1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859606162636465666768697071727374757677787980818283848586878889909192939495969798991001011021031041051061071081091101111121131141151161171181191201211221231241251261271281291301311321331341351361371381391401411421431441451461471481491501511521531541551561571581591601611621631641651661671681691701711721731741751761771781791801811821831841851861871881891901911921931941951961971981992002012022032042052062072082092102112122132142152162172182192202212222232242252262272282292302312322332342352362372382392402412422432442452462472482492502512522532542552562572582592602612622632642652662672682692702712722732742752762772782792802812822832842852862872882892902912922932942952962972982993003013023033043053063073083093103113123133143153163173183193203213223233243253263273283293303313323333343353363373383393403413423433443453463473483493503513523533543553563573583593603613623633643653663673683693703713723733743753763773783793803813823833843853863873883893903913923933943953963973983994004014024034044054064074084094104114124134144154164174184194204214224234244254264274284294304314324334344354364374384394404414424434444454464474484494504514524534544554564574584594604614624634644654664674684694704714724734744754764774784794804814824834844854864874884894904914924934944954964974984995005015025035045055065075085095105115125135145155165175185195205215225235245255265275285295305315325335345355365375385395405415425435445455465475485495505515525535545555565575585595605615625635645655665675685695705715725735745755765775785795805815825835845855865875885895905915925935945955965975985996006016026036046056066076086096106116126136146156166176186196206216226236246256266276286296306316326336346356366376386396406416426436446456466476486496506516526536546556566576586596606616626636646656666676686696706716726736746756766776786796806816826836846856866876886896906916926936946956966976986997007017027037047057067077087097107117127137147157167177187197207217227237247257267277287297307317327337347357367377387397407417427437447457467477487497507517527537547557567577587597607617627637647657667677687697707717727737747757767777787797807817827837847857867877887897907917927937947957967977987998008018028038048058068078088098108118128138148158168178188198208218228238248258268278288298308318328338348358368378388398408418428438448458468478488498508518528538548558568578588598608618628638648658668678688698708718728738748758768778788798808818828838848858868878888898908918928938948958968978988999009019029039049059069079089099109119129139149159169179189199209219229239249259269279289299309319329339349359369379389399409419429439449459469479489499509519529539549559569579589599609619629639649659669679689699709719729739749759769779789799809819829839849859869879889899909919929939949959969979989991000100110021003100410051006100710081009101010111012101310141015101610171018101910201021102210231024102510261027102810291030103110321033103410351036103710381039104010411042104310441045104610471048104910501051105210531054105510561057105810591060106110621063106410651066106710681069107010711072107310741075107610771078107910801081108210831084108510861087108810891090109110921093109410951096109710981099110011011102110311041105110611071108110911101111111211131114111511161117111811191120112111221123112411251126112711281129113011311132113311341135113611371138113911401141114211431144114511461147114811491150115111521153115411551156115711581159116011611162116311641165116611671168116911701171117211731174117511761177117811791180118111821183118411851186118711881189119011911192119311941195119611971198119912001201120212031204120512061207120812091210121112121213121412151216121712181219122012211222122312241225122612271228122912301231123212331234123512361237123812391240124112421243124412451246124712481249125012511252125312541255125612571258125912601261126212631264126512661267126812691270127112721273127412751276127712781279128012811282128312841285128612871288128912901291129212931294129512961297129812991300130113021303130413051306130713081309131013111312131313141315131613171318131913201321132213231324132513261327132813291330133113321333133413351336133713381339134013411342134313441345134613471348134913501351135213531354135513561357135813591360136113621363136413651366136713681369137013711372137313741375137613771378137913801381138213831384138513861387138813891390139113921393139413951396139713981399140014011402140314041405140614071408140914101411141214131414141514161417141814191420142114221423142414251426142714281429143014311432143314341435143614371438143914401441144214431444144514461447144814491450145114521453145414551456145714581459146014611462146314641465146614671468146914701471147214731474147514761477147814791480148114821483148414851486148714881489149014911492149314941495149614971498149915001501150215031504150515061507150815091510151115121513151415151516151715181519152015211522152315241525152615271528152915301531153215331534153515361537153815391540154115421543154415451546154715481549155015511552155315541555155615571558155915601561156215631564156515661567156815691570157115721573157415751576157715781579158015811582158315841585158615871588158915901591159215931594159515961597159815991600160116021603160416051606160716081609161016111612161316141615161616171618161916201621162216231624162516261627162816291630163116321633163416351636163716381639164016411642164316441645164616471648164916501651165216531654165516561657165816591660166116621663166416651666166716681669167016711672167316741675167616771678167916801681168216831684168516861687168816891690169116921693169416951696169716981699170017011702170317041705170617071708170917101711171217131714171517161717171817191720172117221723172417251726172717281729173017311732173317341735173617371738173917401741174217431744174517461747174817491750175117521753175417551756175717581759176017611762176317641765176617671768176917701771177217731774177517761777177817791780178117821783178417851786178717881789179017911792179317941795179617971798179918001801180218031804180518061807180818091810181118121813181418151816181718181819182018211822182318241825182618271828182918301831183218331834183518361837183818391840184118421843184418451846184718481849185018511852185318541855185618571858185918601861186218631864186518661867186818691870187118721873187418751876187718781879188018811882188318841885188618871888188918901891189218931894189518961897189818991900190119021903190419051906190719081909191019111912191319141915191619171918191919201921192219231924192519261927192819291930193119321933193419351936193719381939194019411942194319441945194619471948194919501951195219531954195519561957195819591960196119621963196419651966196719681969197019711972197319741975197619771978197919801981198219831984198519861987198819891990199119921993199419951996199719981999200020012002200320042005200620072008200920102011201220132014201520162017201820192020202120222023202420252026202720282029203020312032203320342035203620372038203920402041204220432044204520462047204820492050205120522053205420552056205720582059206020612062206320642065206620672068206920702071207220732074207520762077207820792080208120822083208420852086208720882089209020912092209320942095209620972098209921002101210221032104210521062107210821092110211121122113211421152116211721182119212021212122212321242125212621272128212921302131213221332134213521362137213821392140214121422143214421452146214721482149215021512152215321542155215621572158215921602161216221632164216521662167216821692170217121722173217421752176217721782179218021812182218321842185218621872188218921902191219221932194219521962197219821992200220122022203220422052206220722082209221022112212221322142215221622172218221922202221222222232224222522262227222822292230223122322233223422352236223722382239224022412242224322442245224622472248224922502251225222532254225522562257225822592260226122622263226422652266226722682269227022712272227322742275227622772278227922802281228222832284228522862287228822892290229122922293229422952296229722982299230023012302230323042305230623072308230923102311231223132314231523162317231823192320232123222323232423252326232723282329233023312332233323342335233623372338233923402341234223432344234523462347234823492350235123522353235423552356235723582359236023612362236323642365236623672368236923702371237223732374237523762377237823792380238123822383238423852386238723882389239023912392239323942395239623972398239924002401240224032404240524062407240824092410241124122413241424152416241724182419242024212422242324242425242624272428242924302431243224332434243524362437243824392440244124422443244424452446244724482449245024512452245324542455245624572458245924602461246224632464246524662467246824692470247124722473247424752476247724782479248024812482248324842485248624872488248924902491249224932494249524962497249824992500250125022503250425052506250725082509251025112512251325142515251625172518251925202521252225232524252525262527252825292530253125322533253425352536253725382539254025412542254325442545254625472548254925502551255225532554255525562557255825592560256125622563256425652566256725682569257025712572257325742575257625772578257925802581258225832584258525862587258825892590259125922593259425952596259725982599260026012602260326042605260626072608260926102611261226132614261526162617261826192620262126222623262426252626262726282629263026312632263326342635263626372638263926402641264226432644264526462647264826492650265126522653265426552656265726582659266026612662266326642665266626672668266926702671267226732674267526762677267826792680268126822683268426852686268726882689269026912692269326942695269626972698269927002701270227032704270527062707270827092710271127122713271427152716271727182719272027212722272327242725272627272728272927302731273227332734273527362737273827392740274127422743274427452746274727482749275027512752275327542755275627572758275927602761276227632764276527662767276827692770277127722773277427752776277727782779278027812782278327842785278627872788278927902791279227932794279527962797279827992800280128022803280428052806280728082809281028112812281328142815281628172818281928202821282228232824282528262827282828292830283128322833283428352836283728382839284028412842284328442845284628472848284928502851285228532854285528562857285828592860286128622863286428652866286728682869287028712872287328742875287628772878287928802881288228832884288528862887288828892890289128922893289428952896289728982899290029012902290329042905290629072908290929102911291229132914291529162917291829192920292129222923292429252926292729282929293029312932293329342935293629372938293929402941294229432944294529462947294829492950295129522953295429552956295729582959296029612962296329642965296629672968296929702971297229732974297529762977297829792980298129822983298429852986298729882989299029912992299329942995299629972998299930003001300230033004300530063007300830093010301130123013301430153016301730183019302030213022302330243025302630273028302930303031303230333034303530363037303830393040304130423043304430453046304730483049305030513052305330543055305630573058305930603061306230633064306530663067306830693070307130723073307430753076307730783079308030813082308330843085308630873088308930903091309230933094309530963097309830993100310131023103310431053106310731083109311031113112311331143115311631173118311931203121312231233124312531263127312831293130313131323133313431353136313731383139314031413142314331443145314631473148314931503151315231533154315531563157315831593160316131623163316431653166316731683169317031713172317331743175317631773178317931803181318231833184318531863187318831893190319131923193319431953196319731983199320032013202320332043205320632073208320932103211321232133214321532163217321832193220322132223223322432253226322732283229323032313232323332343235323632373238323932403241324232433244324532463247324832493250325132523253325432553256325732583259326032613262326332643265326632673268326932703271327232733274327532763277327832793280328132823283328432853286328732883289329032913292329332943295329632973298329933003301330233033304330533063307330833093310331133123313331433153316331733183319332033213322332333243325332633273328332933303331333233333334333533363337333833393340334133423343334433453346334733483349335033513352335333543355335633573358335933603361336233633364336533663367336833693370337133723373337433753376337733783379338033813382338333843385338633873388338933903391339233933394339533963397339833993400340134023403340434053406340734083409341034113412341334143415341634173418341934203421342234233424342534263427342834293430343134323433343434353436343734383439344034413442344334443445344634473448344934503451345234533454345534563457345834593460346134623463346434653466346734683469347034713472347334743475347634773478347934803481348234833484348534863487348834893490349134923493349434953496349734983499350035013502350335043505350635073508350935103511351235133514351535163517351835193520352135223523352435253526352735283529353035313532353335343535353635373538353935403541354235433544354535463547354835493550355135523553355435553556355735583559356035613562356335643565356635673568356935703571357235733574357535763577357835793580358135823583358435853586358735883589359035913592359335943595359635973598359936003601360236033604360536063607360836093610361136123613361436153616361736183619362036213622362336243625362636273628362936303631363236333634363536363637363836393640364136423643364436453646364736483649365036513652365336543655365636573658365936603661366236633664366536663667366836693670367136723673367436753676367736783679368036813682368336843685368636873688368936903691369236933694369536963697369836993700370137023703370437053706370737083709371037113712371337143715371637173718371937203721372237233724372537263727372837293730373137323733373437353736373737383739374037413742374337443745374637473748374937503751375237533754375537563757375837593760376137623763376437653766376737683769377037713772377337743775377637773778377937803781378237833784378537863787378837893790379137923793379437953796379737983799380038013802380338043805380638073808380938103811381238133814381538163817381838193820382138223823382438253826382738283829383038313832383338343835383638373838383938403841384238433844384538463847384838493850385138523853385438553856385738583859386038613862386338643865386638673868386938703871387238733874387538763877387838793880388138823883388438853886388738883889389038913892389338943895389638973898389939003901390239033904390539063907390839093910391139123913391439153916391739183919392039213922392339243925392639273928392939303931393239333934393539363937393839393940394139423943394439453946394739483949395039513952395339543955395639573958395939603961396239633964396539663967396839693970397139723973397439753976397739783979398039813982398339843985398639873988398939903991399239933994399539963997399839994000400140024003400440054006400740084009401040114012401340144015401640174018401940204021402240234024402540264027402840294030403140324033403440354036403740384039404040414042404340444045404640474048404940504051405240534054405540564057405840594060406140624063406440654066406740684069407040714072407340744075407640774078407940804081408240834084408540864087408840894090409140924093409440954096409740984099410041014102410341044105410641074108410941104111411241134114411541164117411841194120412141224123412441254126412741284129413041314132413341344135413641374138413941404141414241434144414541464147414841494150415141524153415441554156415741584159416041614162416341644165416641674168416941704171417241734174417541764177417841794180418141824183418441854186418741884189419041914192419341944195419641974198419942004201420242034204420542064207420842094210421142124213421442154216421742184219422042214222422342244225422642274228422942304231423242334234423542364237423842394240424142424243424442454246424742484249425042514252425342544255425642574258425942604261426242634264426542664267426842694270427142724273427442754276427742784279428042814282428342844285428642874288428942904291429242934294429542964297429842994300430143024303430443054306430743084309431043114312431343144315431643174318431943204321432243234324432543264327432843294330433143324333433443354336433743384339434043414342434343444345434643474348434943504351435243534354435543564357435843594360436143624363436443654366436743684369437043714372437343744375437643774378437943804381438243834384438543864387438843894390439143924393439443954396439743984399440044014402440344044405440644074408440944104411441244134414441544164417441844194420442144224423442444254426442744284429443044314432443344344435443644374438443944404441444244434444444544464447444844494450445144524453445444554456445744584459446044614462446344644465446644674468446944704471447244734474447544764477447844794480448144824483448444854486448744884489449044914492449344944495449644974498449945004501450245034504450545064507450845094510451145124513451445154516451745184519452045214522452345244525452645274528452945304531453245334534453545364537453845394540454145424543454445454546454745484549455045514552455345544555455645574558455945604561456245634564456545664567456845694570457145724573457445754576457745784579458045814582458345844585458645874588458945904591459245934594459545964597459845994600460146024603460446054606460746084609461046114612461346144615461646174618461946204621462246234624462546264627462846294630463146324633463446354636463746384639464046414642464346444645464646474648464946504651465246534654465546564657465846594660466146624663466446654666466746684669467046714672467346744675467646774678467946804681468246834684468546864687468846894690469146924693469446954696469746984699470047014702470347044705470647074708470947104711471247134714471547164717471847194720472147224723472447254726472747284729473047314732473347344735473647374738473947404741474247434744474547464747474847494750475147524753475447554756475747584759476047614762476347644765476647674768476947704771477247734774477547764777477847794780478147824783478447854786478747884789479047914792479347944795479647974798479948004801480248034804480548064807480848094810481148124813481448154816481748184819482048214822482348244825482648274828482948304831483248334834483548364837483848394840484148424843484448454846484748484849485048514852485348544855485648574858485948604861486248634864486548664867486848694870487148724873487448754876487748784879488048814882488348844885488648874888488948904891489248934894489548964897489848994900490149024903490449054906490749084909491049114912491349144915491649174918491949204921492249234924492549264927492849294930493149324933493449354936493749384939494049414942494349444945494649474948494949504951495249534954495549564957495849594960496149624963496449654966496749684969497049714972497349744975497649774978497949804981498249834984498549864987498849894990499149924993499449954996499749984999500050015002500350045005500650075008500950105011501250135014501550165017501850195020502150225023502450255026502750285029503050315032503350345035503650375038503950405041504250435044504550465047504850495050505150525053505450555056505750585059506050615062506350645065506650675068506950705071507250735074507550765077507850795080508150825083508450855086508750885089509050915092509350945095509650975098509951005101510251035104510551065107510851095110511151125113511451155116511751185119512051215122512351245125512651275128512951305131513251335134513551365137513851395140514151425143514451455146514751485149515051515152515351545155515651575158515951605161516251635164516551665167516851695170517151725173517451755176517751785179518051815182518351845185518651875188518951905191519251935194519551965197519851995200520152025203520452055206520752085209521052115212521352145215521652175218521952205221522252235224522552265227522852295230523152325233523452355236523752385239524052415242524352445245524652475248524952505251525252535254525552565257525852595260526152625263526452655266526752685269527052715272527352745275527652775278527952805281528252835284528552865287528852895290529152925293529452955296529752985299530053015302530353045305530653075308530953105311531253135314531553165317531853195320532153225323532453255326532753285329533053315332533353345335533653375338533953405341534253435344534553465347534853495350535153525353535453555356535753585359536053615362536353645365536653675368536953705371537253735374537553765377537853795380538153825383538453855386538753885389539053915392539353945395539653975398539954005401540254035404540554065407540854095410541154125413541454155416541754185419542054215422542354245425542654275428542954305431543254335434543554365437543854395440544154425443544454455446544754485449545054515452545354545455545654575458545954605461546254635464546554665467546854695470547154725473547454755476547754785479548054815482548354845485548654875488548954905491549254935494549554965497549854995500550155025503550455055506550755085509551055115512551355145515551655175518551955205521552255235524552555265527552855295530553155325533553455355536553755385539554055415542554355445545554655475548554955505551555255535554555555565557555855595560556155625563556455655566556755685569557055715572557355745575557655775578557955805581558255835584558555865587558855895590559155925593559455955596559755985599560056015602560356045605560656075608560956105611561256135614561556165617561856195620562156225623562456255626562756285629563056315632563356345635563656375638563956405641564256435644564556465647564856495650565156525653565456555656565756585659566056615662566356645665566656675668566956705671567256735674567556765677567856795680568156825683568456855686568756885689569056915692569356945695569656975698569957005701570257035704570557065707570857095710571157125713571457155716571757185719572057215722572357245725572657275728572957305731573257335734573557365737573857395740574157425743574457455746574757485749575057515752575357545755575657575758575957605761576257635764576557665767576857695770577157725773577457755776577757785779578057815782578357845785578657875788578957905791579257935794579557965797579857995800580158025803580458055806580758085809581058115812581358145815581658175818581958205821582258235824582558265827582858295830583158325833583458355836583758385839584058415842584358445845584658475848584958505851585258535854585558565857585858595860586158625863586458655866586758685869587058715872587358745875587658775878587958805881588258835884588558865887588858895890589158925893589458955896589758985899590059015902590359045905590659075908590959105911591259135914591559165917591859195920592159225923592459255926592759285929593059315932593359345935593659375938593959405941594259435944594559465947594859495950595159525953595459555956595759585959596059615962596359645965596659675968596959705971597259735974597559765977597859795980598159825983598459855986598759885989599059915992599359945995599659975998599960006001600260036004600560066007600860096010601160126013601460156016601760186019602060216022602360246025602660276028602960306031603260336034603560366037603860396040604160426043604460456046604760486049605060516052605360546055605660576058605960606061606260636064606560666067606860696070607160726073607460756076607760786079608060816082608360846085608660876088608960906091609260936094609560966097609860996100610161026103610461056106610761086109611061116112611361146115611661176118611961206121612261236124612561266127612861296130613161326133613461356136613761386139614061416142614361446145614661476148614961506151615261536154615561566157615861596160616161626163616461656166616761686169617061716172617361746175617661776178617961806181618261836184618561866187618861896190619161926193619461956196619761986199620062016202620362046205620662076208620962106211621262136214621562166217621862196220622162226223622462256226622762286229623062316232623362346235623662376238623962406241624262436244624562466247624862496250625162526253625462556256625762586259626062616262626362646265626662676268626962706271627262736274627562766277627862796280628162826283628462856286628762886289629062916292629362946295629662976298629963006301630263036304630563066307630863096310631163126313631463156316631763186319632063216322632363246325632663276328632963306331633263336334633563366337633863396340634163426343634463456346634763486349635063516352635363546355635663576358635963606361636263636364636563666367636863696370637163726373637463756376637763786379638063816382638363846385638663876388638963906391639263936394639563966397639863996400640164026403640464056406640764086409641064116412641364146415641664176418641964206421642264236424642564266427642864296430643164326433643464356436643764386439644064416442644364446445644664476448644964506451645264536454645564566457645864596460646164626463646464656466646764686469647064716472647364746475647664776478647964806481648264836484648564866487648864896490649164926493649464956496649764986499650065016502650365046505650665076508650965106511651265136514651565166517651865196520652165226523652465256526652765286529653065316532653365346535653665376538653965406541654265436544654565466547654865496550655165526553655465556556655765586559656065616562656365646565656665676568656965706571657265736574657565766577657865796580658165826583658465856586658765886589659065916592659365946595659665976598659966006601660266036604660566066607660866096610661166126613661466156616661766186619662066216622662366246625662666276628662966306631663266336634663566366637663866396640664166426643664466456646664766486649665066516652665366546655665666576658665966606661666266636664666566666667666866696670667166726673667466756676667766786679668066816682668366846685668666876688668966906691669266936694669566966697669866996700670167026703670467056706670767086709671067116712671367146715671667176718671967206721672267236724672567266727672867296730673167326733673467356736673767386739674067416742674367446745674667476748674967506751675267536754675567566757675867596760676167626763676467656766676767686769677067716772677367746775677667776778677967806781678267836784678567866787678867896790679167926793679467956796679767986799680068016802680368046805680668076808680968106811681268136814681568166817681868196820682168226823682468256826682768286829683068316832683368346835683668376838683968406841684268436844684568466847684868496850685168526853685468556856685768586859686068616862686368646865686668676868686968706871687268736874687568766877687868796880688168826883688468856886688768886889689068916892689368946895689668976898689969006901690269036904690569066907690869096910691169126913691469156916691769186919692069216922692369246925692669276928692969306931693269336934693569366937693869396940694169426943694469456946694769486949695069516952695369546955695669576958695969606961696269636964696569666967696869696970697169726973697469756976697769786979698069816982698369846985698669876988698969906991699269936994699569966997699869997000700170027003700470057006700770087009701070117012701370147015701670177018701970207021702270237024702570267027702870297030703170327033703470357036703770387039704070417042704370447045704670477048704970507051705270537054705570567057705870597060706170627063706470657066706770687069707070717072707370747075707670777078707970807081708270837084708570867087708870897090709170927093709470957096709770987099710071017102710371047105710671077108710971107111711271137114711571167117711871197120712171227123712471257126712771287129713071317132713371347135713671377138713971407141714271437144714571467147714871497150715171527153715471557156715771587159716071617162716371647165716671677168716971707171717271737174717571767177717871797180718171827183718471857186718771887189719071917192719371947195719671977198719972007201720272037204720572067207720872097210721172127213721472157216721772187219722072217222722372247225722672277228722972307231723272337234723572367237723872397240724172427243724472457246724772487249725072517252725372547255725672577258725972607261726272637264726572667267726872697270727172727273727472757276727772787279728072817282728372847285728672877288728972907291729272937294729572967297729872997300730173027303730473057306730773087309731073117312731373147315731673177318731973207321732273237324732573267327732873297330733173327333733473357336733773387339734073417342734373447345734673477348734973507351735273537354735573567357735873597360736173627363736473657366736773687369737073717372737373747375737673777378737973807381738273837384738573867387738873897390739173927393739473957396739773987399740074017402740374047405740674077408740974107411741274137414741574167417741874197420742174227423742474257426742774287429743074317432743374347435743674377438743974407441744274437444744574467447744874497450745174527453745474557456745774587459746074617462746374647465746674677468746974707471747274737474747574767477747874797480748174827483748474857486748774887489749074917492749374947495749674977498749975007501750275037504750575067507750875097510751175127513751475157516751775187519752075217522752375247525752675277528752975307531753275337534753575367537753875397540754175427543754475457546754775487549755075517552755375547555755675577558755975607561756275637564756575667567756875697570757175727573757475757576757775787579758075817582758375847585758675877588758975907591759275937594759575967597759875997600760176027603760476057606760776087609761076117612761376147615761676177618761976207621762276237624762576267627762876297630763176327633763476357636763776387639764076417642764376447645764676477648764976507651765276537654765576567657765876597660766176627663766476657666766776687669767076717672767376747675767676777678767976807681768276837684768576867687768876897690769176927693769476957696769776987699770077017702770377047705770677077708770977107711771277137714771577167717771877197720772177227723772477257726772777287729773077317732773377347735773677377738773977407741774277437744774577467747774877497750775177527753775477557756775777587759776077617762776377647765776677677768776977707771777277737774777577767777777877797780778177827783778477857786778777887789779077917792779377947795779677977798779978007801780278037804780578067807780878097810781178127813781478157816781778187819782078217822782378247825782678277828782978307831783278337834783578367837783878397840784178427843784478457846784778487849785078517852785378547855785678577858785978607861786278637864786578667867786878697870787178727873787478757876787778787879788078817882788378847885788678877888788978907891789278937894789578967897789878997900790179027903790479057906790779087909791079117912791379147915791679177918791979207921792279237924792579267927792879297930793179327933793479357936793779387939794079417942794379447945794679477948794979507951795279537954795579567957795879597960796179627963796479657966796779687969797079717972797379747975797679777978797979807981798279837984798579867987798879897990799179927993799479957996799779987999800080018002800380048005800680078008800980108011801280138014801580168017801880198020802180228023802480258026802780288029803080318032803380348035803680378038803980408041804280438044804580468047804880498050805180528053805480558056805780588059806080618062806380648065806680678068806980708071807280738074807580768077807880798080808180828083808480858086808780888089809080918092809380948095809680978098809981008101810281038104810581068107810881098110811181128113811481158116811781188119812081218122812381248125812681278128812981308131813281338134813581368137813881398140814181428143814481458146814781488149815081518152815381548155815681578158815981608161816281638164816581668167816881698170817181728173817481758176817781788179818081818182818381848185818681878188818981908191819281938194819581968197819881998200820182028203820482058206820782088209821082118212821382148215821682178218821982208221822282238224822582268227822882298230823182328233823482358236823782388239824082418242824382448245824682478248824982508251825282538254825582568257825882598260826182628263826482658266826782688269827082718272827382748275827682778278827982808281828282838284828582868287828882898290829182928293829482958296829782988299830083018302830383048305830683078308830983108311831283138314831583168317831883198320832183228323832483258326832783288329833083318332833383348335833683378338833983408341834283438344834583468347834883498350835183528353835483558356835783588359836083618362836383648365836683678368836983708371837283738374837583768377837883798380838183828383838483858386838783888389839083918392839383948395839683978398839984008401840284038404840584068407840884098410841184128413841484158416841784188419842084218422842384248425842684278428842984308431843284338434843584368437843884398440844184428443844484458446844784488449845084518452845384548455845684578458845984608461846284638464846584668467846884698470847184728473847484758476847784788479848084818482848384848485848684878488848984908491849284938494849584968497849884998500850185028503850485058506850785088509851085118512851385148515851685178518851985208521852285238524852585268527852885298530853185328533853485358536853785388539854085418542854385448545854685478548854985508551855285538554855585568557855885598560856185628563856485658566856785688569857085718572857385748575857685778578857985808581858285838584858585868587858885898590859185928593859485958596859785988599860086018602860386048605860686078608860986108611861286138614861586168617861886198620862186228623862486258626862786288629863086318632863386348635863686378638863986408641864286438644864586468647864886498650865186528653865486558656865786588659866086618662866386648665866686678668866986708671867286738674867586768677867886798680868186828683868486858686868786888689869086918692869386948695869686978698869987008701870287038704870587068707870887098710871187128713871487158716871787188719872087218722872387248725872687278728872987308731873287338734873587368737873887398740874187428743874487458746874787488749875087518752875387548755875687578758875987608761876287638764876587668767876887698770877187728773877487758776877787788779878087818782878387848785878687878788878987908791879287938794879587968797879887998800880188028803880488058806880788088809881088118812881388148815881688178818881988208821882288238824882588268827882888298830883188328833883488358836883788388839884088418842884388448845884688478848884988508851885288538854885588568857885888598860886188628863886488658866886788688869887088718872887388748875887688778878887988808881888288838884888588868887888888898890889188928893889488958896889788988899890089018902890389048905890689078908890989108911891289138914891589168917891889198920892189228923892489258926892789288929893089318932893389348935893689378938893989408941894289438944894589468947894889498950895189528953895489558956895789588959896089618962896389648965896689678968896989708971897289738974897589768977897889798980898189828983898489858986898789888989899089918992899389948995899689978998899990009001900290039004900590069007900890099010901190129013901490159016901790189019902090219022902390249025902690279028902990309031903290339034903590369037903890399040904190429043904490459046904790489049905090519052905390549055905690579058905990609061906290639064906590669067906890699070907190729073907490759076907790789079908090819082908390849085908690879088908990909091909290939094909590969097909890999100910191029103910491059106910791089109911091119112911391149115911691179118911991209121912291239124912591269127912891299130913191329133913491359136913791389139914091419142914391449145914691479148914991509151915291539154915591569157915891599160916191629163916491659166916791689169917091719172917391749175917691779178917991809181918291839184918591869187918891899190919191929193919491959196919791989199920092019202920392049205920692079208920992109211921292139214921592169217921892199220922192229223922492259226922792289229923092319232923392349235923692379238923992409241924292439244924592469247924892499250925192529253925492559256925792589259926092619262926392649265926692679268926992709271927292739274927592769277927892799280928192829283928492859286928792889289929092919292929392949295929692979298929993009301930293039304930593069307930893099310931193129313931493159316931793189319932093219322932393249325932693279328932993309331933293339334933593369337933893399340934193429343934493459346934793489349935093519352935393549355935693579358935993609361936293639364936593669367936893699370937193729373937493759376937793789379938093819382938393849385938693879388938993909391939293939394939593969397939893999400940194029403940494059406940794089409941094119412941394149415941694179418941994209421942294239424942594269427942894299430943194329433943494359436943794389439944094419442944394449445944694479448944994509451945294539454945594569457945894599460946194629463946494659466946794689469947094719472947394749475947694779478947994809481948294839484948594869487948894899490949194929493949494959496949794989499950095019502950395049505950695079508950995109511951295139514951595169517951895199520952195229523952495259526952795289529953095319532953395349535953695379538953995409541954295439544954595469547954895499550955195529553955495559556955795589559956095619562956395649565956695679568956995709571957295739574957595769577957895799580958195829583958495859586958795889589959095919592959395949595959695979598959996009601960296039604960596069607960896099610961196129613961496159616961796189619962096219622962396249625962696279628962996309631963296339634963596369637963896399640964196429643964496459646964796489649965096519652965396549655965696579658965996609661966296639664966596669667966896699670967196729673967496759676967796789679968096819682968396849685968696879688968996909691969296939694969596969697969896999700970197029703970497059706970797089709971097119712971397149715971697179718971997209721972297239724972597269727972897299730973197329733973497359736973797389739974097419742974397449745974697479748974997509751975297539754975597569757975897599760976197629763976497659766976797689769977097719772977397749775977697779778977997809781978297839784978597869787978897899790979197929793979497959796979797989799980098019802980398049805980698079808980998109811981298139814981598169817981898199820982198229823982498259826982798289829983098319832983398349835983698379838983998409841984298439844984598469847984898499850985198529853985498559856985798589859986098619862986398649865986698679868986998709871987298739874987598769877987898799880988198829883988498859886988798889889989098919892989398949895989698979898989999009901990299039904990599069907990899099910991199129913991499159916991799189919992099219922992399249925992699279928992999309931993299339934993599369937993899399940994199429943994499459946994799489949995099519952995399549955995699579958995999609961996299639964996599669967996899699970997199729973997499759976997799789979998099819982998399849985998699879988998999909991999299939994999599969997999899991000010001100021000310004100051000610007100081000910010100111001210013100141001510016100171001810019100201002110022100231002410025100261002710028100291003010031100321003310034100351003610037100381003910040100411004210043100441004510046100471004810049100501005110052100531005410055100561005710058100591006010061100621006310064100651006610067100681006910070100711007210073100741007510076100771007810079100801008110082100831008410085100861008710088100891009010091100921009310094100951009610097100981009910100101011010210103101041010510106101071010810109101101011110112101131011410115101161011710118101191012010121101221012310124101251012610127101281012910130101311013210133101341013510136101371013810139101401014110142101431014410145101461014710148101491015010151101521015310154101551015610157101581015910160101611016210163101641016510166101671016810169101701017110172101731017410175101761017710178101791018010181101821018310184101851018610187101881018910190101911019210193101941019510196101971019810199102001020110202102031020410205102061020710208102091021010211102121021310214102151021610217102181021910220102211022210223102241022510226102271022810229102301023110232102331023410235102361023710238102391024010241102421024310244102451024610247102481024910250102511025210253102541025510256102571025810259102601026110262102631026410265102661026710268102691027010271102721027310274102751027610277102781027910280102811028210283102841028510286102871028810289102901029110292102931029410295102961029710298102991030010301103021030310304103051030610307103081030910310103111031210313103141031510316103171031810319103201032110322103231032410325103261032710328103291033010331103321033310334103351033610337103381033910340103411034210343103441034510346103471034810349103501035110352103531035410355103561035710358103591036010361103621036310364103651036610367103681036910370103711037210373103741037510376103771037810379103801038110382103831038410385103861038710388103891039010391103921039310394103951039610397103981039910400104011040210403104041040510406104071040810409104101041110412104131041410415104161041710418104191042010421104221042310424104251042610427104281042910430104311043210433104341043510436104371043810439104401044110442104431044410445104461044710448104491045010451104521045310454104551045610457104581045910460104611046210463104641046510466104671046810469104701047110472104731047410475104761047710478104791048010481104821048310484104851048610487104881048910490104911049210493104941049510496104971049810499105001050110502105031050410505105061050710508105091051010511105121051310514105151051610517105181051910520105211052210523105241052510526105271052810529105301053110532105331053410535105361053710538105391054010541105421054310544105451054610547105481054910550105511055210553105541055510556105571055810559105601056110562105631056410565105661056710568105691057010571105721057310574105751057610577105781057910580105811058210583105841058510586105871058810589105901059110592105931059410595105961059710598105991060010601106021060310604106051060610607106081060910610106111061210613106141061510616106171061810619106201062110622106231062410625106261062710628106291063010631106321063310634106351063610637106381063910640106411064210643106441064510646106471064810649106501065110652106531065410655106561065710658106591066010661106621066310664106651066610667106681066910670106711067210673106741067510676106771067810679106801068110682106831068410685106861068710688106891069010691106921069310694106951069610697106981069910700107011070210703107041070510706107071070810709107101071110712107131071410715107161071710718107191072010721107221072310724107251072610727107281072910730107311073210733107341073510736107371073810739107401074110742107431074410745107461074710748107491075010751107521075310754107551075610757107581075910760107611076210763107641076510766107671076810769107701077110772107731077410775107761077710778107791078010781107821078310784107851078610787107881078910790107911079210793107941079510796107971079810799108001080110802108031080410805108061080710808108091081010811108121081310814108151081610817108181081910820108211082210823108241082510826108271082810829108301083110832108331083410835108361083710838108391084010841108421084310844108451084610847108481084910850108511085210853108541085510856108571085810859108601086110862108631086410865108661086710868108691087010871108721087310874108751087610877108781087910880108811088210883108841088510886108871088810889108901089110892108931089410895108961089710898108991090010901109021090310904109051090610907109081090910910109111091210913109141091510916109171091810919109201092110922109231092410925109261092710928109291093010931109321093310934109351093610937109381093910940109411094210943109441094510946109471094810949109501095110952109531095410955109561095710958109591096010961109621096310964109651096610967109681096910970109711097210973109741097510976109771097810979109801098110982109831098410985109861098710988109891099010991109921099310994109951099610997109981099911000110011100211003110041100511006110071100811009110101101111012110131101411015110161101711018110191102011021110221102311024110251102611027110281102911030110311103211033110341103511036110371103811039110401104111042110431104411045110461104711048110491105011051110521105311054110551105611057110581105911060110611106211063110641106511066110671106811069110701107111072110731107411075110761107711078110791108011081110821108311084110851108611087110881108911090110911109211093110941109511096110971109811099111001110111102111031110411105111061110711108111091111011111111121111311114111151111611117111181111911120111211112211123111241112511126111271112811129111301113111132111331113411135111361113711138111391114011141111421114311144111451114611147111481114911150111511115211153111541115511156111571115811159111601116111162111631116411165111661116711168111691117011171111721117311174111751117611177111781117911180111811118211183111841118511186111871118811189111901119111192111931119411195111961119711198111991120011201112021120311204112051120611207112081120911210112111121211213112141121511216112171121811219112201122111222112231122411225112261122711228112291123011231112321123311234112351123611237112381123911240112411124211243112441124511246112471124811249112501125111252112531125411255112561125711258112591126011261112621126311264112651126611267112681126911270112711127211273112741127511276112771127811279112801128111282112831128411285112861128711288112891129011291112921129311294112951129611297112981129911300113011130211303113041130511306113071130811309113101131111312113131131411315113161131711318113191132011321113221132311324113251132611327113281132911330113311133211333113341133511336113371133811339113401134111342113431134411345113461134711348113491135011351113521135311354113551135611357113581135911360113611136211363113641136511366113671136811369113701137111372113731137411375113761137711378113791138011381113821138311384113851138611387113881138911390113911139211393113941139511396113971139811399114001140111402114031140411405114061140711408114091141011411114121141311414114151141611417114181141911420114211142211423114241142511426114271142811429114301143111432114331143411435114361143711438114391144011441114421144311444114451144611447114481144911450114511145211453114541145511456114571145811459114601146111462114631146411465114661146711468114691147011471114721147311474114751147611477114781147911480114811148211483114841148511486114871148811489114901149111492114931149411495114961149711498114991150011501115021150311504115051150611507115081150911510115111151211513115141151511516115171151811519115201152111522115231152411525115261152711528115291153011531115321153311534115351153611537115381153911540115411154211543115441154511546115471154811549115501155111552115531155411555115561155711558115591156011561115621156311564115651156611567115681156911570115711157211573115741157511576115771157811579115801158111582115831158411585115861158711588115891159011591115921159311594115951159611597115981159911600116011160211603116041160511606116071160811609116101161111612116131161411615116161161711618116191162011621116221162311624116251162611627116281162911630116311163211633116341163511636116371163811639116401164111642116431164411645116461164711648116491165011651116521165311654116551165611657116581165911660116611166211663116641166511666116671166811669116701167111672116731167411675116761167711678116791168011681116821168311684116851168611687116881168911690116911169211693116941169511696116971169811699117001170111702117031170411705117061170711708117091171011711117121171311714117151171611717117181171911720117211172211723117241172511726117271172811729117301173111732117331173411735117361173711738117391174011741117421174311744117451174611747117481174911750117511175211753117541175511756117571175811759117601176111762117631176411765117661176711768117691177011771117721177311774117751177611777117781177911780117811178211783117841178511786117871178811789117901179111792117931179411795117961179711798117991180011801118021180311804118051180611807118081180911810118111181211813118141181511816118171181811819118201182111822118231182411825118261182711828118291183011831118321183311834118351183611837118381183911840118411184211843118441184511846118471184811849118501185111852118531185411855118561185711858118591186011861118621186311864118651186611867118681186911870118711187211873118741187511876118771187811879118801188111882118831188411885118861188711888118891189011891118921189311894118951189611897118981189911900119011190211903119041190511906119071190811909119101191111912119131191411915119161191711918119191192011921119221192311924119251192611927119281192911930119311193211933119341193511936119371193811939119401194111942119431194411945119461194711948119491195011951119521195311954119551195611957119581195911960119611196211963119641196511966119671196811969119701197111972119731197411975119761197711978119791198011981119821198311984119851198611987119881198911990119911199211993119941199511996119971199811999120001200112002120031200412005120061200712008120091201012011120121201312014120151201612017120181201912020120211202212023120241202512026120271202812029120301203112032120331203412035120361203712038120391204012041120421204312044120451204612047120481204912050120511205212053120541205512056120571205812059120601206112062120631206412065120661206712068120691207012071120721207312074120751207612077120781207912080120811208212083120841208512086120871208812089120901209112092120931209412095120961209712098120991210012101121021210312104121051210612107121081210912110121111211212113121141211512116121171211812119121201212112122121231212412125121261212712128121291213012131121321213312134121351213612137121381213912140121411214212143121441214512146121471214812149121501215112152121531215412155121561215712158121591216012161121621216312164121651216612167121681216912170121711217212173121741217512176121771217812179121801218112182121831218412185121861218712188121891219012191121921219312194121951219612197121981219912200122011220212203122041220512206122071220812209122101221112212122131221412215122161221712218122191222012221122221222312224122251222612227122281222912230122311223212233122341223512236122371223812239122401224112242122431224412245122461224712248122491225012251122521225312254122551225612257122581225912260122611226212263122641226512266122671226812269122701227112272122731227412275122761227712278122791228012281122821228312284122851228612287122881228912290122911229212293122941229512296122971229812299123001230112302123031230412305123061230712308123091231012311123121231312314123151231612317123181231912320123211232212323123241232512326123271232812329123301233112332123331233412335123361233712338123391234012341123421234312344123451234612347123481234912350123511235212353123541235512356123571235812359123601236112362123631236412365123661236712368123691237012371123721237312374123751237612377123781237912380123811238212383123841238512386123871238812389123901239112392123931239412395123961239712398123991240012401124021240312404124051240612407124081240912410124111241212413124141241512416124171241812419124201242112422124231242412425124261242712428124291243012431124321243312434124351243612437124381243912440124411244212443124441244512446124471244812449124501245112452124531245412455124561245712458124591246012461124621246312464124651246612467124681246912470124711247212473124741247512476124771247812479124801248112482124831248412485124861248712488124891249012491124921249312494124951249612497124981249912500125011250212503125041250512506125071250812509125101251112512125131251412515125161251712518125191252012521125221252312524125251252612527125281252912530125311253212533125341253512536125371253812539125401254112542125431254412545125461254712548125491255012551125521255312554125551255612557125581255912560125611256212563125641256512566125671256812569125701257112572125731257412575125761257712578125791258012581125821258312584125851258612587125881258912590125911259212593125941259512596125971259812599126001260112602126031260412605126061260712608126091261012611126121261312614126151261612617126181261912620126211262212623126241262512626126271262812629126301263112632126331263412635126361263712638126391264012641126421264312644126451264612647126481264912650126511265212653126541265512656126571265812659126601266112662126631266412665126661266712668126691267012671126721267312674126751267612677126781267912680126811268212683126841268512686126871268812689126901269112692126931269412695126961269712698126991270012701127021270312704127051270612707127081270912710127111271212713127141271512716127171271812719127201272112722127231272412725127261272712728127291273012731127321273312734127351273612737127381273912740127411274212743127441274512746127471274812749127501275112752127531275412755127561275712758127591276012761127621276312764127651276612767127681276912770127711277212773127741277512776127771277812779127801278112782127831278412785127861278712788127891279012791127921279312794127951279612797127981279912800128011280212803128041280512806128071280812809128101281112812128131281412815128161281712818128191282012821128221282312824128251282612827128281282912830128311283212833128341283512836128371283812839128401284112842128431284412845128461284712848128491285012851128521285312854128551285612857128581285912860128611286212863128641286512866128671286812869128701287112872128731287412875128761287712878128791288012881128821288312884128851288612887128881288912890128911289212893128941289512896128971289812899129001290112902129031290412905129061290712908129091291012911129121291312914129151291612917129181291912920129211292212923129241292512926129271292812929129301293112932129331293412935129361293712938129391294012941129421294312944129451294612947129481294912950129511295212953129541295512956129571295812959129601296112962129631296412965129661296712968129691297012971129721297312974129751297612977129781297912980129811298212983129841298512986129871298812989129901299112992129931299412995129961299712998129991300013001130021300313004130051300613007130081300913010130111301213013130141301513016130171301813019130201302113022130231302413025130261302713028130291303013031130321303313034130351303613037130381303913040130411304213043130441304513046130471304813049130501305113052130531305413055130561305713058130591306013061130621306313064130651306613067130681306913070130711307213073130741307513076130771307813079130801308113082130831308413085130861308713088130891309013091130921309313094130951309613097130981309913100131011310213103131041310513106131071310813109131101311113112131131311413115131161311713118131191312013121131221312313124131251312613127131281312913130131311313213133131341313513136131371313813139131401314113142131431314413145131461314713148131491315013151131521315313154131551315613157131581315913160131611316213163131641316513166131671316813169131701317113172131731317413175131761317713178131791318013181131821318313184131851318613187131881318913190131911319213193131941319513196131971319813199132001320113202132031320413205132061320713208132091321013211132121321313214132151321613217132181321913220132211322213223132241322513226132271322813229132301323113232132331323413235132361323713238132391324013241132421324313244132451324613247132481324913250132511325213253132541325513256132571325813259132601326113262132631326413265132661326713268132691327013271132721327313274132751327613277132781327913280132811328213283132841328513286132871328813289132901329113292132931329413295132961329713298132991330013301133021330313304133051330613307133081330913310133111331213313133141331513316133171331813319133201332113322133231332413325133261332713328133291333013331133321333313334133351333613337133381333913340133411334213343133441334513346133471334813349133501335113352133531335413355133561335713358133591336013361133621336313364133651336613367133681336913370133711337213373133741337513376133771337813379133801338113382133831338413385133861338713388133891339013391133921339313394133951339613397133981339913400134011340213403134041340513406134071340813409134101341113412134131341413415134161341713418134191342013421134221342313424134251342613427134281342913430134311343213433134341343513436134371343813439134401344113442134431344413445134461344713448134491345013451134521345313454134551345613457134581345913460134611346213463134641346513466134671346813469134701347113472134731347413475134761347713478134791348013481134821348313484134851348613487134881348913490134911349213493134941349513496134971349813499135001350113502135031350413505135061350713508135091351013511135121351313514135151351613517135181351913520135211352213523135241352513526135271352813529135301353113532135331353413535135361353713538135391354013541135421354313544135451354613547135481354913550135511355213553135541355513556135571355813559135601356113562135631356413565135661356713568135691357013571135721357313574135751357613577135781357913580135811358213583135841358513586135871358813589135901359113592135931359413595135961359713598135991360013601136021360313604136051360613607136081360913610136111361213613136141361513616136171361813619136201362113622136231362413625136261362713628136291363013631136321363313634136351363613637136381363913640136411364213643136441364513646136471364813649136501365113652136531365413655136561365713658136591366013661136621366313664136651366613667136681366913670136711367213673136741367513676136771367813679136801368113682136831368413685136861368713688136891369013691136921369313694136951369613697136981369913700137011370213703137041370513706137071370813709137101371113712137131371413715137161371713718137191372013721137221372313724137251372613727137281372913730137311373213733137341373513736137371373813739137401374113742137431374413745137461374713748137491375013751137521375313754137551375613757137581375913760137611376213763137641376513766137671376813769137701377113772137731377413775137761377713778137791378013781137821378313784137851378613787137881378913790137911379213793137941379513796137971379813799138001380113802138031380413805138061380713808138091381013811138121381313814138151381613817138181381913820138211382213823138241382513826138271382813829138301383113832138331383413835138361383713838138391384013841138421384313844138451384613847138481384913850138511385213853138541385513856138571385813859138601386113862138631386413865138661386713868138691387013871138721387313874138751387613877138781387913880138811388213883138841388513886138871388813889138901389113892138931389413895138961389713898138991390013901139021390313904139051390613907139081390913910139111391213913139141391513916139171391813919139201392113922139231392413925139261392713928139291393013931139321393313934139351393613937139381393913940139411394213943139441394513946139471394813949139501395113952139531395413955139561395713958139591396013961139621396313964139651396613967139681396913970139711397213973139741397513976139771397813979139801398113982139831398413985139861398713988139891399013991139921399313994139951399613997139981399914000140011400214003140041400514006140071400814009140101401114012140131401414015140161401714018140191402014021140221402314024140251402614027140281402914030140311403214033140341403514036140371403814039140401404114042140431404414045140461404714048140491405014051140521405314054140551405614057140581405914060140611406214063140641406514066140671406814069140701407114072140731407414075140761407714078140791408014081140821408314084140851408614087140881408914090140911409214093140941409514096140971409814099141001410114102141031410414105141061410714108141091411014111141121411314114141151411614117141181411914120141211412214123141241412514126141271412814129141301413114132141331413414135141361413714138141391414014141141421414314144141451414614147141481414914150141511415214153141541415514156141571415814159141601416114162141631416414165141661416714168141691417014171141721417314174141751417614177141781417914180141811418214183141841418514186141871418814189141901419114192141931419414195141961419714198141991420014201142021420314204142051420614207142081420914210142111421214213142141421514216142171421814219142201422114222142231422414225142261422714228142291423014231142321423314234142351423614237142381423914240142411424214243142441424514246142471424814249142501425114252142531425414255142561425714258142591426014261142621426314264142651426614267142681426914270142711427214273142741427514276142771427814279142801428114282142831428414285142861428714288142891429014291142921429314294142951429614297142981429914300143011430214303143041430514306143071430814309143101431114312143131431414315143161431714318143191432014321143221432314324143251432614327143281432914330143311433214333143341433514336143371433814339143401434114342143431434414345143461434714348143491435014351143521435314354143551435614357143581435914360143611436214363143641436514366143671436814369143701437114372143731437414375143761437714378143791438014381143821438314384143851438614387143881438914390143911439214393143941439514396143971439814399144001440114402144031440414405144061440714408144091441014411144121441314414144151441614417144181441914420144211442214423144241442514426144271442814429144301443114432144331443414435144361443714438144391444014441144421444314444144451444614447144481444914450144511445214453144541445514456144571445814459144601446114462144631446414465144661446714468144691447014471144721447314474144751447614477144781447914480144811448214483144841448514486144871448814489144901449114492144931449414495144961449714498144991450014501145021450314504145051450614507145081450914510145111451214513145141451514516145171451814519145201452114522145231452414525145261452714528145291453014531145321453314534145351453614537145381453914540145411454214543145441454514546145471454814549145501455114552145531455414555145561455714558145591456014561145621456314564145651456614567145681456914570145711457214573145741457514576145771457814579145801458114582145831458414585145861458714588145891459014591145921459314594145951459614597145981459914600146011460214603146041460514606146071460814609146101461114612146131461414615146161461714618146191462014621146221462314624146251462614627146281462914630146311463214633146341463514636146371463814639146401464114642146431464414645146461464714648146491465014651146521465314654146551465614657146581465914660146611466214663146641466514666146671466814669146701467114672146731467414675146761467714678146791468014681146821468314684146851468614687146881468914690146911469214693146941469514696146971469814699147001470114702147031470414705147061470714708147091471014711147121471314714147151471614717147181471914720147211472214723147241472514726147271472814729147301473114732147331473414735147361473714738147391474014741147421474314744147451474614747147481474914750147511475214753147541475514756147571475814759147601476114762147631476414765147661476714768147691477014771147721477314774147751477614777147781477914780147811478214783147841478514786147871478814789147901479114792147931479414795147961479714798147991480014801148021480314804148051480614807148081480914810148111481214813148141481514816148171481814819148201482114822148231482414825148261482714828148291483014831148321483314834148351483614837148381483914840148411484214843148441484514846148471484814849148501485114852148531485414855148561485714858148591486014861148621486314864148651486614867148681486914870148711487214873148741487514876148771487814879148801488114882148831488414885148861488714888148891489014891148921489314894148951489614897148981489914900149011490214903149041490514906149071490814909149101491114912149131491414915149161491714918149191492014921149221492314924149251492614927149281492914930149311493214933149341493514936149371493814939149401494114942149431494414945149461494714948149491495014951149521495314954149551495614957149581495914960149611496214963149641496514966149671496814969149701497114972149731497414975149761497714978149791498014981149821498314984149851498614987149881498914990149911499214993149941499514996149971499814999150001500115002150031500415005150061500715008150091501015011150121501315014150151501615017150181501915020150211502215023150241502515026150271502815029150301503115032150331503415035150361503715038150391504015041150421504315044150451504615047150481504915050150511505215053150541505515056150571505815059150601506115062150631506415065150661506715068150691507015071150721507315074150751507615077150781507915080150811508215083150841508515086150871508815089150901509115092150931509415095150961509715098150991510015101151021510315104151051510615107151081510915110151111511215113151141511515116151171511815119151201512115122151231512415125151261512715128151291513015131151321513315134151351513615137151381513915140151411514215143151441514515146151471514815149151501515115152151531515415155151561515715158151591516015161151621516315164151651516615167151681516915170151711517215173151741517515176151771517815179151801518115182151831518415185151861518715188151891519015191151921519315194151951519615197151981519915200152011520215203152041520515206152071520815209152101521115212152131521415215152161521715218152191522015221152221522315224152251522615227152281522915230152311523215233152341523515236152371523815239152401524115242152431524415245152461524715248152491525015251152521525315254152551525615257152581525915260152611526215263152641526515266152671526815269152701527115272152731527415275152761527715278152791528015281152821528315284152851528615287152881528915290152911529215293152941529515296152971529815299153001530115302153031530415305153061530715308153091531015311153121531315314153151531615317153181531915320153211532215323153241532515326153271532815329153301533115332153331533415335153361533715338153391534015341153421534315344153451534615347153481534915350153511535215353153541535515356153571535815359153601536115362153631536415365153661536715368153691537015371153721537315374153751537615377153781537915380153811538215383153841538515386153871538815389153901539115392153931539415395153961539715398153991540015401154021540315404154051540615407154081540915410154111541215413154141541515416154171541815419154201542115422154231542415425154261542715428154291543015431154321543315434154351543615437154381543915440154411544215443154441544515446154471544815449154501545115452154531545415455154561545715458154591546015461154621546315464154651546615467154681546915470154711547215473154741547515476154771547815479154801548115482154831548415485154861548715488154891549015491154921549315494154951549615497154981549915500155011550215503155041550515506155071550815509155101551115512155131551415515155161551715518155191552015521155221552315524155251552615527155281552915530155311553215533155341553515536155371553815539155401554115542155431554415545155461554715548155491555015551155521555315554155551555615557155581555915560155611556215563155641556515566155671556815569155701557115572155731557415575155761557715578155791558015581155821558315584155851558615587155881558915590155911559215593155941559515596155971559815599156001560115602156031560415605156061560715608156091561015611156121561315614156151561615617156181561915620156211562215623156241562515626156271562815629156301563115632156331563415635156361563715638156391564015641156421564315644156451564615647156481564915650156511565215653156541565515656156571565815659156601566115662156631566415665156661566715668156691567015671156721567315674156751567615677156781567915680156811568215683156841568515686156871568815689156901569115692156931569415695156961569715698156991570015701157021570315704157051570615707157081570915710157111571215713157141571515716157171571815719157201572115722157231572415725157261572715728157291573015731157321573315734157351573615737157381573915740157411574215743157441574515746157471574815749157501575115752157531575415755157561575715758157591576015761157621576315764157651576615767157681576915770157711577215773157741577515776157771577815779157801578115782157831578415785157861578715788157891579015791157921579315794157951579615797157981579915800158011580215803158041580515806158071580815809158101581115812158131581415815158161581715818158191582015821158221582315824158251582615827158281582915830158311583215833158341583515836158371583815839158401584115842158431584415845158461584715848158491585015851158521585315854158551585615857158581585915860158611586215863158641586515866158671586815869158701587115872158731587415875158761587715878158791588015881158821588315884158851588615887158881588915890158911589215893158941589515896158971589815899159001590115902159031590415905159061590715908159091591015911159121591315914159151591615917159181591915920159211592215923159241592515926159271592815929159301593115932159331593415935159361593715938159391594015941159421594315944159451594615947159481594915950159511595215953159541595515956159571595815959159601596115962159631596415965159661596715968159691597015971159721597315974159751597615977159781597915980159811598215983159841598515986159871598815989159901599115992159931599415995159961599715998159991600016001160021600316004160051600616007160081600916010160111601216013160141601516016160171601816019160201602116022160231602416025160261602716028160291603016031160321603316034160351603616037160381603916040160411604216043160441604516046160471604816049160501605116052160531605416055160561605716058160591606016061160621606316064160651606616067160681606916070160711607216073160741607516076160771607816079160801608116082160831608416085160861608716088160891609016091160921609316094160951609616097160981609916100161011610216103161041610516106161071610816109161101611116112161131611416115161161611716118161191612016121161221612316124161251612616127161281612916130161311613216133161341613516136161371613816139161401614116142161431614416145161461614716148161491615016151161521615316154161551615616157161581615916160161611616216163161641616516166161671616816169161701617116172161731617416175161761617716178161791618016181161821618316184161851618616187161881618916190161911619216193161941619516196161971619816199162001620116202162031620416205162061620716208162091621016211162121621316214162151621616217162181621916220162211622216223162241622516226162271622816229162301623116232162331623416235162361623716238162391624016241162421624316244162451624616247162481624916250162511625216253162541625516256162571625816259162601626116262162631626416265162661626716268162691627016271162721627316274162751627616277162781627916280162811628216283162841628516286162871628816289162901629116292162931629416295162961629716298162991630016301163021630316304163051630616307163081630916310163111631216313163141631516316163171631816319163201632116322163231632416325163261632716328163291633016331163321633316334163351633616337163381633916340163411634216343163441634516346163471634816349163501635116352163531635416355163561635716358163591636016361163621636316364163651636616367163681636916370163711637216373163741637516376163771637816379163801638116382163831638416385163861638716388163891639016391163921639316394163951639616397163981639916400164011640216403164041640516406164071640816409164101641116412164131641416415164161641716418164191642016421164221642316424164251642616427164281642916430164311643216433164341643516436164371643816439164401644116442164431644416445164461644716448164491645016451164521645316454164551645616457164581645916460164611646216463164641646516466164671646816469164701647116472164731647416475164761647716478164791648016481164821648316484164851648616487164881648916490164911649216493164941649516496164971649816499165001650116502165031650416505165061650716508165091651016511165121651316514165151651616517165181651916520165211652216523165241652516526165271652816529165301653116532165331653416535165361653716538165391654016541165421654316544165451654616547165481654916550165511655216553165541655516556165571655816559165601656116562165631656416565165661656716568165691657016571165721657316574165751657616577165781657916580165811658216583165841658516586165871658816589165901659116592165931659416595165961659716598165991660016601166021660316604166051660616607166081660916610166111661216613166141661516616166171661816619166201662116622166231662416625166261662716628166291663016631166321663316634166351663616637166381663916640166411664216643166441664516646166471664816649166501665116652166531665416655166561665716658166591666016661166621666316664166651666616667166681666916670166711667216673166741667516676166771667816679166801668116682166831668416685166861668716688166891669016691166921669316694166951669616697166981669916700167011670216703167041670516706167071670816709167101671116712167131671416715167161671716718167191672016721167221672316724167251672616727167281672916730167311673216733167341673516736167371673816739167401674116742167431674416745167461674716748167491675016751167521675316754167551675616757167581675916760167611676216763167641676516766167671676816769167701677116772167731677416775167761677716778167791678016781167821678316784167851678616787167881678916790167911679216793167941679516796167971679816799168001680116802168031680416805168061680716808168091681016811168121681316814168151681616817168181681916820168211682216823168241682516826168271682816829168301683116832168331683416835168361683716838168391684016841168421684316844168451684616847168481684916850168511685216853168541685516856168571685816859168601686116862168631686416865168661686716868168691687016871168721687316874168751687616877168781687916880168811688216883168841688516886168871688816889168901689116892168931689416895168961689716898168991690016901169021690316904169051690616907169081690916910169111691216913169141691516916169171691816919169201692116922169231692416925169261692716928169291693016931169321693316934169351693616937169381693916940169411694216943169441694516946169471694816949169501695116952169531695416955169561695716958169591696016961169621696316964169651696616967169681696916970169711697216973169741697516976169771697816979169801698116982169831698416985169861698716988169891699016991169921699316994169951699616997169981699917000170011700217003170041700517006170071700817009170101701117012170131701417015170161701717018170191702017021170221702317024170251702617027170281702917030170311703217033170341703517036170371703817039170401704117042170431704417045170461704717048170491705017051170521705317054170551705617057170581705917060170611706217063170641706517066170671706817069170701707117072170731707417075170761707717078170791708017081170821708317084170851708617087170881708917090170911709217093170941709517096170971709817099171001710117102171031710417105171061710717108171091711017111171121711317114171151711617117171181711917120171211712217123171241712517126171271712817129171301713117132171331713417135171361713717138171391714017141171421714317144171451714617147171481714917150171511715217153171541715517156171571715817159171601716117162171631716417165171661716717168171691717017171171721717317174171751717617177171781717917180171811718217183171841718517186171871718817189171901719117192171931719417195171961719717198171991720017201172021720317204172051720617207172081720917210172111721217213172141721517216172171721817219172201722117222172231722417225172261722717228172291723017231172321723317234172351723617237172381723917240172411724217243172441724517246172471724817249172501725117252172531725417255172561725717258172591726017261172621726317264172651726617267172681726917270172711727217273172741727517276172771727817279172801728117282172831728417285172861728717288172891729017291172921729317294172951729617297172981729917300173011730217303173041730517306173071730817309173101731117312173131731417315173161731717318173191732017321173221732317324173251732617327173281732917330173311733217333173341733517336173371733817339173401734117342173431734417345173461734717348173491735017351173521735317354173551735617357173581735917360173611736217363173641736517366173671736817369173701737117372173731737417375173761737717378173791738017381173821738317384173851738617387173881738917390173911739217393173941739517396173971739817399174001740117402174031740417405174061740717408174091741017411174121741317414174151741617417174181741917420174211742217423174241742517426174271742817429174301743117432174331743417435174361743717438174391744017441174421744317444174451744617447174481744917450174511745217453174541745517456174571745817459174601746117462174631746417465174661746717468174691747017471174721747317474174751747617477174781747917480174811748217483174841748517486174871748817489174901749117492174931749417495174961749717498174991750017501175021750317504175051750617507175081750917510175111751217513175141751517516175171751817519175201752117522175231752417525175261752717528175291753017531175321753317534175351753617537175381753917540175411754217543175441754517546175471754817549175501755117552175531755417555175561755717558175591756017561175621756317564175651756617567175681756917570175711757217573175741757517576175771757817579175801758117582175831758417585175861758717588175891759017591175921759317594175951759617597175981759917600176011760217603176041760517606176071760817609176101761117612176131761417615176161761717618176191762017621176221762317624176251762617627176281762917630176311763217633176341763517636176371763817639176401764117642176431764417645176461764717648176491765017651176521765317654176551765617657176581765917660176611766217663176641766517666176671766817669176701767117672176731767417675176761767717678176791768017681176821768317684176851768617687176881768917690176911769217693176941769517696176971769817699177001770117702177031770417705177061770717708177091771017711177121771317714177151771617717177181771917720177211772217723177241772517726177271772817729177301773117732177331773417735177361773717738177391774017741177421774317744177451774617747177481774917750177511775217753177541775517756177571775817759177601776117762177631776417765177661776717768177691777017771177721777317774177751777617777177781777917780177811778217783177841778517786177871778817789177901779117792177931779417795177961779717798177991780017801178021780317804178051780617807178081780917810178111781217813178141781517816178171781817819178201782117822178231782417825178261782717828178291783017831178321783317834178351783617837178381783917840178411784217843178441784517846178471784817849178501785117852178531785417855178561785717858178591786017861178621786317864178651786617867178681786917870178711787217873178741787517876178771787817879178801788117882178831788417885178861788717888178891789017891178921789317894178951789617897178981789917900179011790217903179041790517906179071790817909179101791117912179131791417915179161791717918179191792017921179221792317924179251792617927179281792917930179311793217933179341793517936179371793817939179401794117942179431794417945179461794717948179491795017951179521795317954179551795617957179581795917960179611796217963179641796517966179671796817969179701797117972179731797417975179761797717978179791798017981179821798317984179851798617987179881798917990179911799217993179941799517996179971799817999180001800118002180031800418005180061800718008180091801018011180121801318014180151801618017180181801918020180211802218023180241802518026180271802818029180301803118032180331803418035180361803718038180391804018041180421804318044180451804618047180481804918050180511805218053180541805518056180571805818059180601806118062180631806418065180661806718068180691807018071180721807318074180751807618077180781807918080180811808218083180841808518086180871808818089180901809118092180931809418095180961809718098180991810018101181021810318104181051810618107181081810918110181111811218113181141811518116181171811818119181201812118122181231812418125181261812718128181291813018131181321813318134181351813618137181381813918140181411814218143181441814518146181471814818149181501815118152181531815418155181561815718158181591816018161181621816318164181651816618167181681816918170181711817218173181741817518176181771817818179181801818118182181831818418185181861818718188181891819018191181921819318194181951819618197181981819918200182011820218203182041820518206182071820818209182101821118212182131821418215182161821718218182191822018221182221822318224182251822618227182281822918230182311823218233182341823518236182371823818239182401824118242182431824418245182461824718248182491825018251182521825318254182551825618257182581825918260182611826218263182641826518266182671826818269182701827118272182731827418275182761827718278182791828018281182821828318284182851828618287182881828918290182911829218293182941829518296182971829818299183001830118302183031830418305183061830718308183091831018311183121831318314183151831618317183181831918320183211832218323183241832518326183271832818329183301833118332183331833418335183361833718338183391834018341183421834318344183451834618347183481834918350183511835218353183541835518356183571835818359183601836118362183631836418365183661836718368183691837018371183721837318374183751837618377183781837918380183811838218383183841838518386183871838818389183901839118392183931839418395183961839718398183991840018401184021840318404184051840618407184081840918410184111841218413184141841518416184171841818419184201842118422184231842418425184261842718428184291843018431184321843318434184351843618437184381843918440184411844218443184441844518446184471844818449184501845118452184531845418455184561845718458184591846018461184621846318464184651846618467184681846918470184711847218473184741847518476184771847818479184801848118482184831848418485184861848718488184891849018491184921849318494184951849618497184981849918500185011850218503185041850518506185071850818509185101851118512185131851418515185161851718518185191852018521185221852318524185251852618527185281852918530185311853218533185341853518536185371853818539185401854118542185431854418545185461854718548185491855018551185521855318554185551855618557185581855918560185611856218563185641856518566185671856818569185701857118572185731857418575185761857718578185791858018581185821858318584185851858618587185881858918590185911859218593185941859518596185971859818599186001860118602186031860418605186061860718608186091861018611186121861318614186151861618617186181861918620186211862218623186241862518626186271862818629186301863118632186331863418635186361863718638186391864018641186421864318644186451864618647186481864918650186511865218653186541865518656186571865818659186601866118662186631866418665186661866718668186691867018671186721867318674186751867618677186781867918680186811868218683186841868518686186871868818689186901869118692186931869418695186961869718698186991870018701187021870318704187051870618707187081870918710187111871218713187141871518716187171871818719187201872118722187231872418725187261872718728187291873018731187321873318734187351873618737187381873918740187411874218743187441874518746187471874818749187501875118752187531875418755187561875718758187591876018761187621876318764187651876618767187681876918770187711877218773187741877518776187771877818779187801878118782187831878418785187861878718788187891879018791187921879318794187951879618797187981879918800188011880218803188041880518806188071880818809188101881118812188131881418815188161881718818188191882018821188221882318824188251882618827188281882918830188311883218833188341883518836188371883818839188401884118842188431884418845188461884718848188491885018851188521885318854188551885618857188581885918860188611886218863188641886518866188671886818869188701887118872188731887418875188761887718878188791888018881188821888318884188851888618887188881888918890188911889218893188941889518896188971889818899189001890118902189031890418905189061890718908189091891018911189121891318914189151891618917189181891918920189211892218923189241892518926189271892818929189301893118932189331893418935189361893718938189391894018941189421894318944189451894618947189481894918950189511895218953189541895518956189571895818959189601896118962189631896418965189661896718968189691897018971189721897318974189751897618977189781897918980189811898218983189841898518986189871898818989189901899118992189931899418995189961899718998189991900019001190021900319004190051900619007190081900919010190111901219013190141901519016190171901819019190201902119022190231902419025190261902719028190291903019031190321903319034190351903619037190381903919040190411904219043190441904519046190471904819049190501905119052190531905419055190561905719058190591906019061190621906319064190651906619067190681906919070190711907219073190741907519076190771907819079190801908119082190831908419085190861908719088190891909019091190921909319094190951909619097190981909919100191011910219103191041910519106191071910819109191101911119112191131911419115191161911719118191191912019121191221912319124191251912619127191281912919130191311913219133191341913519136191371913819139191401914119142191431914419145191461914719148191491915019151191521915319154191551915619157191581915919160191611916219163191641916519166191671916819169191701917119172191731917419175191761917719178191791918019181191821918319184191851918619187191881918919190191911919219193191941919519196191971919819199192001920119202192031920419205192061920719208192091921019211192121921319214192151921619217192181921919220192211922219223192241922519226192271922819229192301923119232192331923419235192361923719238192391924019241192421924319244192451924619247192481924919250192511925219253192541925519256192571925819259192601926119262192631926419265192661926719268192691927019271192721927319274192751927619277192781927919280192811928219283192841928519286192871928819289192901929119292192931929419295192961929719298192991930019301193021930319304193051930619307193081930919310193111931219313193141931519316193171931819319193201932119322193231932419325193261932719328193291933019331193321933319334193351933619337193381933919340193411934219343193441934519346193471934819349193501935119352193531935419355193561935719358193591936019361193621936319364193651936619367193681936919370193711937219373193741937519376193771937819379193801938119382193831938419385193861938719388193891939019391193921939319394193951939619397193981939919400194011940219403194041940519406194071940819409194101941119412194131941419415194161941719418194191942019421194221942319424194251942619427194281942919430194311943219433194341943519436194371943819439194401944119442194431944419445194461944719448194491945019451194521945319454194551945619457194581945919460194611946219463194641946519466194671946819469194701947119472194731947419475194761947719478194791948019481194821948319484194851948619487194881948919490194911949219493194941949519496194971949819499195001950119502195031950419505195061950719508195091951019511195121951319514195151951619517195181951919520195211952219523195241952519526195271952819529195301953119532195331953419535195361953719538195391954019541195421954319544195451954619547195481954919550195511955219553195541955519556195571955819559195601956119562195631956419565195661956719568195691957019571195721957319574195751957619577195781957919580195811958219583195841958519586195871958819589195901959119592195931959419595195961959719598195991960019601196021960319604196051960619607196081960919610196111961219613196141961519616196171961819619196201962119622196231962419625196261962719628196291963019631196321963319634196351963619637196381963919640196411964219643196441964519646196471964819649196501965119652196531965419655196561965719658196591966019661196621966319664196651966619667196681966919670196711967219673196741967519676196771967819679196801968119682196831968419685196861968719688196891969019691196921969319694196951969619697196981969919700197011970219703197041970519706197071970819709197101971119712197131971419715197161971719718197191972019721197221972319724197251972619727197281972919730197311973219733197341973519736197371973819739197401974119742197431974419745197461974719748197491975019751197521975319754197551975619757197581975919760197611976219763197641976519766197671976819769197701977119772197731977419775197761977719778197791978019781197821978319784197851978619787197881978919790197911979219793197941979519796197971979819799198001980119802198031980419805198061980719808198091981019811198121981319814198151981619817198181981919820198211982219823198241982519826198271982819829198301983119832198331983419835198361983719838198391984019841198421984319844198451984619847198481984919850198511985219853198541985519856198571985819859198601986119862198631986419865198661986719868198691987019871198721987319874198751987619877198781987919880198811988219883198841988519886198871988819889198901989119892198931989419895198961989719898198991990019901199021990319904199051990619907199081990919910199111991219913199141991519916199171991819919199201992119922199231992419925199261992719928199291993019931199321993319934199351993619937199381993919940199411994219943199441994519946199471994819949199501995119952199531995419955199561995719958199591996019961199621996319964199651996619967199681996919970199711997219973199741997519976199771997819979199801998119982199831998419985199861998719988199891999019991199921999319994199951999619997199981999920000200012000220003200042000520006200072000820009200102001120012200132001420015200162001720018200192002020021200222002320024200252002620027200282002920030200312003220033200342003520036200372003820039200402004120042200432004420045200462004720048200492005020051200522005320054200552005620057200582005920060200612006220063200642006520066200672006820069200702007120072200732007420075200762007720078200792008020081200822008320084200852008620087200882008920090200912009220093200942009520096200972009820099201002010120102201032010420105201062010720108201092011020111201122011320114201152011620117201182011920120201212012220123201242012520126201272012820129201302013120132201332013420135201362013720138201392014020141201422014320144201452014620147201482014920150201512015220153201542015520156201572015820159201602016120162201632016420165201662016720168201692017020171201722017320174201752017620177201782017920180201812018220183201842018520186201872018820189201902019120192201932019420195201962019720198201992020020201202022020320204202052020620207202082020920210202112021220213202142021520216202172021820219202202022120222202232022420225202262022720228202292023020231202322023320234202352023620237202382023920240202412024220243202442024520246202472024820249202502025120252202532025420255202562025720258202592026020261202622026320264202652026620267202682026920270202712027220273202742027520276202772027820279202802028120282202832028420285202862028720288202892029020291202922029320294202952029620297202982029920300203012030220303203042030520306203072030820309203102031120312203132031420315203162031720318203192032020321203222032320324203252032620327203282032920330203312033220333203342033520336203372033820339203402034120342203432034420345203462034720348203492035020351203522035320354203552035620357203582035920360203612036220363203642036520366203672036820369203702037120372203732037420375203762037720378203792038020381203822038320384203852038620387203882038920390203912039220393203942039520396203972039820399204002040120402204032040420405204062040720408204092041020411204122041320414204152041620417204182041920420204212042220423204242042520426204272042820429204302043120432204332043420435204362043720438204392044020441204422044320444204452044620447204482044920450204512045220453204542045520456204572045820459204602046120462204632046420465204662046720468204692047020471204722047320474204752047620477204782047920480204812048220483204842048520486204872048820489204902049120492204932049420495204962049720498204992050020501205022050320504205052050620507205082050920510205112051220513205142051520516205172051820519205202052120522205232052420525205262052720528205292053020531205322053320534205352053620537205382053920540205412054220543205442054520546205472054820549205502055120552205532055420555205562055720558205592056020561205622056320564205652056620567205682056920570205712057220573205742057520576205772057820579205802058120582205832058420585205862058720588205892059020591205922059320594205952059620597205982059920600206012060220603206042060520606206072060820609206102061120612206132061420615206162061720618206192062020621206222062320624206252062620627206282062920630206312063220633206342063520636206372063820639206402064120642206432064420645206462064720648206492065020651206522065320654206552065620657206582065920660206612066220663206642066520666206672066820669206702067120672206732067420675206762067720678206792068020681206822068320684206852068620687206882068920690206912069220693206942069520696206972069820699207002070120702207032070420705207062070720708207092071020711207122071320714207152071620717207182071920720207212072220723207242072520726207272072820729207302073120732207332073420735207362073720738207392074020741207422074320744207452074620747207482074920750207512075220753207542075520756207572075820759207602076120762207632076420765207662076720768207692077020771207722077320774207752077620777207782077920780207812078220783207842078520786207872078820789207902079120792207932079420795207962079720798207992080020801208022080320804208052080620807208082080920810208112081220813208142081520816208172081820819208202082120822208232082420825208262082720828208292083020831208322083320834208352083620837208382083920840208412084220843208442084520846208472084820849208502085120852208532085420855208562085720858208592086020861208622086320864208652086620867208682086920870208712087220873208742087520876208772087820879208802088120882208832088420885208862088720888208892089020891208922089320894208952089620897208982089920900209012090220903209042090520906209072090820909209102091120912209132091420915209162091720918209192092020921209222092320924209252092620927209282092920930209312093220933209342093520936209372093820939209402094120942209432094420945209462094720948209492095020951209522095320954209552095620957209582095920960209612096220963209642096520966209672096820969209702097120972209732097420975209762097720978209792098020981209822098320984209852098620987209882098920990209912099220993209942099520996209972099820999210002100121002210032100421005210062100721008210092101021011210122101321014210152101621017210182101921020210212102221023210242102521026210272102821029210302103121032210332103421035210362103721038210392104021041210422104321044210452104621047210482104921050210512105221053210542105521056210572105821059210602106121062210632106421065210662106721068210692107021071210722107321074210752107621077210782107921080210812108221083210842108521086210872108821089210902109121092210932109421095210962109721098210992110021101211022110321104211052110621107211082110921110211112111221113211142111521116211172111821119211202112121122211232112421125211262112721128211292113021131211322113321134211352113621137211382113921140211412114221143211442114521146211472114821149211502115121152211532115421155211562115721158211592116021161211622116321164211652116621167211682116921170211712117221173211742117521176211772117821179211802118121182211832118421185211862118721188211892119021191211922119321194211952119621197211982119921200212012120221203212042120521206212072120821209212102121121212212132121421215212162121721218212192122021221212222122321224212252122621227212282122921230212312123221233212342123521236212372123821239212402124121242212432124421245212462124721248212492125021251212522125321254212552125621257212582125921260212612126221263212642126521266212672126821269212702127121272212732127421275212762127721278212792128021281212822128321284212852128621287212882128921290212912129221293212942129521296212972129821299213002130121302213032130421305213062130721308213092131021311213122131321314213152131621317213182131921320213212132221323213242132521326213272132821329213302133121332213332133421335213362133721338213392134021341213422134321344213452134621347213482134921350213512135221353213542135521356213572135821359213602136121362213632136421365213662136721368213692137021371213722137321374213752137621377213782137921380213812138221383213842138521386213872138821389213902139121392213932139421395213962139721398213992140021401214022140321404214052140621407214082140921410214112141221413214142141521416214172141821419214202142121422214232142421425214262142721428214292143021431214322143321434214352143621437214382143921440214412144221443214442144521446214472144821449214502145121452214532145421455214562145721458214592146021461214622146321464214652146621467214682146921470214712147221473214742147521476214772147821479214802148121482214832148421485214862148721488214892149021491214922149321494214952149621497214982149921500215012150221503215042150521506215072150821509215102151121512215132151421515215162151721518215192152021521215222152321524215252152621527215282152921530215312153221533215342153521536215372153821539215402154121542215432154421545215462154721548215492155021551215522155321554215552155621557215582155921560215612156221563215642156521566215672156821569215702157121572215732157421575215762157721578215792158021581215822158321584215852158621587215882158921590215912159221593215942159521596215972159821599216002160121602216032160421605216062160721608216092161021611216122161321614216152161621617216182161921620216212162221623216242162521626216272162821629216302163121632216332163421635216362163721638216392164021641216422164321644216452164621647216482164921650216512165221653216542165521656216572165821659216602166121662216632166421665216662166721668216692167021671216722167321674216752167621677216782167921680216812168221683216842168521686216872168821689216902169121692216932169421695216962169721698216992170021701217022170321704217052170621707217082170921710217112171221713217142171521716217172171821719217202172121722217232172421725217262172721728217292173021731217322173321734217352173621737217382173921740217412174221743217442174521746217472174821749217502175121752217532175421755217562175721758217592176021761217622176321764217652176621767217682176921770217712177221773217742177521776217772177821779217802178121782217832178421785217862178721788217892179021791217922179321794217952179621797217982179921800218012180221803218042180521806218072180821809218102181121812218132181421815218162181721818218192182021821218222182321824218252182621827218282182921830218312183221833218342183521836218372183821839218402184121842218432184421845218462184721848218492185021851218522185321854218552185621857218582185921860218612186221863218642186521866218672186821869218702187121872218732187421875218762187721878218792188021881218822188321884218852188621887218882188921890218912189221893218942189521896218972189821899219002190121902219032190421905219062190721908219092191021911219122191321914219152191621917219182191921920219212192221923219242192521926219272192821929219302193121932219332193421935219362193721938219392194021941219422194321944219452194621947219482194921950219512195221953219542195521956219572195821959219602196121962219632196421965219662196721968219692197021971219722197321974219752197621977219782197921980219812198221983219842198521986219872198821989219902199121992219932199421995219962199721998219992200022001220022200322004220052200622007220082200922010220112201222013220142201522016220172201822019220202202122022220232202422025220262202722028220292203022031220322203322034220352203622037220382203922040220412204222043220442204522046220472204822049220502205122052220532205422055220562205722058220592206022061220622206322064220652206622067220682206922070220712207222073220742207522076220772207822079220802208122082220832208422085220862208722088220892209022091220922209322094220952209622097220982209922100221012210222103221042210522106221072210822109221102211122112221132211422115221162211722118221192212022121221222212322124221252212622127221282212922130221312213222133221342213522136221372213822139221402214122142221432214422145221462214722148221492215022151221522215322154221552215622157221582215922160221612216222163221642216522166221672216822169221702217122172221732217422175221762217722178221792218022181221822218322184221852218622187221882218922190221912219222193221942219522196221972219822199222002220122202222032220422205222062220722208222092221022211222122221322214222152221622217222182221922220222212222222223222242222522226222272222822229222302223122232222332223422235222362223722238222392224022241222422224322244222452224622247222482224922250222512225222253222542225522256222572225822259222602226122262222632226422265222662226722268222692227022271222722227322274222752227622277222782227922280222812228222283222842228522286222872228822289222902229122292222932229422295222962229722298222992230022301223022230322304223052230622307223082230922310223112231222313223142231522316223172231822319223202232122322223232232422325223262232722328223292233022331223322233322334223352233622337223382233922340223412234222343223442234522346223472234822349223502235122352223532235422355223562235722358223592236022361223622236322364223652236622367223682236922370223712237222373223742237522376223772237822379223802238122382223832238422385223862238722388223892239022391223922239322394223952239622397223982239922400224012240222403224042240522406224072240822409224102241122412224132241422415224162241722418224192242022421224222242322424224252242622427224282242922430224312243222433224342243522436224372243822439224402244122442224432244422445224462244722448224492245022451224522245322454224552245622457224582245922460224612246222463224642246522466224672246822469224702247122472224732247422475224762247722478224792248022481224822248322484224852248622487224882248922490224912249222493224942249522496224972249822499225002250122502225032250422505225062250722508225092251022511225122251322514225152251622517225182251922520225212252222523225242252522526225272252822529225302253122532225332253422535225362253722538225392254022541225422254322544225452254622547225482254922550225512255222553225542255522556225572255822559225602256122562225632256422565225662256722568225692257022571225722257322574225752257622577225782257922580225812258222583225842258522586225872258822589225902259122592225932259422595225962259722598225992260022601226022260322604226052260622607226082260922610226112261222613226142261522616226172261822619226202262122622226232262422625226262262722628226292263022631226322263322634226352263622637226382263922640226412264222643226442264522646226472264822649226502265122652226532265422655226562265722658226592266022661226622266322664226652266622667226682266922670226712267222673226742267522676226772267822679226802268122682226832268422685226862268722688226892269022691226922269322694226952269622697226982269922700227012270222703227042270522706227072270822709227102271122712227132271422715227162271722718227192272022721227222272322724227252272622727227282272922730227312273222733227342273522736227372273822739227402274122742227432274422745227462274722748227492275022751227522275322754227552275622757227582275922760227612276222763227642276522766227672276822769227702277122772227732277422775227762277722778227792278022781227822278322784227852278622787227882278922790227912279222793227942279522796227972279822799228002280122802228032280422805228062280722808228092281022811228122281322814228152281622817228182281922820228212282222823228242282522826228272282822829228302283122832228332283422835228362283722838228392284022841228422284322844228452284622847228482284922850228512285222853228542285522856228572285822859228602286122862228632286422865228662286722868228692287022871228722287322874228752287622877228782287922880228812288222883228842288522886228872288822889228902289122892228932289422895228962289722898228992290022901229022290322904229052290622907229082290922910229112291222913229142291522916229172291822919229202292122922229232292422925229262292722928229292293022931229322293322934229352293622937229382293922940229412294222943229442294522946229472294822949229502295122952229532295422955229562295722958229592296022961229622296322964229652296622967229682296922970229712297222973229742297522976229772297822979229802298122982229832298422985229862298722988229892299022991229922299322994229952299622997229982299923000230012300223003230042300523006230072300823009230102301123012230132301423015230162301723018230192302023021230222302323024230252302623027230282302923030230312303223033230342303523036230372303823039230402304123042230432304423045230462304723048230492305023051230522305323054230552305623057230582305923060230612306223063230642306523066230672306823069230702307123072230732307423075230762307723078230792308023081230822308323084230852308623087230882308923090230912309223093230942309523096230972309823099231002310123102231032310423105231062310723108231092311023111231122311323114231152311623117231182311923120231212312223123231242312523126231272312823129231302313123132231332313423135231362313723138231392314023141231422314323144231452314623147231482314923150231512315223153231542315523156231572315823159231602316123162231632316423165231662316723168231692317023171231722317323174231752317623177231782317923180231812318223183231842318523186231872318823189231902319123192231932319423195231962319723198231992320023201232022320323204232052320623207232082320923210232112321223213232142321523216232172321823219232202322123222232232322423225232262322723228232292323023231232322323323234232352323623237232382323923240232412324223243232442324523246232472324823249232502325123252232532325423255232562325723258232592326023261232622326323264232652326623267232682326923270232712327223273232742327523276232772327823279232802328123282232832328423285232862328723288232892329023291232922329323294232952329623297232982329923300233012330223303233042330523306233072330823309233102331123312233132331423315233162331723318233192332023321233222332323324233252332623327233282332923330233312333223333233342333523336233372333823339233402334123342233432334423345233462334723348233492335023351233522335323354233552335623357233582335923360233612336223363233642336523366233672336823369233702337123372233732337423375233762337723378233792338023381233822338323384233852338623387233882338923390233912339223393233942339523396233972339823399234002340123402234032340423405234062340723408234092341023411234122341323414234152341623417234182341923420234212342223423234242342523426234272342823429234302343123432234332343423435234362343723438234392344023441234422344323444234452344623447234482344923450234512345223453234542345523456234572345823459234602346123462234632346423465234662346723468234692347023471234722347323474234752347623477234782347923480234812348223483234842348523486234872348823489234902349123492234932349423495234962349723498234992350023501235022350323504235052350623507235082350923510235112351223513235142351523516235172351823519235202352123522235232352423525235262352723528235292353023531235322353323534235352353623537235382353923540235412354223543235442354523546235472354823549235502355123552235532355423555235562355723558235592356023561235622356323564235652356623567235682356923570235712357223573235742357523576235772357823579235802358123582235832358423585235862358723588235892359023591235922359323594235952359623597235982359923600236012360223603236042360523606236072360823609236102361123612236132361423615236162361723618236192362023621236222362323624236252362623627236282362923630236312363223633236342363523636236372363823639236402364123642236432364423645236462364723648236492365023651236522365323654236552365623657236582365923660236612366223663236642366523666236672366823669236702367123672236732367423675236762367723678236792368023681236822368323684236852368623687236882368923690236912369223693236942369523696236972369823699237002370123702237032370423705237062370723708237092371023711237122371323714237152371623717237182371923720237212372223723237242372523726237272372823729237302373123732237332373423735237362373723738237392374023741237422374323744237452374623747237482374923750237512375223753237542375523756237572375823759237602376123762237632376423765237662376723768237692377023771237722377323774237752377623777237782377923780237812378223783237842378523786237872378823789237902379123792237932379423795237962379723798237992380023801238022380323804238052380623807238082380923810238112381223813238142381523816238172381823819238202382123822238232382423825238262382723828238292383023831238322383323834238352383623837238382383923840238412384223843238442384523846238472384823849238502385123852238532385423855238562385723858238592386023861238622386323864238652386623867238682386923870238712387223873238742387523876238772387823879238802388123882238832388423885238862388723888238892389023891238922389323894238952389623897238982389923900239012390223903239042390523906239072390823909239102391123912239132391423915239162391723918239192392023921239222392323924239252392623927239282392923930239312393223933239342393523936239372393823939239402394123942239432394423945239462394723948239492395023951239522395323954239552395623957239582395923960239612396223963239642396523966239672396823969239702397123972239732397423975239762397723978239792398023981239822398323984239852398623987239882398923990239912399223993239942399523996239972399823999240002400124002240032400424005240062400724008240092401024011240122401324014240152401624017240182401924020240212402224023240242402524026240272402824029240302403124032240332403424035240362403724038240392404024041240422404324044240452404624047240482404924050240512405224053240542405524056240572405824059240602406124062240632406424065240662406724068240692407024071240722407324074240752407624077240782407924080240812408224083240842408524086240872408824089240902409124092240932409424095240962409724098240992410024101241022410324104241052410624107241082410924110241112411224113241142411524116241172411824119241202412124122241232412424125241262412724128241292413024131241322413324134241352413624137241382413924140241412414224143241442414524146241472414824149241502415124152241532415424155241562415724158241592416024161241622416324164241652416624167241682416924170241712417224173241742417524176241772417824179241802418124182241832418424185241862418724188241892419024191241922419324194241952419624197241982419924200242012420224203242042420524206242072420824209242102421124212242132421424215242162421724218242192422024221242222422324224242252422624227242282422924230242312423224233242342423524236242372423824239242402424124242242432424424245242462424724248242492425024251242522425324254242552425624257242582425924260242612426224263242642426524266242672426824269242702427124272242732427424275242762427724278242792428024281242822428324284242852428624287242882428924290242912429224293242942429524296242972429824299243002430124302243032430424305243062430724308243092431024311243122431324314243152431624317243182431924320243212432224323243242432524326243272432824329243302433124332243332433424335243362433724338243392434024341243422434324344243452434624347243482434924350243512435224353243542435524356243572435824359243602436124362243632436424365243662436724368243692437024371243722437324374243752437624377243782437924380243812438224383243842438524386243872438824389243902439124392243932439424395243962439724398243992440024401244022440324404244052440624407244082440924410244112441224413244142441524416244172441824419244202442124422244232442424425244262442724428244292443024431244322443324434244352443624437244382443924440244412444224443244442444524446244472444824449244502445124452244532445424455244562445724458244592446024461244622446324464244652446624467244682446924470244712447224473244742447524476244772447824479244802448124482244832448424485244862448724488244892449024491244922449324494244952449624497244982449924500245012450224503245042450524506245072450824509245102451124512245132451424515245162451724518245192452024521245222452324524245252452624527245282452924530245312453224533245342453524536245372453824539245402454124542245432454424545245462454724548245492455024551245522455324554245552455624557245582455924560245612456224563245642456524566245672456824569245702457124572245732457424575245762457724578245792458024581245822458324584245852458624587245882458924590245912459224593245942459524596245972459824599246002460124602246032460424605246062460724608246092461024611246122461324614246152461624617246182461924620246212462224623246242462524626246272462824629246302463124632246332463424635246362463724638246392464024641246422464324644246452464624647246482464924650246512465224653246542465524656246572465824659246602466124662246632466424665246662466724668246692467024671246722467324674246752467624677246782467924680246812468224683246842468524686246872468824689246902469124692246932469424695246962469724698246992470024701247022470324704247052470624707247082470924710247112471224713247142471524716247172471824719247202472124722247232472424725247262472724728247292473024731247322473324734247352473624737247382473924740247412474224743247442474524746247472474824749247502475124752247532475424755247562475724758247592476024761247622476324764247652476624767247682476924770247712477224773247742477524776247772477824779247802478124782247832478424785247862478724788247892479024791247922479324794247952479624797247982479924800248012480224803248042480524806248072480824809248102481124812248132481424815248162481724818248192482024821248222482324824248252482624827248282482924830248312483224833248342483524836248372483824839248402484124842248432484424845248462484724848248492485024851248522485324854248552485624857248582485924860248612486224863248642486524866248672486824869248702487124872248732487424875248762487724878248792488024881248822488324884248852488624887248882488924890248912489224893248942489524896248972489824899249002490124902249032490424905249062490724908249092491024911249122491324914249152491624917249182491924920249212492224923249242492524926249272492824929249302493124932249332493424935249362493724938249392494024941249422494324944249452494624947249482494924950249512495224953249542495524956249572495824959249602496124962249632496424965249662496724968249692497024971249722497324974249752497624977249782497924980249812498224983249842498524986249872498824989249902499124992249932499424995249962499724998249992500025001250022500325004250052500625007250082500925010250112501225013250142501525016250172501825019250202502125022250232502425025250262502725028250292503025031250322503325034250352503625037250382503925040250412504225043250442504525046250472504825049250502505125052250532505425055250562505725058250592506025061250622506325064250652506625067250682506925070250712507225073250742507525076250772507825079250802508125082250832508425085250862508725088250892509025091250922509325094250952509625097250982509925100251012510225103251042510525106251072510825109251102511125112251132511425115251162511725118251192512025121251222512325124251252512625127251282512925130251312513225133251342513525136251372513825139251402514125142251432514425145251462514725148251492515025151251522515325154251552515625157251582515925160251612516225163251642516525166251672516825169251702517125172251732517425175251762517725178251792518025181251822518325184251852518625187251882518925190251912519225193251942519525196251972519825199252002520125202252032520425205252062520725208252092521025211252122521325214252152521625217252182521925220252212522225223252242522525226252272522825229252302523125232252332523425235252362523725238252392524025241252422524325244252452524625247252482524925250252512525225253252542525525256252572525825259252602526125262252632526425265252662526725268252692527025271252722527325274252752527625277252782527925280252812528225283252842528525286252872528825289252902529125292252932529425295252962529725298252992530025301253022530325304253052530625307253082530925310253112531225313253142531525316253172531825319253202532125322253232532425325253262532725328253292533025331253322533325334253352533625337253382533925340253412534225343253442534525346253472534825349253502535125352253532535425355253562535725358253592536025361253622536325364253652536625367253682536925370253712537225373253742537525376253772537825379253802538125382253832538425385253862538725388253892539025391253922539325394253952539625397253982539925400254012540225403254042540525406254072540825409254102541125412254132541425415254162541725418254192542025421254222542325424254252542625427254282542925430254312543225433254342543525436254372543825439254402544125442254432544425445254462544725448254492545025451254522545325454254552545625457254582545925460254612546225463254642546525466254672546825469254702547125472254732547425475254762547725478254792548025481254822548325484254852548625487254882548925490254912549225493254942549525496254972549825499255002550125502255032550425505255062550725508255092551025511255122551325514255152551625517255182551925520255212552225523255242552525526255272552825529255302553125532255332553425535255362553725538255392554025541255422554325544255452554625547255482554925550255512555225553255542555525556255572555825559255602556125562255632556425565255662556725568255692557025571255722557325574255752557625577255782557925580255812558225583255842558525586255872558825589255902559125592255932559425595255962559725598255992560025601256022560325604256052560625607256082560925610256112561225613256142561525616256172561825619256202562125622256232562425625256262562725628256292563025631256322563325634256352563625637256382563925640256412564225643256442564525646256472564825649256502565125652256532565425655256562565725658256592566025661256622566325664256652566625667256682566925670256712567225673256742567525676256772567825679256802568125682256832568425685256862568725688256892569025691256922569325694256952569625697256982569925700257012570225703257042570525706257072570825709257102571125712257132571425715257162571725718257192572025721257222572325724257252572625727257282572925730257312573225733257342573525736257372573825739257402574125742257432574425745257462574725748257492575025751257522575325754257552575625757257582575925760257612576225763257642576525766257672576825769257702577125772257732577425775257762577725778257792578025781257822578325784257852578625787257882578925790257912579225793257942579525796257972579825799258002580125802258032580425805258062580725808258092581025811258122581325814258152581625817258182581925820258212582225823258242582525826258272582825829258302583125832258332583425835258362583725838258392584025841258422584325844258452584625847258482584925850258512585225853258542585525856258572585825859258602586125862258632586425865258662586725868258692587025871258722587325874258752587625877258782587925880258812588225883258842588525886258872588825889258902589125892258932589425895258962589725898258992590025901259022590325904259052590625907259082590925910259112591225913259142591525916259172591825919259202592125922259232592425925259262592725928259292593025931259322593325934259352593625937259382593925940259412594225943259442594525946259472594825949259502595125952259532595425955259562595725958259592596025961259622596325964259652596625967259682596925970259712597225973259742597525976259772597825979259802598125982259832598425985259862598725988259892599025991259922599325994259952599625997259982599926000260012600226003260042600526006260072600826009260102601126012260132601426015260162601726018260192602026021260222602326024260252602626027260282602926030260312603226033260342603526036260372603826039260402604126042260432604426045260462604726048260492605026051260522605326054260552605626057260582605926060260612606226063260642606526066260672606826069260702607126072260732607426075260762607726078260792608026081260822608326084260852608626087260882608926090260912609226093260942609526096260972609826099261002610126102261032610426105261062610726108261092611026111261122611326114261152611626117261182611926120261212612226123261242612526126261272612826129261302613126132261332613426135261362613726138261392614026141261422614326144261452614626147261482614926150261512615226153261542615526156261572615826159261602616126162261632616426165261662616726168261692617026171261722617326174261752617626177261782617926180261812618226183261842618526186261872618826189261902619126192261932619426195261962619726198261992620026201262022620326204262052620626207262082620926210262112621226213262142621526216262172621826219262202622126222262232622426225262262622726228262292623026231262322623326234262352623626237262382623926240262412624226243262442624526246262472624826249262502625126252262532625426255262562625726258262592626026261262622626326264262652626626267262682626926270262712627226273262742627526276262772627826279262802628126282262832628426285262862628726288262892629026291262922629326294262952629626297262982629926300263012630226303263042630526306263072630826309263102631126312263132631426315263162631726318263192632026321263222632326324263252632626327263282632926330263312633226333263342633526336263372633826339263402634126342263432634426345263462634726348263492635026351263522635326354263552635626357263582635926360263612636226363263642636526366263672636826369263702637126372263732637426375263762637726378263792638026381263822638326384263852638626387263882638926390263912639226393263942639526396263972639826399264002640126402264032640426405264062640726408264092641026411264122641326414264152641626417264182641926420264212642226423264242642526426264272642826429264302643126432264332643426435264362643726438264392644026441264422644326444264452644626447264482644926450264512645226453264542645526456264572645826459264602646126462264632646426465264662646726468264692647026471264722647326474264752647626477264782647926480264812648226483264842648526486264872648826489264902649126492264932649426495264962649726498264992650026501265022650326504265052650626507265082650926510265112651226513265142651526516265172651826519265202652126522265232652426525265262652726528265292653026531265322653326534265352653626537265382653926540265412654226543265442654526546265472654826549265502655126552265532655426555265562655726558265592656026561265622656326564265652656626567265682656926570265712657226573265742657526576265772657826579265802658126582265832658426585265862658726588265892659026591265922659326594265952659626597265982659926600266012660226603266042660526606266072660826609266102661126612266132661426615266162661726618266192662026621266222662326624266252662626627266282662926630266312663226633266342663526636266372663826639266402664126642266432664426645266462664726648266492665026651266522665326654266552665626657266582665926660266612666226663266642666526666266672666826669266702667126672266732667426675266762667726678266792668026681266822668326684266852668626687266882668926690266912669226693266942669526696266972669826699267002670126702267032670426705267062670726708267092671026711267122671326714267152671626717267182671926720267212672226723267242672526726267272672826729267302673126732267332673426735267362673726738267392674026741267422674326744267452674626747267482674926750267512675226753267542675526756267572675826759267602676126762267632676426765267662676726768267692677026771267722677326774267752677626777267782677926780267812678226783267842678526786267872678826789267902679126792267932679426795267962679726798267992680026801268022680326804268052680626807268082680926810268112681226813268142681526816268172681826819268202682126822268232682426825268262682726828268292683026831268322683326834268352683626837268382683926840268412684226843268442684526846268472684826849268502685126852268532685426855268562685726858268592686026861268622686326864268652686626867268682686926870268712687226873268742687526876268772687826879268802688126882268832688426885268862688726888268892689026891268922689326894268952689626897268982689926900269012690226903269042690526906269072690826909269102691126912269132691426915269162691726918269192692026921269222692326924269252692626927269282692926930269312693226933269342693526936269372693826939269402694126942269432694426945269462694726948269492695026951269522695326954269552695626957269582695926960269612696226963269642696526966269672696826969269702697126972269732697426975269762697726978269792698026981269822698326984269852698626987269882698926990269912699226993269942699526996269972699826999270002700127002270032700427005270062700727008270092701027011270122701327014270152701627017270182701927020270212702227023270242702527026270272702827029270302703127032270332703427035270362703727038270392704027041270422704327044270452704627047270482704927050270512705227053270542705527056270572705827059270602706127062270632706427065270662706727068270692707027071270722707327074270752707627077270782707927080270812708227083270842708527086270872708827089270902709127092270932709427095270962709727098270992710027101271022710327104271052710627107271082710927110271112711227113271142711527116271172711827119271202712127122271232712427125271262712727128271292713027131271322713327134271352713627137271382713927140271412714227143271442714527146271472714827149271502715127152271532715427155271562715727158271592716027161271622716327164271652716627167271682716927170271712717227173271742717527176271772717827179271802718127182271832718427185271862718727188271892719027191271922719327194271952719627197271982719927200272012720227203272042720527206272072720827209272102721127212272132721427215272162721727218272192722027221272222722327224272252722627227272282722927230272312723227233272342723527236272372723827239272402724127242272432724427245272462724727248272492725027251272522725327254272552725627257272582725927260272612726227263272642726527266272672726827269272702727127272272732727427275272762727727278272792728027281272822728327284272852728627287272882728927290272912729227293272942729527296272972729827299273002730127302273032730427305273062730727308273092731027311273122731327314273152731627317273182731927320273212732227323273242732527326273272732827329273302733127332273332733427335273362733727338273392734027341273422734327344273452734627347273482734927350273512735227353273542735527356273572735827359273602736127362273632736427365273662736727368273692737027371273722737327374273752737627377273782737927380273812738227383273842738527386273872738827389273902739127392273932739427395273962739727398273992740027401274022740327404274052740627407274082740927410274112741227413274142741527416274172741827419274202742127422274232742427425274262742727428274292743027431274322743327434274352743627437274382743927440274412744227443274442744527446274472744827449274502745127452274532745427455274562745727458274592746027461274622746327464274652746627467274682746927470274712747227473274742747527476274772747827479274802748127482274832748427485274862748727488274892749027491274922749327494274952749627497274982749927500275012750227503275042750527506275072750827509275102751127512275132751427515275162751727518275192752027521275222752327524275252752627527275282752927530275312753227533275342753527536275372753827539275402754127542275432754427545275462754727548275492755027551275522755327554275552755627557275582755927560275612756227563275642756527566275672756827569275702757127572275732757427575275762757727578275792758027581275822758327584275852758627587275882758927590275912759227593275942759527596275972759827599276002760127602276032760427605276062760727608276092761027611276122761327614276152761627617276182761927620276212762227623276242762527626276272762827629276302763127632276332763427635276362763727638276392764027641276422764327644276452764627647276482764927650276512765227653276542765527656276572765827659276602766127662276632766427665276662766727668276692767027671276722767327674276752767627677276782767927680276812768227683276842768527686276872768827689276902769127692276932769427695276962769727698276992770027701277022770327704277052770627707277082770927710277112771227713277142771527716277172771827719277202772127722277232772427725277262772727728277292773027731277322773327734277352773627737277382773927740277412774227743277442774527746277472774827749277502775127752277532775427755277562775727758277592776027761277622776327764277652776627767277682776927770277712777227773277742777527776277772777827779277802778127782277832778427785277862778727788277892779027791277922779327794277952779627797277982779927800278012780227803278042780527806278072780827809278102781127812278132781427815278162781727818278192782027821278222782327824278252782627827278282782927830278312783227833278342783527836278372783827839278402784127842278432784427845278462784727848278492785027851278522785327854278552785627857278582785927860278612786227863278642786527866278672786827869278702787127872278732787427875278762787727878278792788027881278822788327884278852788627887278882788927890278912789227893278942789527896278972789827899279002790127902279032790427905279062790727908279092791027911279122791327914279152791627917279182791927920279212792227923279242792527926279272792827929279302793127932279332793427935279362793727938279392794027941279422794327944279452794627947279482794927950279512795227953279542795527956279572795827959279602796127962279632796427965279662796727968279692797027971279722797327974279752797627977279782797927980279812798227983279842798527986279872798827989279902799127992279932799427995279962799727998279992800028001280022800328004280052800628007280082800928010280112801228013280142801528016280172801828019280202802128022280232802428025280262802728028280292803028031280322803328034280352803628037280382803928040280412804228043280442804528046280472804828049280502805128052280532805428055280562805728058280592806028061280622806328064280652806628067280682806928070280712807228073280742807528076280772807828079280802808128082280832808428085280862808728088280892809028091280922809328094280952809628097280982809928100281012810228103281042810528106281072810828109281102811128112281132811428115281162811728118281192812028121281222812328124281252812628127281282812928130281312813228133281342813528136281372813828139281402814128142281432814428145281462814728148281492815028151281522815328154281552815628157281582815928160281612816228163281642816528166281672816828169281702817128172281732817428175281762817728178281792818028181281822818328184281852818628187281882818928190281912819228193281942819528196281972819828199282002820128202282032820428205282062820728208282092821028211282122821328214282152821628217282182821928220282212822228223282242822528226282272822828229282302823128232282332823428235282362823728238282392824028241282422824328244282452824628247282482824928250282512825228253282542825528256282572825828259282602826128262282632826428265282662826728268282692827028271282722827328274282752827628277282782827928280282812828228283282842828528286282872828828289282902829128292282932829428295282962829728298282992830028301283022830328304283052830628307283082830928310283112831228313283142831528316283172831828319283202832128322283232832428325283262832728328283292833028331283322833328334283352833628337283382833928340283412834228343283442834528346283472834828349283502835128352283532835428355283562835728358283592836028361283622836328364283652836628367283682836928370283712837228373283742837528376283772837828379283802838128382283832838428385283862838728388283892839028391283922839328394283952839628397283982839928400284012840228403284042840528406284072840828409284102841128412284132841428415284162841728418284192842028421284222842328424284252842628427284282842928430284312843228433284342843528436284372843828439284402844128442284432844428445284462844728448284492845028451284522845328454284552845628457284582845928460284612846228463284642846528466284672846828469284702847128472284732847428475284762847728478284792848028481284822848328484284852848628487284882848928490284912849228493284942849528496284972849828499285002850128502285032850428505285062850728508285092851028511285122851328514285152851628517285182851928520285212852228523285242852528526285272852828529285302853128532285332853428535285362853728538285392854028541285422854328544285452854628547285482854928550285512855228553285542855528556285572855828559285602856128562285632856428565285662856728568285692857028571285722857328574285752857628577285782857928580285812858228583285842858528586285872858828589285902859128592285932859428595285962859728598285992860028601286022860328604286052860628607286082860928610286112861228613286142861528616286172861828619286202862128622286232862428625286262862728628286292863028631286322863328634286352863628637286382863928640286412864228643286442864528646286472864828649286502865128652286532865428655286562865728658286592866028661286622866328664286652866628667286682866928670286712867228673286742867528676286772867828679286802868128682286832868428685286862868728688286892869028691286922869328694286952869628697286982869928700287012870228703287042870528706287072870828709287102871128712287132871428715287162871728718287192872028721287222872328724287252872628727287282872928730287312873228733287342873528736287372873828739287402874128742287432874428745287462874728748287492875028751287522875328754287552875628757287582875928760287612876228763287642876528766287672876828769287702877128772287732877428775287762877728778287792878028781287822878328784287852878628787287882878928790287912879228793287942879528796287972879828799288002880128802288032880428805288062880728808288092881028811288122881328814288152881628817288182881928820288212882228823288242882528826288272882828829288302883128832288332883428835288362883728838288392884028841288422884328844288452884628847288482884928850288512885228853288542885528856288572885828859288602886128862288632886428865288662886728868288692887028871288722887328874288752887628877288782887928880288812888228883288842888528886288872888828889288902889128892288932889428895288962889728898288992890028901289022890328904289052890628907289082890928910289112891228913289142891528916289172891828919289202892128922289232892428925289262892728928289292893028931289322893328934289352893628937289382893928940289412894228943289442894528946289472894828949289502895128952289532895428955289562895728958289592896028961289622896328964289652896628967289682896928970289712897228973289742897528976289772897828979289802898128982289832898428985289862898728988289892899028991289922899328994289952899628997289982899929000290012900229003290042900529006290072900829009290102901129012290132901429015290162901729018290192902029021290222902329024290252902629027290282902929030290312903229033290342903529036290372903829039290402904129042290432904429045290462904729048290492905029051290522905329054290552905629057290582905929060290612906229063290642906529066290672906829069290702907129072290732907429075290762907729078290792908029081290822908329084290852908629087290882908929090290912909229093290942909529096290972909829099291002910129102291032910429105291062910729108291092911029111291122911329114291152911629117291182911929120291212912229123291242912529126291272912829129291302913129132291332913429135291362913729138291392914029141291422914329144291452914629147291482914929150291512915229153291542915529156291572915829159291602916129162291632916429165291662916729168291692917029171291722917329174291752917629177291782917929180291812918229183291842918529186291872918829189291902919129192291932919429195291962919729198291992920029201292022920329204292052920629207292082920929210292112921229213292142921529216292172921829219292202922129222292232922429225292262922729228292292923029231292322923329234292352923629237292382923929240292412924229243292442924529246292472924829249292502925129252292532925429255292562925729258292592926029261292622926329264292652926629267292682926929270292712927229273292742927529276292772927829279292802928129282292832928429285292862928729288292892929029291292922929329294292952929629297292982929929300293012930229303293042930529306293072930829309293102931129312293132931429315293162931729318293192932029321293222932329324293252932629327293282932929330293312933229333293342933529336293372933829339293402934129342293432934429345293462934729348293492935029351293522935329354293552935629357293582935929360293612936229363293642936529366293672936829369293702937129372293732937429375293762937729378293792938029381293822938329384293852938629387293882938929390293912939229393293942939529396293972939829399294002940129402294032940429405294062940729408294092941029411294122941329414294152941629417294182941929420294212942229423294242942529426294272942829429294302943129432294332943429435294362943729438294392944029441294422944329444294452944629447294482944929450294512945229453294542945529456294572945829459294602946129462294632946429465294662946729468294692947029471294722947329474294752947629477294782947929480294812948229483294842948529486294872948829489294902949129492294932949429495294962949729498294992950029501295022950329504295052950629507295082950929510295112951229513295142951529516295172951829519295202952129522295232952429525295262952729528295292953029531295322953329534295352953629537295382953929540295412954229543295442954529546295472954829549295502955129552295532955429555295562955729558295592956029561295622956329564295652956629567295682956929570295712957229573295742957529576295772957829579295802958129582295832958429585295862958729588295892959029591295922959329594295952959629597295982959929600296012960229603296042960529606296072960829609296102961129612296132961429615296162961729618296192962029621296222962329624296252962629627296282962929630296312963229633296342963529636296372963829639296402964129642296432964429645296462964729648296492965029651296522965329654296552965629657296582965929660296612966229663296642966529666296672966829669296702967129672296732967429675296762967729678296792968029681296822968329684296852968629687296882968929690296912969229693296942969529696296972969829699297002970129702297032970429705297062970729708297092971029711297122971329714297152971629717297182971929720297212972229723297242972529726297272972829729297302973129732297332973429735297362973729738297392974029741297422974329744297452974629747297482974929750297512975229753297542975529756297572975829759297602976129762297632976429765297662976729768297692977029771297722977329774297752977629777297782977929780297812978229783297842978529786297872978829789297902979129792297932979429795297962979729798297992980029801298022980329804298052980629807298082980929810298112981229813298142981529816298172981829819298202982129822298232982429825298262982729828298292983029831298322983329834298352983629837298382983929840298412984229843298442984529846298472984829849298502985129852298532985429855298562985729858298592986029861298622986329864298652986629867298682986929870298712987229873298742987529876298772987829879298802988129882298832988429885298862988729888298892989029891298922989329894298952989629897298982989929900299012990229903299042990529906299072990829909299102991129912299132991429915299162991729918299192992029921299222992329924299252992629927299282992929930299312993229933299342993529936299372993829939299402994129942299432994429945299462994729948299492995029951299522995329954299552995629957299582995929960299612996229963299642996529966299672996829969299702997129972299732997429975299762997729978299792998029981299822998329984299852998629987299882998929990299912999229993299942999529996299972999829999300003000130002300033000430005300063000730008300093001030011300123001330014300153001630017300183001930020300213002230023300243002530026300273002830029300303003130032300333003430035300363003730038300393004030041300423004330044300453004630047300483004930050300513005230053300543005530056300573005830059300603006130062300633006430065300663006730068300693007030071300723007330074300753007630077300783007930080300813008230083300843008530086300873008830089300903009130092300933009430095300963009730098300993010030101301023010330104301053010630107301083010930110301113011230113301143011530116301173011830119301203012130122301233012430125301263012730128301293013030131301323013330134301353013630137301383013930140301413014230143301443014530146301473014830149301503015130152301533015430155301563015730158301593016030161301623016330164301653016630167301683016930170301713017230173301743017530176301773017830179301803018130182301833018430185301863018730188301893019030191301923019330194301953019630197301983019930200302013020230203302043020530206302073020830209302103021130212302133021430215302163021730218302193022030221302223022330224302253022630227302283022930230302313023230233302343023530236302373023830239302403024130242302433024430245302463024730248302493025030251302523025330254302553025630257302583025930260302613026230263302643026530266302673026830269302703027130272302733027430275302763027730278302793028030281302823028330284302853028630287302883028930290302913029230293302943029530296302973029830299303003030130302303033030430305303063030730308303093031030311303123031330314303153031630317303183031930320303213032230323303243032530326303273032830329303303033130332303333033430335303363033730338303393034030341303423034330344303453034630347303483034930350303513035230353303543035530356303573035830359303603036130362303633036430365303663036730368303693037030371303723037330374303753037630377303783037930380303813038230383303843038530386303873038830389303903039130392303933039430395303963039730398303993040030401304023040330404304053040630407304083040930410304113041230413304143041530416304173041830419304203042130422304233042430425304263042730428304293043030431304323043330434304353043630437304383043930440304413044230443304443044530446304473044830449304503045130452304533045430455304563045730458304593046030461304623046330464304653046630467304683046930470304713047230473304743047530476304773047830479304803048130482304833048430485304863048730488304893049030491304923049330494304953049630497304983049930500305013050230503305043050530506305073050830509305103051130512305133051430515305163051730518305193052030521305223052330524305253052630527305283052930530305313053230533305343053530536305373053830539305403054130542305433054430545305463054730548305493055030551305523055330554305553055630557305583055930560305613056230563305643056530566305673056830569305703057130572305733057430575305763057730578305793058030581305823058330584305853058630587305883058930590305913059230593305943059530596305973059830599306003060130602306033060430605306063060730608306093061030611306123061330614306153061630617306183061930620306213062230623306243062530626306273062830629306303063130632306333063430635306363063730638306393064030641306423064330644306453064630647306483064930650306513065230653306543065530656306573065830659306603066130662306633066430665306663066730668306693067030671306723067330674306753067630677306783067930680306813068230683306843068530686306873068830689306903069130692306933069430695306963069730698306993070030701307023070330704307053070630707307083070930710307113071230713307143071530716307173071830719307203072130722307233072430725307263072730728307293073030731307323073330734307353073630737307383073930740307413074230743307443074530746307473074830749307503075130752307533075430755307563075730758307593076030761307623076330764307653076630767307683076930770307713077230773307743077530776307773077830779307803078130782307833078430785307863078730788307893079030791307923079330794307953079630797307983079930800308013080230803308043080530806308073080830809308103081130812308133081430815308163081730818308193082030821308223082330824308253082630827308283082930830308313083230833308343083530836308373083830839308403084130842308433084430845308463084730848308493085030851308523085330854308553085630857308583085930860308613086230863308643086530866308673086830869308703087130872308733087430875308763087730878308793088030881308823088330884308853088630887308883088930890308913089230893308943089530896308973089830899309003090130902309033090430905309063090730908309093091030911309123091330914309153091630917309183091930920309213092230923309243092530926309273092830929309303093130932309333093430935309363093730938309393094030941309423094330944309453094630947309483094930950309513095230953309543095530956309573095830959309603096130962309633096430965309663096730968309693097030971309723097330974309753097630977309783097930980309813098230983309843098530986309873098830989309903099130992309933099430995309963099730998309993100031001310023100331004310053100631007310083100931010310113101231013310143101531016310173101831019310203102131022310233102431025310263102731028310293103031031310323103331034310353103631037310383103931040310413104231043310443104531046310473104831049310503105131052310533105431055310563105731058310593106031061310623106331064310653106631067310683106931070310713107231073310743107531076310773107831079310803108131082310833108431085310863108731088310893109031091310923109331094310953109631097310983109931100311013110231103311043110531106311073110831109311103111131112311133111431115311163111731118311193112031121311223112331124311253112631127311283112931130311313113231133311343113531136311373113831139311403114131142311433114431145311463114731148311493115031151311523115331154311553115631157311583115931160311613116231163311643116531166311673116831169311703117131172311733117431175311763117731178311793118031181311823118331184311853118631187311883118931190311913119231193311943119531196311973119831199312003120131202312033120431205312063120731208312093121031211312123121331214312153121631217312183121931220312213122231223312243122531226312273122831229312303123131232312333123431235312363123731238312393124031241312423124331244312453124631247312483124931250312513125231253312543125531256312573125831259312603126131262312633126431265312663126731268312693127031271312723127331274312753127631277312783127931280312813128231283312843128531286312873128831289312903129131292312933129431295312963129731298312993130031301313023130331304313053130631307313083130931310313113131231313313143131531316313173131831319313203132131322313233132431325313263132731328313293133031331313323133331334313353133631337313383133931340313413134231343313443134531346313473134831349313503135131352313533135431355313563135731358313593136031361313623136331364313653136631367313683136931370313713137231373313743137531376313773137831379313803138131382313833138431385313863138731388313893139031391313923139331394313953139631397313983139931400314013140231403314043140531406314073140831409314103141131412314133141431415314163141731418314193142031421314223142331424314253142631427314283142931430314313143231433314343143531436314373143831439314403144131442314433144431445314463144731448314493145031451314523145331454314553145631457314583145931460314613146231463314643146531466314673146831469314703147131472314733147431475314763147731478314793148031481314823148331484314853148631487314883148931490314913149231493314943149531496314973149831499315003150131502315033150431505315063150731508315093151031511315123151331514315153151631517315183151931520315213152231523315243152531526315273152831529315303153131532315333153431535315363153731538315393154031541315423154331544315453154631547315483154931550315513155231553315543155531556315573155831559315603156131562315633156431565315663156731568315693157031571315723157331574315753157631577315783157931580315813158231583315843158531586315873158831589315903159131592315933159431595315963159731598315993160031601316023160331604316053160631607316083160931610316113161231613316143161531616316173161831619316203162131622316233162431625316263162731628316293163031631316323163331634316353163631637316383163931640316413164231643316443164531646316473164831649316503165131652316533165431655316563165731658316593166031661316623166331664316653166631667316683166931670316713167231673316743167531676316773167831679316803168131682316833168431685316863168731688316893169031691316923169331694316953169631697316983169931700317013170231703317043170531706317073170831709317103171131712317133171431715317163171731718317193172031721317223172331724317253172631727317283172931730317313173231733317343173531736317373173831739317403174131742317433174431745317463174731748317493175031751317523175331754317553175631757317583175931760317613176231763317643176531766317673176831769317703177131772317733177431775317763177731778317793178031781317823178331784317853178631787317883178931790317913179231793317943179531796317973179831799318003180131802318033180431805318063180731808318093181031811318123181331814318153181631817318183181931820318213182231823318243182531826318273182831829318303183131832318333183431835318363183731838318393184031841318423184331844318453184631847318483184931850318513185231853318543185531856318573185831859318603186131862318633186431865318663186731868318693187031871318723187331874318753187631877318783187931880318813188231883318843188531886318873188831889318903189131892318933189431895318963189731898318993190031901319023190331904319053190631907319083190931910319113191231913319143191531916319173191831919319203192131922319233192431925319263192731928319293193031931319323193331934319353193631937319383193931940319413194231943319443194531946319473194831949319503195131952319533195431955319563195731958319593196031961319623196331964319653196631967319683196931970319713197231973319743197531976319773197831979319803198131982319833198431985319863198731988319893199031991319923199331994319953199631997319983199932000320013200232003320043200532006320073200832009320103201132012320133201432015320163201732018320193202032021320223202332024320253202632027320283202932030320313203232033320343203532036320373203832039320403204132042320433204432045320463204732048320493205032051320523205332054320553205632057320583205932060320613206232063320643206532066320673206832069320703207132072320733207432075320763207732078320793208032081320823208332084320853208632087320883208932090320913209232093320943209532096320973209832099321003210132102321033210432105321063210732108321093211032111321123211332114321153211632117321183211932120321213212232123321243212532126321273212832129321303213132132321333213432135321363213732138321393214032141321423214332144321453214632147321483214932150321513215232153321543215532156321573215832159321603216132162321633216432165321663216732168321693217032171321723217332174321753217632177321783217932180321813218232183321843218532186321873218832189321903219132192321933219432195321963219732198321993220032201322023220332204322053220632207322083220932210322113221232213322143221532216322173221832219322203222132222322233222432225322263222732228322293223032231322323223332234322353223632237322383223932240322413224232243322443224532246322473224832249322503225132252322533225432255322563225732258322593226032261322623226332264322653226632267322683226932270322713227232273322743227532276322773227832279322803228132282322833228432285322863228732288322893229032291322923229332294322953229632297322983229932300323013230232303323043230532306323073230832309323103231132312323133231432315323163231732318323193232032321323223232332324323253232632327323283232932330323313233232333323343233532336323373233832339323403234132342323433234432345323463234732348323493235032351323523235332354323553235632357323583235932360323613236232363323643236532366323673236832369323703237132372323733237432375323763237732378323793238032381323823238332384323853238632387323883238932390323913239232393323943239532396323973239832399324003240132402324033240432405324063240732408324093241032411324123241332414324153241632417324183241932420324213242232423324243242532426324273242832429324303243132432324333243432435324363243732438324393244032441324423244332444324453244632447324483244932450324513245232453324543245532456324573245832459324603246132462324633246432465324663246732468324693247032471324723247332474324753247632477324783247932480324813248232483324843248532486324873248832489324903249132492324933249432495324963249732498324993250032501325023250332504325053250632507325083250932510325113251232513325143251532516325173251832519325203252132522325233252432525325263252732528325293253032531325323253332534325353253632537325383253932540325413254232543325443254532546325473254832549325503255132552325533255432555325563255732558325593256032561325623256332564325653256632567325683256932570325713257232573325743257532576325773257832579325803258132582325833258432585325863258732588325893259032591325923259332594325953259632597325983259932600326013260232603326043260532606326073260832609326103261132612326133261432615326163261732618326193262032621326223262332624326253262632627326283262932630326313263232633326343263532636326373263832639326403264132642326433264432645326463264732648326493265032651326523265332654326553265632657326583265932660326613266232663326643266532666326673266832669326703267132672326733267432675326763267732678326793268032681326823268332684326853268632687326883268932690326913269232693326943269532696326973269832699327003270132702327033270432705327063270732708327093271032711327123271332714327153271632717327183271932720327213272232723327243272532726327273272832729327303273132732327333273432735 |
- diff --git a/Documentation/hwlat_detector.txt b/Documentation/hwlat_detector.txt
- new file mode 100644
- index 000000000000..cb61516483d3
- @@ -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 --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
- index 39280b72f27a..c46295a8d55b 100644
- @@ -1640,6 +1640,15 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
- 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 --git a/Documentation/sysrq.txt b/Documentation/sysrq.txt
- index 13f5619b2203..f64d075ba647 100644
- @@ -59,10 +59,17 @@ On PowerPC - Press 'ALT - Print Screen (or F13) - <command key>,
- 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 --git a/Documentation/trace/histograms.txt b/Documentation/trace/histograms.txt
- new file mode 100644
- index 000000000000..6f2aeabf7faa
- @@ -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 --git a/Makefile b/Makefile
- index 07070a1e6292..f04a8b6444b9 100644
- @@ -797,6 +797,9 @@ KBUILD_CFLAGS += $(call cc-option,-Werror=strict-prototypes)
- # 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 --git a/arch/Kconfig b/arch/Kconfig
- index 4e949e58b192..3b26d76933fb 100644
- @@ -9,6 +9,7 @@ config OPROFILE
- 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 KPROBES
- 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 --git a/arch/arm/Kconfig b/arch/arm/Kconfig
- index 34e1569a11ee..79c4603e9453 100644
- @@ -33,7 +33,7 @@ config ARM
- 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 @@ config ARM
- 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 --git a/arch/arm/include/asm/switch_to.h b/arch/arm/include/asm/switch_to.h
- index 12ebfcc1d539..c962084605bc 100644
- @@ -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 @@ extern struct task_struct *__switch_to(struct task_struct *, struct thread_info
- #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 --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
- index 776757d1604a..1f36a4eccc72 100644
- @@ -49,6 +49,7 @@ struct cpu_context_save {
- 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 @@ extern int vfp_restore_user_hwstate(struct user_vfp __user *,
- #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 @@ extern int vfp_restore_user_hwstate(struct user_vfp __user *,
- #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 @@ extern int vfp_restore_user_hwstate(struct user_vfp __user *,
- * 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 --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c
- index 871b8267d211..4dbe70de7318 100644
- @@ -65,6 +65,7 @@ int main(void)
- 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 --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
- index 3ce377f7251f..d044cea59f54 100644
- @@ -215,11 +215,18 @@ ENDPROC(__dabt_svc)
- #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 @@ ENDPROC(__irq_svc)
- 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 --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
- index 30a7228eaceb..c3bd6cbfce4b 100644
- @@ -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 @@ ENDPROC(ret_fast_syscall)
- 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 --git a/arch/arm/kernel/patch.c b/arch/arm/kernel/patch.c
- index 69bda1a5707e..1f665acaa6a9 100644
- @@ -15,7 +15,7 @@ struct patch {
- unsigned int insn;
- };
-
- -static DEFINE_SPINLOCK(patch_lock);
- +static DEFINE_RAW_SPINLOCK(patch_lock);
-
- static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags)
- __acquires(&patch_lock)
- @@ -32,7 +32,7 @@ static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags)
- return addr;
-
- if (flags)
- - spin_lock_irqsave(&patch_lock, *flags);
- + raw_spin_lock_irqsave(&patch_lock, *flags);
- else
- __acquire(&patch_lock);
-
- @@ -47,7 +47,7 @@ static void __kprobes patch_unmap(int fixmap, unsigned long *flags)
- clear_fixmap(fixmap);
-
- if (flags)
- - spin_unlock_irqrestore(&patch_lock, *flags);
- + raw_spin_unlock_irqrestore(&patch_lock, *flags);
- else
- __release(&patch_lock);
- }
- diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
- index 4adfb46e3ee9..15f1d94b47c5 100644
- @@ -319,6 +319,30 @@ unsigned long arch_randomize_brk(struct mm_struct *mm)
- }
-
- #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 --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
- index 7b8f2141427b..96541e00b74a 100644
- @@ -572,7 +572,8 @@ do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall)
- */
- 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 --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
- index b26361355dae..e5754e3b03c4 100644
- @@ -230,8 +230,6 @@ int __cpu_disable(void)
- flush_cache_louis();
- local_flush_tlb_all();
-
- - clear_tasks_mm_cpumask(cpu);
- -
- return 0;
- }
-
- @@ -247,6 +245,9 @@ void __cpu_die(unsigned int cpu)
- pr_err("CPU%u: cpu didn't die\n", cpu);
- return;
- }
- +
- + clear_tasks_mm_cpumask(cpu);
- +
- pr_notice("CPU%u: shutdown\n", cpu);
-
- /*
- diff --git a/arch/arm/kernel/unwind.c b/arch/arm/kernel/unwind.c
- index 0bee233fef9a..314cfb232a63 100644
- @@ -93,7 +93,7 @@ extern const struct unwind_idx __start_unwind_idx[];
- 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 @@ static const struct unwind_idx *unwind_find_idx(unsigned long addr)
- /* 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 @@ static const struct unwind_idx *unwind_find_idx(unsigned long addr)
- 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 @@ struct unwind_table *unwind_table_add(unsigned long start, unsigned long size,
- 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 @@ void unwind_table_del(struct unwind_table *tab)
- 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 --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
- index d7bef2144760..36a3e51492f7 100644
- @@ -496,18 +496,18 @@ static void kvm_arm_resume_guest(struct kvm *kvm)
- 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 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
- * 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 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
- local_irq_enable();
- kvm_timer_sync_hwstate(vcpu);
- kvm_vgic_sync_hwstate(vcpu);
- - preempt_enable();
- + migrate_enable();
- continue;
- }
-
- @@ -639,7 +639,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
-
- kvm_vgic_sync_hwstate(vcpu);
-
- - preempt_enable();
- + migrate_enable();
-
- ret = handle_exit(vcpu, run, ret);
- }
- diff --git a/arch/arm/kvm/psci.c b/arch/arm/kvm/psci.c
- index 443db0c43d7c..a08d7a93aebb 100644
- @@ -70,7 +70,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
- {
- 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 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
- 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 --git a/arch/arm/mach-at91/Kconfig b/arch/arm/mach-at91/Kconfig
- index 28656c2b54a0..3f501305ca26 100644
- @@ -99,6 +99,7 @@ config HAVE_AT91_USB_CLK
- config COMMON_CLK_AT91
- bool
- select COMMON_CLK
- + select MFD_SYSCON
-
- config HAVE_AT91_SMD
- bool
- diff --git a/arch/arm/mach-at91/at91rm9200.c b/arch/arm/mach-at91/at91rm9200.c
- index c1a7c6cc00e1..63b4fa25b48a 100644
- @@ -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 @@ static void __init at91rm9200_dt_device_init(void)
-
- of_platform_populate(NULL, of_default_bus_match_table, NULL, soc_dev);
-
- - arm_pm_idle = at91rm9200_idle;
- at91rm9200_pm_init();
- }
-
- diff --git a/arch/arm/mach-at91/at91sam9.c b/arch/arm/mach-at91/at91sam9.c
- index 7eb64f763034..cada2a6412b3 100644
- @@ -62,8 +62,6 @@ static void __init at91sam9_common_init(void)
- 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 --git a/arch/arm/mach-at91/generic.h b/arch/arm/mach-at91/generic.h
- index b0fa7dc7286d..28ca57a2060f 100644
- @@ -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 --git a/arch/arm/mach-at91/pm.c b/arch/arm/mach-at91/pm.c
- index 84eefbc2b4f9..bff0d062bf68 100644
- @@ -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 @@ static int at91_pm_verify_clocks(void)
- 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 @@ static int at91_pm_verify_clocks(void)
-
- 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 @@ static void at91_pm_suspend(suspend_state_t state)
- 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();
- }
- @@ -369,6 +371,21 @@ static __init void at91_dt_ramc(void)
- 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;
- @@ -415,13 +432,36 @@ static void __init at91_pm_sram_init(void)
- &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
- @@ -440,7 +480,7 @@ void __init at91rm9200_pm_init(void)
- 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)
- @@ -448,7 +488,7 @@ void __init at91sam9260_pm_init(void)
- 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)
- @@ -456,7 +496,7 @@ void __init at91sam9g45_pm_init(void)
- 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)
- @@ -464,5 +504,13 @@ void __init at91sam9x5_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;
- - 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 --git a/arch/arm/mach-at91/sama5.c b/arch/arm/mach-at91/sama5.c
- index d9cf6799aec0..df8fdf1cf66d 100644
- @@ -51,7 +51,7 @@ static void __init sama5_dt_device_init(void)
- 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 --git a/arch/arm/mach-exynos/platsmp.c b/arch/arm/mach-exynos/platsmp.c
- index 98a2c0cbb833..310dce500d3e 100644
- @@ -230,7 +230,7 @@ static void __iomem *scu_base_addr(void)
- 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 @@ static void exynos_secondary_init(unsigned int cpu)
- /*
- * 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 @@ static int exynos_boot_secondary(unsigned int cpu, struct task_struct *idle)
- * 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 @@ static int exynos_boot_secondary(unsigned int cpu, struct task_struct *idle)
-
- 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 @@ static int exynos_boot_secondary(unsigned int cpu, struct task_struct *idle)
- * calibrations, then wait for it to finish
- */
- fail:
- - spin_unlock(&boot_lock);
- + raw_spin_unlock(&boot_lock);
-
- return pen_release != -1 ? ret : 0;
- }
- diff --git a/arch/arm/mach-hisi/platmcpm.c b/arch/arm/mach-hisi/platmcpm.c
- index b5f8f5ffda79..9753a84df9c4 100644
- @@ -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 @@ static int hip04_boot_secondary(unsigned int l_cpu, struct task_struct *idle)
- 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 @@ static int hip04_boot_secondary(unsigned int l_cpu, struct task_struct *idle)
-
- out:
- hip04_cpu_table[cluster][cpu]++;
- - spin_unlock_irq(&boot_lock);
- + raw_spin_unlock_irq(&boot_lock);
-
- return 0;
- }
- @@ -162,11 +162,11 @@ static void hip04_cpu_die(unsigned int l_cpu)
- 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 @@ static void hip04_cpu_die(unsigned int l_cpu)
- }
-
- 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 @@ static int hip04_cpu_kill(unsigned int l_cpu)
- 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 @@ static int hip04_cpu_kill(unsigned int l_cpu)
- 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 @@ static int hip04_cpu_kill(unsigned int l_cpu)
- 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 --git a/arch/arm/mach-imx/Kconfig b/arch/arm/mach-imx/Kconfig
- index 8ceda2844c4f..08bcf8fb76f2 100644
- @@ -524,7 +524,7 @@ config SOC_IMX6Q
- 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 --git a/arch/arm/mach-omap2/omap-smp.c b/arch/arm/mach-omap2/omap-smp.c
- index 79e1f876d1c9..7e625c17f78e 100644
- @@ -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 @@ static void omap4_secondary_init(unsigned int cpu)
- /*
- * 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 @@ static int omap4_boot_secondary(unsigned int cpu, struct task_struct *idle)
- * 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 @@ static int omap4_boot_secondary(unsigned int cpu, struct task_struct *idle)
- * 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 --git a/arch/arm/mach-prima2/platsmp.c b/arch/arm/mach-prima2/platsmp.c
- index e46c91094dde..dcb3ed0c26da 100644
- @@ -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 @@ static void sirfsoc_secondary_init(unsigned int cpu)
- /*
- * 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 @@ static int sirfsoc_boot_secondary(unsigned int cpu, struct task_struct *idle)
- /* 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 @@ static int sirfsoc_boot_secondary(unsigned int cpu, struct task_struct *idle)
- * 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 --git a/arch/arm/mach-qcom/platsmp.c b/arch/arm/mach-qcom/platsmp.c
- index 9b00123a315d..0a49fe1bc8cf 100644
- @@ -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 @@ static void qcom_secondary_init(unsigned int cpu)
- /*
- * 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 @@ static int qcom_boot_secondary(unsigned int cpu, int (*func)(unsigned int))
- * 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 @@ static int qcom_boot_secondary(unsigned int cpu, int (*func)(unsigned int))
- * 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 --git a/arch/arm/mach-spear/platsmp.c b/arch/arm/mach-spear/platsmp.c
- index fd4297713d67..b0553b2c2d53 100644
- @@ -32,7 +32,7 @@ static void write_pen_release(int val)
- 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 @@ static void spear13xx_secondary_init(unsigned int cpu)
- /*
- * 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 @@ static int spear13xx_boot_secondary(unsigned int cpu, struct task_struct *idle)
- * 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 @@ static int spear13xx_boot_secondary(unsigned int cpu, struct task_struct *idle)
- * 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 --git a/arch/arm/mach-sti/platsmp.c b/arch/arm/mach-sti/platsmp.c
- index c4ad6eae67fa..e830b20b212f 100644
- @@ -35,7 +35,7 @@ static void write_pen_release(int val)
- 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 @@ static void sti_secondary_init(unsigned int cpu)
- /*
- * 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 @@ static int sti_boot_secondary(unsigned int cpu, struct task_struct *idle)
- * 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 @@ static int sti_boot_secondary(unsigned int cpu, struct task_struct *idle)
- * 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 --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
- index 0d20cd594017..a11dc6d8ca02 100644
- @@ -433,6 +433,9 @@ do_translation_fault(unsigned long addr, unsigned int fsr,
- 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;
-
- @@ -500,6 +503,9 @@ do_translation_fault(unsigned long addr, unsigned int fsr,
- 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 --git a/arch/arm/mm/highmem.c b/arch/arm/mm/highmem.c
- index d02f8187b1cc..542692dbd40a 100644
- @@ -34,6 +34,11 @@ static inline pte_t get_fixmap_pte(unsigned long vaddr)
- 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 @@ EXPORT_SYMBOL(kunmap);
-
- 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 @@ void *kmap_atomic(struct page *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
- /*
- @@ -93,7 +99,10 @@ void *kmap_atomic(struct page *page)
- * 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 @@ void __kunmap_atomic(void *kvaddr)
-
- 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 --git a/arch/arm/plat-versatile/platsmp.c b/arch/arm/plat-versatile/platsmp.c
- index 53feb90c840c..b4a8d54fc3f3 100644
- @@ -30,7 +30,7 @@ static void write_pen_release(int val)
- 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 @@ void versatile_secondary_init(unsigned int cpu)
- /*
- * 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 @@ int versatile_boot_secondary(unsigned int cpu, struct task_struct *idle)
- * 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 @@ int versatile_boot_secondary(unsigned int cpu, struct task_struct *idle)
- * 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 --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
- index 14cdc6dea493..9196cf82f7be 100644
- @@ -76,6 +76,7 @@ config ARM64
- 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_DOM0
-
- 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 --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
- index 90c7ff233735..5f4e89fbc290 100644
- @@ -49,6 +49,7 @@ struct thread_info {
- 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 @@ static inline struct thread_info *current_thread_info(void)
- #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 @@ static inline struct thread_info *current_thread_info(void)
- #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 @@ static inline struct thread_info *current_thread_info(void)
- #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 --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
- index 087cf9a65359..d74475928399 100644
- @@ -35,6 +35,7 @@ int main(void)
- 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 --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
- index dccd0c2e9023..a8d4d065fd81 100644
- @@ -378,11 +378,16 @@ ENDPROC(el1_sync)
- #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
- @@ -396,6 +401,7 @@ ENDPROC(el1_irq)
- 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
-
- @@ -640,6 +646,7 @@ ENDPROC(cpu_switch_to)
- */
- 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 --git a/arch/mips/Kconfig b/arch/mips/Kconfig
- index 8b0424abc84c..5422d4c0bbdf 100644
- @@ -2411,7 +2411,7 @@ config CPU_R4400_WORKAROUNDS
- #
- 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 --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
- index a017b23ee4aa..8d4d9270140f 100644
- @@ -454,8 +454,8 @@ int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu,
-
- 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 @@ static void kvm_mips_comparecount_func(unsigned long data)
- 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 --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
- index dfb1ee8c3e06..cdc3c20ef225 100644
- @@ -60,10 +60,11 @@ config LOCKDEP_SUPPORT
-
- 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 @@ config PPC
- 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 @@ menu "Kernel options"
-
- config HIGHMEM
- bool "High memory support"
- - depends on PPC32
- + depends on PPC32 && !PREEMPT_RT_FULL
-
- source kernel/Kconfig.hz
- source kernel/Kconfig.preempt
- diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
- index a92d95aee42d..20376580583f 100644
- @@ -286,7 +286,7 @@ struct kvmppc_vcore {
- 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;
- @@ -627,7 +627,7 @@ struct kvm_vcpu_arch {
- u8 prodded;
- u32 last_inst;
-
- - wait_queue_head_t *wqp;
- + struct swait_queue_head *wqp;
- struct kvmppc_vcore *vcore;
- int ret;
- int trap;
- diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
- index 7efee4a3240b..40e6fa1b85b2 100644
- @@ -42,6 +42,8 @@ struct thread_info {
- 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 @@ static inline struct thread_info *current_thread_info(void)
- #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 @@ static inline struct thread_info *current_thread_info(void)
- #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 @@ static inline struct thread_info *current_thread_info(void)
- #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 --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
- index 40da69163d51..bd040815334b 100644
- @@ -160,6 +160,7 @@ int main(void)
- 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 --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
- index 2405631e91a2..c21b4b42eaa0 100644
- @@ -818,7 +818,14 @@ user_exc_return: /* r10 contains MSR_KERNEL here */
- 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 @@ user_exc_return: /* r10 contains MSR_KERNEL here */
- */
- 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 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX)
- #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 @@ do_resched: /* r10 contains MSR_KERNEL here */
- 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 --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
- index f6fd0332c3a2..96235fe0a581 100644
- @@ -683,7 +683,7 @@ _GLOBAL(ret_from_except_lite)
- #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 @@ _GLOBAL(ret_from_except_lite)
-
- #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 @@ _GLOBAL(ret_from_except_lite)
- /* 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 --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
- index 290559df1e8b..070afa6da35d 100644
- @@ -614,6 +614,7 @@ void irq_ctx_init(void)
- }
- }
-
- +#ifndef CONFIG_PREEMPT_RT_FULL
- void do_softirq_own_stack(void)
- {
- struct thread_info *curtp, *irqtp;
- @@ -631,6 +632,7 @@ void do_softirq_own_stack(void)
- if (irqtp->flags)
- set_bits(irqtp->flags, &curtp->flags);
- }
- +#endif
-
- irq_hw_number_t virq_to_hw(unsigned int virq)
- {
- diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
- index df4efa304b2c..9cb0c2f6e7ac 100644
- @@ -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 @@ _GLOBAL(call_do_softirq)
- stw r10,THREAD+KSP_LIMIT(r2)
- mtlr r0
- blr
- +#endif
-
- /*
- * void call_do_irq(struct pt_regs *regs, struct thread_info *irqtp);
- diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
- index db475d41b57a..96b7ef80e05d 100644
- @@ -30,6 +30,7 @@
-
- .text
-
- +#ifndef CONFIG_PREEMPT_RT_FULL
- _GLOBAL(call_do_softirq)
- mflr r0
- std r0,16(r1)
- @@ -40,6 +41,7 @@ _GLOBAL(call_do_softirq)
- ld r0,16(r1)
- mtlr r0
- blr
- +#endif
-
- _GLOBAL(call_do_irq)
- mflr r0
- diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
- index c2024ac9d4e8..2303788da7e1 100644
- @@ -172,6 +172,7 @@ config KVM_E500MC
- 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 --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
- index 428563b195c3..4c42c3935025 100644
- @@ -114,11 +114,11 @@ static bool kvmppc_ipi_thread(int cpu)
- 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 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
- 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++;
- }
- }
- @@ -1453,7 +1453,7 @@ static struct kvmppc_vcore *kvmppc_vcore_create(struct kvm *kvm, int core)
- 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;
- @@ -2525,10 +2525,9 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
- {
- 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
- @@ -2542,7 +2541,7 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
- }
-
- if (!do_sleep) {
- - finish_wait(&vc->wq, &wait);
- + finish_swait(&vc->wq, &wait);
- return;
- }
-
- @@ -2550,7 +2549,7 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
- 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);
- @@ -2606,7 +2605,7 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
- 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 --git a/arch/powerpc/platforms/ps3/device-init.c b/arch/powerpc/platforms/ps3/device-init.c
- index 3f175e8aedb4..c4c02f91904c 100644
- @@ -752,7 +752,7 @@ static int ps3_notification_read_write(struct ps3_notification_device *dev,
- }
- 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 --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
- index e9a983f40a24..bbdc539fb3c6 100644
- @@ -427,7 +427,7 @@ struct kvm_s390_irq_payload {
- 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 --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
- index 6a75352f453c..cc862c486002 100644
- @@ -868,13 +868,13 @@ int kvm_s390_handle_wait(struct kvm_vcpu *vcpu)
-
- 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 --git a/arch/sh/kernel/irq.c b/arch/sh/kernel/irq.c
- index 6c0378c0b8b5..abd58b4dff97 100644
- @@ -147,6 +147,7 @@ void irq_ctx_exit(int cpu)
- hardirq_ctx[cpu] = NULL;
- }
-
- +#ifndef CONFIG_PREEMPT_RT_FULL
- void do_softirq_own_stack(void)
- {
- struct thread_info *curctx;
- @@ -174,6 +175,7 @@ void do_softirq_own_stack(void)
- "r5", "r6", "r7", "r8", "r9", "r15", "t", "pr"
- );
- }
- +#endif
- #else
- static inline void handle_one_irq(unsigned int irq)
- {
- diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
- index 94f4ac21761b..d7c369d061cf 100644
- @@ -189,12 +189,10 @@ config NR_CPUS
- 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 --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c
- index bfbde8c4ffb2..62e7e06013c5 100644
- @@ -854,6 +854,7 @@ void __irq_entry handler_irq(int pil, struct pt_regs *regs)
- 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 @@ void do_softirq_own_stack(void)
- __asm__ __volatile__("mov %0, %%sp"
- : : "r" (orig_sp));
- }
- +#endif
-
- #ifdef CONFIG_HOTPLUG_CPU
- void fixup_irqs(void)
- diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
- index 0ef2cdd11616..2eaae0f372fa 100644
- @@ -17,6 +17,7 @@ config X86_64
- ### 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
- @@ -213,8 +214,11 @@ config ARCH_MAY_HAVE_PC_FDC
- 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
- @@ -849,7 +853,7 @@ config IOMMU_HELPER
- 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 --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
- index 3633ad6145c5..c6d5458ee7f9 100644
- @@ -383,14 +383,14 @@ static int ecb_encrypt(struct blkcipher_desc *desc,
- 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 @@ static int ecb_decrypt(struct blkcipher_desc *desc,
- 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 @@ static int cbc_encrypt(struct blkcipher_desc *desc,
- 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 @@ static int cbc_decrypt(struct blkcipher_desc *desc,
- 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 @@ static int ctr_crypt(struct blkcipher_desc *desc,
- 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 --git a/arch/x86/crypto/cast5_avx_glue.c b/arch/x86/crypto/cast5_avx_glue.c
- index 8648158f3916..d7699130ee36 100644
- @@ -59,7 +59,7 @@ static inline void cast5_fpu_end(bool fpu_enabled)
- 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 @@ static int ecb_crypt(struct blkcipher_desc *desc, struct blkcipher_walk *walk,
- 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 @@ static int ecb_crypt(struct blkcipher_desc *desc, struct blkcipher_walk *walk,
- } 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 unsigned int __cbc_decrypt(struct blkcipher_desc *desc,
- 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 @@ static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
- 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 unsigned int __ctr_crypt(struct blkcipher_desc *desc,
- 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 @@ static int ctr_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
- 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 --git a/arch/x86/crypto/glue_helper.c b/arch/x86/crypto/glue_helper.c
- index 6a85598931b5..3a506ce7ed93 100644
- @@ -39,7 +39,7 @@ static int __glue_ecb_crypt_128bit(const struct common_glue_ctx *gctx,
- 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 @@ static int __glue_ecb_crypt_128bit(const struct common_glue_ctx *gctx,
- 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 @@ static int __glue_ecb_crypt_128bit(const struct common_glue_ctx *gctx,
- }
-
- done:
- + glue_fpu_end(fpu_enabled);
- err = blkcipher_walk_done(desc, walk, nbytes);
- }
-
- - glue_fpu_end(fpu_enabled);
- return err;
- }
-
- @@ -194,7 +194,7 @@ int glue_cbc_decrypt_128bit(const struct common_glue_ctx *gctx,
- 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 @@ int glue_cbc_decrypt_128bit(const struct common_glue_ctx *gctx,
-
- 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 @@ int glue_ctr_crypt_128bit(const struct common_glue_ctx *gctx,
- 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 @@ int glue_ctr_crypt_128bit(const struct common_glue_ctx *gctx,
-
- 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 @@ int glue_xts_crypt_128bit(const struct common_glue_ctx *gctx,
- 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 @@ int glue_xts_crypt_128bit(const struct common_glue_ctx *gctx,
-
- /* 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 --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
- index 1a4477cedc49..75a301b6a5b6 100644
- @@ -220,7 +220,7 @@ long syscall_trace_enter(struct pt_regs *regs)
-
- #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 @@ static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags)
- /* 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 --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
- index ae678ad128a9..3bcef8bdb911 100644
- @@ -278,8 +278,24 @@ END(ret_from_exception)
- 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 --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
- index 952b23b5d4e9..459a68cffcc2 100644
- @@ -607,7 +607,23 @@ GLOBAL(retint_user)
- 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:
- @@ -897,6 +913,7 @@ END(native_load_gs_index)
- jmp 2b
- .previous
-
- +#ifndef CONFIG_PREEMPT_RT_FULL
- /* Call softirq on interrupt stack. Interrupts are off. */
- ENTRY(do_softirq_own_stack)
- pushq %rbp
- @@ -909,6 +926,7 @@ ENTRY(do_softirq_own_stack)
- 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 --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
- index 01bcde84d3e4..6f432adc55cd 100644
- @@ -79,17 +79,46 @@ static __always_inline void __preempt_count_sub(int val)
- * 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 --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h
- index 2138c9ae19ee..3f5b4ee2e2c1 100644
- @@ -23,6 +23,19 @@ typedef struct {
- 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 --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h
- index 58505f01962f..02fa39652cd6 100644
- @@ -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 @@ static __always_inline void boot_init_stack_canary(void)
- * 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 --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
- index c7b551028740..ddb63bd90e3c 100644
- @@ -58,6 +58,8 @@ struct thread_info {
- __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 @@ struct thread_info {
- #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 @@ struct thread_info {
- #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 @@ struct thread_info {
- #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 --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h
- index fc808b83fccb..ebb40118abf5 100644
- @@ -615,9 +615,9 @@ struct bau_control {
- 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 @@ static inline int atom_asr(short i, struct atomic_short *v)
- * 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 --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
- index ea7074784cc4..01ec643ce66e 100644
- @@ -492,7 +492,7 @@ struct uv_blade_info {
- 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 --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
- index a1e4a6c3f394..86adbf86f366 100644
- @@ -87,7 +87,9 @@ static u64 acpi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE;
- * ->ioapic_mutex
- * ->ioapic_lock
- */
- +#ifdef CONFIG_X86_IO_APIC
- static DEFINE_MUTEX(acpi_ioapic_lock);
- +#endif
-
- /* --------------------------------------------------------------------------
- Boot-time Configuration
- diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
- index fc91c98bee01..29c4f1b078a1 100644
- @@ -1711,7 +1711,8 @@ static bool io_apic_level_ack_pending(struct mp_chip_data *data)
- 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 --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
- index 4a139465f1d4..ad2afff02b36 100644
- @@ -947,7 +947,7 @@ void __init uv_system_init(void)
- 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 --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
- index 439df975bc7a..b7954ddd6a0a 100644
- @@ -32,6 +32,7 @@ void common(void) {
- 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 @@ void common(void) {
-
- BLANK();
- DEFINE(PTREGS_SIZE, sizeof(struct pt_regs));
- + DEFINE(_PREEMPT_ENABLED, PREEMPT_ENABLED);
- }
- diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
- index 7e8a736d09db..430a4ec07811 100644
- @@ -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 @@ void mce_log_therm_throt_event(__u64 status)
- 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_default(unsigned long interval)
-
- 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 @@ static void mce_timer_fn(unsigned long data)
-
- done:
- __this_cpu_write(mce_next_interval, iv);
- - __restart_timer(t, iv);
- + return __restart_timer(timer, iv);
- }
-
- /*
- @@ -1301,7 +1289,7 @@ static void mce_timer_fn(unsigned long data)
- */
- 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 @@ static void mce_timer_delete_all(void)
- 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 void mce_do_trigger(struct work_struct *work)
-
- 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 @@ static DECLARE_WORK(mce_trigger_work, mce_do_trigger);
- */
- 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 __mcheck_cpu_clear_vendor(struct cpuinfo_x86 *c)
- }
- }
-
- -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 @@ static void mce_start_timer(unsigned int cpu, struct timer_list *t)
-
- 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 @@ static void mce_disable_cpu(void *h)
- 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 @@ static void mce_reenable_cpu(void *h)
- 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 @@ static int
- 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 @@ mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
- 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 @@ static __init int mcheck_init_device(void)
- 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 --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
- index ed446bdcbf31..d2ac364e2118 100644
- @@ -117,7 +117,7 @@ static struct perf_pmu_events_attr event_attr_##v = { \
- };
-
- 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 @@ static enum hrtimer_restart rapl_hrtimer_handle(struct hrtimer *hrtimer)
- 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 @@ static void rapl_pmu_event_start(struct perf_event *event, int mode)
- 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 @@ static void rapl_pmu_event_stop(struct perf_event *event, int mode)
- 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 @@ static void rapl_pmu_event_stop(struct perf_event *event, int mode)
- 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 @@ static int rapl_pmu_event_add(struct perf_event *event, int mode)
- 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 @@ static int rapl_cpu_prepare(int cpu)
- 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 --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c
- index 464ffd69b92e..00db1aad1548 100644
- @@ -42,7 +42,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
- 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 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
- break;
- touch_nmi_watchdog();
- }
- - put_cpu();
- + put_cpu_light();
- }
- EXPORT_SYMBOL(dump_trace);
-
- diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
- index 5f1c6266eb30..c331e3fef465 100644
- @@ -152,7 +152,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
- 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 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
- * 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 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
- 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 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
- 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 --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
- index 38da8f29a9c8..ce71f7098f15 100644
- @@ -128,6 +128,7 @@ void irq_ctx_init(int cpu)
- 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 @@ void do_softirq_own_stack(void)
-
- call_on_stack(__do_softirq, isp);
- }
- +#endif
-
- bool handle_irq(struct irq_desc *desc, struct pt_regs *regs)
- {
- diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
- index 32187f8a49b4..1f456f1e06f8 100644
- @@ -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 @@ static void kvm_io_delay(void)
-
- 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 @@ void kvm_async_pf_task_wait(u32 token)
- 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 @@ void kvm_async_pf_task_wait(u32 token)
- 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;
-
- @@ -168,7 +169,7 @@ void kvm_async_pf_task_wait(u32 token)
- rcu_irq_enter();
- }
- if (!n.halted)
- - finish_wait(&n.wq, &wait);
- + finish_swait(&n.wq, &wait);
-
- rcu_irq_exit();
- return;
- @@ -180,8 +181,8 @@ static void apf_task_wake_one(struct kvm_task_sleep_node *n)
- 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)
- @@ -191,14 +192,14 @@ static void apf_task_wake_all(void)
- 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);
- }
- }
-
- @@ -214,7 +215,7 @@ void kvm_async_pf_task_wake(u32 token)
- }
-
- again:
- - spin_lock(&b->lock);
- + raw_spin_lock(&b->lock);
- n = _find_apf_task(b, token);
- if (!n) {
- /*
- @@ -227,17 +228,17 @@ void kvm_async_pf_task_wake(u32 token)
- * 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);
- @@ -488,7 +489,7 @@ void __init kvm_guest_init(void)
- 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 --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
- index 697f90db0e37..424aec4a4c71 100644
- @@ -231,7 +231,7 @@ pci_serr_error(unsigned char reason, struct pt_regs *regs)
- #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 @@ io_check_error(unsigned char reason, struct pt_regs *regs)
- 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 @@ unknown_nmi_error(unsigned char reason, struct pt_regs *regs)
-
- 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 --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
- index 9f950917528b..4dd4beae917a 100644
- @@ -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 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp)
- }
- 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 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
- 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 --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
- index 9a16932c7258..219ffb9ba3a9 100644
- @@ -730,6 +730,7 @@ static int crashing_cpu;
- 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)
- {
- @@ -792,6 +793,9 @@ void nmi_shootdown_cpus(nmi_shootdown_cb callback)
-
- 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);
- @@ -800,6 +804,22 @@ void nmi_shootdown_cpus(nmi_shootdown_cb callback)
-
- /* 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 --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
- index 1c96f09367ae..ffb6d9859122 100644
- @@ -1195,7 +1195,7 @@ static void apic_update_lvtt(struct kvm_lapic *apic)
- 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 @@ static void apic_timer_expired(struct kvm_lapic *apic)
- 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 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu)
- 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 --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
- index f973cfa8ff4f..b63350721623 100644
- @@ -5836,6 +5836,13 @@ int kvm_arch_init(void *opaque)
- 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 --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c
- index a6d739258137..bd24ba1c4a86 100644
- @@ -32,10 +32,11 @@ EXPORT_SYMBOL(kunmap);
- */
- 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 @@ void *kmap_atomic_prot(struct page *page, pgprot_t prot)
- 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 @@ void __kunmap_atomic(void *kvaddr)
- * 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 @@ void __kunmap_atomic(void *kvaddr)
- #endif
-
- pagefault_enable();
- - preempt_enable();
- + preempt_enable_nort();
- }
- EXPORT_SYMBOL(__kunmap_atomic);
-
- diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c
- index 9c0ff045fdd4..dd25dd1671b6 100644
- @@ -56,6 +56,7 @@ EXPORT_SYMBOL_GPL(iomap_free);
-
- 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 @@ void *kmap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot)
- 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 @@ iounmap_atomic(void __iomem *kvaddr)
- * 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 --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
- index 79377e2a7bcd..dca36c1f1966 100644
- @@ -209,7 +209,15 @@ static void cpa_flush_array(unsigned long *start, int numpages, int cache,
- int in_flags, struct page **pages)
- {
- unsigned int i, level;
- +#ifdef CONFIG_PREEMPT
- + /*
- + * Avoid wbinvd() because it causes latencies on all CPUs,
- + * regardless of any CPU isolation that may be in effect.
- + */
- + unsigned long do_wbinvd = 0;
- +#else
- unsigned long do_wbinvd = cache && numpages >= 1024; /* 4M threshold */
- +#endif
-
- BUG_ON(irqs_disabled());
-
- diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
- index 3b6ec42718e4..7871083de089 100644
- @@ -714,9 +714,9 @@ static void destination_plugged(struct bau_desc *bau_desc,
-
- 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 @@ static void destination_timeout(struct bau_desc *bau_desc,
-
- 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 @@ static void disable_for_period(struct bau_control *bcp, struct ptc_stats *stat)
- 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 @@ static void disable_for_period(struct bau_control *bcp, struct ptc_stats *stat)
- }
- }
- }
- - 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 record_send_stats(cycles_t time1, cycles_t time2,
- */
- 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 @@ static int check_enable(struct bau_control *bcp, struct ptc_stats *stat)
- 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 @@ static int check_enable(struct bau_control *bcp, struct ptc_stats *stat)
- 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 @@ static void __init init_per_cpu_tunables(void)
- 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 --git a/arch/x86/platform/uv/uv_time.c b/arch/x86/platform/uv/uv_time.c
- index 2b158a9fa1d7..5e0b122620cb 100644
- @@ -57,7 +57,7 @@ static DEFINE_PER_CPU(struct clock_event_device, cpu_ced);
-
- /* 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 @@ static __init int uv_rtc_allocate_timers(void)
- 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 @@ static int uv_rtc_set_timer(int cpu, u64 expires)
- 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 @@ static int uv_rtc_set_timer(int cpu, u64 expires)
- 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 @@ static int uv_rtc_unset_timer(int cpu, int force)
- 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 @@ static int uv_rtc_unset_timer(int cpu, int force)
- 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 int uv_rtc_unset_timer(int cpu, int force)
- 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 --git a/block/blk-core.c b/block/blk-core.c
- index f5f1a55703ae..75a76bcc7ac0 100644
- @@ -125,6 +125,9 @@ void blk_rq_init(struct request_queue *q, struct request *rq)
-
- 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 @@ EXPORT_SYMBOL(blk_start_queue_async);
- **/
- void blk_start_queue(struct request_queue *q)
- {
- - WARN_ON(!in_interrupt() && !irqs_disabled());
- + WARN_ON_NONRT(!in_interrupt() && !irqs_disabled());
-
- queue_flag_clear(QUEUE_FLAG_STOPPED, q);
- __blk_run_queue(q);
- @@ -659,7 +662,7 @@ int blk_queue_enter(struct request_queue *q, gfp_t gfp)
- 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 @@ static void blk_queue_usage_counter_release(struct percpu_ref *ref)
- 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 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
- 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.
- @@ -3222,7 +3225,7 @@ static void queue_unplugged(struct request_queue *q, unsigned int depth,
- 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)
- @@ -3270,7 +3273,6 @@ EXPORT_SYMBOL(blk_check_plugged);
- 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;
- @@ -3290,11 +3292,6 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
- 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);
- @@ -3307,7 +3304,7 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
- queue_unplugged(q, depth, from_schedule);
- q = rq->q;
- depth = 0;
- - spin_lock(q->queue_lock);
- + spin_lock_irq(q->queue_lock);
- }
-
- /*
- @@ -3334,8 +3331,6 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
- */
- if (q)
- queue_unplugged(q, depth, from_schedule);
- -
- - local_irq_restore(flags);
- }
-
- void blk_finish_plug(struct blk_plug *plug)
- diff --git a/block/blk-ioc.c b/block/blk-ioc.c
- index 381cb50a673c..dc8785233d94 100644
- @@ -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 @@ static void ioc_release_fn(struct work_struct *work)
- 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 @@ void put_io_context_active(struct io_context *ioc)
- spin_unlock(icq->q->queue_lock);
- } else {
- spin_unlock_irqrestore(&ioc->lock, flags);
- - cpu_relax();
- + cpu_chill();
- goto retry;
- }
- }
- diff --git a/block/blk-iopoll.c b/block/blk-iopoll.c
- index 0736729d6494..3e21e31d0d7e 100644
- @@ -35,6 +35,7 @@ void blk_iopoll_sched(struct blk_iopoll *iop)
- 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 @@ static void blk_iopoll_softirq(struct softirq_action *h)
- __raise_softirq_irqoff(BLOCK_IOPOLL_SOFTIRQ);
-
- local_irq_enable();
- + preempt_check_resched_rt();
- }
-
- /**
- @@ -201,6 +203,7 @@ static int blk_iopoll_cpu_notify(struct notifier_block *self,
- this_cpu_ptr(&blk_cpu_iopoll));
- __raise_softirq_irqoff(BLOCK_IOPOLL_SOFTIRQ);
- local_irq_enable();
- + preempt_check_resched_rt();
- }
-
- return NOTIFY_OK;
- diff --git a/block/blk-mq-cpu.c b/block/blk-mq-cpu.c
- index bb3ed488f7b5..628c6c13c482 100644
- @@ -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 @@ static int blk_mq_main_cpu_notify(struct notifier_block *self,
- 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 @@ static int blk_mq_main_cpu_notify(struct notifier_block *self,
- break;
- }
-
- - raw_spin_unlock(&blk_mq_cpu_notify_lock);
- + spin_unlock(&blk_mq_cpu_notify_lock);
- return ret;
- }
-
- @@ -41,16 +44,16 @@ void blk_mq_register_cpu_notifier(struct blk_mq_cpu_notifier *notifier)
- {
- 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 --git a/block/blk-mq.c b/block/blk-mq.c
- index 0d1af3e44efb..e4fc80184dd8 100644
- @@ -92,7 +92,7 @@ EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_start);
-
- 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 @@ void blk_mq_unfreeze_queue(struct request_queue *q)
- 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 @@ void blk_mq_wake_waiters(struct request_queue *q)
- * 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 @@ static void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
- 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 @@ void blk_mq_end_request(struct request *rq, int error)
- }
- 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 @@ static void __blk_mq_complete_request_remote(void *data)
- 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 @@ static void blk_mq_ipi_complete_request(struct request *rq)
- 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)
- @@ -862,14 +882,14 @@ void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
- 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),
- @@ -1616,7 +1636,7 @@ static int blk_mq_hctx_notify(void *data, unsigned long action,
- {
- 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 --git a/block/blk-mq.h b/block/blk-mq.h
- index 713820b47b31..3cb6feb4fe23 100644
- @@ -74,7 +74,10 @@ struct blk_align_bitmap {
- 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,
- */
- 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 --git a/block/blk-softirq.c b/block/blk-softirq.c
- index 53b1737e978d..81c3c0a62edf 100644
- @@ -51,6 +51,7 @@ static void trigger_softirq(void *data)
- raise_softirq_irqoff(BLOCK_SOFTIRQ);
-
- local_irq_restore(flags);
- + preempt_check_resched_rt();
- }
-
- /*
- @@ -93,6 +94,7 @@ static int blk_cpu_notify(struct notifier_block *self, unsigned long action,
- 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 @@ void __blk_complete_request(struct request *req)
- goto do_local;
-
- local_irq_restore(flags);
- + preempt_check_resched_rt();
- }
-
- /**
- diff --git a/block/bounce.c b/block/bounce.c
- index 1cb5dd3a5da1..2f1ec8a67cbe 100644
- @@ -55,11 +55,11 @@ static void bounce_copy_vec(struct bio_vec *to, unsigned char *vfrom)
- 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 --git a/crypto/algapi.c b/crypto/algapi.c
- index eb58b73ca925..ee228adf2dac 100644
- @@ -732,13 +732,13 @@ EXPORT_SYMBOL_GPL(crypto_spawn_tfm2);
-
- 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 --git a/crypto/api.c b/crypto/api.c
- index bbc147cb5dec..bc1a848f02ec 100644
- @@ -31,7 +31,7 @@ EXPORT_SYMBOL_GPL(crypto_alg_list);
- 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 crypto_probing_notify(unsigned long val, void *v)
- {
- 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 --git a/crypto/internal.h b/crypto/internal.h
- index 00e42a3ed814..2e85551e235f 100644
- @@ -47,7 +47,7 @@ struct crypto_larval {
-
- 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 int crypto_is_moribund(struct crypto_alg *alg)
-
- 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 --git a/drivers/acpi/acpica/acglobal.h b/drivers/acpi/acpica/acglobal.h
- index faa97604d878..941497f31cf0 100644
- @@ -116,7 +116,7 @@ ACPI_GLOBAL(u8, acpi_gbl_global_lock_pending);
- * 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 --git a/drivers/acpi/acpica/hwregs.c b/drivers/acpi/acpica/hwregs.c
- index 3cf77afd142c..dc32e72132f1 100644
- @@ -269,14 +269,14 @@ acpi_status acpi_hw_clear_acpi_status(void)
- 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 --git a/drivers/acpi/acpica/hwxface.c b/drivers/acpi/acpica/hwxface.c
- index b2e50d8007fe..ff007084dc48 100644
- @@ -374,7 +374,7 @@ acpi_status acpi_write_bit_register(u32 register_id, u32 value)
- 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 @@ acpi_status acpi_write_bit_register(u32 register_id, u32 value)
-
- 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 --git a/drivers/acpi/acpica/utmutex.c b/drivers/acpi/acpica/utmutex.c
- index ce406e39b669..41a75eb3ae9d 100644
- @@ -88,7 +88,7 @@ acpi_status acpi_ut_mutex_initialize(void)
- 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 @@ void acpi_ut_mutex_terminate(void)
- /* 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 --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c
- index 18de4c457068..dfecf14df732 100644
- @@ -678,9 +678,9 @@ unsigned int ata_sff_data_xfer_noirq(struct ata_device *dev, unsigned char *buf,
- 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 @@ static void ata_pio_sector(struct ata_queued_cmd *qc)
- 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 @@ static void ata_pio_sector(struct ata_queued_cmd *qc)
- 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 @@ static int __atapi_pio_bytes(struct ata_queued_cmd *qc, unsigned int bytes)
- 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 @@ static int __atapi_pio_bytes(struct ata_queued_cmd *qc, unsigned int bytes)
- 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 --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
- index 502406c9e6e1..91d909148688 100644
- @@ -520,6 +520,8 @@ static struct zram_meta *zram_meta_alloc(char *pool_name, u64 disksize)
- goto out_error;
- }
-
- + zram_meta_init_table_locks(meta, disksize);
- +
- return meta;
-
- out_error:
- @@ -568,12 +570,12 @@ static int zram_decompress_page(struct zram *zram, char *mem, u32 index)
- 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]);
- memset(mem, 0, PAGE_SIZE);
- return 0;
- }
- @@ -584,7 +586,7 @@ static int zram_decompress_page(struct zram *zram, char *mem, u32 index)
- 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 @@ static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec,
- 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 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
- 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 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
- * 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 @@ static void zram_bio_discard(struct zram *zram, u32 index,
- }
-
- 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 @@ static void zram_slot_free_notify(struct block_device *bdev,
- 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 --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h
- index 8e92339686d7..9e3e953d680e 100644
- @@ -72,6 +72,9 @@ enum zram_pageflags {
- 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 @@ struct zram {
- */
- 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 --git a/drivers/char/random.c b/drivers/char/random.c
- index 1822472dffab..46c0e27cf27f 100644
- @@ -260,6 +260,7 @@
- #include <linux/irq.h>
- #include <linux/syscalls.h>
- #include <linux/completion.h>
- +#include <linux/locallock.h>
-
- #include <asm/processor.h>
- #include <asm/uaccess.h>
- @@ -799,8 +800,6 @@ static void add_timer_randomness(struct timer_rand_state *state, unsigned num)
- } sample;
- long delta, delta2, delta3;
-
- - preempt_disable();
- -
- sample.jiffies = jiffies;
- sample.cycles = random_get_entropy();
- sample.num = num;
- @@ -841,7 +840,6 @@ static void add_timer_randomness(struct timer_rand_state *state, unsigned num)
- */
- 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 +892,27 @@ static __u32 get_reg(struct fast_pool *f, struct pt_regs *regs)
- 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);
- @@ -1800,6 +1797,7 @@ int random_int_secret_init(void)
-
- static DEFINE_PER_CPU(__u32 [MD5_DIGEST_WORDS], get_random_int_hash)
- __aligned(sizeof(unsigned long));
- +static DEFINE_LOCAL_IRQ_LOCK(hash_entropy_int_lock);
-
- /*
- * Get a random word for internal kernel use only. Similar to urandom but
- @@ -1815,12 +1813,12 @@ unsigned int get_random_int(void)
- if (arch_get_random_int(&ret))
- return ret;
-
- - hash = get_cpu_var(get_random_int_hash);
- + hash = get_locked_var(hash_entropy_int_lock, get_random_int_hash);
-
- hash[0] += current->pid + jiffies + random_get_entropy();
- md5_transform(hash, random_int_secret);
- ret = hash[0];
- - put_cpu_var(get_random_int_hash);
- + put_locked_var(hash_entropy_int_lock, get_random_int_hash);
-
- return ret;
- }
- @@ -1837,12 +1835,12 @@ unsigned long get_random_long(void)
- if (arch_get_random_long(&ret))
- return ret;
-
- - hash = get_cpu_var(get_random_int_hash);
- + hash = get_locked_var(hash_entropy_int_lock, get_random_int_hash);
-
- hash[0] += current->pid + jiffies + random_get_entropy();
- md5_transform(hash, random_int_secret);
- ret = *(unsigned long *)hash;
- - put_cpu_var(get_random_int_hash);
- + put_locked_var(hash_entropy_int_lock, get_random_int_hash);
-
- return ret;
- }
- diff --git a/drivers/clk/at91/clk-generated.c b/drivers/clk/at91/clk-generated.c
- index abc80949e1dd..4ad3298eb372 100644
- @@ -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 @@ struct clk_generated {
- 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;
- -
- - 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);
- + unsigned long flags;
- +
- + 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 const struct clk_ops generated_ops = {
- */
- 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 void clk_generated_startup(struct clk_generated *gck)
- }
-
- 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 @@ at91_clk_register_generated(struct at91_pmc *pmc, const char *name,
-
- 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 @@ at91_clk_register_generated(struct at91_pmc *pmc, const char *name,
- 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 @@ void __init of_sama5d2_clk_generated_setup(struct device_node *np,
- 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 @@ void __init of_sama5d2_clk_generated_setup(struct device_node *np,
- 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 @@ void __init of_sama5d2_clk_generated_setup(struct device_node *np,
- 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 --git a/drivers/clk/at91/clk-h32mx.c b/drivers/clk/at91/clk-h32mx.c
- index a165230e7eda..8e20c8a76db7 100644
- @@ -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 @@ static unsigned long clk_sama5d4_h32mx_recalc_rate(struct clk_hw *hw,
- 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 @@ static int clk_sama5d4_h32mx_set_rate(struct clk_hw *hw, unsigned long rate,
- 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 @@ static const struct clk_ops h32mx_ops = {
- .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 @@ void __init of_sama5d4_clk_h32mx_setup(struct device_node *np,
- 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 @@ void __init of_sama5d4_clk_h32mx_setup(struct device_node *np,
-
- 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 --git a/drivers/clk/at91/clk-main.c b/drivers/clk/at91/clk-main.c
- index fd7247deabdc..4bfc94d6c26e 100644
- @@ -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_main_rc_osc {
-
- 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 int clk_main_osc_prepare(struct clk_hw *hw)
- 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 @@ static void clk_main_osc_unprepare(struct clk_hw *hw)
- 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 const struct clk_ops main_osc_ops = {
- };
-
- 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 @@ at91_clk_register_main_osc(struct at91_pmc *pmc,
- 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 int clk_main_rc_osc_prepare(struct clk_hw *hw)
- 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;
- +
- + regmap_read(regmap, AT91_CKGR_MOR, &mor);
-
- - if (!(tmp & AT91_PMC_MOSCRCEN))
- + 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;
-
- - return !!((pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_MOSCRCS) &&
- - (pmc_read(pmc, AT91_CKGR_MOR) & AT91_PMC_MOSCRCEN));
- + regmap_read(regmap, AT91_CKGR_MOR, &mor);
- + regmap_read(regmap, AT91_PMC_SR, &status);
- +
- + 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 const struct clk_ops main_rc_osc_ops = {
- };
-
- 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 @@ at91_clk_register_main_rc_osc(struct at91_pmc *pmc,
- 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 @@ static int clk_main_probe_frequency(struct at91_pmc *pmc)
- 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 @@ static unsigned long clk_rm9200_main_recalc_rate(struct clk_hw *hw,
- {
- 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 const struct clk_ops rm9200_main_ops = {
- };
-
- 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 @@ at91_clk_register_rm9200_main(struct at91_pmc *pmc,
- 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 @@ at91_clk_register_rm9200_main(struct at91_pmc *pmc,
- 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 @@ at91_clk_register_rm9200_main(struct at91_pmc *pmc,
- 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 @@ static unsigned long clk_sam9x5_main_recalc_rate(struct clk_hw *hw,
- {
- 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 int clk_sam9x5_main_set_parent(struct clk_hw *hw, u8 index)
- 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 const struct clk_ops sam9x5_main_ops = {
- };
-
- 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 @@ at91_clk_register_sam9x5_main(struct at91_pmc *pmc,
- 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 --git a/drivers/clk/at91/clk-master.c b/drivers/clk/at91/clk-master.c
- index 620ea323356b..7d4a1864ea7c 100644
- @@ -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_layout {
-
- 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 @@ static int clk_master_is_prepared(struct clk_hw *hw)
- {
- 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 @@ static unsigned long clk_master_recalc_rate(struct clk_hw *hw,
- 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 unsigned long clk_master_recalc_rate(struct clk_hw *hw,
- 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 const struct clk_ops master_ops = {
- };
-
- 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 @@ at91_clk_register_master(struct at91_pmc *pmc, unsigned int irq,
- 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 @@ of_at91_clk_master_get_characteristics(struct device_node *np)
- }
-
- 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 @@ of_at91_clk_master_setup(struct device_node *np, struct at91_pmc *pmc,
- 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 @@ of_at91_clk_master_setup(struct device_node *np, struct at91_pmc *pmc,
- 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 --git a/drivers/clk/at91/clk-peripheral.c b/drivers/clk/at91/clk-peripheral.c
- index 58f3b568e9cb..d69cd2a121b1 100644
- @@ -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_peripheral {
-
- 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 @@ struct clk_sam9x5_peripheral {
- 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 @@ static int clk_peripheral_enable(struct clk_hw *hw)
- 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 @@ static void clk_peripheral_disable(struct clk_hw *hw)
- 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 const struct clk_ops peripheral_ops = {
- };
-
- 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 @@ at91_clk_register_peripheral(struct at91_pmc *pmc, const char *name,
-
- 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 void clk_sam9x5_peripheral_autodiv(struct clk_sam9x5_peripheral *periph)
- 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 @@ clk_sam9x5_peripheral_recalc_rate(struct clk_hw *hw,
- 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 const struct clk_ops sam9x5_peripheral_ops = {
- };
-
- 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 @@ at91_clk_register_sam9x5_peripheral(struct at91_pmc *pmc, const char *name,
- 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 @@ at91_clk_register_sam9x5_peripheral(struct at91_pmc *pmc, const char *name,
- }
-
- 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 @@ of_at91_clk_periph_setup(struct device_node *np, struct at91_pmc *pmc, u8 type)
- 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 @@ of_at91_clk_periph_setup(struct device_node *np, struct at91_pmc *pmc, u8 type)
- 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 @@ of_at91_clk_periph_setup(struct device_node *np, struct at91_pmc *pmc, u8 type)
- 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 @@ of_at91_clk_periph_setup(struct device_node *np, struct at91_pmc *pmc, u8 type)
- "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 @@ of_at91_clk_periph_setup(struct device_node *np, struct at91_pmc *pmc, u8 type)
- }
- }
-
- -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 --git a/drivers/clk/at91/clk-pll.c b/drivers/clk/at91/clk-pll.c
- index 18b60f4895a6..fb2e0b56d4b7 100644
- @@ -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_layout {
-
- 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 @@ struct clk_pll {
- 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 @@ static int clk_pll_prepare(struct clk_hw *hw)
- 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_prepare(struct clk_hw *hw)
- 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;
-
- - if (!pll->div || !pll->mul)
- + regmap_read(pll->regmap, PLL_REG(pll->id), &pllr);
- +
- + div = PLL_DIV(pllr);
- + mul = PLL_MUL(pllr, pll->layout);
- +
- + 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 const struct clk_ops pll_ops = {
- };
-
- 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 @@ at91_clk_register_pll(struct at91_pmc *pmc, unsigned int irq, const char *name,
- 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 @@ at91_clk_register_pll(struct at91_pmc *pmc, unsigned int irq, const char *name,
- 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 @@ of_at91_clk_pll_get_characteristics(struct device_node *np)
- }
-
- 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_at91_clk_pll_setup(struct device_node *np, struct at91_pmc *pmc,
-
- 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 @@ of_at91_clk_pll_setup(struct device_node *np, struct at91_pmc *pmc,
- 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 --git a/drivers/clk/at91/clk-plldiv.c b/drivers/clk/at91/clk-plldiv.c
- index ea226562bb40..2bed26481027 100644
- @@ -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 @@ static int clk_plldiv_set_rate(struct clk_hw *hw, unsigned long rate,
- 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 const struct clk_ops plldiv_ops = {
- };
-
- 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 @@ at91_clk_register_plldiv(struct at91_pmc *pmc, const char *name,
- 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 @@ at91_clk_register_plldiv(struct at91_pmc *pmc, const char *name,
- }
-
- 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 --git a/drivers/clk/at91/clk-programmable.c b/drivers/clk/at91/clk-programmable.c
- index 14b270b85fec..bc0be629671b 100644
- @@ -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_layout {
-
- 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 @@ struct clk_programmable {
- 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 @@ static int clk_programmable_set_parent(struct clk_hw *hw, u8 index)
- {
- 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 @@ static int clk_programmable_set_rate(struct clk_hw *hw, unsigned long rate,
- 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 const struct clk_ops programmable_ops = {
- };
-
- 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 @@ at91_clk_register_programmable(struct at91_pmc *pmc,
- 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 const struct clk_programmable_layout at91sam9x5_programmable_layout = {
- };
-
- 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 @@ of_at91_clk_prog_setup(struct device_node *np, struct at91_pmc *pmc,
- 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 @@ of_at91_clk_prog_setup(struct device_node *np, struct at91_pmc *pmc,
- 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 @@ of_at91_clk_prog_setup(struct device_node *np, struct at91_pmc *pmc,
- 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 @@ of_at91_clk_prog_setup(struct device_node *np, struct at91_pmc *pmc,
- }
-
-
- -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 --git a/drivers/clk/at91/clk-slow.c b/drivers/clk/at91/clk-slow.c
- index d0d5076a9b94..221c09684ba3 100644
- @@ -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_slow_rc_osc {
-
- 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 @@ void __init of_at91sam9x5_clk_slow_setup(struct device_node *np,
- 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 const struct clk_ops sam9260_slow_ops = {
- };
-
- 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 @@ at91_clk_register_sam9260_slow(struct at91_pmc *pmc,
- 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 @@ at91_clk_register_sam9260_slow(struct at91_pmc *pmc,
- 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 @@ at91_clk_register_sam9260_slow(struct at91_pmc *pmc,
- 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 --git a/drivers/clk/at91/clk-smd.c b/drivers/clk/at91/clk-smd.c
- index a7f8501cfa05..e6948a52005a 100644
- @@ -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 @@ struct at91sam9x5_clk_smd {
- 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 long at91sam9x5_clk_smd_round_rate(struct clk_hw *hw, unsigned long rate,
-
- 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 const struct clk_ops at91sam9x5_smd_ops = {
- };
-
- 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 @@ at91sam9x5_clk_register_smd(struct at91_pmc *pmc, const char *name,
- 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 @@ at91sam9x5_clk_register_smd(struct at91_pmc *pmc, const char *name,
- 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 @@ void __init of_at91sam9x5_clk_smd_setup(struct device_node *np,
-
- 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 --git a/drivers/clk/at91/clk-system.c b/drivers/clk/at91/clk-system.c
- index 3f5314344286..8f35d8172909 100644
- @@ -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 @@ static inline int is_pck(int id)
- {
- 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 const struct clk_ops system_ops = {
- };
-
- 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 @@ at91_clk_register_system(struct at91_pmc *pmc, const char *name,
-
- 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 @@ of_at91_clk_sys_setup(struct device_node *np, struct at91_pmc *pmc)
- 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 --git a/drivers/clk/at91/clk-usb.c b/drivers/clk/at91/clk-usb.c
- index 8ab8502778a2..650ca45892c0 100644
- @@ -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 at91sam9x5_clk_usb {
-
- struct at91rm9200_clk_usb {
- struct clk_hw hw;
- - struct at91_pmc *pmc;
- + struct regmap *regmap;
- u32 divisors[4];
- };
-
- @@ -45,13 +45,12 @@ struct at91rm9200_clk_usb {
- 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_determine_rate(struct clk_hw *hw,
-
- 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 @@ static int at91sam9x5_clk_usb_set_rate(struct clk_hw *hw, unsigned long rate,
- 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 const struct clk_ops at91sam9x5_usb_ops = {
- 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 const struct clk_ops at91sam9n12_usb_ops = {
- };
-
- 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 @@ at91sam9x5_clk_register_usb(struct at91_pmc *pmc, const char *name,
- 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 @@ at91sam9x5_clk_register_usb(struct at91_pmc *pmc, const char *name,
- }
-
- 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 @@ at91sam9n12_clk_register_usb(struct at91_pmc *pmc, const char *name,
- 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 @@ static unsigned long at91rm9200_clk_usb_recalc_rate(struct clk_hw *hw,
- 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 long at91rm9200_clk_usb_round_rate(struct clk_hw *hw, unsigned long rate,
- 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 @@ static int at91rm9200_clk_usb_set_rate(struct clk_hw *hw, unsigned long rate,
-
- 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 const struct clk_ops at91rm9200_usb_ops = {
- };
-
- 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 @@ at91rm9200_clk_register_usb(struct at91_pmc *pmc, const char *name,
- 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 @@ at91rm9200_clk_register_usb(struct at91_pmc *pmc, const char *name,
- 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 @@ void __init of_at91sam9x5_clk_usb_setup(struct device_node *np,
-
- 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 @@ void __init of_at91sam9n12_clk_usb_setup(struct device_node *np,
-
- 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 @@ void __init of_at91rm9200_clk_usb_setup(struct device_node *np,
-
- 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 --git a/drivers/clk/at91/clk-utmi.c b/drivers/clk/at91/clk-utmi.c
- index ca561e90a60f..61fcf399e58c 100644
- @@ -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;
- + unsigned int uckr = AT91_PMC_UPLLEN | AT91_PMC_UPLLCOUNT |
- + AT91_PMC_BIASEN;
-
- - pmc_write(pmc, AT91_CKGR_UCKR, tmp);
- + regmap_update_bits(utmi->regmap, AT91_CKGR_UCKR, uckr, uckr);
-
- - 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);
- - }
- + while (!clk_utmi_ready(utmi->regmap))
- + cpu_relax();
-
- return 0;
- }
- @@ -64,18 +52,15 @@ static int clk_utmi_prepare(struct clk_hw *hw)
- 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 const struct clk_ops utmi_ops = {
- };
-
- 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 @@ at91_clk_register_utmi(struct at91_pmc *pmc, unsigned int irq,
- 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 --git a/drivers/clk/at91/pmc.c b/drivers/clk/at91/pmc.c
- index 8476b570779b..526df5ba042d 100644
- @@ -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 @@ int of_at91_get_clk_range(struct device_node *np, const char *propname,
- 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 --git a/drivers/clk/at91/pmc.h b/drivers/clk/at91/pmc.h
- index f65739272779..5771fff0ee3f 100644
- @@ -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 @@ struct clk_range {
-
- #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 --git a/drivers/clocksource/tcb_clksrc.c b/drivers/clocksource/tcb_clksrc.c
- index 4da2af9694a2..5b6f57f500b8 100644
- @@ -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 @@ static struct clocksource clksrc = {
- struct tc_clkevt_device {
- struct clock_event_device clkevt;
- struct clk *clk;
- + bool clk_enabled;
- + u32 freq;
- void __iomem *regs;
- };
-
- @@ -82,15 +83,26 @@ static struct tc_clkevt_device *to_tc_clkevt(struct clock_event_device *clkevt)
- 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 @@ static int tc_shutdown(struct clock_event_device *d)
-
- __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 @@ static int tc_set_oneshot(struct clock_event_device *d)
- 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 @@ static int tc_set_periodic(struct clock_event_device *d)
- /* 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 @@ static struct tc_clkevt_device clkevt = {
- .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 @@ static irqreturn_t ch2_irq(int irq, void *handle)
- 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 @@ static int __init setup_clkevents(struct atmel_tc *tc, int clk32k_divisor_idx)
- 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 @@ static int __init setup_clkevents(struct atmel_tc *tc, int clk32k_divisor_idx)
- 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 @@ static int __init tcb_clksrc_init(void)
- 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 --git a/drivers/clocksource/timer-atmel-pit.c b/drivers/clocksource/timer-atmel-pit.c
- index d911c5dca8f1..7a40f7e88468 100644
- @@ -46,6 +46,7 @@ struct pit_data {
- u32 cycle;
- u32 cnt;
- unsigned int irq;
- + bool irq_requested;
- struct clk *mck;
- };
-
- @@ -96,15 +97,29 @@ static int pit_clkevt_shutdown(struct clock_event_device *dev)
-
- /* 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 @@ static void __init at91sam926x_pit_common_init(struct pit_data *data)
- {
- 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 @@ static void __init at91sam926x_pit_common_init(struct pit_data *data)
- 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 --git a/drivers/clocksource/timer-atmel-st.c b/drivers/clocksource/timer-atmel-st.c
- index 29d21d68df5a..103d0fd70cc4 100644
- @@ -115,18 +115,29 @@ static void clkdev32k_disable_and_flush_irq(void)
- 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_oneshot(struct clock_event_device *dev)
-
- 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 @@ static void __init atmel_st_timer_init(struct device_node *node)
- {
- 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 @@ static void __init atmel_st_timer_init(struct device_node *node)
- 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 --git a/drivers/cpufreq/Kconfig.x86 b/drivers/cpufreq/Kconfig.x86
- index c59bdcb83217..8f23161d80be 100644
- @@ -123,7 +123,7 @@ config X86_POWERNOW_K7_ACPI
-
- 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 --git a/drivers/cpuidle/coupled.c b/drivers/cpuidle/coupled.c
- index 344058f8501a..d5657d50ac40 100644
- @@ -119,7 +119,6 @@ struct cpuidle_coupled {
-
- #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 --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
- index 6ed7d63a0688..9da7482ad256 100644
- @@ -1264,7 +1264,9 @@ i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params,
- 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 --git a/drivers/gpu/drm/i915/i915_gem_shrinker.c b/drivers/gpu/drm/i915/i915_gem_shrinker.c
- index c0a96f1ee18e..deb1e207fa3c 100644
- @@ -39,7 +39,7 @@ static bool mutex_is_locked_by(struct mutex *mutex, struct task_struct *task)
- 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 --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
- index b7b0a38acd67..148dcb1349d5 100644
- @@ -812,6 +812,7 @@ static int i915_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe,
- 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 @@ static int i915_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe,
- *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 --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
- index 4f5d07bb3511..8ecd5c016dba 100644
- @@ -11400,7 +11400,7 @@ void intel_check_page_flip(struct drm_device *dev, int pipe)
- 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 --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c
- index 2cc6aa072f4c..b79d33f14868 100644
- @@ -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 @@ static int usecs_to_scanlines(const struct drm_display_mode *adjusted_mode,
- 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 @@ void intel_pipe_update_start(struct intel_crtc *crtc)
- 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 @@ void intel_pipe_update_start(struct intel_crtc *crtc)
- 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 @@ void intel_pipe_update_end(struct intel_crtc *crtc)
-
- 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 --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
- index 3645b223aa37..642854b2ed2c 100644
- @@ -1862,6 +1862,7 @@ int radeon_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe,
- 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 @@ int radeon_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe,
- *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 --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
- index 802dcb409030..d6d9427860d8 100644
- @@ -820,7 +820,7 @@ static void vmbus_isr(void)
- tasklet_schedule(&msg_dpc);
- }
-
- - add_interrupt_randomness(HYPERVISOR_CALLBACK_VECTOR, 0);
- + add_interrupt_randomness(HYPERVISOR_CALLBACK_VECTOR, 0, 0);
- }
-
-
- diff --git a/drivers/i2c/busses/i2c-omap.c b/drivers/i2c/busses/i2c-omap.c
- index 08d26ba61ed3..46b89dd42b10 100644
- @@ -995,15 +995,12 @@ omap_i2c_isr(int irq, void *dev_id)
- 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 --git a/drivers/ide/alim15x3.c b/drivers/ide/alim15x3.c
- index 36f76e28a0bf..394f142f90c7 100644
- @@ -234,7 +234,7 @@ static int init_chipset_ali15x3(struct pci_dev *dev)
-
- 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 @@ static int init_chipset_ali15x3(struct pci_dev *dev)
- }
- pci_dev_put(north);
- pci_dev_put(isa_dev);
- - local_irq_restore(flags);
- + local_irq_restore_nort(flags);
- return 0;
- }
-
- diff --git a/drivers/ide/hpt366.c b/drivers/ide/hpt366.c
- index 696b6c1ec940..0d0a96629b73 100644
- @@ -1241,7 +1241,7 @@ static int init_dma_hpt366(ide_hwif_t *hwif,
-
- 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 @@ static int init_dma_hpt366(ide_hwif_t *hwif,
- 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 --git a/drivers/ide/ide-io-std.c b/drivers/ide/ide-io-std.c
- index 19763977568c..4169433faab5 100644
- @@ -175,7 +175,7 @@ void ide_input_data(ide_drive_t *drive, struct ide_cmd *cmd, void *buf,
- 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 @@ void ide_input_data(ide_drive_t *drive, struct ide_cmd *cmd, void *buf,
- 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 @@ void ide_output_data(ide_drive_t *drive, struct ide_cmd *cmd, void *buf,
- 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 @@ void ide_output_data(ide_drive_t *drive, struct ide_cmd *cmd, void *buf,
- 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 --git a/drivers/ide/ide-io.c b/drivers/ide/ide-io.c
- index 669ea1e45795..e12e43e62245 100644
- @@ -659,7 +659,7 @@ void ide_timer_expiry (unsigned long data)
- /* 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 --git a/drivers/ide/ide-iops.c b/drivers/ide/ide-iops.c
- index 376f2dc410c5..f014dd1b73dc 100644
- @@ -129,12 +129,12 @@ int __ide_wait_stat(ide_drive_t *drive, u8 good, u8 bad,
- 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 --git a/drivers/ide/ide-probe.c b/drivers/ide/ide-probe.c
- index 0b63facd1d87..4ceba37afc0c 100644
- @@ -196,10 +196,10 @@ static void do_identify(ide_drive_t *drive, u8 cmd, u16 *id)
- 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 --git a/drivers/ide/ide-taskfile.c b/drivers/ide/ide-taskfile.c
- index a716693417a3..be0568c722d6 100644
- @@ -250,7 +250,7 @@ void ide_pio_bytes(ide_drive_t *drive, struct ide_cmd *cmd,
-
- 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 @@ void ide_pio_bytes(ide_drive_t *drive, struct ide_cmd *cmd,
- kunmap_atomic(buf);
-
- if (page_is_high)
- - local_irq_restore(flags);
- + local_irq_restore_nort(flags);
-
- len -= nr_bytes;
- }
- @@ -414,7 +414,7 @@ static ide_startstop_t pre_task_out_intr(ide_drive_t *drive,
- }
-
- 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 --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
- index 5580ab0b5781..a123d0439c4c 100644
- @@ -862,7 +862,7 @@ void ipoib_mcast_restart_task(struct work_struct *work)
-
- 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);
-
- @@ -944,7 +944,7 @@ void ipoib_mcast_restart_task(struct work_struct *work)
-
- 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 --git a/drivers/input/gameport/gameport.c b/drivers/input/gameport/gameport.c
- index 4a2a9e370be7..e970d9afd179 100644
- @@ -91,13 +91,13 @@ static int gameport_measure_speed(struct gameport *gameport)
- 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 @@ static int old_gameport_measure_speed(struct gameport *gameport)
- 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 @@ static int old_gameport_measure_speed(struct gameport *gameport)
- 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 --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
- index 52c36394dba5..d777d0197f64 100644
- @@ -2022,10 +2022,10 @@ static int __attach_device(struct iommu_dev_data *dev_data,
- 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);
- @@ -2188,10 +2188,10 @@ static void __detach_device(struct iommu_dev_data *dev_data)
- 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 --git a/drivers/leds/trigger/Kconfig b/drivers/leds/trigger/Kconfig
- index 5bda6a9b56bb..d6286584c807 100644
- @@ -61,7 +61,7 @@ config LEDS_TRIGGER_BACKLIGHT
-
- 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 --git a/drivers/md/bcache/Kconfig b/drivers/md/bcache/Kconfig
- index 4d200883c505..98b64ed5cb81 100644
- @@ -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 --git a/drivers/md/dm.c b/drivers/md/dm.c
- index 9ec6948e3b8b..ecbc23575114 100644
- @@ -2185,7 +2185,7 @@ static void dm_request_fn(struct request_queue *q)
- /* 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 --git a/drivers/md/raid5.c b/drivers/md/raid5.c
- index 86ab6d14d782..573b9ac810da 100644
- @@ -429,7 +429,7 @@ void raid5_release_stripe(struct stripe_head *sh)
- md_wakeup_thread(conf->mddev->thread);
- return;
- slow_path:
- - local_irq_save(flags);
- + local_irq_save_nort(flags);
- /* we are ok here if STRIPE_ON_RELEASE_LIST is set or not */
- if (atomic_dec_and_lock(&sh->count, &conf->device_lock)) {
- INIT_LIST_HEAD(&list);
- @@ -438,7 +438,7 @@ void raid5_release_stripe(struct stripe_head *sh)
- spin_unlock(&conf->device_lock);
- release_inactive_stripe_list(conf, &list, hash);
- }
- - local_irq_restore(flags);
- + local_irq_restore_nort(flags);
- }
-
- static inline void remove_hash(struct stripe_head *sh)
- @@ -1929,8 +1929,9 @@ static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request)
- 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++;
- @@ -1986,7 +1987,8 @@ static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request)
- 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)
- @@ -6433,6 +6435,7 @@ static int raid5_alloc_percpu(struct r5conf *conf)
- __func__, cpu);
- break;
- }
- + spin_lock_init(&per_cpu_ptr(conf->percpu, cpu)->lock);
- }
- put_online_cpus();
-
- diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
- index 517d4b68a1be..efe91887ecd7 100644
- @@ -504,6 +504,7 @@ struct r5conf {
- 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 --git a/drivers/media/platform/vsp1/vsp1_video.c b/drivers/media/platform/vsp1/vsp1_video.c
- index 5ce88e1f5d71..b4f8cd74ecb8 100644
- @@ -520,7 +520,7 @@ static bool vsp1_pipeline_stopped(struct vsp1_pipeline *pipe)
- 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 --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig
- index 4bf7d50b1bc7..6f7e99ad6e29 100644
- @@ -54,6 +54,7 @@ config AD525X_DPOT_SPI
- 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 @@ config ATMEL_TCB_CLKSRC
- 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 @@ config ATMEL_TCB_CLKSRC_BLOCK
- 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 @@ config IBM_ASM
- 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 --git a/drivers/misc/Makefile b/drivers/misc/Makefile
- index 537d7f3b78da..ec4aecba0656 100644
- @@ -39,6 +39,7 @@ obj-$(CONFIG_C2PORT) += c2port/
- 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 --git a/drivers/misc/hwlat_detector.c b/drivers/misc/hwlat_detector.c
- new file mode 100644
- index 000000000000..52f5ad5fd9c0
- @@ -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 --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c
- index acece3299756..58ea04a03fa9 100644
- @@ -1155,15 +1155,12 @@ static irqreturn_t mmci_pio_irq(int irq, void *dev_id)
- 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 @@ static irqreturn_t mmci_pio_irq(int irq, void *dev_id)
-
- 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 --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c
- index 2839af00f20c..4348b9c850d3 100644
- @@ -842,9 +842,9 @@ static void poll_vortex(struct net_device *dev)
- {
- 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 @@ static void vortex_tx_timeout(struct net_device *dev)
- * 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 --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
- index 8b5988e210d5..cf9928ccdd7e 100644
- @@ -2221,11 +2221,7 @@ static netdev_tx_t atl1c_xmit_frame(struct sk_buff *skb,
- }
-
- 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 --git a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
- index 59a03a193e83..734f7a7ad2c3 100644
- @@ -1880,8 +1880,7 @@ static netdev_tx_t atl1e_xmit_frame(struct sk_buff *skb,
- 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 --git a/drivers/net/ethernet/chelsio/cxgb/sge.c b/drivers/net/ethernet/chelsio/cxgb/sge.c
- index 526ea74e82d9..86f467a2c485 100644
- @@ -1664,8 +1664,7 @@ static int t1_sge_tx(struct sk_buff *skb, struct adapter *adapter,
- 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 --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c
- index 9ba975853ec6..813cfa698160 100644
- @@ -4084,12 +4084,7 @@ static netdev_tx_t s2io_xmit(struct sk_buff *skb, struct net_device *dev)
- [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 --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
- index 3b98b263bad0..ca4add749410 100644
- @@ -2137,10 +2137,8 @@ static int pch_gbe_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
- 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 --git a/drivers/net/ethernet/realtek/8139too.c b/drivers/net/ethernet/realtek/8139too.c
- index ef668d300800..d987d571fdd6 100644
- @@ -2229,7 +2229,7 @@ static void rtl8139_poll_controller(struct net_device *dev)
- 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 --git a/drivers/net/ethernet/tehuti/tehuti.c b/drivers/net/ethernet/tehuti/tehuti.c
- index 14c9d1baa85c..e1a5305418a8 100644
- @@ -1629,13 +1629,8 @@ static netdev_tx_t bdx_tx_transmit(struct sk_buff *skb,
- 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 --git a/drivers/net/rionet.c b/drivers/net/rionet.c
- index e7034c55e796..2e4ee0f912bf 100644
- @@ -174,11 +174,7 @@ static int rionet_start_xmit(struct sk_buff *skb, struct net_device *ndev)
- 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 --git a/drivers/net/wireless/orinoco/orinoco_usb.c b/drivers/net/wireless/orinoco/orinoco_usb.c
- index f2cd513d54b2..6c0f4c9638a2 100644
- @@ -697,7 +697,7 @@ static void ezusb_req_ctx_wait(struct ezusb_priv *upriv,
- 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 --git a/drivers/pci/access.c b/drivers/pci/access.c
- index 59ac36fe7c42..7a45a20af78a 100644
- @@ -561,7 +561,7 @@ void pci_cfg_access_unlock(struct pci_dev *dev)
- 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 --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c
- index 9736f9be5447..5fe9b173dcb3 100644
- @@ -60,7 +60,7 @@ struct msm_pinctrl {
- struct notifier_block restart_nb;
- int irq;
-
- - spinlock_t lock;
- + raw_spinlock_t lock;
-
- DECLARE_BITMAP(dual_edge_irqs, MAX_NR_GPIO);
- DECLARE_BITMAP(enabled_irqs, MAX_NR_GPIO);
- @@ -156,14 +156,14 @@ static int msm_pinmux_set_mux(struct pinctrl_dev *pctldev,
- if (WARN_ON(i == g->nfuncs))
- return -EINVAL;
-
- - spin_lock_irqsave(&pctrl->lock, flags);
- + raw_spin_lock_irqsave(&pctrl->lock, flags);
-
- val = readl(pctrl->regs + g->ctl_reg);
- val &= ~(0x7 << g->mux_bit);
- val |= i << g->mux_bit;
- writel(val, pctrl->regs + g->ctl_reg);
-
- - spin_unlock_irqrestore(&pctrl->lock, flags);
- + raw_spin_unlock_irqrestore(&pctrl->lock, flags);
-
- return 0;
- }
- @@ -326,14 +326,14 @@ static int msm_config_group_set(struct pinctrl_dev *pctldev,
- break;
- case PIN_CONFIG_OUTPUT:
- /* set output value */
- - spin_lock_irqsave(&pctrl->lock, flags);
- + raw_spin_lock_irqsave(&pctrl->lock, flags);
- val = readl(pctrl->regs + g->io_reg);
- if (arg)
- val |= BIT(g->out_bit);
- else
- val &= ~BIT(g->out_bit);
- writel(val, pctrl->regs + g->io_reg);
- - spin_unlock_irqrestore(&pctrl->lock, flags);
- + raw_spin_unlock_irqrestore(&pctrl->lock, flags);
-
- /* enable output */
- arg = 1;
- @@ -354,12 +354,12 @@ static int msm_config_group_set(struct pinctrl_dev *pctldev,
- return -EINVAL;
- }
-
- - spin_lock_irqsave(&pctrl->lock, flags);
- + raw_spin_lock_irqsave(&pctrl->lock, flags);
- val = readl(pctrl->regs + g->ctl_reg);
- val &= ~(mask << bit);
- val |= arg << bit;
- writel(val, pctrl->regs + g->ctl_reg);
- - spin_unlock_irqrestore(&pctrl->lock, flags);
- + raw_spin_unlock_irqrestore(&pctrl->lock, flags);
- }
-
- return 0;
- @@ -387,13 +387,13 @@ static int msm_gpio_direction_input(struct gpio_chip *chip, unsigned offset)
-
- g = &pctrl->soc->groups[offset];
-
- - spin_lock_irqsave(&pctrl->lock, flags);
- + raw_spin_lock_irqsave(&pctrl->lock, flags);
-
- val = readl(pctrl->regs + g->ctl_reg);
- val &= ~BIT(g->oe_bit);
- writel(val, pctrl->regs + g->ctl_reg);
-
- - spin_unlock_irqrestore(&pctrl->lock, flags);
- + raw_spin_unlock_irqrestore(&pctrl->lock, flags);
-
- return 0;
- }
- @@ -407,7 +407,7 @@ static int msm_gpio_direction_output(struct gpio_chip *chip, unsigned offset, in
-
- g = &pctrl->soc->groups[offset];
-
- - spin_lock_irqsave(&pctrl->lock, flags);
- + raw_spin_lock_irqsave(&pctrl->lock, flags);
-
- val = readl(pctrl->regs + g->io_reg);
- if (value)
- @@ -420,7 +420,7 @@ static int msm_gpio_direction_output(struct gpio_chip *chip, unsigned offset, in
- val |= BIT(g->oe_bit);
- writel(val, pctrl->regs + g->ctl_reg);
-
- - spin_unlock_irqrestore(&pctrl->lock, flags);
- + raw_spin_unlock_irqrestore(&pctrl->lock, flags);
-
- return 0;
- }
- @@ -446,7 +446,7 @@ static void msm_gpio_set(struct gpio_chip *chip, unsigned offset, int value)
-
- g = &pctrl->soc->groups[offset];
-
- - spin_lock_irqsave(&pctrl->lock, flags);
- + raw_spin_lock_irqsave(&pctrl->lock, flags);
-
- val = readl(pctrl->regs + g->io_reg);
- if (value)
- @@ -455,7 +455,7 @@ static void msm_gpio_set(struct gpio_chip *chip, unsigned offset, int value)
- val &= ~BIT(g->out_bit);
- writel(val, pctrl->regs + g->io_reg);
-
- - spin_unlock_irqrestore(&pctrl->lock, flags);
- + raw_spin_unlock_irqrestore(&pctrl->lock, flags);
- }
-
- #ifdef CONFIG_DEBUG_FS
- @@ -574,7 +574,7 @@ static void msm_gpio_irq_mask(struct irq_data *d)
-
- g = &pctrl->soc->groups[d->hwirq];
-
- - spin_lock_irqsave(&pctrl->lock, flags);
- + raw_spin_lock_irqsave(&pctrl->lock, flags);
-
- val = readl(pctrl->regs + g->intr_cfg_reg);
- val &= ~BIT(g->intr_enable_bit);
- @@ -582,7 +582,7 @@ static void msm_gpio_irq_mask(struct irq_data *d)
-
- clear_bit(d->hwirq, pctrl->enabled_irqs);
-
- - spin_unlock_irqrestore(&pctrl->lock, flags);
- + raw_spin_unlock_irqrestore(&pctrl->lock, flags);
- }
-
- static void msm_gpio_irq_unmask(struct irq_data *d)
- @@ -595,7 +595,7 @@ static void msm_gpio_irq_unmask(struct irq_data *d)
-
- g = &pctrl->soc->groups[d->hwirq];
-
- - spin_lock_irqsave(&pctrl->lock, flags);
- + raw_spin_lock_irqsave(&pctrl->lock, flags);
-
- val = readl(pctrl->regs + g->intr_cfg_reg);
- val |= BIT(g->intr_enable_bit);
- @@ -603,7 +603,7 @@ static void msm_gpio_irq_unmask(struct irq_data *d)
-
- set_bit(d->hwirq, pctrl->enabled_irqs);
-
- - spin_unlock_irqrestore(&pctrl->lock, flags);
- + raw_spin_unlock_irqrestore(&pctrl->lock, flags);
- }
-
- static void msm_gpio_irq_ack(struct irq_data *d)
- @@ -616,7 +616,7 @@ static void msm_gpio_irq_ack(struct irq_data *d)
-
- g = &pctrl->soc->groups[d->hwirq];
-
- - spin_lock_irqsave(&pctrl->lock, flags);
- + raw_spin_lock_irqsave(&pctrl->lock, flags);
-
- val = readl(pctrl->regs + g->intr_status_reg);
- if (g->intr_ack_high)
- @@ -628,7 +628,7 @@ static void msm_gpio_irq_ack(struct irq_data *d)
- if (test_bit(d->hwirq, pctrl->dual_edge_irqs))
- msm_gpio_update_dual_edge_pos(pctrl, g, d);
-
- - spin_unlock_irqrestore(&pctrl->lock, flags);
- + raw_spin_unlock_irqrestore(&pctrl->lock, flags);
- }
-
- static int msm_gpio_irq_set_type(struct irq_data *d, unsigned int type)
- @@ -641,7 +641,7 @@ static int msm_gpio_irq_set_type(struct irq_data *d, unsigned int type)
-
- g = &pctrl->soc->groups[d->hwirq];
-
- - spin_lock_irqsave(&pctrl->lock, flags);
- + raw_spin_lock_irqsave(&pctrl->lock, flags);
-
- /*
- * For hw without possibility of detecting both edges
- @@ -715,7 +715,7 @@ static int msm_gpio_irq_set_type(struct irq_data *d, unsigned int type)
- if (test_bit(d->hwirq, pctrl->dual_edge_irqs))
- msm_gpio_update_dual_edge_pos(pctrl, g, d);
-
- - spin_unlock_irqrestore(&pctrl->lock, flags);
- + raw_spin_unlock_irqrestore(&pctrl->lock, flags);
-
- if (type & (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_LEVEL_HIGH))
- irq_set_handler_locked(d, handle_level_irq);
- @@ -731,11 +731,11 @@ static int msm_gpio_irq_set_wake(struct irq_data *d, unsigned int on)
- struct msm_pinctrl *pctrl = to_msm_pinctrl(gc);
- unsigned long flags;
-
- - spin_lock_irqsave(&pctrl->lock, flags);
- + raw_spin_lock_irqsave(&pctrl->lock, flags);
-
- irq_set_irq_wake(pctrl->irq, on);
-
- - spin_unlock_irqrestore(&pctrl->lock, flags);
- + raw_spin_unlock_irqrestore(&pctrl->lock, flags);
-
- return 0;
- }
- @@ -881,7 +881,7 @@ int msm_pinctrl_probe(struct platform_device *pdev,
- pctrl->soc = soc_data;
- pctrl->chip = msm_gpio_template;
-
- - spin_lock_init(&pctrl->lock);
- + raw_spin_lock_init(&pctrl->lock);
-
- res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- pctrl->regs = devm_ioremap_resource(&pdev->dev, res);
- diff --git a/drivers/scsi/fcoe/fcoe.c b/drivers/scsi/fcoe/fcoe.c
- index f4424063b860..cbbbebd86c6e 100644
- @@ -1286,7 +1286,7 @@ static void fcoe_percpu_thread_destroy(unsigned int cpu)
- 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 @@ static void fcoe_percpu_thread_destroy(unsigned int cpu)
- 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_rcv(struct sk_buff *skb, struct net_device *netdev,
- 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 @@ static inline int fcoe_filter_frames(struct fc_lport *lport,
- 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 @@ static void fcoe_recv_frame(struct sk_buff *skb)
- */
- 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 @@ static void fcoe_recv_frame(struct sk_buff *skb)
- 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 --git a/drivers/scsi/fcoe/fcoe_ctlr.c b/drivers/scsi/fcoe/fcoe_ctlr.c
- index 34a1b1f333b4..d91131210695 100644
- @@ -831,7 +831,7 @@ static unsigned long fcoe_ctlr_age_fcfs(struct fcoe_ctlr *fip)
-
- 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 @@ static unsigned long fcoe_ctlr_age_fcfs(struct fcoe_ctlr *fip)
- 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 --git a/drivers/scsi/libfc/fc_exch.c b/drivers/scsi/libfc/fc_exch.c
- index 30f9ef0c0d4f..6c686bc01a82 100644
- @@ -814,10 +814,10 @@ static struct fc_exch *fc_exch_em_alloc(struct fc_lport *lport,
- }
- 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 --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c
- index 6f5e2720ffad..ee8a8ed49b89 100644
- @@ -190,7 +190,7 @@ static unsigned int sas_ata_qc_issue(struct ata_queued_cmd *qc)
- /* 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 @@ static unsigned int sas_ata_qc_issue(struct ata_queued_cmd *qc)
-
- out:
- spin_lock(ap->lock);
- - local_irq_restore(flags);
- + local_irq_restore_nort(flags);
- return ret;
- }
-
- diff --git a/drivers/scsi/qla2xxx/qla_inline.h b/drivers/scsi/qla2xxx/qla_inline.h
- index fee9eb7c8a60..b42d4adc42dc 100644
- @@ -59,12 +59,12 @@ qla2x00_poll(struct rsp_que *rsp)
- {
- 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 --git a/drivers/thermal/x86_pkg_temp_thermal.c b/drivers/thermal/x86_pkg_temp_thermal.c
- index 7fc919f7da4d..e03fa17b8670 100644
- @@ -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 void pkg_temp_thermal_threshold_work_fn(struct work_struct *work)
- }
- }
-
- -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 @@ static int pkg_temp_thermal_platform_thermal_notify(__u64 msr_val)
- 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 @@ static int pkg_temp_thermal_platform_thermal_notify(__u64 msr_val)
- 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 @@ static int __init pkg_temp_thermal_init(void)
- 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 @@ static int __init pkg_temp_thermal_init(void)
- 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 @@ static void __exit pkg_temp_thermal_exit(void)
- 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 --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c
- index 39126460c1f5..af7701ca4d48 100644
- @@ -58,7 +58,16 @@ static struct uart_driver serial8250_reg;
-
- 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 --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c
- index d42d66b72d5a..c08e0724a487 100644
- @@ -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>
-
- @@ -2846,9 +2847,9 @@ void serial8250_console_write(struct uart_8250_port *up, const char *s,
-
- 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 --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c
- index 899a77187bde..3ff6363b3751 100644
- @@ -2067,13 +2067,19 @@ pl011_console_write(struct console *co, const char *s, unsigned int count)
-
- 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 @@ pl011_console_write(struct console *co, const char *s, unsigned int count)
- 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 --git a/drivers/tty/serial/omap-serial.c b/drivers/tty/serial/omap-serial.c
- index 21fc9b3a27cf..2e32729e6a83 100644
- @@ -1257,13 +1257,10 @@ serial_omap_console_write(struct console *co, const char *s,
-
- 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 @@ serial_omap_console_write(struct console *co, const char *s,
- 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 --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
- index 87a83d925eea..995a37bde992 100644
- @@ -1738,9 +1738,9 @@ static void __usb_hcd_giveback_urb(struct urb *urb)
- * 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 --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c
- index 39bb65265bff..49c167d150ce 100644
- @@ -1404,7 +1404,7 @@ static void ffs_data_put(struct ffs_data *ffs)
- 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 --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c
- index 81f3c9cb333c..c996bd43741a 100644
- @@ -346,7 +346,7 @@ ep_io (struct ep_data *epdata, void *buf, unsigned len)
- 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)) {
- @@ -355,7 +355,7 @@ ep_io (struct ep_data *epdata, void *buf, unsigned len)
- 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 --git a/drivers/usb/gadget/udc/atmel_usba_udc.c b/drivers/usb/gadget/udc/atmel_usba_udc.c
- index 585cb8734f50..1e469be2c216 100644
- @@ -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>
- @@ -1890,20 +1892,15 @@ static int atmel_usba_stop(struct usb_gadget *gadget)
- #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 = {
- @@ -1940,6 +1937,9 @@ static struct usba_ep * atmel_udc_of_init(struct platform_device *pdev,
- 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 --git a/drivers/usb/gadget/udc/atmel_usba_udc.h b/drivers/usb/gadget/udc/atmel_usba_udc.h
- index ea448a344767..3e1c9d589dfa 100644
- @@ -354,6 +354,8 @@ struct usba_udc {
- 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 --git a/fs/aio.c b/fs/aio.c
- index fe4f49212b99..c3194afdc3df 100644
- @@ -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 kioctx {
- 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 @@ static int __init aio_setup(void)
- .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 @@ static int kiocb_cancel(struct aio_kiocb *kiocb)
- 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 @@ static void free_ioctx_reqs(struct percpu_ref *ref)
- 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 @@ static void free_ioctx_reqs(struct percpu_ref *ref)
- * 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 @@ static void free_ioctx_users(struct percpu_ref *ref)
- 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 --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h
- index 502d3892d8a4..05af8d3e6e88 100644
- @@ -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 --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c
- index 7a5a598a2d94..d08bcdc30566 100644
- @@ -150,7 +150,7 @@ static struct dentry *get_next_positive_dentry(struct dentry *prev,
- 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 --git a/fs/buffer.c b/fs/buffer.c
- index 6f7d519a093b..96b943e924cc 100644
- @@ -305,8 +305,7 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate)
- * 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 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate)
- }
- 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 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate)
- 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 @@ void end_buffer_async_write(struct buffer_head *bh, int uptodate)
- }
-
- 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 @@ void end_buffer_async_write(struct buffer_head *bh, int uptodate)
- }
- 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 *alloc_buffer_head(gfp_t gfp_flags)
- 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 --git a/fs/dcache.c b/fs/dcache.c
- index 3ed642e0a0c2..1437dd042e13 100644
- @@ -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>
- @@ -774,6 +775,8 @@ static inline bool fast_dput(struct dentry *dentry)
- */
- void dput(struct dentry *dentry)
- {
- + struct dentry *parent;
- +
- if (unlikely(!dentry))
- return;
-
- @@ -810,9 +813,18 @@ void dput(struct dentry *dentry)
- 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;
- }
- }
- @@ -2425,7 +2437,7 @@ void d_delete(struct dentry * dentry)
- 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 --git a/fs/eventpoll.c b/fs/eventpoll.c
- index 1b08556776ce..06435352045d 100644
- @@ -505,12 +505,12 @@ static int ep_poll_wakeup_proc(void *priv, void *cookie, int call_nests)
- */
- 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 --git a/fs/exec.c b/fs/exec.c
- index 9c5ee2a880aa..c12e576bb209 100644
- @@ -887,12 +887,14 @@ static int exec_mmap(struct mm_struct *mm)
- }
- }
- 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 --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
- index 6ca56f5f72b5..9e145fe7cae0 100644
- @@ -97,8 +97,7 @@ static void ext4_finish_bio(struct bio *bio)
- * We check all buffers in the page under BH_Uptodate_Lock
- * to avoid races with other end io clearing async_write flags
- */
- - local_irq_save(flags);
- - bit_spin_lock(BH_Uptodate_Lock, &head->b_state);
- + flags = bh_uptodate_lock_irqsave(head);
- do {
- if (bh_offset(bh) < bio_start ||
- bh_offset(bh) + bh->b_size > bio_end) {
- @@ -110,8 +109,7 @@ static void ext4_finish_bio(struct bio *bio)
- if (bio->bi_error)
- buffer_io_error(bh);
- } while ((bh = bh->b_this_page) != head);
- - bit_spin_unlock(BH_Uptodate_Lock, &head->b_state);
- - local_irq_restore(flags);
- + bh_uptodate_unlock_irqrestore(head, flags);
- if (!under_io) {
- #ifdef CONFIG_EXT4_FS_ENCRYPTION
- if (ctx)
- diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
- index 2871576fbca4..d1137790ea58 100644
- @@ -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_unlock_op(struct f2fs_sb_info *sbi)
-
- 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 --git a/fs/namespace.c b/fs/namespace.c
- index ec4078d16eb7..1780601dcbdd 100644
- @@ -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 */
- @@ -357,8 +358,11 @@ int __mnt_want_write(struct vfsmount *m)
- * 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 --git a/fs/ntfs/aops.c b/fs/ntfs/aops.c
- index 7521e11db728..f0de4b6b8bf3 100644
- @@ -107,8 +107,7 @@ static void ntfs_end_buffer_async_read(struct buffer_head *bh, int uptodate)
- "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 @@ static void ntfs_end_buffer_async_read(struct buffer_head *bh, int uptodate)
- }
- 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 @@ static void ntfs_end_buffer_async_read(struct buffer_head *bh, int uptodate)
- 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 @@ static void ntfs_end_buffer_async_read(struct buffer_head *bh, int uptodate)
- 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 --git a/fs/timerfd.c b/fs/timerfd.c
- index 1327a02ec778..4260febcb029 100644
- @@ -461,7 +461,10 @@ static int do_timerfd_settime(int ufd, int flags,
- 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 --git a/include/acpi/platform/aclinux.h b/include/acpi/platform/aclinux.h
- index 323e5daece54..cc5fbd534fd4 100644
- @@ -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 --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h
- index 630dd2372238..850e4d993a88 100644
- @@ -206,6 +206,20 @@ extern void warn_slowpath_null(const char *file, const int line);
- # 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 --git a/include/asm-generic/preempt.h b/include/asm-generic/preempt.h
- index 5d8ffa3e6f8c..c1cde3577551 100644
- @@ -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 --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
- index daf17d70aeca..463df8954255 100644
- @@ -212,6 +212,7 @@ static inline u16 blk_mq_unique_tag_to_tag(u32 unique_tag)
-
- 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 --git a/include/linux/blkdev.h b/include/linux/blkdev.h
- index fe14382f9664..a82143ad6702 100644
- @@ -89,6 +89,7 @@ struct request {
- struct list_head queuelist;
- union {
- struct call_single_data csd;
- + struct work_struct work;
- unsigned long fifo_time;
- };
-
- @@ -455,7 +456,7 @@ struct request_queue {
- 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 --git a/include/linux/bottom_half.h b/include/linux/bottom_half.h
- index 8fdcb783197d..d07dbeec7bc1 100644
- @@ -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 @@ static inline void local_bh_enable(void)
- {
- __local_bh_enable_ip(_THIS_IP_, SOFTIRQ_DISABLE_OFFSET);
- }
- +#endif
-
- #endif /* _LINUX_BH_H */
- diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
- index 6fe974dbe741..7242505af75c 100644
- @@ -75,8 +75,50 @@ struct buffer_head {
- 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 --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
- index 8da263299754..0cc474291e08 100644
- @@ -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 @@ struct cgroup_subsys_state {
- /* percpu_ref killing and RCU release */
- struct rcu_head rcu_head;
- struct work_struct destroy_work;
- + struct swork_event destroy_swork;
- };
-
- /*
- diff --git a/include/linux/clk/at91_pmc.h b/include/linux/clk/at91_pmc.h
- index 1e6932222e11..17f413bbbedf 100644
- @@ -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 --git a/include/linux/completion.h b/include/linux/completion.h
- index 5d5aaae3af43..3bca1590e29f 100644
- @@ -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 @@ struct completion {
- static inline void init_completion(struct completion *x)
- {
- x->done = 0;
- - init_waitqueue_head(&x->wait);
- + init_swait_queue_head(&x->wait);
- }
-
- /**
- diff --git a/include/linux/cpu.h b/include/linux/cpu.h
- index 7e04bcd9af8e..e7fa0f6935e6 100644
- @@ -231,6 +231,8 @@ extern void get_online_cpus(void);
- 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 @@ static inline void cpu_hotplug_done(void) {}
- #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 --git a/include/linux/delay.h b/include/linux/delay.h
- index a6ecb34cf547..37caab306336 100644
- @@ -52,4 +52,10 @@ static inline void ssleep(unsigned int seconds)
- 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 --git a/include/linux/ftrace.h b/include/linux/ftrace.h
- index 60048c50404e..f2cd67624f18 100644
- @@ -694,6 +694,18 @@ static inline void __ftrace_enabled_restore(int enabled)
- #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 --git a/include/linux/highmem.h b/include/linux/highmem.h
- index bb3f3297062a..a117a33ef72c 100644
- @@ -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 kunmap(struct page *page)
-
- 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 *kmap_atomic(struct page *page)
- 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 @@ static inline void __kunmap_atomic(void *addr)
-
- #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 --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
- index 2ead22dd74a0..ff317006d3e8 100644
- @@ -87,6 +87,9 @@ enum hrtimer_restart {
- * @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 @@ struct hrtimer {
- 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 hrtimer_sleeper {
- 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 @@ struct hrtimer_sleeper {
- * 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 @@ struct hrtimer_clock_base {
- 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 @@ struct hrtimer_cpu_base {
- 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;
- @@ -202,6 +209,9 @@ struct hrtimer_cpu_base {
- unsigned int nr_retries;
- 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 @@ static inline void hrtimer_restart(struct hrtimer *timer)
- 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);
-
- @@ -436,9 +453,15 @@ static inline int hrtimer_is_queued(struct hrtimer *timer)
- * 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;
- + if (timer->base->cpu_base->running == timer)
- + return 1;
- +#ifdef CONFIG_PREEMPT_RT_BASE
- + if (timer->base->cpu_base->running_soft == timer)
- + return 1;
- +#endif
- + return 0;
- }
-
- /* Forward a hrtimer so it expires after now: */
- diff --git a/include/linux/idr.h b/include/linux/idr.h
- index 013fd9bc4cb6..f62be0aec911 100644
- @@ -95,10 +95,14 @@ bool idr_is_empty(struct idr *idp);
- * 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 --git a/include/linux/init_task.h b/include/linux/init_task.h
- index 1c1ff7e4faa4..60fadde71a44 100644
- @@ -148,9 +148,15 @@ extern struct task_group root_task_group;
- # 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 @@ extern struct task_group root_task_group;
- .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 --git a/include/linux/interrupt.h b/include/linux/interrupt.h
- index ad16809c8596..655cee096aed 100644
- @@ -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 @@ extern void devm_free_irq(struct device *dev, unsigned int irq, void *dev_id);
- #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 @@ extern void resume_device_irqs(void);
- * @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 @@ struct irq_affinity_notify {
- 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 @@ extern int irq_set_irqchip_state(unsigned int irq, enum irqchip_irq_state which,
- 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 @@ struct softirq_action
- 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 @@ static inline void do_softirq_own_stack(void)
- __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 @@ static inline struct task_struct *this_cpu_ksoftirqd(void)
- 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 @@ struct tasklet_struct name = { NULL, 0, ATOMIC_INIT(1), func, data }
- 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 @@ static inline void tasklet_disable(struct tasklet_struct *t)
- 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 @@ void tasklet_hrtimer_cancel(struct tasklet_hrtimer *ttimer)
- 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 --git a/include/linux/irq.h b/include/linux/irq.h
- index f7cade00c525..dac9e11ba037 100644
- @@ -72,6 +72,7 @@ enum irqchip_irq_state;
- * 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 @@ enum {
- 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 --git a/include/linux/irq_work.h b/include/linux/irq_work.h
- index 47b9ebd4a74f..2543aab05daa 100644
- @@ -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 bool irq_work_needs_cpu(void) { return false; }
- 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 --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
- index a587a33363c7..ad57402a242d 100644
- @@ -61,6 +61,7 @@ struct irq_desc {
- 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 --git a/include/linux/irqflags.h b/include/linux/irqflags.h
- index 5dd1272d1ab2..9b77034f7c5e 100644
- @@ -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 --git a/include/linux/jbd2.h b/include/linux/jbd2.h
- index 65407f6c9120..eb5aabe4e18c 100644
- @@ -352,32 +352,56 @@ static inline struct journal_head *bh2jh(struct buffer_head *bh)
-
- 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 --git a/include/linux/kdb.h b/include/linux/kdb.h
- index a19bcf9e762e..897495386446 100644
- @@ -167,6 +167,7 @@ extern __printf(2, 0) int vkdb_printf(enum kdb_msgsrc src, const char *fmt,
- 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_register_flags(char *, kdb_func_t, char *, char *,
- 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 --git a/include/linux/kernel.h b/include/linux/kernel.h
- index 50220cab738c..d68f639f7330 100644
- @@ -188,6 +188,9 @@ extern int _cond_resched(void);
- */
- # 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 @@ extern int _cond_resched(void);
- 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 @@ extern long (*panic_blink)(int state);
- __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);
- @@ -447,6 +452,14 @@ extern int sysctl_panic_on_stackoverflow;
-
- 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 @@ extern enum system_states {
- SYSTEM_HALT,
- SYSTEM_POWER_OFF,
- SYSTEM_RESTART,
- + SYSTEM_SUSPEND,
- } system_state;
-
- #define TAINT_PROPRIETARY_MODULE 0
- diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
- index d7ce4e3280db..0b6d392b38e7 100644
- @@ -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 @@ struct kvm_vcpu {
- 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 @@ static inline bool kvm_arch_has_assigned_device(struct kvm *kvm)
- }
- #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 --git a/include/linux/lglock.h b/include/linux/lglock.h
- index c92ebd100d9b..6f035f635d0e 100644
- @@ -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 @@ struct lglock {
- 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_double_unlock(struct lglock *lg, int cpu1, int cpu2);
- 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 --git a/include/linux/list_bl.h b/include/linux/list_bl.h
- index 8132214e8efd..89ffaa7bd342 100644
- @@ -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_del_init(struct hlist_bl_node *n)
-
- 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 --git a/include/linux/locallock.h b/include/linux/locallock.h
- new file mode 100644
- index 000000000000..0baaf28dc4ee
- @@ -0,0 +1,285 @@
- +#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;
- + } else if (lv->owner == current) {
- + lv->nestcnt++;
- + 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_trylock(lvar) \
- + ({ \
- + preempt_disable(); \
- + 1; \
- + })
- +
- +#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 --git a/include/linux/mm_types.h b/include/linux/mm_types.h
- index 36f4695aa604..2be9cca8be08 100644
- @@ -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>
- @@ -509,6 +510,9 @@ struct mm_struct {
- bool tlb_flush_batched;
- #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 --git a/include/linux/module.h b/include/linux/module.h
- index b229a9961d02..5fea847cf95c 100644
- @@ -500,6 +500,7 @@ static inline int module_is_live(struct module *mod)
- struct module *__module_text_address(unsigned long addr);
- struct module *__module_address(unsigned long addr);
- bool is_module_address(unsigned long addr);
- +bool __is_module_percpu_address(unsigned long addr, unsigned long *can_addr);
- bool is_module_percpu_address(unsigned long addr);
- bool is_module_text_address(unsigned long addr);
-
- @@ -665,6 +666,11 @@ static inline bool is_module_percpu_address(unsigned long addr)
- return false;
- }
-
- +static inline bool __is_module_percpu_address(unsigned long addr, unsigned long *can_addr)
- +{
- + return false;
- +}
- +
- static inline bool is_module_text_address(unsigned long addr)
- {
- return false;
- diff --git a/include/linux/mutex.h b/include/linux/mutex.h
- index 2cb7531e7d7a..b3fdfc820216 100644
- @@ -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 @@ do { \
- 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 __must_check mutex_lock_killable(struct mutex *lock);
- 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 --git a/include/linux/mutex_rt.h b/include/linux/mutex_rt.h
- new file mode 100644
- index 000000000000..e0284edec655
- @@ -0,0 +1,89 @@
- +#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)
- +
- +#ifdef CONFIG_DEBUG_MUTEXES
- +#define mutex_destroy(l) rt_mutex_destroy(&(l)->lock)
- +#else
- +static inline void mutex_destroy(struct mutex *lock) {}
- +#endif
- +
- +#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 --git a/include/linux/netdevice.h b/include/linux/netdevice.h
- index fc54049e8286..5a5588a57cad 100644
- @@ -390,7 +390,19 @@ typedef enum rx_handler_result rx_handler_result_t;
- typedef rx_handler_result_t rx_handler_func_t(struct sk_buff **pskb);
-
- void __napi_schedule(struct napi_struct *n);
- +
- +/*
- + * When PREEMPT_RT_FULL is defined, all device interrupt handlers
- + * run as threads, and they can also be preempted (without PREEMPT_RT
- + * interrupt threads can not be preempted). Which means that calling
- + * __napi_schedule_irqoff() from an interrupt handler can be preempted
- + * and can corrupt the napi->poll_list.
- + */
- +#ifdef CONFIG_PREEMPT_RT_FULL
- +#define __napi_schedule_irqoff(n) __napi_schedule(n)
- +#else
- void __napi_schedule_irqoff(struct napi_struct *n);
- +#endif
-
- static inline bool napi_disable_pending(struct napi_struct *n)
- {
- @@ -2288,11 +2300,20 @@ void netdev_freemem(struct net_device *dev);
- 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);
- @@ -2610,6 +2631,7 @@ struct softnet_data {
- unsigned int dropped;
- struct sk_buff_head input_pkt_queue;
- struct napi_struct backlog;
- + struct sk_buff_head tofree_queue;
-
- };
-
- diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h
- index 04078e8a4803..a61c9609e32f 100644
- @@ -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 @@ void xt_free_table_info(struct xt_table_info *info);
- */
- 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 @@ static inline unsigned int xt_write_recseq_begin(void)
- {
- 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 @@ static inline void xt_write_recseq_end(unsigned int addend)
- /* 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 --git a/include/linux/notifier.h b/include/linux/notifier.h
- index d14a4c362465..2e4414a0c1c4 100644
- @@ -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 @@ struct srcu_notifier_head {
- (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 @@ extern void srcu_init_notifier_head(struct srcu_notifier_head *nh);
- .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 @@ extern void srcu_init_notifier_head(struct srcu_notifier_head *nh);
- 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 @@ static inline int notifier_to_errno(int ret)
-
- /*
- * 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 --git a/include/linux/percpu.h b/include/linux/percpu.h
- index caebf2a758dc..4ecc057b6e27 100644
- @@ -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)
-
- @@ -116,6 +145,7 @@ extern int __init pcpu_page_first_chunk(size_t reserved_size,
- #endif
-
- extern void __percpu *__alloc_reserved_percpu(size_t size, size_t align);
- +extern bool __is_kernel_percpu_address(unsigned long addr, unsigned long *can_addr);
- extern bool is_kernel_percpu_address(unsigned long addr);
-
- #if !defined(CONFIG_SMP) || !defined(CONFIG_HAVE_SETUP_PER_CPU_AREA)
- diff --git a/include/linux/pid.h b/include/linux/pid.h
- index 97b745ddece5..01a5460a0c85 100644
- @@ -2,6 +2,7 @@
- #define _LINUX_PID_H
-
- #include <linux/rcupdate.h>
- +#include <linux/atomic.h>
-
- enum pid_type
- {
- diff --git a/include/linux/preempt.h b/include/linux/preempt.h
- index 7eeceac52dea..f97c54265904 100644
- @@ -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?
- @@ -79,7 +89,6 @@
- #define in_irq() (hardirq_count())
- #define in_softirq() (softirq_count())
- #define in_interrupt() (irq_count())
- -#define in_serving_softirq() (softirq_count() & SOFTIRQ_OFFSET)
- #define in_nmi() (preempt_count() & NMI_MASK)
- #define in_task() (!(preempt_count() & \
- (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET)))
- @@ -96,7 +105,11 @@
- /*
- * 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:
- @@ -145,6 +158,20 @@ extern void preempt_count_sub(int val);
- #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() \
- @@ -153,13 +180,25 @@ do { \
- 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())
-
- @@ -184,6 +223,13 @@ do { \
- __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 { \
- @@ -229,6 +275,7 @@ do { \
- #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 */
- @@ -249,10 +296,31 @@ do { \
- } 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 --git a/include/linux/printk.h b/include/linux/printk.h
- index 9729565c25ff..9cdca696b718 100644
- @@ -117,9 +117,11 @@ int no_printk(const char *fmt, ...)
- #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 --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
- index 5d5174b59802..327dddaf4c8f 100644
- @@ -279,6 +279,8 @@ unsigned int radix_tree_gang_lookup_slot(struct radix_tree_root *root,
- unsigned long first_index, unsigned int max_items);
- int radix_tree_preload(gfp_t gfp_mask);
- int radix_tree_maybe_preload(gfp_t gfp_mask);
- +void radix_tree_preload_end(void);
- +
- void radix_tree_init(void);
- void *radix_tree_tag_set(struct radix_tree_root *root,
- unsigned long index, unsigned int tag);
- @@ -301,11 +303,6 @@ unsigned long radix_tree_range_tag_if_tagged(struct radix_tree_root *root,
- int radix_tree_tagged(struct radix_tree_root *root, unsigned int tag);
- unsigned long radix_tree_locate_item(struct radix_tree_root *root, void *item);
-
- -static inline void radix_tree_preload_end(void)
- -{
- - preempt_enable();
- -}
- -
- /**
- * struct radix_tree_iter - radix tree iterator state
- *
- diff --git a/include/linux/random.h b/include/linux/random.h
- index 9c29122037f9..e7f2f8604918 100644
- @@ -20,7 +20,7 @@ struct random_ready_callback {
- 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 --git a/include/linux/rbtree.h b/include/linux/rbtree.h
- index a5aa7ae671f4..24ddffd25492 100644
- @@ -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 @@ static inline void rb_link_node(struct rb_node *node, struct rb_node *parent,
- *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 --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
- index a0189ba67fde..c2f5f955163d 100644
- @@ -169,6 +169,9 @@ void call_rcu(struct rcu_head *head,
-
- #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(struct rcu_head *head,
- */
- 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 @@ void synchronize_rcu(void);
- * 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 @@ static inline int rcu_preempt_depth(void)
- return 0;
- }
-
- +#define sched_rcu_preempt_depth() rcu_preempt_depth()
- +
- #endif /* #else #ifdef CONFIG_PREEMPT_RCU */
-
- /* Internal to kernel */
- @@ -489,7 +500,14 @@ extern struct lockdep_map rcu_callback_map;
- 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_unlock(void)
- 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_lock_bh(void)
- */
- 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 --git a/include/linux/rcutree.h b/include/linux/rcutree.h
- index 60d15a080d7c..436c9e62bfc6 100644
- @@ -44,7 +44,11 @@ static inline void rcu_virt_note_context_switch(int cpu)
- 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 @@ static inline void synchronize_rcu_bh_expedited(void)
- }
-
- 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(void);
- 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 @@ extern int rcu_scheduler_active __read_mostly;
-
- 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 --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h
- index 1abba5ce2a2f..30211c627511 100644
- @@ -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 rt_mutex {
- 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 @@ struct hrtimer_sleeper;
- # 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_destroy(struct rt_mutex *lock);
-
- 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 --git a/include/linux/rwlock_rt.h b/include/linux/rwlock_rt.h
- new file mode 100644
- index 000000000000..49ed2d45d3be
- @@ -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 --git a/include/linux/rwlock_types.h b/include/linux/rwlock_types.h
- index cc0072e93e36..d0da966ad7a0 100644
- @@ -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 @@ typedef struct {
- 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 --git a/include/linux/rwlock_types_rt.h b/include/linux/rwlock_types_rt.h
- new file mode 100644
- index 000000000000..b13832119591
- @@ -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 --git a/include/linux/rwsem.h b/include/linux/rwsem.h
- index 8f498cdde280..2b2148431f14 100644
- @@ -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 @@ extern void up_read_non_owner(struct rw_semaphore *sem);
- # define up_read_non_owner(sem) up_read(sem)
- #endif
-
- +#endif /* !PREEMPT_RT_FULL */
- +
- #endif /* _LINUX_RWSEM_H */
- diff --git a/include/linux/rwsem_rt.h b/include/linux/rwsem_rt.h
- new file mode 100644
- index 000000000000..f97860b2e2a4
- @@ -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 --git a/include/linux/sched.h b/include/linux/sched.h
- index e887c8d6f395..f37654adf12a 100644
- @@ -26,6 +26,7 @@ struct sched_param {
- #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 @@ extern void update_cpu_load_nohz(void);
- 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;
- @@ -235,17 +234,13 @@ extern char ___assert_task_state[1 - 2*!!(
-
- /* Convenience macros for the sake of wake_up */
- #define TASK_NORMAL (TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE)
- -#define TASK_ALL (TASK_NORMAL | __TASK_STOPPED | __TASK_TRACED)
-
- /* get_task_state() */
- #define TASK_REPORT (TASK_RUNNING | TASK_INTERRUPTIBLE | \
- 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 +306,11 @@ extern char ___assert_task_state[1 - 2*!!(
-
- #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
-
- @@ -979,9 +979,31 @@ struct wake_q_head {
- #define WAKE_Q(name) \
- 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);
- +extern void __wake_q_add(struct wake_q_head *head,
- + struct task_struct *task, bool sleeper);
- +static inline void wake_q_add(struct wake_q_head *head,
- + struct task_struct *task)
- +{
- + __wake_q_add(head, task, false);
- +}
- +
- +static inline void wake_q_add_sleeper(struct wake_q_head *head,
- + struct task_struct *task)
- +{
- + __wake_q_add(head, task, true);
- +}
- +
- +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:
- @@ -1389,6 +1411,7 @@ struct tlbflush_unmap_batch {
-
- 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 */
- @@ -1425,6 +1448,13 @@ struct task_struct {
- #endif
-
- unsigned int policy;
- +#ifdef CONFIG_PREEMPT_RT_FULL
- + int migrate_disable;
- + int migrate_disable_update;
- +# ifdef CONFIG_SCHED_DEBUG
- + int migrate_disable_atomic;
- +# endif
- +#endif
- int nr_cpus_allowed;
- cpumask_t cpus_allowed;
-
- @@ -1536,11 +1566,14 @@ struct task_struct {
- 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
- @@ -1552,6 +1585,9 @@ struct task_struct {
-
- 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 *ptracer_cred; /* Tracer's credentials at attach */
- @@ -1583,10 +1619,15 @@ struct task_struct {
- /* 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;
- @@ -1611,6 +1652,7 @@ struct task_struct {
- raw_spinlock_t pi_lock;
-
- struct wake_q_node wake_q;
- + struct wake_q_node wake_q_sleeper;
-
- #ifdef CONFIG_RT_MUTEXES
- /* PI waiters blocked on a rt_mutex held by this task */
- @@ -1810,6 +1852,12 @@ struct task_struct {
- 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;
- @@ -1826,8 +1874,22 @@ struct task_struct {
- 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 */
- @@ -1846,9 +1908,6 @@ extern int arch_task_struct_size __read_mostly;
- # 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
- @@ -2042,6 +2101,15 @@ extern struct pid *cad_pid;
- 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)
- @@ -2049,6 +2117,7 @@ static inline void put_task_struct(struct task_struct *t)
- 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,
- @@ -2087,6 +2156,7 @@ extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut,
- /*
- * 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 */
- @@ -2251,6 +2321,10 @@ extern void do_set_cpus_allowed(struct task_struct *p,
-
- 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)
- @@ -2263,6 +2337,9 @@ static inline int set_cpus_allowed_ptr(struct task_struct *p,
- 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
- @@ -2472,6 +2549,7 @@ extern void xtime_update(unsigned long ticks);
-
- 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);
- @@ -2595,12 +2673,24 @@ extern struct mm_struct * mm_alloc(void);
-
- /* 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 */
- @@ -2910,6 +3000,43 @@ static inline int test_tsk_need_resched(struct task_struct *tsk)
- 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);
- @@ -2941,6 +3068,51 @@ static inline int signal_pending_state(long state, struct task_struct *p)
- 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
- @@ -2962,12 +3134,16 @@ extern int __cond_resched_lock(spinlock_t *lock);
- __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)
- {
- @@ -3129,6 +3305,31 @@ static inline void set_task_cpu(struct task_struct *p, unsigned int cpu)
-
- #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 --git a/include/linux/seqlock.h b/include/linux/seqlock.h
- index e0582106ef4f..b14f4d2368aa 100644
- @@ -220,20 +220,30 @@ static inline int read_seqcount_retry(const seqcount_t *s, unsigned start)
- 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 @@ typedef struct {
- /*
- * 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 unsigned read_seqretry(const seqlock_t *sl, unsigned start)
- 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 @@ static inline unsigned long __write_seqlock_irqsave(seqlock_t *sl)
- 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 unsigned long __write_seqlock_irqsave(seqlock_t *sl)
- 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 --git a/include/linux/signal.h b/include/linux/signal.h
- index d80259afb9e5..ddd1e6866a54 100644
- @@ -233,6 +233,7 @@ static inline void init_sigpending(struct sigpending *sig)
- }
-
- 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 --git a/include/linux/skbuff.h b/include/linux/skbuff.h
- index b5421f6f155a..b05be76fc504 100644
- @@ -203,6 +203,7 @@ struct sk_buff_head {
-
- __u32 qlen;
- spinlock_t lock;
- + raw_spinlock_t raw_lock;
- };
-
- struct sk_buff;
- @@ -1462,6 +1463,12 @@ static inline void skb_queue_head_init(struct sk_buff_head *list)
- __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 --git a/include/linux/smp.h b/include/linux/smp.h
- index c4414074bd88..e6ab36aeaaab 100644
- @@ -185,6 +185,9 @@ static inline void smp_init(void) { }
- #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 --git a/include/linux/spinlock.h b/include/linux/spinlock.h
- index 47dd0cebd204..02928fa5499d 100644
- @@ -271,7 +271,11 @@ static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock)
- #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 @@ static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock)
- # 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 @@ static __always_inline void spin_unlock(spinlock_t *lock)
- 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 @@ extern int _atomic_dec_and_lock(atomic_t *atomic, spinlock_t *lock);
- #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 --git a/include/linux/spinlock_api_smp.h b/include/linux/spinlock_api_smp.h
- index 5344268e6e62..043263f30e81 100644
- @@ -189,6 +189,8 @@ static inline int __raw_spin_trylock_bh(raw_spinlock_t *lock)
- 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 --git a/include/linux/spinlock_rt.h b/include/linux/spinlock_rt.h
- new file mode 100644
- index 000000000000..7eb87584e843
- @@ -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 --git a/include/linux/spinlock_types.h b/include/linux/spinlock_types.h
- index 73548eb13a5d..10bac715ea96 100644
- @@ -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 --git a/include/linux/spinlock_types_nort.h b/include/linux/spinlock_types_nort.h
- new file mode 100644
- index 000000000000..f1dac1fb1d6a
- @@ -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 --git a/include/linux/spinlock_types_raw.h b/include/linux/spinlock_types_raw.h
- new file mode 100644
- index 000000000000..edffc4d53fc9
- @@ -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 --git a/include/linux/spinlock_types_rt.h b/include/linux/spinlock_types_rt.h
- new file mode 100644
- index 000000000000..9fd431967abc
- @@ -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 --git a/include/linux/srcu.h b/include/linux/srcu.h
- index f5f80c5643ac..ec1a8f01563c 100644
- @@ -84,10 +84,10 @@ int init_srcu_struct(struct srcu_struct *sp);
-
- 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 @@ void process_srcu(struct work_struct *work);
- */
- #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 --git a/include/linux/suspend.h b/include/linux/suspend.h
- index 8b6ec7ef0854..9b77d4cc929f 100644
- @@ -194,6 +194,12 @@ struct platform_freeze_ops {
- 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 --git a/include/linux/swait.h b/include/linux/swait.h
- new file mode 100644
- index 000000000000..83f004a72320
- @@ -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 --git a/include/linux/swap.h b/include/linux/swap.h
- index d8ca2eaa3a8b..19e038054914 100644
- @@ -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 @@ struct swap_info_struct {
- 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 @@ extern unsigned long nr_free_pagecache_pages(void);
-
-
- /* 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 --git a/include/linux/swork.h b/include/linux/swork.h
- new file mode 100644
- index 000000000000..f175fa9a6016
- @@ -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 --git a/include/linux/thread_info.h b/include/linux/thread_info.h
- index ff307b548ed3..be9f9dc6a4e1 100644
- @@ -102,7 +102,17 @@ static inline int test_ti_thread_flag(struct thread_info *ti, int flag)
- #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 --git a/include/linux/timer.h b/include/linux/timer.h
- index 61aa61dc410c..299d2b78591f 100644
- @@ -225,7 +225,7 @@ extern void add_timer(struct timer_list *timer);
-
- 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 --git a/include/linux/trace_events.h b/include/linux/trace_events.h
- index 311176f290b2..62d4bff5f477 100644
- @@ -66,6 +66,9 @@ struct trace_entry {
- 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 --git a/include/linux/uaccess.h b/include/linux/uaccess.h
- index 558129af828a..cf5c472bbc79 100644
- @@ -24,6 +24,7 @@ static __always_inline void pagefault_disabled_dec(void)
- */
- 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 @@ static inline void pagefault_enable(void)
- */
- barrier();
- pagefault_disabled_dec();
- + migrate_enable();
- }
-
- /*
- diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h
- index 4a29c75b146e..0a294e950df8 100644
- @@ -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 --git a/include/linux/vmstat.h b/include/linux/vmstat.h
- index 3e5d9075960f..7eaa847cd5a5 100644
- @@ -33,7 +33,9 @@ DECLARE_PER_CPU(struct vm_event_state, vm_event_states);
- */
- 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_event(enum vm_event_item item)
-
- 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 --git a/include/linux/wait.h b/include/linux/wait.h
- index 513b36f04dfd..981c8a840f96 100644
- @@ -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 --git a/include/net/dst.h b/include/net/dst.h
- index e4f450617919..16cd3ef62202 100644
- @@ -443,7 +443,7 @@ static inline void dst_confirm(struct dst_entry *dst)
- 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 --git a/include/net/neighbour.h b/include/net/neighbour.h
- index 8b683841e574..bf656008f6e7 100644
- @@ -446,7 +446,7 @@ static inline int neigh_hh_bridge(struct hh_cache *hh, struct sk_buff *skb)
- }
- #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 @@ struct neighbour_cb {
-
- #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 --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
- index c68926b4899c..dd0751e76065 100644
- @@ -70,6 +70,7 @@ struct netns_ipv4 {
-
- 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 --git a/include/trace/events/hist.h b/include/trace/events/hist.h
- new file mode 100644
- index 000000000000..f7710de1b1f3
- @@ -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 --git a/include/trace/events/latency_hist.h b/include/trace/events/latency_hist.h
- new file mode 100644
- index 000000000000..d3f2fbd560b1
- @@ -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 --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
- index fff846b512e6..73614ce1d204 100644
- @@ -134,58 +134,28 @@ DEFINE_EVENT(writeback_dirty_inode_template, writeback_dirty_inode,
- #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 @@ DECLARE_EVENT_CLASS(writeback_write_inode_template,
- __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 @@ DECLARE_EVENT_CLASS(writeback_write_inode_template,
- 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 @@ DECLARE_EVENT_CLASS(writeback_work_class,
- __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 @@ DECLARE_EVENT_CLASS(writeback_work_class,
- __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 @@ DECLARE_EVENT_CLASS(writeback_work_class,
- __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 @@ DECLARE_EVENT_CLASS(writeback_class,
- 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 @@ DECLARE_EVENT_CLASS(wbc_class,
- __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 @@ DECLARE_EVENT_CLASS(wbc_class,
- __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 @@ DECLARE_EVENT_CLASS(wbc_class,
- __entry->range_cyclic,
- __entry->range_start,
- __entry->range_end,
- - __get_str(cgroup)
- + __entry->cgroup_ino
- )
- )
-
- @@ -398,7 +368,7 @@ TRACE_EVENT(writeback_queue_io,
- __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 @@ TRACE_EVENT(writeback_queue_io,
- (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 @@ TRACE_EVENT(bdi_dirty_ratelimit,
- __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 @@ TRACE_EVENT(bdi_dirty_ratelimit,
- __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 @@ TRACE_EVENT(bdi_dirty_ratelimit,
- __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 @@ TRACE_EVENT(balance_dirty_pages,
- __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 @@ TRACE_EVENT(balance_dirty_pages,
- __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 @@ TRACE_EVENT(balance_dirty_pages,
- "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 @@ TRACE_EVENT(balance_dirty_pages,
- __entry->pause, /* ms */
- __entry->period, /* ms */
- __entry->think, /* ms */
- - __get_str(cgroup)
- + __entry->cgroup_ino
- )
- );
-
- @@ -609,8 +579,7 @@ TRACE_EVENT(writeback_sb_inodes_requeue,
- __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 @@ TRACE_EVENT(writeback_sb_inodes_requeue,
- __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 @@ DECLARE_EVENT_CLASS(writeback_single_inode_template,
- __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 @@ DECLARE_EVENT_CLASS(writeback_single_inode_template,
- __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 @@ DECLARE_EVENT_CLASS(writeback_single_inode_template,
- __entry->writeback_index,
- __entry->nr_to_write,
- __entry->wrote,
- - __get_str(cgroup)
- + __entry->cgroup_ino
- )
- );
-
- diff --git a/init/Kconfig b/init/Kconfig
- index 235c7a2c0d20..a7c81c0911da 100644
- @@ -498,7 +498,7 @@ config TINY_RCU
-
- 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_FANOUT_LEAF
-
- 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 TREE_RCU_TRACE
- 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 CFS_BANDWIDTH
- 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 @@ choice
-
- 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 SLUB
- 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 @@ endchoice
-
- 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 --git a/init/Makefile b/init/Makefile
- index 7bc47ee31c36..88cf473554e0 100644
- @@ -33,4 +33,4 @@ $(obj)/version.o: include/generated/compile.h
- include/generated/compile.h: FORCE
- @$($(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 --git a/init/main.c b/init/main.c
- index 49926d95442f..995cbb8d09b6 100644
- @@ -532,6 +532,7 @@ asmlinkage __visible void __init start_kernel(void)
- 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 --git a/ipc/msg.c b/ipc/msg.c
- index c6521c205cb4..996d89023552 100644
- @@ -183,20 +183,14 @@ static void ss_wakeup(struct list_head *h, int kill)
- }
- }
-
- -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 @@ static void freeque(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
- {
- 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 @@ static int msgctl_down(struct ipc_namespace *ns, int msqid, int cmd,
- 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 @@ static int msgctl_down(struct ipc_namespace *ns, int msqid, int cmd,
- /* 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 @@ static int msgctl_down(struct ipc_namespace *ns, int msqid, int cmd,
-
- out_unlock0:
- ipc_unlock_object(&msq->q_perm);
- + wake_up_q(&wake_q);
- out_unlock1:
- rcu_read_unlock();
- out_up:
- @@ -566,7 +564,8 @@ static int testmsg(struct msg_msg *msg, long type, int mode)
- 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 @@ static inline int pipelined_send(struct msg_queue *msq, struct msg_msg *msg)
-
- 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 @@ long do_msgsnd(int msqid, long mtype, void __user *mtext,
- struct msg_msg *msg;
- int err;
- struct ipc_namespace *ns;
- + WAKE_Q(wake_q);
-
- ns = current->nsproxy->ipc_ns;
-
- @@ -698,7 +684,7 @@ long do_msgsnd(int msqid, long mtype, void __user *mtext,
- 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 @@ long do_msgsnd(int msqid, long mtype, void __user *mtext,
-
- 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 @@ long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp, int msgfl
- 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 --git a/ipc/sem.c b/ipc/sem.c
- index 9862c3d1c26d..ef34d7376697 100644
- @@ -708,6 +708,13 @@ static int perform_atomic_semop(struct sem_array *sma, struct sem_queue *q)
- 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 @@ static void wake_up_sem_queue_prepare(struct list_head *pt,
- q->pid = error;
-
- list_add_tail(&q->list, pt);
- +#endif
- }
-
- /**
- @@ -732,6 +740,7 @@ static void wake_up_sem_queue_prepare(struct list_head *pt,
- */
- 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 @@ static void wake_up_sem_queue_do(struct list_head *pt)
- }
- if (did_something)
- preempt_enable();
- +#endif
- }
-
- static void unlink_queue(struct sem_array *sma, struct sem_queue *q)
- diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks
- index ebdb0043203a..b9e6aa7e5aa6 100644
- @@ -225,11 +225,11 @@ config ARCH_SUPPORTS_ATOMIC_RMW
-
- 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 --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt
- index 3f9c97419f02..11dbe26a8279 100644
- @@ -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 @@ config PREEMPT_VOLUNTARY
-
- 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 @@ config PREEMPT
- 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 --git a/kernel/cgroup.c b/kernel/cgroup.c
- index 4cb94b678e9f..8c41ee8a6fee 100644
- @@ -4741,10 +4741,10 @@ static void css_free_rcu_fn(struct rcu_head *rcu_head)
- 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;
-
- @@ -4783,8 +4783,8 @@ static void css_release(struct percpu_ref *ref)
- 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,
- @@ -5401,6 +5401,7 @@ static int __init cgroup_wq_init(void)
- */
- 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 --git a/kernel/cpu.c b/kernel/cpu.c
- index 40d20bf5de28..0be18c1684d8 100644
- @@ -75,8 +75,8 @@ static struct {
- #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 @@ static struct {
- #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 @@ static int take_cpu_down(void *_param)
- /* 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 @@ static int _cpu_down(unsigned int cpu, int tasks_frozen)
- 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 @@ static int _cpu_down(unsigned int cpu, int tasks_frozen)
- 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 @@ static int _cpu_down(unsigned int cpu, int tasks_frozen)
- 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 --git a/kernel/cpu_pm.c b/kernel/cpu_pm.c
- index 009cc9a17d95..10f4640f991e 100644
- @@ -22,14 +22,13 @@
- #include <linux/spinlock.h>
- #include <linux/syscore_ops.h>
-
- -static DEFINE_RWLOCK(cpu_pm_notifier_lock);
- -static RAW_NOTIFIER_HEAD(cpu_pm_notifier_chain);
- +static ATOMIC_NOTIFIER_HEAD(cpu_pm_notifier_chain);
-
- static int cpu_pm_notify(enum cpu_pm_event event, int nr_to_call, int *nr_calls)
- {
- int ret;
-
- - ret = __raw_notifier_call_chain(&cpu_pm_notifier_chain, event, NULL,
- + ret = __atomic_notifier_call_chain(&cpu_pm_notifier_chain, event, NULL,
- nr_to_call, nr_calls);
-
- return notifier_to_errno(ret);
- @@ -47,14 +46,7 @@ static int cpu_pm_notify(enum cpu_pm_event event, int nr_to_call, int *nr_calls)
- */
- int cpu_pm_register_notifier(struct notifier_block *nb)
- {
- - unsigned long flags;
- - int ret;
- -
- - write_lock_irqsave(&cpu_pm_notifier_lock, flags);
- - ret = raw_notifier_chain_register(&cpu_pm_notifier_chain, nb);
- - write_unlock_irqrestore(&cpu_pm_notifier_lock, flags);
- -
- - return ret;
- + return atomic_notifier_chain_register(&cpu_pm_notifier_chain, nb);
- }
- EXPORT_SYMBOL_GPL(cpu_pm_register_notifier);
-
- @@ -69,14 +61,7 @@ EXPORT_SYMBOL_GPL(cpu_pm_register_notifier);
- */
- int cpu_pm_unregister_notifier(struct notifier_block *nb)
- {
- - unsigned long flags;
- - int ret;
- -
- - write_lock_irqsave(&cpu_pm_notifier_lock, flags);
- - ret = raw_notifier_chain_unregister(&cpu_pm_notifier_chain, nb);
- - write_unlock_irqrestore(&cpu_pm_notifier_lock, flags);
- -
- - return ret;
- + return atomic_notifier_chain_unregister(&cpu_pm_notifier_chain, nb);
- }
- EXPORT_SYMBOL_GPL(cpu_pm_unregister_notifier);
-
- @@ -100,7 +85,6 @@ int cpu_pm_enter(void)
- int nr_calls;
- int ret = 0;
-
- - read_lock(&cpu_pm_notifier_lock);
- ret = cpu_pm_notify(CPU_PM_ENTER, -1, &nr_calls);
- if (ret)
- /*
- @@ -108,7 +92,6 @@ int cpu_pm_enter(void)
- * PM entry who are notified earlier to prepare for it.
- */
- cpu_pm_notify(CPU_PM_ENTER_FAILED, nr_calls - 1, NULL);
- - read_unlock(&cpu_pm_notifier_lock);
-
- return ret;
- }
- @@ -128,13 +111,7 @@ EXPORT_SYMBOL_GPL(cpu_pm_enter);
- */
- int cpu_pm_exit(void)
- {
- - int ret;
- -
- - read_lock(&cpu_pm_notifier_lock);
- - ret = cpu_pm_notify(CPU_PM_EXIT, -1, NULL);
- - read_unlock(&cpu_pm_notifier_lock);
- -
- - return ret;
- + return cpu_pm_notify(CPU_PM_EXIT, -1, NULL);
- }
- EXPORT_SYMBOL_GPL(cpu_pm_exit);
-
- @@ -159,7 +136,6 @@ int cpu_cluster_pm_enter(void)
- int nr_calls;
- int ret = 0;
-
- - read_lock(&cpu_pm_notifier_lock);
- ret = cpu_pm_notify(CPU_CLUSTER_PM_ENTER, -1, &nr_calls);
- if (ret)
- /*
- @@ -167,7 +143,6 @@ int cpu_cluster_pm_enter(void)
- * PM entry who are notified earlier to prepare for it.
- */
- cpu_pm_notify(CPU_CLUSTER_PM_ENTER_FAILED, nr_calls - 1, NULL);
- - read_unlock(&cpu_pm_notifier_lock);
-
- return ret;
- }
- @@ -190,13 +165,7 @@ EXPORT_SYMBOL_GPL(cpu_cluster_pm_enter);
- */
- int cpu_cluster_pm_exit(void)
- {
- - int ret;
- -
- - read_lock(&cpu_pm_notifier_lock);
- - ret = cpu_pm_notify(CPU_CLUSTER_PM_EXIT, -1, NULL);
- - read_unlock(&cpu_pm_notifier_lock);
- -
- - return ret;
- + return cpu_pm_notify(CPU_CLUSTER_PM_EXIT, -1, NULL);
- }
- EXPORT_SYMBOL_GPL(cpu_cluster_pm_exit);
-
- diff --git a/kernel/cpuset.c b/kernel/cpuset.c
- index dd3ae6ee064d..8dc21a9ac292 100644
- @@ -284,7 +284,7 @@ static struct cpuset top_cpuset = {
- */
-
- static DEFINE_MUTEX(cpuset_mutex);
- -static DEFINE_SPINLOCK(callback_lock);
- +static DEFINE_RAW_SPINLOCK(callback_lock);
-
- static struct workqueue_struct *cpuset_migrate_mm_wq;
-
- @@ -907,9 +907,9 @@ static void update_cpumasks_hier(struct cpuset *cs, struct cpumask *new_cpus)
- continue;
- rcu_read_unlock();
-
- - spin_lock_irq(&callback_lock);
- + raw_spin_lock_irq(&callback_lock);
- cpumask_copy(cp->effective_cpus, new_cpus);
- - spin_unlock_irq(&callback_lock);
- + raw_spin_unlock_irq(&callback_lock);
-
- WARN_ON(!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) &&
- !cpumask_equal(cp->cpus_allowed, cp->effective_cpus));
- @@ -974,9 +974,9 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
- if (retval < 0)
- return retval;
-
- - spin_lock_irq(&callback_lock);
- + raw_spin_lock_irq(&callback_lock);
- cpumask_copy(cs->cpus_allowed, trialcs->cpus_allowed);
- - spin_unlock_irq(&callback_lock);
- + raw_spin_unlock_irq(&callback_lock);
-
- /* use trialcs->cpus_allowed as a temp variable */
- update_cpumasks_hier(cs, trialcs->cpus_allowed);
- @@ -1185,9 +1185,9 @@ static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems)
- continue;
- rcu_read_unlock();
-
- - spin_lock_irq(&callback_lock);
- + raw_spin_lock_irq(&callback_lock);
- cp->effective_mems = *new_mems;
- - spin_unlock_irq(&callback_lock);
- + raw_spin_unlock_irq(&callback_lock);
-
- WARN_ON(!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) &&
- !nodes_equal(cp->mems_allowed, cp->effective_mems));
- @@ -1255,9 +1255,9 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs,
- if (retval < 0)
- goto done;
-
- - spin_lock_irq(&callback_lock);
- + raw_spin_lock_irq(&callback_lock);
- cs->mems_allowed = trialcs->mems_allowed;
- - spin_unlock_irq(&callback_lock);
- + raw_spin_unlock_irq(&callback_lock);
-
- /* use trialcs->mems_allowed as a temp variable */
- update_nodemasks_hier(cs, &trialcs->mems_allowed);
- @@ -1348,9 +1348,9 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs,
- spread_flag_changed = ((is_spread_slab(cs) != is_spread_slab(trialcs))
- || (is_spread_page(cs) != is_spread_page(trialcs)));
-
- - spin_lock_irq(&callback_lock);
- + raw_spin_lock_irq(&callback_lock);
- cs->flags = trialcs->flags;
- - spin_unlock_irq(&callback_lock);
- + raw_spin_unlock_irq(&callback_lock);
-
- if (!cpumask_empty(trialcs->cpus_allowed) && balance_flag_changed)
- rebuild_sched_domains_locked();
- @@ -1762,7 +1762,7 @@ static int cpuset_common_seq_show(struct seq_file *sf, void *v)
- cpuset_filetype_t type = seq_cft(sf)->private;
- int ret = 0;
-
- - spin_lock_irq(&callback_lock);
- + raw_spin_lock_irq(&callback_lock);
-
- switch (type) {
- case FILE_CPULIST:
- @@ -1781,7 +1781,7 @@ static int cpuset_common_seq_show(struct seq_file *sf, void *v)
- ret = -EINVAL;
- }
-
- - spin_unlock_irq(&callback_lock);
- + raw_spin_unlock_irq(&callback_lock);
- return ret;
- }
-
- @@ -1996,12 +1996,12 @@ static int cpuset_css_online(struct cgroup_subsys_state *css)
-
- cpuset_inc();
-
- - spin_lock_irq(&callback_lock);
- + raw_spin_lock_irq(&callback_lock);
- if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys)) {
- cpumask_copy(cs->effective_cpus, parent->effective_cpus);
- cs->effective_mems = parent->effective_mems;
- }
- - spin_unlock_irq(&callback_lock);
- + raw_spin_unlock_irq(&callback_lock);
-
- if (!test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags))
- goto out_unlock;
- @@ -2028,12 +2028,12 @@ static int cpuset_css_online(struct cgroup_subsys_state *css)
- }
- rcu_read_unlock();
-
- - spin_lock_irq(&callback_lock);
- + raw_spin_lock_irq(&callback_lock);
- cs->mems_allowed = parent->mems_allowed;
- cs->effective_mems = parent->mems_allowed;
- cpumask_copy(cs->cpus_allowed, parent->cpus_allowed);
- cpumask_copy(cs->effective_cpus, parent->cpus_allowed);
- - spin_unlock_irq(&callback_lock);
- + raw_spin_unlock_irq(&callback_lock);
- out_unlock:
- mutex_unlock(&cpuset_mutex);
- return 0;
- @@ -2072,7 +2072,7 @@ static void cpuset_css_free(struct cgroup_subsys_state *css)
- static void cpuset_bind(struct cgroup_subsys_state *root_css)
- {
- mutex_lock(&cpuset_mutex);
- - spin_lock_irq(&callback_lock);
- + raw_spin_lock_irq(&callback_lock);
-
- if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys)) {
- cpumask_copy(top_cpuset.cpus_allowed, cpu_possible_mask);
- @@ -2083,7 +2083,7 @@ static void cpuset_bind(struct cgroup_subsys_state *root_css)
- top_cpuset.mems_allowed = top_cpuset.effective_mems;
- }
-
- - spin_unlock_irq(&callback_lock);
- + raw_spin_unlock_irq(&callback_lock);
- mutex_unlock(&cpuset_mutex);
- }
-
- @@ -2184,12 +2184,12 @@ hotplug_update_tasks_legacy(struct cpuset *cs,
- {
- bool is_empty;
-
- - spin_lock_irq(&callback_lock);
- + raw_spin_lock_irq(&callback_lock);
- cpumask_copy(cs->cpus_allowed, new_cpus);
- cpumask_copy(cs->effective_cpus, new_cpus);
- cs->mems_allowed = *new_mems;
- cs->effective_mems = *new_mems;
- - spin_unlock_irq(&callback_lock);
- + raw_spin_unlock_irq(&callback_lock);
-
- /*
- * Don't call update_tasks_cpumask() if the cpuset becomes empty,
- @@ -2226,10 +2226,10 @@ hotplug_update_tasks(struct cpuset *cs,
- if (nodes_empty(*new_mems))
- *new_mems = parent_cs(cs)->effective_mems;
-
- - spin_lock_irq(&callback_lock);
- + raw_spin_lock_irq(&callback_lock);
- cpumask_copy(cs->effective_cpus, new_cpus);
- cs->effective_mems = *new_mems;
- - spin_unlock_irq(&callback_lock);
- + raw_spin_unlock_irq(&callback_lock);
-
- if (cpus_updated)
- update_tasks_cpumask(cs);
- @@ -2322,21 +2322,21 @@ static void cpuset_hotplug_workfn(struct work_struct *work)
-
- /* synchronize cpus_allowed to cpu_active_mask */
- if (cpus_updated) {
- - spin_lock_irq(&callback_lock);
- + raw_spin_lock_irq(&callback_lock);
- if (!on_dfl)
- cpumask_copy(top_cpuset.cpus_allowed, &new_cpus);
- cpumask_copy(top_cpuset.effective_cpus, &new_cpus);
- - spin_unlock_irq(&callback_lock);
- + raw_spin_unlock_irq(&callback_lock);
- /* we don't mess with cpumasks of tasks in top_cpuset */
- }
-
- /* synchronize mems_allowed to N_MEMORY */
- if (mems_updated) {
- - spin_lock_irq(&callback_lock);
- + raw_spin_lock_irq(&callback_lock);
- if (!on_dfl)
- top_cpuset.mems_allowed = new_mems;
- top_cpuset.effective_mems = new_mems;
- - spin_unlock_irq(&callback_lock);
- + raw_spin_unlock_irq(&callback_lock);
- update_tasks_nodemask(&top_cpuset);
- }
-
- @@ -2441,11 +2441,11 @@ void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask)
- {
- unsigned long flags;
-
- - spin_lock_irqsave(&callback_lock, flags);
- + raw_spin_lock_irqsave(&callback_lock, flags);
- rcu_read_lock();
- guarantee_online_cpus(task_cs(tsk), pmask);
- rcu_read_unlock();
- - spin_unlock_irqrestore(&callback_lock, flags);
- + raw_spin_unlock_irqrestore(&callback_lock, flags);
- }
-
- void cpuset_cpus_allowed_fallback(struct task_struct *tsk)
- @@ -2493,11 +2493,11 @@ nodemask_t cpuset_mems_allowed(struct task_struct *tsk)
- nodemask_t mask;
- unsigned long flags;
-
- - spin_lock_irqsave(&callback_lock, flags);
- + raw_spin_lock_irqsave(&callback_lock, flags);
- rcu_read_lock();
- guarantee_online_mems(task_cs(tsk), &mask);
- rcu_read_unlock();
- - spin_unlock_irqrestore(&callback_lock, flags);
- + raw_spin_unlock_irqrestore(&callback_lock, flags);
-
- return mask;
- }
- @@ -2589,14 +2589,14 @@ int __cpuset_node_allowed(int node, gfp_t gfp_mask)
- return 1;
-
- /* Not hardwall and node outside mems_allowed: scan up cpusets */
- - spin_lock_irqsave(&callback_lock, flags);
- + raw_spin_lock_irqsave(&callback_lock, flags);
-
- rcu_read_lock();
- cs = nearest_hardwall_ancestor(task_cs(current));
- allowed = node_isset(node, cs->mems_allowed);
- rcu_read_unlock();
-
- - spin_unlock_irqrestore(&callback_lock, flags);
- + raw_spin_unlock_irqrestore(&callback_lock, flags);
- return allowed;
- }
-
- diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c
- index 77777d918676..3203e9dee9f8 100644
- @@ -554,7 +554,6 @@ int vkdb_printf(enum kdb_msgsrc src, const char *fmt, va_list ap)
- 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 @@ int vkdb_printf(enum kdb_msgsrc src, const char *fmt, va_list ap)
- 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 @@ int vkdb_printf(enum kdb_msgsrc src, const char *fmt, va_list ap)
- } else {
- __release(kdb_printf_lock);
- }
- - kdb_trap_printk = saved_trap_printk;
- preempt_enable();
- return retlen;
- }
- @@ -865,9 +861,11 @@ int kdb_printf(const char *fmt, ...)
- 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 --git a/kernel/events/core.c b/kernel/events/core.c
- index 8f75386e61a7..489cf0e1ac9c 100644
- @@ -802,6 +802,7 @@ static void __perf_mux_hrtimer_init(struct perf_cpu_context *cpuctx, int cpu)
- 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)
- @@ -7241,6 +7242,7 @@ static void perf_swevent_init_hrtimer(struct perf_event *event)
-
- 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 --git a/kernel/exit.c b/kernel/exit.c
- index ffba5df4abd5..e199407f8831 100644
- @@ -144,7 +144,7 @@ static void __exit_signal(struct task_struct *tsk)
- * 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 --git a/kernel/fork.c b/kernel/fork.c
- index ac00f14208b7..9859641947bd 100644
- @@ -109,7 +109,7 @@ int max_threads; /* tunable limit on nr_threads */
-
- 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)
- @@ -246,7 +246,9 @@ static inline void put_signal_struct(struct signal_struct *sig)
- 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);
- @@ -263,7 +265,18 @@ void __put_task_struct(struct task_struct *tsk)
- 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) { }
-
- @@ -388,6 +401,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
- tsk->splice_pipe = NULL;
- tsk->task_frag.page = NULL;
- tsk->wake_q.next = NULL;
- + tsk->wake_q_sleeper.next = NULL;
-
- account_kernel_stack(ti, 1);
-
- @@ -699,6 +713,19 @@ void __mmdrop(struct mm_struct *mm)
- }
- 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.
- */
- @@ -1249,6 +1276,9 @@ static void rt_mutex_init_task(struct task_struct *p)
- */
- 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;
- @@ -1375,15 +1405,16 @@ static struct task_struct *copy_process(unsigned long clone_flags,
- 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 --git a/kernel/futex.c b/kernel/futex.c
- index fc68462801de..b577ac5dc4a0 100644
- @@ -815,7 +815,9 @@ void exit_pi_state_list(struct task_struct *curr)
- * 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 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this,
- 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 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this,
- 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 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this,
- 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 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this,
- * 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 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags,
- 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;
- @@ -2143,11 +2158,11 @@ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked)
- * 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;
- }
- @@ -2694,7 +2709,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
- {
- struct hrtimer_sleeper timeout, *to = NULL;
- struct rt_mutex_waiter rt_waiter;
- - 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;
- @@ -2719,10 +2734,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
- * 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))
- @@ -2753,20 +2765,55 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
- /* 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) {
- @@ -2775,7 +2822,8 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
- * 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);
- if (ret && rt_mutex_owner(&q.pi_state->pi_mutex) == current)
- rt_mutex_unlock(&q.pi_state->pi_mutex);
- @@ -2784,7 +2832,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
- * the requeue_pi() code acquired for us.
- */
- free_pi_state(q.pi_state);
- - spin_unlock(q.lock_ptr);
- + spin_unlock(&hb2->lock);
- }
- } else {
- struct rt_mutex *pi_mutex;
- @@ -2799,7 +2847,8 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
- 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 --git a/kernel/irq/handle.c b/kernel/irq/handle.c
- index 57bff7857e87..6c65c9252991 100644
- @@ -134,6 +134,8 @@ void __irq_wake_thread(struct irq_desc *desc, struct irqaction *action)
-
- 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 @@ irqreturn_t handle_irq_event_percpu(struct irq_desc *desc)
- 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 --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
- index 239e2ae2c947..0b73349a42d5 100644
- @@ -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 --git a/kernel/irq/manage.c b/kernel/irq/manage.c
- index a079ed14f230..2cf55df7ad0e 100644
- @@ -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 @@ static int __init setup_forced_irqthreads(char *arg)
- return 0;
- }
- early_param("threadirqs", setup_forced_irqthreads);
- +# endif
- #endif
-
- static void __synchronize_hardirq(struct irq_desc *desc)
- @@ -181,6 +183,62 @@ static inline void
- 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 @@ int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask,
-
- 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 @@ int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m)
- }
- 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 @@ static void irq_affinity_notify(struct work_struct *work)
- 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 @@ irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify)
- 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 @@ irq_forced_thread_fn(struct irq_desc *desc, struct irqaction *action)
- 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 @@ static int irq_thread(void *data)
- 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);
- }
-
- @@ -1317,6 +1406,9 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
- 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);
-
- @@ -1970,7 +2062,7 @@ EXPORT_SYMBOL_GPL(irq_get_irqchip_state);
- * 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 --git a/kernel/irq/settings.h b/kernel/irq/settings.h
- index 320579d89091..2df2d4445b1e 100644
- @@ -16,6 +16,7 @@ enum {
- _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 @@ enum {
- #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 @@ irq_settings_clr_and_set(struct irq_desc *desc, u32 clr, u32 set)
- 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 --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
- index 32144175458d..ed26f2554972 100644
- @@ -444,6 +444,10 @@ MODULE_PARM_DESC(noirqdebug, "Disable irq lockup detection when true");
-
- 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 @@ module_param(irqfixup, int, 0644);
-
- 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 --git a/kernel/irq_work.c b/kernel/irq_work.c
- index bcf107ce0854..2899ba0d23d1 100644
- @@ -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 @@ void __weak arch_irq_work_raise(void)
- */
- 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 @@ bool irq_work_queue_on(struct irq_work *work, int cpu)
- 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 @@ EXPORT_SYMBOL_GPL(irq_work_queue_on);
- /* 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 @@ bool irq_work_queue(struct irq_work *work)
- /* 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 @@ bool irq_work_needs_cpu(void)
- 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 @@ static void irq_work_run_list(struct llist_head *list)
- 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 @@ static void irq_work_run_list(struct llist_head *list)
- 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 @@ void irq_work_tick(void)
-
- 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 --git a/kernel/ksysfs.c b/kernel/ksysfs.c
- index e83b26464061..c0e08d1cf33e 100644
- @@ -136,6 +136,15 @@ KERNEL_ATTR_RO(vmcoreinfo);
-
- #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 @@ static struct attribute * kernel_attrs[] = {
- &vmcoreinfo_attr.attr,
- #endif
- &rcu_expedited_attr.attr,
- +#ifdef CONFIG_PREEMPT_RT_FULL
- + &realtime_attr.attr,
- +#endif
- NULL
- };
-
- diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile
- index 8e96f6cc2a4a..447b03082d88 100644
- @@ -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_mutex-debug.o = $(CC_FLAGS_FTRACE)
- 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-$(CONFIG_RT_MUTEXES) += rtmutex.o
- obj-$(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 --git a/kernel/locking/lglock.c b/kernel/locking/lglock.c
- index 951cfcd10b4a..57e0ea72c28a 100644
- @@ -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 @@ void lg_double_lock(struct lglock *lg, int cpu1, int cpu2)
- 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 @@ void lg_global_unlock(struct lglock *lg)
-
- 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 --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
- index 0e2c4911ba61..aed13ffa9fd3 100644
- @@ -668,6 +668,7 @@ look_up_lock_class(struct lockdep_map *lock, unsigned int subclass)
- struct lockdep_subclass_key *key;
- struct list_head *hash_head;
- struct lock_class *class;
- + bool is_static = false;
-
- #ifdef CONFIG_DEBUG_LOCKDEP
- /*
- @@ -695,10 +696,23 @@ look_up_lock_class(struct lockdep_map *lock, unsigned int subclass)
-
- /*
- * Static locks do not have their class-keys yet - for them the key
- - * is the lock object itself:
- + * is the lock object itself. If the lock is in the per cpu area,
- + * the canonical address of the lock (per cpu offset removed) is
- + * used.
- */
- - if (unlikely(!lock->key))
- - lock->key = (void *)lock;
- + if (unlikely(!lock->key)) {
- + unsigned long can_addr, addr = (unsigned long)lock;
- +
- + if (__is_kernel_percpu_address(addr, &can_addr))
- + lock->key = (void *)can_addr;
- + else if (__is_module_percpu_address(addr, &can_addr))
- + lock->key = (void *)can_addr;
- + else if (static_obj(lock))
- + lock->key = (void *)lock;
- + else
- + return ERR_PTR(-EINVAL);
- + is_static = true;
- + }
-
- /*
- * NOTE: the class-key must be unique. For dynamic locks, a static
- @@ -730,7 +744,7 @@ look_up_lock_class(struct lockdep_map *lock, unsigned int subclass)
- }
- }
-
- - return NULL;
- + return is_static || static_obj(lock->key) ? NULL : ERR_PTR(-EINVAL);
- }
-
- /*
- @@ -748,19 +762,18 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
- DEBUG_LOCKS_WARN_ON(!irqs_disabled());
-
- class = look_up_lock_class(lock, subclass);
- - if (likely(class))
- + if (likely(!IS_ERR_OR_NULL(class)))
- goto out_set_class_cache;
-
- /*
- * Debug-check: all keys must be persistent!
- - */
- - if (!static_obj(lock->key)) {
- + */
- + if (IS_ERR(class)) {
- debug_locks_off();
- printk("INFO: trying to register non-static key.\n");
- printk("the code is fine but needs lockdep annotation.\n");
- printk("turning off the locking correctness validator.\n");
- dump_stack();
- -
- return NULL;
- }
-
- @@ -3285,7 +3298,7 @@ static int match_held_lock(struct held_lock *hlock, struct lockdep_map *lock)
- * Clearly if the lock hasn't been acquired _ever_, we're not
- * holding it either, so report failure.
- */
- - if (!class)
- + if (IS_ERR_OR_NULL(class))
- return 0;
-
- /*
- @@ -3532,6 +3545,7 @@ static void check_flags(unsigned long flags)
- }
- }
-
- +#ifndef CONFIG_PREEMPT_RT_FULL
- /*
- * We dont accurately track softirq state in e.g.
- * hardirq contexts (such as on 4KSTACKS), so only
- @@ -3546,6 +3560,7 @@ static void check_flags(unsigned long flags)
- DEBUG_LOCKS_WARN_ON(!current->softirqs_enabled);
- }
- }
- +#endif
-
- if (!debug_locks)
- print_irqtrace_events(current);
- @@ -3984,7 +3999,7 @@ void lockdep_reset_lock(struct lockdep_map *lock)
- * If the class exists we look it up and zap it:
- */
- class = look_up_lock_class(lock, j);
- - if (class)
- + if (!IS_ERR_OR_NULL(class))
- zap_class(class);
- }
- /*
- diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c
- index d580b7d6ee6d..4680c502b65b 100644
- @@ -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 --git a/kernel/locking/rt.c b/kernel/locking/rt.c
- new file mode 100644
- index 000000000000..d4ab61c1848b
- @@ -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 --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
- index b066724d7a5b..bb42267257ad 100644
- @@ -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 +21,8 @@
- #include <linux/sched/rt.h>
- #include <linux/sched/deadline.h>
- #include <linux/timer.h>
- +#include <linux/ww_mutex.h>
- +#include <linux/blkdev.h>
-
- #include "rtmutex_common.h"
-
- @@ -133,6 +140,12 @@ static void fixup_rt_mutex_waiters(struct rt_mutex *lock)
- WRITE_ONCE(*p, owner & ~RT_MUTEX_HAS_WAITERS);
- }
-
- +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.
- @@ -163,13 +176,14 @@ static inline void mark_rt_mutex_waiters(struct rt_mutex *lock)
- * 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:
- @@ -211,11 +225,12 @@ static inline void mark_rt_mutex_waiters(struct rt_mutex *lock)
- /*
- * 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
- @@ -412,6 +427,14 @@ static bool rt_mutex_cond_detect_deadlock(struct rt_mutex_waiter *waiter,
- 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:
- */
- @@ -419,7 +442,8 @@ int max_lock_depth = 1024;
-
- 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;
- }
-
- /*
- @@ -497,7 +521,6 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
- 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);
- @@ -540,7 +563,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
- /*
- * [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.
- @@ -556,7 +579,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
- * 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;
-
- /*
- @@ -624,7 +647,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
- * 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;
- }
- @@ -655,7 +678,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
- /*
- * 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);
-
- /*
- @@ -663,14 +686,14 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
- * 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.
- @@ -685,8 +708,8 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
- 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)
- @@ -707,7 +730,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
- 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);
-
- /*
- @@ -718,21 +741,24 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
- * 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)) {
- @@ -786,8 +812,8 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
- 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
- @@ -810,28 +836,46 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
- 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
- @@ -867,8 +911,10 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
- * 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
- @@ -886,14 +932,10 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
- * 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
- @@ -916,7 +958,7 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
- * 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
- @@ -925,7 +967,7 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
- */
- 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. */
- @@ -942,12 +984,444 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
- 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,
- @@ -958,7 +1432,6 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
- 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
- @@ -972,7 +1445,24 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
- 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;
- @@ -985,18 +1475,18 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
-
- 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;
- @@ -1005,7 +1495,7 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
- /* 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
- @@ -1021,12 +1511,12 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
- */
- 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;
- }
- @@ -1035,15 +1525,15 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
- * 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);
-
- @@ -1065,15 +1555,18 @@ static void mark_wakeup_next_waiter(struct wake_q_head *wake_q,
- */
- 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_sleeper(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,
- @@ -1081,13 +1574,12 @@ static void remove_waiter(struct rt_mutex *lock,
- {
- 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
- @@ -1096,7 +1588,7 @@ static void remove_waiter(struct rt_mutex *lock,
- 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);
-
- @@ -1106,9 +1598,10 @@ static void remove_waiter(struct rt_mutex *lock,
- __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
- @@ -1120,12 +1613,12 @@ static void remove_waiter(struct rt_mutex *lock,
- /* 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);
- }
-
- /*
- @@ -1142,17 +1635,17 @@ void rt_mutex_adjust_pi(struct task_struct *task)
- 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);
- }
- @@ -1161,16 +1654,17 @@ void rt_mutex_adjust_pi(struct task_struct *task)
- * __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;
-
- @@ -1179,27 +1673,28 @@ __rt_mutex_slowlock(struct rt_mutex *lock, int state,
- if (try_to_take_rt_mutex(lock, current, waiter))
- break;
-
- - /*
- - * TASK_INTERRUPTIBLE checks for signals and
- - * timeout. Ignored otherwise.
- - */
- - if (unlikely(state == TASK_INTERRUPTIBLE)) {
- - /* Signal pending? */
- - if (signal_pending(current))
- - ret = -EINTR;
- - if (timeout && !timeout->task)
- - ret = -ETIMEDOUT;
- + if (timeout && !timeout->task) {
- + ret = -ETIMEDOUT;
- + break;
- + }
- + if (signal_pending_state(state, current)) {
- + ret = -EINTR;
- + break;
- + }
- +
- + if (ww_ctx && ww_ctx->acquired > 0) {
- + ret = __mutex_lock_check_stamp(lock, ww_ctx);
- if (ret)
- break;
- }
-
- - raw_spin_unlock(&lock->wait_lock);
- + 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);
- }
-
- @@ -1227,26 +1722,112 @@ static void rt_mutex_handle_deadlock(int res, int detect_deadlock,
- }
- }
-
- +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;
- }
-
- @@ -1260,13 +1841,23 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
-
- 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);
- }
-
- /*
- @@ -1275,7 +1866,7 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
- */
- 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))
- @@ -1291,6 +1882,7 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
- */
- static inline int rt_mutex_slowtrylock(struct rt_mutex *lock)
- {
- + unsigned long flags;
- int ret;
-
- /*
- @@ -1302,10 +1894,10 @@ static inline int rt_mutex_slowtrylock(struct rt_mutex *lock)
- 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);
-
- @@ -1315,7 +1907,7 @@ static inline int rt_mutex_slowtrylock(struct rt_mutex *lock)
- */
- fixup_rt_mutex_waiters(lock);
-
- - raw_spin_unlock(&lock->wait_lock);
- + raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
-
- return ret;
- }
- @@ -1325,9 +1917,13 @@ static inline int rt_mutex_slowtrylock(struct rt_mutex *lock)
- * 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);
-
- @@ -1366,10 +1962,10 @@ static bool __sched rt_mutex_slowunlock(struct rt_mutex *lock,
- */
- 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);
- }
-
- /*
- @@ -1378,9 +1974,9 @@ static bool __sched rt_mutex_slowunlock(struct rt_mutex *lock,
- *
- * 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;
- @@ -1394,31 +1990,50 @@ static bool __sched rt_mutex_slowunlock(struct rt_mutex *lock,
- */
- 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);
- + }
- +
- + /*
- + * If rt_mutex blocks, the function sched_submit_work will not call
- + * blk_schedule_flush_plug (because tsk_is_pi_blocked would be true).
- + * We must call blk_schedule_flush_plug here, if we don't call it,
- + * a deadlock in device mapper may happen.
- + */
- + if (unlikely(blk_needs_flush_plug(current)))
- + blk_schedule_flush_plug(current);
- +
- + 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);
- + }
- +
- + if (unlikely(blk_needs_flush_plug(current)))
- + blk_schedule_flush_plug(current);
- +
- + return slowfn(lock, state, timeout, chwalk, ww_ctx);
- }
-
- static inline int
- @@ -1435,17 +2050,20 @@ rt_mutex_fasttrylock(struct rt_mutex *lock,
- 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)
- @@ -1462,7 +2080,7 @@ void __sched rt_mutex_lock(struct rt_mutex *lock)
- {
- 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);
-
- @@ -1479,7 +2097,7 @@ int __sched rt_mutex_lock_interruptible(struct rt_mutex *lock)
- {
- 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);
-
- @@ -1492,10 +2110,29 @@ int rt_mutex_timed_futex_lock(struct rt_mutex *lock,
- 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
- @@ -1516,6 +2153,7 @@ rt_mutex_timed_lock(struct rt_mutex *lock, struct hrtimer_sleeper *timeout)
-
- return rt_mutex_timed_fastlock(lock, TASK_INTERRUPTIBLE, timeout,
- RT_MUTEX_MIN_CHAINWALK,
- + NULL,
- rt_mutex_slowlock);
- }
- EXPORT_SYMBOL_GPL(rt_mutex_timed_lock);
- @@ -1533,7 +2171,11 @@ EXPORT_SYMBOL_GPL(rt_mutex_timed_lock);
- */
- 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);
- @@ -1559,13 +2201,14 @@ EXPORT_SYMBOL_GPL(rt_mutex_unlock);
- * 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);
- }
-
- /**
- @@ -1598,13 +2241,12 @@ EXPORT_SYMBOL_GPL(rt_mutex_destroy);
- 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
- @@ -1619,7 +2261,7 @@ EXPORT_SYMBOL_GPL(__rt_mutex_init);
- 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);
- @@ -1660,13 +2302,42 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
- {
- 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);
- @@ -1681,10 +2352,10 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
- 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);
-
- @@ -1732,12 +2403,12 @@ int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
- {
- 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);
- @@ -1748,7 +2419,93 @@ int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
- */
- 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 --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h
- index e317e1cbb3eb..f457c7574920 100644
- @@ -27,6 +27,7 @@ struct rt_mutex_waiter {
- 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;
- @@ -98,6 +99,9 @@ enum rtmutex_chainwalk {
- /*
- * 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);
- @@ -111,7 +115,8 @@ extern int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
- 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
- @@ -120,4 +125,14 @@ extern void rt_mutex_adjust_prio(struct task_struct *task);
- # 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 --git a/kernel/locking/spinlock.c b/kernel/locking/spinlock.c
- index db3ccb1dd614..909779647bd1 100644
- @@ -124,8 +124,11 @@ void __lockfunc __raw_##op##_lock_bh(locktype##_t *lock) \
- * __[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 @@ void __lockfunc _raw_spin_unlock_bh(raw_spinlock_t *lock)
- 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 @@ void __lockfunc _raw_write_unlock_bh(rwlock_t *lock)
- 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 --git a/kernel/locking/spinlock_debug.c b/kernel/locking/spinlock_debug.c
- index 0374a596cffa..94970338d518 100644
- @@ -31,6 +31,7 @@ void __raw_spin_lock_init(raw_spinlock_t *lock, const char *name,
-
- 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 @@ void __rwlock_init(rwlock_t *lock, const char *name,
- }
-
- EXPORT_SYMBOL(__rwlock_init);
- +#endif
-
- static void spin_dump(raw_spinlock_t *lock, const char *msg)
- {
- @@ -159,6 +161,7 @@ void do_raw_spin_unlock(raw_spinlock_t *lock)
- 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 @@ void do_raw_write_unlock(rwlock_t *lock)
- debug_write_unlock(lock);
- arch_write_unlock(&lock->raw_lock);
- }
- +
- +#endif
- diff --git a/kernel/module.c b/kernel/module.c
- index 0a56098d3738..33c1954b07ed 100644
- @@ -682,16 +682,7 @@ static void percpu_modcopy(struct module *mod,
- memcpy(per_cpu_ptr(mod->percpu, cpu), from, size);
- }
-
- -/**
- - * is_module_percpu_address - test whether address is from module static percpu
- - * @addr: address to test
- - *
- - * Test whether @addr belongs to module static percpu area.
- - *
- - * RETURNS:
- - * %true if @addr is from module static percpu area
- - */
- -bool is_module_percpu_address(unsigned long addr)
- +bool __is_module_percpu_address(unsigned long addr, unsigned long *can_addr)
- {
- struct module *mod;
- unsigned int cpu;
- @@ -705,9 +696,11 @@ bool is_module_percpu_address(unsigned long addr)
- continue;
- for_each_possible_cpu(cpu) {
- void *start = per_cpu_ptr(mod->percpu, cpu);
- + void *va = (void *)addr;
-
- - if ((void *)addr >= start &&
- - (void *)addr < start + mod->percpu_size) {
- + if (va >= start && va < start + mod->percpu_size) {
- + if (can_addr)
- + *can_addr = (unsigned long) (va - start);
- preempt_enable();
- return true;
- }
- @@ -718,6 +711,20 @@ bool is_module_percpu_address(unsigned long addr)
- return false;
- }
-
- +/**
- + * is_module_percpu_address - test whether address is from module static percpu
- + * @addr: address to test
- + *
- + * Test whether @addr belongs to module static percpu area.
- + *
- + * RETURNS:
- + * %true if @addr is from module static percpu area
- + */
- +bool is_module_percpu_address(unsigned long addr)
- +{
- + return __is_module_percpu_address(addr, NULL);
- +}
- +
- #else /* ... !CONFIG_SMP */
-
- static inline void __percpu *mod_percpu(struct module *mod)
- @@ -749,6 +756,11 @@ bool is_module_percpu_address(unsigned long addr)
- return false;
- }
-
- +bool __is_module_percpu_address(unsigned long addr, unsigned long *can_addr)
- +{
- + return false;
- +}
- +
- #endif /* CONFIG_SMP */
-
- #define MODINFO_ATTR(field) \
- diff --git a/kernel/panic.c b/kernel/panic.c
- index 1d07cf9af849..e182564e6533 100644
- @@ -61,6 +61,37 @@ void __weak panic_smp_self_stop(void)
- 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 __weak panic_smp_self_stop(void)
- */
- 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 @@ void panic(const char *fmt, ...)
- * 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 u64 oops_id;
-
- 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 --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
- index 3124cebaec31..c1b981521dd0 100644
- @@ -285,6 +285,8 @@ static int create_image(int platform_mode)
-
- 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 @@ static int create_image(int platform_mode)
- syscore_resume();
-
- Enable_irqs:
- + system_state = SYSTEM_RUNNING;
- local_irq_enable();
-
- Enable_cpus:
- @@ -438,6 +441,7 @@ static int resume_target_kernel(bool platform_mode)
- goto Enable_cpus;
-
- local_irq_disable();
- + system_state = SYSTEM_SUSPEND;
-
- error = syscore_suspend();
- if (error)
- @@ -471,6 +475,7 @@ static int resume_target_kernel(bool platform_mode)
- syscore_resume();
-
- Enable_irqs:
- + system_state = SYSTEM_RUNNING;
- local_irq_enable();
-
- Enable_cpus:
- @@ -556,6 +561,7 @@ int hibernation_platform_enter(void)
- goto Enable_cpus;
-
- local_irq_disable();
- + system_state = SYSTEM_SUSPEND;
- syscore_suspend();
- if (pm_wakeup_pending()) {
- error = -EAGAIN;
- @@ -568,6 +574,7 @@ int hibernation_platform_enter(void)
-
- Power_up:
- syscore_resume();
- + system_state = SYSTEM_RUNNING;
- local_irq_enable();
-
- Enable_cpus:
- @@ -642,6 +649,10 @@ static void power_down(void)
- cpu_relax();
- }
-
- +#ifndef CONFIG_SUSPEND
- +bool pm_in_action;
- +#endif
- +
- /**
- * hibernate - Carry out system hibernation, including saving the image.
- */
- @@ -654,6 +665,8 @@ int hibernate(void)
- 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 @@ int hibernate(void)
- atomic_inc(&snapshot_device_available);
- Unlock:
- unlock_system_sleep();
- + pm_in_action = false;
- return error;
- }
-
- diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
- index f9fe133c13e2..393bc342c586 100644
- @@ -359,6 +359,8 @@ static int suspend_enter(suspend_state_t state, bool *wakeup)
- 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 @@ static int suspend_enter(suspend_state_t state, bool *wakeup)
- syscore_resume();
- }
-
- + system_state = SYSTEM_RUNNING;
- +
- arch_suspend_enable_irqs();
- BUG_ON(irqs_disabled());
-
- @@ -518,6 +522,8 @@ static int enter_state(suspend_state_t state)
- 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 @@ int pm_suspend(suspend_state_t state)
- 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 @@ int pm_suspend(suspend_state_t state)
- } else {
- suspend_stats.success++;
- }
- + pm_in_action = false;
- return error;
- }
- EXPORT_SYMBOL(pm_suspend);
- diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
- index 0b5613554769..99deb2617308 100644
- @@ -241,6 +241,65 @@ struct printk_log {
- */
- 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 @@ static int syslog_print_all(char __user *buf, int size, bool clear)
- {
- char *text;
- int len = 0;
- + int attempts = 0;
-
- text = kmalloc(LOG_LINE_MAX + PREFIX_MAX, GFP_KERNEL);
- if (!text)
- @@ -1214,7 +1274,14 @@ static int syslog_print_all(char __user *buf, int size, bool clear)
- 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 @@ static int syslog_print_all(char __user *buf, int size, bool clear)
- 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 @@ static int syslog_print_all(char __user *buf, int size, bool clear)
- 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 @@ static int syslog_print_all(char __user *buf, int size, bool clear)
- clear_seq = log_next_seq;
- clear_idx = log_next_idx;
- }
- +out:
- raw_spin_unlock_irq(&logbuf_lock);
-
- kfree(text);
- @@ -1443,6 +1527,12 @@ static void call_console_drivers(int level,
- 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 @@ static void call_console_drivers(int level,
- else
- con->write(con, text, len);
- }
- + migrate_enable();
- }
-
- /*
- @@ -1518,6 +1609,15 @@ static inline int can_use_console(unsigned int cpu)
- 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 @@ asmlinkage int vprintk_emit(int facility, int level,
- /* 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 @@ asmlinkage int vprintk_emit(int facility, int level,
- * 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 @@ asmlinkage int vprintk_emit(int facility, int level,
- */
- if (console_trylock_for_printk())
- console_unlock();
- - preempt_enable();
- + migrate_enable();
- lockdep_on();
- }
-
- @@ -1961,26 +2067,6 @@ DEFINE_PER_CPU(printk_func_t, printk_func);
-
- #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 @@ static void console_cont_flush(char *text, size_t size)
- 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 @@ void console_unlock(void)
- 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 @@ void console_unblank(void)
- {
- 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 --git a/kernel/ptrace.c b/kernel/ptrace.c
- index 5e2cd1030702..d4467d4eb488 100644
- @@ -142,7 +142,14 @@ static bool ptrace_freeze_traced(struct task_struct *task)
-
- 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 --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
- index d89328e260df..5bb3364a6284 100644
- @@ -390,6 +390,7 @@ static struct rcu_torture_ops rcu_ops = {
- .name = "rcu"
- };
-
- +#ifndef CONFIG_PREEMPT_RT_FULL
- /*
- * Definitions for rcu_bh torture testing.
- */
- @@ -429,6 +430,12 @@ static struct rcu_torture_ops rcu_bh_ops = {
- .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 --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
- index 8a62cbfe1f2f..f60894c6b35c 100644
- @@ -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 @@ void rcu_sched_qs(void)
- }
- }
-
- +#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 @@ void rcu_bh_qs(void)
- __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 @@ EXPORT_SYMBOL_GPL(rcu_batches_started_sched);
- /*
- * 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 @@ unsigned long rcu_batches_completed_sched(void)
- }
- 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 @@ void rcu_bh_force_quiescent_state(void)
- }
- 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 @@ void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
- 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;
- @@ -1602,7 +1633,6 @@ static int rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp)
- 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,
- @@ -1623,7 +1653,7 @@ static void rcu_gp_kthread_wake(struct rcu_state *rsp)
- !READ_ONCE(rsp->gp_flags) ||
- !rsp->gp_kthread)
- return;
- - wake_up(&rsp->gp_wq);
- + swake_up(&rsp->gp_wq);
- }
-
- /*
- @@ -2003,6 +2033,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
- 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);
- @@ -2041,7 +2072,9 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
- 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);
- @@ -2088,7 +2121,7 @@ static int __noreturn rcu_gp_kthread(void *arg)
- 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;
- @@ -2118,7 +2151,7 @@ static int __noreturn rcu_gp_kthread(void *arg)
- 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. */
- @@ -2242,7 +2275,7 @@ static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags)
- 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. */
- }
-
- /*
- @@ -2903,7 +2936,7 @@ static void force_quiescent_state(struct rcu_state *rsp)
- }
- 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. */
- }
-
- /*
- @@ -2946,18 +2979,17 @@ __rcu_process_callbacks(struct rcu_state *rsp)
- /*
- * 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,
- @@ -2969,18 +3001,105 @@ static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp)
- {
- if (unlikely(!READ_ONCE(rcu_scheduler_fully_active)))
- return;
- - if (likely(!rsp->boost)) {
- - rcu_do_batch(rsp, rdp);
- - return;
- - }
- - invoke_rcu_callbacks_kthread();
- + 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)
- {
- - if (cpu_online(smp_processor_id()))
- - raise_softirq(RCU_SOFTIRQ);
- + 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;
- + }
- + }
- + *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 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)
- +{
- + 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.
- @@ -3126,6 +3245,7 @@ void call_rcu_sched(struct rcu_head *head, rcu_callback_t func)
- }
- EXPORT_SYMBOL_GPL(call_rcu_sched);
-
- +#ifndef CONFIG_PREEMPT_RT_FULL
- /*
- * Queue an RCU callback for invocation after a quicker grace period.
- */
- @@ -3134,6 +3254,7 @@ void call_rcu_bh(struct rcu_head *head, rcu_callback_t func)
- __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.
- @@ -3225,6 +3346,7 @@ void synchronize_sched(void)
- }
- EXPORT_SYMBOL_GPL(synchronize_sched);
-
- +#ifndef CONFIG_PREEMPT_RT_FULL
- /**
- * synchronize_rcu_bh - wait until an rcu_bh grace period has elapsed.
- *
- @@ -3251,6 +3373,7 @@ void synchronize_rcu_bh(void)
- wait_rcu_gp(call_rcu_bh);
- }
- EXPORT_SYMBOL_GPL(synchronize_rcu_bh);
- +#endif
-
- /**
- * get_state_synchronize_rcu - Snapshot current RCU state
- @@ -3536,7 +3659,7 @@ static void __rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
- 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;
- }
- @@ -3793,7 +3916,7 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp)
- 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);
- @@ -3801,7 +3924,7 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp)
- 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;
- }
- @@ -4113,6 +4236,7 @@ static void _rcu_barrier(struct rcu_state *rsp)
- mutex_unlock(&rsp->barrier_mutex);
- }
-
- +#ifndef CONFIG_PREEMPT_RT_FULL
- /**
- * rcu_barrier_bh - Wait until all in-flight call_rcu_bh() callbacks complete.
- */
- @@ -4121,6 +4245,7 @@ void rcu_barrier_bh(void)
- _rcu_barrier(&rcu_bh_state);
- }
- EXPORT_SYMBOL_GPL(rcu_barrier_bh);
- +#endif
-
- /**
- * rcu_barrier_sched - Wait for in-flight call_rcu_sched() callbacks.
- @@ -4467,8 +4592,8 @@ static void __init rcu_init_one(struct rcu_state *rsp,
- }
- }
-
- - 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)
- @@ -4588,12 +4713,13 @@ void __init rcu_init(void)
-
- 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 --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
- index 9fb4e238d4dc..c75834d8de24 100644
- @@ -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 @@ struct rcu_node {
- /* 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 @@ struct rcu_data {
- 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 @@ struct rcu_state {
- 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 @@ struct rcu_state {
- 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 list_head rcu_struct_flavors;
- */
- 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 @@ void call_rcu(struct rcu_head *head, rcu_callback_t func);
- 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 zero_cpu_stall_ticks(struct rcu_data *rdp);
- 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 --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
- index 32cbe72bf545..45e3e3e02a5c 100644
- @@ -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 @@ DEFINE_PER_CPU(char, rcu_cpu_has_work);
-
- #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 @@ void rcu_read_unlock_special(struct task_struct *t)
- }
-
- /* 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 @@ static void rcu_preempt_check_callbacks(void)
- 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 @@ void exit_rcu(void)
-
- #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 @@ static void rcu_initiate_boost_trace(struct rcu_node *rnp)
-
- #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
- @@ -1114,23 +1101,6 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags)
- }
- }
-
- -/*
- - * 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 @@ static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
- 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 @@ static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu)
- 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 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags)
- 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 @@ static void rcu_prepare_kthreads(int cpu)
-
- #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 @@ int rcu_needs_cpu(u64 basemono, u64 *nextevt)
- 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 @@ static bool __maybe_unused rcu_try_advance_all_cbs(void)
- 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 @@ int rcu_needs_cpu(u64 basemono, u64 *nextevt)
- *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 @@ early_param("rcu_nocb_poll", parse_rcu_nocb_poll);
- * 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 @@ static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq)
- 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 @@ static void wake_nocb_leader(struct rcu_data *rdp, bool force)
- 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 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp)
- */
- 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 @@ static void nocb_leader_wait(struct rcu_data *my_rdp)
- /* 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 @@ static void nocb_leader_wait(struct rcu_data *my_rdp)
- * 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 @@ static void nocb_follower_wait(struct rcu_data *rdp)
- 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"! */
- @@ -2365,7 +2265,7 @@ void __init rcu_init_nohz(void)
- 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;
- }
-
- @@ -2515,7 +2415,7 @@ static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu)
- 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)
- {
- }
-
- @@ -2523,6 +2423,11 @@ static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq)
- {
- }
-
- +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 --git a/kernel/rcu/update.c b/kernel/rcu/update.c
- index 5f748c5a40f0..9a3904603ff6 100644
- @@ -276,6 +276,7 @@ int rcu_read_lock_held(void)
- }
- 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 @@ int rcu_read_lock_bh_held(void)
- return in_softirq() || irqs_disabled();
- }
- EXPORT_SYMBOL_GPL(rcu_read_lock_bh_held);
- +#endif
-
- #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
-
- diff --git a/kernel/relay.c b/kernel/relay.c
- index 0b4570cfacae..60684be39f22 100644
- @@ -336,6 +336,10 @@ static void wakeup_readers(unsigned long data)
- {
- 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 @@ static void __relay_reset(struct rchan_buf *buf, unsigned int init)
- 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 @@ size_t relay_switch_subbuf(struct rchan_buf *buf, size_t length)
- 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 --git a/kernel/sched/Makefile b/kernel/sched/Makefile
- index 67687973ce80..01b9994b367a 100644
- @@ -13,7 +13,7 @@ endif
-
- 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 --git a/kernel/sched/completion.c b/kernel/sched/completion.c
- index 8d0f35debf35..b62cf6400fe0 100644
- @@ -30,10 +30,10 @@ void complete(struct completion *x)
- {
- 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 @@ void complete_all(struct completion *x)
- {
- 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 @@ do_wait_for_common(struct completion *x,
- 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 @@ __wait_for_common(struct completion *x,
- {
- 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 @@ bool try_wait_for_completion(struct completion *x)
- 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 @@ bool completion_done(struct completion *x)
- * 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 --git a/kernel/sched/core.c b/kernel/sched/core.c
- index 9d6b3d869592..3e2e4c3de066 100644
- @@ -260,7 +260,11 @@ late_initcall(sched_init_debug);
- * 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 @@ static void init_rq_hrtick(struct rq *rq)
-
- 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)
- @@ -518,9 +523,15 @@ static bool set_nr_if_polling(struct task_struct *p)
- #endif
- #endif
-
- -void wake_q_add(struct wake_q_head *head, struct task_struct *task)
- +void __wake_q_add(struct wake_q_head *head, struct task_struct *task,
- + bool sleeper)
- {
- - struct wake_q_node *node = &task->wake_q;
- + struct wake_q_node *node;
- +
- + if (sleeper)
- + node = &task->wake_q_sleeper;
- + else
- + node = &task->wake_q;
-
- /*
- * Atomically grab the task, if ->wake_q is !nil already it means
- @@ -542,24 +553,33 @@ void wake_q_add(struct wake_q_head *head, struct task_struct *task)
- 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;
-
- while (node != WAKE_Q_TAIL) {
- struct task_struct *task;
-
- - task = container_of(node, struct task_struct, wake_q);
- + if (sleeper)
- + task = container_of(node, struct task_struct, wake_q_sleeper);
- + else
- + task = container_of(node, struct task_struct, wake_q);
- BUG_ON(!task);
- /* task can safely be re-inserted now */
- node = node->next;
- - task->wake_q.next = NULL;
- + if (sleeper)
- + task->wake_q_sleeper.next = NULL;
- + else
- + task->wake_q.next = NULL;
-
- /*
- * 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 +615,38 @@ void resched_curr(struct rq *rq)
- 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);
- @@ -617,11 +669,14 @@ void resched_cpu(int cpu)
- */
- 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) {
- @@ -640,6 +695,8 @@ int get_nohz_timer_target(void)
- cpu = housekeeping_any_cpu();
- unlock:
- rcu_read_unlock();
- +preempt_en_rt:
- + preempt_enable_rt();
- return cpu;
- }
- /*
- @@ -1166,7 +1223,8 @@ void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_ma
- p->nr_cpus_allowed = cpumask_weight(new_mask);
- }
-
- -void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
- +static void __do_set_cpus_allowed_tail(struct task_struct *p,
- + const struct cpumask *new_mask)
- {
- struct rq *rq = task_rq(p);
- bool queued, running;
- @@ -1195,6 +1253,98 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
- enqueue_task(rq, p, ENQUEUE_RESTORE);
- }
-
- +void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
- +{
- + if (__migrate_disabled(p)) {
- + lockdep_assert_held(&p->pi_lock);
- +
- + cpumask_copy(&p->cpus_allowed, new_mask);
- +#if defined(CONFIG_PREEMPT_RT_FULL) && defined(CONFIG_SMP)
- + p->migrate_disable_update = 1;
- +#endif
- + return;
- + }
- + __do_set_cpus_allowed_tail(p, new_mask);
- +}
- +
- +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
- @@ -1234,7 +1384,7 @@ static int __set_cpus_allowed_ptr(struct task_struct *p,
- 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);
- @@ -1410,6 +1560,18 @@ int migrate_swap(struct task_struct *cur, struct task_struct *p)
- 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.
- *
- @@ -1454,7 +1616,7 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state)
- * 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();
- }
- @@ -1469,7 +1631,8 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state)
- 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);
-
- @@ -1626,7 +1789,7 @@ int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags)
- {
- 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);
-
- /*
- @@ -1706,10 +1869,6 @@ static inline void ttwu_activate(struct rq *rq, struct task_struct *p, int en_fl
- {
- 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));
- }
-
- /*
- @@ -1936,8 +2095,27 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
- */
- 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);
-
- @@ -2028,52 +2206,6 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
- return success;
- }
-
- -/**
- - * 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.
- @@ -2092,6 +2224,18 @@ int wake_up_process(struct task_struct *p)
- }
- 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_UNINTERRUPTIBLE, WF_LOCK_SLEEPER);
- +}
- +
- int wake_up_state(struct task_struct *p, unsigned int state)
- {
- return try_to_wake_up(p, state, 0);
- @@ -2278,6 +2422,9 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
- 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);
- @@ -2602,8 +2749,12 @@ static struct rq *finish_task_switch(struct task_struct *prev)
- 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);
- @@ -2934,16 +3085,6 @@ u64 scheduler_tick_max_deferment(void)
- }
- #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))
-
- @@ -2965,7 +3106,7 @@ void preempt_count_add(int val)
- 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
- @@ -2992,7 +3133,7 @@ void preempt_count_sub(int val)
- #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);
- @@ -3047,6 +3188,114 @@ static inline void schedule_debug(struct task_struct *prev)
- 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;
- +
- + if (p->migrate_disable_update) {
- + unsigned long flags;
- + struct rq *rq;
- +
- + rq = task_rq_lock(p, &flags);
- + update_rq_clock(rq);
- +
- + __do_set_cpus_allowed_tail(p, &p->cpus_allowed);
- + task_rq_unlock(rq, p, &flags);
- +
- + p->migrate_disable_update = 0;
- +
- + WARN_ON(smp_processor_id() != task_cpu(p));
- + if (!cpumask_test_cpu(task_cpu(p), &p->cpus_allowed)) {
- + const struct cpumask *cpu_valid_mask = cpu_active_mask;
- + struct migration_arg arg;
- + unsigned int dest_cpu;
- +
- + if (p->flags & PF_KTHREAD) {
- + /*
- + * Kernel threads are allowed on online && !active CPUs
- + */
- + cpu_valid_mask = cpu_online_mask;
- + }
- + dest_cpu = cpumask_any_and(cpu_valid_mask, &p->cpus_allowed);
- + arg.task = p;
- + arg.dest_cpu = dest_cpu;
- +
- + unpin_current_cpu();
- + preempt_lazy_enable();
- + preempt_enable();
- + stop_one_cpu(task_cpu(p), migration_cpu_stop, &arg);
- + tlb_migrate_finish(p->mm);
- + return;
- + }
- + }
- +
- + unpin_current_cpu();
- + preempt_enable();
- + preempt_lazy_enable();
- +}
- +EXPORT_SYMBOL(migrate_enable);
- +#endif
- +
- /*
- * Pick up the highest-prio task:
- */
- @@ -3171,19 +3420,6 @@ static void __sched notrace __schedule(bool preempt)
- } 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;
- }
- @@ -3193,6 +3429,7 @@ static void __sched notrace __schedule(bool preempt)
-
- 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;
-
- @@ -3214,8 +3451,19 @@ static void __sched notrace __schedule(bool preempt)
-
- 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.
- @@ -3224,6 +3472,12 @@ static inline void sched_submit_work(struct task_struct *tsk)
- 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;
- @@ -3234,6 +3488,7 @@ asmlinkage __visible void __sched schedule(void)
- __schedule(false);
- sched_preempt_enable_no_resched();
- } while (need_resched());
- + sched_update_worker(tsk);
- }
- EXPORT_SYMBOL(schedule);
-
- @@ -3282,6 +3537,30 @@ static void __sched notrace preempt_schedule_common(void)
- } 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
- @@ -3296,6 +3575,8 @@ asmlinkage __visible void __sched notrace preempt_schedule(void)
- */
- if (likely(!preemptible()))
- return;
- + if (!preemptible_lazy())
- + return;
-
- preempt_schedule_common();
- }
- @@ -3322,6 +3603,8 @@ asmlinkage __visible void __sched notrace preempt_schedule_notrace(void)
-
- if (likely(!preemptible()))
- return;
- + if (!preemptible_lazy())
- + return;
-
- do {
- preempt_disable_notrace();
- @@ -3331,7 +3614,16 @@ asmlinkage __visible void __sched notrace preempt_schedule_notrace(void)
- * 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();
- @@ -4675,6 +4967,7 @@ int __cond_resched_lock(spinlock_t *lock)
- }
- EXPORT_SYMBOL(__cond_resched_lock);
-
- +#ifndef CONFIG_PREEMPT_RT_FULL
- int __sched __cond_resched_softirq(void)
- {
- BUG_ON(!in_softirq());
- @@ -4688,6 +4981,7 @@ int __sched __cond_resched_softirq(void)
- return 0;
- }
- EXPORT_SYMBOL(__cond_resched_softirq);
- +#endif
-
- /**
- * yield - yield the current processor to other threads.
- @@ -5054,7 +5348,9 @@ void init_idle(struct task_struct *idle, int cpu)
-
- /* 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:
- */
- @@ -5195,6 +5491,8 @@ void sched_setnuma(struct task_struct *p, int nid)
- #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.
- @@ -5209,7 +5507,11 @@ void idle_task_exit(void)
- 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;
- }
-
- /*
- @@ -5581,6 +5883,10 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
-
- 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
- }
- @@ -5911,6 +6217,7 @@ static int init_rootdomain(struct root_domain *rd)
- rd->rto_cpu = -1;
- raw_spin_lock_init(&rd->rto_lock);
- init_irq_work(&rd->rto_push_work, rto_push_irq_work_func);
- + rd->rto_push_work.flags |= IRQ_WORK_HARD_IRQ;
- #endif
-
- init_dl_bw(&rd->dl_bw);
- @@ -7585,7 +7892,7 @@ void __init sched_init(void)
- #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 --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c
- index 5a75b08cfd85..5be58820465c 100644
- @@ -103,10 +103,10 @@ int cpudl_find(struct cpudl *cp, struct task_struct *p,
- 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 --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c
- index 981fcd7dc394..11e9705bf937 100644
- @@ -103,11 +103,11 @@ int cpupri_find(struct cpupri *cp, struct task_struct *p,
- 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 --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
- index a1aecbedf5b1..558b98af241d 100644
- @@ -685,7 +685,7 @@ static cputime_t get_vtime_delta(struct task_struct *tsk)
- {
- 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 @@ static void __vtime_account_system(struct task_struct *tsk)
-
- 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 @@ void vtime_guest_enter(struct task_struct *tsk)
- * 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 vtime_account_idle(struct task_struct *tsk)
-
- 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 @@ cputime_t task_gtime(struct task_struct *t)
- 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 @@ fetch_task_cputime(struct task_struct *t,
- *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 @@ fetch_task_cputime(struct task_struct *t,
- *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 @@ fetch_task_cputime(struct task_struct *t,
- 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 --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
- index a996f7356216..645c18fe2075 100644
- @@ -134,7 +134,7 @@ static void inc_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
- {
- 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 @@ static void dec_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
- {
- 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);
- @@ -702,6 +702,7 @@ void init_dl_task_timer(struct sched_dl_entity *dl_se)
-
- hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
- timer->function = dl_task_timer;
- + timer->irqsafe = 1;
- }
-
- /*
- @@ -1039,7 +1040,7 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
-
- 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);
- }
-
- @@ -1117,9 +1118,9 @@ select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags)
- * 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 &&
- @@ -1140,7 +1141,7 @@ static void check_preempt_equal_dl(struct rq *rq, struct task_struct *p)
- * 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;
-
- @@ -1148,7 +1149,7 @@ static void check_preempt_equal_dl(struct rq *rq, struct task_struct *p)
- * 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;
-
- @@ -1262,7 +1263,7 @@ static void put_prev_task_dl(struct rq *rq, struct task_struct *p)
- {
- 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);
- }
-
- @@ -1385,7 +1386,7 @@ static int find_later_rq(struct task_struct *task)
- if (unlikely(!later_mask))
- return -1;
-
- - if (task->nr_cpus_allowed == 1)
- + if (tsk_nr_cpus_allowed(task) == 1)
- return -1;
-
- /*
- @@ -1491,7 +1492,7 @@ static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq)
- 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);
- @@ -1530,7 +1531,7 @@ static struct task_struct *pick_next_pushable_dl_task(struct rq *rq)
-
- 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));
- @@ -1569,7 +1570,7 @@ static int push_dl_task(struct rq *rq)
- */
- 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;
- }
- @@ -1716,9 +1717,9 @@ static void task_woken_dl(struct rq *rq, struct task_struct *p)
- {
- 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);
- }
- @@ -1819,7 +1820,7 @@ static void switched_to_dl(struct rq *rq, struct task_struct *p)
- {
- 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);
- #endif
- if (dl_task(rq->curr))
- diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
- index 641511771ae6..a2d69b883623 100644
- @@ -251,6 +251,9 @@ void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq)
- 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 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
- #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 --git a/kernel/sched/fair.c b/kernel/sched/fair.c
- index 812069b66f47..ddf1424bcc78 100644
- @@ -3166,7 +3166,7 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
- 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 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
- return;
-
- if (delta > ideal_runtime)
- - resched_curr(rq_of(cfs_rq));
- + resched_curr_lazy(rq_of(cfs_rq));
- }
-
- static void
- @@ -3330,7 +3330,7 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued)
- * 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 @@ static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec)
- * 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
- @@ -4144,7 +4144,7 @@ static void hrtick_start_fair(struct rq *rq, struct task_struct *p)
-
- if (delta < 0) {
- if (rq->curr == p)
- - resched_curr(rq);
- + resched_curr_lazy(rq);
- return;
- }
- hrtick_start(rq, delta);
- @@ -5232,7 +5232,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
- 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
- @@ -7983,7 +7983,7 @@ static void task_fork_fair(struct task_struct *p)
- * '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;
- @@ -8008,7 +8008,7 @@ prio_changed_fair(struct rq *rq, struct task_struct *p, int oldprio)
- */
- if (rq->curr == p) {
- if (p->prio > oldprio)
- - resched_curr(rq);
- + resched_curr_lazy(rq);
- } else
- check_preempt_curr(rq, p, 0);
- }
- diff --git a/kernel/sched/features.h b/kernel/sched/features.h
- index 69631fa46c2f..6d28fcd08872 100644
- @@ -45,11 +45,19 @@ SCHED_FEAT(LB_BIAS, true)
- */
- 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 --git a/kernel/sched/rt.c b/kernel/sched/rt.c
- index 95fefb364dab..14f2d740edab 100644
- @@ -47,6 +47,7 @@ void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime)
-
- 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;
- }
-
- @@ -315,7 +316,7 @@ static void inc_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
- 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);
- @@ -332,7 +333,7 @@ static void dec_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
- 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);
- @@ -1251,7 +1252,7 @@ enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags)
-
- 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);
- }
-
- @@ -1340,7 +1341,7 @@ select_task_rq_rt(struct task_struct *p, int cpu, int sd_flag, int flags)
- * 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);
-
- @@ -1364,7 +1365,7 @@ static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p)
- * 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;
-
- @@ -1372,7 +1373,7 @@ static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p)
- * 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;
-
- @@ -1506,7 +1507,7 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
- * 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);
- }
-
- @@ -1556,7 +1557,7 @@ static int find_lowest_rq(struct task_struct *task)
- 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))
- @@ -1688,7 +1689,7 @@ static struct task_struct *pick_next_pushable_task(struct rq *rq)
-
- 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));
- @@ -2060,9 +2061,9 @@ static void task_woken_rt(struct rq *rq, struct task_struct *p)
- {
- 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);
- }
- @@ -2135,7 +2136,7 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p)
- */
- 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);
- #endif /* CONFIG_SMP */
- if (p->prio < rq->curr->prio)
- diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
- index 448a8266ceea..e45a90ce57f7 100644
- @@ -1110,6 +1110,7 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
- #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
- @@ -1309,6 +1310,15 @@ extern void init_sched_fair_class(void);
- 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 --git a/kernel/sched/swait.c b/kernel/sched/swait.c
- new file mode 100644
- index 000000000000..205fe36868f9
- @@ -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 --git a/kernel/sched/swork.c b/kernel/sched/swork.c
- new file mode 100644
- index 000000000000..1950f40ca725
- @@ -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 --git a/kernel/signal.c b/kernel/signal.c
- index 4a548c6a4118..e870a133857b 100644
- @@ -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>
- @@ -354,13 +355,30 @@ static bool task_participate_group_stop(struct task_struct *task)
- 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;
- @@ -377,7 +395,10 @@ __sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimi
- 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);
- }
- @@ -394,6 +415,13 @@ __sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimi
- 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)
- @@ -403,6 +431,21 @@ static void __sigqueue_free(struct sigqueue *q)
- 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;
- @@ -415,6 +458,21 @@ void flush_sigqueue(struct sigpending *queue)
- }
- }
-
- +/*
- + * 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.
- */
- @@ -534,7 +592,7 @@ static void collect_signal(int sig, struct sigpending *list, siginfo_t *info,
- (info->si_code == SI_TIMER) &&
- (info->si_sys_private);
-
- - __sigqueue_free(first);
- + sigqueue_free_current(first);
- } else {
- /*
- * Ok, it wasn't in the queue. This must be
- @@ -570,6 +628,8 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info)
- bool resched_timer = false;
- int signr;
-
- + WARN_ON_ONCE(tsk != current);
- +
- /* We only dequeue private signals from ourselves, we don't let
- * signalfd steal them
- */
- @@ -1166,8 +1226,8 @@ int do_send_sig_info(int sig, struct siginfo *info, struct task_struct *p,
- * 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;
- @@ -1192,6 +1252,39 @@ force_sig_info(int sig, struct siginfo *info, struct task_struct *t)
- 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.
- */
- @@ -1226,12 +1319,12 @@ struct sighand_struct *__lock_task_sighand(struct task_struct *tsk,
- * 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;
- }
- /*
- @@ -1252,7 +1345,7 @@ struct sighand_struct *__lock_task_sighand(struct task_struct *tsk,
- }
- spin_unlock(&sighand->siglock);
- rcu_read_unlock();
- - local_irq_restore(*flags);
- + local_irq_restore_nort(*flags);
- }
-
- return sighand;
- @@ -1495,7 +1588,8 @@ EXPORT_SYMBOL(kill_pid);
- */
- 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;
- @@ -1856,15 +1950,7 @@ static void ptrace_stop(int exit_code, int why, int clear_code, siginfo_t *info)
- 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 --git a/kernel/softirq.c b/kernel/softirq.c
- index 479e4436f787..cb9c1d5dee10 100644
- @@ -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 @@ EXPORT_SYMBOL(irq_stat);
- 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 @@ static void wakeup_softirqd(void)
- 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 @@ void __local_bh_disable_ip(unsigned long ip, unsigned int cnt)
-
- 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 @@ asmlinkage __visible void __do_softirq(void)
- 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 @@ asmlinkage __visible void __do_softirq(void)
- /* 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) {
- @@ -319,6 +459,310 @@ asmlinkage __visible void do_softirq(void)
- local_irq_restore(flags);
- }
-
- +/*
- + * 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.
- */
- @@ -330,9 +774,9 @@ void irq_enter(void)
- * 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 @@ void irq_enter(void)
-
- 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 @@ static inline void invoke_softirq(void)
- } 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 @@ void irq_exit(void)
- 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 @@ void raise_softirq(unsigned int nr)
- 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 @@ struct tasklet_head {
- 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 @@ void __tasklet_hi_schedule(struct tasklet_struct *t)
- 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 @@ void __tasklet_hi_schedule_first(struct tasklet_struct *t)
- {
- 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 @@ void tasklet_kill(struct tasklet_struct *t)
-
- 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 @@ void __init softirq_init(void)
- 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 notifier_block cpu_nfb = {
-
- 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 --git a/kernel/stop_machine.c b/kernel/stop_machine.c
- index a3bbaee77c58..f84d3b45cda7 100644
- @@ -37,7 +37,7 @@ struct cpu_stop_done {
- 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 @@ static void cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work)
- 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 @@ static int cpu_stop_queue_two_works(int cpu1, struct cpu_stop_work *work1,
- 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 @@ static int cpu_stop_queue_two_works(int cpu1, struct cpu_stop_work *work1,
- __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 @@ int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void *
- 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 @@ int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void *
- 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 DEFINE_MUTEX(stop_cpus_mutex);
-
- 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 @@ static int __stop_cpus(const struct cpumask *cpumask,
- 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 @@ static int cpu_stop_should_run(unsigned int cpu)
- 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 @@ static void cpu_stopper_thread(unsigned int cpu)
-
- 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 @@ static void cpu_stopper_thread(unsigned int cpu)
- 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 @@ static int __init cpu_stop_init(void)
- 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 @@ int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data,
- 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 --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
- index 17f7bcff1e02..120fc8932165 100644
- @@ -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 void clock_was_set_work(struct work_struct *work)
-
- 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 @@ void clock_was_set_delayed(void)
- {
- schedule_work(&hrtimer_work);
- }
- +#endif
-
- #else
-
- @@ -734,11 +775,8 @@ static inline int hrtimer_is_hres_enabled(void) { return 0; }
- 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 @@ u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval)
- }
- 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 @@ static void __remove_hrtimer(struct hrtimer *timer,
- 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 @@ void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
- 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 @@ int hrtimer_cancel(struct hrtimer *timer)
-
- if (ret >= 0)
- return ret;
- - cpu_relax();
- + hrtimer_wait_for_timer(timer);
- }
- }
- EXPORT_SYMBOL_GPL(hrtimer_cancel);
- @@ -1142,6 +1220,7 @@ static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
-
- 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 @@ bool hrtimer_active(const struct hrtimer *timer)
- 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 @@ static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base,
- cpu_base->running = NULL;
- }
-
- -static void __hrtimer_run_queues(struct hrtimer_cpu_base *cpu_base, ktime_t now)
- +#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 int __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 @@ static void __hrtimer_run_queues(struct hrtimer_cpu_base *cpu_base, ktime_t now)
-
- 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 +1505,13 @@ static void __hrtimer_run_queues(struct hrtimer_cpu_base *cpu_base, ktime_t now)
- 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;
- }
- }
- + return raise;
- }
-
- #ifdef CONFIG_HIGH_RES_TIMERS
- @@ -1330,6 +1525,7 @@ void hrtimer_interrupt(struct clock_event_device *dev)
- struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
- ktime_t expires_next, now, entry_time, delta;
- int retries = 0;
- + int raise;
-
- BUG_ON(!cpu_base->hres_active);
- cpu_base->nr_events++;
- @@ -1348,7 +1544,7 @@ void hrtimer_interrupt(struct clock_event_device *dev)
- */
- cpu_base->expires_next.tv64 = KTIME_MAX;
-
- - __hrtimer_run_queues(cpu_base, now);
- + raise = __hrtimer_run_queues(cpu_base, now);
-
- /* Reevaluate the clock bases for the next expiry */
- expires_next = __hrtimer_get_next_event(cpu_base);
- @@ -1359,6 +1555,8 @@ void hrtimer_interrupt(struct clock_event_device *dev)
- cpu_base->expires_next = expires_next;
- cpu_base->in_hrtirq = 0;
- raw_spin_unlock(&cpu_base->lock);
- + if (raise)
- + raise_softirq_irqoff(HRTIMER_SOFTIRQ);
-
- /* Reprogramming necessary ? */
- if (!tick_program_event(expires_next, 0)) {
- @@ -1438,6 +1636,7 @@ void hrtimer_run_queues(void)
- {
- struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
- ktime_t now;
- + int raise;
-
- if (__hrtimer_hres_active(cpu_base))
- return;
- @@ -1456,8 +1655,10 @@ void hrtimer_run_queues(void)
-
- raw_spin_lock(&cpu_base->lock);
- now = hrtimer_update_base(cpu_base);
- - __hrtimer_run_queues(cpu_base, now);
- + raise = __hrtimer_run_queues(cpu_base, now);
- raw_spin_unlock(&cpu_base->lock);
- + if (raise)
- + raise_softirq_irqoff(HRTIMER_SOFTIRQ);
- }
-
- /*
- @@ -1479,16 +1680,18 @@ static enum hrtimer_restart hrtimer_wakeup(struct hrtimer *timer)
- 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 +1733,8 @@ long __sched hrtimer_nanosleep_restart(struct restart_block *restart)
- 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 +1751,10 @@ long __sched hrtimer_nanosleep_restart(struct restart_block *restart)
- 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 +1767,7 @@ long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp,
-
- 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 +1794,12 @@ long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp,
- 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 +1814,26 @@ SYSCALL_DEFINE2(nanosleep, struct timespec __user *, rqtp,
- 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:
- */
- @@ -1613,15 +1845,19 @@ static void init_hrtimers_cpu(int cpu)
- 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
-
- -static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base,
- +static int migrate_hrtimer_list(struct hrtimer_clock_base *old_base,
- struct hrtimer_clock_base *new_base)
- {
- struct hrtimer *timer;
- @@ -1649,12 +1885,21 @@ static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base,
- */
- enqueue_hrtimer(timer, new_base);
- }
- +#ifdef CONFIG_PREEMPT_RT_BASE
- + list_splice_tail(&old_base->expired, &new_base->expired);
- + /*
- + * Tell the caller to raise HRTIMER_SOFTIRQ. We can't safely
- + * acquire ktimersoftd->pi_lock while the base lock is held.
- + */
- + return !list_empty(&new_base->expired);
- +#endif
- + return 0;
- }
-
- static void migrate_hrtimers(int scpu)
- {
- struct hrtimer_cpu_base *old_base, *new_base;
- - int i;
- + int i, raise = 0;
-
- BUG_ON(cpu_online(scpu));
- tick_cancel_sched_timer(scpu);
- @@ -1670,13 +1915,16 @@ static void migrate_hrtimers(int scpu)
- raw_spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING);
-
- for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
- - migrate_hrtimer_list(&old_base->clock_base[i],
- - &new_base->clock_base[i]);
- + raise |= migrate_hrtimer_list(&old_base->clock_base[i],
- + &new_base->clock_base[i]);
- }
-
- raw_spin_unlock(&old_base->lock);
- raw_spin_unlock(&new_base->lock);
-
- + if (raise)
- + raise_softirq_irqoff(HRTIMER_SOFTIRQ);
- +
- /* Check, if we got expired work to do */
- __hrtimer_peek_ahead_timers();
- local_irq_enable();
- @@ -1714,11 +1962,21 @@ static struct notifier_block hrtimers_nb = {
- .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 --git a/kernel/time/itimer.c b/kernel/time/itimer.c
- index 1d5c7204ddc9..184de6751180 100644
- @@ -213,6 +213,7 @@ int do_setitimer(int which, struct itimerval *value, struct itimerval *ovalue)
- /* 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 --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
- index 347fecf86a3f..2ede47408a3e 100644
- @@ -74,7 +74,8 @@ static struct clocksource clocksource_jiffies = {
- .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 get_jiffies_64(void)
- 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 --git a/kernel/time/ntp.c b/kernel/time/ntp.c
- index ab861771e37f..0f6868fd2de6 100644
- @@ -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 @@ static void sync_cmos_clock(struct work_struct *work)
- &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 --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
- index 80016b329d94..b7342b6e6a5a 100644
- @@ -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 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
- /*
- * 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 @@ void posix_cpu_timer_schedule(struct k_itimer *timer)
- /*
- * 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 @@ static inline int fastpath_timer_check(struct task_struct *tsk)
- * 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 @@ void run_posix_cpu_timers(struct task_struct *tsk)
- }
- }
-
- +#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 --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
- index f2826c35e918..464a98155a0e 100644
- @@ -506,6 +506,7 @@ static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer)
- 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 @@ static struct pid *good_sigevent(sigevent_t * event)
- 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 @@ SYSCALL_DEFINE1(timer_getoverrun, timer_t, timer_id)
- 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 @@ SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags,
- 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 @@ SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags,
-
- 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 @@ SYSCALL_DEFINE1(timer_delete, timer_t, timer_id)
- 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 @@ static void itimer_delete(struct k_itimer *timer)
- 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 --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c
- index 53d7184da0be..1b4ac3361c3f 100644
- @@ -106,5 +106,6 @@ void tick_setup_hrtimer_broadcast(void)
- {
- hrtimer_init(&bctimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
- bctimer.function = bc_handler;
- + bctimer.irqsafe = true;
- clockevents_register_device(&ce_broadcast_hrtimer);
- }
- diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
- index 4fcd99e12aa0..5a47f2e98faf 100644
- @@ -79,13 +79,15 @@ int tick_is_oneshot_available(void)
- 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 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast)
- 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 --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
- index e5d228f7224c..45e9456da50f 100644
- @@ -62,7 +62,8 @@ static void tick_do_update_jiffies64(ktime_t now)
- 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 @@ static void tick_do_update_jiffies64(ktime_t now)
- /* 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 @@ static ktime_t tick_init_jiffy_update(void)
- {
- 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 @@ static bool can_stop_full_tick(void)
- 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 void nohz_full_kick_work_func(struct irq_work *work)
-
- static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) = {
- .func = nohz_full_kick_work_func,
- + .flags = IRQ_WORK_HARD_IRQ,
- };
-
- /*
- @@ -583,10 +594,10 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
-
- /* 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;
-
- /*
- @@ -768,14 +779,7 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts)
- 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;
- }
-
- @@ -1115,6 +1119,7 @@ void tick_setup_sched_timer(void)
- * 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 --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
- index 6e4866834d26..6c3e5323d06b 100644
- @@ -2091,8 +2091,10 @@ EXPORT_SYMBOL(hardpps);
- */
- 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 --git a/kernel/time/timekeeping.h b/kernel/time/timekeeping.h
- index 704f595ce83f..763a3e5121ff 100644
- @@ -19,7 +19,8 @@ extern void timekeeping_resume(void);
- 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 --git a/kernel/time/timer.c b/kernel/time/timer.c
- index 125407144c01..13652dafe83a 100644
- @@ -80,6 +80,9 @@ struct tvec_root {
- 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 @@ static struct tvec_base *lock_timer_base(struct timer_list *timer,
- 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 @@ __mod_timer(struct timer_list *timer, unsigned long expires,
- * 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 @@ void add_timer_on(struct timer_list *timer, int cpu)
- }
- 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 @@ int try_to_del_timer_sync(struct timer_list *timer)
- }
- 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 del_timer_sync(struct timer_list *timer)
- 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 @@ static inline void __run_timers(struct tvec_base *base)
- 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 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
- 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 @@ void update_process_times(int user_tick)
-
- /* 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 @@ static void run_timer_softirq(struct softirq_action *h)
- {
- 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 @@ static void migrate_timers(int cpu)
-
- 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 @@ static void migrate_timers(int cpu)
-
- 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 @@ static void __init init_timer_cpu(int cpu)
-
- 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 --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
- index e45db6b0d878..364ccd0eb57b 100644
- @@ -187,6 +187,24 @@ config IRQSOFF_TRACER
- 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 @@ config PREEMPT_TRACER
- 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 @@ config SCHED_TRACER
- 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 --git a/kernel/trace/Makefile b/kernel/trace/Makefile
- index 05ea5167e6bb..bc08c67301ae 100644
- @@ -40,6 +40,10 @@ obj-$(CONFIG_FUNCTION_TRACER) += trace_functions.o
- 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 --git a/kernel/trace/latency_hist.c b/kernel/trace/latency_hist.c
- new file mode 100644
- index 000000000000..7f6ee70dea41
- @@ -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 --git a/kernel/trace/trace.c b/kernel/trace/trace.c
- index 8aef4e63ac57..cdb7742283e5 100644
- @@ -1652,6 +1652,7 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags,
- 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 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags,
- #endif
- ((pc & HARDIRQ_MASK) ? TRACE_FLAG_HARDIRQ : 0) |
- ((pc & SOFTIRQ_OFFSET) ? 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 @@ get_total_entries(struct trace_buffer *buf,
-
- 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 @@ static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file
- 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 --git a/kernel/trace/trace.h b/kernel/trace/trace.h
- index 919d9d07686f..3bf86ece683c 100644
- @@ -117,6 +117,7 @@ struct kretprobe_trace_entry_head {
- * 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 @@ enum trace_flag_type {
- 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 --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
- index 996f0fd34312..5bd79b347398 100644
- @@ -188,6 +188,8 @@ static int trace_define_common_fields(void)
- __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 @@ void *trace_event_buffer_reserve(struct trace_event_buffer *fbuffer,
-
- 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 --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
- index be3222b7d72e..553e71254ad6 100644
- @@ -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 @@ void start_critical_timings(void)
- {
- 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 @@ EXPORT_SYMBOL_GPL(stop_critical_timings);
- #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 @@ void time_hardirqs_off(unsigned long a0, unsigned long a1)
- {
- 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 @@ inline void print_irqtrace_events(struct task_struct *curr)
- */
- 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 @@ void trace_hardirqs_off(void)
- {
- 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 @@ __visible void trace_hardirqs_off_caller(unsigned long caller_addr)
- {
- 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 @@ EXPORT_SYMBOL(trace_hardirqs_off_caller);
- #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 --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
- index 282982195e09..9f19d839a756 100644
- @@ -386,6 +386,7 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry)
- {
- char hardsoft_irq;
- char need_resched;
- + char need_resched_lazy;
- char irqs_off;
- int hardirq;
- int softirq;
- @@ -413,6 +414,8 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry)
- need_resched = '.';
- break;
- }
- + need_resched_lazy =
- + (entry->flags & TRACE_FLAG_NEED_RESCHED_LAZY) ? 'L' : '.';
-
- hardsoft_irq =
- (hardirq && softirq) ? 'H' :
- @@ -420,14 +423,25 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry)
- 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 --git a/kernel/user.c b/kernel/user.c
- index b069ccbfb0b0..1a2e88e98b5e 100644
- @@ -161,11 +161,11 @@ void free_uid(struct user_struct *up)
- 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 --git a/kernel/watchdog.c b/kernel/watchdog.c
- index c1e0b5f429b6..fa2e079cc314 100644
- @@ -299,6 +299,8 @@ static int is_softlockup(unsigned long touch_ts)
-
- #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,
- @@ -332,6 +334,13 @@ static void watchdog_overflow_callback(struct perf_event *event,
- /* 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();
- @@ -349,8 +358,9 @@ static void watchdog_overflow_callback(struct perf_event *event,
- !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;
- @@ -496,6 +506,7 @@ static void watchdog_enable(unsigned int cpu)
- /* 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 --git a/kernel/workqueue.c b/kernel/workqueue.c
- index 85555eb4d3cb..79f33789f330 100644
- @@ -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"
-
- @@ -122,11 +124,16 @@ enum {
- * 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.
- *
- @@ -135,7 +142,7 @@ enum {
- *
- * 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 @@ struct worker_pool {
- 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 @@ struct pool_workqueue {
- /*
- * 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;
- @@ -332,6 +339,8 @@ EXPORT_SYMBOL_GPL(system_power_efficient_wq);
- 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);
-
- @@ -339,20 +348,20 @@ static void workqueue_sysfs_unregister(struct workqueue_struct *wq);
- #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]; \
- @@ -364,7 +373,7 @@ static void workqueue_sysfs_unregister(struct workqueue_struct *wq);
- * @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.
- *
- @@ -396,7 +405,7 @@ static void workqueue_sysfs_unregister(struct workqueue_struct *wq);
- * @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.
- *
- @@ -408,6 +417,31 @@ static void workqueue_sysfs_unregister(struct workqueue_struct *wq);
- 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;
- @@ -558,7 +592,7 @@ static int worker_pool_assign_id(struct worker_pool *pool)
- * @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.
- @@ -702,8 +736,8 @@ static struct pool_workqueue *get_work_pwq(struct work_struct *work)
- * @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
- @@ -840,51 +874,44 @@ static struct worker *first_idle_worker(struct worker_pool *pool)
- */
- 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;
-
- /*
- @@ -893,29 +920,26 @@ struct task_struct *wq_worker_sleeping(struct task_struct *task, int cpu)
- * 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);
- + }
- }
-
- /**
- @@ -1109,12 +1133,14 @@ static void put_pwq_unlocked(struct pool_workqueue *pwq)
- {
- 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);
- + rcu_read_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);
- + rcu_read_unlock();
- }
- }
-
- @@ -1216,7 +1242,7 @@ static int try_to_grab_pending(struct work_struct *work, bool is_dwork,
- 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) {
- @@ -1235,6 +1261,7 @@ static int try_to_grab_pending(struct work_struct *work, bool is_dwork,
- 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.
- @@ -1273,14 +1300,16 @@ static int try_to_grab_pending(struct work_struct *work, bool is_dwork,
- 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;
- }
-
- @@ -1349,7 +1378,7 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
- * 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);
-
- @@ -1357,6 +1386,8 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
- 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();
- @@ -1413,10 +1444,8 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
- /* 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);
- @@ -1432,7 +1461,9 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
-
- insert_work(pwq, work, worklist, work_flags);
-
- +out:
- spin_unlock(&pwq->pool->lock);
- + rcu_read_unlock();
- }
-
- /**
- @@ -1452,14 +1483,14 @@ bool queue_work_on(int cpu, struct workqueue_struct *wq,
- 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);
- @@ -1527,14 +1558,14 @@ bool queue_delayed_work_on(int cpu, struct workqueue_struct *wq,
- 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);
- @@ -1569,7 +1600,7 @@ bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq,
-
- 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 */
- @@ -1602,7 +1633,9 @@ static void worker_enter_idle(struct worker *worker)
- 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);
- @@ -1635,7 +1668,9 @@ static void worker_leave_idle(struct worker *worker)
- 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)
- @@ -1801,7 +1836,9 @@ static void destroy_worker(struct worker *worker)
- 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);
- }
- @@ -2711,14 +2748,14 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr)
-
- 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) {
- @@ -2745,10 +2782,11 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr)
- 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;
- }
-
- @@ -2835,7 +2873,7 @@ static bool __cancel_work_timer(struct work_struct *work, bool is_dwork)
-
- /* 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);
- @@ -2890,10 +2928,10 @@ EXPORT_SYMBOL_GPL(cancel_work_sync);
- */
- 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);
- @@ -2928,7 +2966,7 @@ bool cancel_delayed_work(struct delayed_work *dwork)
-
- 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);
- @@ -3155,7 +3193,7 @@ static void rcu_free_pool(struct rcu_head *rcu)
- * 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().
- @@ -3209,8 +3247,8 @@ static void put_unbound_pool(struct worker_pool *pool)
- 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);
- }
-
- /**
- @@ -3317,14 +3355,14 @@ static void pwq_unbound_release_workfn(struct work_struct *work)
- 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);
- }
-
- /**
- @@ -3991,7 +4029,7 @@ void destroy_workqueue(struct workqueue_struct *wq)
- * 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
- @@ -4085,7 +4123,8 @@ bool workqueue_congested(int cpu, struct workqueue_struct *wq)
- struct pool_workqueue *pwq;
- bool ret;
-
- - rcu_read_lock_sched();
- + rcu_read_lock();
- + preempt_disable();
-
- if (cpu == WORK_CPU_UNBOUND)
- cpu = smp_processor_id();
- @@ -4096,7 +4135,8 @@ bool workqueue_congested(int cpu, struct workqueue_struct *wq)
- 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;
- }
- @@ -4122,15 +4162,15 @@ unsigned int work_busy(struct work_struct *work)
- 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;
- }
- @@ -4319,7 +4359,7 @@ void show_workqueue_state(void)
- unsigned long flags;
- int pi;
-
- - rcu_read_lock_sched();
- + rcu_read_lock();
-
- pr_info("Showing busy workqueues and worker pools:\n");
-
- @@ -4370,7 +4410,7 @@ void show_workqueue_state(void)
- spin_unlock_irqrestore(&pool->lock, flags);
- }
-
- - rcu_read_unlock_sched();
- + rcu_read_unlock();
- }
-
- /*
- @@ -4731,16 +4771,16 @@ bool freeze_workqueues_busy(void)
- * 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);
- @@ -4930,7 +4970,8 @@ static ssize_t wq_pool_ids_show(struct device *dev,
- 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,
- @@ -4938,7 +4979,8 @@ static ssize_t wq_pool_ids_show(struct device *dev,
- delim = " ";
- }
- written += scnprintf(buf + written, PAGE_SIZE - written, "\n");
- - rcu_read_unlock_sched();
- + rcu_read_unlock();
- + put_online_cpus();
-
- return written;
- }
- diff --git a/kernel/workqueue_internal.h b/kernel/workqueue_internal.h
- index 3fa9c146fccb..42d1e3974554 100644
- @@ -44,6 +44,7 @@ struct worker {
- 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
- @@ -69,7 +70,7 @@ static inline struct worker *current_wq_worker(void)
- * 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 --git a/lib/Kconfig b/lib/Kconfig
- index 1a48744253d7..f75de578cca8 100644
- @@ -397,6 +397,7 @@ config CHECK_SIGNATURE
-
- 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 --git a/lib/debugobjects.c b/lib/debugobjects.c
- index 547f7f923dbc..8fcdbc2fc6d0 100644
- @@ -309,7 +309,10 @@ __debug_object_init(void *addr, struct debug_obj_descr *descr, int onstack)
- 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 --git a/lib/idr.c b/lib/idr.c
- index 6098336df267..9decbe914595 100644
- @@ -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(struct idr_layer *, idr_preload_head);
- 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 @@ static struct idr_layer *idr_layer_alloc(gfp_t gfp_mask, struct idr *layer_idr)
- * 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 @@ static void idr_fill_slot(struct idr *idr, void *ptr, int id,
- idr_mark_full(pa, id);
- }
-
- -
- /**
- * idr_preload - preload for idr_alloc()
- * @gfp_mask: allocation mask to use for preloading
- @@ -401,7 +432,7 @@ void idr_preload(gfp_t gfp_mask)
- 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 @@ void idr_preload(gfp_t gfp_mask)
- 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 --git a/lib/locking-selftest.c b/lib/locking-selftest.c
- index 872a15a2a637..b93a6103fa4d 100644
- @@ -590,6 +590,8 @@ GENERATE_TESTCASE(init_held_rsem)
- #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 @@ GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_soft_rlock)
- #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 @@ GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2A_rlock)
- #undef E1
- #undef E2
-
- +#endif
- +
- /*
- * Enabling irqs with an irq-safe lock held:
- */
- @@ -663,6 +670,8 @@ GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2A_rlock)
- #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 @@ GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_soft_rlock)
- #include "locking-selftest-wlock-softirq.h"
- GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_soft_wlock)
-
- +#endif
- +
- #undef E1
- #undef E2
-
- @@ -709,6 +720,8 @@ GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_soft_wlock)
- #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 @@ GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_soft_rlock)
- #include "locking-selftest-wlock-softirq.h"
- GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_soft_wlock)
-
- +#endif
- +
- #undef E1
- #undef E2
- #undef E3
- @@ -757,6 +772,8 @@ GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_soft_wlock)
- #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 @@ GENERATE_PERMUTATIONS_3_EVENTS(irqsafe4_soft_rlock)
- #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 @@ GENERATE_PERMUTATIONS_3_EVENTS(irq_inversion_soft_wlock)
- #undef E2
- #undef E3
-
- +#endif
- +
- +#ifndef CONFIG_PREEMPT_RT_FULL
- +
- /*
- * read-lock / write-lock recursion that is actually safe.
- */
- @@ -876,6 +901,8 @@ GENERATE_PERMUTATIONS_3_EVENTS(irq_read_recursion_soft)
- #undef E2
- #undef E3
-
- +#endif
- +
- /*
- * read-lock / write-lock recursion that is unsafe.
- */
- @@ -1858,6 +1885,7 @@ void locking_selftest(void)
-
- printk(" --------------------------------------------------------------------------\n");
-
- +#ifndef CONFIG_PREEMPT_RT_FULL
- /*
- * irq-context testcases:
- */
- @@ -1870,6 +1898,28 @@ void locking_selftest(void)
-
- 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 --git a/lib/percpu_ida.c b/lib/percpu_ida.c
- index 6d40944960de..822a2c027e72 100644
- @@ -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 @@ int percpu_ida_alloc(struct percpu_ida *pool, int state)
- 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 @@ int percpu_ida_alloc(struct percpu_ida *pool, int state)
-
- if (!tags->nr_free)
- alloc_global_tags(pool, tags);
- +
- if (!tags->nr_free)
- steal_tags(pool, tags);
-
- @@ -184,7 +188,7 @@ int percpu_ida_alloc(struct percpu_ida *pool, int state)
- }
-
- 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 @@ int percpu_ida_alloc(struct percpu_ida *pool, int state)
-
- 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 @@ void percpu_ida_free(struct percpu_ida *pool, unsigned tag)
-
- 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 @@ void percpu_ida_free(struct percpu_ida *pool, unsigned tag)
- 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 @@ int percpu_ida_for_each_free(struct percpu_ida *pool, percpu_ida_cb fn,
- 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 @@ int percpu_ida_for_each_free(struct percpu_ida *pool, percpu_ida_cb fn,
- }
- 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 --git a/lib/radix-tree.c b/lib/radix-tree.c
- index 6b79e9026e24..44bf36a396a9 100644
- @@ -34,7 +34,7 @@
- #include <linux/bitops.h>
- #include <linux/rcupdate.h>
- #include <linux/preempt.h> /* in_interrupt() */
- -
- +#include <linux/locallock.h>
-
- /*
- * The height_to_maxindex array needs to be one deeper than the maximum
- @@ -69,6 +69,7 @@ struct radix_tree_preload {
- struct radix_tree_node *nodes;
- };
- static DEFINE_PER_CPU(struct radix_tree_preload, radix_tree_preloads) = { 0, };
- +static DEFINE_LOCAL_IRQ_LOCK(radix_tree_preloads_lock);
-
- static inline void *ptr_to_indirect(void *ptr)
- {
- @@ -196,13 +197,14 @@ radix_tree_node_alloc(struct radix_tree_root *root)
- * succeed in getting a node here (and never reach
- * kmem_cache_alloc)
- */
- - rtp = this_cpu_ptr(&radix_tree_preloads);
- + rtp = &get_locked_var(radix_tree_preloads_lock, radix_tree_preloads);
- if (rtp->nr) {
- ret = rtp->nodes;
- rtp->nodes = ret->private_data;
- ret->private_data = NULL;
- rtp->nr--;
- }
- + put_locked_var(radix_tree_preloads_lock, radix_tree_preloads);
- /*
- * Update the allocation stack trace as this is more useful
- * for debugging.
- @@ -257,14 +259,14 @@ static int __radix_tree_preload(gfp_t gfp_mask)
- struct radix_tree_node *node;
- int ret = -ENOMEM;
-
- - preempt_disable();
- + local_lock(radix_tree_preloads_lock);
- rtp = this_cpu_ptr(&radix_tree_preloads);
- while (rtp->nr < RADIX_TREE_PRELOAD_SIZE) {
- - preempt_enable();
- + local_unlock(radix_tree_preloads_lock);
- node = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask);
- if (node == NULL)
- goto out;
- - preempt_disable();
- + local_lock(radix_tree_preloads_lock);
- rtp = this_cpu_ptr(&radix_tree_preloads);
- if (rtp->nr < RADIX_TREE_PRELOAD_SIZE) {
- node->private_data = rtp->nodes;
- @@ -306,11 +308,17 @@ int radix_tree_maybe_preload(gfp_t gfp_mask)
- if (gfpflags_allow_blocking(gfp_mask))
- return __radix_tree_preload(gfp_mask);
- /* Preloading doesn't help anything with this gfp mask, skip it */
- - preempt_disable();
- + local_lock(radix_tree_preloads_lock);
- return 0;
- }
- EXPORT_SYMBOL(radix_tree_maybe_preload);
-
- +void radix_tree_preload_end(void)
- +{
- + local_unlock(radix_tree_preloads_lock);
- +}
- +EXPORT_SYMBOL(radix_tree_preload_end);
- +
- /*
- * Return the maximum key which can be store into a
- * radix tree with height HEIGHT.
- diff --git a/lib/rbtree.c b/lib/rbtree.c
- index 1356454e36de..d15d6c4327f1 100644
- @@ -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 @@ struct rb_node *rb_first_postorder(const struct rb_root *root)
- 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 --git a/lib/scatterlist.c b/lib/scatterlist.c
- index bafa9933fa76..ebe3b7edd086 100644
- @@ -620,7 +620,7 @@ void sg_miter_stop(struct sg_mapping_iter *miter)
- 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 @@ size_t sg_copy_buffer(struct scatterlist *sgl, unsigned int nents, void *buf,
- 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 @@ size_t sg_copy_buffer(struct scatterlist *sgl, unsigned int nents, void *buf,
-
- sg_miter_stop(&miter);
-
- - local_irq_restore(flags);
- + local_irq_restore_nort(flags);
- return offset;
- }
- EXPORT_SYMBOL(sg_copy_buffer);
- diff --git a/lib/smp_processor_id.c b/lib/smp_processor_id.c
- index 1afec32de6f2..11fa431046a8 100644
- @@ -39,8 +39,9 @@ notrace static unsigned int check_preemption_disabled(const char *what1,
- 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 --git a/mm/Kconfig b/mm/Kconfig
- index 97a4e06b15c0..9614351e68b8 100644
- @@ -392,7 +392,7 @@ config NOMMU_INITIAL_TRIM_EXCESS
-
- 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 --git a/mm/backing-dev.c b/mm/backing-dev.c
- index a988d4ef39da..f2c2ee1d5191 100644
- @@ -457,9 +457,9 @@ void wb_congested_put(struct bdi_writeback_congested *congested)
- {
- 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 --git a/mm/compaction.c b/mm/compaction.c
- index b6f145ed7ae1..03cac7f6768a 100644
- @@ -1450,10 +1450,12 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
- 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 --git a/mm/filemap.c b/mm/filemap.c
- index 69f75c77c098..b203169ca0b4 100644
- @@ -144,9 +144,12 @@ static int page_cache_tree_insert(struct address_space *mapping,
- * node->private_list is protected by
- * mapping->tree_lock.
- */
- - if (!list_empty(&node->private_list))
- - list_lru_del(&workingset_shadow_nodes,
- + 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 @@ static void page_cache_tree_delete(struct address_space *mapping,
- 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 --git a/mm/highmem.c b/mm/highmem.c
- index 123bcd3ed4f2..16e8cf26d38a 100644
- @@ -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 @@ static inline wait_queue_head_t *get_pkmap_wait_queue_head(unsigned int color)
- 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 --git a/mm/memcontrol.c b/mm/memcontrol.c
- index e25b93a4267d..1c619267d9da 100644
- @@ -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 @@ int do_swap_account __read_mostly;
- #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 drain_local_stock(struct work_struct *dummy)
- */
- 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 @@ static void drain_all_stock(struct mem_cgroup *root_memcg)
- 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 @@ static void drain_all_stock(struct mem_cgroup *root_memcg)
- schedule_work_on(cpu, &stock->work);
- }
- }
- - put_cpu();
- + put_cpu_light();
- put_online_cpus();
- mutex_unlock(&percpu_charge_mutex);
- }
- @@ -4691,12 +4697,12 @@ static int mem_cgroup_move_account(struct page *page,
-
- 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:
- @@ -5486,10 +5492,10 @@ void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg,
- 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) };
- @@ -5545,14 +5551,14 @@ static void uncharge_batch(struct mem_cgroup *memcg, unsigned long pgpgout,
- 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);
- @@ -5762,6 +5768,7 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
- {
- 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);
- @@ -5802,12 +5809,16 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
- * 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 --git a/mm/mmu_context.c b/mm/mmu_context.c
- index 6f4d27c5bb32..5cd25c745a8f 100644
- @@ -23,6 +23,7 @@ void use_mm(struct mm_struct *mm)
- 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 @@ void use_mm(struct mm_struct *mm)
- }
- 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 --git a/mm/page_alloc.c b/mm/page_alloc.c
- index 3c70f03d91ec..e1377f157652 100644
- @@ -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_node_ids);
- 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
- @@ -820,7 +833,7 @@ static inline int free_pages_check(struct page *page)
- }
-
- /*
- - * 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.
- *
- @@ -831,18 +844,53 @@ static inline int free_pages_check(struct page *page)
- * 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;
- @@ -858,7 +906,7 @@ static void free_pcppages_bulk(struct zone *zone, int count,
- 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. */
- @@ -866,24 +914,12 @@ static void free_pcppages_bulk(struct zone *zone, int count,
- 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,
- @@ -892,7 +928,9 @@ static void free_one_page(struct zone *zone,
- 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);
- @@ -902,7 +940,7 @@ static void free_one_page(struct zone *zone,
- 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)
- @@ -1053,10 +1091,10 @@ static void __free_pages_ok(struct page *page, unsigned int order)
- 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,
- @@ -1925,16 +1963,18 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order,
- 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
-
- @@ -1950,16 +1990,21 @@ static void drain_pages_zone(unsigned int cpu, struct zone *zone)
- 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);
- }
-
- /*
- @@ -2045,8 +2090,17 @@ void drain_all_pages(struct zone *zone)
- 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
- @@ -2102,7 +2156,7 @@ void free_hot_cold_page(struct page *page, bool cold)
-
- 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);
-
- /*
- @@ -2128,12 +2182,17 @@ void free_hot_cold_page(struct page *page, bool cold)
- 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);
- }
-
- /*
- @@ -2268,7 +2327,7 @@ struct page *buffered_rmqueue(struct zone *preferred_zone,
- 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)) {
- @@ -2300,7 +2359,7 @@ struct page *buffered_rmqueue(struct zone *preferred_zone,
- */
- 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) {
- @@ -2310,11 +2369,13 @@ struct page *buffered_rmqueue(struct zone *preferred_zone,
- }
- 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));
- @@ -2324,13 +2385,13 @@ struct page *buffered_rmqueue(struct zone *preferred_zone,
-
- __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;
- }
-
- @@ -5999,6 +6060,7 @@ static int page_alloc_cpu_notify(struct notifier_block *self,
- void __init page_alloc_init(void)
- {
- hotcpu_notifier(page_alloc_cpu_notify, 0);
- + local_irq_lock_init(pa_lock);
- }
-
- /*
- @@ -6893,7 +6955,7 @@ void zone_pcp_reset(struct zone *zone)
- 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);
- @@ -6902,7 +6964,7 @@ void zone_pcp_reset(struct zone *zone)
- free_percpu(zone->pageset);
- zone->pageset = &boot_pageset;
- }
- - local_irq_restore(flags);
- + local_unlock_irqrestore(pa_lock, flags);
- }
-
- #ifdef CONFIG_MEMORY_HOTREMOVE
- diff --git a/mm/percpu.c b/mm/percpu.c
- index ef6353f0adbd..33ccbac7cdb8 100644
- @@ -1285,18 +1285,7 @@ void free_percpu(void __percpu *ptr)
- }
- EXPORT_SYMBOL_GPL(free_percpu);
-
- -/**
- - * is_kernel_percpu_address - test whether address is from static percpu area
- - * @addr: address to test
- - *
- - * Test whether @addr belongs to in-kernel static percpu area. Module
- - * static percpu areas are not considered. For those, use
- - * is_module_percpu_address().
- - *
- - * RETURNS:
- - * %true if @addr is from in-kernel static percpu area, %false otherwise.
- - */
- -bool is_kernel_percpu_address(unsigned long addr)
- +bool __is_kernel_percpu_address(unsigned long addr, unsigned long *can_addr)
- {
- #ifdef CONFIG_SMP
- const size_t static_size = __per_cpu_end - __per_cpu_start;
- @@ -1305,15 +1294,35 @@ bool is_kernel_percpu_address(unsigned long addr)
-
- for_each_possible_cpu(cpu) {
- void *start = per_cpu_ptr(base, cpu);
- + void *va = (void *)addr;
-
- - if ((void *)addr >= start && (void *)addr < start + static_size)
- + if (va >= start && va < start + static_size) {
- + if (can_addr)
- + *can_addr = (unsigned long) (va - start);
- return true;
- - }
- + }
- + }
- #endif
- /* on UP, can't distinguish from other static vars, always false */
- return false;
- }
-
- +/**
- + * is_kernel_percpu_address - test whether address is from static percpu area
- + * @addr: address to test
- + *
- + * Test whether @addr belongs to in-kernel static percpu area. Module
- + * static percpu areas are not considered. For those, use
- + * is_module_percpu_address().
- + *
- + * RETURNS:
- + * %true if @addr is from in-kernel static percpu area, %false otherwise.
- + */
- +bool is_kernel_percpu_address(unsigned long addr)
- +{
- + return __is_kernel_percpu_address(addr, NULL);
- +}
- +
- /**
- * per_cpu_ptr_to_phys - convert translated percpu address to physical address
- * @addr: the address to be converted to physical address
- diff --git a/mm/slab.h b/mm/slab.h
- index 7b6087197997..afdc57941179 100644
- @@ -324,7 +324,11 @@ static inline struct kmem_cache *cache_from_obj(struct kmem_cache *s, void *x)
- * 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 --git a/mm/slub.c b/mm/slub.c
- index 4cf3a9c768b1..b183c5271607 100644
- @@ -1075,7 +1075,7 @@ static noinline struct kmem_cache_node *free_debug_processing(
- 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 @@ static noinline struct kmem_cache_node *free_debug_processing(
-
- 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 @@ static inline void dec_slabs_node(struct kmem_cache *s, int node,
-
- #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 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
- 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 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
- page->frozen = 1;
-
- out:
- - if (gfpflags_allow_blocking(flags))
- + if (enableirqs)
- local_irq_disable();
- if (!page)
- return NULL;
- @@ -1529,6 +1542,16 @@ static void __free_slab(struct kmem_cache *s, struct page *page)
- __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 @@ static void free_slab(struct kmem_cache *s, struct page *page)
- }
-
- 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 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n,
- 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 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n,
- break;
-
- }
- - spin_unlock(&n->list_lock);
- + raw_spin_unlock(&n->list_lock);
- return object;
- }
-
- @@ -1944,7 +1973,7 @@ static void deactivate_slab(struct kmem_cache *s, struct page *page,
- * 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 @@ static void deactivate_slab(struct kmem_cache *s, struct page *page,
- * 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 @@ static void deactivate_slab(struct kmem_cache *s, struct page *page,
- 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 @@ static void unfreeze_partials(struct kmem_cache *s,
- 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 @@ static void unfreeze_partials(struct kmem_cache *s,
- }
-
- if (n)
- - spin_unlock(&n->list_lock);
- + raw_spin_unlock(&n->list_lock);
-
- while (discard_page) {
- page = discard_page;
- @@ -2093,14 +2122,21 @@ static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain)
- 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 bool has_cpu_slab(int cpu, void *info)
-
- 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 @@ static unsigned long count_partial(struct kmem_cache_node *n,
- 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 @@ static inline void *get_freelist(struct kmem_cache *s, struct page *page)
- * 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 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
- 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 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
- deactivate_slab(s, page, get_freepointer(s, freelist));
- c->page = NULL;
- c->freelist = NULL;
- - return freelist;
- + goto out;
- }
-
- /*
- @@ -2453,6 +2513,7 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
- {
- void *p;
- unsigned long flags;
- + LIST_HEAD(tofree);
-
- local_irq_save(flags);
- #ifdef CONFIG_PREEMPT
- @@ -2464,8 +2525,9 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
- 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 @@ static void __slab_free(struct kmem_cache *s, struct page *page,
-
- 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 @@ static void __slab_free(struct kmem_cache *s, struct page *page,
- * 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 @@ static void __slab_free(struct kmem_cache *s, struct page *page,
- 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 @@ static void __slab_free(struct kmem_cache *s, struct page *page,
- 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 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
- void **p)
- {
- struct kmem_cache_cpu *c;
- + LIST_HEAD(to_free);
- int i;
-
- /* memcg and kmem_cache debug support */
- @@ -2936,7 +2999,7 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
- * 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 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
- }
- 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 @@ static void
- 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 @@ int __kmem_cache_shrink(struct kmem_cache *s, bool deactivate)
- 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 @@ int __kmem_cache_shrink(struct kmem_cache *s, bool deactivate)
- 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 @@ void __init kmem_cache_init(void)
- {
- 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 @@ static int validate_slab_node(struct kmem_cache *s,
- 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 @@ static int validate_slab_node(struct kmem_cache *s,
- 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 @@ static int list_locations(struct kmem_cache *s, char *buf,
- 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 --git a/mm/swap.c b/mm/swap.c
- index 39395fb549c0..ad16649221d7 100644
- @@ -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_add_pvec);
- 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 @@ void rotate_reclaimable_page(struct page *page)
- 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 @@ static bool need_activate_page_drain(int cpu)
- 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 @@ void activate_page(struct page *page)
-
- 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 @@ static void __lru_cache_activate_page(struct page *page)
- }
- }
-
- - put_cpu_var(lru_add_pvec);
- + put_locked_var(swapvec_lock, lru_add_pvec);
- }
-
- /*
- @@ -630,13 +635,13 @@ EXPORT_SYMBOL(mark_page_accessed);
-
- 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 @@ void lru_add_drain_cpu(int cpu)
- 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 @@ void deactivate_file_page(struct page *page)
- 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 @@ void lru_add_drain_all(void)
- 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 --git a/mm/truncate.c b/mm/truncate.c
- index f4c8270f7b84..ff2d614eb91d 100644
- @@ -56,8 +56,11 @@ static void clear_exceptional_entry(struct address_space *mapping,
- * 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 --git a/mm/vmalloc.c b/mm/vmalloc.c
- index 8e3c9c5a3042..68740314ad54 100644
- @@ -821,7 +821,7 @@ static void *new_vmap_block(unsigned int order, gfp_t gfp_mask)
- 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 @@ static void *new_vmap_block(unsigned int order, gfp_t gfp_mask)
- 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 @@ static void *vb_alloc(unsigned long size, gfp_t gfp_mask)
- 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 @@ static void *vb_alloc(unsigned long size, gfp_t gfp_mask)
- 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 @@ static void *vb_alloc(unsigned long size, gfp_t gfp_mask)
- break;
- }
-
- - put_cpu_var(vmap_block_queue);
- + put_cpu_light();
- rcu_read_unlock();
-
- /* Allocate new block if nothing was found */
- diff --git a/mm/vmstat.c b/mm/vmstat.c
- index 5712cdaae964..71e04bc3fe66 100644
- @@ -226,6 +226,7 @@ void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
- long x;
- long t;
-
- + preempt_disable_rt();
- x = delta + __this_cpu_read(*p);
-
- t = __this_cpu_read(pcp->stat_threshold);
- @@ -235,6 +236,7 @@ void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
- x = 0;
- }
- __this_cpu_write(*p, x);
- + preempt_enable_rt();
- }
- EXPORT_SYMBOL(__mod_zone_page_state);
-
- @@ -267,6 +269,7 @@ void __inc_zone_state(struct zone *zone, enum zone_stat_item item)
- 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 @@ void __inc_zone_state(struct zone *zone, enum zone_stat_item item)
- 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 @@ void __dec_zone_state(struct zone *zone, enum zone_stat_item item)
- 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 @@ void __dec_zone_state(struct zone *zone, enum zone_stat_item item)
- 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 --git a/mm/workingset.c b/mm/workingset.c
- index df66f426fdcf..6db7b243fa0d 100644
- @@ -264,7 +264,8 @@ void workingset_activation(struct page *page)
- * 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 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker,
- 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 @@ static enum lru_status shadow_lru_isolate(struct list_head *item,
- 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 @@ static unsigned long scan_shadow_nodes(struct shrinker *shrinker,
- 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 @@ static int __init workingset_init(void)
- {
- 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 @@ static int __init workingset_init(void)
- 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 --git a/mm/zsmalloc.c b/mm/zsmalloc.c
- index c1ea19478119..529552c3716d 100644
- @@ -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 @@ static unsigned int get_maxobj_per_zspage(int size, int pages_per_zspage)
-
- /* 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 @@ void *zs_map_object(struct zs_pool *pool, unsigned long handle,
- 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 @@ void zs_unmap_object(struct zs_pool *pool, unsigned long handle)
-
- __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 --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
- index c842f40c1173..035a5f6e3de9 100644
- @@ -213,15 +213,13 @@ void hci_send_to_sock(struct hci_dev *hdev, struct sk_buff *skb)
- }
-
- /* Send frame to sockets with specific channel */
- -void hci_send_to_channel(unsigned short channel, struct sk_buff *skb,
- - int flag, struct sock *skip_sk)
- +static void __hci_send_to_channel(unsigned short channel, struct sk_buff *skb,
- + int flag, struct sock *skip_sk)
- {
- struct sock *sk;
-
- BT_DBG("channel %u len %d", channel, skb->len);
-
- - read_lock(&hci_sk_list.lock);
- -
- sk_for_each(sk, &hci_sk_list.head) {
- struct sk_buff *nskb;
-
- @@ -247,6 +245,13 @@ void hci_send_to_channel(unsigned short channel, struct sk_buff *skb,
- kfree_skb(nskb);
- }
-
- +}
- +
- +void hci_send_to_channel(unsigned short channel, struct sk_buff *skb,
- + int flag, struct sock *skip_sk)
- +{
- + read_lock(&hci_sk_list.lock);
- + __hci_send_to_channel(channel, skb, flag, skip_sk);
- read_unlock(&hci_sk_list.lock);
- }
-
- @@ -299,8 +304,8 @@ void hci_send_to_monitor(struct hci_dev *hdev, struct sk_buff *skb)
- hdr->index = cpu_to_le16(hdev->id);
- hdr->len = cpu_to_le16(skb->len);
-
- - hci_send_to_channel(HCI_CHANNEL_MONITOR, skb_copy,
- - HCI_SOCK_TRUSTED, NULL);
- + __hci_send_to_channel(HCI_CHANNEL_MONITOR, skb_copy,
- + HCI_SOCK_TRUSTED, NULL);
- kfree_skb(skb_copy);
- }
-
- diff --git a/net/core/dev.c b/net/core/dev.c
- index 3b67c1e5756f..63614e930907 100644
- @@ -186,6 +186,7 @@ static unsigned int napi_gen_id = NR_CPUS;
- 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 struct hlist_head *dev_index_hash(struct net *net, int ifindex)
- 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 @@ int netdev_get_name(struct net *net, char *name, int ifindex)
- 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 @@ int dev_change_name(struct net_device *dev, const char *newname)
- 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 @@ int dev_change_name(struct net_device *dev, const char *newname)
- 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 @@ int dev_change_name(struct net_device *dev, const char *newname)
- /* 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 @@ int dev_change_name(struct net_device *dev, const char *newname)
- }
-
- return err;
- +
- +outunlock:
- + __raw_write_seqcount_end(&devnet_rename_seq);
- + mutex_unlock(&devnet_rename_mutex);
- + return err;
- }
-
- /**
- @@ -2270,6 +2276,7 @@ static inline void __netif_reschedule(struct Qdisc *q)
- 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)
- @@ -2354,6 +2361,7 @@ void __dev_kfree_skb_irq(struct sk_buff *skb, enum skb_free_reason reason)
- __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);
-
- @@ -2918,7 +2926,11 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
- * 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);
-
- @@ -2978,9 +2990,44 @@ static void skb_update_prio(struct sk_buff *skb)
- #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
-
- /**
- @@ -3175,7 +3222,7 @@ static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv)
-
- 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);
- @@ -3185,9 +3232,9 @@ static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv)
- 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;
- @@ -3561,6 +3608,7 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu,
- rps_unlock(sd);
-
- local_irq_restore(flags);
- + preempt_check_resched_rt();
-
- atomic_long_inc(&skb->dev->rx_dropped);
- kfree_skb(skb);
- @@ -3579,7 +3627,7 @@ static int netif_rx_internal(struct sk_buff *skb)
- struct rps_dev_flow voidflow, *rflow = &voidflow;
- int cpu;
-
- - preempt_disable();
- + migrate_disable();
- rcu_read_lock();
-
- cpu = get_rps_cpu(skb->dev, skb, &rflow);
- @@ -3589,13 +3637,13 @@ static int netif_rx_internal(struct sk_buff *skb)
- 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;
- }
- @@ -3629,16 +3677,44 @@ int netif_rx_ni(struct sk_buff *skb)
-
- 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);
- @@ -3680,7 +3756,7 @@ static void net_tx_action(struct softirq_action *h)
- 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);
- @@ -4102,7 +4178,7 @@ static void flush_backlog(void *arg)
- 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);
- }
- }
- @@ -4111,10 +4187,13 @@ static void flush_backlog(void *arg)
- 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)
- @@ -4581,6 +4660,7 @@ static void net_rps_action_and_irq_enable(struct softnet_data *sd)
- 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) {
- @@ -4594,6 +4674,7 @@ static void net_rps_action_and_irq_enable(struct softnet_data *sd)
- } else
- #endif
- local_irq_enable();
- + preempt_check_resched_rt();
- }
-
- static bool sd_has_rps_ipi_waiting(struct softnet_data *sd)
- @@ -4675,9 +4756,11 @@ void __napi_schedule(struct napi_struct *n)
- local_irq_save(flags);
- ____napi_schedule(this_cpu_ptr(&softnet_data), n);
- local_irq_restore(flags);
- + preempt_check_resched_rt();
- }
- EXPORT_SYMBOL(__napi_schedule);
-
- +#ifndef CONFIG_PREEMPT_RT_FULL
- /**
- * __napi_schedule_irqoff - schedule for receive
- * @n: entry to schedule
- @@ -4689,6 +4772,7 @@ void __napi_schedule_irqoff(struct napi_struct *n)
- ____napi_schedule(this_cpu_ptr(&softnet_data), n);
- }
- EXPORT_SYMBOL(__napi_schedule_irqoff);
- +#endif
-
- void __napi_complete(struct napi_struct *n)
- {
- @@ -4912,13 +4996,21 @@ static void net_rx_action(struct softirq_action *h)
- struct softnet_data *sd = this_cpu_ptr(&softnet_data);
- unsigned long time_limit = jiffies + 2;
- int budget = netdev_budget;
- + struct sk_buff_head tofree_q;
- + struct sk_buff *skb;
- LIST_HEAD(list);
- LIST_HEAD(repoll);
-
- + __skb_queue_head_init(&tofree_q);
- +
- local_irq_disable();
- + skb_queue_splice_init(&sd->tofree_queue, &tofree_q);
- list_splice_init(&sd->poll_list, &list);
- local_irq_enable();
-
- + while ((skb = __skb_dequeue(&tofree_q)))
- + kfree_skb(skb);
- +
- for (;;) {
- struct napi_struct *n;
-
- @@ -4948,7 +5040,7 @@ static void net_rx_action(struct softirq_action *h)
- 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);
- }
- @@ -7287,7 +7379,7 @@ EXPORT_SYMBOL(free_netdev);
- 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();
- @@ -7528,16 +7620,20 @@ static int dev_cpu_callback(struct notifier_block *nfb,
-
- 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;
- }
- @@ -7839,8 +7935,9 @@ static int __init net_dev_init(void)
- 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 --git a/net/core/skbuff.c b/net/core/skbuff.c
- index 86b619501350..f5c4897b52a0 100644
- @@ -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 @@ EXPORT_SYMBOL(build_skb);
-
- 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 @@ static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask)
- 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 @@ EXPORT_SYMBOL(netdev_alloc_frag);
-
- 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 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int len,
- 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 @@ EXPORT_SYMBOL(__netdev_alloc_skb);
- 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 @@ struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len,
- 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 @@ struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len,
- }
-
- /* 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 --git a/net/core/sock.c b/net/core/sock.c
- index cd12cb6fe366..982a06dab369 100644
- @@ -2449,12 +2449,11 @@ void lock_sock_nested(struct sock *sk, int subclass)
- 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 --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
- index 36e26977c908..2c1ce3e80ee4 100644
- @@ -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 @@ static const struct icmp_control icmp_pointers[NR_ICMP_TYPES+1];
- *
- * 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 +219,18 @@ static inline struct sock *icmp_xmit_lock(struct net *net)
-
- local_bh_disable();
-
- + if (!local_trylock(icmp_sk_lock)) {
- + local_bh_enable();
- + return NULL;
- + }
- +
- 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 +240,7 @@ static inline struct sock *icmp_xmit_lock(struct net *net)
- 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 +369,7 @@ static void icmp_push_reply(struct icmp_bxm *icmp_param,
- 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 +392,7 @@ static void icmp_push_reply(struct icmp_bxm *icmp_param,
- skb->ip_summed = CHECKSUM_NONE;
- ip_push_pending_frames(sk, fl4);
- }
- + local_unlock(icmp_sk_lock);
- }
-
- /*
- @@ -890,6 +903,30 @@ static bool icmp_redirect(struct sk_buff *skb)
- return true;
- }
-
- +/*
- + * 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.
- *
- @@ -917,6 +954,11 @@ static bool icmp_echo(struct sk_buff *skb)
- 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 --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
- index 70fb352e317f..1bcd436709a4 100644
- @@ -817,6 +817,13 @@ static struct ctl_table ipv4_net_table[] = {
- .mode = 0644,
- .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,
- diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
- index 61c93a93f228..4df48ae72abc 100644
- @@ -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>
- @@ -570,6 +571,7 @@ void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb)
- }
- EXPORT_SYMBOL(tcp_v4_send_check);
-
- +static DEFINE_LOCAL_IRQ_LOCK(tcp_sk_lock);
- /*
- * This routine will send an RST to the other tcp.
- *
- @@ -691,10 +693,13 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
- 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);
- @@ -776,10 +781,12 @@ static void tcp_v4_send_ack(struct net *net,
- 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 --git a/net/mac80211/rx.c b/net/mac80211/rx.c
- index 3bcabc2ba4a6..c3c798388ab8 100644
- @@ -3605,7 +3605,7 @@ void ieee80211_rx_napi(struct ieee80211_hw *hw, struct sk_buff *skb,
- 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 --git a/net/netfilter/core.c b/net/netfilter/core.c
- index f39276d1c2d7..10880c89d62f 100644
- @@ -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 --git a/net/packet/af_packet.c b/net/packet/af_packet.c
- index 92ca3e106c2b..ddb4970c3e27 100644
- @@ -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>
- @@ -694,7 +695,7 @@ static void prb_retire_rx_blk_timer_expired(unsigned long data)
- if (BLOCK_NUM_PKTS(pbd)) {
- while (atomic_read(&pkc->blk_fill_in_prog)) {
- /* Waiting for skb_copy_bits to finish... */
- - cpu_relax();
- + cpu_chill();
- }
- }
-
- @@ -956,7 +957,7 @@ static void prb_retire_current_block(struct tpacket_kbdq_core *pkc,
- 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 --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c
- index a2340748ec86..19123a97b354 100644
- @@ -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 @@ static inline void wait_clean_list_grace(void)
- 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 --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
- index aa4725038f94..00b81cab28f3 100644
- @@ -893,7 +893,7 @@ void dev_deactivate_many(struct list_head *head)
- /* 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 --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
- index a6cbb2104667..5b69bb580617 100644
- @@ -340,7 +340,7 @@ void svc_xprt_do_enqueue(struct svc_xprt *xprt)
- 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 @@ void svc_xprt_do_enqueue(struct svc_xprt *xprt)
-
- 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 @@ void svc_xprt_do_enqueue(struct svc_xprt *xprt)
- goto redo_search;
- }
- rqstp = NULL;
- - put_cpu();
- + put_cpu_light();
- out:
- trace_svc_xprt_do_enqueue(xprt, rqstp);
- }
- diff --git a/scripts/mkcompile_h b/scripts/mkcompile_h
- index 6fdc97ef6023..523e0420d7f0 100755
- @@ -4,7 +4,8 @@ TARGET=$1
- ARCH=$2
- SMP=$3
- PREEMPT=$4
- -CC=$5
- +RT=$5
- +CC=$6
-
- vecho() { [ "${quiet}" = "silent_" ] || echo "$@" ; }
-
- @@ -57,6 +58,7 @@ UTS_VERSION="#$VERSION"
- 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 --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
- index 4ba64fd49759..34e50186885d 100644
- @@ -135,7 +135,7 @@ EXPORT_SYMBOL_GPL(snd_pcm_stream_unlock);
- 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 @@ void snd_pcm_stream_unlock_irq(struct snd_pcm_substream *substream)
- {
- 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 _snd_pcm_stream_lock_irqsave(struct snd_pcm_substream *substream)
- {
- 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 @@ void snd_pcm_stream_unlock_irqrestore(struct snd_pcm_substream *substream,
- {
- 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 --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c
- index 4f70d12e392d..9378d0919ed8 100644
- @@ -98,8 +98,8 @@ static void async_pf_execute(struct work_struct *work)
- * 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 --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
- index d080f06fd8d9..a8d8150fd398 100644
- @@ -228,8 +228,7 @@ int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
- 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;
- @@ -2008,7 +2007,7 @@ static int kvm_vcpu_check_block(struct kvm_vcpu *vcpu)
- void kvm_vcpu_block(struct kvm_vcpu *vcpu)
- {
- ktime_t start, cur;
- - DEFINE_WAIT(wait);
- + DECLARE_SWAITQUEUE(wait);
- bool waited = false;
- u64 block_ns;
-
- @@ -2033,7 +2032,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu)
- 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;
- @@ -2042,7 +2041,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu)
- schedule();
- }
-
- - finish_wait(&vcpu->wq, &wait);
- + finish_swait(&vcpu->wq, &wait);
- cur = ktime_get();
-
- kvm_arch_vcpu_unblocking(vcpu);
- @@ -2074,11 +2073,11 @@ void kvm_vcpu_kick(struct kvm_vcpu *vcpu)
- {
- 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;
- }
-
- @@ -2179,7 +2178,7 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me)
- 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;
|