| Author | Tokens | Token Proportion | Commits | Commit Proportion |
|---|---|---|---|---|
| Filipe David Borba Manana | 3609 | 23.40% | 35 | 10.26% |
| Josef Bacik | 3160 | 20.49% | 49 | 14.37% |
| Chris Mason | 2940 | 19.06% | 60 | 17.60% |
| Zheng Yan | 2001 | 12.97% | 14 | 4.11% |
| Miao Xie | 1028 | 6.67% | 25 | 7.33% |
| Qu Wenruo | 700 | 4.54% | 15 | 4.40% |
| Christoph Hellwig | 422 | 2.74% | 9 | 2.64% |
| Jeff Mahoney | 233 | 1.51% | 5 | 1.47% |
| Liu Bo | 187 | 1.21% | 11 | 3.23% |
| Goldwyn Rodrigues | 183 | 1.19% | 5 | 1.47% |
| Chandan Rajendra | 145 | 0.94% | 4 | 1.17% |
| Nikolay Borisov | 125 | 0.81% | 21 | 6.16% |
| Josef Whiter | 121 | 0.78% | 5 | 1.47% |
| David Sterba | 76 | 0.49% | 15 | 4.40% |
| Al Viro | 64 | 0.41% | 10 | 2.93% |
| Li Zefan | 42 | 0.27% | 2 | 0.59% |
| Xiaoguang Wang | 40 | 0.26% | 1 | 0.29% |
| Fengguang Wu | 31 | 0.20% | 1 | 0.29% |
| Jeff Layton | 30 | 0.19% | 2 | 0.59% |
| Yan Zheng | 28 | 0.18% | 1 | 0.29% |
| Mingming Cao | 23 | 0.15% | 1 | 0.29% |
| Kirill A. Shutemov | 23 | 0.15% | 2 | 0.59% |
| Davide Italiano | 22 | 0.14% | 1 | 0.29% |
| Tsutomu Itoh | 22 | 0.14% | 3 | 0.88% |
| Xin Zhong | 21 | 0.14% | 1 | 0.29% |
| Shaohua Li | 21 | 0.14% | 1 | 0.29% |
| Jie Liu | 14 | 0.09% | 3 | 0.88% |
| Omar Sandoval | 14 | 0.09% | 3 | 0.88% |
| Dan Carpenter | 8 | 0.05% | 2 | 0.59% |
| Deepa Dinamani | 8 | 0.05% | 3 | 0.88% |
| Mark Fasheh | 7 | 0.05% | 1 | 0.29% |
| Shilong Wang | 6 | 0.04% | 1 | 0.29% |
| Johannes Thumshirn | 6 | 0.04% | 1 | 0.29% |
| Andrew Morton | 6 | 0.04% | 1 | 0.29% |
| Robbie Ko | 5 | 0.03% | 1 | 0.29% |
| Filipe Brandenburger | 5 | 0.03% | 1 | 0.29% |
| Daniel Dressler | 4 | 0.03% | 1 | 0.29% |
| Tejun Heo | 3 | 0.02% | 1 | 0.29% |
| Anand Jain | 3 | 0.02% | 1 | 0.29% |
| Zhao Lei | 3 | 0.02% | 1 | 0.29% |
| Fabian Frederick | 3 | 0.02% | 1 | 0.29% |
| David Howells | 3 | 0.02% | 1 | 0.29% |
| Andrea Gelmini | 2 | 0.01% | 1 | 0.29% |
| Zach Brown | 2 | 0.01% | 1 | 0.29% |
| Darrick J. Wong | 2 | 0.01% | 1 | 0.29% |
| Sven Wegener | 2 | 0.01% | 1 | 0.29% |
| Arnd Bergmann | 2 | 0.01% | 1 | 0.29% |
| Eric Sandeen | 2 | 0.01% | 1 | 0.29% |
| Johannes Weiner | 2 | 0.01% | 1 | 0.29% |
| Alexey Dobriyan | 2 | 0.01% | 2 | 0.59% |
| Miklos Szeredi | 2 | 0.01% | 1 | 0.29% |
| Nicholas D Steeves | 1 | 0.01% | 1 | 0.29% |
| Jan Kara | 1 | 0.01% | 1 | 0.29% |
| Namjae Jeon | 1 | 0.01% | 1 | 0.29% |
| Roel Kluin | 1 | 0.01% | 1 | 0.29% |
| Wanlong Gao | 1 | 0.01% | 1 | 0.29% |
| Mel Gorman | 1 | 0.01% | 1 | 0.29% |
| Luke Dashjr | 1 | 0.01% | 1 | 0.29% |
| Andi Kleen | 1 | 0.01% | 1 | 0.29% |
| Adam Buchbinder | 1 | 0.01% | 1 | 0.29% |
| Total | 15422 | 341 |
123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773774775776777778779780781782783784785786787788789790791792793794795796797798799800801802803804805806807808809810811812813814815816817818819820821822823824825826827828829830831832833834835836837838839840841842843844845846847848849850851852853854855856857858859860861862863864865866867868869870871872873874875876877878879880881882883884885886887888889890891892893894895896897898899900901902903904905906907908909910911912913914915916917918919920921922923924925926927928929930931932933934935936937938939940941942943944945946947948949950951952953954955956957958959960961962963964965966967968969970971972973974975976977978979980981982983984985986987988989990991992993994995996997998999100010011002100310041005100610071008100910101011101210131014101510161017101810191020102110221023102410251026102710281029103010311032103310341035103610371038103910401041104210431044104510461047104810491050105110521053105410551056105710581059106010611062106310641065106610671068106910701071107210731074107510761077107810791080108110821083108410851086108710881089109010911092109310941095109610971098109911001101110211031104110511061107110811091110111111121113111411151116111711181119112011211122112311241125112611271128112911301131113211331134113511361137113811391140114111421143114411451146114711481149115011511152115311541155115611571158115911601161116211631164116511661167116811691170117111721173117411751176117711781179118011811182118311841185118611871188118911901191119211931194119511961197119811991200120112021203120412051206120712081209121012111212121312141215121612171218121912201221122212231224122512261227122812291230123112321233123412351236123712381239124012411242124312441245124612471248124912501251125212531254125512561257125812591260126112621263126412651266126712681269127012711272127312741275127612771278127912801281128212831284128512861287128812891290129112921293129412951296129712981299130013011302130313041305130613071308130913101311131213131314131513161317131813191320132113221323132413251326132713281329133013311332133313341335133613371338133913401341134213431344134513461347134813491350135113521353135413551356135713581359136013611362136313641365136613671368136913701371137213731374137513761377137813791380138113821383138413851386138713881389139013911392139313941395139613971398139914001401140214031404140514061407140814091410141114121413141414151416141714181419142014211422142314241425142614271428142914301431143214331434143514361437143814391440144114421443144414451446144714481449145014511452145314541455145614571458145914601461146214631464146514661467146814691470147114721473147414751476147714781479148014811482148314841485148614871488148914901491149214931494149514961497149814991500150115021503150415051506150715081509151015111512151315141515151615171518151915201521152215231524152515261527152815291530153115321533153415351536153715381539154015411542154315441545154615471548154915501551155215531554155515561557155815591560156115621563156415651566156715681569157015711572157315741575157615771578157915801581158215831584158515861587158815891590159115921593159415951596159715981599160016011602160316041605160616071608160916101611161216131614161516161617161816191620162116221623162416251626162716281629163016311632163316341635163616371638163916401641164216431644164516461647164816491650165116521653165416551656165716581659166016611662166316641665166616671668166916701671167216731674167516761677167816791680168116821683168416851686168716881689169016911692169316941695169616971698169917001701170217031704170517061707170817091710171117121713171417151716171717181719172017211722172317241725172617271728172917301731173217331734173517361737173817391740174117421743174417451746174717481749175017511752175317541755175617571758175917601761176217631764176517661767176817691770177117721773177417751776177717781779178017811782178317841785178617871788178917901791179217931794179517961797179817991800180118021803180418051806180718081809181018111812181318141815181618171818181918201821182218231824182518261827182818291830183118321833183418351836183718381839184018411842184318441845184618471848184918501851185218531854185518561857185818591860186118621863186418651866186718681869187018711872187318741875187618771878187918801881188218831884188518861887188818891890189118921893189418951896189718981899190019011902190319041905190619071908190919101911191219131914191519161917191819191920192119221923192419251926192719281929193019311932193319341935193619371938193919401941194219431944194519461947194819491950195119521953195419551956195719581959196019611962196319641965196619671968196919701971197219731974197519761977197819791980198119821983198419851986198719881989199019911992199319941995199619971998199920002001200220032004200520062007200820092010201120122013201420152016201720182019202020212022202320242025202620272028202920302031203220332034203520362037203820392040204120422043204420452046204720482049205020512052205320542055205620572058205920602061206220632064206520662067206820692070207120722073207420752076207720782079208020812082208320842085208620872088208920902091209220932094209520962097209820992100210121022103210421052106210721082109211021112112211321142115211621172118211921202121212221232124212521262127212821292130213121322133213421352136213721382139214021412142214321442145214621472148214921502151215221532154215521562157215821592160216121622163216421652166216721682169217021712172217321742175217621772178217921802181218221832184218521862187218821892190219121922193219421952196219721982199220022012202220322042205220622072208220922102211221222132214221522162217221822192220222122222223222422252226222722282229223022312232223322342235223622372238223922402241224222432244224522462247224822492250225122522253225422552256225722582259226022612262226322642265226622672268226922702271227222732274227522762277227822792280228122822283228422852286228722882289229022912292229322942295229622972298229923002301230223032304230523062307230823092310231123122313231423152316231723182319232023212322232323242325232623272328232923302331233223332334233523362337233823392340234123422343234423452346234723482349235023512352235323542355235623572358235923602361236223632364236523662367236823692370237123722373237423752376237723782379238023812382238323842385238623872388238923902391239223932394239523962397239823992400240124022403240424052406240724082409241024112412241324142415241624172418241924202421242224232424242524262427242824292430243124322433243424352436243724382439244024412442244324442445244624472448244924502451245224532454245524562457245824592460246124622463246424652466246724682469247024712472247324742475247624772478247924802481248224832484248524862487248824892490249124922493249424952496249724982499250025012502250325042505250625072508250925102511251225132514251525162517251825192520252125222523252425252526252725282529253025312532253325342535253625372538253925402541254225432544254525462547254825492550255125522553255425552556255725582559256025612562256325642565256625672568256925702571257225732574257525762577257825792580258125822583258425852586258725882589259025912592259325942595259625972598259926002601260226032604260526062607260826092610261126122613261426152616261726182619262026212622262326242625262626272628262926302631263226332634263526362637263826392640264126422643264426452646264726482649265026512652265326542655265626572658265926602661266226632664266526662667266826692670267126722673267426752676267726782679268026812682268326842685268626872688268926902691269226932694269526962697269826992700270127022703270427052706270727082709271027112712271327142715271627172718271927202721272227232724272527262727272827292730273127322733273427352736273727382739274027412742274327442745274627472748274927502751275227532754275527562757275827592760276127622763276427652766276727682769277027712772277327742775277627772778277927802781278227832784278527862787278827892790279127922793279427952796279727982799280028012802280328042805280628072808280928102811281228132814281528162817281828192820282128222823282428252826282728282829283028312832283328342835283628372838283928402841284228432844284528462847284828492850285128522853285428552856285728582859286028612862286328642865286628672868286928702871287228732874287528762877287828792880288128822883288428852886288728882889289028912892289328942895289628972898289929002901290229032904290529062907290829092910291129122913291429152916291729182919292029212922292329242925292629272928292929302931293229332934293529362937293829392940294129422943294429452946294729482949295029512952295329542955295629572958295929602961296229632964296529662967296829692970297129722973297429752976297729782979298029812982298329842985298629872988298929902991299229932994299529962997299829993000300130023003300430053006300730083009301030113012301330143015301630173018301930203021302230233024302530263027302830293030303130323033303430353036303730383039304030413042304330443045304630473048304930503051305230533054305530563057305830593060306130623063306430653066306730683069307030713072307330743075307630773078307930803081308230833084308530863087308830893090309130923093309430953096309730983099310031013102310331043105310631073108310931103111311231133114311531163117311831193120312131223123312431253126312731283129313031313132313331343135313631373138313931403141314231433144314531463147314831493150315131523153315431553156315731583159316031613162316331643165316631673168316931703171317231733174317531763177317831793180318131823183318431853186318731883189319031913192319331943195319631973198319932003201320232033204320532063207320832093210321132123213321432153216321732183219322032213222322332243225322632273228322932303231323232333234323532363237323832393240324132423243324432453246324732483249325032513252325332543255325632573258325932603261326232633264326532663267326832693270327132723273327432753276327732783279328032813282328332843285328632873288328932903291329232933294329532963297329832993300330133023303330433053306330733083309331033113312331333143315331633173318331933203321332233233324332533263327332833293330333133323333333433353336333733383339334033413342334333443345334633473348334933503351335233533354335533563357335833593360336133623363336433653366336733683369337033713372337333743375337633773378337933803381338233833384338533863387338833893390339133923393339433953396339733983399340034013402340334043405340634073408340934103411341234133414341534163417341834193420342134223423342434253426342734283429343034313432343334343435343634373438343934403441344234433444344534463447344834493450345134523453345434553456345734583459346034613462346334643465346634673468346934703471347234733474347534763477347834793480348134823483348434853486348734883489349034913492349334943495349634973498349935003501350235033504
// SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2007 Oracle. All rights reserved. */ #include <linux/fs.h> #include <linux/pagemap.h> #include <linux/time.h> #include <linux/init.h> #include <linux/string.h> #include <linux/backing-dev.h> #include <linux/falloc.h> #include <linux/writeback.h> #include <linux/compat.h> #include <linux/slab.h> #include <linux/btrfs.h> #include <linux/uio.h> #include <linux/iversion.h> #include "ctree.h" #include "disk-io.h" #include "transaction.h" #include "btrfs_inode.h" #include "print-tree.h" #include "tree-log.h" #include "locking.h" #include "volumes.h" #include "qgroup.h" #include "compression.h" #include "delalloc-space.h" static struct kmem_cache *btrfs_inode_defrag_cachep; /* * when auto defrag is enabled we * queue up these defrag structs to remember which * inodes need defragging passes */ struct inode_defrag { struct rb_node rb_node; /* objectid */ u64 ino; /* * transid where the defrag was added, we search for * extents newer than this */ u64 transid; /* root objectid */ u64 root; /* last offset we were able to defrag */ u64 last_offset; /* if we've wrapped around back to zero once already */ int cycled; }; static int __compare_inode_defrag(struct inode_defrag *defrag1, struct inode_defrag *defrag2) { if (defrag1->root > defrag2->root) return 1; else if (defrag1->root < defrag2->root) return -1; else if (defrag1->ino > defrag2->ino) return 1; else if (defrag1->ino < defrag2->ino) return -1; else return 0; } /* pop a record for an inode into the defrag tree. The lock * must be held already * * If you're inserting a record for an older transid than an * existing record, the transid already in the tree is lowered * * If an existing record is found the defrag item you * pass in is freed */ static int __btrfs_add_inode_defrag(struct btrfs_inode *inode, struct inode_defrag *defrag) { struct btrfs_fs_info *fs_info = inode->root->fs_info; struct inode_defrag *entry; struct rb_node **p; struct rb_node *parent = NULL; int ret; p = &fs_info->defrag_inodes.rb_node; while (*p) { parent = *p; entry = rb_entry(parent, struct inode_defrag, rb_node); ret = __compare_inode_defrag(defrag, entry); if (ret < 0) p = &parent->rb_left; else if (ret > 0) p = &parent->rb_right; else { /* if we're reinserting an entry for * an old defrag run, make sure to * lower the transid of our existing record */ if (defrag->transid < entry->transid) entry->transid = defrag->transid; if (defrag->last_offset > entry->last_offset) entry->last_offset = defrag->last_offset; return -EEXIST; } } set_bit(BTRFS_INODE_IN_DEFRAG, &inode->runtime_flags); rb_link_node(&defrag->rb_node, parent, p); rb_insert_color(&defrag->rb_node, &fs_info->defrag_inodes); return 0; } static inline int __need_auto_defrag(struct btrfs_fs_info *fs_info) { if (!btrfs_test_opt(fs_info, AUTO_DEFRAG)) return 0; if (btrfs_fs_closing(fs_info)) return 0; return 1; } /* * insert a defrag record for this inode if auto defrag is * enabled */ int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans, struct btrfs_inode *inode) { struct btrfs_root *root = inode->root; struct btrfs_fs_info *fs_info = root->fs_info; struct inode_defrag *defrag; u64 transid; int ret; if (!__need_auto_defrag(fs_info)) return 0; if (test_bit(BTRFS_INODE_IN_DEFRAG, &inode->runtime_flags)) return 0; if (trans) transid = trans->transid; else transid = inode->root->last_trans; defrag = kmem_cache_zalloc(btrfs_inode_defrag_cachep, GFP_NOFS); if (!defrag) return -ENOMEM; defrag->ino = btrfs_ino(inode); defrag->transid = transid; defrag->root = root->root_key.objectid; spin_lock(&fs_info->defrag_inodes_lock); if (!test_bit(BTRFS_INODE_IN_DEFRAG, &inode->runtime_flags)) { /* * If we set IN_DEFRAG flag and evict the inode from memory, * and then re-read this inode, this new inode doesn't have * IN_DEFRAG flag. At the case, we may find the existed defrag. */ ret = __btrfs_add_inode_defrag(inode, defrag); if (ret) kmem_cache_free(btrfs_inode_defrag_cachep, defrag); } else { kmem_cache_free(btrfs_inode_defrag_cachep, defrag); } spin_unlock(&fs_info->defrag_inodes_lock); return 0; } /* * Requeue the defrag object. If there is a defrag object that points to * the same inode in the tree, we will merge them together (by * __btrfs_add_inode_defrag()) and free the one that we want to requeue. */ static void btrfs_requeue_inode_defrag(struct btrfs_inode *inode, struct inode_defrag *defrag) { struct btrfs_fs_info *fs_info = inode->root->fs_info; int ret; if (!__need_auto_defrag(fs_info)) goto out; /* * Here we don't check the IN_DEFRAG flag, because we need merge * them together. */ spin_lock(&fs_info->defrag_inodes_lock); ret = __btrfs_add_inode_defrag(inode, defrag); spin_unlock(&fs_info->defrag_inodes_lock); if (ret) goto out; return; out: kmem_cache_free(btrfs_inode_defrag_cachep, defrag); } /* * pick the defragable inode that we want, if it doesn't exist, we will get * the next one. */ static struct inode_defrag * btrfs_pick_defrag_inode(struct btrfs_fs_info *fs_info, u64 root, u64 ino) { struct inode_defrag *entry = NULL; struct inode_defrag tmp; struct rb_node *p; struct rb_node *parent = NULL; int ret; tmp.ino = ino; tmp.root = root; spin_lock(&fs_info->defrag_inodes_lock); p = fs_info->defrag_inodes.rb_node; while (p) { parent = p; entry = rb_entry(parent, struct inode_defrag, rb_node); ret = __compare_inode_defrag(&tmp, entry); if (ret < 0) p = parent->rb_left; else if (ret > 0) p = parent->rb_right; else goto out; } if (parent && __compare_inode_defrag(&tmp, entry) > 0) { parent = rb_next(parent); if (parent) entry = rb_entry(parent, struct inode_defrag, rb_node); else entry = NULL; } out: if (entry) rb_erase(parent, &fs_info->defrag_inodes); spin_unlock(&fs_info->defrag_inodes_lock); return entry; } void btrfs_cleanup_defrag_inodes(struct btrfs_fs_info *fs_info) { struct inode_defrag *defrag; struct rb_node *node; spin_lock(&fs_info->defrag_inodes_lock); node = rb_first(&fs_info->defrag_inodes); while (node) { rb_erase(node, &fs_info->defrag_inodes); defrag = rb_entry(node, struct inode_defrag, rb_node); kmem_cache_free(btrfs_inode_defrag_cachep, defrag); cond_resched_lock(&fs_info->defrag_inodes_lock); node = rb_first(&fs_info->defrag_inodes); } spin_unlock(&fs_info->defrag_inodes_lock); } #define BTRFS_DEFRAG_BATCH 1024 static int __btrfs_run_defrag_inode(struct btrfs_fs_info *fs_info, struct inode_defrag *defrag) { struct btrfs_root *inode_root; struct inode *inode; struct btrfs_key key; struct btrfs_ioctl_defrag_range_args range; int num_defrag; int index; int ret; /* get the inode */ key.objectid = defrag->root; key.type = BTRFS_ROOT_ITEM_KEY; key.offset = (u64)-1; index = srcu_read_lock(&fs_info->subvol_srcu); inode_root = btrfs_read_fs_root_no_name(fs_info, &key); if (IS_ERR(inode_root)) { ret = PTR_ERR(inode_root); goto cleanup; } key.objectid = defrag->ino; key.type = BTRFS_INODE_ITEM_KEY; key.offset = 0; inode = btrfs_iget(fs_info->sb, &key, inode_root); if (IS_ERR(inode)) { ret = PTR_ERR(inode); goto cleanup; } srcu_read_unlock(&fs_info->subvol_srcu, index); /* do a chunk of defrag */ clear_bit(BTRFS_INODE_IN_DEFRAG, &BTRFS_I(inode)->runtime_flags); memset(&range, 0, sizeof(range)); range.len = (u64)-1; range.start = defrag->last_offset; sb_start_write(fs_info->sb); num_defrag = btrfs_defrag_file(inode, NULL, &range, defrag->transid, BTRFS_DEFRAG_BATCH); sb_end_write(fs_info->sb); /* * if we filled the whole defrag batch, there * must be more work to do. Queue this defrag * again */ if (num_defrag == BTRFS_DEFRAG_BATCH) { defrag->last_offset = range.start; btrfs_requeue_inode_defrag(BTRFS_I(inode), defrag); } else if (defrag->last_offset && !defrag->cycled) { /* * we didn't fill our defrag batch, but * we didn't start at zero. Make sure we loop * around to the start of the file. */ defrag->last_offset = 0; defrag->cycled = 1; btrfs_requeue_inode_defrag(BTRFS_I(inode), defrag); } else { kmem_cache_free(btrfs_inode_defrag_cachep, defrag); } iput(inode); return 0; cleanup: srcu_read_unlock(&fs_info->subvol_srcu, index); kmem_cache_free(btrfs_inode_defrag_cachep, defrag); return ret; } /* * run through the list of inodes in the FS that need * defragging */ int btrfs_run_defrag_inodes(struct btrfs_fs_info *fs_info) { struct inode_defrag *defrag; u64 first_ino = 0; u64 root_objectid = 0; atomic_inc(&fs_info->defrag_running); while (1) { /* Pause the auto defragger. */ if (test_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state)) break; if (!__need_auto_defrag(fs_info)) break; /* find an inode to defrag */ defrag = btrfs_pick_defrag_inode(fs_info, root_objectid, first_ino); if (!defrag) { if (root_objectid || first_ino) { root_objectid = 0; first_ino = 0; continue; } else { break; } } first_ino = defrag->ino + 1; root_objectid = defrag->root; __btrfs_run_defrag_inode(fs_info, defrag); } atomic_dec(&fs_info->defrag_running); /* * during unmount, we use the transaction_wait queue to * wait for the defragger to stop */ wake_up(&fs_info->transaction_wait); return 0; } /* simple helper to fault in pages and copy. This should go away * and be replaced with calls into generic code. */ static noinline int btrfs_copy_from_user(loff_t pos, size_t write_bytes, struct page **prepared_pages, struct iov_iter *i) { size_t copied = 0; size_t total_copied = 0; int pg = 0; int offset = offset_in_page(pos); while (write_bytes > 0) { size_t count = min_t(size_t, PAGE_SIZE - offset, write_bytes); struct page *page = prepared_pages[pg]; /* * Copy data from userspace to the current page */ copied = iov_iter_copy_from_user_atomic(page, i, offset, count); /* Flush processor's dcache for this page */ flush_dcache_page(page); /* * if we get a partial write, we can end up with * partially up to date pages. These add * a lot of complexity, so make sure they don't * happen by forcing this copy to be retried. * * The rest of the btrfs_file_write code will fall * back to page at a time copies after we return 0. */ if (!PageUptodate(page) && copied < count) copied = 0; iov_iter_advance(i, copied); write_bytes -= copied; total_copied += copied; /* Return to btrfs_file_write_iter to fault page */ if (unlikely(copied == 0)) break; if (copied < PAGE_SIZE - offset) { offset += copied; } else { pg++; offset = 0; } } return total_copied; } /* * unlocks pages after btrfs_file_write is done with them */ static void btrfs_drop_pages(struct page **pages, size_t num_pages) { size_t i; for (i = 0; i < num_pages; i++) { /* page checked is some magic around finding pages that * have been modified without going through btrfs_set_page_dirty * clear it here. There should be no need to mark the pages * accessed as prepare_pages should have marked them accessed * in prepare_pages via find_or_create_page() */ ClearPageChecked(pages[i]); unlock_page(pages[i]); put_page(pages[i]); } } static int btrfs_find_new_delalloc_bytes(struct btrfs_inode *inode, const u64 start, const u64 len, struct extent_state **cached_state) { u64 search_start = start; const u64 end = start + len - 1; while (search_start < end) { const u64 search_len = end - search_start + 1; struct extent_map *em; u64 em_len; int ret = 0; em = btrfs_get_extent(inode, NULL, 0, search_start, search_len); if (IS_ERR(em)) return PTR_ERR(em); if (em->block_start != EXTENT_MAP_HOLE) goto next; em_len = em->len; if (em->start < search_start) em_len -= search_start - em->start; if (em_len > search_len) em_len = search_len; ret = set_extent_bit(&inode->io_tree, search_start, search_start + em_len - 1, EXTENT_DELALLOC_NEW, NULL, cached_state, GFP_NOFS); next: search_start = extent_map_end(em); free_extent_map(em); if (ret) return ret; } return 0; } /* * after copy_from_user, pages need to be dirtied and we need to make * sure holes are created between the current EOF and the start of * any next extents (if required). * * this also makes the decision about creating an inline extent vs * doing real data extents, marking pages dirty and delalloc as required. */ int btrfs_dirty_pages(struct inode *inode, struct page **pages, size_t num_pages, loff_t pos, size_t write_bytes, struct extent_state **cached) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); int err = 0; int i; u64 num_bytes; u64 start_pos; u64 end_of_last_block; u64 end_pos = pos + write_bytes; loff_t isize = i_size_read(inode); unsigned int extra_bits = 0; start_pos = pos & ~((u64) fs_info->sectorsize - 1); num_bytes = round_up(write_bytes + pos - start_pos, fs_info->sectorsize); end_of_last_block = start_pos + num_bytes - 1; /* * The pages may have already been dirty, clear out old accounting so * we can set things up properly */ clear_extent_bit(&BTRFS_I(inode)->io_tree, start_pos, end_of_last_block, EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, 0, 0, cached); if (!btrfs_is_free_space_inode(BTRFS_I(inode))) { if (start_pos >= isize && !(BTRFS_I(inode)->flags & BTRFS_INODE_PREALLOC)) { /* * There can't be any extents following eof in this case * so just set the delalloc new bit for the range * directly. */ extra_bits |= EXTENT_DELALLOC_NEW; } else { err = btrfs_find_new_delalloc_bytes(BTRFS_I(inode), start_pos, num_bytes, cached); if (err) return err; } } err = btrfs_set_extent_delalloc(inode, start_pos, end_of_last_block, extra_bits, cached); if (err) return err; for (i = 0; i < num_pages; i++) { struct page *p = pages[i]; SetPageUptodate(p); ClearPageChecked(p); set_page_dirty(p); } /* * we've only changed i_size in ram, and we haven't updated * the disk i_size. There is no need to log the inode * at this time. */ if (end_pos > isize) i_size_write(inode, end_pos); return 0; } /* * this drops all the extents in the cache that intersect the range * [start, end]. Existing extents are split as required. */ void btrfs_drop_extent_cache(struct btrfs_inode *inode, u64 start, u64 end, int skip_pinned) { struct extent_map *em; struct extent_map *split = NULL; struct extent_map *split2 = NULL; struct extent_map_tree *em_tree = &inode->extent_tree; u64 len = end - start + 1; u64 gen; int ret; int testend = 1; unsigned long flags; int compressed = 0; bool modified; WARN_ON(end < start); if (end == (u64)-1) { len = (u64)-1; testend = 0; } while (1) { int no_splits = 0; modified = false; if (!split) split = alloc_extent_map(); if (!split2) split2 = alloc_extent_map(); if (!split || !split2) no_splits = 1; write_lock(&em_tree->lock); em = lookup_extent_mapping(em_tree, start, len); if (!em) { write_unlock(&em_tree->lock); break; } flags = em->flags; gen = em->generation; if (skip_pinned && test_bit(EXTENT_FLAG_PINNED, &em->flags)) { if (testend && em->start + em->len >= start + len) { free_extent_map(em); write_unlock(&em_tree->lock); break; } start = em->start + em->len; if (testend) len = start + len - (em->start + em->len); free_extent_map(em); write_unlock(&em_tree->lock); continue; } compressed = test_bit(EXTENT_FLAG_COMPRESSED, &em->flags); clear_bit(EXTENT_FLAG_PINNED, &em->flags); clear_bit(EXTENT_FLAG_LOGGING, &flags); modified = !list_empty(&em->list); if (no_splits) goto next; if (em->start < start) { split->start = em->start; split->len = start - em->start; if (em->block_start < EXTENT_MAP_LAST_BYTE) { split->orig_start = em->orig_start; split->block_start = em->block_start; if (compressed) split->block_len = em->block_len; else split->block_len = split->len; split->orig_block_len = max(split->block_len, em->orig_block_len); split->ram_bytes = em->ram_bytes; } else { split->orig_start = split->start; split->block_len = 0; split->block_start = em->block_start; split->orig_block_len = 0; split->ram_bytes = split->len; } split->generation = gen; split->flags = flags; split->compress_type = em->compress_type; replace_extent_mapping(em_tree, em, split, modified); free_extent_map(split); split = split2; split2 = NULL; } if (testend && em->start + em->len > start + len) { u64 diff = start + len - em->start; split->start = start + len; split->len = em->start + em->len - (start + len); split->flags = flags; split->compress_type = em->compress_type; split->generation = gen; if (em->block_start < EXTENT_MAP_LAST_BYTE) { split->orig_block_len = max(em->block_len, em->orig_block_len); split->ram_bytes = em->ram_bytes; if (compressed) { split->block_len = em->block_len; split->block_start = em->block_start; split->orig_start = em->orig_start; } else { split->block_len = split->len; split->block_start = em->block_start + diff; split->orig_start = em->orig_start; } } else { split->ram_bytes = split->len; split->orig_start = split->start; split->block_len = 0; split->block_start = em->block_start; split->orig_block_len = 0; } if (extent_map_in_tree(em)) { replace_extent_mapping(em_tree, em, split, modified); } else { ret = add_extent_mapping(em_tree, split, modified); ASSERT(ret == 0); /* Logic error */ } free_extent_map(split); split = NULL; } next: if (extent_map_in_tree(em)) remove_extent_mapping(em_tree, em); write_unlock(&em_tree->lock); /* once for us */ free_extent_map(em); /* once for the tree*/ free_extent_map(em); } if (split) free_extent_map(split); if (split2) free_extent_map(split2); } /* * this is very complex, but the basic idea is to drop all extents * in the range start - end. hint_block is filled in with a block number * that would be a good hint to the block allocator for this file. * * If an extent intersects the range but is not entirely inside the range * it is either truncated or split. Anything entirely inside the range * is deleted from the tree. */ int __btrfs_drop_extents(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct inode *inode, struct btrfs_path *path, u64 start, u64 end, u64 *drop_end, int drop_cache, int replace_extent, u32 extent_item_size, int *key_inserted) { struct btrfs_fs_info *fs_info = root->fs_info; struct extent_buffer *leaf; struct btrfs_file_extent_item *fi; struct btrfs_ref ref = { 0 }; struct btrfs_key key; struct btrfs_key new_key; u64 ino = btrfs_ino(BTRFS_I(inode)); u64 search_start = start; u64 disk_bytenr = 0; u64 num_bytes = 0; u64 extent_offset = 0; u64 extent_end = 0; u64 last_end = start; int del_nr = 0; int del_slot = 0; int extent_type; int recow; int ret; int modify_tree = -1; int update_refs; int found = 0; int leafs_visited = 0; if (drop_cache) btrfs_drop_extent_cache(BTRFS_I(inode), start, end - 1, 0); if (start >= BTRFS_I(inode)->disk_i_size && !replace_extent) modify_tree = 0; update_refs = (test_bit(BTRFS_ROOT_REF_COWS, &root->state) || root == fs_info->tree_root); while (1) { recow = 0; ret = btrfs_lookup_file_extent(trans, root, path, ino, search_start, modify_tree); if (ret < 0) break; if (ret > 0 && path->slots[0] > 0 && search_start == start) { leaf = path->nodes[0]; btrfs_item_key_to_cpu(leaf, &key, path->slots[0] - 1); if (key.objectid == ino && key.type == BTRFS_EXTENT_DATA_KEY) path->slots[0]--; } ret = 0; leafs_visited++; next_slot: leaf = path->nodes[0]; if (path->slots[0] >= btrfs_header_nritems(leaf)) { BUG_ON(del_nr > 0); ret = btrfs_next_leaf(root, path); if (ret < 0) break; if (ret > 0) { ret = 0; break; } leafs_visited++; leaf = path->nodes[0]; recow = 1; } btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); if (key.objectid > ino) break; if (WARN_ON_ONCE(key.objectid < ino) || key.type < BTRFS_EXTENT_DATA_KEY) { ASSERT(del_nr == 0); path->slots[0]++; goto next_slot; } if (key.type > BTRFS_EXTENT_DATA_KEY || key.offset >= end) break; fi = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item); extent_type = btrfs_file_extent_type(leaf, fi); if (extent_type == BTRFS_FILE_EXTENT_REG || extent_type == BTRFS_FILE_EXTENT_PREALLOC) { disk_bytenr = btrfs_file_extent_disk_bytenr(leaf, fi); num_bytes = btrfs_file_extent_disk_num_bytes(leaf, fi); extent_offset = btrfs_file_extent_offset(leaf, fi); extent_end = key.offset + btrfs_file_extent_num_bytes(leaf, fi); } else if (extent_type == BTRFS_FILE_EXTENT_INLINE) { extent_end = key.offset + btrfs_file_extent_ram_bytes(leaf, fi); } else { /* can't happen */ BUG(); } /* * Don't skip extent items representing 0 byte lengths. They * used to be created (bug) if while punching holes we hit * -ENOSPC condition. So if we find one here, just ensure we * delete it, otherwise we would insert a new file extent item * with the same key (offset) as that 0 bytes length file * extent item in the call to setup_items_for_insert() later * in this function. */ if (extent_end == key.offset && extent_end >= search_start) { last_end = extent_end; goto delete_extent_item; } if (extent_end <= search_start) { path->slots[0]++; goto next_slot; } found = 1; search_start = max(key.offset, start); if (recow || !modify_tree) { modify_tree = -1; btrfs_release_path(path); continue; } /* * | - range to drop - | * | -------- extent -------- | */ if (start > key.offset && end < extent_end) { BUG_ON(del_nr > 0); if (extent_type == BTRFS_FILE_EXTENT_INLINE) { ret = -EOPNOTSUPP; break; } memcpy(&new_key, &key, sizeof(new_key)); new_key.offset = start; ret = btrfs_duplicate_item(trans, root, path, &new_key); if (ret == -EAGAIN) { btrfs_release_path(path); continue; } if (ret < 0) break; leaf = path->nodes[0]; fi = btrfs_item_ptr(leaf, path->slots[0] - 1, struct btrfs_file_extent_item); btrfs_set_file_extent_num_bytes(leaf, fi, start - key.offset); fi = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item); extent_offset += start - key.offset; btrfs_set_file_extent_offset(leaf, fi, extent_offset); btrfs_set_file_extent_num_bytes(leaf, fi, extent_end - start); btrfs_mark_buffer_dirty(leaf); if (update_refs && disk_bytenr > 0) { btrfs_init_generic_ref(&ref, BTRFS_ADD_DELAYED_REF, disk_bytenr, num_bytes, 0); btrfs_init_data_ref(&ref, root->root_key.objectid, new_key.objectid, start - extent_offset); ret = btrfs_inc_extent_ref(trans, &ref); BUG_ON(ret); /* -ENOMEM */ } key.offset = start; } /* * From here on out we will have actually dropped something, so * last_end can be updated. */ last_end = extent_end; /* * | ---- range to drop ----- | * | -------- extent -------- | */ if (start <= key.offset && end < extent_end) { if (extent_type == BTRFS_FILE_EXTENT_INLINE) { ret = -EOPNOTSUPP; break; } memcpy(&new_key, &key, sizeof(new_key)); new_key.offset = end; btrfs_set_item_key_safe(fs_info, path, &new_key); extent_offset += end - key.offset; btrfs_set_file_extent_offset(leaf, fi, extent_offset); btrfs_set_file_extent_num_bytes(leaf, fi, extent_end - end); btrfs_mark_buffer_dirty(leaf); if (update_refs && disk_bytenr > 0) inode_sub_bytes(inode, end - key.offset); break; } search_start = extent_end; /* * | ---- range to drop ----- | * | -------- extent -------- | */ if (start > key.offset && end >= extent_end) { BUG_ON(del_nr > 0); if (extent_type == BTRFS_FILE_EXTENT_INLINE) { ret = -EOPNOTSUPP; break; } btrfs_set_file_extent_num_bytes(leaf, fi, start - key.offset); btrfs_mark_buffer_dirty(leaf); if (update_refs && disk_bytenr > 0) inode_sub_bytes(inode, extent_end - start); if (end == extent_end) break; path->slots[0]++; goto next_slot; } /* * | ---- range to drop ----- | * | ------ extent ------ | */ if (start <= key.offset && end >= extent_end) { delete_extent_item: if (del_nr == 0) { del_slot = path->slots[0]; del_nr = 1; } else { BUG_ON(del_slot + del_nr != path->slots[0]); del_nr++; } if (update_refs && extent_type == BTRFS_FILE_EXTENT_INLINE) { inode_sub_bytes(inode, extent_end - key.offset); extent_end = ALIGN(extent_end, fs_info->sectorsize); } else if (update_refs && disk_bytenr > 0) { btrfs_init_generic_ref(&ref, BTRFS_DROP_DELAYED_REF, disk_bytenr, num_bytes, 0); btrfs_init_data_ref(&ref, root->root_key.objectid, key.objectid, key.offset - extent_offset); ret = btrfs_free_extent(trans, &ref); BUG_ON(ret); /* -ENOMEM */ inode_sub_bytes(inode, extent_end - key.offset); } if (end == extent_end) break; if (path->slots[0] + 1 < btrfs_header_nritems(leaf)) { path->slots[0]++; goto next_slot; } ret = btrfs_del_items(trans, root, path, del_slot, del_nr); if (ret) { btrfs_abort_transaction(trans, ret); break; } del_nr = 0; del_slot = 0; btrfs_release_path(path); continue; } BUG(); } if (!ret && del_nr > 0) { /* * Set path->slots[0] to first slot, so that after the delete * if items are move off from our leaf to its immediate left or * right neighbor leafs, we end up with a correct and adjusted * path->slots[0] for our insertion (if replace_extent != 0). */ path->slots[0] = del_slot; ret = btrfs_del_items(trans, root, path, del_slot, del_nr); if (ret) btrfs_abort_transaction(trans, ret); } leaf = path->nodes[0]; /* * If btrfs_del_items() was called, it might have deleted a leaf, in * which case it unlocked our path, so check path->locks[0] matches a * write lock. */ if (!ret && replace_extent && leafs_visited == 1 && (path->locks[0] == BTRFS_WRITE_LOCK_BLOCKING || path->locks[0] == BTRFS_WRITE_LOCK) && btrfs_leaf_free_space(leaf) >= sizeof(struct btrfs_item) + extent_item_size) { key.objectid = ino; key.type = BTRFS_EXTENT_DATA_KEY; key.offset = start; if (!del_nr && path->slots[0] < btrfs_header_nritems(leaf)) { struct btrfs_key slot_key; btrfs_item_key_to_cpu(leaf, &slot_key, path->slots[0]); if (btrfs_comp_cpu_keys(&key, &slot_key) > 0) path->slots[0]++; } setup_items_for_insert(root, path, &key, &extent_item_size, extent_item_size, sizeof(struct btrfs_item) + extent_item_size, 1); *key_inserted = 1; } if (!replace_extent || !(*key_inserted)) btrfs_release_path(path); if (drop_end) *drop_end = found ? min(end, last_end) : end; return ret; } int btrfs_drop_extents(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct inode *inode, u64 start, u64 end, int drop_cache) { struct btrfs_path *path; int ret; path = btrfs_alloc_path(); if (!path) return -ENOMEM; ret = __btrfs_drop_extents(trans, root, inode, path, start, end, NULL, drop_cache, 0, 0, NULL); btrfs_free_path(path); return ret; } static int extent_mergeable(struct extent_buffer *leaf, int slot, u64 objectid, u64 bytenr, u64 orig_offset, u64 *start, u64 *end) { struct btrfs_file_extent_item *fi; struct btrfs_key key; u64 extent_end; if (slot < 0 || slot >= btrfs_header_nritems(leaf)) return 0; btrfs_item_key_to_cpu(leaf, &key, slot); if (key.objectid != objectid || key.type != BTRFS_EXTENT_DATA_KEY) return 0; fi = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item); if (btrfs_file_extent_type(leaf, fi) != BTRFS_FILE_EXTENT_REG || btrfs_file_extent_disk_bytenr(leaf, fi) != bytenr || btrfs_file_extent_offset(leaf, fi) != key.offset - orig_offset || btrfs_file_extent_compression(leaf, fi) || btrfs_file_extent_encryption(leaf, fi) || btrfs_file_extent_other_encoding(leaf, fi)) return 0; extent_end = key.offset + btrfs_file_extent_num_bytes(leaf, fi); if ((*start && *start != key.offset) || (*end && *end != extent_end)) return 0; *start = key.offset; *end = extent_end; return 1; } /* * Mark extent in the range start - end as written. * * This changes extent type from 'pre-allocated' to 'regular'. If only * part of extent is marked as written, the extent will be split into * two or three. */ int btrfs_mark_extent_written(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, u64 start, u64 end) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_root *root = inode->root; struct extent_buffer *leaf; struct btrfs_path *path; struct btrfs_file_extent_item *fi; struct btrfs_ref ref = { 0 }; struct btrfs_key key; struct btrfs_key new_key; u64 bytenr; u64 num_bytes; u64 extent_end; u64 orig_offset; u64 other_start; u64 other_end; u64 split; int del_nr = 0; int del_slot = 0; int recow; int ret; u64 ino = btrfs_ino(inode); path = btrfs_alloc_path(); if (!path) return -ENOMEM; again: recow = 0; split = start; key.objectid = ino; key.type = BTRFS_EXTENT_DATA_KEY; key.offset = split; ret = btrfs_search_slot(trans, root, &key, path, -1, 1); if (ret < 0) goto out; if (ret > 0 && path->slots[0] > 0) path->slots[0]--; leaf = path->nodes[0]; btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); if (key.objectid != ino || key.type != BTRFS_EXTENT_DATA_KEY) { ret = -EINVAL; btrfs_abort_transaction(trans, ret); goto out; } fi = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item); if (btrfs_file_extent_type(leaf, fi) != BTRFS_FILE_EXTENT_PREALLOC) { ret = -EINVAL; btrfs_abort_transaction(trans, ret); goto out; } extent_end = key.offset + btrfs_file_extent_num_bytes(leaf, fi); if (key.offset > start || extent_end < end) { ret = -EINVAL; btrfs_abort_transaction(trans, ret); goto out; } bytenr = btrfs_file_extent_disk_bytenr(leaf, fi); num_bytes = btrfs_file_extent_disk_num_bytes(leaf, fi); orig_offset = key.offset - btrfs_file_extent_offset(leaf, fi); memcpy(&new_key, &key, sizeof(new_key)); if (start == key.offset && end < extent_end) { other_start = 0; other_end = start; if (extent_mergeable(leaf, path->slots[0] - 1, ino, bytenr, orig_offset, &other_start, &other_end)) { new_key.offset = end; btrfs_set_item_key_safe(fs_info, path, &new_key); fi = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item); btrfs_set_file_extent_generation(leaf, fi, trans->transid); btrfs_set_file_extent_num_bytes(leaf, fi, extent_end - end); btrfs_set_file_extent_offset(leaf, fi, end - orig_offset); fi = btrfs_item_ptr(leaf, path->slots[0] - 1, struct btrfs_file_extent_item); btrfs_set_file_extent_generation(leaf, fi, trans->transid); btrfs_set_file_extent_num_bytes(leaf, fi, end - other_start); btrfs_mark_buffer_dirty(leaf); goto out; } } if (start > key.offset && end == extent_end) { other_start = end; other_end = 0; if (extent_mergeable(leaf, path->slots[0] + 1, ino, bytenr, orig_offset, &other_start, &other_end)) { fi = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item); btrfs_set_file_extent_num_bytes(leaf, fi, start - key.offset); btrfs_set_file_extent_generation(leaf, fi, trans->transid); path->slots[0]++; new_key.offset = start; btrfs_set_item_key_safe(fs_info, path, &new_key); fi = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item); btrfs_set_file_extent_generation(leaf, fi, trans->transid); btrfs_set_file_extent_num_bytes(leaf, fi, other_end - start); btrfs_set_file_extent_offset(leaf, fi, start - orig_offset); btrfs_mark_buffer_dirty(leaf); goto out; } } while (start > key.offset || end < extent_end) { if (key.offset == start) split = end; new_key.offset = split; ret = btrfs_duplicate_item(trans, root, path, &new_key); if (ret == -EAGAIN) { btrfs_release_path(path); goto again; } if (ret < 0) { btrfs_abort_transaction(trans, ret); goto out; } leaf = path->nodes[0]; fi = btrfs_item_ptr(leaf, path->slots[0] - 1, struct btrfs_file_extent_item); btrfs_set_file_extent_generation(leaf, fi, trans->transid); btrfs_set_file_extent_num_bytes(leaf, fi, split - key.offset); fi = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item); btrfs_set_file_extent_generation(leaf, fi, trans->transid); btrfs_set_file_extent_offset(leaf, fi, split - orig_offset); btrfs_set_file_extent_num_bytes(leaf, fi, extent_end - split); btrfs_mark_buffer_dirty(leaf); btrfs_init_generic_ref(&ref, BTRFS_ADD_DELAYED_REF, bytenr, num_bytes, 0); btrfs_init_data_ref(&ref, root->root_key.objectid, ino, orig_offset); ret = btrfs_inc_extent_ref(trans, &ref); if (ret) { btrfs_abort_transaction(trans, ret); goto out; } if (split == start) { key.offset = start; } else { if (start != key.offset) { ret = -EINVAL; btrfs_abort_transaction(trans, ret); goto out; } path->slots[0]--; extent_end = end; } recow = 1; } other_start = end; other_end = 0; btrfs_init_generic_ref(&ref, BTRFS_DROP_DELAYED_REF, bytenr, num_bytes, 0); btrfs_init_data_ref(&ref, root->root_key.objectid, ino, orig_offset); if (extent_mergeable(leaf, path->slots[0] + 1, ino, bytenr, orig_offset, &other_start, &other_end)) { if (recow) { btrfs_release_path(path); goto again; } extent_end = other_end; del_slot = path->slots[0] + 1; del_nr++; ret = btrfs_free_extent(trans, &ref); if (ret) { btrfs_abort_transaction(trans, ret); goto out; } } other_start = 0; other_end = start; if (extent_mergeable(leaf, path->slots[0] - 1, ino, bytenr, orig_offset, &other_start, &other_end)) { if (recow) { btrfs_release_path(path); goto again; } key.offset = other_start; del_slot = path->slots[0]; del_nr++; ret = btrfs_free_extent(trans, &ref); if (ret) { btrfs_abort_transaction(trans, ret); goto out; } } if (del_nr == 0) { fi = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item); btrfs_set_file_extent_type(leaf, fi, BTRFS_FILE_EXTENT_REG); btrfs_set_file_extent_generation(leaf, fi, trans->transid); btrfs_mark_buffer_dirty(leaf); } else { fi = btrfs_item_ptr(leaf, del_slot - 1, struct btrfs_file_extent_item); btrfs_set_file_extent_type(leaf, fi, BTRFS_FILE_EXTENT_REG); btrfs_set_file_extent_generation(leaf, fi, trans->transid); btrfs_set_file_extent_num_bytes(leaf, fi, extent_end - key.offset); btrfs_mark_buffer_dirty(leaf); ret = btrfs_del_items(trans, root, path, del_slot, del_nr); if (ret < 0) { btrfs_abort_transaction(trans, ret); goto out; } } out: btrfs_free_path(path); return 0; } /* * on error we return an unlocked page and the error value * on success we return a locked page and 0 */ static int prepare_uptodate_page(struct inode *inode, struct page *page, u64 pos, bool force_uptodate) { int ret = 0; if (((pos & (PAGE_SIZE - 1)) || force_uptodate) && !PageUptodate(page)) { ret = btrfs_readpage(NULL, page); if (ret) return ret; lock_page(page); if (!PageUptodate(page)) { unlock_page(page); return -EIO; } if (page->mapping != inode->i_mapping) { unlock_page(page); return -EAGAIN; } } return 0; } /* * this just gets pages into the page cache and locks them down. */ static noinline int prepare_pages(struct inode *inode, struct page **pages, size_t num_pages, loff_t pos, size_t write_bytes, bool force_uptodate) { int i; unsigned long index = pos >> PAGE_SHIFT; gfp_t mask = btrfs_alloc_write_mask(inode->i_mapping); int err = 0; int faili; for (i = 0; i < num_pages; i++) { again: pages[i] = find_or_create_page(inode->i_mapping, index + i, mask | __GFP_WRITE); if (!pages[i]) { faili = i - 1; err = -ENOMEM; goto fail; } if (i == 0) err = prepare_uptodate_page(inode, pages[i], pos, force_uptodate); if (!err && i == num_pages - 1) err = prepare_uptodate_page(inode, pages[i], pos + write_bytes, false); if (err) { put_page(pages[i]); if (err == -EAGAIN) { err = 0; goto again; } faili = i - 1; goto fail; } wait_on_page_writeback(pages[i]); } return 0; fail: while (faili >= 0) { unlock_page(pages[faili]); put_page(pages[faili]); faili--; } return err; } /* * This function locks the extent and properly waits for data=ordered extents * to finish before allowing the pages to be modified if need. * * The return value: * 1 - the extent is locked * 0 - the extent is not locked, and everything is OK * -EAGAIN - need re-prepare the pages * the other < 0 number - Something wrong happens */ static noinline int lock_and_cleanup_extent_if_need(struct btrfs_inode *inode, struct page **pages, size_t num_pages, loff_t pos, size_t write_bytes, u64 *lockstart, u64 *lockend, struct extent_state **cached_state) { struct btrfs_fs_info *fs_info = inode->root->fs_info; u64 start_pos; u64 last_pos; int i; int ret = 0; start_pos = round_down(pos, fs_info->sectorsize); last_pos = start_pos + round_up(pos + write_bytes - start_pos, fs_info->sectorsize) - 1; if (start_pos < inode->vfs_inode.i_size) { struct btrfs_ordered_extent *ordered; lock_extent_bits(&inode->io_tree, start_pos, last_pos, cached_state); ordered = btrfs_lookup_ordered_range(inode, start_pos, last_pos - start_pos + 1); if (ordered && ordered->file_offset + ordered->num_bytes > start_pos && ordered->file_offset <= last_pos) { unlock_extent_cached(&inode->io_tree, start_pos, last_pos, cached_state); for (i = 0; i < num_pages; i++) { unlock_page(pages[i]); put_page(pages[i]); } btrfs_start_ordered_extent(&inode->vfs_inode, ordered, 1); btrfs_put_ordered_extent(ordered); return -EAGAIN; } if (ordered) btrfs_put_ordered_extent(ordered); *lockstart = start_pos; *lockend = last_pos; ret = 1; } /* * It's possible the pages are dirty right now, but we don't want * to clean them yet because copy_from_user may catch a page fault * and we might have to fall back to one page at a time. If that * happens, we'll unlock these pages and we'd have a window where * reclaim could sneak in and drop the once-dirty page on the floor * without writing it. * * We have the pages locked and the extent range locked, so there's * no way someone can start IO on any dirty pages in this range. * * We'll call btrfs_dirty_pages() later on, and that will flip around * delalloc bits and dirty the pages as required. */ for (i = 0; i < num_pages; i++) { set_page_extent_mapped(pages[i]); WARN_ON(!PageLocked(pages[i])); } return ret; } static noinline int check_can_nocow(struct btrfs_inode *inode, loff_t pos, size_t *write_bytes) { struct btrfs_fs_info *fs_info = inode->root->fs_info; struct btrfs_root *root = inode->root; u64 lockstart, lockend; u64 num_bytes; int ret; ret = btrfs_start_write_no_snapshotting(root); if (!ret) return -EAGAIN; lockstart = round_down(pos, fs_info->sectorsize); lockend = round_up(pos + *write_bytes, fs_info->sectorsize) - 1; btrfs_lock_and_flush_ordered_range(&inode->io_tree, inode, lockstart, lockend, NULL); num_bytes = lockend - lockstart + 1; ret = can_nocow_extent(&inode->vfs_inode, lockstart, &num_bytes, NULL, NULL, NULL); if (ret <= 0) { ret = 0; btrfs_end_write_no_snapshotting(root); } else { *write_bytes = min_t(size_t, *write_bytes , num_bytes - pos + lockstart); } unlock_extent(&inode->io_tree, lockstart, lockend); return ret; } static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb, struct iov_iter *i) { struct file *file = iocb->ki_filp; loff_t pos = iocb->ki_pos; struct inode *inode = file_inode(file); struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_root *root = BTRFS_I(inode)->root; struct page **pages = NULL; struct extent_changeset *data_reserved = NULL; u64 release_bytes = 0; u64 lockstart; u64 lockend; size_t num_written = 0; int nrptrs; int ret = 0; bool only_release_metadata = false; bool force_page_uptodate = false; nrptrs = min(DIV_ROUND_UP(iov_iter_count(i), PAGE_SIZE), PAGE_SIZE / (sizeof(struct page *))); nrptrs = min(nrptrs, current->nr_dirtied_pause - current->nr_dirtied); nrptrs = max(nrptrs, 8); pages = kmalloc_array(nrptrs, sizeof(struct page *), GFP_KERNEL); if (!pages) return -ENOMEM; while (iov_iter_count(i) > 0) { struct extent_state *cached_state = NULL; size_t offset = offset_in_page(pos); size_t sector_offset; size_t write_bytes = min(iov_iter_count(i), nrptrs * (size_t)PAGE_SIZE - offset); size_t num_pages = DIV_ROUND_UP(write_bytes + offset, PAGE_SIZE); size_t reserve_bytes; size_t dirty_pages; size_t copied; size_t dirty_sectors; size_t num_sectors; int extents_locked; WARN_ON(num_pages > nrptrs); /* * Fault pages before locking them in prepare_pages * to avoid recursive lock */ if (unlikely(iov_iter_fault_in_readable(i, write_bytes))) { ret = -EFAULT; break; } only_release_metadata = false; sector_offset = pos & (fs_info->sectorsize - 1); reserve_bytes = round_up(write_bytes + sector_offset, fs_info->sectorsize); extent_changeset_release(data_reserved); ret = btrfs_check_data_free_space(inode, &data_reserved, pos, write_bytes); if (ret < 0) { if ((BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW | BTRFS_INODE_PREALLOC)) && check_can_nocow(BTRFS_I(inode), pos, &write_bytes) > 0) { /* * For nodata cow case, no need to reserve * data space. */ only_release_metadata = true; /* * our prealloc extent may be smaller than * write_bytes, so scale down. */ num_pages = DIV_ROUND_UP(write_bytes + offset, PAGE_SIZE); reserve_bytes = round_up(write_bytes + sector_offset, fs_info->sectorsize); } else { break; } } WARN_ON(reserve_bytes == 0); ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode), reserve_bytes); if (ret) { if (!only_release_metadata) btrfs_free_reserved_data_space(inode, data_reserved, pos, write_bytes); else btrfs_end_write_no_snapshotting(root); break; } release_bytes = reserve_bytes; again: /* * This is going to setup the pages array with the number of * pages we want, so we don't really need to worry about the * contents of pages from loop to loop */ ret = prepare_pages(inode, pages, num_pages, pos, write_bytes, force_page_uptodate); if (ret) { btrfs_delalloc_release_extents(BTRFS_I(inode), reserve_bytes); break; } extents_locked = lock_and_cleanup_extent_if_need( BTRFS_I(inode), pages, num_pages, pos, write_bytes, &lockstart, &lockend, &cached_state); if (extents_locked < 0) { if (extents_locked == -EAGAIN) goto again; btrfs_delalloc_release_extents(BTRFS_I(inode), reserve_bytes); ret = extents_locked; break; } copied = btrfs_copy_from_user(pos, write_bytes, pages, i); num_sectors = BTRFS_BYTES_TO_BLKS(fs_info, reserve_bytes); dirty_sectors = round_up(copied + sector_offset, fs_info->sectorsize); dirty_sectors = BTRFS_BYTES_TO_BLKS(fs_info, dirty_sectors); /* * if we have trouble faulting in the pages, fall * back to one page at a time */ if (copied < write_bytes) nrptrs = 1; if (copied == 0) { force_page_uptodate = true; dirty_sectors = 0; dirty_pages = 0; } else { force_page_uptodate = false; dirty_pages = DIV_ROUND_UP(copied + offset, PAGE_SIZE); } if (num_sectors > dirty_sectors) { /* release everything except the sectors we dirtied */ release_bytes -= dirty_sectors << fs_info->sb->s_blocksize_bits; if (only_release_metadata) { btrfs_delalloc_release_metadata(BTRFS_I(inode), release_bytes, true); } else { u64 __pos; __pos = round_down(pos, fs_info->sectorsize) + (dirty_pages << PAGE_SHIFT); btrfs_delalloc_release_space(inode, data_reserved, __pos, release_bytes, true); } } release_bytes = round_up(copied + sector_offset, fs_info->sectorsize); if (copied > 0) ret = btrfs_dirty_pages(inode, pages, dirty_pages, pos, copied, &cached_state); /* * If we have not locked the extent range, because the range's * start offset is >= i_size, we might still have a non-NULL * cached extent state, acquired while marking the extent range * as delalloc through btrfs_dirty_pages(). Therefore free any * possible cached extent state to avoid a memory leak. */ if (extents_locked) unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend, &cached_state); else free_extent_state(cached_state); btrfs_delalloc_release_extents(BTRFS_I(inode), reserve_bytes); if (ret) { btrfs_drop_pages(pages, num_pages); break; } release_bytes = 0; if (only_release_metadata) btrfs_end_write_no_snapshotting(root); if (only_release_metadata && copied > 0) { lockstart = round_down(pos, fs_info->sectorsize); lockend = round_up(pos + copied, fs_info->sectorsize) - 1; set_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, lockend, EXTENT_NORESERVE, NULL, NULL, GFP_NOFS); } btrfs_drop_pages(pages, num_pages); cond_resched(); balance_dirty_pages_ratelimited(inode->i_mapping); if (dirty_pages < (fs_info->nodesize >> PAGE_SHIFT) + 1) btrfs_btree_balance_dirty(fs_info); pos += copied; num_written += copied; } kfree(pages); if (release_bytes) { if (only_release_metadata) { btrfs_end_write_no_snapshotting(root); btrfs_delalloc_release_metadata(BTRFS_I(inode), release_bytes, true); } else { btrfs_delalloc_release_space(inode, data_reserved, round_down(pos, fs_info->sectorsize), release_bytes, true); } } extent_changeset_free(data_reserved); return num_written ? num_written : ret; } static ssize_t __btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file); loff_t pos; ssize_t written; ssize_t written_buffered; loff_t endbyte; int err; written = generic_file_direct_write(iocb, from); if (written < 0 || !iov_iter_count(from)) return written; pos = iocb->ki_pos; written_buffered = btrfs_buffered_write(iocb, from); if (written_buffered < 0) { err = written_buffered; goto out; } /* * Ensure all data is persisted. We want the next direct IO read to be * able to read what was just written. */ endbyte = pos + written_buffered - 1; err = btrfs_fdatawrite_range(inode, pos, endbyte); if (err) goto out; err = filemap_fdatawait_range(inode->i_mapping, pos, endbyte); if (err) goto out; written += written_buffered; iocb->ki_pos = pos + written_buffered; invalidate_mapping_pages(file->f_mapping, pos >> PAGE_SHIFT, endbyte >> PAGE_SHIFT); out: return written ? written : err; } static void update_time_for_write(struct inode *inode) { struct timespec64 now; if (IS_NOCMTIME(inode)) return; now = current_time(inode); if (!timespec64_equal(&inode->i_mtime, &now)) inode->i_mtime = now; if (!timespec64_equal(&inode->i_ctime, &now)) inode->i_ctime = now; if (IS_I_VERSION(inode)) inode_inc_iversion(inode); } static ssize_t btrfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file); struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_root *root = BTRFS_I(inode)->root; u64 start_pos; u64 end_pos; ssize_t num_written = 0; const bool sync = iocb->ki_flags & IOCB_DSYNC; ssize_t err; loff_t pos; size_t count; loff_t oldsize; int clean_page = 0; if (!(iocb->ki_flags & IOCB_DIRECT) && (iocb->ki_flags & IOCB_NOWAIT)) return -EOPNOTSUPP; if (iocb->ki_flags & IOCB_NOWAIT) { if (!inode_trylock(inode)) return -EAGAIN; } else { inode_lock(inode); } err = generic_write_checks(iocb, from); if (err <= 0) { inode_unlock(inode); return err; } pos = iocb->ki_pos; count = iov_iter_count(from); if (iocb->ki_flags & IOCB_NOWAIT) { /* * We will allocate space in case nodatacow is not set, * so bail */ if (!(BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW | BTRFS_INODE_PREALLOC)) || check_can_nocow(BTRFS_I(inode), pos, &count) <= 0) { inode_unlock(inode); return -EAGAIN; } } current->backing_dev_info = inode_to_bdi(inode); err = file_remove_privs(file); if (err) { inode_unlock(inode); goto out; } /* * If BTRFS flips readonly due to some impossible error * (fs_info->fs_state now has BTRFS_SUPER_FLAG_ERROR), * although we have opened a file as writable, we have * to stop this write operation to ensure FS consistency. */ if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) { inode_unlock(inode); err = -EROFS; goto out; } /* * We reserve space for updating the inode when we reserve space for the * extent we are going to write, so we will enospc out there. We don't * need to start yet another transaction to update the inode as we will * update the inode when we finish writing whatever data we write. */ update_time_for_write(inode); start_pos = round_down(pos, fs_info->sectorsize); oldsize = i_size_read(inode); if (start_pos > oldsize) { /* Expand hole size to cover write data, preventing empty gap */ end_pos = round_up(pos + count, fs_info->sectorsize); err = btrfs_cont_expand(inode, oldsize, end_pos); if (err) { inode_unlock(inode); goto out; } if (start_pos > round_up(oldsize, fs_info->sectorsize)) clean_page = 1; } if (sync) atomic_inc(&BTRFS_I(inode)->sync_writers); if (iocb->ki_flags & IOCB_DIRECT) { num_written = __btrfs_direct_write(iocb, from); } else { num_written = btrfs_buffered_write(iocb, from); if (num_written > 0) iocb->ki_pos = pos + num_written; if (clean_page) pagecache_isize_extended(inode, oldsize, i_size_read(inode)); } inode_unlock(inode); /* * We also have to set last_sub_trans to the current log transid, * otherwise subsequent syncs to a file that's been synced in this * transaction will appear to have already occurred. */ spin_lock(&BTRFS_I(inode)->lock); BTRFS_I(inode)->last_sub_trans = root->log_transid; spin_unlock(&BTRFS_I(inode)->lock); if (num_written > 0) num_written = generic_write_sync(iocb, num_written); if (sync) atomic_dec(&BTRFS_I(inode)->sync_writers); out: current->backing_dev_info = NULL; return num_written ? num_written : err; } int btrfs_release_file(struct inode *inode, struct file *filp) { struct btrfs_file_private *private = filp->private_data; if (private && private->filldir_buf) kfree(private->filldir_buf); kfree(private); filp->private_data = NULL; /* * ordered_data_close is set by setattr when we are about to truncate * a file from a non-zero size to a zero size. This tries to * flush down new bytes that may have been written if the * application were using truncate to replace a file in place. */ if (test_and_clear_bit(BTRFS_INODE_ORDERED_DATA_CLOSE, &BTRFS_I(inode)->runtime_flags)) filemap_flush(inode->i_mapping); return 0; } static int start_ordered_ops(struct inode *inode, loff_t start, loff_t end) { int ret; struct blk_plug plug; /* * This is only called in fsync, which would do synchronous writes, so * a plug can merge adjacent IOs as much as possible. Esp. in case of * multiple disks using raid profile, a large IO can be split to * several segments of stripe length (currently 64K). */ blk_start_plug(&plug); atomic_inc(&BTRFS_I(inode)->sync_writers); ret = btrfs_fdatawrite_range(inode, start, end); atomic_dec(&BTRFS_I(inode)->sync_writers); blk_finish_plug(&plug); return ret; } /* * fsync call for both files and directories. This logs the inode into * the tree log instead of forcing full commits whenever possible. * * It needs to call filemap_fdatawait so that all ordered extent updates are * in the metadata btree are up to date for copying to the log. * * It drops the inode mutex before doing the tree log commit. This is an * important optimization for directories because holding the mutex prevents * new operations on the dir while we write to disk. */ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) { struct dentry *dentry = file_dentry(file); struct inode *inode = d_inode(dentry); struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_trans_handle *trans; struct btrfs_log_ctx ctx; int ret = 0, err; trace_btrfs_sync_file(file, datasync); btrfs_init_log_ctx(&ctx, inode); /* * We write the dirty pages in the range and wait until they complete * out of the ->i_mutex. If so, we can flush the dirty pages by * multi-task, and make the performance up. See * btrfs_wait_ordered_range for an explanation of the ASYNC check. */ ret = start_ordered_ops(inode, start, end); if (ret) goto out; inode_lock(inode); /* * We take the dio_sem here because the tree log stuff can race with * lockless dio writes and get an extent map logged for an extent we * never waited on. We need it this high up for lockdep reasons. */ down_write(&BTRFS_I(inode)->dio_sem); atomic_inc(&root->log_batch); /* * If the inode needs a full sync, make sure we use a full range to * avoid log tree corruption, due to hole detection racing with ordered * extent completion for adjacent ranges, and assertion failures during * hole detection. Do this while holding the inode lock, to avoid races * with other tasks. */ if (test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &BTRFS_I(inode)->runtime_flags)) { start = 0; end = LLONG_MAX; } /* * Before we acquired the inode's lock, someone may have dirtied more * pages in the target range. We need to make sure that writeback for * any such pages does not start while we are logging the inode, because * if it does, any of the following might happen when we are not doing a * full inode sync: * * 1) We log an extent after its writeback finishes but before its * checksums are added to the csum tree, leading to -EIO errors * when attempting to read the extent after a log replay. * * 2) We can end up logging an extent before its writeback finishes. * Therefore after the log replay we will have a file extent item * pointing to an unwritten extent (and no data checksums as well). * * So trigger writeback for any eventual new dirty pages and then we * wait for all ordered extents to complete below. */ ret = start_ordered_ops(inode, start, end); if (ret) { inode_unlock(inode); goto out; } /* * We have to do this here to avoid the priority inversion of waiting on * IO of a lower priority task while holding a transaction open. * * Also, the range length can be represented by u64, we have to do the * typecasts to avoid signed overflow if it's [0, LLONG_MAX]. */ ret = btrfs_wait_ordered_range(inode, start, (u64)end - (u64)start + 1); if (ret) { up_write(&BTRFS_I(inode)->dio_sem); inode_unlock(inode); goto out; } atomic_inc(&root->log_batch); smp_mb(); if (btrfs_inode_in_log(BTRFS_I(inode), fs_info->generation) || BTRFS_I(inode)->last_trans <= fs_info->last_trans_committed) { /* * We've had everything committed since the last time we were * modified so clear this flag in case it was set for whatever * reason, it's no longer relevant. */ clear_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &BTRFS_I(inode)->runtime_flags); /* * An ordered extent might have started before and completed * already with io errors, in which case the inode was not * updated and we end up here. So check the inode's mapping * for any errors that might have happened since we last * checked called fsync. */ ret = filemap_check_wb_err(inode->i_mapping, file->f_wb_err); up_write(&BTRFS_I(inode)->dio_sem); inode_unlock(inode); goto out; } /* * We use start here because we will need to wait on the IO to complete * in btrfs_sync_log, which could require joining a transaction (for * example checking cross references in the nocow path). If we use join * here we could get into a situation where we're waiting on IO to * happen that is blocked on a transaction trying to commit. With start * we inc the extwriter counter, so we wait for all extwriters to exit * before we start blocking joiners. This comment is to keep somebody * from thinking they are super smart and changing this to * btrfs_join_transaction *cough*Josef*cough*. */ trans = btrfs_start_transaction(root, 0); if (IS_ERR(trans)) { ret = PTR_ERR(trans); up_write(&BTRFS_I(inode)->dio_sem); inode_unlock(inode); goto out; } ret = btrfs_log_dentry_safe(trans, dentry, start, end, &ctx); if (ret < 0) { /* Fallthrough and commit/free transaction. */ ret = 1; } /* we've logged all the items and now have a consistent * version of the file in the log. It is possible that * someone will come in and modify the file, but that's * fine because the log is consistent on disk, and we * have references to all of the file's extents * * It is possible that someone will come in and log the * file again, but that will end up using the synchronization * inside btrfs_sync_log to keep things safe. */ up_write(&BTRFS_I(inode)->dio_sem); inode_unlock(inode); if (ret != BTRFS_NO_LOG_SYNC) { if (!ret) { ret = btrfs_sync_log(trans, root, &ctx); if (!ret) { ret = btrfs_end_transaction(trans); goto out; } } ret = btrfs_commit_transaction(trans); } else { ret = btrfs_end_transaction(trans); } out: ASSERT(list_empty(&ctx.list)); err = file_check_and_advance_wb_err(file); if (!ret) ret = err; return ret > 0 ? -EIO : ret; } static const struct vm_operations_struct btrfs_file_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = btrfs_page_mkwrite, }; static int btrfs_file_mmap(struct file *filp, struct vm_area_struct *vma) { struct address_space *mapping = filp->f_mapping; if (!mapping->a_ops->readpage) return -ENOEXEC; file_accessed(filp); vma->vm_ops = &btrfs_file_vm_ops; return 0; } static int hole_mergeable(struct btrfs_inode *inode, struct extent_buffer *leaf, int slot, u64 start, u64 end) { struct btrfs_file_extent_item *fi; struct btrfs_key key; if (slot < 0 || slot >= btrfs_header_nritems(leaf)) return 0; btrfs_item_key_to_cpu(leaf, &key, slot); if (key.objectid != btrfs_ino(inode) || key.type != BTRFS_EXTENT_DATA_KEY) return 0; fi = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item); if (btrfs_file_extent_type(leaf, fi) != BTRFS_FILE_EXTENT_REG) return 0; if (btrfs_file_extent_disk_bytenr(leaf, fi)) return 0; if (key.offset == end) return 1; if (key.offset + btrfs_file_extent_num_bytes(leaf, fi) == start) return 1; return 0; } static int fill_holes(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_path *path, u64 offset, u64 end) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_root *root = inode->root; struct extent_buffer *leaf; struct btrfs_file_extent_item *fi; struct extent_map *hole_em; struct extent_map_tree *em_tree = &inode->extent_tree; struct btrfs_key key; int ret; if (btrfs_fs_incompat(fs_info, NO_HOLES)) goto out; key.objectid = btrfs_ino(inode); key.type = BTRFS_EXTENT_DATA_KEY; key.offset = offset; ret = btrfs_search_slot(trans, root, &key, path, 0, 1); if (ret <= 0) { /* * We should have dropped this offset, so if we find it then * something has gone horribly wrong. */ if (ret == 0) ret = -EINVAL; return ret; } leaf = path->nodes[0]; if (hole_mergeable(inode, leaf, path->slots[0] - 1, offset, end)) { u64 num_bytes; path->slots[0]--; fi = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item); num_bytes = btrfs_file_extent_num_bytes(leaf, fi) + end - offset; btrfs_set_file_extent_num_bytes(leaf, fi, num_bytes); btrfs_set_file_extent_ram_bytes(leaf, fi, num_bytes); btrfs_set_file_extent_offset(leaf, fi, 0); btrfs_mark_buffer_dirty(leaf); goto out; } if (hole_mergeable(inode, leaf, path->slots[0], offset, end)) { u64 num_bytes; key.offset = offset; btrfs_set_item_key_safe(fs_info, path, &key); fi = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item); num_bytes = btrfs_file_extent_num_bytes(leaf, fi) + end - offset; btrfs_set_file_extent_num_bytes(leaf, fi, num_bytes); btrfs_set_file_extent_ram_bytes(leaf, fi, num_bytes); btrfs_set_file_extent_offset(leaf, fi, 0); btrfs_mark_buffer_dirty(leaf); goto out; } btrfs_release_path(path); ret = btrfs_insert_file_extent(trans, root, btrfs_ino(inode), offset, 0, 0, end - offset, 0, end - offset, 0, 0, 0); if (ret) return ret; out: btrfs_release_path(path); hole_em = alloc_extent_map(); if (!hole_em) { btrfs_drop_extent_cache(inode, offset, end - 1, 0); set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags); } else { hole_em->start = offset; hole_em->len = end - offset; hole_em->ram_bytes = hole_em->len; hole_em->orig_start = offset; hole_em->block_start = EXTENT_MAP_HOLE; hole_em->block_len = 0; hole_em->orig_block_len = 0; hole_em->compress_type = BTRFS_COMPRESS_NONE; hole_em->generation = trans->transid; do { btrfs_drop_extent_cache(inode, offset, end - 1, 0); write_lock(&em_tree->lock); ret = add_extent_mapping(em_tree, hole_em, 1); write_unlock(&em_tree->lock); } while (ret == -EEXIST); free_extent_map(hole_em); if (ret) set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags); } return 0; } /* * Find a hole extent on given inode and change start/len to the end of hole * extent.(hole/vacuum extent whose em->start <= start && * em->start + em->len > start) * When a hole extent is found, return 1 and modify start/len. */ static int find_first_non_hole(struct inode *inode, u64 *start, u64 *len) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct extent_map *em; int ret = 0; em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, round_down(*start, fs_info->sectorsize), round_up(*len, fs_info->sectorsize)); if (IS_ERR(em)) return PTR_ERR(em); /* Hole or vacuum extent(only exists in no-hole mode) */ if (em->block_start == EXTENT_MAP_HOLE) { ret = 1; *len = em->start + em->len > *start + *len ? 0 : *start + *len - em->start - em->len; *start = em->start + em->len; } free_extent_map(em); return ret; } static int btrfs_punch_hole_lock_range(struct inode *inode, const u64 lockstart, const u64 lockend, struct extent_state **cached_state) { while (1) { struct btrfs_ordered_extent *ordered; int ret; truncate_pagecache_range(inode, lockstart, lockend); lock_extent_bits(&BTRFS_I(inode)->io_tree, lockstart, lockend, cached_state); ordered = btrfs_lookup_first_ordered_extent(inode, lockend); /* * We need to make sure we have no ordered extents in this range * and nobody raced in and read a page in this range, if we did * we need to try again. */ if ((!ordered || (ordered->file_offset + ordered->num_bytes <= lockstart || ordered->file_offset > lockend)) && !filemap_range_has_page(inode->i_mapping, lockstart, lockend)) { if (ordered) btrfs_put_ordered_extent(ordered); break; } if (ordered) btrfs_put_ordered_extent(ordered); unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend, cached_state); ret = btrfs_wait_ordered_range(inode, lockstart, lockend - lockstart + 1); if (ret) return ret; } return 0; } static int btrfs_insert_clone_extent(struct btrfs_trans_handle *trans, struct inode *inode, struct btrfs_path *path, struct btrfs_clone_extent_info *clone_info, const u64 clone_len) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_file_extent_item *extent; struct extent_buffer *leaf; struct btrfs_key key; int slot; struct btrfs_ref ref = { 0 }; u64 ref_offset; int ret; if (clone_len == 0) return 0; if (clone_info->disk_offset == 0 && btrfs_fs_incompat(fs_info, NO_HOLES)) return 0; key.objectid = btrfs_ino(BTRFS_I(inode)); key.type = BTRFS_EXTENT_DATA_KEY; key.offset = clone_info->file_offset; ret = btrfs_insert_empty_item(trans, root, path, &key, clone_info->item_size); if (ret) return ret; leaf = path->nodes[0]; slot = path->slots[0]; write_extent_buffer(leaf, clone_info->extent_buf, btrfs_item_ptr_offset(leaf, slot), clone_info->item_size); extent = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item); btrfs_set_file_extent_offset(leaf, extent, clone_info->data_offset); btrfs_set_file_extent_num_bytes(leaf, extent, clone_len); btrfs_mark_buffer_dirty(leaf); btrfs_release_path(path); /* If it's a hole, nothing more needs to be done. */ if (clone_info->disk_offset == 0) return 0; inode_add_bytes(inode, clone_len); btrfs_init_generic_ref(&ref, BTRFS_ADD_DELAYED_REF, clone_info->disk_offset, clone_info->disk_len, 0); ref_offset = clone_info->file_offset - clone_info->data_offset; btrfs_init_data_ref(&ref, root->root_key.objectid, btrfs_ino(BTRFS_I(inode)), ref_offset); ret = btrfs_inc_extent_ref(trans, &ref); return ret; } /* * The respective range must have been previously locked, as well as the inode. * The end offset is inclusive (last byte of the range). * @clone_info is NULL for fallocate's hole punching and non-NULL for extent * cloning. * When cloning, we don't want to end up in a state where we dropped extents * without inserting a new one, so we must abort the transaction to avoid a * corruption. */ int btrfs_punch_hole_range(struct inode *inode, struct btrfs_path *path, const u64 start, const u64 end, struct btrfs_clone_extent_info *clone_info, struct btrfs_trans_handle **trans_out) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); u64 min_size = btrfs_calc_insert_metadata_size(fs_info, 1); u64 ino_size = round_up(inode->i_size, fs_info->sectorsize); struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_trans_handle *trans = NULL; struct btrfs_block_rsv *rsv; unsigned int rsv_count; u64 cur_offset; u64 drop_end; u64 len = end - start; int ret = 0; if (end <= start) return -EINVAL; rsv = btrfs_alloc_block_rsv(fs_info, BTRFS_BLOCK_RSV_TEMP); if (!rsv) { ret = -ENOMEM; goto out; } rsv->size = btrfs_calc_insert_metadata_size(fs_info, 1); rsv->failfast = 1; /* * 1 - update the inode * 1 - removing the extents in the range * 1 - adding the hole extent if no_holes isn't set or if we are cloning * an extent */ if (!btrfs_fs_incompat(fs_info, NO_HOLES) || clone_info) rsv_count = 3; else rsv_count = 2; trans = btrfs_start_transaction(root, rsv_count); if (IS_ERR(trans)) { ret = PTR_ERR(trans); trans = NULL; goto out_free; } ret = btrfs_block_rsv_migrate(&fs_info->trans_block_rsv, rsv, min_size, false); BUG_ON(ret); trans->block_rsv = rsv; cur_offset = start; while (cur_offset < end) { ret = __btrfs_drop_extents(trans, root, inode, path, cur_offset, end + 1, &drop_end, 1, 0, 0, NULL); if (ret != -ENOSPC) { /* * When cloning we want to avoid transaction aborts when * nothing was done and we are attempting to clone parts * of inline extents, in such cases -EOPNOTSUPP is * returned by __btrfs_drop_extents() without having * changed anything in the file. */ if (clone_info && ret && ret != -EOPNOTSUPP) btrfs_abort_transaction(trans, ret); break; } trans->block_rsv = &fs_info->trans_block_rsv; if (!clone_info && cur_offset < drop_end && cur_offset < ino_size) { ret = fill_holes(trans, BTRFS_I(inode), path, cur_offset, drop_end); if (ret) { /* * If we failed then we didn't insert our hole * entries for the area we dropped, so now the * fs is corrupted, so we must abort the * transaction. */ btrfs_abort_transaction(trans, ret); break; } } if (clone_info && drop_end > clone_info->file_offset) { u64 clone_len = drop_end - clone_info->file_offset; ret = btrfs_insert_clone_extent(trans, inode, path, clone_info, clone_len); if (ret) { btrfs_abort_transaction(trans, ret); break; } clone_info->data_len -= clone_len; clone_info->data_offset += clone_len; clone_info->file_offset += clone_len; } cur_offset = drop_end; ret = btrfs_update_inode(trans, root, inode); if (ret) break; btrfs_end_transaction(trans); btrfs_btree_balance_dirty(fs_info); trans = btrfs_start_transaction(root, rsv_count); if (IS_ERR(trans)) { ret = PTR_ERR(trans); trans = NULL; break; } ret = btrfs_block_rsv_migrate(&fs_info->trans_block_rsv, rsv, min_size, false); BUG_ON(ret); /* shouldn't happen */ trans->block_rsv = rsv; if (!clone_info) { ret = find_first_non_hole(inode, &cur_offset, &len); if (unlikely(ret < 0)) break; if (ret && !len) { ret = 0; break; } } } /* * If we were cloning, force the next fsync to be a full one since we * we replaced (or just dropped in the case of cloning holes when * NO_HOLES is enabled) extents and extent maps. * This is for the sake of simplicity, and cloning into files larger * than 16Mb would force the full fsync any way (when * try_release_extent_mapping() is invoked during page cache truncation. */ if (clone_info) set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &BTRFS_I(inode)->runtime_flags); if (ret) goto out_trans; trans->block_rsv = &fs_info->trans_block_rsv; /* * If we are using the NO_HOLES feature we might have had already an * hole that overlaps a part of the region [lockstart, lockend] and * ends at (or beyond) lockend. Since we have no file extent items to * represent holes, drop_end can be less than lockend and so we must * make sure we have an extent map representing the existing hole (the * call to __btrfs_drop_extents() might have dropped the existing extent * map representing the existing hole), otherwise the fast fsync path * will not record the existence of the hole region * [existing_hole_start, lockend]. */ if (drop_end <= end) drop_end = end + 1; /* * Don't insert file hole extent item if it's for a range beyond eof * (because it's useless) or if it represents a 0 bytes range (when * cur_offset == drop_end). */ if (!clone_info && cur_offset < ino_size && cur_offset < drop_end) { ret = fill_holes(trans, BTRFS_I(inode), path, cur_offset, drop_end); if (ret) { /* Same comment as above. */ btrfs_abort_transaction(trans, ret); goto out_trans; } } if (clone_info) { ret = btrfs_insert_clone_extent(trans, inode, path, clone_info, clone_info->data_len); if (ret) { btrfs_abort_transaction(trans, ret); goto out_trans; } } out_trans: if (!trans) goto out_free; trans->block_rsv = &fs_info->trans_block_rsv; if (ret) btrfs_end_transaction(trans); else *trans_out = trans; out_free: btrfs_free_block_rsv(fs_info, rsv); out: return ret; } static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_root *root = BTRFS_I(inode)->root; struct extent_state *cached_state = NULL; struct btrfs_path *path; struct btrfs_trans_handle *trans = NULL; u64 lockstart; u64 lockend; u64 tail_start; u64 tail_len; u64 orig_start = offset; int ret = 0; bool same_block; u64 ino_size; bool truncated_block = false; bool updated_inode = false; ret = btrfs_wait_ordered_range(inode, offset, len); if (ret) return ret; inode_lock(inode); ino_size = round_up(inode->i_size, fs_info->sectorsize); ret = find_first_non_hole(inode, &offset, &len); if (ret < 0) goto out_only_mutex; if (ret && !len) { /* Already in a large hole */ ret = 0; goto out_only_mutex; } lockstart = round_up(offset, btrfs_inode_sectorsize(inode)); lockend = round_down(offset + len, btrfs_inode_sectorsize(inode)) - 1; same_block = (BTRFS_BYTES_TO_BLKS(fs_info, offset)) == (BTRFS_BYTES_TO_BLKS(fs_info, offset + len - 1)); /* * We needn't truncate any block which is beyond the end of the file * because we are sure there is no data there. */ /* * Only do this if we are in the same block and we aren't doing the * entire block. */ if (same_block && len < fs_info->sectorsize) { if (offset < ino_size) { truncated_block = true; ret = btrfs_truncate_block(inode, offset, len, 0); } else { ret = 0; } goto out_only_mutex; } /* zero back part of the first block */ if (offset < ino_size) { truncated_block = true; ret = btrfs_truncate_block(inode, offset, 0, 0); if (ret) { inode_unlock(inode); return ret; } } /* Check the aligned pages after the first unaligned page, * if offset != orig_start, which means the first unaligned page * including several following pages are already in holes, * the extra check can be skipped */ if (offset == orig_start) { /* after truncate page, check hole again */ len = offset + len - lockstart; offset = lockstart; ret = find_first_non_hole(inode, &offset, &len); if (ret < 0) goto out_only_mutex; if (ret && !len) { ret = 0; goto out_only_mutex; } lockstart = offset; } /* Check the tail unaligned part is in a hole */ tail_start = lockend + 1; tail_len = offset + len - tail_start; if (tail_len) { ret = find_first_non_hole(inode, &tail_start, &tail_len); if (unlikely(ret < 0)) goto out_only_mutex; if (!ret) { /* zero the front end of the last page */ if (tail_start + tail_len < ino_size) { truncated_block = true; ret = btrfs_truncate_block(inode, tail_start + tail_len, 0, 1); if (ret) goto out_only_mutex; } } } if (lockend < lockstart) { ret = 0; goto out_only_mutex; } ret = btrfs_punch_hole_lock_range(inode, lockstart, lockend, &cached_state); if (ret) goto out_only_mutex; path = btrfs_alloc_path(); if (!path) { ret = -ENOMEM; goto out; } ret = btrfs_punch_hole_range(inode, path, lockstart, lockend, NULL, &trans); btrfs_free_path(path); if (ret) goto out; ASSERT(trans != NULL); inode_inc_iversion(inode); inode->i_mtime = inode->i_ctime = current_time(inode); ret = btrfs_update_inode(trans, root, inode); updated_inode = true; btrfs_end_transaction(trans); btrfs_btree_balance_dirty(fs_info); out: unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend, &cached_state); out_only_mutex: if (!updated_inode && truncated_block && !ret) { /* * If we only end up zeroing part of a page, we still need to * update the inode item, so that all the time fields are * updated as well as the necessary btrfs inode in memory fields * for detecting, at fsync time, if the inode isn't yet in the * log tree or it's there but not up to date. */ struct timespec64 now = current_time(inode); inode_inc_iversion(inode); inode->i_mtime = now; inode->i_ctime = now; trans = btrfs_start_transaction(root, 1); if (IS_ERR(trans)) { ret = PTR_ERR(trans); } else { int ret2; ret = btrfs_update_inode(trans, root, inode); ret2 = btrfs_end_transaction(trans); if (!ret) ret = ret2; } } inode_unlock(inode); return ret; } /* Helper structure to record which range is already reserved */ struct falloc_range { struct list_head list; u64 start; u64 len; }; /* * Helper function to add falloc range * * Caller should have locked the larger range of extent containing * [start, len) */ static int add_falloc_range(struct list_head *head, u64 start, u64 len) { struct falloc_range *prev = NULL; struct falloc_range *range = NULL; if (list_empty(head)) goto insert; /* * As fallocate iterate by bytenr order, we only need to check * the last range. */ prev = list_entry(head->prev, struct falloc_range, list); if (prev->start + prev->len == start) { prev->len += len; return 0; } insert: range = kmalloc(sizeof(*range), GFP_KERNEL); if (!range) return -ENOMEM; range->start = start; range->len = len; list_add_tail(&range->list, head); return 0; } static int btrfs_fallocate_update_isize(struct inode *inode, const u64 end, const int mode) { struct btrfs_trans_handle *trans; struct btrfs_root *root = BTRFS_I(inode)->root; int ret; int ret2; if (mode & FALLOC_FL_KEEP_SIZE || end <= i_size_read(inode)) return 0; trans = btrfs_start_transaction(root, 1); if (IS_ERR(trans)) return PTR_ERR(trans); inode->i_ctime = current_time(inode); i_size_write(inode, end); btrfs_ordered_update_i_size(inode, end, NULL); ret = btrfs_update_inode(trans, root, inode); ret2 = btrfs_end_transaction(trans); return ret ? ret : ret2; } enum { RANGE_BOUNDARY_WRITTEN_EXTENT, RANGE_BOUNDARY_PREALLOC_EXTENT, RANGE_BOUNDARY_HOLE, }; static int btrfs_zero_range_check_range_boundary(struct inode *inode, u64 offset) { const u64 sectorsize = btrfs_inode_sectorsize(inode); struct extent_map *em; int ret; offset = round_down(offset, sectorsize); em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize); if (IS_ERR(em)) return PTR_ERR(em); if (em->block_start == EXTENT_MAP_HOLE) ret = RANGE_BOUNDARY_HOLE; else if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) ret = RANGE_BOUNDARY_PREALLOC_EXTENT; else ret = RANGE_BOUNDARY_WRITTEN_EXTENT; free_extent_map(em); return ret; } static int btrfs_zero_range(struct inode *inode, loff_t offset, loff_t len, const int mode) { struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info; struct extent_map *em; struct extent_changeset *data_reserved = NULL; int ret; u64 alloc_hint = 0; const u64 sectorsize = btrfs_inode_sectorsize(inode); u64 alloc_start = round_down(offset, sectorsize); u64 alloc_end = round_up(offset + len, sectorsize); u64 bytes_to_reserve = 0; bool space_reserved = false; inode_dio_wait(inode); em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, alloc_start, alloc_end - alloc_start); if (IS_ERR(em)) { ret = PTR_ERR(em); goto out; } /* * Avoid hole punching and extent allocation for some cases. More cases * could be considered, but these are unlikely common and we keep things * as simple as possible for now. Also, intentionally, if the target * range contains one or more prealloc extents together with regular * extents and holes, we drop all the existing extents and allocate a * new prealloc extent, so that we get a larger contiguous disk extent. */ if (em->start <= alloc_start && test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) { const u64 em_end = em->start + em->len; if (em_end >= offset + len) { /* * The whole range is already a prealloc extent, * do nothing except updating the inode's i_size if * needed. */ free_extent_map(em); ret = btrfs_fallocate_update_isize(inode, offset + len, mode); goto out; } /* * Part of the range is already a prealloc extent, so operate * only on the remaining part of the range. */ alloc_start = em_end; ASSERT(IS_ALIGNED(alloc_start, sectorsize)); len = offset + len - alloc_start; offset = alloc_start; alloc_hint = em->block_start + em->len; } free_extent_map(em); if (BTRFS_BYTES_TO_BLKS(fs_info, offset) == BTRFS_BYTES_TO_BLKS(fs_info, offset + len - 1)) { em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, alloc_start, sectorsize); if (IS_ERR(em)) { ret = PTR_ERR(em); goto out; } if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) { free_extent_map(em); ret = btrfs_fallocate_update_isize(inode, offset + len, mode); goto out; } if (len < sectorsize && em->block_start != EXTENT_MAP_HOLE) { free_extent_map(em); ret = btrfs_truncate_block(inode, offset, len, 0); if (!ret) ret = btrfs_fallocate_update_isize(inode, offset + len, mode); return ret; } free_extent_map(em); alloc_start = round_down(offset, sectorsize); alloc_end = alloc_start + sectorsize; goto reserve_space; } alloc_start = round_up(offset, sectorsize); alloc_end = round_down(offset + len, sectorsize); /* * For unaligned ranges, check the pages at the boundaries, they might * map to an extent, in which case we need to partially zero them, or * they might map to a hole, in which case we need our allocation range * to cover them. */ if (!IS_ALIGNED(offset, sectorsize)) { ret = btrfs_zero_range_check_range_boundary(inode, offset); if (ret < 0) goto out; if (ret == RANGE_BOUNDARY_HOLE) { alloc_start = round_down(offset, sectorsize); ret = 0; } else if (ret == RANGE_BOUNDARY_WRITTEN_EXTENT) { ret = btrfs_truncate_block(inode, offset, 0, 0); if (ret) goto out; } else { ret = 0; } } if (!IS_ALIGNED(offset + len, sectorsize)) { ret = btrfs_zero_range_check_range_boundary(inode, offset + len); if (ret < 0) goto out; if (ret == RANGE_BOUNDARY_HOLE) { alloc_end = round_up(offset + len, sectorsize); ret = 0; } else if (ret == RANGE_BOUNDARY_WRITTEN_EXTENT) { ret = btrfs_truncate_block(inode, offset + len, 0, 1); if (ret) goto out; } else { ret = 0; } } reserve_space: if (alloc_start < alloc_end) { struct extent_state *cached_state = NULL; const u64 lockstart = alloc_start; const u64 lockend = alloc_end - 1; bytes_to_reserve = alloc_end - alloc_start; ret = btrfs_alloc_data_chunk_ondemand(BTRFS_I(inode), bytes_to_reserve); if (ret < 0) goto out; space_reserved = true; ret = btrfs_qgroup_reserve_data(inode, &data_reserved, alloc_start, bytes_to_reserve); if (ret) goto out; ret = btrfs_punch_hole_lock_range(inode, lockstart, lockend, &cached_state); if (ret) goto out; ret = btrfs_prealloc_file_range(inode, mode, alloc_start, alloc_end - alloc_start, i_blocksize(inode), offset + len, &alloc_hint); unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend, &cached_state); /* btrfs_prealloc_file_range releases reserved space on error */ if (ret) { space_reserved = false; goto out; } } ret = btrfs_fallocate_update_isize(inode, offset + len, mode); out: if (ret && space_reserved) btrfs_free_reserved_data_space(inode, data_reserved, alloc_start, bytes_to_reserve); extent_changeset_free(data_reserved); return ret; } static long btrfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len) { struct inode *inode = file_inode(file); struct extent_state *cached_state = NULL; struct extent_changeset *data_reserved = NULL; struct falloc_range *range; struct falloc_range *tmp; struct list_head reserve_list; u64 cur_offset; u64 last_byte; u64 alloc_start; u64 alloc_end; u64 alloc_hint = 0; u64 locked_end; u64 actual_end = 0; struct extent_map *em; int blocksize = btrfs_inode_sectorsize(inode); int ret; alloc_start = round_down(offset, blocksize); alloc_end = round_up(offset + len, blocksize); cur_offset = alloc_start; /* Make sure we aren't being give some crap mode */ if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE)) return -EOPNOTSUPP; if (mode & FALLOC_FL_PUNCH_HOLE) return btrfs_punch_hole(inode, offset, len); /* * Only trigger disk allocation, don't trigger qgroup reserve * * For qgroup space, it will be checked later. */ if (!(mode & FALLOC_FL_ZERO_RANGE)) { ret = btrfs_alloc_data_chunk_ondemand(BTRFS_I(inode), alloc_end - alloc_start); if (ret < 0) return ret; } inode_lock(inode); if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + len > inode->i_size) { ret = inode_newsize_ok(inode, offset + len); if (ret) goto out; } /* * TODO: Move these two operations after we have checked * accurate reserved space, or fallocate can still fail but * with page truncated or size expanded. * * But that's a minor problem and won't do much harm BTW. */ if (alloc_start > inode->i_size) { ret = btrfs_cont_expand(inode, i_size_read(inode), alloc_start); if (ret) goto out; } else if (offset + len > inode->i_size) { /* * If we are fallocating from the end of the file onward we * need to zero out the end of the block if i_size lands in the * middle of a block. */ ret = btrfs_truncate_block(inode, inode->i_size, 0, 0); if (ret) goto out; } /* * wait for ordered IO before we have any locks. We'll loop again * below with the locks held. */ ret = btrfs_wait_ordered_range(inode, alloc_start, alloc_end - alloc_start); if (ret) goto out; if (mode & FALLOC_FL_ZERO_RANGE) { ret = btrfs_zero_range(inode, offset, len, mode); inode_unlock(inode); return ret; } locked_end = alloc_end - 1; while (1) { struct btrfs_ordered_extent *ordered; /* the extent lock is ordered inside the running * transaction */ lock_extent_bits(&BTRFS_I(inode)->io_tree, alloc_start, locked_end, &cached_state); ordered = btrfs_lookup_first_ordered_extent(inode, locked_end); if (ordered && ordered->file_offset + ordered->num_bytes > alloc_start && ordered->file_offset < alloc_end) { btrfs_put_ordered_extent(ordered); unlock_extent_cached(&BTRFS_I(inode)->io_tree, alloc_start, locked_end, &cached_state); /* * we can't wait on the range with the transaction * running or with the extent lock held */ ret = btrfs_wait_ordered_range(inode, alloc_start, alloc_end - alloc_start); if (ret) goto out; } else { if (ordered) btrfs_put_ordered_extent(ordered); break; } } /* First, check if we exceed the qgroup limit */ INIT_LIST_HEAD(&reserve_list); while (cur_offset < alloc_end) { em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, cur_offset, alloc_end - cur_offset); if (IS_ERR(em)) { ret = PTR_ERR(em); break; } last_byte = min(extent_map_end(em), alloc_end); actual_end = min_t(u64, extent_map_end(em), offset + len); last_byte = ALIGN(last_byte, blocksize); if (em->block_start == EXTENT_MAP_HOLE || (cur_offset >= inode->i_size && !test_bit(EXTENT_FLAG_PREALLOC, &em->flags))) { ret = add_falloc_range(&reserve_list, cur_offset, last_byte - cur_offset); if (ret < 0) { free_extent_map(em); break; } ret = btrfs_qgroup_reserve_data(inode, &data_reserved, cur_offset, last_byte - cur_offset); if (ret < 0) { cur_offset = last_byte; free_extent_map(em); break; } } else { /* * Do not need to reserve unwritten extent for this * range, free reserved data space first, otherwise * it'll result in false ENOSPC error. */ btrfs_free_reserved_data_space(inode, data_reserved, cur_offset, last_byte - cur_offset); } free_extent_map(em); cur_offset = last_byte; } /* * If ret is still 0, means we're OK to fallocate. * Or just cleanup the list and exit. */ list_for_each_entry_safe(range, tmp, &reserve_list, list) { if (!ret) ret = btrfs_prealloc_file_range(inode, mode, range->start, range->len, i_blocksize(inode), offset + len, &alloc_hint); else btrfs_free_reserved_data_space(inode, data_reserved, range->start, range->len); list_del(&range->list); kfree(range); } if (ret < 0) goto out_unlock; /* * We didn't need to allocate any more space, but we still extended the * size of the file so we need to update i_size and the inode item. */ ret = btrfs_fallocate_update_isize(inode, actual_end, mode); out_unlock: unlock_extent_cached(&BTRFS_I(inode)->io_tree, alloc_start, locked_end, &cached_state); out: inode_unlock(inode); /* Let go of our reservation. */ if (ret != 0 && !(mode & FALLOC_FL_ZERO_RANGE)) btrfs_free_reserved_data_space(inode, data_reserved, cur_offset, alloc_end - cur_offset); extent_changeset_free(data_reserved); return ret; } static loff_t find_desired_extent(struct inode *inode, loff_t offset, int whence) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct extent_map *em = NULL; struct extent_state *cached_state = NULL; loff_t i_size = inode->i_size; u64 lockstart; u64 lockend; u64 start; u64 len; int ret = 0; if (i_size == 0 || offset >= i_size) return -ENXIO; /* * offset can be negative, in this case we start finding DATA/HOLE from * the very start of the file. */ start = max_t(loff_t, 0, offset); lockstart = round_down(start, fs_info->sectorsize); lockend = round_up(i_size, fs_info->sectorsize); if (lockend <= lockstart) lockend = lockstart + fs_info->sectorsize; lockend--; len = lockend - lockstart + 1; lock_extent_bits(&BTRFS_I(inode)->io_tree, lockstart, lockend, &cached_state); while (start < i_size) { em = btrfs_get_extent_fiemap(BTRFS_I(inode), start, len); if (IS_ERR(em)) { ret = PTR_ERR(em); em = NULL; break; } if (whence == SEEK_HOLE && (em->block_start == EXTENT_MAP_HOLE || test_bit(EXTENT_FLAG_PREALLOC, &em->flags))) break; else if (whence == SEEK_DATA && (em->block_start != EXTENT_MAP_HOLE && !test_bit(EXTENT_FLAG_PREALLOC, &em->flags))) break; start = em->start + em->len; free_extent_map(em); em = NULL; cond_resched(); } free_extent_map(em); unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend, &cached_state); if (ret) { offset = ret; } else { if (whence == SEEK_DATA && start >= i_size) offset = -ENXIO; else offset = min_t(loff_t, start, i_size); } return offset; } static loff_t btrfs_file_llseek(struct file *file, loff_t offset, int whence) { struct inode *inode = file->f_mapping->host; switch (whence) { default: return generic_file_llseek(file, offset, whence); case SEEK_DATA: case SEEK_HOLE: inode_lock_shared(inode); offset = find_desired_extent(inode, offset, whence); inode_unlock_shared(inode); break; } if (offset < 0) return offset; return vfs_setpos(file, offset, inode->i_sb->s_maxbytes); } static int btrfs_file_open(struct inode *inode, struct file *filp) { filp->f_mode |= FMODE_NOWAIT; return generic_file_open(inode, filp); } const struct file_operations btrfs_file_operations = { .llseek = btrfs_file_llseek, .read_iter = generic_file_read_iter, .splice_read = generic_file_splice_read, .write_iter = btrfs_file_write_iter, .mmap = btrfs_file_mmap, .open = btrfs_file_open, .release = btrfs_release_file, .fsync = btrfs_sync_file, .fallocate = btrfs_fallocate, .unlocked_ioctl = btrfs_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = btrfs_compat_ioctl, #endif .remap_file_range = btrfs_remap_file_range, }; void __cold btrfs_auto_defrag_exit(void) { kmem_cache_destroy(btrfs_inode_defrag_cachep); } int __init btrfs_auto_defrag_init(void) { btrfs_inode_defrag_cachep = kmem_cache_create("btrfs_inode_defrag", sizeof(struct inode_defrag), 0, SLAB_MEM_SPREAD, NULL); if (!btrfs_inode_defrag_cachep) return -ENOMEM; return 0; } int btrfs_fdatawrite_range(struct inode *inode, loff_t start, loff_t end) { int ret; /* * So with compression we will find and lock a dirty page and clear the * first one as dirty, setup an async extent, and immediately return * with the entire range locked but with nobody actually marked with * writeback. So we can't just filemap_write_and_wait_range() and * expect it to work since it will just kick off a thread to do the * actual work. So we need to call filemap_fdatawrite_range _again_ * since it will wait on the page lock, which won't be unlocked until * after the pages have been marked as writeback and so we're good to go * from there. We have to do this otherwise we'll miss the ordered * extents and that results in badness. Please Josef, do not think you * know better and pull this out at some point in the future, it is * right and you are wrong. */ ret = filemap_fdatawrite_range(inode->i_mapping, start, end); if (!ret && test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT, &BTRFS_I(inode)->runtime_flags)) ret = filemap_fdatawrite_range(inode->i_mapping, start, end); return ret; }
Information contained on this website is for historical information purposes only and does not indicate or represent copyright ownership.
Created with Cregit http://github.com/cregit/cregit
Version 2.0-RC1