
- + preempt_enable_rt();
- }
-
- static inline void count_vm_events(enum vm_event_item item, long delta)
- diff -Nur linux-4.4.28.orig/include/linux/wait.h linux-4.4.28/include/linux/wait.h
- --- linux-4.4.28.orig/include/linux/wait.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/linux/wait.h 2016-11-01 21:26:58.748340476 +0100
- @@ -8,6 +8,7 @@
- #include <linux/spinlock.h>
- #include <asm/current.h>
- #include <uapi/linux/wait.h>
- +#include <linux/atomic.h>
-
- typedef struct __wait_queue wait_queue_t;
- typedef int (*wait_queue_func_t)(wait_queue_t *wait, unsigned mode, int flags, void *key);
- diff -Nur linux-4.4.28.orig/include/net/dst.h linux-4.4.28/include/net/dst.h
- --- linux-4.4.28.orig/include/net/dst.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/net/dst.h 2016-11-01 21:26:58.748340476 +0100
- @@ -437,7 +437,7 @@
- static inline int dst_neigh_output(struct dst_entry *dst, struct neighbour *n,
- struct sk_buff *skb)
- {
- - const struct hh_cache *hh;
- + struct hh_cache *hh;
-
- if (dst->pending_confirm) {
- unsigned long now = jiffies;
- diff -Nur linux-4.4.28.orig/include/net/neighbour.h linux-4.4.28/include/net/neighbour.h
- --- linux-4.4.28.orig/include/net/neighbour.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/net/neighbour.h 2016-11-01 21:26:58.748340476 +0100
- @@ -446,7 +446,7 @@
- }
- #endif
-
- -static inline int neigh_hh_output(const struct hh_cache *hh, struct sk_buff *skb)
- +static inline int neigh_hh_output(struct hh_cache *hh, struct sk_buff *skb)
- {
- unsigned int seq;
- int hh_len;
- @@ -501,7 +501,7 @@
-
- #define NEIGH_CB(skb) ((struct neighbour_cb *)(skb)->cb)
-
- -static inline void neigh_ha_snapshot(char *dst, const struct neighbour *n,
- +static inline void neigh_ha_snapshot(char *dst, struct neighbour *n,
- const struct net_device *dev)
- {
- unsigned int seq;
- diff -Nur linux-4.4.28.orig/include/net/netns/ipv4.h linux-4.4.28/include/net/netns/ipv4.h
- --- linux-4.4.28.orig/include/net/netns/ipv4.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/net/netns/ipv4.h 2016-11-01 21:26:58.748340476 +0100
- @@ -70,6 +70,7 @@
-
- int sysctl_icmp_echo_ignore_all;
- int sysctl_icmp_echo_ignore_broadcasts;
- + int sysctl_icmp_echo_sysrq;
- int sysctl_icmp_ignore_bogus_error_responses;
- int sysctl_icmp_ratelimit;
- int sysctl_icmp_ratemask;
- diff -Nur linux-4.4.28.orig/include/trace/events/hist.h linux-4.4.28/include/trace/events/hist.h
- --- linux-4.4.28.orig/include/trace/events/hist.h 1970-01-01 01:00:00.000000000 +0100
- +++ linux-4.4.28/include/trace/events/hist.h 2016-11-01 21:26:58.748340476 +0100
- @@ -0,0 +1,73 @@
- +#undef TRACE_SYSTEM
- +#define TRACE_SYSTEM hist
- +
- +#if !defined(_TRACE_HIST_H) || defined(TRACE_HEADER_MULTI_READ)
- +#define _TRACE_HIST_H
- +
- +#include "latency_hist.h"
- +#include <linux/tracepoint.h>
- +
- +#if !defined(CONFIG_PREEMPT_OFF_HIST) && !defined(CONFIG_INTERRUPT_OFF_HIST)
- +#define trace_preemptirqsoff_hist(a, b)
- +#define trace_preemptirqsoff_hist_rcuidle(a, b)
- +#else
- +TRACE_EVENT(preemptirqsoff_hist,
- +
- + TP_PROTO(int reason, int starthist),
- +
- + TP_ARGS(reason, starthist),
- +
- + TP_STRUCT__entry(
- + __field(int, reason)
- + __field(int, starthist)
- + ),
- +
- + TP_fast_assign(
- + __entry->reason = reason;
- + __entry->starthist = starthist;
- + ),
- +
- + TP_printk("reason=%s starthist=%s", getaction(__entry->reason),
- + __entry->starthist ? "start" : "stop")
- +);
- +#endif
- +
- +#ifndef CONFIG_MISSED_TIMER_OFFSETS_HIST
- +#define trace_hrtimer_interrupt(a, b, c, d)
- +#else
- +TRACE_EVENT(hrtimer_interrupt,
- +
- + TP_PROTO(int cpu, long long offset, struct task_struct *curr,
- + struct task_struct *task),
- +
- + TP_ARGS(cpu, offset, curr, task),
- +
- + TP_STRUCT__entry(
- + __field(int, cpu)
- + __field(long long, offset)
- + __array(char, ccomm, TASK_COMM_LEN)
- + __field(int, cprio)
- + __array(char, tcomm, TASK_COMM_LEN)
- + __field(int, tprio)
- + ),
- +
- + TP_fast_assign(
- + __entry->cpu = cpu;
- + __entry->offset = offset;
- + memcpy(__entry->ccomm, curr->comm, TASK_COMM_LEN);
- + __entry->cprio = curr->prio;
- + memcpy(__entry->tcomm, task != NULL ? task->comm : "<none>",
- + task != NULL ? TASK_COMM_LEN : 7);
- + __entry->tprio = task != NULL ? task->prio : -1;
- + ),
- +
- + TP_printk("cpu=%d offset=%lld curr=%s[%d] thread=%s[%d]",
- + __entry->cpu, __entry->offset, __entry->ccomm,
- + __entry->cprio, __entry->tcomm, __entry->tprio)
- +);
- +#endif
- +
- +#endif /* _TRACE_HIST_H */
- +
- +/* This part must be outside protection */
- +#include <trace/define_trace.h>
- diff -Nur linux-4.4.28.orig/include/trace/events/latency_hist.h linux-4.4.28/include/trace/events/latency_hist.h
- --- linux-4.4.28.orig/include/trace/events/latency_hist.h 1970-01-01 01:00:00.000000000 +0100
- +++ linux-4.4.28/include/trace/events/latency_hist.h 2016-11-01 21:26:58.752340732 +0100
- @@ -0,0 +1,29 @@
- +#ifndef _LATENCY_HIST_H
- +#define _LATENCY_HIST_H
- +
- +enum hist_action {
- + IRQS_ON,
- + PREEMPT_ON,
- + TRACE_STOP,
- + IRQS_OFF,
- + PREEMPT_OFF,
- + TRACE_START,
- +};
- +
- +static char *actions[] = {
- + "IRQS_ON",
- + "PREEMPT_ON",
- + "TRACE_STOP",
- + "IRQS_OFF",
- + "PREEMPT_OFF",
- + "TRACE_START",
- +};
- +
- +static inline char *getaction(int action)
- +{
- + if (action >= 0 && action <= sizeof(actions)/sizeof(actions[0]))
- + return actions[action];
- + return "unknown";
- +}
- +
- +#endif /* _LATENCY_HIST_H */
- diff -Nur linux-4.4.28.orig/include/trace/events/writeback.h linux-4.4.28/include/trace/events/writeback.h
- --- linux-4.4.28.orig/include/trace/events/writeback.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/include/trace/events/writeback.h 2016-11-01 21:26:58.752340732 +0100
- @@ -134,58 +134,28 @@
- #ifdef CREATE_TRACE_POINTS
- #ifdef CONFIG_CGROUP_WRITEBACK
-
- -static inline size_t __trace_wb_cgroup_size(struct bdi_writeback *wb)
- +static inline unsigned int __trace_wb_assign_cgroup(struct bdi_writeback *wb)
- {
- - return kernfs_path_len(wb->memcg_css->cgroup->kn) + 1;
- + return wb->memcg_css->cgroup->kn->ino;
- }
-
- -static inline void __trace_wb_assign_cgroup(char *buf, struct bdi_writeback *wb)
- -{
- - struct cgroup *cgrp = wb->memcg_css->cgroup;
- - char *path;
- -
- - path = cgroup_path(cgrp, buf, kernfs_path_len(cgrp->kn) + 1);
- - WARN_ON_ONCE(path != buf);
- -}
- -
- -static inline size_t __trace_wbc_cgroup_size(struct writeback_control *wbc)
- -{
- - if (wbc->wb)
- - return __trace_wb_cgroup_size(wbc->wb);
- - else
- - return 2;
- -}
- -
- -static inline void __trace_wbc_assign_cgroup(char *buf,
- - struct writeback_control *wbc)
- +static inline unsigned int __trace_wbc_assign_cgroup(struct writeback_control *wbc)
- {
- if (wbc->wb)
- - __trace_wb_assign_cgroup(buf, wbc->wb);
- + return __trace_wb_assign_cgroup(wbc->wb);
- else
- - strcpy(buf, "/");
- + return -1U;
- }
- -
- #else /* CONFIG_CGROUP_WRITEBACK */
-
- -static inline size_t __trace_wb_cgroup_size(struct bdi_writeback *wb)
- -{
- - return 2;
- -}
- -
- -static inline void __trace_wb_assign_cgroup(char *buf, struct bdi_writeback *wb)
- -{
- - strcpy(buf, "/");
- -}
- -
- -static inline size_t __trace_wbc_cgroup_size(struct writeback_control *wbc)
- +static inline unsigned int __trace_wb_assign_cgroup(struct bdi_writeback *wb)
- {
- - return 2;
- + return -1U;
- }
-
- -static inline void __trace_wbc_assign_cgroup(char *buf,
- - struct writeback_control *wbc)
- +static inline unsigned int __trace_wbc_assign_cgroup(struct writeback_control *wbc)
- {
- - strcpy(buf, "/");
- + return -1U;
- }
-
- #endif /* CONFIG_CGROUP_WRITEBACK */
- @@ -201,7 +171,7 @@
- __array(char, name, 32)
- __field(unsigned long, ino)
- __field(int, sync_mode)
- - __dynamic_array(char, cgroup, __trace_wbc_cgroup_size(wbc))
- + __field(unsigned int, cgroup_ino)
- ),
-
- TP_fast_assign(
- @@ -209,14 +179,14 @@
- dev_name(inode_to_bdi(inode)->dev), 32);
- __entry->ino = inode->i_ino;
- __entry->sync_mode = wbc->sync_mode;
- - __trace_wbc_assign_cgroup(__get_str(cgroup), wbc);
- + __entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc);
- ),
-
- - TP_printk("bdi %s: ino=%lu sync_mode=%d cgroup=%s",
- + TP_printk("bdi %s: ino=%lu sync_mode=%d cgroup_ino=%u",
- __entry->name,
- __entry->ino,
- __entry->sync_mode,
- - __get_str(cgroup)
- + __entry->cgroup_ino
- )
- );
-
- @@ -246,7 +216,7 @@
- __field(int, range_cyclic)
- __field(int, for_background)
- __field(int, reason)
- - __dynamic_array(char, cgroup, __trace_wb_cgroup_size(wb))
- + __field(unsigned int, cgroup_ino)
- ),
- TP_fast_assign(
- strncpy(__entry->name,
- @@ -258,10 +228,10 @@
- __entry->range_cyclic = work->range_cyclic;
- __entry->for_background = work->for_background;
- __entry->reason = work->reason;
- - __trace_wb_assign_cgroup(__get_str(cgroup), wb);
- + __entry->cgroup_ino = __trace_wb_assign_cgroup(wb);
- ),
- TP_printk("bdi %s: sb_dev %d:%d nr_pages=%ld sync_mode=%d "
- - "kupdate=%d range_cyclic=%d background=%d reason=%s cgroup=%s",
- + "kupdate=%d range_cyclic=%d background=%d reason=%s cgroup_ino=%u",
- __entry->name,
- MAJOR(__entry->sb_dev), MINOR(__entry->sb_dev),
- __entry->nr_pages,
- @@ -270,7 +240,7 @@
- __entry->range_cyclic,
- __entry->for_background,
- __print_symbolic(__entry->reason, WB_WORK_REASON),
- - __get_str(cgroup)
- + __entry->cgroup_ino
- )
- );
- #define DEFINE_WRITEBACK_WORK_EVENT(name) \
- @@ -300,15 +270,15 @@
- TP_ARGS(wb),
- TP_STRUCT__entry(
- __array(char, name, 32)
- - __dynamic_array(char, cgroup, __trace_wb_cgroup_size(wb))
- + __field(unsigned int, cgroup_ino)
- ),
- TP_fast_assign(
- strncpy(__entry->name, dev_name(wb->bdi->dev), 32);
- - __trace_wb_assign_cgroup(__get_str(cgroup), wb);
- + __entry->cgroup_ino = __trace_wb_assign_cgroup(wb);
- ),
- - TP_printk("bdi %s: cgroup=%s",
- + TP_printk("bdi %s: cgroup_ino=%u",
- __entry->name,
- - __get_str(cgroup)
- + __entry->cgroup_ino
- )
- );
- #define DEFINE_WRITEBACK_EVENT(name) \
- @@ -347,7 +317,7 @@
- __field(int, range_cyclic)
- __field(long, range_start)
- __field(long, range_end)
- - __dynamic_array(char, cgroup, __trace_wbc_cgroup_size(wbc))
- + __field(unsigned int, cgroup_ino)
- ),
-
- TP_fast_assign(
- @@ -361,12 +331,12 @@
- __entry->range_cyclic = wbc->range_cyclic;
- __entry->range_start = (long)wbc->range_start;
- __entry->range_end = (long)wbc->range_end;
- - __trace_wbc_assign_cgroup(__get_str(cgroup), wbc);
- + __entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc);
- ),
-
- TP_printk("bdi %s: towrt=%ld skip=%ld mode=%d kupd=%d "
- "bgrd=%d reclm=%d cyclic=%d "
- - "start=0x%lx end=0x%lx cgroup=%s",
- + "start=0x%lx end=0x%lx cgroup_ino=%u",
- __entry->name,
- __entry->nr_to_write,
- __entry->pages_skipped,
- @@ -377,7 +347,7 @@
- __entry->range_cyclic,
- __entry->range_start,
- __entry->range_end,
- - __get_str(cgroup)
- + __entry->cgroup_ino
- )
- )
-
- @@ -398,7 +368,7 @@
- __field(long, age)
- __field(int, moved)
- __field(int, reason)
- - __dynamic_array(char, cgroup, __trace_wb_cgroup_size(wb))
- + __field(unsigned int, cgroup_ino)
- ),
- TP_fast_assign(
- unsigned long *older_than_this = work->older_than_this;
- @@ -408,15 +378,15 @@
- (jiffies - *older_than_this) * 1000 / HZ : -1;
- __entry->moved = moved;
- __entry->reason = work->reason;
- - __trace_wb_assign_cgroup(__get_str(cgroup), wb);
- + __entry->cgroup_ino = __trace_wb_assign_cgroup(wb);
- ),
- - TP_printk("bdi %s: older=%lu age=%ld enqueue=%d reason=%s cgroup=%s",
- + TP_printk("bdi %s: older=%lu age=%ld enqueue=%d reason=%s cgroup_ino=%u",
- __entry->name,
- __entry->older, /* older_than_this in jiffies */
- __entry->age, /* older_than_this in relative milliseconds */
- __entry->moved,
- __print_symbolic(__entry->reason, WB_WORK_REASON),
- - __get_str(cgroup)
- + __entry->cgroup_ino
- )
- );
-
- @@ -484,7 +454,7 @@
- __field(unsigned long, dirty_ratelimit)
- __field(unsigned long, task_ratelimit)
- __field(unsigned long, balanced_dirty_ratelimit)
- - __dynamic_array(char, cgroup, __trace_wb_cgroup_size(wb))
- + __field(unsigned int, cgroup_ino)
- ),
-
- TP_fast_assign(
- @@ -496,13 +466,13 @@
- __entry->task_ratelimit = KBps(task_ratelimit);
- __entry->balanced_dirty_ratelimit =
- KBps(wb->balanced_dirty_ratelimit);
- - __trace_wb_assign_cgroup(__get_str(cgroup), wb);
- + __entry->cgroup_ino = __trace_wb_assign_cgroup(wb);
- ),
-
- TP_printk("bdi %s: "
- "write_bw=%lu awrite_bw=%lu dirty_rate=%lu "
- "dirty_ratelimit=%lu task_ratelimit=%lu "
- - "balanced_dirty_ratelimit=%lu cgroup=%s",
- + "balanced_dirty_ratelimit=%lu cgroup_ino=%u",
- __entry->bdi,
- __entry->write_bw, /* write bandwidth */
- __entry->avg_write_bw, /* avg write bandwidth */
- @@ -510,7 +480,7 @@
- __entry->dirty_ratelimit, /* base ratelimit */
- __entry->task_ratelimit, /* ratelimit with position control */
- __entry->balanced_dirty_ratelimit, /* the balanced ratelimit */
- - __get_str(cgroup)
- + __entry->cgroup_ino
- )
- );
-
- @@ -548,7 +518,7 @@
- __field( long, pause)
- __field(unsigned long, period)
- __field( long, think)
- - __dynamic_array(char, cgroup, __trace_wb_cgroup_size(wb))
- + __field(unsigned int, cgroup_ino)
- ),
-
- TP_fast_assign(
- @@ -571,7 +541,7 @@
- __entry->period = period * 1000 / HZ;
- __entry->pause = pause * 1000 / HZ;
- __entry->paused = (jiffies - start_time) * 1000 / HZ;
- - __trace_wb_assign_cgroup(__get_str(cgroup), wb);
- + __entry->cgroup_ino = __trace_wb_assign_cgroup(wb);
- ),
-
-
- @@ -580,7 +550,7 @@
- "bdi_setpoint=%lu bdi_dirty=%lu "
- "dirty_ratelimit=%lu task_ratelimit=%lu "
- "dirtied=%u dirtied_pause=%u "
- - "paused=%lu pause=%ld period=%lu think=%ld cgroup=%s",
- + "paused=%lu pause=%ld period=%lu think=%ld cgroup_ino=%u",
- __entry->bdi,
- __entry->limit,
- __entry->setpoint,
- @@ -595,7 +565,7 @@
- __entry->pause, /* ms */
- __entry->period, /* ms */
- __entry->think, /* ms */
- - __get_str(cgroup)
- + __entry->cgroup_ino
- )
- );
-
- @@ -609,8 +579,7 @@
- __field(unsigned long, ino)
- __field(unsigned long, state)
- __field(unsigned long, dirtied_when)
- - __dynamic_array(char, cgroup,
- - __trace_wb_cgroup_size(inode_to_wb(inode)))
- + __field(unsigned int, cgroup_ino)
- ),
-
- TP_fast_assign(
- @@ -619,16 +588,16 @@
- __entry->ino = inode->i_ino;
- __entry->state = inode->i_state;
- __entry->dirtied_when = inode->dirtied_when;
- - __trace_wb_assign_cgroup(__get_str(cgroup), inode_to_wb(inode));
- + __entry->cgroup_ino = __trace_wb_assign_cgroup(inode_to_wb(inode));
- ),
-
- - TP_printk("bdi %s: ino=%lu state=%s dirtied_when=%lu age=%lu cgroup=%s",
- + TP_printk("bdi %s: ino=%lu state=%s dirtied_when=%lu age=%lu cgroup_ino=%u",
- __entry->name,
- __entry->ino,
- show_inode_state(__entry->state),
- __entry->dirtied_when,
- (jiffies - __entry->dirtied_when) / HZ,
- - __get_str(cgroup)
- + __entry->cgroup_ino
- )
- );
-
- @@ -684,7 +653,7 @@
- __field(unsigned long, writeback_index)
- __field(long, nr_to_write)
- __field(unsigned long, wrote)
- - __dynamic_array(char, cgroup, __trace_wbc_cgroup_size(wbc))
- + __field(unsigned int, cgroup_ino)
- ),
-
- TP_fast_assign(
- @@ -696,11 +665,11 @@
- __entry->writeback_index = inode->i_mapping->writeback_index;
- __entry->nr_to_write = nr_to_write;
- __entry->wrote = nr_to_write - wbc->nr_to_write;
- - __trace_wbc_assign_cgroup(__get_str(cgroup), wbc);
- + __entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc);
- ),
-
- TP_printk("bdi %s: ino=%lu state=%s dirtied_when=%lu age=%lu "
- - "index=%lu to_write=%ld wrote=%lu cgroup=%s",
- + "index=%lu to_write=%ld wrote=%lu cgroup_ino=%u",
- __entry->name,
- __entry->ino,
- show_inode_state(__entry->state),
- @@ -709,7 +678,7 @@
- __entry->writeback_index,
- __entry->nr_to_write,
- __entry->wrote,
- - __get_str(cgroup)
- + __entry->cgroup_ino
- )
- );
-
- diff -Nur linux-4.4.28.orig/init/Kconfig linux-4.4.28/init/Kconfig
- --- linux-4.4.28.orig/init/Kconfig 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/init/Kconfig 2016-11-01 21:26:58.752340732 +0100
- @@ -498,7 +498,7 @@
-
- config RCU_EXPERT
- bool "Make expert-level adjustments to RCU configuration"
- - default n
- + default y if PREEMPT_RT_FULL
- help
- This option needs to be enabled if you wish to make
- expert-level adjustments to RCU configuration. By default,
- @@ -614,7 +614,7 @@
-
- config RCU_FAST_NO_HZ
- bool "Accelerate last non-dyntick-idle CPU's grace periods"
- - depends on NO_HZ_COMMON && SMP && RCU_EXPERT
- + depends on NO_HZ_COMMON && SMP && RCU_EXPERT && !PREEMPT_RT_FULL
- default n
- help
- This option permits CPUs to enter dynticks-idle state even if
- @@ -641,7 +641,7 @@
- config RCU_BOOST
- bool "Enable RCU priority boosting"
- depends on RT_MUTEXES && PREEMPT_RCU && RCU_EXPERT
- - default n
- + default y if PREEMPT_RT_FULL
- help
- This option boosts the priority of preempted RCU readers that
- block the current preemptible RCU grace period for too long.
- @@ -1106,6 +1106,7 @@
- config RT_GROUP_SCHED
- bool "Group scheduling for SCHED_RR/FIFO"
- depends on CGROUP_SCHED
- + depends on !PREEMPT_RT_FULL
- default n
- help
- This feature lets you explicitly allocate real CPU bandwidth
- @@ -1719,6 +1720,7 @@
-
- config SLAB
- bool "SLAB"
- + depends on !PREEMPT_RT_FULL
- help
- The regular slab allocator that is established and known to work
- well in all environments. It organizes cache hot objects in
- @@ -1737,6 +1739,7 @@
- config SLOB
- depends on EXPERT
- bool "SLOB (Simple Allocator)"
- + depends on !PREEMPT_RT_FULL
- help
- SLOB replaces the stock allocator with a drastically simpler
- allocator. SLOB is generally more space efficient but
- @@ -1746,7 +1749,7 @@
-
- config SLUB_CPU_PARTIAL
- default y
- - depends on SLUB && SMP
- + depends on SLUB && SMP && !PREEMPT_RT_FULL
- bool "SLUB per cpu partial cache"
- help
- Per cpu partial caches accellerate objects allocation and freeing
- diff -Nur linux-4.4.28.orig/init/main.c linux-4.4.28/init/main.c
- --- linux-4.4.28.orig/init/main.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/init/main.c 2016-11-01 21:26:58.752340732 +0100
- @@ -530,6 +530,7 @@
- setup_command_line(command_line);
- setup_nr_cpu_ids();
- setup_per_cpu_areas();
- + softirq_early_init();
- smp_prepare_boot_cpu(); /* arch-specific boot-cpu hooks */
-
- build_all_zonelists(NULL, NULL);
- diff -Nur linux-4.4.28.orig/init/Makefile linux-4.4.28/init/Makefile
- --- linux-4.4.28.orig/init/Makefile 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/init/Makefile 2016-11-01 21:26:58.752340732 +0100
- @@ -33,4 +33,4 @@
- include/generated/compile.h: FORCE
- @$($(quiet)chk_compile.h)
- $(Q)$(CONFIG_SHELL) $(srctree)/scripts/mkcompile_h $@ \
- - "$(UTS_MACHINE)" "$(CONFIG_SMP)" "$(CONFIG_PREEMPT)" "$(CC) $(KBUILD_CFLAGS)"
- + "$(UTS_MACHINE)" "$(CONFIG_SMP)" "$(CONFIG_PREEMPT)" "$(CONFIG_PREEMPT_RT_FULL)" "$(CC) $(KBUILD_CFLAGS)"
- diff -Nur linux-4.4.28.orig/ipc/msg.c linux-4.4.28/ipc/msg.c
- --- linux-4.4.28.orig/ipc/msg.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/ipc/msg.c 2016-11-01 21:26:58.752340732 +0100
- @@ -183,20 +183,14 @@
- }
- }
-
- -static void expunge_all(struct msg_queue *msq, int res)
- +static void expunge_all(struct msg_queue *msq, int res,
- + struct wake_q_head *wake_q)
- {
- struct msg_receiver *msr, *t;
-
- list_for_each_entry_safe(msr, t, &msq->q_receivers, r_list) {
- - msr->r_msg = NULL; /* initialize expunge ordering */
- - wake_up_process(msr->r_tsk);
- - /*
- - * Ensure that the wakeup is visible before setting r_msg as
- - * the receiving end depends on it: either spinning on a nil,
- - * or dealing with -EAGAIN cases. See lockless receive part 1
- - * and 2 in do_msgrcv().
- - */
- - smp_wmb(); /* barrier (B) */
- +
- + wake_q_add(wake_q, msr->r_tsk);
- msr->r_msg = ERR_PTR(res);
- }
- }
- @@ -213,11 +207,13 @@
- {
- struct msg_msg *msg, *t;
- struct msg_queue *msq = container_of(ipcp, struct msg_queue, q_perm);
- + WAKE_Q(wake_q);
-
- - expunge_all(msq, -EIDRM);
- + expunge_all(msq, -EIDRM, &wake_q);
- ss_wakeup(&msq->q_senders, 1);
- msg_rmid(ns, msq);
- ipc_unlock_object(&msq->q_perm);
- + wake_up_q(&wake_q);
- rcu_read_unlock();
-
- list_for_each_entry_safe(msg, t, &msq->q_messages, m_list) {
- @@ -342,6 +338,7 @@
- struct kern_ipc_perm *ipcp;
- struct msqid64_ds uninitialized_var(msqid64);
- struct msg_queue *msq;
- + WAKE_Q(wake_q);
- int err;
-
- if (cmd == IPC_SET) {
- @@ -389,7 +386,7 @@
- /* sleeping receivers might be excluded by
- * stricter permissions.
- */
- - expunge_all(msq, -EAGAIN);
- + expunge_all(msq, -EAGAIN, &wake_q);
- /* sleeping senders might be able to send
- * due to a larger queue size.
- */
- @@ -402,6 +399,7 @@
-
- out_unlock0:
- ipc_unlock_object(&msq->q_perm);
- + wake_up_q(&wake_q);
- out_unlock1:
- rcu_read_unlock();
- out_up:
- @@ -566,7 +564,8 @@
- return 0;
- }
-
- -static inline int pipelined_send(struct msg_queue *msq, struct msg_msg *msg)
- +static inline int pipelined_send(struct msg_queue *msq, struct msg_msg *msg,
- + struct wake_q_head *wake_q)
- {
- struct msg_receiver *msr, *t;
-
- @@ -577,27 +576,13 @@
-
- list_del(&msr->r_list);
- if (msr->r_maxsize < msg->m_ts) {
- - /* initialize pipelined send ordering */
- - msr->r_msg = NULL;
- - wake_up_process(msr->r_tsk);
- - /* barrier (B) see barrier comment below */
- - smp_wmb();
- + wake_q_add(wake_q, msr->r_tsk);
- msr->r_msg = ERR_PTR(-E2BIG);
- } else {
- - msr->r_msg = NULL;
- msq->q_lrpid = task_pid_vnr(msr->r_tsk);
- msq->q_rtime = get_seconds();
- - wake_up_process(msr->r_tsk);
- - /*
- - * Ensure that the wakeup is visible before
- - * setting r_msg, as the receiving can otherwise
- - * exit - once r_msg is set, the receiver can
- - * continue. See lockless receive part 1 and 2
- - * in do_msgrcv(). Barrier (B).
- - */
- - smp_wmb();
- + wake_q_add(wake_q, msr->r_tsk);
- msr->r_msg = msg;
- -
- return 1;
- }
- }
- @@ -613,6 +598,7 @@
- struct msg_msg *msg;
- int err;
- struct ipc_namespace *ns;
- + WAKE_Q(wake_q);
-
- ns = current->nsproxy->ipc_ns;
-
- @@ -698,7 +684,7 @@
- msq->q_lspid = task_tgid_vnr(current);
- msq->q_stime = get_seconds();
-
- - if (!pipelined_send(msq, msg)) {
- + if (!pipelined_send(msq, msg, &wake_q)) {
- /* no one is waiting for this message, enqueue it */
- list_add_tail(&msg->m_list, &msq->q_messages);
- msq->q_cbytes += msgsz;
- @@ -712,6 +698,7 @@
-
- out_unlock0:
- ipc_unlock_object(&msq->q_perm);
- + wake_up_q(&wake_q);
- out_unlock1:
- rcu_read_unlock();
- if (msg != NULL)
- @@ -932,57 +919,25 @@
- rcu_read_lock();
-
- /* Lockless receive, part 2:
- - * Wait until pipelined_send or expunge_all are outside of
- - * wake_up_process(). There is a race with exit(), see
- - * ipc/mqueue.c for the details. The correct serialization
- - * ensures that a receiver cannot continue without the wakeup
- - * being visibible _before_ setting r_msg:
- + * The work in pipelined_send() and expunge_all():
- + * - Set pointer to message
- + * - Queue the receiver task for later wakeup
- + * - Wake up the process after the lock is dropped.
- *
- - * CPU 0 CPU 1
- - * <loop receiver>
- - * smp_rmb(); (A) <-- pair -. <waker thread>
- - * <load ->r_msg> | msr->r_msg = NULL;
- - * | wake_up_process();
- - * <continue> `------> smp_wmb(); (B)
- - * msr->r_msg = msg;
- - *
- - * Where (A) orders the message value read and where (B) orders
- - * the write to the r_msg -- done in both pipelined_send and
- - * expunge_all.
- + * Should the process wake up before this wakeup (due to a
- + * signal) it will either see the message and continue …
- */
- - for (;;) {
- - /*
- - * Pairs with writer barrier in pipelined_send
- - * or expunge_all.
- - */
- - smp_rmb(); /* barrier (A) */
- - msg = (struct msg_msg *)msr_d.r_msg;
- - if (msg)
- - break;
-
- - /*
- - * The cpu_relax() call is a compiler barrier
- - * which forces everything in this loop to be
- - * re-loaded.
- - */
- - cpu_relax();
- - }
- -
- - /* Lockless receive, part 3:
- - * If there is a message or an error then accept it without
- - * locking.
- - */
- + msg = (struct msg_msg *)msr_d.r_msg;
- if (msg != ERR_PTR(-EAGAIN))
- goto out_unlock1;
-
- - /* Lockless receive, part 3:
- - * Acquire the queue spinlock.
- - */
- + /*
- + * … or see -EAGAIN, acquire the lock to check the message
- + * again.
- + */
- ipc_lock_object(&msq->q_perm);
-
- - /* Lockless receive, part 4:
- - * Repeat test after acquiring the spinlock.
- - */
- msg = (struct msg_msg *)msr_d.r_msg;
- if (msg != ERR_PTR(-EAGAIN))
- goto out_unlock0;
- diff -Nur linux-4.4.28.orig/ipc/sem.c linux-4.4.28/ipc/sem.c
- --- linux-4.4.28.orig/ipc/sem.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/ipc/sem.c 2016-11-01 21:26:58.756340996 +0100
- @@ -708,6 +708,13 @@
- static void wake_up_sem_queue_prepare(struct list_head *pt,
- struct sem_queue *q, int error)
- {
- +#ifdef CONFIG_PREEMPT_RT_BASE
- + struct task_struct *p = q->sleeper;
- + get_task_struct(p);
- + q->status = error;
- + wake_up_process(p);
- + put_task_struct(p);
- +#else
- if (list_empty(pt)) {
- /*
- * Hold preempt off so that we don't get preempted and have the
- @@ -719,6 +726,7 @@
- q->pid = error;
-
- list_add_tail(&q->list, pt);
- +#endif
- }
-
- /**
- @@ -732,6 +740,7 @@
- */
- static void wake_up_sem_queue_do(struct list_head *pt)
- {
- +#ifndef CONFIG_PREEMPT_RT_BASE
- struct sem_queue *q, *t;
- int did_something;
-
- @@ -744,6 +753,7 @@
- }
- if (did_something)
- preempt_enable();
- +#endif
- }
-
- static void unlink_queue(struct sem_array *sma, struct sem_queue *q)
- diff -Nur linux-4.4.28.orig/kernel/cgroup.c linux-4.4.28/kernel/cgroup.c
- --- linux-4.4.28.orig/kernel/cgroup.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/cgroup.c 2016-11-01 21:26:58.756340996 +0100
- @@ -4737,10 +4737,10 @@
- queue_work(cgroup_destroy_wq, &css->destroy_work);
- }
-
- -static void css_release_work_fn(struct work_struct *work)
- +static void css_release_work_fn(struct swork_event *sev)
- {
- struct cgroup_subsys_state *css =
- - container_of(work, struct cgroup_subsys_state, destroy_work);
- + container_of(sev, struct cgroup_subsys_state, destroy_swork);
- struct cgroup_subsys *ss = css->ss;
- struct cgroup *cgrp = css->cgroup;
-
- @@ -4779,8 +4779,8 @@
- struct cgroup_subsys_state *css =
- container_of(ref, struct cgroup_subsys_state, refcnt);
-
- - INIT_WORK(&css->destroy_work, css_release_work_fn);
- - queue_work(cgroup_destroy_wq, &css->destroy_work);
- + INIT_SWORK(&css->destroy_swork, css_release_work_fn);
- + swork_queue(&css->destroy_swork);
- }
-
- static void init_and_link_css(struct cgroup_subsys_state *css,
- @@ -5397,6 +5397,7 @@
- */
- cgroup_destroy_wq = alloc_workqueue("cgroup_destroy", 0, 1);
- BUG_ON(!cgroup_destroy_wq);
- + BUG_ON(swork_get());
-
- /*
- * Used to destroy pidlists and separate to serve as flush domain.
- diff -Nur linux-4.4.28.orig/kernel/cpu.c linux-4.4.28/kernel/cpu.c
- --- linux-4.4.28.orig/kernel/cpu.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/cpu.c 2016-11-01 21:26:58.756340996 +0100
- @@ -75,8 +75,8 @@
- #endif
- } cpu_hotplug = {
- .active_writer = NULL,
- - .wq = __WAIT_QUEUE_HEAD_INITIALIZER(cpu_hotplug.wq),
- .lock = __MUTEX_INITIALIZER(cpu_hotplug.lock),
- + .wq = __WAIT_QUEUE_HEAD_INITIALIZER(cpu_hotplug.wq),
- #ifdef CONFIG_DEBUG_LOCK_ALLOC
- .dep_map = {.name = "cpu_hotplug.lock" },
- #endif
- @@ -89,6 +89,289 @@
- #define cpuhp_lock_acquire() lock_map_acquire(&cpu_hotplug.dep_map)
- #define cpuhp_lock_release() lock_map_release(&cpu_hotplug.dep_map)
-
- +/**
- + * hotplug_pcp - per cpu hotplug descriptor
- + * @unplug: set when pin_current_cpu() needs to sync tasks
- + * @sync_tsk: the task that waits for tasks to finish pinned sections
- + * @refcount: counter of tasks in pinned sections
- + * @grab_lock: set when the tasks entering pinned sections should wait
- + * @synced: notifier for @sync_tsk to tell cpu_down it's finished
- + * @mutex: the mutex to make tasks wait (used when @grab_lock is true)
- + * @mutex_init: zero if the mutex hasn't been initialized yet.
- + *
- + * Although @unplug and @sync_tsk may point to the same task, the @unplug
- + * is used as a flag and still exists after @sync_tsk has exited and
- + * @sync_tsk set to NULL.
- + */
- +struct hotplug_pcp {
- + struct task_struct *unplug;
- + struct task_struct *sync_tsk;
- + int refcount;
- + int grab_lock;
- + struct completion synced;
- + struct completion unplug_wait;
- +#ifdef CONFIG_PREEMPT_RT_FULL
- + /*
- + * Note, on PREEMPT_RT, the hotplug lock must save the state of
- + * the task, otherwise the mutex will cause the task to fail
- + * to sleep when required. (Because it's called from migrate_disable())
- + *
- + * The spinlock_t on PREEMPT_RT is a mutex that saves the task's
- + * state.
- + */
- + spinlock_t lock;
- +#else
- + struct mutex mutex;
- +#endif
- + int mutex_init;
- +};
- +
- +#ifdef CONFIG_PREEMPT_RT_FULL
- +# define hotplug_lock(hp) rt_spin_lock__no_mg(&(hp)->lock)
- +# define hotplug_unlock(hp) rt_spin_unlock__no_mg(&(hp)->lock)
- +#else
- +# define hotplug_lock(hp) mutex_lock(&(hp)->mutex)
- +# define hotplug_unlock(hp) mutex_unlock(&(hp)->mutex)
- +#endif
- +
- +static DEFINE_PER_CPU(struct hotplug_pcp, hotplug_pcp);
- +
- +/**
- + * pin_current_cpu - Prevent the current cpu from being unplugged
- + *
- + * Lightweight version of get_online_cpus() to prevent cpu from being
- + * unplugged when code runs in a migration disabled region.
- + *
- + * Must be called with preemption disabled (preempt_count = 1)!
- + */
- +void pin_current_cpu(void)
- +{
- + struct hotplug_pcp *hp;
- + int force = 0;
- +
- +retry:
- + hp = this_cpu_ptr(&hotplug_pcp);
- +
- + if (!hp->unplug || hp->refcount || force || preempt_count() > 1 ||
- + hp->unplug == current) {
- + hp->refcount++;
- + return;
- + }
- + if (hp->grab_lock) {
- + preempt_enable();
- + hotplug_lock(hp);
- + hotplug_unlock(hp);
- + } else {
- + preempt_enable();
- + /*
- + * Try to push this task off of this CPU.
- + */
- + if (!migrate_me()) {
- + preempt_disable();
- + hp = this_cpu_ptr(&hotplug_pcp);
- + if (!hp->grab_lock) {
- + /*
- + * Just let it continue it's already pinned
- + * or about to sleep.
- + */
- + force = 1;
- + goto retry;
- + }
- + preempt_enable();
- + }
- + }
- + preempt_disable();
- + goto retry;
- +}
- +
- +/**
- + * unpin_current_cpu - Allow unplug of current cpu
- + *
- + * Must be called with preemption or interrupts disabled!
- + */
- +void unpin_current_cpu(void)
- +{
- + struct hotplug_pcp *hp = this_cpu_ptr(&hotplug_pcp);
- +
- + WARN_ON(hp->refcount <= 0);
- +
- + /* This is safe. sync_unplug_thread is pinned to this cpu */
- + if (!--hp->refcount && hp->unplug && hp->unplug != current)
- + wake_up_process(hp->unplug);
- +}
- +
- +static void wait_for_pinned_cpus(struct hotplug_pcp *hp)
- +{
- + set_current_state(TASK_UNINTERRUPTIBLE);
- + while (hp->refcount) {
- + schedule_preempt_disabled();
- + set_current_state(TASK_UNINTERRUPTIBLE);
- + }
- +}
- +
- +static int sync_unplug_thread(void *data)
- +{
- + struct hotplug_pcp *hp = data;
- +
- + wait_for_completion(&hp->unplug_wait);
- + preempt_disable();
- + hp->unplug = current;
- + wait_for_pinned_cpus(hp);
- +
- + /*
- + * This thread will synchronize the cpu_down() with threads
- + * that have pinned the CPU. When the pinned CPU count reaches
- + * zero, we inform the cpu_down code to continue to the next step.
- + */
- + set_current_state(TASK_UNINTERRUPTIBLE);
- + preempt_enable();
- + complete(&hp->synced);
- +
- + /*
- + * If all succeeds, the next step will need tasks to wait till
- + * the CPU is offline before continuing. To do this, the grab_lock
- + * is set and tasks going into pin_current_cpu() will block on the
- + * mutex. But we still need to wait for those that are already in
- + * pinned CPU sections. If the cpu_down() failed, the kthread_should_stop()
- + * will kick this thread out.
- + */
- + while (!hp->grab_lock && !kthread_should_stop()) {
- + schedule();
- + set_current_state(TASK_UNINTERRUPTIBLE);
- + }
- +
- + /* Make sure grab_lock is seen before we see a stale completion */
- + smp_mb();
- +
- + /*
- + * Now just before cpu_down() enters stop machine, we need to make
- + * sure all tasks that are in pinned CPU sections are out, and new
- + * tasks will now grab the lock, keeping them from entering pinned
- + * CPU sections.
- + */
- + if (!kthread_should_stop()) {
- + preempt_disable();
- + wait_for_pinned_cpus(hp);
- + preempt_enable();
- + complete(&hp->synced);
- + }
- +
- + set_current_state(TASK_UNINTERRUPTIBLE);
- + while (!kthread_should_stop()) {
- + schedule();
- + set_current_state(TASK_UNINTERRUPTIBLE);
- + }
- + set_current_state(TASK_RUNNING);
- +
- + /*
- + * Force this thread off this CPU as it's going down and
- + * we don't want any more work on this CPU.
- + */
- + current->flags &= ~PF_NO_SETAFFINITY;
- + set_cpus_allowed_ptr(current, cpu_present_mask);
- + migrate_me();
- + return 0;
- +}
- +
- +static void __cpu_unplug_sync(struct hotplug_pcp *hp)
- +{
- + wake_up_process(hp->sync_tsk);
- + wait_for_completion(&hp->synced);
- +}
- +
- +static void __cpu_unplug_wait(unsigned int cpu)
- +{
- + struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu);
- +
- + complete(&hp->unplug_wait);
- + wait_for_completion(&hp->synced);
- +}
- +
- +/*
- + * Start the sync_unplug_thread on the target cpu and wait for it to
- + * complete.
- + */
- +static int cpu_unplug_begin(unsigned int cpu)
- +{
- + struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu);
- + int err;
- +
- + /* Protected by cpu_hotplug.lock */
- + if (!hp->mutex_init) {
- +#ifdef CONFIG_PREEMPT_RT_FULL
- + spin_lock_init(&hp->lock);
- +#else
- + mutex_init(&hp->mutex);
- +#endif
- + hp->mutex_init = 1;
- + }
- +
- + /* Inform the scheduler to migrate tasks off this CPU */
- + tell_sched_cpu_down_begin(cpu);
- +
- + init_completion(&hp->synced);
- + init_completion(&hp->unplug_wait);
- +
- + hp->sync_tsk = kthread_create(sync_unplug_thread, hp, "sync_unplug/%d", cpu);
- + if (IS_ERR(hp->sync_tsk)) {
- + err = PTR_ERR(hp->sync_tsk);
- + hp->sync_tsk = NULL;
- + return err;
- + }
- + kthread_bind(hp->sync_tsk, cpu);
- +
- + /*
- + * Wait for tasks to get out of the pinned sections,
- + * it's still OK if new tasks enter. Some CPU notifiers will
- + * wait for tasks that are going to enter these sections and
- + * we must not have them block.
- + */
- + wake_up_process(hp->sync_tsk);
- + return 0;
- +}
- +
- +static void cpu_unplug_sync(unsigned int cpu)
- +{
- + struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu);
- +
- + init_completion(&hp->synced);
- + /* The completion needs to be initialzied before setting grab_lock */
- + smp_wmb();
- +
- + /* Grab the mutex before setting grab_lock */
- + hotplug_lock(hp);
- + hp->grab_lock = 1;
- +
- + /*
- + * The CPU notifiers have been completed.
- + * Wait for tasks to get out of pinned CPU sections and have new
- + * tasks block until the CPU is completely down.
- + */
- + __cpu_unplug_sync(hp);
- +
- + /* All done with the sync thread */
- + kthread_stop(hp->sync_tsk);
- + hp->sync_tsk = NULL;
- +}
- +
- +static void cpu_unplug_done(unsigned int cpu)
- +{
- + struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu);
- +
- + hp->unplug = NULL;
- + /* Let all tasks know cpu unplug is finished before cleaning up */
- + smp_wmb();
- +
- + if (hp->sync_tsk)
- + kthread_stop(hp->sync_tsk);
- +
- + if (hp->grab_lock) {
- + hotplug_unlock(hp);
- + /* protected by cpu_hotplug.lock */
- + hp->grab_lock = 0;
- + }
- + tell_sched_cpu_down_done(cpu);
- +}
-
- void get_online_cpus(void)
- {
- @@ -338,13 +621,15 @@
- /* Requires cpu_add_remove_lock to be held */
- static int _cpu_down(unsigned int cpu, int tasks_frozen)
- {
- - int err, nr_calls = 0;
- + int mycpu, err, nr_calls = 0;
- void *hcpu = (void *)(long)cpu;
- unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0;
- struct take_cpu_down_param tcd_param = {
- .mod = mod,
- .hcpu = hcpu,
- };
- + cpumask_var_t cpumask;
- + cpumask_var_t cpumask_org;
-
- if (num_online_cpus() == 1)
- return -EBUSY;
- @@ -352,7 +637,34 @@
- if (!cpu_online(cpu))
- return -EINVAL;
-
- + /* Move the downtaker off the unplug cpu */
- + if (!alloc_cpumask_var(&cpumask, GFP_KERNEL))
- + return -ENOMEM;
- + if (!alloc_cpumask_var(&cpumask_org, GFP_KERNEL)) {
- + free_cpumask_var(cpumask);
- + return -ENOMEM;
- + }
- +
- + cpumask_copy(cpumask_org, tsk_cpus_allowed(current));
- + cpumask_andnot(cpumask, cpu_online_mask, cpumask_of(cpu));
- + set_cpus_allowed_ptr(current, cpumask);
- + free_cpumask_var(cpumask);
- + migrate_disable();
- + mycpu = smp_processor_id();
- + if (mycpu == cpu) {
- + printk(KERN_ERR "Yuck! Still on unplug CPU\n!");
- + migrate_enable();
- + err = -EBUSY;
- + goto restore_cpus;
- + }
- + migrate_enable();
- +
- cpu_hotplug_begin();
- + err = cpu_unplug_begin(cpu);
- + if (err) {
- + printk("cpu_unplug_begin(%d) failed\n", cpu);
- + goto out_cancel;
- + }
-
- err = __cpu_notify(CPU_DOWN_PREPARE | mod, hcpu, -1, &nr_calls);
- if (err) {
- @@ -378,8 +690,12 @@
- else
- synchronize_rcu();
-
- + __cpu_unplug_wait(cpu);
- smpboot_park_threads(cpu);
-
- + /* Notifiers are done. Don't let any more tasks pin this CPU. */
- + cpu_unplug_sync(cpu);
- +
- /*
- * Prevent irq alloc/free while the dying cpu reorganizes the
- * interrupt affinities.
- @@ -424,9 +740,14 @@
- check_for_tasks(cpu);
-
- out_release:
- + cpu_unplug_done(cpu);
- +out_cancel:
- cpu_hotplug_done();
- if (!err)
- cpu_notify_nofail(CPU_POST_DEAD | mod, hcpu);
- +restore_cpus:
- + set_cpus_allowed_ptr(current, cpumask_org);
- + free_cpumask_var(cpumask_org);
- return err;
- }
-
- diff -Nur linux-4.4.28.orig/kernel/debug/kdb/kdb_io.c linux-4.4.28/kernel/debug/kdb/kdb_io.c
- --- linux-4.4.28.orig/kernel/debug/kdb/kdb_io.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/debug/kdb/kdb_io.c 2016-11-01 21:26:58.756340996 +0100
- @@ -554,7 +554,6 @@
- int linecount;
- int colcount;
- int logging, saved_loglevel = 0;
- - int saved_trap_printk;
- int got_printf_lock = 0;
- int retlen = 0;
- int fnd, len;
- @@ -565,8 +564,6 @@
- unsigned long uninitialized_var(flags);
-
- preempt_disable();
- - saved_trap_printk = kdb_trap_printk;
- - kdb_trap_printk = 0;
-
- /* Serialize kdb_printf if multiple cpus try to write at once.
- * But if any cpu goes recursive in kdb, just print the output,
- @@ -855,7 +852,6 @@
- } else {
- __release(kdb_printf_lock);
- }
- - kdb_trap_printk = saved_trap_printk;
- preempt_enable();
- return retlen;
- }
- @@ -865,9 +861,11 @@
- va_list ap;
- int r;
-
- + kdb_trap_printk++;
- va_start(ap, fmt);
- r = vkdb_printf(KDB_MSGSRC_INTERNAL, fmt, ap);
- va_end(ap);
- + kdb_trap_printk--;
-
- return r;
- }
- diff -Nur linux-4.4.28.orig/kernel/events/core.c linux-4.4.28/kernel/events/core.c
- --- linux-4.4.28.orig/kernel/events/core.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/events/core.c 2016-11-01 21:26:58.760341249 +0100
- @@ -802,6 +802,7 @@
- raw_spin_lock_init(&cpuctx->hrtimer_lock);
- hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED);
- timer->function = perf_mux_hrtimer_handler;
- + timer->irqsafe = 1;
- }
-
- static int perf_mux_hrtimer_restart(struct perf_cpu_context *cpuctx)
- @@ -7240,6 +7241,7 @@
-
- hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
- hwc->hrtimer.function = perf_swevent_hrtimer;
- + hwc->hrtimer.irqsafe = 1;
-
- /*
- * Since hrtimers have a fixed rate, we can do a static freq->period
- diff -Nur linux-4.4.28.orig/kernel/exit.c linux-4.4.28/kernel/exit.c
- --- linux-4.4.28.orig/kernel/exit.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/exit.c 2016-11-01 21:26:58.760341249 +0100
- @@ -144,7 +144,7 @@
- * Do this under ->siglock, we can race with another thread
- * doing sigqueue_free() if we have SIGQUEUE_PREALLOC signals.
- */
- - flush_sigqueue(&tsk->pending);
- + flush_task_sigqueue(tsk);
- tsk->sighand = NULL;
- spin_unlock(&sighand->siglock);
-
- diff -Nur linux-4.4.28.orig/kernel/fork.c linux-4.4.28/kernel/fork.c
- --- linux-4.4.28.orig/kernel/fork.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/fork.c 2016-11-01 21:26:58.764341506 +0100
- @@ -108,7 +108,7 @@
-
- DEFINE_PER_CPU(unsigned long, process_counts) = 0;
-
- -__cacheline_aligned DEFINE_RWLOCK(tasklist_lock); /* outer */
- +DEFINE_RWLOCK(tasklist_lock); /* outer */
-
- #ifdef CONFIG_PROVE_RCU
- int lockdep_tasklist_lock_is_held(void)
- @@ -244,7 +244,9 @@
- if (atomic_dec_and_test(&sig->sigcnt))
- free_signal_struct(sig);
- }
- -
- +#ifdef CONFIG_PREEMPT_RT_BASE
- +static
- +#endif
- void __put_task_struct(struct task_struct *tsk)
- {
- WARN_ON(!tsk->exit_state);
- @@ -261,7 +263,18 @@
- if (!profile_handoff_task(tsk))
- free_task(tsk);
- }
- +#ifndef CONFIG_PREEMPT_RT_BASE
- EXPORT_SYMBOL_GPL(__put_task_struct);
- +#else
- +void __put_task_struct_cb(struct rcu_head *rhp)
- +{
- + struct task_struct *tsk = container_of(rhp, struct task_struct, put_rcu);
- +
- + __put_task_struct(tsk);
- +
- +}
- +EXPORT_SYMBOL_GPL(__put_task_struct_cb);
- +#endif
-
- void __init __weak arch_task_cache_init(void) { }
-
- @@ -689,6 +702,19 @@
- }
- EXPORT_SYMBOL_GPL(__mmdrop);
-
- +#ifdef CONFIG_PREEMPT_RT_BASE
- +/*
- + * RCU callback for delayed mm drop. Not strictly rcu, but we don't
- + * want another facility to make this work.
- + */
- +void __mmdrop_delayed(struct rcu_head *rhp)
- +{
- + struct mm_struct *mm = container_of(rhp, struct mm_struct, delayed_drop);
- +
- + __mmdrop(mm);
- +}
- +#endif
- +
- /*
- * Decrement the use count and release all resources for an mm.
- */
- @@ -1239,6 +1265,9 @@
- */
- static void posix_cpu_timers_init(struct task_struct *tsk)
- {
- +#ifdef CONFIG_PREEMPT_RT_BASE
- + tsk->posix_timer_list = NULL;
- +#endif
- tsk->cputime_expires.prof_exp = 0;
- tsk->cputime_expires.virt_exp = 0;
- tsk->cputime_expires.sched_exp = 0;
- @@ -1364,15 +1393,16 @@
- spin_lock_init(&p->alloc_lock);
-
- init_sigpending(&p->pending);
- + p->sigqueue_cache = NULL;
-
- p->utime = p->stime = p->gtime = 0;
- p->utimescaled = p->stimescaled = 0;
- prev_cputime_init(&p->prev_cputime);
-
- #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
- - seqlock_init(&p->vtime_seqlock);
- + seqcount_init(&p->vtime_seqcount);
- p->vtime_snap = 0;
- - p->vtime_snap_whence = VTIME_SLEEPING;
- + p->vtime_snap_whence = VTIME_INACTIVE;
- #endif
-
- #if defined(SPLIT_RSS_COUNTING)
- diff -Nur linux-4.4.28.orig/kernel/futex.c linux-4.4.28/kernel/futex.c
- --- linux-4.4.28.orig/kernel/futex.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/futex.c 2016-11-01 21:26:58.764341506 +0100
- @@ -815,7 +815,9 @@
- * task still owns the PI-state:
- */
- if (head->next != next) {
- + raw_spin_unlock_irq(&curr->pi_lock);
- spin_unlock(&hb->lock);
- + raw_spin_lock_irq(&curr->pi_lock);
- continue;
- }
-
- @@ -1210,6 +1212,7 @@
- struct futex_pi_state *pi_state = this->pi_state;
- u32 uninitialized_var(curval), newval;
- WAKE_Q(wake_q);
- + WAKE_Q(wake_sleeper_q);
- bool deboost;
- int ret = 0;
-
- @@ -1223,7 +1226,7 @@
- if (pi_state->owner != current)
- return -EINVAL;
-
- - raw_spin_lock(&pi_state->pi_mutex.wait_lock);
- + raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
- new_owner = rt_mutex_next_owner(&pi_state->pi_mutex);
-
- /*
- @@ -1259,24 +1262,25 @@
- ret = -EINVAL;
- }
- if (ret) {
- - raw_spin_unlock(&pi_state->pi_mutex.wait_lock);
- + raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
- return ret;
- }
-
- - raw_spin_lock_irq(&pi_state->owner->pi_lock);
- + raw_spin_lock(&pi_state->owner->pi_lock);
- WARN_ON(list_empty(&pi_state->list));
- list_del_init(&pi_state->list);
- - raw_spin_unlock_irq(&pi_state->owner->pi_lock);
- + raw_spin_unlock(&pi_state->owner->pi_lock);
-
- - raw_spin_lock_irq(&new_owner->pi_lock);
- + raw_spin_lock(&new_owner->pi_lock);
- WARN_ON(!list_empty(&pi_state->list));
- list_add(&pi_state->list, &new_owner->pi_state_list);
- pi_state->owner = new_owner;
- - raw_spin_unlock_irq(&new_owner->pi_lock);
- + raw_spin_unlock(&new_owner->pi_lock);
-
- - raw_spin_unlock(&pi_state->pi_mutex.wait_lock);
- + raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
-
- - deboost = rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q);
- + deboost = rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q,
- + &wake_sleeper_q);
-
- /*
- * First unlock HB so the waiter does not spin on it once he got woken
- @@ -1284,8 +1288,9 @@
- * deboost first (and lose our higher priority), then the task might get
- * scheduled away before the wake up can take place.
- */
- - spin_unlock(&hb->lock);
- + deboost |= spin_unlock_no_deboost(&hb->lock);
- wake_up_q(&wake_q);
- + wake_up_q_sleeper(&wake_sleeper_q);
- if (deboost)
- rt_mutex_adjust_prio(current);
-
- @@ -1822,6 +1827,16 @@
- requeue_pi_wake_futex(this, &key2, hb2);
- drop_count++;
- continue;
- + } else if (ret == -EAGAIN) {
- + /*
- + * Waiter was woken by timeout or
- + * signal and has set pi_blocked_on to
- + * PI_WAKEUP_INPROGRESS before we
- + * tried to enqueue it on the rtmutex.
- + */
- + this->pi_state = NULL;
- + free_pi_state(pi_state);
- + continue;
- } else if (ret) {
- /* -EDEADLK */
- this->pi_state = NULL;
- @@ -2139,11 +2154,11 @@
- * we returned due to timeout or signal without taking the
- * rt_mutex. Too late.
- */
- - raw_spin_lock(&q->pi_state->pi_mutex.wait_lock);
- + raw_spin_lock_irq(&q->pi_state->pi_mutex.wait_lock);
- owner = rt_mutex_owner(&q->pi_state->pi_mutex);
- if (!owner)
- owner = rt_mutex_next_owner(&q->pi_state->pi_mutex);
- - raw_spin_unlock(&q->pi_state->pi_mutex.wait_lock);
- + raw_spin_unlock_irq(&q->pi_state->pi_mutex.wait_lock);
- ret = fixup_pi_state_owner(uaddr, q, owner);
- goto out;
- }
- @@ -2691,7 +2706,7 @@
- struct hrtimer_sleeper timeout, *to = NULL;
- struct rt_mutex_waiter rt_waiter;
- struct rt_mutex *pi_mutex = NULL;
- - struct futex_hash_bucket *hb;
- + struct futex_hash_bucket *hb, *hb2;
- union futex_key key2 = FUTEX_KEY_INIT;
- struct futex_q q = futex_q_init;
- int res, ret;
- @@ -2716,10 +2731,7 @@
- * The waiter is allocated on our stack, manipulated by the requeue
- * code while we sleep on uaddr.
- */
- - debug_rt_mutex_init_waiter(&rt_waiter);
- - RB_CLEAR_NODE(&rt_waiter.pi_tree_entry);
- - RB_CLEAR_NODE(&rt_waiter.tree_entry);
- - rt_waiter.task = NULL;
- + rt_mutex_init_waiter(&rt_waiter, false);
-
- ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, VERIFY_WRITE);
- if (unlikely(ret != 0))
- @@ -2750,20 +2762,55 @@
- /* Queue the futex_q, drop the hb lock, wait for wakeup. */
- futex_wait_queue_me(hb, &q, to);
-
- - spin_lock(&hb->lock);
- - ret = handle_early_requeue_pi_wakeup(hb, &q, &key2, to);
- - spin_unlock(&hb->lock);
- - if (ret)
- - goto out_put_keys;
- + /*
- + * On RT we must avoid races with requeue and trying to block
- + * on two mutexes (hb->lock and uaddr2's rtmutex) by
- + * serializing access to pi_blocked_on with pi_lock.
- + */
- + raw_spin_lock_irq(¤t->pi_lock);
- + if (current->pi_blocked_on) {
- + /*
- + * We have been requeued or are in the process of
- + * being requeued.
- + */
- + raw_spin_unlock_irq(¤t->pi_lock);
- + } else {
- + /*
- + * Setting pi_blocked_on to PI_WAKEUP_INPROGRESS
- + * prevents a concurrent requeue from moving us to the
- + * uaddr2 rtmutex. After that we can safely acquire
- + * (and possibly block on) hb->lock.
- + */
- + current->pi_blocked_on = PI_WAKEUP_INPROGRESS;
- + raw_spin_unlock_irq(¤t->pi_lock);
- +
- + spin_lock(&hb->lock);
- +
- + /*
- + * Clean up pi_blocked_on. We might leak it otherwise
- + * when we succeeded with the hb->lock in the fast
- + * path.
- + */
- + raw_spin_lock_irq(¤t->pi_lock);
- + current->pi_blocked_on = NULL;
- + raw_spin_unlock_irq(¤t->pi_lock);
- +
- + ret = handle_early_requeue_pi_wakeup(hb, &q, &key2, to);
- + spin_unlock(&hb->lock);
- + if (ret)
- + goto out_put_keys;
- + }
-
- /*
- - * In order for us to be here, we know our q.key == key2, and since
- - * we took the hb->lock above, we also know that futex_requeue() has
- - * completed and we no longer have to concern ourselves with a wakeup
- - * race with the atomic proxy lock acquisition by the requeue code. The
- - * futex_requeue dropped our key1 reference and incremented our key2
- - * reference count.
- + * In order to be here, we have either been requeued, are in
- + * the process of being requeued, or requeue successfully
- + * acquired uaddr2 on our behalf. If pi_blocked_on was
- + * non-null above, we may be racing with a requeue. Do not
- + * rely on q->lock_ptr to be hb2->lock until after blocking on
- + * hb->lock or hb2->lock. The futex_requeue dropped our key1
- + * reference and incremented our key2 reference count.
- */
- + hb2 = hash_futex(&key2);
-
- /* Check if the requeue code acquired the second futex for us. */
- if (!q.rt_waiter) {
- @@ -2772,14 +2819,15 @@
- * did a lock-steal - fix up the PI-state in that case.
- */
- if (q.pi_state && (q.pi_state->owner != current)) {
- - spin_lock(q.lock_ptr);
- + spin_lock(&hb2->lock);
- + BUG_ON(&hb2->lock != q.lock_ptr);
- ret = fixup_pi_state_owner(uaddr2, &q, current);
- /*
- * Drop the reference to the pi state which
- * the requeue_pi() code acquired for us.
- */
- free_pi_state(q.pi_state);
- - spin_unlock(q.lock_ptr);
- + spin_unlock(&hb2->lock);
- }
- } else {
- /*
- @@ -2792,7 +2840,8 @@
- ret = rt_mutex_finish_proxy_lock(pi_mutex, to, &rt_waiter);
- debug_rt_mutex_free_waiter(&rt_waiter);
-
- - spin_lock(q.lock_ptr);
- + spin_lock(&hb2->lock);
- + BUG_ON(&hb2->lock != q.lock_ptr);
- /*
- * Fixup the pi_state owner and possibly acquire the lock if we
- * haven't already.
- diff -Nur linux-4.4.28.orig/kernel/irq/handle.c linux-4.4.28/kernel/irq/handle.c
- --- linux-4.4.28.orig/kernel/irq/handle.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/irq/handle.c 2016-11-01 21:26:58.764341506 +0100
- @@ -134,6 +134,8 @@
-
- irqreturn_t handle_irq_event_percpu(struct irq_desc *desc)
- {
- + struct pt_regs *regs = get_irq_regs();
- + u64 ip = regs ? instruction_pointer(regs) : 0;
- irqreturn_t retval = IRQ_NONE;
- unsigned int flags = 0, irq = desc->irq_data.irq;
- struct irqaction *action = desc->action;
- @@ -176,7 +178,11 @@
- action = action->next;
- }
-
- - add_interrupt_randomness(irq, flags);
- +#ifdef CONFIG_PREEMPT_RT_FULL
- + desc->random_ip = ip;
- +#else
- + add_interrupt_randomness(irq, flags, ip);
- +#endif
-
- if (!noirqdebug)
- note_interrupt(desc, retval);
- diff -Nur linux-4.4.28.orig/kernel/irq/irqdesc.c linux-4.4.28/kernel/irq/irqdesc.c
- --- linux-4.4.28.orig/kernel/irq/irqdesc.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/irq/irqdesc.c 2016-11-01 21:26:58.764341506 +0100
- @@ -24,10 +24,27 @@
- static struct lock_class_key irq_desc_lock_class;
-
- #if defined(CONFIG_SMP)
- +static int __init irq_affinity_setup(char *str)
- +{
- + zalloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT);
- + cpulist_parse(str, irq_default_affinity);
- + /*
- + * Set at least the boot cpu. We don't want to end up with
- + * bugreports caused by random comandline masks
- + */
- + cpumask_set_cpu(smp_processor_id(), irq_default_affinity);
- + return 1;
- +}
- +__setup("irqaffinity=", irq_affinity_setup);
- +
- static void __init init_irq_default_affinity(void)
- {
- - alloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT);
- - cpumask_setall(irq_default_affinity);
- +#ifdef CONFIG_CPUMASK_OFFSTACK
- + if (!irq_default_affinity)
- + zalloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT);
- +#endif
- + if (cpumask_empty(irq_default_affinity))
- + cpumask_setall(irq_default_affinity);
- }
- #else
- static void __init init_irq_default_affinity(void)
- diff -Nur linux-4.4.28.orig/kernel/irq/manage.c linux-4.4.28/kernel/irq/manage.c
- --- linux-4.4.28.orig/kernel/irq/manage.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/irq/manage.c 2016-11-01 21:26:58.764341506 +0100
- @@ -22,6 +22,7 @@
- #include "internals.h"
-
- #ifdef CONFIG_IRQ_FORCED_THREADING
- +# ifndef CONFIG_PREEMPT_RT_BASE
- __read_mostly bool force_irqthreads;
-
- static int __init setup_forced_irqthreads(char *arg)
- @@ -30,6 +31,7 @@
- return 0;
- }
- early_param("threadirqs", setup_forced_irqthreads);
- +# endif
- #endif
-
- static void __synchronize_hardirq(struct irq_desc *desc)
- @@ -181,6 +183,62 @@
- irq_get_pending(struct cpumask *mask, struct irq_desc *desc) { }
- #endif
-
- +#ifdef CONFIG_PREEMPT_RT_FULL
- +static void _irq_affinity_notify(struct irq_affinity_notify *notify);
- +static struct task_struct *set_affinity_helper;
- +static LIST_HEAD(affinity_list);
- +static DEFINE_RAW_SPINLOCK(affinity_list_lock);
- +
- +static int set_affinity_thread(void *unused)
- +{
- + while (1) {
- + struct irq_affinity_notify *notify;
- + int empty;
- +
- + set_current_state(TASK_INTERRUPTIBLE);
- +
- + raw_spin_lock_irq(&affinity_list_lock);
- + empty = list_empty(&affinity_list);
- + raw_spin_unlock_irq(&affinity_list_lock);
- +
- + if (empty)
- + schedule();
- + if (kthread_should_stop())
- + break;
- + set_current_state(TASK_RUNNING);
- +try_next:
- + notify = NULL;
- +
- + raw_spin_lock_irq(&affinity_list_lock);
- + if (!list_empty(&affinity_list)) {
- + notify = list_first_entry(&affinity_list,
- + struct irq_affinity_notify, list);
- + list_del_init(¬ify->list);
- + }
- + raw_spin_unlock_irq(&affinity_list_lock);
- +
- + if (!notify)
- + continue;
- + _irq_affinity_notify(notify);
- + goto try_next;
- + }
- + return 0;
- +}
- +
- +static void init_helper_thread(void)
- +{
- + if (set_affinity_helper)
- + return;
- + set_affinity_helper = kthread_run(set_affinity_thread, NULL,
- + "affinity-cb");
- + WARN_ON(IS_ERR(set_affinity_helper));
- +}
- +#else
- +
- +static inline void init_helper_thread(void) { }
- +
- +#endif
- +
- int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask,
- bool force)
- {
- @@ -220,7 +278,17 @@
-
- if (desc->affinity_notify) {
- kref_get(&desc->affinity_notify->kref);
- +
- +#ifdef CONFIG_PREEMPT_RT_FULL
- + raw_spin_lock(&affinity_list_lock);
- + if (list_empty(&desc->affinity_notify->list))
- + list_add_tail(&affinity_list,
- + &desc->affinity_notify->list);
- + raw_spin_unlock(&affinity_list_lock);
- + wake_up_process(set_affinity_helper);
- +#else
- schedule_work(&desc->affinity_notify->work);
- +#endif
- }
- irqd_set(data, IRQD_AFFINITY_SET);
-
- @@ -258,10 +326,8 @@
- }
- EXPORT_SYMBOL_GPL(irq_set_affinity_hint);
-
- -static void irq_affinity_notify(struct work_struct *work)
- +static void _irq_affinity_notify(struct irq_affinity_notify *notify)
- {
- - struct irq_affinity_notify *notify =
- - container_of(work, struct irq_affinity_notify, work);
- struct irq_desc *desc = irq_to_desc(notify->irq);
- cpumask_var_t cpumask;
- unsigned long flags;
- @@ -283,6 +349,13 @@
- kref_put(¬ify->kref, notify->release);
- }
-
- +static void irq_affinity_notify(struct work_struct *work)
- +{
- + struct irq_affinity_notify *notify =
- + container_of(work, struct irq_affinity_notify, work);
- + _irq_affinity_notify(notify);
- +}
- +
- /**
- * irq_set_affinity_notifier - control notification of IRQ affinity changes
- * @irq: Interrupt for which to enable/disable notification
- @@ -312,6 +385,8 @@
- notify->irq = irq;
- kref_init(¬ify->kref);
- INIT_WORK(¬ify->work, irq_affinity_notify);
- + INIT_LIST_HEAD(¬ify->list);
- + init_helper_thread();
- }
-
- raw_spin_lock_irqsave(&desc->lock, flags);
- @@ -865,7 +940,15 @@
- local_bh_disable();
- ret = action->thread_fn(action->irq, action->dev_id);
- irq_finalize_oneshot(desc, action);
- - local_bh_enable();
- + /*
- + * Interrupts which have real time requirements can be set up
- + * to avoid softirq processing in the thread handler. This is
- + * safe as these interrupts do not raise soft interrupts.
- + */
- + if (irq_settings_no_softirq_call(desc))
- + _local_bh_enable();
- + else
- + local_bh_enable();
- return ret;
- }
-
- @@ -962,6 +1045,12 @@
- if (action_ret == IRQ_WAKE_THREAD)
- irq_wake_secondary(desc, action);
-
- +#ifdef CONFIG_PREEMPT_RT_FULL
- + migrate_disable();
- + add_interrupt_randomness(action->irq, 0,
- + desc->random_ip ^ (unsigned long) action);
- + migrate_enable();
- +#endif
- wake_threads_waitq(desc);
- }
-
- @@ -1315,6 +1404,9 @@
- irqd_set(&desc->irq_data, IRQD_NO_BALANCING);
- }
-
- + if (new->flags & IRQF_NO_SOFTIRQ_CALL)
- + irq_settings_set_no_softirq_call(desc);
- +
- /* Set default affinity mask once everything is setup */
- setup_affinity(desc, mask);
-
- @@ -1968,7 +2060,7 @@
- * This call sets the internal irqchip state of an interrupt,
- * depending on the value of @which.
- *
- - * This function should be called with preemption disabled if the
- + * This function should be called with migration disabled if the
- * interrupt controller has per-cpu registers.
- */
- int irq_set_irqchip_state(unsigned int irq, enum irqchip_irq_state which,
- diff -Nur linux-4.4.28.orig/kernel/irq/settings.h linux-4.4.28/kernel/irq/settings.h
- --- linux-4.4.28.orig/kernel/irq/settings.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/irq/settings.h 2016-11-01 21:26:58.764341506 +0100
- @@ -16,6 +16,7 @@
- _IRQ_PER_CPU_DEVID = IRQ_PER_CPU_DEVID,
- _IRQ_IS_POLLED = IRQ_IS_POLLED,
- _IRQ_DISABLE_UNLAZY = IRQ_DISABLE_UNLAZY,
- + _IRQ_NO_SOFTIRQ_CALL = IRQ_NO_SOFTIRQ_CALL,
- _IRQF_MODIFY_MASK = IRQF_MODIFY_MASK,
- };
-
- @@ -30,6 +31,7 @@
- #define IRQ_PER_CPU_DEVID GOT_YOU_MORON
- #define IRQ_IS_POLLED GOT_YOU_MORON
- #define IRQ_DISABLE_UNLAZY GOT_YOU_MORON
- +#define IRQ_NO_SOFTIRQ_CALL GOT_YOU_MORON
- #undef IRQF_MODIFY_MASK
- #define IRQF_MODIFY_MASK GOT_YOU_MORON
-
- @@ -40,6 +42,16 @@
- desc->status_use_accessors |= (set & _IRQF_MODIFY_MASK);
- }
-
- +static inline bool irq_settings_no_softirq_call(struct irq_desc *desc)
- +{
- + return desc->status_use_accessors & _IRQ_NO_SOFTIRQ_CALL;
- +}
- +
- +static inline void irq_settings_set_no_softirq_call(struct irq_desc *desc)
- +{
- + desc->status_use_accessors |= _IRQ_NO_SOFTIRQ_CALL;
- +}
- +
- static inline bool irq_settings_is_per_cpu(struct irq_desc *desc)
- {
- return desc->status_use_accessors & _IRQ_PER_CPU;
- diff -Nur linux-4.4.28.orig/kernel/irq/spurious.c linux-4.4.28/kernel/irq/spurious.c
- --- linux-4.4.28.orig/kernel/irq/spurious.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/irq/spurious.c 2016-11-01 21:26:58.764341506 +0100
- @@ -444,6 +444,10 @@
-
- static int __init irqfixup_setup(char *str)
- {
- +#ifdef CONFIG_PREEMPT_RT_BASE
- + pr_warn("irqfixup boot option not supported w/ CONFIG_PREEMPT_RT_BASE\n");
- + return 1;
- +#endif
- irqfixup = 1;
- printk(KERN_WARNING "Misrouted IRQ fixup support enabled.\n");
- printk(KERN_WARNING "This may impact system performance.\n");
- @@ -456,6 +460,10 @@
-
- static int __init irqpoll_setup(char *str)
- {
- +#ifdef CONFIG_PREEMPT_RT_BASE
- + pr_warn("irqpoll boot option not supported w/ CONFIG_PREEMPT_RT_BASE\n");
- + return 1;
- +#endif
- irqfixup = 2;
- printk(KERN_WARNING "Misrouted IRQ fixup and polling support "
- "enabled\n");
- diff -Nur linux-4.4.28.orig/kernel/irq_work.c linux-4.4.28/kernel/irq_work.c
- --- linux-4.4.28.orig/kernel/irq_work.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/irq_work.c 2016-11-01 21:26:58.768341770 +0100
- @@ -17,6 +17,7 @@
- #include <linux/cpu.h>
- #include <linux/notifier.h>
- #include <linux/smp.h>
- +#include <linux/interrupt.h>
- #include <asm/processor.h>
-
-
- @@ -65,6 +66,8 @@
- */
- bool irq_work_queue_on(struct irq_work *work, int cpu)
- {
- + struct llist_head *list;
- +
- /* All work should have been flushed before going offline */
- WARN_ON_ONCE(cpu_is_offline(cpu));
-
- @@ -75,7 +78,12 @@
- if (!irq_work_claim(work))
- return false;
-
- - if (llist_add(&work->llnode, &per_cpu(raised_list, cpu)))
- + if (IS_ENABLED(CONFIG_PREEMPT_RT_FULL) && !(work->flags & IRQ_WORK_HARD_IRQ))
- + list = &per_cpu(lazy_list, cpu);
- + else
- + list = &per_cpu(raised_list, cpu);
- +
- + if (llist_add(&work->llnode, list))
- arch_send_call_function_single_ipi(cpu);
-
- return true;
- @@ -86,6 +94,9 @@
- /* Enqueue the irq work @work on the current CPU */
- bool irq_work_queue(struct irq_work *work)
- {
- + struct llist_head *list;
- + bool lazy_work, realtime = IS_ENABLED(CONFIG_PREEMPT_RT_FULL);
- +
- /* Only queue if not already pending */
- if (!irq_work_claim(work))
- return false;
- @@ -93,13 +104,15 @@
- /* Queue the entry and raise the IPI if needed. */
- preempt_disable();
-
- - /* If the work is "lazy", handle it from next tick if any */
- - if (work->flags & IRQ_WORK_LAZY) {
- - if (llist_add(&work->llnode, this_cpu_ptr(&lazy_list)) &&
- - tick_nohz_tick_stopped())
- - arch_irq_work_raise();
- - } else {
- - if (llist_add(&work->llnode, this_cpu_ptr(&raised_list)))
- + lazy_work = work->flags & IRQ_WORK_LAZY;
- +
- + if (lazy_work || (realtime && !(work->flags & IRQ_WORK_HARD_IRQ)))
- + list = this_cpu_ptr(&lazy_list);
- + else
- + list = this_cpu_ptr(&raised_list);
- +
- + if (llist_add(&work->llnode, list)) {
- + if (!lazy_work || tick_nohz_tick_stopped())
- arch_irq_work_raise();
- }
-
- @@ -116,9 +129,8 @@
- raised = this_cpu_ptr(&raised_list);
- lazy = this_cpu_ptr(&lazy_list);
-
- - if (llist_empty(raised) || arch_irq_work_has_interrupt())
- - if (llist_empty(lazy))
- - return false;
- + if (llist_empty(raised) && llist_empty(lazy))
- + return false;
-
- /* All work should have been flushed before going offline */
- WARN_ON_ONCE(cpu_is_offline(smp_processor_id()));
- @@ -132,7 +144,7 @@
- struct irq_work *work;
- struct llist_node *llnode;
-
- - BUG_ON(!irqs_disabled());
- + BUG_ON_NONRT(!irqs_disabled());
-
- if (llist_empty(list))
- return;
- @@ -169,7 +181,16 @@
- void irq_work_run(void)
- {
- irq_work_run_list(this_cpu_ptr(&raised_list));
- - irq_work_run_list(this_cpu_ptr(&lazy_list));
- + if (IS_ENABLED(CONFIG_PREEMPT_RT_FULL)) {
- + /*
- + * NOTE: we raise softirq via IPI for safety,
- + * and execute in irq_work_tick() to move the
- + * overhead from hard to soft irq context.
- + */
- + if (!llist_empty(this_cpu_ptr(&lazy_list)))
- + raise_softirq(TIMER_SOFTIRQ);
- + } else
- + irq_work_run_list(this_cpu_ptr(&lazy_list));
- }
- EXPORT_SYMBOL_GPL(irq_work_run);
-
- @@ -179,8 +200,17 @@
-
- if (!llist_empty(raised) && !arch_irq_work_has_interrupt())
- irq_work_run_list(raised);
- +
- + if (!IS_ENABLED(CONFIG_PREEMPT_RT_FULL))
- + irq_work_run_list(this_cpu_ptr(&lazy_list));
- +}
- +
- +#if defined(CONFIG_IRQ_WORK) && defined(CONFIG_PREEMPT_RT_FULL)
- +void irq_work_tick_soft(void)
- +{
- irq_work_run_list(this_cpu_ptr(&lazy_list));
- }
- +#endif
-
- /*
- * Synchronize against the irq_work @entry, ensures the entry is not
- diff -Nur linux-4.4.28.orig/kernel/Kconfig.locks linux-4.4.28/kernel/Kconfig.locks
- --- linux-4.4.28.orig/kernel/Kconfig.locks 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/Kconfig.locks 2016-11-01 21:26:58.756340996 +0100
- @@ -225,11 +225,11 @@
-
- config MUTEX_SPIN_ON_OWNER
- def_bool y
- - depends on SMP && !DEBUG_MUTEXES && ARCH_SUPPORTS_ATOMIC_RMW
- + depends on SMP && !DEBUG_MUTEXES && ARCH_SUPPORTS_ATOMIC_RMW && !PREEMPT_RT_FULL
-
- config RWSEM_SPIN_ON_OWNER
- def_bool y
- - depends on SMP && RWSEM_XCHGADD_ALGORITHM && ARCH_SUPPORTS_ATOMIC_RMW
- + depends on SMP && RWSEM_XCHGADD_ALGORITHM && ARCH_SUPPORTS_ATOMIC_RMW && !PREEMPT_RT_FULL
-
- config LOCK_SPIN_ON_OWNER
- def_bool y
- diff -Nur linux-4.4.28.orig/kernel/Kconfig.preempt linux-4.4.28/kernel/Kconfig.preempt
- --- linux-4.4.28.orig/kernel/Kconfig.preempt 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/Kconfig.preempt 2016-11-01 21:26:58.756340996 +0100
- @@ -1,3 +1,16 @@
- +config PREEMPT
- + bool
- + select PREEMPT_COUNT
- +
- +config PREEMPT_RT_BASE
- + bool
- + select PREEMPT
- +
- +config HAVE_PREEMPT_LAZY
- + bool
- +
- +config PREEMPT_LAZY
- + def_bool y if HAVE_PREEMPT_LAZY && PREEMPT_RT_FULL
-
- choice
- prompt "Preemption Model"
- @@ -33,9 +46,9 @@
-
- Select this if you are building a kernel for a desktop system.
-
- -config PREEMPT
- +config PREEMPT__LL
- bool "Preemptible Kernel (Low-Latency Desktop)"
- - select PREEMPT_COUNT
- + select PREEMPT
- select UNINLINE_SPIN_UNLOCK if !ARCH_INLINE_SPIN_UNLOCK
- help
- This option reduces the latency of the kernel by making
- @@ -52,6 +65,22 @@
- embedded system with latency requirements in the milliseconds
- range.
-
- +config PREEMPT_RTB
- + bool "Preemptible Kernel (Basic RT)"
- + select PREEMPT_RT_BASE
- + help
- + This option is basically the same as (Low-Latency Desktop) but
- + enables changes which are preliminary for the full preemptible
- + RT kernel.
- +
- +config PREEMPT_RT_FULL
- + bool "Fully Preemptible Kernel (RT)"
- + depends on IRQ_FORCED_THREADING
- + select PREEMPT_RT_BASE
- + select PREEMPT_RCU
- + help
- + All and everything
- +
- endchoice
-
- config PREEMPT_COUNT
- diff -Nur linux-4.4.28.orig/kernel/ksysfs.c linux-4.4.28/kernel/ksysfs.c
- --- linux-4.4.28.orig/kernel/ksysfs.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/ksysfs.c 2016-11-01 21:26:58.768341770 +0100
- @@ -136,6 +136,15 @@
-
- #endif /* CONFIG_KEXEC_CORE */
-
- +#if defined(CONFIG_PREEMPT_RT_FULL)
- +static ssize_t realtime_show(struct kobject *kobj,
- + struct kobj_attribute *attr, char *buf)
- +{
- + return sprintf(buf, "%d\n", 1);
- +}
- +KERNEL_ATTR_RO(realtime);
- +#endif
- +
- /* whether file capabilities are enabled */
- static ssize_t fscaps_show(struct kobject *kobj,
- struct kobj_attribute *attr, char *buf)
- @@ -203,6 +212,9 @@
- &vmcoreinfo_attr.attr,
- #endif
- &rcu_expedited_attr.attr,
- +#ifdef CONFIG_PREEMPT_RT_FULL
- + &realtime_attr.attr,
- +#endif
- NULL
- };
-
- diff -Nur linux-4.4.28.orig/kernel/locking/lglock.c linux-4.4.28/kernel/locking/lglock.c
- --- linux-4.4.28.orig/kernel/locking/lglock.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/locking/lglock.c 2016-11-01 21:26:58.768341770 +0100
- @@ -4,6 +4,15 @@
- #include <linux/cpu.h>
- #include <linux/string.h>
-
- +#ifndef CONFIG_PREEMPT_RT_FULL
- +# define lg_lock_ptr arch_spinlock_t
- +# define lg_do_lock(l) arch_spin_lock(l)
- +# define lg_do_unlock(l) arch_spin_unlock(l)
- +#else
- +# define lg_lock_ptr struct rt_mutex
- +# define lg_do_lock(l) __rt_spin_lock__no_mg(l)
- +# define lg_do_unlock(l) __rt_spin_unlock(l)
- +#endif
- /*
- * Note there is no uninit, so lglocks cannot be defined in
- * modules (but it's fine to use them from there)
- @@ -12,51 +21,60 @@
-
- void lg_lock_init(struct lglock *lg, char *name)
- {
- +#ifdef CONFIG_PREEMPT_RT_FULL
- + int i;
- +
- + for_each_possible_cpu(i) {
- + struct rt_mutex *lock = per_cpu_ptr(lg->lock, i);
- +
- + rt_mutex_init(lock);
- + }
- +#endif
- LOCKDEP_INIT_MAP(&lg->lock_dep_map, name, &lg->lock_key, 0);
- }
- EXPORT_SYMBOL(lg_lock_init);
-
- void lg_local_lock(struct lglock *lg)
- {
- - arch_spinlock_t *lock;
- + lg_lock_ptr *lock;
-
- - preempt_disable();
- + migrate_disable();
- lock_acquire_shared(&lg->lock_dep_map, 0, 0, NULL, _RET_IP_);
- lock = this_cpu_ptr(lg->lock);
- - arch_spin_lock(lock);
- + lg_do_lock(lock);
- }
- EXPORT_SYMBOL(lg_local_lock);
-
- void lg_local_unlock(struct lglock *lg)
- {
- - arch_spinlock_t *lock;
- + lg_lock_ptr *lock;
-
- lock_release(&lg->lock_dep_map, 1, _RET_IP_);
- lock = this_cpu_ptr(lg->lock);
- - arch_spin_unlock(lock);
- - preempt_enable();
- + lg_do_unlock(lock);
- + migrate_enable();
- }
- EXPORT_SYMBOL(lg_local_unlock);
-
- void lg_local_lock_cpu(struct lglock *lg, int cpu)
- {
- - arch_spinlock_t *lock;
- + lg_lock_ptr *lock;
-
- - preempt_disable();
- + preempt_disable_nort();
- lock_acquire_shared(&lg->lock_dep_map, 0, 0, NULL, _RET_IP_);
- lock = per_cpu_ptr(lg->lock, cpu);
- - arch_spin_lock(lock);
- + lg_do_lock(lock);
- }
- EXPORT_SYMBOL(lg_local_lock_cpu);
-
- void lg_local_unlock_cpu(struct lglock *lg, int cpu)
- {
- - arch_spinlock_t *lock;
- + lg_lock_ptr *lock;
-
- lock_release(&lg->lock_dep_map, 1, _RET_IP_);
- lock = per_cpu_ptr(lg->lock, cpu);
- - arch_spin_unlock(lock);
- - preempt_enable();
- + lg_do_unlock(lock);
- + preempt_enable_nort();
- }
- EXPORT_SYMBOL(lg_local_unlock_cpu);
-
- @@ -68,30 +86,30 @@
- if (cpu2 < cpu1)
- swap(cpu1, cpu2);
-
- - preempt_disable();
- + preempt_disable_nort();
- lock_acquire_shared(&lg->lock_dep_map, 0, 0, NULL, _RET_IP_);
- - arch_spin_lock(per_cpu_ptr(lg->lock, cpu1));
- - arch_spin_lock(per_cpu_ptr(lg->lock, cpu2));
- + lg_do_lock(per_cpu_ptr(lg->lock, cpu1));
- + lg_do_lock(per_cpu_ptr(lg->lock, cpu2));
- }
-
- void lg_double_unlock(struct lglock *lg, int cpu1, int cpu2)
- {
- lock_release(&lg->lock_dep_map, 1, _RET_IP_);
- - arch_spin_unlock(per_cpu_ptr(lg->lock, cpu1));
- - arch_spin_unlock(per_cpu_ptr(lg->lock, cpu2));
- - preempt_enable();
- + lg_do_unlock(per_cpu_ptr(lg->lock, cpu1));
- + lg_do_unlock(per_cpu_ptr(lg->lock, cpu2));
- + preempt_enable_nort();
- }
-
- void lg_global_lock(struct lglock *lg)
- {
- int i;
-
- - preempt_disable();
- + preempt_disable_nort();
- lock_acquire_exclusive(&lg->lock_dep_map, 0, 0, NULL, _RET_IP_);
- for_each_possible_cpu(i) {
- - arch_spinlock_t *lock;
- + lg_lock_ptr *lock;
- lock = per_cpu_ptr(lg->lock, i);
- - arch_spin_lock(lock);
- + lg_do_lock(lock);
- }
- }
- EXPORT_SYMBOL(lg_global_lock);
- @@ -102,10 +120,35 @@
-
- lock_release(&lg->lock_dep_map, 1, _RET_IP_);
- for_each_possible_cpu(i) {
- - arch_spinlock_t *lock;
- + lg_lock_ptr *lock;
- lock = per_cpu_ptr(lg->lock, i);
- - arch_spin_unlock(lock);
- + lg_do_unlock(lock);
- }
- - preempt_enable();
- + preempt_enable_nort();
- }
- EXPORT_SYMBOL(lg_global_unlock);
- +
- +#ifdef CONFIG_PREEMPT_RT_FULL
- +/*
- + * HACK: If you use this, you get to keep the pieces.
- + * Used in queue_stop_cpus_work() when stop machinery
- + * is called from inactive CPU, so we can't schedule.
- + */
- +# define lg_do_trylock_relax(l) \
- + do { \
- + while (!__rt_spin_trylock(l)) \
- + cpu_relax(); \
- + } while (0)
- +
- +void lg_global_trylock_relax(struct lglock *lg)
- +{
- + int i;
- +
- + lock_acquire_exclusive(&lg->lock_dep_map, 0, 0, NULL, _RET_IP_);
- + for_each_possible_cpu(i) {
- + lg_lock_ptr *lock;
- + lock = per_cpu_ptr(lg->lock, i);
- + lg_do_trylock_relax(lock);
- + }
- +}
- +#endif
- diff -Nur linux-4.4.28.orig/kernel/locking/lockdep.c linux-4.4.28/kernel/locking/lockdep.c
- --- linux-4.4.28.orig/kernel/locking/lockdep.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/locking/lockdep.c 2016-11-01 21:26:58.768341770 +0100
- @@ -3525,6 +3525,7 @@
- }
- }
-
- +#ifndef CONFIG_PREEMPT_RT_FULL
- /*
- * We dont accurately track softirq state in e.g.
- * hardirq contexts (such as on 4KSTACKS), so only
- @@ -3539,6 +3540,7 @@
- DEBUG_LOCKS_WARN_ON(!current->softirqs_enabled);
- }
- }
- +#endif
-
- if (!debug_locks)
- print_irqtrace_events(current);
- diff -Nur linux-4.4.28.orig/kernel/locking/locktorture.c linux-4.4.28/kernel/locking/locktorture.c
- --- linux-4.4.28.orig/kernel/locking/locktorture.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/locking/locktorture.c 2016-11-01 21:26:58.768341770 +0100
- @@ -26,7 +26,6 @@
- #include <linux/kthread.h>
- #include <linux/sched/rt.h>
- #include <linux/spinlock.h>
- -#include <linux/rwlock.h>
- #include <linux/mutex.h>
- #include <linux/rwsem.h>
- #include <linux/smp.h>
- diff -Nur linux-4.4.28.orig/kernel/locking/Makefile linux-4.4.28/kernel/locking/Makefile
- --- linux-4.4.28.orig/kernel/locking/Makefile 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/locking/Makefile 2016-11-01 21:26:58.768341770 +0100
- @@ -1,5 +1,5 @@
-
- -obj-y += mutex.o semaphore.o rwsem.o percpu-rwsem.o
- +obj-y += semaphore.o percpu-rwsem.o
-
- ifdef CONFIG_FUNCTION_TRACER
- CFLAGS_REMOVE_lockdep.o = $(CC_FLAGS_FTRACE)
- @@ -8,7 +8,11 @@
- CFLAGS_REMOVE_rtmutex-debug.o = $(CC_FLAGS_FTRACE)
- endif
-
- +ifneq ($(CONFIG_PREEMPT_RT_FULL),y)
- +obj-y += mutex.o
- obj-$(CONFIG_DEBUG_MUTEXES) += mutex-debug.o
- +obj-y += rwsem.o
- +endif
- obj-$(CONFIG_LOCKDEP) += lockdep.o
- ifeq ($(CONFIG_PROC_FS),y)
- obj-$(CONFIG_LOCKDEP) += lockdep_proc.o
- @@ -22,7 +26,10 @@
- obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o
- obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o
- obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.o
- +ifneq ($(CONFIG_PREEMPT_RT_FULL),y)
- obj-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o
- obj-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem-xadd.o
- +endif
- +obj-$(CONFIG_PREEMPT_RT_FULL) += rt.o
- obj-$(CONFIG_QUEUED_RWLOCKS) += qrwlock.o
- obj-$(CONFIG_LOCK_TORTURE_TEST) += locktorture.o
- diff -Nur linux-4.4.28.orig/kernel/locking/rt.c linux-4.4.28/kernel/locking/rt.c
- --- linux-4.4.28.orig/kernel/locking/rt.c 1970-01-01 01:00:00.000000000 +0100
- +++ linux-4.4.28/kernel/locking/rt.c 2016-11-01 21:26:58.768341770 +0100
- @@ -0,0 +1,474 @@
- +/*
- + * kernel/rt.c
- + *
- + * Real-Time Preemption Support
- + *
- + * started by Ingo Molnar:
- + *
- + * Copyright (C) 2004-2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
- + * Copyright (C) 2006, Timesys Corp., Thomas Gleixner <tglx@timesys.com>
- + *
- + * historic credit for proving that Linux spinlocks can be implemented via
- + * RT-aware mutexes goes to many people: The Pmutex project (Dirk Grambow
- + * and others) who prototyped it on 2.4 and did lots of comparative
- + * research and analysis; TimeSys, for proving that you can implement a
- + * fully preemptible kernel via the use of IRQ threading and mutexes;
- + * Bill Huey for persuasively arguing on lkml that the mutex model is the
- + * right one; and to MontaVista, who ported pmutexes to 2.6.
- + *
- + * This code is a from-scratch implementation and is not based on pmutexes,
- + * but the idea of converting spinlocks to mutexes is used here too.
- + *
- + * lock debugging, locking tree, deadlock detection:
- + *
- + * Copyright (C) 2004, LynuxWorks, Inc., Igor Manyilov, Bill Huey
- + * Released under the General Public License (GPL).
- + *
- + * Includes portions of the generic R/W semaphore implementation from:
- + *
- + * Copyright (c) 2001 David Howells (dhowells@redhat.com).
- + * - Derived partially from idea by Andrea Arcangeli <andrea@suse.de>
- + * - Derived also from comments by Linus
- + *
- + * Pending ownership of locks and ownership stealing:
- + *
- + * Copyright (C) 2005, Kihon Technologies Inc., Steven Rostedt
- + *
- + * (also by Steven Rostedt)
- + * - Converted single pi_lock to individual task locks.
- + *
- + * By Esben Nielsen:
- + * Doing priority inheritance with help of the scheduler.
- + *
- + * Copyright (C) 2006, Timesys Corp., Thomas Gleixner <tglx@timesys.com>
- + * - major rework based on Esben Nielsens initial patch
- + * - replaced thread_info references by task_struct refs
- + * - removed task->pending_owner dependency
- + * - BKL drop/reacquire for semaphore style locks to avoid deadlocks
- + * in the scheduler return path as discussed with Steven Rostedt
- + *
- + * Copyright (C) 2006, Kihon Technologies Inc.
- + * Steven Rostedt <rostedt@goodmis.org>
- + * - debugged and patched Thomas Gleixner's rework.
- + * - added back the cmpxchg to the rework.
- + * - turned atomic require back on for SMP.
- + */
- +
- +#include <linux/spinlock.h>
- +#include <linux/rtmutex.h>
- +#include <linux/sched.h>
- +#include <linux/delay.h>
- +#include <linux/module.h>
- +#include <linux/kallsyms.h>
- +#include <linux/syscalls.h>
- +#include <linux/interrupt.h>
- +#include <linux/plist.h>
- +#include <linux/fs.h>
- +#include <linux/futex.h>
- +#include <linux/hrtimer.h>
- +
- +#include "rtmutex_common.h"
- +
- +/*
- + * struct mutex functions
- + */
- +void __mutex_do_init(struct mutex *mutex, const char *name,
- + struct lock_class_key *key)
- +{
- +#ifdef CONFIG_DEBUG_LOCK_ALLOC
- + /*
- + * Make sure we are not reinitializing a held lock:
- + */
- + debug_check_no_locks_freed((void *)mutex, sizeof(*mutex));
- + lockdep_init_map(&mutex->dep_map, name, key, 0);
- +#endif
- + mutex->lock.save_state = 0;
- +}
- +EXPORT_SYMBOL(__mutex_do_init);
- +
- +void __lockfunc _mutex_lock(struct mutex *lock)
- +{
- + mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_);
- + rt_mutex_lock(&lock->lock);
- +}
- +EXPORT_SYMBOL(_mutex_lock);
- +
- +int __lockfunc _mutex_lock_interruptible(struct mutex *lock)
- +{
- + int ret;
- +
- + mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_);
- + ret = rt_mutex_lock_interruptible(&lock->lock);
- + if (ret)
- + mutex_release(&lock->dep_map, 1, _RET_IP_);
- + return ret;
- +}
- +EXPORT_SYMBOL(_mutex_lock_interruptible);
- +
- +int __lockfunc _mutex_lock_killable(struct mutex *lock)
- +{
- + int ret;
- +
- + mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_);
- + ret = rt_mutex_lock_killable(&lock->lock);
- + if (ret)
- + mutex_release(&lock->dep_map, 1, _RET_IP_);
- + return ret;
- +}
- +EXPORT_SYMBOL(_mutex_lock_killable);
- +
- +#ifdef CONFIG_DEBUG_LOCK_ALLOC
- +void __lockfunc _mutex_lock_nested(struct mutex *lock, int subclass)
- +{
- + mutex_acquire_nest(&lock->dep_map, subclass, 0, NULL, _RET_IP_);
- + rt_mutex_lock(&lock->lock);
- +}
- +EXPORT_SYMBOL(_mutex_lock_nested);
- +
- +void __lockfunc _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest)
- +{
- + mutex_acquire_nest(&lock->dep_map, 0, 0, nest, _RET_IP_);
- + rt_mutex_lock(&lock->lock);
- +}
- +EXPORT_SYMBOL(_mutex_lock_nest_lock);
- +
- +int __lockfunc _mutex_lock_interruptible_nested(struct mutex *lock, int subclass)
- +{
- + int ret;
- +
- + mutex_acquire_nest(&lock->dep_map, subclass, 0, NULL, _RET_IP_);
- + ret = rt_mutex_lock_interruptible(&lock->lock);
- + if (ret)
- + mutex_release(&lock->dep_map, 1, _RET_IP_);
- + return ret;
- +}
- +EXPORT_SYMBOL(_mutex_lock_interruptible_nested);
- +
- +int __lockfunc _mutex_lock_killable_nested(struct mutex *lock, int subclass)
- +{
- + int ret;
- +
- + mutex_acquire(&lock->dep_map, subclass, 0, _RET_IP_);
- + ret = rt_mutex_lock_killable(&lock->lock);
- + if (ret)
- + mutex_release(&lock->dep_map, 1, _RET_IP_);
- + return ret;
- +}
- +EXPORT_SYMBOL(_mutex_lock_killable_nested);
- +#endif
- +
- +int __lockfunc _mutex_trylock(struct mutex *lock)
- +{
- + int ret = rt_mutex_trylock(&lock->lock);
- +
- + if (ret)
- + mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_);
- +
- + return ret;
- +}
- +EXPORT_SYMBOL(_mutex_trylock);
- +
- +void __lockfunc _mutex_unlock(struct mutex *lock)
- +{
- + mutex_release(&lock->dep_map, 1, _RET_IP_);
- + rt_mutex_unlock(&lock->lock);
- +}
- +EXPORT_SYMBOL(_mutex_unlock);
- +
- +/*
- + * rwlock_t functions
- + */
- +int __lockfunc rt_write_trylock(rwlock_t *rwlock)
- +{
- + int ret;
- +
- + migrate_disable();
- + ret = rt_mutex_trylock(&rwlock->lock);
- + if (ret)
- + rwlock_acquire(&rwlock->dep_map, 0, 1, _RET_IP_);
- + else
- + migrate_enable();
- +
- + return ret;
- +}
- +EXPORT_SYMBOL(rt_write_trylock);
- +
- +int __lockfunc rt_write_trylock_irqsave(rwlock_t *rwlock, unsigned long *flags)
- +{
- + int ret;
- +
- + *flags = 0;
- + ret = rt_write_trylock(rwlock);
- + return ret;
- +}
- +EXPORT_SYMBOL(rt_write_trylock_irqsave);
- +
- +int __lockfunc rt_read_trylock(rwlock_t *rwlock)
- +{
- + struct rt_mutex *lock = &rwlock->lock;
- + int ret = 1;
- +
- + /*
- + * recursive read locks succeed when current owns the lock,
- + * but not when read_depth == 0 which means that the lock is
- + * write locked.
- + */
- + if (rt_mutex_owner(lock) != current) {
- + migrate_disable();
- + ret = rt_mutex_trylock(lock);
- + if (ret)
- + rwlock_acquire(&rwlock->dep_map, 0, 1, _RET_IP_);
- + else
- + migrate_enable();
- +
- + } else if (!rwlock->read_depth) {
- + ret = 0;
- + }
- +
- + if (ret)
- + rwlock->read_depth++;
- +
- + return ret;
- +}
- +EXPORT_SYMBOL(rt_read_trylock);
- +
- +void __lockfunc rt_write_lock(rwlock_t *rwlock)
- +{
- + rwlock_acquire(&rwlock->dep_map, 0, 0, _RET_IP_);
- + __rt_spin_lock(&rwlock->lock);
- +}
- +EXPORT_SYMBOL(rt_write_lock);
- +
- +void __lockfunc rt_read_lock(rwlock_t *rwlock)
- +{
- + struct rt_mutex *lock = &rwlock->lock;
- +
- +
- + /*
- + * recursive read locks succeed when current owns the lock
- + */
- + if (rt_mutex_owner(lock) != current) {
- + rwlock_acquire(&rwlock->dep_map, 0, 0, _RET_IP_);
- + __rt_spin_lock(lock);
- + }
- + rwlock->read_depth++;
- +}
- +
- +EXPORT_SYMBOL(rt_read_lock);
- +
- +void __lockfunc rt_write_unlock(rwlock_t *rwlock)
- +{
- + /* NOTE: we always pass in '1' for nested, for simplicity */
- + rwlock_release(&rwlock->dep_map, 1, _RET_IP_);
- + __rt_spin_unlock(&rwlock->lock);
- + migrate_enable();
- +}
- +EXPORT_SYMBOL(rt_write_unlock);
- +
- +void __lockfunc rt_read_unlock(rwlock_t *rwlock)
- +{
- + /* Release the lock only when read_depth is down to 0 */
- + if (--rwlock->read_depth == 0) {
- + rwlock_release(&rwlock->dep_map, 1, _RET_IP_);
- + __rt_spin_unlock(&rwlock->lock);
- + migrate_enable();
- + }
- +}
- +EXPORT_SYMBOL(rt_read_unlock);
- +
- +unsigned long __lockfunc rt_write_lock_irqsave(rwlock_t *rwlock)
- +{
- + rt_write_lock(rwlock);
- +
- + return 0;
- +}
- +EXPORT_SYMBOL(rt_write_lock_irqsave);
- +
- +unsigned long __lockfunc rt_read_lock_irqsave(rwlock_t *rwlock)
- +{
- + rt_read_lock(rwlock);
- +
- + return 0;
- +}
- +EXPORT_SYMBOL(rt_read_lock_irqsave);
- +
- +void __rt_rwlock_init(rwlock_t *rwlock, char *name, struct lock_class_key *key)
- +{
- +#ifdef CONFIG_DEBUG_LOCK_ALLOC
- + /*
- + * Make sure we are not reinitializing a held lock:
- + */
- + debug_check_no_locks_freed((void *)rwlock, sizeof(*rwlock));
- + lockdep_init_map(&rwlock->dep_map, name, key, 0);
- +#endif
- + rwlock->lock.save_state = 1;
- + rwlock->read_depth = 0;
- +}
- +EXPORT_SYMBOL(__rt_rwlock_init);
- +
- +/*
- + * rw_semaphores
- + */
- +
- +void rt_up_write(struct rw_semaphore *rwsem)
- +{
- + rwsem_release(&rwsem->dep_map, 1, _RET_IP_);
- + rt_mutex_unlock(&rwsem->lock);
- +}
- +EXPORT_SYMBOL(rt_up_write);
- +
- +void __rt_up_read(struct rw_semaphore *rwsem)
- +{
- + if (--rwsem->read_depth == 0)
- + rt_mutex_unlock(&rwsem->lock);
- +}
- +
- +void rt_up_read(struct rw_semaphore *rwsem)
- +{
- + rwsem_release(&rwsem->dep_map, 1, _RET_IP_);
- + __rt_up_read(rwsem);
- +}
- +EXPORT_SYMBOL(rt_up_read);
- +
- +/*
- + * downgrade a write lock into a read lock
- + * - just wake up any readers at the front of the queue
- + */
- +void rt_downgrade_write(struct rw_semaphore *rwsem)
- +{
- + BUG_ON(rt_mutex_owner(&rwsem->lock) != current);
- + rwsem->read_depth = 1;
- +}
- +EXPORT_SYMBOL(rt_downgrade_write);
- +
- +int rt_down_write_trylock(struct rw_semaphore *rwsem)
- +{
- + int ret = rt_mutex_trylock(&rwsem->lock);
- +
- + if (ret)
- + rwsem_acquire(&rwsem->dep_map, 0, 1, _RET_IP_);
- + return ret;
- +}
- +EXPORT_SYMBOL(rt_down_write_trylock);
- +
- +void rt_down_write(struct rw_semaphore *rwsem)
- +{
- + rwsem_acquire(&rwsem->dep_map, 0, 0, _RET_IP_);
- + rt_mutex_lock(&rwsem->lock);
- +}
- +EXPORT_SYMBOL(rt_down_write);
- +
- +void rt_down_write_nested(struct rw_semaphore *rwsem, int subclass)
- +{
- + rwsem_acquire(&rwsem->dep_map, subclass, 0, _RET_IP_);
- + rt_mutex_lock(&rwsem->lock);
- +}
- +EXPORT_SYMBOL(rt_down_write_nested);
- +
- +void rt_down_write_nested_lock(struct rw_semaphore *rwsem,
- + struct lockdep_map *nest)
- +{
- + rwsem_acquire_nest(&rwsem->dep_map, 0, 0, nest, _RET_IP_);
- + rt_mutex_lock(&rwsem->lock);
- +}
- +EXPORT_SYMBOL(rt_down_write_nested_lock);
- +
- +int rt__down_read_trylock(struct rw_semaphore *rwsem)
- +{
- + struct rt_mutex *lock = &rwsem->lock;
- + int ret = 1;
- +
- + /*
- + * recursive read locks succeed when current owns the rwsem,
- + * but not when read_depth == 0 which means that the rwsem is
- + * write locked.
- + */
- + if (rt_mutex_owner(lock) != current)
- + ret = rt_mutex_trylock(&rwsem->lock);
- + else if (!rwsem->read_depth)
- + ret = 0;
- +
- + if (ret)
- + rwsem->read_depth++;
- + return ret;
- +
- +}
- +
- +int rt_down_read_trylock(struct rw_semaphore *rwsem)
- +{
- + int ret;
- +
- + ret = rt__down_read_trylock(rwsem);
- + if (ret)
- + rwsem_acquire(&rwsem->dep_map, 0, 1, _RET_IP_);
- +
- + return ret;
- +}
- +EXPORT_SYMBOL(rt_down_read_trylock);
- +
- +void rt__down_read(struct rw_semaphore *rwsem)
- +{
- + struct rt_mutex *lock = &rwsem->lock;
- +
- + if (rt_mutex_owner(lock) != current)
- + rt_mutex_lock(&rwsem->lock);
- + rwsem->read_depth++;
- +}
- +EXPORT_SYMBOL(rt__down_read);
- +
- +static void __rt_down_read(struct rw_semaphore *rwsem, int subclass)
- +{
- + rwsem_acquire_read(&rwsem->dep_map, subclass, 0, _RET_IP_);
- + rt__down_read(rwsem);
- +}
- +
- +void rt_down_read(struct rw_semaphore *rwsem)
- +{
- + __rt_down_read(rwsem, 0);
- +}
- +EXPORT_SYMBOL(rt_down_read);
- +
- +void rt_down_read_nested(struct rw_semaphore *rwsem, int subclass)
- +{
- + __rt_down_read(rwsem, subclass);
- +}
- +EXPORT_SYMBOL(rt_down_read_nested);
- +
- +void __rt_rwsem_init(struct rw_semaphore *rwsem, const char *name,
- + struct lock_class_key *key)
- +{
- +#ifdef CONFIG_DEBUG_LOCK_ALLOC
- + /*
- + * Make sure we are not reinitializing a held lock:
- + */
- + debug_check_no_locks_freed((void *)rwsem, sizeof(*rwsem));
- + lockdep_init_map(&rwsem->dep_map, name, key, 0);
- +#endif
- + rwsem->read_depth = 0;
- + rwsem->lock.save_state = 0;
- +}
- +EXPORT_SYMBOL(__rt_rwsem_init);
- +
- +/**
- + * atomic_dec_and_mutex_lock - return holding mutex if we dec to 0
- + * @cnt: the atomic which we are to dec
- + * @lock: the mutex to return holding if we dec to 0
- + *
- + * return true and hold lock if we dec to 0, return false otherwise
- + */
- +int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock)
- +{
- + /* dec if we can't possibly hit 0 */
- + if (atomic_add_unless(cnt, -1, 1))
- + return 0;
- + /* we might hit 0, so take the lock */
- + mutex_lock(lock);
- + if (!atomic_dec_and_test(cnt)) {
- + /* when we actually did the dec, we didn't hit 0 */
- + mutex_unlock(lock);
- + return 0;
- + }
- + /* we hit 0, and we hold the lock */
- + return 1;
- +}
- +EXPORT_SYMBOL(atomic_dec_and_mutex_lock);
- diff -Nur linux-4.4.28.orig/kernel/locking/rtmutex.c linux-4.4.28/kernel/locking/rtmutex.c
- --- linux-4.4.28.orig/kernel/locking/rtmutex.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/locking/rtmutex.c 2016-11-01 21:26:58.772342023 +0100
- @@ -7,6 +7,11 @@
- * Copyright (C) 2005-2006 Timesys Corp., Thomas Gleixner <tglx@timesys.com>
- * Copyright (C) 2005 Kihon Technologies Inc., Steven Rostedt
- * Copyright (C) 2006 Esben Nielsen
- + * Adaptive Spinlocks:
- + * Copyright (C) 2008 Novell, Inc., Gregory Haskins, Sven Dietrich,
- + * and Peter Morreale,
- + * Adaptive Spinlocks simplification:
- + * Copyright (C) 2008 Red Hat, Inc., Steven Rostedt <srostedt@redhat.com>
- *
- * See Documentation/locking/rt-mutex-design.txt for details.
- */
- @@ -16,6 +21,7 @@
- #include <linux/sched/rt.h>
- #include <linux/sched/deadline.h>
- #include <linux/timer.h>
- +#include <linux/ww_mutex.h>
-
- #include "rtmutex_common.h"
-
- @@ -69,6 +75,12 @@
- clear_rt_mutex_waiters(lock);
- }
-
- +static int rt_mutex_real_waiter(struct rt_mutex_waiter *waiter)
- +{
- + return waiter && waiter != PI_WAKEUP_INPROGRESS &&
- + waiter != PI_REQUEUE_INPROGRESS;
- +}
- +
- /*
- * We can speed up the acquire/release, if there's no debugging state to be
- * set up.
- @@ -99,13 +111,14 @@
- * 2) Drop lock->wait_lock
- * 3) Try to unlock the lock with cmpxchg
- */
- -static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock)
- +static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock,
- + unsigned long flags)
- __releases(lock->wait_lock)
- {
- struct task_struct *owner = rt_mutex_owner(lock);
-
- clear_rt_mutex_waiters(lock);
- - raw_spin_unlock(&lock->wait_lock);
- + raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
- /*
- * If a new waiter comes in between the unlock and the cmpxchg
- * we have two situations:
- @@ -147,11 +160,12 @@
- /*
- * Simple slow path only version: lock->owner is protected by lock->wait_lock.
- */
- -static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock)
- +static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock,
- + unsigned long flags)
- __releases(lock->wait_lock)
- {
- lock->owner = NULL;
- - raw_spin_unlock(&lock->wait_lock);
- + raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
- return true;
- }
- #endif
- @@ -348,6 +362,14 @@
- return debug_rt_mutex_detect_deadlock(waiter, chwalk);
- }
-
- +static void rt_mutex_wake_waiter(struct rt_mutex_waiter *waiter)
- +{
- + if (waiter->savestate)
- + wake_up_lock_sleeper(waiter->task);
- + else
- + wake_up_process(waiter->task);
- +}
- +
- /*
- * Max number of times we'll walk the boosting chain:
- */
- @@ -355,7 +377,8 @@
-
- static inline struct rt_mutex *task_blocked_on_lock(struct task_struct *p)
- {
- - return p->pi_blocked_on ? p->pi_blocked_on->lock : NULL;
- + return rt_mutex_real_waiter(p->pi_blocked_on) ?
- + p->pi_blocked_on->lock : NULL;
- }
-
- /*
- @@ -433,7 +456,6 @@
- int ret = 0, depth = 0;
- struct rt_mutex *lock;
- bool detect_deadlock;
- - unsigned long flags;
- bool requeue = true;
-
- detect_deadlock = rt_mutex_cond_detect_deadlock(orig_waiter, chwalk);
- @@ -476,7 +498,7 @@
- /*
- * [1] Task cannot go away as we did a get_task() before !
- */
- - raw_spin_lock_irqsave(&task->pi_lock, flags);
- + raw_spin_lock_irq(&task->pi_lock);
-
- /*
- * [2] Get the waiter on which @task is blocked on.
- @@ -492,7 +514,7 @@
- * reached or the state of the chain has changed while we
- * dropped the locks.
- */
- - if (!waiter)
- + if (!rt_mutex_real_waiter(waiter))
- goto out_unlock_pi;
-
- /*
- @@ -560,7 +582,7 @@
- * operations.
- */
- if (!raw_spin_trylock(&lock->wait_lock)) {
- - raw_spin_unlock_irqrestore(&task->pi_lock, flags);
- + raw_spin_unlock_irq(&task->pi_lock);
- cpu_relax();
- goto retry;
- }
- @@ -591,7 +613,7 @@
- /*
- * No requeue[7] here. Just release @task [8]
- */
- - raw_spin_unlock_irqrestore(&task->pi_lock, flags);
- + raw_spin_unlock(&task->pi_lock);
- put_task_struct(task);
-
- /*
- @@ -599,14 +621,14 @@
- * If there is no owner of the lock, end of chain.
- */
- if (!rt_mutex_owner(lock)) {
- - raw_spin_unlock(&lock->wait_lock);
- + raw_spin_unlock_irq(&lock->wait_lock);
- return 0;
- }
-
- /* [10] Grab the next task, i.e. owner of @lock */
- task = rt_mutex_owner(lock);
- get_task_struct(task);
- - raw_spin_lock_irqsave(&task->pi_lock, flags);
- + raw_spin_lock(&task->pi_lock);
-
- /*
- * No requeue [11] here. We just do deadlock detection.
- @@ -621,8 +643,8 @@
- top_waiter = rt_mutex_top_waiter(lock);
-
- /* [13] Drop locks */
- - raw_spin_unlock_irqrestore(&task->pi_lock, flags);
- - raw_spin_unlock(&lock->wait_lock);
- + raw_spin_unlock(&task->pi_lock);
- + raw_spin_unlock_irq(&lock->wait_lock);
-
- /* If owner is not blocked, end of chain. */
- if (!next_lock)
- @@ -643,7 +665,7 @@
- rt_mutex_enqueue(lock, waiter);
-
- /* [8] Release the task */
- - raw_spin_unlock_irqrestore(&task->pi_lock, flags);
- + raw_spin_unlock(&task->pi_lock);
- put_task_struct(task);
-
- /*
- @@ -654,21 +676,24 @@
- * follow here. This is the end of the chain we are walking.
- */
- if (!rt_mutex_owner(lock)) {
- + struct rt_mutex_waiter *lock_top_waiter;
- +
- /*
- * If the requeue [7] above changed the top waiter,
- * then we need to wake the new top waiter up to try
- * to get the lock.
- */
- - if (prerequeue_top_waiter != rt_mutex_top_waiter(lock))
- - wake_up_process(rt_mutex_top_waiter(lock)->task);
- - raw_spin_unlock(&lock->wait_lock);
- + lock_top_waiter = rt_mutex_top_waiter(lock);
- + if (prerequeue_top_waiter != lock_top_waiter)
- + rt_mutex_wake_waiter(lock_top_waiter);
- + raw_spin_unlock_irq(&lock->wait_lock);
- return 0;
- }
-
- /* [10] Grab the next task, i.e. the owner of @lock */
- task = rt_mutex_owner(lock);
- get_task_struct(task);
- - raw_spin_lock_irqsave(&task->pi_lock, flags);
- + raw_spin_lock(&task->pi_lock);
-
- /* [11] requeue the pi waiters if necessary */
- if (waiter == rt_mutex_top_waiter(lock)) {
- @@ -722,8 +747,8 @@
- top_waiter = rt_mutex_top_waiter(lock);
-
- /* [13] Drop the locks */
- - raw_spin_unlock_irqrestore(&task->pi_lock, flags);
- - raw_spin_unlock(&lock->wait_lock);
- + raw_spin_unlock(&task->pi_lock);
- + raw_spin_unlock_irq(&lock->wait_lock);
-
- /*
- * Make the actual exit decisions [12], based on the stored
- @@ -746,28 +771,46 @@
- goto again;
-
- out_unlock_pi:
- - raw_spin_unlock_irqrestore(&task->pi_lock, flags);
- + raw_spin_unlock_irq(&task->pi_lock);
- out_put_task:
- put_task_struct(task);
-
- return ret;
- }
-
- +
- +#define STEAL_NORMAL 0
- +#define STEAL_LATERAL 1
- +
- +/*
- + * Note that RT tasks are excluded from lateral-steals to prevent the
- + * introduction of an unbounded latency
- + */
- +static inline int lock_is_stealable(struct task_struct *task,
- + struct task_struct *pendowner, int mode)
- +{
- + if (mode == STEAL_NORMAL || rt_task(task)) {
- + if (task->prio >= pendowner->prio)
- + return 0;
- + } else if (task->prio > pendowner->prio)
- + return 0;
- + return 1;
- +}
- +
- /*
- * Try to take an rt-mutex
- *
- - * Must be called with lock->wait_lock held.
- + * Must be called with lock->wait_lock held and interrupts disabled
- *
- * @lock: The lock to be acquired.
- * @task: The task which wants to acquire the lock
- * @waiter: The waiter that is queued to the lock's wait tree if the
- * callsite called task_blocked_on_lock(), otherwise NULL
- */
- -static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
- - struct rt_mutex_waiter *waiter)
- +static int __try_to_take_rt_mutex(struct rt_mutex *lock,
- + struct task_struct *task,
- + struct rt_mutex_waiter *waiter, int mode)
- {
- - unsigned long flags;
- -
- /*
- * Before testing whether we can acquire @lock, we set the
- * RT_MUTEX_HAS_WAITERS bit in @lock->owner. This forces all
- @@ -803,8 +846,10 @@
- * If waiter is not the highest priority waiter of
- * @lock, give up.
- */
- - if (waiter != rt_mutex_top_waiter(lock))
- + if (waiter != rt_mutex_top_waiter(lock)) {
- + /* XXX lock_is_stealable() ? */
- return 0;
- + }
-
- /*
- * We can acquire the lock. Remove the waiter from the
- @@ -822,14 +867,10 @@
- * not need to be dequeued.
- */
- if (rt_mutex_has_waiters(lock)) {
- - /*
- - * If @task->prio is greater than or equal to
- - * the top waiter priority (kernel view),
- - * @task lost.
- - */
- - if (task->prio >= rt_mutex_top_waiter(lock)->prio)
- - return 0;
- + struct task_struct *pown = rt_mutex_top_waiter(lock)->task;
-
- + if (task != pown && !lock_is_stealable(task, pown, mode))
- + return 0;
- /*
- * The current top waiter stays enqueued. We
- * don't have to change anything in the lock
- @@ -852,7 +893,7 @@
- * case, but conditionals are more expensive than a redundant
- * store.
- */
- - raw_spin_lock_irqsave(&task->pi_lock, flags);
- + raw_spin_lock(&task->pi_lock);
- task->pi_blocked_on = NULL;
- /*
- * Finish the lock acquisition. @task is the new owner. If
- @@ -861,7 +902,7 @@
- */
- if (rt_mutex_has_waiters(lock))
- rt_mutex_enqueue_pi(task, rt_mutex_top_waiter(lock));
- - raw_spin_unlock_irqrestore(&task->pi_lock, flags);
- + raw_spin_unlock(&task->pi_lock);
-
- takeit:
- /* We got the lock. */
- @@ -878,12 +919,444 @@
- return 1;
- }
-
- +#ifdef CONFIG_PREEMPT_RT_FULL
- +/*
- + * preemptible spin_lock functions:
- + */
- +static inline void rt_spin_lock_fastlock(struct rt_mutex *lock,
- + void (*slowfn)(struct rt_mutex *lock,
- + bool mg_off),
- + bool do_mig_dis)
- +{
- + might_sleep_no_state_check();
- +
- + if (do_mig_dis)
- + migrate_disable();
- +
- + if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current)))
- + rt_mutex_deadlock_account_lock(lock, current);
- + else
- + slowfn(lock, do_mig_dis);
- +}
- +
- +static inline int rt_spin_lock_fastunlock(struct rt_mutex *lock,
- + int (*slowfn)(struct rt_mutex *lock))
- +{
- + if (likely(rt_mutex_cmpxchg_release(lock, current, NULL))) {
- + rt_mutex_deadlock_account_unlock(current);
- + return 0;
- + }
- + return slowfn(lock);
- +}
- +#ifdef CONFIG_SMP
- +/*
- + * Note that owner is a speculative pointer and dereferencing relies
- + * on rcu_read_lock() and the check against the lock owner.
- + */
- +static int adaptive_wait(struct rt_mutex *lock,
- + struct task_struct *owner)
- +{
- + int res = 0;
- +
- + rcu_read_lock();
- + for (;;) {
- + if (owner != rt_mutex_owner(lock))
- + break;
- + /*
- + * Ensure that owner->on_cpu is dereferenced _after_
- + * checking the above to be valid.
- + */
- + barrier();
- + if (!owner->on_cpu) {
- + res = 1;
- + break;
- + }
- + cpu_relax();
- + }
- + rcu_read_unlock();
- + return res;
- +}
- +#else
- +static int adaptive_wait(struct rt_mutex *lock,
- + struct task_struct *orig_owner)
- +{
- + return 1;
- +}
- +#endif
- +
- +static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
- + struct rt_mutex_waiter *waiter,
- + struct task_struct *task,
- + enum rtmutex_chainwalk chwalk);
- +/*
- + * Slow path lock function spin_lock style: this variant is very
- + * careful not to miss any non-lock wakeups.
- + *
- + * We store the current state under p->pi_lock in p->saved_state and
- + * the try_to_wake_up() code handles this accordingly.
- + */
- +static void noinline __sched rt_spin_lock_slowlock(struct rt_mutex *lock,
- + bool mg_off)
- +{
- + struct task_struct *lock_owner, *self = current;
- + struct rt_mutex_waiter waiter, *top_waiter;
- + unsigned long flags;
- + int ret;
- +
- + rt_mutex_init_waiter(&waiter, true);
- +
- + raw_spin_lock_irqsave(&lock->wait_lock, flags);
- +
- + if (__try_to_take_rt_mutex(lock, self, NULL, STEAL_LATERAL)) {
- + raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
- + return;
- + }
- +
- + BUG_ON(rt_mutex_owner(lock) == self);
- +
- + /*
- + * We save whatever state the task is in and we'll restore it
- + * after acquiring the lock taking real wakeups into account
- + * as well. We are serialized via pi_lock against wakeups. See
- + * try_to_wake_up().
- + */
- + raw_spin_lock(&self->pi_lock);
- + self->saved_state = self->state;
- + __set_current_state_no_track(TASK_UNINTERRUPTIBLE);
- + raw_spin_unlock(&self->pi_lock);
- +
- + ret = task_blocks_on_rt_mutex(lock, &waiter, self, RT_MUTEX_MIN_CHAINWALK);
- + BUG_ON(ret);
- +
- + for (;;) {
- + /* Try to acquire the lock again. */
- + if (__try_to_take_rt_mutex(lock, self, &waiter, STEAL_LATERAL))
- + break;
- +
- + top_waiter = rt_mutex_top_waiter(lock);
- + lock_owner = rt_mutex_owner(lock);
- +
- + raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
- +
- + debug_rt_mutex_print_deadlock(&waiter);
- +
- + if (top_waiter != &waiter || adaptive_wait(lock, lock_owner)) {
- + if (mg_off)
- + migrate_enable();
- + schedule();
- + if (mg_off)
- + migrate_disable();
- + }
- +
- + raw_spin_lock_irqsave(&lock->wait_lock, flags);
- +
- + raw_spin_lock(&self->pi_lock);
- + __set_current_state_no_track(TASK_UNINTERRUPTIBLE);
- + raw_spin_unlock(&self->pi_lock);
- + }
- +
- + /*
- + * Restore the task state to current->saved_state. We set it
- + * to the original state above and the try_to_wake_up() code
- + * has possibly updated it when a real (non-rtmutex) wakeup
- + * happened while we were blocked. Clear saved_state so
- + * try_to_wakeup() does not get confused.
- + */
- + raw_spin_lock(&self->pi_lock);
- + __set_current_state_no_track(self->saved_state);
- + self->saved_state = TASK_RUNNING;
- + raw_spin_unlock(&self->pi_lock);
- +
- + /*
- + * try_to_take_rt_mutex() sets the waiter bit
- + * unconditionally. We might have to fix that up:
- + */
- + fixup_rt_mutex_waiters(lock);
- +
- + BUG_ON(rt_mutex_has_waiters(lock) && &waiter == rt_mutex_top_waiter(lock));
- + BUG_ON(!RB_EMPTY_NODE(&waiter.tree_entry));
- +
- + raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
- +
- + debug_rt_mutex_free_waiter(&waiter);
- +}
- +
- +static void mark_wakeup_next_waiter(struct wake_q_head *wake_q,
- + struct wake_q_head *wake_sleeper_q,
- + struct rt_mutex *lock);
- +/*
- + * Slow path to release a rt_mutex spin_lock style
- + */
- +static int noinline __sched rt_spin_lock_slowunlock(struct rt_mutex *lock)
- +{
- + unsigned long flags;
- + WAKE_Q(wake_q);
- + WAKE_Q(wake_sleeper_q);
- +
- + raw_spin_lock_irqsave(&lock->wait_lock, flags);
- +
- + debug_rt_mutex_unlock(lock);
- +
- + rt_mutex_deadlock_account_unlock(current);
- +
- + if (!rt_mutex_has_waiters(lock)) {
- + lock->owner = NULL;
- + raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
- + return 0;
- + }
- +
- + mark_wakeup_next_waiter(&wake_q, &wake_sleeper_q, lock);
- +
- + raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
- + wake_up_q(&wake_q);
- + wake_up_q_sleeper(&wake_sleeper_q);
- +
- + /* Undo pi boosting.when necessary */
- + rt_mutex_adjust_prio(current);
- + return 0;
- +}
- +
- +static int noinline __sched rt_spin_lock_slowunlock_no_deboost(struct rt_mutex *lock)
- +{
- + unsigned long flags;
- + WAKE_Q(wake_q);
- + WAKE_Q(wake_sleeper_q);
- +
- + raw_spin_lock_irqsave(&lock->wait_lock, flags);
- +
- + debug_rt_mutex_unlock(lock);
- +
- + rt_mutex_deadlock_account_unlock(current);
- +
- + if (!rt_mutex_has_waiters(lock)) {
- + lock->owner = NULL;
- + raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
- + return 0;
- + }
- +
- + mark_wakeup_next_waiter(&wake_q, &wake_sleeper_q, lock);
- +
- + raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
- + wake_up_q(&wake_q);
- + wake_up_q_sleeper(&wake_sleeper_q);
- + return 1;
- +}
- +
- +void __lockfunc rt_spin_lock__no_mg(spinlock_t *lock)
- +{
- + rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock, false);
- + spin_acquire(&lock->dep_map, 0, 0, _RET_IP_);
- +}
- +EXPORT_SYMBOL(rt_spin_lock__no_mg);
- +
- +void __lockfunc rt_spin_lock(spinlock_t *lock)
- +{
- + rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock, true);
- + spin_acquire(&lock->dep_map, 0, 0, _RET_IP_);
- +}
- +EXPORT_SYMBOL(rt_spin_lock);
- +
- +void __lockfunc __rt_spin_lock(struct rt_mutex *lock)
- +{
- + rt_spin_lock_fastlock(lock, rt_spin_lock_slowlock, true);
- +}
- +EXPORT_SYMBOL(__rt_spin_lock);
- +
- +void __lockfunc __rt_spin_lock__no_mg(struct rt_mutex *lock)
- +{
- + rt_spin_lock_fastlock(lock, rt_spin_lock_slowlock, false);
- +}
- +EXPORT_SYMBOL(__rt_spin_lock__no_mg);
- +
- +#ifdef CONFIG_DEBUG_LOCK_ALLOC
- +void __lockfunc rt_spin_lock_nested(spinlock_t *lock, int subclass)
- +{
- + spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_);
- + rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock, true);
- +}
- +EXPORT_SYMBOL(rt_spin_lock_nested);
- +#endif
- +
- +void __lockfunc rt_spin_unlock__no_mg(spinlock_t *lock)
- +{
- + /* NOTE: we always pass in '1' for nested, for simplicity */
- + spin_release(&lock->dep_map, 1, _RET_IP_);
- + rt_spin_lock_fastunlock(&lock->lock, rt_spin_lock_slowunlock);
- +}
- +EXPORT_SYMBOL(rt_spin_unlock__no_mg);
- +
- +void __lockfunc rt_spin_unlock(spinlock_t *lock)
- +{
- + /* NOTE: we always pass in '1' for nested, for simplicity */
- + spin_release(&lock->dep_map, 1, _RET_IP_);
- + rt_spin_lock_fastunlock(&lock->lock, rt_spin_lock_slowunlock);
- + migrate_enable();
- +}
- +EXPORT_SYMBOL(rt_spin_unlock);
- +
- +int __lockfunc rt_spin_unlock_no_deboost(spinlock_t *lock)
- +{
- + int ret;
- +
- + /* NOTE: we always pass in '1' for nested, for simplicity */
- + spin_release(&lock->dep_map, 1, _RET_IP_);
- + ret = rt_spin_lock_fastunlock(&lock->lock, rt_spin_lock_slowunlock_no_deboost);
- + migrate_enable();
- + return ret;
- +}
- +
- +void __lockfunc __rt_spin_unlock(struct rt_mutex *lock)
- +{
- + rt_spin_lock_fastunlock(lock, rt_spin_lock_slowunlock);
- +}
- +EXPORT_SYMBOL(__rt_spin_unlock);
- +
- +/*
- + * Wait for the lock to get unlocked: instead of polling for an unlock
- + * (like raw spinlocks do), we lock and unlock, to force the kernel to
- + * schedule if there's contention:
- + */
- +void __lockfunc rt_spin_unlock_wait(spinlock_t *lock)
- +{
- + spin_lock(lock);
- + spin_unlock(lock);
- +}
- +EXPORT_SYMBOL(rt_spin_unlock_wait);
- +
- +int __lockfunc __rt_spin_trylock(struct rt_mutex *lock)
- +{
- + return rt_mutex_trylock(lock);
- +}
- +
- +int __lockfunc rt_spin_trylock__no_mg(spinlock_t *lock)
- +{
- + int ret;
- +
- + ret = rt_mutex_trylock(&lock->lock);
- + if (ret)
- + spin_acquire(&lock->dep_map, 0, 1, _RET_IP_);
- + return ret;
- +}
- +EXPORT_SYMBOL(rt_spin_trylock__no_mg);
- +
- +int __lockfunc rt_spin_trylock(spinlock_t *lock)
- +{
- + int ret;
- +
- + migrate_disable();
- + ret = rt_mutex_trylock(&lock->lock);
- + if (ret)
- + spin_acquire(&lock->dep_map, 0, 1, _RET_IP_);
- + else
- + migrate_enable();
- + return ret;
- +}
- +EXPORT_SYMBOL(rt_spin_trylock);
- +
- +int __lockfunc rt_spin_trylock_bh(spinlock_t *lock)
- +{
- + int ret;
- +
- + local_bh_disable();
- + ret = rt_mutex_trylock(&lock->lock);
- + if (ret) {
- + migrate_disable();
- + spin_acquire(&lock->dep_map, 0, 1, _RET_IP_);
- + } else
- + local_bh_enable();
- + return ret;
- +}
- +EXPORT_SYMBOL(rt_spin_trylock_bh);
- +
- +int __lockfunc rt_spin_trylock_irqsave(spinlock_t *lock, unsigned long *flags)
- +{
- + int ret;
- +
- + *flags = 0;
- + ret = rt_mutex_trylock(&lock->lock);
- + if (ret) {
- + migrate_disable();
- + spin_acquire(&lock->dep_map, 0, 1, _RET_IP_);
- + }
- + return ret;
- +}
- +EXPORT_SYMBOL(rt_spin_trylock_irqsave);
- +
- +int atomic_dec_and_spin_lock(atomic_t *atomic, spinlock_t *lock)
- +{
- + /* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */
- + if (atomic_add_unless(atomic, -1, 1))
- + return 0;
- + rt_spin_lock(lock);
- + if (atomic_dec_and_test(atomic))
- + return 1;
- + rt_spin_unlock(lock);
- + return 0;
- +}
- +EXPORT_SYMBOL(atomic_dec_and_spin_lock);
- +
- + void
- +__rt_spin_lock_init(spinlock_t *lock, char *name, struct lock_class_key *key)
- +{
- +#ifdef CONFIG_DEBUG_LOCK_ALLOC
- + /*
- + * Make sure we are not reinitializing a held lock:
- + */
- + debug_check_no_locks_freed((void *)lock, sizeof(*lock));
- + lockdep_init_map(&lock->dep_map, name, key, 0);
- +#endif
- +}
- +EXPORT_SYMBOL(__rt_spin_lock_init);
- +
- +#endif /* PREEMPT_RT_FULL */
- +
- +#ifdef CONFIG_PREEMPT_RT_FULL
- + static inline int __sched
- +__mutex_lock_check_stamp(struct rt_mutex *lock, struct ww_acquire_ctx *ctx)
- +{
- + struct ww_mutex *ww = container_of(lock, struct ww_mutex, base.lock);
- + struct ww_acquire_ctx *hold_ctx = ACCESS_ONCE(ww->ctx);
- +
- + if (!hold_ctx)
- + return 0;
- +
- + if (unlikely(ctx == hold_ctx))
- + return -EALREADY;
- +
- + if (ctx->stamp - hold_ctx->stamp <= LONG_MAX &&
- + (ctx->stamp != hold_ctx->stamp || ctx > hold_ctx)) {
- +#ifdef CONFIG_DEBUG_MUTEXES
- + DEBUG_LOCKS_WARN_ON(ctx->contending_lock);
- + ctx->contending_lock = ww;
- +#endif
- + return -EDEADLK;
- + }
- +
- + return 0;
- +}
- +#else
- + static inline int __sched
- +__mutex_lock_check_stamp(struct rt_mutex *lock, struct ww_acquire_ctx *ctx)
- +{
- + BUG();
- + return 0;
- +}
- +
- +#endif
- +
- +static inline int
- +try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
- + struct rt_mutex_waiter *waiter)
- +{
- + return __try_to_take_rt_mutex(lock, task, waiter, STEAL_NORMAL);
- +}
- +
- /*
- * Task blocks on lock.
- *
- * Prepare waiter and propagate pi chain
- *
- - * This must be called with lock->wait_lock held.
- + * This must be called with lock->wait_lock held and interrupts disabled
- */
- static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
- struct rt_mutex_waiter *waiter,
- @@ -894,7 +1367,6 @@
- struct rt_mutex_waiter *top_waiter = waiter;
- struct rt_mutex *next_lock;
- int chain_walk = 0, res;
- - unsigned long flags;
-
- /*
- * Early deadlock detection. We really don't want the task to
- @@ -908,7 +1380,24 @@
- if (owner == task)
- return -EDEADLK;
-
- - raw_spin_lock_irqsave(&task->pi_lock, flags);
- + raw_spin_lock(&task->pi_lock);
- +
- + /*
- + * In the case of futex requeue PI, this will be a proxy
- + * lock. The task will wake unaware that it is enqueueed on
- + * this lock. Avoid blocking on two locks and corrupting
- + * pi_blocked_on via the PI_WAKEUP_INPROGRESS
- + * flag. futex_wait_requeue_pi() sets this when it wakes up
- + * before requeue (due to a signal or timeout). Do not enqueue
- + * the task if PI_WAKEUP_INPROGRESS is set.
- + */
- + if (task != current && task->pi_blocked_on == PI_WAKEUP_INPROGRESS) {
- + raw_spin_unlock(&task->pi_lock);
- + return -EAGAIN;
- + }
- +
- + BUG_ON(rt_mutex_real_waiter(task->pi_blocked_on));
- +
- __rt_mutex_adjust_prio(task);
- waiter->task = task;
- waiter->lock = lock;
- @@ -921,18 +1410,18 @@
-
- task->pi_blocked_on = waiter;
-
- - raw_spin_unlock_irqrestore(&task->pi_lock, flags);
- + raw_spin_unlock(&task->pi_lock);
-
- if (!owner)
- return 0;
-
- - raw_spin_lock_irqsave(&owner->pi_lock, flags);
- + raw_spin_lock(&owner->pi_lock);
- if (waiter == rt_mutex_top_waiter(lock)) {
- rt_mutex_dequeue_pi(owner, top_waiter);
- rt_mutex_enqueue_pi(owner, waiter);
-
- __rt_mutex_adjust_prio(owner);
- - if (owner->pi_blocked_on)
- + if (rt_mutex_real_waiter(owner->pi_blocked_on))
- chain_walk = 1;
- } else if (rt_mutex_cond_detect_deadlock(waiter, chwalk)) {
- chain_walk = 1;
- @@ -941,7 +1430,7 @@
- /* Store the lock on which owner is blocked or NULL */
- next_lock = task_blocked_on_lock(owner);
-
- - raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
- + raw_spin_unlock(&owner->pi_lock);
- /*
- * Even if full deadlock detection is on, if the owner is not
- * blocked itself, we can avoid finding this out in the chain
- @@ -957,12 +1446,12 @@
- */
- get_task_struct(owner);
-
- - raw_spin_unlock(&lock->wait_lock);
- + raw_spin_unlock_irq(&lock->wait_lock);
-
- res = rt_mutex_adjust_prio_chain(owner, chwalk, lock,
- next_lock, waiter, task);
-
- - raw_spin_lock(&lock->wait_lock);
- + raw_spin_lock_irq(&lock->wait_lock);
-
- return res;
- }
- @@ -971,15 +1460,15 @@
- * Remove the top waiter from the current tasks pi waiter tree and
- * queue it up.
- *
- - * Called with lock->wait_lock held.
- + * Called with lock->wait_lock held and interrupts disabled.
- */
- static void mark_wakeup_next_waiter(struct wake_q_head *wake_q,
- + struct wake_q_head *wake_sleeper_q,
- struct rt_mutex *lock)
- {
- struct rt_mutex_waiter *waiter;
- - unsigned long flags;
-
- - raw_spin_lock_irqsave(¤t->pi_lock, flags);
- + raw_spin_lock(¤t->pi_lock);
-
- waiter = rt_mutex_top_waiter(lock);
-
- @@ -1001,15 +1490,18 @@
- */
- lock->owner = (void *) RT_MUTEX_HAS_WAITERS;
-
- - raw_spin_unlock_irqrestore(¤t->pi_lock, flags);
- + raw_spin_unlock(¤t->pi_lock);
-
- - wake_q_add(wake_q, waiter->task);
- + if (waiter->savestate)
- + wake_q_add(wake_sleeper_q, waiter->task);
- + else
- + wake_q_add(wake_q, waiter->task);
- }
-
- /*
- * Remove a waiter from a lock and give up
- *
- - * Must be called with lock->wait_lock held and
- + * Must be called with lock->wait_lock held and interrupts disabled. I must
- * have just failed to try_to_take_rt_mutex().
- */
- static void remove_waiter(struct rt_mutex *lock,
- @@ -1017,13 +1509,12 @@
- {
- bool is_top_waiter = (waiter == rt_mutex_top_waiter(lock));
- struct task_struct *owner = rt_mutex_owner(lock);
- - struct rt_mutex *next_lock;
- - unsigned long flags;
- + struct rt_mutex *next_lock = NULL;
-
- - raw_spin_lock_irqsave(¤t->pi_lock, flags);
- + raw_spin_lock(¤t->pi_lock);
- rt_mutex_dequeue(lock, waiter);
- current->pi_blocked_on = NULL;
- - raw_spin_unlock_irqrestore(¤t->pi_lock, flags);
- + raw_spin_unlock(¤t->pi_lock);
-
- /*
- * Only update priority if the waiter was the highest priority
- @@ -1032,7 +1523,7 @@
- if (!owner || !is_top_waiter)
- return;
-
- - raw_spin_lock_irqsave(&owner->pi_lock, flags);
- + raw_spin_lock(&owner->pi_lock);
-
- rt_mutex_dequeue_pi(owner, waiter);
-
- @@ -1042,9 +1533,10 @@
- __rt_mutex_adjust_prio(owner);
-
- /* Store the lock on which owner is blocked or NULL */
- - next_lock = task_blocked_on_lock(owner);
- + if (rt_mutex_real_waiter(owner->pi_blocked_on))
- + next_lock = task_blocked_on_lock(owner);
-
- - raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
- + raw_spin_unlock(&owner->pi_lock);
-
- /*
- * Don't walk the chain, if the owner task is not blocked
- @@ -1056,12 +1548,12 @@
- /* gets dropped in rt_mutex_adjust_prio_chain()! */
- get_task_struct(owner);
-
- - raw_spin_unlock(&lock->wait_lock);
- + raw_spin_unlock_irq(&lock->wait_lock);
-
- rt_mutex_adjust_prio_chain(owner, RT_MUTEX_MIN_CHAINWALK, lock,
- next_lock, NULL, current);
-
- - raw_spin_lock(&lock->wait_lock);
- + raw_spin_lock_irq(&lock->wait_lock);
- }
-
- /*
- @@ -1078,17 +1570,17 @@
- raw_spin_lock_irqsave(&task->pi_lock, flags);
-
- waiter = task->pi_blocked_on;
- - if (!waiter || (waiter->prio == task->prio &&
- + if (!rt_mutex_real_waiter(waiter) || (waiter->prio == task->prio &&
- !dl_prio(task->prio))) {
- raw_spin_unlock_irqrestore(&task->pi_lock, flags);
- return;
- }
- next_lock = waiter->lock;
- - raw_spin_unlock_irqrestore(&task->pi_lock, flags);
-
- /* gets dropped in rt_mutex_adjust_prio_chain()! */
- get_task_struct(task);
-
- + raw_spin_unlock_irqrestore(&task->pi_lock, flags);
- rt_mutex_adjust_prio_chain(task, RT_MUTEX_MIN_CHAINWALK, NULL,
- next_lock, NULL, task);
- }
- @@ -1097,16 +1589,17 @@
- * __rt_mutex_slowlock() - Perform the wait-wake-try-to-take loop
- * @lock: the rt_mutex to take
- * @state: the state the task should block in (TASK_INTERRUPTIBLE
- - * or TASK_UNINTERRUPTIBLE)
- + * or TASK_UNINTERRUPTIBLE)
- * @timeout: the pre-initialized and started timer, or NULL for none
- * @waiter: the pre-initialized rt_mutex_waiter
- *
- - * lock->wait_lock must be held by the caller.
- + * Must be called with lock->wait_lock held and interrupts disabled
- */
- static int __sched
- __rt_mutex_slowlock(struct rt_mutex *lock, int state,
- struct hrtimer_sleeper *timeout,
- - struct rt_mutex_waiter *waiter)
- + struct rt_mutex_waiter *waiter,
- + struct ww_acquire_ctx *ww_ctx)
- {
- int ret = 0;
-
- @@ -1129,13 +1622,19 @@
- break;
- }
-
- - raw_spin_unlock(&lock->wait_lock);
- + if (ww_ctx && ww_ctx->acquired > 0) {
- + ret = __mutex_lock_check_stamp(lock, ww_ctx);
- + if (ret)
- + break;
- + }
- +
- + raw_spin_unlock_irq(&lock->wait_lock);
-
- debug_rt_mutex_print_deadlock(waiter);
-
- schedule();
-
- - raw_spin_lock(&lock->wait_lock);
- + raw_spin_lock_irq(&lock->wait_lock);
- set_current_state(state);
- }
-
- @@ -1163,26 +1662,112 @@
- }
- }
-
- +static __always_inline void ww_mutex_lock_acquired(struct ww_mutex *ww,
- + struct ww_acquire_ctx *ww_ctx)
- +{
- +#ifdef CONFIG_DEBUG_MUTEXES
- + /*
- + * If this WARN_ON triggers, you used ww_mutex_lock to acquire,
- + * but released with a normal mutex_unlock in this call.
- + *
- + * This should never happen, always use ww_mutex_unlock.
- + */
- + DEBUG_LOCKS_WARN_ON(ww->ctx);
- +
- + /*
- + * Not quite done after calling ww_acquire_done() ?
- + */
- + DEBUG_LOCKS_WARN_ON(ww_ctx->done_acquire);
- +
- + if (ww_ctx->contending_lock) {
- + /*
- + * After -EDEADLK you tried to
- + * acquire a different ww_mutex? Bad!
- + */
- + DEBUG_LOCKS_WARN_ON(ww_ctx->contending_lock != ww);
- +
- + /*
- + * You called ww_mutex_lock after receiving -EDEADLK,
- + * but 'forgot' to unlock everything else first?
- + */
- + DEBUG_LOCKS_WARN_ON(ww_ctx->acquired > 0);
- + ww_ctx->contending_lock = NULL;
- + }
- +
- + /*
- + * Naughty, using a different class will lead to undefined behavior!
- + */
- + DEBUG_LOCKS_WARN_ON(ww_ctx->ww_class != ww->ww_class);
- +#endif
- + ww_ctx->acquired++;
- +}
- +
- +#ifdef CONFIG_PREEMPT_RT_FULL
- +static void ww_mutex_account_lock(struct rt_mutex *lock,
- + struct ww_acquire_ctx *ww_ctx)
- +{
- + struct ww_mutex *ww = container_of(lock, struct ww_mutex, base.lock);
- + struct rt_mutex_waiter *waiter, *n;
- +
- + /*
- + * This branch gets optimized out for the common case,
- + * and is only important for ww_mutex_lock.
- + */
- + ww_mutex_lock_acquired(ww, ww_ctx);
- + ww->ctx = ww_ctx;
- +
- + /*
- + * Give any possible sleeping processes the chance to wake up,
- + * so they can recheck if they have to back off.
- + */
- + rbtree_postorder_for_each_entry_safe(waiter, n, &lock->waiters,
- + tree_entry) {
- + /* XXX debug rt mutex waiter wakeup */
- +
- + BUG_ON(waiter->lock != lock);
- + rt_mutex_wake_waiter(waiter);
- + }
- +}
- +
- +#else
- +
- +static void ww_mutex_account_lock(struct rt_mutex *lock,
- + struct ww_acquire_ctx *ww_ctx)
- +{
- + BUG();
- +}
- +#endif
- +
- /*
- * Slow path lock function:
- */
- static int __sched
- rt_mutex_slowlock(struct rt_mutex *lock, int state,
- struct hrtimer_sleeper *timeout,
- - enum rtmutex_chainwalk chwalk)
- + enum rtmutex_chainwalk chwalk,
- + struct ww_acquire_ctx *ww_ctx)
- {
- struct rt_mutex_waiter waiter;
- + unsigned long flags;
- int ret = 0;
-
- - debug_rt_mutex_init_waiter(&waiter);
- - RB_CLEAR_NODE(&waiter.pi_tree_entry);
- - RB_CLEAR_NODE(&waiter.tree_entry);
- + rt_mutex_init_waiter(&waiter, false);
-
- - raw_spin_lock(&lock->wait_lock);
- + /*
- + * Technically we could use raw_spin_[un]lock_irq() here, but this can
- + * be called in early boot if the cmpxchg() fast path is disabled
- + * (debug, no architecture support). In this case we will acquire the
- + * rtmutex with lock->wait_lock held. But we cannot unconditionally
- + * enable interrupts in that early boot case. So we need to use the
- + * irqsave/restore variants.
- + */
- + raw_spin_lock_irqsave(&lock->wait_lock, flags);
-
- /* Try to acquire the lock again: */
- if (try_to_take_rt_mutex(lock, current, NULL)) {
- - raw_spin_unlock(&lock->wait_lock);
- + if (ww_ctx)
- + ww_mutex_account_lock(lock, ww_ctx);
- + raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
- return 0;
- }
-
- @@ -1196,13 +1781,23 @@
-
- if (likely(!ret))
- /* sleep on the mutex */
- - ret = __rt_mutex_slowlock(lock, state, timeout, &waiter);
- + ret = __rt_mutex_slowlock(lock, state, timeout, &waiter,
- + ww_ctx);
- + else if (ww_ctx) {
- + /* ww_mutex received EDEADLK, let it become EALREADY */
- + ret = __mutex_lock_check_stamp(lock, ww_ctx);
- + BUG_ON(!ret);
- + }
-
- if (unlikely(ret)) {
- __set_current_state(TASK_RUNNING);
- if (rt_mutex_has_waiters(lock))
- remove_waiter(lock, &waiter);
- - rt_mutex_handle_deadlock(ret, chwalk, &waiter);
- + /* ww_mutex want to report EDEADLK/EALREADY, let them */
- + if (!ww_ctx)
- + rt_mutex_handle_deadlock(ret, chwalk, &waiter);
- + } else if (ww_ctx) {
- + ww_mutex_account_lock(lock, ww_ctx);
- }
-
- /*
- @@ -1211,7 +1806,7 @@
- */
- fixup_rt_mutex_waiters(lock);
-
- - raw_spin_unlock(&lock->wait_lock);
- + raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
-
- /* Remove pending timer: */
- if (unlikely(timeout))
- @@ -1227,6 +1822,7 @@
- */
- static inline int rt_mutex_slowtrylock(struct rt_mutex *lock)
- {
- + unsigned long flags;
- int ret;
-
- /*
- @@ -1238,10 +1834,10 @@
- return 0;
-
- /*
- - * The mutex has currently no owner. Lock the wait lock and
- - * try to acquire the lock.
- + * The mutex has currently no owner. Lock the wait lock and try to
- + * acquire the lock. We use irqsave here to support early boot calls.
- */
- - raw_spin_lock(&lock->wait_lock);
- + raw_spin_lock_irqsave(&lock->wait_lock, flags);
-
- ret = try_to_take_rt_mutex(lock, current, NULL);
-
- @@ -1251,7 +1847,7 @@
- */
- fixup_rt_mutex_waiters(lock);
-
- - raw_spin_unlock(&lock->wait_lock);
- + raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
-
- return ret;
- }
- @@ -1261,9 +1857,13 @@
- * Return whether the current task needs to undo a potential priority boosting.
- */
- static bool __sched rt_mutex_slowunlock(struct rt_mutex *lock,
- - struct wake_q_head *wake_q)
- + struct wake_q_head *wake_q,
- + struct wake_q_head *wake_sleeper_q)
- {
- - raw_spin_lock(&lock->wait_lock);
- + unsigned long flags;
- +
- + /* irqsave required to support early boot calls */
- + raw_spin_lock_irqsave(&lock->wait_lock, flags);
-
- debug_rt_mutex_unlock(lock);
-
- @@ -1302,10 +1902,10 @@
- */
- while (!rt_mutex_has_waiters(lock)) {
- /* Drops lock->wait_lock ! */
- - if (unlock_rt_mutex_safe(lock) == true)
- + if (unlock_rt_mutex_safe(lock, flags) == true)
- return false;
- /* Relock the rtmutex and try again */
- - raw_spin_lock(&lock->wait_lock);
- + raw_spin_lock_irqsave(&lock->wait_lock, flags);
- }
-
- /*
- @@ -1314,9 +1914,9 @@
- *
- * Queue the next waiter for wakeup once we release the wait_lock.
- */
- - mark_wakeup_next_waiter(wake_q, lock);
- + mark_wakeup_next_waiter(wake_q, wake_sleeper_q, lock);
-
- - raw_spin_unlock(&lock->wait_lock);
- + raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
-
- /* check PI boosting */
- return true;
- @@ -1330,31 +1930,36 @@
- */
- static inline int
- rt_mutex_fastlock(struct rt_mutex *lock, int state,
- + struct ww_acquire_ctx *ww_ctx,
- int (*slowfn)(struct rt_mutex *lock, int state,
- struct hrtimer_sleeper *timeout,
- - enum rtmutex_chainwalk chwalk))
- + enum rtmutex_chainwalk chwalk,
- + struct ww_acquire_ctx *ww_ctx))
- {
- if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) {
- rt_mutex_deadlock_account_lock(lock, current);
- return 0;
- } else
- - return slowfn(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK);
- + return slowfn(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK,
- + ww_ctx);
- }
-
- static inline int
- rt_mutex_timed_fastlock(struct rt_mutex *lock, int state,
- struct hrtimer_sleeper *timeout,
- enum rtmutex_chainwalk chwalk,
- + struct ww_acquire_ctx *ww_ctx,
- int (*slowfn)(struct rt_mutex *lock, int state,
- struct hrtimer_sleeper *timeout,
- - enum rtmutex_chainwalk chwalk))
- + enum rtmutex_chainwalk chwalk,
- + struct ww_acquire_ctx *ww_ctx))
- {
- if (chwalk == RT_MUTEX_MIN_CHAINWALK &&
- likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) {
- rt_mutex_deadlock_account_lock(lock, current);
- return 0;
- } else
- - return slowfn(lock, state, timeout, chwalk);
- + return slowfn(lock, state, timeout, chwalk, ww_ctx);
- }
-
- static inline int
- @@ -1371,17 +1976,20 @@
- static inline void
- rt_mutex_fastunlock(struct rt_mutex *lock,
- bool (*slowfn)(struct rt_mutex *lock,
- - struct wake_q_head *wqh))
- + struct wake_q_head *wqh,
- + struct wake_q_head *wq_sleeper))
- {
- WAKE_Q(wake_q);
- + WAKE_Q(wake_sleeper_q);
-
- if (likely(rt_mutex_cmpxchg_release(lock, current, NULL))) {
- rt_mutex_deadlock_account_unlock(current);
-
- } else {
- - bool deboost = slowfn(lock, &wake_q);
- + bool deboost = slowfn(lock, &wake_q, &wake_sleeper_q);
-
- wake_up_q(&wake_q);
- + wake_up_q_sleeper(&wake_sleeper_q);
-
- /* Undo pi boosting if necessary: */
- if (deboost)
- @@ -1398,7 +2006,7 @@
- {
- might_sleep();
-
- - rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, rt_mutex_slowlock);
- + rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, NULL, rt_mutex_slowlock);
- }
- EXPORT_SYMBOL_GPL(rt_mutex_lock);
-
- @@ -1415,7 +2023,7 @@
- {
- might_sleep();
-
- - return rt_mutex_fastlock(lock, TASK_INTERRUPTIBLE, rt_mutex_slowlock);
- + return rt_mutex_fastlock(lock, TASK_INTERRUPTIBLE, NULL, rt_mutex_slowlock);
- }
- EXPORT_SYMBOL_GPL(rt_mutex_lock_interruptible);
-
- @@ -1428,11 +2036,30 @@
- might_sleep();
-
- return rt_mutex_timed_fastlock(lock, TASK_INTERRUPTIBLE, timeout,
- - RT_MUTEX_FULL_CHAINWALK,
- + RT_MUTEX_FULL_CHAINWALK, NULL,
- rt_mutex_slowlock);
- }
-
- /**
- + * rt_mutex_lock_killable - lock a rt_mutex killable
- + *
- + * @lock: the rt_mutex to be locked
- + * @detect_deadlock: deadlock detection on/off
- + *
- + * Returns:
- + * 0 on success
- + * -EINTR when interrupted by a signal
- + * -EDEADLK when the lock would deadlock (when deadlock detection is on)
- + */
- +int __sched rt_mutex_lock_killable(struct rt_mutex *lock)
- +{
- + might_sleep();
- +
- + return rt_mutex_fastlock(lock, TASK_KILLABLE, NULL, rt_mutex_slowlock);
- +}
- +EXPORT_SYMBOL_GPL(rt_mutex_lock_killable);
- +
- +/**
- * rt_mutex_timed_lock - lock a rt_mutex interruptible
- * the timeout structure is provided
- * by the caller
- @@ -1452,6 +2079,7 @@
-
- return rt_mutex_timed_fastlock(lock, TASK_INTERRUPTIBLE, timeout,
- RT_MUTEX_MIN_CHAINWALK,
- + NULL,
- rt_mutex_slowlock);
- }
- EXPORT_SYMBOL_GPL(rt_mutex_timed_lock);
- @@ -1469,7 +2097,11 @@
- */
- int __sched rt_mutex_trylock(struct rt_mutex *lock)
- {
- +#ifdef CONFIG_PREEMPT_RT_FULL
- + if (WARN_ON_ONCE(in_irq() || in_nmi()))
- +#else
- if (WARN_ON(in_irq() || in_nmi() || in_serving_softirq()))
- +#endif
- return 0;
-
- return rt_mutex_fasttrylock(lock, rt_mutex_slowtrylock);
- @@ -1495,13 +2127,14 @@
- * required or not.
- */
- bool __sched rt_mutex_futex_unlock(struct rt_mutex *lock,
- - struct wake_q_head *wqh)
- + struct wake_q_head *wqh,
- + struct wake_q_head *wq_sleeper)
- {
- if (likely(rt_mutex_cmpxchg_release(lock, current, NULL))) {
- rt_mutex_deadlock_account_unlock(current);
- return false;
- }
- - return rt_mutex_slowunlock(lock, wqh);
- + return rt_mutex_slowunlock(lock, wqh, wq_sleeper);
- }
-
- /**
- @@ -1534,13 +2167,12 @@
- void __rt_mutex_init(struct rt_mutex *lock, const char *name)
- {
- lock->owner = NULL;
- - raw_spin_lock_init(&lock->wait_lock);
- lock->waiters = RB_ROOT;
- lock->waiters_leftmost = NULL;
-
- debug_rt_mutex_init(lock, name);
- }
- -EXPORT_SYMBOL_GPL(__rt_mutex_init);
- +EXPORT_SYMBOL(__rt_mutex_init);
-
- /**
- * rt_mutex_init_proxy_locked - initialize and lock a rt_mutex on behalf of a
- @@ -1555,7 +2187,7 @@
- void rt_mutex_init_proxy_locked(struct rt_mutex *lock,
- struct task_struct *proxy_owner)
- {
- - __rt_mutex_init(lock, NULL);
- + rt_mutex_init(lock);
- debug_rt_mutex_proxy_lock(lock, proxy_owner);
- rt_mutex_set_owner(lock, proxy_owner);
- rt_mutex_deadlock_account_lock(lock, proxy_owner);
- @@ -1596,13 +2228,42 @@
- {
- int ret;
-
- - raw_spin_lock(&lock->wait_lock);
- + raw_spin_lock_irq(&lock->wait_lock);
-
- if (try_to_take_rt_mutex(lock, task, NULL)) {
- - raw_spin_unlock(&lock->wait_lock);
- + raw_spin_unlock_irq(&lock->wait_lock);
- return 1;
- }
-
- +#ifdef CONFIG_PREEMPT_RT_FULL
- + /*
- + * In PREEMPT_RT there's an added race.
- + * If the task, that we are about to requeue, times out,
- + * it can set the PI_WAKEUP_INPROGRESS. This tells the requeue
- + * to skip this task. But right after the task sets
- + * its pi_blocked_on to PI_WAKEUP_INPROGRESS it can then
- + * block on the spin_lock(&hb->lock), which in RT is an rtmutex.
- + * This will replace the PI_WAKEUP_INPROGRESS with the actual
- + * lock that it blocks on. We *must not* place this task
- + * on this proxy lock in that case.
- + *
- + * To prevent this race, we first take the task's pi_lock
- + * and check if it has updated its pi_blocked_on. If it has,
- + * we assume that it woke up and we return -EAGAIN.
- + * Otherwise, we set the task's pi_blocked_on to
- + * PI_REQUEUE_INPROGRESS, so that if the task is waking up
- + * it will know that we are in the process of requeuing it.
- + */
- + raw_spin_lock(&task->pi_lock);
- + if (task->pi_blocked_on) {
- + raw_spin_unlock(&task->pi_lock);
- + raw_spin_unlock_irq(&lock->wait_lock);
- + return -EAGAIN;
- + }
- + task->pi_blocked_on = PI_REQUEUE_INPROGRESS;
- + raw_spin_unlock(&task->pi_lock);
- +#endif
- +
- /* We enforce deadlock detection for futexes */
- ret = task_blocks_on_rt_mutex(lock, waiter, task,
- RT_MUTEX_FULL_CHAINWALK);
- @@ -1617,10 +2278,10 @@
- ret = 0;
- }
-
- - if (unlikely(ret))
- + if (ret && rt_mutex_has_waiters(lock))
- remove_waiter(lock, waiter);
-
- - raw_spin_unlock(&lock->wait_lock);
- + raw_spin_unlock_irq(&lock->wait_lock);
-
- debug_rt_mutex_print_deadlock(waiter);
-
- @@ -1668,12 +2329,12 @@
- {
- int ret;
-
- - raw_spin_lock(&lock->wait_lock);
- + raw_spin_lock_irq(&lock->wait_lock);
-
- set_current_state(TASK_INTERRUPTIBLE);
-
- /* sleep on the mutex */
- - ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter);
- + ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter, NULL);
-
- if (unlikely(ret))
- remove_waiter(lock, waiter);
- @@ -1684,7 +2345,93 @@
- */
- fixup_rt_mutex_waiters(lock);
-
- - raw_spin_unlock(&lock->wait_lock);
- + raw_spin_unlock_irq(&lock->wait_lock);
-
- return ret;
- }
- +
- +static inline int
- +ww_mutex_deadlock_injection(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
- +{
- +#ifdef CONFIG_DEBUG_WW_MUTEX_SLOWPATH
- + unsigned tmp;
- +
- + if (ctx->deadlock_inject_countdown-- == 0) {
- + tmp = ctx->deadlock_inject_interval;
- + if (tmp > UINT_MAX/4)
- + tmp = UINT_MAX;
- + else
- + tmp = tmp*2 + tmp + tmp/2;
- +
- + ctx->deadlock_inject_interval = tmp;
- + ctx->deadlock_inject_countdown = tmp;
- + ctx->contending_lock = lock;
- +
- + ww_mutex_unlock(lock);
- +
- + return -EDEADLK;
- + }
- +#endif
- +
- + return 0;
- +}
- +
- +#ifdef CONFIG_PREEMPT_RT_FULL
- +int __sched
- +__ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ww_ctx)
- +{
- + int ret;
- +
- + might_sleep();
- +
- + mutex_acquire_nest(&lock->base.dep_map, 0, 0, &ww_ctx->dep_map, _RET_IP_);
- + ret = rt_mutex_slowlock(&lock->base.lock, TASK_INTERRUPTIBLE, NULL, 0, ww_ctx);
- + if (ret)
- + mutex_release(&lock->base.dep_map, 1, _RET_IP_);
- + else if (!ret && ww_ctx->acquired > 1)
- + return ww_mutex_deadlock_injection(lock, ww_ctx);
- +
- + return ret;
- +}
- +EXPORT_SYMBOL_GPL(__ww_mutex_lock_interruptible);
- +
- +int __sched
- +__ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ww_ctx)
- +{
- + int ret;
- +
- + might_sleep();
- +
- + mutex_acquire_nest(&lock->base.dep_map, 0, 0, &ww_ctx->dep_map, _RET_IP_);
- + ret = rt_mutex_slowlock(&lock->base.lock, TASK_UNINTERRUPTIBLE, NULL, 0, ww_ctx);
- + if (ret)
- + mutex_release(&lock->base.dep_map, 1, _RET_IP_);
- + else if (!ret && ww_ctx->acquired > 1)
- + return ww_mutex_deadlock_injection(lock, ww_ctx);
- +
- + return ret;
- +}
- +EXPORT_SYMBOL_GPL(__ww_mutex_lock);
- +
- +void __sched ww_mutex_unlock(struct ww_mutex *lock)
- +{
- + int nest = !!lock->ctx;
- +
- + /*
- + * The unlocking fastpath is the 0->1 transition from 'locked'
- + * into 'unlocked' state:
- + */
- + if (nest) {
- +#ifdef CONFIG_DEBUG_MUTEXES
- + DEBUG_LOCKS_WARN_ON(!lock->ctx->acquired);
- +#endif
- + if (lock->ctx->acquired > 0)
- + lock->ctx->acquired--;
- + lock->ctx = NULL;
- + }
- +
- + mutex_release(&lock->base.dep_map, nest, _RET_IP_);
- + rt_mutex_unlock(&lock->base.lock);
- +}
- +EXPORT_SYMBOL(ww_mutex_unlock);
- +#endif
- diff -Nur linux-4.4.28.orig/kernel/locking/rtmutex_common.h linux-4.4.28/kernel/locking/rtmutex_common.h
- --- linux-4.4.28.orig/kernel/locking/rtmutex_common.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/locking/rtmutex_common.h 2016-11-01 21:26:58.772342023 +0100
- @@ -27,6 +27,7 @@
- struct rb_node pi_tree_entry;
- struct task_struct *task;
- struct rt_mutex *lock;
- + bool savestate;
- #ifdef CONFIG_DEBUG_RT_MUTEXES
- unsigned long ip;
- struct pid *deadlock_task_pid;
- @@ -97,6 +98,9 @@
- /*
- * PI-futex support (proxy locking functions, etc.):
- */
- +#define PI_WAKEUP_INPROGRESS ((struct rt_mutex_waiter *) 1)
- +#define PI_REQUEUE_INPROGRESS ((struct rt_mutex_waiter *) 2)
- +
- extern struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock);
- extern void rt_mutex_init_proxy_locked(struct rt_mutex *lock,
- struct task_struct *proxy_owner);
- @@ -110,7 +114,8 @@
- struct rt_mutex_waiter *waiter);
- extern int rt_mutex_timed_futex_lock(struct rt_mutex *l, struct hrtimer_sleeper *to);
- extern bool rt_mutex_futex_unlock(struct rt_mutex *lock,
- - struct wake_q_head *wqh);
- + struct wake_q_head *wqh,
- + struct wake_q_head *wq_sleeper);
- extern void rt_mutex_adjust_prio(struct task_struct *task);
-
- #ifdef CONFIG_DEBUG_RT_MUTEXES
- @@ -119,4 +124,14 @@
- # include "rtmutex.h"
- #endif
-
- +static inline void
- +rt_mutex_init_waiter(struct rt_mutex_waiter *waiter, bool savestate)
- +{
- + debug_rt_mutex_init_waiter(waiter);
- + waiter->task = NULL;
- + waiter->savestate = savestate;
- + RB_CLEAR_NODE(&waiter->pi_tree_entry);
- + RB_CLEAR_NODE(&waiter->tree_entry);
- +}
- +
- #endif
- diff -Nur linux-4.4.28.orig/kernel/locking/spinlock.c linux-4.4.28/kernel/locking/spinlock.c
- --- linux-4.4.28.orig/kernel/locking/spinlock.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/locking/spinlock.c 2016-11-01 21:26:58.772342023 +0100
- @@ -124,8 +124,11 @@
- * __[spin|read|write]_lock_bh()
- */
- BUILD_LOCK_OPS(spin, raw_spinlock);
- +
- +#ifndef CONFIG_PREEMPT_RT_FULL
- BUILD_LOCK_OPS(read, rwlock);
- BUILD_LOCK_OPS(write, rwlock);
- +#endif
-
- #endif
-
- @@ -209,6 +212,8 @@
- EXPORT_SYMBOL(_raw_spin_unlock_bh);
- #endif
-
- +#ifndef CONFIG_PREEMPT_RT_FULL
- +
- #ifndef CONFIG_INLINE_READ_TRYLOCK
- int __lockfunc _raw_read_trylock(rwlock_t *lock)
- {
- @@ -353,6 +358,8 @@
- EXPORT_SYMBOL(_raw_write_unlock_bh);
- #endif
-
- +#endif /* !PREEMPT_RT_FULL */
- +
- #ifdef CONFIG_DEBUG_LOCK_ALLOC
-
- void __lockfunc _raw_spin_lock_nested(raw_spinlock_t *lock, int subclass)
- diff -Nur linux-4.4.28.orig/kernel/locking/spinlock_debug.c linux-4.4.28/kernel/locking/spinlock_debug.c
- --- linux-4.4.28.orig/kernel/locking/spinlock_debug.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/locking/spinlock_debug.c 2016-11-01 21:26:58.772342023 +0100
- @@ -31,6 +31,7 @@
-
- EXPORT_SYMBOL(__raw_spin_lock_init);
-
- +#ifndef CONFIG_PREEMPT_RT_FULL
- void __rwlock_init(rwlock_t *lock, const char *name,
- struct lock_class_key *key)
- {
- @@ -48,6 +49,7 @@
- }
-
- EXPORT_SYMBOL(__rwlock_init);
- +#endif
-
- static void spin_dump(raw_spinlock_t *lock, const char *msg)
- {
- @@ -159,6 +161,7 @@
- arch_spin_unlock(&lock->raw_lock);
- }
-
- +#ifndef CONFIG_PREEMPT_RT_FULL
- static void rwlock_bug(rwlock_t *lock, const char *msg)
- {
- if (!debug_locks_off())
- @@ -300,3 +303,5 @@
- debug_write_unlock(lock);
- arch_write_unlock(&lock->raw_lock);
- }
- +
- +#endif
- diff -Nur linux-4.4.28.orig/kernel/panic.c linux-4.4.28/kernel/panic.c
- --- linux-4.4.28.orig/kernel/panic.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/panic.c 2016-11-01 21:26:58.772342023 +0100
- @@ -61,6 +61,37 @@
- cpu_relax();
- }
-
- +/*
- + * Stop ourselves in NMI context if another CPU has already panicked. Arch code
- + * may override this to prepare for crash dumping, e.g. save regs info.
- + */
- +void __weak nmi_panic_self_stop(struct pt_regs *regs)
- +{
- + panic_smp_self_stop();
- +}
- +
- +atomic_t panic_cpu = ATOMIC_INIT(PANIC_CPU_INVALID);
- +
- +/*
- + * A variant of panic() called from NMI context. We return if we've already
- + * panicked on this CPU. If another CPU already panicked, loop in
- + * nmi_panic_self_stop() which can provide architecture dependent code such
- + * as saving register state for crash dump.
- + */
- +void nmi_panic(struct pt_regs *regs, const char *msg)
- +{
- + int old_cpu, cpu;
- +
- + cpu = raw_smp_processor_id();
- + old_cpu = atomic_cmpxchg(&panic_cpu, PANIC_CPU_INVALID, cpu);
- +
- + if (old_cpu == PANIC_CPU_INVALID)
- + panic("%s", msg);
- + else if (old_cpu != cpu)
- + nmi_panic_self_stop(regs);
- +}
- +EXPORT_SYMBOL(nmi_panic);
- +
- /**
- * panic - halt the system
- * @fmt: The text string to print
- @@ -71,17 +102,17 @@
- */
- void panic(const char *fmt, ...)
- {
- - static DEFINE_SPINLOCK(panic_lock);
- static char buf[1024];
- va_list args;
- long i, i_next = 0;
- int state = 0;
- + int old_cpu, this_cpu;
-
- /*
- * Disable local interrupts. This will prevent panic_smp_self_stop
- * from deadlocking the first cpu that invokes the panic, since
- * there is nothing to prevent an interrupt handler (that runs
- - * after the panic_lock is acquired) from invoking panic again.
- + * after setting panic_cpu) from invoking panic() again.
- */
- local_irq_disable();
-
- @@ -94,8 +125,16 @@
- * multiple parallel invocations of panic, all other CPUs either
- * stop themself or will wait until they are stopped by the 1st CPU
- * with smp_send_stop().
- + *
- + * `old_cpu == PANIC_CPU_INVALID' means this is the 1st CPU which
- + * comes here, so go ahead.
- + * `old_cpu == this_cpu' means we came from nmi_panic() which sets
- + * panic_cpu to this CPU. In this case, this is also the 1st CPU.
- */
- - if (!spin_trylock(&panic_lock))
- + this_cpu = raw_smp_processor_id();
- + old_cpu = atomic_cmpxchg(&panic_cpu, PANIC_CPU_INVALID, this_cpu);
- +
- + if (old_cpu != PANIC_CPU_INVALID && old_cpu != this_cpu)
- panic_smp_self_stop();
-
- console_verbose();
- @@ -400,9 +439,11 @@
-
- static int init_oops_id(void)
- {
- +#ifndef CONFIG_PREEMPT_RT_FULL
- if (!oops_id)
- get_random_bytes(&oops_id, sizeof(oops_id));
- else
- +#endif
- oops_id++;
-
- return 0;
- diff -Nur linux-4.4.28.orig/kernel/power/hibernate.c linux-4.4.28/kernel/power/hibernate.c
- --- linux-4.4.28.orig/kernel/power/hibernate.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/power/hibernate.c 2016-11-01 21:26:58.772342023 +0100
- @@ -285,6 +285,8 @@
-
- local_irq_disable();
-
- + system_state = SYSTEM_SUSPEND;
- +
- error = syscore_suspend();
- if (error) {
- printk(KERN_ERR "PM: Some system devices failed to power down, "
- @@ -314,6 +316,7 @@
- syscore_resume();
-
- Enable_irqs:
- + system_state = SYSTEM_RUNNING;
- local_irq_enable();
-
- Enable_cpus:
- @@ -438,6 +441,7 @@
- goto Enable_cpus;
-
- local_irq_disable();
- + system_state = SYSTEM_SUSPEND;
-
- error = syscore_suspend();
- if (error)
- @@ -471,6 +475,7 @@
- syscore_resume();
-
- Enable_irqs:
- + system_state = SYSTEM_RUNNING;
- local_irq_enable();
-
- Enable_cpus:
- @@ -556,6 +561,7 @@
- goto Enable_cpus;
-
- local_irq_disable();
- + system_state = SYSTEM_SUSPEND;
- syscore_suspend();
- if (pm_wakeup_pending()) {
- error = -EAGAIN;
- @@ -568,6 +574,7 @@
-
- Power_up:
- syscore_resume();
- + system_state = SYSTEM_RUNNING;
- local_irq_enable();
-
- Enable_cpus:
- @@ -642,6 +649,10 @@
- cpu_relax();
- }
-
- +#ifndef CONFIG_SUSPEND
- +bool pm_in_action;
- +#endif
- +
- /**
- * hibernate - Carry out system hibernation, including saving the image.
- */
- @@ -654,6 +665,8 @@
- return -EPERM;
- }
-
- + pm_in_action = true;
- +
- lock_system_sleep();
- /* The snapshot device should not be opened while we're running */
- if (!atomic_add_unless(&snapshot_device_available, -1, 0)) {
- @@ -719,6 +732,7 @@
- atomic_inc(&snapshot_device_available);
- Unlock:
- unlock_system_sleep();
- + pm_in_action = false;
- return error;
- }
-
- diff -Nur linux-4.4.28.orig/kernel/power/suspend.c linux-4.4.28/kernel/power/suspend.c
- --- linux-4.4.28.orig/kernel/power/suspend.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/power/suspend.c 2016-11-01 21:26:58.772342023 +0100
- @@ -359,6 +359,8 @@
- arch_suspend_disable_irqs();
- BUG_ON(!irqs_disabled());
-
- + system_state = SYSTEM_SUSPEND;
- +
- error = syscore_suspend();
- if (!error) {
- *wakeup = pm_wakeup_pending();
- @@ -375,6 +377,8 @@
- syscore_resume();
- }
-
- + system_state = SYSTEM_RUNNING;
- +
- arch_suspend_enable_irqs();
- BUG_ON(irqs_disabled());
-
- @@ -518,6 +522,8 @@
- return error;
- }
-
- +bool pm_in_action;
- +
- /**
- * pm_suspend - Externally visible function for suspending the system.
- * @state: System sleep state to enter.
- @@ -532,6 +538,8 @@
- if (state <= PM_SUSPEND_ON || state >= PM_SUSPEND_MAX)
- return -EINVAL;
-
- + pm_in_action = true;
- +
- error = enter_state(state);
- if (error) {
- suspend_stats.fail++;
- @@ -539,6 +547,7 @@
- } else {
- suspend_stats.success++;
- }
- + pm_in_action = false;
- return error;
- }
- EXPORT_SYMBOL(pm_suspend);
- diff -Nur linux-4.4.28.orig/kernel/printk/printk.c linux-4.4.28/kernel/printk/printk.c
- --- linux-4.4.28.orig/kernel/printk/printk.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/printk/printk.c 2016-11-01 21:26:58.776342279 +0100
- @@ -241,6 +241,65 @@
- */
- static DEFINE_RAW_SPINLOCK(logbuf_lock);
-
- +#ifdef CONFIG_EARLY_PRINTK
- +struct console *early_console;
- +
- +static void early_vprintk(const char *fmt, va_list ap)
- +{
- + if (early_console) {
- + char buf[512];
- + int n = vscnprintf(buf, sizeof(buf), fmt, ap);
- +
- + early_console->write(early_console, buf, n);
- + }
- +}
- +
- +asmlinkage void early_printk(const char *fmt, ...)
- +{
- + va_list ap;
- +
- + va_start(ap, fmt);
- + early_vprintk(fmt, ap);
- + va_end(ap);
- +}
- +
- +/*
- + * This is independent of any log levels - a global
- + * kill switch that turns off all of printk.
- + *
- + * Used by the NMI watchdog if early-printk is enabled.
- + */
- +static bool __read_mostly printk_killswitch;
- +
- +static int __init force_early_printk_setup(char *str)
- +{
- + printk_killswitch = true;
- + return 0;
- +}
- +early_param("force_early_printk", force_early_printk_setup);
- +
- +void printk_kill(void)
- +{
- + printk_killswitch = true;
- +}
- +
- +#ifdef CONFIG_PRINTK
- +static int forced_early_printk(const char *fmt, va_list ap)
- +{
- + if (!printk_killswitch)
- + return 0;
- + early_vprintk(fmt, ap);
- + return 1;
- +}
- +#endif
- +
- +#else
- +static inline int forced_early_printk(const char *fmt, va_list ap)
- +{
- + return 0;
- +}
- +#endif
- +
- #ifdef CONFIG_PRINTK
- DECLARE_WAIT_QUEUE_HEAD(log_wait);
- /* the next printk record to read by syslog(READ) or /proc/kmsg */
- @@ -1203,6 +1262,7 @@
- {
- char *text;
- int len = 0;
- + int attempts = 0;
-
- text = kmalloc(LOG_LINE_MAX + PREFIX_MAX, GFP_KERNEL);
- if (!text)
- @@ -1214,7 +1274,14 @@
- u64 seq;
- u32 idx;
- enum log_flags prev;
- -
- + int num_msg;
- +try_again:
- + attempts++;
- + if (attempts > 10) {
- + len = -EBUSY;
- + goto out;
- + }
- + num_msg = 0;
- if (clear_seq < log_first_seq) {
- /* messages are gone, move to first available one */
- clear_seq = log_first_seq;
- @@ -1235,6 +1302,14 @@
- prev = msg->flags;
- idx = log_next(idx);
- seq++;
- + num_msg++;
- + if (num_msg > 5) {
- + num_msg = 0;
- + raw_spin_unlock_irq(&logbuf_lock);
- + raw_spin_lock_irq(&logbuf_lock);
- + if (clear_seq < log_first_seq)
- + goto try_again;
- + }
- }
-
- /* move first record forward until length fits into the buffer */
- @@ -1248,6 +1323,14 @@
- prev = msg->flags;
- idx = log_next(idx);
- seq++;
- + num_msg++;
- + if (num_msg > 5) {
- + num_msg = 0;
- + raw_spin_unlock_irq(&logbuf_lock);
- + raw_spin_lock_irq(&logbuf_lock);
- + if (clear_seq < log_first_seq)
- + goto try_again;
- + }
- }
-
- /* last message fitting into this dump */
- @@ -1288,6 +1371,7 @@
- clear_seq = log_next_seq;
- clear_idx = log_next_idx;
- }
- +out:
- raw_spin_unlock_irq(&logbuf_lock);
-
- kfree(text);
- @@ -1443,6 +1527,12 @@
- if (!console_drivers)
- return;
-
- + if (IS_ENABLED(CONFIG_PREEMPT_RT_BASE)) {
- + if (in_irq() || in_nmi())
- + return;
- + }
- +
- + migrate_disable();
- for_each_console(con) {
- if (exclusive_console && con != exclusive_console)
- continue;
- @@ -1458,6 +1548,7 @@
- else
- con->write(con, text, len);
- }
- + migrate_enable();
- }
-
- /*
- @@ -1518,6 +1609,15 @@
- static int console_trylock_for_printk(void)
- {
- unsigned int cpu = smp_processor_id();
- +#ifdef CONFIG_PREEMPT_RT_FULL
- + int lock = !early_boot_irqs_disabled && (preempt_count() == 0) &&
- + !irqs_disabled();
- +#else
- + int lock = 1;
- +#endif
- +
- + if (!lock)
- + return 0;
-
- if (!console_trylock())
- return 0;
- @@ -1672,6 +1772,13 @@
- /* cpu currently holding logbuf_lock in this function */
- static unsigned int logbuf_cpu = UINT_MAX;
-
- + /*
- + * Fall back to early_printk if a debugging subsystem has
- + * killed printk output
- + */
- + if (unlikely(forced_early_printk(fmt, args)))
- + return 1;
- +
- if (level == LOGLEVEL_SCHED) {
- level = LOGLEVEL_DEFAULT;
- in_sched = true;
- @@ -1813,8 +1920,7 @@
- * console_sem which would prevent anyone from printing to
- * console
- */
- - preempt_disable();
- -
- + migrate_disable();
- /*
- * Try to acquire and then immediately release the console
- * semaphore. The release will print out buffers and wake up
- @@ -1822,7 +1928,7 @@
- */
- if (console_trylock_for_printk())
- console_unlock();
- - preempt_enable();
- + migrate_enable();
- lockdep_on();
- }
-
- @@ -1961,26 +2067,6 @@
-
- #endif /* CONFIG_PRINTK */
-
- -#ifdef CONFIG_EARLY_PRINTK
- -struct console *early_console;
- -
- -asmlinkage __visible void early_printk(const char *fmt, ...)
- -{
- - va_list ap;
- - char buf[512];
- - int n;
- -
- - if (!early_console)
- - return;
- -
- - va_start(ap, fmt);
- - n = vscnprintf(buf, sizeof(buf), fmt, ap);
- - va_end(ap);
- -
- - early_console->write(early_console, buf, n);
- -}
- -#endif
- -
- static int __add_preferred_console(char *name, int idx, char *options,
- char *brl_options)
- {
- @@ -2202,11 +2288,16 @@
- goto out;
-
- len = cont_print_text(text, size);
- +#ifdef CONFIG_PREEMPT_RT_FULL
- + raw_spin_unlock_irqrestore(&logbuf_lock, flags);
- + call_console_drivers(cont.level, NULL, 0, text, len);
- +#else
- raw_spin_unlock(&logbuf_lock);
- stop_critical_timings();
- call_console_drivers(cont.level, NULL, 0, text, len);
- start_critical_timings();
- local_irq_restore(flags);
- +#endif
- return;
- out:
- raw_spin_unlock_irqrestore(&logbuf_lock, flags);
- @@ -2316,13 +2407,17 @@
- console_idx = log_next(console_idx);
- console_seq++;
- console_prev = msg->flags;
- +#ifdef CONFIG_PREEMPT_RT_FULL
- + raw_spin_unlock_irqrestore(&logbuf_lock, flags);
- + call_console_drivers(level, ext_text, ext_len, text, len);
- +#else
- raw_spin_unlock(&logbuf_lock);
-
- stop_critical_timings(); /* don't trace print latency */
- call_console_drivers(level, ext_text, ext_len, text, len);
- start_critical_timings();
- local_irq_restore(flags);
- -
- +#endif
- if (do_cond_resched)
- cond_resched();
- }
- @@ -2374,6 +2469,11 @@
- {
- struct console *c;
-
- + if (IS_ENABLED(CONFIG_PREEMPT_RT_BASE)) {
- + if (in_irq() || in_nmi())
- + return;
- + }
- +
- /*
- * console_unblank can no longer be called in interrupt context unless
- * oops_in_progress is set to 1..
- diff -Nur linux-4.4.28.orig/kernel/ptrace.c linux-4.4.28/kernel/ptrace.c
- --- linux-4.4.28.orig/kernel/ptrace.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/ptrace.c 2016-11-01 21:26:58.776342279 +0100
- @@ -129,7 +129,14 @@
-
- spin_lock_irq(&task->sighand->siglock);
- if (task_is_traced(task) && !__fatal_signal_pending(task)) {
- - task->state = __TASK_TRACED;
- + unsigned long flags;
- +
- + raw_spin_lock_irqsave(&task->pi_lock, flags);
- + if (task->state & __TASK_TRACED)
- + task->state = __TASK_TRACED;
- + else
- + task->saved_state = __TASK_TRACED;
- + raw_spin_unlock_irqrestore(&task->pi_lock, flags);
- ret = true;
- }
- spin_unlock_irq(&task->sighand->siglock);
- diff -Nur linux-4.4.28.orig/kernel/rcu/rcutorture.c linux-4.4.28/kernel/rcu/rcutorture.c
- --- linux-4.4.28.orig/kernel/rcu/rcutorture.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/rcu/rcutorture.c 2016-11-01 21:26:58.776342279 +0100
- @@ -390,6 +390,7 @@
- .name = "rcu"
- };
-
- +#ifndef CONFIG_PREEMPT_RT_FULL
- /*
- * Definitions for rcu_bh torture testing.
- */
- @@ -429,6 +430,12 @@
- .name = "rcu_bh"
- };
-
- +#else
- +static struct rcu_torture_ops rcu_bh_ops = {
- + .ttype = INVALID_RCU_FLAVOR,
- +};
- +#endif
- +
- /*
- * Don't even think about trying any of these in real life!!!
- * The names includes "busted", and they really means it!
- diff -Nur linux-4.4.28.orig/kernel/rcu/tree.c linux-4.4.28/kernel/rcu/tree.c
- --- linux-4.4.28.orig/kernel/rcu/tree.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/rcu/tree.c 2016-11-01 21:26:58.780342543 +0100
- @@ -56,6 +56,11 @@
- #include <linux/random.h>
- #include <linux/trace_events.h>
- #include <linux/suspend.h>
- +#include <linux/delay.h>
- +#include <linux/gfp.h>
- +#include <linux/oom.h>
- +#include <linux/smpboot.h>
- +#include "../time/tick-internal.h"
-
- #include "tree.h"
- #include "rcu.h"
- @@ -266,6 +271,19 @@
- }
- }
-
- +#ifdef CONFIG_PREEMPT_RT_FULL
- +static void rcu_preempt_qs(void);
- +
- +void rcu_bh_qs(void)
- +{
- + unsigned long flags;
- +
- + /* Callers to this function, rcu_preempt_qs(), must disable irqs. */
- + local_irq_save(flags);
- + rcu_preempt_qs();
- + local_irq_restore(flags);
- +}
- +#else
- void rcu_bh_qs(void)
- {
- if (__this_cpu_read(rcu_bh_data.cpu_no_qs.s)) {
- @@ -275,6 +293,7 @@
- __this_cpu_write(rcu_bh_data.cpu_no_qs.b.norm, false);
- }
- }
- +#endif
-
- static DEFINE_PER_CPU(int, rcu_sched_qs_mask);
-
- @@ -435,11 +454,13 @@
- /*
- * Return the number of RCU BH batches started thus far for debug & stats.
- */
- +#ifndef CONFIG_PREEMPT_RT_FULL
- unsigned long rcu_batches_started_bh(void)
- {
- return rcu_bh_state.gpnum;
- }
- EXPORT_SYMBOL_GPL(rcu_batches_started_bh);
- +#endif
-
- /*
- * Return the number of RCU batches completed thus far for debug & stats.
- @@ -459,6 +480,7 @@
- }
- EXPORT_SYMBOL_GPL(rcu_batches_completed_sched);
-
- +#ifndef CONFIG_PREEMPT_RT_FULL
- /*
- * Return the number of RCU BH batches completed thus far for debug & stats.
- */
- @@ -486,6 +508,13 @@
- }
- EXPORT_SYMBOL_GPL(rcu_bh_force_quiescent_state);
-
- +#else
- +void rcu_force_quiescent_state(void)
- +{
- +}
- +EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);
- +#endif
- +
- /*
- * Force a quiescent state for RCU-sched.
- */
- @@ -536,9 +565,11 @@
- case RCU_FLAVOR:
- rsp = rcu_state_p;
- break;
- +#ifndef CONFIG_PREEMPT_RT_FULL
- case RCU_BH_FLAVOR:
- rsp = &rcu_bh_state;
- break;
- +#endif
- case RCU_SCHED_FLAVOR:
- rsp = &rcu_sched_state;
- break;
- @@ -1590,7 +1621,6 @@
- int needmore;
- struct rcu_data *rdp = this_cpu_ptr(rsp->rda);
-
- - rcu_nocb_gp_cleanup(rsp, rnp);
- rnp->need_future_gp[c & 0x1] = 0;
- needmore = rnp->need_future_gp[(c + 1) & 0x1];
- trace_rcu_future_gp(rnp, rdp, c,
- @@ -1611,7 +1641,7 @@
- !READ_ONCE(rsp->gp_flags) ||
- !rsp->gp_kthread)
- return;
- - wake_up(&rsp->gp_wq);
- + swake_up(&rsp->gp_wq);
- }
-
- /*
- @@ -1991,6 +2021,7 @@
- int nocb = 0;
- struct rcu_data *rdp;
- struct rcu_node *rnp = rcu_get_root(rsp);
- + struct swait_queue_head *sq;
-
- WRITE_ONCE(rsp->gp_activity, jiffies);
- raw_spin_lock_irq(&rnp->lock);
- @@ -2029,7 +2060,9 @@
- needgp = __note_gp_changes(rsp, rnp, rdp) || needgp;
- /* smp_mb() provided by prior unlock-lock pair. */
- nocb += rcu_future_gp_cleanup(rsp, rnp);
- + sq = rcu_nocb_gp_get(rnp);
- raw_spin_unlock_irq(&rnp->lock);
- + rcu_nocb_gp_cleanup(sq);
- cond_resched_rcu_qs();
- WRITE_ONCE(rsp->gp_activity, jiffies);
- rcu_gp_slow(rsp, gp_cleanup_delay);
- @@ -2076,7 +2109,7 @@
- READ_ONCE(rsp->gpnum),
- TPS("reqwait"));
- rsp->gp_state = RCU_GP_WAIT_GPS;
- - wait_event_interruptible(rsp->gp_wq,
- + swait_event_interruptible(rsp->gp_wq,
- READ_ONCE(rsp->gp_flags) &
- RCU_GP_FLAG_INIT);
- rsp->gp_state = RCU_GP_DONE_GPS;
- @@ -2106,7 +2139,7 @@
- READ_ONCE(rsp->gpnum),
- TPS("fqswait"));
- rsp->gp_state = RCU_GP_WAIT_FQS;
- - ret = wait_event_interruptible_timeout(rsp->gp_wq,
- + ret = swait_event_interruptible_timeout(rsp->gp_wq,
- rcu_gp_fqs_check_wake(rsp, &gf), j);
- rsp->gp_state = RCU_GP_DOING_FQS;
- /* Locking provides needed memory barriers. */
- @@ -2230,7 +2263,7 @@
- WARN_ON_ONCE(!rcu_gp_in_progress(rsp));
- WRITE_ONCE(rsp->gp_flags, READ_ONCE(rsp->gp_flags) | RCU_GP_FLAG_FQS);
- raw_spin_unlock_irqrestore(&rcu_get_root(rsp)->lock, flags);
- - rcu_gp_kthread_wake(rsp);
- + swake_up(&rsp->gp_wq); /* Memory barrier implied by swake_up() path. */
- }
-
- /*
- @@ -2891,7 +2924,7 @@
- }
- WRITE_ONCE(rsp->gp_flags, READ_ONCE(rsp->gp_flags) | RCU_GP_FLAG_FQS);
- raw_spin_unlock_irqrestore(&rnp_old->lock, flags);
- - rcu_gp_kthread_wake(rsp);
- + swake_up(&rsp->gp_wq); /* Memory barrier implied by swake_up() path. */
- }
-
- /*
- @@ -2934,18 +2967,17 @@
- /*
- * Do RCU core processing for the current CPU.
- */
- -static void rcu_process_callbacks(struct softirq_action *unused)
- +static void rcu_process_callbacks(void)
- {
- struct rcu_state *rsp;
-
- if (cpu_is_offline(smp_processor_id()))
- return;
- - trace_rcu_utilization(TPS("Start RCU core"));
- for_each_rcu_flavor(rsp)
- __rcu_process_callbacks(rsp);
- - trace_rcu_utilization(TPS("End RCU core"));
- }
-
- +static DEFINE_PER_CPU(struct task_struct *, rcu_cpu_kthread_task);
- /*
- * Schedule RCU callback invocation. If the specified type of RCU
- * does not support RCU priority boosting, just do a direct call,
- @@ -2957,18 +2989,105 @@
- {
- if (unlikely(!READ_ONCE(rcu_scheduler_fully_active)))
- return;
- - if (likely(!rsp->boost)) {
- - rcu_do_batch(rsp, rdp);
- + rcu_do_batch(rsp, rdp);
- +}
- +
- +static void rcu_wake_cond(struct task_struct *t, int status)
- +{
- + /*
- + * If the thread is yielding, only wake it when this
- + * is invoked from idle
- + */
- + if (t && (status != RCU_KTHREAD_YIELDING || is_idle_task(current)))
- + wake_up_process(t);
- +}
- +
- +/*
- + * Wake up this CPU's rcuc kthread to do RCU core processing.
- + */
- +static void invoke_rcu_core(void)
- +{
- + unsigned long flags;
- + struct task_struct *t;
- +
- + if (!cpu_online(smp_processor_id()))
- return;
- + local_irq_save(flags);
- + __this_cpu_write(rcu_cpu_has_work, 1);
- + t = __this_cpu_read(rcu_cpu_kthread_task);
- + if (t != NULL && current != t)
- + rcu_wake_cond(t, __this_cpu_read(rcu_cpu_kthread_status));
- + local_irq_restore(flags);
- +}
- +
- +static void rcu_cpu_kthread_park(unsigned int cpu)
- +{
- + per_cpu(rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU;
- +}
- +
- +static int rcu_cpu_kthread_should_run(unsigned int cpu)
- +{
- + return __this_cpu_read(rcu_cpu_has_work);
- +}
- +
- +/*
- + * Per-CPU kernel thread that invokes RCU callbacks. This replaces the
- + * RCU softirq used in flavors and configurations of RCU that do not
- + * support RCU priority boosting.
- + */
- +static void rcu_cpu_kthread(unsigned int cpu)
- +{
- + unsigned int *statusp = this_cpu_ptr(&rcu_cpu_kthread_status);
- + char work, *workp = this_cpu_ptr(&rcu_cpu_has_work);
- + int spincnt;
- +
- + for (spincnt = 0; spincnt < 10; spincnt++) {
- + trace_rcu_utilization(TPS("Start CPU kthread@rcu_wait"));
- + local_bh_disable();
- + *statusp = RCU_KTHREAD_RUNNING;
- + this_cpu_inc(rcu_cpu_kthread_loops);
- + local_irq_disable();
- + work = *workp;
- + *workp = 0;
- + local_irq_enable();
- + if (work)
- + rcu_process_callbacks();
- + local_bh_enable();
- + if (*workp == 0) {
- + trace_rcu_utilization(TPS("End CPU kthread@rcu_wait"));
- + *statusp = RCU_KTHREAD_WAITING;
- + return;
- + }
- }
- - invoke_rcu_callbacks_kthread();
- + *statusp = RCU_KTHREAD_YIELDING;
- + trace_rcu_utilization(TPS("Start CPU kthread@rcu_yield"));
- + schedule_timeout_interruptible(2);
- + trace_rcu_utilization(TPS("End CPU kthread@rcu_yield"));
- + *statusp = RCU_KTHREAD_WAITING;
- }
-
- -static void invoke_rcu_core(void)
- +static struct smp_hotplug_thread rcu_cpu_thread_spec = {
- + .store = &rcu_cpu_kthread_task,
- + .thread_should_run = rcu_cpu_kthread_should_run,
- + .thread_fn = rcu_cpu_kthread,
- + .thread_comm = "rcuc/%u",
- + .setup = rcu_cpu_kthread_setup,
- + .park = rcu_cpu_kthread_park,
- +};
- +
- +/*
- + * Spawn per-CPU RCU core processing kthreads.
- + */
- +static int __init rcu_spawn_core_kthreads(void)
- {
- - if (cpu_online(smp_processor_id()))
- - raise_softirq(RCU_SOFTIRQ);
- + int cpu;
- +
- + for_each_possible_cpu(cpu)
- + per_cpu(rcu_cpu_has_work, cpu) = 0;
- + BUG_ON(smpboot_register_percpu_thread(&rcu_cpu_thread_spec));
- + return 0;
- }
- +early_initcall(rcu_spawn_core_kthreads);
-
- /*
- * Handle any core-RCU processing required by a call_rcu() invocation.
- @@ -3114,6 +3233,7 @@
- }
- EXPORT_SYMBOL_GPL(call_rcu_sched);
-
- +#ifndef CONFIG_PREEMPT_RT_FULL
- /*
- * Queue an RCU callback for invocation after a quicker grace period.
- */
- @@ -3122,6 +3242,7 @@
- __call_rcu(head, func, &rcu_bh_state, -1, 0);
- }
- EXPORT_SYMBOL_GPL(call_rcu_bh);
- +#endif
-
- /*
- * Queue an RCU callback for lazy invocation after a grace period.
- @@ -3213,6 +3334,7 @@
- }
- EXPORT_SYMBOL_GPL(synchronize_sched);
-
- +#ifndef CONFIG_PREEMPT_RT_FULL
- /**
- * synchronize_rcu_bh - wait until an rcu_bh grace period has elapsed.
- *
- @@ -3239,6 +3361,7 @@
- wait_rcu_gp(call_rcu_bh);
- }
- EXPORT_SYMBOL_GPL(synchronize_rcu_bh);
- +#endif
-
- /**
- * get_state_synchronize_rcu - Snapshot current RCU state
- @@ -3524,7 +3647,7 @@
- raw_spin_unlock_irqrestore(&rnp->lock, flags);
- if (wake) {
- smp_mb(); /* EGP done before wake_up(). */
- - wake_up(&rsp->expedited_wq);
- + swake_up(&rsp->expedited_wq);
- }
- break;
- }
- @@ -3781,7 +3904,7 @@
- jiffies_start = jiffies;
-
- for (;;) {
- - ret = wait_event_interruptible_timeout(
- + ret = swait_event_timeout(
- rsp->expedited_wq,
- sync_rcu_preempt_exp_done(rnp_root),
- jiffies_stall);
- @@ -3789,7 +3912,7 @@
- return;
- if (ret < 0) {
- /* Hit a signal, disable CPU stall warnings. */
- - wait_event(rsp->expedited_wq,
- + swait_event(rsp->expedited_wq,
- sync_rcu_preempt_exp_done(rnp_root));
- return;
- }
- @@ -4101,6 +4224,7 @@
- mutex_unlock(&rsp->barrier_mutex);
- }
-
- +#ifndef CONFIG_PREEMPT_RT_FULL
- /**
- * rcu_barrier_bh - Wait until all in-flight call_rcu_bh() callbacks complete.
- */
- @@ -4109,6 +4233,7 @@
- _rcu_barrier(&rcu_bh_state);
- }
- EXPORT_SYMBOL_GPL(rcu_barrier_bh);
- +#endif
-
- /**
- * rcu_barrier_sched - Wait for in-flight call_rcu_sched() callbacks.
- @@ -4455,8 +4580,8 @@
- }
- }
-
- - init_waitqueue_head(&rsp->gp_wq);
- - init_waitqueue_head(&rsp->expedited_wq);
- + init_swait_queue_head(&rsp->gp_wq);
- + init_swait_queue_head(&rsp->expedited_wq);
- rnp = rsp->level[rcu_num_lvls - 1];
- for_each_possible_cpu(i) {
- while (i > rnp->grphi)
- @@ -4576,12 +4701,13 @@
-
- rcu_bootup_announce();
- rcu_init_geometry();
- +#ifndef CONFIG_PREEMPT_RT_FULL
- rcu_init_one(&rcu_bh_state, &rcu_bh_data);
- +#endif
- rcu_init_one(&rcu_sched_state, &rcu_sched_data);
- if (dump_tree)
- rcu_dump_rcu_node_tree(&rcu_sched_state);
- __rcu_init_preempt();
- - open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
-
- /*
- * We don't need protection against CPU-hotplug here because
- diff -Nur linux-4.4.28.orig/kernel/rcu/tree.h linux-4.4.28/kernel/rcu/tree.h
- --- linux-4.4.28.orig/kernel/rcu/tree.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/rcu/tree.h 2016-11-01 21:26:58.780342543 +0100
- @@ -27,6 +27,7 @@
- #include <linux/threads.h>
- #include <linux/cpumask.h>
- #include <linux/seqlock.h>
- +#include <linux/swait.h>
- #include <linux/stop_machine.h>
-
- /*
- @@ -241,7 +242,7 @@
- /* Refused to boost: not sure why, though. */
- /* This can happen due to race conditions. */
- #ifdef CONFIG_RCU_NOCB_CPU
- - wait_queue_head_t nocb_gp_wq[2];
- + struct swait_queue_head nocb_gp_wq[2];
- /* Place for rcu_nocb_kthread() to wait GP. */
- #endif /* #ifdef CONFIG_RCU_NOCB_CPU */
- int need_future_gp[2];
- @@ -393,7 +394,7 @@
- atomic_long_t nocb_q_count_lazy; /* invocation (all stages). */
- struct rcu_head *nocb_follower_head; /* CBs ready to invoke. */
- struct rcu_head **nocb_follower_tail;
- - wait_queue_head_t nocb_wq; /* For nocb kthreads to sleep on. */
- + struct swait_queue_head nocb_wq; /* For nocb kthreads to sleep on. */
- struct task_struct *nocb_kthread;
- int nocb_defer_wakeup; /* Defer wakeup of nocb_kthread. */
-
- @@ -472,7 +473,7 @@
- unsigned long gpnum; /* Current gp number. */
- unsigned long completed; /* # of last completed gp. */
- struct task_struct *gp_kthread; /* Task for grace periods. */
- - wait_queue_head_t gp_wq; /* Where GP task waits. */
- + struct swait_queue_head gp_wq; /* Where GP task waits. */
- short gp_flags; /* Commands for GP task. */
- short gp_state; /* GP kthread sleep state. */
-
- @@ -504,7 +505,7 @@
- atomic_long_t expedited_workdone3; /* # done by others #3. */
- atomic_long_t expedited_normal; /* # fallbacks to normal. */
- atomic_t expedited_need_qs; /* # CPUs left to check in. */
- - wait_queue_head_t expedited_wq; /* Wait for check-ins. */
- + struct swait_queue_head expedited_wq; /* Wait for check-ins. */
- int ncpus_snap; /* # CPUs seen last time. */
-
- unsigned long jiffies_force_qs; /* Time at which to invoke */
- @@ -556,18 +557,18 @@
- */
- extern struct rcu_state rcu_sched_state;
-
- +#ifndef CONFIG_PREEMPT_RT_FULL
- extern struct rcu_state rcu_bh_state;
- +#endif
-
- #ifdef CONFIG_PREEMPT_RCU
- extern struct rcu_state rcu_preempt_state;
- #endif /* #ifdef CONFIG_PREEMPT_RCU */
-
- -#ifdef CONFIG_RCU_BOOST
- DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_status);
- DECLARE_PER_CPU(int, rcu_cpu_kthread_cpu);
- DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_loops);
- DECLARE_PER_CPU(char, rcu_cpu_has_work);
- -#endif /* #ifdef CONFIG_RCU_BOOST */
-
- #ifndef RCU_TREE_NONCORE
-
- @@ -587,10 +588,9 @@
- static void __init __rcu_init_preempt(void);
- static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags);
- static void rcu_preempt_boost_start_gp(struct rcu_node *rnp);
- -static void invoke_rcu_callbacks_kthread(void);
- static bool rcu_is_callbacks_kthread(void);
- +static void rcu_cpu_kthread_setup(unsigned int cpu);
- #ifdef CONFIG_RCU_BOOST
- -static void rcu_preempt_do_callbacks(void);
- static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
- struct rcu_node *rnp);
- #endif /* #ifdef CONFIG_RCU_BOOST */
- @@ -607,7 +607,8 @@
- static void increment_cpu_stall_ticks(void);
- static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu);
- static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq);
- -static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp);
- +static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp);
- +static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq);
- static void rcu_init_one_nocb(struct rcu_node *rnp);
- static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
- bool lazy, unsigned long flags);
- diff -Nur linux-4.4.28.orig/kernel/rcu/tree_plugin.h linux-4.4.28/kernel/rcu/tree_plugin.h
- --- linux-4.4.28.orig/kernel/rcu/tree_plugin.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/rcu/tree_plugin.h 2016-11-01 21:26:58.780342543 +0100
- @@ -24,25 +24,10 @@
- * Paul E. McKenney <paulmck@linux.vnet.ibm.com>
- */
-
- -#include <linux/delay.h>
- -#include <linux/gfp.h>
- -#include <linux/oom.h>
- -#include <linux/smpboot.h>
- -#include "../time/tick-internal.h"
- -
- #ifdef CONFIG_RCU_BOOST
-
- #include "../locking/rtmutex_common.h"
-
- -/*
- - * Control variables for per-CPU and per-rcu_node kthreads. These
- - * handle all flavors of RCU.
- - */
- -static DEFINE_PER_CPU(struct task_struct *, rcu_cpu_kthread_task);
- -DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_status);
- -DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_loops);
- -DEFINE_PER_CPU(char, rcu_cpu_has_work);
- -
- #else /* #ifdef CONFIG_RCU_BOOST */
-
- /*
- @@ -55,6 +40,14 @@
-
- #endif /* #else #ifdef CONFIG_RCU_BOOST */
-
- +/*
- + * Control variables for per-CPU and per-rcu_node kthreads. These
- + * handle all flavors of RCU.
- + */
- +DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_status);
- +DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_loops);
- +DEFINE_PER_CPU(char, rcu_cpu_has_work);
- +
- #ifdef CONFIG_RCU_NOCB_CPU
- static cpumask_var_t rcu_nocb_mask; /* CPUs to have callbacks offloaded. */
- static bool have_rcu_nocb_mask; /* Was rcu_nocb_mask allocated? */
- @@ -432,7 +425,7 @@
- }
-
- /* Hardware IRQ handlers cannot block, complain if they get here. */
- - if (in_irq() || in_serving_softirq()) {
- + if (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_OFFSET)) {
- lockdep_rcu_suspicious(__FILE__, __LINE__,
- "rcu_read_unlock() from irq or softirq with blocking in critical section!!!\n");
- pr_alert("->rcu_read_unlock_special: %#x (b: %d, enq: %d nq: %d)\n",
- @@ -645,15 +638,6 @@
- t->rcu_read_unlock_special.b.need_qs = true;
- }
-
- -#ifdef CONFIG_RCU_BOOST
- -
- -static void rcu_preempt_do_callbacks(void)
- -{
- - rcu_do_batch(rcu_state_p, this_cpu_ptr(rcu_data_p));
- -}
- -
- -#endif /* #ifdef CONFIG_RCU_BOOST */
- -
- /*
- * Queue a preemptible-RCU callback for invocation after a grace period.
- */
- @@ -930,6 +914,19 @@
-
- #endif /* #else #ifdef CONFIG_PREEMPT_RCU */
-
- +/*
- + * If boosting, set rcuc kthreads to realtime priority.
- + */
- +static void rcu_cpu_kthread_setup(unsigned int cpu)
- +{
- +#ifdef CONFIG_RCU_BOOST
- + struct sched_param sp;
- +
- + sp.sched_priority = kthread_prio;
- + sched_setscheduler_nocheck(current, SCHED_FIFO, &sp);
- +#endif /* #ifdef CONFIG_RCU_BOOST */
- +}
- +
- #ifdef CONFIG_RCU_BOOST
-
- #include "../locking/rtmutex_common.h"
- @@ -961,16 +958,6 @@
-
- #endif /* #else #ifdef CONFIG_RCU_TRACE */
-
- -static void rcu_wake_cond(struct task_struct *t, int status)
- -{
- - /*
- - * If the thread is yielding, only wake it when this
- - * is invoked from idle
- - */
- - if (status != RCU_KTHREAD_YIELDING || is_idle_task(current))
- - wake_up_process(t);
- -}
- -
- /*
- * Carry out RCU priority boosting on the task indicated by ->exp_tasks
- * or ->boost_tasks, advancing the pointer to the next task in the
- @@ -1115,23 +1102,6 @@
- }
-
- /*
- - * Wake up the per-CPU kthread to invoke RCU callbacks.
- - */
- -static void invoke_rcu_callbacks_kthread(void)
- -{
- - unsigned long flags;
- -
- - local_irq_save(flags);
- - __this_cpu_write(rcu_cpu_has_work, 1);
- - if (__this_cpu_read(rcu_cpu_kthread_task) != NULL &&
- - current != __this_cpu_read(rcu_cpu_kthread_task)) {
- - rcu_wake_cond(__this_cpu_read(rcu_cpu_kthread_task),
- - __this_cpu_read(rcu_cpu_kthread_status));
- - }
- - local_irq_restore(flags);
- -}
- -
- -/*
- * Is the current CPU running the RCU-callbacks kthread?
- * Caller must have preemption disabled.
- */
- @@ -1186,67 +1156,6 @@
- return 0;
- }
-
- -static void rcu_kthread_do_work(void)
- -{
- - rcu_do_batch(&rcu_sched_state, this_cpu_ptr(&rcu_sched_data));
- - rcu_do_batch(&rcu_bh_state, this_cpu_ptr(&rcu_bh_data));
- - rcu_preempt_do_callbacks();
- -}
- -
- -static void rcu_cpu_kthread_setup(unsigned int cpu)
- -{
- - struct sched_param sp;
- -
- - sp.sched_priority = kthread_prio;
- - sched_setscheduler_nocheck(current, SCHED_FIFO, &sp);
- -}
- -
- -static void rcu_cpu_kthread_park(unsigned int cpu)
- -{
- - per_cpu(rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU;
- -}
- -
- -static int rcu_cpu_kthread_should_run(unsigned int cpu)
- -{
- - return __this_cpu_read(rcu_cpu_has_work);
- -}
- -
- -/*
- - * Per-CPU kernel thread that invokes RCU callbacks. This replaces the
- - * RCU softirq used in flavors and configurations of RCU that do not
- - * support RCU priority boosting.
- - */
- -static void rcu_cpu_kthread(unsigned int cpu)
- -{
- - unsigned int *statusp = this_cpu_ptr(&rcu_cpu_kthread_status);
- - char work, *workp = this_cpu_ptr(&rcu_cpu_has_work);
- - int spincnt;
- -
- - for (spincnt = 0; spincnt < 10; spincnt++) {
- - trace_rcu_utilization(TPS("Start CPU kthread@rcu_wait"));
- - local_bh_disable();
- - *statusp = RCU_KTHREAD_RUNNING;
- - this_cpu_inc(rcu_cpu_kthread_loops);
- - local_irq_disable();
- - work = *workp;
- - *workp = 0;
- - local_irq_enable();
- - if (work)
- - rcu_kthread_do_work();
- - local_bh_enable();
- - if (*workp == 0) {
- - trace_rcu_utilization(TPS("End CPU kthread@rcu_wait"));
- - *statusp = RCU_KTHREAD_WAITING;
- - return;
- - }
- - }
- - *statusp = RCU_KTHREAD_YIELDING;
- - trace_rcu_utilization(TPS("Start CPU kthread@rcu_yield"));
- - schedule_timeout_interruptible(2);
- - trace_rcu_utilization(TPS("End CPU kthread@rcu_yield"));
- - *statusp = RCU_KTHREAD_WAITING;
- -}
- -
- /*
- * Set the per-rcu_node kthread's affinity to cover all CPUs that are
- * served by the rcu_node in question. The CPU hotplug lock is still
- @@ -1276,26 +1185,12 @@
- free_cpumask_var(cm);
- }
-
- -static struct smp_hotplug_thread rcu_cpu_thread_spec = {
- - .store = &rcu_cpu_kthread_task,
- - .thread_should_run = rcu_cpu_kthread_should_run,
- - .thread_fn = rcu_cpu_kthread,
- - .thread_comm = "rcuc/%u",
- - .setup = rcu_cpu_kthread_setup,
- - .park = rcu_cpu_kthread_park,
- -};
- -
- /*
- * Spawn boost kthreads -- called as soon as the scheduler is running.
- */
- static void __init rcu_spawn_boost_kthreads(void)
- {
- struct rcu_node *rnp;
- - int cpu;
- -
- - for_each_possible_cpu(cpu)
- - per_cpu(rcu_cpu_has_work, cpu) = 0;
- - BUG_ON(smpboot_register_percpu_thread(&rcu_cpu_thread_spec));
- rcu_for_each_leaf_node(rcu_state_p, rnp)
- (void)rcu_spawn_one_boost_kthread(rcu_state_p, rnp);
- }
- @@ -1318,11 +1213,6 @@
- raw_spin_unlock_irqrestore(&rnp->lock, flags);
- }
-
- -static void invoke_rcu_callbacks_kthread(void)
- -{
- - WARN_ON_ONCE(1);
- -}
- -
- static bool rcu_is_callbacks_kthread(void)
- {
- return false;
- @@ -1346,7 +1236,7 @@
-
- #endif /* #else #ifdef CONFIG_RCU_BOOST */
-
- -#if !defined(CONFIG_RCU_FAST_NO_HZ)
- +#if !defined(CONFIG_RCU_FAST_NO_HZ) || defined(CONFIG_PREEMPT_RT_FULL)
-
- /*
- * Check to see if any future RCU-related work will need to be done
- @@ -1363,7 +1253,9 @@
- return IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL)
- ? 0 : rcu_cpu_has_callbacks(NULL);
- }
- +#endif /* !defined(CONFIG_RCU_FAST_NO_HZ) || defined(CONFIG_PREEMPT_RT_FULL) */
-
- +#if !defined(CONFIG_RCU_FAST_NO_HZ)
- /*
- * Because we do not have RCU_FAST_NO_HZ, don't bother cleaning up
- * after it.
- @@ -1459,6 +1351,8 @@
- return cbs_ready;
- }
-
- +#ifndef CONFIG_PREEMPT_RT_FULL
- +
- /*
- * Allow the CPU to enter dyntick-idle mode unless it has callbacks ready
- * to invoke. If the CPU has callbacks, try to advance them. Tell the
- @@ -1504,6 +1398,7 @@
- *nextevt = basemono + dj * TICK_NSEC;
- return 0;
- }
- +#endif /* #ifndef CONFIG_PREEMPT_RT_FULL */
-
- /*
- * Prepare a CPU for idle from an RCU perspective. The first major task
- @@ -1822,9 +1717,9 @@
- * Wake up any no-CBs CPUs' kthreads that were waiting on the just-ended
- * grace period.
- */
- -static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp)
- +static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq)
- {
- - wake_up_all(&rnp->nocb_gp_wq[rnp->completed & 0x1]);
- + swake_up_all(sq);
- }
-
- /*
- @@ -1840,10 +1735,15 @@
- rnp->need_future_gp[(rnp->completed + 1) & 0x1] += nrq;
- }
-
- +static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp)
- +{
- + return &rnp->nocb_gp_wq[rnp->completed & 0x1];
- +}
- +
- static void rcu_init_one_nocb(struct rcu_node *rnp)
- {
- - init_waitqueue_head(&rnp->nocb_gp_wq[0]);
- - init_waitqueue_head(&rnp->nocb_gp_wq[1]);
- + init_swait_queue_head(&rnp->nocb_gp_wq[0]);
- + init_swait_queue_head(&rnp->nocb_gp_wq[1]);
- }
-
- #ifndef CONFIG_RCU_NOCB_CPU_ALL
- @@ -1868,7 +1768,7 @@
- if (READ_ONCE(rdp_leader->nocb_leader_sleep) || force) {
- /* Prior smp_mb__after_atomic() orders against prior enqueue. */
- WRITE_ONCE(rdp_leader->nocb_leader_sleep, false);
- - wake_up(&rdp_leader->nocb_wq);
- + swake_up(&rdp_leader->nocb_wq);
- }
- }
-
- @@ -2081,7 +1981,7 @@
- */
- trace_rcu_future_gp(rnp, rdp, c, TPS("StartWait"));
- for (;;) {
- - wait_event_interruptible(
- + swait_event_interruptible(
- rnp->nocb_gp_wq[c & 0x1],
- (d = ULONG_CMP_GE(READ_ONCE(rnp->completed), c)));
- if (likely(d))
- @@ -2109,7 +2009,7 @@
- /* Wait for callbacks to appear. */
- if (!rcu_nocb_poll) {
- trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu, "Sleep");
- - wait_event_interruptible(my_rdp->nocb_wq,
- + swait_event_interruptible(my_rdp->nocb_wq,
- !READ_ONCE(my_rdp->nocb_leader_sleep));
- /* Memory barrier handled by smp_mb() calls below and repoll. */
- } else if (firsttime) {
- @@ -2184,7 +2084,7 @@
- * List was empty, wake up the follower.
- * Memory barriers supplied by atomic_long_add().
- */
- - wake_up(&rdp->nocb_wq);
- + swake_up(&rdp->nocb_wq);
- }
- }
-
- @@ -2205,7 +2105,7 @@
- if (!rcu_nocb_poll) {
- trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
- "FollowerSleep");
- - wait_event_interruptible(rdp->nocb_wq,
- + swait_event_interruptible(rdp->nocb_wq,
- READ_ONCE(rdp->nocb_follower_head));
- } else if (firsttime) {
- /* Don't drown trace log with "Poll"! */
- @@ -2364,7 +2264,7 @@
- static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp)
- {
- rdp->nocb_tail = &rdp->nocb_head;
- - init_waitqueue_head(&rdp->nocb_wq);
- + init_swait_queue_head(&rdp->nocb_wq);
- rdp->nocb_follower_tail = &rdp->nocb_follower_head;
- }
-
- @@ -2514,7 +2414,7 @@
- return false;
- }
-
- -static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp)
- +static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq)
- {
- }
-
- @@ -2522,6 +2422,11 @@
- {
- }
-
- +static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp)
- +{
- + return NULL;
- +}
- +
- static void rcu_init_one_nocb(struct rcu_node *rnp)
- {
- }
- diff -Nur linux-4.4.28.orig/kernel/rcu/update.c linux-4.4.28/kernel/rcu/update.c
- --- linux-4.4.28.orig/kernel/rcu/update.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/rcu/update.c 2016-11-01 21:26:58.780342543 +0100
- @@ -276,6 +276,7 @@
- }
- EXPORT_SYMBOL_GPL(rcu_read_lock_held);
-
- +#ifndef CONFIG_PREEMPT_RT_FULL
- /**
- * rcu_read_lock_bh_held() - might we be in RCU-bh read-side critical section?
- *
- @@ -302,6 +303,7 @@
- return in_softirq() || irqs_disabled();
- }
- EXPORT_SYMBOL_GPL(rcu_read_lock_bh_held);
- +#endif
-
- #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
-
- diff -Nur linux-4.4.28.orig/kernel/relay.c linux-4.4.28/kernel/relay.c
- --- linux-4.4.28.orig/kernel/relay.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/relay.c 2016-11-01 21:26:58.780342543 +0100
- @@ -336,6 +336,10 @@
- {
- struct rchan_buf *buf = (struct rchan_buf *)data;
- wake_up_interruptible(&buf->read_wait);
- + /*
- + * Stupid polling for now:
- + */
- + mod_timer(&buf->timer, jiffies + 1);
- }
-
- /**
- @@ -353,6 +357,7 @@
- init_waitqueue_head(&buf->read_wait);
- kref_init(&buf->kref);
- setup_timer(&buf->timer, wakeup_readers, (unsigned long)buf);
- + mod_timer(&buf->timer, jiffies + 1);
- } else
- del_timer_sync(&buf->timer);
-
- @@ -736,15 +741,6 @@
- else
- buf->early_bytes += buf->chan->subbuf_size -
- buf->padding[old_subbuf];
- - smp_mb();
- - if (waitqueue_active(&buf->read_wait))
- - /*
- - * Calling wake_up_interruptible() from here
- - * will deadlock if we happen to be logging
- - * from the scheduler (trying to re-grab
- - * rq->lock), so defer it.
- - */
- - mod_timer(&buf->timer, jiffies + 1);
- }
-
- old = buf->data;
- diff -Nur linux-4.4.28.orig/kernel/sched/completion.c linux-4.4.28/kernel/sched/completion.c
- --- linux-4.4.28.orig/kernel/sched/completion.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/sched/completion.c 2016-11-01 21:26:58.780342543 +0100
- @@ -30,10 +30,10 @@
- {
- unsigned long flags;
-
- - spin_lock_irqsave(&x->wait.lock, flags);
- + raw_spin_lock_irqsave(&x->wait.lock, flags);
- x->done++;
- - __wake_up_locked(&x->wait, TASK_NORMAL, 1);
- - spin_unlock_irqrestore(&x->wait.lock, flags);
- + swake_up_locked(&x->wait);
- + raw_spin_unlock_irqrestore(&x->wait.lock, flags);
- }
- EXPORT_SYMBOL(complete);
-
- @@ -50,10 +50,10 @@
- {
- unsigned long flags;
-
- - spin_lock_irqsave(&x->wait.lock, flags);
- + raw_spin_lock_irqsave(&x->wait.lock, flags);
- x->done += UINT_MAX/2;
- - __wake_up_locked(&x->wait, TASK_NORMAL, 0);
- - spin_unlock_irqrestore(&x->wait.lock, flags);
- + swake_up_all_locked(&x->wait);
- + raw_spin_unlock_irqrestore(&x->wait.lock, flags);
- }
- EXPORT_SYMBOL(complete_all);
-
- @@ -62,20 +62,20 @@
- long (*action)(long), long timeout, int state)
- {
- if (!x->done) {
- - DECLARE_WAITQUEUE(wait, current);
- + DECLARE_SWAITQUEUE(wait);
-
- - __add_wait_queue_tail_exclusive(&x->wait, &wait);
- + __prepare_to_swait(&x->wait, &wait);
- do {
- if (signal_pending_state(state, current)) {
- timeout = -ERESTARTSYS;
- break;
- }
- __set_current_state(state);
- - spin_unlock_irq(&x->wait.lock);
- + raw_spin_unlock_irq(&x->wait.lock);
- timeout = action(timeout);
- - spin_lock_irq(&x->wait.lock);
- + raw_spin_lock_irq(&x->wait.lock);
- } while (!x->done && timeout);
- - __remove_wait_queue(&x->wait, &wait);
- + __finish_swait(&x->wait, &wait);
- if (!x->done)
- return timeout;
- }
- @@ -89,9 +89,9 @@
- {
- might_sleep();
-
- - spin_lock_irq(&x->wait.lock);
- + raw_spin_lock_irq(&x->wait.lock);
- timeout = do_wait_for_common(x, action, timeout, state);
- - spin_unlock_irq(&x->wait.lock);
- + raw_spin_unlock_irq(&x->wait.lock);
- return timeout;
- }
-
- @@ -277,12 +277,12 @@
- if (!READ_ONCE(x->done))
- return 0;
-
- - spin_lock_irqsave(&x->wait.lock, flags);
- + raw_spin_lock_irqsave(&x->wait.lock, flags);
- if (!x->done)
- ret = 0;
- else
- x->done--;
- - spin_unlock_irqrestore(&x->wait.lock, flags);
- + raw_spin_unlock_irqrestore(&x->wait.lock, flags);
- return ret;
- }
- EXPORT_SYMBOL(try_wait_for_completion);
- @@ -311,7 +311,7 @@
- * after it's acquired the lock.
- */
- smp_rmb();
- - spin_unlock_wait(&x->wait.lock);
- + raw_spin_unlock_wait(&x->wait.lock);
- return true;
- }
- EXPORT_SYMBOL(completion_done);
- diff -Nur linux-4.4.28.orig/kernel/sched/core.c linux-4.4.28/kernel/sched/core.c
- --- linux-4.4.28.orig/kernel/sched/core.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/sched/core.c 2016-11-01 21:26:58.784342796 +0100
- @@ -260,7 +260,11 @@
- * Number of tasks to iterate in a single balance run.
- * Limited because this is done with IRQs disabled.
- */
- +#ifndef CONFIG_PREEMPT_RT_FULL
- const_debug unsigned int sysctl_sched_nr_migrate = 32;
- +#else
- +const_debug unsigned int sysctl_sched_nr_migrate = 8;
- +#endif
-
- /*
- * period over which we average the RT time consumption, measured
- @@ -438,6 +442,7 @@
-
- hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
- rq->hrtick_timer.function = hrtick;
- + rq->hrtick_timer.irqsafe = 1;
- }
- #else /* CONFIG_SCHED_HRTICK */
- static inline void hrtick_clear(struct rq *rq)
- @@ -542,7 +547,7 @@
- head->lastp = &node->next;
- }
-
- -void wake_up_q(struct wake_q_head *head)
- +void __wake_up_q(struct wake_q_head *head, bool sleeper)
- {
- struct wake_q_node *node = head->first;
-
- @@ -559,7 +564,10 @@
- * wake_up_process() implies a wmb() to pair with the queueing
- * in wake_q_add() so as not to miss wakeups.
- */
- - wake_up_process(task);
- + if (sleeper)
- + wake_up_lock_sleeper(task);
- + else
- + wake_up_process(task);
- put_task_struct(task);
- }
- }
- @@ -595,6 +603,38 @@
- trace_sched_wake_idle_without_ipi(cpu);
- }
-
- +#ifdef CONFIG_PREEMPT_LAZY
- +void resched_curr_lazy(struct rq *rq)
- +{
- + struct task_struct *curr = rq->curr;
- + int cpu;
- +
- + if (!sched_feat(PREEMPT_LAZY)) {
- + resched_curr(rq);
- + return;
- + }
- +
- + lockdep_assert_held(&rq->lock);
- +
- + if (test_tsk_need_resched(curr))
- + return;
- +
- + if (test_tsk_need_resched_lazy(curr))
- + return;
- +
- + set_tsk_need_resched_lazy(curr);
- +
- + cpu = cpu_of(rq);
- + if (cpu == smp_processor_id())
- + return;
- +
- + /* NEED_RESCHED_LAZY must be visible before we test polling */
- + smp_mb();
- + if (!tsk_is_polling(curr))
- + smp_send_reschedule(cpu);
- +}
- +#endif
- +
- void resched_cpu(int cpu)
- {
- struct rq *rq = cpu_rq(cpu);
- @@ -618,11 +658,14 @@
- */
- int get_nohz_timer_target(void)
- {
- - int i, cpu = smp_processor_id();
- + int i, cpu;
- struct sched_domain *sd;
-
- + preempt_disable_rt();
- + cpu = smp_processor_id();
- +
- if (!idle_cpu(cpu) && is_housekeeping_cpu(cpu))
- - return cpu;
- + goto preempt_en_rt;
-
- rcu_read_lock();
- for_each_domain(cpu, sd) {
- @@ -641,6 +684,8 @@
- cpu = housekeeping_any_cpu();
- unlock:
- rcu_read_unlock();
- +preempt_en_rt:
- + preempt_enable_rt();
- return cpu;
- }
- /*
- @@ -1174,6 +1219,11 @@
-
- lockdep_assert_held(&p->pi_lock);
-
- + if (__migrate_disabled(p)) {
- + cpumask_copy(&p->cpus_allowed, new_mask);
- + return;
- + }
- +
- queued = task_on_rq_queued(p);
- running = task_current(rq, p);
-
- @@ -1196,6 +1246,84 @@
- enqueue_task(rq, p, ENQUEUE_RESTORE);
- }
-
- +static DEFINE_PER_CPU(struct cpumask, sched_cpumasks);
- +static DEFINE_MUTEX(sched_down_mutex);
- +static cpumask_t sched_down_cpumask;
- +
- +void tell_sched_cpu_down_begin(int cpu)
- +{
- + mutex_lock(&sched_down_mutex);
- + cpumask_set_cpu(cpu, &sched_down_cpumask);
- + mutex_unlock(&sched_down_mutex);
- +}
- +
- +void tell_sched_cpu_down_done(int cpu)
- +{
- + mutex_lock(&sched_down_mutex);
- + cpumask_clear_cpu(cpu, &sched_down_cpumask);
- + mutex_unlock(&sched_down_mutex);
- +}
- +
- +/**
- + * migrate_me - try to move the current task off this cpu
- + *
- + * Used by the pin_current_cpu() code to try to get tasks
- + * to move off the current CPU as it is going down.
- + * It will only move the task if the task isn't pinned to
- + * the CPU (with migrate_disable, affinity or NO_SETAFFINITY)
- + * and the task has to be in a RUNNING state. Otherwise the
- + * movement of the task will wake it up (change its state
- + * to running) when the task did not expect it.
- + *
- + * Returns 1 if it succeeded in moving the current task
- + * 0 otherwise.
- + */
- +int migrate_me(void)
- +{
- + struct task_struct *p = current;
- + struct migration_arg arg;
- + struct cpumask *cpumask;
- + struct cpumask *mask;
- + unsigned long flags;
- + unsigned int dest_cpu;
- + struct rq *rq;
- +
- + /*
- + * We can not migrate tasks bounded to a CPU or tasks not
- + * running. The movement of the task will wake it up.
- + */
- + if (p->flags & PF_NO_SETAFFINITY || p->state)
- + return 0;
- +
- + mutex_lock(&sched_down_mutex);
- + rq = task_rq_lock(p, &flags);
- +
- + cpumask = this_cpu_ptr(&sched_cpumasks);
- + mask = &p->cpus_allowed;
- +
- + cpumask_andnot(cpumask, mask, &sched_down_cpumask);
- +
- + if (!cpumask_weight(cpumask)) {
- + /* It's only on this CPU? */
- + task_rq_unlock(rq, p, &flags);
- + mutex_unlock(&sched_down_mutex);
- + return 0;
- + }
- +
- + dest_cpu = cpumask_any_and(cpu_active_mask, cpumask);
- +
- + arg.task = p;
- + arg.dest_cpu = dest_cpu;
- +
- + task_rq_unlock(rq, p, &flags);
- +
- + stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg);
- + tlb_migrate_finish(p->mm);
- + mutex_unlock(&sched_down_mutex);
- +
- + return 1;
- +}
- +
- /*
- * Change a given task's CPU affinity. Migrate the thread to a
- * proper CPU and schedule it away if the CPU it's executing on
- @@ -1235,7 +1363,7 @@
- do_set_cpus_allowed(p, new_mask);
-
- /* Can the task run on the task's current CPU? If so, we're done */
- - if (cpumask_test_cpu(task_cpu(p), new_mask))
- + if (cpumask_test_cpu(task_cpu(p), new_mask) || __migrate_disabled(p))
- goto out;
-
- dest_cpu = cpumask_any_and(cpu_active_mask, new_mask);
- @@ -1411,6 +1539,18 @@
- return ret;
- }
-
- +static bool check_task_state(struct task_struct *p, long match_state)
- +{
- + bool match = false;
- +
- + raw_spin_lock_irq(&p->pi_lock);
- + if (p->state == match_state || p->saved_state == match_state)
- + match = true;
- + raw_spin_unlock_irq(&p->pi_lock);
- +
- + return match;
- +}
- +
- /*
- * wait_task_inactive - wait for a thread to unschedule.
- *
- @@ -1455,7 +1595,7 @@
- * is actually now running somewhere else!
- */
- while (task_running(rq, p)) {
- - if (match_state && unlikely(p->state != match_state))
- + if (match_state && !check_task_state(p, match_state))
- return 0;
- cpu_relax();
- }
- @@ -1470,7 +1610,8 @@
- running = task_running(rq, p);
- queued = task_on_rq_queued(p);
- ncsw = 0;
- - if (!match_state || p->state == match_state)
- + if (!match_state || p->state == match_state ||
- + p->saved_state == match_state)
- ncsw = p->nvcsw | LONG_MIN; /* sets MSB */
- task_rq_unlock(rq, p, &flags);
-
- @@ -1627,7 +1768,7 @@
- {
- lockdep_assert_held(&p->pi_lock);
-
- - if (p->nr_cpus_allowed > 1)
- + if (tsk_nr_cpus_allowed(p) > 1)
- cpu = p->sched_class->select_task_rq(p, cpu, sd_flags, wake_flags);
-
- /*
- @@ -1707,10 +1848,6 @@
- {
- activate_task(rq, p, en_flags);
- p->on_rq = TASK_ON_RQ_QUEUED;
- -
- - /* if a worker is waking up, notify workqueue */
- - if (p->flags & PF_WQ_WORKER)
- - wq_worker_waking_up(p, cpu_of(rq));
- }
-
- /*
- @@ -1937,8 +2074,27 @@
- */
- smp_mb__before_spinlock();
- raw_spin_lock_irqsave(&p->pi_lock, flags);
- - if (!(p->state & state))
- + if (!(p->state & state)) {
- + /*
- + * The task might be running due to a spinlock sleeper
- + * wakeup. Check the saved state and set it to running
- + * if the wakeup condition is true.
- + */
- + if (!(wake_flags & WF_LOCK_SLEEPER)) {
- + if (p->saved_state & state) {
- + p->saved_state = TASK_RUNNING;
- + success = 1;
- + }
- + }
- goto out;
- + }
- +
- + /*
- + * If this is a regular wakeup, then we can unconditionally
- + * clear the saved state of a "lock sleeper".
- + */
- + if (!(wake_flags & WF_LOCK_SLEEPER))
- + p->saved_state = TASK_RUNNING;
-
- trace_sched_waking(p);
-
- @@ -2030,52 +2186,6 @@
- }
-
- /**
- - * try_to_wake_up_local - try to wake up a local task with rq lock held
- - * @p: the thread to be awakened
- - *
- - * Put @p on the run-queue if it's not already there. The caller must
- - * ensure that this_rq() is locked, @p is bound to this_rq() and not
- - * the current task.
- - */
- -static void try_to_wake_up_local(struct task_struct *p)
- -{
- - struct rq *rq = task_rq(p);
- -
- - if (WARN_ON_ONCE(rq != this_rq()) ||
- - WARN_ON_ONCE(p == current))
- - return;
- -
- - lockdep_assert_held(&rq->lock);
- -
- - if (!raw_spin_trylock(&p->pi_lock)) {
- - /*
- - * This is OK, because current is on_cpu, which avoids it being
- - * picked for load-balance and preemption/IRQs are still
- - * disabled avoiding further scheduler activity on it and we've
- - * not yet picked a replacement task.
- - */
- - lockdep_unpin_lock(&rq->lock);
- - raw_spin_unlock(&rq->lock);
- - raw_spin_lock(&p->pi_lock);
- - raw_spin_lock(&rq->lock);
- - lockdep_pin_lock(&rq->lock);
- - }
- -
- - if (!(p->state & TASK_NORMAL))
- - goto out;
- -
- - trace_sched_waking(p);
- -
- - if (!task_on_rq_queued(p))
- - ttwu_activate(rq, p, ENQUEUE_WAKEUP);
- -
- - ttwu_do_wakeup(rq, p, 0);
- - ttwu_stat(p, smp_processor_id(), 0);
- -out:
- - raw_spin_unlock(&p->pi_lock);
- -}
- -
- -/**
- * wake_up_process - Wake up a specific process
- * @p: The process to be woken up.
- *
- @@ -2093,6 +2203,18 @@
- }
- EXPORT_SYMBOL(wake_up_process);
-
- +/**
- + * wake_up_lock_sleeper - Wake up a specific process blocked on a "sleeping lock"
- + * @p: The process to be woken up.
- + *
- + * Same as wake_up_process() above, but wake_flags=WF_LOCK_SLEEPER to indicate
- + * the nature of the wakeup.
- + */
- +int wake_up_lock_sleeper(struct task_struct *p)
- +{
- + return try_to_wake_up(p, TASK_ALL, WF_LOCK_SLEEPER);
- +}
- +
- int wake_up_state(struct task_struct *p, unsigned int state)
- {
- return try_to_wake_up(p, state, 0);
- @@ -2279,6 +2401,9 @@
- p->on_cpu = 0;
- #endif
- init_task_preempt_count(p);
- +#ifdef CONFIG_HAVE_PREEMPT_LAZY
- + task_thread_info(p)->preempt_lazy_count = 0;
- +#endif
- #ifdef CONFIG_SMP
- plist_node_init(&p->pushable_tasks, MAX_PRIO);
- RB_CLEAR_NODE(&p->pushable_dl_tasks);
- @@ -2603,8 +2728,12 @@
- finish_arch_post_lock_switch();
-
- fire_sched_in_preempt_notifiers(current);
- + /*
- + * We use mmdrop_delayed() here so we don't have to do the
- + * full __mmdrop() when we are the last user.
- + */
- if (mm)
- - mmdrop(mm);
- + mmdrop_delayed(mm);
- if (unlikely(prev_state == TASK_DEAD)) {
- if (prev->sched_class->task_dead)
- prev->sched_class->task_dead(prev);
- @@ -2935,16 +3064,6 @@
- }
- #endif
-
- -notrace unsigned long get_parent_ip(unsigned long addr)
- -{
- - if (in_lock_functions(addr)) {
- - addr = CALLER_ADDR2;
- - if (in_lock_functions(addr))
- - addr = CALLER_ADDR3;
- - }
- - return addr;
- -}
- -
- #if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \
- defined(CONFIG_PREEMPT_TRACER))
-
- @@ -2966,7 +3085,7 @@
- PREEMPT_MASK - 10);
- #endif
- if (preempt_count() == val) {
- - unsigned long ip = get_parent_ip(CALLER_ADDR1);
- + unsigned long ip = get_lock_parent_ip();
- #ifdef CONFIG_DEBUG_PREEMPT
- current->preempt_disable_ip = ip;
- #endif
- @@ -2993,7 +3112,7 @@
- #endif
-
- if (preempt_count() == val)
- - trace_preempt_on(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
- + trace_preempt_on(CALLER_ADDR0, get_lock_parent_ip());
- __preempt_count_sub(val);
- }
- EXPORT_SYMBOL(preempt_count_sub);
- @@ -3048,6 +3167,77 @@
- schedstat_inc(this_rq(), sched_count);
- }
-
- +#if defined(CONFIG_PREEMPT_RT_FULL) && defined(CONFIG_SMP)
- +
- +void migrate_disable(void)
- +{
- + struct task_struct *p = current;
- +
- + if (in_atomic() || irqs_disabled()) {
- +#ifdef CONFIG_SCHED_DEBUG
- + p->migrate_disable_atomic++;
- +#endif
- + return;
- + }
- +
- +#ifdef CONFIG_SCHED_DEBUG
- + if (unlikely(p->migrate_disable_atomic)) {
- + tracing_off();
- + WARN_ON_ONCE(1);
- + }
- +#endif
- +
- + if (p->migrate_disable) {
- + p->migrate_disable++;
- + return;
- + }
- +
- + preempt_disable();
- + preempt_lazy_disable();
- + pin_current_cpu();
- + p->migrate_disable = 1;
- + preempt_enable();
- +}
- +EXPORT_SYMBOL(migrate_disable);
- +
- +void migrate_enable(void)
- +{
- + struct task_struct *p = current;
- +
- + if (in_atomic() || irqs_disabled()) {
- +#ifdef CONFIG_SCHED_DEBUG
- + p->migrate_disable_atomic--;
- +#endif
- + return;
- + }
- +
- +#ifdef CONFIG_SCHED_DEBUG
- + if (unlikely(p->migrate_disable_atomic)) {
- + tracing_off();
- + WARN_ON_ONCE(1);
- + }
- +#endif
- + WARN_ON_ONCE(p->migrate_disable <= 0);
- +
- + if (p->migrate_disable > 1) {
- + p->migrate_disable--;
- + return;
- + }
- +
- + preempt_disable();
- + /*
- + * Clearing migrate_disable causes tsk_cpus_allowed to
- + * show the tasks original cpu affinity.
- + */
- + p->migrate_disable = 0;
- +
- + unpin_current_cpu();
- + preempt_enable();
- + preempt_lazy_enable();
- +}
- +EXPORT_SYMBOL(migrate_enable);
- +#endif
- +
- /*
- * Pick up the highest-prio task:
- */
- @@ -3172,19 +3362,6 @@
- } else {
- deactivate_task(rq, prev, DEQUEUE_SLEEP);
- prev->on_rq = 0;
- -
- - /*
- - * If a worker went to sleep, notify and ask workqueue
- - * whether it wants to wake up a task to maintain
- - * concurrency.
- - */
- - if (prev->flags & PF_WQ_WORKER) {
- - struct task_struct *to_wakeup;
- -
- - to_wakeup = wq_worker_sleeping(prev, cpu);
- - if (to_wakeup)
- - try_to_wake_up_local(to_wakeup);
- - }
- }
- switch_count = &prev->nvcsw;
- }
- @@ -3194,6 +3371,7 @@
-
- next = pick_next_task(rq, prev);
- clear_tsk_need_resched(prev);
- + clear_tsk_need_resched_lazy(prev);
- clear_preempt_need_resched();
- rq->clock_skip_update = 0;
-
- @@ -3215,9 +3393,20 @@
-
- static inline void sched_submit_work(struct task_struct *tsk)
- {
- - if (!tsk->state || tsk_is_pi_blocked(tsk))
- + if (!tsk->state)
- return;
- /*
- + * If a worker went to sleep, notify and ask workqueue whether
- + * it wants to wake up a task to maintain concurrency.
- + */
- + if (tsk->flags & PF_WQ_WORKER)
- + wq_worker_sleeping(tsk);
- +
- +
- + if (tsk_is_pi_blocked(tsk))
- + return;
- +
- + /*
- * If we are going to sleep and we have plugged IO queued,
- * make sure to submit it to avoid deadlocks.
- */
- @@ -3225,6 +3414,12 @@
- blk_schedule_flush_plug(tsk);
- }
-
- +static void sched_update_worker(struct task_struct *tsk)
- +{
- + if (tsk->flags & PF_WQ_WORKER)
- + wq_worker_running(tsk);
- +}
- +
- asmlinkage __visible void __sched schedule(void)
- {
- struct task_struct *tsk = current;
- @@ -3235,6 +3430,7 @@
- __schedule(false);
- sched_preempt_enable_no_resched();
- } while (need_resched());
- + sched_update_worker(tsk);
- }
- EXPORT_SYMBOL(schedule);
-
- @@ -3283,6 +3479,30 @@
- } while (need_resched());
- }
-
- +#ifdef CONFIG_PREEMPT_LAZY
- +/*
- + * If TIF_NEED_RESCHED is then we allow to be scheduled away since this is
- + * set by a RT task. Oterwise we try to avoid beeing scheduled out as long as
- + * preempt_lazy_count counter >0.
- + */
- +static __always_inline int preemptible_lazy(void)
- +{
- + if (test_thread_flag(TIF_NEED_RESCHED))
- + return 1;
- + if (current_thread_info()->preempt_lazy_count)
- + return 0;
- + return 1;
- +}
- +
- +#else
- +
- +static inline int preemptible_lazy(void)
- +{
- + return 1;
- +}
- +
- +#endif
- +
- #ifdef CONFIG_PREEMPT
- /*
- * this is the entry point to schedule() from in-kernel preemption
- @@ -3297,6 +3517,8 @@
- */
- if (likely(!preemptible()))
- return;
- + if (!preemptible_lazy())
- + return;
-
- preempt_schedule_common();
- }
- @@ -3323,6 +3545,8 @@
-
- if (likely(!preemptible()))
- return;
- + if (!preemptible_lazy())
- + return;
-
- do {
- preempt_disable_notrace();
- @@ -3332,7 +3556,16 @@
- * an infinite recursion.
- */
- prev_ctx = exception_enter();
- + /*
- + * The add/subtract must not be traced by the function
- + * tracer. But we still want to account for the
- + * preempt off latency tracer. Since the _notrace versions
- + * of add/subtract skip the accounting for latency tracer
- + * we must force it manually.
- + */
- + start_critical_timings();
- __schedule(true);
- + stop_critical_timings();
- exception_exit(prev_ctx);
-
- preempt_enable_no_resched_notrace();
- @@ -4676,6 +4909,7 @@
- }
- EXPORT_SYMBOL(__cond_resched_lock);
-
- +#ifndef CONFIG_PREEMPT_RT_FULL
- int __sched __cond_resched_softirq(void)
- {
- BUG_ON(!in_softirq());
- @@ -4689,6 +4923,7 @@
- return 0;
- }
- EXPORT_SYMBOL(__cond_resched_softirq);
- +#endif
-
- /**
- * yield - yield the current processor to other threads.
- @@ -5055,7 +5290,9 @@
-
- /* Set the preempt count _outside_ the spinlocks! */
- init_idle_preempt_count(idle, cpu);
- -
- +#ifdef CONFIG_HAVE_PREEMPT_LAZY
- + task_thread_info(idle)->preempt_lazy_count = 0;
- +#endif
- /*
- * The idle tasks have their own, simple scheduling class:
- */
- @@ -5196,6 +5433,8 @@
- #endif /* CONFIG_NUMA_BALANCING */
-
- #ifdef CONFIG_HOTPLUG_CPU
- +static DEFINE_PER_CPU(struct mm_struct *, idle_last_mm);
- +
- /*
- * Ensures that the idle task is using init_mm right before its cpu goes
- * offline.
- @@ -5210,7 +5449,11 @@
- switch_mm(mm, &init_mm, current);
- finish_arch_post_lock_switch();
- }
- - mmdrop(mm);
- + /*
- + * Defer the cleanup to an alive cpu. On RT we can neither
- + * call mmdrop() nor mmdrop_delayed() from here.
- + */
- + per_cpu(idle_last_mm, smp_processor_id()) = mm;
- }
-
- /*
- @@ -5583,6 +5826,10 @@
-
- case CPU_DEAD:
- calc_load_migrate(rq);
- + if (per_cpu(idle_last_mm, cpu)) {
- + mmdrop(per_cpu(idle_last_mm, cpu));
- + per_cpu(idle_last_mm, cpu) = NULL;
- + }
- break;
- #endif
- }
- @@ -7566,7 +7813,7 @@
- #ifdef CONFIG_DEBUG_ATOMIC_SLEEP
- static inline int preempt_count_equals(int preempt_offset)
- {
- - int nested = preempt_count() + rcu_preempt_depth();
- + int nested = preempt_count() + sched_rcu_preempt_depth();
-
- return (nested == preempt_offset);
- }
- diff -Nur linux-4.4.28.orig/kernel/sched/cpudeadline.c linux-4.4.28/kernel/sched/cpudeadline.c
- --- linux-4.4.28.orig/kernel/sched/cpudeadline.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/sched/cpudeadline.c 2016-11-01 21:26:58.784342796 +0100
- @@ -103,10 +103,10 @@
- const struct sched_dl_entity *dl_se = &p->dl;
-
- if (later_mask &&
- - cpumask_and(later_mask, cp->free_cpus, &p->cpus_allowed)) {
- + cpumask_and(later_mask, cp->free_cpus, tsk_cpus_allowed(p))) {
- best_cpu = cpumask_any(later_mask);
- goto out;
- - } else if (cpumask_test_cpu(cpudl_maximum(cp), &p->cpus_allowed) &&
- + } else if (cpumask_test_cpu(cpudl_maximum(cp), tsk_cpus_allowed(p)) &&
- dl_time_before(dl_se->deadline, cp->elements[0].dl)) {
- best_cpu = cpudl_maximum(cp);
- if (later_mask)
- diff -Nur linux-4.4.28.orig/kernel/sched/cpupri.c linux-4.4.28/kernel/sched/cpupri.c
- --- linux-4.4.28.orig/kernel/sched/cpupri.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/sched/cpupri.c 2016-11-01 21:26:58.784342796 +0100
- @@ -103,11 +103,11 @@
- if (skip)
- continue;
-
- - if (cpumask_any_and(&p->cpus_allowed, vec->mask) >= nr_cpu_ids)
- + if (cpumask_any_and(tsk_cpus_allowed(p), vec->mask) >= nr_cpu_ids)
- continue;
-
- if (lowest_mask) {
- - cpumask_and(lowest_mask, &p->cpus_allowed, vec->mask);
- + cpumask_and(lowest_mask, tsk_cpus_allowed(p), vec->mask);
-
- /*
- * We have to ensure that we have at least one bit
- diff -Nur linux-4.4.28.orig/kernel/sched/cputime.c linux-4.4.28/kernel/sched/cputime.c
- --- linux-4.4.28.orig/kernel/sched/cputime.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/sched/cputime.c 2016-11-01 21:26:58.788343053 +0100
- @@ -685,7 +685,7 @@
- {
- unsigned long long delta = vtime_delta(tsk);
-
- - WARN_ON_ONCE(tsk->vtime_snap_whence == VTIME_SLEEPING);
- + WARN_ON_ONCE(tsk->vtime_snap_whence == VTIME_INACTIVE);
- tsk->vtime_snap += delta;
-
- /* CHECKME: always safe to convert nsecs to cputime? */
- @@ -701,37 +701,37 @@
-
- void vtime_account_system(struct task_struct *tsk)
- {
- - write_seqlock(&tsk->vtime_seqlock);
- + write_seqcount_begin(&tsk->vtime_seqcount);
- __vtime_account_system(tsk);
- - write_sequnlock(&tsk->vtime_seqlock);
- + write_seqcount_end(&tsk->vtime_seqcount);
- }
-
- void vtime_gen_account_irq_exit(struct task_struct *tsk)
- {
- - write_seqlock(&tsk->vtime_seqlock);
- + write_seqcount_begin(&tsk->vtime_seqcount);
- __vtime_account_system(tsk);
- if (context_tracking_in_user())
- tsk->vtime_snap_whence = VTIME_USER;
- - write_sequnlock(&tsk->vtime_seqlock);
- + write_seqcount_end(&tsk->vtime_seqcount);
- }
-
- void vtime_account_user(struct task_struct *tsk)
- {
- cputime_t delta_cpu;
-
- - write_seqlock(&tsk->vtime_seqlock);
- + write_seqcount_begin(&tsk->vtime_seqcount);
- delta_cpu = get_vtime_delta(tsk);
- tsk->vtime_snap_whence = VTIME_SYS;
- account_user_time(tsk, delta_cpu, cputime_to_scaled(delta_cpu));
- - write_sequnlock(&tsk->vtime_seqlock);
- + write_seqcount_end(&tsk->vtime_seqcount);
- }
-
- void vtime_user_enter(struct task_struct *tsk)
- {
- - write_seqlock(&tsk->vtime_seqlock);
- + write_seqcount_begin(&tsk->vtime_seqcount);
- __vtime_account_system(tsk);
- tsk->vtime_snap_whence = VTIME_USER;
- - write_sequnlock(&tsk->vtime_seqlock);
- + write_seqcount_end(&tsk->vtime_seqcount);
- }
-
- void vtime_guest_enter(struct task_struct *tsk)
- @@ -743,19 +743,19 @@
- * synchronization against the reader (task_gtime())
- * that can thus safely catch up with a tickless delta.
- */
- - write_seqlock(&tsk->vtime_seqlock);
- + write_seqcount_begin(&tsk->vtime_seqcount);
- __vtime_account_system(tsk);
- current->flags |= PF_VCPU;
- - write_sequnlock(&tsk->vtime_seqlock);
- + write_seqcount_end(&tsk->vtime_seqcount);
- }
- EXPORT_SYMBOL_GPL(vtime_guest_enter);
-
- void vtime_guest_exit(struct task_struct *tsk)
- {
- - write_seqlock(&tsk->vtime_seqlock);
- + write_seqcount_begin(&tsk->vtime_seqcount);
- __vtime_account_system(tsk);
- current->flags &= ~PF_VCPU;
- - write_sequnlock(&tsk->vtime_seqlock);
- + write_seqcount_end(&tsk->vtime_seqcount);
- }
- EXPORT_SYMBOL_GPL(vtime_guest_exit);
-
- @@ -768,24 +768,26 @@
-
- void arch_vtime_task_switch(struct task_struct *prev)
- {
- - write_seqlock(&prev->vtime_seqlock);
- - prev->vtime_snap_whence = VTIME_SLEEPING;
- - write_sequnlock(&prev->vtime_seqlock);
- + write_seqcount_begin(&prev->vtime_seqcount);
- + prev->vtime_snap_whence = VTIME_INACTIVE;
- + write_seqcount_end(&prev->vtime_seqcount);
-
- - write_seqlock(¤t->vtime_seqlock);
- + write_seqcount_begin(¤t->vtime_seqcount);
- current->vtime_snap_whence = VTIME_SYS;
- current->vtime_snap = sched_clock_cpu(smp_processor_id());
- - write_sequnlock(¤t->vtime_seqlock);
- + write_seqcount_end(¤t->vtime_seqcount);
- }
-
- void vtime_init_idle(struct task_struct *t, int cpu)
- {
- unsigned long flags;
-
- - write_seqlock_irqsave(&t->vtime_seqlock, flags);
- + local_irq_save(flags);
- + write_seqcount_begin(&t->vtime_seqcount);
- t->vtime_snap_whence = VTIME_SYS;
- t->vtime_snap = sched_clock_cpu(cpu);
- - write_sequnlock_irqrestore(&t->vtime_seqlock, flags);
- + write_seqcount_end(&t->vtime_seqcount);
- + local_irq_restore(flags);
- }
-
- cputime_t task_gtime(struct task_struct *t)
- @@ -797,13 +799,13 @@
- return t->gtime;
-
- do {
- - seq = read_seqbegin(&t->vtime_seqlock);
- + seq = read_seqcount_begin(&t->vtime_seqcount);
-
- gtime = t->gtime;
- if (t->flags & PF_VCPU)
- gtime += vtime_delta(t);
-
- - } while (read_seqretry(&t->vtime_seqlock, seq));
- + } while (read_seqcount_retry(&t->vtime_seqcount, seq));
-
- return gtime;
- }
- @@ -826,7 +828,7 @@
- *udelta = 0;
- *sdelta = 0;
-
- - seq = read_seqbegin(&t->vtime_seqlock);
- + seq = read_seqcount_begin(&t->vtime_seqcount);
-
- if (u_dst)
- *u_dst = *u_src;
- @@ -834,7 +836,7 @@
- *s_dst = *s_src;
-
- /* Task is sleeping, nothing to add */
- - if (t->vtime_snap_whence == VTIME_SLEEPING ||
- + if (t->vtime_snap_whence == VTIME_INACTIVE ||
- is_idle_task(t))
- continue;
-
- @@ -850,7 +852,7 @@
- if (t->vtime_snap_whence == VTIME_SYS)
- *sdelta = delta;
- }
- - } while (read_seqretry(&t->vtime_seqlock, seq));
- + } while (read_seqcount_retry(&t->vtime_seqcount, seq));
- }
-
-
- diff -Nur linux-4.4.28.orig/kernel/sched/deadline.c linux-4.4.28/kernel/sched/deadline.c
- --- linux-4.4.28.orig/kernel/sched/deadline.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/sched/deadline.c 2016-11-01 21:26:58.788343053 +0100
- @@ -134,7 +134,7 @@
- {
- struct task_struct *p = dl_task_of(dl_se);
-
- - if (p->nr_cpus_allowed > 1)
- + if (tsk_nr_cpus_allowed(p) > 1)
- dl_rq->dl_nr_migratory++;
-
- update_dl_migration(dl_rq);
- @@ -144,7 +144,7 @@
- {
- struct task_struct *p = dl_task_of(dl_se);
-
- - if (p->nr_cpus_allowed > 1)
- + if (tsk_nr_cpus_allowed(p) > 1)
- dl_rq->dl_nr_migratory--;
-
- update_dl_migration(dl_rq);
- @@ -697,6 +697,7 @@
-
- hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
- timer->function = dl_task_timer;
- + timer->irqsafe = 1;
- }
-
- static
- @@ -989,7 +990,7 @@
-
- enqueue_dl_entity(&p->dl, pi_se, flags);
-
- - if (!task_current(rq, p) && p->nr_cpus_allowed > 1)
- + if (!task_current(rq, p) && tsk_nr_cpus_allowed(p) > 1)
- enqueue_pushable_dl_task(rq, p);
- }
-
- @@ -1067,9 +1068,9 @@
- * try to make it stay here, it might be important.
- */
- if (unlikely(dl_task(curr)) &&
- - (curr->nr_cpus_allowed < 2 ||
- + (tsk_nr_cpus_allowed(curr) < 2 ||
- !dl_entity_preempt(&p->dl, &curr->dl)) &&
- - (p->nr_cpus_allowed > 1)) {
- + (tsk_nr_cpus_allowed(p) > 1)) {
- int target = find_later_rq(p);
-
- if (target != -1 &&
- @@ -1090,7 +1091,7 @@
- * Current can't be migrated, useless to reschedule,
- * let's hope p can move out.
- */
- - if (rq->curr->nr_cpus_allowed == 1 ||
- + if (tsk_nr_cpus_allowed(rq->curr) == 1 ||
- cpudl_find(&rq->rd->cpudl, rq->curr, NULL) == -1)
- return;
-
- @@ -1098,7 +1099,7 @@
- * p is migratable, so let's not schedule it and
- * see if it is pushed or pulled somewhere else.
- */
- - if (p->nr_cpus_allowed != 1 &&
- + if (tsk_nr_cpus_allowed(p) != 1 &&
- cpudl_find(&rq->rd->cpudl, p, NULL) != -1)
- return;
-
- @@ -1212,7 +1213,7 @@
- {
- update_curr_dl(rq);
-
- - if (on_dl_rq(&p->dl) && p->nr_cpus_allowed > 1)
- + if (on_dl_rq(&p->dl) && tsk_nr_cpus_allowed(p) > 1)
- enqueue_pushable_dl_task(rq, p);
- }
-
- @@ -1335,7 +1336,7 @@
- if (unlikely(!later_mask))
- return -1;
-
- - if (task->nr_cpus_allowed == 1)
- + if (tsk_nr_cpus_allowed(task) == 1)
- return -1;
-
- /*
- @@ -1441,7 +1442,7 @@
- if (double_lock_balance(rq, later_rq)) {
- if (unlikely(task_rq(task) != rq ||
- !cpumask_test_cpu(later_rq->cpu,
- - &task->cpus_allowed) ||
- + tsk_cpus_allowed(task)) ||
- task_running(rq, task) ||
- !task_on_rq_queued(task))) {
- double_unlock_balance(rq, later_rq);
- @@ -1480,7 +1481,7 @@
-
- BUG_ON(rq->cpu != task_cpu(p));
- BUG_ON(task_current(rq, p));
- - BUG_ON(p->nr_cpus_allowed <= 1);
- + BUG_ON(tsk_nr_cpus_allowed(p) <= 1);
-
- BUG_ON(!task_on_rq_queued(p));
- BUG_ON(!dl_task(p));
- @@ -1519,7 +1520,7 @@
- */
- if (dl_task(rq->curr) &&
- dl_time_before(next_task->dl.deadline, rq->curr->dl.deadline) &&
- - rq->curr->nr_cpus_allowed > 1) {
- + tsk_nr_cpus_allowed(rq->curr) > 1) {
- resched_curr(rq);
- return 0;
- }
- @@ -1666,9 +1667,9 @@
- {
- if (!task_running(rq, p) &&
- !test_tsk_need_resched(rq->curr) &&
- - p->nr_cpus_allowed > 1 &&
- + tsk_nr_cpus_allowed(p) > 1 &&
- dl_task(rq->curr) &&
- - (rq->curr->nr_cpus_allowed < 2 ||
- + (tsk_nr_cpus_allowed(rq->curr) < 2 ||
- !dl_entity_preempt(&p->dl, &rq->curr->dl))) {
- push_dl_tasks(rq);
- }
- @@ -1769,7 +1770,7 @@
- {
- if (task_on_rq_queued(p) && rq->curr != p) {
- #ifdef CONFIG_SMP
- - if (p->nr_cpus_allowed > 1 && rq->dl.overloaded)
- + if (tsk_nr_cpus_allowed(p) > 1 && rq->dl.overloaded)
- queue_push_tasks(rq);
- #else
- if (dl_task(rq->curr))
- diff -Nur linux-4.4.28.orig/kernel/sched/debug.c linux-4.4.28/kernel/sched/debug.c
- --- linux-4.4.28.orig/kernel/sched/debug.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/sched/debug.c 2016-11-01 21:26:58.788343053 +0100
- @@ -251,6 +251,9 @@
- P(rt_throttled);
- PN(rt_time);
- PN(rt_runtime);
- +#ifdef CONFIG_SMP
- + P(rt_nr_migratory);
- +#endif
-
- #undef PN
- #undef P
- @@ -635,6 +638,10 @@
- #endif
- P(policy);
- P(prio);
- +#ifdef CONFIG_PREEMPT_RT_FULL
- + P(migrate_disable);
- +#endif
- + P(nr_cpus_allowed);
- #undef PN
- #undef __PN
- #undef P
- diff -Nur linux-4.4.28.orig/kernel/sched/fair.c linux-4.4.28/kernel/sched/fair.c
- --- linux-4.4.28.orig/kernel/sched/fair.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/sched/fair.c 2016-11-01 21:26:58.792343317 +0100
- @@ -3166,7 +3166,7 @@
- ideal_runtime = sched_slice(cfs_rq, curr);
- delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime;
- if (delta_exec > ideal_runtime) {
- - resched_curr(rq_of(cfs_rq));
- + resched_curr_lazy(rq_of(cfs_rq));
- /*
- * The current task ran long enough, ensure it doesn't get
- * re-elected due to buddy favours.
- @@ -3190,7 +3190,7 @@
- return;
-
- if (delta > ideal_runtime)
- - resched_curr(rq_of(cfs_rq));
- + resched_curr_lazy(rq_of(cfs_rq));
- }
-
- static void
- @@ -3330,7 +3330,7 @@
- * validating it and just reschedule.
- */
- if (queued) {
- - resched_curr(rq_of(cfs_rq));
- + resched_curr_lazy(rq_of(cfs_rq));
- return;
- }
- /*
- @@ -3512,7 +3512,7 @@
- * hierarchy can be throttled
- */
- if (!assign_cfs_rq_runtime(cfs_rq) && likely(cfs_rq->curr))
- - resched_curr(rq_of(cfs_rq));
- + resched_curr_lazy(rq_of(cfs_rq));
- }
-
- static __always_inline
- @@ -4124,7 +4124,7 @@
-
- if (delta < 0) {
- if (rq->curr == p)
- - resched_curr(rq);
- + resched_curr_lazy(rq);
- return;
- }
- hrtick_start(rq, delta);
- @@ -5213,7 +5213,7 @@
- return;
-
- preempt:
- - resched_curr(rq);
- + resched_curr_lazy(rq);
- /*
- * Only set the backward buddy when the current task is still
- * on the rq. This can happen when a wakeup gets interleaved
- @@ -7964,7 +7964,7 @@
- * 'current' within the tree based on its new key value.
- */
- swap(curr->vruntime, se->vruntime);
- - resched_curr(rq);
- + resched_curr_lazy(rq);
- }
-
- se->vruntime -= cfs_rq->min_vruntime;
- @@ -7989,7 +7989,7 @@
- */
- if (rq->curr == p) {
- if (p->prio > oldprio)
- - resched_curr(rq);
- + resched_curr_lazy(rq);
- } else
- check_preempt_curr(rq, p, 0);
- }
- diff -Nur linux-4.4.28.orig/kernel/sched/features.h linux-4.4.28/kernel/sched/features.h
- --- linux-4.4.28.orig/kernel/sched/features.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/sched/features.h 2016-11-01 21:26:58.792343317 +0100
- @@ -45,11 +45,19 @@
- */
- SCHED_FEAT(NONTASK_CAPACITY, true)
-
- +#ifdef CONFIG_PREEMPT_RT_FULL
- +SCHED_FEAT(TTWU_QUEUE, false)
- +# ifdef CONFIG_PREEMPT_LAZY
- +SCHED_FEAT(PREEMPT_LAZY, true)
- +# endif
- +#else
- +
- /*
- * Queue remote wakeups on the target CPU and process them
- * using the scheduler IPI. Reduces rq->lock contention/bounces.
- */
- SCHED_FEAT(TTWU_QUEUE, true)
- +#endif
-
- #ifdef HAVE_RT_PUSH_IPI
- /*
- diff -Nur linux-4.4.28.orig/kernel/sched/Makefile linux-4.4.28/kernel/sched/Makefile
- --- linux-4.4.28.orig/kernel/sched/Makefile 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/sched/Makefile 2016-11-01 21:26:58.780342543 +0100
- @@ -13,7 +13,7 @@
-
- obj-y += core.o loadavg.o clock.o cputime.o
- obj-y += idle_task.o fair.o rt.o deadline.o stop_task.o
- -obj-y += wait.o completion.o idle.o
- +obj-y += wait.o swait.o swork.o completion.o idle.o
- obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o
- obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o
- obj-$(CONFIG_SCHEDSTATS) += stats.o
- diff -Nur linux-4.4.28.orig/kernel/sched/rt.c linux-4.4.28/kernel/sched/rt.c
- --- linux-4.4.28.orig/kernel/sched/rt.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/sched/rt.c 2016-11-01 21:26:58.792343317 +0100
- @@ -47,6 +47,7 @@
-
- hrtimer_init(&rt_b->rt_period_timer,
- CLOCK_MONOTONIC, HRTIMER_MODE_REL);
- + rt_b->rt_period_timer.irqsafe = 1;
- rt_b->rt_period_timer.function = sched_rt_period_timer;
- }
-
- @@ -93,6 +94,7 @@
- rt_rq->push_cpu = nr_cpu_ids;
- raw_spin_lock_init(&rt_rq->push_lock);
- init_irq_work(&rt_rq->push_work, push_irq_work_func);
- + rt_rq->push_work.flags |= IRQ_WORK_HARD_IRQ;
- #endif
- #endif /* CONFIG_SMP */
- /* We start is dequeued state, because no RT tasks are queued */
- @@ -326,7 +328,7 @@
- rt_rq = &rq_of_rt_rq(rt_rq)->rt;
-
- rt_rq->rt_nr_total++;
- - if (p->nr_cpus_allowed > 1)
- + if (tsk_nr_cpus_allowed(p) > 1)
- rt_rq->rt_nr_migratory++;
-
- update_rt_migration(rt_rq);
- @@ -343,7 +345,7 @@
- rt_rq = &rq_of_rt_rq(rt_rq)->rt;
-
- rt_rq->rt_nr_total--;
- - if (p->nr_cpus_allowed > 1)
- + if (tsk_nr_cpus_allowed(p) > 1)
- rt_rq->rt_nr_migratory--;
-
- update_rt_migration(rt_rq);
- @@ -1262,7 +1264,7 @@
-
- enqueue_rt_entity(rt_se, flags & ENQUEUE_HEAD);
-
- - if (!task_current(rq, p) && p->nr_cpus_allowed > 1)
- + if (!task_current(rq, p) && tsk_nr_cpus_allowed(p) > 1)
- enqueue_pushable_task(rq, p);
- }
-
- @@ -1351,7 +1353,7 @@
- * will have to sort it out.
- */
- if (curr && unlikely(rt_task(curr)) &&
- - (curr->nr_cpus_allowed < 2 ||
- + (tsk_nr_cpus_allowed(curr) < 2 ||
- curr->prio <= p->prio)) {
- int target = find_lowest_rq(p);
-
- @@ -1375,7 +1377,7 @@
- * Current can't be migrated, useless to reschedule,
- * let's hope p can move out.
- */
- - if (rq->curr->nr_cpus_allowed == 1 ||
- + if (tsk_nr_cpus_allowed(rq->curr) == 1 ||
- !cpupri_find(&rq->rd->cpupri, rq->curr, NULL))
- return;
-
- @@ -1383,7 +1385,7 @@
- * p is migratable, so let's not schedule it and
- * see if it is pushed or pulled somewhere else.
- */
- - if (p->nr_cpus_allowed != 1
- + if (tsk_nr_cpus_allowed(p) != 1
- && cpupri_find(&rq->rd->cpupri, p, NULL))
- return;
-
- @@ -1517,7 +1519,7 @@
- * The previous task needs to be made eligible for pushing
- * if it is still active
- */
- - if (on_rt_rq(&p->rt) && p->nr_cpus_allowed > 1)
- + if (on_rt_rq(&p->rt) && tsk_nr_cpus_allowed(p) > 1)
- enqueue_pushable_task(rq, p);
- }
-
- @@ -1567,7 +1569,7 @@
- if (unlikely(!lowest_mask))
- return -1;
-
- - if (task->nr_cpus_allowed == 1)
- + if (tsk_nr_cpus_allowed(task) == 1)
- return -1; /* No other targets possible */
-
- if (!cpupri_find(&task_rq(task)->rd->cpupri, task, lowest_mask))
- @@ -1699,7 +1701,7 @@
-
- BUG_ON(rq->cpu != task_cpu(p));
- BUG_ON(task_current(rq, p));
- - BUG_ON(p->nr_cpus_allowed <= 1);
- + BUG_ON(tsk_nr_cpus_allowed(p) <= 1);
-
- BUG_ON(!task_on_rq_queued(p));
- BUG_ON(!rt_task(p));
- @@ -2059,9 +2061,9 @@
- {
- if (!task_running(rq, p) &&
- !test_tsk_need_resched(rq->curr) &&
- - p->nr_cpus_allowed > 1 &&
- + tsk_nr_cpus_allowed(p) > 1 &&
- (dl_task(rq->curr) || rt_task(rq->curr)) &&
- - (rq->curr->nr_cpus_allowed < 2 ||
- + (tsk_nr_cpus_allowed(rq->curr) < 2 ||
- rq->curr->prio <= p->prio))
- push_rt_tasks(rq);
- }
- @@ -2134,7 +2136,7 @@
- */
- if (task_on_rq_queued(p) && rq->curr != p) {
- #ifdef CONFIG_SMP
- - if (p->nr_cpus_allowed > 1 && rq->rt.overloaded)
- + if (tsk_nr_cpus_allowed(p) > 1 && rq->rt.overloaded)
- queue_push_tasks(rq);
- #else
- if (p->prio < rq->curr->prio)
- diff -Nur linux-4.4.28.orig/kernel/sched/sched.h linux-4.4.28/kernel/sched/sched.h
- --- linux-4.4.28.orig/kernel/sched/sched.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/sched/sched.h 2016-11-01 21:26:58.792343317 +0100
- @@ -1100,6 +1100,7 @@
- #define WF_SYNC 0x01 /* waker goes to sleep after wakeup */
- #define WF_FORK 0x02 /* child wakeup after fork */
- #define WF_MIGRATED 0x4 /* internal use, task got migrated */
- +#define WF_LOCK_SLEEPER 0x08 /* wakeup spinlock "sleeper" */
-
- /*
- * To aid in avoiding the subversion of "niceness" due to uneven distribution
- @@ -1299,6 +1300,15 @@
- extern void resched_curr(struct rq *rq);
- extern void resched_cpu(int cpu);
-
- +#ifdef CONFIG_PREEMPT_LAZY
- +extern void resched_curr_lazy(struct rq *rq);
- +#else
- +static inline void resched_curr_lazy(struct rq *rq)
- +{
- + resched_curr(rq);
- +}
- +#endif
- +
- extern struct rt_bandwidth def_rt_bandwidth;
- extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime);
-
- diff -Nur linux-4.4.28.orig/kernel/sched/swait.c linux-4.4.28/kernel/sched/swait.c
- --- linux-4.4.28.orig/kernel/sched/swait.c 1970-01-01 01:00:00.000000000 +0100
- +++ linux-4.4.28/kernel/sched/swait.c 2016-11-01 21:26:58.792343317 +0100
- @@ -0,0 +1,143 @@
- +#include <linux/sched.h>
- +#include <linux/swait.h>
- +#include <linux/suspend.h>
- +
- +void __init_swait_queue_head(struct swait_queue_head *q, const char *name,
- + struct lock_class_key *key)
- +{
- + raw_spin_lock_init(&q->lock);
- + lockdep_set_class_and_name(&q->lock, key, name);
- + INIT_LIST_HEAD(&q->task_list);
- +}
- +EXPORT_SYMBOL(__init_swait_queue_head);
- +
- +/*
- + * The thing about the wake_up_state() return value; I think we can ignore it.
- + *
- + * If for some reason it would return 0, that means the previously waiting
- + * task is already running, so it will observe condition true (or has already).
- + */
- +void swake_up_locked(struct swait_queue_head *q)
- +{
- + struct swait_queue *curr;
- +
- + if (list_empty(&q->task_list))
- + return;
- +
- + curr = list_first_entry(&q->task_list, typeof(*curr), task_list);
- + wake_up_process(curr->task);
- + list_del_init(&curr->task_list);
- +}
- +EXPORT_SYMBOL(swake_up_locked);
- +
- +void swake_up_all_locked(struct swait_queue_head *q)
- +{
- + struct swait_queue *curr;
- + int wakes = 0;
- +
- + while (!list_empty(&q->task_list)) {
- +
- + curr = list_first_entry(&q->task_list, typeof(*curr),
- + task_list);
- + wake_up_process(curr->task);
- + list_del_init(&curr->task_list);
- + wakes++;
- + }
- + if (pm_in_action)
- + return;
- + WARN(wakes > 2, "complate_all() with %d waiters\n", wakes);
- +}
- +EXPORT_SYMBOL(swake_up_all_locked);
- +
- +void swake_up(struct swait_queue_head *q)
- +{
- + unsigned long flags;
- +
- + if (!swait_active(q))
- + return;
- +
- + raw_spin_lock_irqsave(&q->lock, flags);
- + swake_up_locked(q);
- + raw_spin_unlock_irqrestore(&q->lock, flags);
- +}
- +EXPORT_SYMBOL(swake_up);
- +
- +/*
- + * Does not allow usage from IRQ disabled, since we must be able to
- + * release IRQs to guarantee bounded hold time.
- + */
- +void swake_up_all(struct swait_queue_head *q)
- +{
- + struct swait_queue *curr;
- + LIST_HEAD(tmp);
- +
- + if (!swait_active(q))
- + return;
- +
- + raw_spin_lock_irq(&q->lock);
- + list_splice_init(&q->task_list, &tmp);
- + while (!list_empty(&tmp)) {
- + curr = list_first_entry(&tmp, typeof(*curr), task_list);
- +
- + wake_up_state(curr->task, TASK_NORMAL);
- + list_del_init(&curr->task_list);
- +
- + if (list_empty(&tmp))
- + break;
- +
- + raw_spin_unlock_irq(&q->lock);
- + raw_spin_lock_irq(&q->lock);
- + }
- + raw_spin_unlock_irq(&q->lock);
- +}
- +EXPORT_SYMBOL(swake_up_all);
- +
- +void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait)
- +{
- + wait->task = current;
- + if (list_empty(&wait->task_list))
- + list_add(&wait->task_list, &q->task_list);
- +}
- +
- +void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int state)
- +{
- + unsigned long flags;
- +
- + raw_spin_lock_irqsave(&q->lock, flags);
- + __prepare_to_swait(q, wait);
- + set_current_state(state);
- + raw_spin_unlock_irqrestore(&q->lock, flags);
- +}
- +EXPORT_SYMBOL(prepare_to_swait);
- +
- +long prepare_to_swait_event(struct swait_queue_head *q, struct swait_queue *wait, int state)
- +{
- + if (signal_pending_state(state, current))
- + return -ERESTARTSYS;
- +
- + prepare_to_swait(q, wait, state);
- +
- + return 0;
- +}
- +EXPORT_SYMBOL(prepare_to_swait_event);
- +
- +void __finish_swait(struct swait_queue_head *q, struct swait_queue *wait)
- +{
- + __set_current_state(TASK_RUNNING);
- + if (!list_empty(&wait->task_list))
- + list_del_init(&wait->task_list);
- +}
- +
- +void finish_swait(struct swait_queue_head *q, struct swait_queue *wait)
- +{
- + unsigned long flags;
- +
- + __set_current_state(TASK_RUNNING);
- +
- + if (!list_empty_careful(&wait->task_list)) {
- + raw_spin_lock_irqsave(&q->lock, flags);
- + list_del_init(&wait->task_list);
- + raw_spin_unlock_irqrestore(&q->lock, flags);
- + }
- +}
- +EXPORT_SYMBOL(finish_swait);
- diff -Nur linux-4.4.28.orig/kernel/sched/swork.c linux-4.4.28/kernel/sched/swork.c
- --- linux-4.4.28.orig/kernel/sched/swork.c 1970-01-01 01:00:00.000000000 +0100
- +++ linux-4.4.28/kernel/sched/swork.c 2016-11-01 21:26:58.792343317 +0100
- @@ -0,0 +1,173 @@
- +/*
- + * Copyright (C) 2014 BMW Car IT GmbH, Daniel Wagner daniel.wagner@bmw-carit.de
- + *
- + * Provides a framework for enqueuing callbacks from irq context
- + * PREEMPT_RT_FULL safe. The callbacks are executed in kthread context.
- + */
- +
- +#include <linux/swait.h>
- +#include <linux/swork.h>
- +#include <linux/kthread.h>
- +#include <linux/slab.h>
- +#include <linux/spinlock.h>
- +#include <linux/export.h>
- +
- +#define SWORK_EVENT_PENDING (1 << 0)
- +
- +static DEFINE_MUTEX(worker_mutex);
- +static struct sworker *glob_worker;
- +
- +struct sworker {
- + struct list_head events;
- + struct swait_queue_head wq;
- +
- + raw_spinlock_t lock;
- +
- + struct task_struct *task;
- + int refs;
- +};
- +
- +static bool swork_readable(struct sworker *worker)
- +{
- + bool r;
- +
- + if (kthread_should_stop())
- + return true;
- +
- + raw_spin_lock_irq(&worker->lock);
- + r = !list_empty(&worker->events);
- + raw_spin_unlock_irq(&worker->lock);
- +
- + return r;
- +}
- +
- +static int swork_kthread(void *arg)
- +{
- + struct sworker *worker = arg;
- +
- + for (;;) {
- + swait_event_interruptible(worker->wq,
- + swork_readable(worker));
- + if (kthread_should_stop())
- + break;
- +
- + raw_spin_lock_irq(&worker->lock);
- + while (!list_empty(&worker->events)) {
- + struct swork_event *sev;
- +
- + sev = list_first_entry(&worker->events,
- + struct swork_event, item);
- + list_del(&sev->item);
- + raw_spin_unlock_irq(&worker->lock);
- +
- + WARN_ON_ONCE(!test_and_clear_bit(SWORK_EVENT_PENDING,
- + &sev->flags));
- + sev->func(sev);
- + raw_spin_lock_irq(&worker->lock);
- + }
- + raw_spin_unlock_irq(&worker->lock);
- + }
- + return 0;
- +}
- +
- +static struct sworker *swork_create(void)
- +{
- + struct sworker *worker;
- +
- + worker = kzalloc(sizeof(*worker), GFP_KERNEL);
- + if (!worker)
- + return ERR_PTR(-ENOMEM);
- +
- + INIT_LIST_HEAD(&worker->events);
- + raw_spin_lock_init(&worker->lock);
- + init_swait_queue_head(&worker->wq);
- +
- + worker->task = kthread_run(swork_kthread, worker, "kswork");
- + if (IS_ERR(worker->task)) {
- + kfree(worker);
- + return ERR_PTR(-ENOMEM);
- + }
- +
- + return worker;
- +}
- +
- +static void swork_destroy(struct sworker *worker)
- +{
- + kthread_stop(worker->task);
- +
- + WARN_ON(!list_empty(&worker->events));
- + kfree(worker);
- +}
- +
- +/**
- + * swork_queue - queue swork
- + *
- + * Returns %false if @work was already on a queue, %true otherwise.
- + *
- + * The work is queued and processed on a random CPU
- + */
- +bool swork_queue(struct swork_event *sev)
- +{
- + unsigned long flags;
- +
- + if (test_and_set_bit(SWORK_EVENT_PENDING, &sev->flags))
- + return false;
- +
- + raw_spin_lock_irqsave(&glob_worker->lock, flags);
- + list_add_tail(&sev->item, &glob_worker->events);
- + raw_spin_unlock_irqrestore(&glob_worker->lock, flags);
- +
- + swake_up(&glob_worker->wq);
- + return true;
- +}
- +EXPORT_SYMBOL_GPL(swork_queue);
- +
- +/**
- + * swork_get - get an instance of the sworker
- + *
- + * Returns an negative error code if the initialization if the worker did not
- + * work, %0 otherwise.
- + *
- + */
- +int swork_get(void)
- +{
- + struct sworker *worker;
- +
- + mutex_lock(&worker_mutex);
- + if (!glob_worker) {
- + worker = swork_create();
- + if (IS_ERR(worker)) {
- + mutex_unlock(&worker_mutex);
- + return -ENOMEM;
- + }
- +
- + glob_worker = worker;
- + }
- +
- + glob_worker->refs++;
- + mutex_unlock(&worker_mutex);
- +
- + return 0;
- +}
- +EXPORT_SYMBOL_GPL(swork_get);
- +
- +/**
- + * swork_put - puts an instance of the sworker
- + *
- + * Will destroy the sworker thread. This function must not be called until all
- + * queued events have been completed.
- + */
- +void swork_put(void)
- +{
- + mutex_lock(&worker_mutex);
- +
- + glob_worker->refs--;
- + if (glob_worker->refs > 0)
- + goto out;
- +
- + swork_destroy(glob_worker);
- + glob_worker = NULL;
- +out:
- + mutex_unlock(&worker_mutex);
- +}
- +EXPORT_SYMBOL_GPL(swork_put);
- diff -Nur linux-4.4.28.orig/kernel/signal.c linux-4.4.28/kernel/signal.c
- --- linux-4.4.28.orig/kernel/signal.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/signal.c 2016-11-01 21:26:58.796343570 +0100
- @@ -14,6 +14,7 @@
- #include <linux/export.h>
- #include <linux/init.h>
- #include <linux/sched.h>
- +#include <linux/sched/rt.h>
- #include <linux/fs.h>
- #include <linux/tty.h>
- #include <linux/binfmts.h>
- @@ -352,13 +353,30 @@
- return false;
- }
-
- +static inline struct sigqueue *get_task_cache(struct task_struct *t)
- +{
- + struct sigqueue *q = t->sigqueue_cache;
- +
- + if (cmpxchg(&t->sigqueue_cache, q, NULL) != q)
- + return NULL;
- + return q;
- +}
- +
- +static inline int put_task_cache(struct task_struct *t, struct sigqueue *q)
- +{
- + if (cmpxchg(&t->sigqueue_cache, NULL, q) == NULL)
- + return 0;
- + return 1;
- +}
- +
- /*
- * allocate a new signal queue record
- * - this may be called without locks if and only if t == current, otherwise an
- * appropriate lock must be held to stop the target task from exiting
- */
- static struct sigqueue *
- -__sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimit)
- +__sigqueue_do_alloc(int sig, struct task_struct *t, gfp_t flags,
- + int override_rlimit, int fromslab)
- {
- struct sigqueue *q = NULL;
- struct user_struct *user;
- @@ -375,7 +393,10 @@
- if (override_rlimit ||
- atomic_read(&user->sigpending) <=
- task_rlimit(t, RLIMIT_SIGPENDING)) {
- - q = kmem_cache_alloc(sigqueue_cachep, flags);
- + if (!fromslab)
- + q = get_task_cache(t);
- + if (!q)
- + q = kmem_cache_alloc(sigqueue_cachep, flags);
- } else {
- print_dropped_signal(sig);
- }
- @@ -392,6 +413,13 @@
- return q;
- }
-
- +static struct sigqueue *
- +__sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags,
- + int override_rlimit)
- +{
- + return __sigqueue_do_alloc(sig, t, flags, override_rlimit, 0);
- +}
- +
- static void __sigqueue_free(struct sigqueue *q)
- {
- if (q->flags & SIGQUEUE_PREALLOC)
- @@ -401,6 +429,21 @@
- kmem_cache_free(sigqueue_cachep, q);
- }
-
- +static void sigqueue_free_current(struct sigqueue *q)
- +{
- + struct user_struct *up;
- +
- + if (q->flags & SIGQUEUE_PREALLOC)
- + return;
- +
- + up = q->user;
- + if (rt_prio(current->normal_prio) && !put_task_cache(current, q)) {
- + atomic_dec(&up->sigpending);
- + free_uid(up);
- + } else
- + __sigqueue_free(q);
- +}
- +
- void flush_sigqueue(struct sigpending *queue)
- {
- struct sigqueue *q;
- @@ -414,6 +457,21 @@
- }
-
- /*
- + * Called from __exit_signal. Flush tsk->pending and
- + * tsk->sigqueue_cache
- + */
- +void flush_task_sigqueue(struct task_struct *tsk)
- +{
- + struct sigqueue *q;
- +
- + flush_sigqueue(&tsk->pending);
- +
- + q = get_task_cache(tsk);
- + if (q)
- + kmem_cache_free(sigqueue_cachep, q);
- +}
- +
- +/*
- * Flush all pending signals for this kthread.
- */
- void flush_signals(struct task_struct *t)
- @@ -525,7 +583,7 @@
- still_pending:
- list_del_init(&first->list);
- copy_siginfo(info, &first->info);
- - __sigqueue_free(first);
- + sigqueue_free_current(first);
- } else {
- /*
- * Ok, it wasn't in the queue. This must be
- @@ -560,6 +618,8 @@
- {
- int signr;
-
- + WARN_ON_ONCE(tsk != current);
- +
- /* We only dequeue private signals from ourselves, we don't let
- * signalfd steal them
- */
- @@ -1156,8 +1216,8 @@
- * We don't want to have recursive SIGSEGV's etc, for example,
- * that is why we also clear SIGNAL_UNKILLABLE.
- */
- -int
- -force_sig_info(int sig, struct siginfo *info, struct task_struct *t)
- +static int
- +do_force_sig_info(int sig, struct siginfo *info, struct task_struct *t)
- {
- unsigned long int flags;
- int ret, blocked, ignored;
- @@ -1182,6 +1242,39 @@
- return ret;
- }
-
- +int force_sig_info(int sig, struct siginfo *info, struct task_struct *t)
- +{
- +/*
- + * On some archs, PREEMPT_RT has to delay sending a signal from a trap
- + * since it can not enable preemption, and the signal code's spin_locks
- + * turn into mutexes. Instead, it must set TIF_NOTIFY_RESUME which will
- + * send the signal on exit of the trap.
- + */
- +#ifdef ARCH_RT_DELAYS_SIGNAL_SEND
- + if (in_atomic()) {
- + if (WARN_ON_ONCE(t != current))
- + return 0;
- + if (WARN_ON_ONCE(t->forced_info.si_signo))
- + return 0;
- +
- + if (is_si_special(info)) {
- + WARN_ON_ONCE(info != SEND_SIG_PRIV);
- + t->forced_info.si_signo = sig;
- + t->forced_info.si_errno = 0;
- + t->forced_info.si_code = SI_KERNEL;
- + t->forced_info.si_pid = 0;
- + t->forced_info.si_uid = 0;
- + } else {
- + t->forced_info = *info;
- + }
- +
- + set_tsk_thread_flag(t, TIF_NOTIFY_RESUME);
- + return 0;
- + }
- +#endif
- + return do_force_sig_info(sig, info, t);
- +}
- +
- /*
- * Nuke all other threads in the group.
- */
- @@ -1216,12 +1309,12 @@
- * Disable interrupts early to avoid deadlocks.
- * See rcu_read_unlock() comment header for details.
- */
- - local_irq_save(*flags);
- + local_irq_save_nort(*flags);
- rcu_read_lock();
- sighand = rcu_dereference(tsk->sighand);
- if (unlikely(sighand == NULL)) {
- rcu_read_unlock();
- - local_irq_restore(*flags);
- + local_irq_restore_nort(*flags);
- break;
- }
- /*
- @@ -1242,7 +1335,7 @@
- }
- spin_unlock(&sighand->siglock);
- rcu_read_unlock();
- - local_irq_restore(*flags);
- + local_irq_restore_nort(*flags);
- }
-
- return sighand;
- @@ -1485,7 +1578,8 @@
- */
- struct sigqueue *sigqueue_alloc(void)
- {
- - struct sigqueue *q = __sigqueue_alloc(-1, current, GFP_KERNEL, 0);
- + /* Preallocated sigqueue objects always from the slabcache ! */
- + struct sigqueue *q = __sigqueue_do_alloc(-1, current, GFP_KERNEL, 0, 1);
-
- if (q)
- q->flags |= SIGQUEUE_PREALLOC;
- @@ -1846,15 +1940,7 @@
- if (gstop_done && ptrace_reparented(current))
- do_notify_parent_cldstop(current, false, why);
-
- - /*
- - * Don't want to allow preemption here, because
- - * sys_ptrace() needs this task to be inactive.
- - *
- - * XXX: implement read_unlock_no_resched().
- - */
- - preempt_disable();
- read_unlock(&tasklist_lock);
- - preempt_enable_no_resched();
- freezable_schedule();
- } else {
- /*
- diff -Nur linux-4.4.28.orig/kernel/softirq.c linux-4.4.28/kernel/softirq.c
- --- linux-4.4.28.orig/kernel/softirq.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/softirq.c 2016-11-01 21:26:58.796343570 +0100
- @@ -21,10 +21,12 @@
- #include <linux/freezer.h>
- #include <linux/kthread.h>
- #include <linux/rcupdate.h>
- +#include <linux/delay.h>
- #include <linux/ftrace.h>
- #include <linux/smp.h>
- #include <linux/smpboot.h>
- #include <linux/tick.h>
- +#include <linux/locallock.h>
- #include <linux/irq.h>
-
- #define CREATE_TRACE_POINTS
- @@ -56,12 +58,108 @@
- static struct softirq_action softirq_vec[NR_SOFTIRQS] __cacheline_aligned_in_smp;
-
- DEFINE_PER_CPU(struct task_struct *, ksoftirqd);
- +#ifdef CONFIG_PREEMPT_RT_FULL
- +#define TIMER_SOFTIRQS ((1 << TIMER_SOFTIRQ) | (1 << HRTIMER_SOFTIRQ))
- +DEFINE_PER_CPU(struct task_struct *, ktimer_softirqd);
- +#endif
-
- const char * const softirq_to_name[NR_SOFTIRQS] = {
- "HI", "TIMER", "NET_TX", "NET_RX", "BLOCK", "BLOCK_IOPOLL",
- "TASKLET", "SCHED", "HRTIMER", "RCU"
- };
-
- +#ifdef CONFIG_NO_HZ_COMMON
- +# ifdef CONFIG_PREEMPT_RT_FULL
- +
- +struct softirq_runner {
- + struct task_struct *runner[NR_SOFTIRQS];
- +};
- +
- +static DEFINE_PER_CPU(struct softirq_runner, softirq_runners);
- +
- +static inline void softirq_set_runner(unsigned int sirq)
- +{
- + struct softirq_runner *sr = this_cpu_ptr(&softirq_runners);
- +
- + sr->runner[sirq] = current;
- +}
- +
- +static inline void softirq_clr_runner(unsigned int sirq)
- +{
- + struct softirq_runner *sr = this_cpu_ptr(&softirq_runners);
- +
- + sr->runner[sirq] = NULL;
- +}
- +
- +/*
- + * On preempt-rt a softirq running context might be blocked on a
- + * lock. There might be no other runnable task on this CPU because the
- + * lock owner runs on some other CPU. So we have to go into idle with
- + * the pending bit set. Therefor we need to check this otherwise we
- + * warn about false positives which confuses users and defeats the
- + * whole purpose of this test.
- + *
- + * This code is called with interrupts disabled.
- + */
- +void softirq_check_pending_idle(void)
- +{
- + static int rate_limit;
- + struct softirq_runner *sr = this_cpu_ptr(&softirq_runners);
- + u32 warnpending;
- + int i;
- +
- + if (rate_limit >= 10)
- + return;
- +
- + warnpending = local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK;
- + for (i = 0; i < NR_SOFTIRQS; i++) {
- + struct task_struct *tsk = sr->runner[i];
- +
- + /*
- + * The wakeup code in rtmutex.c wakes up the task
- + * _before_ it sets pi_blocked_on to NULL under
- + * tsk->pi_lock. So we need to check for both: state
- + * and pi_blocked_on.
- + */
- + if (tsk) {
- + raw_spin_lock(&tsk->pi_lock);
- + if (tsk->pi_blocked_on || tsk->state == TASK_RUNNING) {
- + /* Clear all bits pending in that task */
- + warnpending &= ~(tsk->softirqs_raised);
- + warnpending &= ~(1 << i);
- + }
- + raw_spin_unlock(&tsk->pi_lock);
- + }
- + }
- +
- + if (warnpending) {
- + printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n",
- + warnpending);
- + rate_limit++;
- + }
- +}
- +# else
- +/*
- + * On !PREEMPT_RT we just printk rate limited:
- + */
- +void softirq_check_pending_idle(void)
- +{
- + static int rate_limit;
- +
- + if (rate_limit < 10 &&
- + (local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK)) {
- + printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n",
- + local_softirq_pending());
- + rate_limit++;
- + }
- +}
- +# endif
- +
- +#else /* !CONFIG_NO_HZ_COMMON */
- +static inline void softirq_set_runner(unsigned int sirq) { }
- +static inline void softirq_clr_runner(unsigned int sirq) { }
- +#endif
- +
- /*
- * we cannot loop indefinitely here to avoid userspace starvation,
- * but we also don't want to introduce a worst case 1/HZ latency
- @@ -77,6 +175,79 @@
- wake_up_process(tsk);
- }
-
- +#ifdef CONFIG_PREEMPT_RT_FULL
- +static void wakeup_timer_softirqd(void)
- +{
- + /* Interrupts are disabled: no need to stop preemption */
- + struct task_struct *tsk = __this_cpu_read(ktimer_softirqd);
- +
- + if (tsk && tsk->state != TASK_RUNNING)
- + wake_up_process(tsk);
- +}
- +#endif
- +
- +static void handle_softirq(unsigned int vec_nr)
- +{
- + struct softirq_action *h = softirq_vec + vec_nr;
- + int prev_count;
- +
- + prev_count = preempt_count();
- +
- + kstat_incr_softirqs_this_cpu(vec_nr);
- +
- + trace_softirq_entry(vec_nr);
- + h->action(h);
- + trace_softirq_exit(vec_nr);
- + if (unlikely(prev_count != preempt_count())) {
- + pr_err("huh, entered softirq %u %s %p with preempt_count %08x, exited with %08x?\n",
- + vec_nr, softirq_to_name[vec_nr], h->action,
- + prev_count, preempt_count());
- + preempt_count_set(prev_count);
- + }
- +}
- +
- +#ifndef CONFIG_PREEMPT_RT_FULL
- +static inline int ksoftirqd_softirq_pending(void)
- +{
- + return local_softirq_pending();
- +}
- +
- +static void handle_pending_softirqs(u32 pending)
- +{
- + struct softirq_action *h = softirq_vec;
- + int softirq_bit;
- +
- + local_irq_enable();
- +
- + h = softirq_vec;
- +
- + while ((softirq_bit = ffs(pending))) {
- + unsigned int vec_nr;
- +
- + h += softirq_bit - 1;
- + vec_nr = h - softirq_vec;
- + handle_softirq(vec_nr);
- +
- + h++;
- + pending >>= softirq_bit;
- + }
- +
- + rcu_bh_qs();
- + local_irq_disable();
- +}
- +
- +static void run_ksoftirqd(unsigned int cpu)
- +{
- + local_irq_disable();
- + if (ksoftirqd_softirq_pending()) {
- + __do_softirq();
- + local_irq_enable();
- + cond_resched_rcu_qs();
- + return;
- + }
- + local_irq_enable();
- +}
- +
- /*
- * preempt_count and SOFTIRQ_OFFSET usage:
- * - preempt_count is changed by SOFTIRQ_OFFSET on entering or leaving
- @@ -116,9 +287,9 @@
-
- if (preempt_count() == cnt) {
- #ifdef CONFIG_DEBUG_PREEMPT
- - current->preempt_disable_ip = get_parent_ip(CALLER_ADDR1);
- + current->preempt_disable_ip = get_lock_parent_ip();
- #endif
- - trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
- + trace_preempt_off(CALLER_ADDR0, get_lock_parent_ip());
- }
- }
- EXPORT_SYMBOL(__local_bh_disable_ip);
- @@ -232,10 +403,8 @@
- unsigned long end = jiffies + MAX_SOFTIRQ_TIME;
- unsigned long old_flags = current->flags;
- int max_restart = MAX_SOFTIRQ_RESTART;
- - struct softirq_action *h;
- bool in_hardirq;
- __u32 pending;
- - int softirq_bit;
-
- /*
- * Mask out PF_MEMALLOC s current task context is borrowed for the
- @@ -254,36 +423,7 @@
- /* Reset the pending bitmask before enabling irqs */
- set_softirq_pending(0);
-
- - local_irq_enable();
- -
- - h = softirq_vec;
- -
- - while ((softirq_bit = ffs(pending))) {
- - unsigned int vec_nr;
- - int prev_count;
- -
- - h += softirq_bit - 1;
- -
- - vec_nr = h - softirq_vec;
- - prev_count = preempt_count();
- -
- - kstat_incr_softirqs_this_cpu(vec_nr);
- -
- - trace_softirq_entry(vec_nr);
- - h->action(h);
- - trace_softirq_exit(vec_nr);
- - if (unlikely(prev_count != preempt_count())) {
- - pr_err("huh, entered softirq %u %s %p with preempt_count %08x, exited with %08x?\n",
- - vec_nr, softirq_to_name[vec_nr], h->action,
- - prev_count, preempt_count());
- - preempt_count_set(prev_count);
- - }
- - h++;
- - pending >>= softirq_bit;
- - }
- -
- - rcu_bh_qs();
- - local_irq_disable();
- + handle_pending_softirqs(pending);
-
- pending = local_softirq_pending();
- if (pending) {
- @@ -320,6 +460,310 @@
- }
-
- /*
- + * This function must run with irqs disabled!
- + */
- +void raise_softirq_irqoff(unsigned int nr)
- +{
- + __raise_softirq_irqoff(nr);
- +
- + /*
- + * If we're in an interrupt or softirq, we're done
- + * (this also catches softirq-disabled code). We will
- + * actually run the softirq once we return from
- + * the irq or softirq.
- + *
- + * Otherwise we wake up ksoftirqd to make sure we
- + * schedule the softirq soon.
- + */
- + if (!in_interrupt())
- + wakeup_softirqd();
- +}
- +
- +void __raise_softirq_irqoff(unsigned int nr)
- +{
- + trace_softirq_raise(nr);
- + or_softirq_pending(1UL << nr);
- +}
- +
- +static inline void local_bh_disable_nort(void) { local_bh_disable(); }
- +static inline void _local_bh_enable_nort(void) { _local_bh_enable(); }
- +static void ksoftirqd_set_sched_params(unsigned int cpu) { }
- +
- +#else /* !PREEMPT_RT_FULL */
- +
- +/*
- + * On RT we serialize softirq execution with a cpu local lock per softirq
- + */
- +static DEFINE_PER_CPU(struct local_irq_lock [NR_SOFTIRQS], local_softirq_locks);
- +
- +void __init softirq_early_init(void)
- +{
- + int i;
- +
- + for (i = 0; i < NR_SOFTIRQS; i++)
- + local_irq_lock_init(local_softirq_locks[i]);
- +}
- +
- +static void lock_softirq(int which)
- +{
- + local_lock(local_softirq_locks[which]);
- +}
- +
- +static void unlock_softirq(int which)
- +{
- + local_unlock(local_softirq_locks[which]);
- +}
- +
- +static void do_single_softirq(int which)
- +{
- + unsigned long old_flags = current->flags;
- +
- + current->flags &= ~PF_MEMALLOC;
- + vtime_account_irq_enter(current);
- + current->flags |= PF_IN_SOFTIRQ;
- + lockdep_softirq_enter();
- + local_irq_enable();
- + handle_softirq(which);
- + local_irq_disable();
- + lockdep_softirq_exit();
- + current->flags &= ~PF_IN_SOFTIRQ;
- + vtime_account_irq_enter(current);
- + tsk_restore_flags(current, old_flags, PF_MEMALLOC);
- +}
- +
- +/*
- + * Called with interrupts disabled. Process softirqs which were raised
- + * in current context (or on behalf of ksoftirqd).
- + */
- +static void do_current_softirqs(void)
- +{
- + while (current->softirqs_raised) {
- + int i = __ffs(current->softirqs_raised);
- + unsigned int pending, mask = (1U << i);
- +
- + current->softirqs_raised &= ~mask;
- + local_irq_enable();
- +
- + /*
- + * If the lock is contended, we boost the owner to
- + * process the softirq or leave the critical section
- + * now.
- + */
- + lock_softirq(i);
- + local_irq_disable();
- + softirq_set_runner(i);
- + /*
- + * Check with the local_softirq_pending() bits,
- + * whether we need to process this still or if someone
- + * else took care of it.
- + */
- + pending = local_softirq_pending();
- + if (pending & mask) {
- + set_softirq_pending(pending & ~mask);
- + do_single_softirq(i);
- + }
- + softirq_clr_runner(i);
- + WARN_ON(current->softirq_nestcnt != 1);
- + local_irq_enable();
- + unlock_softirq(i);
- + local_irq_disable();
- + }
- +}
- +
- +void __local_bh_disable(void)
- +{
- + if (++current->softirq_nestcnt == 1)
- + migrate_disable();
- +}
- +EXPORT_SYMBOL(__local_bh_disable);
- +
- +void __local_bh_enable(void)
- +{
- + if (WARN_ON(current->softirq_nestcnt == 0))
- + return;
- +
- + local_irq_disable();
- + if (current->softirq_nestcnt == 1 && current->softirqs_raised)
- + do_current_softirqs();
- + local_irq_enable();
- +
- + if (--current->softirq_nestcnt == 0)
- + migrate_enable();
- +}
- +EXPORT_SYMBOL(__local_bh_enable);
- +
- +void _local_bh_enable(void)
- +{
- + if (WARN_ON(current->softirq_nestcnt == 0))
- + return;
- + if (--current->softirq_nestcnt == 0)
- + migrate_enable();
- +}
- +EXPORT_SYMBOL(_local_bh_enable);
- +
- +int in_serving_softirq(void)
- +{
- + return current->flags & PF_IN_SOFTIRQ;
- +}
- +EXPORT_SYMBOL(in_serving_softirq);
- +
- +/* Called with preemption disabled */
- +static void run_ksoftirqd(unsigned int cpu)
- +{
- + local_irq_disable();
- + current->softirq_nestcnt++;
- +
- + do_current_softirqs();
- + current->softirq_nestcnt--;
- + local_irq_enable();
- + cond_resched_rcu_qs();
- +}
- +
- +/*
- + * Called from netif_rx_ni(). Preemption enabled, but migration
- + * disabled. So the cpu can't go away under us.
- + */
- +void thread_do_softirq(void)
- +{
- + if (!in_serving_softirq() && current->softirqs_raised) {
- + current->softirq_nestcnt++;
- + do_current_softirqs();
- + current->softirq_nestcnt--;
- + }
- +}
- +
- +static void do_raise_softirq_irqoff(unsigned int nr)
- +{
- + unsigned int mask;
- +
- + mask = 1UL << nr;
- +
- + trace_softirq_raise(nr);
- + or_softirq_pending(mask);
- +
- + /*
- + * If we are not in a hard interrupt and inside a bh disabled
- + * region, we simply raise the flag on current. local_bh_enable()
- + * will make sure that the softirq is executed. Otherwise we
- + * delegate it to ksoftirqd.
- + */
- + if (!in_irq() && current->softirq_nestcnt)
- + current->softirqs_raised |= mask;
- + else if (!__this_cpu_read(ksoftirqd) || !__this_cpu_read(ktimer_softirqd))
- + return;
- +
- + if (mask & TIMER_SOFTIRQS)
- + __this_cpu_read(ktimer_softirqd)->softirqs_raised |= mask;
- + else
- + __this_cpu_read(ksoftirqd)->softirqs_raised |= mask;
- +}
- +
- +static void wakeup_proper_softirq(unsigned int nr)
- +{
- + if ((1UL << nr) & TIMER_SOFTIRQS)
- + wakeup_timer_softirqd();
- + else
- + wakeup_softirqd();
- +}
- +
- +
- +void __raise_softirq_irqoff(unsigned int nr)
- +{
- + do_raise_softirq_irqoff(nr);
- + if (!in_irq() && !current->softirq_nestcnt)
- + wakeup_proper_softirq(nr);
- +}
- +
- +/*
- + * Same as __raise_softirq_irqoff() but will process them in ksoftirqd
- + */
- +void __raise_softirq_irqoff_ksoft(unsigned int nr)
- +{
- + unsigned int mask;
- +
- + if (WARN_ON_ONCE(!__this_cpu_read(ksoftirqd) ||
- + !__this_cpu_read(ktimer_softirqd)))
- + return;
- + mask = 1UL << nr;
- +
- + trace_softirq_raise(nr);
- + or_softirq_pending(mask);
- + if (mask & TIMER_SOFTIRQS)
- + __this_cpu_read(ktimer_softirqd)->softirqs_raised |= mask;
- + else
- + __this_cpu_read(ksoftirqd)->softirqs_raised |= mask;
- + wakeup_proper_softirq(nr);
- +}
- +
- +/*
- + * This function must run with irqs disabled!
- + */
- +void raise_softirq_irqoff(unsigned int nr)
- +{
- + do_raise_softirq_irqoff(nr);
- +
- + /*
- + * If we're in an hard interrupt we let irq return code deal
- + * with the wakeup of ksoftirqd.
- + */
- + if (in_irq())
- + return;
- + /*
- + * If we are in thread context but outside of a bh disabled
- + * region, we need to wake ksoftirqd as well.
- + *
- + * CHECKME: Some of the places which do that could be wrapped
- + * into local_bh_disable/enable pairs. Though it's unclear
- + * whether this is worth the effort. To find those places just
- + * raise a WARN() if the condition is met.
- + */
- + if (!current->softirq_nestcnt)
- + wakeup_proper_softirq(nr);
- +}
- +
- +static inline int ksoftirqd_softirq_pending(void)
- +{
- + return current->softirqs_raised;
- +}
- +
- +static inline void local_bh_disable_nort(void) { }
- +static inline void _local_bh_enable_nort(void) { }
- +
- +static inline void ksoftirqd_set_sched_params(unsigned int cpu)
- +{
- + /* Take over all but timer pending softirqs when starting */
- + local_irq_disable();
- + current->softirqs_raised = local_softirq_pending() & ~TIMER_SOFTIRQS;
- + local_irq_enable();
- +}
- +
- +static inline void ktimer_softirqd_set_sched_params(unsigned int cpu)
- +{
- + struct sched_param param = { .sched_priority = 1 };
- +
- + sched_setscheduler(current, SCHED_FIFO, ¶m);
- +
- + /* Take over timer pending softirqs when starting */
- + local_irq_disable();
- + current->softirqs_raised = local_softirq_pending() & TIMER_SOFTIRQS;
- + local_irq_enable();
- +}
- +
- +static inline void ktimer_softirqd_clr_sched_params(unsigned int cpu,
- + bool online)
- +{
- + struct sched_param param = { .sched_priority = 0 };
- +
- + sched_setscheduler(current, SCHED_NORMAL, ¶m);
- +}
- +
- +static int ktimer_softirqd_should_run(unsigned int cpu)
- +{
- + return current->softirqs_raised;
- +}
- +
- +#endif /* PREEMPT_RT_FULL */
- +/*
- * Enter an interrupt context.
- */
- void irq_enter(void)
- @@ -330,9 +774,9 @@
- * Prevent raise_softirq from needlessly waking up ksoftirqd
- * here, as softirq will be serviced on return from interrupt.
- */
- - local_bh_disable();
- + local_bh_disable_nort();
- tick_irq_enter();
- - _local_bh_enable();
- + _local_bh_enable_nort();
- }
-
- __irq_enter();
- @@ -340,6 +784,7 @@
-
- static inline void invoke_softirq(void)
- {
- +#ifndef CONFIG_PREEMPT_RT_FULL
- if (!force_irqthreads) {
- #ifdef CONFIG_HAVE_IRQ_EXIT_ON_IRQ_STACK
- /*
- @@ -359,6 +804,18 @@
- } else {
- wakeup_softirqd();
- }
- +#else /* PREEMPT_RT_FULL */
- + unsigned long flags;
- +
- + local_irq_save(flags);
- + if (__this_cpu_read(ksoftirqd) &&
- + __this_cpu_read(ksoftirqd)->softirqs_raised)
- + wakeup_softirqd();
- + if (__this_cpu_read(ktimer_softirqd) &&
- + __this_cpu_read(ktimer_softirqd)->softirqs_raised)
- + wakeup_timer_softirqd();
- + local_irq_restore(flags);
- +#endif
- }
-
- static inline void tick_irq_exit(void)
- @@ -395,26 +852,6 @@
- trace_hardirq_exit(); /* must be last! */
- }
-
- -/*
- - * This function must run with irqs disabled!
- - */
- -inline void raise_softirq_irqoff(unsigned int nr)
- -{
- - __raise_softirq_irqoff(nr);
- -
- - /*
- - * If we're in an interrupt or softirq, we're done
- - * (this also catches softirq-disabled code). We will
- - * actually run the softirq once we return from
- - * the irq or softirq.
- - *
- - * Otherwise we wake up ksoftirqd to make sure we
- - * schedule the softirq soon.
- - */
- - if (!in_interrupt())
- - wakeup_softirqd();
- -}
- -
- void raise_softirq(unsigned int nr)
- {
- unsigned long flags;
- @@ -424,12 +861,6 @@
- local_irq_restore(flags);
- }
-
- -void __raise_softirq_irqoff(unsigned int nr)
- -{
- - trace_softirq_raise(nr);
- - or_softirq_pending(1UL << nr);
- -}
- -
- void open_softirq(int nr, void (*action)(struct softirq_action *))
- {
- softirq_vec[nr].action = action;
- @@ -446,15 +877,45 @@
- static DEFINE_PER_CPU(struct tasklet_head, tasklet_vec);
- static DEFINE_PER_CPU(struct tasklet_head, tasklet_hi_vec);
-
- +static void inline
- +__tasklet_common_schedule(struct tasklet_struct *t, struct tasklet_head *head, unsigned int nr)
- +{
- + if (tasklet_trylock(t)) {
- +again:
- + /* We may have been preempted before tasklet_trylock
- + * and __tasklet_action may have already run.
- + * So double check the sched bit while the takslet
- + * is locked before adding it to the list.
- + */
- + if (test_bit(TASKLET_STATE_SCHED, &t->state)) {
- + t->next = NULL;
- + *head->tail = t;
- + head->tail = &(t->next);
- + raise_softirq_irqoff(nr);
- + tasklet_unlock(t);
- + } else {
- + /* This is subtle. If we hit the corner case above
- + * It is possible that we get preempted right here,
- + * and another task has successfully called
- + * tasklet_schedule(), then this function, and
- + * failed on the trylock. Thus we must be sure
- + * before releasing the tasklet lock, that the
- + * SCHED_BIT is clear. Otherwise the tasklet
- + * may get its SCHED_BIT set, but not added to the
- + * list
- + */
- + if (!tasklet_tryunlock(t))
- + goto again;
- + }
- + }
- +}
- +
- void __tasklet_schedule(struct tasklet_struct *t)
- {
- unsigned long flags;
-
- local_irq_save(flags);
- - t->next = NULL;
- - *__this_cpu_read(tasklet_vec.tail) = t;
- - __this_cpu_write(tasklet_vec.tail, &(t->next));
- - raise_softirq_irqoff(TASKLET_SOFTIRQ);
- + __tasklet_common_schedule(t, this_cpu_ptr(&tasklet_vec), TASKLET_SOFTIRQ);
- local_irq_restore(flags);
- }
- EXPORT_SYMBOL(__tasklet_schedule);
- @@ -464,10 +925,7 @@
- unsigned long flags;
-
- local_irq_save(flags);
- - t->next = NULL;
- - *__this_cpu_read(tasklet_hi_vec.tail) = t;
- - __this_cpu_write(tasklet_hi_vec.tail, &(t->next));
- - raise_softirq_irqoff(HI_SOFTIRQ);
- + __tasklet_common_schedule(t, this_cpu_ptr(&tasklet_hi_vec), HI_SOFTIRQ);
- local_irq_restore(flags);
- }
- EXPORT_SYMBOL(__tasklet_hi_schedule);
- @@ -476,82 +934,122 @@
- {
- BUG_ON(!irqs_disabled());
-
- - t->next = __this_cpu_read(tasklet_hi_vec.head);
- - __this_cpu_write(tasklet_hi_vec.head, t);
- - __raise_softirq_irqoff(HI_SOFTIRQ);
- + __tasklet_hi_schedule(t);
- }
- EXPORT_SYMBOL(__tasklet_hi_schedule_first);
-
- -static void tasklet_action(struct softirq_action *a)
- +void tasklet_enable(struct tasklet_struct *t)
- {
- - struct tasklet_struct *list;
- + if (!atomic_dec_and_test(&t->count))
- + return;
- + if (test_and_clear_bit(TASKLET_STATE_PENDING, &t->state))
- + tasklet_schedule(t);
- +}
- +EXPORT_SYMBOL(tasklet_enable);
-
- - local_irq_disable();
- - list = __this_cpu_read(tasklet_vec.head);
- - __this_cpu_write(tasklet_vec.head, NULL);
- - __this_cpu_write(tasklet_vec.tail, this_cpu_ptr(&tasklet_vec.head));
- - local_irq_enable();
- +static void __tasklet_action(struct softirq_action *a,
- + struct tasklet_struct *list)
- +{
- + int loops = 1000000;
-
- while (list) {
- struct tasklet_struct *t = list;
-
- list = list->next;
-
- - if (tasklet_trylock(t)) {
- - if (!atomic_read(&t->count)) {
- - if (!test_and_clear_bit(TASKLET_STATE_SCHED,
- - &t->state))
- - BUG();
- - t->func(t->data);
- - tasklet_unlock(t);
- - continue;
- - }
- - tasklet_unlock(t);
- + /*
- + * Should always succeed - after a tasklist got on the
- + * list (after getting the SCHED bit set from 0 to 1),
- + * nothing but the tasklet softirq it got queued to can
- + * lock it:
- + */
- + if (!tasklet_trylock(t)) {
- + WARN_ON(1);
- + continue;
- }
-
- - local_irq_disable();
- t->next = NULL;
- - *__this_cpu_read(tasklet_vec.tail) = t;
- - __this_cpu_write(tasklet_vec.tail, &(t->next));
- - __raise_softirq_irqoff(TASKLET_SOFTIRQ);
- - local_irq_enable();
- +
- + /*
- + * If we cannot handle the tasklet because it's disabled,
- + * mark it as pending. tasklet_enable() will later
- + * re-schedule the tasklet.
- + */
- + if (unlikely(atomic_read(&t->count))) {
- +out_disabled:
- + /* implicit unlock: */
- + wmb();
- + t->state = TASKLET_STATEF_PENDING;
- + continue;
- + }
- +
- + /*
- + * After this point on the tasklet might be rescheduled
- + * on another CPU, but it can only be added to another
- + * CPU's tasklet list if we unlock the tasklet (which we
- + * dont do yet).
- + */
- + if (!test_and_clear_bit(TASKLET_STATE_SCHED, &t->state))
- + WARN_ON(1);
- +
- +again:
- + t->func(t->data);
- +
- + /*
- + * Try to unlock the tasklet. We must use cmpxchg, because
- + * another CPU might have scheduled or disabled the tasklet.
- + * We only allow the STATE_RUN -> 0 transition here.
- + */
- + while (!tasklet_tryunlock(t)) {
- + /*
- + * If it got disabled meanwhile, bail out:
- + */
- + if (atomic_read(&t->count))
- + goto out_disabled;
- + /*
- + * If it got scheduled meanwhile, re-execute
- + * the tasklet function:
- + */
- + if (test_and_clear_bit(TASKLET_STATE_SCHED, &t->state))
- + goto again;
- + if (!--loops) {
- + printk("hm, tasklet state: %08lx\n", t->state);
- + WARN_ON(1);
- + tasklet_unlock(t);
- + break;
- + }
- + }
- }
- }
-
- +static void tasklet_action(struct softirq_action *a)
- +{
- + struct tasklet_struct *list;
- +
- + local_irq_disable();
- +
- + list = __this_cpu_read(tasklet_vec.head);
- + __this_cpu_write(tasklet_vec.head, NULL);
- + __this_cpu_write(tasklet_vec.tail, this_cpu_ptr(&tasklet_vec.head));
- +
- + local_irq_enable();
- +
- + __tasklet_action(a, list);
- +}
- +
- static void tasklet_hi_action(struct softirq_action *a)
- {
- struct tasklet_struct *list;
-
- local_irq_disable();
- +
- list = __this_cpu_read(tasklet_hi_vec.head);
- __this_cpu_write(tasklet_hi_vec.head, NULL);
- __this_cpu_write(tasklet_hi_vec.tail, this_cpu_ptr(&tasklet_hi_vec.head));
- - local_irq_enable();
-
- - while (list) {
- - struct tasklet_struct *t = list;
- -
- - list = list->next;
- -
- - if (tasklet_trylock(t)) {
- - if (!atomic_read(&t->count)) {
- - if (!test_and_clear_bit(TASKLET_STATE_SCHED,
- - &t->state))
- - BUG();
- - t->func(t->data);
- - tasklet_unlock(t);
- - continue;
- - }
- - tasklet_unlock(t);
- - }
- + local_irq_enable();
-
- - local_irq_disable();
- - t->next = NULL;
- - *__this_cpu_read(tasklet_hi_vec.tail) = t;
- - __this_cpu_write(tasklet_hi_vec.tail, &(t->next));
- - __raise_softirq_irqoff(HI_SOFTIRQ);
- - local_irq_enable();
- - }
- + __tasklet_action(a, list);
- }
-
- void tasklet_init(struct tasklet_struct *t,
- @@ -572,7 +1070,7 @@
-
- while (test_and_set_bit(TASKLET_STATE_SCHED, &t->state)) {
- do {
- - yield();
- + msleep(1);
- } while (test_bit(TASKLET_STATE_SCHED, &t->state));
- }
- tasklet_unlock_wait(t);
- @@ -646,25 +1144,26 @@
- open_softirq(HI_SOFTIRQ, tasklet_hi_action);
- }
-
- -static int ksoftirqd_should_run(unsigned int cpu)
- -{
- - return local_softirq_pending();
- -}
- -
- -static void run_ksoftirqd(unsigned int cpu)
- +#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL)
- +void tasklet_unlock_wait(struct tasklet_struct *t)
- {
- - local_irq_disable();
- - if (local_softirq_pending()) {
- + while (test_bit(TASKLET_STATE_RUN, &(t)->state)) {
- /*
- - * We can safely run softirq on inline stack, as we are not deep
- - * in the task stack here.
- + * Hack for now to avoid this busy-loop:
- */
- - __do_softirq();
- - local_irq_enable();
- - cond_resched_rcu_qs();
- - return;
- +#ifdef CONFIG_PREEMPT_RT_FULL
- + msleep(1);
- +#else
- + barrier();
- +#endif
- }
- - local_irq_enable();
- +}
- +EXPORT_SYMBOL(tasklet_unlock_wait);
- +#endif
- +
- +static int ksoftirqd_should_run(unsigned int cpu)
- +{
- + return ksoftirqd_softirq_pending();
- }
-
- #ifdef CONFIG_HOTPLUG_CPU
- @@ -746,16 +1245,31 @@
-
- static struct smp_hotplug_thread softirq_threads = {
- .store = &ksoftirqd,
- + .setup = ksoftirqd_set_sched_params,
- .thread_should_run = ksoftirqd_should_run,
- .thread_fn = run_ksoftirqd,
- .thread_comm = "ksoftirqd/%u",
- };
-
- +#ifdef CONFIG_PREEMPT_RT_FULL
- +static struct smp_hotplug_thread softirq_timer_threads = {
- + .store = &ktimer_softirqd,
- + .setup = ktimer_softirqd_set_sched_params,
- + .cleanup = ktimer_softirqd_clr_sched_params,
- + .thread_should_run = ktimer_softirqd_should_run,
- + .thread_fn = run_ksoftirqd,
- + .thread_comm = "ktimersoftd/%u",
- +};
- +#endif
- +
- static __init int spawn_ksoftirqd(void)
- {
- register_cpu_notifier(&cpu_nfb);
-
- BUG_ON(smpboot_register_percpu_thread(&softirq_threads));
- +#ifdef CONFIG_PREEMPT_RT_FULL
- + BUG_ON(smpboot_register_percpu_thread(&softirq_timer_threads));
- +#endif
-
- return 0;
- }
- diff -Nur linux-4.4.28.orig/kernel/stop_machine.c linux-4.4.28/kernel/stop_machine.c
- --- linux-4.4.28.orig/kernel/stop_machine.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/stop_machine.c 2016-11-01 21:26:58.796343570 +0100
- @@ -37,7 +37,7 @@
- struct cpu_stopper {
- struct task_struct *thread;
-
- - spinlock_t lock;
- + raw_spinlock_t lock;
- bool enabled; /* is this stopper enabled? */
- struct list_head works; /* list of pending works */
-
- @@ -86,12 +86,12 @@
- struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);
- unsigned long flags;
-
- - spin_lock_irqsave(&stopper->lock, flags);
- + raw_spin_lock_irqsave(&stopper->lock, flags);
- if (stopper->enabled)
- __cpu_stop_queue_work(stopper, work);
- else
- cpu_stop_signal_done(work->done, false);
- - spin_unlock_irqrestore(&stopper->lock, flags);
- + raw_spin_unlock_irqrestore(&stopper->lock, flags);
- }
-
- /**
- @@ -224,8 +224,8 @@
- int err;
-
- lg_double_lock(&stop_cpus_lock, cpu1, cpu2);
- - spin_lock_irq(&stopper1->lock);
- - spin_lock_nested(&stopper2->lock, SINGLE_DEPTH_NESTING);
- + raw_spin_lock_irq(&stopper1->lock);
- + raw_spin_lock_nested(&stopper2->lock, SINGLE_DEPTH_NESTING);
-
- err = -ENOENT;
- if (!stopper1->enabled || !stopper2->enabled)
- @@ -235,8 +235,8 @@
- __cpu_stop_queue_work(stopper1, work1);
- __cpu_stop_queue_work(stopper2, work2);
- unlock:
- - spin_unlock(&stopper2->lock);
- - spin_unlock_irq(&stopper1->lock);
- + raw_spin_unlock(&stopper2->lock);
- + raw_spin_unlock_irq(&stopper1->lock);
- lg_double_unlock(&stop_cpus_lock, cpu1, cpu2);
-
- return err;
- @@ -258,7 +258,7 @@
- struct cpu_stop_work work1, work2;
- struct multi_stop_data msdata;
-
- - preempt_disable();
- + preempt_disable_nort();
- msdata = (struct multi_stop_data){
- .fn = fn,
- .data = arg,
- @@ -278,11 +278,11 @@
- if (cpu1 > cpu2)
- swap(cpu1, cpu2);
- if (cpu_stop_queue_two_works(cpu1, &work1, cpu2, &work2)) {
- - preempt_enable();
- + preempt_enable_nort();
- return -ENOENT;
- }
-
- - preempt_enable();
- + preempt_enable_nort();
-
- wait_for_completion(&done.completion);
-
- @@ -315,17 +315,20 @@
-
- static void queue_stop_cpus_work(const struct cpumask *cpumask,
- cpu_stop_fn_t fn, void *arg,
- - struct cpu_stop_done *done)
- + struct cpu_stop_done *done, bool inactive)
- {
- struct cpu_stop_work *work;
- unsigned int cpu;
-
- /*
- - * Disable preemption while queueing to avoid getting
- - * preempted by a stopper which might wait for other stoppers
- - * to enter @fn which can lead to deadlock.
- + * Make sure that all work is queued on all cpus before
- + * any of the cpus can execute it.
- */
- - lg_global_lock(&stop_cpus_lock);
- + if (!inactive)
- + lg_global_lock(&stop_cpus_lock);
- + else
- + lg_global_trylock_relax(&stop_cpus_lock);
- +
- for_each_cpu(cpu, cpumask) {
- work = &per_cpu(cpu_stopper.stop_work, cpu);
- work->fn = fn;
- @@ -342,7 +345,7 @@
- struct cpu_stop_done done;
-
- cpu_stop_init_done(&done, cpumask_weight(cpumask));
- - queue_stop_cpus_work(cpumask, fn, arg, &done);
- + queue_stop_cpus_work(cpumask, fn, arg, &done, false);
- wait_for_completion(&done.completion);
- return done.executed ? done.ret : -ENOENT;
- }
- @@ -422,9 +425,9 @@
- unsigned long flags;
- int run;
-
- - spin_lock_irqsave(&stopper->lock, flags);
- + raw_spin_lock_irqsave(&stopper->lock, flags);
- run = !list_empty(&stopper->works);
- - spin_unlock_irqrestore(&stopper->lock, flags);
- + raw_spin_unlock_irqrestore(&stopper->lock, flags);
- return run;
- }
-
- @@ -436,13 +439,13 @@
-
- repeat:
- work = NULL;
- - spin_lock_irq(&stopper->lock);
- + raw_spin_lock_irq(&stopper->lock);
- if (!list_empty(&stopper->works)) {
- work = list_first_entry(&stopper->works,
- struct cpu_stop_work, list);
- list_del_init(&work->list);
- }
- - spin_unlock_irq(&stopper->lock);
- + raw_spin_unlock_irq(&stopper->lock);
-
- if (work) {
- cpu_stop_fn_t fn = work->fn;
- @@ -450,6 +453,16 @@
- struct cpu_stop_done *done = work->done;
- char ksym_buf[KSYM_NAME_LEN] __maybe_unused;
-
- + /*
- + * Wait until the stopper finished scheduling on all
- + * cpus
- + */
- + lg_global_lock(&stop_cpus_lock);
- + /*
- + * Let other cpu threads continue as well
- + */
- + lg_global_unlock(&stop_cpus_lock);
- +
- /* cpu stop callbacks are not allowed to sleep */
- preempt_disable();
-
- @@ -520,10 +533,12 @@
- for_each_possible_cpu(cpu) {
- struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);
-
- - spin_lock_init(&stopper->lock);
- + raw_spin_lock_init(&stopper->lock);
- INIT_LIST_HEAD(&stopper->works);
- }
-
- + lg_lock_init(&stop_cpus_lock, "stop_cpus_lock");
- +
- BUG_ON(smpboot_register_percpu_thread(&cpu_stop_threads));
- stop_machine_unpark(raw_smp_processor_id());
- stop_machine_initialized = true;
- @@ -620,7 +635,7 @@
- set_state(&msdata, MULTI_STOP_PREPARE);
- cpu_stop_init_done(&done, num_active_cpus());
- queue_stop_cpus_work(cpu_active_mask, multi_cpu_stop, &msdata,
- - &done);
- + &done, true);
- ret = multi_cpu_stop(&msdata);
-
- /* Busy wait for completion. */
- diff -Nur linux-4.4.28.orig/kernel/time/hrtimer.c linux-4.4.28/kernel/time/hrtimer.c
- --- linux-4.4.28.orig/kernel/time/hrtimer.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/time/hrtimer.c 2016-11-01 21:26:58.796343570 +0100
- @@ -48,11 +48,13 @@
- #include <linux/sched/rt.h>
- #include <linux/sched/deadline.h>
- #include <linux/timer.h>
- +#include <linux/kthread.h>
- #include <linux/freezer.h>
-
- #include <asm/uaccess.h>
-
- #include <trace/events/timer.h>
- +#include <trace/events/hist.h>
-
- #include "tick-internal.h"
-
- @@ -717,6 +719,44 @@
-
- static DECLARE_WORK(hrtimer_work, clock_was_set_work);
-
- +#ifdef CONFIG_PREEMPT_RT_FULL
- +/*
- + * RT can not call schedule_work from real interrupt context.
- + * Need to make a thread to do the real work.
- + */
- +static struct task_struct *clock_set_delay_thread;
- +static bool do_clock_set_delay;
- +
- +static int run_clock_set_delay(void *ignore)
- +{
- + while (!kthread_should_stop()) {
- + set_current_state(TASK_INTERRUPTIBLE);
- + if (do_clock_set_delay) {
- + do_clock_set_delay = false;
- + schedule_work(&hrtimer_work);
- + }
- + schedule();
- + }
- + __set_current_state(TASK_RUNNING);
- + return 0;
- +}
- +
- +void clock_was_set_delayed(void)
- +{
- + do_clock_set_delay = true;
- + /* Make visible before waking up process */
- + smp_wmb();
- + wake_up_process(clock_set_delay_thread);
- +}
- +
- +static __init int create_clock_set_delay_thread(void)
- +{
- + clock_set_delay_thread = kthread_run(run_clock_set_delay, NULL, "kclksetdelayd");
- + BUG_ON(!clock_set_delay_thread);
- + return 0;
- +}
- +early_initcall(create_clock_set_delay_thread);
- +#else /* PREEMPT_RT_FULL */
- /*
- * Called from timekeeping and resume code to reprogramm the hrtimer
- * interrupt device on all cpus.
- @@ -725,6 +765,7 @@
- {
- schedule_work(&hrtimer_work);
- }
- +#endif
-
- #else
-
- @@ -734,11 +775,8 @@
- static inline void hrtimer_switch_to_hres(void) { }
- static inline void
- hrtimer_force_reprogram(struct hrtimer_cpu_base *base, int skip_equal) { }
- -static inline int hrtimer_reprogram(struct hrtimer *timer,
- - struct hrtimer_clock_base *base)
- -{
- - return 0;
- -}
- +static inline void hrtimer_reprogram(struct hrtimer *timer,
- + struct hrtimer_clock_base *base) { }
- static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base) { }
- static inline void retrigger_next_event(void *arg) { }
-
- @@ -870,6 +908,32 @@
- }
- EXPORT_SYMBOL_GPL(hrtimer_forward);
-
- +#ifdef CONFIG_PREEMPT_RT_BASE
- +# define wake_up_timer_waiters(b) wake_up(&(b)->wait)
- +
- +/**
- + * hrtimer_wait_for_timer - Wait for a running timer
- + *
- + * @timer: timer to wait for
- + *
- + * The function waits in case the timers callback function is
- + * currently executed on the waitqueue of the timer base. The
- + * waitqueue is woken up after the timer callback function has
- + * finished execution.
- + */
- +void hrtimer_wait_for_timer(const struct hrtimer *timer)
- +{
- + struct hrtimer_clock_base *base = timer->base;
- +
- + if (base && base->cpu_base && !timer->irqsafe)
- + wait_event(base->cpu_base->wait,
- + !(hrtimer_callback_running(timer)));
- +}
- +
- +#else
- +# define wake_up_timer_waiters(b) do { } while (0)
- +#endif
- +
- /*
- * enqueue_hrtimer - internal function to (re)start a timer
- *
- @@ -911,6 +975,11 @@
- if (!(state & HRTIMER_STATE_ENQUEUED))
- return;
-
- + if (unlikely(!list_empty(&timer->cb_entry))) {
- + list_del_init(&timer->cb_entry);
- + return;
- + }
- +
- if (!timerqueue_del(&base->active, &timer->node))
- cpu_base->active_bases &= ~(1 << base->index);
-
- @@ -1006,7 +1075,16 @@
- new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED);
-
- timer_stats_hrtimer_set_start_info(timer);
- +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
- + {
- + ktime_t now = new_base->get_time();
-
- + if (ktime_to_ns(tim) < ktime_to_ns(now))
- + timer->praecox = now;
- + else
- + timer->praecox = ktime_set(0, 0);
- + }
- +#endif
- leftmost = enqueue_hrtimer(timer, new_base);
- if (!leftmost)
- goto unlock;
- @@ -1078,7 +1156,7 @@
-
- if (ret >= 0)
- return ret;
- - cpu_relax();
- + hrtimer_wait_for_timer(timer);
- }
- }
- EXPORT_SYMBOL_GPL(hrtimer_cancel);
- @@ -1142,6 +1220,7 @@
-
- base = hrtimer_clockid_to_base(clock_id);
- timer->base = &cpu_base->clock_base[base];
- + INIT_LIST_HEAD(&timer->cb_entry);
- timerqueue_init(&timer->node);
-
- #ifdef CONFIG_TIMER_STATS
- @@ -1182,6 +1261,7 @@
- seq = raw_read_seqcount_begin(&cpu_base->seq);
-
- if (timer->state != HRTIMER_STATE_INACTIVE ||
- + cpu_base->running_soft == timer ||
- cpu_base->running == timer)
- return true;
-
- @@ -1280,10 +1360,112 @@
- cpu_base->running = NULL;
- }
-
- +#ifdef CONFIG_PREEMPT_RT_BASE
- +static void hrtimer_rt_reprogram(int restart, struct hrtimer *timer,
- + struct hrtimer_clock_base *base)
- +{
- + int leftmost;
- +
- + if (restart != HRTIMER_NORESTART &&
- + !(timer->state & HRTIMER_STATE_ENQUEUED)) {
- +
- + leftmost = enqueue_hrtimer(timer, base);
- + if (!leftmost)
- + return;
- +#ifdef CONFIG_HIGH_RES_TIMERS
- + if (!hrtimer_is_hres_active(timer)) {
- + /*
- + * Kick to reschedule the next tick to handle the new timer
- + * on dynticks target.
- + */
- + if (base->cpu_base->nohz_active)
- + wake_up_nohz_cpu(base->cpu_base->cpu);
- + } else {
- +
- + hrtimer_reprogram(timer, base);
- + }
- +#endif
- + }
- +}
- +
- +/*
- + * The changes in mainline which removed the callback modes from
- + * hrtimer are not yet working with -rt. The non wakeup_process()
- + * based callbacks which involve sleeping locks need to be treated
- + * seperately.
- + */
- +static void hrtimer_rt_run_pending(void)
- +{
- + enum hrtimer_restart (*fn)(struct hrtimer *);
- + struct hrtimer_cpu_base *cpu_base;
- + struct hrtimer_clock_base *base;
- + struct hrtimer *timer;
- + int index, restart;
- +
- + local_irq_disable();
- + cpu_base = &per_cpu(hrtimer_bases, smp_processor_id());
- +
- + raw_spin_lock(&cpu_base->lock);
- +
- + for (index = 0; index < HRTIMER_MAX_CLOCK_BASES; index++) {
- + base = &cpu_base->clock_base[index];
- +
- + while (!list_empty(&base->expired)) {
- + timer = list_first_entry(&base->expired,
- + struct hrtimer, cb_entry);
- +
- + /*
- + * Same as the above __run_hrtimer function
- + * just we run with interrupts enabled.
- + */
- + debug_deactivate(timer);
- + cpu_base->running_soft = timer;
- + raw_write_seqcount_barrier(&cpu_base->seq);
- +
- + __remove_hrtimer(timer, base, HRTIMER_STATE_INACTIVE, 0);
- + timer_stats_account_hrtimer(timer);
- + fn = timer->function;
- +
- + raw_spin_unlock_irq(&cpu_base->lock);
- + restart = fn(timer);
- + raw_spin_lock_irq(&cpu_base->lock);
- +
- + hrtimer_rt_reprogram(restart, timer, base);
- + raw_write_seqcount_barrier(&cpu_base->seq);
- +
- + WARN_ON_ONCE(cpu_base->running_soft != timer);
- + cpu_base->running_soft = NULL;
- + }
- + }
- +
- + raw_spin_unlock_irq(&cpu_base->lock);
- +
- + wake_up_timer_waiters(cpu_base);
- +}
- +
- +static int hrtimer_rt_defer(struct hrtimer *timer)
- +{
- + if (timer->irqsafe)
- + return 0;
- +
- + __remove_hrtimer(timer, timer->base, timer->state, 0);
- + list_add_tail(&timer->cb_entry, &timer->base->expired);
- + return 1;
- +}
- +
- +#else
- +
- +static inline int hrtimer_rt_defer(struct hrtimer *timer) { return 0; }
- +
- +#endif
- +
- +static enum hrtimer_restart hrtimer_wakeup(struct hrtimer *timer);
- +
- static void __hrtimer_run_queues(struct hrtimer_cpu_base *cpu_base, ktime_t now)
- {
- struct hrtimer_clock_base *base = cpu_base->clock_base;
- unsigned int active = cpu_base->active_bases;
- + int raise = 0;
-
- for (; active; base++, active >>= 1) {
- struct timerqueue_node *node;
- @@ -1299,6 +1481,15 @@
-
- timer = container_of(node, struct hrtimer, node);
-
- + trace_hrtimer_interrupt(raw_smp_processor_id(),
- + ktime_to_ns(ktime_sub(ktime_to_ns(timer->praecox) ?
- + timer->praecox : hrtimer_get_expires(timer),
- + basenow)),
- + current,
- + timer->function == hrtimer_wakeup ?
- + container_of(timer, struct hrtimer_sleeper,
- + timer)->task : NULL);
- +
- /*
- * The immediate goal for using the softexpires is
- * minimizing wakeups, not running timers at the
- @@ -1314,9 +1505,14 @@
- if (basenow.tv64 < hrtimer_get_softexpires_tv64(timer))
- break;
-
- - __run_hrtimer(cpu_base, base, timer, &basenow);
- + if (!hrtimer_rt_defer(timer))
- + __run_hrtimer(cpu_base, base, timer, &basenow);
- + else
- + raise = 1;
- }
- }
- + if (raise)
- + raise_softirq_irqoff(HRTIMER_SOFTIRQ);
- }
-
- #ifdef CONFIG_HIGH_RES_TIMERS
- @@ -1479,16 +1675,18 @@
- void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, struct task_struct *task)
- {
- sl->timer.function = hrtimer_wakeup;
- + sl->timer.irqsafe = 1;
- sl->task = task;
- }
- EXPORT_SYMBOL_GPL(hrtimer_init_sleeper);
-
- -static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mode)
- +static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mode,
- + unsigned long state)
- {
- hrtimer_init_sleeper(t, current);
-
- do {
- - set_current_state(TASK_INTERRUPTIBLE);
- + set_current_state(state);
- hrtimer_start_expires(&t->timer, mode);
-
- if (likely(t->task))
- @@ -1530,7 +1728,8 @@
- HRTIMER_MODE_ABS);
- hrtimer_set_expires_tv64(&t.timer, restart->nanosleep.expires);
-
- - if (do_nanosleep(&t, HRTIMER_MODE_ABS))
- + /* cpu_chill() does not care about restart state. */
- + if (do_nanosleep(&t, HRTIMER_MODE_ABS, TASK_INTERRUPTIBLE))
- goto out;
-
- rmtp = restart->nanosleep.rmtp;
- @@ -1547,8 +1746,10 @@
- return ret;
- }
-
- -long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp,
- - const enum hrtimer_mode mode, const clockid_t clockid)
- +static long
- +__hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp,
- + const enum hrtimer_mode mode, const clockid_t clockid,
- + unsigned long state)
- {
- struct restart_block *restart;
- struct hrtimer_sleeper t;
- @@ -1561,7 +1762,7 @@
-
- hrtimer_init_on_stack(&t.timer, clockid, mode);
- hrtimer_set_expires_range_ns(&t.timer, timespec_to_ktime(*rqtp), slack);
- - if (do_nanosleep(&t, mode))
- + if (do_nanosleep(&t, mode, state))
- goto out;
-
- /* Absolute timers do not update the rmtp value and restart: */
- @@ -1588,6 +1789,12 @@
- return ret;
- }
-
- +long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp,
- + const enum hrtimer_mode mode, const clockid_t clockid)
- +{
- + return __hrtimer_nanosleep(rqtp, rmtp, mode, clockid, TASK_INTERRUPTIBLE);
- +}
- +
- SYSCALL_DEFINE2(nanosleep, struct timespec __user *, rqtp,
- struct timespec __user *, rmtp)
- {
- @@ -1602,6 +1809,26 @@
- return hrtimer_nanosleep(&tu, rmtp, HRTIMER_MODE_REL, CLOCK_MONOTONIC);
- }
-
- +#ifdef CONFIG_PREEMPT_RT_FULL
- +/*
- + * Sleep for 1 ms in hope whoever holds what we want will let it go.
- + */
- +void cpu_chill(void)
- +{
- + struct timespec tu = {
- + .tv_nsec = NSEC_PER_MSEC,
- + };
- + unsigned int freeze_flag = current->flags & PF_NOFREEZE;
- +
- + current->flags |= PF_NOFREEZE;
- + __hrtimer_nanosleep(&tu, NULL, HRTIMER_MODE_REL, CLOCK_MONOTONIC,
- + TASK_UNINTERRUPTIBLE);
- + if (!freeze_flag)
- + current->flags &= ~PF_NOFREEZE;
- +}
- +EXPORT_SYMBOL(cpu_chill);
- +#endif
- +
- /*
- * Functions related to boot-time initialization:
- */
- @@ -1613,10 +1840,14 @@
- for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
- cpu_base->clock_base[i].cpu_base = cpu_base;
- timerqueue_init_head(&cpu_base->clock_base[i].active);
- + INIT_LIST_HEAD(&cpu_base->clock_base[i].expired);
- }
-
- cpu_base->cpu = cpu;
- hrtimer_init_hres(cpu_base);
- +#ifdef CONFIG_PREEMPT_RT_BASE
- + init_waitqueue_head(&cpu_base->wait);
- +#endif
- }
-
- #ifdef CONFIG_HOTPLUG_CPU
- @@ -1714,11 +1945,21 @@
- .notifier_call = hrtimer_cpu_notify,
- };
-
- +#ifdef CONFIG_PREEMPT_RT_BASE
- +static void run_hrtimer_softirq(struct softirq_action *h)
- +{
- + hrtimer_rt_run_pending();
- +}
- +#endif
- +
- void __init hrtimers_init(void)
- {
- hrtimer_cpu_notify(&hrtimers_nb, (unsigned long)CPU_UP_PREPARE,
- (void *)(long)smp_processor_id());
- register_cpu_notifier(&hrtimers_nb);
- +#ifdef CONFIG_PREEMPT_RT_BASE
- + open_softirq(HRTIMER_SOFTIRQ, run_hrtimer_softirq);
- +#endif
- }
-
- /**
- diff -Nur linux-4.4.28.orig/kernel/time/itimer.c linux-4.4.28/kernel/time/itimer.c
- --- linux-4.4.28.orig/kernel/time/itimer.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/time/itimer.c 2016-11-01 21:26:58.796343570 +0100
- @@ -213,6 +213,7 @@
- /* We are sharing ->siglock with it_real_fn() */
- if (hrtimer_try_to_cancel(timer) < 0) {
- spin_unlock_irq(&tsk->sighand->siglock);
- + hrtimer_wait_for_timer(&tsk->signal->real_timer);
- goto again;
- }
- expires = timeval_to_ktime(value->it_value);
- diff -Nur linux-4.4.28.orig/kernel/time/jiffies.c linux-4.4.28/kernel/time/jiffies.c
- --- linux-4.4.28.orig/kernel/time/jiffies.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/time/jiffies.c 2016-11-01 21:26:58.796343570 +0100
- @@ -74,7 +74,8 @@
- .max_cycles = 10,
- };
-
- -__cacheline_aligned_in_smp DEFINE_SEQLOCK(jiffies_lock);
- +__cacheline_aligned_in_smp DEFINE_RAW_SPINLOCK(jiffies_lock);
- +__cacheline_aligned_in_smp seqcount_t jiffies_seq;
-
- #if (BITS_PER_LONG < 64)
- u64 get_jiffies_64(void)
- @@ -83,9 +84,9 @@
- u64 ret;
-
- do {
- - seq = read_seqbegin(&jiffies_lock);
- + seq = read_seqcount_begin(&jiffies_seq);
- ret = jiffies_64;
- - } while (read_seqretry(&jiffies_lock, seq));
- + } while (read_seqcount_retry(&jiffies_seq, seq));
- return ret;
- }
- EXPORT_SYMBOL(get_jiffies_64);
- diff -Nur linux-4.4.28.orig/kernel/time/ntp.c linux-4.4.28/kernel/time/ntp.c
- --- linux-4.4.28.orig/kernel/time/ntp.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/time/ntp.c 2016-11-01 21:26:58.796343570 +0100
- @@ -10,6 +10,7 @@
- #include <linux/workqueue.h>
- #include <linux/hrtimer.h>
- #include <linux/jiffies.h>
- +#include <linux/kthread.h>
- #include <linux/math64.h>
- #include <linux/timex.h>
- #include <linux/time.h>
- @@ -562,10 +563,52 @@
- &sync_cmos_work, timespec64_to_jiffies(&next));
- }
-
- +#ifdef CONFIG_PREEMPT_RT_FULL
- +/*
- + * RT can not call schedule_delayed_work from real interrupt context.
- + * Need to make a thread to do the real work.
- + */
- +static struct task_struct *cmos_delay_thread;
- +static bool do_cmos_delay;
- +
- +static int run_cmos_delay(void *ignore)
- +{
- + while (!kthread_should_stop()) {
- + set_current_state(TASK_INTERRUPTIBLE);
- + if (do_cmos_delay) {
- + do_cmos_delay = false;
- + queue_delayed_work(system_power_efficient_wq,
- + &sync_cmos_work, 0);
- + }
- + schedule();
- + }
- + __set_current_state(TASK_RUNNING);
- + return 0;
- +}
- +
- +void ntp_notify_cmos_timer(void)
- +{
- + do_cmos_delay = true;
- + /* Make visible before waking up process */
- + smp_wmb();
- + wake_up_process(cmos_delay_thread);
- +}
- +
- +static __init int create_cmos_delay_thread(void)
- +{
- + cmos_delay_thread = kthread_run(run_cmos_delay, NULL, "kcmosdelayd");
- + BUG_ON(!cmos_delay_thread);
- + return 0;
- +}
- +early_initcall(create_cmos_delay_thread);
- +
- +#else
- +
- void ntp_notify_cmos_timer(void)
- {
- queue_delayed_work(system_power_efficient_wq, &sync_cmos_work, 0);
- }
- +#endif /* CONFIG_PREEMPT_RT_FULL */
-
- #else
- void ntp_notify_cmos_timer(void) { }
- diff -Nur linux-4.4.28.orig/kernel/time/posix-cpu-timers.c linux-4.4.28/kernel/time/posix-cpu-timers.c
- --- linux-4.4.28.orig/kernel/time/posix-cpu-timers.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/time/posix-cpu-timers.c 2016-11-01 21:26:58.800343826 +0100
- @@ -3,6 +3,7 @@
- */
-
- #include <linux/sched.h>
- +#include <linux/sched/rt.h>
- #include <linux/posix-timers.h>
- #include <linux/errno.h>
- #include <linux/math64.h>
- @@ -650,7 +651,7 @@
- /*
- * Disarm any old timer after extracting its expiry time.
- */
- - WARN_ON_ONCE(!irqs_disabled());
- + WARN_ON_ONCE_NONRT(!irqs_disabled());
-
- ret = 0;
- old_incr = timer->it.cpu.incr;
- @@ -1092,7 +1093,7 @@
- /*
- * Now re-arm for the new expiry time.
- */
- - WARN_ON_ONCE(!irqs_disabled());
- + WARN_ON_ONCE_NONRT(!irqs_disabled());
- arm_timer(timer);
- unlock_task_sighand(p, &flags);
-
- @@ -1183,13 +1184,13 @@
- * already updated our counts. We need to check if any timers fire now.
- * Interrupts are disabled.
- */
- -void run_posix_cpu_timers(struct task_struct *tsk)
- +static void __run_posix_cpu_timers(struct task_struct *tsk)
- {
- LIST_HEAD(firing);
- struct k_itimer *timer, *next;
- unsigned long flags;
-
- - WARN_ON_ONCE(!irqs_disabled());
- + WARN_ON_ONCE_NONRT(!irqs_disabled());
-
- /*
- * The fast path checks that there are no expired thread or thread
- @@ -1243,6 +1244,190 @@
- }
- }
-
- +#ifdef CONFIG_PREEMPT_RT_BASE
- +#include <linux/kthread.h>
- +#include <linux/cpu.h>
- +DEFINE_PER_CPU(struct task_struct *, posix_timer_task);
- +DEFINE_PER_CPU(struct task_struct *, posix_timer_tasklist);
- +
- +static int posix_cpu_timers_thread(void *data)
- +{
- + int cpu = (long)data;
- +
- + BUG_ON(per_cpu(posix_timer_task,cpu) != current);
- +
- + while (!kthread_should_stop()) {
- + struct task_struct *tsk = NULL;
- + struct task_struct *next = NULL;
- +
- + if (cpu_is_offline(cpu))
- + goto wait_to_die;
- +
- + /* grab task list */
- + raw_local_irq_disable();
- + tsk = per_cpu(posix_timer_tasklist, cpu);
- + per_cpu(posix_timer_tasklist, cpu) = NULL;
- + raw_local_irq_enable();
- +
- + /* its possible the list is empty, just return */
- + if (!tsk) {
- + set_current_state(TASK_INTERRUPTIBLE);
- + schedule();
- + __set_current_state(TASK_RUNNING);
- + continue;
- + }
- +
- + /* Process task list */
- + while (1) {
- + /* save next */
- + next = tsk->posix_timer_list;
- +
- + /* run the task timers, clear its ptr and
- + * unreference it
- + */
- + __run_posix_cpu_timers(tsk);
- + tsk->posix_timer_list = NULL;
- + put_task_struct(tsk);
- +
- + /* check if this is the last on the list */
- + if (next == tsk)
- + break;
- + tsk = next;
- + }
- + }
- + return 0;
- +
- +wait_to_die:
- + /* Wait for kthread_stop */
- + set_current_state(TASK_INTERRUPTIBLE);
- + while (!kthread_should_stop()) {
- + schedule();
- + set_current_state(TASK_INTERRUPTIBLE);
- + }
- + __set_current_state(TASK_RUNNING);
- + return 0;
- +}
- +
- +static inline int __fastpath_timer_check(struct task_struct *tsk)
- +{
- + /* tsk == current, ensure it is safe to use ->signal/sighand */
- + if (unlikely(tsk->exit_state))
- + return 0;
- +
- + if (!task_cputime_zero(&tsk->cputime_expires))
- + return 1;
- +
- + if (!task_cputime_zero(&tsk->signal->cputime_expires))
- + return 1;
- +
- + return 0;
- +}
- +
- +void run_posix_cpu_timers(struct task_struct *tsk)
- +{
- + unsigned long cpu = smp_processor_id();
- + struct task_struct *tasklist;
- +
- + BUG_ON(!irqs_disabled());
- + if(!per_cpu(posix_timer_task, cpu))
- + return;
- + /* get per-cpu references */
- + tasklist = per_cpu(posix_timer_tasklist, cpu);
- +
- + /* check to see if we're already queued */
- + if (!tsk->posix_timer_list && __fastpath_timer_check(tsk)) {
- + get_task_struct(tsk);
- + if (tasklist) {
- + tsk->posix_timer_list = tasklist;
- + } else {
- + /*
- + * The list is terminated by a self-pointing
- + * task_struct
- + */
- + tsk->posix_timer_list = tsk;
- + }
- + per_cpu(posix_timer_tasklist, cpu) = tsk;
- +
- + wake_up_process(per_cpu(posix_timer_task, cpu));
- + }
- +}
- +
- +/*
- + * posix_cpu_thread_call - callback that gets triggered when a CPU is added.
- + * Here we can start up the necessary migration thread for the new CPU.
- + */
- +static int posix_cpu_thread_call(struct notifier_block *nfb,
- + unsigned long action, void *hcpu)
- +{
- + int cpu = (long)hcpu;
- + struct task_struct *p;
- + struct sched_param param;
- +
- + switch (action) {
- + case CPU_UP_PREPARE:
- + p = kthread_create(posix_cpu_timers_thread, hcpu,
- + "posixcputmr/%d",cpu);
- + if (IS_ERR(p))
- + return NOTIFY_BAD;
- + p->flags |= PF_NOFREEZE;
- + kthread_bind(p, cpu);
- + /* Must be high prio to avoid getting starved */
- + param.sched_priority = MAX_RT_PRIO-1;
- + sched_setscheduler(p, SCHED_FIFO, ¶m);
- + per_cpu(posix_timer_task,cpu) = p;
- + break;
- + case CPU_ONLINE:
- + /* Strictly unneccessary, as first user will wake it. */
- + wake_up_process(per_cpu(posix_timer_task,cpu));
- + break;
- +#ifdef CONFIG_HOTPLUG_CPU
- + case CPU_UP_CANCELED:
- + /* Unbind it from offline cpu so it can run. Fall thru. */
- + kthread_bind(per_cpu(posix_timer_task, cpu),
- + cpumask_any(cpu_online_mask));
- + kthread_stop(per_cpu(posix_timer_task,cpu));
- + per_cpu(posix_timer_task,cpu) = NULL;
- + break;
- + case CPU_DEAD:
- + kthread_stop(per_cpu(posix_timer_task,cpu));
- + per_cpu(posix_timer_task,cpu) = NULL;
- + break;
- +#endif
- + }
- + return NOTIFY_OK;
- +}
- +
- +/* Register at highest priority so that task migration (migrate_all_tasks)
- + * happens before everything else.
- + */
- +static struct notifier_block posix_cpu_thread_notifier = {
- + .notifier_call = posix_cpu_thread_call,
- + .priority = 10
- +};
- +
- +static int __init posix_cpu_thread_init(void)
- +{
- + void *hcpu = (void *)(long)smp_processor_id();
- + /* Start one for boot CPU. */
- + unsigned long cpu;
- +
- + /* init the per-cpu posix_timer_tasklets */
- + for_each_possible_cpu(cpu)
- + per_cpu(posix_timer_tasklist, cpu) = NULL;
- +
- + posix_cpu_thread_call(&posix_cpu_thread_notifier, CPU_UP_PREPARE, hcpu);
- + posix_cpu_thread_call(&posix_cpu_thread_notifier, CPU_ONLINE, hcpu);
- + register_cpu_notifier(&posix_cpu_thread_notifier);
- + return 0;
- +}
- +early_initcall(posix_cpu_thread_init);
- +#else /* CONFIG_PREEMPT_RT_BASE */
- +void run_posix_cpu_timers(struct task_struct *tsk)
- +{
- + __run_posix_cpu_timers(tsk);
- +}
- +#endif /* CONFIG_PREEMPT_RT_BASE */
- +
- /*
- * Set one of the process-wide special case CPU timers or RLIMIT_CPU.
- * The tsk->sighand->siglock must be held by the caller.
- diff -Nur linux-4.4.28.orig/kernel/time/posix-timers.c linux-4.4.28/kernel/time/posix-timers.c
- --- linux-4.4.28.orig/kernel/time/posix-timers.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/time/posix-timers.c 2016-11-01 21:26:58.800343826 +0100
- @@ -506,6 +506,7 @@
- static struct pid *good_sigevent(sigevent_t * event)
- {
- struct task_struct *rtn = current->group_leader;
- + int sig = event->sigev_signo;
-
- if ((event->sigev_notify & SIGEV_THREAD_ID ) &&
- (!(rtn = find_task_by_vpid(event->sigev_notify_thread_id)) ||
- @@ -514,7 +515,8 @@
- return NULL;
-
- if (((event->sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE) &&
- - ((event->sigev_signo <= 0) || (event->sigev_signo > SIGRTMAX)))
- + (sig <= 0 || sig > SIGRTMAX || sig_kernel_only(sig) ||
- + sig_kernel_coredump(sig)))
- return NULL;
-
- return task_pid(rtn);
- @@ -826,6 +828,20 @@
- return overrun;
- }
-
- +/*
- + * Protected by RCU!
- + */
- +static void timer_wait_for_callback(struct k_clock *kc, struct k_itimer *timr)
- +{
- +#ifdef CONFIG_PREEMPT_RT_FULL
- + if (kc->timer_set == common_timer_set)
- + hrtimer_wait_for_timer(&timr->it.real.timer);
- + else
- + /* FIXME: Whacky hack for posix-cpu-timers */
- + schedule_timeout(1);
- +#endif
- +}
- +
- /* Set a POSIX.1b interval timer. */
- /* timr->it_lock is taken. */
- static int
- @@ -903,6 +919,7 @@
- if (!timr)
- return -EINVAL;
-
- + rcu_read_lock();
- kc = clockid_to_kclock(timr->it_clock);
- if (WARN_ON_ONCE(!kc || !kc->timer_set))
- error = -EINVAL;
- @@ -911,9 +928,12 @@
-
- unlock_timer(timr, flag);
- if (error == TIMER_RETRY) {
- + timer_wait_for_callback(kc, timr);
- rtn = NULL; // We already got the old time...
- + rcu_read_unlock();
- goto retry;
- }
- + rcu_read_unlock();
-
- if (old_setting && !error &&
- copy_to_user(old_setting, &old_spec, sizeof (old_spec)))
- @@ -951,10 +971,15 @@
- if (!timer)
- return -EINVAL;
-
- + rcu_read_lock();
- if (timer_delete_hook(timer) == TIMER_RETRY) {
- unlock_timer(timer, flags);
- + timer_wait_for_callback(clockid_to_kclock(timer->it_clock),
- + timer);
- + rcu_read_unlock();
- goto retry_delete;
- }
- + rcu_read_unlock();
-
- spin_lock(¤t->sighand->siglock);
- list_del(&timer->list);
- @@ -980,8 +1005,18 @@
- retry_delete:
- spin_lock_irqsave(&timer->it_lock, flags);
-
- + /* On RT we can race with a deletion */
- + if (!timer->it_signal) {
- + unlock_timer(timer, flags);
- + return;
- + }
- +
- if (timer_delete_hook(timer) == TIMER_RETRY) {
- + rcu_read_lock();
- unlock_timer(timer, flags);
- + timer_wait_for_callback(clockid_to_kclock(timer->it_clock),
- + timer);
- + rcu_read_unlock();
- goto retry_delete;
- }
- list_del(&timer->list);
- diff -Nur linux-4.4.28.orig/kernel/time/tick-broadcast-hrtimer.c linux-4.4.28/kernel/time/tick-broadcast-hrtimer.c
- --- linux-4.4.28.orig/kernel/time/tick-broadcast-hrtimer.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/time/tick-broadcast-hrtimer.c 2016-11-01 21:26:58.800343826 +0100
- @@ -106,5 +106,6 @@
- {
- hrtimer_init(&bctimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
- bctimer.function = bc_handler;
- + bctimer.irqsafe = true;
- clockevents_register_device(&ce_broadcast_hrtimer);
- }
- diff -Nur linux-4.4.28.orig/kernel/time/tick-common.c linux-4.4.28/kernel/time/tick-common.c
- --- linux-4.4.28.orig/kernel/time/tick-common.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/time/tick-common.c 2016-11-01 21:26:58.800343826 +0100
- @@ -79,13 +79,15 @@
- static void tick_periodic(int cpu)
- {
- if (tick_do_timer_cpu == cpu) {
- - write_seqlock(&jiffies_lock);
- + raw_spin_lock(&jiffies_lock);
- + write_seqcount_begin(&jiffies_seq);
-
- /* Keep track of the next tick event */
- tick_next_period = ktime_add(tick_next_period, tick_period);
-
- do_timer(1);
- - write_sequnlock(&jiffies_lock);
- + write_seqcount_end(&jiffies_seq);
- + raw_spin_unlock(&jiffies_lock);
- update_wall_time();
- }
-
- @@ -157,9 +159,9 @@
- ktime_t next;
-
- do {
- - seq = read_seqbegin(&jiffies_lock);
- + seq = read_seqcount_begin(&jiffies_seq);
- next = tick_next_period;
- - } while (read_seqretry(&jiffies_lock, seq));
- + } while (read_seqcount_retry(&jiffies_seq, seq));
-
- clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT);
-
- diff -Nur linux-4.4.28.orig/kernel/time/tick-sched.c linux-4.4.28/kernel/time/tick-sched.c
- --- linux-4.4.28.orig/kernel/time/tick-sched.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/time/tick-sched.c 2016-11-01 21:26:58.800343826 +0100
- @@ -62,7 +62,8 @@
- return;
-
- /* Reevalute with jiffies_lock held */
- - write_seqlock(&jiffies_lock);
- + raw_spin_lock(&jiffies_lock);
- + write_seqcount_begin(&jiffies_seq);
-
- delta = ktime_sub(now, last_jiffies_update);
- if (delta.tv64 >= tick_period.tv64) {
- @@ -85,10 +86,12 @@
- /* Keep the tick_next_period variable up to date */
- tick_next_period = ktime_add(last_jiffies_update, tick_period);
- } else {
- - write_sequnlock(&jiffies_lock);
- + write_seqcount_end(&jiffies_seq);
- + raw_spin_unlock(&jiffies_lock);
- return;
- }
- - write_sequnlock(&jiffies_lock);
- + write_seqcount_end(&jiffies_seq);
- + raw_spin_unlock(&jiffies_lock);
- update_wall_time();
- }
-
- @@ -99,12 +102,14 @@
- {
- ktime_t period;
-
- - write_seqlock(&jiffies_lock);
- + raw_spin_lock(&jiffies_lock);
- + write_seqcount_begin(&jiffies_seq);
- /* Did we start the jiffies update yet ? */
- if (last_jiffies_update.tv64 == 0)
- last_jiffies_update = tick_next_period;
- period = last_jiffies_update;
- - write_sequnlock(&jiffies_lock);
- + write_seqcount_end(&jiffies_seq);
- + raw_spin_unlock(&jiffies_lock);
- return period;
- }
-
- @@ -176,6 +181,11 @@
- return false;
- }
-
- + if (!arch_irq_work_has_interrupt()) {
- + trace_tick_stop(0, "missing irq work interrupt\n");
- + return false;
- + }
- +
- /* sched_clock_tick() needs us? */
- #ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
- /*
- @@ -204,6 +214,7 @@
-
- static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) = {
- .func = nohz_full_kick_work_func,
- + .flags = IRQ_WORK_HARD_IRQ,
- };
-
- /*
- @@ -578,10 +589,10 @@
-
- /* Read jiffies and the time when jiffies were updated last */
- do {
- - seq = read_seqbegin(&jiffies_lock);
- + seq = read_seqcount_begin(&jiffies_seq);
- basemono = last_jiffies_update.tv64;
- basejiff = jiffies;
- - } while (read_seqretry(&jiffies_lock, seq));
- + } while (read_seqcount_retry(&jiffies_seq, seq));
- ts->last_jiffies = basejiff;
-
- if (rcu_needs_cpu(basemono, &next_rcu) ||
- @@ -753,14 +764,7 @@
- return false;
-
- if (unlikely(local_softirq_pending() && cpu_online(cpu))) {
- - static int ratelimit;
- -
- - if (ratelimit < 10 &&
- - (local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK)) {
- - pr_warn("NOHZ: local_softirq_pending %02x\n",
- - (unsigned int) local_softirq_pending());
- - ratelimit++;
- - }
- + softirq_check_pending_idle();
- return false;
- }
-
- @@ -1100,6 +1104,7 @@
- * Emulate tick processing via per-CPU hrtimers:
- */
- hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
- + ts->sched_timer.irqsafe = 1;
- ts->sched_timer.function = tick_sched_timer;
-
- /* Get the next period (per cpu) */
- diff -Nur linux-4.4.28.orig/kernel/time/timekeeping.c linux-4.4.28/kernel/time/timekeeping.c
- --- linux-4.4.28.orig/kernel/time/timekeeping.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/time/timekeeping.c 2016-11-01 21:26:58.800343826 +0100
- @@ -2070,8 +2070,10 @@
- */
- void xtime_update(unsigned long ticks)
- {
- - write_seqlock(&jiffies_lock);
- + raw_spin_lock(&jiffies_lock);
- + write_seqcount_begin(&jiffies_seq);
- do_timer(ticks);
- - write_sequnlock(&jiffies_lock);
- + write_seqcount_end(&jiffies_seq);
- + raw_spin_unlock(&jiffies_lock);
- update_wall_time();
- }
- diff -Nur linux-4.4.28.orig/kernel/time/timekeeping.h linux-4.4.28/kernel/time/timekeeping.h
- --- linux-4.4.28.orig/kernel/time/timekeeping.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/time/timekeeping.h 2016-11-01 21:26:58.800343826 +0100
- @@ -19,7 +19,8 @@
- extern void do_timer(unsigned long ticks);
- extern void update_wall_time(void);
-
- -extern seqlock_t jiffies_lock;
- +extern raw_spinlock_t jiffies_lock;
- +extern seqcount_t jiffies_seq;
-
- #define CS_NAME_LEN 32
-
- diff -Nur linux-4.4.28.orig/kernel/time/timer.c linux-4.4.28/kernel/time/timer.c
- --- linux-4.4.28.orig/kernel/time/timer.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/time/timer.c 2016-11-01 21:26:58.804344090 +0100
- @@ -80,6 +80,9 @@
- struct tvec_base {
- spinlock_t lock;
- struct timer_list *running_timer;
- +#ifdef CONFIG_PREEMPT_RT_FULL
- + wait_queue_head_t wait_for_running_timer;
- +#endif
- unsigned long timer_jiffies;
- unsigned long next_timer;
- unsigned long active_timers;
- @@ -777,6 +780,39 @@
- cpu_relax();
- }
- }
- +#ifdef CONFIG_PREEMPT_RT_FULL
- +static inline struct tvec_base *switch_timer_base(struct timer_list *timer,
- + struct tvec_base *old,
- + struct tvec_base *new)
- +{
- + /*
- + * We cannot do the below because we might be preempted and
- + * then the preempter would see NULL and loop forever.
- + */
- + if (spin_trylock(&new->lock)) {
- + WRITE_ONCE(timer->flags,
- + (timer->flags & ~TIMER_BASEMASK) | new->cpu);
- + spin_unlock(&old->lock);
- + return new;
- + }
- + return old;
- +}
- +
- +#else
- +static inline struct tvec_base *switch_timer_base(struct timer_list *timer,
- + struct tvec_base *old,
- + struct tvec_base *new)
- +{
- + /* See the comment in lock_timer_base() */
- + timer->flags |= TIMER_MIGRATING;
- +
- + spin_unlock(&old->lock);
- + spin_lock(&new->lock);
- + WRITE_ONCE(timer->flags,
- + (timer->flags & ~TIMER_BASEMASK) | new->cpu);
- + return new;
- +}
- +#endif
-
- static inline int
- __mod_timer(struct timer_list *timer, unsigned long expires,
- @@ -807,16 +843,8 @@
- * handler yet has not finished. This also guarantees that
- * the timer is serialized wrt itself.
- */
- - if (likely(base->running_timer != timer)) {
- - /* See the comment in lock_timer_base() */
- - timer->flags |= TIMER_MIGRATING;
- -
- - spin_unlock(&base->lock);
- - base = new_base;
- - spin_lock(&base->lock);
- - WRITE_ONCE(timer->flags,
- - (timer->flags & ~TIMER_BASEMASK) | base->cpu);
- - }
- + if (likely(base->running_timer != timer))
- + base = switch_timer_base(timer, base, new_base);
- }
-
- timer->expires = expires;
- @@ -1006,6 +1034,33 @@
- }
- EXPORT_SYMBOL_GPL(add_timer_on);
-
- +#ifdef CONFIG_PREEMPT_RT_FULL
- +/*
- + * Wait for a running timer
- + */
- +static void wait_for_running_timer(struct timer_list *timer)
- +{
- + struct tvec_base *base;
- + u32 tf = timer->flags;
- +
- + if (tf & TIMER_MIGRATING)
- + return;
- +
- + base = per_cpu_ptr(&tvec_bases, tf & TIMER_CPUMASK);
- + wait_event(base->wait_for_running_timer,
- + base->running_timer != timer);
- +}
- +
- +# define wakeup_timer_waiters(b) wake_up_all(&(b)->wait_for_running_timer)
- +#else
- +static inline void wait_for_running_timer(struct timer_list *timer)
- +{
- + cpu_relax();
- +}
- +
- +# define wakeup_timer_waiters(b) do { } while (0)
- +#endif
- +
- /**
- * del_timer - deactive a timer.
- * @timer: the timer to be deactivated
- @@ -1063,7 +1118,7 @@
- }
- EXPORT_SYMBOL(try_to_del_timer_sync);
-
- -#ifdef CONFIG_SMP
- +#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL)
- /**
- * del_timer_sync - deactivate a timer and wait for the handler to finish.
- * @timer: the timer to be deactivated
- @@ -1123,7 +1178,7 @@
- int ret = try_to_del_timer_sync(timer);
- if (ret >= 0)
- return ret;
- - cpu_relax();
- + wait_for_running_timer(timer);
- }
- }
- EXPORT_SYMBOL(del_timer_sync);
- @@ -1248,16 +1303,18 @@
- if (irqsafe) {
- spin_unlock(&base->lock);
- call_timer_fn(timer, fn, data);
- + base->running_timer = NULL;
- spin_lock(&base->lock);
- } else {
- spin_unlock_irq(&base->lock);
- call_timer_fn(timer, fn, data);
- + base->running_timer = NULL;
- spin_lock_irq(&base->lock);
- }
- }
- }
- - base->running_timer = NULL;
- spin_unlock_irq(&base->lock);
- + wakeup_timer_waiters(base);
- }
-
- #ifdef CONFIG_NO_HZ_COMMON
- @@ -1390,6 +1447,14 @@
- if (cpu_is_offline(smp_processor_id()))
- return expires;
-
- +#ifdef CONFIG_PREEMPT_RT_FULL
- + /*
- + * On PREEMPT_RT we cannot sleep here. As a result we can't take
- + * the base lock to check when the next timer is pending and so
- + * we assume the next jiffy.
- + */
- + return basem + TICK_NSEC;
- +#endif
- spin_lock(&base->lock);
- if (base->active_timers) {
- if (time_before_eq(base->next_timer, base->timer_jiffies))
- @@ -1416,13 +1481,13 @@
-
- /* Note: this timer irq context must be accounted for as well. */
- account_process_tick(p, user_tick);
- + scheduler_tick();
- run_local_timers();
- rcu_check_callbacks(user_tick);
- -#ifdef CONFIG_IRQ_WORK
- +#if defined(CONFIG_IRQ_WORK)
- if (in_irq())
- irq_work_tick();
- #endif
- - scheduler_tick();
- run_posix_cpu_timers(p);
- }
-
- @@ -1433,6 +1498,8 @@
- {
- struct tvec_base *base = this_cpu_ptr(&tvec_bases);
-
- + irq_work_tick_soft();
- +
- if (time_after_eq(jiffies, base->timer_jiffies))
- __run_timers(base);
- }
- @@ -1589,7 +1656,7 @@
-
- BUG_ON(cpu_online(cpu));
- old_base = per_cpu_ptr(&tvec_bases, cpu);
- - new_base = get_cpu_ptr(&tvec_bases);
- + new_base = get_local_ptr(&tvec_bases);
- /*
- * The caller is globally serialized and nobody else
- * takes two locks at once, deadlock is not possible.
- @@ -1613,7 +1680,7 @@
-
- spin_unlock(&old_base->lock);
- spin_unlock_irq(&new_base->lock);
- - put_cpu_ptr(&tvec_bases);
- + put_local_ptr(&tvec_bases);
- }
-
- static int timer_cpu_notify(struct notifier_block *self,
- @@ -1645,6 +1712,9 @@
-
- base->cpu = cpu;
- spin_lock_init(&base->lock);
- +#ifdef CONFIG_PREEMPT_RT_FULL
- + init_waitqueue_head(&base->wait_for_running_timer);
- +#endif
-
- base->timer_jiffies = jiffies;
- base->next_timer = base->timer_jiffies;
- diff -Nur linux-4.4.28.orig/kernel/trace/Kconfig linux-4.4.28/kernel/trace/Kconfig
- --- linux-4.4.28.orig/kernel/trace/Kconfig 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/trace/Kconfig 2016-11-01 21:26:58.804344090 +0100
- @@ -187,6 +187,24 @@
- enabled. This option and the preempt-off timing option can be
- used together or separately.)
-
- +config INTERRUPT_OFF_HIST
- + bool "Interrupts-off Latency Histogram"
- + depends on IRQSOFF_TRACER
- + help
- + This option generates continuously updated histograms (one per cpu)
- + of the duration of time periods with interrupts disabled. The
- + histograms are disabled by default. To enable them, write a non-zero
- + number to
- +
- + /sys/kernel/debug/tracing/latency_hist/enable/preemptirqsoff
- +
- + If PREEMPT_OFF_HIST is also selected, additional histograms (one
- + per cpu) are generated that accumulate the duration of time periods
- + when both interrupts and preemption are disabled. The histogram data
- + will be located in the debug file system at
- +
- + /sys/kernel/debug/tracing/latency_hist/irqsoff
- +
- config PREEMPT_TRACER
- bool "Preemption-off Latency Tracer"
- default n
- @@ -211,6 +229,24 @@
- enabled. This option and the irqs-off timing option can be
- used together or separately.)
-
- +config PREEMPT_OFF_HIST
- + bool "Preemption-off Latency Histogram"
- + depends on PREEMPT_TRACER
- + help
- + This option generates continuously updated histograms (one per cpu)
- + of the duration of time periods with preemption disabled. The
- + histograms are disabled by default. To enable them, write a non-zero
- + number to
- +
- + /sys/kernel/debug/tracing/latency_hist/enable/preemptirqsoff
- +
- + If INTERRUPT_OFF_HIST is also selected, additional histograms (one
- + per cpu) are generated that accumulate the duration of time periods
- + when both interrupts and preemption are disabled. The histogram data
- + will be located in the debug file system at
- +
- + /sys/kernel/debug/tracing/latency_hist/preemptoff
- +
- config SCHED_TRACER
- bool "Scheduling Latency Tracer"
- select GENERIC_TRACER
- @@ -221,6 +257,74 @@
- This tracer tracks the latency of the highest priority task
- to be scheduled in, starting from the point it has woken up.
-
- +config WAKEUP_LATENCY_HIST
- + bool "Scheduling Latency Histogram"
- + depends on SCHED_TRACER
- + help
- + This option generates continuously updated histograms (one per cpu)
- + of the scheduling latency of the highest priority task.
- + The histograms are disabled by default. To enable them, write a
- + non-zero number to
- +
- + /sys/kernel/debug/tracing/latency_hist/enable/wakeup
- +
- + Two different algorithms are used, one to determine the latency of
- + processes that exclusively use the highest priority of the system and
- + another one to determine the latency of processes that share the
- + highest system priority with other processes. The former is used to
- + improve hardware and system software, the latter to optimize the
- + priority design of a given system. The histogram data will be
- + located in the debug file system at
- +
- + /sys/kernel/debug/tracing/latency_hist/wakeup
- +
- + and
- +
- + /sys/kernel/debug/tracing/latency_hist/wakeup/sharedprio
- +
- + If both Scheduling Latency Histogram and Missed Timer Offsets
- + Histogram are selected, additional histogram data will be collected
- + that contain, in addition to the wakeup latency, the timer latency, in
- + case the wakeup was triggered by an expired timer. These histograms
- + are available in the
- +
- + /sys/kernel/debug/tracing/latency_hist/timerandwakeup
- +
- + directory. They reflect the apparent interrupt and scheduling latency
- + and are best suitable to determine the worst-case latency of a given
- + system. To enable these histograms, write a non-zero number to
- +
- + /sys/kernel/debug/tracing/latency_hist/enable/timerandwakeup
- +
- +config MISSED_TIMER_OFFSETS_HIST
- + depends on HIGH_RES_TIMERS
- + select GENERIC_TRACER
- + bool "Missed Timer Offsets Histogram"
- + help
- + Generate a histogram of missed timer offsets in microseconds. The
- + histograms are disabled by default. To enable them, write a non-zero
- + number to
- +
- + /sys/kernel/debug/tracing/latency_hist/enable/missed_timer_offsets
- +
- + The histogram data will be located in the debug file system at
- +
- + /sys/kernel/debug/tracing/latency_hist/missed_timer_offsets
- +
- + If both Scheduling Latency Histogram and Missed Timer Offsets
- + Histogram are selected, additional histogram data will be collected
- + that contain, in addition to the wakeup latency, the timer latency, in
- + case the wakeup was triggered by an expired timer. These histograms
- + are available in the
- +
- + /sys/kernel/debug/tracing/latency_hist/timerandwakeup
- +
- + directory. They reflect the apparent interrupt and scheduling latency
- + and are best suitable to determine the worst-case latency of a given
- + system. To enable these histograms, write a non-zero number to
- +
- + /sys/kernel/debug/tracing/latency_hist/enable/timerandwakeup
- +
- config ENABLE_DEFAULT_TRACERS
- bool "Trace process context switches and events"
- depends on !GENERIC_TRACER
- diff -Nur linux-4.4.28.orig/kernel/trace/latency_hist.c linux-4.4.28/kernel/trace/latency_hist.c
- --- linux-4.4.28.orig/kernel/trace/latency_hist.c 1970-01-01 01:00:00.000000000 +0100
- +++ linux-4.4.28/kernel/trace/latency_hist.c 2016-11-01 21:26:58.804344090 +0100
- @@ -0,0 +1,1178 @@
- +/*
- + * kernel/trace/latency_hist.c
- + *
- + * Add support for histograms of preemption-off latency and
- + * interrupt-off latency and wakeup latency, it depends on
- + * Real-Time Preemption Support.
- + *
- + * Copyright (C) 2005 MontaVista Software, Inc.
- + * Yi Yang <yyang@ch.mvista.com>
- + *
- + * Converted to work with the new latency tracer.
- + * Copyright (C) 2008 Red Hat, Inc.
- + * Steven Rostedt <srostedt@redhat.com>
- + *
- + */
- +#include <linux/module.h>
- +#include <linux/debugfs.h>
- +#include <linux/seq_file.h>
- +#include <linux/percpu.h>
- +#include <linux/kallsyms.h>
- +#include <linux/uaccess.h>
- +#include <linux/sched.h>
- +#include <linux/sched/rt.h>
- +#include <linux/slab.h>
- +#include <linux/atomic.h>
- +#include <asm/div64.h>
- +
- +#include "trace.h"
- +#include <trace/events/sched.h>
- +
- +#define NSECS_PER_USECS 1000L
- +
- +#define CREATE_TRACE_POINTS
- +#include <trace/events/hist.h>
- +
- +enum {
- + IRQSOFF_LATENCY = 0,
- + PREEMPTOFF_LATENCY,
- + PREEMPTIRQSOFF_LATENCY,
- + WAKEUP_LATENCY,
- + WAKEUP_LATENCY_SHAREDPRIO,
- + MISSED_TIMER_OFFSETS,
- + TIMERANDWAKEUP_LATENCY,
- + MAX_LATENCY_TYPE,
- +};
- +
- +#define MAX_ENTRY_NUM 10240
- +
- +struct hist_data {
- + atomic_t hist_mode; /* 0 log, 1 don't log */
- + long offset; /* set it to MAX_ENTRY_NUM/2 for a bipolar scale */
- + long min_lat;
- + long max_lat;
- + unsigned long long below_hist_bound_samples;
- + unsigned long long above_hist_bound_samples;
- + long long accumulate_lat;
- + unsigned long long total_samples;
- + unsigned long long hist_array[MAX_ENTRY_NUM];
- +};
- +
- +struct enable_data {
- + int latency_type;
- + int enabled;
- +};
- +
- +static char *latency_hist_dir_root = "latency_hist";
- +
- +#ifdef CONFIG_INTERRUPT_OFF_HIST
- +static DEFINE_PER_CPU(struct hist_data, irqsoff_hist);
- +static char *irqsoff_hist_dir = "irqsoff";
- +static DEFINE_PER_CPU(cycles_t, hist_irqsoff_start);
- +static DEFINE_PER_CPU(int, hist_irqsoff_counting);
- +#endif
- +
- +#ifdef CONFIG_PREEMPT_OFF_HIST
- +static DEFINE_PER_CPU(struct hist_data, preemptoff_hist);
- +static char *preemptoff_hist_dir = "preemptoff";
- +static DEFINE_PER_CPU(cycles_t, hist_preemptoff_start);
- +static DEFINE_PER_CPU(int, hist_preemptoff_counting);
- +#endif
- +
- +#if defined(CONFIG_PREEMPT_OFF_HIST) && defined(CONFIG_INTERRUPT_OFF_HIST)
- +static DEFINE_PER_CPU(struct hist_data, preemptirqsoff_hist);
- +static char *preemptirqsoff_hist_dir = "preemptirqsoff";
- +static DEFINE_PER_CPU(cycles_t, hist_preemptirqsoff_start);
- +static DEFINE_PER_CPU(int, hist_preemptirqsoff_counting);
- +#endif
- +
- +#if defined(CONFIG_PREEMPT_OFF_HIST) || defined(CONFIG_INTERRUPT_OFF_HIST)
- +static notrace void probe_preemptirqsoff_hist(void *v, int reason, int start);
- +static struct enable_data preemptirqsoff_enabled_data = {
- + .latency_type = PREEMPTIRQSOFF_LATENCY,
- + .enabled = 0,
- +};
- +#endif
- +
- +#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \
- + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
- +struct maxlatproc_data {
- + char comm[FIELD_SIZEOF(struct task_struct, comm)];
- + char current_comm[FIELD_SIZEOF(struct task_struct, comm)];
- + int pid;
- + int current_pid;
- + int prio;
- + int current_prio;
- + long latency;
- + long timeroffset;
- + cycle_t timestamp;
- +};
- +#endif
- +
- +#ifdef CONFIG_WAKEUP_LATENCY_HIST
- +static DEFINE_PER_CPU(struct hist_data, wakeup_latency_hist);
- +static DEFINE_PER_CPU(struct hist_data, wakeup_latency_hist_sharedprio);
- +static char *wakeup_latency_hist_dir = "wakeup";
- +static char *wakeup_latency_hist_dir_sharedprio = "sharedprio";
- +static notrace void probe_wakeup_latency_hist_start(void *v,
- + struct task_struct *p);
- +static notrace void probe_wakeup_latency_hist_stop(void *v,
- + bool preempt, struct task_struct *prev, struct task_struct *next);
- +static notrace void probe_sched_migrate_task(void *,
- + struct task_struct *task, int cpu);
- +static struct enable_data wakeup_latency_enabled_data = {
- + .latency_type = WAKEUP_LATENCY,
- + .enabled = 0,
- +};
- +static DEFINE_PER_CPU(struct maxlatproc_data, wakeup_maxlatproc);
- +static DEFINE_PER_CPU(struct maxlatproc_data, wakeup_maxlatproc_sharedprio);
- +static DEFINE_PER_CPU(struct task_struct *, wakeup_task);
- +static DEFINE_PER_CPU(int, wakeup_sharedprio);
- +static unsigned long wakeup_pid;
- +#endif
- +
- +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
- +static DEFINE_PER_CPU(struct hist_data, missed_timer_offsets);
- +static char *missed_timer_offsets_dir = "missed_timer_offsets";
- +static notrace void probe_hrtimer_interrupt(void *v, int cpu,
- + long long offset, struct task_struct *curr, struct task_struct *task);
- +static struct enable_data missed_timer_offsets_enabled_data = {
- + .latency_type = MISSED_TIMER_OFFSETS,
- + .enabled = 0,
- +};
- +static DEFINE_PER_CPU(struct maxlatproc_data, missed_timer_offsets_maxlatproc);
- +static unsigned long missed_timer_offsets_pid;
- +#endif
- +
- +#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \
- + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
- +static DEFINE_PER_CPU(struct hist_data, timerandwakeup_latency_hist);
- +static char *timerandwakeup_latency_hist_dir = "timerandwakeup";
- +static struct enable_data timerandwakeup_enabled_data = {
- + .latency_type = TIMERANDWAKEUP_LATENCY,
- + .enabled = 0,
- +};
- +static DEFINE_PER_CPU(struct maxlatproc_data, timerandwakeup_maxlatproc);
- +#endif
- +
- +void notrace latency_hist(int latency_type, int cpu, long latency,
- + long timeroffset, cycle_t stop,
- + struct task_struct *p)
- +{
- + struct hist_data *my_hist;
- +#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \
- + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
- + struct maxlatproc_data *mp = NULL;
- +#endif
- +
- + if (!cpu_possible(cpu) || latency_type < 0 ||
- + latency_type >= MAX_LATENCY_TYPE)
- + return;
- +
- + switch (latency_type) {
- +#ifdef CONFIG_INTERRUPT_OFF_HIST
- + case IRQSOFF_LATENCY:
- + my_hist = &per_cpu(irqsoff_hist, cpu);
- + break;
- +#endif
- +#ifdef CONFIG_PREEMPT_OFF_HIST
- + case PREEMPTOFF_LATENCY:
- + my_hist = &per_cpu(preemptoff_hist, cpu);
- + break;
- +#endif
- +#if defined(CONFIG_PREEMPT_OFF_HIST) && defined(CONFIG_INTERRUPT_OFF_HIST)
- + case PREEMPTIRQSOFF_LATENCY:
- + my_hist = &per_cpu(preemptirqsoff_hist, cpu);
- + break;
- +#endif
- +#ifdef CONFIG_WAKEUP_LATENCY_HIST
- + case WAKEUP_LATENCY:
- + my_hist = &per_cpu(wakeup_latency_hist, cpu);
- + mp = &per_cpu(wakeup_maxlatproc, cpu);
- + break;
- + case WAKEUP_LATENCY_SHAREDPRIO:
- + my_hist = &per_cpu(wakeup_latency_hist_sharedprio, cpu);
- + mp = &per_cpu(wakeup_maxlatproc_sharedprio, cpu);
- + break;
- +#endif
- +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
- + case MISSED_TIMER_OFFSETS:
- + my_hist = &per_cpu(missed_timer_offsets, cpu);
- + mp = &per_cpu(missed_timer_offsets_maxlatproc, cpu);
- + break;
- +#endif
- +#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \
- + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
- + case TIMERANDWAKEUP_LATENCY:
- + my_hist = &per_cpu(timerandwakeup_latency_hist, cpu);
- + mp = &per_cpu(timerandwakeup_maxlatproc, cpu);
- + break;
- +#endif
- +
- + default:
- + return;
- + }
- +
- + latency += my_hist->offset;
- +
- + if (atomic_read(&my_hist->hist_mode) == 0)
- + return;
- +
- + if (latency < 0 || latency >= MAX_ENTRY_NUM) {
- + if (latency < 0)
- + my_hist->below_hist_bound_samples++;
- + else
- + my_hist->above_hist_bound_samples++;
- + } else
- + my_hist->hist_array[latency]++;
- +
- + if (unlikely(latency > my_hist->max_lat ||
- + my_hist->min_lat == LONG_MAX)) {
- +#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \
- + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
- + if (latency_type == WAKEUP_LATENCY ||
- + latency_type == WAKEUP_LATENCY_SHAREDPRIO ||
- + latency_type == MISSED_TIMER_OFFSETS ||
- + latency_type == TIMERANDWAKEUP_LATENCY) {
- + strncpy(mp->comm, p->comm, sizeof(mp->comm));
- + strncpy(mp->current_comm, current->comm,
- + sizeof(mp->current_comm));
- + mp->pid = task_pid_nr(p);
- + mp->current_pid = task_pid_nr(current);
- + mp->prio = p->prio;
- + mp->current_prio = current->prio;
- + mp->latency = latency;
- + mp->timeroffset = timeroffset;
- + mp->timestamp = stop;
- + }
- +#endif
- + my_hist->max_lat = latency;
- + }
- + if (unlikely(latency < my_hist->min_lat))
- + my_hist->min_lat = latency;
- + my_hist->total_samples++;
- + my_hist->accumulate_lat += latency;
- +}
- +
- +static void *l_start(struct seq_file *m, loff_t *pos)
- +{
- + loff_t *index_ptr = NULL;
- + loff_t index = *pos;
- + struct hist_data *my_hist = m->private;
- +
- + if (index == 0) {
- + char minstr[32], avgstr[32], maxstr[32];
- +
- + atomic_dec(&my_hist->hist_mode);
- +
- + if (likely(my_hist->total_samples)) {
- + long avg = (long) div64_s64(my_hist->accumulate_lat,
- + my_hist->total_samples);
- + snprintf(minstr, sizeof(minstr), "%ld",
- + my_hist->min_lat - my_hist->offset);
- + snprintf(avgstr, sizeof(avgstr), "%ld",
- + avg - my_hist->offset);
- + snprintf(maxstr, sizeof(maxstr), "%ld",
- + my_hist->max_lat - my_hist->offset);
- + } else {
- + strcpy(minstr, "<undef>");
- + strcpy(avgstr, minstr);
- + strcpy(maxstr, minstr);
- + }
- +
- + seq_printf(m, "#Minimum latency: %s microseconds\n"
- + "#Average latency: %s microseconds\n"
- + "#Maximum latency: %s microseconds\n"
- + "#Total samples: %llu\n"
- + "#There are %llu samples lower than %ld"
- + " microseconds.\n"
- + "#There are %llu samples greater or equal"
- + " than %ld microseconds.\n"
- + "#usecs\t%16s\n",
- + minstr, avgstr, maxstr,
- + my_hist->total_samples,
- + my_hist->below_hist_bound_samples,
- + -my_hist->offset,
- + my_hist->above_hist_bound_samples,
- + MAX_ENTRY_NUM - my_hist->offset,
- + "samples");
- + }
- + if (index < MAX_ENTRY_NUM) {
- + index_ptr = kmalloc(sizeof(loff_t), GFP_KERNEL);
- + if (index_ptr)
- + *index_ptr = index;
- + }
- +
- + return index_ptr;
- +}
- +
- +static void *l_next(struct seq_file *m, void *p, loff_t *pos)
- +{
- + loff_t *index_ptr = p;
- + struct hist_data *my_hist = m->private;
- +
- + if (++*pos >= MAX_ENTRY_NUM) {
- + atomic_inc(&my_hist->hist_mode);
- + return NULL;
- + }
- + *index_ptr = *pos;
- + return index_ptr;
- +}
- +
- +static void l_stop(struct seq_file *m, void *p)
- +{
- + kfree(p);
- +}
- +
- +static int l_show(struct seq_file *m, void *p)
- +{
- + int index = *(loff_t *) p;
- + struct hist_data *my_hist = m->private;
- +
- + seq_printf(m, "%6ld\t%16llu\n", index - my_hist->offset,
- + my_hist->hist_array[index]);
- + return 0;
- +}
- +
- +static const struct seq_operations latency_hist_seq_op = {
- + .start = l_start,
- + .next = l_next,
- + .stop = l_stop,
- + .show = l_show
- +};
- +
- +static int latency_hist_open(struct inode *inode, struct file *file)
- +{
- + int ret;
- +
- + ret = seq_open(file, &latency_hist_seq_op);
- + if (!ret) {
- + struct seq_file *seq = file->private_data;
- + seq->private = inode->i_private;
- + }
- + return ret;
- +}
- +
- +static const struct file_operations latency_hist_fops = {
- + .open = latency_hist_open,
- + .read = seq_read,
- + .llseek = seq_lseek,
- + .release = seq_release,
- +};
- +
- +#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \
- + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
- +static void clear_maxlatprocdata(struct maxlatproc_data *mp)
- +{
- + mp->comm[0] = mp->current_comm[0] = '\0';
- + mp->prio = mp->current_prio = mp->pid = mp->current_pid =
- + mp->latency = mp->timeroffset = -1;
- + mp->timestamp = 0;
- +}
- +#endif
- +
- +static void hist_reset(struct hist_data *hist)
- +{
- + atomic_dec(&hist->hist_mode);
- +
- + memset(hist->hist_array, 0, sizeof(hist->hist_array));
- + hist->below_hist_bound_samples = 0ULL;
- + hist->above_hist_bound_samples = 0ULL;
- + hist->min_lat = LONG_MAX;
- + hist->max_lat = LONG_MIN;
- + hist->total_samples = 0ULL;
- + hist->accumulate_lat = 0LL;
- +
- + atomic_inc(&hist->hist_mode);
- +}
- +
- +static ssize_t
- +latency_hist_reset(struct file *file, const char __user *a,
- + size_t size, loff_t *off)
- +{
- + int cpu;
- + struct hist_data *hist = NULL;
- +#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \
- + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
- + struct maxlatproc_data *mp = NULL;
- +#endif
- + off_t latency_type = (off_t) file->private_data;
- +
- + for_each_online_cpu(cpu) {
- +
- + switch (latency_type) {
- +#ifdef CONFIG_PREEMPT_OFF_HIST
- + case PREEMPTOFF_LATENCY:
- + hist = &per_cpu(preemptoff_hist, cpu);
- + break;
- +#endif
- +#ifdef CONFIG_INTERRUPT_OFF_HIST
- + case IRQSOFF_LATENCY:
- + hist = &per_cpu(irqsoff_hist, cpu);
- + break;
- +#endif
- +#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST)
- + case PREEMPTIRQSOFF_LATENCY:
- + hist = &per_cpu(preemptirqsoff_hist, cpu);
- + break;
- +#endif
- +#ifdef CONFIG_WAKEUP_LATENCY_HIST
- + case WAKEUP_LATENCY:
- + hist = &per_cpu(wakeup_latency_hist, cpu);
- + mp = &per_cpu(wakeup_maxlatproc, cpu);
- + break;
- + case WAKEUP_LATENCY_SHAREDPRIO:
- + hist = &per_cpu(wakeup_latency_hist_sharedprio, cpu);
- + mp = &per_cpu(wakeup_maxlatproc_sharedprio, cpu);
- + break;
- +#endif
- +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
- + case MISSED_TIMER_OFFSETS:
- + hist = &per_cpu(missed_timer_offsets, cpu);
- + mp = &per_cpu(missed_timer_offsets_maxlatproc, cpu);
- + break;
- +#endif
- +#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \
- + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
- + case TIMERANDWAKEUP_LATENCY:
- + hist = &per_cpu(timerandwakeup_latency_hist, cpu);
- + mp = &per_cpu(timerandwakeup_maxlatproc, cpu);
- + break;
- +#endif
- + }
- +
- + hist_reset(hist);
- +#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \
- + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
- + if (latency_type == WAKEUP_LATENCY ||
- + latency_type == WAKEUP_LATENCY_SHAREDPRIO ||
- + latency_type == MISSED_TIMER_OFFSETS ||
- + latency_type == TIMERANDWAKEUP_LATENCY)
- + clear_maxlatprocdata(mp);
- +#endif
- + }
- +
- + return size;
- +}
- +
- +#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \
- + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
- +static ssize_t
- +show_pid(struct file *file, char __user *ubuf, size_t cnt, loff_t *ppos)
- +{
- + char buf[64];
- + int r;
- + unsigned long *this_pid = file->private_data;
- +
- + r = snprintf(buf, sizeof(buf), "%lu\n", *this_pid);
- + return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
- +}
- +
- +static ssize_t do_pid(struct file *file, const char __user *ubuf,
- + size_t cnt, loff_t *ppos)
- +{
- + char buf[64];
- + unsigned long pid;
- + unsigned long *this_pid = file->private_data;
- +
- + if (cnt >= sizeof(buf))
- + return -EINVAL;
- +
- + if (copy_from_user(&buf, ubuf, cnt))
- + return -EFAULT;
- +
- + buf[cnt] = '\0';
- +
- + if (kstrtoul(buf, 10, &pid))
- + return -EINVAL;
- +
- + *this_pid = pid;
- +
- + return cnt;
- +}
- +#endif
- +
- +#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \
- + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
- +static ssize_t
- +show_maxlatproc(struct file *file, char __user *ubuf, size_t cnt, loff_t *ppos)
- +{
- + int r;
- + struct maxlatproc_data *mp = file->private_data;
- + int strmaxlen = (TASK_COMM_LEN * 2) + (8 * 8);
- + unsigned long long t;
- + unsigned long usecs, secs;
- + char *buf;
- +
- + if (mp->pid == -1 || mp->current_pid == -1) {
- + buf = "(none)\n";
- + return simple_read_from_buffer(ubuf, cnt, ppos, buf,
- + strlen(buf));
- + }
- +
- + buf = kmalloc(strmaxlen, GFP_KERNEL);
- + if (buf == NULL)
- + return -ENOMEM;
- +
- + t = ns2usecs(mp->timestamp);
- + usecs = do_div(t, USEC_PER_SEC);
- + secs = (unsigned long) t;
- + r = snprintf(buf, strmaxlen,
- + "%d %d %ld (%ld) %s <- %d %d %s %lu.%06lu\n", mp->pid,
- + MAX_RT_PRIO-1 - mp->prio, mp->latency, mp->timeroffset, mp->comm,
- + mp->current_pid, MAX_RT_PRIO-1 - mp->current_prio, mp->current_comm,
- + secs, usecs);
- + r = simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
- + kfree(buf);
- + return r;
- +}
- +#endif
- +
- +static ssize_t
- +show_enable(struct file *file, char __user *ubuf, size_t cnt, loff_t *ppos)
- +{
- + char buf[64];
- + struct enable_data *ed = file->private_data;
- + int r;
- +
- + r = snprintf(buf, sizeof(buf), "%d\n", ed->enabled);
- + return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
- +}
- +
- +static ssize_t
- +do_enable(struct file *file, const char __user *ubuf, size_t cnt, loff_t *ppos)
- +{
- + char buf[64];
- + long enable;
- + struct enable_data *ed = file->private_data;
- +
- + if (cnt >= sizeof(buf))
- + return -EINVAL;
- +
- + if (copy_from_user(&buf, ubuf, cnt))
- + return -EFAULT;
- +
- + buf[cnt] = 0;
- +
- + if (kstrtoul(buf, 10, &enable))
- + return -EINVAL;
- +
- + if ((enable && ed->enabled) || (!enable && !ed->enabled))
- + return cnt;
- +
- + if (enable) {
- + int ret;
- +
- + switch (ed->latency_type) {
- +#if defined(CONFIG_INTERRUPT_OFF_HIST) || defined(CONFIG_PREEMPT_OFF_HIST)
- + case PREEMPTIRQSOFF_LATENCY:
- + ret = register_trace_preemptirqsoff_hist(
- + probe_preemptirqsoff_hist, NULL);
- + if (ret) {
- + pr_info("wakeup trace: Couldn't assign "
- + "probe_preemptirqsoff_hist "
- + "to trace_preemptirqsoff_hist\n");
- + return ret;
- + }
- + break;
- +#endif
- +#ifdef CONFIG_WAKEUP_LATENCY_HIST
- + case WAKEUP_LATENCY:
- + ret = register_trace_sched_wakeup(
- + probe_wakeup_latency_hist_start, NULL);
- + if (ret) {
- + pr_info("wakeup trace: Couldn't assign "
- + "probe_wakeup_latency_hist_start "
- + "to trace_sched_wakeup\n");
- + return ret;
- + }
- + ret = register_trace_sched_wakeup_new(
- + probe_wakeup_latency_hist_start, NULL);
- + if (ret) {
- + pr_info("wakeup trace: Couldn't assign "
- + "probe_wakeup_latency_hist_start "
- + "to trace_sched_wakeup_new\n");
- + unregister_trace_sched_wakeup(
- + probe_wakeup_latency_hist_start, NULL);
- + return ret;
- + }
- + ret = register_trace_sched_switch(
- + probe_wakeup_latency_hist_stop, NULL);
- + if (ret) {
- + pr_info("wakeup trace: Couldn't assign "
- + "probe_wakeup_latency_hist_stop "
- + "to trace_sched_switch\n");
- + unregister_trace_sched_wakeup(
- + probe_wakeup_latency_hist_start, NULL);
- + unregister_trace_sched_wakeup_new(
- + probe_wakeup_latency_hist_start, NULL);
- + return ret;
- + }
- + ret = register_trace_sched_migrate_task(
- + probe_sched_migrate_task, NULL);
- + if (ret) {
- + pr_info("wakeup trace: Couldn't assign "
- + "probe_sched_migrate_task "
- + "to trace_sched_migrate_task\n");
- + unregister_trace_sched_wakeup(
- + probe_wakeup_latency_hist_start, NULL);
- + unregister_trace_sched_wakeup_new(
- + probe_wakeup_latency_hist_start, NULL);
- + unregister_trace_sched_switch(
- + probe_wakeup_latency_hist_stop, NULL);
- + return ret;
- + }
- + break;
- +#endif
- +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
- + case MISSED_TIMER_OFFSETS:
- + ret = register_trace_hrtimer_interrupt(
- + probe_hrtimer_interrupt, NULL);
- + if (ret) {
- + pr_info("wakeup trace: Couldn't assign "
- + "probe_hrtimer_interrupt "
- + "to trace_hrtimer_interrupt\n");
- + return ret;
- + }
- + break;
- +#endif
- +#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \
- + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
- + case TIMERANDWAKEUP_LATENCY:
- + if (!wakeup_latency_enabled_data.enabled ||
- + !missed_timer_offsets_enabled_data.enabled)
- + return -EINVAL;
- + break;
- +#endif
- + default:
- + break;
- + }
- + } else {
- + switch (ed->latency_type) {
- +#if defined(CONFIG_INTERRUPT_OFF_HIST) || defined(CONFIG_PREEMPT_OFF_HIST)
- + case PREEMPTIRQSOFF_LATENCY:
- + {
- + int cpu;
- +
- + unregister_trace_preemptirqsoff_hist(
- + probe_preemptirqsoff_hist, NULL);
- + for_each_online_cpu(cpu) {
- +#ifdef CONFIG_INTERRUPT_OFF_HIST
- + per_cpu(hist_irqsoff_counting,
- + cpu) = 0;
- +#endif
- +#ifdef CONFIG_PREEMPT_OFF_HIST
- + per_cpu(hist_preemptoff_counting,
- + cpu) = 0;
- +#endif
- +#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST)
- + per_cpu(hist_preemptirqsoff_counting,
- + cpu) = 0;
- +#endif
- + }
- + }
- + break;
- +#endif
- +#ifdef CONFIG_WAKEUP_LATENCY_HIST
- + case WAKEUP_LATENCY:
- + {
- + int cpu;
- +
- + unregister_trace_sched_wakeup(
- + probe_wakeup_latency_hist_start, NULL);
- + unregister_trace_sched_wakeup_new(
- + probe_wakeup_latency_hist_start, NULL);
- + unregister_trace_sched_switch(
- + probe_wakeup_latency_hist_stop, NULL);
- + unregister_trace_sched_migrate_task(
- + probe_sched_migrate_task, NULL);
- +
- + for_each_online_cpu(cpu) {
- + per_cpu(wakeup_task, cpu) = NULL;
- + per_cpu(wakeup_sharedprio, cpu) = 0;
- + }
- + }
- +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
- + timerandwakeup_enabled_data.enabled = 0;
- +#endif
- + break;
- +#endif
- +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
- + case MISSED_TIMER_OFFSETS:
- + unregister_trace_hrtimer_interrupt(
- + probe_hrtimer_interrupt, NULL);
- +#ifdef CONFIG_WAKEUP_LATENCY_HIST
- + timerandwakeup_enabled_data.enabled = 0;
- +#endif
- + break;
- +#endif
- + default:
- + break;
- + }
- + }
- + ed->enabled = enable;
- + return cnt;
- +}
- +
- +static const struct file_operations latency_hist_reset_fops = {
- + .open = tracing_open_generic,
- + .write = latency_hist_reset,
- +};
- +
- +static const struct file_operations enable_fops = {
- + .open = tracing_open_generic,
- + .read = show_enable,
- + .write = do_enable,
- +};
- +
- +#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \
- + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
- +static const struct file_operations pid_fops = {
- + .open = tracing_open_generic,
- + .read = show_pid,
- + .write = do_pid,
- +};
- +
- +static const struct file_operations maxlatproc_fops = {
- + .open = tracing_open_generic,
- + .read = show_maxlatproc,
- +};
- +#endif
- +
- +#if defined(CONFIG_INTERRUPT_OFF_HIST) || defined(CONFIG_PREEMPT_OFF_HIST)
- +static notrace void probe_preemptirqsoff_hist(void *v, int reason,
- + int starthist)
- +{
- + int cpu = raw_smp_processor_id();
- + int time_set = 0;
- +
- + if (starthist) {
- + cycle_t uninitialized_var(start);
- +
- + if (!preempt_count() && !irqs_disabled())
- + return;
- +
- +#ifdef CONFIG_INTERRUPT_OFF_HIST
- + if ((reason == IRQS_OFF || reason == TRACE_START) &&
- + !per_cpu(hist_irqsoff_counting, cpu)) {
- + per_cpu(hist_irqsoff_counting, cpu) = 1;
- + start = ftrace_now(cpu);
- + time_set++;
- + per_cpu(hist_irqsoff_start, cpu) = start;
- + }
- +#endif
- +
- +#ifdef CONFIG_PREEMPT_OFF_HIST
- + if ((reason == PREEMPT_OFF || reason == TRACE_START) &&
- + !per_cpu(hist_preemptoff_counting, cpu)) {
- + per_cpu(hist_preemptoff_counting, cpu) = 1;
- + if (!(time_set++))
- + start = ftrace_now(cpu);
- + per_cpu(hist_preemptoff_start, cpu) = start;
- + }
- +#endif
- +
- +#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST)
- + if (per_cpu(hist_irqsoff_counting, cpu) &&
- + per_cpu(hist_preemptoff_counting, cpu) &&
- + !per_cpu(hist_preemptirqsoff_counting, cpu)) {
- + per_cpu(hist_preemptirqsoff_counting, cpu) = 1;
- + if (!time_set)
- + start = ftrace_now(cpu);
- + per_cpu(hist_preemptirqsoff_start, cpu) = start;
- + }
- +#endif
- + } else {
- + cycle_t uninitialized_var(stop);
- +
- +#ifdef CONFIG_INTERRUPT_OFF_HIST
- + if ((reason == IRQS_ON || reason == TRACE_STOP) &&
- + per_cpu(hist_irqsoff_counting, cpu)) {
- + cycle_t start = per_cpu(hist_irqsoff_start, cpu);
- +
- + stop = ftrace_now(cpu);
- + time_set++;
- + if (start) {
- + long latency = ((long) (stop - start)) /
- + NSECS_PER_USECS;
- +
- + latency_hist(IRQSOFF_LATENCY, cpu, latency, 0,
- + stop, NULL);
- + }
- + per_cpu(hist_irqsoff_counting, cpu) = 0;
- + }
- +#endif
- +
- +#ifdef CONFIG_PREEMPT_OFF_HIST
- + if ((reason == PREEMPT_ON || reason == TRACE_STOP) &&
- + per_cpu(hist_preemptoff_counting, cpu)) {
- + cycle_t start = per_cpu(hist_preemptoff_start, cpu);
- +
- + if (!(time_set++))
- + stop = ftrace_now(cpu);
- + if (start) {
- + long latency = ((long) (stop - start)) /
- + NSECS_PER_USECS;
- +
- + latency_hist(PREEMPTOFF_LATENCY, cpu, latency,
- + 0, stop, NULL);
- + }
- + per_cpu(hist_preemptoff_counting, cpu) = 0;
- + }
- +#endif
- +
- +#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST)
- + if ((!per_cpu(hist_irqsoff_counting, cpu) ||
- + !per_cpu(hist_preemptoff_counting, cpu)) &&
- + per_cpu(hist_preemptirqsoff_counting, cpu)) {
- + cycle_t start = per_cpu(hist_preemptirqsoff_start, cpu);
- +
- + if (!time_set)
- + stop = ftrace_now(cpu);
- + if (start) {
- + long latency = ((long) (stop - start)) /
- + NSECS_PER_USECS;
- +
- + latency_hist(PREEMPTIRQSOFF_LATENCY, cpu,
- + latency, 0, stop, NULL);
- + }
- + per_cpu(hist_preemptirqsoff_counting, cpu) = 0;
- + }
- +#endif
- + }
- +}
- +#endif
- +
- +#ifdef CONFIG_WAKEUP_LATENCY_HIST
- +static DEFINE_RAW_SPINLOCK(wakeup_lock);
- +static notrace void probe_sched_migrate_task(void *v, struct task_struct *task,
- + int cpu)
- +{
- + int old_cpu = task_cpu(task);
- +
- + if (cpu != old_cpu) {
- + unsigned long flags;
- + struct task_struct *cpu_wakeup_task;
- +
- + raw_spin_lock_irqsave(&wakeup_lock, flags);
- +
- + cpu_wakeup_task = per_cpu(wakeup_task, old_cpu);
- + if (task == cpu_wakeup_task) {
- + put_task_struct(cpu_wakeup_task);
- + per_cpu(wakeup_task, old_cpu) = NULL;
- + cpu_wakeup_task = per_cpu(wakeup_task, cpu) = task;
- + get_task_struct(cpu_wakeup_task);
- + }
- +
- + raw_spin_unlock_irqrestore(&wakeup_lock, flags);
- + }
- +}
- +
- +static notrace void probe_wakeup_latency_hist_start(void *v,
- + struct task_struct *p)
- +{
- + unsigned long flags;
- + struct task_struct *curr = current;
- + int cpu = task_cpu(p);
- + struct task_struct *cpu_wakeup_task;
- +
- + raw_spin_lock_irqsave(&wakeup_lock, flags);
- +
- + cpu_wakeup_task = per_cpu(wakeup_task, cpu);
- +
- + if (wakeup_pid) {
- + if ((cpu_wakeup_task && p->prio == cpu_wakeup_task->prio) ||
- + p->prio == curr->prio)
- + per_cpu(wakeup_sharedprio, cpu) = 1;
- + if (likely(wakeup_pid != task_pid_nr(p)))
- + goto out;
- + } else {
- + if (likely(!rt_task(p)) ||
- + (cpu_wakeup_task && p->prio > cpu_wakeup_task->prio) ||
- + p->prio > curr->prio)
- + goto out;
- + if ((cpu_wakeup_task && p->prio == cpu_wakeup_task->prio) ||
- + p->prio == curr->prio)
- + per_cpu(wakeup_sharedprio, cpu) = 1;
- + }
- +
- + if (cpu_wakeup_task)
- + put_task_struct(cpu_wakeup_task);
- + cpu_wakeup_task = per_cpu(wakeup_task, cpu) = p;
- + get_task_struct(cpu_wakeup_task);
- + cpu_wakeup_task->preempt_timestamp_hist =
- + ftrace_now(raw_smp_processor_id());
- +out:
- + raw_spin_unlock_irqrestore(&wakeup_lock, flags);
- +}
- +
- +static notrace void probe_wakeup_latency_hist_stop(void *v,
- + bool preempt, struct task_struct *prev, struct task_struct *next)
- +{
- + unsigned long flags;
- + int cpu = task_cpu(next);
- + long latency;
- + cycle_t stop;
- + struct task_struct *cpu_wakeup_task;
- +
- + raw_spin_lock_irqsave(&wakeup_lock, flags);
- +
- + cpu_wakeup_task = per_cpu(wakeup_task, cpu);
- +
- + if (cpu_wakeup_task == NULL)
- + goto out;
- +
- + /* Already running? */
- + if (unlikely(current == cpu_wakeup_task))
- + goto out_reset;
- +
- + if (next != cpu_wakeup_task) {
- + if (next->prio < cpu_wakeup_task->prio)
- + goto out_reset;
- +
- + if (next->prio == cpu_wakeup_task->prio)
- + per_cpu(wakeup_sharedprio, cpu) = 1;
- +
- + goto out;
- + }
- +
- + if (current->prio == cpu_wakeup_task->prio)
- + per_cpu(wakeup_sharedprio, cpu) = 1;
- +
- + /*
- + * The task we are waiting for is about to be switched to.
- + * Calculate latency and store it in histogram.
- + */
- + stop = ftrace_now(raw_smp_processor_id());
- +
- + latency = ((long) (stop - next->preempt_timestamp_hist)) /
- + NSECS_PER_USECS;
- +
- + if (per_cpu(wakeup_sharedprio, cpu)) {
- + latency_hist(WAKEUP_LATENCY_SHAREDPRIO, cpu, latency, 0, stop,
- + next);
- + per_cpu(wakeup_sharedprio, cpu) = 0;
- + } else {
- + latency_hist(WAKEUP_LATENCY, cpu, latency, 0, stop, next);
- +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
- + if (timerandwakeup_enabled_data.enabled) {
- + latency_hist(TIMERANDWAKEUP_LATENCY, cpu,
- + next->timer_offset + latency, next->timer_offset,
- + stop, next);
- + }
- +#endif
- + }
- +
- +out_reset:
- +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
- + next->timer_offset = 0;
- +#endif
- + put_task_struct(cpu_wakeup_task);
- + per_cpu(wakeup_task, cpu) = NULL;
- +out:
- + raw_spin_unlock_irqrestore(&wakeup_lock, flags);
- +}
- +#endif
- +
- +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
- +static notrace void probe_hrtimer_interrupt(void *v, int cpu,
- + long long latency_ns, struct task_struct *curr,
- + struct task_struct *task)
- +{
- + if (latency_ns <= 0 && task != NULL && rt_task(task) &&
- + (task->prio < curr->prio ||
- + (task->prio == curr->prio &&
- + !cpumask_test_cpu(cpu, &task->cpus_allowed)))) {
- + long latency;
- + cycle_t now;
- +
- + if (missed_timer_offsets_pid) {
- + if (likely(missed_timer_offsets_pid !=
- + task_pid_nr(task)))
- + return;
- + }
- +
- + now = ftrace_now(cpu);
- + latency = (long) div_s64(-latency_ns, NSECS_PER_USECS);
- + latency_hist(MISSED_TIMER_OFFSETS, cpu, latency, latency, now,
- + task);
- +#ifdef CONFIG_WAKEUP_LATENCY_HIST
- + task->timer_offset = latency;
- +#endif
- + }
- +}
- +#endif
- +
- +static __init int latency_hist_init(void)
- +{
- + struct dentry *latency_hist_root = NULL;
- + struct dentry *dentry;
- +#ifdef CONFIG_WAKEUP_LATENCY_HIST
- + struct dentry *dentry_sharedprio;
- +#endif
- + struct dentry *entry;
- + struct dentry *enable_root;
- + int i = 0;
- + struct hist_data *my_hist;
- + char name[64];
- + char *cpufmt = "CPU%d";
- +#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \
- + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
- + char *cpufmt_maxlatproc = "max_latency-CPU%d";
- + struct maxlatproc_data *mp = NULL;
- +#endif
- +
- + dentry = tracing_init_dentry();
- + latency_hist_root = debugfs_create_dir(latency_hist_dir_root, dentry);
- + enable_root = debugfs_create_dir("enable", latency_hist_root);
- +
- +#ifdef CONFIG_INTERRUPT_OFF_HIST
- + dentry = debugfs_create_dir(irqsoff_hist_dir, latency_hist_root);
- + for_each_possible_cpu(i) {
- + sprintf(name, cpufmt, i);
- + entry = debugfs_create_file(name, 0444, dentry,
- + &per_cpu(irqsoff_hist, i), &latency_hist_fops);
- + my_hist = &per_cpu(irqsoff_hist, i);
- + atomic_set(&my_hist->hist_mode, 1);
- + my_hist->min_lat = LONG_MAX;
- + }
- + entry = debugfs_create_file("reset", 0644, dentry,
- + (void *)IRQSOFF_LATENCY, &latency_hist_reset_fops);
- +#endif
- +
- +#ifdef CONFIG_PREEMPT_OFF_HIST
- + dentry = debugfs_create_dir(preemptoff_hist_dir,
- + latency_hist_root);
- + for_each_possible_cpu(i) {
- + sprintf(name, cpufmt, i);
- + entry = debugfs_create_file(name, 0444, dentry,
- + &per_cpu(preemptoff_hist, i), &latency_hist_fops);
- + my_hist = &per_cpu(preemptoff_hist, i);
- + atomic_set(&my_hist->hist_mode, 1);
- + my_hist->min_lat = LONG_MAX;
- + }
- + entry = debugfs_create_file("reset", 0644, dentry,
- + (void *)PREEMPTOFF_LATENCY, &latency_hist_reset_fops);
- +#endif
- +
- +#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST)
- + dentry = debugfs_create_dir(preemptirqsoff_hist_dir,
- + latency_hist_root);
- + for_each_possible_cpu(i) {
- + sprintf(name, cpufmt, i);
- + entry = debugfs_create_file(name, 0444, dentry,
- + &per_cpu(preemptirqsoff_hist, i), &latency_hist_fops);
- + my_hist = &per_cpu(preemptirqsoff_hist, i);
- + atomic_set(&my_hist->hist_mode, 1);
- + my_hist->min_lat = LONG_MAX;
- + }
- + entry = debugfs_create_file("reset", 0644, dentry,
- + (void *)PREEMPTIRQSOFF_LATENCY, &latency_hist_reset_fops);
- +#endif
- +
- +#if defined(CONFIG_INTERRUPT_OFF_HIST) || defined(CONFIG_PREEMPT_OFF_HIST)
- + entry = debugfs_create_file("preemptirqsoff", 0644,
- + enable_root, (void *)&preemptirqsoff_enabled_data,
- + &enable_fops);
- +#endif
- +
- +#ifdef CONFIG_WAKEUP_LATENCY_HIST
- + dentry = debugfs_create_dir(wakeup_latency_hist_dir,
- + latency_hist_root);
- + dentry_sharedprio = debugfs_create_dir(
- + wakeup_latency_hist_dir_sharedprio, dentry);
- + for_each_possible_cpu(i) {
- + sprintf(name, cpufmt, i);
- +
- + entry = debugfs_create_file(name, 0444, dentry,
- + &per_cpu(wakeup_latency_hist, i),
- + &latency_hist_fops);
- + my_hist = &per_cpu(wakeup_latency_hist, i);
- + atomic_set(&my_hist->hist_mode, 1);
- + my_hist->min_lat = LONG_MAX;
- +
- + entry = debugfs_create_file(name, 0444, dentry_sharedprio,
- + &per_cpu(wakeup_latency_hist_sharedprio, i),
- + &latency_hist_fops);
- + my_hist = &per_cpu(wakeup_latency_hist_sharedprio, i);
- + atomic_set(&my_hist->hist_mode, 1);
- + my_hist->min_lat = LONG_MAX;
- +
- + sprintf(name, cpufmt_maxlatproc, i);
- +
- + mp = &per_cpu(wakeup_maxlatproc, i);
- + entry = debugfs_create_file(name, 0444, dentry, mp,
- + &maxlatproc_fops);
- + clear_maxlatprocdata(mp);
- +
- + mp = &per_cpu(wakeup_maxlatproc_sharedprio, i);
- + entry = debugfs_create_file(name, 0444, dentry_sharedprio, mp,
- + &maxlatproc_fops);
- + clear_maxlatprocdata(mp);
- + }
- + entry = debugfs_create_file("pid", 0644, dentry,
- + (void *)&wakeup_pid, &pid_fops);
- + entry = debugfs_create_file("reset", 0644, dentry,
- + (void *)WAKEUP_LATENCY, &latency_hist_reset_fops);
- + entry = debugfs_create_file("reset", 0644, dentry_sharedprio,
- + (void *)WAKEUP_LATENCY_SHAREDPRIO, &latency_hist_reset_fops);
- + entry = debugfs_create_file("wakeup", 0644,
- + enable_root, (void *)&wakeup_latency_enabled_data,
- + &enable_fops);
- +#endif
- +
- +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
- + dentry = debugfs_create_dir(missed_timer_offsets_dir,
- + latency_hist_root);
- + for_each_possible_cpu(i) {
- + sprintf(name, cpufmt, i);
- + entry = debugfs_create_file(name, 0444, dentry,
- + &per_cpu(missed_timer_offsets, i), &latency_hist_fops);
- + my_hist = &per_cpu(missed_timer_offsets, i);
- + atomic_set(&my_hist->hist_mode, 1);
- + my_hist->min_lat = LONG_MAX;
- +
- + sprintf(name, cpufmt_maxlatproc, i);
- + mp = &per_cpu(missed_timer_offsets_maxlatproc, i);
- + entry = debugfs_create_file(name, 0444, dentry, mp,
- + &maxlatproc_fops);
- + clear_maxlatprocdata(mp);
- + }
- + entry = debugfs_create_file("pid", 0644, dentry,
- + (void *)&missed_timer_offsets_pid, &pid_fops);
- + entry = debugfs_create_file("reset", 0644, dentry,
- + (void *)MISSED_TIMER_OFFSETS, &latency_hist_reset_fops);
- + entry = debugfs_create_file("missed_timer_offsets", 0644,
- + enable_root, (void *)&missed_timer_offsets_enabled_data,
- + &enable_fops);
- +#endif
- +
- +#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \
- + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
- + dentry = debugfs_create_dir(timerandwakeup_latency_hist_dir,
- + latency_hist_root);
- + for_each_possible_cpu(i) {
- + sprintf(name, cpufmt, i);
- + entry = debugfs_create_file(name, 0444, dentry,
- + &per_cpu(timerandwakeup_latency_hist, i),
- + &latency_hist_fops);
- + my_hist = &per_cpu(timerandwakeup_latency_hist, i);
- + atomic_set(&my_hist->hist_mode, 1);
- + my_hist->min_lat = LONG_MAX;
- +
- + sprintf(name, cpufmt_maxlatproc, i);
- + mp = &per_cpu(timerandwakeup_maxlatproc, i);
- + entry = debugfs_create_file(name, 0444, dentry, mp,
- + &maxlatproc_fops);
- + clear_maxlatprocdata(mp);
- + }
- + entry = debugfs_create_file("reset", 0644, dentry,
- + (void *)TIMERANDWAKEUP_LATENCY, &latency_hist_reset_fops);
- + entry = debugfs_create_file("timerandwakeup", 0644,
- + enable_root, (void *)&timerandwakeup_enabled_data,
- + &enable_fops);
- +#endif
- + return 0;
- +}
- +
- +device_initcall(latency_hist_init);
- diff -Nur linux-4.4.28.orig/kernel/trace/Makefile linux-4.4.28/kernel/trace/Makefile
- --- linux-4.4.28.orig/kernel/trace/Makefile 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/trace/Makefile 2016-11-01 21:26:58.804344090 +0100
- @@ -40,6 +40,10 @@
- obj-$(CONFIG_IRQSOFF_TRACER) += trace_irqsoff.o
- obj-$(CONFIG_PREEMPT_TRACER) += trace_irqsoff.o
- obj-$(CONFIG_SCHED_TRACER) += trace_sched_wakeup.o
- +obj-$(CONFIG_INTERRUPT_OFF_HIST) += latency_hist.o
- +obj-$(CONFIG_PREEMPT_OFF_HIST) += latency_hist.o
- +obj-$(CONFIG_WAKEUP_LATENCY_HIST) += latency_hist.o
- +obj-$(CONFIG_MISSED_TIMER_OFFSETS_HIST) += latency_hist.o
- obj-$(CONFIG_NOP_TRACER) += trace_nop.o
- obj-$(CONFIG_STACK_TRACER) += trace_stack.o
- obj-$(CONFIG_MMIOTRACE) += trace_mmiotrace.o
- diff -Nur linux-4.4.28.orig/kernel/trace/trace.c linux-4.4.28/kernel/trace/trace.c
- --- linux-4.4.28.orig/kernel/trace/trace.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/trace/trace.c 2016-11-01 21:26:58.808344343 +0100
- @@ -1652,6 +1652,7 @@
- struct task_struct *tsk = current;
-
- entry->preempt_count = pc & 0xff;
- + entry->preempt_lazy_count = preempt_lazy_count();
- entry->pid = (tsk) ? tsk->pid : 0;
- entry->flags =
- #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT
- @@ -1661,8 +1662,11 @@
- #endif
- ((pc & HARDIRQ_MASK) ? TRACE_FLAG_HARDIRQ : 0) |
- ((pc & SOFTIRQ_MASK) ? TRACE_FLAG_SOFTIRQ : 0) |
- - (tif_need_resched() ? TRACE_FLAG_NEED_RESCHED : 0) |
- + (tif_need_resched_now() ? TRACE_FLAG_NEED_RESCHED : 0) |
- + (need_resched_lazy() ? TRACE_FLAG_NEED_RESCHED_LAZY : 0) |
- (test_preempt_need_resched() ? TRACE_FLAG_PREEMPT_RESCHED : 0);
- +
- + entry->migrate_disable = (tsk) ? __migrate_disabled(tsk) & 0xFF : 0;
- }
- EXPORT_SYMBOL_GPL(tracing_generic_entry_update);
-
- @@ -2555,14 +2559,17 @@
-
- static void print_lat_help_header(struct seq_file *m)
- {
- - seq_puts(m, "# _------=> CPU# \n"
- - "# / _-----=> irqs-off \n"
- - "# | / _----=> need-resched \n"
- - "# || / _---=> hardirq/softirq \n"
- - "# ||| / _--=> preempt-depth \n"
- - "# |||| / delay \n"
- - "# cmd pid ||||| time | caller \n"
- - "# \\ / ||||| \\ | / \n");
- + seq_puts(m, "# _--------=> CPU# \n"
- + "# / _-------=> irqs-off \n"
- + "# | / _------=> need-resched \n"
- + "# || / _-----=> need-resched_lazy \n"
- + "# ||| / _----=> hardirq/softirq \n"
- + "# |||| / _---=> preempt-depth \n"
- + "# ||||| / _--=> preempt-lazy-depth\n"
- + "# |||||| / _-=> migrate-disable \n"
- + "# ||||||| / delay \n"
- + "# cmd pid |||||||| time | caller \n"
- + "# \\ / |||||||| \\ | / \n");
- }
-
- static void print_event_info(struct trace_buffer *buf, struct seq_file *m)
- @@ -2588,11 +2595,14 @@
- print_event_info(buf, m);
- seq_puts(m, "# _-----=> irqs-off\n"
- "# / _----=> need-resched\n"
- - "# | / _---=> hardirq/softirq\n"
- - "# || / _--=> preempt-depth\n"
- - "# ||| / delay\n"
- - "# TASK-PID CPU# |||| TIMESTAMP FUNCTION\n"
- - "# | | | |||| | |\n");
- + "# |/ _-----=> need-resched_lazy\n"
- + "# || / _---=> hardirq/softirq\n"
- + "# ||| / _--=> preempt-depth\n"
- + "# |||| / _-=> preempt-lazy-depth\n"
- + "# ||||| / _-=> migrate-disable \n"
- + "# |||||| / delay\n"
- + "# TASK-PID CPU# ||||||| TIMESTAMP FUNCTION\n"
- + "# | | | ||||||| | |\n");
- }
-
- void
- diff -Nur linux-4.4.28.orig/kernel/trace/trace_events.c linux-4.4.28/kernel/trace/trace_events.c
- --- linux-4.4.28.orig/kernel/trace/trace_events.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/trace/trace_events.c 2016-11-01 21:26:58.808344343 +0100
- @@ -188,6 +188,8 @@
- __common_field(unsigned char, flags);
- __common_field(unsigned char, preempt_count);
- __common_field(int, pid);
- + __common_field(unsigned short, migrate_disable);
- + __common_field(unsigned short, padding);
-
- return ret;
- }
- @@ -244,6 +246,14 @@
-
- local_save_flags(fbuffer->flags);
- fbuffer->pc = preempt_count();
- + /*
- + * If CONFIG_PREEMPT is enabled, then the tracepoint itself disables
- + * preemption (adding one to the preempt_count). Since we are
- + * interested in the preempt_count at the time the tracepoint was
- + * hit, we need to subtract one to offset the increment.
- + */
- + if (IS_ENABLED(CONFIG_PREEMPT))
- + fbuffer->pc--;
- fbuffer->trace_file = trace_file;
-
- fbuffer->event =
- diff -Nur linux-4.4.28.orig/kernel/trace/trace.h linux-4.4.28/kernel/trace/trace.h
- --- linux-4.4.28.orig/kernel/trace/trace.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/trace/trace.h 2016-11-01 21:26:58.808344343 +0100
- @@ -117,6 +117,7 @@
- * NEED_RESCHED - reschedule is requested
- * HARDIRQ - inside an interrupt handler
- * SOFTIRQ - inside a softirq handler
- + * NEED_RESCHED_LAZY - lazy reschedule is requested
- */
- enum trace_flag_type {
- TRACE_FLAG_IRQS_OFF = 0x01,
- @@ -125,6 +126,7 @@
- TRACE_FLAG_HARDIRQ = 0x08,
- TRACE_FLAG_SOFTIRQ = 0x10,
- TRACE_FLAG_PREEMPT_RESCHED = 0x20,
- + TRACE_FLAG_NEED_RESCHED_LAZY = 0x40,
- };
-
- #define TRACE_BUF_SIZE 1024
- diff -Nur linux-4.4.28.orig/kernel/trace/trace_irqsoff.c linux-4.4.28/kernel/trace/trace_irqsoff.c
- --- linux-4.4.28.orig/kernel/trace/trace_irqsoff.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/trace/trace_irqsoff.c 2016-11-01 21:26:58.808344343 +0100
- @@ -13,6 +13,7 @@
- #include <linux/uaccess.h>
- #include <linux/module.h>
- #include <linux/ftrace.h>
- +#include <trace/events/hist.h>
-
- #include "trace.h"
-
- @@ -424,11 +425,13 @@
- {
- if (preempt_trace() || irq_trace())
- start_critical_timing(CALLER_ADDR0, CALLER_ADDR1);
- + trace_preemptirqsoff_hist_rcuidle(TRACE_START, 1);
- }
- EXPORT_SYMBOL_GPL(start_critical_timings);
-
- void stop_critical_timings(void)
- {
- + trace_preemptirqsoff_hist_rcuidle(TRACE_STOP, 0);
- if (preempt_trace() || irq_trace())
- stop_critical_timing(CALLER_ADDR0, CALLER_ADDR1);
- }
- @@ -438,6 +441,7 @@
- #ifdef CONFIG_PROVE_LOCKING
- void time_hardirqs_on(unsigned long a0, unsigned long a1)
- {
- + trace_preemptirqsoff_hist_rcuidle(IRQS_ON, 0);
- if (!preempt_trace() && irq_trace())
- stop_critical_timing(a0, a1);
- }
- @@ -446,6 +450,7 @@
- {
- if (!preempt_trace() && irq_trace())
- start_critical_timing(a0, a1);
- + trace_preemptirqsoff_hist_rcuidle(IRQS_OFF, 1);
- }
-
- #else /* !CONFIG_PROVE_LOCKING */
- @@ -471,6 +476,7 @@
- */
- void trace_hardirqs_on(void)
- {
- + trace_preemptirqsoff_hist(IRQS_ON, 0);
- if (!preempt_trace() && irq_trace())
- stop_critical_timing(CALLER_ADDR0, CALLER_ADDR1);
- }
- @@ -480,11 +486,13 @@
- {
- if (!preempt_trace() && irq_trace())
- start_critical_timing(CALLER_ADDR0, CALLER_ADDR1);
- + trace_preemptirqsoff_hist(IRQS_OFF, 1);
- }
- EXPORT_SYMBOL(trace_hardirqs_off);
-
- __visible void trace_hardirqs_on_caller(unsigned long caller_addr)
- {
- + trace_preemptirqsoff_hist(IRQS_ON, 0);
- if (!preempt_trace() && irq_trace())
- stop_critical_timing(CALLER_ADDR0, caller_addr);
- }
- @@ -494,6 +502,7 @@
- {
- if (!preempt_trace() && irq_trace())
- start_critical_timing(CALLER_ADDR0, caller_addr);
- + trace_preemptirqsoff_hist(IRQS_OFF, 1);
- }
- EXPORT_SYMBOL(trace_hardirqs_off_caller);
-
- @@ -503,12 +512,14 @@
- #ifdef CONFIG_PREEMPT_TRACER
- void trace_preempt_on(unsigned long a0, unsigned long a1)
- {
- + trace_preemptirqsoff_hist(PREEMPT_ON, 0);
- if (preempt_trace() && !irq_trace())
- stop_critical_timing(a0, a1);
- }
-
- void trace_preempt_off(unsigned long a0, unsigned long a1)
- {
- + trace_preemptirqsoff_hist(PREEMPT_ON, 1);
- if (preempt_trace() && !irq_trace())
- start_critical_timing(a0, a1);
- }
- diff -Nur linux-4.4.28.orig/kernel/trace/trace_output.c linux-4.4.28/kernel/trace/trace_output.c
- --- linux-4.4.28.orig/kernel/trace/trace_output.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/trace/trace_output.c 2016-11-01 21:26:58.808344343 +0100
- @@ -386,6 +386,7 @@
- {
- char hardsoft_irq;
- char need_resched;
- + char need_resched_lazy;
- char irqs_off;
- int hardirq;
- int softirq;
- @@ -413,6 +414,8 @@
- need_resched = '.';
- break;
- }
- + need_resched_lazy =
- + (entry->flags & TRACE_FLAG_NEED_RESCHED_LAZY) ? 'L' : '.';
-
- hardsoft_irq =
- (hardirq && softirq) ? 'H' :
- @@ -420,14 +423,25 @@
- softirq ? 's' :
- '.';
-
- - trace_seq_printf(s, "%c%c%c",
- - irqs_off, need_resched, hardsoft_irq);
- + trace_seq_printf(s, "%c%c%c%c",
- + irqs_off, need_resched, need_resched_lazy,
- + hardsoft_irq);
-
- if (entry->preempt_count)
- trace_seq_printf(s, "%x", entry->preempt_count);
- else
- trace_seq_putc(s, '.');
-
- + if (entry->preempt_lazy_count)
- + trace_seq_printf(s, "%x", entry->preempt_lazy_count);
- + else
- + trace_seq_putc(s, '.');
- +
- + if (entry->migrate_disable)
- + trace_seq_printf(s, "%x", entry->migrate_disable);
- + else
- + trace_seq_putc(s, '.');
- +
- return !trace_seq_has_overflowed(s);
- }
-
- diff -Nur linux-4.4.28.orig/kernel/user.c linux-4.4.28/kernel/user.c
- --- linux-4.4.28.orig/kernel/user.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/user.c 2016-11-01 21:26:58.808344343 +0100
- @@ -161,11 +161,11 @@
- if (!up)
- return;
-
- - local_irq_save(flags);
- + local_irq_save_nort(flags);
- if (atomic_dec_and_lock(&up->__count, &uidhash_lock))
- free_user(up, flags);
- else
- - local_irq_restore(flags);
- + local_irq_restore_nort(flags);
- }
-
- struct user_struct *alloc_uid(kuid_t uid)
- diff -Nur linux-4.4.28.orig/kernel/watchdog.c linux-4.4.28/kernel/watchdog.c
- --- linux-4.4.28.orig/kernel/watchdog.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/watchdog.c 2016-11-01 21:26:58.808344343 +0100
- @@ -299,6 +299,8 @@
-
- #ifdef CONFIG_HARDLOCKUP_DETECTOR
-
- +static DEFINE_RAW_SPINLOCK(watchdog_output_lock);
- +
- static struct perf_event_attr wd_hw_attr = {
- .type = PERF_TYPE_HARDWARE,
- .config = PERF_COUNT_HW_CPU_CYCLES,
- @@ -333,6 +335,13 @@
- /* only print hardlockups once */
- if (__this_cpu_read(hard_watchdog_warn) == true)
- return;
- + /*
- + * If early-printk is enabled then make sure we do not
- + * lock up in printk() and kill console logging:
- + */
- + printk_kill();
- +
- + raw_spin_lock(&watchdog_output_lock);
-
- pr_emerg("Watchdog detected hard LOCKUP on cpu %d", this_cpu);
- print_modules();
- @@ -350,8 +359,9 @@
- !test_and_set_bit(0, &hardlockup_allcpu_dumped))
- trigger_allbutself_cpu_backtrace();
-
- + raw_spin_unlock(&watchdog_output_lock);
- if (hardlockup_panic)
- - panic("Hard LOCKUP");
- + nmi_panic(regs, "Hard LOCKUP");
-
- __this_cpu_write(hard_watchdog_warn, true);
- return;
- @@ -497,6 +507,7 @@
- /* kick off the timer for the hardlockup detector */
- hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
- hrtimer->function = watchdog_timer_fn;
- + hrtimer->irqsafe = 1;
-
- /* Enable the perf event */
- watchdog_nmi_enable(cpu);
- diff -Nur linux-4.4.28.orig/kernel/workqueue.c linux-4.4.28/kernel/workqueue.c
- --- linux-4.4.28.orig/kernel/workqueue.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/workqueue.c 2016-11-01 21:26:58.812344600 +0100
- @@ -48,6 +48,8 @@
- #include <linux/nodemask.h>
- #include <linux/moduleparam.h>
- #include <linux/uaccess.h>
- +#include <linux/locallock.h>
- +#include <linux/delay.h>
-
- #include "workqueue_internal.h"
-
- @@ -121,11 +123,16 @@
- * cpu or grabbing pool->lock is enough for read access. If
- * POOL_DISASSOCIATED is set, it's identical to L.
- *
- + * On RT we need the extra protection via rt_lock_idle_list() for
- + * the list manipulations against read access from
- + * wq_worker_sleeping(). All other places are nicely serialized via
- + * pool->lock.
- + *
- * A: pool->attach_mutex protected.
- *
- * PL: wq_pool_mutex protected.
- *
- - * PR: wq_pool_mutex protected for writes. Sched-RCU protected for reads.
- + * PR: wq_pool_mutex protected for writes. RCU protected for reads.
- *
- * PW: wq_pool_mutex and wq->mutex protected for writes. Either for reads.
- *
- @@ -134,7 +141,7 @@
- *
- * WQ: wq->mutex protected.
- *
- - * WR: wq->mutex protected for writes. Sched-RCU protected for reads.
- + * WR: wq->mutex protected for writes. RCU protected for reads.
- *
- * MD: wq_mayday_lock protected.
- */
- @@ -183,7 +190,7 @@
- atomic_t nr_running ____cacheline_aligned_in_smp;
-
- /*
- - * Destruction of pool is sched-RCU protected to allow dereferences
- + * Destruction of pool is RCU protected to allow dereferences
- * from get_work_pool().
- */
- struct rcu_head rcu;
- @@ -212,7 +219,7 @@
- /*
- * Release of unbound pwq is punted to system_wq. See put_pwq()
- * and pwq_unbound_release_workfn() for details. pool_workqueue
- - * itself is also sched-RCU protected so that the first pwq can be
- + * itself is also RCU protected so that the first pwq can be
- * determined without grabbing wq->mutex.
- */
- struct work_struct unbound_release_work;
- @@ -331,6 +338,8 @@
- struct workqueue_struct *system_freezable_power_efficient_wq __read_mostly;
- EXPORT_SYMBOL_GPL(system_freezable_power_efficient_wq);
-
- +static DEFINE_LOCAL_IRQ_LOCK(pendingb_lock);
- +
- static int worker_thread(void *__worker);
- static void workqueue_sysfs_unregister(struct workqueue_struct *wq);
-
- @@ -338,20 +347,20 @@
- #include <trace/events/workqueue.h>
-
- #define assert_rcu_or_pool_mutex() \
- - RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \
- + RCU_LOCKDEP_WARN(!rcu_read_lock_held() && \
- !lockdep_is_held(&wq_pool_mutex), \
- - "sched RCU or wq_pool_mutex should be held")
- + "RCU or wq_pool_mutex should be held")
-
- #define assert_rcu_or_wq_mutex(wq) \
- - RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \
- + RCU_LOCKDEP_WARN(!rcu_read_lock_held() && \
- !lockdep_is_held(&wq->mutex), \
- - "sched RCU or wq->mutex should be held")
- + "RCU or wq->mutex should be held")
-
- #define assert_rcu_or_wq_mutex_or_pool_mutex(wq) \
- - RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \
- + RCU_LOCKDEP_WARN(!rcu_read_lock_held() && \
- !lockdep_is_held(&wq->mutex) && \
- !lockdep_is_held(&wq_pool_mutex), \
- - "sched RCU, wq->mutex or wq_pool_mutex should be held")
- + "RCU, wq->mutex or wq_pool_mutex should be held")
-
- #define for_each_cpu_worker_pool(pool, cpu) \
- for ((pool) = &per_cpu(cpu_worker_pools, cpu)[0]; \
- @@ -363,7 +372,7 @@
- * @pool: iteration cursor
- * @pi: integer used for iteration
- *
- - * This must be called either with wq_pool_mutex held or sched RCU read
- + * This must be called either with wq_pool_mutex held or RCU read
- * locked. If the pool needs to be used beyond the locking in effect, the
- * caller is responsible for guaranteeing that the pool stays online.
- *
- @@ -395,7 +404,7 @@
- * @pwq: iteration cursor
- * @wq: the target workqueue
- *
- - * This must be called either with wq->mutex held or sched RCU read locked.
- + * This must be called either with wq->mutex held or RCU read locked.
- * If the pwq needs to be used beyond the locking in effect, the caller is
- * responsible for guaranteeing that the pwq stays online.
- *
- @@ -407,6 +416,31 @@
- if (({ assert_rcu_or_wq_mutex(wq); false; })) { } \
- else
-
- +#ifdef CONFIG_PREEMPT_RT_BASE
- +static inline void rt_lock_idle_list(struct worker_pool *pool)
- +{
- + preempt_disable();
- +}
- +static inline void rt_unlock_idle_list(struct worker_pool *pool)
- +{
- + preempt_enable();
- +}
- +static inline void sched_lock_idle_list(struct worker_pool *pool) { }
- +static inline void sched_unlock_idle_list(struct worker_pool *pool) { }
- +#else
- +static inline void rt_lock_idle_list(struct worker_pool *pool) { }
- +static inline void rt_unlock_idle_list(struct worker_pool *pool) { }
- +static inline void sched_lock_idle_list(struct worker_pool *pool)
- +{
- + spin_lock_irq(&pool->lock);
- +}
- +static inline void sched_unlock_idle_list(struct worker_pool *pool)
- +{
- + spin_unlock_irq(&pool->lock);
- +}
- +#endif
- +
- +
- #ifdef CONFIG_DEBUG_OBJECTS_WORK
-
- static struct debug_obj_descr work_debug_descr;
- @@ -557,7 +591,7 @@
- * @wq: the target workqueue
- * @node: the node ID
- *
- - * This must be called with any of wq_pool_mutex, wq->mutex or sched RCU
- + * This must be called with any of wq_pool_mutex, wq->mutex or RCU
- * read locked.
- * If the pwq needs to be used beyond the locking in effect, the caller is
- * responsible for guaranteeing that the pwq stays online.
- @@ -701,8 +735,8 @@
- * @work: the work item of interest
- *
- * Pools are created and destroyed under wq_pool_mutex, and allows read
- - * access under sched-RCU read lock. As such, this function should be
- - * called under wq_pool_mutex or with preemption disabled.
- + * access under RCU read lock. As such, this function should be
- + * called under wq_pool_mutex or inside of a rcu_read_lock() region.
- *
- * All fields of the returned pool are accessible as long as the above
- * mentioned locking is in effect. If the returned pool needs to be used
- @@ -839,51 +873,44 @@
- */
- static void wake_up_worker(struct worker_pool *pool)
- {
- - struct worker *worker = first_idle_worker(pool);
- + struct worker *worker;
- +
- + rt_lock_idle_list(pool);
- +
- + worker = first_idle_worker(pool);
-
- if (likely(worker))
- wake_up_process(worker->task);
- +
- + rt_unlock_idle_list(pool);
- }
-
- /**
- - * wq_worker_waking_up - a worker is waking up
- - * @task: task waking up
- - * @cpu: CPU @task is waking up to
- + * wq_worker_running - a worker is running again
- + * @task: task returning from sleep
- *
- - * This function is called during try_to_wake_up() when a worker is
- - * being awoken.
- - *
- - * CONTEXT:
- - * spin_lock_irq(rq->lock)
- + * This function is called when a worker returns from schedule()
- */
- -void wq_worker_waking_up(struct task_struct *task, int cpu)
- +void wq_worker_running(struct task_struct *task)
- {
- struct worker *worker = kthread_data(task);
-
- - if (!(worker->flags & WORKER_NOT_RUNNING)) {
- - WARN_ON_ONCE(worker->pool->cpu != cpu);
- + if (!worker->sleeping)
- + return;
- + if (!(worker->flags & WORKER_NOT_RUNNING))
- atomic_inc(&worker->pool->nr_running);
- - }
- + worker->sleeping = 0;
- }
-
- /**
- * wq_worker_sleeping - a worker is going to sleep
- * @task: task going to sleep
- - * @cpu: CPU in question, must be the current CPU number
- - *
- - * This function is called during schedule() when a busy worker is
- - * going to sleep. Worker on the same cpu can be woken up by
- - * returning pointer to its task.
- - *
- - * CONTEXT:
- - * spin_lock_irq(rq->lock)
- - *
- - * Return:
- - * Worker task on @cpu to wake up, %NULL if none.
- + * This function is called from schedule() when a busy worker is
- + * going to sleep.
- */
- -struct task_struct *wq_worker_sleeping(struct task_struct *task, int cpu)
- +void wq_worker_sleeping(struct task_struct *task)
- {
- - struct worker *worker = kthread_data(task), *to_wakeup = NULL;
- + struct worker *worker = kthread_data(task);
- struct worker_pool *pool;
-
- /*
- @@ -892,29 +919,26 @@
- * checking NOT_RUNNING.
- */
- if (worker->flags & WORKER_NOT_RUNNING)
- - return NULL;
- + return;
-
- pool = worker->pool;
-
- - /* this can only happen on the local cpu */
- - if (WARN_ON_ONCE(cpu != raw_smp_processor_id() || pool->cpu != cpu))
- - return NULL;
- + if (WARN_ON_ONCE(worker->sleeping))
- + return;
- +
- + worker->sleeping = 1;
-
- /*
- * The counterpart of the following dec_and_test, implied mb,
- * worklist not empty test sequence is in insert_work().
- * Please read comment there.
- - *
- - * NOT_RUNNING is clear. This means that we're bound to and
- - * running on the local cpu w/ rq lock held and preemption
- - * disabled, which in turn means that none else could be
- - * manipulating idle_list, so dereferencing idle_list without pool
- - * lock is safe.
- */
- if (atomic_dec_and_test(&pool->nr_running) &&
- - !list_empty(&pool->worklist))
- - to_wakeup = first_idle_worker(pool);
- - return to_wakeup ? to_wakeup->task : NULL;
- + !list_empty(&pool->worklist)) {
- + sched_lock_idle_list(pool);
- + wake_up_worker(pool);
- + sched_unlock_idle_list(pool);
- + }
- }
-
- /**
- @@ -1108,12 +1132,12 @@
- {
- if (pwq) {
- /*
- - * As both pwqs and pools are sched-RCU protected, the
- + * As both pwqs and pools are RCU protected, the
- * following lock operations are safe.
- */
- - spin_lock_irq(&pwq->pool->lock);
- + local_spin_lock_irq(pendingb_lock, &pwq->pool->lock);
- put_pwq(pwq);
- - spin_unlock_irq(&pwq->pool->lock);
- + local_spin_unlock_irq(pendingb_lock, &pwq->pool->lock);
- }
- }
-
- @@ -1215,7 +1239,7 @@
- struct worker_pool *pool;
- struct pool_workqueue *pwq;
-
- - local_irq_save(*flags);
- + local_lock_irqsave(pendingb_lock, *flags);
-
- /* try to steal the timer if it exists */
- if (is_dwork) {
- @@ -1234,6 +1258,7 @@
- if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)))
- return 0;
-
- + rcu_read_lock();
- /*
- * The queueing is in progress, or it is already queued. Try to
- * steal it from ->worklist without clearing WORK_STRUCT_PENDING.
- @@ -1272,14 +1297,16 @@
- set_work_pool_and_keep_pending(work, pool->id);
-
- spin_unlock(&pool->lock);
- + rcu_read_unlock();
- return 1;
- }
- spin_unlock(&pool->lock);
- fail:
- - local_irq_restore(*flags);
- + rcu_read_unlock();
- + local_unlock_irqrestore(pendingb_lock, *flags);
- if (work_is_canceling(work))
- return -ENOENT;
- - cpu_relax();
- + cpu_chill();
- return -EAGAIN;
- }
-
- @@ -1348,7 +1375,7 @@
- * queued or lose PENDING. Grabbing PENDING and queueing should
- * happen with IRQ disabled.
- */
- - WARN_ON_ONCE(!irqs_disabled());
- + WARN_ON_ONCE_NONRT(!irqs_disabled());
-
- debug_work_activate(work);
-
- @@ -1356,6 +1383,8 @@
- if (unlikely(wq->flags & __WQ_DRAINING) &&
- WARN_ON_ONCE(!is_chained_work(wq)))
- return;
- +
- + rcu_read_lock();
- retry:
- if (req_cpu == WORK_CPU_UNBOUND)
- cpu = raw_smp_processor_id();
- @@ -1412,10 +1441,8 @@
- /* pwq determined, queue */
- trace_workqueue_queue_work(req_cpu, pwq, work);
-
- - if (WARN_ON(!list_empty(&work->entry))) {
- - spin_unlock(&pwq->pool->lock);
- - return;
- - }
- + if (WARN_ON(!list_empty(&work->entry)))
- + goto out;
-
- pwq->nr_in_flight[pwq->work_color]++;
- work_flags = work_color_to_flags(pwq->work_color);
- @@ -1431,7 +1458,9 @@
-
- insert_work(pwq, work, worklist, work_flags);
-
- +out:
- spin_unlock(&pwq->pool->lock);
- + rcu_read_unlock();
- }
-
- /**
- @@ -1451,14 +1480,14 @@
- bool ret = false;
- unsigned long flags;
-
- - local_irq_save(flags);
- + local_lock_irqsave(pendingb_lock,flags);
-
- if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) {
- __queue_work(cpu, wq, work);
- ret = true;
- }
-
- - local_irq_restore(flags);
- + local_unlock_irqrestore(pendingb_lock, flags);
- return ret;
- }
- EXPORT_SYMBOL(queue_work_on);
- @@ -1525,14 +1554,14 @@
- unsigned long flags;
-
- /* read the comment in __queue_work() */
- - local_irq_save(flags);
- + local_lock_irqsave(pendingb_lock, flags);
-
- if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) {
- __queue_delayed_work(cpu, wq, dwork, delay);
- ret = true;
- }
-
- - local_irq_restore(flags);
- + local_unlock_irqrestore(pendingb_lock, flags);
- return ret;
- }
- EXPORT_SYMBOL(queue_delayed_work_on);
- @@ -1567,7 +1596,7 @@
-
- if (likely(ret >= 0)) {
- __queue_delayed_work(cpu, wq, dwork, delay);
- - local_irq_restore(flags);
- + local_unlock_irqrestore(pendingb_lock, flags);
- }
-
- /* -ENOENT from try_to_grab_pending() becomes %true */
- @@ -1600,7 +1629,9 @@
- worker->last_active = jiffies;
-
- /* idle_list is LIFO */
- + rt_lock_idle_list(pool);
- list_add(&worker->entry, &pool->idle_list);
- + rt_unlock_idle_list(pool);
-
- if (too_many_workers(pool) && !timer_pending(&pool->idle_timer))
- mod_timer(&pool->idle_timer, jiffies + IDLE_WORKER_TIMEOUT);
- @@ -1633,7 +1664,9 @@
- return;
- worker_clr_flags(worker, WORKER_IDLE);
- pool->nr_idle--;
- + rt_lock_idle_list(pool);
- list_del_init(&worker->entry);
- + rt_unlock_idle_list(pool);
- }
-
- static struct worker *alloc_worker(int node)
- @@ -1799,7 +1832,9 @@
- pool->nr_workers--;
- pool->nr_idle--;
-
- + rt_lock_idle_list(pool);
- list_del_init(&worker->entry);
- + rt_unlock_idle_list(pool);
- worker->flags |= WORKER_DIE;
- wake_up_process(worker->task);
- }
- @@ -2716,14 +2751,14 @@
-
- might_sleep();
-
- - local_irq_disable();
- + rcu_read_lock();
- pool = get_work_pool(work);
- if (!pool) {
- - local_irq_enable();
- + rcu_read_unlock();
- return false;
- }
-
- - spin_lock(&pool->lock);
- + spin_lock_irq(&pool->lock);
- /* see the comment in try_to_grab_pending() with the same code */
- pwq = get_work_pwq(work);
- if (pwq) {
- @@ -2750,10 +2785,11 @@
- else
- lock_map_acquire_read(&pwq->wq->lockdep_map);
- lock_map_release(&pwq->wq->lockdep_map);
- -
- + rcu_read_unlock();
- return true;
- already_gone:
- spin_unlock_irq(&pool->lock);
- + rcu_read_unlock();
- return false;
- }
-
- @@ -2840,7 +2876,7 @@
-
- /* tell other tasks trying to grab @work to back off */
- mark_work_canceling(work);
- - local_irq_restore(flags);
- + local_unlock_irqrestore(pendingb_lock, flags);
-
- flush_work(work);
- clear_work_data(work);
- @@ -2895,10 +2931,10 @@
- */
- bool flush_delayed_work(struct delayed_work *dwork)
- {
- - local_irq_disable();
- + local_lock_irq(pendingb_lock);
- if (del_timer_sync(&dwork->timer))
- __queue_work(dwork->cpu, dwork->wq, &dwork->work);
- - local_irq_enable();
- + local_unlock_irq(pendingb_lock);
- return flush_work(&dwork->work);
- }
- EXPORT_SYMBOL(flush_delayed_work);
- @@ -2933,7 +2969,7 @@
-
- set_work_pool_and_clear_pending(&dwork->work,
- get_work_pool_id(&dwork->work));
- - local_irq_restore(flags);
- + local_unlock_irqrestore(pendingb_lock, flags);
- return ret;
- }
- EXPORT_SYMBOL(cancel_delayed_work);
- @@ -3161,7 +3197,7 @@
- * put_unbound_pool - put a worker_pool
- * @pool: worker_pool to put
- *
- - * Put @pool. If its refcnt reaches zero, it gets destroyed in sched-RCU
- + * Put @pool. If its refcnt reaches zero, it gets destroyed in RCU
- * safe manner. get_unbound_pool() calls this function on its failure path
- * and this function should be able to release pools which went through,
- * successfully or not, init_worker_pool().
- @@ -3215,8 +3251,8 @@
- del_timer_sync(&pool->idle_timer);
- del_timer_sync(&pool->mayday_timer);
-
- - /* sched-RCU protected to allow dereferences from get_work_pool() */
- - call_rcu_sched(&pool->rcu, rcu_free_pool);
- + /* RCU protected to allow dereferences from get_work_pool() */
- + call_rcu(&pool->rcu, rcu_free_pool);
- }
-
- /**
- @@ -3323,14 +3359,14 @@
- put_unbound_pool(pool);
- mutex_unlock(&wq_pool_mutex);
-
- - call_rcu_sched(&pwq->rcu, rcu_free_pwq);
- + call_rcu(&pwq->rcu, rcu_free_pwq);
-
- /*
- * If we're the last pwq going away, @wq is already dead and no one
- * is gonna access it anymore. Schedule RCU free.
- */
- if (is_last)
- - call_rcu_sched(&wq->rcu, rcu_free_wq);
- + call_rcu(&wq->rcu, rcu_free_wq);
- }
-
- /**
- @@ -3983,7 +4019,7 @@
- * The base ref is never dropped on per-cpu pwqs. Directly
- * schedule RCU free.
- */
- - call_rcu_sched(&wq->rcu, rcu_free_wq);
- + call_rcu(&wq->rcu, rcu_free_wq);
- } else {
- /*
- * We're the sole accessor of @wq at this point. Directly
- @@ -4076,7 +4112,8 @@
- struct pool_workqueue *pwq;
- bool ret;
-
- - rcu_read_lock_sched();
- + rcu_read_lock();
- + preempt_disable();
-
- if (cpu == WORK_CPU_UNBOUND)
- cpu = smp_processor_id();
- @@ -4087,7 +4124,8 @@
- pwq = unbound_pwq_by_node(wq, cpu_to_node(cpu));
-
- ret = !list_empty(&pwq->delayed_works);
- - rcu_read_unlock_sched();
- + preempt_enable();
- + rcu_read_unlock();
-
- return ret;
- }
- @@ -4113,15 +4151,15 @@
- if (work_pending(work))
- ret |= WORK_BUSY_PENDING;
-
- - local_irq_save(flags);
- + rcu_read_lock();
- pool = get_work_pool(work);
- if (pool) {
- - spin_lock(&pool->lock);
- + spin_lock_irqsave(&pool->lock, flags);
- if (find_worker_executing_work(pool, work))
- ret |= WORK_BUSY_RUNNING;
- - spin_unlock(&pool->lock);
- + spin_unlock_irqrestore(&pool->lock, flags);
- }
- - local_irq_restore(flags);
- + rcu_read_unlock();
-
- return ret;
- }
- @@ -4310,7 +4348,7 @@
- unsigned long flags;
- int pi;
-
- - rcu_read_lock_sched();
- + rcu_read_lock();
-
- pr_info("Showing busy workqueues and worker pools:\n");
-
- @@ -4361,7 +4399,7 @@
- spin_unlock_irqrestore(&pool->lock, flags);
- }
-
- - rcu_read_unlock_sched();
- + rcu_read_unlock();
- }
-
- /*
- @@ -4722,16 +4760,16 @@
- * nr_active is monotonically decreasing. It's safe
- * to peek without lock.
- */
- - rcu_read_lock_sched();
- + rcu_read_lock();
- for_each_pwq(pwq, wq) {
- WARN_ON_ONCE(pwq->nr_active < 0);
- if (pwq->nr_active) {
- busy = true;
- - rcu_read_unlock_sched();
- + rcu_read_unlock();
- goto out_unlock;
- }
- }
- - rcu_read_unlock_sched();
- + rcu_read_unlock();
- }
- out_unlock:
- mutex_unlock(&wq_pool_mutex);
- @@ -4921,7 +4959,8 @@
- const char *delim = "";
- int node, written = 0;
-
- - rcu_read_lock_sched();
- + get_online_cpus();
- + rcu_read_lock();
- for_each_node(node) {
- written += scnprintf(buf + written, PAGE_SIZE - written,
- "%s%d:%d", delim, node,
- @@ -4929,7 +4968,8 @@
- delim = " ";
- }
- written += scnprintf(buf + written, PAGE_SIZE - written, "\n");
- - rcu_read_unlock_sched();
- + rcu_read_unlock();
- + put_online_cpus();
-
- return written;
- }
- diff -Nur linux-4.4.28.orig/kernel/workqueue_internal.h linux-4.4.28/kernel/workqueue_internal.h
- --- linux-4.4.28.orig/kernel/workqueue_internal.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/kernel/workqueue_internal.h 2016-11-01 21:26:58.812344600 +0100
- @@ -43,6 +43,7 @@
- unsigned long last_active; /* L: last active timestamp */
- unsigned int flags; /* X: flags */
- int id; /* I: worker id */
- + int sleeping; /* None */
-
- /*
- * Opaque string set with work_set_desc(). Printed out with task
- @@ -68,7 +69,7 @@
- * Scheduler hooks for concurrency managed workqueue. Only to be used from
- * sched/core.c and workqueue.c.
- */
- -void wq_worker_waking_up(struct task_struct *task, int cpu);
- -struct task_struct *wq_worker_sleeping(struct task_struct *task, int cpu);
- +void wq_worker_running(struct task_struct *task);
- +void wq_worker_sleeping(struct task_struct *task);
-
- #endif /* _KERNEL_WORKQUEUE_INTERNAL_H */
- diff -Nur linux-4.4.28.orig/lib/debugobjects.c linux-4.4.28/lib/debugobjects.c
- --- linux-4.4.28.orig/lib/debugobjects.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/lib/debugobjects.c 2016-11-01 21:26:58.812344600 +0100
- @@ -309,7 +309,10 @@
- struct debug_obj *obj;
- unsigned long flags;
-
- - fill_pool();
- +#ifdef CONFIG_PREEMPT_RT_FULL
- + if (preempt_count() == 0 && !irqs_disabled())
- +#endif
- + fill_pool();
-
- db = get_bucket((unsigned long) addr);
-
- diff -Nur linux-4.4.28.orig/lib/idr.c linux-4.4.28/lib/idr.c
- --- linux-4.4.28.orig/lib/idr.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/lib/idr.c 2016-11-01 21:26:58.812344600 +0100
- @@ -30,6 +30,7 @@
- #include <linux/idr.h>
- #include <linux/spinlock.h>
- #include <linux/percpu.h>
- +#include <linux/locallock.h>
-
- #define MAX_IDR_SHIFT (sizeof(int) * 8 - 1)
- #define MAX_IDR_BIT (1U << MAX_IDR_SHIFT)
- @@ -45,6 +46,37 @@
- static DEFINE_PER_CPU(int, idr_preload_cnt);
- static DEFINE_SPINLOCK(simple_ida_lock);
-
- +#ifdef CONFIG_PREEMPT_RT_FULL
- +static DEFINE_LOCAL_IRQ_LOCK(idr_lock);
- +
- +static inline void idr_preload_lock(void)
- +{
- + local_lock(idr_lock);
- +}
- +
- +static inline void idr_preload_unlock(void)
- +{
- + local_unlock(idr_lock);
- +}
- +
- +void idr_preload_end(void)
- +{
- + idr_preload_unlock();
- +}
- +EXPORT_SYMBOL(idr_preload_end);
- +#else
- +static inline void idr_preload_lock(void)
- +{
- + preempt_disable();
- +}
- +
- +static inline void idr_preload_unlock(void)
- +{
- + preempt_enable();
- +}
- +#endif
- +
- +
- /* the maximum ID which can be allocated given idr->layers */
- static int idr_max(int layers)
- {
- @@ -115,14 +147,14 @@
- * context. See idr_preload() for details.
- */
- if (!in_interrupt()) {
- - preempt_disable();
- + idr_preload_lock();
- new = __this_cpu_read(idr_preload_head);
- if (new) {
- __this_cpu_write(idr_preload_head, new->ary[0]);
- __this_cpu_dec(idr_preload_cnt);
- new->ary[0] = NULL;
- }
- - preempt_enable();
- + idr_preload_unlock();
- if (new)
- return new;
- }
- @@ -366,7 +398,6 @@
- idr_mark_full(pa, id);
- }
-
- -
- /**
- * idr_preload - preload for idr_alloc()
- * @gfp_mask: allocation mask to use for preloading
- @@ -401,7 +432,7 @@
- WARN_ON_ONCE(in_interrupt());
- might_sleep_if(gfpflags_allow_blocking(gfp_mask));
-
- - preempt_disable();
- + idr_preload_lock();
-
- /*
- * idr_alloc() is likely to succeed w/o full idr_layer buffer and
- @@ -413,9 +444,9 @@
- while (__this_cpu_read(idr_preload_cnt) < MAX_IDR_FREE) {
- struct idr_layer *new;
-
- - preempt_enable();
- + idr_preload_unlock();
- new = kmem_cache_zalloc(idr_layer_cache, gfp_mask);
- - preempt_disable();
- + idr_preload_lock();
- if (!new)
- break;
-
- diff -Nur linux-4.4.28.orig/lib/Kconfig linux-4.4.28/lib/Kconfig
- --- linux-4.4.28.orig/lib/Kconfig 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/lib/Kconfig 2016-11-01 21:26:58.812344600 +0100
- @@ -397,6 +397,7 @@
-
- config CPUMASK_OFFSTACK
- bool "Force CPU masks off stack" if DEBUG_PER_CPU_MAPS
- + depends on !PREEMPT_RT_FULL
- help
- Use dynamic allocation for cpumask_var_t, instead of putting
- them on the stack. This is a bit more expensive, but avoids
- diff -Nur linux-4.4.28.orig/lib/locking-selftest.c linux-4.4.28/lib/locking-selftest.c
- --- linux-4.4.28.orig/lib/locking-selftest.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/lib/locking-selftest.c 2016-11-01 21:26:58.816344864 +0100
- @@ -590,6 +590,8 @@
- #include "locking-selftest-spin-hardirq.h"
- GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_hard_spin)
-
- +#ifndef CONFIG_PREEMPT_RT_FULL
- +
- #include "locking-selftest-rlock-hardirq.h"
- GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_hard_rlock)
-
- @@ -605,9 +607,12 @@
- #include "locking-selftest-wlock-softirq.h"
- GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_soft_wlock)
-
- +#endif
- +
- #undef E1
- #undef E2
-
- +#ifndef CONFIG_PREEMPT_RT_FULL
- /*
- * Enabling hardirqs with a softirq-safe lock held:
- */
- @@ -640,6 +645,8 @@
- #undef E1
- #undef E2
-
- +#endif
- +
- /*
- * Enabling irqs with an irq-safe lock held:
- */
- @@ -663,6 +670,8 @@
- #include "locking-selftest-spin-hardirq.h"
- GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_hard_spin)
-
- +#ifndef CONFIG_PREEMPT_RT_FULL
- +
- #include "locking-selftest-rlock-hardirq.h"
- GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_hard_rlock)
-
- @@ -678,6 +687,8 @@
- #include "locking-selftest-wlock-softirq.h"
- GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_soft_wlock)
-
- +#endif
- +
- #undef E1
- #undef E2
-
- @@ -709,6 +720,8 @@
- #include "locking-selftest-spin-hardirq.h"
- GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_hard_spin)
-
- +#ifndef CONFIG_PREEMPT_RT_FULL
- +
- #include "locking-selftest-rlock-hardirq.h"
- GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_hard_rlock)
-
- @@ -724,6 +737,8 @@
- #include "locking-selftest-wlock-softirq.h"
- GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_soft_wlock)
-
- +#endif
- +
- #undef E1
- #undef E2
- #undef E3
- @@ -757,6 +772,8 @@
- #include "locking-selftest-spin-hardirq.h"
- GENERATE_PERMUTATIONS_3_EVENTS(irqsafe4_hard_spin)
-
- +#ifndef CONFIG_PREEMPT_RT_FULL
- +
- #include "locking-selftest-rlock-hardirq.h"
- GENERATE_PERMUTATIONS_3_EVENTS(irqsafe4_hard_rlock)
-
- @@ -772,10 +789,14 @@
- #include "locking-selftest-wlock-softirq.h"
- GENERATE_PERMUTATIONS_3_EVENTS(irqsafe4_soft_wlock)
-
- +#endif
- +
- #undef E1
- #undef E2
- #undef E3
-
- +#ifndef CONFIG_PREEMPT_RT_FULL
- +
- /*
- * read-lock / write-lock irq inversion.
- *
- @@ -838,6 +859,10 @@
- #undef E2
- #undef E3
-
- +#endif
- +
- +#ifndef CONFIG_PREEMPT_RT_FULL
- +
- /*
- * read-lock / write-lock recursion that is actually safe.
- */
- @@ -876,6 +901,8 @@
- #undef E2
- #undef E3
-
- +#endif
- +
- /*
- * read-lock / write-lock recursion that is unsafe.
- */
- @@ -1858,6 +1885,7 @@
-
- printk(" --------------------------------------------------------------------------\n");
-
- +#ifndef CONFIG_PREEMPT_RT_FULL
- /*
- * irq-context testcases:
- */
- @@ -1870,6 +1898,28 @@
-
- DO_TESTCASE_6x2("irq read-recursion", irq_read_recursion);
- // DO_TESTCASE_6x2B("irq read-recursion #2", irq_read_recursion2);
- +#else
- + /* On -rt, we only do hardirq context test for raw spinlock */
- + DO_TESTCASE_1B("hard-irqs-on + irq-safe-A", irqsafe1_hard_spin, 12);
- + DO_TESTCASE_1B("hard-irqs-on + irq-safe-A", irqsafe1_hard_spin, 21);
- +
- + DO_TESTCASE_1B("hard-safe-A + irqs-on", irqsafe2B_hard_spin, 12);
- + DO_TESTCASE_1B("hard-safe-A + irqs-on", irqsafe2B_hard_spin, 21);
- +
- + DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 123);
- + DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 132);
- + DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 213);
- + DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 231);
- + DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 312);
- + DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 321);
- +
- + DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 123);
- + DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 132);
- + DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 213);
- + DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 231);
- + DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 312);
- + DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 321);
- +#endif
-
- ww_tests();
-
- diff -Nur linux-4.4.28.orig/lib/percpu_ida.c linux-4.4.28/lib/percpu_ida.c
- --- linux-4.4.28.orig/lib/percpu_ida.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/lib/percpu_ida.c 2016-11-01 21:26:58.816344864 +0100
- @@ -26,6 +26,9 @@
- #include <linux/string.h>
- #include <linux/spinlock.h>
- #include <linux/percpu_ida.h>
- +#include <linux/locallock.h>
- +
- +static DEFINE_LOCAL_IRQ_LOCK(irq_off_lock);
-
- struct percpu_ida_cpu {
- /*
- @@ -148,13 +151,13 @@
- unsigned long flags;
- int tag;
-
- - local_irq_save(flags);
- + local_lock_irqsave(irq_off_lock, flags);
- tags = this_cpu_ptr(pool->tag_cpu);
-
- /* Fastpath */
- tag = alloc_local_tag(tags);
- if (likely(tag >= 0)) {
- - local_irq_restore(flags);
- + local_unlock_irqrestore(irq_off_lock, flags);
- return tag;
- }
-
- @@ -173,6 +176,7 @@
-
- if (!tags->nr_free)
- alloc_global_tags(pool, tags);
- +
- if (!tags->nr_free)
- steal_tags(pool, tags);
-
- @@ -184,7 +188,7 @@
- }
-
- spin_unlock(&pool->lock);
- - local_irq_restore(flags);
- + local_unlock_irqrestore(irq_off_lock, flags);
-
- if (tag >= 0 || state == TASK_RUNNING)
- break;
- @@ -196,7 +200,7 @@
-
- schedule();
-
- - local_irq_save(flags);
- + local_lock_irqsave(irq_off_lock, flags);
- tags = this_cpu_ptr(pool->tag_cpu);
- }
- if (state != TASK_RUNNING)
- @@ -221,7 +225,7 @@
-
- BUG_ON(tag >= pool->nr_tags);
-
- - local_irq_save(flags);
- + local_lock_irqsave(irq_off_lock, flags);
- tags = this_cpu_ptr(pool->tag_cpu);
-
- spin_lock(&tags->lock);
- @@ -253,7 +257,7 @@
- spin_unlock(&pool->lock);
- }
-
- - local_irq_restore(flags);
- + local_unlock_irqrestore(irq_off_lock, flags);
- }
- EXPORT_SYMBOL_GPL(percpu_ida_free);
-
- @@ -345,7 +349,7 @@
- struct percpu_ida_cpu *remote;
- unsigned cpu, i, err = 0;
-
- - local_irq_save(flags);
- + local_lock_irqsave(irq_off_lock, flags);
- for_each_possible_cpu(cpu) {
- remote = per_cpu_ptr(pool->tag_cpu, cpu);
- spin_lock(&remote->lock);
- @@ -367,7 +371,7 @@
- }
- spin_unlock(&pool->lock);
- out:
- - local_irq_restore(flags);
- + local_unlock_irqrestore(irq_off_lock, flags);
- return err;
- }
- EXPORT_SYMBOL_GPL(percpu_ida_for_each_free);
- diff -Nur linux-4.4.28.orig/lib/radix-tree.c linux-4.4.28/lib/radix-tree.c
- --- linux-4.4.28.orig/lib/radix-tree.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/lib/radix-tree.c 2016-11-01 21:26:58.816344864 +0100
- @@ -196,13 +196,14 @@
- * succeed in getting a node here (and never reach
- * kmem_cache_alloc)
- */
- - rtp = this_cpu_ptr(&radix_tree_preloads);
- + rtp = &get_cpu_var(radix_tree_preloads);
- if (rtp->nr) {
- ret = rtp->nodes;
- rtp->nodes = ret->private_data;
- ret->private_data = NULL;
- rtp->nr--;
- }
- + put_cpu_var(radix_tree_preloads);
- /*
- * Update the allocation stack trace as this is more useful
- * for debugging.
- @@ -242,6 +243,7 @@
- call_rcu(&node->rcu_head, radix_tree_node_rcu_free);
- }
-
- +#ifndef CONFIG_PREEMPT_RT_FULL
- /*
- * Load up this CPU's radix_tree_node buffer with sufficient objects to
- * ensure that the addition of a single element in the tree cannot fail. On
- @@ -310,6 +312,7 @@
- return 0;
- }
- EXPORT_SYMBOL(radix_tree_maybe_preload);
- +#endif
-
- /*
- * Return the maximum key which can be store into a
- diff -Nur linux-4.4.28.orig/lib/rbtree.c linux-4.4.28/lib/rbtree.c
- --- linux-4.4.28.orig/lib/rbtree.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/lib/rbtree.c 2016-11-01 21:26:58.816344864 +0100
- @@ -23,6 +23,7 @@
-
- #include <linux/rbtree_augmented.h>
- #include <linux/export.h>
- +#include <linux/rcupdate.h>
-
- /*
- * red-black trees properties: http://en.wikipedia.org/wiki/Rbtree
- @@ -590,3 +591,13 @@
- return rb_left_deepest_node(root->rb_node);
- }
- EXPORT_SYMBOL(rb_first_postorder);
- +
- +void rb_link_node_rcu(struct rb_node *node, struct rb_node *parent,
- + struct rb_node **rb_link)
- +{
- + node->__rb_parent_color = (unsigned long)parent;
- + node->rb_left = node->rb_right = NULL;
- +
- + rcu_assign_pointer(*rb_link, node);
- +}
- +EXPORT_SYMBOL(rb_link_node_rcu);
- diff -Nur linux-4.4.28.orig/lib/scatterlist.c linux-4.4.28/lib/scatterlist.c
- --- linux-4.4.28.orig/lib/scatterlist.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/lib/scatterlist.c 2016-11-01 21:26:58.816344864 +0100
- @@ -620,7 +620,7 @@
- flush_kernel_dcache_page(miter->page);
-
- if (miter->__flags & SG_MITER_ATOMIC) {
- - WARN_ON_ONCE(preemptible());
- + WARN_ON_ONCE(!pagefault_disabled());
- kunmap_atomic(miter->addr);
- } else
- kunmap(miter->page);
- @@ -664,7 +664,7 @@
- if (!sg_miter_skip(&miter, skip))
- return false;
-
- - local_irq_save(flags);
- + local_irq_save_nort(flags);
-
- while (sg_miter_next(&miter) && offset < buflen) {
- unsigned int len;
- @@ -681,7 +681,7 @@
-
- sg_miter_stop(&miter);
-
- - local_irq_restore(flags);
- + local_irq_restore_nort(flags);
- return offset;
- }
- EXPORT_SYMBOL(sg_copy_buffer);
- diff -Nur linux-4.4.28.orig/lib/smp_processor_id.c linux-4.4.28/lib/smp_processor_id.c
- --- linux-4.4.28.orig/lib/smp_processor_id.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/lib/smp_processor_id.c 2016-11-01 21:26:58.816344864 +0100
- @@ -39,8 +39,9 @@
- if (!printk_ratelimit())
- goto out_enable;
-
- - printk(KERN_ERR "BUG: using %s%s() in preemptible [%08x] code: %s/%d\n",
- - what1, what2, preempt_count() - 1, current->comm, current->pid);
- + printk(KERN_ERR "BUG: using %s%s() in preemptible [%08x %08x] code: %s/%d\n",
- + what1, what2, preempt_count() - 1, __migrate_disabled(current),
- + current->comm, current->pid);
-
- print_symbol("caller is %s\n", (long)__builtin_return_address(0));
- dump_stack();
- diff -Nur linux-4.4.28.orig/Makefile linux-4.4.28/Makefile
- --- linux-4.4.28.orig/Makefile 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/Makefile 2016-11-01 21:26:56.688207681 +0100
- @@ -394,7 +394,7 @@
- KBUILD_CFLAGS := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \
- -fno-strict-aliasing -fno-common \
- -Werror-implicit-function-declaration \
- - -Wno-format-security \
- + -Wno-format-security -fno-PIE \
- -std=gnu89
-
- KBUILD_AFLAGS_KERNEL :=
- @@ -783,6 +783,9 @@
- # Prohibit date/time macros, which would make the build non-deterministic
- KBUILD_CFLAGS += $(call cc-option,-Werror=date-time)
-
- +# enforce correct pointer usage
- +KBUILD_CFLAGS += $(call cc-option,-Werror=incompatible-pointer-types)
- +
- # use the deterministic mode of AR if available
- KBUILD_ARFLAGS := $(call ar-option,D)
-
- diff -Nur linux-4.4.28.orig/mm/backing-dev.c linux-4.4.28/mm/backing-dev.c
- --- linux-4.4.28.orig/mm/backing-dev.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/mm/backing-dev.c 2016-11-01 21:26:58.816344864 +0100
- @@ -457,9 +457,9 @@
- {
- unsigned long flags;
-
- - local_irq_save(flags);
- + local_irq_save_nort(flags);
- if (!atomic_dec_and_lock(&congested->refcnt, &cgwb_lock)) {
- - local_irq_restore(flags);
- + local_irq_restore_nort(flags);
- return;
- }
-
- diff -Nur linux-4.4.28.orig/mm/compaction.c linux-4.4.28/mm/compaction.c
- --- linux-4.4.28.orig/mm/compaction.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/mm/compaction.c 2016-11-01 21:26:58.816344864 +0100
- @@ -1430,10 +1430,12 @@
- cc->migrate_pfn & ~((1UL << cc->order) - 1);
-
- if (cc->last_migrated_pfn < current_block_start) {
- - cpu = get_cpu();
- + cpu = get_cpu_light();
- + local_lock_irq(swapvec_lock);
- lru_add_drain_cpu(cpu);
- + local_unlock_irq(swapvec_lock);
- drain_local_pages(zone);
- - put_cpu();
- + put_cpu_light();
- /* No more flushing until we migrate again */
- cc->last_migrated_pfn = 0;
- }
- diff -Nur linux-4.4.28.orig/mm/filemap.c linux-4.4.28/mm/filemap.c
- --- linux-4.4.28.orig/mm/filemap.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/mm/filemap.c 2016-11-01 21:29:56.667809032 +0100
- @@ -144,9 +144,12 @@
- * node->private_list is protected by
- * mapping->tree_lock.
- */
- - if (!list_empty(&node->private_list))
- - list_lru_del(&workingset_shadow_nodes,
- - &node->private_list);
- + if (!list_empty(&node->private_list)) {
- + local_lock(workingset_shadow_lock);
- + list_lru_del(&__workingset_shadow_nodes,
- + &node->private_list);
- + local_unlock(workingset_shadow_lock);
- + }
- }
- return 0;
- }
- @@ -218,7 +221,9 @@
- if (!workingset_node_pages(node) &&
- list_empty(&node->private_list)) {
- node->private_data = mapping;
- - list_lru_add(&workingset_shadow_nodes, &node->private_list);
- + local_lock(workingset_shadow_lock);
- + list_lru_add(&__workingset_shadow_nodes, &node->private_list);
- + local_unlock(workingset_shadow_lock);
- }
- }
-
- diff -Nur linux-4.4.28.orig/mm/highmem.c linux-4.4.28/mm/highmem.c
- --- linux-4.4.28.orig/mm/highmem.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/mm/highmem.c 2016-11-01 21:26:58.820345117 +0100
- @@ -29,10 +29,11 @@
- #include <linux/kgdb.h>
- #include <asm/tlbflush.h>
-
- -
- +#ifndef CONFIG_PREEMPT_RT_FULL
- #if defined(CONFIG_HIGHMEM) || defined(CONFIG_X86_32)
- DEFINE_PER_CPU(int, __kmap_atomic_idx);
- #endif
- +#endif
-
- /*
- * Virtual_count is not a pure "count".
- @@ -107,8 +108,9 @@
- unsigned long totalhigh_pages __read_mostly;
- EXPORT_SYMBOL(totalhigh_pages);
-
- -
- +#ifndef CONFIG_PREEMPT_RT_FULL
- EXPORT_PER_CPU_SYMBOL(__kmap_atomic_idx);
- +#endif
-
- unsigned int nr_free_highpages (void)
- {
- diff -Nur linux-4.4.28.orig/mm/Kconfig linux-4.4.28/mm/Kconfig
- --- linux-4.4.28.orig/mm/Kconfig 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/mm/Kconfig 2016-11-01 21:26:58.816344864 +0100
- @@ -392,7 +392,7 @@
-
- config TRANSPARENT_HUGEPAGE
- bool "Transparent Hugepage Support"
- - depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE
- + depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE && !PREEMPT_RT_FULL
- select COMPACTION
- help
- Transparent Hugepages allows the kernel to use huge pages and
- diff -Nur linux-4.4.28.orig/mm/memcontrol.c linux-4.4.28/mm/memcontrol.c
- --- linux-4.4.28.orig/mm/memcontrol.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/mm/memcontrol.c 2016-11-01 21:26:58.820345117 +0100
- @@ -67,6 +67,8 @@
- #include <net/sock.h>
- #include <net/ip.h>
- #include <net/tcp_memcontrol.h>
- +#include <linux/locallock.h>
- +
- #include "slab.h"
-
- #include <asm/uaccess.h>
- @@ -87,6 +89,7 @@
- #define do_swap_account 0
- #endif
-
- +static DEFINE_LOCAL_IRQ_LOCK(event_lock);
- static const char * const mem_cgroup_stat_names[] = {
- "cache",
- "rss",
- @@ -1922,14 +1925,17 @@
- */
- static void refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
- {
- - struct memcg_stock_pcp *stock = &get_cpu_var(memcg_stock);
- + struct memcg_stock_pcp *stock;
- + int cpu = get_cpu_light();
- +
- + stock = &per_cpu(memcg_stock, cpu);
-
- if (stock->cached != memcg) { /* reset if necessary */
- drain_stock(stock);
- stock->cached = memcg;
- }
- stock->nr_pages += nr_pages;
- - put_cpu_var(memcg_stock);
- + put_cpu_light();
- }
-
- /*
- @@ -1945,7 +1951,7 @@
- return;
- /* Notify other cpus that system-wide "drain" is running */
- get_online_cpus();
- - curcpu = get_cpu();
- + curcpu = get_cpu_light();
- for_each_online_cpu(cpu) {
- struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu);
- struct mem_cgroup *memcg;
- @@ -1962,7 +1968,7 @@
- schedule_work_on(cpu, &stock->work);
- }
- }
- - put_cpu();
- + put_cpu_light();
- put_online_cpus();
- mutex_unlock(&percpu_charge_mutex);
- }
- @@ -4700,12 +4706,12 @@
-
- ret = 0;
-
- - local_irq_disable();
- + local_lock_irq(event_lock);
- mem_cgroup_charge_statistics(to, page, nr_pages);
- memcg_check_events(to, page);
- mem_cgroup_charge_statistics(from, page, -nr_pages);
- memcg_check_events(from, page);
- - local_irq_enable();
- + local_unlock_irq(event_lock);
- out_unlock:
- unlock_page(page);
- out:
- @@ -5495,10 +5501,10 @@
- VM_BUG_ON_PAGE(!PageTransHuge(page), page);
- }
-
- - local_irq_disable();
- + local_lock_irq(event_lock);
- mem_cgroup_charge_statistics(memcg, page, nr_pages);
- memcg_check_events(memcg, page);
- - local_irq_enable();
- + local_unlock_irq(event_lock);
-
- if (do_swap_account && PageSwapCache(page)) {
- swp_entry_t entry = { .val = page_private(page) };
- @@ -5554,14 +5560,14 @@
- memcg_oom_recover(memcg);
- }
-
- - local_irq_save(flags);
- + local_lock_irqsave(event_lock, flags);
- __this_cpu_sub(memcg->stat->count[MEM_CGROUP_STAT_RSS], nr_anon);
- __this_cpu_sub(memcg->stat->count[MEM_CGROUP_STAT_CACHE], nr_file);
- __this_cpu_sub(memcg->stat->count[MEM_CGROUP_STAT_RSS_HUGE], nr_huge);
- __this_cpu_add(memcg->stat->events[MEM_CGROUP_EVENTS_PGPGOUT], pgpgout);
- __this_cpu_add(memcg->stat->nr_page_events, nr_pages);
- memcg_check_events(memcg, dummy_page);
- - local_irq_restore(flags);
- + local_unlock_irqrestore(event_lock, flags);
-
- if (!mem_cgroup_is_root(memcg))
- css_put_many(&memcg->css, nr_pages);
- @@ -5753,6 +5759,7 @@
- {
- struct mem_cgroup *memcg, *swap_memcg;
- unsigned short oldid;
- + unsigned long flags;
-
- VM_BUG_ON_PAGE(PageLRU(page), page);
- VM_BUG_ON_PAGE(page_count(page), page);
- @@ -5793,12 +5800,16 @@
- * important here to have the interrupts disabled because it is the
- * only synchronisation we have for udpating the per-CPU variables.
- */
- + local_lock_irqsave(event_lock, flags);
- +#ifndef CONFIG_PREEMPT_RT_BASE
- VM_BUG_ON(!irqs_disabled());
- +#endif
- mem_cgroup_charge_statistics(memcg, page, -1);
- memcg_check_events(memcg, page);
-
- if (!mem_cgroup_is_root(memcg))
- css_put(&memcg->css);
- + local_unlock_irqrestore(event_lock, flags);
- }
-
- /**
- diff -Nur linux-4.4.28.orig/mm/mmu_context.c linux-4.4.28/mm/mmu_context.c
- --- linux-4.4.28.orig/mm/mmu_context.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/mm/mmu_context.c 2016-11-01 21:26:58.820345117 +0100
- @@ -23,6 +23,7 @@
- struct task_struct *tsk = current;
-
- task_lock(tsk);
- + preempt_disable_rt();
- active_mm = tsk->active_mm;
- if (active_mm != mm) {
- atomic_inc(&mm->mm_count);
- @@ -30,6 +31,7 @@
- }
- tsk->mm = mm;
- switch_mm(active_mm, mm, tsk);
- + preempt_enable_rt();
- task_unlock(tsk);
- #ifdef finish_arch_post_lock_switch
- finish_arch_post_lock_switch();
- diff -Nur linux-4.4.28.orig/mm/page_alloc.c linux-4.4.28/mm/page_alloc.c
- --- linux-4.4.28.orig/mm/page_alloc.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/mm/page_alloc.c 2016-11-01 21:26:58.824345373 +0100
- @@ -60,6 +60,7 @@
- #include <linux/page_ext.h>
- #include <linux/hugetlb.h>
- #include <linux/sched/rt.h>
- +#include <linux/locallock.h>
- #include <linux/page_owner.h>
- #include <linux/kthread.h>
-
- @@ -264,6 +265,18 @@
- EXPORT_SYMBOL(nr_online_nodes);
- #endif
-
- +static DEFINE_LOCAL_IRQ_LOCK(pa_lock);
- +
- +#ifdef CONFIG_PREEMPT_RT_BASE
- +# define cpu_lock_irqsave(cpu, flags) \
- + local_lock_irqsave_on(pa_lock, flags, cpu)
- +# define cpu_unlock_irqrestore(cpu, flags) \
- + local_unlock_irqrestore_on(pa_lock, flags, cpu)
- +#else
- +# define cpu_lock_irqsave(cpu, flags) local_irq_save(flags)
- +# define cpu_unlock_irqrestore(cpu, flags) local_irq_restore(flags)
- +#endif
- +
- int page_group_by_mobility_disabled __read_mostly;
-
- #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
- @@ -786,7 +799,7 @@
- }
-
- /*
- - * Frees a number of pages from the PCP lists
- + * Frees a number of pages which have been collected from the pcp lists.
- * Assumes all pages on list are in same zone, and of same order.
- * count is the number of pages to free.
- *
- @@ -797,18 +810,53 @@
- * pinned" detection logic.
- */
- static void free_pcppages_bulk(struct zone *zone, int count,
- - struct per_cpu_pages *pcp)
- + struct list_head *list)
- {
- - int migratetype = 0;
- - int batch_free = 0;
- int to_free = count;
- unsigned long nr_scanned;
- + unsigned long flags;
- +
- + spin_lock_irqsave(&zone->lock, flags);
-
- - spin_lock(&zone->lock);
- nr_scanned = zone_page_state(zone, NR_PAGES_SCANNED);
- if (nr_scanned)
- __mod_zone_page_state(zone, NR_PAGES_SCANNED, -nr_scanned);
-
- + while (!list_empty(list)) {
- + struct page *page = list_first_entry(list, struct page, lru);
- + int mt; /* migratetype of the to-be-freed page */
- +
- + /* must delete as __free_one_page list manipulates */
- + list_del(&page->lru);
- +
- + mt = get_pcppage_migratetype(page);
- + /* MIGRATE_ISOLATE page should not go to pcplists */
- + VM_BUG_ON_PAGE(is_migrate_isolate(mt), page);
- + /* Pageblock could have been isolated meanwhile */
- + if (unlikely(has_isolate_pageblock(zone)))
- + mt = get_pageblock_migratetype(page);
- +
- + __free_one_page(page, page_to_pfn(page), zone, 0, mt);
- + trace_mm_page_pcpu_drain(page, 0, mt);
- + to_free--;
- + }
- + WARN_ON(to_free != 0);
- + spin_unlock_irqrestore(&zone->lock, flags);
- +}
- +
- +/*
- + * Moves a number of pages from the PCP lists to free list which
- + * is freed outside of the locked region.
- + *
- + * Assumes all pages on list are in same zone, and of same order.
- + * count is the number of pages to free.
- + */
- +static void isolate_pcp_pages(int to_free, struct per_cpu_pages *src,
- + struct list_head *dst)
- +{
- + int migratetype = 0;
- + int batch_free = 0;
- +
- while (to_free) {
- struct page *page;
- struct list_head *list;
- @@ -824,7 +872,7 @@
- batch_free++;
- if (++migratetype == MIGRATE_PCPTYPES)
- migratetype = 0;
- - list = &pcp->lists[migratetype];
- + list = &src->lists[migratetype];
- } while (list_empty(list));
-
- /* This is the only non-empty list. Free them all. */
- @@ -832,24 +880,12 @@
- batch_free = to_free;
-
- do {
- - int mt; /* migratetype of the to-be-freed page */
- -
- - page = list_entry(list->prev, struct page, lru);
- - /* must delete as __free_one_page list manipulates */
- + page = list_last_entry(list, struct page, lru);
- list_del(&page->lru);
-
- - mt = get_pcppage_migratetype(page);
- - /* MIGRATE_ISOLATE page should not go to pcplists */
- - VM_BUG_ON_PAGE(is_migrate_isolate(mt), page);
- - /* Pageblock could have been isolated meanwhile */
- - if (unlikely(has_isolate_pageblock(zone)))
- - mt = get_pageblock_migratetype(page);
- -
- - __free_one_page(page, page_to_pfn(page), zone, 0, mt);
- - trace_mm_page_pcpu_drain(page, 0, mt);
- + list_add(&page->lru, dst);
- } while (--to_free && --batch_free && !list_empty(list));
- }
- - spin_unlock(&zone->lock);
- }
-
- static void free_one_page(struct zone *zone,
- @@ -858,7 +894,9 @@
- int migratetype)
- {
- unsigned long nr_scanned;
- - spin_lock(&zone->lock);
- + unsigned long flags;
- +
- + spin_lock_irqsave(&zone->lock, flags);
- nr_scanned = zone_page_state(zone, NR_PAGES_SCANNED);
- if (nr_scanned)
- __mod_zone_page_state(zone, NR_PAGES_SCANNED, -nr_scanned);
- @@ -868,7 +906,7 @@
- migratetype = get_pfnblock_migratetype(page, pfn);
- }
- __free_one_page(page, pfn, zone, order, migratetype);
- - spin_unlock(&zone->lock);
- + spin_unlock_irqrestore(&zone->lock, flags);
- }
-
- static int free_tail_pages_check(struct page *head_page, struct page *page)
- @@ -1019,10 +1057,10 @@
- return;
-
- migratetype = get_pfnblock_migratetype(page, pfn);
- - local_irq_save(flags);
- + local_lock_irqsave(pa_lock, flags);
- __count_vm_events(PGFREE, 1 << order);
- free_one_page(page_zone(page), page, pfn, order, migratetype);
- - local_irq_restore(flags);
- + local_unlock_irqrestore(pa_lock, flags);
- }
-
- static void __init __free_pages_boot_core(struct page *page,
- @@ -1879,16 +1917,18 @@
- void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp)
- {
- unsigned long flags;
- + LIST_HEAD(dst);
- int to_drain, batch;
-
- - local_irq_save(flags);
- + local_lock_irqsave(pa_lock, flags);
- batch = READ_ONCE(pcp->batch);
- to_drain = min(pcp->count, batch);
- if (to_drain > 0) {
- - free_pcppages_bulk(zone, to_drain, pcp);
- + isolate_pcp_pages(to_drain, pcp, &dst);
- pcp->count -= to_drain;
- }
- - local_irq_restore(flags);
- + local_unlock_irqrestore(pa_lock, flags);
- + free_pcppages_bulk(zone, to_drain, &dst);
- }
- #endif
-
- @@ -1904,16 +1944,21 @@
- unsigned long flags;
- struct per_cpu_pageset *pset;
- struct per_cpu_pages *pcp;
- + LIST_HEAD(dst);
- + int count;
-
- - local_irq_save(flags);
- + cpu_lock_irqsave(cpu, flags);
- pset = per_cpu_ptr(zone->pageset, cpu);
-
- pcp = &pset->pcp;
- - if (pcp->count) {
- - free_pcppages_bulk(zone, pcp->count, pcp);
- + count = pcp->count;
- + if (count) {
- + isolate_pcp_pages(count, pcp, &dst);
- pcp->count = 0;
- }
- - local_irq_restore(flags);
- + cpu_unlock_irqrestore(cpu, flags);
- + if (count)
- + free_pcppages_bulk(zone, count, &dst);
- }
-
- /*
- @@ -1999,8 +2044,17 @@
- else
- cpumask_clear_cpu(cpu, &cpus_with_pcps);
- }
- +#ifndef CONFIG_PREEMPT_RT_BASE
- on_each_cpu_mask(&cpus_with_pcps, (smp_call_func_t) drain_local_pages,
- zone, 1);
- +#else
- + for_each_cpu(cpu, &cpus_with_pcps) {
- + if (zone)
- + drain_pages_zone(cpu, zone);
- + else
- + drain_pages(cpu);
- + }
- +#endif
- }
-
- #ifdef CONFIG_HIBERNATION
- @@ -2056,7 +2110,7 @@
-
- migratetype = get_pfnblock_migratetype(page, pfn);
- set_pcppage_migratetype(page, migratetype);
- - local_irq_save(flags);
- + local_lock_irqsave(pa_lock, flags);
- __count_vm_event(PGFREE);
-
- /*
- @@ -2082,12 +2136,17 @@
- pcp->count++;
- if (pcp->count >= pcp->high) {
- unsigned long batch = READ_ONCE(pcp->batch);
- - free_pcppages_bulk(zone, batch, pcp);
- + LIST_HEAD(dst);
- +
- + isolate_pcp_pages(batch, pcp, &dst);
- pcp->count -= batch;
- + local_unlock_irqrestore(pa_lock, flags);
- + free_pcppages_bulk(zone, batch, &dst);
- + return;
- }
-
- out:
- - local_irq_restore(flags);
- + local_unlock_irqrestore(pa_lock, flags);
- }
-
- /*
- @@ -2222,7 +2281,7 @@
- struct per_cpu_pages *pcp;
- struct list_head *list;
-
- - local_irq_save(flags);
- + local_lock_irqsave(pa_lock, flags);
- pcp = &this_cpu_ptr(zone->pageset)->pcp;
- list = &pcp->lists[migratetype];
- if (list_empty(list)) {
- @@ -2254,7 +2313,7 @@
- */
- WARN_ON_ONCE(order > 1);
- }
- - spin_lock_irqsave(&zone->lock, flags);
- + local_spin_lock_irqsave(pa_lock, &zone->lock, flags);
-
- page = NULL;
- if (alloc_flags & ALLOC_HARDER) {
- @@ -2264,11 +2323,13 @@
- }
- if (!page)
- page = __rmqueue(zone, order, migratetype, gfp_flags);
- - spin_unlock(&zone->lock);
- - if (!page)
- + if (!page) {
- + spin_unlock(&zone->lock);
- goto failed;
- + }
- __mod_zone_freepage_state(zone, -(1 << order),
- get_pcppage_migratetype(page));
- + spin_unlock(&zone->lock);
- }
-
- __mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order));
- @@ -2278,13 +2339,13 @@
-
- __count_zone_vm_events(PGALLOC, zone, 1 << order);
- zone_statistics(preferred_zone, zone, gfp_flags);
- - local_irq_restore(flags);
- + local_unlock_irqrestore(pa_lock, flags);
-
- VM_BUG_ON_PAGE(bad_range(zone, page), page);
- return page;
-
- failed:
- - local_irq_restore(flags);
- + local_unlock_irqrestore(pa_lock, flags);
- return NULL;
- }
-
- @@ -5950,6 +6011,7 @@
- void __init page_alloc_init(void)
- {
- hotcpu_notifier(page_alloc_cpu_notify, 0);
- + local_irq_lock_init(pa_lock);
- }
-
- /*
- @@ -6844,7 +6906,7 @@
- struct per_cpu_pageset *pset;
-
- /* avoid races with drain_pages() */
- - local_irq_save(flags);
- + local_lock_irqsave(pa_lock, flags);
- if (zone->pageset != &boot_pageset) {
- for_each_online_cpu(cpu) {
- pset = per_cpu_ptr(zone->pageset, cpu);
- @@ -6853,7 +6915,7 @@
- free_percpu(zone->pageset);
- zone->pageset = &boot_pageset;
- }
- - local_irq_restore(flags);
- + local_unlock_irqrestore(pa_lock, flags);
- }
-
- #ifdef CONFIG_MEMORY_HOTREMOVE
- diff -Nur linux-4.4.28.orig/mm/slab.h linux-4.4.28/mm/slab.h
- --- linux-4.4.28.orig/mm/slab.h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/mm/slab.h 2016-11-01 21:26:58.824345373 +0100
- @@ -324,7 +324,11 @@
- * The slab lists for all objects.
- */
- struct kmem_cache_node {
- +#ifdef CONFIG_SLUB
- + raw_spinlock_t list_lock;
- +#else
- spinlock_t list_lock;
- +#endif
-
- #ifdef CONFIG_SLAB
- struct list_head slabs_partial; /* partial list first, better asm code */
- diff -Nur linux-4.4.28.orig/mm/slub.c linux-4.4.28/mm/slub.c
- --- linux-4.4.28.orig/mm/slub.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/mm/slub.c 2016-11-01 21:26:58.828345638 +0100
- @@ -1075,7 +1075,7 @@
- void *object = head;
- int cnt = 0;
-
- - spin_lock_irqsave(&n->list_lock, *flags);
- + raw_spin_lock_irqsave(&n->list_lock, *flags);
- slab_lock(page);
-
- if (!check_slab(s, page))
- @@ -1136,7 +1136,7 @@
-
- fail:
- slab_unlock(page);
- - spin_unlock_irqrestore(&n->list_lock, *flags);
- + raw_spin_unlock_irqrestore(&n->list_lock, *flags);
- slab_fix(s, "Object at 0x%p not freed", object);
- return NULL;
- }
- @@ -1263,6 +1263,12 @@
-
- #endif /* CONFIG_SLUB_DEBUG */
-
- +struct slub_free_list {
- + raw_spinlock_t lock;
- + struct list_head list;
- +};
- +static DEFINE_PER_CPU(struct slub_free_list, slub_free_list);
- +
- /*
- * Hooks for other subsystems that check memory allocations. In a typical
- * production configuration these hooks all should produce no code at all.
- @@ -1399,10 +1405,17 @@
- gfp_t alloc_gfp;
- void *start, *p;
- int idx, order;
- + bool enableirqs = false;
-
- flags &= gfp_allowed_mask;
-
- if (gfpflags_allow_blocking(flags))
- + enableirqs = true;
- +#ifdef CONFIG_PREEMPT_RT_FULL
- + if (system_state == SYSTEM_RUNNING)
- + enableirqs = true;
- +#endif
- + if (enableirqs)
- local_irq_enable();
-
- flags |= s->allocflags;
- @@ -1473,7 +1486,7 @@
- page->frozen = 1;
-
- out:
- - if (gfpflags_allow_blocking(flags))
- + if (enableirqs)
- local_irq_disable();
- if (!page)
- return NULL;
- @@ -1529,6 +1542,16 @@
- __free_kmem_pages(page, order);
- }
-
- +static void free_delayed(struct list_head *h)
- +{
- + while(!list_empty(h)) {
- + struct page *page = list_first_entry(h, struct page, lru);
- +
- + list_del(&page->lru);
- + __free_slab(page->slab_cache, page);
- + }
- +}
- +
- #define need_reserve_slab_rcu \
- (sizeof(((struct page *)NULL)->lru) < sizeof(struct rcu_head))
-
- @@ -1560,6 +1583,12 @@
- }
-
- call_rcu(head, rcu_free_slab);
- + } else if (irqs_disabled()) {
- + struct slub_free_list *f = this_cpu_ptr(&slub_free_list);
- +
- + raw_spin_lock(&f->lock);
- + list_add(&page->lru, &f->list);
- + raw_spin_unlock(&f->lock);
- } else
- __free_slab(s, page);
- }
- @@ -1673,7 +1702,7 @@
- if (!n || !n->nr_partial)
- return NULL;
-
- - spin_lock(&n->list_lock);
- + raw_spin_lock(&n->list_lock);
- list_for_each_entry_safe(page, page2, &n->partial, lru) {
- void *t;
-
- @@ -1698,7 +1727,7 @@
- break;
-
- }
- - spin_unlock(&n->list_lock);
- + raw_spin_unlock(&n->list_lock);
- return object;
- }
-
- @@ -1944,7 +1973,7 @@
- * that acquire_slab() will see a slab page that
- * is frozen
- */
- - spin_lock(&n->list_lock);
- + raw_spin_lock(&n->list_lock);
- }
- } else {
- m = M_FULL;
- @@ -1955,7 +1984,7 @@
- * slabs from diagnostic functions will not see
- * any frozen slabs.
- */
- - spin_lock(&n->list_lock);
- + raw_spin_lock(&n->list_lock);
- }
- }
-
- @@ -1990,7 +2019,7 @@
- goto redo;
-
- if (lock)
- - spin_unlock(&n->list_lock);
- + raw_spin_unlock(&n->list_lock);
-
- if (m == M_FREE) {
- stat(s, DEACTIVATE_EMPTY);
- @@ -2022,10 +2051,10 @@
- n2 = get_node(s, page_to_nid(page));
- if (n != n2) {
- if (n)
- - spin_unlock(&n->list_lock);
- + raw_spin_unlock(&n->list_lock);
-
- n = n2;
- - spin_lock(&n->list_lock);
- + raw_spin_lock(&n->list_lock);
- }
-
- do {
- @@ -2054,7 +2083,7 @@
- }
-
- if (n)
- - spin_unlock(&n->list_lock);
- + raw_spin_unlock(&n->list_lock);
-
- while (discard_page) {
- page = discard_page;
- @@ -2093,14 +2122,21 @@
- pobjects = oldpage->pobjects;
- pages = oldpage->pages;
- if (drain && pobjects > s->cpu_partial) {
- + struct slub_free_list *f;
- unsigned long flags;
- + LIST_HEAD(tofree);
- /*
- * partial array is full. Move the existing
- * set to the per node partial list.
- */
- local_irq_save(flags);
- unfreeze_partials(s, this_cpu_ptr(s->cpu_slab));
- + f = this_cpu_ptr(&slub_free_list);
- + raw_spin_lock(&f->lock);
- + list_splice_init(&f->list, &tofree);
- + raw_spin_unlock(&f->lock);
- local_irq_restore(flags);
- + free_delayed(&tofree);
- oldpage = NULL;
- pobjects = 0;
- pages = 0;
- @@ -2172,7 +2208,22 @@
-
- static void flush_all(struct kmem_cache *s)
- {
- + LIST_HEAD(tofree);
- + int cpu;
- +
- on_each_cpu_cond(has_cpu_slab, flush_cpu_slab, s, 1, GFP_ATOMIC);
- + for_each_online_cpu(cpu) {
- + struct slub_free_list *f;
- +
- + if (!has_cpu_slab(cpu, s))
- + continue;
- +
- + f = &per_cpu(slub_free_list, cpu);
- + raw_spin_lock_irq(&f->lock);
- + list_splice_init(&f->list, &tofree);
- + raw_spin_unlock_irq(&f->lock);
- + free_delayed(&tofree);
- + }
- }
-
- /*
- @@ -2208,10 +2259,10 @@
- unsigned long x = 0;
- struct page *page;
-
- - spin_lock_irqsave(&n->list_lock, flags);
- + raw_spin_lock_irqsave(&n->list_lock, flags);
- list_for_each_entry(page, &n->partial, lru)
- x += get_count(page);
- - spin_unlock_irqrestore(&n->list_lock, flags);
- + raw_spin_unlock_irqrestore(&n->list_lock, flags);
- return x;
- }
- #endif /* CONFIG_SLUB_DEBUG || CONFIG_SYSFS */
- @@ -2349,8 +2400,10 @@
- * already disabled (which is the case for bulk allocation).
- */
- static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
- - unsigned long addr, struct kmem_cache_cpu *c)
- + unsigned long addr, struct kmem_cache_cpu *c,
- + struct list_head *to_free)
- {
- + struct slub_free_list *f;
- void *freelist;
- struct page *page;
-
- @@ -2410,6 +2463,13 @@
- VM_BUG_ON(!c->page->frozen);
- c->freelist = get_freepointer(s, freelist);
- c->tid = next_tid(c->tid);
- +
- +out:
- + f = this_cpu_ptr(&slub_free_list);
- + raw_spin_lock(&f->lock);
- + list_splice_init(&f->list, to_free);
- + raw_spin_unlock(&f->lock);
- +
- return freelist;
-
- new_slab:
- @@ -2441,7 +2501,7 @@
- deactivate_slab(s, page, get_freepointer(s, freelist));
- c->page = NULL;
- c->freelist = NULL;
- - return freelist;
- + goto out;
- }
-
- /*
- @@ -2453,6 +2513,7 @@
- {
- void *p;
- unsigned long flags;
- + LIST_HEAD(tofree);
-
- local_irq_save(flags);
- #ifdef CONFIG_PREEMPT
- @@ -2464,8 +2525,9 @@
- c = this_cpu_ptr(s->cpu_slab);
- #endif
-
- - p = ___slab_alloc(s, gfpflags, node, addr, c);
- + p = ___slab_alloc(s, gfpflags, node, addr, c, &tofree);
- local_irq_restore(flags);
- + free_delayed(&tofree);
- return p;
- }
-
- @@ -2652,7 +2714,7 @@
-
- do {
- if (unlikely(n)) {
- - spin_unlock_irqrestore(&n->list_lock, flags);
- + raw_spin_unlock_irqrestore(&n->list_lock, flags);
- n = NULL;
- }
- prior = page->freelist;
- @@ -2684,7 +2746,7 @@
- * Otherwise the list_lock will synchronize with
- * other processors updating the list of slabs.
- */
- - spin_lock_irqsave(&n->list_lock, flags);
- + raw_spin_lock_irqsave(&n->list_lock, flags);
-
- }
- }
- @@ -2726,7 +2788,7 @@
- add_partial(n, page, DEACTIVATE_TO_TAIL);
- stat(s, FREE_ADD_PARTIAL);
- }
- - spin_unlock_irqrestore(&n->list_lock, flags);
- + raw_spin_unlock_irqrestore(&n->list_lock, flags);
- return;
-
- slab_empty:
- @@ -2741,7 +2803,7 @@
- remove_full(s, n, page);
- }
-
- - spin_unlock_irqrestore(&n->list_lock, flags);
- + raw_spin_unlock_irqrestore(&n->list_lock, flags);
- stat(s, FREE_SLAB);
- discard_slab(s, page);
- }
- @@ -2913,6 +2975,7 @@
- void **p)
- {
- struct kmem_cache_cpu *c;
- + LIST_HEAD(to_free);
- int i;
-
- /* memcg and kmem_cache debug support */
- @@ -2936,7 +2999,7 @@
- * of re-populating per CPU c->freelist
- */
- p[i] = ___slab_alloc(s, flags, NUMA_NO_NODE,
- - _RET_IP_, c);
- + _RET_IP_, c, &to_free);
- if (unlikely(!p[i]))
- goto error;
-
- @@ -2948,6 +3011,7 @@
- }
- c->tid = next_tid(c->tid);
- local_irq_enable();
- + free_delayed(&to_free);
-
- /* Clear memory outside IRQ disabled fastpath loop */
- if (unlikely(flags & __GFP_ZERO)) {
- @@ -3095,7 +3159,7 @@
- init_kmem_cache_node(struct kmem_cache_node *n)
- {
- n->nr_partial = 0;
- - spin_lock_init(&n->list_lock);
- + raw_spin_lock_init(&n->list_lock);
- INIT_LIST_HEAD(&n->partial);
- #ifdef CONFIG_SLUB_DEBUG
- atomic_long_set(&n->nr_slabs, 0);
- @@ -3677,7 +3741,7 @@
- for (i = 0; i < SHRINK_PROMOTE_MAX; i++)
- INIT_LIST_HEAD(promote + i);
-
- - spin_lock_irqsave(&n->list_lock, flags);
- + raw_spin_lock_irqsave(&n->list_lock, flags);
-
- /*
- * Build lists of slabs to discard or promote.
- @@ -3708,7 +3772,7 @@
- for (i = SHRINK_PROMOTE_MAX - 1; i >= 0; i--)
- list_splice(promote + i, &n->partial);
-
- - spin_unlock_irqrestore(&n->list_lock, flags);
- + raw_spin_unlock_irqrestore(&n->list_lock, flags);
-
- /* Release empty slabs */
- list_for_each_entry_safe(page, t, &discard, lru)
- @@ -3884,6 +3948,12 @@
- {
- static __initdata struct kmem_cache boot_kmem_cache,
- boot_kmem_cache_node;
- + int cpu;
- +
- + for_each_possible_cpu(cpu) {
- + raw_spin_lock_init(&per_cpu(slub_free_list, cpu).lock);
- + INIT_LIST_HEAD(&per_cpu(slub_free_list, cpu).list);
- + }
-
- if (debug_guardpage_minorder())
- slub_max_order = 0;
- @@ -4127,7 +4197,7 @@
- struct page *page;
- unsigned long flags;
-
- - spin_lock_irqsave(&n->list_lock, flags);
- + raw_spin_lock_irqsave(&n->list_lock, flags);
-
- list_for_each_entry(page, &n->partial, lru) {
- validate_slab_slab(s, page, map);
- @@ -4149,7 +4219,7 @@
- s->name, count, atomic_long_read(&n->nr_slabs));
-
- out:
- - spin_unlock_irqrestore(&n->list_lock, flags);
- + raw_spin_unlock_irqrestore(&n->list_lock, flags);
- return count;
- }
-
- @@ -4337,12 +4407,12 @@
- if (!atomic_long_read(&n->nr_slabs))
- continue;
-
- - spin_lock_irqsave(&n->list_lock, flags);
- + raw_spin_lock_irqsave(&n->list_lock, flags);
- list_for_each_entry(page, &n->partial, lru)
- process_slab(&t, s, page, alloc, map);
- list_for_each_entry(page, &n->full, lru)
- process_slab(&t, s, page, alloc, map);
- - spin_unlock_irqrestore(&n->list_lock, flags);
- + raw_spin_unlock_irqrestore(&n->list_lock, flags);
- }
-
- for (i = 0; i < t.count; i++) {
- diff -Nur linux-4.4.28.orig/mm/swap.c linux-4.4.28/mm/swap.c
- --- linux-4.4.28.orig/mm/swap.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/mm/swap.c 2016-11-01 21:26:58.828345638 +0100
- @@ -31,6 +31,7 @@
- #include <linux/memcontrol.h>
- #include <linux/gfp.h>
- #include <linux/uio.h>
- +#include <linux/locallock.h>
- #include <linux/hugetlb.h>
- #include <linux/page_idle.h>
-
- @@ -46,6 +47,9 @@
- static DEFINE_PER_CPU(struct pagevec, lru_rotate_pvecs);
- static DEFINE_PER_CPU(struct pagevec, lru_deactivate_file_pvecs);
-
- +static DEFINE_LOCAL_IRQ_LOCK(rotate_lock);
- +DEFINE_LOCAL_IRQ_LOCK(swapvec_lock);
- +
- /*
- * This path almost never happens for VM activity - pages are normally
- * freed via pagevecs. But it gets used by networking.
- @@ -481,11 +485,11 @@
- unsigned long flags;
-
- page_cache_get(page);
- - local_irq_save(flags);
- + local_lock_irqsave(rotate_lock, flags);
- pvec = this_cpu_ptr(&lru_rotate_pvecs);
- if (!pagevec_add(pvec, page))
- pagevec_move_tail(pvec);
- - local_irq_restore(flags);
- + local_unlock_irqrestore(rotate_lock, flags);
- }
- }
-
- @@ -536,12 +540,13 @@
- void activate_page(struct page *page)
- {
- if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
- - struct pagevec *pvec = &get_cpu_var(activate_page_pvecs);
- + struct pagevec *pvec = &get_locked_var(swapvec_lock,
- + activate_page_pvecs);
-
- page_cache_get(page);
- if (!pagevec_add(pvec, page))
- pagevec_lru_move_fn(pvec, __activate_page, NULL);
- - put_cpu_var(activate_page_pvecs);
- + put_locked_var(swapvec_lock, activate_page_pvecs);
- }
- }
-
- @@ -567,7 +572,7 @@
-
- static void __lru_cache_activate_page(struct page *page)
- {
- - struct pagevec *pvec = &get_cpu_var(lru_add_pvec);
- + struct pagevec *pvec = &get_locked_var(swapvec_lock, lru_add_pvec);
- int i;
-
- /*
- @@ -589,7 +594,7 @@
- }
- }
-
- - put_cpu_var(lru_add_pvec);
- + put_locked_var(swapvec_lock, lru_add_pvec);
- }
-
- /*
- @@ -630,13 +635,13 @@
-
- static void __lru_cache_add(struct page *page)
- {
- - struct pagevec *pvec = &get_cpu_var(lru_add_pvec);
- + struct pagevec *pvec = &get_locked_var(swapvec_lock, lru_add_pvec);
-
- page_cache_get(page);
- if (!pagevec_space(pvec))
- __pagevec_lru_add(pvec);
- pagevec_add(pvec, page);
- - put_cpu_var(lru_add_pvec);
- + put_locked_var(swapvec_lock, lru_add_pvec);
- }
-
- /**
- @@ -816,9 +821,15 @@
- unsigned long flags;
-
- /* No harm done if a racing interrupt already did this */
- - local_irq_save(flags);
- +#ifdef CONFIG_PREEMPT_RT_BASE
- + local_lock_irqsave_on(rotate_lock, flags, cpu);
- + pagevec_move_tail(pvec);
- + local_unlock_irqrestore_on(rotate_lock, flags, cpu);
- +#else
- + local_lock_irqsave(rotate_lock, flags);
- pagevec_move_tail(pvec);
- - local_irq_restore(flags);
- + local_unlock_irqrestore(rotate_lock, flags);
- +#endif
- }
-
- pvec = &per_cpu(lru_deactivate_file_pvecs, cpu);
- @@ -846,26 +857,47 @@
- return;
-
- if (likely(get_page_unless_zero(page))) {
- - struct pagevec *pvec = &get_cpu_var(lru_deactivate_file_pvecs);
- + struct pagevec *pvec = &get_locked_var(swapvec_lock,
- + lru_deactivate_file_pvecs);
-
- if (!pagevec_add(pvec, page))
- pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, NULL);
- - put_cpu_var(lru_deactivate_file_pvecs);
- + put_locked_var(swapvec_lock, lru_deactivate_file_pvecs);
- }
- }
-
- void lru_add_drain(void)
- {
- - lru_add_drain_cpu(get_cpu());
- - put_cpu();
- + lru_add_drain_cpu(local_lock_cpu(swapvec_lock));
- + local_unlock_cpu(swapvec_lock);
- }
-
- +
- +#ifdef CONFIG_PREEMPT_RT_BASE
- +static inline void remote_lru_add_drain(int cpu, struct cpumask *has_work)
- +{
- + local_lock_on(swapvec_lock, cpu);
- + lru_add_drain_cpu(cpu);
- + local_unlock_on(swapvec_lock, cpu);
- +}
- +
- +#else
- +
- static void lru_add_drain_per_cpu(struct work_struct *dummy)
- {
- lru_add_drain();
- }
-
- static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work);
- +static inline void remote_lru_add_drain(int cpu, struct cpumask *has_work)
- +{
- + struct work_struct *work = &per_cpu(lru_add_drain_work, cpu);
- +
- + INIT_WORK(work, lru_add_drain_per_cpu);
- + schedule_work_on(cpu, work);
- + cpumask_set_cpu(cpu, has_work);
- +}
- +#endif
-
- void lru_add_drain_all(void)
- {
- @@ -878,20 +910,17 @@
- cpumask_clear(&has_work);
-
- for_each_online_cpu(cpu) {
- - struct work_struct *work = &per_cpu(lru_add_drain_work, cpu);
- -
- if (pagevec_count(&per_cpu(lru_add_pvec, cpu)) ||
- pagevec_count(&per_cpu(lru_rotate_pvecs, cpu)) ||
- pagevec_count(&per_cpu(lru_deactivate_file_pvecs, cpu)) ||
- - need_activate_page_drain(cpu)) {
- - INIT_WORK(work, lru_add_drain_per_cpu);
- - schedule_work_on(cpu, work);
- - cpumask_set_cpu(cpu, &has_work);
- - }
- + need_activate_page_drain(cpu))
- + remote_lru_add_drain(cpu, &has_work);
- }
-
- +#ifndef CONFIG_PREEMPT_RT_BASE
- for_each_cpu(cpu, &has_work)
- flush_work(&per_cpu(lru_add_drain_work, cpu));
- +#endif
-
- put_online_cpus();
- mutex_unlock(&lock);
- diff -Nur linux-4.4.28.orig/mm/truncate.c linux-4.4.28/mm/truncate.c
- --- linux-4.4.28.orig/mm/truncate.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/mm/truncate.c 2016-11-01 21:26:58.828345638 +0100
- @@ -56,8 +56,11 @@
- * protected by mapping->tree_lock.
- */
- if (!workingset_node_shadows(node) &&
- - !list_empty(&node->private_list))
- - list_lru_del(&workingset_shadow_nodes, &node->private_list);
- + !list_empty(&node->private_list)) {
- + local_lock(workingset_shadow_lock);
- + list_lru_del(&__workingset_shadow_nodes, &node->private_list);
- + local_unlock(workingset_shadow_lock);
- + }
- __radix_tree_delete_node(&mapping->page_tree, node);
- unlock:
- spin_unlock_irq(&mapping->tree_lock);
- diff -Nur linux-4.4.28.orig/mm/vmalloc.c linux-4.4.28/mm/vmalloc.c
- --- linux-4.4.28.orig/mm/vmalloc.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/mm/vmalloc.c 2016-11-01 21:26:58.828345638 +0100
- @@ -821,7 +821,7 @@
- struct vmap_block *vb;
- struct vmap_area *va;
- unsigned long vb_idx;
- - int node, err;
- + int node, err, cpu;
- void *vaddr;
-
- node = numa_node_id();
- @@ -864,11 +864,12 @@
- BUG_ON(err);
- radix_tree_preload_end();
-
- - vbq = &get_cpu_var(vmap_block_queue);
- + cpu = get_cpu_light();
- + vbq = this_cpu_ptr(&vmap_block_queue);
- spin_lock(&vbq->lock);
- list_add_tail_rcu(&vb->free_list, &vbq->free);
- spin_unlock(&vbq->lock);
- - put_cpu_var(vmap_block_queue);
- + put_cpu_light();
-
- return vaddr;
- }
- @@ -937,6 +938,7 @@
- struct vmap_block *vb;
- void *vaddr = NULL;
- unsigned int order;
- + int cpu;
-
- BUG_ON(offset_in_page(size));
- BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC);
- @@ -951,7 +953,8 @@
- order = get_order(size);
-
- rcu_read_lock();
- - vbq = &get_cpu_var(vmap_block_queue);
- + cpu = get_cpu_light();
- + vbq = this_cpu_ptr(&vmap_block_queue);
- list_for_each_entry_rcu(vb, &vbq->free, free_list) {
- unsigned long pages_off;
-
- @@ -974,7 +977,7 @@
- break;
- }
-
- - put_cpu_var(vmap_block_queue);
- + put_cpu_light();
- rcu_read_unlock();
-
- /* Allocate new block if nothing was found */
- diff -Nur linux-4.4.28.orig/mm/vmstat.c linux-4.4.28/mm/vmstat.c
- --- linux-4.4.28.orig/mm/vmstat.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/mm/vmstat.c 2016-11-01 21:26:58.828345638 +0100
- @@ -226,6 +226,7 @@
- long x;
- long t;
-
- + preempt_disable_rt();
- x = delta + __this_cpu_read(*p);
-
- t = __this_cpu_read(pcp->stat_threshold);
- @@ -235,6 +236,7 @@
- x = 0;
- }
- __this_cpu_write(*p, x);
- + preempt_enable_rt();
- }
- EXPORT_SYMBOL(__mod_zone_page_state);
-
- @@ -267,6 +269,7 @@
- s8 __percpu *p = pcp->vm_stat_diff + item;
- s8 v, t;
-
- + preempt_disable_rt();
- v = __this_cpu_inc_return(*p);
- t = __this_cpu_read(pcp->stat_threshold);
- if (unlikely(v > t)) {
- @@ -275,6 +278,7 @@
- zone_page_state_add(v + overstep, zone, item);
- __this_cpu_write(*p, -overstep);
- }
- + preempt_enable_rt();
- }
-
- void __inc_zone_page_state(struct page *page, enum zone_stat_item item)
- @@ -289,6 +293,7 @@
- s8 __percpu *p = pcp->vm_stat_diff + item;
- s8 v, t;
-
- + preempt_disable_rt();
- v = __this_cpu_dec_return(*p);
- t = __this_cpu_read(pcp->stat_threshold);
- if (unlikely(v < - t)) {
- @@ -297,6 +302,7 @@
- zone_page_state_add(v - overstep, zone, item);
- __this_cpu_write(*p, overstep);
- }
- + preempt_enable_rt();
- }
-
- void __dec_zone_page_state(struct page *page, enum zone_stat_item item)
- diff -Nur linux-4.4.28.orig/mm/workingset.c linux-4.4.28/mm/workingset.c
- --- linux-4.4.28.orig/mm/workingset.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/mm/workingset.c 2016-11-01 21:26:58.832345891 +0100
- @@ -264,7 +264,8 @@
- * point where they would still be useful.
- */
-
- -struct list_lru workingset_shadow_nodes;
- +struct list_lru __workingset_shadow_nodes;
- +DEFINE_LOCAL_IRQ_LOCK(workingset_shadow_lock);
-
- static unsigned long count_shadow_nodes(struct shrinker *shrinker,
- struct shrink_control *sc)
- @@ -274,9 +275,9 @@
- unsigned long pages;
-
- /* list_lru lock nests inside IRQ-safe mapping->tree_lock */
- - local_irq_disable();
- - shadow_nodes = list_lru_shrink_count(&workingset_shadow_nodes, sc);
- - local_irq_enable();
- + local_lock_irq(workingset_shadow_lock);
- + shadow_nodes = list_lru_shrink_count(&__workingset_shadow_nodes, sc);
- + local_unlock_irq(workingset_shadow_lock);
-
- pages = node_present_pages(sc->nid);
- /*
- @@ -361,9 +362,9 @@
- spin_unlock(&mapping->tree_lock);
- ret = LRU_REMOVED_RETRY;
- out:
- - local_irq_enable();
- + local_unlock_irq(workingset_shadow_lock);
- cond_resched();
- - local_irq_disable();
- + local_lock_irq(workingset_shadow_lock);
- spin_lock(lru_lock);
- return ret;
- }
- @@ -374,10 +375,10 @@
- unsigned long ret;
-
- /* list_lru lock nests inside IRQ-safe mapping->tree_lock */
- - local_irq_disable();
- - ret = list_lru_shrink_walk(&workingset_shadow_nodes, sc,
- + local_lock_irq(workingset_shadow_lock);
- + ret = list_lru_shrink_walk(&__workingset_shadow_nodes, sc,
- shadow_lru_isolate, NULL);
- - local_irq_enable();
- + local_unlock_irq(workingset_shadow_lock);
- return ret;
- }
-
- @@ -398,7 +399,7 @@
- {
- int ret;
-
- - ret = list_lru_init_key(&workingset_shadow_nodes, &shadow_nodes_key);
- + ret = list_lru_init_key(&__workingset_shadow_nodes, &shadow_nodes_key);
- if (ret)
- goto err;
- ret = register_shrinker(&workingset_shadow_shrinker);
- @@ -406,7 +407,7 @@
- goto err_list_lru;
- return 0;
- err_list_lru:
- - list_lru_destroy(&workingset_shadow_nodes);
- + list_lru_destroy(&__workingset_shadow_nodes);
- err:
- return ret;
- }
- diff -Nur linux-4.4.28.orig/mm/zsmalloc.c linux-4.4.28/mm/zsmalloc.c
- --- linux-4.4.28.orig/mm/zsmalloc.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/mm/zsmalloc.c 2016-11-01 21:26:58.832345891 +0100
- @@ -64,6 +64,7 @@
- #include <linux/debugfs.h>
- #include <linux/zsmalloc.h>
- #include <linux/zpool.h>
- +#include <linux/locallock.h>
-
- /*
- * This must be power of 2 and greater than of equal to sizeof(link_free).
- @@ -403,6 +404,7 @@
-
- /* per-cpu VM mapping areas for zspage accesses that cross page boundaries */
- static DEFINE_PER_CPU(struct mapping_area, zs_map_area);
- +static DEFINE_LOCAL_IRQ_LOCK(zs_map_area_lock);
-
- static int is_first_page(struct page *page)
- {
- @@ -1289,7 +1291,7 @@
- class = pool->size_class[class_idx];
- off = obj_idx_to_offset(page, obj_idx, class->size);
-
- - area = &get_cpu_var(zs_map_area);
- + area = &get_locked_var(zs_map_area_lock, zs_map_area);
- area->vm_mm = mm;
- if (off + class->size <= PAGE_SIZE) {
- /* this object is contained entirely within a page */
- @@ -1342,7 +1344,7 @@
-
- __zs_unmap_object(area, pages, off, class->size);
- }
- - put_cpu_var(zs_map_area);
- + put_locked_var(zs_map_area_lock, zs_map_area);
- unpin_tag(handle);
- }
- EXPORT_SYMBOL_GPL(zs_unmap_object);
- diff -Nur linux-4.4.28.orig/net/core/dev.c linux-4.4.28/net/core/dev.c
- --- linux-4.4.28.orig/net/core/dev.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/net/core/dev.c 2016-11-01 21:26:58.836346147 +0100
- @@ -186,6 +186,7 @@
- static DEFINE_HASHTABLE(napi_hash, 8);
-
- static seqcount_t devnet_rename_seq;
- +static DEFINE_MUTEX(devnet_rename_mutex);
-
- static inline void dev_base_seq_inc(struct net *net)
- {
- @@ -207,14 +208,14 @@
- static inline void rps_lock(struct softnet_data *sd)
- {
- #ifdef CONFIG_RPS
- - spin_lock(&sd->input_pkt_queue.lock);
- + raw_spin_lock(&sd->input_pkt_queue.raw_lock);
- #endif
- }
-
- static inline void rps_unlock(struct softnet_data *sd)
- {
- #ifdef CONFIG_RPS
- - spin_unlock(&sd->input_pkt_queue.lock);
- + raw_spin_unlock(&sd->input_pkt_queue.raw_lock);
- #endif
- }
-
- @@ -884,7 +885,8 @@
- strcpy(name, dev->name);
- rcu_read_unlock();
- if (read_seqcount_retry(&devnet_rename_seq, seq)) {
- - cond_resched();
- + mutex_lock(&devnet_rename_mutex);
- + mutex_unlock(&devnet_rename_mutex);
- goto retry;
- }
-
- @@ -1153,20 +1155,17 @@
- if (dev->flags & IFF_UP)
- return -EBUSY;
-
- - write_seqcount_begin(&devnet_rename_seq);
- + mutex_lock(&devnet_rename_mutex);
- + __raw_write_seqcount_begin(&devnet_rename_seq);
-
- - if (strncmp(newname, dev->name, IFNAMSIZ) == 0) {
- - write_seqcount_end(&devnet_rename_seq);
- - return 0;
- - }
- + if (strncmp(newname, dev->name, IFNAMSIZ) == 0)
- + goto outunlock;
-
- memcpy(oldname, dev->name, IFNAMSIZ);
-
- err = dev_get_valid_name(net, dev, newname);
- - if (err < 0) {
- - write_seqcount_end(&devnet_rename_seq);
- - return err;
- - }
- + if (err < 0)
- + goto outunlock;
-
- if (oldname[0] && !strchr(oldname, '%'))
- netdev_info(dev, "renamed from %s\n", oldname);
- @@ -1179,11 +1178,12 @@
- if (ret) {
- memcpy(dev->name, oldname, IFNAMSIZ);
- dev->name_assign_type = old_assign_type;
- - write_seqcount_end(&devnet_rename_seq);
- - return ret;
- + err = ret;
- + goto outunlock;
- }
-
- - write_seqcount_end(&devnet_rename_seq);
- + __raw_write_seqcount_end(&devnet_rename_seq);
- + mutex_unlock(&devnet_rename_mutex);
-
- netdev_adjacent_rename_links(dev, oldname);
-
- @@ -1204,7 +1204,8 @@
- /* err >= 0 after dev_alloc_name() or stores the first errno */
- if (err >= 0) {
- err = ret;
- - write_seqcount_begin(&devnet_rename_seq);
- + mutex_lock(&devnet_rename_mutex);
- + __raw_write_seqcount_begin(&devnet_rename_seq);
- memcpy(dev->name, oldname, IFNAMSIZ);
- memcpy(oldname, newname, IFNAMSIZ);
- dev->name_assign_type = old_assign_type;
- @@ -1217,6 +1218,11 @@
- }
-
- return err;
- +
- +outunlock:
- + __raw_write_seqcount_end(&devnet_rename_seq);
- + mutex_unlock(&devnet_rename_mutex);
- + return err;
- }
-
- /**
- @@ -2246,6 +2252,7 @@
- sd->output_queue_tailp = &q->next_sched;
- raise_softirq_irqoff(NET_TX_SOFTIRQ);
- local_irq_restore(flags);
- + preempt_check_resched_rt();
- }
-
- void __netif_schedule(struct Qdisc *q)
- @@ -2327,6 +2334,7 @@
- __this_cpu_write(softnet_data.completion_queue, skb);
- raise_softirq_irqoff(NET_TX_SOFTIRQ);
- local_irq_restore(flags);
- + preempt_check_resched_rt();
- }
- EXPORT_SYMBOL(__dev_kfree_skb_irq);
-
- @@ -2883,7 +2891,11 @@
- * This permits __QDISC___STATE_RUNNING owner to get the lock more
- * often and dequeue packets faster.
- */
- +#ifdef CONFIG_PREEMPT_RT_FULL
- + contended = true;
- +#else
- contended = qdisc_is_running(q);
- +#endif
- if (unlikely(contended))
- spin_lock(&q->busylock);
-
- @@ -2943,9 +2955,44 @@
- #define skb_update_prio(skb)
- #endif
-
- +#ifdef CONFIG_PREEMPT_RT_FULL
- +
- +static inline int xmit_rec_read(void)
- +{
- + return current->xmit_recursion;
- +}
- +
- +static inline void xmit_rec_inc(void)
- +{
- + current->xmit_recursion++;
- +}
- +
- +static inline void xmit_rec_dec(void)
- +{
- + current->xmit_recursion--;
- +}
- +
- +#else
- +
- DEFINE_PER_CPU(int, xmit_recursion);
- EXPORT_SYMBOL(xmit_recursion);
-
- +static inline int xmit_rec_read(void)
- +{
- + return __this_cpu_read(xmit_recursion);
- +}
- +
- +static inline void xmit_rec_inc(void)
- +{
- + __this_cpu_inc(xmit_recursion);
- +}
- +
- +static inline void xmit_rec_dec(void)
- +{
- + __this_cpu_dec(xmit_recursion);
- +}
- +#endif
- +
- #define RECURSION_LIMIT 10
-
- /**
- @@ -3138,7 +3185,7 @@
-
- if (txq->xmit_lock_owner != cpu) {
-
- - if (__this_cpu_read(xmit_recursion) > RECURSION_LIMIT)
- + if (xmit_rec_read() > RECURSION_LIMIT)
- goto recursion_alert;
-
- skb = validate_xmit_skb(skb, dev);
- @@ -3148,9 +3195,9 @@
- HARD_TX_LOCK(dev, txq, cpu);
-
- if (!netif_xmit_stopped(txq)) {
- - __this_cpu_inc(xmit_recursion);
- + xmit_rec_inc();
- skb = dev_hard_start_xmit(skb, dev, txq, &rc);
- - __this_cpu_dec(xmit_recursion);
- + xmit_rec_dec();
- if (dev_xmit_complete(rc)) {
- HARD_TX_UNLOCK(dev, txq);
- goto out;
- @@ -3524,6 +3571,7 @@
- rps_unlock(sd);
-
- local_irq_restore(flags);
- + preempt_check_resched_rt();
-
- atomic_long_inc(&skb->dev->rx_dropped);
- kfree_skb(skb);
- @@ -3542,7 +3590,7 @@
- struct rps_dev_flow voidflow, *rflow = &voidflow;
- int cpu;
-
- - preempt_disable();
- + migrate_disable();
- rcu_read_lock();
-
- cpu = get_rps_cpu(skb->dev, skb, &rflow);
- @@ -3552,13 +3600,13 @@
- ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail);
-
- rcu_read_unlock();
- - preempt_enable();
- + migrate_enable();
- } else
- #endif
- {
- unsigned int qtail;
- - ret = enqueue_to_backlog(skb, get_cpu(), &qtail);
- - put_cpu();
- + ret = enqueue_to_backlog(skb, get_cpu_light(), &qtail);
- + put_cpu_light();
- }
- return ret;
- }
- @@ -3592,16 +3640,44 @@
-
- trace_netif_rx_ni_entry(skb);
-
- - preempt_disable();
- + local_bh_disable();
- err = netif_rx_internal(skb);
- - if (local_softirq_pending())
- - do_softirq();
- - preempt_enable();
- + local_bh_enable();
-
- return err;
- }
- EXPORT_SYMBOL(netif_rx_ni);
-
- +#ifdef CONFIG_PREEMPT_RT_FULL
- +/*
- + * RT runs ksoftirqd as a real time thread and the root_lock is a
- + * "sleeping spinlock". If the trylock fails then we can go into an
- + * infinite loop when ksoftirqd preempted the task which actually
- + * holds the lock, because we requeue q and raise NET_TX softirq
- + * causing ksoftirqd to loop forever.
- + *
- + * It's safe to use spin_lock on RT here as softirqs run in thread
- + * context and cannot deadlock against the thread which is holding
- + * root_lock.
- + *
- + * On !RT the trylock might fail, but there we bail out from the
- + * softirq loop after 10 attempts which we can't do on RT. And the
- + * task holding root_lock cannot be preempted, so the only downside of
- + * that trylock is that we need 10 loops to decide that we should have
- + * given up in the first one :)
- + */
- +static inline int take_root_lock(spinlock_t *lock)
- +{
- + spin_lock(lock);
- + return 1;
- +}
- +#else
- +static inline int take_root_lock(spinlock_t *lock)
- +{
- + return spin_trylock(lock);
- +}
- +#endif
- +
- static void net_tx_action(struct softirq_action *h)
- {
- struct softnet_data *sd = this_cpu_ptr(&softnet_data);
- @@ -3643,7 +3719,7 @@
- head = head->next_sched;
-
- root_lock = qdisc_lock(q);
- - if (spin_trylock(root_lock)) {
- + if (take_root_lock(root_lock)) {
- smp_mb__before_atomic();
- clear_bit(__QDISC_STATE_SCHED,
- &q->state);
- @@ -4065,7 +4141,7 @@
- skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) {
- if (skb->dev == dev) {
- __skb_unlink(skb, &sd->input_pkt_queue);
- - kfree_skb(skb);
- + __skb_queue_tail(&sd->tofree_queue, skb);
- input_queue_head_incr(sd);
- }
- }
- @@ -4074,10 +4150,13 @@
- skb_queue_walk_safe(&sd->process_queue, skb, tmp) {
- if (skb->dev == dev) {
- __skb_unlink(skb, &sd->process_queue);
- - kfree_skb(skb);
- + __skb_queue_tail(&sd->tofree_queue, skb);
- input_queue_head_incr(sd);
- }
- }
- +
- + if (!skb_queue_empty(&sd->tofree_queue))
- + raise_softirq_irqoff(NET_RX_SOFTIRQ);
- }
-
- static int napi_gro_complete(struct sk_buff *skb)
- @@ -4531,6 +4610,7 @@
- sd->rps_ipi_list = NULL;
-
- local_irq_enable();
- + preempt_check_resched_rt();
-
- /* Send pending IPI's to kick RPS processing on remote cpus. */
- while (remsd) {
- @@ -4544,6 +4624,7 @@
- } else
- #endif
- local_irq_enable();
- + preempt_check_resched_rt();
- }
-
- static bool sd_has_rps_ipi_waiting(struct softnet_data *sd)
- @@ -4625,6 +4706,7 @@
- local_irq_save(flags);
- ____napi_schedule(this_cpu_ptr(&softnet_data), n);
- local_irq_restore(flags);
- + preempt_check_resched_rt();
- }
- EXPORT_SYMBOL(__napi_schedule);
-
- @@ -4901,7 +4983,7 @@
- list_splice_tail(&repoll, &list);
- list_splice(&list, &sd->poll_list);
- if (!list_empty(&sd->poll_list))
- - __raise_softirq_irqoff(NET_RX_SOFTIRQ);
- + __raise_softirq_irqoff_ksoft(NET_RX_SOFTIRQ);
-
- net_rps_action_and_irq_enable(sd);
- }
- @@ -7234,7 +7316,7 @@
- void synchronize_net(void)
- {
- might_sleep();
- - if (rtnl_is_locked())
- + if (rtnl_is_locked() && !IS_ENABLED(CONFIG_PREEMPT_RT_FULL))
- synchronize_rcu_expedited();
- else
- synchronize_rcu();
- @@ -7475,16 +7557,20 @@
-
- raise_softirq_irqoff(NET_TX_SOFTIRQ);
- local_irq_enable();
- + preempt_check_resched_rt();
-
- /* Process offline CPU's input_pkt_queue */
- while ((skb = __skb_dequeue(&oldsd->process_queue))) {
- netif_rx_ni(skb);
- input_queue_head_incr(oldsd);
- }
- - while ((skb = skb_dequeue(&oldsd->input_pkt_queue))) {
- + while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) {
- netif_rx_ni(skb);
- input_queue_head_incr(oldsd);
- }
- + while ((skb = __skb_dequeue(&oldsd->tofree_queue))) {
- + kfree_skb(skb);
- + }
-
- return NOTIFY_OK;
- }
- @@ -7786,8 +7872,9 @@
- for_each_possible_cpu(i) {
- struct softnet_data *sd = &per_cpu(softnet_data, i);
-
- - skb_queue_head_init(&sd->input_pkt_queue);
- - skb_queue_head_init(&sd->process_queue);
- + skb_queue_head_init_raw(&sd->input_pkt_queue);
- + skb_queue_head_init_raw(&sd->process_queue);
- + skb_queue_head_init_raw(&sd->tofree_queue);
- INIT_LIST_HEAD(&sd->poll_list);
- sd->output_queue_tailp = &sd->output_queue;
- #ifdef CONFIG_RPS
- diff -Nur linux-4.4.28.orig/net/core/skbuff.c linux-4.4.28/net/core/skbuff.c
- --- linux-4.4.28.orig/net/core/skbuff.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/net/core/skbuff.c 2016-11-01 21:26:58.836346147 +0100
- @@ -63,6 +63,7 @@
- #include <linux/errqueue.h>
- #include <linux/prefetch.h>
- #include <linux/if_vlan.h>
- +#include <linux/locallock.h>
-
- #include <net/protocol.h>
- #include <net/dst.h>
- @@ -351,6 +352,8 @@
-
- static DEFINE_PER_CPU(struct page_frag_cache, netdev_alloc_cache);
- static DEFINE_PER_CPU(struct page_frag_cache, napi_alloc_cache);
- +static DEFINE_LOCAL_IRQ_LOCK(netdev_alloc_lock);
- +static DEFINE_LOCAL_IRQ_LOCK(napi_alloc_cache_lock);
-
- static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask)
- {
- @@ -358,10 +361,10 @@
- unsigned long flags;
- void *data;
-
- - local_irq_save(flags);
- + local_lock_irqsave(netdev_alloc_lock, flags);
- nc = this_cpu_ptr(&netdev_alloc_cache);
- data = __alloc_page_frag(nc, fragsz, gfp_mask);
- - local_irq_restore(flags);
- + local_unlock_irqrestore(netdev_alloc_lock, flags);
- return data;
- }
-
- @@ -380,9 +383,13 @@
-
- static void *__napi_alloc_frag(unsigned int fragsz, gfp_t gfp_mask)
- {
- - struct page_frag_cache *nc = this_cpu_ptr(&napi_alloc_cache);
- + struct page_frag_cache *nc;
- + void *data;
-
- - return __alloc_page_frag(nc, fragsz, gfp_mask);
- + nc = &get_locked_var(napi_alloc_cache_lock, napi_alloc_cache);
- + data = __alloc_page_frag(nc, fragsz, gfp_mask);
- + put_locked_var(napi_alloc_cache_lock, napi_alloc_cache);
- + return data;
- }
-
- void *napi_alloc_frag(unsigned int fragsz)
- @@ -429,13 +436,13 @@
- if (sk_memalloc_socks())
- gfp_mask |= __GFP_MEMALLOC;
-
- - local_irq_save(flags);
- + local_lock_irqsave(netdev_alloc_lock, flags);
-
- nc = this_cpu_ptr(&netdev_alloc_cache);
- data = __alloc_page_frag(nc, len, gfp_mask);
- pfmemalloc = nc->pfmemalloc;
-
- - local_irq_restore(flags);
- + local_unlock_irqrestore(netdev_alloc_lock, flags);
-
- if (unlikely(!data))
- return NULL;
- @@ -476,9 +483,10 @@
- struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len,
- gfp_t gfp_mask)
- {
- - struct page_frag_cache *nc = this_cpu_ptr(&napi_alloc_cache);
- + struct page_frag_cache *nc;
- struct sk_buff *skb;
- void *data;
- + bool pfmemalloc;
-
- len += NET_SKB_PAD + NET_IP_ALIGN;
-
- @@ -496,7 +504,11 @@
- if (sk_memalloc_socks())
- gfp_mask |= __GFP_MEMALLOC;
-
- + nc = &get_locked_var(napi_alloc_cache_lock, napi_alloc_cache);
- data = __alloc_page_frag(nc, len, gfp_mask);
- + pfmemalloc = nc->pfmemalloc;
- + put_locked_var(napi_alloc_cache_lock, napi_alloc_cache);
- +
- if (unlikely(!data))
- return NULL;
-
- @@ -507,7 +519,7 @@
- }
-
- /* use OR instead of assignment to avoid clearing of bits in mask */
- - if (nc->pfmemalloc)
- + if (pfmemalloc)
- skb->pfmemalloc = 1;
- skb->head_frag = 1;
-
- diff -Nur linux-4.4.28.orig/net/core/sock.c linux-4.4.28/net/core/sock.c
- --- linux-4.4.28.orig/net/core/sock.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/net/core/sock.c 2016-11-01 21:26:58.836346147 +0100
- @@ -2435,12 +2435,11 @@
- if (sk->sk_lock.owned)
- __lock_sock(sk);
- sk->sk_lock.owned = 1;
- - spin_unlock(&sk->sk_lock.slock);
- + spin_unlock_bh(&sk->sk_lock.slock);
- /*
- * The sk_lock has mutex_lock() semantics here:
- */
- mutex_acquire(&sk->sk_lock.dep_map, subclass, 0, _RET_IP_);
- - local_bh_enable();
- }
- EXPORT_SYMBOL(lock_sock_nested);
-
- diff -Nur linux-4.4.28.orig/net/ipv4/icmp.c linux-4.4.28/net/ipv4/icmp.c
- --- linux-4.4.28.orig/net/ipv4/icmp.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/net/ipv4/icmp.c 2016-11-01 21:26:58.836346147 +0100
- @@ -69,6 +69,7 @@
- #include <linux/jiffies.h>
- #include <linux/kernel.h>
- #include <linux/fcntl.h>
- +#include <linux/sysrq.h>
- #include <linux/socket.h>
- #include <linux/in.h>
- #include <linux/inet.h>
- @@ -77,6 +78,7 @@
- #include <linux/string.h>
- #include <linux/netfilter_ipv4.h>
- #include <linux/slab.h>
- +#include <linux/locallock.h>
- #include <net/snmp.h>
- #include <net/ip.h>
- #include <net/route.h>
- @@ -204,6 +206,8 @@
- *
- * On SMP we have one ICMP socket per-cpu.
- */
- +static DEFINE_LOCAL_IRQ_LOCK(icmp_sk_lock);
- +
- static struct sock *icmp_sk(struct net *net)
- {
- return *this_cpu_ptr(net->ipv4.icmp_sk);
- @@ -215,12 +219,14 @@
-
- local_bh_disable();
-
- + local_lock(icmp_sk_lock);
- sk = icmp_sk(net);
-
- if (unlikely(!spin_trylock(&sk->sk_lock.slock))) {
- /* This can happen if the output path signals a
- * dst_link_failure() for an outgoing ICMP packet.
- */
- + local_unlock(icmp_sk_lock);
- local_bh_enable();
- return NULL;
- }
- @@ -230,6 +236,7 @@
- static inline void icmp_xmit_unlock(struct sock *sk)
- {
- spin_unlock_bh(&sk->sk_lock.slock);
- + local_unlock(icmp_sk_lock);
- }
-
- int sysctl_icmp_msgs_per_sec __read_mostly = 1000;
- @@ -358,6 +365,7 @@
- struct sock *sk;
- struct sk_buff *skb;
-
- + local_lock(icmp_sk_lock);
- sk = icmp_sk(dev_net((*rt)->dst.dev));
- if (ip_append_data(sk, fl4, icmp_glue_bits, icmp_param,
- icmp_param->data_len+icmp_param->head_len,
- @@ -380,6 +388,7 @@
- skb->ip_summed = CHECKSUM_NONE;
- ip_push_pending_frames(sk, fl4);
- }
- + local_unlock(icmp_sk_lock);
- }
-
- /*
- @@ -891,6 +900,30 @@
- }
-
- /*
- + * 32bit and 64bit have different timestamp length, so we check for
- + * the cookie at offset 20 and verify it is repeated at offset 50
- + */
- +#define CO_POS0 20
- +#define CO_POS1 50
- +#define CO_SIZE sizeof(int)
- +#define ICMP_SYSRQ_SIZE 57
- +
- +/*
- + * We got a ICMP_SYSRQ_SIZE sized ping request. Check for the cookie
- + * pattern and if it matches send the next byte as a trigger to sysrq.
- + */
- +static void icmp_check_sysrq(struct net *net, struct sk_buff *skb)
- +{
- + int cookie = htonl(net->ipv4.sysctl_icmp_echo_sysrq);
- + char *p = skb->data;
- +
- + if (!memcmp(&cookie, p + CO_POS0, CO_SIZE) &&
- + !memcmp(&cookie, p + CO_POS1, CO_SIZE) &&
- + p[CO_POS0 + CO_SIZE] == p[CO_POS1 + CO_SIZE])
- + handle_sysrq(p[CO_POS0 + CO_SIZE]);
- +}
- +
- +/*
- * Handle ICMP_ECHO ("ping") requests.
- *
- * RFC 1122: 3.2.2.6 MUST have an echo server that answers ICMP echo
- @@ -917,6 +950,11 @@
- icmp_param.data_len = skb->len;
- icmp_param.head_len = sizeof(struct icmphdr);
- icmp_reply(&icmp_param, skb);
- +
- + if (skb->len == ICMP_SYSRQ_SIZE &&
- + net->ipv4.sysctl_icmp_echo_sysrq) {
- + icmp_check_sysrq(net, skb);
- + }
- }
- /* should there be an ICMP stat for ignored echos? */
- return true;
- diff -Nur linux-4.4.28.orig/net/ipv4/sysctl_net_ipv4.c linux-4.4.28/net/ipv4/sysctl_net_ipv4.c
- --- linux-4.4.28.orig/net/ipv4/sysctl_net_ipv4.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/net/ipv4/sysctl_net_ipv4.c 2016-11-01 21:26:58.836346147 +0100
- @@ -818,6 +818,13 @@
- .proc_handler = proc_dointvec
- },
- {
- + .procname = "icmp_echo_sysrq",
- + .data = &init_net.ipv4.sysctl_icmp_echo_sysrq,
- + .maxlen = sizeof(int),
- + .mode = 0644,
- + .proc_handler = proc_dointvec
- + },
- + {
- .procname = "icmp_ignore_bogus_error_responses",
- .data = &init_net.ipv4.sysctl_icmp_ignore_bogus_error_responses,
- .maxlen = sizeof(int),
- diff -Nur linux-4.4.28.orig/net/ipv4/tcp_ipv4.c linux-4.4.28/net/ipv4/tcp_ipv4.c
- --- linux-4.4.28.orig/net/ipv4/tcp_ipv4.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/net/ipv4/tcp_ipv4.c 2016-11-01 21:26:58.840346411 +0100
- @@ -62,6 +62,7 @@
- #include <linux/init.h>
- #include <linux/times.h>
- #include <linux/slab.h>
- +#include <linux/locallock.h>
-
- #include <net/net_namespace.h>
- #include <net/icmp.h>
- @@ -566,6 +567,7 @@
- }
- EXPORT_SYMBOL(tcp_v4_send_check);
-
- +static DEFINE_LOCAL_IRQ_LOCK(tcp_sk_lock);
- /*
- * This routine will send an RST to the other tcp.
- *
- @@ -687,10 +689,13 @@
- arg.bound_dev_if = sk->sk_bound_dev_if;
-
- arg.tos = ip_hdr(skb)->tos;
- +
- + local_lock(tcp_sk_lock);
- ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk),
- skb, &TCP_SKB_CB(skb)->header.h4.opt,
- ip_hdr(skb)->saddr, ip_hdr(skb)->daddr,
- &arg, arg.iov[0].iov_len);
- + local_unlock(tcp_sk_lock);
-
- TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS);
- TCP_INC_STATS_BH(net, TCP_MIB_OUTRSTS);
- @@ -772,10 +777,12 @@
- if (oif)
- arg.bound_dev_if = oif;
- arg.tos = tos;
- + local_lock(tcp_sk_lock);
- ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk),
- skb, &TCP_SKB_CB(skb)->header.h4.opt,
- ip_hdr(skb)->saddr, ip_hdr(skb)->daddr,
- &arg, arg.iov[0].iov_len);
- + local_unlock(tcp_sk_lock);
-
- TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS);
- }
- diff -Nur linux-4.4.28.orig/net/mac80211/rx.c linux-4.4.28/net/mac80211/rx.c
- --- linux-4.4.28.orig/net/mac80211/rx.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/net/mac80211/rx.c 2016-11-01 21:26:58.840346411 +0100
- @@ -3574,7 +3574,7 @@
- struct ieee80211_supported_band *sband;
- struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb);
-
- - WARN_ON_ONCE(softirq_count() == 0);
- + WARN_ON_ONCE_NONRT(softirq_count() == 0);
-
- if (WARN_ON(status->band >= IEEE80211_NUM_BANDS))
- goto drop;
- diff -Nur linux-4.4.28.orig/net/netfilter/core.c linux-4.4.28/net/netfilter/core.c
- --- linux-4.4.28.orig/net/netfilter/core.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/net/netfilter/core.c 2016-11-01 21:26:58.840346411 +0100
- @@ -22,11 +22,17 @@
- #include <linux/proc_fs.h>
- #include <linux/mutex.h>
- #include <linux/slab.h>
- +#include <linux/locallock.h>
- #include <net/net_namespace.h>
- #include <net/sock.h>
-
- #include "nf_internals.h"
-
- +#ifdef CONFIG_PREEMPT_RT_BASE
- +DEFINE_LOCAL_IRQ_LOCK(xt_write_lock);
- +EXPORT_PER_CPU_SYMBOL(xt_write_lock);
- +#endif
- +
- static DEFINE_MUTEX(afinfo_mutex);
-
- const struct nf_afinfo __rcu *nf_afinfo[NFPROTO_NUMPROTO] __read_mostly;
- diff -Nur linux-4.4.28.orig/net/packet/af_packet.c linux-4.4.28/net/packet/af_packet.c
- --- linux-4.4.28.orig/net/packet/af_packet.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/net/packet/af_packet.c 2016-11-01 21:26:58.844346664 +0100
- @@ -63,6 +63,7 @@
- #include <linux/if_packet.h>
- #include <linux/wireless.h>
- #include <linux/kernel.h>
- +#include <linux/delay.h>
- #include <linux/kmod.h>
- #include <linux/slab.h>
- #include <linux/vmalloc.h>
- @@ -695,7 +696,7 @@
- if (BLOCK_NUM_PKTS(pbd)) {
- while (atomic_read(&pkc->blk_fill_in_prog)) {
- /* Waiting for skb_copy_bits to finish... */
- - cpu_relax();
- + cpu_chill();
- }
- }
-
- @@ -957,7 +958,7 @@
- if (!(status & TP_STATUS_BLK_TMO)) {
- while (atomic_read(&pkc->blk_fill_in_prog)) {
- /* Waiting for skb_copy_bits to finish... */
- - cpu_relax();
- + cpu_chill();
- }
- }
- prb_close_block(pkc, pbd, po, status);
- diff -Nur linux-4.4.28.orig/net/rds/ib_rdma.c linux-4.4.28/net/rds/ib_rdma.c
- --- linux-4.4.28.orig/net/rds/ib_rdma.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/net/rds/ib_rdma.c 2016-11-01 21:26:58.844346664 +0100
- @@ -34,6 +34,7 @@
- #include <linux/slab.h>
- #include <linux/rculist.h>
- #include <linux/llist.h>
- +#include <linux/delay.h>
-
- #include "rds.h"
- #include "ib.h"
- @@ -313,7 +314,7 @@
- for_each_online_cpu(cpu) {
- flag = &per_cpu(clean_list_grace, cpu);
- while (test_bit(CLEAN_LIST_BUSY_BIT, flag))
- - cpu_relax();
- + cpu_chill();
- }
- }
-
- diff -Nur linux-4.4.28.orig/net/sched/sch_generic.c linux-4.4.28/net/sched/sch_generic.c
- --- linux-4.4.28.orig/net/sched/sch_generic.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/net/sched/sch_generic.c 2016-11-01 21:26:58.844346664 +0100
- @@ -893,7 +893,7 @@
- /* Wait for outstanding qdisc_run calls. */
- list_for_each_entry(dev, head, close_list)
- while (some_qdisc_is_busy(dev))
- - yield();
- + msleep(1);
- }
-
- void dev_deactivate(struct net_device *dev)
- diff -Nur linux-4.4.28.orig/net/sunrpc/svc_xprt.c linux-4.4.28/net/sunrpc/svc_xprt.c
- --- linux-4.4.28.orig/net/sunrpc/svc_xprt.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/net/sunrpc/svc_xprt.c 2016-11-01 21:26:58.844346664 +0100
- @@ -340,7 +340,7 @@
- goto out;
- }
-
- - cpu = get_cpu();
- + cpu = get_cpu_light();
- pool = svc_pool_for_cpu(xprt->xpt_server, cpu);
-
- atomic_long_inc(&pool->sp_stats.packets);
- @@ -376,7 +376,7 @@
-
- atomic_long_inc(&pool->sp_stats.threads_woken);
- wake_up_process(rqstp->rq_task);
- - put_cpu();
- + put_cpu_light();
- goto out;
- }
- rcu_read_unlock();
- @@ -397,7 +397,7 @@
- goto redo_search;
- }
- rqstp = NULL;
- - put_cpu();
- + put_cpu_light();
- out:
- trace_svc_xprt_do_enqueue(xprt, rqstp);
- }
- diff -Nur linux-4.4.28.orig/scripts/mkcompile_h linux-4.4.28/scripts/mkcompile_h
- --- linux-4.4.28.orig/scripts/mkcompile_h 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/scripts/mkcompile_h 2016-11-01 21:26:58.844346664 +0100
- @@ -4,7 +4,8 @@
- ARCH=$2
- SMP=$3
- PREEMPT=$4
- -CC=$5
- +RT=$5
- +CC=$6
-
- vecho() { [ "${quiet}" = "silent_" ] || echo "$@" ; }
-
- @@ -57,6 +58,7 @@
- CONFIG_FLAGS=""
- if [ -n "$SMP" ] ; then CONFIG_FLAGS="SMP"; fi
- if [ -n "$PREEMPT" ] ; then CONFIG_FLAGS="$CONFIG_FLAGS PREEMPT"; fi
- +if [ -n "$RT" ] ; then CONFIG_FLAGS="$CONFIG_FLAGS RT"; fi
- UTS_VERSION="$UTS_VERSION $CONFIG_FLAGS $TIMESTAMP"
-
- # Truncate to maximum length
- diff -Nur linux-4.4.28.orig/sound/core/pcm_native.c linux-4.4.28/sound/core/pcm_native.c
- --- linux-4.4.28.orig/sound/core/pcm_native.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/sound/core/pcm_native.c 2016-11-01 21:26:58.844346664 +0100
- @@ -135,7 +135,7 @@
- void snd_pcm_stream_lock_irq(struct snd_pcm_substream *substream)
- {
- if (!substream->pcm->nonatomic)
- - local_irq_disable();
- + local_irq_disable_nort();
- snd_pcm_stream_lock(substream);
- }
- EXPORT_SYMBOL_GPL(snd_pcm_stream_lock_irq);
- @@ -150,7 +150,7 @@
- {
- snd_pcm_stream_unlock(substream);
- if (!substream->pcm->nonatomic)
- - local_irq_enable();
- + local_irq_enable_nort();
- }
- EXPORT_SYMBOL_GPL(snd_pcm_stream_unlock_irq);
-
- @@ -158,7 +158,7 @@
- {
- unsigned long flags = 0;
- if (!substream->pcm->nonatomic)
- - local_irq_save(flags);
- + local_irq_save_nort(flags);
- snd_pcm_stream_lock(substream);
- return flags;
- }
- @@ -176,7 +176,7 @@
- {
- snd_pcm_stream_unlock(substream);
- if (!substream->pcm->nonatomic)
- - local_irq_restore(flags);
- + local_irq_restore_nort(flags);
- }
- EXPORT_SYMBOL_GPL(snd_pcm_stream_unlock_irqrestore);
-
- diff -Nur linux-4.4.28.orig/virt/kvm/async_pf.c linux-4.4.28/virt/kvm/async_pf.c
- --- linux-4.4.28.orig/virt/kvm/async_pf.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/virt/kvm/async_pf.c 2016-11-01 21:26:58.844346664 +0100
- @@ -98,8 +98,8 @@
- * This memory barrier pairs with prepare_to_wait's set_current_state()
- */
- smp_mb();
- - if (waitqueue_active(&vcpu->wq))
- - wake_up_interruptible(&vcpu->wq);
- + if (swait_active(&vcpu->wq))
- + swake_up(&vcpu->wq);
-
- mmput(mm);
- kvm_put_kvm(vcpu->kvm);
- diff -Nur linux-4.4.28.orig/virt/kvm/kvm_main.c linux-4.4.28/virt/kvm/kvm_main.c
- --- linux-4.4.28.orig/virt/kvm/kvm_main.c 2016-10-28 09:53:25.000000000 +0200
- +++ linux-4.4.28/virt/kvm/kvm_main.c 2016-11-01 21:26:58.848346921 +0100
- @@ -228,8 +228,7 @@
- vcpu->kvm = kvm;
- vcpu->vcpu_id = id;
- vcpu->pid = NULL;
- - vcpu->halt_poll_ns = 0;
- - init_waitqueue_head(&vcpu->wq);
- + init_swait_queue_head(&vcpu->wq);
- kvm_async_pf_vcpu_init(vcpu);
-
- vcpu->pre_pcpu = -1;
- @@ -2005,7 +2004,7 @@
- void kvm_vcpu_block(struct kvm_vcpu *vcpu)
- {
- ktime_t start, cur;
- - DEFINE_WAIT(wait);
- + DECLARE_SWAITQUEUE(wait);
- bool waited = false;
- u64 block_ns;
-
- @@ -2030,7 +2029,7 @@
- kvm_arch_vcpu_blocking(vcpu);
-
- for (;;) {
- - prepare_to_wait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE);
- + prepare_to_swait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE);
-
- if (kvm_vcpu_check_block(vcpu) < 0)
- break;
- @@ -2039,7 +2038,7 @@
- schedule();
- }
-
- - finish_wait(&vcpu->wq, &wait);
- + finish_swait(&vcpu->wq, &wait);
- cur = ktime_get();
-
- kvm_arch_vcpu_unblocking(vcpu);
- @@ -2071,11 +2070,11 @@
- {
- int me;
- int cpu = vcpu->cpu;
- - wait_queue_head_t *wqp;
- + struct swait_queue_head *wqp;
-
- wqp = kvm_arch_vcpu_wq(vcpu);
- - if (waitqueue_active(wqp)) {
- - wake_up_interruptible(wqp);
- + if (swait_active(wqp)) {
- + swake_up(wqp);
- ++vcpu->stat.halt_wakeup;
- }
-
- @@ -2176,7 +2175,7 @@
- continue;
- if (vcpu == me)
- continue;
- - if (waitqueue_active(&vcpu->wq) && !kvm_arch_vcpu_runnable(vcpu))
- + if (swait_active(&vcpu->wq) && !kvm_arch_vcpu_runnable(vcpu))
- continue;
- if (!kvm_vcpu_eligible_for_directed_yield(vcpu))
- continue;
|
