1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859606162636465666768697071727374757677787980818283848586878889909192939495969798991001011021031041051061071081091101111121131141151161171181191201211221231241251261271281291301311321331341351361371381391401411421431441451461471481491501511521531541551561571581591601611621631641651661671681691701711721731741751761771781791801811821831841851861871881891901911921931941951961971981992002012022032042052062072082092102112122132142152162172182192202212222232242252262272282292302312322332342352362372382392402412422432442452462472482492502512522532542552562572582592602612622632642652662672682692702712722732742752762772782792802812822832842852862872882892902912922932942952962972982993003013023033043053063073083093103113123133143153163173183193203213223233243253263273283293303313323333343353363373383393403413423433443453463473483493503513523533543553563573583593603613623633643653663673683693703713723733743753763773783793803813823833843853863873883893903913923933943953963973983994004014024034044054064074084094104114124134144154164174184194204214224234244254264274284294304314324334344354364374384394404414424434444454464474484494504514524534544554564574584594604614624634644654664674684694704714724734744754764774784794804814824834844854864874884894904914924934944954964974984995005015025035045055065075085095105115125135145155165175185195205215225235245255265275285295305315325335345355365375385395405415425435445455465475485495505515525535545555565575585595605615625635645655665675685695705715725735745755765775785795805815825835845855865875885895905915925935945955965975985996006016026036046056066076086096106116126136146156166176186196206216226236246256266276286296306316326336346356366376386396406416426436446456466476486496506516526536546556566576586596606616626636646656666676686696706716726736746756766776786796806816826836846856866876886896906916926936946956966976986997007017027037047057067077087097107117127137147157167177187197207217227237247257267277287297307317327337347357367377387397407417427437447457467477487497507517527537547557567577587597607617627637647657667677687697707717727737747757767777787797807817827837847857867877887897907917927937947957967977987998008018028038048058068078088098108118128138148158168178188198208218228238248258268278288298308318328338348358368378388398408418428438448458468478488498508518528538548558568578588598608618628638648658668678688698708718728738748758768778788798808818828838848858868878888898908918928938948958968978988999009019029039049059069079089099109119129139149159169179189199209219229239249259269279289299309319329339349359369379389399409419429439449459469479489499509519529539549559569579589599609619629639649659669679689699709719729739749759769779789799809819829839849859869879889899909919929939949959969979989991000100110021003100410051006100710081009101010111012101310141015101610171018101910201021102210231024102510261027102810291030103110321033103410351036103710381039104010411042104310441045104610471048104910501051105210531054105510561057105810591060106110621063106410651066106710681069107010711072107310741075107610771078107910801081108210831084108510861087108810891090109110921093109410951096109710981099110011011102110311041105110611071108110911101111111211131114111511161117111811191120112111221123112411251126112711281129113011311132113311341135113611371138113911401141114211431144114511461147114811491150115111521153115411551156115711581159116011611162116311641165116611671168116911701171117211731174117511761177117811791180118111821183118411851186118711881189119011911192119311941195119611971198119912001201120212031204120512061207120812091210121112121213121412151216121712181219122012211222122312241225122612271228122912301231123212331234123512361237123812391240124112421243124412451246124712481249125012511252125312541255125612571258125912601261126212631264126512661267126812691270127112721273127412751276127712781279128012811282128312841285128612871288128912901291129212931294129512961297129812991300130113021303130413051306130713081309131013111312131313141315131613171318131913201321132213231324132513261327132813291330133113321333133413351336133713381339134013411342134313441345134613471348134913501351135213531354135513561357135813591360136113621363136413651366136713681369137013711372137313741375137613771378137913801381138213831384138513861387138813891390139113921393139413951396139713981399140014011402140314041405140614071408140914101411141214131414141514161417141814191420142114221423142414251426142714281429143014311432143314341435143614371438143914401441144214431444144514461447144814491450145114521453145414551456145714581459146014611462146314641465146614671468146914701471147214731474147514761477147814791480148114821483148414851486148714881489149014911492149314941495149614971498149915001501150215031504150515061507150815091510151115121513151415151516151715181519152015211522152315241525152615271528152915301531153215331534153515361537153815391540154115421543154415451546154715481549155015511552155315541555155615571558155915601561156215631564156515661567156815691570157115721573157415751576157715781579158015811582158315841585158615871588158915901591159215931594159515961597159815991600160116021603160416051606160716081609161016111612161316141615161616171618161916201621162216231624162516261627162816291630163116321633163416351636163716381639164016411642164316441645164616471648164916501651165216531654165516561657165816591660166116621663166416651666166716681669167016711672167316741675167616771678167916801681168216831684168516861687168816891690169116921693169416951696169716981699170017011702170317041705170617071708170917101711171217131714171517161717171817191720172117221723172417251726172717281729173017311732173317341735173617371738173917401741174217431744174517461747174817491750175117521753175417551756175717581759176017611762176317641765176617671768176917701771177217731774177517761777177817791780178117821783178417851786178717881789179017911792179317941795179617971798179918001801180218031804180518061807180818091810181118121813181418151816181718181819182018211822182318241825182618271828182918301831183218331834183518361837183818391840184118421843184418451846184718481849185018511852185318541855185618571858185918601861186218631864186518661867186818691870187118721873187418751876187718781879188018811882188318841885188618871888188918901891189218931894189518961897189818991900190119021903190419051906190719081909191019111912191319141915191619171918191919201921192219231924192519261927192819291930193119321933193419351936193719381939194019411942194319441945194619471948194919501951195219531954195519561957195819591960196119621963196419651966196719681969197019711972197319741975197619771978197919801981198219831984198519861987198819891990199119921993199419951996199719981999200020012002200320042005200620072008200920102011201220132014201520162017201820192020202120222023202420252026202720282029203020312032203320342035203620372038203920402041204220432044204520462047204820492050205120522053205420552056205720582059206020612062206320642065206620672068206920702071207220732074207520762077207820792080208120822083208420852086208720882089209020912092209320942095209620972098209921002101210221032104210521062107210821092110211121122113211421152116211721182119212021212122212321242125212621272128212921302131213221332134213521362137213821392140214121422143214421452146214721482149215021512152215321542155215621572158215921602161216221632164216521662167216821692170217121722173217421752176217721782179218021812182218321842185218621872188218921902191219221932194219521962197219821992200220122022203220422052206220722082209221022112212221322142215221622172218221922202221222222232224222522262227222822292230223122322233223422352236223722382239224022412242224322442245224622472248224922502251225222532254225522562257225822592260226122622263226422652266226722682269227022712272227322742275227622772278227922802281228222832284228522862287228822892290229122922293229422952296229722982299230023012302230323042305230623072308230923102311231223132314231523162317231823192320232123222323232423252326232723282329233023312332233323342335233623372338233923402341234223432344234523462347234823492350235123522353235423552356235723582359236023612362236323642365236623672368236923702371237223732374237523762377237823792380238123822383238423852386238723882389239023912392239323942395239623972398239924002401240224032404240524062407240824092410241124122413241424152416241724182419242024212422242324242425242624272428242924302431243224332434243524362437243824392440244124422443244424452446244724482449245024512452245324542455245624572458245924602461246224632464246524662467246824692470247124722473247424752476247724782479248024812482248324842485248624872488248924902491249224932494249524962497249824992500250125022503250425052506250725082509251025112512251325142515251625172518251925202521252225232524252525262527252825292530253125322533253425352536253725382539254025412542254325442545254625472548254925502551255225532554255525562557255825592560256125622563256425652566256725682569257025712572257325742575257625772578257925802581258225832584258525862587258825892590259125922593259425952596259725982599260026012602260326042605260626072608260926102611261226132614261526162617261826192620262126222623262426252626262726282629263026312632263326342635263626372638263926402641264226432644264526462647264826492650265126522653265426552656265726582659266026612662266326642665266626672668266926702671267226732674267526762677267826792680268126822683268426852686268726882689269026912692269326942695269626972698269927002701270227032704270527062707270827092710271127122713271427152716271727182719272027212722272327242725272627272728272927302731273227332734273527362737273827392740274127422743274427452746274727482749275027512752275327542755275627572758275927602761276227632764276527662767276827692770277127722773277427752776277727782779278027812782278327842785278627872788278927902791279227932794279527962797279827992800280128022803280428052806280728082809281028112812281328142815281628172818281928202821282228232824282528262827282828292830283128322833283428352836283728382839284028412842284328442845284628472848284928502851285228532854285528562857285828592860286128622863286428652866286728682869287028712872287328742875287628772878287928802881288228832884288528862887288828892890289128922893289428952896289728982899290029012902290329042905290629072908290929102911291229132914291529162917291829192920292129222923292429252926292729282929293029312932293329342935293629372938293929402941294229432944294529462947294829492950295129522953295429552956295729582959296029612962296329642965296629672968296929702971297229732974297529762977297829792980298129822983298429852986298729882989299029912992299329942995299629972998299930003001300230033004300530063007300830093010301130123013301430153016301730183019302030213022302330243025302630273028302930303031303230333034303530363037303830393040304130423043304430453046304730483049305030513052305330543055305630573058305930603061306230633064306530663067306830693070307130723073307430753076307730783079308030813082308330843085308630873088308930903091309230933094309530963097309830993100310131023103310431053106310731083109311031113112311331143115311631173118311931203121312231233124312531263127312831293130313131323133313431353136313731383139314031413142314331443145314631473148314931503151315231533154315531563157315831593160316131623163316431653166316731683169317031713172317331743175317631773178317931803181318231833184318531863187318831893190319131923193319431953196319731983199320032013202320332043205320632073208320932103211321232133214321532163217321832193220322132223223322432253226322732283229323032313232323332343235323632373238323932403241324232433244324532463247324832493250325132523253325432553256325732583259326032613262326332643265326632673268326932703271327232733274327532763277327832793280328132823283328432853286328732883289329032913292329332943295329632973298329933003301330233033304330533063307330833093310331133123313 |
- /*
- * fs/dcache.c
- *
- * Complete reimplementation
- * (C) 1997 Thomas Schoebel-Theuer,
- * with heavy changes by Linus Torvalds
- */
- /*
- * Notes on the allocation strategy:
- *
- * The dcache is a master of the icache - whenever a dcache entry
- * exists, the inode will always exist. "iput()" is done either when
- * the dcache entry is deleted or garbage collected.
- */
- #include <linux/syscalls.h>
- #include <linux/string.h>
- #include <linux/mm.h>
- #include <linux/fs.h>
- #include <linux/fsnotify.h>
- #include <linux/slab.h>
- #include <linux/init.h>
- #include <linux/hash.h>
- #include <linux/cache.h>
- #include <linux/export.h>
- #include <linux/mount.h>
- #include <linux/file.h>
- #include <asm/uaccess.h>
- #include <linux/security.h>
- #include <linux/seqlock.h>
- #include <linux/swap.h>
- #include <linux/bootmem.h>
- #include <linux/fs_struct.h>
- #include <linux/hardirq.h>
- #include <linux/bit_spinlock.h>
- #include <linux/rculist_bl.h>
- #include <linux/prefetch.h>
- #include <linux/ratelimit.h>
- #include "internal.h"
- #include "mount.h"
- /*
- * Usage:
- * dcache->d_inode->i_lock protects:
- * - i_dentry, d_u.d_alias, d_inode of aliases
- * dcache_hash_bucket lock protects:
- * - the dcache hash table
- * s_anon bl list spinlock protects:
- * - the s_anon list (see __d_drop)
- * dentry->d_sb->s_dentry_lru_lock protects:
- * - the dcache lru lists and counters
- * d_lock protects:
- * - d_flags
- * - d_name
- * - d_lru
- * - d_count
- * - d_unhashed()
- * - d_parent and d_subdirs
- * - childrens' d_child and d_parent
- * - d_u.d_alias, d_inode
- *
- * Ordering:
- * dentry->d_inode->i_lock
- * dentry->d_lock
- * dentry->d_sb->s_dentry_lru_lock
- * dcache_hash_bucket lock
- * s_anon lock
- *
- * If there is an ancestor relationship:
- * dentry->d_parent->...->d_parent->d_lock
- * ...
- * dentry->d_parent->d_lock
- * dentry->d_lock
- *
- * If no ancestor relationship:
- * if (dentry1 < dentry2)
- * dentry1->d_lock
- * dentry2->d_lock
- */
- int sysctl_vfs_cache_pressure __read_mostly = 100;
- EXPORT_SYMBOL_GPL(sysctl_vfs_cache_pressure);
- __cacheline_aligned_in_smp DEFINE_SEQLOCK(rename_lock);
- EXPORT_SYMBOL(rename_lock);
- static struct kmem_cache *dentry_cache __read_mostly;
- /*
- * This is the single most critical data structure when it comes
- * to the dcache: the hashtable for lookups. Somebody should try
- * to make this good - I've just made it work.
- *
- * This hash-function tries to avoid losing too many bits of hash
- * information, yet avoid using a prime hash-size or similar.
- */
- static unsigned int d_hash_mask __read_mostly;
- static unsigned int d_hash_shift __read_mostly;
- static struct hlist_bl_head *dentry_hashtable __read_mostly;
- static inline struct hlist_bl_head *d_hash(const struct dentry *parent,
- unsigned int hash)
- {
- hash += (unsigned long) parent / L1_CACHE_BYTES;
- return dentry_hashtable + hash_32(hash, d_hash_shift);
- }
- /* Statistics gathering. */
- struct dentry_stat_t dentry_stat = {
- .age_limit = 45,
- };
- static DEFINE_PER_CPU(long, nr_dentry);
- static DEFINE_PER_CPU(long, nr_dentry_unused);
- #if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS)
- /*
- * Here we resort to our own counters instead of using generic per-cpu counters
- * for consistency with what the vfs inode code does. We are expected to harvest
- * better code and performance by having our own specialized counters.
- *
- * Please note that the loop is done over all possible CPUs, not over all online
- * CPUs. The reason for this is that we don't want to play games with CPUs going
- * on and off. If one of them goes off, we will just keep their counters.
- *
- * glommer: See cffbc8a for details, and if you ever intend to change this,
- * please update all vfs counters to match.
- */
- static long get_nr_dentry(void)
- {
- int i;
- long sum = 0;
- for_each_possible_cpu(i)
- sum += per_cpu(nr_dentry, i);
- return sum < 0 ? 0 : sum;
- }
- static long get_nr_dentry_unused(void)
- {
- int i;
- long sum = 0;
- for_each_possible_cpu(i)
- sum += per_cpu(nr_dentry_unused, i);
- return sum < 0 ? 0 : sum;
- }
- int proc_nr_dentry(ctl_table *table, int write, void __user *buffer,
- size_t *lenp, loff_t *ppos)
- {
- dentry_stat.nr_dentry = get_nr_dentry();
- dentry_stat.nr_unused = get_nr_dentry_unused();
- return proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
- }
- #endif
- /*
- * Compare 2 name strings, return 0 if they match, otherwise non-zero.
- * The strings are both count bytes long, and count is non-zero.
- */
- #ifdef CONFIG_DCACHE_WORD_ACCESS
- #include <asm/word-at-a-time.h>
- /*
- * NOTE! 'cs' and 'scount' come from a dentry, so it has a
- * aligned allocation for this particular component. We don't
- * strictly need the load_unaligned_zeropad() safety, but it
- * doesn't hurt either.
- *
- * In contrast, 'ct' and 'tcount' can be from a pathname, and do
- * need the careful unaligned handling.
- */
- static inline int dentry_string_cmp(const unsigned char *cs, const unsigned char *ct, unsigned tcount)
- {
- unsigned long a,b,mask;
- for (;;) {
- a = *(unsigned long *)cs;
- b = load_unaligned_zeropad(ct);
- if (tcount < sizeof(unsigned long))
- break;
- if (unlikely(a != b))
- return 1;
- cs += sizeof(unsigned long);
- ct += sizeof(unsigned long);
- tcount -= sizeof(unsigned long);
- if (!tcount)
- return 0;
- }
- mask = ~(~0ul << tcount*8);
- return unlikely(!!((a ^ b) & mask));
- }
- #else
- static inline int dentry_string_cmp(const unsigned char *cs, const unsigned char *ct, unsigned tcount)
- {
- do {
- if (*cs != *ct)
- return 1;
- cs++;
- ct++;
- tcount--;
- } while (tcount);
- return 0;
- }
- #endif
- static inline int dentry_cmp(const struct dentry *dentry, const unsigned char *ct, unsigned tcount)
- {
- const unsigned char *cs;
- /*
- * Be careful about RCU walk racing with rename:
- * use ACCESS_ONCE to fetch the name pointer.
- *
- * NOTE! Even if a rename will mean that the length
- * was not loaded atomically, we don't care. The
- * RCU walk will check the sequence count eventually,
- * and catch it. And we won't overrun the buffer,
- * because we're reading the name pointer atomically,
- * and a dentry name is guaranteed to be properly
- * terminated with a NUL byte.
- *
- * End result: even if 'len' is wrong, we'll exit
- * early because the data cannot match (there can
- * be no NUL in the ct/tcount data)
- */
- cs = ACCESS_ONCE(dentry->d_name.name);
- smp_read_barrier_depends();
- return dentry_string_cmp(cs, ct, tcount);
- }
- struct external_name {
- union {
- atomic_t count;
- struct rcu_head head;
- } u;
- unsigned char name[];
- };
- static inline struct external_name *external_name(struct dentry *dentry)
- {
- return container_of(dentry->d_name.name, struct external_name, name[0]);
- }
- static void __d_free(struct rcu_head *head)
- {
- struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu);
- kmem_cache_free(dentry_cache, dentry);
- }
- static void __d_free_external(struct rcu_head *head)
- {
- struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu);
- kfree(external_name(dentry));
- kmem_cache_free(dentry_cache, dentry);
- }
- static void dentry_free(struct dentry *dentry)
- {
- if (unlikely(dname_external(dentry))) {
- struct external_name *p = external_name(dentry);
- if (likely(atomic_dec_and_test(&p->u.count))) {
- call_rcu(&dentry->d_u.d_rcu, __d_free_external);
- return;
- }
- }
- /* if dentry was never visible to RCU, immediate free is OK */
- if (!(dentry->d_flags & DCACHE_RCUACCESS))
- __d_free(&dentry->d_u.d_rcu);
- else
- call_rcu(&dentry->d_u.d_rcu, __d_free);
- }
- /*
- * no locks, please.
- */
- static void d_free(struct dentry *dentry)
- {
- WARN_ON(!list_empty(&dentry->d_u.d_alias));
- BUG_ON(dentry->d_count);
- this_cpu_dec(nr_dentry);
- if (dentry->d_op && dentry->d_op->d_release)
- dentry->d_op->d_release(dentry);
- dentry_free(dentry);
- }
- void take_dentry_name_snapshot(struct name_snapshot *name, struct dentry *dentry)
- {
- spin_lock(&dentry->d_lock);
- if (unlikely(dname_external(dentry))) {
- struct external_name *p = external_name(dentry);
- atomic_inc(&p->u.count);
- spin_unlock(&dentry->d_lock);
- name->name = p->name;
- } else {
- memcpy(name->inline_name, dentry->d_iname, DNAME_INLINE_LEN);
- spin_unlock(&dentry->d_lock);
- name->name = name->inline_name;
- }
- }
- EXPORT_SYMBOL(take_dentry_name_snapshot);
- void release_dentry_name_snapshot(struct name_snapshot *name)
- {
- if (unlikely(name->name != name->inline_name)) {
- struct external_name *p;
- p = container_of(name->name, struct external_name, name[0]);
- if (unlikely(atomic_dec_and_test(&p->u.count)))
- kfree_rcu(p, u.head);
- }
- }
- EXPORT_SYMBOL(release_dentry_name_snapshot);
- /**
- * dentry_rcuwalk_barrier - invalidate in-progress rcu-walk lookups
- * @dentry: the target dentry
- * After this call, in-progress rcu-walk path lookup will fail. This
- * should be called after unhashing, and after changing d_inode (if
- * the dentry has not already been unhashed).
- */
- static inline void dentry_rcuwalk_barrier(struct dentry *dentry)
- {
- assert_spin_locked(&dentry->d_lock);
- /* Go through a barrier */
- write_seqcount_barrier(&dentry->d_seq);
- }
- /*
- * Release the dentry's inode, using the filesystem
- * d_iput() operation if defined. Dentry has no refcount
- * and is unhashed.
- */
- static void dentry_iput(struct dentry * dentry)
- __releases(dentry->d_lock)
- __releases(dentry->d_inode->i_lock)
- {
- struct inode *inode = dentry->d_inode;
- if (inode) {
- dentry->d_inode = NULL;
- list_del_init(&dentry->d_u.d_alias);
- spin_unlock(&dentry->d_lock);
- spin_unlock(&inode->i_lock);
- if (!inode->i_nlink)
- fsnotify_inoderemove(inode);
- if (dentry->d_op && dentry->d_op->d_iput)
- dentry->d_op->d_iput(dentry, inode);
- else
- iput(inode);
- } else {
- spin_unlock(&dentry->d_lock);
- }
- }
- /*
- * Release the dentry's inode, using the filesystem
- * d_iput() operation if defined. dentry remains in-use.
- */
- static void dentry_unlink_inode(struct dentry * dentry)
- __releases(dentry->d_lock)
- __releases(dentry->d_inode->i_lock)
- {
- struct inode *inode = dentry->d_inode;
- dentry->d_inode = NULL;
- list_del_init(&dentry->d_u.d_alias);
- dentry_rcuwalk_barrier(dentry);
- spin_unlock(&dentry->d_lock);
- spin_unlock(&inode->i_lock);
- if (!inode->i_nlink)
- fsnotify_inoderemove(inode);
- if (dentry->d_op && dentry->d_op->d_iput)
- dentry->d_op->d_iput(dentry, inode);
- else
- iput(inode);
- }
- /*
- * dentry_lru_(add|del|prune|move_tail) must be called with d_lock held.
- */
- static void dentry_lru_add(struct dentry *dentry)
- {
- if (list_empty(&dentry->d_lru)) {
- spin_lock(&dentry->d_sb->s_dentry_lru_lock);
- list_add(&dentry->d_lru, &dentry->d_sb->s_dentry_lru);
- dentry->d_sb->s_nr_dentry_unused++;
- this_cpu_inc(nr_dentry_unused);
- spin_unlock(&dentry->d_sb->s_dentry_lru_lock);
- }
- }
- static void __dentry_lru_del(struct dentry *dentry)
- {
- list_del_init(&dentry->d_lru);
- dentry->d_flags &= ~DCACHE_SHRINK_LIST;
- dentry->d_sb->s_nr_dentry_unused--;
- this_cpu_dec(nr_dentry_unused);
- }
- /*
- * Remove a dentry with references from the LRU.
- */
- static void dentry_lru_del(struct dentry *dentry)
- {
- if (!list_empty(&dentry->d_lru)) {
- spin_lock(&dentry->d_sb->s_dentry_lru_lock);
- __dentry_lru_del(dentry);
- spin_unlock(&dentry->d_sb->s_dentry_lru_lock);
- }
- }
- /*
- * Remove a dentry that is unreferenced and about to be pruned
- * (unhashed and destroyed) from the LRU, and inform the file system.
- * This wrapper should be called _prior_ to unhashing a victim dentry.
- */
- static void dentry_lru_prune(struct dentry *dentry)
- {
- if (!list_empty(&dentry->d_lru)) {
- if (dentry->d_flags & DCACHE_OP_PRUNE)
- dentry->d_op->d_prune(dentry);
- spin_lock(&dentry->d_sb->s_dentry_lru_lock);
- __dentry_lru_del(dentry);
- spin_unlock(&dentry->d_sb->s_dentry_lru_lock);
- }
- }
- static void dentry_lru_move_list(struct dentry *dentry, struct list_head *list)
- {
- spin_lock(&dentry->d_sb->s_dentry_lru_lock);
- if (list_empty(&dentry->d_lru)) {
- list_add_tail(&dentry->d_lru, list);
- dentry->d_sb->s_nr_dentry_unused++;
- this_cpu_inc(nr_dentry_unused);
- } else {
- list_move_tail(&dentry->d_lru, list);
- }
- spin_unlock(&dentry->d_sb->s_dentry_lru_lock);
- }
- /**
- * d_kill - kill dentry and return parent
- * @dentry: dentry to kill
- * @parent: parent dentry
- *
- * The dentry must already be unhashed and removed from the LRU.
- *
- * If this is the root of the dentry tree, return NULL.
- *
- * dentry->d_lock and parent->d_lock must be held by caller, and are dropped by
- * d_kill.
- */
- static struct dentry *d_kill(struct dentry *dentry, struct dentry *parent)
- __releases(dentry->d_lock)
- __releases(parent->d_lock)
- __releases(dentry->d_inode->i_lock)
- {
- __list_del_entry(&dentry->d_child);
- /*
- * Inform ascending readers that we are no longer attached to the
- * dentry tree
- */
- dentry->d_flags |= DCACHE_DENTRY_KILLED;
- if (parent)
- spin_unlock(&parent->d_lock);
- dentry_iput(dentry);
- /*
- * dentry_iput drops the locks, at which point nobody (except
- * transient RCU lookups) can reach this dentry.
- */
- d_free(dentry);
- return parent;
- }
- /*
- * Unhash a dentry without inserting an RCU walk barrier or checking that
- * dentry->d_lock is locked. The caller must take care of that, if
- * appropriate.
- */
- static void __d_shrink(struct dentry *dentry)
- {
- if (!d_unhashed(dentry)) {
- struct hlist_bl_head *b;
- if (unlikely(dentry->d_flags & DCACHE_DISCONNECTED))
- b = &dentry->d_sb->s_anon;
- else
- b = d_hash(dentry->d_parent, dentry->d_name.hash);
- hlist_bl_lock(b);
- __hlist_bl_del(&dentry->d_hash);
- dentry->d_hash.pprev = NULL;
- hlist_bl_unlock(b);
- }
- }
- /**
- * d_drop - drop a dentry
- * @dentry: dentry to drop
- *
- * d_drop() unhashes the entry from the parent dentry hashes, so that it won't
- * be found through a VFS lookup any more. Note that this is different from
- * deleting the dentry - d_delete will try to mark the dentry negative if
- * possible, giving a successful _negative_ lookup, while d_drop will
- * just make the cache lookup fail.
- *
- * d_drop() is used mainly for stuff that wants to invalidate a dentry for some
- * reason (NFS timeouts or autofs deletes).
- *
- * __d_drop requires dentry->d_lock.
- */
- void __d_drop(struct dentry *dentry)
- {
- if (!d_unhashed(dentry)) {
- __d_shrink(dentry);
- dentry_rcuwalk_barrier(dentry);
- }
- }
- EXPORT_SYMBOL(__d_drop);
- void d_drop(struct dentry *dentry)
- {
- spin_lock(&dentry->d_lock);
- __d_drop(dentry);
- spin_unlock(&dentry->d_lock);
- }
- EXPORT_SYMBOL(d_drop);
- /*
- * d_clear_need_lookup - drop a dentry from cache and clear the need lookup flag
- * @dentry: dentry to drop
- *
- * This is called when we do a lookup on a placeholder dentry that needed to be
- * looked up. The dentry should have been hashed in order for it to be found by
- * the lookup code, but now needs to be unhashed while we do the actual lookup
- * and clear the DCACHE_NEED_LOOKUP flag.
- */
- void d_clear_need_lookup(struct dentry *dentry)
- {
- spin_lock(&dentry->d_lock);
- __d_drop(dentry);
- dentry->d_flags &= ~DCACHE_NEED_LOOKUP;
- spin_unlock(&dentry->d_lock);
- }
- EXPORT_SYMBOL(d_clear_need_lookup);
- /*
- * Finish off a dentry we've decided to kill.
- * dentry->d_lock must be held, returns with it unlocked.
- * If ref is non-zero, then decrement the refcount too.
- * Returns dentry requiring refcount drop, or NULL if we're done.
- */
- static inline struct dentry *dentry_kill(struct dentry *dentry, int ref)
- __releases(dentry->d_lock)
- {
- struct inode *inode;
- struct dentry *parent;
- inode = dentry->d_inode;
- if (inode && !spin_trylock(&inode->i_lock)) {
- relock:
- spin_unlock(&dentry->d_lock);
- cpu_relax();
- return dentry; /* try again with same dentry */
- }
- if (IS_ROOT(dentry))
- parent = NULL;
- else
- parent = dentry->d_parent;
- if (parent && !spin_trylock(&parent->d_lock)) {
- if (inode)
- spin_unlock(&inode->i_lock);
- goto relock;
- }
- if (ref)
- dentry->d_count--;
- /*
- * if dentry was on the d_lru list delete it from there.
- * inform the fs via d_prune that this dentry is about to be
- * unhashed and destroyed.
- */
- dentry_lru_prune(dentry);
- /* if it was on the hash then remove it */
- __d_drop(dentry);
- return d_kill(dentry, parent);
- }
- /*
- * This is dput
- *
- * This is complicated by the fact that we do not want to put
- * dentries that are no longer on any hash chain on the unused
- * list: we'd much rather just get rid of them immediately.
- *
- * However, that implies that we have to traverse the dentry
- * tree upwards to the parents which might _also_ now be
- * scheduled for deletion (it may have been only waiting for
- * its last child to go away).
- *
- * This tail recursion is done by hand as we don't want to depend
- * on the compiler to always get this right (gcc generally doesn't).
- * Real recursion would eat up our stack space.
- */
- /*
- * dput - release a dentry
- * @dentry: dentry to release
- *
- * Release a dentry. This will drop the usage count and if appropriate
- * call the dentry unlink method as well as removing it from the queues and
- * releasing its resources. If the parent dentries were scheduled for release
- * they too may now get deleted.
- */
- void dput(struct dentry *dentry)
- {
- if (!dentry)
- return;
- repeat:
- if (dentry->d_count == 1)
- might_sleep();
- spin_lock(&dentry->d_lock);
- BUG_ON(!dentry->d_count);
- if (dentry->d_count > 1) {
- dentry->d_count--;
- spin_unlock(&dentry->d_lock);
- return;
- }
- if (dentry->d_flags & DCACHE_OP_DELETE) {
- if (dentry->d_op->d_delete(dentry))
- goto kill_it;
- }
- /* Unreachable? Get rid of it */
- if (d_unhashed(dentry))
- goto kill_it;
- /*
- * If this dentry needs lookup, don't set the referenced flag so that it
- * is more likely to be cleaned up by the dcache shrinker in case of
- * memory pressure.
- */
- if (!d_need_lookup(dentry))
- dentry->d_flags |= DCACHE_REFERENCED;
- dentry_lru_add(dentry);
- dentry->d_count--;
- spin_unlock(&dentry->d_lock);
- return;
- kill_it:
- dentry = dentry_kill(dentry, 1);
- if (dentry)
- goto repeat;
- }
- EXPORT_SYMBOL(dput);
- /**
- * d_invalidate - invalidate a dentry
- * @dentry: dentry to invalidate
- *
- * Try to invalidate the dentry if it turns out to be
- * possible. If there are other dentries that can be
- * reached through this one we can't delete it and we
- * return -EBUSY. On success we return 0.
- *
- * no dcache lock.
- */
-
- int d_invalidate(struct dentry * dentry)
- {
- /*
- * If it's already been dropped, return OK.
- */
- spin_lock(&dentry->d_lock);
- if (d_unhashed(dentry)) {
- spin_unlock(&dentry->d_lock);
- return 0;
- }
- /*
- * Check whether to do a partial shrink_dcache
- * to get rid of unused child entries.
- */
- if (!list_empty(&dentry->d_subdirs)) {
- spin_unlock(&dentry->d_lock);
- shrink_dcache_parent(dentry);
- spin_lock(&dentry->d_lock);
- }
- /*
- * Somebody else still using it?
- *
- * If it's a directory, we can't drop it
- * for fear of somebody re-populating it
- * with children (even though dropping it
- * would make it unreachable from the root,
- * we might still populate it if it was a
- * working directory or similar).
- * We also need to leave mountpoints alone,
- * directory or not.
- */
- if (dentry->d_count > 1 && dentry->d_inode) {
- if (S_ISDIR(dentry->d_inode->i_mode) || d_mountpoint(dentry)) {
- spin_unlock(&dentry->d_lock);
- return -EBUSY;
- }
- }
- __d_drop(dentry);
- spin_unlock(&dentry->d_lock);
- return 0;
- }
- EXPORT_SYMBOL(d_invalidate);
- /* This must be called with d_lock held */
- static inline void __dget_dlock(struct dentry *dentry)
- {
- dentry->d_count++;
- }
- static inline void __dget(struct dentry *dentry)
- {
- spin_lock(&dentry->d_lock);
- __dget_dlock(dentry);
- spin_unlock(&dentry->d_lock);
- }
- struct dentry *dget_parent(struct dentry *dentry)
- {
- struct dentry *ret;
- repeat:
- /*
- * Don't need rcu_dereference because we re-check it was correct under
- * the lock.
- */
- rcu_read_lock();
- ret = dentry->d_parent;
- spin_lock(&ret->d_lock);
- if (unlikely(ret != dentry->d_parent)) {
- spin_unlock(&ret->d_lock);
- rcu_read_unlock();
- goto repeat;
- }
- rcu_read_unlock();
- BUG_ON(!ret->d_count);
- ret->d_count++;
- spin_unlock(&ret->d_lock);
- return ret;
- }
- EXPORT_SYMBOL(dget_parent);
- /**
- * d_find_alias - grab a hashed alias of inode
- * @inode: inode in question
- *
- * If inode has a hashed alias, or is a directory and has any alias,
- * acquire the reference to alias and return it. Otherwise return NULL.
- * Notice that if inode is a directory there can be only one alias and
- * it can be unhashed only if it has no children, or if it is the root
- * of a filesystem.
- *
- * If the inode has an IS_ROOT, DCACHE_DISCONNECTED alias, then prefer
- * any other hashed alias over that.
- */
- static struct dentry *__d_find_alias(struct inode *inode)
- {
- struct dentry *alias, *discon_alias;
- again:
- discon_alias = NULL;
- list_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) {
- spin_lock(&alias->d_lock);
- if (S_ISDIR(inode->i_mode) || !d_unhashed(alias)) {
- if (IS_ROOT(alias) &&
- (alias->d_flags & DCACHE_DISCONNECTED)) {
- discon_alias = alias;
- } else {
- __dget_dlock(alias);
- spin_unlock(&alias->d_lock);
- return alias;
- }
- }
- spin_unlock(&alias->d_lock);
- }
- if (discon_alias) {
- alias = discon_alias;
- spin_lock(&alias->d_lock);
- if (S_ISDIR(inode->i_mode) || !d_unhashed(alias)) {
- if (IS_ROOT(alias) &&
- (alias->d_flags & DCACHE_DISCONNECTED)) {
- __dget_dlock(alias);
- spin_unlock(&alias->d_lock);
- return alias;
- }
- }
- spin_unlock(&alias->d_lock);
- goto again;
- }
- return NULL;
- }
- struct dentry *d_find_alias(struct inode *inode)
- {
- struct dentry *de = NULL;
- if (!list_empty(&inode->i_dentry)) {
- spin_lock(&inode->i_lock);
- de = __d_find_alias(inode);
- spin_unlock(&inode->i_lock);
- }
- return de;
- }
- EXPORT_SYMBOL(d_find_alias);
- /*
- * Try to kill dentries associated with this inode.
- * WARNING: you must own a reference to inode.
- */
- void d_prune_aliases(struct inode *inode)
- {
- struct dentry *dentry;
- restart:
- spin_lock(&inode->i_lock);
- list_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) {
- spin_lock(&dentry->d_lock);
- if (!dentry->d_count) {
- __dget_dlock(dentry);
- __d_drop(dentry);
- spin_unlock(&dentry->d_lock);
- spin_unlock(&inode->i_lock);
- dput(dentry);
- goto restart;
- }
- spin_unlock(&dentry->d_lock);
- }
- spin_unlock(&inode->i_lock);
- }
- EXPORT_SYMBOL(d_prune_aliases);
- /*
- * Try to throw away a dentry - free the inode, dput the parent.
- * Requires dentry->d_lock is held, and dentry->d_count == 0.
- * Releases dentry->d_lock.
- *
- * This may fail if locks cannot be acquired no problem, just try again.
- */
- static void try_prune_one_dentry(struct dentry *dentry)
- __releases(dentry->d_lock)
- {
- struct dentry *parent;
- parent = dentry_kill(dentry, 0);
- /*
- * If dentry_kill returns NULL, we have nothing more to do.
- * if it returns the same dentry, trylocks failed. In either
- * case, just loop again.
- *
- * Otherwise, we need to prune ancestors too. This is necessary
- * to prevent quadratic behavior of shrink_dcache_parent(), but
- * is also expected to be beneficial in reducing dentry cache
- * fragmentation.
- */
- if (!parent)
- return;
- if (parent == dentry)
- return;
- /* Prune ancestors. */
- dentry = parent;
- while (dentry) {
- spin_lock(&dentry->d_lock);
- if (dentry->d_count > 1) {
- dentry->d_count--;
- spin_unlock(&dentry->d_lock);
- return;
- }
- dentry = dentry_kill(dentry, 1);
- }
- }
- static void shrink_dentry_list(struct list_head *list)
- {
- struct dentry *dentry;
- rcu_read_lock();
- for (;;) {
- dentry = list_entry_rcu(list->prev, struct dentry, d_lru);
- if (&dentry->d_lru == list)
- break; /* empty */
- spin_lock(&dentry->d_lock);
- if (dentry != list_entry(list->prev, struct dentry, d_lru)) {
- spin_unlock(&dentry->d_lock);
- continue;
- }
- /*
- * We found an inuse dentry which was not removed from
- * the LRU because of laziness during lookup. Do not free
- * it - just keep it off the LRU list.
- */
- if (dentry->d_count) {
- dentry_lru_del(dentry);
- spin_unlock(&dentry->d_lock);
- continue;
- }
- rcu_read_unlock();
- try_prune_one_dentry(dentry);
- rcu_read_lock();
- }
- rcu_read_unlock();
- }
- /**
- * prune_dcache_sb - shrink the dcache
- * @sb: superblock
- * @count: number of entries to try to free
- *
- * Attempt to shrink the superblock dcache LRU by @count entries. This is
- * done when we need more memory an called from the superblock shrinker
- * function.
- *
- * This function may fail to free any resources if all the dentries are in
- * use.
- */
- long prune_dcache_sb(struct super_block *sb, unsigned long nr_to_scan)
- {
- struct dentry *dentry;
- LIST_HEAD(referenced);
- LIST_HEAD(tmp);
- long freed = 0;
- relock:
- spin_lock(&sb->s_dentry_lru_lock);
- while (!list_empty(&sb->s_dentry_lru)) {
- dentry = list_entry(sb->s_dentry_lru.prev,
- struct dentry, d_lru);
- BUG_ON(dentry->d_sb != sb);
- if (!spin_trylock(&dentry->d_lock)) {
- spin_unlock(&sb->s_dentry_lru_lock);
- cpu_relax();
- goto relock;
- }
- if (dentry->d_flags & DCACHE_REFERENCED) {
- dentry->d_flags &= ~DCACHE_REFERENCED;
- list_move(&dentry->d_lru, &referenced);
- spin_unlock(&dentry->d_lock);
- } else {
- list_move_tail(&dentry->d_lru, &tmp);
- dentry->d_flags |= DCACHE_SHRINK_LIST;
- spin_unlock(&dentry->d_lock);
- freed++;
- if (!--nr_to_scan)
- break;
- }
- cond_resched_lock(&sb->s_dentry_lru_lock);
- }
- if (!list_empty(&referenced))
- list_splice(&referenced, &sb->s_dentry_lru);
- spin_unlock(&sb->s_dentry_lru_lock);
- shrink_dentry_list(&tmp);
- return freed;
- }
- /**
- * shrink_dcache_sb - shrink dcache for a superblock
- * @sb: superblock
- *
- * Shrink the dcache for the specified super block. This is used to free
- * the dcache before unmounting a file system.
- */
- void shrink_dcache_sb(struct super_block *sb)
- {
- LIST_HEAD(tmp);
- spin_lock(&sb->s_dentry_lru_lock);
- while (!list_empty(&sb->s_dentry_lru)) {
- list_splice_init(&sb->s_dentry_lru, &tmp);
- spin_unlock(&sb->s_dentry_lru_lock);
- shrink_dentry_list(&tmp);
- spin_lock(&sb->s_dentry_lru_lock);
- }
- spin_unlock(&sb->s_dentry_lru_lock);
- }
- EXPORT_SYMBOL(shrink_dcache_sb);
- /*
- * destroy a single subtree of dentries for unmount
- * - see the comments on shrink_dcache_for_umount() for a description of the
- * locking
- */
- static void shrink_dcache_for_umount_subtree(struct dentry *dentry)
- {
- struct dentry *parent;
- BUG_ON(!IS_ROOT(dentry));
- for (;;) {
- /* descend to the first leaf in the current subtree */
- while (!list_empty(&dentry->d_subdirs))
- dentry = list_entry(dentry->d_subdirs.next,
- struct dentry, d_child);
- /* consume the dentries from this leaf up through its parents
- * until we find one with children or run out altogether */
- do {
- struct inode *inode;
- /*
- * remove the dentry from the lru, and inform
- * the fs that this dentry is about to be
- * unhashed and destroyed.
- */
- dentry_lru_prune(dentry);
- __d_shrink(dentry);
- if (dentry->d_count != 0) {
- printk(KERN_ERR
- "BUG: Dentry %p{i=%lx,n=%s}"
- " still in use (%d)"
- " [unmount of %s %s]\n",
- dentry,
- dentry->d_inode ?
- dentry->d_inode->i_ino : 0UL,
- dentry->d_name.name,
- dentry->d_count,
- dentry->d_sb->s_type->name,
- dentry->d_sb->s_id);
- BUG();
- }
- if (IS_ROOT(dentry)) {
- parent = NULL;
- list_del(&dentry->d_child);
- } else {
- parent = dentry->d_parent;
- parent->d_count--;
- list_del(&dentry->d_child);
- }
- inode = dentry->d_inode;
- if (inode) {
- dentry->d_inode = NULL;
- list_del_init(&dentry->d_u.d_alias);
- if (dentry->d_op && dentry->d_op->d_iput)
- dentry->d_op->d_iput(dentry, inode);
- else
- iput(inode);
- }
- d_free(dentry);
- /* finished when we fall off the top of the tree,
- * otherwise we ascend to the parent and move to the
- * next sibling if there is one */
- if (!parent)
- return;
- dentry = parent;
- } while (list_empty(&dentry->d_subdirs));
- dentry = list_entry(dentry->d_subdirs.next,
- struct dentry, d_child);
- }
- }
- /*
- * destroy the dentries attached to a superblock on unmounting
- * - we don't need to use dentry->d_lock because:
- * - the superblock is detached from all mountings and open files, so the
- * dentry trees will not be rearranged by the VFS
- * - s_umount is write-locked, so the memory pressure shrinker will ignore
- * any dentries belonging to this superblock that it comes across
- * - the filesystem itself is no longer permitted to rearrange the dentries
- * in this superblock
- */
- void shrink_dcache_for_umount(struct super_block *sb)
- {
- struct dentry *dentry;
- if (down_read_trylock(&sb->s_umount))
- BUG();
- dentry = sb->s_root;
- sb->s_root = NULL;
- dentry->d_count--;
- shrink_dcache_for_umount_subtree(dentry);
- while (!hlist_bl_empty(&sb->s_anon)) {
- dentry = hlist_bl_entry(hlist_bl_first(&sb->s_anon), struct dentry, d_hash);
- shrink_dcache_for_umount_subtree(dentry);
- }
- }
- /*
- * Search for at least 1 mount point in the dentry's subdirs.
- * We descend to the next level whenever the d_subdirs
- * list is non-empty and continue searching.
- */
-
- /**
- * have_submounts - check for mounts over a dentry
- * @parent: dentry to check.
- *
- * Return true if the parent or its subdirectories contain
- * a mount point
- */
- int have_submounts(struct dentry *parent)
- {
- struct dentry *this_parent;
- struct list_head *next;
- unsigned seq;
- int locked = 0;
- seq = read_seqbegin(&rename_lock);
- again:
- this_parent = parent;
- if (d_mountpoint(parent))
- goto positive;
- spin_lock(&this_parent->d_lock);
- repeat:
- next = this_parent->d_subdirs.next;
- resume:
- while (next != &this_parent->d_subdirs) {
- struct list_head *tmp = next;
- struct dentry *dentry = list_entry(tmp, struct dentry, d_child);
- next = tmp->next;
- spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
- /* Have we found a mount point ? */
- if (d_mountpoint(dentry)) {
- spin_unlock(&dentry->d_lock);
- spin_unlock(&this_parent->d_lock);
- goto positive;
- }
- if (!list_empty(&dentry->d_subdirs)) {
- spin_unlock(&this_parent->d_lock);
- spin_release(&dentry->d_lock.dep_map, 1, _RET_IP_);
- this_parent = dentry;
- spin_acquire(&this_parent->d_lock.dep_map, 0, 1, _RET_IP_);
- goto repeat;
- }
- spin_unlock(&dentry->d_lock);
- }
- /*
- * All done at this level ... ascend and resume the search.
- */
- rcu_read_lock();
- ascend:
- if (this_parent != parent) {
- struct dentry *child = this_parent;
- this_parent = child->d_parent;
- spin_unlock(&child->d_lock);
- spin_lock(&this_parent->d_lock);
- /* might go back up the wrong parent if we have had a rename */
- if (!locked && read_seqretry(&rename_lock, seq))
- goto rename_retry;
- next = child->d_child.next;
- while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED)) {
- if (next == &this_parent->d_subdirs)
- goto ascend;
- child = list_entry(next, struct dentry, d_child);
- next = next->next;
- }
- rcu_read_unlock();
- goto resume;
- }
- if (!locked && read_seqretry(&rename_lock, seq))
- goto rename_retry;
- spin_unlock(&this_parent->d_lock);
- rcu_read_unlock();
- if (locked)
- write_sequnlock(&rename_lock);
- return 0; /* No mount points found in tree */
- positive:
- if (!locked && read_seqretry(&rename_lock, seq))
- goto rename_retry_unlocked;
- if (locked)
- write_sequnlock(&rename_lock);
- return 1;
- rename_retry:
- spin_unlock(&this_parent->d_lock);
- rcu_read_unlock();
- if (locked)
- goto again;
- rename_retry_unlocked:
- locked = 1;
- write_seqlock(&rename_lock);
- goto again;
- }
- EXPORT_SYMBOL(have_submounts);
- /*
- * Search the dentry child list of the specified parent,
- * and move any unused dentries to the end of the unused
- * list for prune_dcache(). We descend to the next level
- * whenever the d_subdirs list is non-empty and continue
- * searching.
- *
- * It returns zero iff there are no unused children,
- * otherwise it returns the number of children moved to
- * the end of the unused list. This may not be the total
- * number of unused children, because select_parent can
- * drop the lock and return early due to latency
- * constraints.
- */
- static int select_parent(struct dentry *parent, struct list_head *dispose)
- {
- struct dentry *this_parent;
- struct list_head *next;
- unsigned seq;
- int found = 0;
- int locked = 0;
- seq = read_seqbegin(&rename_lock);
- again:
- this_parent = parent;
- spin_lock(&this_parent->d_lock);
- repeat:
- next = this_parent->d_subdirs.next;
- resume:
- while (next != &this_parent->d_subdirs) {
- struct list_head *tmp = next;
- struct dentry *dentry = list_entry(tmp, struct dentry, d_child);
- next = tmp->next;
- spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
- /*
- * move only zero ref count dentries to the dispose list.
- *
- * Those which are presently on the shrink list, being processed
- * by shrink_dentry_list(), shouldn't be moved. Otherwise the
- * loop in shrink_dcache_parent() might not make any progress
- * and loop forever.
- */
- if (dentry->d_count) {
- dentry_lru_del(dentry);
- } else if (!(dentry->d_flags & DCACHE_SHRINK_LIST)) {
- dentry_lru_move_list(dentry, dispose);
- dentry->d_flags |= DCACHE_SHRINK_LIST;
- found++;
- }
- /*
- * We can return to the caller if we have found some (this
- * ensures forward progress). We'll be coming back to find
- * the rest.
- */
- if (found && need_resched()) {
- spin_unlock(&dentry->d_lock);
- rcu_read_lock();
- goto out;
- }
- /*
- * Descend a level if the d_subdirs list is non-empty.
- */
- if (!list_empty(&dentry->d_subdirs)) {
- spin_unlock(&this_parent->d_lock);
- spin_release(&dentry->d_lock.dep_map, 1, _RET_IP_);
- this_parent = dentry;
- spin_acquire(&this_parent->d_lock.dep_map, 0, 1, _RET_IP_);
- goto repeat;
- }
- spin_unlock(&dentry->d_lock);
- }
- /*
- * All done at this level ... ascend and resume the search.
- */
- rcu_read_lock();
- ascend:
- if (this_parent != parent) {
- struct dentry *child = this_parent;
- this_parent = child->d_parent;
- spin_unlock(&child->d_lock);
- spin_lock(&this_parent->d_lock);
- /* might go back up the wrong parent if we have had a rename */
- if (!locked && read_seqretry(&rename_lock, seq))
- goto rename_retry;
- /* go into the first sibling still alive */
- do {
- next = child->d_child.next;
- if (next == &this_parent->d_subdirs)
- goto ascend;
- child = list_entry(next, struct dentry, d_child);
- } while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED));
- rcu_read_unlock();
- goto resume;
- }
- out:
- if (!locked && read_seqretry(&rename_lock, seq))
- goto rename_retry;
- spin_unlock(&this_parent->d_lock);
- rcu_read_unlock();
- if (locked)
- write_sequnlock(&rename_lock);
- return found;
- rename_retry:
- spin_unlock(&this_parent->d_lock);
- rcu_read_unlock();
- if (found)
- return found;
- if (locked)
- goto again;
- locked = 1;
- write_seqlock(&rename_lock);
- goto again;
- }
- /**
- * shrink_dcache_parent - prune dcache
- * @parent: parent of entries to prune
- *
- * Prune the dcache to remove unused children of the parent dentry.
- */
- void shrink_dcache_parent(struct dentry * parent)
- {
- LIST_HEAD(dispose);
- int found;
- while ((found = select_parent(parent, &dispose)) != 0) {
- shrink_dentry_list(&dispose);
- cond_resched();
- }
- }
- EXPORT_SYMBOL(shrink_dcache_parent);
- /**
- * __d_alloc - allocate a dcache entry
- * @sb: filesystem it will belong to
- * @name: qstr of the name
- *
- * Allocates a dentry. It returns %NULL if there is insufficient memory
- * available. On a success the dentry is returned. The name passed in is
- * copied and the copy passed in may be reused after this call.
- */
-
- struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name)
- {
- struct dentry *dentry;
- char *dname;
- dentry = kmem_cache_alloc(dentry_cache, GFP_KERNEL);
- if (!dentry)
- return NULL;
- /*
- * We guarantee that the inline name is always NUL-terminated.
- * This way the memcpy() done by the name switching in rename
- * will still always have a NUL at the end, even if we might
- * be overwriting an internal NUL character
- */
- dentry->d_iname[DNAME_INLINE_LEN-1] = 0;
- if (name->len > DNAME_INLINE_LEN-1) {
- size_t size = offsetof(struct external_name, name[1]);
- struct external_name *p = kmalloc(size + name->len, GFP_KERNEL);
- if (!p) {
- kmem_cache_free(dentry_cache, dentry);
- return NULL;
- }
- atomic_set(&p->u.count, 1);
- dname = p->name;
- } else {
- dname = dentry->d_iname;
- }
- dentry->d_name.len = name->len;
- dentry->d_name.hash = name->hash;
- memcpy(dname, name->name, name->len);
- dname[name->len] = 0;
- /* Make sure we always see the terminating NUL character */
- smp_wmb();
- dentry->d_name.name = dname;
- dentry->d_count = 1;
- dentry->d_flags = 0;
- spin_lock_init(&dentry->d_lock);
- seqcount_init(&dentry->d_seq);
- dentry->d_inode = NULL;
- dentry->d_parent = dentry;
- dentry->d_sb = sb;
- dentry->d_op = NULL;
- dentry->d_fsdata = NULL;
- INIT_HLIST_BL_NODE(&dentry->d_hash);
- INIT_LIST_HEAD(&dentry->d_lru);
- INIT_LIST_HEAD(&dentry->d_subdirs);
- INIT_LIST_HEAD(&dentry->d_u.d_alias);
- INIT_LIST_HEAD(&dentry->d_child);
- d_set_d_op(dentry, dentry->d_sb->s_d_op);
- this_cpu_inc(nr_dentry);
- return dentry;
- }
- /**
- * d_alloc - allocate a dcache entry
- * @parent: parent of entry to allocate
- * @name: qstr of the name
- *
- * Allocates a dentry. It returns %NULL if there is insufficient memory
- * available. On a success the dentry is returned. The name passed in is
- * copied and the copy passed in may be reused after this call.
- */
- struct dentry *d_alloc(struct dentry * parent, const struct qstr *name)
- {
- struct dentry *dentry = __d_alloc(parent->d_sb, name);
- if (!dentry)
- return NULL;
- spin_lock(&parent->d_lock);
- /*
- * don't need child lock because it is not subject
- * to concurrency here
- */
- __dget_dlock(parent);
- dentry->d_parent = parent;
- list_add(&dentry->d_child, &parent->d_subdirs);
- spin_unlock(&parent->d_lock);
- return dentry;
- }
- EXPORT_SYMBOL(d_alloc);
- struct dentry *d_alloc_pseudo(struct super_block *sb, const struct qstr *name)
- {
- struct dentry *dentry = __d_alloc(sb, name);
- if (dentry)
- dentry->d_flags |= DCACHE_DISCONNECTED;
- return dentry;
- }
- EXPORT_SYMBOL(d_alloc_pseudo);
- struct dentry *d_alloc_name(struct dentry *parent, const char *name)
- {
- struct qstr q;
- q.name = name;
- q.len = strlen(name);
- q.hash = full_name_hash(q.name, q.len);
- return d_alloc(parent, &q);
- }
- EXPORT_SYMBOL(d_alloc_name);
- void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op)
- {
- WARN_ON_ONCE(dentry->d_op);
- WARN_ON_ONCE(dentry->d_flags & (DCACHE_OP_HASH |
- DCACHE_OP_COMPARE |
- DCACHE_OP_REVALIDATE |
- DCACHE_OP_DELETE ));
- dentry->d_op = op;
- if (!op)
- return;
- if (op->d_hash)
- dentry->d_flags |= DCACHE_OP_HASH;
- if (op->d_compare)
- dentry->d_flags |= DCACHE_OP_COMPARE;
- if (op->d_revalidate)
- dentry->d_flags |= DCACHE_OP_REVALIDATE;
- if (op->d_delete)
- dentry->d_flags |= DCACHE_OP_DELETE;
- if (op->d_prune)
- dentry->d_flags |= DCACHE_OP_PRUNE;
- }
- EXPORT_SYMBOL(d_set_d_op);
- static void __d_instantiate(struct dentry *dentry, struct inode *inode)
- {
- spin_lock(&dentry->d_lock);
- if (inode) {
- if (unlikely(IS_AUTOMOUNT(inode)))
- dentry->d_flags |= DCACHE_NEED_AUTOMOUNT;
- list_add(&dentry->d_u.d_alias, &inode->i_dentry);
- }
- dentry->d_inode = inode;
- dentry_rcuwalk_barrier(dentry);
- spin_unlock(&dentry->d_lock);
- fsnotify_d_instantiate(dentry, inode);
- }
- /**
- * d_instantiate - fill in inode information for a dentry
- * @entry: dentry to complete
- * @inode: inode to attach to this dentry
- *
- * Fill in inode information in the entry.
- *
- * This turns negative dentries into productive full members
- * of society.
- *
- * NOTE! This assumes that the inode count has been incremented
- * (or otherwise set) by the caller to indicate that it is now
- * in use by the dcache.
- */
-
- void d_instantiate(struct dentry *entry, struct inode * inode)
- {
- BUG_ON(!list_empty(&entry->d_u.d_alias));
- if (inode)
- spin_lock(&inode->i_lock);
- __d_instantiate(entry, inode);
- if (inode)
- spin_unlock(&inode->i_lock);
- security_d_instantiate(entry, inode);
- }
- EXPORT_SYMBOL(d_instantiate);
- /**
- * d_instantiate_unique - instantiate a non-aliased dentry
- * @entry: dentry to instantiate
- * @inode: inode to attach to this dentry
- *
- * Fill in inode information in the entry. On success, it returns NULL.
- * If an unhashed alias of "entry" already exists, then we return the
- * aliased dentry instead and drop one reference to inode.
- *
- * Note that in order to avoid conflicts with rename() etc, the caller
- * had better be holding the parent directory semaphore.
- *
- * This also assumes that the inode count has been incremented
- * (or otherwise set) by the caller to indicate that it is now
- * in use by the dcache.
- */
- static struct dentry *__d_instantiate_unique(struct dentry *entry,
- struct inode *inode)
- {
- struct dentry *alias;
- int len = entry->d_name.len;
- const char *name = entry->d_name.name;
- unsigned int hash = entry->d_name.hash;
- if (!inode) {
- __d_instantiate(entry, NULL);
- return NULL;
- }
- list_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) {
- /*
- * Don't need alias->d_lock here, because aliases with
- * d_parent == entry->d_parent are not subject to name or
- * parent changes, because the parent inode i_mutex is held.
- */
- if (alias->d_name.hash != hash)
- continue;
- if (alias->d_parent != entry->d_parent)
- continue;
- if (alias->d_name.len != len)
- continue;
- if (dentry_cmp(alias, name, len))
- continue;
- __dget(alias);
- return alias;
- }
- __d_instantiate(entry, inode);
- return NULL;
- }
- struct dentry *d_instantiate_unique(struct dentry *entry, struct inode *inode)
- {
- struct dentry *result;
- BUG_ON(!list_empty(&entry->d_u.d_alias));
- if (inode)
- spin_lock(&inode->i_lock);
- result = __d_instantiate_unique(entry, inode);
- if (inode)
- spin_unlock(&inode->i_lock);
- if (!result) {
- security_d_instantiate(entry, inode);
- return NULL;
- }
- BUG_ON(!d_unhashed(result));
- iput(inode);
- return result;
- }
- EXPORT_SYMBOL(d_instantiate_unique);
- struct dentry *d_make_root(struct inode *root_inode)
- {
- struct dentry *res = NULL;
- if (root_inode) {
- static const struct qstr name = QSTR_INIT("/", 1);
- res = __d_alloc(root_inode->i_sb, &name);
- if (res)
- d_instantiate(res, root_inode);
- else
- iput(root_inode);
- }
- return res;
- }
- EXPORT_SYMBOL(d_make_root);
- static struct dentry * __d_find_any_alias(struct inode *inode)
- {
- struct dentry *alias;
- if (list_empty(&inode->i_dentry))
- return NULL;
- alias = list_first_entry(&inode->i_dentry, struct dentry, d_u.d_alias);
- __dget(alias);
- return alias;
- }
- /**
- * d_find_any_alias - find any alias for a given inode
- * @inode: inode to find an alias for
- *
- * If any aliases exist for the given inode, take and return a
- * reference for one of them. If no aliases exist, return %NULL.
- */
- struct dentry *d_find_any_alias(struct inode *inode)
- {
- struct dentry *de;
- spin_lock(&inode->i_lock);
- de = __d_find_any_alias(inode);
- spin_unlock(&inode->i_lock);
- return de;
- }
- EXPORT_SYMBOL(d_find_any_alias);
- /**
- * d_obtain_alias - find or allocate a dentry for a given inode
- * @inode: inode to allocate the dentry for
- *
- * Obtain a dentry for an inode resulting from NFS filehandle conversion or
- * similar open by handle operations. The returned dentry may be anonymous,
- * or may have a full name (if the inode was already in the cache).
- *
- * When called on a directory inode, we must ensure that the inode only ever
- * has one dentry. If a dentry is found, that is returned instead of
- * allocating a new one.
- *
- * On successful return, the reference to the inode has been transferred
- * to the dentry. In case of an error the reference on the inode is released.
- * To make it easier to use in export operations a %NULL or IS_ERR inode may
- * be passed in and will be the error will be propagate to the return value,
- * with a %NULL @inode replaced by ERR_PTR(-ESTALE).
- */
- struct dentry *d_obtain_alias(struct inode *inode)
- {
- static const struct qstr anonstring = { .name = "/", .len = 1 };
- struct dentry *tmp;
- struct dentry *res;
- if (!inode)
- return ERR_PTR(-ESTALE);
- if (IS_ERR(inode))
- return ERR_CAST(inode);
- res = d_find_any_alias(inode);
- if (res)
- goto out_iput;
- tmp = __d_alloc(inode->i_sb, &anonstring);
- if (!tmp) {
- res = ERR_PTR(-ENOMEM);
- goto out_iput;
- }
- spin_lock(&inode->i_lock);
- res = __d_find_any_alias(inode);
- if (res) {
- spin_unlock(&inode->i_lock);
- dput(tmp);
- goto out_iput;
- }
- /* attach a disconnected dentry */
- spin_lock(&tmp->d_lock);
- tmp->d_inode = inode;
- tmp->d_flags |= DCACHE_DISCONNECTED;
- list_add(&tmp->d_u.d_alias, &inode->i_dentry);
- hlist_bl_lock(&tmp->d_sb->s_anon);
- hlist_bl_add_head(&tmp->d_hash, &tmp->d_sb->s_anon);
- hlist_bl_unlock(&tmp->d_sb->s_anon);
- spin_unlock(&tmp->d_lock);
- spin_unlock(&inode->i_lock);
- security_d_instantiate(tmp, inode);
- return tmp;
- out_iput:
- if (res && !IS_ERR(res))
- security_d_instantiate(res, inode);
- iput(inode);
- return res;
- }
- EXPORT_SYMBOL(d_obtain_alias);
- /**
- * d_splice_alias - splice a disconnected dentry into the tree if one exists
- * @inode: the inode which may have a disconnected dentry
- * @dentry: a negative dentry which we want to point to the inode.
- *
- * If inode is a directory and has a 'disconnected' dentry (i.e. IS_ROOT and
- * DCACHE_DISCONNECTED), then d_move that in place of the given dentry
- * and return it, else simply d_add the inode to the dentry and return NULL.
- *
- * This is needed in the lookup routine of any filesystem that is exportable
- * (via knfsd) so that we can build dcache paths to directories effectively.
- *
- * If a dentry was found and moved, then it is returned. Otherwise NULL
- * is returned. This matches the expected return value of ->lookup.
- *
- */
- struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry)
- {
- struct dentry *new = NULL;
- if (IS_ERR(inode))
- return ERR_CAST(inode);
- if (inode && S_ISDIR(inode->i_mode)) {
- spin_lock(&inode->i_lock);
- new = __d_find_any_alias(inode);
- if (new) {
- spin_unlock(&inode->i_lock);
- security_d_instantiate(new, inode);
- d_move(new, dentry);
- iput(inode);
- } else {
- /* already taking inode->i_lock, so d_add() by hand */
- __d_instantiate(dentry, inode);
- spin_unlock(&inode->i_lock);
- security_d_instantiate(dentry, inode);
- d_rehash(dentry);
- }
- } else
- d_add(dentry, inode);
- return new;
- }
- EXPORT_SYMBOL(d_splice_alias);
- /**
- * d_add_ci - lookup or allocate new dentry with case-exact name
- * @inode: the inode case-insensitive lookup has found
- * @dentry: the negative dentry that was passed to the parent's lookup func
- * @name: the case-exact name to be associated with the returned dentry
- *
- * This is to avoid filling the dcache with case-insensitive names to the
- * same inode, only the actual correct case is stored in the dcache for
- * case-insensitive filesystems.
- *
- * For a case-insensitive lookup match and if the the case-exact dentry
- * already exists in in the dcache, use it and return it.
- *
- * If no entry exists with the exact case name, allocate new dentry with
- * the exact case, and return the spliced entry.
- */
- struct dentry *d_add_ci(struct dentry *dentry, struct inode *inode,
- struct qstr *name)
- {
- int error;
- struct dentry *found;
- struct dentry *new;
- /*
- * First check if a dentry matching the name already exists,
- * if not go ahead and create it now.
- */
- found = d_hash_and_lookup(dentry->d_parent, name);
- if (!found) {
- new = d_alloc(dentry->d_parent, name);
- if (!new) {
- error = -ENOMEM;
- goto err_out;
- }
- found = d_splice_alias(inode, new);
- if (found) {
- dput(new);
- return found;
- }
- return new;
- }
- /*
- * If a matching dentry exists, and it's not negative use it.
- *
- * Decrement the reference count to balance the iget() done
- * earlier on.
- */
- if (found->d_inode) {
- if (unlikely(found->d_inode != inode)) {
- /* This can't happen because bad inodes are unhashed. */
- BUG_ON(!is_bad_inode(inode));
- BUG_ON(!is_bad_inode(found->d_inode));
- }
- iput(inode);
- return found;
- }
- /*
- * We are going to instantiate this dentry, unhash it and clear the
- * lookup flag so we can do that.
- */
- if (unlikely(d_need_lookup(found)))
- d_clear_need_lookup(found);
- /*
- * Negative dentry: instantiate it unless the inode is a directory and
- * already has a dentry.
- */
- new = d_splice_alias(inode, found);
- if (new) {
- dput(found);
- found = new;
- }
- return found;
- err_out:
- iput(inode);
- return ERR_PTR(error);
- }
- EXPORT_SYMBOL(d_add_ci);
- /*
- * Do the slow-case of the dentry name compare.
- *
- * Unlike the dentry_cmp() function, we need to atomically
- * load the name, length and inode information, so that the
- * filesystem can rely on them, and can use the 'name' and
- * 'len' information without worrying about walking off the
- * end of memory etc.
- *
- * Thus the read_seqcount_retry() and the "duplicate" info
- * in arguments (the low-level filesystem should not look
- * at the dentry inode or name contents directly, since
- * rename can change them while we're in RCU mode).
- */
- enum slow_d_compare {
- D_COMP_OK,
- D_COMP_NOMATCH,
- D_COMP_SEQRETRY,
- };
- static noinline enum slow_d_compare slow_dentry_cmp(
- const struct dentry *parent,
- struct inode *inode,
- struct dentry *dentry,
- unsigned int seq,
- const struct qstr *name)
- {
- int tlen = dentry->d_name.len;
- const char *tname = dentry->d_name.name;
- struct inode *i = dentry->d_inode;
- if (read_seqcount_retry(&dentry->d_seq, seq)) {
- cpu_relax();
- return D_COMP_SEQRETRY;
- }
- if (parent->d_op->d_compare(parent, inode,
- dentry, i,
- tlen, tname, name))
- return D_COMP_NOMATCH;
- return D_COMP_OK;
- }
- /**
- * __d_lookup_rcu - search for a dentry (racy, store-free)
- * @parent: parent dentry
- * @name: qstr of name we wish to find
- * @seqp: returns d_seq value at the point where the dentry was found
- * @inode: returns dentry->d_inode when the inode was found valid.
- * Returns: dentry, or NULL
- *
- * __d_lookup_rcu is the dcache lookup function for rcu-walk name
- * resolution (store-free path walking) design described in
- * Documentation/filesystems/path-lookup.txt.
- *
- * This is not to be used outside core vfs.
- *
- * __d_lookup_rcu must only be used in rcu-walk mode, ie. with vfsmount lock
- * held, and rcu_read_lock held. The returned dentry must not be stored into
- * without taking d_lock and checking d_seq sequence count against @seq
- * returned here.
- *
- * A refcount may be taken on the found dentry with the __d_rcu_to_refcount
- * function.
- *
- * Alternatively, __d_lookup_rcu may be called again to look up the child of
- * the returned dentry, so long as its parent's seqlock is checked after the
- * child is looked up. Thus, an interlocking stepping of sequence lock checks
- * is formed, giving integrity down the path walk.
- *
- * NOTE! The caller *has* to check the resulting dentry against the sequence
- * number we've returned before using any of the resulting dentry state!
- */
- struct dentry *__d_lookup_rcu(const struct dentry *parent,
- const struct qstr *name,
- unsigned *seqp, struct inode *inode)
- {
- u64 hashlen = name->hash_len;
- const unsigned char *str = name->name;
- struct hlist_bl_head *b = d_hash(parent, hashlen_hash(hashlen));
- struct hlist_bl_node *node;
- struct dentry *dentry;
- /*
- * Note: There is significant duplication with __d_lookup_rcu which is
- * required to prevent single threaded performance regressions
- * especially on architectures where smp_rmb (in seqcounts) are costly.
- * Keep the two functions in sync.
- */
- /*
- * The hash list is protected using RCU.
- *
- * Carefully use d_seq when comparing a candidate dentry, to avoid
- * races with d_move().
- *
- * It is possible that concurrent renames can mess up our list
- * walk here and result in missing our dentry, resulting in the
- * false-negative result. d_lookup() protects against concurrent
- * renames using rename_lock seqlock.
- *
- * See Documentation/filesystems/path-lookup.txt for more details.
- */
- hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) {
- unsigned seq;
- seqretry:
- /*
- * The dentry sequence count protects us from concurrent
- * renames, and thus protects inode, parent and name fields.
- *
- * The caller must perform a seqcount check in order
- * to do anything useful with the returned dentry,
- * including using the 'd_inode' pointer.
- *
- * NOTE! We do a "raw" seqcount_begin here. That means that
- * we don't wait for the sequence count to stabilize if it
- * is in the middle of a sequence change. If we do the slow
- * dentry compare, we will do seqretries until it is stable,
- * and if we end up with a successful lookup, we actually
- * want to exit RCU lookup anyway.
- */
- seq = raw_seqcount_begin(&dentry->d_seq);
- if (dentry->d_parent != parent)
- continue;
- if (d_unhashed(dentry))
- continue;
- *seqp = seq;
- if (unlikely(parent->d_flags & DCACHE_OP_COMPARE)) {
- if (dentry->d_name.hash != hashlen_hash(hashlen))
- continue;
- switch (slow_dentry_cmp(parent, inode, dentry, seq, name)) {
- case D_COMP_OK:
- return dentry;
- case D_COMP_NOMATCH:
- continue;
- default:
- goto seqretry;
- }
- }
- if (dentry->d_name.hash_len != hashlen)
- continue;
- if (!dentry_cmp(dentry, str, hashlen_len(hashlen)))
- return dentry;
- }
- return NULL;
- }
- /**
- * d_lookup - search for a dentry
- * @parent: parent dentry
- * @name: qstr of name we wish to find
- * Returns: dentry, or NULL
- *
- * d_lookup searches the children of the parent dentry for the name in
- * question. If the dentry is found its reference count is incremented and the
- * dentry is returned. The caller must use dput to free the entry when it has
- * finished using it. %NULL is returned if the dentry does not exist.
- */
- struct dentry *d_lookup(const struct dentry *parent, const struct qstr *name)
- {
- struct dentry *dentry;
- unsigned seq;
- do {
- seq = read_seqbegin(&rename_lock);
- dentry = __d_lookup(parent, name);
- if (dentry)
- break;
- } while (read_seqretry(&rename_lock, seq));
- return dentry;
- }
- EXPORT_SYMBOL(d_lookup);
- /**
- * __d_lookup - search for a dentry (racy)
- * @parent: parent dentry
- * @name: qstr of name we wish to find
- * Returns: dentry, or NULL
- *
- * __d_lookup is like d_lookup, however it may (rarely) return a
- * false-negative result due to unrelated rename activity.
- *
- * __d_lookup is slightly faster by avoiding rename_lock read seqlock,
- * however it must be used carefully, eg. with a following d_lookup in
- * the case of failure.
- *
- * __d_lookup callers must be commented.
- */
- struct dentry *__d_lookup(const struct dentry *parent, const struct qstr *name)
- {
- unsigned int len = name->len;
- unsigned int hash = name->hash;
- const unsigned char *str = name->name;
- struct hlist_bl_head *b = d_hash(parent, hash);
- struct hlist_bl_node *node;
- struct dentry *found = NULL;
- struct dentry *dentry;
- /*
- * Note: There is significant duplication with __d_lookup_rcu which is
- * required to prevent single threaded performance regressions
- * especially on architectures where smp_rmb (in seqcounts) are costly.
- * Keep the two functions in sync.
- */
- /*
- * The hash list is protected using RCU.
- *
- * Take d_lock when comparing a candidate dentry, to avoid races
- * with d_move().
- *
- * It is possible that concurrent renames can mess up our list
- * walk here and result in missing our dentry, resulting in the
- * false-negative result. d_lookup() protects against concurrent
- * renames using rename_lock seqlock.
- *
- * See Documentation/filesystems/path-lookup.txt for more details.
- */
- rcu_read_lock();
-
- hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) {
- if (dentry->d_name.hash != hash)
- continue;
- spin_lock(&dentry->d_lock);
- if (dentry->d_parent != parent)
- goto next;
- if (d_unhashed(dentry))
- goto next;
- /*
- * It is safe to compare names since d_move() cannot
- * change the qstr (protected by d_lock).
- */
- if (parent->d_flags & DCACHE_OP_COMPARE) {
- int tlen = dentry->d_name.len;
- const char *tname = dentry->d_name.name;
- if (parent->d_op->d_compare(parent, parent->d_inode,
- dentry, dentry->d_inode,
- tlen, tname, name))
- goto next;
- } else {
- if (dentry->d_name.len != len)
- goto next;
- if (dentry_cmp(dentry, str, len))
- goto next;
- }
- dentry->d_count++;
- found = dentry;
- spin_unlock(&dentry->d_lock);
- break;
- next:
- spin_unlock(&dentry->d_lock);
- }
- rcu_read_unlock();
- return found;
- }
- /**
- * d_hash_and_lookup - hash the qstr then search for a dentry
- * @dir: Directory to search in
- * @name: qstr of name we wish to find
- *
- * On hash failure or on lookup failure NULL is returned.
- */
- struct dentry *d_hash_and_lookup(struct dentry *dir, struct qstr *name)
- {
- struct dentry *dentry = NULL;
- /*
- * Check for a fs-specific hash function. Note that we must
- * calculate the standard hash first, as the d_op->d_hash()
- * routine may choose to leave the hash value unchanged.
- */
- name->hash = full_name_hash(name->name, name->len);
- if (dir->d_flags & DCACHE_OP_HASH) {
- if (dir->d_op->d_hash(dir, dir->d_inode, name) < 0)
- goto out;
- }
- dentry = d_lookup(dir, name);
- out:
- return dentry;
- }
- /**
- * d_validate - verify dentry provided from insecure source (deprecated)
- * @dentry: The dentry alleged to be valid child of @dparent
- * @dparent: The parent dentry (known to be valid)
- *
- * An insecure source has sent us a dentry, here we verify it and dget() it.
- * This is used by ncpfs in its readdir implementation.
- * Zero is returned in the dentry is invalid.
- *
- * This function is slow for big directories, and deprecated, do not use it.
- */
- int d_validate(struct dentry *dentry, struct dentry *dparent)
- {
- struct dentry *child;
- spin_lock(&dparent->d_lock);
- list_for_each_entry(child, &dparent->d_subdirs, d_child) {
- if (dentry == child) {
- spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
- __dget_dlock(dentry);
- spin_unlock(&dentry->d_lock);
- spin_unlock(&dparent->d_lock);
- return 1;
- }
- }
- spin_unlock(&dparent->d_lock);
- return 0;
- }
- EXPORT_SYMBOL(d_validate);
- /*
- * When a file is deleted, we have two options:
- * - turn this dentry into a negative dentry
- * - unhash this dentry and free it.
- *
- * Usually, we want to just turn this into
- * a negative dentry, but if anybody else is
- * currently using the dentry or the inode
- * we can't do that and we fall back on removing
- * it from the hash queues and waiting for
- * it to be deleted later when it has no users
- */
-
- /**
- * d_delete - delete a dentry
- * @dentry: The dentry to delete
- *
- * Turn the dentry into a negative dentry if possible, otherwise
- * remove it from the hash queues so it can be deleted later
- */
-
- void d_delete(struct dentry * dentry)
- {
- struct inode *inode;
- int isdir = 0;
- /*
- * Are we the only user?
- */
- again:
- spin_lock(&dentry->d_lock);
- inode = dentry->d_inode;
- isdir = S_ISDIR(inode->i_mode);
- if (dentry->d_count == 1) {
- if (!spin_trylock(&inode->i_lock)) {
- spin_unlock(&dentry->d_lock);
- cpu_relax();
- goto again;
- }
- dentry->d_flags &= ~DCACHE_CANT_MOUNT;
- dentry_unlink_inode(dentry);
- fsnotify_nameremove(dentry, isdir);
- return;
- }
- if (!d_unhashed(dentry))
- __d_drop(dentry);
- spin_unlock(&dentry->d_lock);
- fsnotify_nameremove(dentry, isdir);
- }
- EXPORT_SYMBOL(d_delete);
- static void __d_rehash(struct dentry * entry, struct hlist_bl_head *b)
- {
- BUG_ON(!d_unhashed(entry));
- hlist_bl_lock(b);
- entry->d_flags |= DCACHE_RCUACCESS;
- hlist_bl_add_head_rcu(&entry->d_hash, b);
- hlist_bl_unlock(b);
- }
- static void _d_rehash(struct dentry * entry)
- {
- __d_rehash(entry, d_hash(entry->d_parent, entry->d_name.hash));
- }
- /**
- * d_rehash - add an entry back to the hash
- * @entry: dentry to add to the hash
- *
- * Adds a dentry to the hash according to its name.
- */
-
- void d_rehash(struct dentry * entry)
- {
- spin_lock(&entry->d_lock);
- _d_rehash(entry);
- spin_unlock(&entry->d_lock);
- }
- EXPORT_SYMBOL(d_rehash);
- /**
- * dentry_update_name_case - update case insensitive dentry with a new name
- * @dentry: dentry to be updated
- * @name: new name
- *
- * Update a case insensitive dentry with new case of name.
- *
- * dentry must have been returned by d_lookup with name @name. Old and new
- * name lengths must match (ie. no d_compare which allows mismatched name
- * lengths).
- *
- * Parent inode i_mutex must be held over d_lookup and into this call (to
- * keep renames and concurrent inserts, and readdir(2) away).
- */
- void dentry_update_name_case(struct dentry *dentry, struct qstr *name)
- {
- BUG_ON(!mutex_is_locked(&dentry->d_parent->d_inode->i_mutex));
- BUG_ON(dentry->d_name.len != name->len); /* d_lookup gives this */
- spin_lock(&dentry->d_lock);
- write_seqcount_begin(&dentry->d_seq);
- memcpy((unsigned char *)dentry->d_name.name, name->name, name->len);
- write_seqcount_end(&dentry->d_seq);
- spin_unlock(&dentry->d_lock);
- }
- EXPORT_SYMBOL(dentry_update_name_case);
- static void switch_names(struct dentry *dentry, struct dentry *target)
- {
- if (unlikely(dname_external(target))) {
- if (unlikely(dname_external(dentry))) {
- /*
- * Both external: swap the pointers
- */
- swap(target->d_name.name, dentry->d_name.name);
- } else {
- /*
- * dentry:internal, target:external. Steal target's
- * storage and make target internal.
- */
- memcpy(target->d_iname, dentry->d_name.name,
- dentry->d_name.len + 1);
- dentry->d_name.name = target->d_name.name;
- target->d_name.name = target->d_iname;
- }
- } else {
- if (unlikely(dname_external(dentry))) {
- /*
- * dentry:external, target:internal. Give dentry's
- * storage to target and make dentry internal
- */
- memcpy(dentry->d_iname, target->d_name.name,
- target->d_name.len + 1);
- target->d_name.name = dentry->d_name.name;
- dentry->d_name.name = dentry->d_iname;
- } else {
- /*
- * Both are internal. Just copy target to dentry
- */
- memcpy(dentry->d_iname, target->d_name.name,
- target->d_name.len + 1);
- dentry->d_name.len = target->d_name.len;
- return;
- }
- }
- swap(dentry->d_name.len, target->d_name.len);
- }
- static void copy_name(struct dentry *dentry, struct dentry *target)
- {
- struct external_name *old_name = NULL;
- if (unlikely(dname_external(dentry)))
- old_name = external_name(dentry);
- if (unlikely(dname_external(target))) {
- atomic_inc(&external_name(target)->u.count);
- dentry->d_name = target->d_name;
- } else {
- memcpy(dentry->d_iname, target->d_name.name,
- target->d_name.len + 1);
- dentry->d_name.name = dentry->d_iname;
- dentry->d_name.len = target->d_name.len;
- }
- if (old_name && likely(atomic_dec_and_test(&old_name->u.count)))
- kfree_rcu(old_name, u.head);
- }
- static void dentry_lock_for_move(struct dentry *dentry, struct dentry *target)
- {
- /*
- * XXXX: do we really need to take target->d_lock?
- */
- if (IS_ROOT(dentry) || dentry->d_parent == target->d_parent)
- spin_lock(&target->d_parent->d_lock);
- else {
- if (d_ancestor(dentry->d_parent, target->d_parent)) {
- spin_lock(&dentry->d_parent->d_lock);
- spin_lock_nested(&target->d_parent->d_lock,
- DENTRY_D_LOCK_NESTED);
- } else {
- spin_lock(&target->d_parent->d_lock);
- spin_lock_nested(&dentry->d_parent->d_lock,
- DENTRY_D_LOCK_NESTED);
- }
- }
- if (target < dentry) {
- spin_lock_nested(&target->d_lock, 2);
- spin_lock_nested(&dentry->d_lock, 3);
- } else {
- spin_lock_nested(&dentry->d_lock, 2);
- spin_lock_nested(&target->d_lock, 3);
- }
- }
- static void dentry_unlock_parents_for_move(struct dentry *dentry,
- struct dentry *target)
- {
- if (target->d_parent != dentry->d_parent)
- spin_unlock(&dentry->d_parent->d_lock);
- if (target->d_parent != target)
- spin_unlock(&target->d_parent->d_lock);
- }
- /*
- * When switching names, the actual string doesn't strictly have to
- * be preserved in the target - because we're dropping the target
- * anyway. As such, we can just do a simple memcpy() to copy over
- * the new name before we switch.
- *
- * Note that we have to be a lot more careful about getting the hash
- * switched - we have to switch the hash value properly even if it
- * then no longer matches the actual (corrupted) string of the target.
- * The hash value has to match the hash queue that the dentry is on..
- */
- /*
- * __d_move - move a dentry
- * @dentry: entry to move
- * @target: new dentry
- *
- * Update the dcache to reflect the move of a file name. Negative
- * dcache entries should not be moved in this way. Caller must hold
- * rename_lock, the i_mutex of the source and target directories,
- * and the sb->s_vfs_rename_mutex if they differ. See lock_rename().
- */
- static void __d_move(struct dentry * dentry, struct dentry * target)
- {
- if (!dentry->d_inode)
- printk(KERN_WARNING "VFS: moving negative dcache entry\n");
- BUG_ON(d_ancestor(dentry, target));
- BUG_ON(d_ancestor(target, dentry));
- dentry_lock_for_move(dentry, target);
- write_seqcount_begin(&dentry->d_seq);
- write_seqcount_begin(&target->d_seq);
- /* __d_drop does write_seqcount_barrier, but they're OK to nest. */
- /*
- * Move the dentry to the target hash queue. Don't bother checking
- * for the same hash queue because of how unlikely it is.
- */
- __d_drop(dentry);
- __d_rehash(dentry, d_hash(target->d_parent, target->d_name.hash));
- /* Unhash the target: dput() will then get rid of it */
- __d_drop(target);
- list_del(&dentry->d_child);
- list_del(&target->d_child);
- /* Switch the names.. */
- copy_name(dentry, target);
- swap(dentry->d_name.hash, target->d_name.hash);
- /* ... and switch the parents */
- if (IS_ROOT(dentry)) {
- dentry->d_parent = target->d_parent;
- target->d_parent = target;
- INIT_LIST_HEAD(&target->d_child);
- } else {
- swap(dentry->d_parent, target->d_parent);
- /* And add them back to the (new) parent lists */
- list_add(&target->d_child, &target->d_parent->d_subdirs);
- }
- list_add(&dentry->d_child, &dentry->d_parent->d_subdirs);
- write_seqcount_end(&target->d_seq);
- write_seqcount_end(&dentry->d_seq);
- dentry_unlock_parents_for_move(dentry, target);
- spin_unlock(&target->d_lock);
- fsnotify_d_move(dentry);
- spin_unlock(&dentry->d_lock);
- }
- /*
- * d_move - move a dentry
- * @dentry: entry to move
- * @target: new dentry
- *
- * Update the dcache to reflect the move of a file name. Negative
- * dcache entries should not be moved in this way. See the locking
- * requirements for __d_move.
- */
- void d_move(struct dentry *dentry, struct dentry *target)
- {
- write_seqlock(&rename_lock);
- __d_move(dentry, target);
- write_sequnlock(&rename_lock);
- }
- EXPORT_SYMBOL(d_move);
- /**
- * d_ancestor - search for an ancestor
- * @p1: ancestor dentry
- * @p2: child dentry
- *
- * Returns the ancestor dentry of p2 which is a child of p1, if p1 is
- * an ancestor of p2, else NULL.
- */
- struct dentry *d_ancestor(struct dentry *p1, struct dentry *p2)
- {
- struct dentry *p;
- for (p = p2; !IS_ROOT(p); p = p->d_parent) {
- if (p->d_parent == p1)
- return p;
- }
- return NULL;
- }
- /*
- * This helper attempts to cope with remotely renamed directories
- *
- * It assumes that the caller is already holding
- * dentry->d_parent->d_inode->i_mutex, inode->i_lock and rename_lock
- *
- * Note: If ever the locking in lock_rename() changes, then please
- * remember to update this too...
- */
- static struct dentry *__d_unalias(struct inode *inode,
- struct dentry *dentry, struct dentry *alias)
- {
- struct mutex *m1 = NULL, *m2 = NULL;
- struct dentry *ret = ERR_PTR(-EBUSY);
- /* If alias and dentry share a parent, then no extra locks required */
- if (alias->d_parent == dentry->d_parent)
- goto out_unalias;
- /* See lock_rename() */
- if (!mutex_trylock(&dentry->d_sb->s_vfs_rename_mutex))
- goto out_err;
- m1 = &dentry->d_sb->s_vfs_rename_mutex;
- if (!mutex_trylock(&alias->d_parent->d_inode->i_mutex))
- goto out_err;
- m2 = &alias->d_parent->d_inode->i_mutex;
- out_unalias:
- if (likely(!d_mountpoint(alias))) {
- __d_move(alias, dentry);
- ret = alias;
- }
- out_err:
- spin_unlock(&inode->i_lock);
- if (m2)
- mutex_unlock(m2);
- if (m1)
- mutex_unlock(m1);
- return ret;
- }
- /*
- * Prepare an anonymous dentry for life in the superblock's dentry tree as a
- * named dentry in place of the dentry to be replaced.
- * returns with anon->d_lock held!
- */
- static void __d_materialise_dentry(struct dentry *dentry, struct dentry *anon)
- {
- struct dentry *dparent, *aparent;
- dentry_lock_for_move(anon, dentry);
- write_seqcount_begin(&dentry->d_seq);
- write_seqcount_begin(&anon->d_seq);
- dparent = dentry->d_parent;
- aparent = anon->d_parent;
- switch_names(dentry, anon);
- swap(dentry->d_name.hash, anon->d_name.hash);
- dentry->d_parent = (aparent == anon) ? dentry : aparent;
- list_del(&dentry->d_child);
- if (!IS_ROOT(dentry))
- list_add(&dentry->d_child, &dentry->d_parent->d_subdirs);
- else
- INIT_LIST_HEAD(&dentry->d_child);
- anon->d_parent = (dparent == dentry) ? anon : dparent;
- list_del(&anon->d_child);
- if (!IS_ROOT(anon))
- list_add(&anon->d_child, &anon->d_parent->d_subdirs);
- else
- INIT_LIST_HEAD(&anon->d_child);
- write_seqcount_end(&dentry->d_seq);
- write_seqcount_end(&anon->d_seq);
- dentry_unlock_parents_for_move(anon, dentry);
- spin_unlock(&dentry->d_lock);
- /* anon->d_lock still locked, returns locked */
- anon->d_flags &= ~DCACHE_DISCONNECTED;
- }
- /**
- * d_materialise_unique - introduce an inode into the tree
- * @dentry: candidate dentry
- * @inode: inode to bind to the dentry, to which aliases may be attached
- *
- * Introduces an dentry into the tree, substituting an extant disconnected
- * root directory alias in its place if there is one. Caller must hold the
- * i_mutex of the parent directory.
- */
- struct dentry *d_materialise_unique(struct dentry *dentry, struct inode *inode)
- {
- struct dentry *actual;
- BUG_ON(!d_unhashed(dentry));
- if (!inode) {
- actual = dentry;
- __d_instantiate(dentry, NULL);
- d_rehash(actual);
- goto out_nolock;
- }
- spin_lock(&inode->i_lock);
- if (S_ISDIR(inode->i_mode)) {
- struct dentry *alias;
- /* Does an aliased dentry already exist? */
- alias = __d_find_alias(inode);
- if (alias) {
- actual = alias;
- write_seqlock(&rename_lock);
- if (d_ancestor(alias, dentry)) {
- /* Check for loops */
- actual = ERR_PTR(-ELOOP);
- spin_unlock(&inode->i_lock);
- } else if (IS_ROOT(alias)) {
- /* Is this an anonymous mountpoint that we
- * could splice into our tree? */
- __d_materialise_dentry(dentry, alias);
- write_sequnlock(&rename_lock);
- __d_drop(alias);
- goto found;
- } else {
- /* Nope, but we must(!) avoid directory
- * aliasing. This drops inode->i_lock */
- actual = __d_unalias(inode, dentry, alias);
- }
- write_sequnlock(&rename_lock);
- if (IS_ERR(actual)) {
- if (PTR_ERR(actual) == -ELOOP)
- pr_warn_ratelimited(
- "VFS: Lookup of '%s' in %s %s"
- " would have caused loop\n",
- dentry->d_name.name,
- inode->i_sb->s_type->name,
- inode->i_sb->s_id);
- dput(alias);
- }
- goto out_nolock;
- }
- }
- /* Add a unique reference */
- actual = __d_instantiate_unique(dentry, inode);
- if (!actual)
- actual = dentry;
- else
- BUG_ON(!d_unhashed(actual));
- spin_lock(&actual->d_lock);
- found:
- _d_rehash(actual);
- spin_unlock(&actual->d_lock);
- spin_unlock(&inode->i_lock);
- out_nolock:
- if (actual == dentry) {
- security_d_instantiate(dentry, inode);
- return NULL;
- }
- iput(inode);
- return actual;
- }
- EXPORT_SYMBOL_GPL(d_materialise_unique);
- static int prepend(char **buffer, int *buflen, const char *str, int namelen)
- {
- *buflen -= namelen;
- if (*buflen < 0)
- return -ENAMETOOLONG;
- *buffer -= namelen;
- memcpy(*buffer, str, namelen);
- return 0;
- }
- static int prepend_name(char **buffer, int *buflen, struct qstr *name)
- {
- return prepend(buffer, buflen, name->name, name->len);
- }
- /**
- * prepend_path - Prepend path string to a buffer
- * @path: the dentry/vfsmount to report
- * @root: root vfsmnt/dentry
- * @buffer: pointer to the end of the buffer
- * @buflen: pointer to buffer length
- *
- * Caller holds the rename_lock.
- */
- static int prepend_path(const struct path *path,
- const struct path *root,
- char **buffer, int *buflen)
- {
- struct dentry *dentry = path->dentry;
- struct vfsmount *vfsmnt = path->mnt;
- struct mount *mnt = real_mount(vfsmnt);
- char *orig_buffer = *buffer;
- int orig_len = *buflen;
- bool slash = false;
- int error = 0;
- while (dentry != root->dentry || vfsmnt != root->mnt) {
- struct dentry * parent;
- if (dentry == vfsmnt->mnt_root || IS_ROOT(dentry)) {
- /* Escaped? */
- if (dentry != vfsmnt->mnt_root) {
- *buffer = orig_buffer;
- *buflen = orig_len;
- slash = false;
- error = 3;
- goto global_root;
- }
- /* Global root? */
- if (!mnt_has_parent(mnt))
- goto global_root;
- dentry = mnt->mnt_mountpoint;
- mnt = mnt->mnt_parent;
- vfsmnt = &mnt->mnt;
- continue;
- }
- parent = dentry->d_parent;
- prefetch(parent);
- spin_lock(&dentry->d_lock);
- error = prepend_name(buffer, buflen, &dentry->d_name);
- spin_unlock(&dentry->d_lock);
- if (!error)
- error = prepend(buffer, buflen, "/", 1);
- if (error)
- break;
- slash = true;
- dentry = parent;
- }
- if (!error && !slash)
- error = prepend(buffer, buflen, "/", 1);
- return error;
- global_root:
- /*
- * Filesystems needing to implement special "root names"
- * should do so with ->d_dname()
- */
- if (IS_ROOT(dentry) &&
- (dentry->d_name.len != 1 || dentry->d_name.name[0] != '/')) {
- WARN(1, "Root dentry has weird name <%.*s>\n",
- (int) dentry->d_name.len, dentry->d_name.name);
- }
- if (!slash)
- error = prepend(buffer, buflen, "/", 1);
- if (!error)
- error = is_mounted(vfsmnt) ? 1 : 2;
- return error;
- }
- /**
- * __d_path - return the path of a dentry
- * @path: the dentry/vfsmount to report
- * @root: root vfsmnt/dentry
- * @buf: buffer to return value in
- * @buflen: buffer length
- *
- * Convert a dentry into an ASCII path name.
- *
- * Returns a pointer into the buffer or an error code if the
- * path was too long.
- *
- * "buflen" should be positive.
- *
- * If the path is not reachable from the supplied root, return %NULL.
- */
- char *__d_path(const struct path *path,
- const struct path *root,
- char *buf, int buflen)
- {
- char *res = buf + buflen;
- int error;
- prepend(&res, &buflen, "\0", 1);
- br_read_lock(&vfsmount_lock);
- write_seqlock(&rename_lock);
- error = prepend_path(path, root, &res, &buflen);
- write_sequnlock(&rename_lock);
- br_read_unlock(&vfsmount_lock);
- if (error < 0)
- return ERR_PTR(error);
- if (error > 0)
- return NULL;
- return res;
- }
- char *d_absolute_path(const struct path *path,
- char *buf, int buflen)
- {
- struct path root = {};
- char *res = buf + buflen;
- int error;
- prepend(&res, &buflen, "\0", 1);
- br_read_lock(&vfsmount_lock);
- write_seqlock(&rename_lock);
- error = prepend_path(path, &root, &res, &buflen);
- write_sequnlock(&rename_lock);
- br_read_unlock(&vfsmount_lock);
- if (error > 1)
- error = -EINVAL;
- if (error < 0)
- return ERR_PTR(error);
- return res;
- }
- /*
- * same as __d_path but appends "(deleted)" for unlinked files.
- */
- static int path_with_deleted(const struct path *path,
- const struct path *root,
- char **buf, int *buflen)
- {
- prepend(buf, buflen, "\0", 1);
- if (d_unlinked(path->dentry)) {
- int error = prepend(buf, buflen, " (deleted)", 10);
- if (error)
- return error;
- }
- return prepend_path(path, root, buf, buflen);
- }
- static int prepend_unreachable(char **buffer, int *buflen)
- {
- return prepend(buffer, buflen, "(unreachable)", 13);
- }
- /**
- * d_path - return the path of a dentry
- * @path: path to report
- * @buf: buffer to return value in
- * @buflen: buffer length
- *
- * Convert a dentry into an ASCII path name. If the entry has been deleted
- * the string " (deleted)" is appended. Note that this is ambiguous.
- *
- * Returns a pointer into the buffer or an error code if the path was
- * too long. Note: Callers should use the returned pointer, not the passed
- * in buffer, to use the name! The implementation often starts at an offset
- * into the buffer, and may leave 0 bytes at the start.
- *
- * "buflen" should be positive.
- */
- char *d_path(const struct path *path, char *buf, int buflen)
- {
- char *res = buf + buflen;
- struct path root;
- int error;
- /*
- * We have various synthetic filesystems that never get mounted. On
- * these filesystems dentries are never used for lookup purposes, and
- * thus don't need to be hashed. They also don't need a name until a
- * user wants to identify the object in /proc/pid/fd/. The little hack
- * below allows us to generate a name for these objects on demand:
- */
- if (path->dentry->d_op && path->dentry->d_op->d_dname)
- return path->dentry->d_op->d_dname(path->dentry, buf, buflen);
- get_fs_root(current->fs, &root);
- br_read_lock(&vfsmount_lock);
- write_seqlock(&rename_lock);
- error = path_with_deleted(path, &root, &res, &buflen);
- write_sequnlock(&rename_lock);
- br_read_unlock(&vfsmount_lock);
- if (error < 0)
- res = ERR_PTR(error);
- path_put(&root);
- return res;
- }
- EXPORT_SYMBOL(d_path);
- /**
- * d_path_with_unreachable - return the path of a dentry
- * @path: path to report
- * @buf: buffer to return value in
- * @buflen: buffer length
- *
- * The difference from d_path() is that this prepends "(unreachable)"
- * to paths which are unreachable from the current process' root.
- */
- char *d_path_with_unreachable(const struct path *path, char *buf, int buflen)
- {
- char *res = buf + buflen;
- struct path root;
- int error;
- if (path->dentry->d_op && path->dentry->d_op->d_dname)
- return path->dentry->d_op->d_dname(path->dentry, buf, buflen);
- get_fs_root(current->fs, &root);
- write_seqlock(&rename_lock);
- error = path_with_deleted(path, &root, &res, &buflen);
- if (error > 0)
- error = prepend_unreachable(&res, &buflen);
- write_sequnlock(&rename_lock);
- path_put(&root);
- if (error)
- res = ERR_PTR(error);
- return res;
- }
- /*
- * Helper function for dentry_operations.d_dname() members
- */
- char *dynamic_dname(struct dentry *dentry, char *buffer, int buflen,
- const char *fmt, ...)
- {
- va_list args;
- char temp[64];
- int sz;
- va_start(args, fmt);
- sz = vsnprintf(temp, sizeof(temp), fmt, args) + 1;
- va_end(args);
- if (sz > sizeof(temp) || sz > buflen)
- return ERR_PTR(-ENAMETOOLONG);
- buffer += buflen - sz;
- return memcpy(buffer, temp, sz);
- }
- /*
- * Write full pathname from the root of the filesystem into the buffer.
- */
- static char *__dentry_path(struct dentry *dentry, char *buf, int buflen)
- {
- char *end = buf + buflen;
- char *retval;
- prepend(&end, &buflen, "\0", 1);
- if (buflen < 1)
- goto Elong;
- /* Get '/' right */
- retval = end-1;
- *retval = '/';
- while (!IS_ROOT(dentry)) {
- struct dentry *parent = dentry->d_parent;
- int error;
- prefetch(parent);
- spin_lock(&dentry->d_lock);
- error = prepend_name(&end, &buflen, &dentry->d_name);
- spin_unlock(&dentry->d_lock);
- if (error != 0 || prepend(&end, &buflen, "/", 1) != 0)
- goto Elong;
- retval = end;
- dentry = parent;
- }
- return retval;
- Elong:
- return ERR_PTR(-ENAMETOOLONG);
- }
- char *dentry_path_raw(struct dentry *dentry, char *buf, int buflen)
- {
- char *retval;
- write_seqlock(&rename_lock);
- retval = __dentry_path(dentry, buf, buflen);
- write_sequnlock(&rename_lock);
- return retval;
- }
- EXPORT_SYMBOL(dentry_path_raw);
- char *dentry_path(struct dentry *dentry, char *buf, int buflen)
- {
- char *p = NULL;
- char *retval;
- write_seqlock(&rename_lock);
- if (d_unlinked(dentry)) {
- p = buf + buflen;
- if (prepend(&p, &buflen, "//deleted", 10) != 0)
- goto Elong;
- buflen++;
- }
- retval = __dentry_path(dentry, buf, buflen);
- write_sequnlock(&rename_lock);
- if (!IS_ERR(retval) && p)
- *p = '/'; /* restore '/' overriden with '\0' */
- return retval;
- Elong:
- return ERR_PTR(-ENAMETOOLONG);
- }
- /*
- * NOTE! The user-level library version returns a
- * character pointer. The kernel system call just
- * returns the length of the buffer filled (which
- * includes the ending '\0' character), or a negative
- * error value. So libc would do something like
- *
- * char *getcwd(char * buf, size_t size)
- * {
- * int retval;
- *
- * retval = sys_getcwd(buf, size);
- * if (retval >= 0)
- * return buf;
- * errno = -retval;
- * return NULL;
- * }
- */
- SYSCALL_DEFINE2(getcwd, char __user *, buf, unsigned long, size)
- {
- int error;
- struct path pwd, root;
- char *page = (char *) __get_free_page(GFP_USER);
- if (!page)
- return -ENOMEM;
- get_fs_root_and_pwd(current->fs, &root, &pwd);
- error = -ENOENT;
- br_read_lock(&vfsmount_lock);
- write_seqlock(&rename_lock);
- if (!d_unlinked(pwd.dentry)) {
- unsigned long len;
- char *cwd = page + PAGE_SIZE;
- int buflen = PAGE_SIZE;
- prepend(&cwd, &buflen, "\0", 1);
- error = prepend_path(&pwd, &root, &cwd, &buflen);
- write_sequnlock(&rename_lock);
- br_read_unlock(&vfsmount_lock);
- if (error < 0)
- goto out;
- /* Unreachable from current root */
- if (error > 0) {
- error = prepend_unreachable(&cwd, &buflen);
- if (error)
- goto out;
- }
- error = -ERANGE;
- len = PAGE_SIZE + page - cwd;
- if (len <= size) {
- error = len;
- if (copy_to_user(buf, cwd, len))
- error = -EFAULT;
- }
- } else {
- write_sequnlock(&rename_lock);
- br_read_unlock(&vfsmount_lock);
- }
- out:
- path_put(&pwd);
- path_put(&root);
- free_page((unsigned long) page);
- return error;
- }
- /*
- * Test whether new_dentry is a subdirectory of old_dentry.
- *
- * Trivially implemented using the dcache structure
- */
- /**
- * is_subdir - is new dentry a subdirectory of old_dentry
- * @new_dentry: new dentry
- * @old_dentry: old dentry
- *
- * Returns 1 if new_dentry is a subdirectory of the parent (at any depth).
- * Returns 0 otherwise.
- * Caller must ensure that "new_dentry" is pinned before calling is_subdir()
- */
-
- int is_subdir(struct dentry *new_dentry, struct dentry *old_dentry)
- {
- int result;
- unsigned seq;
- if (new_dentry == old_dentry)
- return 1;
- do {
- /* for restarting inner loop in case of seq retry */
- seq = read_seqbegin(&rename_lock);
- /*
- * Need rcu_readlock to protect against the d_parent trashing
- * due to d_move
- */
- rcu_read_lock();
- if (d_ancestor(old_dentry, new_dentry))
- result = 1;
- else
- result = 0;
- rcu_read_unlock();
- } while (read_seqretry(&rename_lock, seq));
- return result;
- }
- void d_genocide(struct dentry *root)
- {
- struct dentry *this_parent;
- struct list_head *next;
- unsigned seq;
- int locked = 0;
- seq = read_seqbegin(&rename_lock);
- again:
- this_parent = root;
- spin_lock(&this_parent->d_lock);
- repeat:
- next = this_parent->d_subdirs.next;
- resume:
- while (next != &this_parent->d_subdirs) {
- struct list_head *tmp = next;
- struct dentry *dentry = list_entry(tmp, struct dentry, d_child);
- next = tmp->next;
- spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
- if (d_unhashed(dentry) || !dentry->d_inode) {
- spin_unlock(&dentry->d_lock);
- continue;
- }
- if (!list_empty(&dentry->d_subdirs)) {
- spin_unlock(&this_parent->d_lock);
- spin_release(&dentry->d_lock.dep_map, 1, _RET_IP_);
- this_parent = dentry;
- spin_acquire(&this_parent->d_lock.dep_map, 0, 1, _RET_IP_);
- goto repeat;
- }
- if (!(dentry->d_flags & DCACHE_GENOCIDE)) {
- dentry->d_flags |= DCACHE_GENOCIDE;
- dentry->d_count--;
- }
- spin_unlock(&dentry->d_lock);
- }
- rcu_read_lock();
- ascend:
- if (this_parent != root) {
- struct dentry *child = this_parent;
- if (!(this_parent->d_flags & DCACHE_GENOCIDE)) {
- this_parent->d_flags |= DCACHE_GENOCIDE;
- this_parent->d_count--;
- }
- this_parent = child->d_parent;
- spin_unlock(&child->d_lock);
- spin_lock(&this_parent->d_lock);
- /* might go back up the wrong parent if we have had a rename */
- if (!locked && read_seqretry(&rename_lock, seq))
- goto rename_retry;
- next = child->d_child.next;
- while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED)) {
- if (next == &this_parent->d_subdirs)
- goto ascend;
- child = list_entry(next, struct dentry, d_child);
- next = next->next;
- }
- rcu_read_unlock();
- goto resume;
- }
- if (!locked && read_seqretry(&rename_lock, seq))
- goto rename_retry;
- spin_unlock(&this_parent->d_lock);
- rcu_read_unlock();
- if (locked)
- write_sequnlock(&rename_lock);
- return;
- rename_retry:
- spin_unlock(&this_parent->d_lock);
- rcu_read_unlock();
- if (locked)
- goto again;
- locked = 1;
- write_seqlock(&rename_lock);
- goto again;
- }
- /**
- * find_inode_number - check for dentry with name
- * @dir: directory to check
- * @name: Name to find.
- *
- * Check whether a dentry already exists for the given name,
- * and return the inode number if it has an inode. Otherwise
- * 0 is returned.
- *
- * This routine is used to post-process directory listings for
- * filesystems using synthetic inode numbers, and is necessary
- * to keep getcwd() working.
- */
-
- ino_t find_inode_number(struct dentry *dir, struct qstr *name)
- {
- struct dentry * dentry;
- ino_t ino = 0;
- dentry = d_hash_and_lookup(dir, name);
- if (dentry) {
- if (dentry->d_inode)
- ino = dentry->d_inode->i_ino;
- dput(dentry);
- }
- return ino;
- }
- EXPORT_SYMBOL(find_inode_number);
- static __initdata unsigned long dhash_entries;
- static int __init set_dhash_entries(char *str)
- {
- if (!str)
- return 0;
- dhash_entries = simple_strtoul(str, &str, 0);
- return 1;
- }
- __setup("dhash_entries=", set_dhash_entries);
- static void __init dcache_init_early(void)
- {
- unsigned int loop;
- /* If hashes are distributed across NUMA nodes, defer
- * hash allocation until vmalloc space is available.
- */
- if (hashdist)
- return;
- dentry_hashtable =
- alloc_large_system_hash("Dentry cache",
- sizeof(struct hlist_bl_head),
- dhash_entries,
- 13,
- HASH_EARLY,
- &d_hash_shift,
- &d_hash_mask,
- 0,
- 0);
- for (loop = 0; loop < (1U << d_hash_shift); loop++)
- INIT_HLIST_BL_HEAD(dentry_hashtable + loop);
- }
- static void __init dcache_init(void)
- {
- unsigned int loop;
- /*
- * A constructor could be added for stable state like the lists,
- * but it is probably not worth it because of the cache nature
- * of the dcache.
- */
- dentry_cache = KMEM_CACHE(dentry,
- SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|SLAB_MEM_SPREAD);
- /* Hash may have been set up in dcache_init_early */
- if (!hashdist)
- return;
- dentry_hashtable =
- alloc_large_system_hash("Dentry cache",
- sizeof(struct hlist_bl_head),
- dhash_entries,
- 13,
- 0,
- &d_hash_shift,
- &d_hash_mask,
- 0,
- 0);
- for (loop = 0; loop < (1U << d_hash_shift); loop++)
- INIT_HLIST_BL_HEAD(dentry_hashtable + loop);
- }
- /* SLAB cache for __getname() consumers */
- struct kmem_cache *names_cachep __read_mostly;
- EXPORT_SYMBOL(names_cachep);
- EXPORT_SYMBOL(d_genocide);
- void __init vfs_caches_init_early(void)
- {
- dcache_init_early();
- inode_init_early();
- }
- void __init vfs_caches_init(unsigned long mempages)
- {
- unsigned long reserve;
- /* Base hash sizes on available memory, with a reserve equal to
- 150% of current kernel size */
- reserve = min((mempages - nr_free_pages()) * 3/2, mempages - 1);
- mempages -= reserve;
- names_cachep = kmem_cache_create("names_cache", PATH_MAX, 0,
- SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
- dcache_init();
- inode_init();
- files_init(mempages);
- mnt_init();
- bdev_cache_init();
- chrdev_init();
- }
|