1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859606162636465666768697071727374757677787980818283848586878889909192939495969798991001011021031041051061071081091101111121131141151161171181191201211221231241251261271281291301311321331341351361371381391401411421431441451461471481491501511521531541551561571581591601611621631641651661671681691701711721731741751761771781791801811821831841851861871881891901911921931941951961971981992002012022032042052062072082092102112122132142152162172182192202212222232242252262272282292302312322332342352362372382392402412422432442452462472482492502512522532542552562572582592602612622632642652662672682692702712722732742752762772782792802812822832842852862872882892902912922932942952962972982993003013023033043053063073083093103113123133143153163173183193203213223233243253263273283293303313323333343353363373383393403413423433443453463473483493503513523533543553563573583593603613623633643653663673683693703713723733743753763773783793803813823833843853863873883893903913923933943953963973983994004014024034044054064074084094104114124134144154164174184194204214224234244254264274284294304314324334344354364374384394404414424434444454464474484494504514524534544554564574584594604614624634644654664674684694704714724734744754764774784794804814824834844854864874884894904914924934944954964974984995005015025035045055065075085095105115125135145155165175185195205215225235245255265275285295305315325335345355365375385395405415425435445455465475485495505515525535545555565575585595605615625635645655665675685695705715725735745755765775785795805815825835845855865875885895905915925935945955965975985996006016026036046056066076086096106116126136146156166176186196206216226236246256266276286296306316326336346356366376386396406416426436446456466476486496506516526536546556566576586596606616626636646656666676686696706716726736746756766776786796806816826836846856866876886896906916926936946956966976986997007017027037047057067077087097107117127137147157167177187197207217227237247257267277287297307317327337347357367377387397407417427437447457467477487497507517527537547557567577587597607617627637647657667677687697707717727737747757767777787797807817827837847857867877887897907917927937947957967977987998008018028038048058068078088098108118128138148158168178188198208218228238248258268278288298308318328338348358368378388398408418428438448458468478488498508518528538548558568578588598608618628638648658668678688698708718728738748758768778788798808818828838848858868878888898908918928938948958968978988999009019029039049059069079089099109119129139149159169179189199209219229239249259269279289299309319329339349359369379389399409419429439449459469479489499509519529539549559569579589599609619629639649659669679689699709719729739749759769779789799809819829839849859869879889899909919929939949959969979989991000100110021003100410051006100710081009101010111012101310141015101610171018101910201021102210231024102510261027102810291030103110321033103410351036103710381039104010411042104310441045104610471048104910501051105210531054105510561057105810591060106110621063106410651066106710681069107010711072107310741075107610771078107910801081108210831084108510861087108810891090109110921093109410951096109710981099110011011102110311041105110611071108110911101111111211131114111511161117111811191120112111221123112411251126112711281129113011311132113311341135113611371138113911401141114211431144114511461147114811491150115111521153115411551156115711581159116011611162116311641165116611671168116911701171117211731174117511761177117811791180118111821183118411851186118711881189119011911192119311941195119611971198119912001201120212031204120512061207120812091210121112121213121412151216121712181219122012211222122312241225122612271228122912301231123212331234123512361237123812391240124112421243124412451246124712481249125012511252125312541255125612571258125912601261126212631264126512661267126812691270127112721273127412751276127712781279128012811282128312841285128612871288128912901291129212931294129512961297129812991300130113021303130413051306130713081309131013111312131313141315131613171318131913201321132213231324132513261327132813291330133113321333133413351336133713381339134013411342134313441345134613471348134913501351135213531354135513561357135813591360136113621363136413651366136713681369137013711372137313741375137613771378137913801381138213831384138513861387138813891390139113921393139413951396139713981399140014011402140314041405140614071408140914101411141214131414141514161417141814191420142114221423142414251426142714281429143014311432143314341435143614371438143914401441144214431444144514461447144814491450145114521453145414551456145714581459146014611462146314641465146614671468146914701471147214731474147514761477147814791480148114821483148414851486148714881489149014911492149314941495149614971498149915001501150215031504150515061507150815091510151115121513151415151516151715181519152015211522152315241525152615271528152915301531153215331534153515361537153815391540154115421543154415451546154715481549155015511552155315541555155615571558155915601561156215631564156515661567156815691570157115721573157415751576157715781579158015811582158315841585158615871588158915901591159215931594159515961597159815991600160116021603160416051606160716081609161016111612161316141615161616171618161916201621162216231624162516261627162816291630163116321633163416351636163716381639164016411642164316441645164616471648164916501651165216531654165516561657165816591660166116621663166416651666166716681669167016711672167316741675167616771678167916801681168216831684168516861687168816891690169116921693169416951696169716981699170017011702170317041705170617071708170917101711171217131714171517161717171817191720172117221723172417251726172717281729173017311732173317341735173617371738173917401741174217431744174517461747174817491750175117521753175417551756175717581759176017611762176317641765176617671768176917701771177217731774177517761777177817791780178117821783178417851786178717881789179017911792179317941795179617971798179918001801180218031804180518061807180818091810181118121813181418151816181718181819182018211822182318241825182618271828182918301831183218331834183518361837183818391840184118421843184418451846184718481849185018511852185318541855185618571858185918601861186218631864186518661867186818691870187118721873187418751876187718781879188018811882188318841885188618871888188918901891189218931894189518961897189818991900190119021903190419051906190719081909191019111912191319141915191619171918191919201921192219231924192519261927192819291930193119321933193419351936193719381939194019411942194319441945194619471948194919501951195219531954195519561957195819591960196119621963196419651966196719681969197019711972197319741975197619771978197919801981198219831984198519861987198819891990199119921993199419951996199719981999200020012002200320042005200620072008200920102011201220132014201520162017201820192020202120222023202420252026202720282029203020312032203320342035203620372038203920402041204220432044204520462047204820492050205120522053205420552056205720582059206020612062206320642065206620672068206920702071207220732074207520762077207820792080208120822083208420852086208720882089209020912092209320942095209620972098209921002101210221032104210521062107210821092110211121122113211421152116211721182119212021212122212321242125212621272128212921302131213221332134213521362137213821392140214121422143214421452146214721482149215021512152215321542155215621572158215921602161216221632164216521662167216821692170217121722173217421752176217721782179218021812182218321842185218621872188218921902191219221932194219521962197219821992200220122022203220422052206220722082209221022112212221322142215221622172218221922202221222222232224222522262227222822292230223122322233223422352236223722382239224022412242224322442245224622472248224922502251225222532254225522562257225822592260226122622263226422652266226722682269227022712272227322742275227622772278227922802281228222832284228522862287228822892290229122922293229422952296229722982299230023012302230323042305230623072308230923102311231223132314231523162317231823192320232123222323232423252326232723282329233023312332233323342335233623372338233923402341234223432344234523462347234823492350235123522353235423552356235723582359236023612362236323642365236623672368236923702371237223732374237523762377237823792380238123822383238423852386238723882389239023912392239323942395239623972398239924002401240224032404240524062407240824092410241124122413241424152416241724182419242024212422242324242425242624272428242924302431243224332434243524362437243824392440244124422443244424452446244724482449245024512452245324542455245624572458245924602461246224632464246524662467246824692470247124722473247424752476247724782479248024812482248324842485248624872488248924902491249224932494249524962497249824992500250125022503250425052506250725082509251025112512251325142515251625172518251925202521252225232524252525262527252825292530253125322533253425352536253725382539254025412542254325442545254625472548254925502551255225532554255525562557255825592560256125622563256425652566256725682569257025712572257325742575257625772578257925802581258225832584258525862587258825892590259125922593259425952596259725982599260026012602260326042605260626072608260926102611261226132614261526162617261826192620262126222623262426252626262726282629263026312632263326342635263626372638263926402641264226432644264526462647264826492650265126522653265426552656265726582659266026612662266326642665266626672668266926702671267226732674267526762677267826792680268126822683268426852686268726882689269026912692269326942695269626972698269927002701270227032704270527062707270827092710271127122713271427152716271727182719272027212722272327242725272627272728272927302731273227332734273527362737273827392740274127422743274427452746274727482749275027512752275327542755275627572758275927602761276227632764276527662767276827692770277127722773277427752776277727782779278027812782278327842785278627872788278927902791279227932794279527962797279827992800280128022803280428052806280728082809281028112812281328142815281628172818281928202821282228232824282528262827282828292830283128322833283428352836283728382839284028412842284328442845284628472848284928502851285228532854285528562857285828592860286128622863286428652866286728682869287028712872287328742875287628772878287928802881288228832884288528862887288828892890289128922893289428952896289728982899290029012902290329042905290629072908290929102911291229132914291529162917291829192920292129222923292429252926292729282929293029312932293329342935293629372938293929402941294229432944294529462947294829492950295129522953295429552956295729582959296029612962296329642965296629672968296929702971297229732974297529762977297829792980298129822983298429852986298729882989299029912992299329942995299629972998299930003001300230033004300530063007300830093010301130123013301430153016301730183019302030213022302330243025302630273028302930303031303230333034303530363037303830393040304130423043304430453046304730483049305030513052305330543055305630573058305930603061306230633064306530663067306830693070307130723073307430753076307730783079308030813082308330843085308630873088308930903091309230933094309530963097309830993100310131023103310431053106310731083109311031113112311331143115311631173118311931203121312231233124312531263127312831293130313131323133313431353136313731383139314031413142314331443145314631473148314931503151315231533154315531563157315831593160316131623163316431653166316731683169317031713172317331743175317631773178317931803181318231833184318531863187318831893190319131923193319431953196319731983199320032013202320332043205320632073208320932103211321232133214321532163217321832193220322132223223322432253226322732283229323032313232323332343235323632373238323932403241324232433244324532463247324832493250325132523253325432553256325732583259326032613262326332643265326632673268326932703271327232733274327532763277327832793280328132823283328432853286328732883289329032913292329332943295329632973298329933003301330233033304330533063307330833093310331133123313331433153316331733183319332033213322332333243325332633273328332933303331333233333334333533363337333833393340334133423343334433453346334733483349335033513352335333543355335633573358335933603361336233633364336533663367336833693370337133723373337433753376337733783379338033813382338333843385338633873388338933903391339233933394339533963397339833993400340134023403340434053406340734083409341034113412341334143415341634173418341934203421342234233424342534263427342834293430343134323433343434353436343734383439344034413442344334443445344634473448344934503451345234533454345534563457345834593460346134623463346434653466346734683469347034713472347334743475347634773478347934803481348234833484348534863487348834893490349134923493349434953496349734983499350035013502350335043505350635073508350935103511351235133514351535163517351835193520352135223523352435253526352735283529353035313532353335343535353635373538353935403541354235433544354535463547354835493550355135523553355435553556355735583559356035613562356335643565356635673568356935703571357235733574357535763577357835793580358135823583358435853586358735883589359035913592359335943595359635973598359936003601360236033604360536063607360836093610361136123613361436153616361736183619362036213622362336243625362636273628362936303631363236333634363536363637363836393640364136423643364436453646364736483649365036513652365336543655365636573658365936603661366236633664366536663667366836693670367136723673367436753676367736783679368036813682368336843685368636873688368936903691369236933694369536963697369836993700370137023703370437053706370737083709371037113712371337143715371637173718371937203721372237233724372537263727372837293730373137323733373437353736373737383739374037413742374337443745374637473748374937503751375237533754375537563757375837593760376137623763376437653766376737683769377037713772377337743775377637773778377937803781378237833784378537863787378837893790379137923793379437953796379737983799380038013802380338043805380638073808380938103811381238133814381538163817381838193820382138223823382438253826382738283829383038313832383338343835383638373838383938403841384238433844384538463847384838493850385138523853385438553856385738583859386038613862386338643865386638673868386938703871387238733874387538763877387838793880388138823883388438853886388738883889389038913892389338943895389638973898389939003901390239033904390539063907390839093910391139123913391439153916391739183919392039213922392339243925392639273928392939303931393239333934393539363937393839393940394139423943394439453946394739483949395039513952395339543955395639573958395939603961396239633964396539663967396839693970397139723973397439753976397739783979398039813982398339843985398639873988398939903991399239933994399539963997399839994000400140024003400440054006400740084009401040114012401340144015401640174018401940204021402240234024402540264027402840294030403140324033403440354036403740384039404040414042404340444045404640474048404940504051405240534054405540564057405840594060406140624063406440654066406740684069407040714072407340744075407640774078407940804081408240834084408540864087408840894090409140924093409440954096409740984099410041014102410341044105410641074108410941104111411241134114411541164117411841194120412141224123412441254126412741284129413041314132413341344135413641374138413941404141414241434144414541464147414841494150415141524153415441554156415741584159416041614162416341644165416641674168416941704171417241734174417541764177417841794180418141824183418441854186418741884189419041914192419341944195419641974198419942004201420242034204420542064207420842094210421142124213421442154216421742184219422042214222422342244225422642274228422942304231423242334234423542364237423842394240424142424243424442454246424742484249425042514252425342544255425642574258425942604261426242634264426542664267426842694270427142724273427442754276427742784279428042814282428342844285428642874288428942904291429242934294429542964297429842994300430143024303430443054306430743084309431043114312431343144315431643174318431943204321432243234324432543264327432843294330433143324333433443354336433743384339434043414342434343444345434643474348434943504351435243534354435543564357435843594360436143624363436443654366436743684369437043714372437343744375437643774378437943804381438243834384438543864387438843894390439143924393439443954396439743984399440044014402440344044405440644074408440944104411441244134414441544164417441844194420442144224423442444254426442744284429443044314432443344344435443644374438443944404441444244434444444544464447444844494450445144524453445444554456445744584459446044614462446344644465446644674468446944704471447244734474447544764477447844794480448144824483448444854486448744884489449044914492449344944495449644974498449945004501450245034504450545064507450845094510451145124513451445154516451745184519452045214522452345244525452645274528452945304531453245334534453545364537453845394540454145424543454445454546454745484549455045514552455345544555455645574558455945604561456245634564456545664567456845694570457145724573457445754576457745784579458045814582458345844585458645874588458945904591459245934594459545964597459845994600460146024603460446054606460746084609461046114612461346144615461646174618461946204621462246234624462546264627462846294630463146324633463446354636463746384639464046414642464346444645464646474648464946504651465246534654465546564657465846594660466146624663466446654666466746684669467046714672467346744675467646774678467946804681468246834684468546864687468846894690469146924693469446954696469746984699470047014702470347044705470647074708470947104711471247134714471547164717471847194720472147224723472447254726472747284729473047314732473347344735473647374738473947404741474247434744474547464747474847494750475147524753475447554756475747584759476047614762476347644765476647674768476947704771477247734774477547764777477847794780478147824783478447854786478747884789479047914792479347944795479647974798479948004801480248034804480548064807480848094810481148124813481448154816481748184819482048214822482348244825482648274828482948304831483248334834483548364837483848394840484148424843484448454846484748484849485048514852485348544855485648574858485948604861486248634864486548664867486848694870487148724873487448754876487748784879488048814882488348844885488648874888488948904891489248934894489548964897489848994900490149024903490449054906490749084909491049114912491349144915491649174918491949204921492249234924492549264927492849294930493149324933493449354936493749384939494049414942494349444945494649474948494949504951495249534954495549564957495849594960496149624963496449654966496749684969497049714972497349744975497649774978497949804981498249834984498549864987498849894990499149924993499449954996499749984999500050015002500350045005500650075008500950105011501250135014501550165017501850195020502150225023502450255026502750285029503050315032503350345035503650375038503950405041504250435044504550465047504850495050505150525053505450555056505750585059506050615062506350645065506650675068506950705071507250735074507550765077507850795080508150825083508450855086508750885089509050915092509350945095509650975098509951005101510251035104510551065107510851095110511151125113511451155116511751185119512051215122512351245125512651275128512951305131513251335134513551365137513851395140514151425143514451455146514751485149515051515152515351545155515651575158515951605161516251635164516551665167516851695170517151725173517451755176517751785179518051815182518351845185518651875188518951905191519251935194519551965197519851995200520152025203520452055206520752085209521052115212521352145215521652175218521952205221522252235224522552265227522852295230523152325233523452355236523752385239524052415242524352445245524652475248524952505251525252535254525552565257525852595260526152625263526452655266526752685269527052715272527352745275527652775278527952805281528252835284528552865287528852895290529152925293529452955296529752985299530053015302530353045305530653075308530953105311531253135314531553165317531853195320532153225323532453255326532753285329533053315332533353345335533653375338533953405341534253435344534553465347534853495350535153525353535453555356535753585359536053615362536353645365536653675368536953705371537253735374537553765377537853795380538153825383538453855386538753885389539053915392539353945395539653975398539954005401540254035404540554065407540854095410541154125413541454155416541754185419542054215422542354245425542654275428542954305431543254335434543554365437543854395440544154425443544454455446544754485449545054515452545354545455545654575458545954605461546254635464546554665467546854695470547154725473547454755476547754785479548054815482548354845485548654875488548954905491549254935494549554965497549854995500550155025503550455055506550755085509551055115512551355145515551655175518551955205521552255235524552555265527552855295530553155325533553455355536553755385539554055415542554355445545554655475548554955505551555255535554555555565557555855595560556155625563556455655566556755685569557055715572557355745575557655775578557955805581558255835584558555865587558855895590559155925593559455955596559755985599560056015602560356045605560656075608560956105611561256135614561556165617561856195620562156225623562456255626562756285629563056315632563356345635563656375638563956405641564256435644564556465647564856495650565156525653565456555656565756585659566056615662566356645665566656675668566956705671567256735674567556765677567856795680568156825683568456855686568756885689569056915692569356945695569656975698569957005701570257035704570557065707570857095710571157125713571457155716571757185719572057215722572357245725572657275728572957305731573257335734573557365737573857395740574157425743574457455746574757485749575057515752575357545755575657575758575957605761576257635764576557665767576857695770577157725773577457755776577757785779578057815782578357845785578657875788578957905791579257935794579557965797579857995800580158025803580458055806580758085809581058115812581358145815581658175818581958205821582258235824582558265827582858295830583158325833583458355836583758385839584058415842584358445845584658475848584958505851585258535854585558565857585858595860586158625863586458655866586758685869587058715872587358745875587658775878587958805881588258835884588558865887588858895890589158925893589458955896589758985899590059015902590359045905590659075908590959105911591259135914591559165917591859195920592159225923592459255926592759285929593059315932593359345935593659375938593959405941594259435944594559465947594859495950595159525953595459555956595759585959596059615962596359645965596659675968596959705971597259735974597559765977597859795980598159825983598459855986598759885989599059915992599359945995599659975998599960006001600260036004600560066007600860096010601160126013601460156016601760186019602060216022602360246025602660276028602960306031603260336034603560366037603860396040604160426043604460456046604760486049605060516052605360546055605660576058605960606061606260636064606560666067606860696070607160726073607460756076607760786079608060816082608360846085608660876088608960906091609260936094609560966097609860996100610161026103610461056106610761086109611061116112611361146115611661176118611961206121612261236124612561266127612861296130613161326133613461356136613761386139614061416142614361446145614661476148614961506151615261536154615561566157615861596160616161626163616461656166616761686169617061716172617361746175617661776178617961806181618261836184618561866187618861896190619161926193619461956196619761986199620062016202620362046205620662076208620962106211621262136214621562166217621862196220622162226223622462256226622762286229623062316232623362346235623662376238623962406241624262436244624562466247624862496250625162526253625462556256625762586259626062616262626362646265626662676268626962706271627262736274627562766277627862796280628162826283628462856286628762886289629062916292629362946295629662976298629963006301630263036304630563066307630863096310631163126313631463156316631763186319632063216322632363246325632663276328632963306331633263336334633563366337633863396340634163426343634463456346634763486349635063516352635363546355635663576358635963606361636263636364636563666367636863696370637163726373637463756376637763786379638063816382638363846385638663876388638963906391639263936394639563966397639863996400640164026403640464056406640764086409641064116412641364146415641664176418641964206421642264236424642564266427642864296430643164326433643464356436643764386439644064416442644364446445644664476448/*
 * Copyright (c) 2013-2015, Mellanox Technologies. All rights reserved.
 *
 * This software is available to you under a choice of one of two
 * licenses.  You may choose to be licensed under the terms of the GNU
 * General Public License (GPL) Version 2, available from the file
 * COPYING in the main directory of this source tree, or the
 * OpenIB.org BSD license below:
 *
 *     Redistribution and use in source and binary forms, with or
 *     without modification, are permitted provided that the following
 *     conditions are met:
 *
 *      - Redistributions of source code must retain the above
 *        copyright notice, this list of conditions and the following
 *        disclaimer.
 *
 *      - Redistributions in binary form must reproduce the above
 *        copyright notice, this list of conditions and the following
 *        disclaimer in the documentation and/or other materials
 *        provided with the distribution.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
 * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
 * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
 * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
 * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
 * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 * SOFTWARE.
 */

#include <linux/debugfs.h>
#include <linux/highmem.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/errno.h>
#include <linux/pci.h>
#include <linux/dma-mapping.h>
#include <linux/slab.h>
#include <linux/bitmap.h>
#if defined(CONFIG_X86)
#include <asm/pat.h>
#endif
#include <linux/sched.h>
#include <linux/sched/mm.h>
#include <linux/sched/task.h>
#include <linux/delay.h>
#include <rdma/ib_user_verbs.h>
#include <rdma/ib_addr.h>
#include <rdma/ib_cache.h>
#include <linux/mlx5/port.h>
#include <linux/mlx5/vport.h>
#include <linux/mlx5/fs.h>
#include <linux/list.h>
#include <rdma/ib_smi.h>
#include <rdma/ib_umem.h>
#include <linux/in.h>
#include <linux/etherdevice.h>
#include "mlx5_ib.h"
#include "ib_rep.h"
#include "cmd.h"
#include <linux/mlx5/fs_helpers.h>
#include <linux/mlx5/accel.h>
#include <rdma/uverbs_std_types.h>
#include <rdma/mlx5_user_ioctl_verbs.h>
#include <rdma/mlx5_user_ioctl_cmds.h>

#define UVERBS_MODULE_NAME mlx5_ib
#include <rdma/uverbs_named_ioctl.h>

#define DRIVER_NAME "mlx5_ib"
#define DRIVER_VERSION "5.0-0"

MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>");
MODULE_DESCRIPTION("Mellanox Connect-IB HCA IB driver");
MODULE_LICENSE("Dual BSD/GPL");

static char mlx5_version[] =
	DRIVER_NAME ": Mellanox Connect-IB Infiniband driver v"
	DRIVER_VERSION "\n";

struct mlx5_ib_event_work {
	struct work_struct	work;
	struct mlx5_core_dev	*dev;
	void			*context;
	enum mlx5_dev_event	event;
	unsigned long		param;
};

enum {
	MLX5_ATOMIC_SIZE_QP_8BYTES = 1 << 3,
};

static struct workqueue_struct *mlx5_ib_event_wq;
static LIST_HEAD(mlx5_ib_unaffiliated_port_list);
static LIST_HEAD(mlx5_ib_dev_list);
/*
 * This mutex should be held when accessing either of the above lists
 */
static DEFINE_MUTEX(mlx5_ib_multiport_mutex);

/* We can't use an array for xlt_emergency_page because dma_map_single
 * doesn't work on kernel modules memory
 */
static unsigned long xlt_emergency_page;
static struct mutex xlt_emergency_page_mutex;

struct mlx5_ib_dev *mlx5_ib_get_ibdev_from_mpi(struct mlx5_ib_multiport_info *mpi)
{
	struct mlx5_ib_dev *dev;

	mutex_lock(&mlx5_ib_multiport_mutex);
	dev = mpi->ibdev;
	mutex_unlock(&mlx5_ib_multiport_mutex);
	return dev;
}

static enum rdma_link_layer
mlx5_port_type_cap_to_rdma_ll(int port_type_cap)
{
	switch (port_type_cap) {
	case MLX5_CAP_PORT_TYPE_IB:
		return IB_LINK_LAYER_INFINIBAND;
	case MLX5_CAP_PORT_TYPE_ETH:
		return IB_LINK_LAYER_ETHERNET;
	default:
		return IB_LINK_LAYER_UNSPECIFIED;
	}
}

static enum rdma_link_layer
mlx5_ib_port_link_layer(struct ib_device *device, u8 port_num)
{
	struct mlx5_ib_dev *dev = to_mdev(device);
	int port_type_cap = MLX5_CAP_GEN(dev->mdev, port_type);

	return mlx5_port_type_cap_to_rdma_ll(port_type_cap);
}

static int get_port_state(struct ib_device *ibdev,
			  u8 port_num,
			  enum ib_port_state *state)
{
	struct ib_port_attr attr;
	int ret;

	memset(&attr, 0, sizeof(attr));
	ret = ibdev->query_port(ibdev, port_num, &attr);
	if (!ret)
		*state = attr.state;
	return ret;
}

static int mlx5_netdev_event(struct notifier_block *this,
			     unsigned long event, void *ptr)
{
	struct mlx5_roce *roce = container_of(this, struct mlx5_roce, nb);
	struct net_device *ndev = netdev_notifier_info_to_dev(ptr);
	u8 port_num = roce->native_port_num;
	struct mlx5_core_dev *mdev;
	struct mlx5_ib_dev *ibdev;

	ibdev = roce->dev;
	mdev = mlx5_ib_get_native_port_mdev(ibdev, port_num, NULL);
	if (!mdev)
		return NOTIFY_DONE;

	switch (event) {
	case NETDEV_REGISTER:
	case NETDEV_UNREGISTER:
		write_lock(&roce->netdev_lock);
		if (ibdev->rep) {
			struct mlx5_eswitch *esw = ibdev->mdev->priv.eswitch;
			struct net_device *rep_ndev;

			rep_ndev = mlx5_ib_get_rep_netdev(esw,
							  ibdev->rep->vport);
			if (rep_ndev == ndev)
				roce->netdev = (event == NETDEV_UNREGISTER) ?
					NULL : ndev;
		} else if (ndev->dev.parent == &mdev->pdev->dev) {
			roce->netdev = (event == NETDEV_UNREGISTER) ?
				NULL : ndev;
		}
		write_unlock(&roce->netdev_lock);
		break;

	case NETDEV_CHANGE:
	case NETDEV_UP:
	case NETDEV_DOWN: {
		struct net_device *lag_ndev = mlx5_lag_get_roce_netdev(mdev);
		struct net_device *upper = NULL;

		if (lag_ndev) {
			upper = netdev_master_upper_dev_get(lag_ndev);
			dev_put(lag_ndev);
		}

		if ((upper == ndev || (!upper && ndev == roce->netdev))
		    && ibdev->ib_active) {
			struct ib_event ibev = { };
			enum ib_port_state port_state;

			if (get_port_state(&ibdev->ib_dev, port_num,
					   &port_state))
				goto done;

			if (roce->last_port_state == port_state)
				goto done;

			roce->last_port_state = port_state;
			ibev.device = &ibdev->ib_dev;
			if (port_state == IB_PORT_DOWN)
				ibev.event = IB_EVENT_PORT_ERR;
			else if (port_state == IB_PORT_ACTIVE)
				ibev.event = IB_EVENT_PORT_ACTIVE;
			else
				goto done;

			ibev.element.port_num = port_num;
			ib_dispatch_event(&ibev);
		}
		break;
	}

	default:
		break;
	}
done:
	mlx5_ib_put_native_port_mdev(ibdev, port_num);
	return NOTIFY_DONE;
}

static struct net_device *mlx5_ib_get_netdev(struct ib_device *device,
					     u8 port_num)
{
	struct mlx5_ib_dev *ibdev = to_mdev(device);
	struct net_device *ndev;
	struct mlx5_core_dev *mdev;

	mdev = mlx5_ib_get_native_port_mdev(ibdev, port_num, NULL);
	if (!mdev)
		return NULL;

	ndev = mlx5_lag_get_roce_netdev(mdev);
	if (ndev)
		goto out;

	/* Ensure ndev does not disappear before we invoke dev_hold()
	 */
	read_lock(&ibdev->roce[port_num - 1].netdev_lock);
	ndev = ibdev->roce[port_num - 1].netdev;
	if (ndev)
		dev_hold(ndev);
	read_unlock(&ibdev->roce[port_num - 1].netdev_lock);

out:
	mlx5_ib_put_native_port_mdev(ibdev, port_num);
	return ndev;
}

struct mlx5_core_dev *mlx5_ib_get_native_port_mdev(struct mlx5_ib_dev *ibdev,
						   u8 ib_port_num,
						   u8 *native_port_num)
{
	enum rdma_link_layer ll = mlx5_ib_port_link_layer(&ibdev->ib_dev,
							  ib_port_num);
	struct mlx5_core_dev *mdev = NULL;
	struct mlx5_ib_multiport_info *mpi;
	struct mlx5_ib_port *port;

	if (!mlx5_core_mp_enabled(ibdev->mdev) ||
	    ll != IB_LINK_LAYER_ETHERNET) {
		if (native_port_num)
			*native_port_num = ib_port_num;
		return ibdev->mdev;
	}

	if (native_port_num)
		*native_port_num = 1;

	port = &ibdev->port[ib_port_num - 1];
	if (!port)
		return NULL;

	spin_lock(&port->mp.mpi_lock);
	mpi = ibdev->port[ib_port_num - 1].mp.mpi;
	if (mpi && !mpi->unaffiliate) {
		mdev = mpi->mdev;
		/* If it's the master no need to refcount, it'll exist
		 * as long as the ib_dev exists.
		 */
		if (!mpi->is_master)
			mpi->mdev_refcnt++;
	}
	spin_unlock(&port->mp.mpi_lock);

	return mdev;
}

void mlx5_ib_put_native_port_mdev(struct mlx5_ib_dev *ibdev, u8 port_num)
{
	enum rdma_link_layer ll = mlx5_ib_port_link_layer(&ibdev->ib_dev,
							  port_num);
	struct mlx5_ib_multiport_info *mpi;
	struct mlx5_ib_port *port;

	if (!mlx5_core_mp_enabled(ibdev->mdev) || ll != IB_LINK_LAYER_ETHERNET)
		return;

	port = &ibdev->port[port_num - 1];

	spin_lock(&port->mp.mpi_lock);
	mpi = ibdev->port[port_num - 1].mp.mpi;
	if (mpi->is_master)
		goto out;

	mpi->mdev_refcnt--;
	if (mpi->unaffiliate)
		complete(&mpi->unref_comp);
out:
	spin_unlock(&port->mp.mpi_lock);
}

static int translate_eth_proto_oper(u32 eth_proto_oper, u8 *active_speed,
				    u8 *active_width)
{
	switch (eth_proto_oper) {
	case MLX5E_PROT_MASK(MLX5E_1000BASE_CX_SGMII):
	case MLX5E_PROT_MASK(MLX5E_1000BASE_KX):
	case MLX5E_PROT_MASK(MLX5E_100BASE_TX):
	case MLX5E_PROT_MASK(MLX5E_1000BASE_T):
		*active_width = IB_WIDTH_1X;
		*active_speed = IB_SPEED_SDR;
		break;
	case MLX5E_PROT_MASK(MLX5E_10GBASE_T):
	case MLX5E_PROT_MASK(MLX5E_10GBASE_CX4):
	case MLX5E_PROT_MASK(MLX5E_10GBASE_KX4):
	case MLX5E_PROT_MASK(MLX5E_10GBASE_KR):
	case MLX5E_PROT_MASK(MLX5E_10GBASE_CR):
	case MLX5E_PROT_MASK(MLX5E_10GBASE_SR):
	case MLX5E_PROT_MASK(MLX5E_10GBASE_ER):
		*active_width = IB_WIDTH_1X;
		*active_speed = IB_SPEED_QDR;
		break;
	case MLX5E_PROT_MASK(MLX5E_25GBASE_CR):
	case MLX5E_PROT_MASK(MLX5E_25GBASE_KR):
	case MLX5E_PROT_MASK(MLX5E_25GBASE_SR):
		*active_width = IB_WIDTH_1X;
		*active_speed = IB_SPEED_EDR;
		break;
	case MLX5E_PROT_MASK(MLX5E_40GBASE_CR4):
	case MLX5E_PROT_MASK(MLX5E_40GBASE_KR4):
	case MLX5E_PROT_MASK(MLX5E_40GBASE_SR4):
	case MLX5E_PROT_MASK(MLX5E_40GBASE_LR4):
		*active_width = IB_WIDTH_4X;
		*active_speed = IB_SPEED_QDR;
		break;
	case MLX5E_PROT_MASK(MLX5E_50GBASE_CR2):
	case MLX5E_PROT_MASK(MLX5E_50GBASE_KR2):
	case MLX5E_PROT_MASK(MLX5E_50GBASE_SR2):
		*active_width = IB_WIDTH_1X;
		*active_speed = IB_SPEED_HDR;
		break;
	case MLX5E_PROT_MASK(MLX5E_56GBASE_R4):
		*active_width = IB_WIDTH_4X;
		*active_speed = IB_SPEED_FDR;
		break;
	case MLX5E_PROT_MASK(MLX5E_100GBASE_CR4):
	case MLX5E_PROT_MASK(MLX5E_100GBASE_SR4):
	case MLX5E_PROT_MASK(MLX5E_100GBASE_KR4):
	case MLX5E_PROT_MASK(MLX5E_100GBASE_LR4):
		*active_width = IB_WIDTH_4X;
		*active_speed = IB_SPEED_EDR;
		break;
	default:
		return -EINVAL;
	}

	return 0;
}

static int mlx5_query_port_roce(struct ib_device *device, u8 port_num,
				struct ib_port_attr *props)
{
	struct mlx5_ib_dev *dev = to_mdev(device);
	struct mlx5_core_dev *mdev;
	struct net_device *ndev, *upper;
	enum ib_mtu ndev_ib_mtu;
	bool put_mdev = true;
	u16 qkey_viol_cntr;
	u32 eth_prot_oper;
	u8 mdev_port_num;
	int err;

	mdev = mlx5_ib_get_native_port_mdev(dev, port_num, &mdev_port_num);
	if (!mdev) {
		/* This means the port isn't affiliated yet. Get the
		 * info for the master port instead.
		 */
		put_mdev = false;
		mdev = dev->mdev;
		mdev_port_num = 1;
		port_num = 1;
	}

	/* Possible bad flows are checked before filling out props so in case
	 * of an error it will still be zeroed out.
	 */
	err = mlx5_query_port_eth_proto_oper(mdev, &eth_prot_oper,
					     mdev_port_num);
	if (err)
		goto out;

	props->active_width     = IB_WIDTH_4X;
	props->active_speed     = IB_SPEED_QDR;

	translate_eth_proto_oper(eth_prot_oper, &props->active_speed,
				 &props->active_width);

	props->port_cap_flags |= IB_PORT_CM_SUP;
	props->ip_gids = true;

	props->gid_tbl_len      = MLX5_CAP_ROCE(dev->mdev,
						roce_address_table_size);
	props->max_mtu          = IB_MTU_4096;
	props->max_msg_sz       = 1 << MLX5_CAP_GEN(dev->mdev, log_max_msg);
	props->pkey_tbl_len     = 1;
	props->state            = IB_PORT_DOWN;
	props->phys_state       = 3;

	mlx5_query_nic_vport_qkey_viol_cntr(mdev, &qkey_viol_cntr);
	props->qkey_viol_cntr = qkey_viol_cntr;

	/* If this is a stub query for an unaffiliated port stop here */
	if (!put_mdev)
		goto out;

	ndev = mlx5_ib_get_netdev(device, port_num);
	if (!ndev)
		goto out;

	if (mlx5_lag_is_active(dev->mdev)) {
		rcu_read_lock();
		upper = netdev_master_upper_dev_get_rcu(ndev);
		if (upper) {
			dev_put(ndev);
			ndev = upper;
			dev_hold(ndev);
		}
		rcu_read_unlock();
	}

	if (netif_running(ndev) && netif_carrier_ok(ndev)) {
		props->state      = IB_PORT_ACTIVE;
		props->phys_state = 5;
	}

	ndev_ib_mtu = iboe_get_mtu(ndev->mtu);

	dev_put(ndev);

	props->active_mtu	= min(props->max_mtu, ndev_ib_mtu);
out:
	if (put_mdev)
		mlx5_ib_put_native_port_mdev(dev, port_num);
	return err;
}

static int set_roce_addr(struct mlx5_ib_dev *dev, u8 port_num,
			 unsigned int index, const union ib_gid *gid,
			 const struct ib_gid_attr *attr)
{
	enum ib_gid_type gid_type = IB_GID_TYPE_IB;
	u8 roce_version = 0;
	u8 roce_l3_type = 0;
	bool vlan = false;
	u8 mac[ETH_ALEN];
	u16 vlan_id = 0;

	if (gid) {
		gid_type = attr->gid_type;
		ether_addr_copy(mac, attr->ndev->dev_addr);

		if (is_vlan_dev(attr->ndev)) {
			vlan = true;
			vlan_id = vlan_dev_vlan_id(attr->ndev);
		}
	}

	switch (gid_type) {
	case IB_GID_TYPE_IB:
		roce_version = MLX5_ROCE_VERSION_1;
		break;
	case IB_GID_TYPE_ROCE_UDP_ENCAP:
		roce_version = MLX5_ROCE_VERSION_2;
		if (ipv6_addr_v4mapped((void *)gid))
			roce_l3_type = MLX5_ROCE_L3_TYPE_IPV4;
		else
			roce_l3_type = MLX5_ROCE_L3_TYPE_IPV6;
		break;

	default:
		mlx5_ib_warn(dev, "Unexpected GID type %u\n", gid_type);
	}

	return mlx5_core_roce_gid_set(dev->mdev, index, roce_version,
				      roce_l3_type, gid->raw, mac, vlan,
				      vlan_id, port_num);
}

static int mlx5_ib_add_gid(const struct ib_gid_attr *attr,
			   __always_unused void **context)
{
	return set_roce_addr(to_mdev(attr->device), attr->port_num,
			     attr->index, &attr->gid, attr);
}

static int mlx5_ib_del_gid(const struct ib_gid_attr *attr,
			   __always_unused void **context)
{
	return set_roce_addr(to_mdev(attr->device), attr->port_num,
			     attr->index, NULL, NULL);
}

__be16 mlx5_get_roce_udp_sport(struct mlx5_ib_dev *dev,
			       const struct ib_gid_attr *attr)
{
	if (attr->gid_type != IB_GID_TYPE_ROCE_UDP_ENCAP)
		return 0;

	return cpu_to_be16(MLX5_CAP_ROCE(dev->mdev, r_roce_min_src_udp_port));
}

static int mlx5_use_mad_ifc(struct mlx5_ib_dev *dev)
{
	if (MLX5_CAP_GEN(dev->mdev, port_type) == MLX5_CAP_PORT_TYPE_IB)
		return !MLX5_CAP_GEN(dev->mdev, ib_virt);
	return 0;
}

enum {
	MLX5_VPORT_ACCESS_METHOD_MAD,
	MLX5_VPORT_ACCESS_METHOD_HCA,
	MLX5_VPORT_ACCESS_METHOD_NIC,
};

static int mlx5_get_vport_access_method(struct ib_device *ibdev)
{
	if (mlx5_use_mad_ifc(to_mdev(ibdev)))
		return MLX5_VPORT_ACCESS_METHOD_MAD;

	if (mlx5_ib_port_link_layer(ibdev, 1) ==
	    IB_LINK_LAYER_ETHERNET)
		return MLX5_VPORT_ACCESS_METHOD_NIC;

	return MLX5_VPORT_ACCESS_METHOD_HCA;
}

static void get_atomic_caps(struct mlx5_ib_dev *dev,
			    u8 atomic_size_qp,
			    struct ib_device_attr *props)
{
	u8 tmp;
	u8 atomic_operations = MLX5_CAP_ATOMIC(dev->mdev, atomic_operations);
	u8 atomic_req_8B_endianness_mode =
		MLX5_CAP_ATOMIC(dev->mdev, atomic_req_8B_endianness_mode);

	/* Check if HW supports 8 bytes standard atomic operations and capable
	 * of host endianness respond
	 */
	tmp = MLX5_ATOMIC_OPS_CMP_SWAP | MLX5_ATOMIC_OPS_FETCH_ADD;
	if (((atomic_operations & tmp) == tmp) &&
	    (atomic_size_qp & MLX5_ATOMIC_SIZE_QP_8BYTES) &&
	    (atomic_req_8B_endianness_mode)) {
		props->atomic_cap = IB_ATOMIC_HCA;
	} else {
		props->atomic_cap = IB_ATOMIC_NONE;
	}
}

static void get_atomic_caps_qp(struct mlx5_ib_dev *dev,
			       struct ib_device_attr *props)
{
	u8 atomic_size_qp = MLX5_CAP_ATOMIC(dev->mdev, atomic_size_qp);

	get_atomic_caps(dev, atomic_size_qp, props);
}

static void get_atomic_caps_dc(struct mlx5_ib_dev *dev,
			       struct ib_device_attr *props)
{
	u8 atomic_size_qp = MLX5_CAP_ATOMIC(dev->mdev, atomic_size_dc);

	get_atomic_caps(dev, atomic_size_qp, props);
}

bool mlx5_ib_dc_atomic_is_supported(struct mlx5_ib_dev *dev)
{
	struct ib_device_attr props = {};

	get_atomic_caps_dc(dev, &props);
	return (props.atomic_cap == IB_ATOMIC_HCA) ? true : false;
}
static int mlx5_query_system_image_guid(struct ib_device *ibdev,
					__be64 *sys_image_guid)
{
	struct mlx5_ib_dev *dev = to_mdev(ibdev);
	struct mlx5_core_dev *mdev = dev->mdev;
	u64 tmp;
	int err;

	switch (mlx5_get_vport_access_method(ibdev)) {
	case MLX5_VPORT_ACCESS_METHOD_MAD:
		return mlx5_query_mad_ifc_system_image_guid(ibdev,
							    sys_image_guid);

	case MLX5_VPORT_ACCESS_METHOD_HCA:
		err = mlx5_query_hca_vport_system_image_guid(mdev, &tmp);
		break;

	case MLX5_VPORT_ACCESS_METHOD_NIC:
		err = mlx5_query_nic_vport_system_image_guid(mdev, &tmp);
		break;

	default:
		return -EINVAL;
	}

	if (!err)
		*sys_image_guid = cpu_to_be64(tmp);

	return err;

}

static int mlx5_query_max_pkeys(struct ib_device *ibdev,
				u16 *max_pkeys)
{
	struct mlx5_ib_dev *dev = to_mdev(ibdev);
	struct mlx5_core_dev *mdev = dev->mdev;

	switch (mlx5_get_vport_access_method(ibdev)) {
	case MLX5_VPORT_ACCESS_METHOD_MAD:
		return mlx5_query_mad_ifc_max_pkeys(ibdev, max_pkeys);

	case MLX5_VPORT_ACCESS_METHOD_HCA:
	case MLX5_VPORT_ACCESS_METHOD_NIC:
		*max_pkeys = mlx5_to_sw_pkey_sz(MLX5_CAP_GEN(mdev,
						pkey_table_size));
		return 0;

	default:
		return -EINVAL;
	}
}

static int mlx5_query_vendor_id(struct ib_device *ibdev,
				u32 *vendor_id)
{
	struct mlx5_ib_dev *dev = to_mdev(ibdev);

	switch (mlx5_get_vport_access_method(ibdev)) {
	case MLX5_VPORT_ACCESS_METHOD_MAD:
		return mlx5_query_mad_ifc_vendor_id(ibdev, vendor_id);

	case MLX5_VPORT_ACCESS_METHOD_HCA:
	case MLX5_VPORT_ACCESS_METHOD_NIC:
		return mlx5_core_query_vendor_id(dev->mdev, vendor_id);

	default:
		return -EINVAL;
	}
}

static int mlx5_query_node_guid(struct mlx5_ib_dev *dev,
				__be64 *node_guid)
{
	u64 tmp;
	int err;

	switch (mlx5_get_vport_access_method(&dev->ib_dev)) {
	case MLX5_VPORT_ACCESS_METHOD_MAD:
		return mlx5_query_mad_ifc_node_guid(dev, node_guid);

	case MLX5_VPORT_ACCESS_METHOD_HCA:
		err = mlx5_query_hca_vport_node_guid(dev->mdev, &tmp);
		break;

	case MLX5_VPORT_ACCESS_METHOD_NIC:
		err = mlx5_query_nic_vport_node_guid(dev->mdev, &tmp);
		break;

	default:
		return -EINVAL;
	}

	if (!err)
		*node_guid = cpu_to_be64(tmp);

	return err;
}

struct mlx5_reg_node_desc {
	u8	desc[IB_DEVICE_NODE_DESC_MAX];
};

static int mlx5_query_node_desc(struct mlx5_ib_dev *dev, char *node_desc)
{
	struct mlx5_reg_node_desc in;

	if (mlx5_use_mad_ifc(dev))
		return mlx5_query_mad_ifc_node_desc(dev, node_desc);

	memset(&in, 0, sizeof(in));

	return mlx5_core_access_reg(dev->mdev, &in, sizeof(in), node_desc,
				    sizeof(struct mlx5_reg_node_desc),
				    MLX5_REG_NODE_DESC, 0, 0);
}

static int mlx5_ib_query_device(struct ib_device *ibdev,
				struct ib_device_attr *props,
				struct ib_udata *uhw)
{
	struct mlx5_ib_dev *dev = to_mdev(ibdev);
	struct mlx5_core_dev *mdev = dev->mdev;
	int err = -ENOMEM;
	int max_sq_desc;
	int max_rq_sg;
	int max_sq_sg;
	u64 min_page_size = 1ull << MLX5_CAP_GEN(mdev, log_pg_sz);
	bool raw_support = !mlx5_core_mp_enabled(mdev);
	struct mlx5_ib_query_device_resp resp = {};
	size_t resp_len;
	u64 max_tso;

	resp_len = sizeof(resp.comp_mask) + sizeof(resp.response_length);
	if (uhw->outlen && uhw->outlen < resp_len)
		return -EINVAL;
	else
		resp.response_length = resp_len;

	if (uhw->inlen && !ib_is_udata_cleared(uhw, 0, uhw->inlen))
		return -EINVAL;

	memset(props, 0, sizeof(*props));
	err = mlx5_query_system_image_guid(ibdev,
					   &props->sys_image_guid);
	if (err)
		return err;

	err = mlx5_query_max_pkeys(ibdev, &props->max_pkeys);
	if (err)
		return err;

	err = mlx5_query_vendor_id(ibdev, &props->vendor_id);
	if (err)
		return err;

	props->fw_ver = ((u64)fw_rev_maj(dev->mdev) << 32) |
		(fw_rev_min(dev->mdev) << 16) |
		fw_rev_sub(dev->mdev);
	props->device_cap_flags    = IB_DEVICE_CHANGE_PHY_PORT |
		IB_DEVICE_PORT_ACTIVE_EVENT		|
		IB_DEVICE_SYS_IMAGE_GUID		|
		IB_DEVICE_RC_RNR_NAK_GEN;

	if (MLX5_CAP_GEN(mdev, pkv))
		props->device_cap_flags |= IB_DEVICE_BAD_PKEY_CNTR;
	if (MLX5_CAP_GEN(mdev, qkv))
		props->device_cap_flags |= IB_DEVICE_BAD_QKEY_CNTR;
	if (MLX5_CAP_GEN(mdev, apm))
		props->device_cap_flags |= IB_DEVICE_AUTO_PATH_MIG;
	if (MLX5_CAP_GEN(mdev, xrc))
		props->device_cap_flags |= IB_DEVICE_XRC;
	if (MLX5_CAP_GEN(mdev, imaicl)) {
		props->device_cap_flags |= IB_DEVICE_MEM_WINDOW |
					   IB_DEVICE_MEM_WINDOW_TYPE_2B;
		props->max_mw = 1 << MLX5_CAP_GEN(mdev, log_max_mkey);
		/* We support 'Gappy' memory registration too */
		props->device_cap_flags |= IB_DEVICE_SG_GAPS_REG;
	}
	props->device_cap_flags |= IB_DEVICE_MEM_MGT_EXTENSIONS;
	if (MLX5_CAP_GEN(mdev, sho)) {
		props->device_cap_flags |= IB_DEVICE_SIGNATURE_HANDOVER;
		/* At this stage no support for signature handover */
		props->sig_prot_cap = IB_PROT_T10DIF_TYPE_1 |
				      IB_PROT_T10DIF_TYPE_2 |
				      IB_PROT_T10DIF_TYPE_3;
		props->sig_guard_cap = IB_GUARD_T10DIF_CRC |
				       IB_GUARD_T10DIF_CSUM;
	}
	if (MLX5_CAP_GEN(mdev, block_lb_mc))
		props->device_cap_flags |= IB_DEVICE_BLOCK_MULTICAST_LOOPBACK;

	if (MLX5_CAP_GEN(dev->mdev, eth_net_offloads) && raw_support) {
		if (MLX5_CAP_ETH(mdev, csum_cap)) {
			/* Legacy bit to support old userspace libraries */
			props->device_cap_flags |= IB_DEVICE_RAW_IP_CSUM;
			props->raw_packet_caps |= IB_RAW_PACKET_CAP_IP_CSUM;
		}

		if (MLX5_CAP_ETH(dev->mdev, vlan_cap))
			props->raw_packet_caps |=
				IB_RAW_PACKET_CAP_CVLAN_STRIPPING;

		if (field_avail(typeof(resp), tso_caps, uhw->outlen)) {
			max_tso = MLX5_CAP_ETH(mdev, max_lso_cap);
			if (max_tso) {
				resp.tso_caps.max_tso = 1 << max_tso;
				resp.tso_caps.supported_qpts |=
					1 << IB_QPT_RAW_PACKET;
				resp.response_length += sizeof(resp.tso_caps);
			}
		}

		if (field_avail(typeof(resp), rss_caps, uhw->outlen)) {
			resp.rss_caps.rx_hash_function =
						MLX5_RX_HASH_FUNC_TOEPLITZ;
			resp.rss_caps.rx_hash_fields_mask =
						MLX5_RX_HASH_SRC_IPV4 |
						MLX5_RX_HASH_DST_IPV4 |
						MLX5_RX_HASH_SRC_IPV6 |
						MLX5_RX_HASH_DST_IPV6 |
						MLX5_RX_HASH_SRC_PORT_TCP |
						MLX5_RX_HASH_DST_PORT_TCP |
						MLX5_RX_HASH_SRC_PORT_UDP |
						MLX5_RX_HASH_DST_PORT_UDP |
						MLX5_RX_HASH_INNER;
			if (mlx5_accel_ipsec_device_caps(dev->mdev) &
			    MLX5_ACCEL_IPSEC_CAP_DEVICE)
				resp.rss_caps.rx_hash_fields_mask |=
					MLX5_RX_HASH_IPSEC_SPI;
			resp.response_length += sizeof(resp.rss_caps);
		}
	} else {
		if (field_avail(typeof(resp), tso_caps, uhw->outlen))
			resp.response_length += sizeof(resp.tso_caps);
		if (field_avail(typeof(resp), rss_caps, uhw->outlen))
			resp.response_length += sizeof(resp.rss_caps);
	}

	if (MLX5_CAP_GEN(mdev, ipoib_basic_offloads)) {
		props->device_cap_flags |= IB_DEVICE_UD_IP_CSUM;
		props->device_cap_flags |= IB_DEVICE_UD_TSO;
	}

	if (MLX5_CAP_GEN(dev->mdev, rq_delay_drop) &&
	    MLX5_CAP_GEN(dev->mdev, general_notification_event) &&
	    raw_support)
		props->raw_packet_caps |= IB_RAW_PACKET_CAP_DELAY_DROP;

	if (MLX5_CAP_GEN(mdev, ipoib_enhanced_offloads) &&
	    MLX5_CAP_IPOIB_ENHANCED(mdev, csum_cap))
		props->device_cap_flags |= IB_DEVICE_UD_IP_CSUM;

	if (MLX5_CAP_GEN(dev->mdev, eth_net_offloads) &&
	    MLX5_CAP_ETH(dev->mdev, scatter_fcs) &&
	    raw_support) {
		/* Legacy bit to support old userspace libraries */
		props->device_cap_flags |= IB_DEVICE_RAW_SCATTER_FCS;
		props->raw_packet_caps |= IB_RAW_PACKET_CAP_SCATTER_FCS;
	}

	if (MLX5_CAP_DEV_MEM(mdev, memic)) {
		props->max_dm_size =
			MLX5_CAP_DEV_MEM(mdev, max_memic_size);
	}

	if (mlx5_get_flow_namespace(dev->mdev, MLX5_FLOW_NAMESPACE_BYPASS))
		props->device_cap_flags |= IB_DEVICE_MANAGED_FLOW_STEERING;

	if (MLX5_CAP_GEN(mdev, end_pad))
		props->device_cap_flags |= IB_DEVICE_PCI_WRITE_END_PADDING;

	props->vendor_part_id	   = mdev->pdev->device;
	props->hw_ver		   = mdev->pdev->revision;

	props->max_mr_size	   = ~0ull;
	props->page_size_cap	   = ~(min_page_size - 1);
	props->max_qp		   = 1 << MLX5_CAP_GEN(mdev, log_max_qp);
	props->max_qp_wr	   = 1 << MLX5_CAP_GEN(mdev, log_max_qp_sz);
	max_rq_sg =  MLX5_CAP_GEN(mdev, max_wqe_sz_rq) /
		     sizeof(struct mlx5_wqe_data_seg);
	max_sq_desc = min_t(int, MLX5_CAP_GEN(mdev, max_wqe_sz_sq), 512);
	max_sq_sg = (max_sq_desc - sizeof(struct mlx5_wqe_ctrl_seg) -
		     sizeof(struct mlx5_wqe_raddr_seg)) /
		sizeof(struct mlx5_wqe_data_seg);
	props->max_send_sge = max_sq_sg;
	props->max_recv_sge = max_rq_sg;
	props->max_sge_rd	   = MLX5_MAX_SGE_RD;
	props->max_cq		   = 1 << MLX5_CAP_GEN(mdev, log_max_cq);
	props->max_cqe = (1 << MLX5_CAP_GEN(mdev, log_max_cq_sz)) - 1;
	props->max_mr		   = 1 << MLX5_CAP_GEN(mdev, log_max_mkey);
	props->max_pd		   = 1 << MLX5_CAP_GEN(mdev, log_max_pd);
	props->max_qp_rd_atom	   = 1 << MLX5_CAP_GEN(mdev, log_max_ra_req_qp);
	props->max_qp_init_rd_atom = 1 << MLX5_CAP_GEN(mdev, log_max_ra_res_qp);
	props->max_srq		   = 1 << MLX5_CAP_GEN(mdev, log_max_srq);
	props->max_srq_wr = (1 << MLX5_CAP_GEN(mdev, log_max_srq_sz)) - 1;
	props->local_ca_ack_delay  = MLX5_CAP_GEN(mdev, local_ca_ack_delay);
	props->max_res_rd_atom	   = props->max_qp_rd_atom * props->max_qp;
	props->max_srq_sge	   = max_rq_sg - 1;
	props->max_fast_reg_page_list_len =
		1 << MLX5_CAP_GEN(mdev, log_max_klm_list_size);
	get_atomic_caps_qp(dev, props);
	props->masked_atomic_cap   = IB_ATOMIC_NONE;
	props->max_mcast_grp	   = 1 << MLX5_CAP_GEN(mdev, log_max_mcg);
	props->max_mcast_qp_attach = MLX5_CAP_GEN(mdev, max_qp_mcg);
	props->max_total_mcast_qp_attach = props->max_mcast_qp_attach *
					   props->max_mcast_grp;
	props->max_map_per_fmr = INT_MAX; /* no limit in ConnectIB */
	props->max_ah = INT_MAX;
	props->hca_core_clock = MLX5_CAP_GEN(mdev, device_frequency_khz);
	props->timestamp_mask = 0x7FFFFFFFFFFFFFFFULL;

#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
	if (MLX5_CAP_GEN(mdev, pg))
		props->device_cap_flags |= IB_DEVICE_ON_DEMAND_PAGING;
	props->odp_caps = dev->odp_caps;
#endif

	if (MLX5_CAP_GEN(mdev, cd))
		props->device_cap_flags |= IB_DEVICE_CROSS_CHANNEL;

	if (!mlx5_core_is_pf(mdev))
		props->device_cap_flags |= IB_DEVICE_VIRTUAL_FUNCTION;

	if (mlx5_ib_port_link_layer(ibdev, 1) ==
	    IB_LINK_LAYER_ETHERNET && raw_support) {
		props->rss_caps.max_rwq_indirection_tables =
			1 << MLX5_CAP_GEN(dev->mdev, log_max_rqt);
		props->rss_caps.max_rwq_indirection_table_size =
			1 << MLX5_CAP_GEN(dev->mdev, log_max_rqt_size);
		props->rss_caps.supported_qpts = 1 << IB_QPT_RAW_PACKET;
		props->max_wq_type_rq =
			1 << MLX5_CAP_GEN(dev->mdev, log_max_rq);
	}

	if (MLX5_CAP_GEN(mdev, tag_matching)) {
		props->tm_caps.max_rndv_hdr_size = MLX5_TM_MAX_RNDV_MSG_SIZE;
		props->tm_caps.max_num_tags =
			(1 << MLX5_CAP_GEN(mdev, log_tag_matching_list_sz)) - 1;
		props->tm_caps.flags = IB_TM_CAP_RC;
		props->tm_caps.max_ops =
			1 << MLX5_CAP_GEN(mdev, log_max_qp_sz);
		props->tm_caps.max_sge = MLX5_TM_MAX_SGE;
	}

	if (MLX5_CAP_GEN(dev->mdev, cq_moderation)) {
		props->cq_caps.max_cq_moderation_count =
						MLX5_MAX_CQ_COUNT;
		props->cq_caps.max_cq_moderation_period =
						MLX5_MAX_CQ_PERIOD;
	}

	if (field_avail(typeof(resp), cqe_comp_caps, uhw->outlen)) {
		resp.response_length += sizeof(resp.cqe_comp_caps);

		if (MLX5_CAP_GEN(dev->mdev, cqe_compression)) {
			resp.cqe_comp_caps.max_num =
				MLX5_CAP_GEN(dev->mdev,
					     cqe_compression_max_num);

			resp.cqe_comp_caps.supported_format =
				MLX5_IB_CQE_RES_FORMAT_HASH |
				MLX5_IB_CQE_RES_FORMAT_CSUM;

			if (MLX5_CAP_GEN(dev->mdev, mini_cqe_resp_stride_index))
				resp.cqe_comp_caps.supported_format |=
					MLX5_IB_CQE_RES_FORMAT_CSUM_STRIDX;
		}
	}

	if (field_avail(typeof(resp), packet_pacing_caps, uhw->outlen) &&
	    raw_support) {
		if (MLX5_CAP_QOS(mdev, packet_pacing) &&
		    MLX5_CAP_GEN(mdev, qos)) {
			resp.packet_pacing_caps.qp_rate_limit_max =
				MLX5_CAP_QOS(mdev, packet_pacing_max_rate);
			resp.packet_pacing_caps.qp_rate_limit_min =
				MLX5_CAP_QOS(mdev, packet_pacing_min_rate);
			resp.packet_pacing_caps.supported_qpts |=
				1 << IB_QPT_RAW_PACKET;
			if (MLX5_CAP_QOS(mdev, packet_pacing_burst_bound) &&
			    MLX5_CAP_QOS(mdev, packet_pacing_typical_size))
				resp.packet_pacing_caps.cap_flags |=
					MLX5_IB_PP_SUPPORT_BURST;
		}
		resp.response_length += sizeof(resp.packet_pacing_caps);
	}

	if (field_avail(typeof(resp), mlx5_ib_support_multi_pkt_send_wqes,
			uhw->outlen)) {
		if (MLX5_CAP_ETH(mdev, multi_pkt_send_wqe))
			resp.mlx5_ib_support_multi_pkt_send_wqes =
				MLX5_IB_ALLOW_MPW;

		if (MLX5_CAP_ETH(mdev, enhanced_multi_pkt_send_wqe))
			resp.mlx5_ib_support_multi_pkt_send_wqes |=
				MLX5_IB_SUPPORT_EMPW;

		resp.response_length +=
			sizeof(resp.mlx5_ib_support_multi_pkt_send_wqes);
	}

	if (field_avail(typeof(resp), flags, uhw->outlen)) {
		resp.response_length += sizeof(resp.flags);

		if (MLX5_CAP_GEN(mdev, cqe_compression_128))
			resp.flags |=
				MLX5_IB_QUERY_DEV_RESP_FLAGS_CQE_128B_COMP;

		if (MLX5_CAP_GEN(mdev, cqe_128_always))
			resp.flags |= MLX5_IB_QUERY_DEV_RESP_FLAGS_CQE_128B_PAD;
	}

	if (field_avail(typeof(resp), sw_parsing_caps,
			uhw->outlen)) {
		resp.response_length += sizeof(resp.sw_parsing_caps);
		if (MLX5_CAP_ETH(mdev, swp)) {
			resp.sw_parsing_caps.sw_parsing_offloads |=
				MLX5_IB_SW_PARSING;

			if (MLX5_CAP_ETH(mdev, swp_csum))
				resp.sw_parsing_caps.sw_parsing_offloads |=
					MLX5_IB_SW_PARSING_CSUM;

			if (MLX5_CAP_ETH(mdev, swp_lso))
				resp.sw_parsing_caps.sw_parsing_offloads |=
					MLX5_IB_SW_PARSING_LSO;

			if (resp.sw_parsing_caps.sw_parsing_offloads)
				resp.sw_parsing_caps.supported_qpts =
					BIT(IB_QPT_RAW_PACKET);
		}
	}

	if (field_avail(typeof(resp), striding_rq_caps, uhw->outlen) &&
	    raw_support) {
		resp.response_length += sizeof(resp.striding_rq_caps);
		if (MLX5_CAP_GEN(mdev, striding_rq)) {
			resp.striding_rq_caps.min_single_stride_log_num_of_bytes =
				MLX5_MIN_SINGLE_STRIDE_LOG_NUM_BYTES;
			resp.striding_rq_caps.max_single_stride_log_num_of_bytes =
				MLX5_MAX_SINGLE_STRIDE_LOG_NUM_BYTES;
			resp.striding_rq_caps.min_single_wqe_log_num_of_strides =
				MLX5_MIN_SINGLE_WQE_LOG_NUM_STRIDES;
			resp.striding_rq_caps.max_single_wqe_log_num_of_strides =
				MLX5_MAX_SINGLE_WQE_LOG_NUM_STRIDES;
			resp.striding_rq_caps.supported_qpts =
				BIT(IB_QPT_RAW_PACKET);
		}
	}

	if (field_avail(typeof(resp), tunnel_offloads_caps,
			uhw->outlen)) {
		resp.response_length += sizeof(resp.tunnel_offloads_caps);
		if (MLX5_CAP_ETH(mdev, tunnel_stateless_vxlan))
			resp.tunnel_offloads_caps |=
				MLX5_IB_TUNNELED_OFFLOADS_VXLAN;
		if (MLX5_CAP_ETH(mdev, tunnel_stateless_geneve_rx))
			resp.tunnel_offloads_caps |=
				MLX5_IB_TUNNELED_OFFLOADS_GENEVE;
		if (MLX5_CAP_ETH(mdev, tunnel_stateless_gre))
			resp.tunnel_offloads_caps |=
				MLX5_IB_TUNNELED_OFFLOADS_GRE;
		if (MLX5_CAP_GEN(mdev, flex_parser_protocols) &
		    MLX5_FLEX_PROTO_CW_MPLS_GRE)
			resp.tunnel_offloads_caps |=
				MLX5_IB_TUNNELED_OFFLOADS_MPLS_GRE;
		if (MLX5_CAP_GEN(mdev, flex_parser_protocols) &
		    MLX5_FLEX_PROTO_CW_MPLS_UDP)
			resp.tunnel_offloads_caps |=
				MLX5_IB_TUNNELED_OFFLOADS_MPLS_UDP;
	}

	if (uhw->outlen) {
		err = ib_copy_to_udata(uhw, &resp, resp.response_length);

		if (err)
			return err;
	}

	return 0;
}

enum mlx5_ib_width {
	MLX5_IB_WIDTH_1X	= 1 << 0,
	MLX5_IB_WIDTH_2X	= 1 << 1,
	MLX5_IB_WIDTH_4X	= 1 << 2,
	MLX5_IB_WIDTH_8X	= 1 << 3,
	MLX5_IB_WIDTH_12X	= 1 << 4
};

static int translate_active_width(struct ib_device *ibdev, u8 active_width,
				  u8 *ib_width)
{
	struct mlx5_ib_dev *dev = to_mdev(ibdev);
	int err = 0;

	if (active_width & MLX5_IB_WIDTH_1X) {
		*ib_width = IB_WIDTH_1X;
	} else if (active_width & MLX5_IB_WIDTH_2X) {
		mlx5_ib_dbg(dev, "active_width %d is not supported by IB spec\n",
			    (int)active_width);
		err = -EINVAL;
	} else if (active_width & MLX5_IB_WIDTH_4X) {
		*ib_width = IB_WIDTH_4X;
	} else if (active_width & MLX5_IB_WIDTH_8X) {
		*ib_width = IB_WIDTH_8X;
	} else if (active_width & MLX5_IB_WIDTH_12X) {
		*ib_width = IB_WIDTH_12X;
	} else {
		mlx5_ib_dbg(dev, "Invalid active_width %d\n",
			    (int)active_width);
		err = -EINVAL;
	}

	return err;
}

static int mlx5_mtu_to_ib_mtu(int mtu)
{
	switch (mtu) {
	case 256: return 1;
	case 512: return 2;
	case 1024: return 3;
	case 2048: return 4;
	case 4096: return 5;
	default:
		pr_warn("invalid mtu\n");
		return -1;
	}
}

enum ib_max_vl_num {
	__IB_MAX_VL_0		= 1,
	__IB_MAX_VL_0_1		= 2,
	__IB_MAX_VL_0_3		= 3,
	__IB_MAX_VL_0_7		= 4,
	__IB_MAX_VL_0_14	= 5,
};

enum mlx5_vl_hw_cap {
	MLX5_VL_HW_0	= 1,
	MLX5_VL_HW_0_1	= 2,
	MLX5_VL_HW_0_2	= 3,
	MLX5_VL_HW_0_3	= 4,
	MLX5_VL_HW_0_4	= 5,
	MLX5_VL_HW_0_5	= 6,
	MLX5_VL_HW_0_6	= 7,
	MLX5_VL_HW_0_7	= 8,
	MLX5_VL_HW_0_14	= 15
};

static int translate_max_vl_num(struct ib_device *ibdev, u8 vl_hw_cap,
				u8 *max_vl_num)
{
	switch (vl_hw_cap) {
	case MLX5_VL_HW_0:
		*max_vl_num = __IB_MAX_VL_0;
		break;
	case MLX5_VL_HW_0_1:
		*max_vl_num = __IB_MAX_VL_0_1;
		break;
	case MLX5_VL_HW_0_3:
		*max_vl_num = __IB_MAX_VL_0_3;
		break;
	case MLX5_VL_HW_0_7:
		*max_vl_num = __IB_MAX_VL_0_7;
		break;
	case MLX5_VL_HW_0_14:
		*max_vl_num = __IB_MAX_VL_0_14;
		break;

	default:
		return -EINVAL;
	}

	return 0;
}

static int mlx5_query_hca_port(struct ib_device *ibdev, u8 port,
			       struct ib_port_attr *props)
{
	struct mlx5_ib_dev *dev = to_mdev(ibdev);
	struct mlx5_core_dev *mdev = dev->mdev;
	struct mlx5_hca_vport_context *rep;
	u16 max_mtu;
	u16 oper_mtu;
	int err;
	u8 ib_link_width_oper;
	u8 vl_hw_cap;

	rep = kzalloc(sizeof(*rep), GFP_KERNEL);
	if (!rep) {
		err = -ENOMEM;
		goto out;
	}

	/* props being zeroed by the caller, avoid zeroing it here */

	err = mlx5_query_hca_vport_context(mdev, 0, port, 0, rep);
	if (err)
		goto out;

	props->lid		= rep->lid;
	props->lmc		= rep->lmc;
	props->sm_lid		= rep->sm_lid;
	props->sm_sl		= rep->sm_sl;
	props->state		= rep->vport_state;
	props->phys_state	= rep->port_physical_state;
	props->port_cap_flags	= rep->cap_mask1;
	props->gid_tbl_len	= mlx5_get_gid_table_len(MLX5_CAP_GEN(mdev, gid_table_size));
	props->max_msg_sz	= 1 << MLX5_CAP_GEN(mdev, log_max_msg);
	props->pkey_tbl_len	= mlx5_to_sw_pkey_sz(MLX5_CAP_GEN(mdev, pkey_table_size));
	props->bad_pkey_cntr	= rep->pkey_violation_counter;
	props->qkey_viol_cntr	= rep->qkey_violation_counter;
	props->subnet_timeout	= rep->subnet_timeout;
	props->init_type_reply	= rep->init_type_reply;

	err = mlx5_query_port_link_width_oper(mdev, &ib_link_width_oper, port);
	if (err)
		goto out;

	err = translate_active_width(ibdev, ib_link_width_oper,
				     &props->active_width);
	if (err)
		goto out;
	err = mlx5_query_port_ib_proto_oper(mdev, &props->active_speed, port);
	if (err)
		goto out;

	mlx5_query_port_max_mtu(mdev, &max_mtu, port);

	props->max_mtu = mlx5_mtu_to_ib_mtu(max_mtu);

	mlx5_query_port_oper_mtu(mdev, &oper_mtu, port);

	props->active_mtu = mlx5_mtu_to_ib_mtu(oper_mtu);

	err = mlx5_query_port_vl_hw_cap(mdev, &vl_hw_cap, port);
	if (err)
		goto out;

	err = translate_max_vl_num(ibdev, vl_hw_cap,
				   &props->max_vl_num);
out:
	kfree(rep);
	return err;
}

int mlx5_ib_query_port(struct ib_device *ibdev, u8 port,
		       struct ib_port_attr *props)
{
	unsigned int count;
	int ret;

	switch (mlx5_get_vport_access_method(ibdev)) {
	case MLX5_VPORT_ACCESS_METHOD_MAD:
		ret = mlx5_query_mad_ifc_port(ibdev, port, props);
		break;

	case MLX5_VPORT_ACCESS_METHOD_HCA:
		ret = mlx5_query_hca_port(ibdev, port, props);
		break;

	case MLX5_VPORT_ACCESS_METHOD_NIC:
		ret = mlx5_query_port_roce(ibdev, port, props);
		break;

	default:
		ret = -EINVAL;
	}

	if (!ret && props) {
		struct mlx5_ib_dev *dev = to_mdev(ibdev);
		struct mlx5_core_dev *mdev;
		bool put_mdev = true;

		mdev = mlx5_ib_get_native_port_mdev(dev, port, NULL);
		if (!mdev) {
			/* If the port isn't affiliated yet query the master.
			 * The master and slave will have the same values.
			 */
			mdev = dev->mdev;
			port = 1;
			put_mdev = false;
		}
		count = mlx5_core_reserved_gids_count(mdev);
		if (put_mdev)
			mlx5_ib_put_native_port_mdev(dev, port);
		props->gid_tbl_len -= count;
	}
	return ret;
}

static int mlx5_ib_rep_query_port(struct ib_device *ibdev, u8 port,
				  struct ib_port_attr *props)
{
	int ret;

	/* Only link layer == ethernet is valid for representors */
	ret = mlx5_query_port_roce(ibdev, port, props);
	if (ret || !props)
		return ret;

	/* We don't support GIDS */
	props->gid_tbl_len = 0;

	return ret;
}

static int mlx5_ib_query_gid(struct ib_device *ibdev, u8 port, int index,
			     union ib_gid *gid)
{
	struct mlx5_ib_dev *dev = to_mdev(ibdev);
	struct mlx5_core_dev *mdev = dev->mdev;

	switch (mlx5_get_vport_access_method(ibdev)) {
	case MLX5_VPORT_ACCESS_METHOD_MAD:
		return mlx5_query_mad_ifc_gids(ibdev, port, index, gid);

	case MLX5_VPORT_ACCESS_METHOD_HCA:
		return mlx5_query_hca_vport_gid(mdev, 0, port, 0, index, gid);

	default:
		return -EINVAL;
	}

}

static int mlx5_query_hca_nic_pkey(struct ib_device *ibdev, u8 port,
				   u16 index, u16 *pkey)
{
	struct mlx5_ib_dev *dev = to_mdev(ibdev);
	struct mlx5_core_dev *mdev;
	bool put_mdev = true;
	u8 mdev_port_num;
	int err;

	mdev = mlx5_ib_get_native_port_mdev(dev, port, &mdev_port_num);
	if (!mdev) {
		/* The port isn't affiliated yet, get the PKey from the master
		 * port. For RoCE the PKey tables will be the same.
		 */
		put_mdev = false;
		mdev = dev->mdev;
		mdev_port_num = 1;
	}

	err = mlx5_query_hca_vport_pkey(mdev, 0, mdev_port_num, 0,
					index, pkey);
	if (put_mdev)
		mlx5_ib_put_native_port_mdev(dev, port);

	return err;
}

static int mlx5_ib_query_pkey(struct ib_device *ibdev, u8 port, u16 index,
			      u16 *pkey)
{
	switch (mlx5_get_vport_access_method(ibdev)) {
	case MLX5_VPORT_ACCESS_METHOD_MAD:
		return mlx5_query_mad_ifc_pkey(ibdev, port, index, pkey);

	case MLX5_VPORT_ACCESS_METHOD_HCA:
	case MLX5_VPORT_ACCESS_METHOD_NIC:
		return mlx5_query_hca_nic_pkey(ibdev, port, index, pkey);
	default:
		return -EINVAL;
	}
}

static int mlx5_ib_modify_device(struct ib_device *ibdev, int mask,
				 struct ib_device_modify *props)
{
	struct mlx5_ib_dev *dev = to_mdev(ibdev);
	struct mlx5_reg_node_desc in;
	struct mlx5_reg_node_desc out;
	int err;

	if (mask & ~IB_DEVICE_MODIFY_NODE_DESC)
		return -EOPNOTSUPP;

	if (!(mask & IB_DEVICE_MODIFY_NODE_DESC))
		return 0;

	/*
	 * If possible, pass node desc to FW, so it can generate
	 * a 144 trap.  If cmd fails, just ignore.
	 */
	memcpy(&in, props->node_desc, IB_DEVICE_NODE_DESC_MAX);
	err = mlx5_core_access_reg(dev->mdev, &in, sizeof(in), &out,
				   sizeof(out), MLX5_REG_NODE_DESC, 0, 1);
	if (err)
		return err;

	memcpy(ibdev->node_desc, props->node_desc, IB_DEVICE_NODE_DESC_MAX);

	return err;
}

static int set_port_caps_atomic(struct mlx5_ib_dev *dev, u8 port_num, u32 mask,
				u32 value)
{
	struct mlx5_hca_vport_context ctx = {};
	struct mlx5_core_dev *mdev;
	u8 mdev_port_num;
	int err;

	mdev = mlx5_ib_get_native_port_mdev(dev, port_num, &mdev_port_num);
	if (!mdev)
		return -ENODEV;

	err = mlx5_query_hca_vport_context(mdev, 0, mdev_port_num, 0, &ctx);
	if (err)
		goto out;

	if (~ctx.cap_mask1_perm & mask) {
		mlx5_ib_warn(dev, "trying to change bitmask 0x%X but change supported 0x%X\n",
			     mask, ctx.cap_mask1_perm);
		err = -EINVAL;
		goto out;
	}

	ctx.cap_mask1 = value;
	ctx.cap_mask1_perm = mask;
	err = mlx5_core_modify_hca_vport_context(mdev, 0, mdev_port_num,
						 0, &ctx);

out:
	mlx5_ib_put_native_port_mdev(dev, port_num);

	return err;
}

static int mlx5_ib_modify_port(struct ib_device *ibdev, u8 port, int mask,
			       struct ib_port_modify *props)
{
	struct mlx5_ib_dev *dev = to_mdev(ibdev);
	struct ib_port_attr attr;
	u32 tmp;
	int err;
	u32 change_mask;
	u32 value;
	bool is_ib = (mlx5_ib_port_link_layer(ibdev, port) ==
		      IB_LINK_LAYER_INFINIBAND);

	/* CM layer calls ib_modify_port() regardless of the link layer. For
	 * Ethernet ports, qkey violation and Port capabilities are meaningless.
	 */
	if (!is_ib)
		return 0;

	if (MLX5_CAP_GEN(dev->mdev, ib_virt) && is_ib) {
		change_mask = props->clr_port_cap_mask | props->set_port_cap_mask;
		value = ~props->clr_port_cap_mask | props->set_port_cap_mask;
		return set_port_caps_atomic(dev, port, change_mask, value);
	}

	mutex_lock(&dev->cap_mask_mutex);

	err = ib_query_port(ibdev, port, &attr);
	if (err)
		goto out;

	tmp = (attr.port_cap_flags | props->set_port_cap_mask) &
		~props->clr_port_cap_mask;

	err = mlx5_set_port_caps(dev->mdev, port, tmp);

out:
	mutex_unlock(&dev->cap_mask_mutex);
	return err;
}

static void print_lib_caps(struct mlx5_ib_dev *dev, u64 caps)
{
	mlx5_ib_dbg(dev, "MLX5_LIB_CAP_4K_UAR = %s\n",
		    caps & MLX5_LIB_CAP_4K_UAR ? "y" : "n");
}

static u16 calc_dynamic_bfregs(int uars_per_sys_page)
{
	/* Large page with non 4k uar support might limit the dynamic size */
	if (uars_per_sys_page == 1  && PAGE_SIZE > 4096)
		return MLX5_MIN_DYN_BFREGS;

	return MLX5_MAX_DYN_BFREGS;
}

static int calc_total_bfregs(struct mlx5_ib_dev *dev, bool lib_uar_4k,
			     struct mlx5_ib_alloc_ucontext_req_v2 *req,
			     struct mlx5_bfreg_info *bfregi)
{
	int uars_per_sys_page;
	int bfregs_per_sys_page;
	int ref_bfregs = req->total_num_bfregs;

	if (req->total_num_bfregs == 0)
		return -EINVAL;

	BUILD_BUG_ON(MLX5_MAX_BFREGS % MLX5_NON_FP_BFREGS_IN_PAGE);
	BUILD_BUG_ON(MLX5_MAX_BFREGS < MLX5_NON_FP_BFREGS_IN_PAGE);

	if (req->total_num_bfregs > MLX5_MAX_BFREGS)
		return -ENOMEM;

	uars_per_sys_page = get_uars_per_sys_page(dev, lib_uar_4k);
	bfregs_per_sys_page = uars_per_sys_page * MLX5_NON_FP_BFREGS_PER_UAR;
	/* This holds the required static allocation asked by the user */
	req->total_num_bfregs = ALIGN(req->total_num_bfregs, bfregs_per_sys_page);
	if (req->num_low_latency_bfregs > req->total_num_bfregs - 1)
		return -EINVAL;

	bfregi->num_static_sys_pages = req->total_num_bfregs / bfregs_per_sys_page;
	bfregi->num_dyn_bfregs = ALIGN(calc_dynamic_bfregs(uars_per_sys_page), bfregs_per_sys_page);
	bfregi->total_num_bfregs = req->total_num_bfregs + bfregi->num_dyn_bfregs;
	bfregi->num_sys_pages = bfregi->total_num_bfregs / bfregs_per_sys_page;

	mlx5_ib_dbg(dev, "uar_4k: fw support %s, lib support %s, user requested %d bfregs, allocated %d, total bfregs %d, using %d sys pages\n",
		    MLX5_CAP_GEN(dev->mdev, uar_4k) ? "yes" : "no",
		    lib_uar_4k ? "yes" : "no", ref_bfregs,
		    req->total_num_bfregs, bfregi->total_num_bfregs,
		    bfregi->num_sys_pages);

	return 0;
}

static int allocate_uars(struct mlx5_ib_dev *dev, struct mlx5_ib_ucontext *context)
{
	struct mlx5_bfreg_info *bfregi;
	int err;
	int i;

	bfregi = &context->bfregi;
	for (i = 0; i < bfregi->num_static_sys_pages; i++) {
		err = mlx5_cmd_alloc_uar(dev->mdev, &bfregi->sys_pages[i]);
		if (err)
			goto error;

		mlx5_ib_dbg(dev, "allocated uar %d\n", bfregi->sys_pages[i]);
	}

	for (i = bfregi->num_static_sys_pages; i < bfregi->num_sys_pages; i++)
		bfregi->sys_pages[i] = MLX5_IB_INVALID_UAR_INDEX;

	return 0;

error:
	for (--i; i >= 0; i--)
		if (mlx5_cmd_free_uar(dev->mdev, bfregi->sys_pages[i]))
			mlx5_ib_warn(dev, "failed to free uar %d\n", i);

	return err;
}

static void deallocate_uars(struct mlx5_ib_dev *dev,
			    struct mlx5_ib_ucontext *context)
{
	struct mlx5_bfreg_info *bfregi;
	int i;

	bfregi = &context->bfregi;
	for (i = 0; i < bfregi->num_sys_pages; i++)
		if (i < bfregi->num_static_sys_pages ||
		    bfregi->sys_pages[i] != MLX5_IB_INVALID_UAR_INDEX)
			mlx5_cmd_free_uar(dev->mdev, bfregi->sys_pages[i]);
}

int mlx5_ib_enable_lb(struct mlx5_ib_dev *dev, bool td, bool qp)
{
	int err = 0;

	mutex_lock(&dev->lb.mutex);
	if (td)
		dev->lb.user_td++;
	if (qp)
		dev->lb.qps++;

	if (dev->lb.user_td == 2 ||
	    dev->lb.qps == 1) {
		if (!dev->lb.enabled) {
			err = mlx5_nic_vport_update_local_lb(dev->mdev, true);
			dev->lb.enabled = true;
		}
	}

	mutex_unlock(&dev->lb.mutex);

	return err;
}

void mlx5_ib_disable_lb(struct mlx5_ib_dev *dev, bool td, bool qp)
{
	mutex_lock(&dev->lb.mutex);
	if (td)
		dev->lb.user_td--;
	if (qp)
		dev->lb.qps--;

	if (dev->lb.user_td == 1 &&
	    dev->lb.qps == 0) {
		if (dev->lb.enabled) {
			mlx5_nic_vport_update_local_lb(dev->mdev, false);
			dev->lb.enabled = false;
		}
	}

	mutex_unlock(&dev->lb.mutex);
}

static int mlx5_ib_alloc_transport_domain(struct mlx5_ib_dev *dev, u32 *tdn,
					  u16 uid)
{
	int err;

	if (!MLX5_CAP_GEN(dev->mdev, log_max_transport_domain))
		return 0;

	err = mlx5_cmd_alloc_transport_domain(dev->mdev, tdn, uid);
	if (err)
		return err;

	if ((MLX5_CAP_GEN(dev->mdev, port_type) != MLX5_CAP_PORT_TYPE_ETH) ||
	    (!MLX5_CAP_GEN(dev->mdev, disable_local_lb_uc) &&
	     !MLX5_CAP_GEN(dev->mdev, disable_local_lb_mc)))
		return err;

	return mlx5_ib_enable_lb(dev, true, false);
}

static void mlx5_ib_dealloc_transport_domain(struct mlx5_ib_dev *dev, u32 tdn,
					     u16 uid)
{
	if (!MLX5_CAP_GEN(dev->mdev, log_max_transport_domain))
		return;

	mlx5_cmd_dealloc_transport_domain(dev->mdev, tdn, uid);

	if ((MLX5_CAP_GEN(dev->mdev, port_type) != MLX5_CAP_PORT_TYPE_ETH) ||
	    (!MLX5_CAP_GEN(dev->mdev, disable_local_lb_uc) &&
	     !MLX5_CAP_GEN(dev->mdev, disable_local_lb_mc)))
		return;

	mlx5_ib_disable_lb(dev, true, false);
}

static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
						  struct ib_udata *udata)
{
	struct mlx5_ib_dev *dev = to_mdev(ibdev);
	struct mlx5_ib_alloc_ucontext_req_v2 req = {};
	struct mlx5_ib_alloc_ucontext_resp resp = {};
	struct mlx5_core_dev *mdev = dev->mdev;
	struct mlx5_ib_ucontext *context;
	struct mlx5_bfreg_info *bfregi;
	int ver;
	int err;
	size_t min_req_v2 = offsetof(struct mlx5_ib_alloc_ucontext_req_v2,
				     max_cqe_version);
	u32 dump_fill_mkey;
	bool lib_uar_4k;

	if (!dev->ib_active)
		return ERR_PTR(-EAGAIN);

	if (udata->inlen == sizeof(struct mlx5_ib_alloc_ucontext_req))
		ver = 0;
	else if (udata->inlen >= min_req_v2)
		ver = 2;
	else
		return ERR_PTR(-EINVAL);

	err = ib_copy_from_udata(&req, udata, min(udata->inlen, sizeof(req)));
	if (err)
		return ERR_PTR(err);

	if (req.flags & ~MLX5_IB_ALLOC_UCTX_DEVX)
		return ERR_PTR(-EOPNOTSUPP);

	if (req.comp_mask || req.reserved0 || req.reserved1 || req.reserved2)
		return ERR_PTR(-EOPNOTSUPP);

	req.total_num_bfregs = ALIGN(req.total_num_bfregs,
				    MLX5_NON_FP_BFREGS_PER_UAR);
	if (req.num_low_latency_bfregs > req.total_num_bfregs - 1)
		return ERR_PTR(-EINVAL);

	resp.qp_tab_size = 1 << MLX5_CAP_GEN(dev->mdev, log_max_qp);
	if (mlx5_core_is_pf(dev->mdev) && MLX5_CAP_GEN(dev->mdev, bf))
		resp.bf_reg_size = 1 << MLX5_CAP_GEN(dev->mdev, log_bf_reg_size);
	resp.cache_line_size = cache_line_size();
	resp.max_sq_desc_sz = MLX5_CAP_GEN(dev->mdev, max_wqe_sz_sq);
	resp.max_rq_desc_sz = MLX5_CAP_GEN(dev->mdev, max_wqe_sz_rq);
	resp.max_send_wqebb = 1 << MLX5_CAP_GEN(dev->mdev, log_max_qp_sz);
	resp.max_recv_wr = 1 << MLX5_CAP_GEN(dev->mdev, log_max_qp_sz);
	resp.max_srq_recv_wr = 1 << MLX5_CAP_GEN(dev->mdev, log_max_srq_sz);
	resp.cqe_version = min_t(__u8,
				 (__u8)MLX5_CAP_GEN(dev->mdev, cqe_version),
				 req.max_cqe_version);
	resp.log_uar_size = MLX5_CAP_GEN(dev->mdev, uar_4k) ?
				MLX5_ADAPTER_PAGE_SHIFT : PAGE_SHIFT;
	resp.num_uars_per_page = MLX5_CAP_GEN(dev->mdev, uar_4k) ?
					MLX5_CAP_GEN(dev->mdev, num_of_uars_per_page) : 1;
	resp.response_length = min(offsetof(typeof(resp), response_length) +
				   sizeof(resp.response_length), udata->outlen);

	if (mlx5_accel_ipsec_device_caps(dev->mdev) & MLX5_ACCEL_IPSEC_CAP_DEVICE) {
		if (mlx5_get_flow_namespace(dev->mdev, MLX5_FLOW_NAMESPACE_EGRESS))
			resp.flow_action_flags |= MLX5_USER_ALLOC_UCONTEXT_FLOW_ACTION_FLAGS_ESP_AES_GCM;
		if (mlx5_accel_ipsec_device_caps(dev->mdev) & MLX5_ACCEL_IPSEC_CAP_REQUIRED_METADATA)
			resp.flow_action_flags |= MLX5_USER_ALLOC_UCONTEXT_FLOW_ACTION_FLAGS_ESP_AES_GCM_REQ_METADATA;
		if (MLX5_CAP_FLOWTABLE(dev->mdev, flow_table_properties_nic_receive.ft_field_support.outer_esp_spi))
			resp.flow_action_flags |= MLX5_USER_ALLOC_UCONTEXT_FLOW_ACTION_FLAGS_ESP_AES_GCM_SPI_STEERING;
		if (mlx5_accel_ipsec_device_caps(dev->mdev) & MLX5_ACCEL_IPSEC_CAP_TX_IV_IS_ESN)
			resp.flow_action_flags |= MLX5_USER_ALLOC_UCONTEXT_FLOW_ACTION_FLAGS_ESP_AES_GCM_TX_IV_IS_ESN;
		/* MLX5_USER_ALLOC_UCONTEXT_FLOW_ACTION_FLAGS_ESP_AES_GCM_FULL_OFFLOAD is currently always 0 */
	}

	context = kzalloc(sizeof(*context), GFP_KERNEL);
	if (!context)
		return ERR_PTR(-ENOMEM);

	lib_uar_4k = req.lib_caps & MLX5_LIB_CAP_4K_UAR;
	bfregi = &context->bfregi;

	/* updates req->total_num_bfregs */
	err = calc_total_bfregs(dev, lib_uar_4k, &req, bfregi);
	if (err)
		goto out_ctx;

	mutex_init(&bfregi->lock);
	bfregi->lib_uar_4k = lib_uar_4k;
	bfregi->count = kcalloc(bfregi->total_num_bfregs, sizeof(*bfregi->count),
				GFP_KERNEL);
	if (!bfregi->count) {
		err = -ENOMEM;
		goto out_ctx;
	}

	bfregi->sys_pages = kcalloc(bfregi->num_sys_pages,
				    sizeof(*bfregi->sys_pages),
				    GFP_KERNEL);
	if (!bfregi->sys_pages) {
		err = -ENOMEM;
		goto out_count;
	}

	err = allocate_uars(dev, context);
	if (err)
		goto out_sys_pages;

#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
	context->ibucontext.invalidate_range = &mlx5_ib_invalidate_range;
#endif

	if (req.flags & MLX5_IB_ALLOC_UCTX_DEVX) {
		err = mlx5_ib_devx_create(dev);
		if (err < 0)
			goto out_uars;
		context->devx_uid = err;
	}

	err = mlx5_ib_alloc_transport_domain(dev, &context->tdn,
					     context->devx_uid);
	if (err)
		goto out_devx;

	if (MLX5_CAP_GEN(dev->mdev, dump_fill_mkey)) {
		err = mlx5_cmd_dump_fill_mkey(dev->mdev, &dump_fill_mkey);
		if (err)
			goto out_mdev;
	}

	INIT_LIST_HEAD(&context->db_page_list);
	mutex_init(&context->db_page_mutex);

	resp.tot_bfregs = req.total_num_bfregs;
	resp.num_ports = dev->num_ports;

	if (field_avail(typeof(resp), cqe_version, udata->outlen))
		resp.response_length += sizeof(resp.cqe_version);

	if (field_avail(typeof(resp), cmds_supp_uhw, udata->outlen)) {
		resp.cmds_supp_uhw |= MLX5_USER_CMDS_SUPP_UHW_QUERY_DEVICE |
				      MLX5_USER_CMDS_SUPP_UHW_CREATE_AH;
		resp.response_length += sizeof(resp.cmds_supp_uhw);
	}

	if (field_avail(typeof(resp), eth_min_inline, udata->outlen)) {
		if (mlx5_ib_port_link_layer(ibdev, 1) == IB_LINK_LAYER_ETHERNET) {
			mlx5_query_min_inline(dev->mdev, &resp.eth_min_inline);
			resp.eth_min_inline++;
		}
		resp.response_length += sizeof(resp.eth_min_inline);
	}

	if (field_avail(typeof(resp), clock_info_versions, udata->outlen)) {
		if (mdev->clock_info)
			resp.clock_info_versions = BIT(MLX5_IB_CLOCK_INFO_V1);
		resp.response_length += sizeof(resp.clock_info_versions);
	}

	/*
	 * We don't want to expose information from the PCI bar that is located
	 * after 4096 bytes, so if the arch only supports larger pages, let's
	 * pretend we don't support reading the HCA's core clock. This is also
	 * forced by mmap function.
	 */
	if (field_avail(typeof(resp), hca_core_clock_offset, udata->outlen)) {
		if (PAGE_SIZE <= 4096) {
			resp.comp_mask |=
				MLX5_IB_ALLOC_UCONTEXT_RESP_MASK_CORE_CLOCK_OFFSET;
			resp.hca_core_clock_offset =
				offsetof(struct mlx5_init_seg, internal_timer_h) % PAGE_SIZE;
		}
		resp.response_length += sizeof(resp.hca_core_clock_offset);
	}

	if (field_avail(typeof(resp), log_uar_size, udata->outlen))
		resp.response_length += sizeof(resp.log_uar_size);

	if (field_avail(typeof(resp), num_uars_per_page, udata->outlen))
		resp.response_length += sizeof(resp.num_uars_per_page);

	if (field_avail(typeof(resp), num_dyn_bfregs, udata->outlen)) {
		resp.num_dyn_bfregs = bfregi->num_dyn_bfregs;
		resp.response_length += sizeof(resp.num_dyn_bfregs);
	}

	if (field_avail(typeof(resp), dump_fill_mkey, udata->outlen)) {
		if (MLX5_CAP_GEN(dev->mdev, dump_fill_mkey)) {
			resp.dump_fill_mkey = dump_fill_mkey;
			resp.comp_mask |=
				MLX5_IB_ALLOC_UCONTEXT_RESP_MASK_DUMP_FILL_MKEY;
		}
		resp.response_length += sizeof(resp.dump_fill_mkey);
	}

	err = ib_copy_to_udata(udata, &resp, resp.response_length);
	if (err)
		goto out_mdev;

	bfregi->ver = ver;
	bfregi->num_low_latency_bfregs = req.num_low_latency_bfregs;
	context->cqe_version = resp.cqe_version;
	context->lib_caps = req.lib_caps;
	print_lib_caps(dev, context->lib_caps);

	if (mlx5_lag_is_active(dev->mdev)) {
		u8 port = mlx5_core_native_port_num(dev->mdev);

		atomic_set(&context->tx_port_affinity,
			   atomic_add_return(
				   1, &dev->roce[port].tx_port_affinity));
	}

	return &context->ibucontext;

out_mdev:
	mlx5_ib_dealloc_transport_domain(dev, context->tdn, context->devx_uid);
out_devx:
	if (req.flags & MLX5_IB_ALLOC_UCTX_DEVX)
		mlx5_ib_devx_destroy(dev, context->devx_uid);

out_uars:
	deallocate_uars(dev, context);

out_sys_pages:
	kfree(bfregi->sys_pages);

out_count:
	kfree(bfregi->count);

out_ctx:
	kfree(context);

	return ERR_PTR(err);
}

static int mlx5_ib_dealloc_ucontext(struct ib_ucontext *ibcontext)
{
	struct mlx5_ib_ucontext *context = to_mucontext(ibcontext);
	struct mlx5_ib_dev *dev = to_mdev(ibcontext->device);
	struct mlx5_bfreg_info *bfregi;

#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
	/* All umem's must be destroyed before destroying the ucontext. */
	mutex_lock(&ibcontext->per_mm_list_lock);
	WARN_ON(!list_empty(&ibcontext->per_mm_list));
	mutex_unlock(&ibcontext->per_mm_list_lock);
#endif

	bfregi = &context->bfregi;
	mlx5_ib_dealloc_transport_domain(dev, context->tdn, context->devx_uid);

	if (context->devx_uid)
		mlx5_ib_devx_destroy(dev, context->devx_uid);

	deallocate_uars(dev, context);
	kfree(bfregi->sys_pages);
	kfree(bfregi->count);
	kfree(context);

	return 0;
}

static phys_addr_t uar_index2pfn(struct mlx5_ib_dev *dev,
				 int uar_idx)
{
	int fw_uars_per_page;

	fw_uars_per_page = MLX5_CAP_GEN(dev->mdev, uar_4k) ? MLX5_UARS_IN_PAGE : 1;

	return (pci_resource_start(dev->mdev->pdev, 0) >> PAGE_SHIFT) + uar_idx / fw_uars_per_page;
}

static int get_command(unsigned long offset)
{
	return (offset >> MLX5_IB_MMAP_CMD_SHIFT) & MLX5_IB_MMAP_CMD_MASK;
}

static int get_arg(unsigned long offset)
{
	return offset & ((1 << MLX5_IB_MMAP_CMD_SHIFT) - 1);
}

static int get_index(unsigned long offset)
{
	return get_arg(offset);
}

/* Index resides in an extra byte to enable larger values than 255 */
static int get_extended_index(unsigned long offset)
{
	return get_arg(offset) | ((offset >> 16) & 0xff) << 8;
}


static void mlx5_ib_disassociate_ucontext(struct ib_ucontext *ibcontext)
{
}

static inline char *mmap_cmd2str(enum mlx5_ib_mmap_cmd cmd)
{
	switch (cmd) {
	case MLX5_IB_MMAP_WC_PAGE:
		return "WC";
	case MLX5_IB_MMAP_REGULAR_PAGE:
		return "best effort WC";
	case MLX5_IB_MMAP_NC_PAGE:
		return "NC";
	case MLX5_IB_MMAP_DEVICE_MEM:
		return "Device Memory";
	default:
		return NULL;
	}
}

static int mlx5_ib_mmap_clock_info_page(struct mlx5_ib_dev *dev,
					struct vm_area_struct *vma,
					struct mlx5_ib_ucontext *context)
{
	if (vma->vm_end - vma->vm_start != PAGE_SIZE)
		return -EINVAL;

	if (get_index(vma->vm_pgoff) != MLX5_IB_CLOCK_INFO_V1)
		return -EOPNOTSUPP;

	if (vma->vm_flags & VM_WRITE)
		return -EPERM;

	if (!dev->mdev->clock_info_page)
		return -EOPNOTSUPP;

	return rdma_user_mmap_page(&context->ibucontext, vma,
				   dev->mdev->clock_info_page, PAGE_SIZE);
}

static int uar_mmap(struct mlx5_ib_dev *dev, enum mlx5_ib_mmap_cmd cmd,
		    struct vm_area_struct *vma,
		    struct mlx5_ib_ucontext *context)
{
	struct mlx5_bfreg_info *bfregi = &context->bfregi;
	int err;
	unsigned long idx;
	phys_addr_t pfn;
	pgprot_t prot;
	u32 bfreg_dyn_idx = 0;
	u32 uar_index;
	int dyn_uar = (cmd == MLX5_IB_MMAP_ALLOC_WC);
	int max_valid_idx = dyn_uar ? bfregi->num_sys_pages :
				bfregi->num_static_sys_pages;

	if (vma->vm_end - vma->vm_start != PAGE_SIZE)
		return -EINVAL;

	if (dyn_uar)
		idx = get_extended_index(vma->vm_pgoff) + bfregi->num_static_sys_pages;
	else
		idx = get_index(vma->vm_pgoff);

	if (idx >= max_valid_idx) {
		mlx5_ib_warn(dev, "invalid uar index %lu, max=%d\n",
			     idx, max_valid_idx);
		return -EINVAL;
	}

	switch (cmd) {
	case MLX5_IB_MMAP_WC_PAGE:
	case MLX5_IB_MMAP_ALLOC_WC:
/* Some architectures don't support WC memory */
#if defined(CONFIG_X86)
		if (!pat_enabled())
			return -EPERM;
#elif !(defined(CONFIG_PPC) || (defined(CONFIG_ARM) && defined(CONFIG_MMU)))
			return -EPERM;
#endif
	/* fall through */
	case MLX5_IB_MMAP_REGULAR_PAGE:
		/* For MLX5_IB_MMAP_REGULAR_PAGE do the best effort to get WC */
		prot = pgprot_writecombine(vma->vm_page_prot);
		break;
	case MLX5_IB_MMAP_NC_PAGE:
		prot = pgprot_noncached(vma->vm_page_prot);
		break;
	default:
		return -EINVAL;
	}

	if (dyn_uar) {
		int uars_per_page;

		uars_per_page = get_uars_per_sys_page(dev, bfregi->lib_uar_4k);
		bfreg_dyn_idx = idx * (uars_per_page * MLX5_NON_FP_BFREGS_PER_UAR);
		if (bfreg_dyn_idx >= bfregi->total_num_bfregs) {
			mlx5_ib_warn(dev, "invalid bfreg_dyn_idx %u, max=%u\n",
				     bfreg_dyn_idx, bfregi->total_num_bfregs);
			return -EINVAL;
		}

		mutex_lock(&bfregi->lock);
		/* Fail if uar already allocated, first bfreg index of each
		 * page holds its count.
		 */
		if (bfregi->count[bfreg_dyn_idx]) {
			mlx5_ib_warn(dev, "wrong offset, idx %lu is busy, bfregn=%u\n", idx, bfreg_dyn_idx);
			mutex_unlock(&bfregi->lock);
			return -EINVAL;
		}

		bfregi->count[bfreg_dyn_idx]++;
		mutex_unlock(&bfregi->lock);

		err = mlx5_cmd_alloc_uar(dev->mdev, &uar_index);
		if (err) {
			mlx5_ib_warn(dev, "UAR alloc failed\n");
			goto free_bfreg;
		}
	} else {
		uar_index = bfregi->sys_pages[idx];
	}

	pfn = uar_index2pfn(dev, uar_index);
	mlx5_ib_dbg(dev, "uar idx 0x%lx, pfn %pa\n", idx, &pfn);

	err = rdma_user_mmap_io(&context->ibucontext, vma, pfn, PAGE_SIZE,
				prot);
	if (err) {
		mlx5_ib_err(dev,
			    "rdma_user_mmap_io failed with error=%d, mmap_cmd=%s\n",
			    err, mmap_cmd2str(cmd));
		goto err;
	}

	if (dyn_uar)
		bfregi->sys_pages[idx] = uar_index;
	return 0;

err:
	if (!dyn_uar)
		return err;

	mlx5_cmd_free_uar(dev->mdev, idx);

free_bfreg:
	mlx5_ib_free_bfreg(dev, bfregi, bfreg_dyn_idx);

	return err;
}

static int dm_mmap(struct ib_ucontext *context, struct vm_area_struct *vma)
{
	struct mlx5_ib_ucontext *mctx = to_mucontext(context);
	struct mlx5_ib_dev *dev = to_mdev(context->device);
	u16 page_idx = get_extended_index(vma->vm_pgoff);
	size_t map_size = vma->vm_end - vma->vm_start;
	u32 npages = map_size >> PAGE_SHIFT;
	phys_addr_t pfn;

	if (find_next_zero_bit(mctx->dm_pages, page_idx + npages, page_idx) !=
	    page_idx + npages)
		return -EINVAL;

	pfn = ((pci_resource_start(dev->mdev->pdev, 0) +
	      MLX5_CAP64_DEV_MEM(dev->mdev, memic_bar_start_addr)) >>
	      PAGE_SHIFT) +
	      page_idx;
	return rdma_user_mmap_io(context, vma, pfn, map_size,
				 pgprot_writecombine(vma->vm_page_prot));
}

static int mlx5_ib_mmap(struct ib_ucontext *ibcontext, struct vm_area_struct *vma)
{
	struct mlx5_ib_ucontext *context = to_mucontext(ibcontext);
	struct mlx5_ib_dev *dev = to_mdev(ibcontext->device);
	unsigned long command;
	phys_addr_t pfn;

	command = get_command(vma->vm_pgoff);
	switch (command) {
	case MLX5_IB_MMAP_WC_PAGE:
	case MLX5_IB_MMAP_NC_PAGE:
	case MLX5_IB_MMAP_REGULAR_PAGE:
	case MLX5_IB_MMAP_ALLOC_WC:
		return uar_mmap(dev, command, vma, context);

	case MLX5_IB_MMAP_GET_CONTIGUOUS_PAGES:
		return -ENOSYS;

	case MLX5_IB_MMAP_CORE_CLOCK:
		if (vma->vm_end - vma->vm_start != PAGE_SIZE)
			return -EINVAL;

		if (vma->vm_flags & VM_WRITE)
			return -EPERM;

		/* Don't expose to user-space information it shouldn't have */
		if (PAGE_SIZE > 4096)
			return -EOPNOTSUPP;

		vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
		pfn = (dev->mdev->iseg_base +
		       offsetof(struct mlx5_init_seg, internal_timer_h)) >>
			PAGE_SHIFT;
		if (io_remap_pfn_range(vma, vma->vm_start, pfn,
				       PAGE_SIZE, vma->vm_page_prot))
			return -EAGAIN;
		break;
	case MLX5_IB_MMAP_CLOCK_INFO:
		return mlx5_ib_mmap_clock_info_page(dev, vma, context);

	case MLX5_IB_MMAP_DEVICE_MEM:
		return dm_mmap(ibcontext, vma);

	default:
		return -EINVAL;
	}

	return 0;
}

struct ib_dm *mlx5_ib_alloc_dm(struct ib_device *ibdev,
			       struct ib_ucontext *context,
			       struct ib_dm_alloc_attr *attr,
			       struct uverbs_attr_bundle *attrs)
{
	u64 act_size = roundup(attr->length, MLX5_MEMIC_BASE_SIZE);
	struct mlx5_memic *memic = &to_mdev(ibdev)->memic;
	phys_addr_t memic_addr;
	struct mlx5_ib_dm *dm;
	u64 start_offset;
	u32 page_idx;
	int err;

	dm = kzalloc(sizeof(*dm), GFP_KERNEL);
	if (!dm)
		return ERR_PTR(-ENOMEM);

	mlx5_ib_dbg(to_mdev(ibdev), "alloc_memic req: user_length=0x%llx act_length=0x%llx log_alignment=%d\n",
		    attr->length, act_size, attr->alignment);

	err = mlx5_cmd_alloc_memic(memic, &memic_addr,
				   act_size, attr->alignment);
	if (err)
		goto err_free;

	start_offset = memic_addr & ~PAGE_MASK;
	page_idx = (memic_addr - pci_resource_start(memic->dev->pdev, 0) -
		    MLX5_CAP64_DEV_MEM(memic->dev, memic_bar_start_addr)) >>
		    PAGE_SHIFT;

	err = uverbs_copy_to(attrs,
			     MLX5_IB_ATTR_ALLOC_DM_RESP_START_OFFSET,
			     &start_offset, sizeof(start_offset));
	if (err)
		goto err_dealloc;

	err = uverbs_copy_to(attrs,
			     MLX5_IB_ATTR_ALLOC_DM_RESP_PAGE_INDEX,
			     &page_idx, sizeof(page_idx));
	if (err)
		goto err_dealloc;

	bitmap_set(to_mucontext(context)->dm_pages, page_idx,
		   DIV_ROUND_UP(act_size, PAGE_SIZE));

	dm->dev_addr = memic_addr;

	return &dm->ibdm;

err_dealloc:
	mlx5_cmd_dealloc_memic(memic, memic_addr,
			       act_size);
err_free:
	kfree(dm);
	return ERR_PTR(err);
}

int mlx5_ib_dealloc_dm(struct ib_dm *ibdm)
{
	struct mlx5_memic *memic = &to_mdev(ibdm->device)->memic;
	struct mlx5_ib_dm *dm = to_mdm(ibdm);
	u64 act_size = roundup(dm->ibdm.length, MLX5_MEMIC_BASE_SIZE);
	u32 page_idx;
	int ret;

	ret = mlx5_cmd_dealloc_memic(memic, dm->dev_addr, act_size);
	if (ret)
		return ret;

	page_idx = (dm->dev_addr - pci_resource_start(memic->dev->pdev, 0) -
		    MLX5_CAP64_DEV_MEM(memic->dev, memic_bar_start_addr)) >>
		    PAGE_SHIFT;
	bitmap_clear(to_mucontext(ibdm->uobject->context)->dm_pages,
		     page_idx,
		     DIV_ROUND_UP(act_size, PAGE_SIZE));

	kfree(dm);

	return 0;
}

static struct ib_pd *mlx5_ib_alloc_pd(struct ib_device *ibdev,
				      struct ib_ucontext *context,
				      struct ib_udata *udata)
{
	struct mlx5_ib_alloc_pd_resp resp;
	struct mlx5_ib_pd *pd;
	int err;
	u32 out[MLX5_ST_SZ_DW(alloc_pd_out)] = {};
	u32 in[MLX5_ST_SZ_DW(alloc_pd_in)]   = {};
	u16 uid = 0;

	pd = kmalloc(sizeof(*pd), GFP_KERNEL);
	if (!pd)
		return ERR_PTR(-ENOMEM);

	uid = context ? to_mucontext(context)->devx_uid : 0;
	MLX5_SET(alloc_pd_in, in, opcode, MLX5_CMD_OP_ALLOC_PD);
	MLX5_SET(alloc_pd_in, in, uid, uid);
	err = mlx5_cmd_exec(to_mdev(ibdev)->mdev, in, sizeof(in),
			    out, sizeof(out));
	if (err) {
		kfree(pd);
		return ERR_PTR(err);
	}

	pd->pdn = MLX5_GET(alloc_pd_out, out, pd);
	pd->uid = uid;
	if (context) {
		resp.pdn = pd->pdn;
		if (ib_copy_to_udata(udata, &resp, sizeof(resp))) {
			mlx5_cmd_dealloc_pd(to_mdev(ibdev)->mdev, pd->pdn, uid);
			kfree(pd);
			return ERR_PTR(-EFAULT);
		}
	}

	return &pd->ibpd;
}

static int mlx5_ib_dealloc_pd(struct ib_pd *pd)
{
	struct mlx5_ib_dev *mdev = to_mdev(pd->device);
	struct mlx5_ib_pd *mpd = to_mpd(pd);

	mlx5_cmd_dealloc_pd(mdev->mdev, mpd->pdn, mpd->uid);
	kfree(mpd);

	return 0;
}

enum {
	MATCH_CRITERIA_ENABLE_OUTER_BIT,
	MATCH_CRITERIA_ENABLE_MISC_BIT,
	MATCH_CRITERIA_ENABLE_INNER_BIT,
	MATCH_CRITERIA_ENABLE_MISC2_BIT
};

#define HEADER_IS_ZERO(match_criteria, headers)			           \
	!(memchr_inv(MLX5_ADDR_OF(fte_match_param, match_criteria, headers), \
		    0, MLX5_FLD_SZ_BYTES(fte_match_param, headers)))       \

static u8 get_match_criteria_enable(u32 *match_criteria)
{
	u8 match_criteria_enable;

	match_criteria_enable =
		(!HEADER_IS_ZERO(match_criteria, outer_headers)) <<
		MATCH_CRITERIA_ENABLE_OUTER_BIT;
	match_criteria_enable |=
		(!HEADER_IS_ZERO(match_criteria, misc_parameters)) <<
		MATCH_CRITERIA_ENABLE_MISC_BIT;
	match_criteria_enable |=
		(!HEADER_IS_ZERO(match_criteria, inner_headers)) <<
		MATCH_CRITERIA_ENABLE_INNER_BIT;
	match_criteria_enable |=
		(!HEADER_IS_ZERO(match_criteria, misc_parameters_2)) <<
		MATCH_CRITERIA_ENABLE_MISC2_BIT;

	return match_criteria_enable;
}

static void set_proto(void *outer_c, void *outer_v, u8 mask, u8 val)
{
	MLX5_SET(fte_match_set_lyr_2_4, outer_c, ip_protocol, mask);
	MLX5_SET(fte_match_set_lyr_2_4, outer_v, ip_protocol, val);
}

static void set_flow_label(void *misc_c, void *misc_v, u32 mask, u32 val,
			   bool inner)
{
	if (inner) {
		MLX5_SET(fte_match_set_misc,
			 misc_c, inner_ipv6_flow_label, mask);
		MLX5_SET(fte_match_set_misc,
			 misc_v, inner_ipv6_flow_label, val);
	} else {
		MLX5_SET(fte_match_set_misc,
			 misc_c, outer_ipv6_flow_label, mask);
		MLX5_SET(fte_match_set_misc,
			 misc_v, outer_ipv6_flow_label, val);
	}
}

static void set_tos(void *outer_c, void *outer_v, u8 mask, u8 val)
{
	MLX5_SET(fte_match_set_lyr_2_4, outer_c, ip_ecn, mask);
	MLX5_SET(fte_match_set_lyr_2_4, outer_v, ip_ecn, val);
	MLX5_SET(fte_match_set_lyr_2_4, outer_c, ip_dscp, mask >> 2);
	MLX5_SET(fte_match_set_lyr_2_4, outer_v, ip_dscp, val >> 2);
}

static int check_mpls_supp_fields(u32 field_support, const __be32 *set_mask)
{
	if (MLX5_GET(fte_match_mpls, set_mask, mpls_label) &&
	    !(field_support & MLX5_FIELD_SUPPORT_MPLS_LABEL))
		return -EOPNOTSUPP;

	if (MLX5_GET(fte_match_mpls, set_mask, mpls_exp) &&
	    !(field_support & MLX5_FIELD_SUPPORT_MPLS_EXP))
		return -EOPNOTSUPP;

	if (MLX5_GET(fte_match_mpls, set_mask, mpls_s_bos) &&
	    !(field_support & MLX5_FIELD_SUPPORT_MPLS_S_BOS))
		return -EOPNOTSUPP;

	if (MLX5_GET(fte_match_mpls, set_mask, mpls_ttl) &&
	    !(field_support & MLX5_FIELD_SUPPORT_MPLS_TTL))
		return -EOPNOTSUPP;

	return 0;
}

#define LAST_ETH_FIELD vlan_tag
#define LAST_IB_FIELD sl
#define LAST_IPV4_FIELD tos
#define LAST_IPV6_FIELD traffic_class
#define LAST_TCP_UDP_FIELD src_port
#define LAST_TUNNEL_FIELD tunnel_id
#define LAST_FLOW_TAG_FIELD tag_id
#define LAST_DROP_FIELD size
#define LAST_COUNTERS_FIELD counters

/* Field is the last supported field */
#define FIELDS_NOT_SUPPORTED(filter, field)\
	memchr_inv((void *)&filter.field  +\
		   sizeof(filter.field), 0,\
		   sizeof(filter) -\
		   offsetof(typeof(filter), field) -\
		   sizeof(filter.field))

int parse_flow_flow_action(struct mlx5_ib_flow_action *maction,
			   bool is_egress,
			   struct mlx5_flow_act *action)
{

	switch (maction->ib_action.type) {
	case IB_FLOW_ACTION_ESP:
		if (action->action & (MLX5_FLOW_CONTEXT_ACTION_ENCRYPT |
				      MLX5_FLOW_CONTEXT_ACTION_DECRYPT))
			return -EINVAL;
		/* Currently only AES_GCM keymat is supported by the driver */
		action->esp_id = (uintptr_t)maction->esp_aes_gcm.ctx;
		action->action |= is_egress ?
			MLX5_FLOW_CONTEXT_ACTION_ENCRYPT :
			MLX5_FLOW_CONTEXT_ACTION_DECRYPT;
		return 0;
	case IB_FLOW_ACTION_UNSPECIFIED:
		if (maction->flow_action_raw.sub_type ==
		    MLX5_IB_FLOW_ACTION_MODIFY_HEADER) {
			if (action->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
				return -EINVAL;
			action->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
			action->modify_id = maction->flow_action_raw.action_id;
			return 0;
		}
		if (maction->flow_action_raw.sub_type ==
		    MLX5_IB_FLOW_ACTION_DECAP) {
			if (action->action & MLX5_FLOW_CONTEXT_ACTION_DECAP)
				return -EINVAL;
			action->action |= MLX5_FLOW_CONTEXT_ACTION_DECAP;
			return 0;
		}
		if (maction->flow_action_raw.sub_type ==
		    MLX5_IB_FLOW_ACTION_PACKET_REFORMAT) {
			if (action->action &
			    MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT)
				return -EINVAL;
			action->action |=
				MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT;
			action->reformat_id =
				maction->flow_action_raw.action_id;
			return 0;
		}
		/* fall through */
	default:
		return -EOPNOTSUPP;
	}
}

static int parse_flow_attr(struct mlx5_core_dev *mdev, u32 *match_c,
			   u32 *match_v, const union ib_flow_spec *ib_spec,
			   const struct ib_flow_attr *flow_attr,
			   struct mlx5_flow_act *action, u32 prev_type)
{
	void *misc_params_c = MLX5_ADDR_OF(fte_match_param, match_c,
					   misc_parameters);
	void *misc_params_v = MLX5_ADDR_OF(fte_match_param, match_v,
					   misc_parameters);
	void *misc_params2_c = MLX5_ADDR_OF(fte_match_param, match_c,
					    misc_parameters_2);
	void *misc_params2_v = MLX5_ADDR_OF(fte_match_param, match_v,
					    misc_parameters_2);
	void *headers_c;
	void *headers_v;
	int match_ipv;
	int ret;

	if (ib_spec->type & IB_FLOW_SPEC_INNER) {
		headers_c = MLX5_ADDR_OF(fte_match_param, match_c,
					 inner_headers);
		headers_v = MLX5_ADDR_OF(fte_match_param, match_v,
					 inner_headers);
		match_ipv = MLX5_CAP_FLOWTABLE_NIC_RX(mdev,
					ft_field_support.inner_ip_version);
	} else {
		headers_c = MLX5_ADDR_OF(fte_match_param, match_c,
					 outer_headers);
		headers_v = MLX5_ADDR_OF(fte_match_param, match_v,
					 outer_headers);
		match_ipv = MLX5_CAP_FLOWTABLE_NIC_RX(mdev,
					ft_field_support.outer_ip_version);
	}

	switch (ib_spec->type & ~IB_FLOW_SPEC_INNER) {
	case IB_FLOW_SPEC_ETH:
		if (FIELDS_NOT_SUPPORTED(ib_spec->eth.mask, LAST_ETH_FIELD))
			return -EOPNOTSUPP;

		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c,
					     dmac_47_16),
				ib_spec->eth.mask.dst_mac);
		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v,
					     dmac_47_16),
				ib_spec->eth.val.dst_mac);

		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c,
					     smac_47_16),
				ib_spec->eth.mask.src_mac);
		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v,
					     smac_47_16),
				ib_spec->eth.val.src_mac);

		if (ib_spec->eth.mask.vlan_tag) {
			MLX5_SET(fte_match_set_lyr_2_4, headers_c,
				 cvlan_tag, 1);
			MLX5_SET(fte_match_set_lyr_2_4, headers_v,
				 cvlan_tag, 1);

			MLX5_SET(fte_match_set_lyr_2_4, headers_c,
				 first_vid, ntohs(ib_spec->eth.mask.vlan_tag));
			MLX5_SET(fte_match_set_lyr_2_4, headers_v,
				 first_vid, ntohs(ib_spec->eth.val.vlan_tag));

			MLX5_SET(fte_match_set_lyr_2_4, headers_c,
				 first_cfi,
				 ntohs(ib_spec->eth.mask.vlan_tag) >> 12);
			MLX5_SET(fte_match_set_lyr_2_4, headers_v,
				 first_cfi,
				 ntohs(ib_spec->eth.val.vlan_tag) >> 12);

			MLX5_SET(fte_match_set_lyr_2_4, headers_c,
				 first_prio,
				 ntohs(ib_spec->eth.mask.vlan_tag) >> 13);
			MLX5_SET(fte_match_set_lyr_2_4, headers_v,
				 first_prio,
				 ntohs(ib_spec->eth.val.vlan_tag) >> 13);
		}
		MLX5_SET(fte_match_set_lyr_2_4, headers_c,
			 ethertype, ntohs(ib_spec->eth.mask.ether_type));
		MLX5_SET(fte_match_set_lyr_2_4, headers_v,
			 ethertype, ntohs(ib_spec->eth.val.ether_type));
		break;
	case IB_FLOW_SPEC_IPV4:
		if (FIELDS_NOT_SUPPORTED(ib_spec->ipv4.mask, LAST_IPV4_FIELD))
			return -EOPNOTSUPP;

		if (match_ipv) {
			MLX5_SET(fte_match_set_lyr_2_4, headers_c,
				 ip_version, 0xf);
			MLX5_SET(fte_match_set_lyr_2_4, headers_v,
				 ip_version, MLX5_FS_IPV4_VERSION);
		} else {
			MLX5_SET(fte_match_set_lyr_2_4, headers_c,
				 ethertype, 0xffff);
			MLX5_SET(fte_match_set_lyr_2_4, headers_v,
				 ethertype, ETH_P_IP);
		}

		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c,
				    src_ipv4_src_ipv6.ipv4_layout.ipv4),
		       &ib_spec->ipv4.mask.src_ip,
		       sizeof(ib_spec->ipv4.mask.src_ip));
		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v,
				    src_ipv4_src_ipv6.ipv4_layout.ipv4),
		       &ib_spec->ipv4.val.src_ip,
		       sizeof(ib_spec->ipv4.val.src_ip));
		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c,
				    dst_ipv4_dst_ipv6.ipv4_layout.ipv4),
		       &ib_spec->ipv4.mask.dst_ip,
		       sizeof(ib_spec->ipv4.mask.dst_ip));
		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v,
				    dst_ipv4_dst_ipv6.ipv4_layout.ipv4),
		       &ib_spec->ipv4.val.dst_ip,
		       sizeof(ib_spec->ipv4.val.dst_ip));

		set_tos(headers_c, headers_v,
			ib_spec->ipv4.mask.tos, ib_spec->ipv4.val.tos);

		set_proto(headers_c, headers_v,
			  ib_spec->ipv4.mask.proto, ib_spec->ipv4.val.proto);
		break;
	case IB_FLOW_SPEC_IPV6:
		if (FIELDS_NOT_SUPPORTED(ib_spec->ipv6.mask, LAST_IPV6_FIELD))
			return -EOPNOTSUPP;

		if (match_ipv) {
			MLX5_SET(fte_match_set_lyr_2_4, headers_c,
				 ip_version, 0xf);
			MLX5_SET(fte_match_set_lyr_2_4, headers_v,
				 ip_version, MLX5_FS_IPV6_VERSION);
		} else {
			MLX5_SET(fte_match_set_lyr_2_4, headers_c,
				 ethertype, 0xffff);
			MLX5_SET(fte_match_set_lyr_2_4, headers_v,
				 ethertype, ETH_P_IPV6);
		}

		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c,
				    src_ipv4_src_ipv6.ipv6_layout.ipv6),
		       &ib_spec->ipv6.mask.src_ip,
		       sizeof(ib_spec->ipv6.mask.src_ip));
		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v,
				    src_ipv4_src_ipv6.ipv6_layout.ipv6),
		       &ib_spec->ipv6.val.src_ip,
		       sizeof(ib_spec->ipv6.val.src_ip));
		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c,
				    dst_ipv4_dst_ipv6.ipv6_layout.ipv6),
		       &ib_spec->ipv6.mask.dst_ip,
		       sizeof(ib_spec->ipv6.mask.dst_ip));
		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v,
				    dst_ipv4_dst_ipv6.ipv6_layout.ipv6),
		       &ib_spec->ipv6.val.dst_ip,
		       sizeof(ib_spec->ipv6.val.dst_ip));

		set_tos(headers_c, headers_v,
			ib_spec->ipv6.mask.traffic_class,
			ib_spec->ipv6.val.traffic_class);

		set_proto(headers_c, headers_v,
			  ib_spec->ipv6.mask.next_hdr,
			  ib_spec->ipv6.val.next_hdr);

		set_flow_label(misc_params_c, misc_params_v,
			       ntohl(ib_spec->ipv6.mask.flow_label),
			       ntohl(ib_spec->ipv6.val.flow_label),
			       ib_spec->type & IB_FLOW_SPEC_INNER);
		break;
	case IB_FLOW_SPEC_ESP:
		if (ib_spec->esp.mask.seq)
			return -EOPNOTSUPP;

		MLX5_SET(fte_match_set_misc, misc_params_c, outer_esp_spi,
			 ntohl(ib_spec->esp.mask.spi));
		MLX5_SET(fte_match_set_misc, misc_params_v, outer_esp_spi,
			 ntohl(ib_spec->esp.val.spi));
		break;
	case IB_FLOW_SPEC_TCP:
		if (FIELDS_NOT_SUPPORTED(ib_spec->tcp_udp.mask,
					 LAST_TCP_UDP_FIELD))
			return -EOPNOTSUPP;

		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_protocol,
			 0xff);
		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_protocol,
			 IPPROTO_TCP);

		MLX5_SET(fte_match_set_lyr_2_4, headers_c, tcp_sport,
			 ntohs(ib_spec->tcp_udp.mask.src_port));
		MLX5_SET(fte_match_set_lyr_2_4, headers_v, tcp_sport,
			 ntohs(ib_spec->tcp_udp.val.src_port));

		MLX5_SET(fte_match_set_lyr_2_4, headers_c, tcp_dport,
			 ntohs(ib_spec->tcp_udp.mask.dst_port));
		MLX5_SET(fte_match_set_lyr_2_4, headers_v, tcp_dport,
			 ntohs(ib_spec->tcp_udp.val.dst_port));
		break;
	case IB_FLOW_SPEC_UDP:
		if (FIELDS_NOT_SUPPORTED(ib_spec->tcp_udp.mask,
					 LAST_TCP_UDP_FIELD))
			return -EOPNOTSUPP;

		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_protocol,
			 0xff);
		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_protocol,
			 IPPROTO_UDP);

		MLX5_SET(fte_match_set_lyr_2_4, headers_c, udp_sport,
			 ntohs(ib_spec->tcp_udp.mask.src_port));
		MLX5_SET(fte_match_set_lyr_2_4, headers_v, udp_sport,
			 ntohs(ib_spec->tcp_udp.val.src_port));

		MLX5_SET(fte_match_set_lyr_2_4, headers_c, udp_dport,
			 ntohs(ib_spec->tcp_udp.mask.dst_port));
		MLX5_SET(fte_match_set_lyr_2_4, headers_v, udp_dport,
			 ntohs(ib_spec->tcp_udp.val.dst_port));
		break;
	case IB_FLOW_SPEC_GRE:
		if (ib_spec->gre.mask.c_ks_res0_ver)
			return -EOPNOTSUPP;

		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_protocol,
			 0xff);
		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_protocol,
			 IPPROTO_GRE);

		MLX5_SET(fte_match_set_misc, misc_params_c, gre_protocol,
			 ntohs(ib_spec->gre.mask.protocol));
		MLX5_SET(fte_match_set_misc, misc_params_v, gre_protocol,
			 ntohs(ib_spec->gre.val.protocol));

		memcpy(MLX5_ADDR_OF(fte_match_set_misc, misc_params_c,
				    gre_key_h),
		       &ib_spec->gre.mask.key,
		       sizeof(ib_spec->gre.mask.key));
		memcpy(MLX5_ADDR_OF(fte_match_set_misc, misc_params_v,
				    gre_key_h),
		       &ib_spec->gre.val.key,
		       sizeof(ib_spec->gre.val.key));
		break;
	case IB_FLOW_SPEC_MPLS:
		switch (prev_type) {
		case IB_FLOW_SPEC_UDP:
			if (check_mpls_supp_fields(MLX5_CAP_FLOWTABLE_NIC_RX(mdev,
						   ft_field_support.outer_first_mpls_over_udp),
						   &ib_spec->mpls.mask.tag))
				return -EOPNOTSUPP;

			memcpy(MLX5_ADDR_OF(fte_match_set_misc2, misc_params2_v,
					    outer_first_mpls_over_udp),
			       &ib_spec->mpls.val.tag,
			       sizeof(ib_spec->mpls.val.tag));
			memcpy(MLX5_ADDR_OF(fte_match_set_misc2, misc_params2_c,
					    outer_first_mpls_over_udp),
			       &ib_spec->mpls.mask.tag,
			       sizeof(ib_spec->mpls.mask.tag));
			break;
		case IB_FLOW_SPEC_GRE:
			if (check_mpls_supp_fields(MLX5_CAP_FLOWTABLE_NIC_RX(mdev,
						   ft_field_support.outer_first_mpls_over_gre),
						   &ib_spec->mpls.mask.tag))
				return -EOPNOTSUPP;

			memcpy(MLX5_ADDR_OF(fte_match_set_misc2, misc_params2_v,
					    outer_first_mpls_over_gre),
			       &ib_spec->mpls.val.tag,
			       sizeof(ib_spec->mpls.val.tag));
			memcpy(MLX5_ADDR_OF(fte_match_set_misc2, misc_params2_c,
					    outer_first_mpls_over_gre),
			       &ib_spec->mpls.mask.tag,
			       sizeof(ib_spec->mpls.mask.tag));
			break;
		default:
			if (ib_spec->type & IB_FLOW_SPEC_INNER) {
				if (check_mpls_supp_fields(MLX5_CAP_FLOWTABLE_NIC_RX(mdev,
							   ft_field_support.inner_first_mpls),
							   &ib_spec->mpls.mask.tag))
					return -EOPNOTSUPP;

				memcpy(MLX5_ADDR_OF(fte_match_set_misc2, misc_params2_v,
						    inner_first_mpls),
				       &ib_spec->mpls.val.tag,
				       sizeof(ib_spec->mpls.val.tag));
				memcpy(MLX5_ADDR_OF(fte_match_set_misc2, misc_params2_c,
						    inner_first_mpls),
				       &ib_spec->mpls.mask.tag,
				       sizeof(ib_spec->mpls.mask.tag));
			} else {
				if (check_mpls_supp_fields(MLX5_CAP_FLOWTABLE_NIC_RX(mdev,
							   ft_field_support.outer_first_mpls),
							   &ib_spec->mpls.mask.tag))
					return -EOPNOTSUPP;

				memcpy(MLX5_ADDR_OF(fte_match_set_misc2, misc_params2_v,
						    outer_first_mpls),
				       &ib_spec->mpls.val.tag,
				       sizeof(ib_spec->mpls.val.tag));
				memcpy(MLX5_ADDR_OF(fte_match_set_misc2, misc_params2_c,
						    outer_first_mpls),
				       &ib_spec->mpls.mask.tag,
				       sizeof(ib_spec->mpls.mask.tag));
			}
		}
		break;
	case IB_FLOW_SPEC_VXLAN_TUNNEL:
		if (FIELDS_NOT_SUPPORTED(ib_spec->tunnel.mask,
					 LAST_TUNNEL_FIELD))
			return -EOPNOTSUPP;

		MLX5_SET(fte_match_set_misc, misc_params_c, vxlan_vni,
			 ntohl(ib_spec->tunnel.mask.tunnel_id));
		MLX5_SET(fte_match_set_misc, misc_params_v, vxlan_vni,
			 ntohl(ib_spec->tunnel.val.tunnel_id));
		break;
	case IB_FLOW_SPEC_ACTION_TAG:
		if (FIELDS_NOT_SUPPORTED(ib_spec->flow_tag,
					 LAST_FLOW_TAG_FIELD))
			return -EOPNOTSUPP;
		if (ib_spec->flow_tag.tag_id >= BIT(24))
			return -EINVAL;

		action->flow_tag = ib_spec->flow_tag.tag_id;
		action->flags |= FLOW_ACT_HAS_TAG;
		break;
	case IB_FLOW_SPEC_ACTION_DROP:
		if (FIELDS_NOT_SUPPORTED(ib_spec->drop,
					 LAST_DROP_FIELD))
			return -EOPNOTSUPP;
		action->action |= MLX5_FLOW_CONTEXT_ACTION_DROP;
		break;
	case IB_FLOW_SPEC_ACTION_HANDLE:
		ret = parse_flow_flow_action(to_mflow_act(ib_spec->action.act),
			flow_attr->flags & IB_FLOW_ATTR_FLAGS_EGRESS, action);
		if (ret)
			return ret;
		break;
	case IB_FLOW_SPEC_ACTION_COUNT:
		if (FIELDS_NOT_SUPPORTED(ib_spec->flow_count,
					 LAST_COUNTERS_FIELD))
			return -EOPNOTSUPP;

		/* for now support only one counters spec per flow */
		if (action->action & MLX5_FLOW_CONTEXT_ACTION_COUNT)
			return -EINVAL;

		action->counters = ib_spec->flow_count.counters;
		action->action |= MLX5_FLOW_CONTEXT_ACTION_COUNT;
		break;
	default:
		return -EINVAL;
	}

	return 0;
}

/* If a flow could catch both multicast and unicast packets,
 * it won't fall into the multicast flow steering table and this rule
 * could steal other multicast packets.
 */
static bool flow_is_multicast_only(const struct ib_flow_attr *ib_attr)
{
	union ib_flow_spec *flow_spec;

	if (ib_attr->type != IB_FLOW_ATTR_NORMAL ||
	    ib_attr->num_of_specs < 1)
		return false;

	flow_spec = (union ib_flow_spec *)(ib_attr + 1);
	if (flow_spec->type == IB_FLOW_SPEC_IPV4) {
		struct ib_flow_spec_ipv4 *ipv4_spec;

		ipv4_spec = (struct ib_flow_spec_ipv4 *)flow_spec;
		if (ipv4_is_multicast(ipv4_spec->val.dst_ip))
			return true;

		return false;
	}

	if (flow_spec->type == IB_FLOW_SPEC_ETH) {
		struct ib_flow_spec_eth *eth_spec;

		eth_spec = (struct ib_flow_spec_eth *)flow_spec;
		return is_multicast_ether_addr(eth_spec->mask.dst_mac) &&
		       is_multicast_ether_addr(eth_spec->val.dst_mac);
	}

	return false;
}

enum valid_spec {
	VALID_SPEC_INVALID,
	VALID_SPEC_VALID,
	VALID_SPEC_NA,
};

static enum valid_spec
is_valid_esp_aes_gcm(struct mlx5_core_dev *mdev,
		     const struct mlx5_flow_spec *spec,
		     const struct mlx5_flow_act *flow_act,
		     bool egress)
{
	const u32 *match_c = spec->match_criteria;
	bool is_crypto =
		(flow_act->action & (MLX5_FLOW_CONTEXT_ACTION_ENCRYPT |
				     MLX5_FLOW_CONTEXT_ACTION_DECRYPT));
	bool is_ipsec = mlx5_fs_is_ipsec_flow(match_c);
	bool is_drop = flow_act->action & MLX5_FLOW_CONTEXT_ACTION_DROP;

	/*
	 * Currently only crypto is supported in egress, when regular egress
	 * rules would be supported, always return VALID_SPEC_NA.
	 */
	if (!is_crypto)
		return VALID_SPEC_NA;

	return is_crypto && is_ipsec &&
		(!egress || (!is_drop && !(flow_act->flags & FLOW_ACT_HAS_TAG))) ?
		VALID_SPEC_VALID : VALID_SPEC_INVALID;
}

static bool is_valid_spec(struct mlx5_core_dev *mdev,
			  const struct mlx5_flow_spec *spec,
			  const struct mlx5_flow_act *flow_act,
			  bool egress)
{
	/* We curretly only support ipsec egress flow */
	return is_valid_esp_aes_gcm(mdev, spec, flow_act, egress) != VALID_SPEC_INVALID;
}

static bool is_valid_ethertype(struct mlx5_core_dev *mdev,
			       const struct ib_flow_attr *flow_attr,
			       bool check_inner)
{
	union ib_flow_spec *ib_spec = (union ib_flow_spec *)(flow_attr + 1);
	int match_ipv = check_inner ?
			MLX5_CAP_FLOWTABLE_NIC_RX(mdev,
					ft_field_support.inner_ip_version) :
			MLX5_CAP_FLOWTABLE_NIC_RX(mdev,
					ft_field_support.outer_ip_version);
	int inner_bit = check_inner ? IB_FLOW_SPEC_INNER : 0;
	bool ipv4_spec_valid, ipv6_spec_valid;
	unsigned int ip_spec_type = 0;
	bool has_ethertype = false;
	unsigned int spec_index;
	bool mask_valid = true;
	u16 eth_type = 0;
	bool type_valid;

	/* Validate that ethertype is correct */
	for (spec_index = 0; spec_index < flow_attr->num_of_specs; spec_index++) {
		if ((ib_spec->type == (IB_FLOW_SPEC_ETH | inner_bit)) &&
		    ib_spec->eth.mask.ether_type) {
			mask_valid = (ib_spec->eth.mask.ether_type ==
				      htons(0xffff));
			has_ethertype = true;
			eth_type = ntohs(ib_spec->eth.val.ether_type);
		} else if ((ib_spec->type == (IB_FLOW_SPEC_IPV4 | inner_bit)) ||
			   (ib_spec->type == (IB_FLOW_SPEC_IPV6 | inner_bit))) {
			ip_spec_type = ib_spec->type;
		}
		ib_spec = (void *)ib_spec + ib_spec->size;
	}

	type_valid = (!has_ethertype) || (!ip_spec_type);
	if (!type_valid && mask_valid) {
		ipv4_spec_valid = (eth_type == ETH_P_IP) &&
			(ip_spec_type == (IB_FLOW_SPEC_IPV4 | inner_bit));
		ipv6_spec_valid = (eth_type == ETH_P_IPV6) &&
			(ip_spec_type == (IB_FLOW_SPEC_IPV6 | inner_bit));

		type_valid = (ipv4_spec_valid) || (ipv6_spec_valid) ||
			     (((eth_type == ETH_P_MPLS_UC) ||
			       (eth_type == ETH_P_MPLS_MC)) && match_ipv);
	}

	return type_valid;
}

static bool is_valid_attr(struct mlx5_core_dev *mdev,
			  const struct ib_flow_attr *flow_attr)
{
	return is_valid_ethertype(mdev, flow_attr, false) &&
	       is_valid_ethertype(mdev, flow_attr, true);
}

static void put_flow_table(struct mlx5_ib_dev *dev,
			   struct mlx5_ib_flow_prio *prio, bool ft_added)
{
	prio->refcount -= !!ft_added;
	if (!prio->refcount) {
		mlx5_destroy_flow_table(prio->flow_table);
		prio->flow_table = NULL;
	}
}

static void counters_clear_description(struct ib_counters *counters)
{
	struct mlx5_ib_mcounters *mcounters = to_mcounters(counters);

	mutex_lock(&mcounters->mcntrs_mutex);
	kfree(mcounters->counters_data);
	mcounters->counters_data = NULL;
	mcounters->cntrs_max_index = 0;
	mutex_unlock(&mcounters->mcntrs_mutex);
}

static int mlx5_ib_destroy_flow(struct ib_flow *flow_id)
{
	struct mlx5_ib_flow_handler *handler = container_of(flow_id,
							  struct mlx5_ib_flow_handler,
							  ibflow);
	struct mlx5_ib_flow_handler *iter, *tmp;
	struct mlx5_ib_dev *dev = handler->dev;

	mutex_lock(&dev->flow_db->lock);

	list_for_each_entry_safe(iter, tmp, &handler->list, list) {
		mlx5_del_flow_rules(iter->rule);
		put_flow_table(dev, iter->prio, true);
		list_del(&iter->list);
		kfree(iter);
	}

	mlx5_del_flow_rules(handler->rule);
	put_flow_table(dev, handler->prio, true);
	if (handler->ibcounters &&
	    atomic_read(&handler->ibcounters->usecnt) == 1)
		counters_clear_description(handler->ibcounters);

	mutex_unlock(&dev->flow_db->lock);
	if (handler->flow_matcher)
		atomic_dec(&handler->flow_matcher->usecnt);
	kfree(handler);

	return 0;
}

static int ib_prio_to_core_prio(unsigned int priority, bool dont_trap)
{
	priority *= 2;
	if (!dont_trap)
		priority++;
	return priority;
}

enum flow_table_type {
	MLX5_IB_FT_RX,
	MLX5_IB_FT_TX
};

#define MLX5_FS_MAX_TYPES	 6
#define MLX5_FS_MAX_ENTRIES	 BIT(16)

static struct mlx5_ib_flow_prio *_get_prio(struct mlx5_flow_namespace *ns,
					   struct mlx5_ib_flow_prio *prio,
					   int priority,
					   int num_entries, int num_groups,
					   u32 flags)
{
	struct mlx5_flow_table *ft;

	ft = mlx5_create_auto_grouped_flow_table(ns, priority,
						 num_entries,
						 num_groups,
						 0, flags);
	if (IS_ERR(ft))
		return ERR_CAST(ft);

	prio->flow_table = ft;
	prio->refcount = 0;
	return prio;
}

static struct mlx5_ib_flow_prio *get_flow_table(struct mlx5_ib_dev *dev,
						struct ib_flow_attr *flow_attr,
						enum flow_table_type ft_type)
{
	bool dont_trap = flow_attr->flags & IB_FLOW_ATTR_FLAGS_DONT_TRAP;
	struct mlx5_flow_namespace *ns = NULL;
	struct mlx5_ib_flow_prio *prio;
	struct mlx5_flow_table *ft;
	int max_table_size;
	int num_entries;
	int num_groups;
	u32 flags = 0;
	int priority;

	max_table_size = BIT(MLX5_CAP_FLOWTABLE_NIC_RX(dev->mdev,
						       log_max_ft_size));
	if (flow_attr->type == IB_FLOW_ATTR_NORMAL) {
		enum mlx5_flow_namespace_type fn_type;

		if (flow_is_multicast_only(flow_attr) &&
		    !dont_trap)
			priority = MLX5_IB_FLOW_MCAST_PRIO;
		else
			priority = ib_prio_to_core_prio(flow_attr->priority,
							dont_trap);
		if (ft_type == MLX5_IB_FT_RX) {
			fn_type = MLX5_FLOW_NAMESPACE_BYPASS;
			prio = &dev->flow_db->prios[priority];
			if (!dev->rep &&
			    MLX5_CAP_FLOWTABLE_NIC_RX(dev->mdev, decap))
				flags |= MLX5_FLOW_TABLE_TUNNEL_EN_DECAP;
			if (!dev->rep &&
			    MLX5_CAP_FLOWTABLE_NIC_RX(dev->mdev,
					reformat_l3_tunnel_to_l2))
				flags |= MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT;
		} else {
			max_table_size =
				BIT(MLX5_CAP_FLOWTABLE_NIC_TX(dev->mdev,
							      log_max_ft_size));
			fn_type = MLX5_FLOW_NAMESPACE_EGRESS;
			prio = &dev->flow_db->egress_prios[priority];
			if (!dev->rep &&
			    MLX5_CAP_FLOWTABLE_NIC_TX(dev->mdev, reformat))
				flags |= MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT;
		}
		ns = mlx5_get_flow_namespace(dev->mdev, fn_type);
		num_entries = MLX5_FS_MAX_ENTRIES;
		num_groups = MLX5_FS_MAX_TYPES;
	} else if (flow_attr->type == IB_FLOW_ATTR_ALL_DEFAULT ||
		   flow_attr->type == IB_FLOW_ATTR_MC_DEFAULT) {
		ns = mlx5_get_flow_namespace(dev->mdev,
					     MLX5_FLOW_NAMESPACE_LEFTOVERS);
		build_leftovers_ft_param(&priority,
					 &num_entries,
					 &num_groups);
		prio = &dev->flow_db->prios[MLX5_IB_FLOW_LEFTOVERS_PRIO];
	} else if (flow_attr->type == IB_FLOW_ATTR_SNIFFER) {
		if (!MLX5_CAP_FLOWTABLE(dev->mdev,
					allow_sniffer_and_nic_rx_shared_tir))
			return ERR_PTR(-ENOTSUPP);

		ns = mlx5_get_flow_namespace(dev->mdev, ft_type == MLX5_IB_FT_RX ?
					     MLX5_FLOW_NAMESPACE_SNIFFER_RX :
					     MLX5_FLOW_NAMESPACE_SNIFFER_TX);

		prio = &dev->flow_db->sniffer[ft_type];
		priority = 0;
		num_entries = 1;
		num_groups = 1;
	}

	if (!ns)
		return ERR_PTR(-ENOTSUPP);

	if (num_entries > max_table_size)
		return ERR_PTR(-ENOMEM);

	ft = prio->flow_table;
	if (!ft)
		return _get_prio(ns, prio, priority, num_entries, num_groups,
				 flags);

	return prio;
}

static void set_underlay_qp(struct mlx5_ib_dev *dev,
			    struct mlx5_flow_spec *spec,
			    u32 underlay_qpn)
{
	void *misc_params_c = MLX5_ADDR_OF(fte_match_param,
					   spec->match_criteria,
					   misc_parameters);
	void *misc_params_v = MLX5_ADDR_OF(fte_match_param, spec->match_value,
					   misc_parameters);

	if (underlay_qpn &&
	    MLX5_CAP_FLOWTABLE_NIC_RX(dev->mdev,
				      ft_field_support.bth_dst_qp)) {
		MLX5_SET(fte_match_set_misc,
			 misc_params_v, bth_dst_qp, underlay_qpn);
		MLX5_SET(fte_match_set_misc,
			 misc_params_c, bth_dst_qp, 0xffffff);
	}
}

static int read_flow_counters(struct ib_device *ibdev,
			      struct mlx5_read_counters_attr *read_attr)
{
	struct mlx5_fc *fc = read_attr->hw_cntrs_hndl;
	struct mlx5_ib_dev *dev = to_mdev(ibdev);

	return mlx5_fc_query(dev->mdev, fc,
			     &read_attr->out[IB_COUNTER_PACKETS],
			     &read_attr->out[IB_COUNTER_BYTES]);
}

/* flow counters currently expose two counters packets and bytes */
#define FLOW_COUNTERS_NUM 2
static int counters_set_description(struct ib_counters *counters,
				    enum mlx5_ib_counters_type counters_type,
				    struct mlx5_ib_flow_counters_desc *desc_data,
				    u32 ncounters)
{
	struct mlx5_ib_mcounters *mcounters = to_mcounters(counters);
	u32 cntrs_max_index = 0;
	int i;

	if (counters_type != MLX5_IB_COUNTERS_FLOW)
		return -EINVAL;

	/* init the fields for the object */
	mcounters->type = counters_type;
	mcounters->read_counters = read_flow_counters;
	mcounters->counters_num = FLOW_COUNTERS_NUM;
	mcounters->ncounters = ncounters;
	/* each counter entry have both description and index pair */
	for (i = 0; i < ncounters; i++) {
		if (desc_data[i].description > IB_COUNTER_BYTES)
			return -EINVAL;

		if (cntrs_max_index <= desc_data[i].index)
			cntrs_max_index = desc_data[i].index + 1;
	}

	mutex_lock(&mcounters->mcntrs_mutex);
	mcounters->counters_data = desc_data;
	mcounters->cntrs_max_index = cntrs_max_index;
	mutex_unlock(&mcounters->mcntrs_mutex);

	return 0;
}

#define MAX_COUNTERS_NUM (USHRT_MAX / (sizeof(u32) * 2))
static int flow_counters_set_data(struct ib_counters *ibcounters,
				  struct mlx5_ib_create_flow *ucmd)
{
	struct mlx5_ib_mcounters *mcounters = to_mcounters(ibcounters);
	struct mlx5_ib_flow_counters_data *cntrs_data = NULL;
	struct mlx5_ib_flow_counters_desc *desc_data = NULL;
	bool hw_hndl = false;
	int ret = 0;

	if (ucmd && ucmd->ncounters_data != 0) {
		cntrs_data = ucmd->data;
		if (cntrs_data->ncounters > MAX_COUNTERS_NUM)
			return -EINVAL;

		desc_data = kcalloc(cntrs_data->ncounters,
				    sizeof(*desc_data),
				    GFP_KERNEL);
		if (!desc_data)
			return  -ENOMEM;

		if (copy_from_user(desc_data,
				   u64_to_user_ptr(cntrs_data->counters_data),
				   sizeof(*desc_data) * cntrs_data->ncounters)) {
			ret = -EFAULT;
			goto free;
		}
	}

	if (!mcounters->hw_cntrs_hndl) {
		mcounters->hw_cntrs_hndl = mlx5_fc_create(
			to_mdev(ibcounters->device)->mdev, false);
		if (IS_ERR(mcounters->hw_cntrs_hndl)) {
			ret = PTR_ERR(mcounters->hw_cntrs_hndl);
			goto free;
		}
		hw_hndl = true;
	}

	if (desc_data) {
		/* counters already bound to at least one flow */
		if (mcounters->cntrs_max_index) {
			ret = -EINVAL;
			goto free_hndl;
		}

		ret = counters_set_description(ibcounters,
					       MLX5_IB_COUNTERS_FLOW,
					       desc_data,
					       cntrs_data->ncounters);
		if (ret)
			goto free_hndl;

	} else if (!mcounters->cntrs_max_index) {
		/* counters not bound yet, must have udata passed */
		ret = -EINVAL;
		goto free_hndl;
	}

	return 0;

free_hndl:
	if (hw_hndl) {
		mlx5_fc_destroy(to_mdev(ibcounters->device)->mdev,
				mcounters->hw_cntrs_hndl);
		mcounters->hw_cntrs_hndl = NULL;
	}
free:
	kfree(desc_data);
	return ret;
}

static struct mlx5_ib_flow_handler *_create_flow_rule(struct mlx5_ib_dev *dev,
						      struct mlx5_ib_flow_prio *ft_prio,
						      const struct ib_flow_attr *flow_attr,
						      struct mlx5_flow_destination *dst,
						      u32 underlay_qpn,
						      struct mlx5_ib_create_flow *ucmd)
{
	struct mlx5_flow_table	*ft = ft_prio->flow_table;
	struct mlx5_ib_flow_handler *handler;
	struct mlx5_flow_act flow_act = {.flow_tag = MLX5_FS_DEFAULT_FLOW_TAG};
	struct mlx5_flow_spec *spec;
	struct mlx5_flow_destination dest_arr[2] = {};
	struct mlx5_flow_destination *rule_dst = dest_arr;
	const void *ib_flow = (const void *)flow_attr + sizeof(*flow_attr);
	unsigned int spec_index;
	u32 prev_type = 0;
	int err = 0;
	int dest_num = 0;
	bool is_egress = flow_attr->flags & IB_FLOW_ATTR_FLAGS_EGRESS;

	if (!is_valid_attr(dev->mdev, flow_attr))
		return ERR_PTR(-EINVAL);

	if (dev->rep && is_egress)
		return ERR_PTR(-EINVAL);

	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
	handler = kzalloc(sizeof(*handler), GFP_KERNEL);
	if (!handler || !spec) {
		err = -ENOMEM;
		goto free;
	}

	INIT_LIST_HEAD(&handler->list);
	if (dst) {
		memcpy(&dest_arr[0], dst, sizeof(*dst));
		dest_num++;
	}

	for (spec_index = 0; spec_index < flow_attr->num_of_specs; spec_index++) {
		err = parse_flow_attr(dev->mdev, spec->match_criteria,
				      spec->match_value,
				      ib_flow, flow_attr, &flow_act,
				      prev_type);
		if (err < 0)
			goto free;

		prev_type = ((union ib_flow_spec *)ib_flow)->type;
		ib_flow += ((union ib_flow_spec *)ib_flow)->size;
	}

	if (!flow_is_multicast_only(flow_attr))
		set_underlay_qp(dev, spec, underlay_qpn);

	if (dev->rep) {
		void *misc;

		misc = MLX5_ADDR_OF(fte_match_param, spec->match_value,
				    misc_parameters);
		MLX5_SET(fte_match_set_misc, misc, source_port,
			 dev->rep->vport);
		misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
				    misc_parameters);
		MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
	}

	spec->match_criteria_enable = get_match_criteria_enable(spec->match_criteria);

	if (is_egress &&
	    !is_valid_spec(dev->mdev, spec, &flow_act, is_egress)) {
		err = -EINVAL;
		goto free;
	}

	if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_COUNT) {
		struct mlx5_ib_mcounters *mcounters;

		err = flow_counters_set_data(flow_act.counters, ucmd);
		if (err)
			goto free;

		mcounters = to_mcounters(flow_act.counters);
		handler->ibcounters = flow_act.counters;
		dest_arr[dest_num].type =
			MLX5_FLOW_DESTINATION_TYPE_COUNTER;
		dest_arr[dest_num].counter_id =
			mlx5_fc_id(mcounters->hw_cntrs_hndl);
		dest_num++;
	}

	if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_DROP) {
		if (!(flow_act.action & MLX5_FLOW_CONTEXT_ACTION_COUNT)) {
			rule_dst = NULL;
			dest_num = 0;
		}
	} else {
		if (is_egress)
			flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_ALLOW;
		else
			flow_act.action |=
				dest_num ?  MLX5_FLOW_CONTEXT_ACTION_FWD_DEST :
					MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO;
	}

	if ((flow_act.flags & FLOW_ACT_HAS_TAG)  &&
	    (flow_attr->type == IB_FLOW_ATTR_ALL_DEFAULT ||
	     flow_attr->type == IB_FLOW_ATTR_MC_DEFAULT)) {
		mlx5_ib_warn(dev, "Flow tag %u and attribute type %x isn't allowed in leftovers\n",
			     flow_act.flow_tag, flow_attr->type);
		err = -EINVAL;
		goto free;
	}
	handler->rule = mlx5_add_flow_rules(ft, spec,
					    &flow_act,
					    rule_dst, dest_num);

	if (IS_ERR(handler->rule)) {
		err = PTR_ERR(handler->rule);
		goto free;
	}

	ft_prio->refcount++;
	handler->prio = ft_prio;
	handler->dev = dev;

	ft_prio->flow_table = ft;
free:
	if (err && handler) {
		if (handler->ibcounters &&
		    atomic_read(&handler->ibcounters->usecnt) == 1)
			counters_clear_description(handler->ibcounters);
		kfree(handler);
	}
	kvfree(spec);
	return err ? ERR_PTR(err) : handler;
}

static struct mlx5_ib_flow_handler *create_flow_rule(struct mlx5_ib_dev *dev,
						     struct mlx5_ib_flow_prio *ft_prio,
						     const struct ib_flow_attr *flow_attr,
						     struct mlx5_flow_destination *dst)
{
	return _create_flow_rule(dev, ft_prio, flow_attr, dst, 0, NULL);
}

static struct mlx5_ib_flow_handler *create_dont_trap_rule(struct mlx5_ib_dev *dev,
							  struct mlx5_ib_flow_prio *ft_prio,
							  struct ib_flow_attr *flow_attr,
							  struct mlx5_flow_destination *dst)
{
	struct mlx5_ib_flow_handler *handler_dst = NULL;
	struct mlx5_ib_flow_handler *handler = NULL;

	handler = create_flow_rule(dev, ft_prio, flow_attr, NULL);
	if (!IS_ERR(handler)) {
		handler_dst = create_flow_rule(dev, ft_prio,
					       flow_attr, dst);
		if (IS_ERR(handler_dst)) {
			mlx5_del_flow_rules(handler->rule);
			ft_prio->refcount--;
			kfree(handler);
			handler = handler_dst;
		} else {
			list_add(&handler_dst->list, &handler->list);
		}
	}

	return handler;
}
enum {
	LEFTOVERS_MC,
	LEFTOVERS_UC,
};

static struct mlx5_ib_flow_handler *create_leftovers_rule(struct mlx5_ib_dev *dev,
							  struct mlx5_ib_flow_prio *ft_prio,
							  struct ib_flow_attr *flow_attr,
							  struct mlx5_flow_destination *dst)
{
	struct mlx5_ib_flow_handler *handler_ucast = NULL;
	struct mlx5_ib_flow_handler *handler = NULL;

	static struct {
		struct ib_flow_attr	flow_attr;
		struct ib_flow_spec_eth eth_flow;
	} leftovers_specs[] = {
		[LEFTOVERS_MC] = {
			.flow_attr = {
				.num_of_specs = 1,
				.size = sizeof(leftovers_specs[0])
			},
			.eth_flow = {
				.type = IB_FLOW_SPEC_ETH,
				.size = sizeof(struct ib_flow_spec_eth),
				.mask = {.dst_mac = {0x1} },
				.val =  {.dst_mac = {0x1} }
			}
		},
		[LEFTOVERS_UC] = {
			.flow_attr = {
				.num_of_specs = 1,
				.size = sizeof(leftovers_specs[0])
			},
			.eth_flow = {
				.type = IB_FLOW_SPEC_ETH,
				.size = sizeof(struct ib_flow_spec_eth),
				.mask = {.dst_mac = {0x1} },
				.val = {.dst_mac = {} }
			}
		}
	};

	handler = create_flow_rule(dev, ft_prio,
				   &leftovers_specs[LEFTOVERS_MC].flow_attr,
				   dst);
	if (!IS_ERR(handler) &&
	    flow_attr->type == IB_FLOW_ATTR_ALL_DEFAULT) {
		handler_ucast = create_flow_rule(dev, ft_prio,
						 &leftovers_specs[LEFTOVERS_UC].flow_attr,
						 dst);
		if (IS_ERR(handler_ucast)) {
			mlx5_del_flow_rules(handler->rule);
			ft_prio->refcount--;
			kfree(handler);
			handler = handler_ucast;
		} else {
			list_add(&handler_ucast->list, &handler->list);
		}
	}

	return handler;
}

static struct mlx5_ib_flow_handler *create_sniffer_rule(struct mlx5_ib_dev *dev,
							struct mlx5_ib_flow_prio *ft_rx,
							struct mlx5_ib_flow_prio *ft_tx,
							struct mlx5_flow_destination *dst)
{
	struct mlx5_ib_flow_handler *handler_rx;
	struct mlx5_ib_flow_handler *handler_tx;
	int err;
	static const struct ib_flow_attr flow_attr  = {
		.num_of_specs = 0,
		.size = sizeof(flow_attr)
	};

	handler_rx = create_flow_rule(dev, ft_rx, &flow_attr, dst);
	if (IS_ERR(handler_rx)) {
		err = PTR_ERR(handler_rx);
		goto err;
	}

	handler_tx = create_flow_rule(dev, ft_tx, &flow_attr, dst);
	if (IS_ERR(handler_tx)) {
		err = PTR_ERR(handler_tx);
		goto err_tx;
	}

	list_add(&handler_tx->list, &handler_rx->list);

	return handler_rx;

err_tx:
	mlx5_del_flow_rules(handler_rx->rule);
	ft_rx->refcount--;
	kfree(handler_rx);
err:
	return ERR_PTR(err);
}

static struct ib_flow *mlx5_ib_create_flow(struct ib_qp *qp,
					   struct ib_flow_attr *flow_attr,
					   int domain,
					   struct ib_udata *udata)
{
	struct mlx5_ib_dev *dev = to_mdev(qp->device);
	struct mlx5_ib_qp *mqp = to_mqp(qp);
	struct mlx5_ib_flow_handler *handler = NULL;
	struct mlx5_flow_destination *dst = NULL;
	struct mlx5_ib_flow_prio *ft_prio_tx = NULL;
	struct mlx5_ib_flow_prio *ft_prio;
	bool is_egress = flow_attr->flags & IB_FLOW_ATTR_FLAGS_EGRESS;
	struct mlx5_ib_create_flow *ucmd = NULL, ucmd_hdr;
	size_t min_ucmd_sz, required_ucmd_sz;
	int err;
	int underlay_qpn;

	if (udata && udata->inlen) {
		min_ucmd_sz = offsetof(typeof(ucmd_hdr), reserved) +
				sizeof(ucmd_hdr.reserved);
		if (udata->inlen < min_ucmd_sz)
			return ERR_PTR(-EOPNOTSUPP);

		err = ib_copy_from_udata(&ucmd_hdr, udata, min_ucmd_sz);
		if (err)
			return ERR_PTR(err);

		/* currently supports only one counters data */
		if (ucmd_hdr.ncounters_data > 1)
			return ERR_PTR(-EINVAL);

		required_ucmd_sz = min_ucmd_sz +
			sizeof(struct mlx5_ib_flow_counters_data) *
			ucmd_hdr.ncounters_data;
		if (udata->inlen > required_ucmd_sz &&
		    !ib_is_udata_cleared(udata, required_ucmd_sz,
					 udata->inlen - required_ucmd_sz))
			return ERR_PTR(-EOPNOTSUPP);

		ucmd = kzalloc(required_ucmd_sz, GFP_KERNEL);
		if (!ucmd)
			return ERR_PTR(-ENOMEM);

		err = ib_copy_from_udata(ucmd, udata, required_ucmd_sz);
		if (err)
			goto free_ucmd;
	}

	if (flow_attr->priority > MLX5_IB_FLOW_LAST_PRIO) {
		err = -ENOMEM;
		goto free_ucmd;
	}

	if (domain != IB_FLOW_DOMAIN_USER ||
	    flow_attr->port > dev->num_ports ||
	    (flow_attr->flags & ~(IB_FLOW_ATTR_FLAGS_DONT_TRAP |
				  IB_FLOW_ATTR_FLAGS_EGRESS))) {
		err = -EINVAL;
		goto free_ucmd;
	}

	if (is_egress &&
	    (flow_attr->type == IB_FLOW_ATTR_ALL_DEFAULT ||
	     flow_attr->type == IB_FLOW_ATTR_MC_DEFAULT)) {
		err = -EINVAL;
		goto free_ucmd;
	}

	dst = kzalloc(sizeof(*dst), GFP_KERNEL);
	if (!dst) {
		err = -ENOMEM;
		goto free_ucmd;
	}

	mutex_lock(&dev->flow_db->lock);

	ft_prio = get_flow_table(dev, flow_attr,
				 is_egress ? MLX5_IB_FT_TX : MLX5_IB_FT_RX);
	if (IS_ERR(ft_prio)) {
		err = PTR_ERR(ft_prio);
		goto unlock;
	}
	if (flow_attr->type == IB_FLOW_ATTR_SNIFFER) {
		ft_prio_tx = get_flow_table(dev, flow_attr, MLX5_IB_FT_TX);
		if (IS_ERR(ft_prio_tx)) {
			err = PTR_ERR(ft_prio_tx);
			ft_prio_tx = NULL;
			goto destroy_ft;
		}
	}

	if (is_egress) {
		dst->type = MLX5_FLOW_DESTINATION_TYPE_PORT;
	} else {
		dst->type = MLX5_FLOW_DESTINATION_TYPE_TIR;
		if (mqp->flags & MLX5_IB_QP_RSS)
			dst->tir_num = mqp->rss_qp.tirn;
		else
			dst->tir_num = mqp->raw_packet_qp.rq.tirn;
	}

	if (flow_attr->type == IB_FLOW_ATTR_NORMAL) {
		if (flow_attr->flags & IB_FLOW_ATTR_FLAGS_DONT_TRAP)  {
			handler = create_dont_trap_rule(dev, ft_prio,
							flow_attr, dst);
		} else {
			underlay_qpn = (mqp->flags & MLX5_IB_QP_UNDERLAY) ?
					mqp->underlay_qpn : 0;
			handler = _create_flow_rule(dev, ft_prio, flow_attr,
						    dst, underlay_qpn, ucmd);
		}
	} else if (flow_attr->type == IB_FLOW_ATTR_ALL_DEFAULT ||
		   flow_attr->type == IB_FLOW_ATTR_MC_DEFAULT) {
		handler = create_leftovers_rule(dev, ft_prio, flow_attr,
						dst);
	} else if (flow_attr->type == IB_FLOW_ATTR_SNIFFER) {
		handler = create_sniffer_rule(dev, ft_prio, ft_prio_tx, dst);
	} else {
		err = -EINVAL;
		goto destroy_ft;
	}

	if (IS_ERR(handler)) {
		err = PTR_ERR(handler);
		handler = NULL;
		goto destroy_ft;
	}

	mutex_unlock(&dev->flow_db->lock);
	kfree(dst);
	kfree(ucmd);

	return &handler->ibflow;

destroy_ft:
	put_flow_table(dev, ft_prio, false);
	if (ft_prio_tx)
		put_flow_table(dev, ft_prio_tx, false);
unlock:
	mutex_unlock(&dev->flow_db->lock);
	kfree(dst);
free_ucmd:
	kfree(ucmd);
	return ERR_PTR(err);
}

static struct mlx5_ib_flow_prio *
_get_flow_table(struct mlx5_ib_dev *dev,
		struct mlx5_ib_flow_matcher *fs_matcher,
		bool mcast)
{
	struct mlx5_flow_namespace *ns = NULL;
	struct mlx5_ib_flow_prio *prio;
	int max_table_size;
	u32 flags = 0;
	int priority;

	if (fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_BYPASS) {
		max_table_size = BIT(MLX5_CAP_FLOWTABLE_NIC_RX(dev->mdev,
					log_max_ft_size));
		if (MLX5_CAP_FLOWTABLE_NIC_RX(dev->mdev, decap))
			flags |= MLX5_FLOW_TABLE_TUNNEL_EN_DECAP;
		if (MLX5_CAP_FLOWTABLE_NIC_RX(dev->mdev,
					      reformat_l3_tunnel_to_l2))
			flags |= MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT;
	} else { /* Can only be MLX5_FLOW_NAMESPACE_EGRESS */
		max_table_size = BIT(MLX5_CAP_FLOWTABLE_NIC_TX(dev->mdev,
					log_max_ft_size));
		if (MLX5_CAP_FLOWTABLE_NIC_TX(dev->mdev, reformat))
			flags |= MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT;
	}

	if (max_table_size < MLX5_FS_MAX_ENTRIES)
		return ERR_PTR(-ENOMEM);

	if (mcast)
		priority = MLX5_IB_FLOW_MCAST_PRIO;
	else
		priority = ib_prio_to_core_prio(fs_matcher->priority, false);

	ns = mlx5_get_flow_namespace(dev->mdev, fs_matcher->ns_type);
	if (!ns)
		return ERR_PTR(-ENOTSUPP);

	if (fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_BYPASS)
		prio = &dev->flow_db->prios[priority];
	else
		prio = &dev->flow_db->egress_prios[priority];

	if (prio->flow_table)
		return prio;

	return _get_prio(ns, prio, priority, MLX5_FS_MAX_ENTRIES,
			 MLX5_FS_MAX_TYPES, flags);
}

static struct mlx5_ib_flow_handler *
_create_raw_flow_rule(struct mlx5_ib_dev *dev,
		      struct mlx5_ib_flow_prio *ft_prio,
		      struct mlx5_flow_destination *dst,
		      struct mlx5_ib_flow_matcher  *fs_matcher,
		      struct mlx5_flow_act *flow_act,
		      void *cmd_in, int inlen)
{
	struct mlx5_ib_flow_handler *handler;
	struct mlx5_flow_spec *spec;
	struct mlx5_flow_table *ft = ft_prio->flow_table;
	int err = 0;

	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
	handler = kzalloc(sizeof(*handler), GFP_KERNEL);
	if (!handler || !spec) {
		err = -ENOMEM;
		goto free;
	}

	INIT_LIST_HEAD(&handler->list);

	memcpy(spec->match_value, cmd_in, inlen);
	memcpy(spec->match_criteria, fs_matcher->matcher_mask.match_params,
	       fs_matcher->mask_len);
	spec->match_criteria_enable = fs_matcher->match_criteria_enable;

	handler->rule = mlx5_add_flow_rules(ft, spec,
					    flow_act, dst, 1);

	if (IS_ERR(handler->rule)) {
		err = PTR_ERR(handler->rule);
		goto free;
	}

	ft_prio->refcount++;
	handler->prio = ft_prio;
	handler->dev = dev;
	ft_prio->flow_table = ft;

free:
	if (err)
		kfree(handler);
	kvfree(spec);
	return err ? ERR_PTR(err) : handler;
}

static bool raw_fs_is_multicast(struct mlx5_ib_flow_matcher *fs_matcher,
				void *match_v)
{
	void *match_c;
	void *match_v_set_lyr_2_4, *match_c_set_lyr_2_4;
	void *dmac, *dmac_mask;
	void *ipv4, *ipv4_mask;

	if (!(fs_matcher->match_criteria_enable &
	      (1 << MATCH_CRITERIA_ENABLE_OUTER_BIT)))
		return false;

	match_c = fs_matcher->matcher_mask.match_params;
	match_v_set_lyr_2_4 = MLX5_ADDR_OF(fte_match_param, match_v,
					   outer_headers);
	match_c_set_lyr_2_4 = MLX5_ADDR_OF(fte_match_param, match_c,
					   outer_headers);

	dmac = MLX5_ADDR_OF(fte_match_set_lyr_2_4, match_v_set_lyr_2_4,
			    dmac_47_16);
	dmac_mask = MLX5_ADDR_OF(fte_match_set_lyr_2_4, match_c_set_lyr_2_4,
				 dmac_47_16);

	if (is_multicast_ether_addr(dmac) &&
	    is_multicast_ether_addr(dmac_mask))
		return true;

	ipv4 = MLX5_ADDR_OF(fte_match_set_lyr_2_4, match_v_set_lyr_2_4,
			    dst_ipv4_dst_ipv6.ipv4_layout.ipv4);

	ipv4_mask = MLX5_ADDR_OF(fte_match_set_lyr_2_4, match_c_set_lyr_2_4,
				 dst_ipv4_dst_ipv6.ipv4_layout.ipv4);

	if (ipv4_is_multicast(*(__be32 *)(ipv4)) &&
	    ipv4_is_multicast(*(__be32 *)(ipv4_mask)))
		return true;

	return false;
}

struct mlx5_ib_flow_handler *
mlx5_ib_raw_fs_rule_add(struct mlx5_ib_dev *dev,
			struct mlx5_ib_flow_matcher *fs_matcher,
			struct mlx5_flow_act *flow_act,
			void *cmd_in, int inlen, int dest_id,
			int dest_type)
{
	struct mlx5_flow_destination *dst;
	struct mlx5_ib_flow_prio *ft_prio;
	struct mlx5_ib_flow_handler *handler;
	bool mcast;
	int err;

	if (fs_matcher->flow_type != MLX5_IB_FLOW_TYPE_NORMAL)
		return ERR_PTR(-EOPNOTSUPP);

	if (fs_matcher->priority > MLX5_IB_FLOW_LAST_PRIO)
		return ERR_PTR(-ENOMEM);

	dst = kzalloc(sizeof(*dst), GFP_KERNEL);
	if (!dst)
		return ERR_PTR(-ENOMEM);

	mcast = raw_fs_is_multicast(fs_matcher, cmd_in);
	mutex_lock(&dev->flow_db->lock);

	ft_prio = _get_flow_table(dev, fs_matcher, mcast);
	if (IS_ERR(ft_prio)) {
		err = PTR_ERR(ft_prio);
		goto unlock;
	}

	if (dest_type == MLX5_FLOW_DESTINATION_TYPE_TIR) {
		dst->type = dest_type;
		dst->tir_num = dest_id;
		flow_act->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
	} else if (dest_type == MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE) {
		dst->type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE_NUM;
		dst->ft_num = dest_id;
		flow_act->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
	} else {
		dst->type = MLX5_FLOW_DESTINATION_TYPE_PORT;
		flow_act->action |= MLX5_FLOW_CONTEXT_ACTION_ALLOW;
	}

	handler = _create_raw_flow_rule(dev, ft_prio, dst, fs_matcher, flow_act,
					cmd_in, inlen);

	if (IS_ERR(handler)) {
		err = PTR_ERR(handler);
		goto destroy_ft;
	}

	mutex_unlock(&dev->flow_db->lock);
	atomic_inc(&fs_matcher->usecnt);
	handler->flow_matcher = fs_matcher;

	kfree(dst);

	return handler;

destroy_ft:
	put_flow_table(dev, ft_prio, false);
unlock:
	mutex_unlock(&dev->flow_db->lock);
	kfree(dst);

	return ERR_PTR(err);
}

static u32 mlx5_ib_flow_action_flags_to_accel_xfrm_flags(u32 mlx5_flags)
{
	u32 flags = 0;

	if (mlx5_flags & MLX5_IB_UAPI_FLOW_ACTION_FLAGS_REQUIRE_METADATA)
		flags |= MLX5_ACCEL_XFRM_FLAG_REQUIRE_METADATA;

	return flags;
}

#define MLX5_FLOW_ACTION_ESP_CREATE_LAST_SUPPORTED	MLX5_IB_UAPI_FLOW_ACTION_FLAGS_REQUIRE_METADATA
static struct ib_flow_action *
mlx5_ib_create_flow_action_esp(struct ib_device *device,
			       const struct ib_flow_action_attrs_esp *attr,
			       struct uverbs_attr_bundle *attrs)
{
	struct mlx5_ib_dev *mdev = to_mdev(device);
	struct ib_uverbs_flow_action_esp_keymat_aes_gcm *aes_gcm;
	struct mlx5_accel_esp_xfrm_attrs accel_attrs = {};
	struct mlx5_ib_flow_action *action;
	u64 action_flags;
	u64 flags;
	int err = 0;

	err = uverbs_get_flags64(
		&action_flags, attrs, MLX5_IB_ATTR_CREATE_FLOW_ACTION_FLAGS,
		((MLX5_FLOW_ACTION_ESP_CREATE_LAST_SUPPORTED << 1) - 1));
	if (err)
		return ERR_PTR(err);

	flags = mlx5_ib_flow_action_flags_to_accel_xfrm_flags(action_flags);

	/* We current only support a subset of the standard features. Only a
	 * keymat of type AES_GCM, with icv_len == 16, iv_algo == SEQ and esn
	 * (with overlap). Full offload mode isn't supported.
	 */
	if (!attr->keymat || attr->replay || attr->encap ||
	    attr->spi || attr->seq || attr->tfc_pad ||
	    attr->hard_limit_pkts ||
	    (attr->flags & ~(IB_FLOW_ACTION_ESP_FLAGS_ESN_TRIGGERED |
			     IB_UVERBS_FLOW_ACTION_ESP_FLAGS_ENCRYPT)))
		return ERR_PTR(-EOPNOTSUPP);

	if (attr->keymat->protocol !=
	    IB_UVERBS_FLOW_ACTION_ESP_KEYMAT_AES_GCM)
		return ERR_PTR(-EOPNOTSUPP);

	aes_gcm = &attr->keymat->keymat.aes_gcm;

	if (aes_gcm->icv_len != 16 ||
	    aes_gcm->iv_algo != IB_UVERBS_FLOW_ACTION_IV_ALGO_SEQ)
		return ERR_PTR(-EOPNOTSUPP);

	action = kmalloc(sizeof(*action), GFP_KERNEL);
	if (!action)
		return ERR_PTR(-ENOMEM);

	action->esp_aes_gcm.ib_flags = attr->flags;
	memcpy(&accel_attrs.keymat.aes_gcm.aes_key, &aes_gcm->aes_key,
	       sizeof(accel_attrs.keymat.aes_gcm.aes_key));
	accel_attrs.keymat.aes_gcm.key_len = aes_gcm->key_len * 8;
	memcpy(&accel_attrs.keymat.aes_gcm.salt, &aes_gcm->salt,
	       sizeof(accel_attrs.keymat.aes_gcm.salt));
	memcpy(&accel_attrs.keymat.aes_gcm.seq_iv, &aes_gcm->iv,
	       sizeof(accel_attrs.keymat.aes_gcm.seq_iv));
	accel_attrs.keymat.aes_gcm.icv_len = aes_gcm->icv_len * 8;
	accel_attrs.keymat.aes_gcm.iv_algo = MLX5_ACCEL_ESP_AES_GCM_IV_ALGO_SEQ;
	accel_attrs.keymat_type = MLX5_ACCEL_ESP_KEYMAT_AES_GCM;

	accel_attrs.esn = attr->esn;
	if (attr->flags & IB_FLOW_ACTION_ESP_FLAGS_ESN_TRIGGERED)
		accel_attrs.flags |= MLX5_ACCEL_ESP_FLAGS_ESN_TRIGGERED;
	if (attr->flags & IB_UVERBS_FLOW_ACTION_ESP_FLAGS_ESN_NEW_WINDOW)
		accel_attrs.flags |= MLX5_ACCEL_ESP_FLAGS_ESN_STATE_OVERLAP;

	if (attr->flags & IB_UVERBS_FLOW_ACTION_ESP_FLAGS_ENCRYPT)
		accel_attrs.action |= MLX5_ACCEL_ESP_ACTION_ENCRYPT;

	action->esp_aes_gcm.ctx =
		mlx5_accel_esp_create_xfrm(mdev->mdev, &accel_attrs, flags);
	if (IS_ERR(action->esp_aes_gcm.ctx)) {
		err = PTR_ERR(action->esp_aes_gcm.ctx);
		goto err_parse;
	}

	action->esp_aes_gcm.ib_flags = attr->flags;

	return &action->ib_action;

err_parse:
	kfree(action);
	return ERR_PTR(err);
}

static int
mlx5_ib_modify_flow_action_esp(struct ib_flow_action *action,
			       const struct ib_flow_action_attrs_esp *attr,
			       struct uverbs_attr_bundle *attrs)
{
	struct mlx5_ib_flow_action *maction = to_mflow_act(action);
	struct mlx5_accel_esp_xfrm_attrs accel_attrs;
	int err = 0;

	if (attr->keymat || attr->replay || attr->encap ||
	    attr->spi || attr->seq || attr->tfc_pad ||
	    attr->hard_limit_pkts ||
	    (attr->flags & ~(IB_FLOW_ACTION_ESP_FLAGS_ESN_TRIGGERED |
			     IB_FLOW_ACTION_ESP_FLAGS_MOD_ESP_ATTRS |
			     IB_UVERBS_FLOW_ACTION_ESP_FLAGS_ESN_NEW_WINDOW)))
		return -EOPNOTSUPP;

	/* Only the ESN value or the MLX5_ACCEL_ESP_FLAGS_ESN_STATE_OVERLAP can
	 * be modified.
	 */
	if (!(maction->esp_aes_gcm.ib_flags &
	      IB_FLOW_ACTION_ESP_FLAGS_ESN_TRIGGERED) &&
	    attr->flags & (IB_FLOW_ACTION_ESP_FLAGS_ESN_TRIGGERED |
			   IB_UVERBS_FLOW_ACTION_ESP_FLAGS_ESN_NEW_WINDOW))
		return -EINVAL;

	memcpy(&accel_attrs, &maction->esp_aes_gcm.ctx->attrs,
	       sizeof(accel_attrs));

	accel_attrs.esn = attr->esn;
	if (attr->flags & IB_UVERBS_FLOW_ACTION_ESP_FLAGS_ESN_NEW_WINDOW)
		accel_attrs.flags |= MLX5_ACCEL_ESP_FLAGS_ESN_STATE_OVERLAP;
	else
		accel_attrs.flags &= ~MLX5_ACCEL_ESP_FLAGS_ESN_STATE_OVERLAP;

	err = mlx5_accel_esp_modify_xfrm(maction->esp_aes_gcm.ctx,
					 &accel_attrs);
	if (err)
		return err;

	maction->esp_aes_gcm.ib_flags &=
		~IB_UVERBS_FLOW_ACTION_ESP_FLAGS_ESN_NEW_WINDOW;
	maction->esp_aes_gcm.ib_flags |=
		attr->flags & IB_UVERBS_FLOW_ACTION_ESP_FLAGS_ESN_NEW_WINDOW;

	return 0;
}

static int mlx5_ib_destroy_flow_action(struct ib_flow_action *action)
{
	struct mlx5_ib_flow_action *maction = to_mflow_act(action);

	switch (action->type) {
	case IB_FLOW_ACTION_ESP:
		/*
		 * We only support aes_gcm by now, so we implicitly know this is
		 * the underline crypto.
		 */
		mlx5_accel_esp_destroy_xfrm(maction->esp_aes_gcm.ctx);
		break;
	case IB_FLOW_ACTION_UNSPECIFIED:
		mlx5_ib_destroy_flow_action_raw(maction);
		break;
	default:
		WARN_ON(true);
		break;
	}

	kfree(maction);
	return 0;
}

static int mlx5_ib_mcg_attach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
{
	struct mlx5_ib_dev *dev = to_mdev(ibqp->device);
	struct mlx5_ib_qp *mqp = to_mqp(ibqp);
	int err;
	u16 uid;

	uid = ibqp->pd ?
		to_mpd(ibqp->pd)->uid : 0;

	if (mqp->flags & MLX5_IB_QP_UNDERLAY) {
		mlx5_ib_dbg(dev, "Attaching a multi cast group to underlay QP is not supported\n");
		return -EOPNOTSUPP;
	}

	err = mlx5_cmd_attach_mcg(dev->mdev, gid, ibqp->qp_num, uid);
	if (err)
		mlx5_ib_warn(dev, "failed attaching QPN 0x%x, MGID %pI6\n",
			     ibqp->qp_num, gid->raw);

	return err;
}

static int mlx5_ib_mcg_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
{
	struct mlx5_ib_dev *dev = to_mdev(ibqp->device);
	int err;
	u16 uid;

	uid = ibqp->pd ?
		to_mpd(ibqp->pd)->uid : 0;
	err = mlx5_cmd_detach_mcg(dev->mdev, gid, ibqp->qp_num, uid);
	if (err)
		mlx5_ib_warn(dev, "failed detaching QPN 0x%x, MGID %pI6\n",
			     ibqp->qp_num, gid->raw);

	return err;
}

static int init_node_data(struct mlx5_ib_dev *dev)
{
	int err;

	err = mlx5_query_node_desc(dev, dev->ib_dev.node_desc);
	if (err)
		return err;

	dev->mdev->rev_id = dev->mdev->pdev->revision;

	return mlx5_query_node_guid(dev, &dev->ib_dev.node_guid);
}

static ssize_t fw_pages_show(struct device *device,
			     struct device_attribute *attr, char *buf)
{
	struct mlx5_ib_dev *dev =
		container_of(device, struct mlx5_ib_dev, ib_dev.dev);

	return sprintf(buf, "%d\n", dev->mdev->priv.fw_pages);
}
static DEVICE_ATTR_RO(fw_pages);

static ssize_t reg_pages_show(struct device *device,
			      struct device_attribute *attr, char *buf)
{
	struct mlx5_ib_dev *dev =
		container_of(device, struct mlx5_ib_dev, ib_dev.dev);

	return sprintf(buf, "%d\n", atomic_read(&dev->mdev->priv.reg_pages));
}
static DEVICE_ATTR_RO(reg_pages);

static ssize_t hca_type_show(struct device *device,
			     struct device_attribute *attr, char *buf)
{
	struct mlx5_ib_dev *dev =
		container_of(device, struct mlx5_ib_dev, ib_dev.dev);
	return sprintf(buf, "MT%d\n", dev->mdev->pdev->device);
}
static DEVICE_ATTR_RO(hca_type);

static ssize_t hw_rev_show(struct device *device,
			   struct device_attribute *attr, char *buf)
{
	struct mlx5_ib_dev *dev =
		container_of(device, struct mlx5_ib_dev, ib_dev.dev);
	return sprintf(buf, "%x\n", dev->mdev->rev_id);
}
static DEVICE_ATTR_RO(hw_rev);

static ssize_t board_id_show(struct device *device,
			     struct device_attribute *attr, char *buf)
{
	struct mlx5_ib_dev *dev =
		container_of(device, struct mlx5_ib_dev, ib_dev.dev);
	return sprintf(buf, "%.*s\n", MLX5_BOARD_ID_LEN,
		       dev->mdev->board_id);
}
static DEVICE_ATTR_RO(board_id);

static struct attribute *mlx5_class_attributes[] = {
	&dev_attr_hw_rev.attr,
	&dev_attr_hca_type.attr,
	&dev_attr_board_id.attr,
	&dev_attr_fw_pages.attr,
	&dev_attr_reg_pages.attr,
	NULL,
};

static const struct attribute_group mlx5_attr_group = {
	.attrs = mlx5_class_attributes,
};

static void pkey_change_handler(struct work_struct *work)
{
	struct mlx5_ib_port_resources *ports =
		container_of(work, struct mlx5_ib_port_resources,
			     pkey_change_work);

	mutex_lock(&ports->devr->mutex);
	mlx5_ib_gsi_pkey_change(ports->gsi);
	mutex_unlock(&ports->devr->mutex);
}

static void mlx5_ib_handle_internal_error(struct mlx5_ib_dev *ibdev)
{
	struct mlx5_ib_qp *mqp;
	struct mlx5_ib_cq *send_mcq, *recv_mcq;
	struct mlx5_core_cq *mcq;
	struct list_head cq_armed_list;
	unsigned long flags_qp;
	unsigned long flags_cq;
	unsigned long flags;

	INIT_LIST_HEAD(&cq_armed_list);

	/* Go over qp list reside on that ibdev, sync with create/destroy qp.*/
	spin_lock_irqsave(&ibdev->reset_flow_resource_lock, flags);
	list_for_each_entry(mqp, &ibdev->qp_list, qps_list) {
		spin_lock_irqsave(&mqp->sq.lock, flags_qp);
		if (mqp->sq.tail != mqp->sq.head) {
			send_mcq = to_mcq(mqp->ibqp.send_cq);
			spin_lock_irqsave(&send_mcq->lock, flags_cq);
			if (send_mcq->mcq.comp &&
			    mqp->ibqp.send_cq->comp_handler) {
				if (!send_mcq->mcq.reset_notify_added) {
					send_mcq->mcq.reset_notify_added = 1;
					list_add_tail(&send_mcq->mcq.reset_notify,
						      &cq_armed_list);
				}
			}
			spin_unlock_irqrestore(&send_mcq->lock, flags_cq);
		}
		spin_unlock_irqrestore(&mqp->sq.lock, flags_qp);
		spin_lock_irqsave(&mqp->rq.lock, flags_qp);
		/* no handling is needed for SRQ */
		if (!mqp->ibqp.srq) {
			if (mqp->rq.tail != mqp->rq.head) {
				recv_mcq = to_mcq(mqp->ibqp.recv_cq);
				spin_lock_irqsave(&recv_mcq->lock, flags_cq);
				if (recv_mcq->mcq.comp &&
				    mqp->ibqp.recv_cq->comp_handler) {
					if (!recv_mcq->mcq.reset_notify_added) {
						recv_mcq->mcq.reset_notify_added = 1;
						list_add_tail(&recv_mcq->mcq.reset_notify,
							      &cq_armed_list);
					}
				}
				spin_unlock_irqrestore(&recv_mcq->lock,
						       flags_cq);
			}
		}
		spin_unlock_irqrestore(&mqp->rq.lock, flags_qp);
	}
	/*At that point all inflight post send were put to be executed as of we
	 * lock/unlock above locks Now need to arm all involved CQs.
	 */
	list_for_each_entry(mcq, &cq_armed_list, reset_notify) {
		mcq->comp(mcq);
	}
	spin_unlock_irqrestore(&ibdev->reset_flow_resource_lock, flags);
}

static void delay_drop_handler(struct work_struct *work)
{
	int err;
	struct mlx5_ib_delay_drop *delay_drop =
		container_of(work, struct mlx5_ib_delay_drop,
			     delay_drop_work);

	atomic_inc(&delay_drop->events_cnt);

	mutex_lock(&delay_drop->lock);
	err = mlx5_core_set_delay_drop(delay_drop->dev->mdev,
				       delay_drop->timeout);
	if (err) {
		mlx5_ib_warn(delay_drop->dev, "Failed to set delay drop, timeout=%u\n",
			     delay_drop->timeout);
		delay_drop->activate = false;
	}
	mutex_unlock(&delay_drop->lock);
}

static void mlx5_ib_handle_event(struct work_struct *_work)
{
	struct mlx5_ib_event_work *work =
		container_of(_work, struct mlx5_ib_event_work, work);
	struct mlx5_ib_dev *ibdev;
	struct ib_event ibev;
	bool fatal = false;
	u8 port = (u8)work->param;

	if (mlx5_core_is_mp_slave(work->dev)) {
		ibdev = mlx5_ib_get_ibdev_from_mpi(work->context);
		if (!ibdev)
			goto out;
	} else {
		ibdev = work->context;
	}

	switch (work->event) {
	case MLX5_DEV_EVENT_SYS_ERROR:
		ibev.event = IB_EVENT_DEVICE_FATAL;
		mlx5_ib_handle_internal_error(ibdev);
		fatal = true;
		break;

	case MLX5_DEV_EVENT_PORT_UP:
	case MLX5_DEV_EVENT_PORT_DOWN:
	case MLX5_DEV_EVENT_PORT_INITIALIZED:
		/* In RoCE, port up/down events are handled in
		 * mlx5_netdev_event().
		 */
		if (mlx5_ib_port_link_layer(&ibdev->ib_dev, port) ==
			IB_LINK_LAYER_ETHERNET)
			goto out;

		ibev.event = (work->event == MLX5_DEV_EVENT_PORT_UP) ?
			     IB_EVENT_PORT_ACTIVE : IB_EVENT_PORT_ERR;
		break;

	case MLX5_DEV_EVENT_LID_CHANGE:
		ibev.event = IB_EVENT_LID_CHANGE;
		break;

	case MLX5_DEV_EVENT_PKEY_CHANGE:
		ibev.event = IB_EVENT_PKEY_CHANGE;
		schedule_work(&ibdev->devr.ports[port - 1].pkey_change_work);
		break;

	case MLX5_DEV_EVENT_GUID_CHANGE:
		ibev.event = IB_EVENT_GID_CHANGE;
		break;

	case MLX5_DEV_EVENT_CLIENT_REREG:
		ibev.event = IB_EVENT_CLIENT_REREGISTER;
		break;
	case MLX5_DEV_EVENT_DELAY_DROP_TIMEOUT:
		schedule_work(&ibdev->delay_drop.delay_drop_work);
		goto out;
	default:
		goto out;
	}

	ibev.device	      = &ibdev->ib_dev;
	ibev.element.port_num = port;

	if (!rdma_is_port_valid(&ibdev->ib_dev, port)) {
		mlx5_ib_warn(ibdev, "warning: event on port %d\n", port);
		goto out;
	}

	if (ibdev->ib_active)
		ib_dispatch_event(&ibev);

	if (fatal)
		ibdev->ib_active = false;
out:
	kfree(work);
}

static void mlx5_ib_event(struct mlx5_core_dev *dev, void *context,
			  enum mlx5_dev_event event, unsigned long param)
{
	struct mlx5_ib_event_work *work;

	work = kmalloc(sizeof(*work), GFP_ATOMIC);
	if (!work)
		return;

	INIT_WORK(&work->work, mlx5_ib_handle_event);
	work->dev = dev;
	work->param = param;
	work->context = context;
	work->event = event;

	queue_work(mlx5_ib_event_wq, &work->work);
}

static int set_has_smi_cap(struct mlx5_ib_dev *dev)
{
	struct mlx5_hca_vport_context vport_ctx;
	int err;
	int port;

	for (port = 1; port <= dev->num_ports; port++) {
		dev->mdev->port_caps[port - 1].has_smi = false;
		if (MLX5_CAP_GEN(dev->mdev, port_type) ==
		    MLX5_CAP_PORT_TYPE_IB) {
			if (MLX5_CAP_GEN(dev->mdev, ib_virt)) {
				err = mlx5_query_hca_vport_context(dev->mdev, 0,
								   port, 0,
								   &vport_ctx);
				if (err) {
					mlx5_ib_err(dev, "query_hca_vport_context for port=%d failed %d\n",
						    port, err);
					return err;
				}
				dev->mdev->port_caps[port - 1].has_smi =
					vport_ctx.has_smi;
			} else {
				dev->mdev->port_caps[port - 1].has_smi = true;
			}
		}
	}
	return 0;
}

static void get_ext_port_caps(struct mlx5_ib_dev *dev)
{
	int port;

	for (port = 1; port <= dev->num_ports; port++)
		mlx5_query_ext_port_caps(dev, port);
}

static int get_port_caps(struct mlx5_ib_dev *dev, u8 port)
{
	struct ib_device_attr *dprops = NULL;
	struct ib_port_attr *pprops = NULL;
	int err = -ENOMEM;
	struct ib_udata uhw = {.inlen = 0, .outlen = 0};

	pprops = kmalloc(sizeof(*pprops), GFP_KERNEL);
	if (!pprops)
		goto out;

	dprops = kmalloc(sizeof(*dprops), GFP_KERNEL);
	if (!dprops)
		goto out;

	err = set_has_smi_cap(dev);
	if (err)
		goto out;

	err = mlx5_ib_query_device(&dev->ib_dev, dprops, &uhw);
	if (err) {
		mlx5_ib_warn(dev, "query_device failed %d\n", err);
		goto out;
	}

	memset(pprops, 0, sizeof(*pprops));
	err = mlx5_ib_query_port(&dev->ib_dev, port, pprops);
	if (err) {
		mlx5_ib_warn(dev, "query_port %d failed %d\n",
			     port, err);
		goto out;
	}

	dev->mdev->port_caps[port - 1].pkey_table_len =
					dprops->max_pkeys;
	dev->mdev->port_caps[port - 1].gid_table_len =
					pprops->gid_tbl_len;
	mlx5_ib_dbg(dev, "port %d: pkey_table_len %d, gid_table_len %d\n",
		    port, dprops->max_pkeys, pprops->gid_tbl_len);

out:
	kfree(pprops);
	kfree(dprops);

	return err;
}

static void destroy_umrc_res(struct mlx5_ib_dev *dev)
{
	int err;

	err = mlx5_mr_cache_cleanup(dev);
	if (err)
		mlx5_ib_warn(dev, "mr cache cleanup failed\n");

	if (dev->umrc.qp)
		mlx5_ib_destroy_qp(dev->umrc.qp);
	if (dev->umrc.cq)
		ib_free_cq(dev->umrc.cq);
	if (dev->umrc.pd)
		ib_dealloc_pd(dev->umrc.pd);
}

enum {
	MAX_UMR_WR = 128,
};

static int create_umr_res(struct mlx5_ib_dev *dev)
{
	struct ib_qp_init_attr *init_attr = NULL;
	struct ib_qp_attr *attr = NULL;
	struct ib_pd *pd;
	struct ib_cq *cq;
	struct ib_qp *qp;
	int ret;

	attr = kzalloc(sizeof(*attr), GFP_KERNEL);
	init_attr = kzalloc(sizeof(*init_attr), GFP_KERNEL);
	if (!attr || !init_attr) {
		ret = -ENOMEM;
		goto error_0;
	}

	pd = ib_alloc_pd(&dev->ib_dev, 0);
	if (IS_ERR(pd)) {
		mlx5_ib_dbg(dev, "Couldn't create PD for sync UMR QP\n");
		ret = PTR_ERR(pd);
		goto error_0;
	}

	cq = ib_alloc_cq(&dev->ib_dev, NULL, 128, 0, IB_POLL_SOFTIRQ);
	if (IS_ERR(cq)) {
		mlx5_ib_dbg(dev, "Couldn't create CQ for sync UMR QP\n");
		ret = PTR_ERR(cq);
		goto error_2;
	}

	init_attr->send_cq = cq;
	init_attr->recv_cq = cq;
	init_attr->sq_sig_type = IB_SIGNAL_ALL_WR;
	init_attr->cap.max_send_wr = MAX_UMR_WR;
	init_attr->cap.max_send_sge = 1;
	init_attr->qp_type = MLX5_IB_QPT_REG_UMR;
	init_attr->port_num = 1;
	qp = mlx5_ib_create_qp(pd, init_attr, NULL);
	if (IS_ERR(qp)) {
		mlx5_ib_dbg(dev, "Couldn't create sync UMR QP\n");
		ret = PTR_ERR(qp);
		goto error_3;
	}
	qp->device     = &dev->ib_dev;
	qp->real_qp    = qp;
	qp->uobject    = NULL;
	qp->qp_type    = MLX5_IB_QPT_REG_UMR;
	qp->send_cq    = init_attr->send_cq;
	qp->recv_cq    = init_attr->recv_cq;

	attr->qp_state = IB_QPS_INIT;
	attr->port_num = 1;
	ret = mlx5_ib_modify_qp(qp, attr, IB_QP_STATE | IB_QP_PKEY_INDEX |
				IB_QP_PORT, NULL);
	if (ret) {
		mlx5_ib_dbg(dev, "Couldn't modify UMR QP\n");
		goto error_4;
	}

	memset(attr, 0, sizeof(*attr));
	attr->qp_state = IB_QPS_RTR;
	attr->path_mtu = IB_MTU_256;

	ret = mlx5_ib_modify_qp(qp, attr, IB_QP_STATE, NULL);
	if (ret) {
		mlx5_ib_dbg(dev, "Couldn't modify umr QP to rtr\n");
		goto error_4;
	}

	memset(attr, 0, sizeof(*attr));
	attr->qp_state = IB_QPS_RTS;
	ret = mlx5_ib_modify_qp(qp, attr, IB_QP_STATE, NULL);
	if (ret) {
		mlx5_ib_dbg(dev, "Couldn't modify umr QP to rts\n");
		goto error_4;
	}

	dev->umrc.qp = qp;
	dev->umrc.cq = cq;
	dev->umrc.pd = pd;

	sema_init(&dev->umrc.sem, MAX_UMR_WR);
	ret = mlx5_mr_cache_init(dev);
	if (ret) {
		mlx5_ib_warn(dev, "mr cache init failed %d\n", ret);
		goto error_4;
	}

	kfree(attr);
	kfree(init_attr);

	return 0;

error_4:
	mlx5_ib_destroy_qp(qp);
	dev->umrc.qp = NULL;

error_3:
	ib_free_cq(cq);
	dev->umrc.cq = NULL;

error_2:
	ib_dealloc_pd(pd);
	dev->umrc.pd = NULL;

error_0:
	kfree(attr);
	kfree(init_attr);
	return ret;
}

static u8 mlx5_get_umr_fence(u8 umr_fence_cap)
{
	switch (umr_fence_cap) {
	case MLX5_CAP_UMR_FENCE_NONE:
		return MLX5_FENCE_MODE_NONE;
	case MLX5_CAP_UMR_FENCE_SMALL:
		return MLX5_FENCE_MODE_INITIATOR_SMALL;
	default:
		return MLX5_FENCE_MODE_STRONG_ORDERING;
	}
}

static int create_dev_resources(struct mlx5_ib_resources *devr)
{
	struct ib_srq_init_attr attr;
	struct mlx5_ib_dev *dev;
	struct ib_cq_init_attr cq_attr = {.cqe = 1};
	int port;
	int ret = 0;

	dev = container_of(devr, struct mlx5_ib_dev, devr);

	mutex_init(&devr->mutex);

	devr->p0 = mlx5_ib_alloc_pd(&dev->ib_dev, NULL, NULL);
	if (IS_ERR(devr->p0)) {
		ret = PTR_ERR(devr->p0);
		goto error0;
	}
	devr->p0->device  = &dev->ib_dev;
	devr->p0->uobject = NULL;
	atomic_set(&devr->p0->usecnt, 0);

	devr->c0 = mlx5_ib_create_cq(&dev->ib_dev, &cq_attr, NULL, NULL);
	if (IS_ERR(devr->c0)) {
		ret = PTR_ERR(devr->c0);
		goto error1;
	}
	devr->c0->device        = &dev->ib_dev;
	devr->c0->uobject       = NULL;
	devr->c0->comp_handler  = NULL;
	devr->c0->event_handler = NULL;
	devr->c0->cq_context    = NULL;
	atomic_set(&devr->c0->usecnt, 0);

	devr->x0 = mlx5_ib_alloc_xrcd(&dev->ib_dev, NULL, NULL);
	if (IS_ERR(devr->x0)) {
		ret = PTR_ERR(devr->x0);
		goto error2;
	}
	devr->x0->device = &dev->ib_dev;
	devr->x0->inode = NULL;
	atomic_set(&devr->x0->usecnt, 0);
	mutex_init(&devr->x0->tgt_qp_mutex);
	INIT_LIST_HEAD(&devr->x0->tgt_qp_list);

	devr->x1 = mlx5_ib_alloc_xrcd(&dev->ib_dev, NULL, NULL);
	if (IS_ERR(devr->x1)) {
		ret = PTR_ERR(devr->x1);
		goto error3;
	}
	devr->x1->device = &dev->ib_dev;
	devr->x1->inode = NULL;
	atomic_set(&devr->x1->usecnt, 0);
	mutex_init(&devr->x1->tgt_qp_mutex);
	INIT_LIST_HEAD(&devr->x1->tgt_qp_list);

	memset(&attr, 0, sizeof(attr));
	attr.attr.max_sge = 1;
	attr.attr.max_wr = 1;
	attr.srq_type = IB_SRQT_XRC;
	attr.ext.cq = devr->c0;
	attr.ext.xrc.xrcd = devr->x0;

	devr->s0 = mlx5_ib_create_srq(devr->p0, &attr, NULL);
	if (IS_ERR(devr->s0)) {
		ret = PTR_ERR(devr->s0);
		goto error4;
	}
	devr->s0->device	= &dev->ib_dev;
	devr->s0->pd		= devr->p0;
	devr->s0->uobject       = NULL;
	devr->s0->event_handler = NULL;
	devr->s0->srq_context   = NULL;
	devr->s0->srq_type      = IB_SRQT_XRC;
	devr->s0->ext.xrc.xrcd	= devr->x0;
	devr->s0->ext.cq	= devr->c0;
	atomic_inc(&devr->s0->ext.xrc.xrcd->usecnt);
	atomic_inc(&devr->s0->ext.cq->usecnt);
	atomic_inc(&devr->p0->usecnt);
	atomic_set(&devr->s0->usecnt, 0);

	memset(&attr, 0, sizeof(attr));
	attr.attr.max_sge = 1;
	attr.attr.max_wr = 1;
	attr.srq_type = IB_SRQT_BASIC;
	devr->s1 = mlx5_ib_create_srq(devr->p0, &attr, NULL);
	if (IS_ERR(devr->s1)) {
		ret = PTR_ERR(devr->s1);
		goto error5;
	}
	devr->s1->device	= &dev->ib_dev;
	devr->s1->pd		= devr->p0;
	devr->s1->uobject       = NULL;
	devr->s1->event_handler = NULL;
	devr->s1->srq_context   = NULL;
	devr->s1->srq_type      = IB_SRQT_BASIC;
	devr->s1->ext.cq	= devr->c0;
	atomic_inc(&devr->p0->usecnt);
	atomic_set(&devr->s1->usecnt, 0);

	for (port = 0; port < ARRAY_SIZE(devr->ports); ++port) {
		INIT_WORK(&devr->ports[port].pkey_change_work,
			  pkey_change_handler);
		devr->ports[port].devr = devr;
	}

	return 0;

error5:
	mlx5_ib_destroy_srq(devr->s0);
error4:
	mlx5_ib_dealloc_xrcd(devr->x1);
error3:
	mlx5_ib_dealloc_xrcd(devr->x0);
error2:
	mlx5_ib_destroy_cq(devr->c0);
error1:
	mlx5_ib_dealloc_pd(devr->p0);
error0:
	return ret;
}

static void destroy_dev_resources(struct mlx5_ib_resources *devr)
{
	struct mlx5_ib_dev *dev =
		container_of(devr, struct mlx5_ib_dev, devr);
	int port;

	mlx5_ib_destroy_srq(devr->s1);
	mlx5_ib_destroy_srq(devr->s0);
	mlx5_ib_dealloc_xrcd(devr->x0);
	mlx5_ib_dealloc_xrcd(devr->x1);
	mlx5_ib_destroy_cq(devr->c0);
	mlx5_ib_dealloc_pd(devr->p0);

	/* Make sure no change P_Key work items are still executing */
	for (port = 0; port < dev->num_ports; ++port)
		cancel_work_sync(&devr->ports[port].pkey_change_work);
}

static u32 get_core_cap_flags(struct ib_device *ibdev,
			      struct mlx5_hca_vport_context *rep)
{
	struct mlx5_ib_dev *dev = to_mdev(ibdev);
	enum rdma_link_layer ll = mlx5_ib_port_link_layer(ibdev, 1);
	u8 l3_type_cap = MLX5_CAP_ROCE(dev->mdev, l3_type);
	u8 roce_version_cap = MLX5_CAP_ROCE(dev->mdev, roce_version);
	bool raw_support = !mlx5_core_mp_enabled(dev->mdev);
	u32 ret = 0;

	if (rep->grh_required)
		ret |= RDMA_CORE_CAP_IB_GRH_REQUIRED;

	if (ll == IB_LINK_LAYER_INFINIBAND)
		return ret | RDMA_CORE_PORT_IBA_IB;

	if (raw_support)
		ret |= RDMA_CORE_PORT_RAW_PACKET;

	if (!(l3_type_cap & MLX5_ROCE_L3_TYPE_IPV4_CAP))
		return ret;

	if (!(l3_type_cap & MLX5_ROCE_L3_TYPE_IPV6_CAP))
		return ret;

	if (roce_version_cap & MLX5_ROCE_VERSION_1_CAP)
		ret |= RDMA_CORE_PORT_IBA_ROCE;

	if (roce_version_cap & MLX5_ROCE_VERSION_2_CAP)
		ret |= RDMA_CORE_PORT_IBA_ROCE_UDP_ENCAP;

	return ret;
}

static int mlx5_port_immutable(struct ib_device *ibdev, u8 port_num,
			       struct ib_port_immutable *immutable)
{
	struct ib_port_attr attr;
	struct mlx5_ib_dev *dev = to_mdev(ibdev);
	enum rdma_link_layer ll = mlx5_ib_port_link_layer(ibdev, port_num);
	struct mlx5_hca_vport_context rep = {0};
	int err;

	err = ib_query_port(ibdev, port_num, &attr);
	if (err)
		return err;

	if (ll == IB_LINK_LAYER_INFINIBAND) {
		err = mlx5_query_hca_vport_context(dev->mdev, 0, port_num, 0,
						   &rep);
		if (err)
			return err;
	}

	immutable->pkey_tbl_len = attr.pkey_tbl_len;
	immutable->gid_tbl_len = attr.gid_tbl_len;
	immutable->core_cap_flags = get_core_cap_flags(ibdev, &rep);
	if ((ll == IB_LINK_LAYER_INFINIBAND) || MLX5_CAP_GEN(dev->mdev, roce))
		immutable->max_mad_size = IB_MGMT_MAD_SIZE;

	return 0;
}

static int mlx5_port_rep_immutable(struct ib_device *ibdev, u8 port_num,
				   struct ib_port_immutable *immutable)
{
	struct ib_port_attr attr;
	int err;

	immutable->core_cap_flags = RDMA_CORE_PORT_RAW_PACKET;

	err = ib_query_port(ibdev, port_num, &attr);
	if (err)
		return err;

	immutable->pkey_tbl_len = attr.pkey_tbl_len;
	immutable->gid_tbl_len = attr.gid_tbl_len;
	immutable->core_cap_flags = RDMA_CORE_PORT_RAW_PACKET;

	return 0;
}

static void get_dev_fw_str(struct ib_device *ibdev, char *str)
{
	struct mlx5_ib_dev *dev =
		container_of(ibdev, struct mlx5_ib_dev, ib_dev);
	snprintf(str, IB_FW_VERSION_NAME_MAX, "%d.%d.%04d",
		 fw_rev_maj(dev->mdev), fw_rev_min(dev->mdev),
		 fw_rev_sub(dev->mdev));
}

static int mlx5_eth_lag_init(struct mlx5_ib_dev *dev)
{
	struct mlx5_core_dev *mdev = dev->mdev;
	struct mlx5_flow_namespace *ns = mlx5_get_flow_namespace(mdev,
								 MLX5_FLOW_NAMESPACE_LAG);
	struct mlx5_flow_table *ft;
	int err;

	if (!ns || !mlx5_lag_is_active(mdev))
		return 0;

	err = mlx5_cmd_create_vport_lag(mdev);
	if (err)
		return err;

	ft = mlx5_create_lag_demux_flow_table(ns, 0, 0);
	if (IS_ERR(ft)) {
		err = PTR_ERR(ft);
		goto err_destroy_vport_lag;
	}

	dev->flow_db->lag_demux_ft = ft;
	return 0;

err_destroy_vport_lag:
	mlx5_cmd_destroy_vport_lag(mdev);
	return err;
}

static void mlx5_eth_lag_cleanup(struct mlx5_ib_dev *dev)
{
	struct mlx5_core_dev *mdev = dev->mdev;

	if (dev->flow_db->lag_demux_ft) {
		mlx5_destroy_flow_table(dev->flow_db->lag_demux_ft);
		dev->flow_db->lag_demux_ft = NULL;

		mlx5_cmd_destroy_vport_lag(mdev);
	}
}

static int mlx5_add_netdev_notifier(struct mlx5_ib_dev *dev, u8 port_num)
{
	int err;

	dev->roce[port_num].nb.notifier_call = mlx5_netdev_event;
	err = register_netdevice_notifier(&dev->roce[port_num].nb);
	if (err) {
		dev->roce[port_num].nb.notifier_call = NULL;
		return err;
	}

	return 0;
}

static void mlx5_remove_netdev_notifier(struct mlx5_ib_dev *dev, u8 port_num)
{
	if (dev->roce[port_num].nb.notifier_call) {
		unregister_netdevice_notifier(&dev->roce[port_num].nb);
		dev->roce[port_num].nb.notifier_call = NULL;
	}
}

static int mlx5_enable_eth(struct mlx5_ib_dev *dev)
{
	int err;

	if (MLX5_CAP_GEN(dev->mdev, roce)) {
		err = mlx5_nic_vport_enable_roce(dev->mdev);
		if (err)
			return err;
	}

	err = mlx5_eth_lag_init(dev);
	if (err)
		goto err_disable_roce;

	return 0;

err_disable_roce:
	if (MLX5_CAP_GEN(dev->mdev, roce))
		mlx5_nic_vport_disable_roce(dev->mdev);

	return err;
}

static void mlx5_disable_eth(struct mlx5_ib_dev *dev)
{
	mlx5_eth_lag_cleanup(dev);
	if (MLX5_CAP_GEN(dev->mdev, roce))
		mlx5_nic_vport_disable_roce(dev->mdev);
}

struct mlx5_ib_counter {
	const char *name;
	size_t offset;
};

#define INIT_Q_COUNTER(_name)		\
	{ .name = #_name, .offset = MLX5_BYTE_OFF(query_q_counter_out, _name)}

static const struct mlx5_ib_counter basic_q_cnts[] = {
	INIT_Q_COUNTER(rx_write_requests),
	INIT_Q_COUNTER(rx_read_requests),
	INIT_Q_COUNTER(rx_atomic_requests),
	INIT_Q_COUNTER(out_of_buffer),
};

static const struct mlx5_ib_counter out_of_seq_q_cnts[] = {
	INIT_Q_COUNTER(out_of_sequence),
};

static const struct mlx5_ib_counter retrans_q_cnts[] = {
	INIT_Q_COUNTER(duplicate_request),
	INIT_Q_COUNTER(rnr_nak_retry_err),
	INIT_Q_COUNTER(packet_seq_err),
	INIT_Q_COUNTER(implied_nak_seq_err),
	INIT_Q_COUNTER(local_ack_timeout_err),
};

#define INIT_CONG_COUNTER(_name)		\
	{ .name = #_name, .offset =	\
		MLX5_BYTE_OFF(query_cong_statistics_out, _name ## _high)}

static const struct mlx5_ib_counter cong_cnts[] = {
	INIT_CONG_COUNTER(rp_cnp_ignored),
	INIT_CONG_COUNTER(rp_cnp_handled),
	INIT_CONG_COUNTER(np_ecn_marked_roce_packets),
	INIT_CONG_COUNTER(np_cnp_sent),
};

static const struct mlx5_ib_counter extended_err_cnts[] = {
	INIT_Q_COUNTER(resp_local_length_error),
	INIT_Q_COUNTER(resp_cqe_error),
	INIT_Q_COUNTER(req_cqe_error),
	INIT_Q_COUNTER(req_remote_invalid_request),
	INIT_Q_COUNTER(req_remote_access_errors),
	INIT_Q_COUNTER(resp_remote_access_errors),
	INIT_Q_COUNTER(resp_cqe_flush_error),
	INIT_Q_COUNTER(req_cqe_flush_error),
};

#define INIT_EXT_PPCNT_COUNTER(_name)		\
	{ .name = #_name, .offset =	\
	MLX5_BYTE_OFF(ppcnt_reg, \
		      counter_set.eth_extended_cntrs_grp_data_layout._name##_high)}

static const struct mlx5_ib_counter ext_ppcnt_cnts[] = {
	INIT_EXT_PPCNT_COUNTER(rx_icrc_encapsulated),
};

static void mlx5_ib_dealloc_counters(struct mlx5_ib_dev *dev)
{
	int i;

	for (i = 0; i < dev->num_ports; i++) {
		if (dev->port[i].cnts.set_id_valid)
			mlx5_core_dealloc_q_counter(dev->mdev,
						    dev->port[i].cnts.set_id);
		kfree(dev->port[i].cnts.names);
		kfree(dev->port[i].cnts.offsets);
	}
}

static int __mlx5_ib_alloc_counters(struct mlx5_ib_dev *dev,
				    struct mlx5_ib_counters *cnts)
{
	u32 num_counters;

	num_counters = ARRAY_SIZE(basic_q_cnts);

	if (MLX5_CAP_GEN(dev->mdev, out_of_seq_cnt))
		num_counters += ARRAY_SIZE(out_of_seq_q_cnts);

	if (MLX5_CAP_GEN(dev->mdev, retransmission_q_counters))
		num_counters += ARRAY_SIZE(retrans_q_cnts);

	if (MLX5_CAP_GEN(dev->mdev, enhanced_error_q_counters))
		num_counters += ARRAY_SIZE(extended_err_cnts);

	cnts->num_q_counters = num_counters;

	if (MLX5_CAP_GEN(dev->mdev, cc_query_allowed)) {
		cnts->num_cong_counters = ARRAY_SIZE(cong_cnts);
		num_counters += ARRAY_SIZE(cong_cnts);
	}
	if (MLX5_CAP_PCAM_FEATURE(dev->mdev, rx_icrc_encapsulated_counter)) {
		cnts->num_ext_ppcnt_counters = ARRAY_SIZE(ext_ppcnt_cnts);
		num_counters += ARRAY_SIZE(ext_ppcnt_cnts);
	}
	cnts->names = kcalloc(num_counters, sizeof(cnts->names), GFP_KERNEL);
	if (!cnts->names)
		return -ENOMEM;

	cnts->offsets = kcalloc(num_counters,
				sizeof(cnts->offsets), GFP_KERNEL);
	if (!cnts->offsets)
		goto err_names;

	return 0;

err_names:
	kfree(cnts->names);
	cnts->names = NULL;
	return -ENOMEM;
}

static void mlx5_ib_fill_counters(struct mlx5_ib_dev *dev,
				  const char **names,
				  size_t *offsets)
{
	int i;
	int j = 0;

	for (i = 0; i < ARRAY_SIZE(basic_q_cnts); i++, j++) {
		names[j] = basic_q_cnts[i].name;
		offsets[j] = basic_q_cnts[i].offset;
	}

	if (