1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859606162636465666768697071727374757677787980818283848586878889909192939495969798991001011021031041051061071081091101111121131141151161171181191201211221231241251261271281291301311321331341351361371381391401411421431441451461471481491501511521531541551561571581591601611621631641651661671681691701711721731741751761771781791801811821831841851861871881891901911921931941951961971981992002012022032042052062072082092102112122132142152162172182192202212222232242252262272282292302312322332342352362372382392402412422432442452462472482492502512522532542552562572582592602612622632642652662672682692702712722732742752762772782792802812822832842852862872882892902912922932942952962972982993003013023033043053063073083093103113123133143153163173183193203213223233243253263273283293303313323333343353363373383393403413423433443453463473483493503513523533543553563573583593603613623633643653663673683693703713723733743753763773783793803813823833843853863873883893903913923933943953963973983994004014024034044054064074084094104114124134144154164174184194204214224234244254264274284294304314324334344354364374384394404414424434444454464474484494504514524534544554564574584594604614624634644654664674684694704714724734744754764774784794804814824834844854864874884894904914924934944954964974984995005015025035045055065075085095105115125135145155165175185195205215225235245255265275285295305315325335345355365375385395405415425435445455465475485495505515525535545555565575585595605615625635645655665675685695705715725735745755765775785795805815825835845855865875885895905915925935945955965975985996006016026036046056066076086096106116126136146156166176186196206216226236246256266276286296306316326336346356366376386396406416426436446456466476486496506516526536546556566576586596606616626636646656666676686696706716726736746756766776786796806816826836846856866876886896906916926936946956966976986997007017027037047057067077087097107117127137147157167177187197207217227237247257267277287297307317327337347357367377387397407417427437447457467477487497507517527537547557567577587597607617627637647657667677687697707717727737747757767777787797807817827837847857867877887897907917927937947957967977987998008018028038048058068078088098108118128138148158168178188198208218228238248258268278288298308318328338348358368378388398408418428438448458468478488498508518528538548558568578588598608618628638648658668678688698708718728738748758768778788798808818828838848858868878888898908918928938948958968978988999009019029039049059069079089099109119129139149159169179189199209219229239249259269279289299309319329339349359369379389399409419429439449459469479489499509519529539549559569579589599609619629639649659669679689699709719729739749759769779789799809819829839849859869879889899909919929939949959969979989991000100110021003100410051006100710081009101010111012101310141015101610171018101910201021102210231024102510261027102810291030103110321033103410351036103710381039104010411042104310441045104610471048104910501051105210531054105510561057105810591060106110621063106410651066106710681069107010711072107310741075107610771078107910801081108210831084108510861087108810891090109110921093109410951096109710981099110011011102110311041105110611071108110911101111111211131114111511161117111811191120112111221123112411251126112711281129113011311132113311341135113611371138113911401141114211431144114511461147114811491150115111521153115411551156115711581159116011611162116311641165116611671168116911701171117211731174117511761177117811791180118111821183118411851186118711881189119011911192119311941195119611971198119912001201120212031204120512061207120812091210121112121213121412151216121712181219122012211222122312241225122612271228122912301231123212331234123512361237123812391240124112421243124412451246124712481249125012511252125312541255125612571258125912601261126212631264126512661267126812691270127112721273127412751276127712781279128012811282128312841285128612871288128912901291129212931294129512961297129812991300130113021303130413051306130713081309131013111312131313141315131613171318131913201321132213231324132513261327132813291330133113321333133413351336133713381339134013411342134313441345134613471348134913501351135213531354135513561357135813591360136113621363136413651366136713681369137013711372137313741375137613771378137913801381138213831384138513861387138813891390139113921393139413951396139713981399140014011402140314041405140614071408140914101411141214131414141514161417141814191420142114221423142414251426142714281429143014311432143314341435143614371438143914401441144214431444144514461447144814491450145114521453145414551456145714581459146014611462146314641465146614671468146914701471147214731474147514761477147814791480148114821483148414851486148714881489149014911492149314941495149614971498149915001501150215031504150515061507150815091510151115121513151415151516151715181519152015211522152315241525152615271528152915301531153215331534153515361537153815391540154115421543154415451546154715481549155015511552155315541555155615571558155915601561156215631564156515661567156815691570157115721573157415751576157715781579158015811582158315841585158615871588158915901591159215931594159515961597159815991600160116021603160416051606160716081609161016111612161316141615161616171618161916201621162216231624162516261627162816291630163116321633163416351636163716381639164016411642164316441645164616471648164916501651165216531654165516561657165816591660166116621663166416651666166716681669167016711672167316741675167616771678167916801681168216831684168516861687168816891690169116921693169416951696169716981699170017011702170317041705170617071708170917101711171217131714171517161717171817191720172117221723172417251726172717281729173017311732173317341735173617371738173917401741174217431744174517461747174817491750175117521753175417551756175717581759176017611762176317641765176617671768176917701771177217731774177517761777177817791780178117821783178417851786178717881789179017911792179317941795179617971798179918001801180218031804180518061807180818091810181118121813181418151816181718181819182018211822182318241825182618271828182918301831183218331834183518361837183818391840184118421843184418451846184718481849185018511852185318541855185618571858185918601861186218631864186518661867186818691870187118721873187418751876187718781879188018811882188318841885188618871888188918901891189218931894189518961897189818991900190119021903190419051906190719081909191019111912191319141915191619171918191919201921192219231924192519261927192819291930193119321933193419351936193719381939194019411942194319441945194619471948194919501951195219531954195519561957195819591960196119621963196419651966196719681969197019711972197319741975197619771978197919801981198219831984198519861987198819891990199119921993199419951996199719981999200020012002200320042005200620072008200920102011201220132014201520162017201820192020202120222023202420252026202720282029203020312032203320342035203620372038203920402041204220432044204520462047204820492050205120522053205420552056205720582059206020612062206320642065206620672068206920702071207220732074207520762077207820792080208120822083208420852086208720882089209020912092209320942095209620972098209921002101210221032104210521062107210821092110211121122113211421152116211721182119212021212122212321242125212621272128212921302131213221332134213521362137213821392140214121422143214421452146214721482149215021512152215321542155215621572158215921602161216221632164216521662167216821692170217121722173217421752176217721782179218021812182218321842185218621872188218921902191219221932194219521962197219821992200220122022203220422052206220722082209221022112212221322142215221622172218221922202221222222232224222522262227222822292230223122322233223422352236223722382239224022412242224322442245224622472248224922502251225222532254225522562257225822592260226122622263226422652266226722682269227022712272227322742275227622772278227922802281228222832284228522862287228822892290229122922293229422952296229722982299230023012302230323042305230623072308230923102311231223132314231523162317231823192320232123222323232423252326232723282329233023312332233323342335233623372338233923402341234223432344234523462347234823492350235123522353235423552356235723582359236023612362236323642365236623672368236923702371237223732374237523762377237823792380238123822383238423852386238723882389239023912392239323942395239623972398239924002401240224032404240524062407240824092410241124122413241424152416241724182419242024212422242324242425242624272428242924302431243224332434243524362437243824392440244124422443244424452446244724482449245024512452245324542455245624572458245924602461246224632464246524662467246824692470247124722473247424752476247724782479248024812482248324842485248624872488248924902491249224932494249524962497249824992500250125022503250425052506250725082509251025112512251325142515251625172518251925202521252225232524252525262527252825292530253125322533253425352536253725382539254025412542254325442545254625472548254925502551255225532554255525562557255825592560256125622563256425652566256725682569257025712572257325742575257625772578257925802581258225832584258525862587258825892590259125922593259425952596259725982599260026012602260326042605260626072608260926102611261226132614261526162617261826192620262126222623262426252626262726282629263026312632263326342635263626372638263926402641264226432644264526462647264826492650265126522653265426552656265726582659266026612662266326642665266626672668266926702671267226732674267526762677267826792680268126822683268426852686268726882689269026912692269326942695269626972698269927002701270227032704270527062707270827092710271127122713271427152716271727182719272027212722272327242725272627272728272927302731273227332734273527362737273827392740274127422743274427452746274727482749275027512752275327542755275627572758275927602761276227632764276527662767276827692770277127722773277427752776277727782779278027812782278327842785278627872788278927902791279227932794279527962797279827992800280128022803280428052806280728082809281028112812281328142815281628172818281928202821282228232824282528262827282828292830283128322833283428352836283728382839284028412842284328442845284628472848284928502851285228532854285528562857285828592860286128622863286428652866286728682869287028712872287328742875287628772878287928802881288228832884288528862887288828892890289128922893289428952896289728982899290029012902290329042905290629072908290929102911291229132914291529162917291829192920292129222923292429252926292729282929293029312932293329342935293629372938293929402941294229432944294529462947294829492950295129522953295429552956295729582959296029612962296329642965296629672968296929702971297229732974297529762977297829792980298129822983298429852986298729882989299029912992299329942995299629972998299930003001300230033004300530063007300830093010301130123013301430153016301730183019302030213022302330243025302630273028302930303031303230333034303530363037303830393040304130423043304430453046304730483049305030513052305330543055305630573058305930603061306230633064306530663067306830693070307130723073307430753076307730783079308030813082308330843085308630873088308930903091309230933094309530963097309830993100310131023103310431053106310731083109311031113112311331143115311631173118311931203121312231233124312531263127312831293130313131323133313431353136313731383139314031413142314331443145314631473148314931503151315231533154315531563157315831593160316131623163316431653166316731683169317031713172317331743175317631773178317931803181318231833184318531863187318831893190319131923193319431953196319731983199320032013202320332043205320632073208320932103211321232133214321532163217321832193220322132223223322432253226322732283229323032313232323332343235323632373238323932403241324232433244324532463247324832493250325132523253325432553256325732583259326032613262326332643265326632673268326932703271327232733274327532763277327832793280328132823283328432853286328732883289329032913292329332943295329632973298329933003301330233033304330533063307330833093310331133123313331433153316331733183319332033213322332333243325332633273328332933303331333233333334333533363337333833393340334133423343334433453346334733483349335033513352335333543355335633573358335933603361336233633364336533663367336833693370337133723373337433753376337733783379338033813382338333843385338633873388338933903391339233933394339533963397339833993400340134023403340434053406340734083409341034113412341334143415341634173418341934203421342234233424342534263427342834293430343134323433343434353436343734383439344034413442344334443445344634473448344934503451345234533454345534563457345834593460346134623463346434653466346734683469347034713472347334743475347634773478347934803481348234833484348534863487348834893490349134923493349434953496349734983499350035013502350335043505350635073508350935103511351235133514351535163517351835193520352135223523352435253526352735283529353035313532353335343535353635373538353935403541354235433544354535463547354835493550355135523553355435553556355735583559356035613562356335643565356635673568356935703571357235733574357535763577357835793580358135823583358435853586358735883589359035913592359335943595359635973598359936003601360236033604360536063607360836093610361136123613361436153616361736183619362036213622362336243625362636273628362936303631363236333634363536363637363836393640364136423643364436453646364736483649365036513652365336543655365636573658365936603661366236633664366536663667366836693670367136723673367436753676367736783679368036813682368336843685368636873688368936903691369236933694369536963697369836993700370137023703370437053706370737083709371037113712371337143715371637173718371937203721372237233724372537263727372837293730373137323733373437353736373737383739374037413742374337443745374637473748374937503751375237533754375537563757375837593760376137623763376437653766376737683769377037713772377337743775377637773778377937803781378237833784378537863787378837893790379137923793379437953796379737983799380038013802380338043805380638073808380938103811381238133814381538163817381838193820382138223823382438253826382738283829383038313832383338343835383638373838383938403841384238433844384538463847384838493850385138523853385438553856385738583859386038613862386338643865386638673868386938703871387238733874387538763877387838793880388138823883388438853886388738883889389038913892389338943895389638973898389939003901390239033904390539063907390839093910391139123913391439153916391739183919392039213922392339243925392639273928392939303931393239333934393539363937393839393940394139423943394439453946394739483949395039513952395339543955395639573958395939603961396239633964396539663967396839693970397139723973397439753976397739783979398039813982398339843985398639873988398939903991399239933994399539963997399839994000400140024003400440054006400740084009401040114012401340144015401640174018401940204021402240234024402540264027402840294030403140324033403440354036403740384039404040414042404340444045404640474048404940504051405240534054405540564057405840594060406140624063406440654066406740684069407040714072407340744075407640774078407940804081408240834084408540864087408840894090409140924093409440954096409740984099410041014102410341044105410641074108410941104111411241134114411541164117411841194120412141224123412441254126412741284129413041314132413341344135413641374138413941404141414241434144414541464147414841494150415141524153415441554156415741584159416041614162416341644165416641674168416941704171417241734174417541764177417841794180418141824183418441854186418741884189419041914192419341944195419641974198419942004201420242034204420542064207420842094210421142124213421442154216421742184219422042214222422342244225422642274228422942304231423242334234423542364237423842394240424142424243424442454246424742484249425042514252425342544255425642574258425942604261426242634264426542664267426842694270427142724273427442754276427742784279428042814282428342844285428642874288428942904291429242934294429542964297429842994300430143024303430443054306430743084309431043114312431343144315431643174318431943204321432243234324432543264327432843294330433143324333433443354336433743384339434043414342434343444345434643474348434943504351435243534354435543564357435843594360436143624363436443654366436743684369437043714372437343744375437643774378437943804381438243834384438543864387438843894390439143924393439443954396439743984399440044014402440344044405440644074408440944104411441244134414441544164417441844194420442144224423442444254426442744284429443044314432443344344435443644374438443944404441444244434444444544464447444844494450445144524453445444554456445744584459446044614462446344644465446644674468446944704471447244734474447544764477447844794480448144824483448444854486448744884489449044914492449344944495449644974498449945004501450245034504450545064507450845094510451145124513451445154516451745184519452045214522452345244525452645274528452945304531453245334534453545364537453845394540454145424543454445454546454745484549455045514552455345544555455645574558455945604561456245634564456545664567456845694570457145724573457445754576457745784579458045814582458345844585458645874588458945904591459245934594459545964597459845994600460146024603460446054606460746084609461046114612461346144615461646174618461946204621462246234624462546264627462846294630463146324633463446354636463746384639464046414642464346444645464646474648464946504651465246534654465546564657465846594660466146624663466446654666466746684669467046714672467346744675467646774678467946804681468246834684468546864687468846894690469146924693469446954696469746984699470047014702470347044705470647074708470947104711471247134714471547164717471847194720472147224723472447254726472747284729473047314732473347344735473647374738473947404741474247434744474547464747474847494750475147524753475447554756475747584759476047614762476347644765476647674768476947704771477247734774477547764777477847794780478147824783478447854786478747884789479047914792479347944795479647974798479948004801480248034804480548064807480848094810481148124813481448154816481748184819482048214822482348244825482648274828482948304831483248334834483548364837483848394840484148424843484448454846484748484849485048514852485348544855485648574858485948604861486248634864486548664867486848694870487148724873487448754876487748784879488048814882488348844885488648874888488948904891489248934894489548964897489848994900490149024903490449054906490749084909491049114912491349144915491649174918491949204921492249234924492549264927492849294930493149324933493449354936493749384939494049414942494349444945494649474948494949504951495249534954495549564957495849594960496149624963496449654966496749684969497049714972497349744975497649774978497949804981498249834984498549864987498849894990499149924993499449954996499749984999500050015002500350045005500650075008500950105011501250135014501550165017501850195020502150225023502450255026502750285029503050315032503350345035503650375038503950405041504250435044504550465047504850495050505150525053505450555056505750585059506050615062506350645065506650675068506950705071507250735074507550765077507850795080508150825083508450855086508750885089509050915092509350945095509650975098509951005101510251035104510551065107510851095110511151125113511451155116511751185119512051215122512351245125512651275128512951305131513251335134513551365137513851395140514151425143514451455146514751485149515051515152515351545155515651575158515951605161516251635164516551665167516851695170517151725173517451755176517751785179518051815182518351845185518651875188518951905191519251935194519551965197519851995200520152025203520452055206520752085209521052115212521352145215521652175218521952205221522252235224522552265227522852295230523152325233523452355236523752385239524052415242524352445245524652475248524952505251525252535254525552565257525852595260526152625263526452655266526752685269527052715272527352745275527652775278527952805281528252835284528552865287528852895290529152925293529452955296529752985299530053015302530353045305530653075308530953105311531253135314531553165317531853195320532153225323532453255326532753285329533053315332533353345335533653375338533953405341534253435344534553465347534853495350535153525353535453555356535753585359536053615362 |
- // SPDX-License-Identifier: GPL-2.0
- /*
- * fs/f2fs/segment.c
- *
- * Copyright (c) 2012 Samsung Electronics Co., Ltd.
- * http://www.samsung.com/
- */
- #include <linux/fs.h>
- #include <linux/f2fs_fs.h>
- #include <linux/bio.h>
- #include <linux/blkdev.h>
- #include <linux/prefetch.h>
- #include <linux/kthread.h>
- #include <linux/swap.h>
- #include <linux/timer.h>
- #include <linux/freezer.h>
- #include <linux/sched/signal.h>
- #include "f2fs.h"
- #include "segment.h"
- #include "node.h"
- #include "gc.h"
- #include <trace/events/f2fs.h>
- #define __reverse_ffz(x) __reverse_ffs(~(x))
- static struct kmem_cache *discard_entry_slab;
- static struct kmem_cache *discard_cmd_slab;
- static struct kmem_cache *sit_entry_set_slab;
- static struct kmem_cache *inmem_entry_slab;
- static unsigned long __reverse_ulong(unsigned char *str)
- {
- unsigned long tmp = 0;
- int shift = 24, idx = 0;
- #if BITS_PER_LONG == 64
- shift = 56;
- #endif
- while (shift >= 0) {
- tmp |= (unsigned long)str[idx++] << shift;
- shift -= BITS_PER_BYTE;
- }
- return tmp;
- }
- /*
- * __reverse_ffs is copied from include/asm-generic/bitops/__ffs.h since
- * MSB and LSB are reversed in a byte by f2fs_set_bit.
- */
- static inline unsigned long __reverse_ffs(unsigned long word)
- {
- int num = 0;
- #if BITS_PER_LONG == 64
- if ((word & 0xffffffff00000000UL) == 0)
- num += 32;
- else
- word >>= 32;
- #endif
- if ((word & 0xffff0000) == 0)
- num += 16;
- else
- word >>= 16;
- if ((word & 0xff00) == 0)
- num += 8;
- else
- word >>= 8;
- if ((word & 0xf0) == 0)
- num += 4;
- else
- word >>= 4;
- if ((word & 0xc) == 0)
- num += 2;
- else
- word >>= 2;
- if ((word & 0x2) == 0)
- num += 1;
- return num;
- }
- /*
- * __find_rev_next(_zero)_bit is copied from lib/find_next_bit.c because
- * f2fs_set_bit makes MSB and LSB reversed in a byte.
- * @size must be integral times of unsigned long.
- * Example:
- * MSB <--> LSB
- * f2fs_set_bit(0, bitmap) => 1000 0000
- * f2fs_set_bit(7, bitmap) => 0000 0001
- */
- static unsigned long __find_rev_next_bit(const unsigned long *addr,
- unsigned long size, unsigned long offset)
- {
- const unsigned long *p = addr + BIT_WORD(offset);
- unsigned long result = size;
- unsigned long tmp;
- if (offset >= size)
- return size;
- size -= (offset & ~(BITS_PER_LONG - 1));
- offset %= BITS_PER_LONG;
- while (1) {
- if (*p == 0)
- goto pass;
- tmp = __reverse_ulong((unsigned char *)p);
- tmp &= ~0UL >> offset;
- if (size < BITS_PER_LONG)
- tmp &= (~0UL << (BITS_PER_LONG - size));
- if (tmp)
- goto found;
- pass:
- if (size <= BITS_PER_LONG)
- break;
- size -= BITS_PER_LONG;
- offset = 0;
- p++;
- }
- return result;
- found:
- return result - size + __reverse_ffs(tmp);
- }
- static unsigned long __find_rev_next_zero_bit(const unsigned long *addr,
- unsigned long size, unsigned long offset)
- {
- const unsigned long *p = addr + BIT_WORD(offset);
- unsigned long result = size;
- unsigned long tmp;
- if (offset >= size)
- return size;
- size -= (offset & ~(BITS_PER_LONG - 1));
- offset %= BITS_PER_LONG;
- while (1) {
- if (*p == ~0UL)
- goto pass;
- tmp = __reverse_ulong((unsigned char *)p);
- if (offset)
- tmp |= ~0UL << (BITS_PER_LONG - offset);
- if (size < BITS_PER_LONG)
- tmp |= ~0UL >> size;
- if (tmp != ~0UL)
- goto found;
- pass:
- if (size <= BITS_PER_LONG)
- break;
- size -= BITS_PER_LONG;
- offset = 0;
- p++;
- }
- return result;
- found:
- return result - size + __reverse_ffz(tmp);
- }
- bool f2fs_need_SSR(struct f2fs_sb_info *sbi)
- {
- int node_secs = get_blocktype_secs(sbi, F2FS_DIRTY_NODES);
- int dent_secs = get_blocktype_secs(sbi, F2FS_DIRTY_DENTS);
- int imeta_secs = get_blocktype_secs(sbi, F2FS_DIRTY_IMETA);
- if (f2fs_lfs_mode(sbi))
- return false;
- if (sbi->gc_mode == GC_URGENT_HIGH)
- return true;
- if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
- return true;
- return free_sections(sbi) <= (node_secs + 2 * dent_secs + imeta_secs +
- SM_I(sbi)->min_ssr_sections + reserved_sections(sbi));
- }
- void f2fs_register_inmem_page(struct inode *inode, struct page *page)
- {
- struct inmem_pages *new;
- set_page_private_atomic(page);
- new = f2fs_kmem_cache_alloc(inmem_entry_slab, GFP_NOFS);
- /* add atomic page indices to the list */
- new->page = page;
- INIT_LIST_HEAD(&new->list);
- /* increase reference count with clean state */
- get_page(page);
- mutex_lock(&F2FS_I(inode)->inmem_lock);
- list_add_tail(&new->list, &F2FS_I(inode)->inmem_pages);
- inc_page_count(F2FS_I_SB(inode), F2FS_INMEM_PAGES);
- mutex_unlock(&F2FS_I(inode)->inmem_lock);
- trace_f2fs_register_inmem_page(page, INMEM);
- }
- static int __revoke_inmem_pages(struct inode *inode,
- struct list_head *head, bool drop, bool recover,
- bool trylock)
- {
- struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- struct inmem_pages *cur, *tmp;
- int err = 0;
- list_for_each_entry_safe(cur, tmp, head, list) {
- struct page *page = cur->page;
- if (drop)
- trace_f2fs_commit_inmem_page(page, INMEM_DROP);
- if (trylock) {
- /*
- * to avoid deadlock in between page lock and
- * inmem_lock.
- */
- if (!trylock_page(page))
- continue;
- } else {
- lock_page(page);
- }
- f2fs_wait_on_page_writeback(page, DATA, true, true);
- if (recover) {
- struct dnode_of_data dn;
- struct node_info ni;
- trace_f2fs_commit_inmem_page(page, INMEM_REVOKE);
- retry:
- set_new_dnode(&dn, inode, NULL, NULL, 0);
- err = f2fs_get_dnode_of_data(&dn, page->index,
- LOOKUP_NODE);
- if (err) {
- if (err == -ENOMEM) {
- congestion_wait(BLK_RW_ASYNC,
- DEFAULT_IO_TIMEOUT);
- cond_resched();
- goto retry;
- }
- err = -EAGAIN;
- goto next;
- }
- err = f2fs_get_node_info(sbi, dn.nid, &ni, false);
- if (err) {
- f2fs_put_dnode(&dn);
- return err;
- }
- if (cur->old_addr == NEW_ADDR) {
- f2fs_invalidate_blocks(sbi, dn.data_blkaddr);
- f2fs_update_data_blkaddr(&dn, NEW_ADDR);
- } else
- f2fs_replace_block(sbi, &dn, dn.data_blkaddr,
- cur->old_addr, ni.version, true, true);
- f2fs_put_dnode(&dn);
- }
- next:
- /* we don't need to invalidate this in the sccessful status */
- if (drop || recover) {
- ClearPageUptodate(page);
- clear_page_private_gcing(page);
- }
- detach_page_private(page);
- set_page_private(page, 0);
- f2fs_put_page(page, 1);
- list_del(&cur->list);
- kmem_cache_free(inmem_entry_slab, cur);
- dec_page_count(F2FS_I_SB(inode), F2FS_INMEM_PAGES);
- }
- return err;
- }
- void f2fs_drop_inmem_pages_all(struct f2fs_sb_info *sbi, bool gc_failure)
- {
- struct list_head *head = &sbi->inode_list[ATOMIC_FILE];
- struct inode *inode;
- struct f2fs_inode_info *fi;
- unsigned int count = sbi->atomic_files;
- unsigned int looped = 0;
- next:
- spin_lock(&sbi->inode_lock[ATOMIC_FILE]);
- if (list_empty(head)) {
- spin_unlock(&sbi->inode_lock[ATOMIC_FILE]);
- return;
- }
- fi = list_first_entry(head, struct f2fs_inode_info, inmem_ilist);
- inode = igrab(&fi->vfs_inode);
- if (inode)
- list_move_tail(&fi->inmem_ilist, head);
- spin_unlock(&sbi->inode_lock[ATOMIC_FILE]);
- if (inode) {
- if (gc_failure) {
- if (!fi->i_gc_failures[GC_FAILURE_ATOMIC])
- goto skip;
- }
- set_inode_flag(inode, FI_ATOMIC_REVOKE_REQUEST);
- f2fs_drop_inmem_pages(inode);
- skip:
- iput(inode);
- }
- congestion_wait(BLK_RW_ASYNC, DEFAULT_IO_TIMEOUT);
- cond_resched();
- if (gc_failure) {
- if (++looped >= count)
- return;
- }
- goto next;
- }
- void f2fs_drop_inmem_pages(struct inode *inode)
- {
- struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- struct f2fs_inode_info *fi = F2FS_I(inode);
- do {
- mutex_lock(&fi->inmem_lock);
- if (list_empty(&fi->inmem_pages)) {
- fi->i_gc_failures[GC_FAILURE_ATOMIC] = 0;
- spin_lock(&sbi->inode_lock[ATOMIC_FILE]);
- if (!list_empty(&fi->inmem_ilist))
- list_del_init(&fi->inmem_ilist);
- if (f2fs_is_atomic_file(inode)) {
- clear_inode_flag(inode, FI_ATOMIC_FILE);
- sbi->atomic_files--;
- }
- spin_unlock(&sbi->inode_lock[ATOMIC_FILE]);
- mutex_unlock(&fi->inmem_lock);
- break;
- }
- __revoke_inmem_pages(inode, &fi->inmem_pages,
- true, false, true);
- mutex_unlock(&fi->inmem_lock);
- } while (1);
- }
- void f2fs_drop_inmem_page(struct inode *inode, struct page *page)
- {
- struct f2fs_inode_info *fi = F2FS_I(inode);
- struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- struct list_head *head = &fi->inmem_pages;
- struct inmem_pages *cur = NULL;
- f2fs_bug_on(sbi, !page_private_atomic(page));
- mutex_lock(&fi->inmem_lock);
- list_for_each_entry(cur, head, list) {
- if (cur->page == page)
- break;
- }
- f2fs_bug_on(sbi, list_empty(head) || cur->page != page);
- list_del(&cur->list);
- mutex_unlock(&fi->inmem_lock);
- dec_page_count(sbi, F2FS_INMEM_PAGES);
- kmem_cache_free(inmem_entry_slab, cur);
- ClearPageUptodate(page);
- clear_page_private_atomic(page);
- f2fs_put_page(page, 0);
- detach_page_private(page);
- set_page_private(page, 0);
- trace_f2fs_commit_inmem_page(page, INMEM_INVALIDATE);
- }
- static int __f2fs_commit_inmem_pages(struct inode *inode)
- {
- struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- struct f2fs_inode_info *fi = F2FS_I(inode);
- struct inmem_pages *cur, *tmp;
- struct f2fs_io_info fio = {
- .sbi = sbi,
- .ino = inode->i_ino,
- .type = DATA,
- .op = REQ_OP_WRITE,
- .op_flags = REQ_SYNC | REQ_PRIO,
- .io_type = FS_DATA_IO,
- };
- struct list_head revoke_list;
- bool submit_bio = false;
- int err = 0;
- INIT_LIST_HEAD(&revoke_list);
- list_for_each_entry_safe(cur, tmp, &fi->inmem_pages, list) {
- struct page *page = cur->page;
- lock_page(page);
- if (page->mapping == inode->i_mapping) {
- trace_f2fs_commit_inmem_page(page, INMEM);
- f2fs_wait_on_page_writeback(page, DATA, true, true);
- set_page_dirty(page);
- if (clear_page_dirty_for_io(page)) {
- inode_dec_dirty_pages(inode);
- f2fs_remove_dirty_inode(inode);
- }
- retry:
- fio.page = page;
- fio.old_blkaddr = NULL_ADDR;
- fio.encrypted_page = NULL;
- fio.need_lock = LOCK_DONE;
- err = f2fs_do_write_data_page(&fio);
- if (err) {
- if (err == -ENOMEM) {
- congestion_wait(BLK_RW_ASYNC,
- DEFAULT_IO_TIMEOUT);
- cond_resched();
- goto retry;
- }
- unlock_page(page);
- break;
- }
- /* record old blkaddr for revoking */
- cur->old_addr = fio.old_blkaddr;
- submit_bio = true;
- }
- unlock_page(page);
- list_move_tail(&cur->list, &revoke_list);
- }
- if (submit_bio)
- f2fs_submit_merged_write_cond(sbi, inode, NULL, 0, DATA);
- if (err) {
- /*
- * try to revoke all committed pages, but still we could fail
- * due to no memory or other reason, if that happened, EAGAIN
- * will be returned, which means in such case, transaction is
- * already not integrity, caller should use journal to do the
- * recovery or rewrite & commit last transaction. For other
- * error number, revoking was done by filesystem itself.
- */
- err = __revoke_inmem_pages(inode, &revoke_list,
- false, true, false);
- /* drop all uncommitted pages */
- __revoke_inmem_pages(inode, &fi->inmem_pages,
- true, false, false);
- } else {
- __revoke_inmem_pages(inode, &revoke_list,
- false, false, false);
- }
- return err;
- }
- int f2fs_commit_inmem_pages(struct inode *inode)
- {
- struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- struct f2fs_inode_info *fi = F2FS_I(inode);
- int err;
- f2fs_balance_fs(sbi, true);
- f2fs_down_write(&fi->i_gc_rwsem[WRITE]);
- f2fs_lock_op(sbi);
- set_inode_flag(inode, FI_ATOMIC_COMMIT);
- mutex_lock(&fi->inmem_lock);
- err = __f2fs_commit_inmem_pages(inode);
- mutex_unlock(&fi->inmem_lock);
- clear_inode_flag(inode, FI_ATOMIC_COMMIT);
- f2fs_unlock_op(sbi);
- f2fs_up_write(&fi->i_gc_rwsem[WRITE]);
- return err;
- }
- /*
- * This function balances dirty node and dentry pages.
- * In addition, it controls garbage collection.
- */
- void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need)
- {
- if (time_to_inject(sbi, FAULT_CHECKPOINT)) {
- f2fs_show_injection_info(sbi, FAULT_CHECKPOINT);
- f2fs_stop_checkpoint(sbi, false);
- }
- /* balance_fs_bg is able to be pending */
- if (need && excess_cached_nats(sbi))
- f2fs_balance_fs_bg(sbi, false);
- if (!f2fs_is_checkpoint_ready(sbi))
- return;
- /*
- * We should do GC or end up with checkpoint, if there are so many dirty
- * dir/node pages without enough free segments.
- */
- if (has_not_enough_free_secs(sbi, 0, 0)) {
- if (test_opt(sbi, GC_MERGE) && sbi->gc_thread &&
- sbi->gc_thread->f2fs_gc_task) {
- DEFINE_WAIT(wait);
- prepare_to_wait(&sbi->gc_thread->fggc_wq, &wait,
- TASK_UNINTERRUPTIBLE);
- wake_up(&sbi->gc_thread->gc_wait_queue_head);
- io_schedule();
- finish_wait(&sbi->gc_thread->fggc_wq, &wait);
- } else {
- f2fs_down_write(&sbi->gc_lock);
- f2fs_gc(sbi, false, false, false, NULL_SEGNO);
- }
- }
- }
- void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi, bool from_bg)
- {
- if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
- return;
- /* try to shrink extent cache when there is no enough memory */
- if (!f2fs_available_free_memory(sbi, EXTENT_CACHE))
- f2fs_shrink_extent_tree(sbi, EXTENT_CACHE_SHRINK_NUMBER);
- /* check the # of cached NAT entries */
- if (!f2fs_available_free_memory(sbi, NAT_ENTRIES))
- f2fs_try_to_free_nats(sbi, NAT_ENTRY_PER_BLOCK);
- if (!f2fs_available_free_memory(sbi, FREE_NIDS))
- f2fs_try_to_free_nids(sbi, MAX_FREE_NIDS);
- else
- f2fs_build_free_nids(sbi, false, false);
- if (excess_dirty_nats(sbi) || excess_dirty_nodes(sbi) ||
- excess_prefree_segs(sbi))
- goto do_sync;
- /* there is background inflight IO or foreground operation recently */
- if (is_inflight_io(sbi, REQ_TIME) ||
- (!f2fs_time_over(sbi, REQ_TIME) && f2fs_rwsem_is_locked(&sbi->cp_rwsem)))
- return;
- /* exceed periodical checkpoint timeout threshold */
- if (f2fs_time_over(sbi, CP_TIME))
- goto do_sync;
- /* checkpoint is the only way to shrink partial cached entries */
- if (f2fs_available_free_memory(sbi, NAT_ENTRIES) ||
- f2fs_available_free_memory(sbi, INO_ENTRIES))
- return;
- do_sync:
- if (test_opt(sbi, DATA_FLUSH) && from_bg) {
- struct blk_plug plug;
- mutex_lock(&sbi->flush_lock);
- blk_start_plug(&plug);
- f2fs_sync_dirty_inodes(sbi, FILE_INODE);
- blk_finish_plug(&plug);
- mutex_unlock(&sbi->flush_lock);
- }
- f2fs_sync_fs(sbi->sb, true);
- stat_inc_bg_cp_count(sbi->stat_info);
- }
- static int __submit_flush_wait(struct f2fs_sb_info *sbi,
- struct block_device *bdev)
- {
- int ret = blkdev_issue_flush(bdev, GFP_NOFS);
- trace_f2fs_issue_flush(bdev, test_opt(sbi, NOBARRIER),
- test_opt(sbi, FLUSH_MERGE), ret);
- return ret;
- }
- static int submit_flush_wait(struct f2fs_sb_info *sbi, nid_t ino)
- {
- int ret = 0;
- int i;
- if (!f2fs_is_multi_device(sbi))
- return __submit_flush_wait(sbi, sbi->sb->s_bdev);
- for (i = 0; i < sbi->s_ndevs; i++) {
- if (!f2fs_is_dirty_device(sbi, ino, i, FLUSH_INO))
- continue;
- ret = __submit_flush_wait(sbi, FDEV(i).bdev);
- if (ret)
- break;
- }
- return ret;
- }
- static int issue_flush_thread(void *data)
- {
- struct f2fs_sb_info *sbi = data;
- struct flush_cmd_control *fcc = SM_I(sbi)->fcc_info;
- wait_queue_head_t *q = &fcc->flush_wait_queue;
- repeat:
- if (kthread_should_stop())
- return 0;
- if (!llist_empty(&fcc->issue_list)) {
- struct flush_cmd *cmd, *next;
- int ret;
- fcc->dispatch_list = llist_del_all(&fcc->issue_list);
- fcc->dispatch_list = llist_reverse_order(fcc->dispatch_list);
- cmd = llist_entry(fcc->dispatch_list, struct flush_cmd, llnode);
- ret = submit_flush_wait(sbi, cmd->ino);
- atomic_inc(&fcc->issued_flush);
- llist_for_each_entry_safe(cmd, next,
- fcc->dispatch_list, llnode) {
- cmd->ret = ret;
- complete(&cmd->wait);
- }
- fcc->dispatch_list = NULL;
- }
- wait_event_interruptible(*q,
- kthread_should_stop() || !llist_empty(&fcc->issue_list));
- goto repeat;
- }
- int f2fs_issue_flush(struct f2fs_sb_info *sbi, nid_t ino)
- {
- struct flush_cmd_control *fcc = SM_I(sbi)->fcc_info;
- struct flush_cmd cmd;
- int ret;
- if (test_opt(sbi, NOBARRIER))
- return 0;
- if (!test_opt(sbi, FLUSH_MERGE)) {
- atomic_inc(&fcc->queued_flush);
- ret = submit_flush_wait(sbi, ino);
- atomic_dec(&fcc->queued_flush);
- atomic_inc(&fcc->issued_flush);
- return ret;
- }
- if (atomic_inc_return(&fcc->queued_flush) == 1 ||
- f2fs_is_multi_device(sbi)) {
- ret = submit_flush_wait(sbi, ino);
- atomic_dec(&fcc->queued_flush);
- atomic_inc(&fcc->issued_flush);
- return ret;
- }
- cmd.ino = ino;
- init_completion(&cmd.wait);
- llist_add(&cmd.llnode, &fcc->issue_list);
- /*
- * update issue_list before we wake up issue_flush thread, this
- * smp_mb() pairs with another barrier in ___wait_event(), see
- * more details in comments of waitqueue_active().
- */
- smp_mb();
- if (waitqueue_active(&fcc->flush_wait_queue))
- wake_up(&fcc->flush_wait_queue);
- if (fcc->f2fs_issue_flush) {
- wait_for_completion(&cmd.wait);
- atomic_dec(&fcc->queued_flush);
- } else {
- struct llist_node *list;
- list = llist_del_all(&fcc->issue_list);
- if (!list) {
- wait_for_completion(&cmd.wait);
- atomic_dec(&fcc->queued_flush);
- } else {
- struct flush_cmd *tmp, *next;
- ret = submit_flush_wait(sbi, ino);
- llist_for_each_entry_safe(tmp, next, list, llnode) {
- if (tmp == &cmd) {
- cmd.ret = ret;
- atomic_dec(&fcc->queued_flush);
- continue;
- }
- tmp->ret = ret;
- complete(&tmp->wait);
- }
- }
- }
- return cmd.ret;
- }
- int f2fs_create_flush_cmd_control(struct f2fs_sb_info *sbi)
- {
- dev_t dev = sbi->sb->s_bdev->bd_dev;
- struct flush_cmd_control *fcc;
- int err = 0;
- if (SM_I(sbi)->fcc_info) {
- fcc = SM_I(sbi)->fcc_info;
- if (fcc->f2fs_issue_flush)
- return err;
- goto init_thread;
- }
- fcc = f2fs_kzalloc(sbi, sizeof(struct flush_cmd_control), GFP_KERNEL);
- if (!fcc)
- return -ENOMEM;
- atomic_set(&fcc->issued_flush, 0);
- atomic_set(&fcc->queued_flush, 0);
- init_waitqueue_head(&fcc->flush_wait_queue);
- init_llist_head(&fcc->issue_list);
- SM_I(sbi)->fcc_info = fcc;
- if (!test_opt(sbi, FLUSH_MERGE))
- return err;
- init_thread:
- fcc->f2fs_issue_flush = kthread_run(issue_flush_thread, sbi,
- "f2fs_flush-%u:%u", MAJOR(dev), MINOR(dev));
- if (IS_ERR(fcc->f2fs_issue_flush)) {
- err = PTR_ERR(fcc->f2fs_issue_flush);
- kfree(fcc);
- SM_I(sbi)->fcc_info = NULL;
- return err;
- }
- return err;
- }
- void f2fs_destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free)
- {
- struct flush_cmd_control *fcc = SM_I(sbi)->fcc_info;
- if (fcc && fcc->f2fs_issue_flush) {
- struct task_struct *flush_thread = fcc->f2fs_issue_flush;
- fcc->f2fs_issue_flush = NULL;
- kthread_stop(flush_thread);
- }
- if (free) {
- kfree(fcc);
- SM_I(sbi)->fcc_info = NULL;
- }
- }
- int f2fs_flush_device_cache(struct f2fs_sb_info *sbi)
- {
- int ret = 0, i;
- if (!f2fs_is_multi_device(sbi))
- return 0;
- if (test_opt(sbi, NOBARRIER))
- return 0;
- for (i = 1; i < sbi->s_ndevs; i++) {
- if (!f2fs_test_bit(i, (char *)&sbi->dirty_device))
- continue;
- ret = __submit_flush_wait(sbi, FDEV(i).bdev);
- if (ret)
- break;
- spin_lock(&sbi->dev_lock);
- f2fs_clear_bit(i, (char *)&sbi->dirty_device);
- spin_unlock(&sbi->dev_lock);
- }
- return ret;
- }
- static void __locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno,
- enum dirty_type dirty_type)
- {
- struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
- /* need not be added */
- if (IS_CURSEG(sbi, segno))
- return;
- if (!test_and_set_bit(segno, dirty_i->dirty_segmap[dirty_type]))
- dirty_i->nr_dirty[dirty_type]++;
- if (dirty_type == DIRTY) {
- struct seg_entry *sentry = get_seg_entry(sbi, segno);
- enum dirty_type t = sentry->type;
- if (unlikely(t >= DIRTY)) {
- f2fs_bug_on(sbi, 1);
- return;
- }
- if (!test_and_set_bit(segno, dirty_i->dirty_segmap[t]))
- dirty_i->nr_dirty[t]++;
- if (__is_large_section(sbi)) {
- unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
- block_t valid_blocks =
- get_valid_blocks(sbi, segno, true);
- f2fs_bug_on(sbi, unlikely(!valid_blocks ||
- valid_blocks == BLKS_PER_SEC(sbi)));
- if (!IS_CURSEC(sbi, secno))
- set_bit(secno, dirty_i->dirty_secmap);
- }
- }
- }
- static void __remove_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno,
- enum dirty_type dirty_type)
- {
- struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
- block_t valid_blocks;
- if (test_and_clear_bit(segno, dirty_i->dirty_segmap[dirty_type]))
- dirty_i->nr_dirty[dirty_type]--;
- if (dirty_type == DIRTY) {
- struct seg_entry *sentry = get_seg_entry(sbi, segno);
- enum dirty_type t = sentry->type;
- if (test_and_clear_bit(segno, dirty_i->dirty_segmap[t]))
- dirty_i->nr_dirty[t]--;
- valid_blocks = get_valid_blocks(sbi, segno, true);
- if (valid_blocks == 0) {
- clear_bit(GET_SEC_FROM_SEG(sbi, segno),
- dirty_i->victim_secmap);
- #ifdef CONFIG_F2FS_CHECK_FS
- clear_bit(segno, SIT_I(sbi)->invalid_segmap);
- #endif
- }
- if (__is_large_section(sbi)) {
- unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
- if (!valid_blocks ||
- valid_blocks == BLKS_PER_SEC(sbi)) {
- clear_bit(secno, dirty_i->dirty_secmap);
- return;
- }
- if (!IS_CURSEC(sbi, secno))
- set_bit(secno, dirty_i->dirty_secmap);
- }
- }
- }
- /*
- * Should not occur error such as -ENOMEM.
- * Adding dirty entry into seglist is not critical operation.
- * If a given segment is one of current working segments, it won't be added.
- */
- static void locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno)
- {
- struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
- unsigned short valid_blocks, ckpt_valid_blocks;
- unsigned int usable_blocks;
- if (segno == NULL_SEGNO || IS_CURSEG(sbi, segno))
- return;
- usable_blocks = f2fs_usable_blks_in_seg(sbi, segno);
- mutex_lock(&dirty_i->seglist_lock);
- valid_blocks = get_valid_blocks(sbi, segno, false);
- ckpt_valid_blocks = get_ckpt_valid_blocks(sbi, segno, false);
- if (valid_blocks == 0 && (!is_sbi_flag_set(sbi, SBI_CP_DISABLED) ||
- ckpt_valid_blocks == usable_blocks)) {
- __locate_dirty_segment(sbi, segno, PRE);
- __remove_dirty_segment(sbi, segno, DIRTY);
- } else if (valid_blocks < usable_blocks) {
- __locate_dirty_segment(sbi, segno, DIRTY);
- } else {
- /* Recovery routine with SSR needs this */
- __remove_dirty_segment(sbi, segno, DIRTY);
- }
- mutex_unlock(&dirty_i->seglist_lock);
- }
- /* This moves currently empty dirty blocks to prefree. Must hold seglist_lock */
- void f2fs_dirty_to_prefree(struct f2fs_sb_info *sbi)
- {
- struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
- unsigned int segno;
- mutex_lock(&dirty_i->seglist_lock);
- for_each_set_bit(segno, dirty_i->dirty_segmap[DIRTY], MAIN_SEGS(sbi)) {
- if (get_valid_blocks(sbi, segno, false))
- continue;
- if (IS_CURSEG(sbi, segno))
- continue;
- __locate_dirty_segment(sbi, segno, PRE);
- __remove_dirty_segment(sbi, segno, DIRTY);
- }
- mutex_unlock(&dirty_i->seglist_lock);
- }
- block_t f2fs_get_unusable_blocks(struct f2fs_sb_info *sbi)
- {
- int ovp_hole_segs =
- (overprovision_segments(sbi) - reserved_segments(sbi));
- block_t ovp_holes = ovp_hole_segs << sbi->log_blocks_per_seg;
- struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
- block_t holes[2] = {0, 0}; /* DATA and NODE */
- block_t unusable;
- struct seg_entry *se;
- unsigned int segno;
- mutex_lock(&dirty_i->seglist_lock);
- for_each_set_bit(segno, dirty_i->dirty_segmap[DIRTY], MAIN_SEGS(sbi)) {
- se = get_seg_entry(sbi, segno);
- if (IS_NODESEG(se->type))
- holes[NODE] += f2fs_usable_blks_in_seg(sbi, segno) -
- se->valid_blocks;
- else
- holes[DATA] += f2fs_usable_blks_in_seg(sbi, segno) -
- se->valid_blocks;
- }
- mutex_unlock(&dirty_i->seglist_lock);
- unusable = holes[DATA] > holes[NODE] ? holes[DATA] : holes[NODE];
- if (unusable > ovp_holes)
- return unusable - ovp_holes;
- return 0;
- }
- int f2fs_disable_cp_again(struct f2fs_sb_info *sbi, block_t unusable)
- {
- int ovp_hole_segs =
- (overprovision_segments(sbi) - reserved_segments(sbi));
- if (unusable > F2FS_OPTION(sbi).unusable_cap)
- return -EAGAIN;
- if (is_sbi_flag_set(sbi, SBI_CP_DISABLED_QUICK) &&
- dirty_segments(sbi) > ovp_hole_segs)
- return -EAGAIN;
- return 0;
- }
- /* This is only used by SBI_CP_DISABLED */
- static unsigned int get_free_segment(struct f2fs_sb_info *sbi)
- {
- struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
- unsigned int segno = 0;
- mutex_lock(&dirty_i->seglist_lock);
- for_each_set_bit(segno, dirty_i->dirty_segmap[DIRTY], MAIN_SEGS(sbi)) {
- if (get_valid_blocks(sbi, segno, false))
- continue;
- if (get_ckpt_valid_blocks(sbi, segno, false))
- continue;
- mutex_unlock(&dirty_i->seglist_lock);
- return segno;
- }
- mutex_unlock(&dirty_i->seglist_lock);
- return NULL_SEGNO;
- }
- static struct discard_cmd *__create_discard_cmd(struct f2fs_sb_info *sbi,
- struct block_device *bdev, block_t lstart,
- block_t start, block_t len)
- {
- struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
- struct list_head *pend_list;
- struct discard_cmd *dc;
- f2fs_bug_on(sbi, !len);
- pend_list = &dcc->pend_list[plist_idx(len)];
- dc = f2fs_kmem_cache_alloc(discard_cmd_slab, GFP_NOFS);
- INIT_LIST_HEAD(&dc->list);
- dc->bdev = bdev;
- dc->lstart = lstart;
- dc->start = start;
- dc->len = len;
- dc->ref = 0;
- dc->state = D_PREP;
- dc->queued = 0;
- dc->error = 0;
- init_completion(&dc->wait);
- list_add_tail(&dc->list, pend_list);
- spin_lock_init(&dc->lock);
- dc->bio_ref = 0;
- atomic_inc(&dcc->discard_cmd_cnt);
- dcc->undiscard_blks += len;
- return dc;
- }
- static struct discard_cmd *__attach_discard_cmd(struct f2fs_sb_info *sbi,
- struct block_device *bdev, block_t lstart,
- block_t start, block_t len,
- struct rb_node *parent, struct rb_node **p,
- bool leftmost)
- {
- struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
- struct discard_cmd *dc;
- dc = __create_discard_cmd(sbi, bdev, lstart, start, len);
- rb_link_node(&dc->rb_node, parent, p);
- rb_insert_color_cached(&dc->rb_node, &dcc->root, leftmost);
- return dc;
- }
- static void __detach_discard_cmd(struct discard_cmd_control *dcc,
- struct discard_cmd *dc)
- {
- if (dc->state == D_DONE)
- atomic_sub(dc->queued, &dcc->queued_discard);
- list_del(&dc->list);
- rb_erase_cached(&dc->rb_node, &dcc->root);
- dcc->undiscard_blks -= dc->len;
- kmem_cache_free(discard_cmd_slab, dc);
- atomic_dec(&dcc->discard_cmd_cnt);
- }
- static void __remove_discard_cmd(struct f2fs_sb_info *sbi,
- struct discard_cmd *dc)
- {
- struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
- unsigned long flags;
- trace_f2fs_remove_discard(dc->bdev, dc->start, dc->len);
- spin_lock_irqsave(&dc->lock, flags);
- if (dc->bio_ref) {
- spin_unlock_irqrestore(&dc->lock, flags);
- return;
- }
- spin_unlock_irqrestore(&dc->lock, flags);
- f2fs_bug_on(sbi, dc->ref);
- if (dc->error == -EOPNOTSUPP)
- dc->error = 0;
- if (dc->error)
- printk_ratelimited(
- "%sF2FS-fs (%s): Issue discard(%u, %u, %u) failed, ret: %d",
- KERN_INFO, sbi->sb->s_id,
- dc->lstart, dc->start, dc->len, dc->error);
- __detach_discard_cmd(dcc, dc);
- }
- static void f2fs_submit_discard_endio(struct bio *bio)
- {
- struct discard_cmd *dc = (struct discard_cmd *)bio->bi_private;
- unsigned long flags;
- spin_lock_irqsave(&dc->lock, flags);
- if (!dc->error)
- dc->error = blk_status_to_errno(bio->bi_status);
- dc->bio_ref--;
- if (!dc->bio_ref && dc->state == D_SUBMIT) {
- dc->state = D_DONE;
- complete_all(&dc->wait);
- }
- spin_unlock_irqrestore(&dc->lock, flags);
- bio_put(bio);
- }
- static void __check_sit_bitmap(struct f2fs_sb_info *sbi,
- block_t start, block_t end)
- {
- #ifdef CONFIG_F2FS_CHECK_FS
- struct seg_entry *sentry;
- unsigned int segno;
- block_t blk = start;
- unsigned long offset, size, max_blocks = sbi->blocks_per_seg;
- unsigned long *map;
- while (blk < end) {
- segno = GET_SEGNO(sbi, blk);
- sentry = get_seg_entry(sbi, segno);
- offset = GET_BLKOFF_FROM_SEG0(sbi, blk);
- if (end < START_BLOCK(sbi, segno + 1))
- size = GET_BLKOFF_FROM_SEG0(sbi, end);
- else
- size = max_blocks;
- map = (unsigned long *)(sentry->cur_valid_map);
- offset = __find_rev_next_bit(map, size, offset);
- f2fs_bug_on(sbi, offset != size);
- blk = START_BLOCK(sbi, segno + 1);
- }
- #endif
- }
- static void __init_discard_policy(struct f2fs_sb_info *sbi,
- struct discard_policy *dpolicy,
- int discard_type, unsigned int granularity)
- {
- struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
- /* common policy */
- dpolicy->type = discard_type;
- dpolicy->sync = true;
- dpolicy->ordered = false;
- dpolicy->granularity = granularity;
- dpolicy->max_requests = DEF_MAX_DISCARD_REQUEST;
- dpolicy->io_aware_gran = MAX_PLIST_NUM;
- dpolicy->timeout = false;
- if (discard_type == DPOLICY_BG) {
- dpolicy->min_interval = DEF_MIN_DISCARD_ISSUE_TIME;
- dpolicy->mid_interval = DEF_MID_DISCARD_ISSUE_TIME;
- dpolicy->max_interval = DEF_MAX_DISCARD_ISSUE_TIME;
- dpolicy->io_aware = true;
- dpolicy->sync = false;
- dpolicy->ordered = true;
- if (utilization(sbi) > DEF_DISCARD_URGENT_UTIL) {
- dpolicy->granularity = 1;
- if (atomic_read(&dcc->discard_cmd_cnt))
- dpolicy->max_interval =
- DEF_MIN_DISCARD_ISSUE_TIME;
- }
- } else if (discard_type == DPOLICY_FORCE) {
- dpolicy->min_interval = DEF_MIN_DISCARD_ISSUE_TIME;
- dpolicy->mid_interval = DEF_MID_DISCARD_ISSUE_TIME;
- dpolicy->max_interval = DEF_MAX_DISCARD_ISSUE_TIME;
- dpolicy->io_aware = false;
- } else if (discard_type == DPOLICY_FSTRIM) {
- dpolicy->io_aware = false;
- } else if (discard_type == DPOLICY_UMOUNT) {
- dpolicy->io_aware = false;
- /* we need to issue all to keep CP_TRIMMED_FLAG */
- dpolicy->granularity = 1;
- dpolicy->timeout = true;
- }
- }
- static void __update_discard_tree_range(struct f2fs_sb_info *sbi,
- struct block_device *bdev, block_t lstart,
- block_t start, block_t len);
- /* this function is copied from blkdev_issue_discard from block/blk-lib.c */
- static int __submit_discard_cmd(struct f2fs_sb_info *sbi,
- struct discard_policy *dpolicy,
- struct discard_cmd *dc,
- unsigned int *issued)
- {
- struct block_device *bdev = dc->bdev;
- struct request_queue *q = bdev_get_queue(bdev);
- unsigned int max_discard_blocks =
- SECTOR_TO_BLOCK(q->limits.max_discard_sectors);
- struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
- struct list_head *wait_list = (dpolicy->type == DPOLICY_FSTRIM) ?
- &(dcc->fstrim_list) : &(dcc->wait_list);
- int flag = dpolicy->sync ? REQ_SYNC : 0;
- block_t lstart, start, len, total_len;
- int err = 0;
- if (dc->state != D_PREP)
- return 0;
- if (is_sbi_flag_set(sbi, SBI_NEED_FSCK))
- return 0;
- trace_f2fs_issue_discard(bdev, dc->start, dc->len);
- lstart = dc->lstart;
- start = dc->start;
- len = dc->len;
- total_len = len;
- dc->len = 0;
- while (total_len && *issued < dpolicy->max_requests && !err) {
- struct bio *bio = NULL;
- unsigned long flags;
- bool last = true;
- if (len > max_discard_blocks) {
- len = max_discard_blocks;
- last = false;
- }
- (*issued)++;
- if (*issued == dpolicy->max_requests)
- last = true;
- dc->len += len;
- if (time_to_inject(sbi, FAULT_DISCARD)) {
- f2fs_show_injection_info(sbi, FAULT_DISCARD);
- err = -EIO;
- goto submit;
- }
- err = __blkdev_issue_discard(bdev,
- SECTOR_FROM_BLOCK(start),
- SECTOR_FROM_BLOCK(len),
- GFP_NOFS, 0, &bio);
- submit:
- if (err) {
- spin_lock_irqsave(&dc->lock, flags);
- if (dc->state == D_PARTIAL)
- dc->state = D_SUBMIT;
- spin_unlock_irqrestore(&dc->lock, flags);
- break;
- }
- f2fs_bug_on(sbi, !bio);
- /*
- * should keep before submission to avoid D_DONE
- * right away
- */
- spin_lock_irqsave(&dc->lock, flags);
- if (last)
- dc->state = D_SUBMIT;
- else
- dc->state = D_PARTIAL;
- dc->bio_ref++;
- spin_unlock_irqrestore(&dc->lock, flags);
- atomic_inc(&dcc->queued_discard);
- dc->queued++;
- list_move_tail(&dc->list, wait_list);
- /* sanity check on discard range */
- __check_sit_bitmap(sbi, lstart, lstart + len);
- bio->bi_private = dc;
- bio->bi_end_io = f2fs_submit_discard_endio;
- bio->bi_opf |= flag;
- submit_bio(bio);
- atomic_inc(&dcc->issued_discard);
- f2fs_update_iostat(sbi, FS_DISCARD, 1);
- lstart += len;
- start += len;
- total_len -= len;
- len = total_len;
- }
- if (!err && len) {
- dcc->undiscard_blks -= len;
- __update_discard_tree_range(sbi, bdev, lstart, start, len);
- }
- return err;
- }
- static void __insert_discard_tree(struct f2fs_sb_info *sbi,
- struct block_device *bdev, block_t lstart,
- block_t start, block_t len,
- struct rb_node **insert_p,
- struct rb_node *insert_parent)
- {
- struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
- struct rb_node **p;
- struct rb_node *parent = NULL;
- bool leftmost = true;
- if (insert_p && insert_parent) {
- parent = insert_parent;
- p = insert_p;
- goto do_insert;
- }
- p = f2fs_lookup_rb_tree_for_insert(sbi, &dcc->root, &parent,
- lstart, &leftmost);
- do_insert:
- __attach_discard_cmd(sbi, bdev, lstart, start, len, parent,
- p, leftmost);
- }
- static void __relocate_discard_cmd(struct discard_cmd_control *dcc,
- struct discard_cmd *dc)
- {
- list_move_tail(&dc->list, &dcc->pend_list[plist_idx(dc->len)]);
- }
- static void __punch_discard_cmd(struct f2fs_sb_info *sbi,
- struct discard_cmd *dc, block_t blkaddr)
- {
- struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
- struct discard_info di = dc->di;
- bool modified = false;
- if (dc->state == D_DONE || dc->len == 1) {
- __remove_discard_cmd(sbi, dc);
- return;
- }
- dcc->undiscard_blks -= di.len;
- if (blkaddr > di.lstart) {
- dc->len = blkaddr - dc->lstart;
- dcc->undiscard_blks += dc->len;
- __relocate_discard_cmd(dcc, dc);
- modified = true;
- }
- if (blkaddr < di.lstart + di.len - 1) {
- if (modified) {
- __insert_discard_tree(sbi, dc->bdev, blkaddr + 1,
- di.start + blkaddr + 1 - di.lstart,
- di.lstart + di.len - 1 - blkaddr,
- NULL, NULL);
- } else {
- dc->lstart++;
- dc->len--;
- dc->start++;
- dcc->undiscard_blks += dc->len;
- __relocate_discard_cmd(dcc, dc);
- }
- }
- }
- static void __update_discard_tree_range(struct f2fs_sb_info *sbi,
- struct block_device *bdev, block_t lstart,
- block_t start, block_t len)
- {
- struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
- struct discard_cmd *prev_dc = NULL, *next_dc = NULL;
- struct discard_cmd *dc;
- struct discard_info di = {0};
- struct rb_node **insert_p = NULL, *insert_parent = NULL;
- struct request_queue *q = bdev_get_queue(bdev);
- unsigned int max_discard_blocks =
- SECTOR_TO_BLOCK(q->limits.max_discard_sectors);
- block_t end = lstart + len;
- dc = (struct discard_cmd *)f2fs_lookup_rb_tree_ret(&dcc->root,
- NULL, lstart,
- (struct rb_entry **)&prev_dc,
- (struct rb_entry **)&next_dc,
- &insert_p, &insert_parent, true, NULL);
- if (dc)
- prev_dc = dc;
- if (!prev_dc) {
- di.lstart = lstart;
- di.len = next_dc ? next_dc->lstart - lstart : len;
- di.len = min(di.len, len);
- di.start = start;
- }
- while (1) {
- struct rb_node *node;
- bool merged = false;
- struct discard_cmd *tdc = NULL;
- if (prev_dc) {
- di.lstart = prev_dc->lstart + prev_dc->len;
- if (di.lstart < lstart)
- di.lstart = lstart;
- if (di.lstart >= end)
- break;
- if (!next_dc || next_dc->lstart > end)
- di.len = end - di.lstart;
- else
- di.len = next_dc->lstart - di.lstart;
- di.start = start + di.lstart - lstart;
- }
- if (!di.len)
- goto next;
- if (prev_dc && prev_dc->state == D_PREP &&
- prev_dc->bdev == bdev &&
- __is_discard_back_mergeable(&di, &prev_dc->di,
- max_discard_blocks)) {
- prev_dc->di.len += di.len;
- dcc->undiscard_blks += di.len;
- __relocate_discard_cmd(dcc, prev_dc);
- di = prev_dc->di;
- tdc = prev_dc;
- merged = true;
- }
- if (next_dc && next_dc->state == D_PREP &&
- next_dc->bdev == bdev &&
- __is_discard_front_mergeable(&di, &next_dc->di,
- max_discard_blocks)) {
- next_dc->di.lstart = di.lstart;
- next_dc->di.len += di.len;
- next_dc->di.start = di.start;
- dcc->undiscard_blks += di.len;
- __relocate_discard_cmd(dcc, next_dc);
- if (tdc)
- __remove_discard_cmd(sbi, tdc);
- merged = true;
- }
- if (!merged) {
- __insert_discard_tree(sbi, bdev, di.lstart, di.start,
- di.len, NULL, NULL);
- }
- next:
- prev_dc = next_dc;
- if (!prev_dc)
- break;
- node = rb_next(&prev_dc->rb_node);
- next_dc = rb_entry_safe(node, struct discard_cmd, rb_node);
- }
- }
- static int __queue_discard_cmd(struct f2fs_sb_info *sbi,
- struct block_device *bdev, block_t blkstart, block_t blklen)
- {
- block_t lblkstart = blkstart;
- if (!f2fs_bdev_support_discard(bdev))
- return 0;
- trace_f2fs_queue_discard(bdev, blkstart, blklen);
- if (f2fs_is_multi_device(sbi)) {
- int devi = f2fs_target_device_index(sbi, blkstart);
- blkstart -= FDEV(devi).start_blk;
- }
- mutex_lock(&SM_I(sbi)->dcc_info->cmd_lock);
- __update_discard_tree_range(sbi, bdev, lblkstart, blkstart, blklen);
- mutex_unlock(&SM_I(sbi)->dcc_info->cmd_lock);
- return 0;
- }
- static unsigned int __issue_discard_cmd_orderly(struct f2fs_sb_info *sbi,
- struct discard_policy *dpolicy)
- {
- struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
- struct discard_cmd *prev_dc = NULL, *next_dc = NULL;
- struct rb_node **insert_p = NULL, *insert_parent = NULL;
- struct discard_cmd *dc;
- struct blk_plug plug;
- unsigned int pos = dcc->next_pos;
- unsigned int issued = 0;
- bool io_interrupted = false;
- mutex_lock(&dcc->cmd_lock);
- dc = (struct discard_cmd *)f2fs_lookup_rb_tree_ret(&dcc->root,
- NULL, pos,
- (struct rb_entry **)&prev_dc,
- (struct rb_entry **)&next_dc,
- &insert_p, &insert_parent, true, NULL);
- if (!dc)
- dc = next_dc;
- blk_start_plug(&plug);
- while (dc) {
- struct rb_node *node;
- int err = 0;
- if (dc->state != D_PREP)
- goto next;
- if (dpolicy->io_aware && !is_idle(sbi, DISCARD_TIME)) {
- io_interrupted = true;
- break;
- }
- dcc->next_pos = dc->lstart + dc->len;
- err = __submit_discard_cmd(sbi, dpolicy, dc, &issued);
- if (issued >= dpolicy->max_requests)
- break;
- next:
- node = rb_next(&dc->rb_node);
- if (err)
- __remove_discard_cmd(sbi, dc);
- dc = rb_entry_safe(node, struct discard_cmd, rb_node);
- }
- blk_finish_plug(&plug);
- if (!dc)
- dcc->next_pos = 0;
- mutex_unlock(&dcc->cmd_lock);
- if (!issued && io_interrupted)
- issued = -1;
- return issued;
- }
- static unsigned int __wait_all_discard_cmd(struct f2fs_sb_info *sbi,
- struct discard_policy *dpolicy);
- static int __issue_discard_cmd(struct f2fs_sb_info *sbi,
- struct discard_policy *dpolicy)
- {
- struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
- struct list_head *pend_list;
- struct discard_cmd *dc, *tmp;
- struct blk_plug plug;
- int i, issued;
- bool io_interrupted = false;
- if (dpolicy->timeout)
- f2fs_update_time(sbi, UMOUNT_DISCARD_TIMEOUT);
- retry:
- issued = 0;
- for (i = MAX_PLIST_NUM - 1; i >= 0; i--) {
- if (dpolicy->timeout &&
- f2fs_time_over(sbi, UMOUNT_DISCARD_TIMEOUT))
- break;
- if (i + 1 < dpolicy->granularity)
- break;
- if (i < DEFAULT_DISCARD_GRANULARITY && dpolicy->ordered)
- return __issue_discard_cmd_orderly(sbi, dpolicy);
- pend_list = &dcc->pend_list[i];
- mutex_lock(&dcc->cmd_lock);
- if (list_empty(pend_list))
- goto next;
- if (unlikely(dcc->rbtree_check))
- f2fs_bug_on(sbi, !f2fs_check_rb_tree_consistence(sbi,
- &dcc->root, false));
- blk_start_plug(&plug);
- list_for_each_entry_safe(dc, tmp, pend_list, list) {
- f2fs_bug_on(sbi, dc->state != D_PREP);
- if (dpolicy->timeout &&
- f2fs_time_over(sbi, UMOUNT_DISCARD_TIMEOUT))
- break;
- if (dpolicy->io_aware && i < dpolicy->io_aware_gran &&
- !is_idle(sbi, DISCARD_TIME)) {
- io_interrupted = true;
- break;
- }
- __submit_discard_cmd(sbi, dpolicy, dc, &issued);
- if (issued >= dpolicy->max_requests)
- break;
- }
- blk_finish_plug(&plug);
- next:
- mutex_unlock(&dcc->cmd_lock);
- if (issued >= dpolicy->max_requests || io_interrupted)
- break;
- }
- if (dpolicy->type == DPOLICY_UMOUNT && issued) {
- __wait_all_discard_cmd(sbi, dpolicy);
- goto retry;
- }
- if (!issued && io_interrupted)
- issued = -1;
- return issued;
- }
- static bool __drop_discard_cmd(struct f2fs_sb_info *sbi)
- {
- struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
- struct list_head *pend_list;
- struct discard_cmd *dc, *tmp;
- int i;
- bool dropped = false;
- mutex_lock(&dcc->cmd_lock);
- for (i = MAX_PLIST_NUM - 1; i >= 0; i--) {
- pend_list = &dcc->pend_list[i];
- list_for_each_entry_safe(dc, tmp, pend_list, list) {
- f2fs_bug_on(sbi, dc->state != D_PREP);
- __remove_discard_cmd(sbi, dc);
- dropped = true;
- }
- }
- mutex_unlock(&dcc->cmd_lock);
- return dropped;
- }
- void f2fs_drop_discard_cmd(struct f2fs_sb_info *sbi)
- {
- __drop_discard_cmd(sbi);
- }
- static unsigned int __wait_one_discard_bio(struct f2fs_sb_info *sbi,
- struct discard_cmd *dc)
- {
- struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
- unsigned int len = 0;
- wait_for_completion_io(&dc->wait);
- mutex_lock(&dcc->cmd_lock);
- f2fs_bug_on(sbi, dc->state != D_DONE);
- dc->ref--;
- if (!dc->ref) {
- if (!dc->error)
- len = dc->len;
- __remove_discard_cmd(sbi, dc);
- }
- mutex_unlock(&dcc->cmd_lock);
- return len;
- }
- static unsigned int __wait_discard_cmd_range(struct f2fs_sb_info *sbi,
- struct discard_policy *dpolicy,
- block_t start, block_t end)
- {
- struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
- struct list_head *wait_list = (dpolicy->type == DPOLICY_FSTRIM) ?
- &(dcc->fstrim_list) : &(dcc->wait_list);
- struct discard_cmd *dc, *tmp;
- bool need_wait;
- unsigned int trimmed = 0;
- next:
- need_wait = false;
- mutex_lock(&dcc->cmd_lock);
- list_for_each_entry_safe(dc, tmp, wait_list, list) {
- if (dc->lstart + dc->len <= start || end <= dc->lstart)
- continue;
- if (dc->len < dpolicy->granularity)
- continue;
- if (dc->state == D_DONE && !dc->ref) {
- wait_for_completion_io(&dc->wait);
- if (!dc->error)
- trimmed += dc->len;
- __remove_discard_cmd(sbi, dc);
- } else {
- dc->ref++;
- need_wait = true;
- break;
- }
- }
- mutex_unlock(&dcc->cmd_lock);
- if (need_wait) {
- trimmed += __wait_one_discard_bio(sbi, dc);
- goto next;
- }
- return trimmed;
- }
- static unsigned int __wait_all_discard_cmd(struct f2fs_sb_info *sbi,
- struct discard_policy *dpolicy)
- {
- struct discard_policy dp;
- unsigned int discard_blks;
- if (dpolicy)
- return __wait_discard_cmd_range(sbi, dpolicy, 0, UINT_MAX);
- /* wait all */
- __init_discard_policy(sbi, &dp, DPOLICY_FSTRIM, 1);
- discard_blks = __wait_discard_cmd_range(sbi, &dp, 0, UINT_MAX);
- __init_discard_policy(sbi, &dp, DPOLICY_UMOUNT, 1);
- discard_blks += __wait_discard_cmd_range(sbi, &dp, 0, UINT_MAX);
- return discard_blks;
- }
- /* This should be covered by global mutex, &sit_i->sentry_lock */
- static void f2fs_wait_discard_bio(struct f2fs_sb_info *sbi, block_t blkaddr)
- {
- struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
- struct discard_cmd *dc;
- bool need_wait = false;
- mutex_lock(&dcc->cmd_lock);
- dc = (struct discard_cmd *)f2fs_lookup_rb_tree(&dcc->root,
- NULL, blkaddr);
- if (dc) {
- if (dc->state == D_PREP) {
- __punch_discard_cmd(sbi, dc, blkaddr);
- } else {
- dc->ref++;
- need_wait = true;
- }
- }
- mutex_unlock(&dcc->cmd_lock);
- if (need_wait)
- __wait_one_discard_bio(sbi, dc);
- }
- void f2fs_stop_discard_thread(struct f2fs_sb_info *sbi)
- {
- struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
- if (dcc && dcc->f2fs_issue_discard) {
- struct task_struct *discard_thread = dcc->f2fs_issue_discard;
- dcc->f2fs_issue_discard = NULL;
- kthread_stop(discard_thread);
- }
- }
- /* This comes from f2fs_put_super */
- bool f2fs_issue_discard_timeout(struct f2fs_sb_info *sbi)
- {
- struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
- struct discard_policy dpolicy;
- bool dropped;
- __init_discard_policy(sbi, &dpolicy, DPOLICY_UMOUNT,
- dcc->discard_granularity);
- __issue_discard_cmd(sbi, &dpolicy);
- dropped = __drop_discard_cmd(sbi);
- /* just to make sure there is no pending discard commands */
- __wait_all_discard_cmd(sbi, NULL);
- f2fs_bug_on(sbi, atomic_read(&dcc->discard_cmd_cnt));
- return dropped;
- }
- static int issue_discard_thread(void *data)
- {
- struct f2fs_sb_info *sbi = data;
- struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
- wait_queue_head_t *q = &dcc->discard_wait_queue;
- struct discard_policy dpolicy;
- unsigned int wait_ms = DEF_MIN_DISCARD_ISSUE_TIME;
- int issued;
- set_freezable();
- do {
- if (sbi->gc_mode == GC_URGENT_HIGH ||
- !f2fs_available_free_memory(sbi, DISCARD_CACHE))
- __init_discard_policy(sbi, &dpolicy, DPOLICY_FORCE, 1);
- else
- __init_discard_policy(sbi, &dpolicy, DPOLICY_BG,
- dcc->discard_granularity);
- if (!atomic_read(&dcc->discard_cmd_cnt))
- wait_ms = dpolicy.max_interval;
- wait_event_interruptible_timeout(*q,
- kthread_should_stop() || freezing(current) ||
- dcc->discard_wake,
- msecs_to_jiffies(wait_ms));
- if (dcc->discard_wake)
- dcc->discard_wake = 0;
- /* clean up pending candidates before going to sleep */
- if (atomic_read(&dcc->queued_discard))
- __wait_all_discard_cmd(sbi, NULL);
- if (try_to_freeze())
- continue;
- if (f2fs_readonly(sbi->sb))
- continue;
- if (kthread_should_stop())
- return 0;
- if (is_sbi_flag_set(sbi, SBI_NEED_FSCK)) {
- wait_ms = dpolicy.max_interval;
- continue;
- }
- if (!atomic_read(&dcc->discard_cmd_cnt))
- continue;
- sb_start_intwrite(sbi->sb);
- issued = __issue_discard_cmd(sbi, &dpolicy);
- if (issued > 0) {
- __wait_all_discard_cmd(sbi, &dpolicy);
- wait_ms = dpolicy.min_interval;
- } else if (issued == -1) {
- wait_ms = f2fs_time_to_wait(sbi, DISCARD_TIME);
- if (!wait_ms)
- wait_ms = dpolicy.mid_interval;
- } else {
- wait_ms = dpolicy.max_interval;
- }
- sb_end_intwrite(sbi->sb);
- } while (!kthread_should_stop());
- return 0;
- }
- #ifdef CONFIG_BLK_DEV_ZONED
- static int __f2fs_issue_discard_zone(struct f2fs_sb_info *sbi,
- struct block_device *bdev, block_t blkstart, block_t blklen)
- {
- sector_t sector, nr_sects;
- block_t lblkstart = blkstart;
- int devi = 0;
- if (f2fs_is_multi_device(sbi)) {
- devi = f2fs_target_device_index(sbi, blkstart);
- if (blkstart < FDEV(devi).start_blk ||
- blkstart > FDEV(devi).end_blk) {
- f2fs_err(sbi, "Invalid block %x", blkstart);
- return -EIO;
- }
- blkstart -= FDEV(devi).start_blk;
- }
- /* For sequential zones, reset the zone write pointer */
- if (f2fs_blkz_is_seq(sbi, devi, blkstart)) {
- sector = SECTOR_FROM_BLOCK(blkstart);
- nr_sects = SECTOR_FROM_BLOCK(blklen);
- if (sector & (bdev_zone_sectors(bdev) - 1) ||
- nr_sects != bdev_zone_sectors(bdev)) {
- f2fs_err(sbi, "(%d) %s: Unaligned zone reset attempted (block %x + %x)",
- devi, sbi->s_ndevs ? FDEV(devi).path : "",
- blkstart, blklen);
- return -EIO;
- }
- trace_f2fs_issue_reset_zone(bdev, blkstart);
- return blkdev_zone_mgmt(bdev, REQ_OP_ZONE_RESET,
- sector, nr_sects, GFP_NOFS);
- }
- /* For conventional zones, use regular discard if supported */
- return __queue_discard_cmd(sbi, bdev, lblkstart, blklen);
- }
- #endif
- static int __issue_discard_async(struct f2fs_sb_info *sbi,
- struct block_device *bdev, block_t blkstart, block_t blklen)
- {
- #ifdef CONFIG_BLK_DEV_ZONED
- if (f2fs_sb_has_blkzoned(sbi) && bdev_is_zoned(bdev))
- return __f2fs_issue_discard_zone(sbi, bdev, blkstart, blklen);
- #endif
- return __queue_discard_cmd(sbi, bdev, blkstart, blklen);
- }
- static int f2fs_issue_discard(struct f2fs_sb_info *sbi,
- block_t blkstart, block_t blklen)
- {
- sector_t start = blkstart, len = 0;
- struct block_device *bdev;
- struct seg_entry *se;
- unsigned int offset;
- block_t i;
- int err = 0;
- bdev = f2fs_target_device(sbi, blkstart, NULL);
- for (i = blkstart; i < blkstart + blklen; i++, len++) {
- if (i != start) {
- struct block_device *bdev2 =
- f2fs_target_device(sbi, i, NULL);
- if (bdev2 != bdev) {
- err = __issue_discard_async(sbi, bdev,
- start, len);
- if (err)
- return err;
- bdev = bdev2;
- start = i;
- len = 0;
- }
- }
- se = get_seg_entry(sbi, GET_SEGNO(sbi, i));
- offset = GET_BLKOFF_FROM_SEG0(sbi, i);
- if (!f2fs_test_and_set_bit(offset, se->discard_map))
- sbi->discard_blks--;
- }
- if (len)
- err = __issue_discard_async(sbi, bdev, start, len);
- return err;
- }
- static bool add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc,
- bool check_only)
- {
- int entries = SIT_VBLOCK_MAP_SIZE / sizeof(unsigned long);
- int max_blocks = sbi->blocks_per_seg;
- struct seg_entry *se = get_seg_entry(sbi, cpc->trim_start);
- unsigned long *cur_map = (unsigned long *)se->cur_valid_map;
- unsigned long *ckpt_map = (unsigned long *)se->ckpt_valid_map;
- unsigned long *discard_map = (unsigned long *)se->discard_map;
- unsigned long *dmap = SIT_I(sbi)->tmp_map;
- unsigned int start = 0, end = -1;
- bool force = (cpc->reason & CP_DISCARD);
- struct discard_entry *de = NULL;
- struct list_head *head = &SM_I(sbi)->dcc_info->entry_list;
- int i;
- if (se->valid_blocks == max_blocks || !f2fs_hw_support_discard(sbi))
- return false;
- if (!force) {
- if (!f2fs_realtime_discard_enable(sbi) || !se->valid_blocks ||
- SM_I(sbi)->dcc_info->nr_discards >=
- SM_I(sbi)->dcc_info->max_discards)
- return false;
- }
- /* SIT_VBLOCK_MAP_SIZE should be multiple of sizeof(unsigned long) */
- for (i = 0; i < entries; i++)
- dmap[i] = force ? ~ckpt_map[i] & ~discard_map[i] :
- (cur_map[i] ^ ckpt_map[i]) & ckpt_map[i];
- while (force || SM_I(sbi)->dcc_info->nr_discards <=
- SM_I(sbi)->dcc_info->max_discards) {
- start = __find_rev_next_bit(dmap, max_blocks, end + 1);
- if (start >= max_blocks)
- break;
- end = __find_rev_next_zero_bit(dmap, max_blocks, start + 1);
- if (force && start && end != max_blocks
- && (end - start) < cpc->trim_minlen)
- continue;
- if (check_only)
- return true;
- if (!de) {
- de = f2fs_kmem_cache_alloc(discard_entry_slab,
- GFP_F2FS_ZERO);
- de->start_blkaddr = START_BLOCK(sbi, cpc->trim_start);
- list_add_tail(&de->list, head);
- }
- for (i = start; i < end; i++)
- __set_bit_le(i, (void *)de->discard_map);
- SM_I(sbi)->dcc_info->nr_discards += end - start;
- }
- return false;
- }
- static void release_discard_addr(struct discard_entry *entry)
- {
- list_del(&entry->list);
- kmem_cache_free(discard_entry_slab, entry);
- }
- void f2fs_release_discard_addrs(struct f2fs_sb_info *sbi)
- {
- struct list_head *head = &(SM_I(sbi)->dcc_info->entry_list);
- struct discard_entry *entry, *this;
- /* drop caches */
- list_for_each_entry_safe(entry, this, head, list)
- release_discard_addr(entry);
- }
- /*
- * Should call f2fs_clear_prefree_segments after checkpoint is done.
- */
- static void set_prefree_as_free_segments(struct f2fs_sb_info *sbi)
- {
- struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
- unsigned int segno;
- mutex_lock(&dirty_i->seglist_lock);
- for_each_set_bit(segno, dirty_i->dirty_segmap[PRE], MAIN_SEGS(sbi))
- __set_test_and_free(sbi, segno, false);
- mutex_unlock(&dirty_i->seglist_lock);
- }
- void f2fs_clear_prefree_segments(struct f2fs_sb_info *sbi,
- struct cp_control *cpc)
- {
- struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
- struct list_head *head = &dcc->entry_list;
- struct discard_entry *entry, *this;
- struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
- unsigned long *prefree_map = dirty_i->dirty_segmap[PRE];
- unsigned int start = 0, end = -1;
- unsigned int secno, start_segno;
- bool force = (cpc->reason & CP_DISCARD);
- bool need_align = f2fs_lfs_mode(sbi) && __is_large_section(sbi);
- mutex_lock(&dirty_i->seglist_lock);
- while (1) {
- int i;
- if (need_align && end != -1)
- end--;
- start = find_next_bit(prefree_map, MAIN_SEGS(sbi), end + 1);
- if (start >= MAIN_SEGS(sbi))
- break;
- end = find_next_zero_bit(prefree_map, MAIN_SEGS(sbi),
- start + 1);
- if (need_align) {
- start = rounddown(start, sbi->segs_per_sec);
- end = roundup(end, sbi->segs_per_sec);
- }
- for (i = start; i < end; i++) {
- if (test_and_clear_bit(i, prefree_map))
- dirty_i->nr_dirty[PRE]--;
- }
- if (!f2fs_realtime_discard_enable(sbi))
- continue;
- if (force && start >= cpc->trim_start &&
- (end - 1) <= cpc->trim_end)
- continue;
- if (!f2fs_lfs_mode(sbi) || !__is_large_section(sbi)) {
- f2fs_issue_discard(sbi, START_BLOCK(sbi, start),
- (end - start) << sbi->log_blocks_per_seg);
- continue;
- }
- next:
- secno = GET_SEC_FROM_SEG(sbi, start);
- start_segno = GET_SEG_FROM_SEC(sbi, secno);
- if (!IS_CURSEC(sbi, secno) &&
- !get_valid_blocks(sbi, start, true))
- f2fs_issue_discard(sbi, START_BLOCK(sbi, start_segno),
- sbi->segs_per_sec << sbi->log_blocks_per_seg);
- start = start_segno + sbi->segs_per_sec;
- if (start < end)
- goto next;
- else
- end = start - 1;
- }
- mutex_unlock(&dirty_i->seglist_lock);
- /* send small discards */
- list_for_each_entry_safe(entry, this, head, list) {
- unsigned int cur_pos = 0, next_pos, len, total_len = 0;
- bool is_valid = test_bit_le(0, entry->discard_map);
- find_next:
- if (is_valid) {
- next_pos = find_next_zero_bit_le(entry->discard_map,
- sbi->blocks_per_seg, cur_pos);
- len = next_pos - cur_pos;
- if (f2fs_sb_has_blkzoned(sbi) ||
- (force && len < cpc->trim_minlen))
- goto skip;
- f2fs_issue_discard(sbi, entry->start_blkaddr + cur_pos,
- len);
- total_len += len;
- } else {
- next_pos = find_next_bit_le(entry->discard_map,
- sbi->blocks_per_seg, cur_pos);
- }
- skip:
- cur_pos = next_pos;
- is_valid = !is_valid;
- if (cur_pos < sbi->blocks_per_seg)
- goto find_next;
- release_discard_addr(entry);
- dcc->nr_discards -= total_len;
- }
- wake_up_discard_thread(sbi, false);
- }
- static int create_discard_cmd_control(struct f2fs_sb_info *sbi)
- {
- dev_t dev = sbi->sb->s_bdev->bd_dev;
- struct discard_cmd_control *dcc;
- int err = 0, i;
- if (SM_I(sbi)->dcc_info) {
- dcc = SM_I(sbi)->dcc_info;
- goto init_thread;
- }
- dcc = f2fs_kzalloc(sbi, sizeof(struct discard_cmd_control), GFP_KERNEL);
- if (!dcc)
- return -ENOMEM;
- dcc->discard_granularity = DEFAULT_DISCARD_GRANULARITY;
- INIT_LIST_HEAD(&dcc->entry_list);
- for (i = 0; i < MAX_PLIST_NUM; i++)
- INIT_LIST_HEAD(&dcc->pend_list[i]);
- INIT_LIST_HEAD(&dcc->wait_list);
- INIT_LIST_HEAD(&dcc->fstrim_list);
- mutex_init(&dcc->cmd_lock);
- atomic_set(&dcc->issued_discard, 0);
- atomic_set(&dcc->queued_discard, 0);
- atomic_set(&dcc->discard_cmd_cnt, 0);
- dcc->nr_discards = 0;
- dcc->max_discards = MAIN_SEGS(sbi) << sbi->log_blocks_per_seg;
- dcc->undiscard_blks = 0;
- dcc->next_pos = 0;
- dcc->root = RB_ROOT_CACHED;
- dcc->rbtree_check = false;
- init_waitqueue_head(&dcc->discard_wait_queue);
- SM_I(sbi)->dcc_info = dcc;
- init_thread:
- dcc->f2fs_issue_discard = kthread_run(issue_discard_thread, sbi,
- "f2fs_discard-%u:%u", MAJOR(dev), MINOR(dev));
- if (IS_ERR(dcc->f2fs_issue_discard)) {
- err = PTR_ERR(dcc->f2fs_issue_discard);
- kfree(dcc);
- SM_I(sbi)->dcc_info = NULL;
- return err;
- }
- return err;
- }
- static void destroy_discard_cmd_control(struct f2fs_sb_info *sbi)
- {
- struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
- if (!dcc)
- return;
- f2fs_stop_discard_thread(sbi);
- /*
- * Recovery can cache discard commands, so in error path of
- * fill_super(), it needs to give a chance to handle them.
- */
- if (unlikely(atomic_read(&dcc->discard_cmd_cnt)))
- f2fs_issue_discard_timeout(sbi);
- kfree(dcc);
- SM_I(sbi)->dcc_info = NULL;
- }
- static bool __mark_sit_entry_dirty(struct f2fs_sb_info *sbi, unsigned int segno)
- {
- struct sit_info *sit_i = SIT_I(sbi);
- if (!__test_and_set_bit(segno, sit_i->dirty_sentries_bitmap)) {
- sit_i->dirty_sentries++;
- return false;
- }
- return true;
- }
- static void __set_sit_entry_type(struct f2fs_sb_info *sbi, int type,
- unsigned int segno, int modified)
- {
- struct seg_entry *se = get_seg_entry(sbi, segno);
- se->type = type;
- if (modified)
- __mark_sit_entry_dirty(sbi, segno);
- }
- static inline unsigned long long get_segment_mtime(struct f2fs_sb_info *sbi,
- block_t blkaddr)
- {
- unsigned int segno = GET_SEGNO(sbi, blkaddr);
- if (segno == NULL_SEGNO)
- return 0;
- return get_seg_entry(sbi, segno)->mtime;
- }
- static void update_segment_mtime(struct f2fs_sb_info *sbi, block_t blkaddr,
- unsigned long long old_mtime)
- {
- struct seg_entry *se;
- unsigned int segno = GET_SEGNO(sbi, blkaddr);
- unsigned long long ctime = get_mtime(sbi, false);
- unsigned long long mtime = old_mtime ? old_mtime : ctime;
- if (segno == NULL_SEGNO)
- return;
- se = get_seg_entry(sbi, segno);
- if (!se->mtime)
- se->mtime = mtime;
- else
- se->mtime = div_u64(se->mtime * se->valid_blocks + mtime,
- se->valid_blocks + 1);
- if (ctime > SIT_I(sbi)->max_mtime)
- SIT_I(sbi)->max_mtime = ctime;
- }
- static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del)
- {
- struct seg_entry *se;
- unsigned int segno, offset;
- long int new_vblocks;
- bool exist;
- #ifdef CONFIG_F2FS_CHECK_FS
- bool mir_exist;
- #endif
- segno = GET_SEGNO(sbi, blkaddr);
- se = get_seg_entry(sbi, segno);
- new_vblocks = se->valid_blocks + del;
- offset = GET_BLKOFF_FROM_SEG0(sbi, blkaddr);
- f2fs_bug_on(sbi, (new_vblocks < 0 ||
- (new_vblocks > f2fs_usable_blks_in_seg(sbi, segno))));
- se->valid_blocks = new_vblocks;
- /* Update valid block bitmap */
- if (del > 0) {
- exist = f2fs_test_and_set_bit(offset, se->cur_valid_map);
- #ifdef CONFIG_F2FS_CHECK_FS
- mir_exist = f2fs_test_and_set_bit(offset,
- se->cur_valid_map_mir);
- if (unlikely(exist != mir_exist)) {
- f2fs_err(sbi, "Inconsistent error when setting bitmap, blk:%u, old bit:%d",
- blkaddr, exist);
- f2fs_bug_on(sbi, 1);
- }
- #endif
- if (unlikely(exist)) {
- f2fs_err(sbi, "Bitmap was wrongly set, blk:%u",
- blkaddr);
- f2fs_bug_on(sbi, 1);
- se->valid_blocks--;
- del = 0;
- }
- if (!f2fs_test_and_set_bit(offset, se->discard_map))
- sbi->discard_blks--;
- /*
- * SSR should never reuse block which is checkpointed
- * or newly invalidated.
- */
- if (!is_sbi_flag_set(sbi, SBI_CP_DISABLED)) {
- if (!f2fs_test_and_set_bit(offset, se->ckpt_valid_map))
- se->ckpt_valid_blocks++;
- }
- } else {
- exist = f2fs_test_and_clear_bit(offset, se->cur_valid_map);
- #ifdef CONFIG_F2FS_CHECK_FS
- mir_exist = f2fs_test_and_clear_bit(offset,
- se->cur_valid_map_mir);
- if (unlikely(exist != mir_exist)) {
- f2fs_err(sbi, "Inconsistent error when clearing bitmap, blk:%u, old bit:%d",
- blkaddr, exist);
- f2fs_bug_on(sbi, 1);
- }
- #endif
- if (unlikely(!exist)) {
- f2fs_err(sbi, "Bitmap was wrongly cleared, blk:%u",
- blkaddr);
- f2fs_bug_on(sbi, 1);
- se->valid_blocks++;
- del = 0;
- } else if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) {
- /*
- * If checkpoints are off, we must not reuse data that
- * was used in the previous checkpoint. If it was used
- * before, we must track that to know how much space we
- * really have.
- */
- if (f2fs_test_bit(offset, se->ckpt_valid_map)) {
- spin_lock(&sbi->stat_lock);
- sbi->unusable_block_count++;
- spin_unlock(&sbi->stat_lock);
- }
- }
- if (f2fs_test_and_clear_bit(offset, se->discard_map))
- sbi->discard_blks++;
- }
- if (!f2fs_test_bit(offset, se->ckpt_valid_map))
- se->ckpt_valid_blocks += del;
- __mark_sit_entry_dirty(sbi, segno);
- /* update total number of valid blocks to be written in ckpt area */
- SIT_I(sbi)->written_valid_blocks += del;
- if (__is_large_section(sbi))
- get_sec_entry(sbi, segno)->valid_blocks += del;
- }
- void f2fs_invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr)
- {
- unsigned int segno = GET_SEGNO(sbi, addr);
- struct sit_info *sit_i = SIT_I(sbi);
- f2fs_bug_on(sbi, addr == NULL_ADDR);
- if (addr == NEW_ADDR || addr == COMPRESS_ADDR)
- return;
- invalidate_mapping_pages(META_MAPPING(sbi), addr, addr);
- f2fs_invalidate_compress_page(sbi, addr);
- /* add it into sit main buffer */
- down_write(&sit_i->sentry_lock);
- update_segment_mtime(sbi, addr, 0);
- update_sit_entry(sbi, addr, -1);
- /* add it into dirty seglist */
- locate_dirty_segment(sbi, segno);
- up_write(&sit_i->sentry_lock);
- }
- bool f2fs_is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr)
- {
- struct sit_info *sit_i = SIT_I(sbi);
- unsigned int segno, offset;
- struct seg_entry *se;
- bool is_cp = false;
- if (!__is_valid_data_blkaddr(blkaddr))
- return true;
- down_read(&sit_i->sentry_lock);
- segno = GET_SEGNO(sbi, blkaddr);
- se = get_seg_entry(sbi, segno);
- offset = GET_BLKOFF_FROM_SEG0(sbi, blkaddr);
- if (f2fs_test_bit(offset, se->ckpt_valid_map))
- is_cp = true;
- up_read(&sit_i->sentry_lock);
- return is_cp;
- }
- /*
- * This function should be resided under the curseg_mutex lock
- */
- static void __add_sum_entry(struct f2fs_sb_info *sbi, int type,
- struct f2fs_summary *sum)
- {
- struct curseg_info *curseg = CURSEG_I(sbi, type);
- void *addr = curseg->sum_blk;
- addr += curseg->next_blkoff * sizeof(struct f2fs_summary);
- memcpy(addr, sum, sizeof(struct f2fs_summary));
- }
- /*
- * Calculate the number of current summary pages for writing
- */
- int f2fs_npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra)
- {
- int valid_sum_count = 0;
- int i, sum_in_page;
- for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) {
- if (sbi->ckpt->alloc_type[i] == SSR)
- valid_sum_count += sbi->blocks_per_seg;
- else {
- if (for_ra)
- valid_sum_count += le16_to_cpu(
- F2FS_CKPT(sbi)->cur_data_blkoff[i]);
- else
- valid_sum_count += curseg_blkoff(sbi, i);
- }
- }
- sum_in_page = (PAGE_SIZE - 2 * SUM_JOURNAL_SIZE -
- SUM_FOOTER_SIZE) / SUMMARY_SIZE;
- if (valid_sum_count <= sum_in_page)
- return 1;
- else if ((valid_sum_count - sum_in_page) <=
- (PAGE_SIZE - SUM_FOOTER_SIZE) / SUMMARY_SIZE)
- return 2;
- return 3;
- }
- /*
- * Caller should put this summary page
- */
- struct page *f2fs_get_sum_page(struct f2fs_sb_info *sbi, unsigned int segno)
- {
- if (unlikely(f2fs_cp_error(sbi)))
- return ERR_PTR(-EIO);
- return f2fs_get_meta_page_retry(sbi, GET_SUM_BLOCK(sbi, segno));
- }
- void f2fs_update_meta_page(struct f2fs_sb_info *sbi,
- void *src, block_t blk_addr)
- {
- struct page *page = f2fs_grab_meta_page(sbi, blk_addr);
- memcpy(page_address(page), src, PAGE_SIZE);
- set_page_dirty(page);
- f2fs_put_page(page, 1);
- }
- static void write_sum_page(struct f2fs_sb_info *sbi,
- struct f2fs_summary_block *sum_blk, block_t blk_addr)
- {
- f2fs_update_meta_page(sbi, (void *)sum_blk, blk_addr);
- }
- static void write_current_sum_page(struct f2fs_sb_info *sbi,
- int type, block_t blk_addr)
- {
- struct curseg_info *curseg = CURSEG_I(sbi, type);
- struct page *page = f2fs_grab_meta_page(sbi, blk_addr);
- struct f2fs_summary_block *src = curseg->sum_blk;
- struct f2fs_summary_block *dst;
- dst = (struct f2fs_summary_block *)page_address(page);
- memset(dst, 0, PAGE_SIZE);
- mutex_lock(&curseg->curseg_mutex);
- down_read(&curseg->journal_rwsem);
- memcpy(&dst->journal, curseg->journal, SUM_JOURNAL_SIZE);
- up_read(&curseg->journal_rwsem);
- memcpy(dst->entries, src->entries, SUM_ENTRY_SIZE);
- memcpy(&dst->footer, &src->footer, SUM_FOOTER_SIZE);
- mutex_unlock(&curseg->curseg_mutex);
- set_page_dirty(page);
- f2fs_put_page(page, 1);
- }
- static int is_next_segment_free(struct f2fs_sb_info *sbi,
- struct curseg_info *curseg, int type)
- {
- unsigned int segno = curseg->segno + 1;
- struct free_segmap_info *free_i = FREE_I(sbi);
- if (segno < MAIN_SEGS(sbi) && segno % sbi->segs_per_sec)
- return !test_bit(segno, free_i->free_segmap);
- return 0;
- }
- /*
- * Find a new segment from the free segments bitmap to right order
- * This function should be returned with success, otherwise BUG
- */
- static void get_new_segment(struct f2fs_sb_info *sbi,
- unsigned int *newseg, bool new_sec, int dir)
- {
- struct free_segmap_info *free_i = FREE_I(sbi);
- unsigned int segno, secno, zoneno;
- unsigned int total_zones = MAIN_SECS(sbi) / sbi->secs_per_zone;
- unsigned int hint = GET_SEC_FROM_SEG(sbi, *newseg);
- unsigned int old_zoneno = GET_ZONE_FROM_SEG(sbi, *newseg);
- unsigned int left_start = hint;
- bool init = true;
- int go_left = 0;
- int i;
- spin_lock(&free_i->segmap_lock);
- if (!new_sec && ((*newseg + 1) % sbi->segs_per_sec)) {
- segno = find_next_zero_bit(free_i->free_segmap,
- GET_SEG_FROM_SEC(sbi, hint + 1), *newseg + 1);
- if (segno < GET_SEG_FROM_SEC(sbi, hint + 1))
- goto got_it;
- }
- find_other_zone:
- secno = find_next_zero_bit(free_i->free_secmap, MAIN_SECS(sbi), hint);
- if (secno >= MAIN_SECS(sbi)) {
- if (dir == ALLOC_RIGHT) {
- secno = find_next_zero_bit(free_i->free_secmap,
- MAIN_SECS(sbi), 0);
- f2fs_bug_on(sbi, secno >= MAIN_SECS(sbi));
- } else {
- go_left = 1;
- left_start = hint - 1;
- }
- }
- if (go_left == 0)
- goto skip_left;
- while (test_bit(left_start, free_i->free_secmap)) {
- if (left_start > 0) {
- left_start--;
- continue;
- }
- left_start = find_next_zero_bit(free_i->free_secmap,
- MAIN_SECS(sbi), 0);
- f2fs_bug_on(sbi, left_start >= MAIN_SECS(sbi));
- break;
- }
- secno = left_start;
- skip_left:
- segno = GET_SEG_FROM_SEC(sbi, secno);
- zoneno = GET_ZONE_FROM_SEC(sbi, secno);
- /* give up on finding another zone */
- if (!init)
- goto got_it;
- if (sbi->secs_per_zone == 1)
- goto got_it;
- if (zoneno == old_zoneno)
- goto got_it;
- if (dir == ALLOC_LEFT) {
- if (!go_left && zoneno + 1 >= total_zones)
- goto got_it;
- if (go_left && zoneno == 0)
- goto got_it;
- }
- for (i = 0; i < NR_CURSEG_TYPE; i++)
- if (CURSEG_I(sbi, i)->zone == zoneno)
- break;
- if (i < NR_CURSEG_TYPE) {
- /* zone is in user, try another */
- if (go_left)
- hint = zoneno * sbi->secs_per_zone - 1;
- else if (zoneno + 1 >= total_zones)
- hint = 0;
- else
- hint = (zoneno + 1) * sbi->secs_per_zone;
- init = false;
- goto find_other_zone;
- }
- got_it:
- /* set it as dirty segment in free segmap */
- f2fs_bug_on(sbi, test_bit(segno, free_i->free_segmap));
- __set_inuse(sbi, segno);
- *newseg = segno;
- spin_unlock(&free_i->segmap_lock);
- }
- static void reset_curseg(struct f2fs_sb_info *sbi, int type, int modified)
- {
- struct curseg_info *curseg = CURSEG_I(sbi, type);
- struct summary_footer *sum_footer;
- unsigned short seg_type = curseg->seg_type;
- curseg->inited = true;
- curseg->segno = curseg->next_segno;
- curseg->zone = GET_ZONE_FROM_SEG(sbi, curseg->segno);
- curseg->next_blkoff = 0;
- curseg->next_segno = NULL_SEGNO;
- sum_footer = &(curseg->sum_blk->footer);
- memset(sum_footer, 0, sizeof(struct summary_footer));
- sanity_check_seg_type(sbi, seg_type);
- if (IS_DATASEG(seg_type))
- SET_SUM_TYPE(sum_footer, SUM_TYPE_DATA);
- if (IS_NODESEG(seg_type))
- SET_SUM_TYPE(sum_footer, SUM_TYPE_NODE);
- __set_sit_entry_type(sbi, seg_type, curseg->segno, modified);
- }
- static unsigned int __get_next_segno(struct f2fs_sb_info *sbi, int type)
- {
- struct curseg_info *curseg = CURSEG_I(sbi, type);
- unsigned short seg_type = curseg->seg_type;
- sanity_check_seg_type(sbi, seg_type);
- /* if segs_per_sec is large than 1, we need to keep original policy. */
- if (__is_large_section(sbi))
- return curseg->segno;
- /* inmem log may not locate on any segment after mount */
- if (!curseg->inited)
- return 0;
- if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
- return 0;
- if (test_opt(sbi, NOHEAP) &&
- (seg_type == CURSEG_HOT_DATA || IS_NODESEG(seg_type)))
- return 0;
- if (SIT_I(sbi)->last_victim[ALLOC_NEXT])
- return SIT_I(sbi)->last_victim[ALLOC_NEXT];
- /* find segments from 0 to reuse freed segments */
- if (F2FS_OPTION(sbi).alloc_mode == ALLOC_MODE_REUSE)
- return 0;
- return curseg->segno;
- }
- /*
- * Allocate a current working segment.
- * This function always allocates a free segment in LFS manner.
- */
- static void new_curseg(struct f2fs_sb_info *sbi, int type, bool new_sec)
- {
- struct curseg_info *curseg = CURSEG_I(sbi, type);
- unsigned short seg_type = curseg->seg_type;
- unsigned int segno = curseg->segno;
- int dir = ALLOC_LEFT;
- if (curseg->inited)
- write_sum_page(sbi, curseg->sum_blk,
- GET_SUM_BLOCK(sbi, segno));
- if (seg_type == CURSEG_WARM_DATA || seg_type == CURSEG_COLD_DATA)
- dir = ALLOC_RIGHT;
- if (test_opt(sbi, NOHEAP))
- dir = ALLOC_RIGHT;
- segno = __get_next_segno(sbi, type);
- get_new_segment(sbi, &segno, new_sec, dir);
- curseg->next_segno = segno;
- reset_curseg(sbi, type, 1);
- curseg->alloc_type = LFS;
- }
- static int __next_free_blkoff(struct f2fs_sb_info *sbi,
- int segno, block_t start)
- {
- struct seg_entry *se = get_seg_entry(sbi, segno);
- int entries = SIT_VBLOCK_MAP_SIZE / sizeof(unsigned long);
- unsigned long *target_map = SIT_I(sbi)->tmp_map;
- unsigned long *ckpt_map = (unsigned long *)se->ckpt_valid_map;
- unsigned long *cur_map = (unsigned long *)se->cur_valid_map;
- int i;
- for (i = 0; i < entries; i++)
- target_map[i] = ckpt_map[i] | cur_map[i];
- return __find_rev_next_zero_bit(target_map, sbi->blocks_per_seg, start);
- }
- /*
- * If a segment is written by LFS manner, next block offset is just obtained
- * by increasing the current block offset. However, if a segment is written by
- * SSR manner, next block offset obtained by calling __next_free_blkoff
- */
- static void __refresh_next_blkoff(struct f2fs_sb_info *sbi,
- struct curseg_info *seg)
- {
- if (seg->alloc_type == SSR)
- seg->next_blkoff =
- __next_free_blkoff(sbi, seg->segno,
- seg->next_blkoff + 1);
- else
- seg->next_blkoff++;
- }
- bool f2fs_segment_has_free_slot(struct f2fs_sb_info *sbi, int segno)
- {
- return __next_free_blkoff(sbi, segno, 0) < sbi->blocks_per_seg;
- }
- /*
- * This function always allocates a used segment(from dirty seglist) by SSR
- * manner, so it should recover the existing segment information of valid blocks
- */
- static void change_curseg(struct f2fs_sb_info *sbi, int type, bool flush)
- {
- struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
- struct curseg_info *curseg = CURSEG_I(sbi, type);
- unsigned int new_segno = curseg->next_segno;
- struct f2fs_summary_block *sum_node;
- struct page *sum_page;
- if (flush)
- write_sum_page(sbi, curseg->sum_blk,
- GET_SUM_BLOCK(sbi, curseg->segno));
- __set_test_and_inuse(sbi, new_segno);
- mutex_lock(&dirty_i->seglist_lock);
- __remove_dirty_segment(sbi, new_segno, PRE);
- __remove_dirty_segment(sbi, new_segno, DIRTY);
- mutex_unlock(&dirty_i->seglist_lock);
- reset_curseg(sbi, type, 1);
- curseg->alloc_type = SSR;
- curseg->next_blkoff = __next_free_blkoff(sbi, curseg->segno, 0);
- sum_page = f2fs_get_sum_page(sbi, new_segno);
- if (IS_ERR(sum_page)) {
- /* GC won't be able to use stale summary pages by cp_error */
- memset(curseg->sum_blk, 0, SUM_ENTRY_SIZE);
- return;
- }
- sum_node = (struct f2fs_summary_block *)page_address(sum_page);
- memcpy(curseg->sum_blk, sum_node, SUM_ENTRY_SIZE);
- f2fs_put_page(sum_page, 1);
- }
- static int get_ssr_segment(struct f2fs_sb_info *sbi, int type,
- int alloc_mode, unsigned long long age);
- static void get_atssr_segment(struct f2fs_sb_info *sbi, int type,
- int target_type, int alloc_mode,
- unsigned long long age)
- {
- struct curseg_info *curseg = CURSEG_I(sbi, type);
- curseg->seg_type = target_type;
- if (get_ssr_segment(sbi, type, alloc_mode, age)) {
- struct seg_entry *se = get_seg_entry(sbi, curseg->next_segno);
- curseg->seg_type = se->type;
- change_curseg(sbi, type, true);
- } else {
- /* allocate cold segment by default */
- curseg->seg_type = CURSEG_COLD_DATA;
- new_curseg(sbi, type, true);
- }
- stat_inc_seg_type(sbi, curseg);
- }
- static void __f2fs_init_atgc_curseg(struct f2fs_sb_info *sbi)
- {
- struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_ALL_DATA_ATGC);
- if (!sbi->am.atgc_enabled)
- return;
- f2fs_down_read(&SM_I(sbi)->curseg_lock);
- mutex_lock(&curseg->curseg_mutex);
- down_write(&SIT_I(sbi)->sentry_lock);
- get_atssr_segment(sbi, CURSEG_ALL_DATA_ATGC, CURSEG_COLD_DATA, SSR, 0);
- up_write(&SIT_I(sbi)->sentry_lock);
- mutex_unlock(&curseg->curseg_mutex);
- f2fs_up_read(&SM_I(sbi)->curseg_lock);
- }
- void f2fs_init_inmem_curseg(struct f2fs_sb_info *sbi)
- {
- __f2fs_init_atgc_curseg(sbi);
- }
- static void __f2fs_save_inmem_curseg(struct f2fs_sb_info *sbi, int type)
- {
- struct curseg_info *curseg = CURSEG_I(sbi, type);
- mutex_lock(&curseg->curseg_mutex);
- if (!curseg->inited)
- goto out;
- if (get_valid_blocks(sbi, curseg->segno, false)) {
- write_sum_page(sbi, curseg->sum_blk,
- GET_SUM_BLOCK(sbi, curseg->segno));
- } else {
- mutex_lock(&DIRTY_I(sbi)->seglist_lock);
- __set_test_and_free(sbi, curseg->segno, true);
- mutex_unlock(&DIRTY_I(sbi)->seglist_lock);
- }
- out:
- mutex_unlock(&curseg->curseg_mutex);
- }
- void f2fs_save_inmem_curseg(struct f2fs_sb_info *sbi)
- {
- __f2fs_save_inmem_curseg(sbi, CURSEG_COLD_DATA_PINNED);
- if (sbi->am.atgc_enabled)
- __f2fs_save_inmem_curseg(sbi, CURSEG_ALL_DATA_ATGC);
- }
- static void __f2fs_restore_inmem_curseg(struct f2fs_sb_info *sbi, int type)
- {
- struct curseg_info *curseg = CURSEG_I(sbi, type);
- mutex_lock(&curseg->curseg_mutex);
- if (!curseg->inited)
- goto out;
- if (get_valid_blocks(sbi, curseg->segno, false))
- goto out;
- mutex_lock(&DIRTY_I(sbi)->seglist_lock);
- __set_test_and_inuse(sbi, curseg->segno);
- mutex_unlock(&DIRTY_I(sbi)->seglist_lock);
- out:
- mutex_unlock(&curseg->curseg_mutex);
- }
- void f2fs_restore_inmem_curseg(struct f2fs_sb_info *sbi)
- {
- __f2fs_restore_inmem_curseg(sbi, CURSEG_COLD_DATA_PINNED);
- if (sbi->am.atgc_enabled)
- __f2fs_restore_inmem_curseg(sbi, CURSEG_ALL_DATA_ATGC);
- }
- static int get_ssr_segment(struct f2fs_sb_info *sbi, int type,
- int alloc_mode, unsigned long long age)
- {
- struct curseg_info *curseg = CURSEG_I(sbi, type);
- const struct victim_selection *v_ops = DIRTY_I(sbi)->v_ops;
- unsigned segno = NULL_SEGNO;
- unsigned short seg_type = curseg->seg_type;
- int i, cnt;
- bool reversed = false;
- sanity_check_seg_type(sbi, seg_type);
- /* f2fs_need_SSR() already forces to do this */
- if (!v_ops->get_victim(sbi, &segno, BG_GC, seg_type, alloc_mode, age)) {
- curseg->next_segno = segno;
- return 1;
- }
- /* For node segments, let's do SSR more intensively */
- if (IS_NODESEG(seg_type)) {
- if (seg_type >= CURSEG_WARM_NODE) {
- reversed = true;
- i = CURSEG_COLD_NODE;
- } else {
- i = CURSEG_HOT_NODE;
- }
- cnt = NR_CURSEG_NODE_TYPE;
- } else {
- if (seg_type >= CURSEG_WARM_DATA) {
- reversed = true;
- i = CURSEG_COLD_DATA;
- } else {
- i = CURSEG_HOT_DATA;
- }
- cnt = NR_CURSEG_DATA_TYPE;
- }
- for (; cnt-- > 0; reversed ? i-- : i++) {
- if (i == seg_type)
- continue;
- if (!v_ops->get_victim(sbi, &segno, BG_GC, i, alloc_mode, age)) {
- curseg->next_segno = segno;
- return 1;
- }
- }
- /* find valid_blocks=0 in dirty list */
- if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) {
- segno = get_free_segment(sbi);
- if (segno != NULL_SEGNO) {
- curseg->next_segno = segno;
- return 1;
- }
- }
- return 0;
- }
- /*
- * flush out current segment and replace it with new segment
- * This function should be returned with success, otherwise BUG
- */
- static void allocate_segment_by_default(struct f2fs_sb_info *sbi,
- int type, bool force)
- {
- struct curseg_info *curseg = CURSEG_I(sbi, type);
- if (force)
- new_curseg(sbi, type, true);
- else if (!is_set_ckpt_flags(sbi, CP_CRC_RECOVERY_FLAG) &&
- curseg->seg_type == CURSEG_WARM_NODE)
- new_curseg(sbi, type, false);
- else if (curseg->alloc_type == LFS &&
- is_next_segment_free(sbi, curseg, type) &&
- likely(!is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
- new_curseg(sbi, type, false);
- else if (f2fs_need_SSR(sbi) &&
- get_ssr_segment(sbi, type, SSR, 0))
- change_curseg(sbi, type, true);
- else
- new_curseg(sbi, type, false);
- stat_inc_seg_type(sbi, curseg);
- }
- void f2fs_allocate_segment_for_resize(struct f2fs_sb_info *sbi, int type,
- unsigned int start, unsigned int end)
- {
- struct curseg_info *curseg = CURSEG_I(sbi, type);
- unsigned int segno;
- f2fs_down_read(&SM_I(sbi)->curseg_lock);
- mutex_lock(&curseg->curseg_mutex);
- down_write(&SIT_I(sbi)->sentry_lock);
- segno = CURSEG_I(sbi, type)->segno;
- if (segno < start || segno > end)
- goto unlock;
- if (f2fs_need_SSR(sbi) && get_ssr_segment(sbi, type, SSR, 0))
- change_curseg(sbi, type, true);
- else
- new_curseg(sbi, type, true);
- stat_inc_seg_type(sbi, curseg);
- locate_dirty_segment(sbi, segno);
- unlock:
- up_write(&SIT_I(sbi)->sentry_lock);
- if (segno != curseg->segno)
- f2fs_notice(sbi, "For resize: curseg of type %d: %u ==> %u",
- type, segno, curseg->segno);
- mutex_unlock(&curseg->curseg_mutex);
- f2fs_up_read(&SM_I(sbi)->curseg_lock);
- }
- static void __allocate_new_segment(struct f2fs_sb_info *sbi, int type,
- bool new_sec, bool force)
- {
- struct curseg_info *curseg = CURSEG_I(sbi, type);
- unsigned int old_segno;
- if (!curseg->inited)
- goto alloc;
- if (force || curseg->next_blkoff ||
- get_valid_blocks(sbi, curseg->segno, new_sec))
- goto alloc;
- if (!get_ckpt_valid_blocks(sbi, curseg->segno, new_sec))
- return;
- alloc:
- old_segno = curseg->segno;
- SIT_I(sbi)->s_ops->allocate_segment(sbi, type, true);
- locate_dirty_segment(sbi, old_segno);
- }
- static void __allocate_new_section(struct f2fs_sb_info *sbi,
- int type, bool force)
- {
- __allocate_new_segment(sbi, type, true, force);
- }
- void f2fs_allocate_new_section(struct f2fs_sb_info *sbi, int type, bool force)
- {
- f2fs_down_read(&SM_I(sbi)->curseg_lock);
- down_write(&SIT_I(sbi)->sentry_lock);
- __allocate_new_section(sbi, type, force);
- up_write(&SIT_I(sbi)->sentry_lock);
- f2fs_up_read(&SM_I(sbi)->curseg_lock);
- }
- void f2fs_allocate_new_segments(struct f2fs_sb_info *sbi)
- {
- int i;
- f2fs_down_read(&SM_I(sbi)->curseg_lock);
- down_write(&SIT_I(sbi)->sentry_lock);
- for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++)
- __allocate_new_segment(sbi, i, false, false);
- up_write(&SIT_I(sbi)->sentry_lock);
- f2fs_up_read(&SM_I(sbi)->curseg_lock);
- }
- static const struct segment_allocation default_salloc_ops = {
- .allocate_segment = allocate_segment_by_default,
- };
- bool f2fs_exist_trim_candidates(struct f2fs_sb_info *sbi,
- struct cp_control *cpc)
- {
- __u64 trim_start = cpc->trim_start;
- bool has_candidate = false;
- down_write(&SIT_I(sbi)->sentry_lock);
- for (; cpc->trim_start <= cpc->trim_end; cpc->trim_start++) {
- if (add_discard_addrs(sbi, cpc, true)) {
- has_candidate = true;
- break;
- }
- }
- up_write(&SIT_I(sbi)->sentry_lock);
- cpc->trim_start = trim_start;
- return has_candidate;
- }
- static unsigned int __issue_discard_cmd_range(struct f2fs_sb_info *sbi,
- struct discard_policy *dpolicy,
- unsigned int start, unsigned int end)
- {
- struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
- struct discard_cmd *prev_dc = NULL, *next_dc = NULL;
- struct rb_node **insert_p = NULL, *insert_parent = NULL;
- struct discard_cmd *dc;
- struct blk_plug plug;
- int issued;
- unsigned int trimmed = 0;
- next:
- issued = 0;
- mutex_lock(&dcc->cmd_lock);
- if (unlikely(dcc->rbtree_check))
- f2fs_bug_on(sbi, !f2fs_check_rb_tree_consistence(sbi,
- &dcc->root, false));
- dc = (struct discard_cmd *)f2fs_lookup_rb_tree_ret(&dcc->root,
- NULL, start,
- (struct rb_entry **)&prev_dc,
- (struct rb_entry **)&next_dc,
- &insert_p, &insert_parent, true, NULL);
- if (!dc)
- dc = next_dc;
- blk_start_plug(&plug);
- while (dc && dc->lstart <= end) {
- struct rb_node *node;
- int err = 0;
- if (dc->len < dpolicy->granularity)
- goto skip;
- if (dc->state != D_PREP) {
- list_move_tail(&dc->list, &dcc->fstrim_list);
- goto skip;
- }
- err = __submit_discard_cmd(sbi, dpolicy, dc, &issued);
- if (issued >= dpolicy->max_requests) {
- start = dc->lstart + dc->len;
- if (err)
- __remove_discard_cmd(sbi, dc);
- blk_finish_plug(&plug);
- mutex_unlock(&dcc->cmd_lock);
- trimmed += __wait_all_discard_cmd(sbi, NULL);
- congestion_wait(BLK_RW_ASYNC, DEFAULT_IO_TIMEOUT);
- goto next;
- }
- skip:
- node = rb_next(&dc->rb_node);
- if (err)
- __remove_discard_cmd(sbi, dc);
- dc = rb_entry_safe(node, struct discard_cmd, rb_node);
- if (fatal_signal_pending(current))
- break;
- }
- blk_finish_plug(&plug);
- mutex_unlock(&dcc->cmd_lock);
- return trimmed;
- }
- int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range)
- {
- __u64 start = F2FS_BYTES_TO_BLK(range->start);
- __u64 end = start + F2FS_BYTES_TO_BLK(range->len) - 1;
- unsigned int start_segno, end_segno;
- block_t start_block, end_block;
- struct cp_control cpc;
- struct discard_policy dpolicy;
- unsigned long long trimmed = 0;
- int err = 0;
- bool need_align = f2fs_lfs_mode(sbi) && __is_large_section(sbi);
- if (start >= MAX_BLKADDR(sbi) || range->len < sbi->blocksize)
- return -EINVAL;
- if (end < MAIN_BLKADDR(sbi))
- goto out;
- if (is_sbi_flag_set(sbi, SBI_NEED_FSCK)) {
- f2fs_warn(sbi, "Found FS corruption, run fsck to fix.");
- return -EFSCORRUPTED;
- }
- /* start/end segment number in main_area */
- start_segno = (start <= MAIN_BLKADDR(sbi)) ? 0 : GET_SEGNO(sbi, start);
- end_segno = (end >= MAX_BLKADDR(sbi)) ? MAIN_SEGS(sbi) - 1 :
- GET_SEGNO(sbi, end);
- if (need_align) {
- start_segno = rounddown(start_segno, sbi->segs_per_sec);
- end_segno = roundup(end_segno + 1, sbi->segs_per_sec) - 1;
- }
- cpc.reason = CP_DISCARD;
- cpc.trim_minlen = max_t(__u64, 1, F2FS_BYTES_TO_BLK(range->minlen));
- cpc.trim_start = start_segno;
- cpc.trim_end = end_segno;
- if (sbi->discard_blks == 0)
- goto out;
- f2fs_down_write(&sbi->gc_lock);
- err = f2fs_write_checkpoint(sbi, &cpc);
- f2fs_up_write(&sbi->gc_lock);
- if (err)
- goto out;
- /*
- * We filed discard candidates, but actually we don't need to wait for
- * all of them, since they'll be issued in idle time along with runtime
- * discard option. User configuration looks like using runtime discard
- * or periodic fstrim instead of it.
- */
- if (f2fs_realtime_discard_enable(sbi))
- goto out;
- start_block = START_BLOCK(sbi, start_segno);
- end_block = START_BLOCK(sbi, end_segno + 1);
- __init_discard_policy(sbi, &dpolicy, DPOLICY_FSTRIM, cpc.trim_minlen);
- trimmed = __issue_discard_cmd_range(sbi, &dpolicy,
- start_block, end_block);
- trimmed += __wait_discard_cmd_range(sbi, &dpolicy,
- start_block, end_block);
- out:
- if (!err)
- range->len = F2FS_BLK_TO_BYTES(trimmed);
- return err;
- }
- static bool __has_curseg_space(struct f2fs_sb_info *sbi,
- struct curseg_info *curseg)
- {
- return curseg->next_blkoff < f2fs_usable_blks_in_seg(sbi,
- curseg->segno);
- }
- int f2fs_rw_hint_to_seg_type(enum rw_hint hint)
- {
- switch (hint) {
- case WRITE_LIFE_SHORT:
- return CURSEG_HOT_DATA;
- case WRITE_LIFE_EXTREME:
- return CURSEG_COLD_DATA;
- default:
- return CURSEG_WARM_DATA;
- }
- }
- /* This returns write hints for each segment type. This hints will be
- * passed down to block layer. There are mapping tables which depend on
- * the mount option 'whint_mode'.
- *
- * 1) whint_mode=off. F2FS only passes down WRITE_LIFE_NOT_SET.
- *
- * 2) whint_mode=user-based. F2FS tries to pass down hints given by users.
- *
- * User F2FS Block
- * ---- ---- -----
- * META WRITE_LIFE_NOT_SET
- * HOT_NODE "
- * WARM_NODE "
- * COLD_NODE "
- * ioctl(COLD) COLD_DATA WRITE_LIFE_EXTREME
- * extension list " "
- *
- * -- buffered io
- * WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME
- * WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT
- * WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET
- * WRITE_LIFE_NONE " "
- * WRITE_LIFE_MEDIUM " "
- * WRITE_LIFE_LONG " "
- *
- * -- direct io
- * WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME
- * WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT
- * WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET
- * WRITE_LIFE_NONE " WRITE_LIFE_NONE
- * WRITE_LIFE_MEDIUM " WRITE_LIFE_MEDIUM
- * WRITE_LIFE_LONG " WRITE_LIFE_LONG
- *
- * 3) whint_mode=fs-based. F2FS passes down hints with its policy.
- *
- * User F2FS Block
- * ---- ---- -----
- * META WRITE_LIFE_MEDIUM;
- * HOT_NODE WRITE_LIFE_NOT_SET
- * WARM_NODE "
- * COLD_NODE WRITE_LIFE_NONE
- * ioctl(COLD) COLD_DATA WRITE_LIFE_EXTREME
- * extension list " "
- *
- * -- buffered io
- * WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME
- * WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT
- * WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_LONG
- * WRITE_LIFE_NONE " "
- * WRITE_LIFE_MEDIUM " "
- * WRITE_LIFE_LONG " "
- *
- * -- direct io
- * WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME
- * WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT
- * WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET
- * WRITE_LIFE_NONE " WRITE_LIFE_NONE
- * WRITE_LIFE_MEDIUM " WRITE_LIFE_MEDIUM
- * WRITE_LIFE_LONG " WRITE_LIFE_LONG
- */
- enum rw_hint f2fs_io_type_to_rw_hint(struct f2fs_sb_info *sbi,
- enum page_type type, enum temp_type temp)
- {
- if (F2FS_OPTION(sbi).whint_mode == WHINT_MODE_USER) {
- if (type == DATA) {
- if (temp == WARM)
- return WRITE_LIFE_NOT_SET;
- else if (temp == HOT)
- return WRITE_LIFE_SHORT;
- else if (temp == COLD)
- return WRITE_LIFE_EXTREME;
- } else {
- return WRITE_LIFE_NOT_SET;
- }
- } else if (F2FS_OPTION(sbi).whint_mode == WHINT_MODE_FS) {
- if (type == DATA) {
- if (temp == WARM)
- return WRITE_LIFE_LONG;
- else if (temp == HOT)
- return WRITE_LIFE_SHORT;
- else if (temp == COLD)
- return WRITE_LIFE_EXTREME;
- } else if (type == NODE) {
- if (temp == WARM || temp == HOT)
- return WRITE_LIFE_NOT_SET;
- else if (temp == COLD)
- return WRITE_LIFE_NONE;
- } else if (type == META) {
- return WRITE_LIFE_MEDIUM;
- }
- }
- return WRITE_LIFE_NOT_SET;
- }
- static int __get_segment_type_2(struct f2fs_io_info *fio)
- {
- if (fio->type == DATA)
- return CURSEG_HOT_DATA;
- else
- return CURSEG_HOT_NODE;
- }
- static int __get_segment_type_4(struct f2fs_io_info *fio)
- {
- if (fio->type == DATA) {
- struct inode *inode = fio->page->mapping->host;
- if (S_ISDIR(inode->i_mode))
- return CURSEG_HOT_DATA;
- else
- return CURSEG_COLD_DATA;
- } else {
- if (IS_DNODE(fio->page) && is_cold_node(fio->page))
- return CURSEG_WARM_NODE;
- else
- return CURSEG_COLD_NODE;
- }
- }
- static int __get_segment_type_6(struct f2fs_io_info *fio)
- {
- if (fio->type == DATA) {
- struct inode *inode = fio->page->mapping->host;
- if (is_inode_flag_set(inode, FI_ALIGNED_WRITE))
- return CURSEG_COLD_DATA_PINNED;
- if (page_private_gcing(fio->page)) {
- if (fio->sbi->am.atgc_enabled &&
- (fio->io_type == FS_DATA_IO) &&
- (fio->sbi->gc_mode != GC_URGENT_HIGH))
- return CURSEG_ALL_DATA_ATGC;
- else
- return CURSEG_COLD_DATA;
- }
- if (file_is_cold(inode) || f2fs_need_compress_data(inode))
- return CURSEG_COLD_DATA;
- if (file_is_hot(inode) ||
- is_inode_flag_set(inode, FI_HOT_DATA) ||
- f2fs_is_atomic_file(inode) ||
- f2fs_is_volatile_file(inode))
- return CURSEG_HOT_DATA;
- return f2fs_rw_hint_to_seg_type(inode->i_write_hint);
- } else {
- if (IS_DNODE(fio->page))
- return is_cold_node(fio->page) ? CURSEG_WARM_NODE :
- CURSEG_HOT_NODE;
- return CURSEG_COLD_NODE;
- }
- }
- static int __get_segment_type(struct f2fs_io_info *fio)
- {
- int type = 0;
- switch (F2FS_OPTION(fio->sbi).active_logs) {
- case 2:
- type = __get_segment_type_2(fio);
- break;
- case 4:
- type = __get_segment_type_4(fio);
- break;
- case 6:
- type = __get_segment_type_6(fio);
- break;
- default:
- f2fs_bug_on(fio->sbi, true);
- }
- if (IS_HOT(type))
- fio->temp = HOT;
- else if (IS_WARM(type))
- fio->temp = WARM;
- else
- fio->temp = COLD;
- return type;
- }
- void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
- block_t old_blkaddr, block_t *new_blkaddr,
- struct f2fs_summary *sum, int type,
- struct f2fs_io_info *fio)
- {
- struct sit_info *sit_i = SIT_I(sbi);
- struct curseg_info *curseg = CURSEG_I(sbi, type);
- unsigned long long old_mtime;
- bool from_gc = (type == CURSEG_ALL_DATA_ATGC);
- struct seg_entry *se = NULL;
- f2fs_down_read(&SM_I(sbi)->curseg_lock);
- mutex_lock(&curseg->curseg_mutex);
- down_write(&sit_i->sentry_lock);
- if (from_gc) {
- f2fs_bug_on(sbi, GET_SEGNO(sbi, old_blkaddr) == NULL_SEGNO);
- se = get_seg_entry(sbi, GET_SEGNO(sbi, old_blkaddr));
- sanity_check_seg_type(sbi, se->type);
- f2fs_bug_on(sbi, IS_NODESEG(se->type));
- }
- *new_blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
- f2fs_bug_on(sbi, curseg->next_blkoff >= sbi->blocks_per_seg);
- f2fs_wait_discard_bio(sbi, *new_blkaddr);
- /*
- * __add_sum_entry should be resided under the curseg_mutex
- * because, this function updates a summary entry in the
- * current summary block.
- */
- __add_sum_entry(sbi, type, sum);
- __refresh_next_blkoff(sbi, curseg);
- stat_inc_block_count(sbi, curseg);
- if (from_gc) {
- old_mtime = get_segment_mtime(sbi, old_blkaddr);
- } else {
- update_segment_mtime(sbi, old_blkaddr, 0);
- old_mtime = 0;
- }
- update_segment_mtime(sbi, *new_blkaddr, old_mtime);
- /*
- * SIT information should be updated before segment allocation,
- * since SSR needs latest valid block information.
- */
- update_sit_entry(sbi, *new_blkaddr, 1);
- if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO)
- update_sit_entry(sbi, old_blkaddr, -1);
- if (!__has_curseg_space(sbi, curseg)) {
- if (from_gc)
- get_atssr_segment(sbi, type, se->type,
- AT_SSR, se->mtime);
- else
- sit_i->s_ops->allocate_segment(sbi, type, false);
- }
- /*
- * segment dirty status should be updated after segment allocation,
- * so we just need to update status only one time after previous
- * segment being closed.
- */
- locate_dirty_segment(sbi, GET_SEGNO(sbi, old_blkaddr));
- locate_dirty_segment(sbi, GET_SEGNO(sbi, *new_blkaddr));
- up_write(&sit_i->sentry_lock);
- if (page && IS_NODESEG(type)) {
- fill_node_footer_blkaddr(page, NEXT_FREE_BLKADDR(sbi, curseg));
- f2fs_inode_chksum_set(sbi, page);
- }
- if (fio) {
- struct f2fs_bio_info *io;
- if (F2FS_IO_ALIGNED(sbi))
- fio->retry = false;
- INIT_LIST_HEAD(&fio->list);
- fio->in_list = true;
- io = sbi->write_io[fio->type] + fio->temp;
- spin_lock(&io->io_lock);
- list_add_tail(&fio->list, &io->io_list);
- spin_unlock(&io->io_lock);
- }
- mutex_unlock(&curseg->curseg_mutex);
- f2fs_up_read(&SM_I(sbi)->curseg_lock);
- }
- static void update_device_state(struct f2fs_io_info *fio)
- {
- struct f2fs_sb_info *sbi = fio->sbi;
- unsigned int devidx;
- if (!f2fs_is_multi_device(sbi))
- return;
- devidx = f2fs_target_device_index(sbi, fio->new_blkaddr);
- /* update device state for fsync */
- f2fs_set_dirty_device(sbi, fio->ino, devidx, FLUSH_INO);
- /* update device state for checkpoint */
- if (!f2fs_test_bit(devidx, (char *)&sbi->dirty_device)) {
- spin_lock(&sbi->dev_lock);
- f2fs_set_bit(devidx, (char *)&sbi->dirty_device);
- spin_unlock(&sbi->dev_lock);
- }
- }
- static void do_write_page(struct f2fs_summary *sum, struct f2fs_io_info *fio)
- {
- int type = __get_segment_type(fio);
- bool keep_order = (f2fs_lfs_mode(fio->sbi) && type == CURSEG_COLD_DATA);
- if (keep_order)
- f2fs_down_read(&fio->sbi->io_order_lock);
- reallocate:
- f2fs_allocate_data_block(fio->sbi, fio->page, fio->old_blkaddr,
- &fio->new_blkaddr, sum, type, fio);
- if (GET_SEGNO(fio->sbi, fio->old_blkaddr) != NULL_SEGNO) {
- invalidate_mapping_pages(META_MAPPING(fio->sbi),
- fio->old_blkaddr, fio->old_blkaddr);
- f2fs_invalidate_compress_page(fio->sbi, fio->old_blkaddr);
- }
- /* writeout dirty page into bdev */
- f2fs_submit_page_write(fio);
- if (fio->retry) {
- fio->old_blkaddr = fio->new_blkaddr;
- goto reallocate;
- }
- update_device_state(fio);
- if (keep_order)
- f2fs_up_read(&fio->sbi->io_order_lock);
- }
- void f2fs_do_write_meta_page(struct f2fs_sb_info *sbi, struct page *page,
- enum iostat_type io_type)
- {
- struct f2fs_io_info fio = {
- .sbi = sbi,
- .type = META,
- .temp = HOT,
- .op = REQ_OP_WRITE,
- .op_flags = REQ_SYNC | REQ_META | REQ_PRIO,
- .old_blkaddr = page->index,
- .new_blkaddr = page->index,
- .page = page,
- .encrypted_page = NULL,
- .in_list = false,
- };
- if (unlikely(page->index >= MAIN_BLKADDR(sbi)))
- fio.op_flags &= ~REQ_META;
- set_page_writeback(page);
- ClearPageError(page);
- f2fs_submit_page_write(&fio);
- stat_inc_meta_count(sbi, page->index);
- f2fs_update_iostat(sbi, io_type, F2FS_BLKSIZE);
- }
- void f2fs_do_write_node_page(unsigned int nid, struct f2fs_io_info *fio)
- {
- struct f2fs_summary sum;
- set_summary(&sum, nid, 0, 0);
- do_write_page(&sum, fio);
- f2fs_update_iostat(fio->sbi, fio->io_type, F2FS_BLKSIZE);
- }
- void f2fs_outplace_write_data(struct dnode_of_data *dn,
- struct f2fs_io_info *fio)
- {
- struct f2fs_sb_info *sbi = fio->sbi;
- struct f2fs_summary sum;
- f2fs_bug_on(sbi, dn->data_blkaddr == NULL_ADDR);
- set_summary(&sum, dn->nid, dn->ofs_in_node, fio->version);
- do_write_page(&sum, fio);
- f2fs_update_data_blkaddr(dn, fio->new_blkaddr);
- f2fs_update_iostat(sbi, fio->io_type, F2FS_BLKSIZE);
- }
- int f2fs_inplace_write_data(struct f2fs_io_info *fio)
- {
- int err;
- struct f2fs_sb_info *sbi = fio->sbi;
- unsigned int segno;
- fio->new_blkaddr = fio->old_blkaddr;
- /* i/o temperature is needed for passing down write hints */
- __get_segment_type(fio);
- segno = GET_SEGNO(sbi, fio->new_blkaddr);
- if (!IS_DATASEG(get_seg_entry(sbi, segno)->type)) {
- set_sbi_flag(sbi, SBI_NEED_FSCK);
- f2fs_warn(sbi, "%s: incorrect segment(%u) type, run fsck to fix.",
- __func__, segno);
- err = -EFSCORRUPTED;
- goto drop_bio;
- }
- if (f2fs_cp_error(sbi)) {
- err = -EIO;
- goto drop_bio;
- }
- stat_inc_inplace_blocks(fio->sbi);
- if (fio->bio && !(SM_I(sbi)->ipu_policy & (1 << F2FS_IPU_NOCACHE)))
- err = f2fs_merge_page_bio(fio);
- else
- err = f2fs_submit_page_bio(fio);
- if (!err) {
- update_device_state(fio);
- f2fs_update_iostat(fio->sbi, fio->io_type, F2FS_BLKSIZE);
- }
- return err;
- drop_bio:
- if (fio->bio && *(fio->bio)) {
- struct bio *bio = *(fio->bio);
- bio->bi_status = BLK_STS_IOERR;
- bio_endio(bio);
- *(fio->bio) = NULL;
- }
- return err;
- }
- static inline int __f2fs_get_curseg(struct f2fs_sb_info *sbi,
- unsigned int segno)
- {
- int i;
- for (i = CURSEG_HOT_DATA; i < NO_CHECK_TYPE; i++) {
- if (CURSEG_I(sbi, i)->segno == segno)
- break;
- }
- return i;
- }
- void f2fs_do_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
- block_t old_blkaddr, block_t new_blkaddr,
- bool recover_curseg, bool recover_newaddr,
- bool from_gc)
- {
- struct sit_info *sit_i = SIT_I(sbi);
- struct curseg_info *curseg;
- unsigned int segno, old_cursegno;
- struct seg_entry *se;
- int type;
- unsigned short old_blkoff;
- unsigned char old_alloc_type;
- segno = GET_SEGNO(sbi, new_blkaddr);
- se = get_seg_entry(sbi, segno);
- type = se->type;
- f2fs_down_write(&SM_I(sbi)->curseg_lock);
- if (!recover_curseg) {
- /* for recovery flow */
- if (se->valid_blocks == 0 && !IS_CURSEG(sbi, segno)) {
- if (old_blkaddr == NULL_ADDR)
- type = CURSEG_COLD_DATA;
- else
- type = CURSEG_WARM_DATA;
- }
- } else {
- if (IS_CURSEG(sbi, segno)) {
- /* se->type is volatile as SSR allocation */
- type = __f2fs_get_curseg(sbi, segno);
- f2fs_bug_on(sbi, type == NO_CHECK_TYPE);
- } else {
- type = CURSEG_WARM_DATA;
- }
- }
- f2fs_bug_on(sbi, !IS_DATASEG(type));
- curseg = CURSEG_I(sbi, type);
- mutex_lock(&curseg->curseg_mutex);
- down_write(&sit_i->sentry_lock);
- old_cursegno = curseg->segno;
- old_blkoff = curseg->next_blkoff;
- old_alloc_type = curseg->alloc_type;
- /* change the current segment */
- if (segno != curseg->segno) {
- curseg->next_segno = segno;
- change_curseg(sbi, type, true);
- }
- curseg->next_blkoff = GET_BLKOFF_FROM_SEG0(sbi, new_blkaddr);
- __add_sum_entry(sbi, type, sum);
- if (!recover_curseg || recover_newaddr) {
- if (!from_gc)
- update_segment_mtime(sbi, new_blkaddr, 0);
- update_sit_entry(sbi, new_blkaddr, 1);
- }
- if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO) {
- invalidate_mapping_pages(META_MAPPING(sbi),
- old_blkaddr, old_blkaddr);
- f2fs_invalidate_compress_page(sbi, old_blkaddr);
- if (!from_gc)
- update_segment_mtime(sbi, old_blkaddr, 0);
- update_sit_entry(sbi, old_blkaddr, -1);
- }
- locate_dirty_segment(sbi, GET_SEGNO(sbi, old_blkaddr));
- locate_dirty_segment(sbi, GET_SEGNO(sbi, new_blkaddr));
- locate_dirty_segment(sbi, old_cursegno);
- if (recover_curseg) {
- if (old_cursegno != curseg->segno) {
- curseg->next_segno = old_cursegno;
- change_curseg(sbi, type, true);
- }
- curseg->next_blkoff = old_blkoff;
- curseg->alloc_type = old_alloc_type;
- }
- up_write(&sit_i->sentry_lock);
- mutex_unlock(&curseg->curseg_mutex);
- f2fs_up_write(&SM_I(sbi)->curseg_lock);
- }
- void f2fs_replace_block(struct f2fs_sb_info *sbi, struct dnode_of_data *dn,
- block_t old_addr, block_t new_addr,
- unsigned char version, bool recover_curseg,
- bool recover_newaddr)
- {
- struct f2fs_summary sum;
- set_summary(&sum, dn->nid, dn->ofs_in_node, version);
- f2fs_do_replace_block(sbi, &sum, old_addr, new_addr,
- recover_curseg, recover_newaddr, false);
- f2fs_update_data_blkaddr(dn, new_addr);
- }
- void f2fs_wait_on_page_writeback(struct page *page,
- enum page_type type, bool ordered, bool locked)
- {
- if (PageWriteback(page)) {
- struct f2fs_sb_info *sbi = F2FS_P_SB(page);
- /* submit cached LFS IO */
- f2fs_submit_merged_write_cond(sbi, NULL, page, 0, type);
- /* sbumit cached IPU IO */
- f2fs_submit_merged_ipu_write(sbi, NULL, page);
- if (ordered) {
- wait_on_page_writeback(page);
- f2fs_bug_on(sbi, locked && PageWriteback(page));
- } else {
- wait_for_stable_page(page);
- }
- }
- }
- void f2fs_wait_on_block_writeback(struct inode *inode, block_t blkaddr)
- {
- struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- struct page *cpage;
- if (!f2fs_post_read_required(inode))
- return;
- if (!__is_valid_data_blkaddr(blkaddr))
- return;
- cpage = find_lock_page(META_MAPPING(sbi), blkaddr);
- if (cpage) {
- f2fs_wait_on_page_writeback(cpage, DATA, true, true);
- f2fs_put_page(cpage, 1);
- }
- }
- void f2fs_wait_on_block_writeback_range(struct inode *inode, block_t blkaddr,
- block_t len)
- {
- block_t i;
- for (i = 0; i < len; i++)
- f2fs_wait_on_block_writeback(inode, blkaddr + i);
- }
- static int read_compacted_summaries(struct f2fs_sb_info *sbi)
- {
- struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
- struct curseg_info *seg_i;
- unsigned char *kaddr;
- struct page *page;
- block_t start;
- int i, j, offset;
- start = start_sum_block(sbi);
- page = f2fs_get_meta_page(sbi, start++);
- if (IS_ERR(page))
- return PTR_ERR(page);
- kaddr = (unsigned char *)page_address(page);
- /* Step 1: restore nat cache */
- seg_i = CURSEG_I(sbi, CURSEG_HOT_DATA);
- memcpy(seg_i->journal, kaddr, SUM_JOURNAL_SIZE);
- /* Step 2: restore sit cache */
- seg_i = CURSEG_I(sbi, CURSEG_COLD_DATA);
- memcpy(seg_i->journal, kaddr + SUM_JOURNAL_SIZE, SUM_JOURNAL_SIZE);
- offset = 2 * SUM_JOURNAL_SIZE;
- /* Step 3: restore summary entries */
- for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) {
- unsigned short blk_off;
- unsigned int segno;
- seg_i = CURSEG_I(sbi, i);
- segno = le32_to_cpu(ckpt->cur_data_segno[i]);
- blk_off = le16_to_cpu(ckpt->cur_data_blkoff[i]);
- seg_i->next_segno = segno;
- reset_curseg(sbi, i, 0);
- seg_i->alloc_type = ckpt->alloc_type[i];
- seg_i->next_blkoff = blk_off;
- if (seg_i->alloc_type == SSR)
- blk_off = sbi->blocks_per_seg;
- for (j = 0; j < blk_off; j++) {
- struct f2fs_summary *s;
- s = (struct f2fs_summary *)(kaddr + offset);
- seg_i->sum_blk->entries[j] = *s;
- offset += SUMMARY_SIZE;
- if (offset + SUMMARY_SIZE <= PAGE_SIZE -
- SUM_FOOTER_SIZE)
- continue;
- f2fs_put_page(page, 1);
- page = NULL;
- page = f2fs_get_meta_page(sbi, start++);
- if (IS_ERR(page))
- return PTR_ERR(page);
- kaddr = (unsigned char *)page_address(page);
- offset = 0;
- }
- }
- f2fs_put_page(page, 1);
- return 0;
- }
- static int read_normal_summaries(struct f2fs_sb_info *sbi, int type)
- {
- struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
- struct f2fs_summary_block *sum;
- struct curseg_info *curseg;
- struct page *new;
- unsigned short blk_off;
- unsigned int segno = 0;
- block_t blk_addr = 0;
- int err = 0;
- /* get segment number and block addr */
- if (IS_DATASEG(type)) {
- segno = le32_to_cpu(ckpt->cur_data_segno[type]);
- blk_off = le16_to_cpu(ckpt->cur_data_blkoff[type -
- CURSEG_HOT_DATA]);
- if (__exist_node_summaries(sbi))
- blk_addr = sum_blk_addr(sbi, NR_CURSEG_PERSIST_TYPE, type);
- else
- blk_addr = sum_blk_addr(sbi, NR_CURSEG_DATA_TYPE, type);
- } else {
- segno = le32_to_cpu(ckpt->cur_node_segno[type -
- CURSEG_HOT_NODE]);
- blk_off = le16_to_cpu(ckpt->cur_node_blkoff[type -
- CURSEG_HOT_NODE]);
- if (__exist_node_summaries(sbi))
- blk_addr = sum_blk_addr(sbi, NR_CURSEG_NODE_TYPE,
- type - CURSEG_HOT_NODE);
- else
- blk_addr = GET_SUM_BLOCK(sbi, segno);
- }
- new = f2fs_get_meta_page(sbi, blk_addr);
- if (IS_ERR(new))
- return PTR_ERR(new);
- sum = (struct f2fs_summary_block *)page_address(new);
- if (IS_NODESEG(type)) {
- if (__exist_node_summaries(sbi)) {
- struct f2fs_summary *ns = &sum->entries[0];
- int i;
- for (i = 0; i < sbi->blocks_per_seg; i++, ns++) {
- ns->version = 0;
- ns->ofs_in_node = 0;
- }
- } else {
- err = f2fs_restore_node_summary(sbi, segno, sum);
- if (err)
- goto out;
- }
- }
- /* set uncompleted segment to curseg */
- curseg = CURSEG_I(sbi, type);
- mutex_lock(&curseg->curseg_mutex);
- /* update journal info */
- down_write(&curseg->journal_rwsem);
- memcpy(curseg->journal, &sum->journal, SUM_JOURNAL_SIZE);
- up_write(&curseg->journal_rwsem);
- memcpy(curseg->sum_blk->entries, sum->entries, SUM_ENTRY_SIZE);
- memcpy(&curseg->sum_blk->footer, &sum->footer, SUM_FOOTER_SIZE);
- curseg->next_segno = segno;
- reset_curseg(sbi, type, 0);
- curseg->alloc_type = ckpt->alloc_type[type];
- curseg->next_blkoff = blk_off;
- mutex_unlock(&curseg->curseg_mutex);
- out:
- f2fs_put_page(new, 1);
- return err;
- }
- static int restore_curseg_summaries(struct f2fs_sb_info *sbi)
- {
- struct f2fs_journal *sit_j = CURSEG_I(sbi, CURSEG_COLD_DATA)->journal;
- struct f2fs_journal *nat_j = CURSEG_I(sbi, CURSEG_HOT_DATA)->journal;
- int type = CURSEG_HOT_DATA;
- int err;
- if (is_set_ckpt_flags(sbi, CP_COMPACT_SUM_FLAG)) {
- int npages = f2fs_npages_for_summary_flush(sbi, true);
- if (npages >= 2)
- f2fs_ra_meta_pages(sbi, start_sum_block(sbi), npages,
- META_CP, true);
- /* restore for compacted data summary */
- err = read_compacted_summaries(sbi);
- if (err)
- return err;
- type = CURSEG_HOT_NODE;
- }
- if (__exist_node_summaries(sbi))
- f2fs_ra_meta_pages(sbi,
- sum_blk_addr(sbi, NR_CURSEG_PERSIST_TYPE, type),
- NR_CURSEG_PERSIST_TYPE - type, META_CP, true);
- for (; type <= CURSEG_COLD_NODE; type++) {
- err = read_normal_summaries(sbi, type);
- if (err)
- return err;
- }
- /* sanity check for summary blocks */
- if (nats_in_cursum(nat_j) > NAT_JOURNAL_ENTRIES ||
- sits_in_cursum(sit_j) > SIT_JOURNAL_ENTRIES) {
- f2fs_err(sbi, "invalid journal entries nats %u sits %u",
- nats_in_cursum(nat_j), sits_in_cursum(sit_j));
- return -EINVAL;
- }
- return 0;
- }
- static void write_compacted_summaries(struct f2fs_sb_info *sbi, block_t blkaddr)
- {
- struct page *page;
- unsigned char *kaddr;
- struct f2fs_summary *summary;
- struct curseg_info *seg_i;
- int written_size = 0;
- int i, j;
- page = f2fs_grab_meta_page(sbi, blkaddr++);
- kaddr = (unsigned char *)page_address(page);
- memset(kaddr, 0, PAGE_SIZE);
- /* Step 1: write nat cache */
- seg_i = CURSEG_I(sbi, CURSEG_HOT_DATA);
- memcpy(kaddr, seg_i->journal, SUM_JOURNAL_SIZE);
- written_size += SUM_JOURNAL_SIZE;
- /* Step 2: write sit cache */
- seg_i = CURSEG_I(sbi, CURSEG_COLD_DATA);
- memcpy(kaddr + written_size, seg_i->journal, SUM_JOURNAL_SIZE);
- written_size += SUM_JOURNAL_SIZE;
- /* Step 3: write summary entries */
- for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) {
- unsigned short blkoff;
- seg_i = CURSEG_I(sbi, i);
- if (sbi->ckpt->alloc_type[i] == SSR)
- blkoff = sbi->blocks_per_seg;
- else
- blkoff = curseg_blkoff(sbi, i);
- for (j = 0; j < blkoff; j++) {
- if (!page) {
- page = f2fs_grab_meta_page(sbi, blkaddr++);
- kaddr = (unsigned char *)page_address(page);
- memset(kaddr, 0, PAGE_SIZE);
- written_size = 0;
- }
- summary = (struct f2fs_summary *)(kaddr + written_size);
- *summary = seg_i->sum_blk->entries[j];
- written_size += SUMMARY_SIZE;
- if (written_size + SUMMARY_SIZE <= PAGE_SIZE -
- SUM_FOOTER_SIZE)
- continue;
- set_page_dirty(page);
- f2fs_put_page(page, 1);
- page = NULL;
- }
- }
- if (page) {
- set_page_dirty(page);
- f2fs_put_page(page, 1);
- }
- }
- static void write_normal_summaries(struct f2fs_sb_info *sbi,
- block_t blkaddr, int type)
- {
- int i, end;
- if (IS_DATASEG(type))
- end = type + NR_CURSEG_DATA_TYPE;
- else
- end = type + NR_CURSEG_NODE_TYPE;
- for (i = type; i < end; i++)
- write_current_sum_page(sbi, i, blkaddr + (i - type));
- }
- void f2fs_write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk)
- {
- if (is_set_ckpt_flags(sbi, CP_COMPACT_SUM_FLAG))
- write_compacted_summaries(sbi, start_blk);
- else
- write_normal_summaries(sbi, start_blk, CURSEG_HOT_DATA);
- }
- void f2fs_write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk)
- {
- write_normal_summaries(sbi, start_blk, CURSEG_HOT_NODE);
- }
- int f2fs_lookup_journal_in_cursum(struct f2fs_journal *journal, int type,
- unsigned int val, int alloc)
- {
- int i;
- if (type == NAT_JOURNAL) {
- for (i = 0; i < nats_in_cursum(journal); i++) {
- if (le32_to_cpu(nid_in_journal(journal, i)) == val)
- return i;
- }
- if (alloc && __has_cursum_space(journal, 1, NAT_JOURNAL))
- return update_nats_in_cursum(journal, 1);
- } else if (type == SIT_JOURNAL) {
- for (i = 0; i < sits_in_cursum(journal); i++)
- if (le32_to_cpu(segno_in_journal(journal, i)) == val)
- return i;
- if (alloc && __has_cursum_space(journal, 1, SIT_JOURNAL))
- return update_sits_in_cursum(journal, 1);
- }
- return -1;
- }
- static struct page *get_current_sit_page(struct f2fs_sb_info *sbi,
- unsigned int segno)
- {
- return f2fs_get_meta_page(sbi, current_sit_addr(sbi, segno));
- }
- static struct page *get_next_sit_page(struct f2fs_sb_info *sbi,
- unsigned int start)
- {
- struct sit_info *sit_i = SIT_I(sbi);
- struct page *page;
- pgoff_t src_off, dst_off;
- src_off = current_sit_addr(sbi, start);
- dst_off = next_sit_addr(sbi, src_off);
- page = f2fs_grab_meta_page(sbi, dst_off);
- seg_info_to_sit_page(sbi, page, start);
- set_page_dirty(page);
- set_to_next_sit(sit_i, start);
- return page;
- }
- static struct sit_entry_set *grab_sit_entry_set(void)
- {
- struct sit_entry_set *ses =
- f2fs_kmem_cache_alloc(sit_entry_set_slab, GFP_NOFS);
- ses->entry_cnt = 0;
- INIT_LIST_HEAD(&ses->set_list);
- return ses;
- }
- static void release_sit_entry_set(struct sit_entry_set *ses)
- {
- list_del(&ses->set_list);
- kmem_cache_free(sit_entry_set_slab, ses);
- }
- static void adjust_sit_entry_set(struct sit_entry_set *ses,
- struct list_head *head)
- {
- struct sit_entry_set *next = ses;
- if (list_is_last(&ses->set_list, head))
- return;
- list_for_each_entry_continue(next, head, set_list)
- if (ses->entry_cnt <= next->entry_cnt)
- break;
- list_move_tail(&ses->set_list, &next->set_list);
- }
- static void add_sit_entry(unsigned int segno, struct list_head *head)
- {
- struct sit_entry_set *ses;
- unsigned int start_segno = START_SEGNO(segno);
- list_for_each_entry(ses, head, set_list) {
- if (ses->start_segno == start_segno) {
- ses->entry_cnt++;
- adjust_sit_entry_set(ses, head);
- return;
- }
- }
- ses = grab_sit_entry_set();
- ses->start_segno = start_segno;
- ses->entry_cnt++;
- list_add(&ses->set_list, head);
- }
- static void add_sits_in_set(struct f2fs_sb_info *sbi)
- {
- struct f2fs_sm_info *sm_info = SM_I(sbi);
- struct list_head *set_list = &sm_info->sit_entry_set;
- unsigned long *bitmap = SIT_I(sbi)->dirty_sentries_bitmap;
- unsigned int segno;
- for_each_set_bit(segno, bitmap, MAIN_SEGS(sbi))
- add_sit_entry(segno, set_list);
- }
- static void remove_sits_in_journal(struct f2fs_sb_info *sbi)
- {
- struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_COLD_DATA);
- struct f2fs_journal *journal = curseg->journal;
- int i;
- down_write(&curseg->journal_rwsem);
- for (i = 0; i < sits_in_cursum(journal); i++) {
- unsigned int segno;
- bool dirtied;
- segno = le32_to_cpu(segno_in_journal(journal, i));
- dirtied = __mark_sit_entry_dirty(sbi, segno);
- if (!dirtied)
- add_sit_entry(segno, &SM_I(sbi)->sit_entry_set);
- }
- update_sits_in_cursum(journal, -i);
- up_write(&curseg->journal_rwsem);
- }
- /*
- * CP calls this function, which flushes SIT entries including sit_journal,
- * and moves prefree segs to free segs.
- */
- void f2fs_flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
- {
- struct sit_info *sit_i = SIT_I(sbi);
- unsigned long *bitmap = sit_i->dirty_sentries_bitmap;
- struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_COLD_DATA);
- struct f2fs_journal *journal = curseg->journal;
- struct sit_entry_set *ses, *tmp;
- struct list_head *head = &SM_I(sbi)->sit_entry_set;
- bool to_journal = !is_sbi_flag_set(sbi, SBI_IS_RESIZEFS);
- struct seg_entry *se;
- down_write(&sit_i->sentry_lock);
- if (!sit_i->dirty_sentries)
- goto out;
- /*
- * add and account sit entries of dirty bitmap in sit entry
- * set temporarily
- */
- add_sits_in_set(sbi);
- /*
- * if there are no enough space in journal to store dirty sit
- * entries, remove all entries from journal and add and account
- * them in sit entry set.
- */
- if (!__has_cursum_space(journal, sit_i->dirty_sentries, SIT_JOURNAL) ||
- !to_journal)
- remove_sits_in_journal(sbi);
- /*
- * there are two steps to flush sit entries:
- * #1, flush sit entries to journal in current cold data summary block.
- * #2, flush sit entries to sit page.
- */
- list_for_each_entry_safe(ses, tmp, head, set_list) {
- struct page *page = NULL;
- struct f2fs_sit_block *raw_sit = NULL;
- unsigned int start_segno = ses->start_segno;
- unsigned int end = min(start_segno + SIT_ENTRY_PER_BLOCK,
- (unsigned long)MAIN_SEGS(sbi));
- unsigned int segno = start_segno;
- if (to_journal &&
- !__has_cursum_space(journal, ses->entry_cnt, SIT_JOURNAL))
- to_journal = false;
- if (to_journal) {
- down_write(&curseg->journal_rwsem);
- } else {
- page = get_next_sit_page(sbi, start_segno);
- raw_sit = page_address(page);
- }
- /* flush dirty sit entries in region of current sit set */
- for_each_set_bit_from(segno, bitmap, end) {
- int offset, sit_offset;
- se = get_seg_entry(sbi, segno);
- #ifdef CONFIG_F2FS_CHECK_FS
- if (memcmp(se->cur_valid_map, se->cur_valid_map_mir,
- SIT_VBLOCK_MAP_SIZE))
- f2fs_bug_on(sbi, 1);
- #endif
- /* add discard candidates */
- if (!(cpc->reason & CP_DISCARD)) {
- cpc->trim_start = segno;
- add_discard_addrs(sbi, cpc, false);
- }
- if (to_journal) {
- offset = f2fs_lookup_journal_in_cursum(journal,
- SIT_JOURNAL, segno, 1);
- f2fs_bug_on(sbi, offset < 0);
- segno_in_journal(journal, offset) =
- cpu_to_le32(segno);
- seg_info_to_raw_sit(se,
- &sit_in_journal(journal, offset));
- check_block_count(sbi, segno,
- &sit_in_journal(journal, offset));
- } else {
- sit_offset = SIT_ENTRY_OFFSET(sit_i, segno);
- seg_info_to_raw_sit(se,
- &raw_sit->entries[sit_offset]);
- check_block_count(sbi, segno,
- &raw_sit->entries[sit_offset]);
- }
- __clear_bit(segno, bitmap);
- sit_i->dirty_sentries--;
- ses->entry_cnt--;
- }
- if (to_journal)
- up_write(&curseg->journal_rwsem);
- else
- f2fs_put_page(page, 1);
- f2fs_bug_on(sbi, ses->entry_cnt);
- release_sit_entry_set(ses);
- }
- f2fs_bug_on(sbi, !list_empty(head));
- f2fs_bug_on(sbi, sit_i->dirty_sentries);
- out:
- if (cpc->reason & CP_DISCARD) {
- __u64 trim_start = cpc->trim_start;
- for (; cpc->trim_start <= cpc->trim_end; cpc->trim_start++)
- add_discard_addrs(sbi, cpc, false);
- cpc->trim_start = trim_start;
- }
- up_write(&sit_i->sentry_lock);
- set_prefree_as_free_segments(sbi);
- }
- static int build_sit_info(struct f2fs_sb_info *sbi)
- {
- struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
- struct sit_info *sit_i;
- unsigned int sit_segs, start;
- char *src_bitmap, *bitmap;
- unsigned int bitmap_size, main_bitmap_size, sit_bitmap_size;
- /* allocate memory for SIT information */
- sit_i = f2fs_kzalloc(sbi, sizeof(struct sit_info), GFP_KERNEL);
- if (!sit_i)
- return -ENOMEM;
- SM_I(sbi)->sit_info = sit_i;
- sit_i->sentries =
- f2fs_kvzalloc(sbi, array_size(sizeof(struct seg_entry),
- MAIN_SEGS(sbi)),
- GFP_KERNEL);
- if (!sit_i->sentries)
- return -ENOMEM;
- main_bitmap_size = f2fs_bitmap_size(MAIN_SEGS(sbi));
- sit_i->dirty_sentries_bitmap = f2fs_kvzalloc(sbi, main_bitmap_size,
- GFP_KERNEL);
- if (!sit_i->dirty_sentries_bitmap)
- return -ENOMEM;
- #ifdef CONFIG_F2FS_CHECK_FS
- bitmap_size = MAIN_SEGS(sbi) * SIT_VBLOCK_MAP_SIZE * 4;
- #else
- bitmap_size = MAIN_SEGS(sbi) * SIT_VBLOCK_MAP_SIZE * 3;
- #endif
- sit_i->bitmap = f2fs_kvzalloc(sbi, bitmap_size, GFP_KERNEL);
- if (!sit_i->bitmap)
- return -ENOMEM;
- bitmap = sit_i->bitmap;
- for (start = 0; start < MAIN_SEGS(sbi); start++) {
- sit_i->sentries[start].cur_valid_map = bitmap;
- bitmap += SIT_VBLOCK_MAP_SIZE;
- sit_i->sentries[start].ckpt_valid_map = bitmap;
- bitmap += SIT_VBLOCK_MAP_SIZE;
- #ifdef CONFIG_F2FS_CHECK_FS
- sit_i->sentries[start].cur_valid_map_mir = bitmap;
- bitmap += SIT_VBLOCK_MAP_SIZE;
- #endif
- sit_i->sentries[start].discard_map = bitmap;
- bitmap += SIT_VBLOCK_MAP_SIZE;
- }
- sit_i->tmp_map = f2fs_kzalloc(sbi, SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
- if (!sit_i->tmp_map)
- return -ENOMEM;
- if (__is_large_section(sbi)) {
- sit_i->sec_entries =
- f2fs_kvzalloc(sbi, array_size(sizeof(struct sec_entry),
- MAIN_SECS(sbi)),
- GFP_KERNEL);
- if (!sit_i->sec_entries)
- return -ENOMEM;
- }
- /* get information related with SIT */
- sit_segs = le32_to_cpu(raw_super->segment_count_sit) >> 1;
- /* setup SIT bitmap from ckeckpoint pack */
- sit_bitmap_size = __bitmap_size(sbi, SIT_BITMAP);
- src_bitmap = __bitmap_ptr(sbi, SIT_BITMAP);
- sit_i->sit_bitmap = kmemdup(src_bitmap, sit_bitmap_size, GFP_KERNEL);
- if (!sit_i->sit_bitmap)
- return -ENOMEM;
- #ifdef CONFIG_F2FS_CHECK_FS
- sit_i->sit_bitmap_mir = kmemdup(src_bitmap,
- sit_bitmap_size, GFP_KERNEL);
- if (!sit_i->sit_bitmap_mir)
- return -ENOMEM;
- sit_i->invalid_segmap = f2fs_kvzalloc(sbi,
- main_bitmap_size, GFP_KERNEL);
- if (!sit_i->invalid_segmap)
- return -ENOMEM;
- #endif
- /* init SIT information */
- sit_i->s_ops = &default_salloc_ops;
- sit_i->sit_base_addr = le32_to_cpu(raw_super->sit_blkaddr);
- sit_i->sit_blocks = sit_segs << sbi->log_blocks_per_seg;
- sit_i->written_valid_blocks = 0;
- sit_i->bitmap_size = sit_bitmap_size;
- sit_i->dirty_sentries = 0;
- sit_i->sents_per_block = SIT_ENTRY_PER_BLOCK;
- sit_i->elapsed_time = le64_to_cpu(sbi->ckpt->elapsed_time);
- sit_i->mounted_time = ktime_get_boottime_seconds();
- init_rwsem(&sit_i->sentry_lock);
- return 0;
- }
- static int build_free_segmap(struct f2fs_sb_info *sbi)
- {
- struct free_segmap_info *free_i;
- unsigned int bitmap_size, sec_bitmap_size;
- /* allocate memory for free segmap information */
- free_i = f2fs_kzalloc(sbi, sizeof(struct free_segmap_info), GFP_KERNEL);
- if (!free_i)
- return -ENOMEM;
- SM_I(sbi)->free_info = free_i;
- bitmap_size = f2fs_bitmap_size(MAIN_SEGS(sbi));
- free_i->free_segmap = f2fs_kvmalloc(sbi, bitmap_size, GFP_KERNEL);
- if (!free_i->free_segmap)
- return -ENOMEM;
- sec_bitmap_size = f2fs_bitmap_size(MAIN_SECS(sbi));
- free_i->free_secmap = f2fs_kvmalloc(sbi, sec_bitmap_size, GFP_KERNEL);
- if (!free_i->free_secmap)
- return -ENOMEM;
- /* set all segments as dirty temporarily */
- memset(free_i->free_segmap, 0xff, bitmap_size);
- memset(free_i->free_secmap, 0xff, sec_bitmap_size);
- /* init free segmap information */
- free_i->start_segno = GET_SEGNO_FROM_SEG0(sbi, MAIN_BLKADDR(sbi));
- free_i->free_segments = 0;
- free_i->free_sections = 0;
- spin_lock_init(&free_i->segmap_lock);
- return 0;
- }
- static int build_curseg(struct f2fs_sb_info *sbi)
- {
- struct curseg_info *array;
- int i;
- array = f2fs_kzalloc(sbi, array_size(NR_CURSEG_TYPE,
- sizeof(*array)), GFP_KERNEL);
- if (!array)
- return -ENOMEM;
- SM_I(sbi)->curseg_array = array;
- for (i = 0; i < NO_CHECK_TYPE; i++) {
- mutex_init(&array[i].curseg_mutex);
- array[i].sum_blk = f2fs_kzalloc(sbi, PAGE_SIZE, GFP_KERNEL);
- if (!array[i].sum_blk)
- return -ENOMEM;
- init_rwsem(&array[i].journal_rwsem);
- array[i].journal = f2fs_kzalloc(sbi,
- sizeof(struct f2fs_journal), GFP_KERNEL);
- if (!array[i].journal)
- return -ENOMEM;
- if (i < NR_PERSISTENT_LOG)
- array[i].seg_type = CURSEG_HOT_DATA + i;
- else if (i == CURSEG_COLD_DATA_PINNED)
- array[i].seg_type = CURSEG_COLD_DATA;
- else if (i == CURSEG_ALL_DATA_ATGC)
- array[i].seg_type = CURSEG_COLD_DATA;
- array[i].segno = NULL_SEGNO;
- array[i].next_blkoff = 0;
- array[i].inited = false;
- }
- return restore_curseg_summaries(sbi);
- }
- static int build_sit_entries(struct f2fs_sb_info *sbi)
- {
- struct sit_info *sit_i = SIT_I(sbi);
- struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_COLD_DATA);
- struct f2fs_journal *journal = curseg->journal;
- struct seg_entry *se;
- struct f2fs_sit_entry sit;
- int sit_blk_cnt = SIT_BLK_CNT(sbi);
- unsigned int i, start, end;
- unsigned int readed, start_blk = 0;
- int err = 0;
- block_t total_node_blocks = 0;
- do {
- readed = f2fs_ra_meta_pages(sbi, start_blk, BIO_MAX_PAGES,
- META_SIT, true);
- start = start_blk * sit_i->sents_per_block;
- end = (start_blk + readed) * sit_i->sents_per_block;
- for (; start < end && start < MAIN_SEGS(sbi); start++) {
- struct f2fs_sit_block *sit_blk;
- struct page *page;
- se = &sit_i->sentries[start];
- page = get_current_sit_page(sbi, start);
- if (IS_ERR(page))
- return PTR_ERR(page);
- sit_blk = (struct f2fs_sit_block *)page_address(page);
- sit = sit_blk->entries[SIT_ENTRY_OFFSET(sit_i, start)];
- f2fs_put_page(page, 1);
- err = check_block_count(sbi, start, &sit);
- if (err)
- return err;
- seg_info_from_raw_sit(se, &sit);
- if (IS_NODESEG(se->type))
- total_node_blocks += se->valid_blocks;
- /* build discard map only one time */
- if (is_set_ckpt_flags(sbi, CP_TRIMMED_FLAG)) {
- memset(se->discard_map, 0xff,
- SIT_VBLOCK_MAP_SIZE);
- } else {
- memcpy(se->discard_map,
- se->cur_valid_map,
- SIT_VBLOCK_MAP_SIZE);
- sbi->discard_blks +=
- sbi->blocks_per_seg -
- se->valid_blocks;
- }
- if (__is_large_section(sbi))
- get_sec_entry(sbi, start)->valid_blocks +=
- se->valid_blocks;
- }
- start_blk += readed;
- } while (start_blk < sit_blk_cnt);
- down_read(&curseg->journal_rwsem);
- for (i = 0; i < sits_in_cursum(journal); i++) {
- unsigned int old_valid_blocks;
- start = le32_to_cpu(segno_in_journal(journal, i));
- if (start >= MAIN_SEGS(sbi)) {
- f2fs_err(sbi, "Wrong journal entry on segno %u",
- start);
- err = -EFSCORRUPTED;
- break;
- }
- se = &sit_i->sentries[start];
- sit = sit_in_journal(journal, i);
- old_valid_blocks = se->valid_blocks;
- if (IS_NODESEG(se->type))
- total_node_blocks -= old_valid_blocks;
- err = check_block_count(sbi, start, &sit);
- if (err)
- break;
- seg_info_from_raw_sit(se, &sit);
- if (IS_NODESEG(se->type))
- total_node_blocks += se->valid_blocks;
- if (is_set_ckpt_flags(sbi, CP_TRIMMED_FLAG)) {
- memset(se->discard_map, 0xff, SIT_VBLOCK_MAP_SIZE);
- } else {
- memcpy(se->discard_map, se->cur_valid_map,
- SIT_VBLOCK_MAP_SIZE);
- sbi->discard_blks += old_valid_blocks;
- sbi->discard_blks -= se->valid_blocks;
- }
- if (__is_large_section(sbi)) {
- get_sec_entry(sbi, start)->valid_blocks +=
- se->valid_blocks;
- get_sec_entry(sbi, start)->valid_blocks -=
- old_valid_blocks;
- }
- }
- up_read(&curseg->journal_rwsem);
- if (!err && total_node_blocks != valid_node_count(sbi)) {
- f2fs_err(sbi, "SIT is corrupted node# %u vs %u",
- total_node_blocks, valid_node_count(sbi));
- err = -EFSCORRUPTED;
- }
- return err;
- }
- static void init_free_segmap(struct f2fs_sb_info *sbi)
- {
- unsigned int start;
- int type;
- struct seg_entry *sentry;
- for (start = 0; start < MAIN_SEGS(sbi); start++) {
- if (f2fs_usable_blks_in_seg(sbi, start) == 0)
- continue;
- sentry = get_seg_entry(sbi, start);
- if (!sentry->valid_blocks)
- __set_free(sbi, start);
- else
- SIT_I(sbi)->written_valid_blocks +=
- sentry->valid_blocks;
- }
- /* set use the current segments */
- for (type = CURSEG_HOT_DATA; type <= CURSEG_COLD_NODE; type++) {
- struct curseg_info *curseg_t = CURSEG_I(sbi, type);
- __set_test_and_inuse(sbi, curseg_t->segno);
- }
- }
- static void init_dirty_segmap(struct f2fs_sb_info *sbi)
- {
- struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
- struct free_segmap_info *free_i = FREE_I(sbi);
- unsigned int segno = 0, offset = 0, secno;
- block_t valid_blocks, usable_blks_in_seg;
- block_t blks_per_sec = BLKS_PER_SEC(sbi);
- while (1) {
- /* find dirty segment based on free segmap */
- segno = find_next_inuse(free_i, MAIN_SEGS(sbi), offset);
- if (segno >= MAIN_SEGS(sbi))
- break;
- offset = segno + 1;
- valid_blocks = get_valid_blocks(sbi, segno, false);
- usable_blks_in_seg = f2fs_usable_blks_in_seg(sbi, segno);
- if (valid_blocks == usable_blks_in_seg || !valid_blocks)
- continue;
- if (valid_blocks > usable_blks_in_seg) {
- f2fs_bug_on(sbi, 1);
- continue;
- }
- mutex_lock(&dirty_i->seglist_lock);
- __locate_dirty_segment(sbi, segno, DIRTY);
- mutex_unlock(&dirty_i->seglist_lock);
- }
- if (!__is_large_section(sbi))
- return;
- mutex_lock(&dirty_i->seglist_lock);
- for (segno = 0; segno < MAIN_SEGS(sbi); segno += sbi->segs_per_sec) {
- valid_blocks = get_valid_blocks(sbi, segno, true);
- secno = GET_SEC_FROM_SEG(sbi, segno);
- if (!valid_blocks || valid_blocks == blks_per_sec)
- continue;
- if (IS_CURSEC(sbi, secno))
- continue;
- set_bit(secno, dirty_i->dirty_secmap);
- }
- mutex_unlock(&dirty_i->seglist_lock);
- }
- static int init_victim_secmap(struct f2fs_sb_info *sbi)
- {
- struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
- unsigned int bitmap_size = f2fs_bitmap_size(MAIN_SECS(sbi));
- dirty_i->victim_secmap = f2fs_kvzalloc(sbi, bitmap_size, GFP_KERNEL);
- if (!dirty_i->victim_secmap)
- return -ENOMEM;
- return 0;
- }
- static int build_dirty_segmap(struct f2fs_sb_info *sbi)
- {
- struct dirty_seglist_info *dirty_i;
- unsigned int bitmap_size, i;
- /* allocate memory for dirty segments list information */
- dirty_i = f2fs_kzalloc(sbi, sizeof(struct dirty_seglist_info),
- GFP_KERNEL);
- if (!dirty_i)
- return -ENOMEM;
- SM_I(sbi)->dirty_info = dirty_i;
- mutex_init(&dirty_i->seglist_lock);
- bitmap_size = f2fs_bitmap_size(MAIN_SEGS(sbi));
- for (i = 0; i < NR_DIRTY_TYPE; i++) {
- dirty_i->dirty_segmap[i] = f2fs_kvzalloc(sbi, bitmap_size,
- GFP_KERNEL);
- if (!dirty_i->dirty_segmap[i])
- return -ENOMEM;
- }
- if (__is_large_section(sbi)) {
- bitmap_size = f2fs_bitmap_size(MAIN_SECS(sbi));
- dirty_i->dirty_secmap = f2fs_kvzalloc(sbi,
- bitmap_size, GFP_KERNEL);
- if (!dirty_i->dirty_secmap)
- return -ENOMEM;
- }
- init_dirty_segmap(sbi);
- return init_victim_secmap(sbi);
- }
- static int sanity_check_curseg(struct f2fs_sb_info *sbi)
- {
- int i;
- /*
- * In LFS/SSR curseg, .next_blkoff should point to an unused blkaddr;
- * In LFS curseg, all blkaddr after .next_blkoff should be unused.
- */
- for (i = 0; i < NR_PERSISTENT_LOG; i++) {
- struct curseg_info *curseg = CURSEG_I(sbi, i);
- struct seg_entry *se = get_seg_entry(sbi, curseg->segno);
- unsigned int blkofs = curseg->next_blkoff;
- if (f2fs_sb_has_readonly(sbi) &&
- i != CURSEG_HOT_DATA && i != CURSEG_HOT_NODE)
- continue;
- sanity_check_seg_type(sbi, curseg->seg_type);
- if (curseg->alloc_type != LFS && curseg->alloc_type != SSR) {
- f2fs_err(sbi,
- "Current segment has invalid alloc_type:%d",
- curseg->alloc_type);
- return -EFSCORRUPTED;
- }
- if (f2fs_test_bit(blkofs, se->cur_valid_map))
- goto out;
- if (curseg->alloc_type == SSR)
- continue;
- for (blkofs += 1; blkofs < sbi->blocks_per_seg; blkofs++) {
- if (!f2fs_test_bit(blkofs, se->cur_valid_map))
- continue;
- out:
- f2fs_err(sbi,
- "Current segment's next free block offset is inconsistent with bitmap, logtype:%u, segno:%u, type:%u, next_blkoff:%u, blkofs:%u",
- i, curseg->segno, curseg->alloc_type,
- curseg->next_blkoff, blkofs);
- return -EFSCORRUPTED;
- }
- }
- return 0;
- }
- #ifdef CONFIG_BLK_DEV_ZONED
- static int check_zone_write_pointer(struct f2fs_sb_info *sbi,
- struct f2fs_dev_info *fdev,
- struct blk_zone *zone)
- {
- unsigned int wp_segno, wp_blkoff, zone_secno, zone_segno, segno;
- block_t zone_block, wp_block, last_valid_block;
- unsigned int log_sectors_per_block = sbi->log_blocksize - SECTOR_SHIFT;
- int i, s, b, ret;
- struct seg_entry *se;
- if (zone->type != BLK_ZONE_TYPE_SEQWRITE_REQ)
- return 0;
- wp_block = fdev->start_blk + (zone->wp >> log_sectors_per_block);
- wp_segno = GET_SEGNO(sbi, wp_block);
- wp_blkoff = wp_block - START_BLOCK(sbi, wp_segno);
- zone_block = fdev->start_blk + (zone->start >> log_sectors_per_block);
- zone_segno = GET_SEGNO(sbi, zone_block);
- zone_secno = GET_SEC_FROM_SEG(sbi, zone_segno);
- if (zone_segno >= MAIN_SEGS(sbi))
- return 0;
- /*
- * Skip check of zones cursegs point to, since
- * fix_curseg_write_pointer() checks them.
- */
- for (i = 0; i < NO_CHECK_TYPE; i++)
- if (zone_secno == GET_SEC_FROM_SEG(sbi,
- CURSEG_I(sbi, i)->segno))
- return 0;
- /*
- * Get last valid block of the zone.
- */
- last_valid_block = zone_block - 1;
- for (s = sbi->segs_per_sec - 1; s >= 0; s--) {
- segno = zone_segno + s;
- se = get_seg_entry(sbi, segno);
- for (b = sbi->blocks_per_seg - 1; b >= 0; b--)
- if (f2fs_test_bit(b, se->cur_valid_map)) {
- last_valid_block = START_BLOCK(sbi, segno) + b;
- break;
- }
- if (last_valid_block >= zone_block)
- break;
- }
- /*
- * If last valid block is beyond the write pointer, report the
- * inconsistency. This inconsistency does not cause write error
- * because the zone will not be selected for write operation until
- * it get discarded. Just report it.
- */
- if (last_valid_block >= wp_block) {
- f2fs_notice(sbi, "Valid block beyond write pointer: "
- "valid block[0x%x,0x%x] wp[0x%x,0x%x]",
- GET_SEGNO(sbi, last_valid_block),
- GET_BLKOFF_FROM_SEG0(sbi, last_valid_block),
- wp_segno, wp_blkoff);
- return 0;
- }
- /*
- * If there is no valid block in the zone and if write pointer is
- * not at zone start, reset the write pointer.
- */
- if (last_valid_block + 1 == zone_block && zone->wp != zone->start) {
- f2fs_notice(sbi,
- "Zone without valid block has non-zero write "
- "pointer. Reset the write pointer: wp[0x%x,0x%x]",
- wp_segno, wp_blkoff);
- ret = __f2fs_issue_discard_zone(sbi, fdev->bdev, zone_block,
- zone->len >> log_sectors_per_block);
- if (ret) {
- f2fs_err(sbi, "Discard zone failed: %s (errno=%d)",
- fdev->path, ret);
- return ret;
- }
- }
- return 0;
- }
- static struct f2fs_dev_info *get_target_zoned_dev(struct f2fs_sb_info *sbi,
- block_t zone_blkaddr)
- {
- int i;
- for (i = 0; i < sbi->s_ndevs; i++) {
- if (!bdev_is_zoned(FDEV(i).bdev))
- continue;
- if (sbi->s_ndevs == 1 || (FDEV(i).start_blk <= zone_blkaddr &&
- zone_blkaddr <= FDEV(i).end_blk))
- return &FDEV(i);
- }
- return NULL;
- }
- static int report_one_zone_cb(struct blk_zone *zone, unsigned int idx,
- void *data)
- {
- memcpy(data, zone, sizeof(struct blk_zone));
- return 0;
- }
- static int fix_curseg_write_pointer(struct f2fs_sb_info *sbi, int type)
- {
- struct curseg_info *cs = CURSEG_I(sbi, type);
- struct f2fs_dev_info *zbd;
- struct blk_zone zone;
- unsigned int cs_section, wp_segno, wp_blkoff, wp_sector_off;
- block_t cs_zone_block, wp_block;
- unsigned int log_sectors_per_block = sbi->log_blocksize - SECTOR_SHIFT;
- sector_t zone_sector;
- int err;
- cs_section = GET_SEC_FROM_SEG(sbi, cs->segno);
- cs_zone_block = START_BLOCK(sbi, GET_SEG_FROM_SEC(sbi, cs_section));
- zbd = get_target_zoned_dev(sbi, cs_zone_block);
- if (!zbd)
- return 0;
- /* report zone for the sector the curseg points to */
- zone_sector = (sector_t)(cs_zone_block - zbd->start_blk)
- << log_sectors_per_block;
- err = blkdev_report_zones(zbd->bdev, zone_sector, 1,
- report_one_zone_cb, &zone);
- if (err != 1) {
- f2fs_err(sbi, "Report zone failed: %s errno=(%d)",
- zbd->path, err);
- return err;
- }
- if (zone.type != BLK_ZONE_TYPE_SEQWRITE_REQ)
- return 0;
- wp_block = zbd->start_blk + (zone.wp >> log_sectors_per_block);
- wp_segno = GET_SEGNO(sbi, wp_block);
- wp_blkoff = wp_block - START_BLOCK(sbi, wp_segno);
- wp_sector_off = zone.wp & GENMASK(log_sectors_per_block - 1, 0);
- if (cs->segno == wp_segno && cs->next_blkoff == wp_blkoff &&
- wp_sector_off == 0)
- return 0;
- f2fs_notice(sbi, "Unaligned curseg[%d] with write pointer: "
- "curseg[0x%x,0x%x] wp[0x%x,0x%x]",
- type, cs->segno, cs->next_blkoff, wp_segno, wp_blkoff);
- f2fs_notice(sbi, "Assign new section to curseg[%d]: "
- "curseg[0x%x,0x%x]", type, cs->segno, cs->next_blkoff);
- f2fs_allocate_new_section(sbi, type, true);
- /* check consistency of the zone curseg pointed to */
- if (check_zone_write_pointer(sbi, zbd, &zone))
- return -EIO;
- /* check newly assigned zone */
- cs_section = GET_SEC_FROM_SEG(sbi, cs->segno);
- cs_zone_block = START_BLOCK(sbi, GET_SEG_FROM_SEC(sbi, cs_section));
- zbd = get_target_zoned_dev(sbi, cs_zone_block);
- if (!zbd)
- return 0;
- zone_sector = (sector_t)(cs_zone_block - zbd->start_blk)
- << log_sectors_per_block;
- err = blkdev_report_zones(zbd->bdev, zone_sector, 1,
- report_one_zone_cb, &zone);
- if (err != 1) {
- f2fs_err(sbi, "Report zone failed: %s errno=(%d)",
- zbd->path, err);
- return err;
- }
- if (zone.type != BLK_ZONE_TYPE_SEQWRITE_REQ)
- return 0;
- if (zone.wp != zone.start) {
- f2fs_notice(sbi,
- "New zone for curseg[%d] is not yet discarded. "
- "Reset the zone: curseg[0x%x,0x%x]",
- type, cs->segno, cs->next_blkoff);
- err = __f2fs_issue_discard_zone(sbi, zbd->bdev,
- zone_sector >> log_sectors_per_block,
- zone.len >> log_sectors_per_block);
- if (err) {
- f2fs_err(sbi, "Discard zone failed: %s (errno=%d)",
- zbd->path, err);
- return err;
- }
- }
- return 0;
- }
- int f2fs_fix_curseg_write_pointer(struct f2fs_sb_info *sbi)
- {
- int i, ret;
- for (i = 0; i < NR_PERSISTENT_LOG; i++) {
- ret = fix_curseg_write_pointer(sbi, i);
- if (ret)
- return ret;
- }
- return 0;
- }
- struct check_zone_write_pointer_args {
- struct f2fs_sb_info *sbi;
- struct f2fs_dev_info *fdev;
- };
- static int check_zone_write_pointer_cb(struct blk_zone *zone, unsigned int idx,
- void *data)
- {
- struct check_zone_write_pointer_args *args;
- args = (struct check_zone_write_pointer_args *)data;
- return check_zone_write_pointer(args->sbi, args->fdev, zone);
- }
- int f2fs_check_write_pointer(struct f2fs_sb_info *sbi)
- {
- int i, ret;
- struct check_zone_write_pointer_args args;
- for (i = 0; i < sbi->s_ndevs; i++) {
- if (!bdev_is_zoned(FDEV(i).bdev))
- continue;
- args.sbi = sbi;
- args.fdev = &FDEV(i);
- ret = blkdev_report_zones(FDEV(i).bdev, 0, BLK_ALL_ZONES,
- check_zone_write_pointer_cb, &args);
- if (ret < 0)
- return ret;
- }
- return 0;
- }
- static bool is_conv_zone(struct f2fs_sb_info *sbi, unsigned int zone_idx,
- unsigned int dev_idx)
- {
- if (!bdev_is_zoned(FDEV(dev_idx).bdev))
- return true;
- return !test_bit(zone_idx, FDEV(dev_idx).blkz_seq);
- }
- /* Return the zone index in the given device */
- static unsigned int get_zone_idx(struct f2fs_sb_info *sbi, unsigned int secno,
- int dev_idx)
- {
- block_t sec_start_blkaddr = START_BLOCK(sbi, GET_SEG_FROM_SEC(sbi, secno));
- return (sec_start_blkaddr - FDEV(dev_idx).start_blk) >>
- sbi->log_blocks_per_blkz;
- }
- /*
- * Return the usable segments in a section based on the zone's
- * corresponding zone capacity. Zone is equal to a section.
- */
- static inline unsigned int f2fs_usable_zone_segs_in_sec(
- struct f2fs_sb_info *sbi, unsigned int segno)
- {
- unsigned int dev_idx, zone_idx, unusable_segs_in_sec;
- dev_idx = f2fs_target_device_index(sbi, START_BLOCK(sbi, segno));
- zone_idx = get_zone_idx(sbi, GET_SEC_FROM_SEG(sbi, segno), dev_idx);
- /* Conventional zone's capacity is always equal to zone size */
- if (is_conv_zone(sbi, zone_idx, dev_idx))
- return sbi->segs_per_sec;
- /*
- * If the zone_capacity_blocks array is NULL, then zone capacity
- * is equal to the zone size for all zones
- */
- if (!FDEV(dev_idx).zone_capacity_blocks)
- return sbi->segs_per_sec;
- /* Get the segment count beyond zone capacity block */
- unusable_segs_in_sec = (sbi->blocks_per_blkz -
- FDEV(dev_idx).zone_capacity_blocks[zone_idx]) >>
- sbi->log_blocks_per_seg;
- return sbi->segs_per_sec - unusable_segs_in_sec;
- }
- /*
- * Return the number of usable blocks in a segment. The number of blocks
- * returned is always equal to the number of blocks in a segment for
- * segments fully contained within a sequential zone capacity or a
- * conventional zone. For segments partially contained in a sequential
- * zone capacity, the number of usable blocks up to the zone capacity
- * is returned. 0 is returned in all other cases.
- */
- static inline unsigned int f2fs_usable_zone_blks_in_seg(
- struct f2fs_sb_info *sbi, unsigned int segno)
- {
- block_t seg_start, sec_start_blkaddr, sec_cap_blkaddr;
- unsigned int zone_idx, dev_idx, secno;
- secno = GET_SEC_FROM_SEG(sbi, segno);
- seg_start = START_BLOCK(sbi, segno);
- dev_idx = f2fs_target_device_index(sbi, seg_start);
- zone_idx = get_zone_idx(sbi, secno, dev_idx);
- /*
- * Conventional zone's capacity is always equal to zone size,
- * so, blocks per segment is unchanged.
- */
- if (is_conv_zone(sbi, zone_idx, dev_idx))
- return sbi->blocks_per_seg;
- if (!FDEV(dev_idx).zone_capacity_blocks)
- return sbi->blocks_per_seg;
- sec_start_blkaddr = START_BLOCK(sbi, GET_SEG_FROM_SEC(sbi, secno));
- sec_cap_blkaddr = sec_start_blkaddr +
- FDEV(dev_idx).zone_capacity_blocks[zone_idx];
- /*
- * If segment starts before zone capacity and spans beyond
- * zone capacity, then usable blocks are from seg start to
- * zone capacity. If the segment starts after the zone capacity,
- * then there are no usable blocks.
- */
- if (seg_start >= sec_cap_blkaddr)
- return 0;
- if (seg_start + sbi->blocks_per_seg > sec_cap_blkaddr)
- return sec_cap_blkaddr - seg_start;
- return sbi->blocks_per_seg;
- }
- #else
- int f2fs_fix_curseg_write_pointer(struct f2fs_sb_info *sbi)
- {
- return 0;
- }
- int f2fs_check_write_pointer(struct f2fs_sb_info *sbi)
- {
- return 0;
- }
- static inline unsigned int f2fs_usable_zone_blks_in_seg(struct f2fs_sb_info *sbi,
- unsigned int segno)
- {
- return 0;
- }
- static inline unsigned int f2fs_usable_zone_segs_in_sec(struct f2fs_sb_info *sbi,
- unsigned int segno)
- {
- return 0;
- }
- #endif
- unsigned int f2fs_usable_blks_in_seg(struct f2fs_sb_info *sbi,
- unsigned int segno)
- {
- if (f2fs_sb_has_blkzoned(sbi))
- return f2fs_usable_zone_blks_in_seg(sbi, segno);
- return sbi->blocks_per_seg;
- }
- unsigned int f2fs_usable_segs_in_sec(struct f2fs_sb_info *sbi,
- unsigned int segno)
- {
- if (f2fs_sb_has_blkzoned(sbi))
- return f2fs_usable_zone_segs_in_sec(sbi, segno);
- return sbi->segs_per_sec;
- }
- /*
- * Update min, max modified time for cost-benefit GC algorithm
- */
- static void init_min_max_mtime(struct f2fs_sb_info *sbi)
- {
- struct sit_info *sit_i = SIT_I(sbi);
- unsigned int segno;
- down_write(&sit_i->sentry_lock);
- sit_i->min_mtime = ULLONG_MAX;
- for (segno = 0; segno < MAIN_SEGS(sbi); segno += sbi->segs_per_sec) {
- unsigned int i;
- unsigned long long mtime = 0;
- for (i = 0; i < sbi->segs_per_sec; i++)
- mtime += get_seg_entry(sbi, segno + i)->mtime;
- mtime = div_u64(mtime, sbi->segs_per_sec);
- if (sit_i->min_mtime > mtime)
- sit_i->min_mtime = mtime;
- }
- sit_i->max_mtime = get_mtime(sbi, false);
- sit_i->dirty_max_mtime = 0;
- up_write(&sit_i->sentry_lock);
- }
- int f2fs_build_segment_manager(struct f2fs_sb_info *sbi)
- {
- struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
- struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
- struct f2fs_sm_info *sm_info;
- int err;
- sm_info = f2fs_kzalloc(sbi, sizeof(struct f2fs_sm_info), GFP_KERNEL);
- if (!sm_info)
- return -ENOMEM;
- /* init sm info */
- sbi->sm_info = sm_info;
- sm_info->seg0_blkaddr = le32_to_cpu(raw_super->segment0_blkaddr);
- sm_info->main_blkaddr = le32_to_cpu(raw_super->main_blkaddr);
- sm_info->segment_count = le32_to_cpu(raw_super->segment_count);
- sm_info->reserved_segments = le32_to_cpu(ckpt->rsvd_segment_count);
- sm_info->ovp_segments = le32_to_cpu(ckpt->overprov_segment_count);
- sm_info->main_segments = le32_to_cpu(raw_super->segment_count_main);
- sm_info->ssa_blkaddr = le32_to_cpu(raw_super->ssa_blkaddr);
- sm_info->rec_prefree_segments = sm_info->main_segments *
- DEF_RECLAIM_PREFREE_SEGMENTS / 100;
- if (sm_info->rec_prefree_segments > DEF_MAX_RECLAIM_PREFREE_SEGMENTS)
- sm_info->rec_prefree_segments = DEF_MAX_RECLAIM_PREFREE_SEGMENTS;
- if (!f2fs_lfs_mode(sbi))
- sm_info->ipu_policy = 1 << F2FS_IPU_FSYNC;
- sm_info->min_ipu_util = DEF_MIN_IPU_UTIL;
- sm_info->min_fsync_blocks = DEF_MIN_FSYNC_BLOCKS;
- sm_info->min_seq_blocks = sbi->blocks_per_seg * sbi->segs_per_sec;
- sm_info->min_hot_blocks = DEF_MIN_HOT_BLOCKS;
- sm_info->min_ssr_sections = reserved_sections(sbi);
- INIT_LIST_HEAD(&sm_info->sit_entry_set);
- init_f2fs_rwsem(&sm_info->curseg_lock);
- if (!f2fs_readonly(sbi->sb)) {
- err = f2fs_create_flush_cmd_control(sbi);
- if (err)
- return err;
- }
- err = create_discard_cmd_control(sbi);
- if (err)
- return err;
- err = build_sit_info(sbi);
- if (err)
- return err;
- err = build_free_segmap(sbi);
- if (err)
- return err;
- err = build_curseg(sbi);
- if (err)
- return err;
- /* reinit free segmap based on SIT */
- err = build_sit_entries(sbi);
- if (err)
- return err;
- init_free_segmap(sbi);
- err = build_dirty_segmap(sbi);
- if (err)
- return err;
- err = sanity_check_curseg(sbi);
- if (err)
- return err;
- init_min_max_mtime(sbi);
- return 0;
- }
- static void discard_dirty_segmap(struct f2fs_sb_info *sbi,
- enum dirty_type dirty_type)
- {
- struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
- mutex_lock(&dirty_i->seglist_lock);
- kvfree(dirty_i->dirty_segmap[dirty_type]);
- dirty_i->nr_dirty[dirty_type] = 0;
- mutex_unlock(&dirty_i->seglist_lock);
- }
- static void destroy_victim_secmap(struct f2fs_sb_info *sbi)
- {
- struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
- kvfree(dirty_i->victim_secmap);
- }
- static void destroy_dirty_segmap(struct f2fs_sb_info *sbi)
- {
- struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
- int i;
- if (!dirty_i)
- return;
- /* discard pre-free/dirty segments list */
- for (i = 0; i < NR_DIRTY_TYPE; i++)
- discard_dirty_segmap(sbi, i);
- if (__is_large_section(sbi)) {
- mutex_lock(&dirty_i->seglist_lock);
- kvfree(dirty_i->dirty_secmap);
- mutex_unlock(&dirty_i->seglist_lock);
- }
- destroy_victim_secmap(sbi);
- SM_I(sbi)->dirty_info = NULL;
- kfree(dirty_i);
- }
- static void destroy_curseg(struct f2fs_sb_info *sbi)
- {
- struct curseg_info *array = SM_I(sbi)->curseg_array;
- int i;
- if (!array)
- return;
- SM_I(sbi)->curseg_array = NULL;
- for (i = 0; i < NR_CURSEG_TYPE; i++) {
- kfree(array[i].sum_blk);
- kfree(array[i].journal);
- }
- kfree(array);
- }
- static void destroy_free_segmap(struct f2fs_sb_info *sbi)
- {
- struct free_segmap_info *free_i = SM_I(sbi)->free_info;
- if (!free_i)
- return;
- SM_I(sbi)->free_info = NULL;
- kvfree(free_i->free_segmap);
- kvfree(free_i->free_secmap);
- kfree(free_i);
- }
- static void destroy_sit_info(struct f2fs_sb_info *sbi)
- {
- struct sit_info *sit_i = SIT_I(sbi);
- if (!sit_i)
- return;
- if (sit_i->sentries)
- kvfree(sit_i->bitmap);
- kfree(sit_i->tmp_map);
- kvfree(sit_i->sentries);
- kvfree(sit_i->sec_entries);
- kvfree(sit_i->dirty_sentries_bitmap);
- SM_I(sbi)->sit_info = NULL;
- kvfree(sit_i->sit_bitmap);
- #ifdef CONFIG_F2FS_CHECK_FS
- kvfree(sit_i->sit_bitmap_mir);
- kvfree(sit_i->invalid_segmap);
- #endif
- kfree(sit_i);
- }
- void f2fs_destroy_segment_manager(struct f2fs_sb_info *sbi)
- {
- struct f2fs_sm_info *sm_info = SM_I(sbi);
- if (!sm_info)
- return;
- f2fs_destroy_flush_cmd_control(sbi, true);
- destroy_discard_cmd_control(sbi);
- destroy_dirty_segmap(sbi);
- destroy_curseg(sbi);
- destroy_free_segmap(sbi);
- destroy_sit_info(sbi);
- sbi->sm_info = NULL;
- kfree(sm_info);
- }
- int __init f2fs_create_segment_manager_caches(void)
- {
- discard_entry_slab = f2fs_kmem_cache_create("f2fs_discard_entry",
- sizeof(struct discard_entry));
- if (!discard_entry_slab)
- goto fail;
- discard_cmd_slab = f2fs_kmem_cache_create("f2fs_discard_cmd",
- sizeof(struct discard_cmd));
- if (!discard_cmd_slab)
- goto destroy_discard_entry;
- sit_entry_set_slab = f2fs_kmem_cache_create("f2fs_sit_entry_set",
- sizeof(struct sit_entry_set));
- if (!sit_entry_set_slab)
- goto destroy_discard_cmd;
- inmem_entry_slab = f2fs_kmem_cache_create("f2fs_inmem_page_entry",
- sizeof(struct inmem_pages));
- if (!inmem_entry_slab)
- goto destroy_sit_entry_set;
- return 0;
- destroy_sit_entry_set:
- kmem_cache_destroy(sit_entry_set_slab);
- destroy_discard_cmd:
- kmem_cache_destroy(discard_cmd_slab);
- destroy_discard_entry:
- kmem_cache_destroy(discard_entry_slab);
- fail:
- return -ENOMEM;
- }
- void f2fs_destroy_segment_manager_caches(void)
- {
- kmem_cache_destroy(sit_entry_set_slab);
- kmem_cache_destroy(discard_cmd_slab);
- kmem_cache_destroy(discard_entry_slab);
- kmem_cache_destroy(inmem_entry_slab);
- }
|