| Author | Tokens | Token Proportion | Commits | Commit Proportion |
|---|---|---|---|---|
| Eric Whitney | 3705 | 39.39% | 7 | 7.29% |
| Zheng Liu | 3062 | 32.55% | 13 | 13.54% |
| Dmitriy Monakhov | 596 | 6.34% | 3 | 3.12% |
| zhangyi (F) | 578 | 6.15% | 10 | 10.42% |
| Baokun Li | 443 | 4.71% | 11 | 11.46% |
| Theodore Y. Ts'o | 370 | 3.93% | 15 | 15.62% |
| Jan Kara | 211 | 2.24% | 8 | 8.33% |
| Yang Guo | 94 | 1.00% | 1 | 1.04% |
| Dave Kleikamp | 82 | 0.87% | 1 | 1.04% |
| Harshad Shirwadkar | 67 | 0.71% | 1 | 1.04% |
| Qi Zheng | 45 | 0.48% | 1 | 1.04% |
| Lukas Czerner | 35 | 0.37% | 5 | 5.21% |
| Yan Zheng | 23 | 0.24% | 1 | 1.04% |
| Mingming Cao | 20 | 0.21% | 1 | 1.04% |
| David Chinner | 14 | 0.15% | 1 | 1.04% |
| Luis Henriques (SUSE) | 14 | 0.15% | 1 | 1.04% |
| Darrick J. Wong | 9 | 0.10% | 1 | 1.04% |
| Aneesh Kumar K.V | 7 | 0.07% | 1 | 1.04% |
| Eryu Guan | 5 | 0.05% | 1 | 1.04% |
| Akira Fujita | 5 | 0.05% | 1 | 1.04% |
| Ye Bin | 4 | 0.04% | 2 | 2.08% |
| Arnd Bergmann | 4 | 0.04% | 1 | 1.04% |
| Linus Torvalds | 3 | 0.03% | 1 | 1.04% |
| Alex Tomas | 2 | 0.02% | 1 | 1.04% |
| Christoph Hellwig | 2 | 0.02% | 2 | 2.08% |
| Jchao Sun | 2 | 0.02% | 1 | 1.04% |
| Jason Yan | 1 | 0.01% | 1 | 1.04% |
| Kalpak Shah | 1 | 0.01% | 1 | 1.04% |
| Greg Kroah-Hartman | 1 | 0.01% | 1 | 1.04% |
| Masahiro Yamada | 1 | 0.01% | 1 | 1.04% |
| Total | 9406 | 96 |
12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394959697989910010110210310410510610710810911011111211311411511611711811912012112212312412512612712812913013113213313413513613713813914014114214314414514614714814915015115215315415515615715815916016116216316416516616716816917017117217317417517617717817918018118218318418518618718818919019119219319419519619719819920020120220320420520620720820921021121221321421521621721821922022122222322422522622722822923023123223323423523623723823924024124224324424524624724824925025125225325425525625725825926026126226326426526626726826927027127227327427527627727827928028128228328428528628728828929029129229329429529629729829930030130230330430530630730830931031131231331431531631731831932032132232332432532632732832933033133233333433533633733833934034134234334434534634734834935035135235335435535635735835936036136236336436536636736836937037137237337437537637737837938038138238338438538638738838939039139239339439539639739839940040140240340440540640740840941041141241341441541641741841942042142242342442542642742842943043143243343443543643743843944044144244344444544644744844945045145245345445545645745845946046146246346446546646746846947047147247347447547647747847948048148248348448548648748848949049149249349449549649749849950050150250350450550650750850951051151251351451551651751851952052152252352452552652752852953053153253353453553653753853954054154254354454554654754854955055155255355455555655755855956056156256356456556656756856957057157257357457557657757857958058158258358458558658758858959059159259359459559659759859960060160260360460560660760860961061161261361461561661761861962062162262362462562662762862963063163263363463563663763863964064164264364464564664764864965065165265365465565665765865966066166266366466566666766866967067167267367467567667767867968068168268368468568668768868969069169269369469569669769869970070170270370470570670770870971071171271371471571671771871972072172272372472572672772872973073173273373473573673773873974074174274374474574674774874975075175275375475575675775875976076176276376476576676776876977077177277377477577677777877978078178278378478578678778878979079179279379479579679779879980080180280380480580680780880981081181281381481581681781881982082182282382482582682782882983083183283383483583683783883984084184284384484584684784884985085185285385485585685785885986086186286386486586686786886987087187287387487587687787887988088188288388488588688788888989089189289389489589689789889990090190290390490590690790890991091191291391491591691791891992092192292392492592692792892993093193293393493593693793893994094194294394494594694794894995095195295395495595695795895996096196296396496596696796896997097197297397497597697797897998098198298398498598698798898999099199299399499599699799899910001001100210031004100510061007100810091010101110121013101410151016101710181019102010211022102310241025102610271028102910301031103210331034103510361037103810391040104110421043104410451046104710481049105010511052105310541055105610571058105910601061106210631064106510661067106810691070107110721073107410751076107710781079108010811082108310841085108610871088108910901091109210931094109510961097109810991100110111021103110411051106110711081109111011111112111311141115111611171118111911201121112211231124112511261127112811291130113111321133113411351136113711381139114011411142114311441145114611471148114911501151115211531154115511561157115811591160116111621163116411651166116711681169117011711172117311741175117611771178117911801181118211831184118511861187118811891190119111921193119411951196119711981199120012011202120312041205120612071208120912101211121212131214121512161217121812191220122112221223122412251226122712281229123012311232123312341235123612371238123912401241124212431244124512461247124812491250125112521253125412551256125712581259126012611262126312641265126612671268126912701271127212731274127512761277127812791280128112821283128412851286128712881289129012911292129312941295129612971298129913001301130213031304130513061307130813091310131113121313131413151316131713181319132013211322132313241325132613271328132913301331133213331334133513361337133813391340134113421343134413451346134713481349135013511352135313541355135613571358135913601361136213631364136513661367136813691370137113721373137413751376137713781379138013811382138313841385138613871388138913901391139213931394139513961397139813991400140114021403140414051406140714081409141014111412141314141415141614171418141914201421142214231424142514261427142814291430143114321433143414351436143714381439144014411442144314441445144614471448144914501451145214531454145514561457145814591460146114621463146414651466146714681469147014711472147314741475147614771478147914801481148214831484148514861487148814891490149114921493149414951496149714981499150015011502150315041505150615071508150915101511151215131514151515161517151815191520152115221523152415251526152715281529153015311532153315341535153615371538153915401541154215431544154515461547154815491550155115521553155415551556155715581559156015611562156315641565156615671568156915701571157215731574157515761577157815791580158115821583158415851586158715881589159015911592159315941595159615971598159916001601160216031604160516061607160816091610161116121613161416151616161716181619162016211622162316241625162616271628162916301631163216331634163516361637163816391640164116421643164416451646164716481649165016511652165316541655165616571658165916601661166216631664166516661667166816691670167116721673167416751676167716781679168016811682168316841685168616871688168916901691169216931694169516961697169816991700170117021703170417051706170717081709171017111712171317141715171617171718171917201721172217231724172517261727172817291730173117321733173417351736173717381739174017411742174317441745174617471748174917501751175217531754175517561757175817591760176117621763176417651766176717681769177017711772177317741775177617771778177917801781178217831784178517861787178817891790179117921793179417951796179717981799180018011802180318041805180618071808180918101811181218131814181518161817181818191820182118221823182418251826182718281829183018311832183318341835183618371838183918401841184218431844184518461847184818491850185118521853185418551856185718581859186018611862186318641865186618671868186918701871187218731874187518761877187818791880188118821883188418851886188718881889189018911892189318941895189618971898189919001901190219031904190519061907190819091910191119121913191419151916191719181919192019211922192319241925192619271928192919301931193219331934193519361937193819391940194119421943194419451946194719481949195019511952195319541955195619571958195919601961196219631964196519661967196819691970197119721973197419751976197719781979198019811982198319841985198619871988198919901991199219931994199519961997199819992000200120022003200420052006200720082009201020112012201320142015201620172018201920202021202220232024202520262027202820292030203120322033203420352036203720382039204020412042204320442045204620472048204920502051205220532054205520562057205820592060206120622063206420652066206720682069207020712072207320742075207620772078207920802081208220832084208520862087208820892090209120922093209420952096209720982099210021012102210321042105210621072108210921102111211221132114211521162117211821192120212121222123212421252126212721282129213021312132213321342135213621372138213921402141214221432144214521462147214821492150215121522153215421552156215721582159216021612162216321642165216621672168216921702171217221732174217521762177217821792180218121822183218421852186218721882189219021912192219321942195219621972198219922002201220222032204220522062207220822092210221122122213221422152216221722182219222022212222222322242225222622272228222922302231223222332234223522362237223822392240224122422243224422452246224722482249225022512252225322542255225622572258225922602261226222632264226522662267226822692270227122722273227422752276
// SPDX-License-Identifier: GPL-2.0 /* * fs/ext4/extents_status.c * * Written by Yongqiang Yang <xiaoqiangnk@gmail.com> * Modified by * Allison Henderson <achender@linux.vnet.ibm.com> * Hugh Dickins <hughd@google.com> * Zheng Liu <wenqing.lz@taobao.com> * * Ext4 extents status tree core functions. */ #include <linux/list_sort.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include "ext4.h" #include <trace/events/ext4.h> /* * According to previous discussion in Ext4 Developer Workshop, we * will introduce a new structure called io tree to track all extent * status in order to solve some problems that we have met * (e.g. Reservation space warning), and provide extent-level locking. * Delay extent tree is the first step to achieve this goal. It is * original built by Yongqiang Yang. At that time it is called delay * extent tree, whose goal is only track delayed extents in memory to * simplify the implementation of fiemap and bigalloc, and introduce * lseek SEEK_DATA/SEEK_HOLE support. That is why it is still called * delay extent tree at the first commit. But for better understand * what it does, it has been rename to extent status tree. * * Step1: * Currently the first step has been done. All delayed extents are * tracked in the tree. It maintains the delayed extent when a delayed * allocation is issued, and the delayed extent is written out or * invalidated. Therefore the implementation of fiemap and bigalloc * are simplified, and SEEK_DATA/SEEK_HOLE are introduced. * * The following comment describes the implemenmtation of extent * status tree and future works. * * Step2: * In this step all extent status are tracked by extent status tree. * Thus, we can first try to lookup a block mapping in this tree before * finding it in extent tree. Hence, single extent cache can be removed * because extent status tree can do a better job. Extents in status * tree are loaded on-demand. Therefore, the extent status tree may not * contain all of the extents in a file. Meanwhile we define a shrinker * to reclaim memory from extent status tree because fragmented extent * tree will make status tree cost too much memory. written/unwritten/- * hole extents in the tree will be reclaimed by this shrinker when we * are under high memory pressure. Delayed extents will not be * reclimed because fiemap, bigalloc, and seek_data/hole need it. */ /* * Extent status tree implementation for ext4. * * * ========================================================================== * Extent status tree tracks all extent status. * * 1. Why we need to implement extent status tree? * * Without extent status tree, ext4 identifies a delayed extent by looking * up page cache, this has several deficiencies - complicated, buggy, * and inefficient code. * * FIEMAP, SEEK_HOLE/DATA, bigalloc, and writeout all need to know if a * block or a range of blocks are belonged to a delayed extent. * * Let us have a look at how they do without extent status tree. * -- FIEMAP * FIEMAP looks up page cache to identify delayed allocations from holes. * * -- SEEK_HOLE/DATA * SEEK_HOLE/DATA has the same problem as FIEMAP. * * -- bigalloc * bigalloc looks up page cache to figure out if a block is * already under delayed allocation or not to determine whether * quota reserving is needed for the cluster. * * -- writeout * Writeout looks up whole page cache to see if a buffer is * mapped, If there are not very many delayed buffers, then it is * time consuming. * * With extent status tree implementation, FIEMAP, SEEK_HOLE/DATA, * bigalloc and writeout can figure out if a block or a range of * blocks is under delayed allocation(belonged to a delayed extent) or * not by searching the extent tree. * * * ========================================================================== * 2. Ext4 extent status tree impelmentation * * -- extent * A extent is a range of blocks which are contiguous logically and * physically. Unlike extent in extent tree, this extent in ext4 is * a in-memory struct, there is no corresponding on-disk data. There * is no limit on length of extent, so an extent can contain as many * blocks as they are contiguous logically and physically. * * -- extent status tree * Every inode has an extent status tree and all allocation blocks * are added to the tree with different status. The extent in the * tree are ordered by logical block no. * * -- operations on a extent status tree * There are three important operations on a delayed extent tree: find * next extent, adding a extent(a range of blocks) and removing a extent. * * -- race on a extent status tree * Extent status tree is protected by inode->i_es_lock. * * -- memory consumption * Fragmented extent tree will make extent status tree cost too much * memory. Hence, we will reclaim written/unwritten/hole extents from * the tree under a heavy memory pressure. * * * ========================================================================== * 3. Performance analysis * * -- overhead * 1. There is a cache extent for write access, so if writes are * not very random, adding space operaions are in O(1) time. * * -- gain * 2. Code is much simpler, more readable, more maintainable and * more efficient. * * * ========================================================================== * 4. TODO list * * -- Refactor delayed space reservation * * -- Extent-level locking */ static struct kmem_cache *ext4_es_cachep; static struct kmem_cache *ext4_pending_cachep; static int __es_insert_extent(struct inode *inode, struct extent_status *newes, struct extent_status *prealloc); static int __es_remove_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t end, int *reserved, struct extent_status *prealloc); static int es_reclaim_extents(struct ext4_inode_info *ei, int *nr_to_scan); static int __es_shrink(struct ext4_sb_info *sbi, int nr_to_scan, struct ext4_inode_info *locked_ei); static int __revise_pending(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len, struct pending_reservation **prealloc); int __init ext4_init_es(void) { ext4_es_cachep = KMEM_CACHE(extent_status, SLAB_RECLAIM_ACCOUNT); if (ext4_es_cachep == NULL) return -ENOMEM; return 0; } void ext4_exit_es(void) { kmem_cache_destroy(ext4_es_cachep); } void ext4_es_init_tree(struct ext4_es_tree *tree) { tree->root = RB_ROOT; tree->cache_es = NULL; } #ifdef ES_DEBUG__ static void ext4_es_print_tree(struct inode *inode) { struct ext4_es_tree *tree; struct rb_node *node; printk(KERN_DEBUG "status extents for inode %lu:", inode->i_ino); tree = &EXT4_I(inode)->i_es_tree; node = rb_first(&tree->root); while (node) { struct extent_status *es; es = rb_entry(node, struct extent_status, rb_node); printk(KERN_DEBUG " [%u/%u) %llu %x", es->es_lblk, es->es_len, ext4_es_pblock(es), ext4_es_status(es)); node = rb_next(node); } printk(KERN_DEBUG "\n"); } #else #define ext4_es_print_tree(inode) #endif static inline ext4_lblk_t ext4_es_end(struct extent_status *es) { BUG_ON(es->es_lblk + es->es_len < es->es_lblk); return es->es_lblk + es->es_len - 1; } /* * search through the tree for an delayed extent with a given offset. If * it can't be found, try to find next extent. */ static struct extent_status *__es_tree_search(struct rb_root *root, ext4_lblk_t lblk) { struct rb_node *node = root->rb_node; struct extent_status *es = NULL; while (node) { es = rb_entry(node, struct extent_status, rb_node); if (lblk < es->es_lblk) node = node->rb_left; else if (lblk > ext4_es_end(es)) node = node->rb_right; else return es; } if (es && lblk < es->es_lblk) return es; if (es && lblk > ext4_es_end(es)) { node = rb_next(&es->rb_node); return node ? rb_entry(node, struct extent_status, rb_node) : NULL; } return NULL; } /* * ext4_es_find_extent_range - find extent with specified status within block * range or next extent following block range in * extents status tree * * @inode - file containing the range * @matching_fn - pointer to function that matches extents with desired status * @lblk - logical block defining start of range * @end - logical block defining end of range * @es - extent found, if any * * Find the first extent within the block range specified by @lblk and @end * in the extents status tree that satisfies @matching_fn. If a match * is found, it's returned in @es. If not, and a matching extent is found * beyond the block range, it's returned in @es. If no match is found, an * extent is returned in @es whose es_lblk, es_len, and es_pblk components * are 0. */ static void __es_find_extent_range(struct inode *inode, int (*matching_fn)(struct extent_status *es), ext4_lblk_t lblk, ext4_lblk_t end, struct extent_status *es) { struct ext4_es_tree *tree = NULL; struct extent_status *es1 = NULL; struct rb_node *node; WARN_ON(es == NULL); WARN_ON(end < lblk); tree = &EXT4_I(inode)->i_es_tree; /* see if the extent has been cached */ es->es_lblk = es->es_len = es->es_pblk = 0; es1 = READ_ONCE(tree->cache_es); if (es1 && in_range(lblk, es1->es_lblk, es1->es_len)) { es_debug("%u cached by [%u/%u) %llu %x\n", lblk, es1->es_lblk, es1->es_len, ext4_es_pblock(es1), ext4_es_status(es1)); goto out; } es1 = __es_tree_search(&tree->root, lblk); out: if (es1 && !matching_fn(es1)) { while ((node = rb_next(&es1->rb_node)) != NULL) { es1 = rb_entry(node, struct extent_status, rb_node); if (es1->es_lblk > end) { es1 = NULL; break; } if (matching_fn(es1)) break; } } if (es1 && matching_fn(es1)) { WRITE_ONCE(tree->cache_es, es1); es->es_lblk = es1->es_lblk; es->es_len = es1->es_len; es->es_pblk = es1->es_pblk; } } /* * Locking for __es_find_extent_range() for external use */ void ext4_es_find_extent_range(struct inode *inode, int (*matching_fn)(struct extent_status *es), ext4_lblk_t lblk, ext4_lblk_t end, struct extent_status *es) { es->es_lblk = es->es_len = es->es_pblk = 0; if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) return; trace_ext4_es_find_extent_range_enter(inode, lblk); read_lock(&EXT4_I(inode)->i_es_lock); __es_find_extent_range(inode, matching_fn, lblk, end, es); read_unlock(&EXT4_I(inode)->i_es_lock); trace_ext4_es_find_extent_range_exit(inode, es); } /* * __es_scan_range - search block range for block with specified status * in extents status tree * * @inode - file containing the range * @matching_fn - pointer to function that matches extents with desired status * @lblk - logical block defining start of range * @end - logical block defining end of range * * Returns true if at least one block in the specified block range satisfies * the criterion specified by @matching_fn, and false if not. If at least * one extent has the specified status, then there is at least one block * in the cluster with that status. Should only be called by code that has * taken i_es_lock. */ static bool __es_scan_range(struct inode *inode, int (*matching_fn)(struct extent_status *es), ext4_lblk_t start, ext4_lblk_t end) { struct extent_status es; __es_find_extent_range(inode, matching_fn, start, end, &es); if (es.es_len == 0) return false; /* no matching extent in the tree */ else if (es.es_lblk <= start && start < es.es_lblk + es.es_len) return true; else if (start <= es.es_lblk && es.es_lblk <= end) return true; else return false; } /* * Locking for __es_scan_range() for external use */ bool ext4_es_scan_range(struct inode *inode, int (*matching_fn)(struct extent_status *es), ext4_lblk_t lblk, ext4_lblk_t end) { bool ret; if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) return false; read_lock(&EXT4_I(inode)->i_es_lock); ret = __es_scan_range(inode, matching_fn, lblk, end); read_unlock(&EXT4_I(inode)->i_es_lock); return ret; } /* * __es_scan_clu - search cluster for block with specified status in * extents status tree * * @inode - file containing the cluster * @matching_fn - pointer to function that matches extents with desired status * @lblk - logical block in cluster to be searched * * Returns true if at least one extent in the cluster containing @lblk * satisfies the criterion specified by @matching_fn, and false if not. If at * least one extent has the specified status, then there is at least one block * in the cluster with that status. Should only be called by code that has * taken i_es_lock. */ static bool __es_scan_clu(struct inode *inode, int (*matching_fn)(struct extent_status *es), ext4_lblk_t lblk) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); ext4_lblk_t lblk_start, lblk_end; lblk_start = EXT4_LBLK_CMASK(sbi, lblk); lblk_end = lblk_start + sbi->s_cluster_ratio - 1; return __es_scan_range(inode, matching_fn, lblk_start, lblk_end); } /* * Locking for __es_scan_clu() for external use */ bool ext4_es_scan_clu(struct inode *inode, int (*matching_fn)(struct extent_status *es), ext4_lblk_t lblk) { bool ret; if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) return false; read_lock(&EXT4_I(inode)->i_es_lock); ret = __es_scan_clu(inode, matching_fn, lblk); read_unlock(&EXT4_I(inode)->i_es_lock); return ret; } static void ext4_es_list_add(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); if (!list_empty(&ei->i_es_list)) return; spin_lock(&sbi->s_es_lock); if (list_empty(&ei->i_es_list)) { list_add_tail(&ei->i_es_list, &sbi->s_es_list); sbi->s_es_nr_inode++; } spin_unlock(&sbi->s_es_lock); } static void ext4_es_list_del(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); spin_lock(&sbi->s_es_lock); if (!list_empty(&ei->i_es_list)) { list_del_init(&ei->i_es_list); sbi->s_es_nr_inode--; WARN_ON_ONCE(sbi->s_es_nr_inode < 0); } spin_unlock(&sbi->s_es_lock); } static inline struct pending_reservation *__alloc_pending(bool nofail) { if (!nofail) return kmem_cache_alloc(ext4_pending_cachep, GFP_ATOMIC); return kmem_cache_zalloc(ext4_pending_cachep, GFP_KERNEL | __GFP_NOFAIL); } static inline void __free_pending(struct pending_reservation *pr) { kmem_cache_free(ext4_pending_cachep, pr); } /* * Returns true if we cannot fail to allocate memory for this extent_status * entry and cannot reclaim it until its status changes. */ static inline bool ext4_es_must_keep(struct extent_status *es) { /* fiemap, bigalloc, and seek_data/hole need to use it. */ if (ext4_es_is_delayed(es)) return true; return false; } static inline struct extent_status *__es_alloc_extent(bool nofail) { if (!nofail) return kmem_cache_alloc(ext4_es_cachep, GFP_ATOMIC); return kmem_cache_zalloc(ext4_es_cachep, GFP_KERNEL | __GFP_NOFAIL); } static void ext4_es_init_extent(struct inode *inode, struct extent_status *es, ext4_lblk_t lblk, ext4_lblk_t len, ext4_fsblk_t pblk) { es->es_lblk = lblk; es->es_len = len; es->es_pblk = pblk; /* We never try to reclaim a must kept extent, so we don't count it. */ if (!ext4_es_must_keep(es)) { if (!EXT4_I(inode)->i_es_shk_nr++) ext4_es_list_add(inode); percpu_counter_inc(&EXT4_SB(inode->i_sb)-> s_es_stats.es_stats_shk_cnt); } EXT4_I(inode)->i_es_all_nr++; percpu_counter_inc(&EXT4_SB(inode->i_sb)->s_es_stats.es_stats_all_cnt); } static inline void __es_free_extent(struct extent_status *es) { kmem_cache_free(ext4_es_cachep, es); } static void ext4_es_free_extent(struct inode *inode, struct extent_status *es) { EXT4_I(inode)->i_es_all_nr--; percpu_counter_dec(&EXT4_SB(inode->i_sb)->s_es_stats.es_stats_all_cnt); /* Decrease the shrink counter when we can reclaim the extent. */ if (!ext4_es_must_keep(es)) { BUG_ON(EXT4_I(inode)->i_es_shk_nr == 0); if (!--EXT4_I(inode)->i_es_shk_nr) ext4_es_list_del(inode); percpu_counter_dec(&EXT4_SB(inode->i_sb)-> s_es_stats.es_stats_shk_cnt); } __es_free_extent(es); } /* * Check whether or not two extents can be merged * Condition: * - logical block number is contiguous * - physical block number is contiguous * - status is equal */ static int ext4_es_can_be_merged(struct extent_status *es1, struct extent_status *es2) { if (ext4_es_type(es1) != ext4_es_type(es2)) return 0; if (((__u64) es1->es_len) + es2->es_len > EXT_MAX_BLOCKS) { pr_warn("ES assertion failed when merging extents. " "The sum of lengths of es1 (%d) and es2 (%d) " "is bigger than allowed file size (%d)\n", es1->es_len, es2->es_len, EXT_MAX_BLOCKS); WARN_ON(1); return 0; } if (((__u64) es1->es_lblk) + es1->es_len != es2->es_lblk) return 0; if ((ext4_es_is_written(es1) || ext4_es_is_unwritten(es1)) && (ext4_es_pblock(es1) + es1->es_len == ext4_es_pblock(es2))) return 1; if (ext4_es_is_hole(es1)) return 1; /* we need to check delayed extent */ if (ext4_es_is_delayed(es1)) return 1; return 0; } static struct extent_status * ext4_es_try_to_merge_left(struct inode *inode, struct extent_status *es) { struct ext4_es_tree *tree = &EXT4_I(inode)->i_es_tree; struct extent_status *es1; struct rb_node *node; node = rb_prev(&es->rb_node); if (!node) return es; es1 = rb_entry(node, struct extent_status, rb_node); if (ext4_es_can_be_merged(es1, es)) { es1->es_len += es->es_len; if (ext4_es_is_referenced(es)) ext4_es_set_referenced(es1); rb_erase(&es->rb_node, &tree->root); ext4_es_free_extent(inode, es); es = es1; } return es; } static struct extent_status * ext4_es_try_to_merge_right(struct inode *inode, struct extent_status *es) { struct ext4_es_tree *tree = &EXT4_I(inode)->i_es_tree; struct extent_status *es1; struct rb_node *node; node = rb_next(&es->rb_node); if (!node) return es; es1 = rb_entry(node, struct extent_status, rb_node); if (ext4_es_can_be_merged(es, es1)) { es->es_len += es1->es_len; if (ext4_es_is_referenced(es1)) ext4_es_set_referenced(es); rb_erase(node, &tree->root); ext4_es_free_extent(inode, es1); } return es; } #ifdef ES_AGGRESSIVE_TEST #include "ext4_extents.h" /* Needed when ES_AGGRESSIVE_TEST is defined */ static void ext4_es_insert_extent_ext_check(struct inode *inode, struct extent_status *es) { struct ext4_ext_path *path = NULL; struct ext4_extent *ex; ext4_lblk_t ee_block; ext4_fsblk_t ee_start; unsigned short ee_len; int depth, ee_status, es_status; path = ext4_find_extent(inode, es->es_lblk, NULL, EXT4_EX_NOCACHE); if (IS_ERR(path)) return; depth = ext_depth(inode); ex = path[depth].p_ext; if (ex) { ee_block = le32_to_cpu(ex->ee_block); ee_start = ext4_ext_pblock(ex); ee_len = ext4_ext_get_actual_len(ex); ee_status = ext4_ext_is_unwritten(ex) ? 1 : 0; es_status = ext4_es_is_unwritten(es) ? 1 : 0; /* * Make sure ex and es are not overlap when we try to insert * a delayed/hole extent. */ if (!ext4_es_is_written(es) && !ext4_es_is_unwritten(es)) { if (in_range(es->es_lblk, ee_block, ee_len)) { pr_warn("ES insert assertion failed for " "inode: %lu we can find an extent " "at block [%d/%d/%llu/%c], but we " "want to add a delayed/hole extent " "[%d/%d/%llu/%x]\n", inode->i_ino, ee_block, ee_len, ee_start, ee_status ? 'u' : 'w', es->es_lblk, es->es_len, ext4_es_pblock(es), ext4_es_status(es)); } goto out; } /* * We don't check ee_block == es->es_lblk, etc. because es * might be a part of whole extent, vice versa. */ if (es->es_lblk < ee_block || ext4_es_pblock(es) != ee_start + es->es_lblk - ee_block) { pr_warn("ES insert assertion failed for inode: %lu " "ex_status [%d/%d/%llu/%c] != " "es_status [%d/%d/%llu/%c]\n", inode->i_ino, ee_block, ee_len, ee_start, ee_status ? 'u' : 'w', es->es_lblk, es->es_len, ext4_es_pblock(es), es_status ? 'u' : 'w'); goto out; } if (ee_status ^ es_status) { pr_warn("ES insert assertion failed for inode: %lu " "ex_status [%d/%d/%llu/%c] != " "es_status [%d/%d/%llu/%c]\n", inode->i_ino, ee_block, ee_len, ee_start, ee_status ? 'u' : 'w', es->es_lblk, es->es_len, ext4_es_pblock(es), es_status ? 'u' : 'w'); } } else { /* * We can't find an extent on disk. So we need to make sure * that we don't want to add an written/unwritten extent. */ if (!ext4_es_is_delayed(es) && !ext4_es_is_hole(es)) { pr_warn("ES insert assertion failed for inode: %lu " "can't find an extent at block %d but we want " "to add a written/unwritten extent " "[%d/%d/%llu/%x]\n", inode->i_ino, es->es_lblk, es->es_lblk, es->es_len, ext4_es_pblock(es), ext4_es_status(es)); } } out: ext4_free_ext_path(path); } static void ext4_es_insert_extent_ind_check(struct inode *inode, struct extent_status *es) { struct ext4_map_blocks map; int retval; /* * Here we call ext4_ind_map_blocks to lookup a block mapping because * 'Indirect' structure is defined in indirect.c. So we couldn't * access direct/indirect tree from outside. It is too dirty to define * this function in indirect.c file. */ map.m_lblk = es->es_lblk; map.m_len = es->es_len; retval = ext4_ind_map_blocks(NULL, inode, &map, 0); if (retval > 0) { if (ext4_es_is_delayed(es) || ext4_es_is_hole(es)) { /* * We want to add a delayed/hole extent but this * block has been allocated. */ pr_warn("ES insert assertion failed for inode: %lu " "We can find blocks but we want to add a " "delayed/hole extent [%d/%d/%llu/%x]\n", inode->i_ino, es->es_lblk, es->es_len, ext4_es_pblock(es), ext4_es_status(es)); return; } else if (ext4_es_is_written(es)) { if (retval != es->es_len) { pr_warn("ES insert assertion failed for " "inode: %lu retval %d != es_len %d\n", inode->i_ino, retval, es->es_len); return; } if (map.m_pblk != ext4_es_pblock(es)) { pr_warn("ES insert assertion failed for " "inode: %lu m_pblk %llu != " "es_pblk %llu\n", inode->i_ino, map.m_pblk, ext4_es_pblock(es)); return; } } else { /* * We don't need to check unwritten extent because * indirect-based file doesn't have it. */ BUG(); } } else if (retval == 0) { if (ext4_es_is_written(es)) { pr_warn("ES insert assertion failed for inode: %lu " "We can't find the block but we want to add " "a written extent [%d/%d/%llu/%x]\n", inode->i_ino, es->es_lblk, es->es_len, ext4_es_pblock(es), ext4_es_status(es)); return; } } } static inline void ext4_es_insert_extent_check(struct inode *inode, struct extent_status *es) { /* * We don't need to worry about the race condition because * caller takes i_data_sem locking. */ BUG_ON(!rwsem_is_locked(&EXT4_I(inode)->i_data_sem)); if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) ext4_es_insert_extent_ext_check(inode, es); else ext4_es_insert_extent_ind_check(inode, es); } #else static inline void ext4_es_insert_extent_check(struct inode *inode, struct extent_status *es) { } #endif static int __es_insert_extent(struct inode *inode, struct extent_status *newes, struct extent_status *prealloc) { struct ext4_es_tree *tree = &EXT4_I(inode)->i_es_tree; struct rb_node **p = &tree->root.rb_node; struct rb_node *parent = NULL; struct extent_status *es; while (*p) { parent = *p; es = rb_entry(parent, struct extent_status, rb_node); if (newes->es_lblk < es->es_lblk) { if (ext4_es_can_be_merged(newes, es)) { /* * Here we can modify es_lblk directly * because it isn't overlapped. */ es->es_lblk = newes->es_lblk; es->es_len += newes->es_len; if (ext4_es_is_written(es) || ext4_es_is_unwritten(es)) ext4_es_store_pblock(es, newes->es_pblk); es = ext4_es_try_to_merge_left(inode, es); goto out; } p = &(*p)->rb_left; } else if (newes->es_lblk > ext4_es_end(es)) { if (ext4_es_can_be_merged(es, newes)) { es->es_len += newes->es_len; es = ext4_es_try_to_merge_right(inode, es); goto out; } p = &(*p)->rb_right; } else { BUG(); return -EINVAL; } } if (prealloc) es = prealloc; else es = __es_alloc_extent(false); if (!es) return -ENOMEM; ext4_es_init_extent(inode, es, newes->es_lblk, newes->es_len, newes->es_pblk); rb_link_node(&es->rb_node, parent, p); rb_insert_color(&es->rb_node, &tree->root); out: tree->cache_es = es; return 0; } /* * ext4_es_insert_extent() adds information to an inode's extent * status tree. */ void ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len, ext4_fsblk_t pblk, unsigned int status, int flags) { struct extent_status newes; ext4_lblk_t end = lblk + len - 1; int err1 = 0, err2 = 0, err3 = 0; int resv_used = 0, pending = 0; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct extent_status *es1 = NULL; struct extent_status *es2 = NULL; struct pending_reservation *pr = NULL; bool revise_pending = false; if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) return; es_debug("add [%u/%u) %llu %x %x to extent status tree of inode %lu\n", lblk, len, pblk, status, flags, inode->i_ino); if (!len) return; BUG_ON(end < lblk); WARN_ON_ONCE(status & EXTENT_STATUS_DELAYED); newes.es_lblk = lblk; newes.es_len = len; ext4_es_store_pblock_status(&newes, pblk, status); trace_ext4_es_insert_extent(inode, &newes); ext4_es_insert_extent_check(inode, &newes); revise_pending = sbi->s_cluster_ratio > 1 && test_opt(inode->i_sb, DELALLOC) && (status & (EXTENT_STATUS_WRITTEN | EXTENT_STATUS_UNWRITTEN)); retry: if (err1 && !es1) es1 = __es_alloc_extent(true); if ((err1 || err2) && !es2) es2 = __es_alloc_extent(true); if ((err1 || err2 || err3 < 0) && revise_pending && !pr) pr = __alloc_pending(true); write_lock(&EXT4_I(inode)->i_es_lock); err1 = __es_remove_extent(inode, lblk, end, &resv_used, es1); if (err1 != 0) goto error; /* Free preallocated extent if it didn't get used. */ if (es1) { if (!es1->es_len) __es_free_extent(es1); es1 = NULL; } err2 = __es_insert_extent(inode, &newes, es2); if (err2 == -ENOMEM && !ext4_es_must_keep(&newes)) err2 = 0; if (err2 != 0) goto error; /* Free preallocated extent if it didn't get used. */ if (es2) { if (!es2->es_len) __es_free_extent(es2); es2 = NULL; } if (revise_pending) { err3 = __revise_pending(inode, lblk, len, &pr); if (err3 < 0) goto error; if (pr) { __free_pending(pr); pr = NULL; } pending = err3; } error: write_unlock(&EXT4_I(inode)->i_es_lock); /* * Reduce the reserved cluster count to reflect successful deferred * allocation of delayed allocated clusters or direct allocation of * clusters discovered to be delayed allocated. Once allocated, a * cluster is not included in the reserved count. * * When direct allocating (from fallocate, filemap, DIO, or clusters * allocated when delalloc has been disabled by ext4_nonda_switch()) * an extent either 1) contains delayed blocks but start with * non-delayed allocated blocks (e.g. hole) or 2) contains non-delayed * allocated blocks which belong to delayed allocated clusters when * bigalloc feature is enabled, quota has already been claimed by * ext4_mb_new_blocks(), so release the quota reservations made for * any previously delayed allocated clusters instead of claim them * again. */ resv_used += pending; if (resv_used) ext4_da_update_reserve_space(inode, resv_used, flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE); if (err1 || err2 || err3 < 0) goto retry; ext4_es_print_tree(inode); return; } /* * ext4_es_cache_extent() inserts information into the extent status * tree if and only if there isn't information about the range in * question already. */ void ext4_es_cache_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len, ext4_fsblk_t pblk, unsigned int status) { struct extent_status *es; struct extent_status newes; ext4_lblk_t end = lblk + len - 1; if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) return; newes.es_lblk = lblk; newes.es_len = len; ext4_es_store_pblock_status(&newes, pblk, status); trace_ext4_es_cache_extent(inode, &newes); if (!len) return; BUG_ON(end < lblk); write_lock(&EXT4_I(inode)->i_es_lock); es = __es_tree_search(&EXT4_I(inode)->i_es_tree.root, lblk); if (!es || es->es_lblk > end) __es_insert_extent(inode, &newes, NULL); write_unlock(&EXT4_I(inode)->i_es_lock); } /* * ext4_es_lookup_extent() looks up an extent in extent status tree. * * ext4_es_lookup_extent is called by ext4_map_blocks/ext4_da_map_blocks. * * Return: 1 on found, 0 on not */ int ext4_es_lookup_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t *next_lblk, struct extent_status *es) { struct ext4_es_tree *tree; struct ext4_es_stats *stats; struct extent_status *es1 = NULL; struct rb_node *node; int found = 0; if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) return 0; trace_ext4_es_lookup_extent_enter(inode, lblk); es_debug("lookup extent in block %u\n", lblk); tree = &EXT4_I(inode)->i_es_tree; read_lock(&EXT4_I(inode)->i_es_lock); /* find extent in cache firstly */ es->es_lblk = es->es_len = es->es_pblk = 0; es1 = READ_ONCE(tree->cache_es); if (es1 && in_range(lblk, es1->es_lblk, es1->es_len)) { es_debug("%u cached by [%u/%u)\n", lblk, es1->es_lblk, es1->es_len); found = 1; goto out; } node = tree->root.rb_node; while (node) { es1 = rb_entry(node, struct extent_status, rb_node); if (lblk < es1->es_lblk) node = node->rb_left; else if (lblk > ext4_es_end(es1)) node = node->rb_right; else { found = 1; break; } } out: stats = &EXT4_SB(inode->i_sb)->s_es_stats; if (found) { BUG_ON(!es1); es->es_lblk = es1->es_lblk; es->es_len = es1->es_len; es->es_pblk = es1->es_pblk; if (!ext4_es_is_referenced(es1)) ext4_es_set_referenced(es1); percpu_counter_inc(&stats->es_stats_cache_hits); if (next_lblk) { node = rb_next(&es1->rb_node); if (node) { es1 = rb_entry(node, struct extent_status, rb_node); *next_lblk = es1->es_lblk; } else *next_lblk = 0; } } else { percpu_counter_inc(&stats->es_stats_cache_misses); } read_unlock(&EXT4_I(inode)->i_es_lock); trace_ext4_es_lookup_extent_exit(inode, es, found); return found; } struct rsvd_count { int ndelayed; bool first_do_lblk_found; ext4_lblk_t first_do_lblk; ext4_lblk_t last_do_lblk; struct extent_status *left_es; bool partial; ext4_lblk_t lclu; }; /* * init_rsvd - initialize reserved count data before removing block range * in file from extent status tree * * @inode - file containing range * @lblk - first block in range * @es - pointer to first extent in range * @rc - pointer to reserved count data * * Assumes es is not NULL */ static void init_rsvd(struct inode *inode, ext4_lblk_t lblk, struct extent_status *es, struct rsvd_count *rc) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct rb_node *node; rc->ndelayed = 0; /* * for bigalloc, note the first delayed block in the range has not * been found, record the extent containing the block to the left of * the region to be removed, if any, and note that there's no partial * cluster to track */ if (sbi->s_cluster_ratio > 1) { rc->first_do_lblk_found = false; if (lblk > es->es_lblk) { rc->left_es = es; } else { node = rb_prev(&es->rb_node); rc->left_es = node ? rb_entry(node, struct extent_status, rb_node) : NULL; } rc->partial = false; } } /* * count_rsvd - count the clusters containing delayed blocks in a range * within an extent and add to the running tally in rsvd_count * * @inode - file containing extent * @lblk - first block in range * @len - length of range in blocks * @es - pointer to extent containing clusters to be counted * @rc - pointer to reserved count data * * Tracks partial clusters found at the beginning and end of extents so * they aren't overcounted when they span adjacent extents */ static void count_rsvd(struct inode *inode, ext4_lblk_t lblk, long len, struct extent_status *es, struct rsvd_count *rc) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); ext4_lblk_t i, end, nclu; if (!ext4_es_is_delayed(es)) return; WARN_ON(len <= 0); if (sbi->s_cluster_ratio == 1) { rc->ndelayed += (int) len; return; } /* bigalloc */ i = (lblk < es->es_lblk) ? es->es_lblk : lblk; end = lblk + (ext4_lblk_t) len - 1; end = (end > ext4_es_end(es)) ? ext4_es_end(es) : end; /* record the first block of the first delayed extent seen */ if (!rc->first_do_lblk_found) { rc->first_do_lblk = i; rc->first_do_lblk_found = true; } /* update the last lblk in the region seen so far */ rc->last_do_lblk = end; /* * if we're tracking a partial cluster and the current extent * doesn't start with it, count it and stop tracking */ if (rc->partial && (rc->lclu != EXT4_B2C(sbi, i))) { rc->ndelayed++; rc->partial = false; } /* * if the first cluster doesn't start on a cluster boundary but * ends on one, count it */ if (EXT4_LBLK_COFF(sbi, i) != 0) { if (end >= EXT4_LBLK_CFILL(sbi, i)) { rc->ndelayed++; rc->partial = false; i = EXT4_LBLK_CFILL(sbi, i) + 1; } } /* * if the current cluster starts on a cluster boundary, count the * number of whole delayed clusters in the extent */ if ((i + sbi->s_cluster_ratio - 1) <= end) { nclu = (end - i + 1) >> sbi->s_cluster_bits; rc->ndelayed += nclu; i += nclu << sbi->s_cluster_bits; } /* * start tracking a partial cluster if there's a partial at the end * of the current extent and we're not already tracking one */ if (!rc->partial && i <= end) { rc->partial = true; rc->lclu = EXT4_B2C(sbi, i); } } /* * __pr_tree_search - search for a pending cluster reservation * * @root - root of pending reservation tree * @lclu - logical cluster to search for * * Returns the pending reservation for the cluster identified by @lclu * if found. If not, returns a reservation for the next cluster if any, * and if not, returns NULL. */ static struct pending_reservation *__pr_tree_search(struct rb_root *root, ext4_lblk_t lclu) { struct rb_node *node = root->rb_node; struct pending_reservation *pr = NULL; while (node) { pr = rb_entry(node, struct pending_reservation, rb_node); if (lclu < pr->lclu) node = node->rb_left; else if (lclu > pr->lclu) node = node->rb_right; else return pr; } if (pr && lclu < pr->lclu) return pr; if (pr && lclu > pr->lclu) { node = rb_next(&pr->rb_node); return node ? rb_entry(node, struct pending_reservation, rb_node) : NULL; } return NULL; } /* * get_rsvd - calculates and returns the number of cluster reservations to be * released when removing a block range from the extent status tree * and releases any pending reservations within the range * * @inode - file containing block range * @end - last block in range * @right_es - pointer to extent containing next block beyond end or NULL * @rc - pointer to reserved count data * * The number of reservations to be released is equal to the number of * clusters containing delayed blocks within the range, minus the number of * clusters still containing delayed blocks at the ends of the range, and * minus the number of pending reservations within the range. */ static unsigned int get_rsvd(struct inode *inode, ext4_lblk_t end, struct extent_status *right_es, struct rsvd_count *rc) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct pending_reservation *pr; struct ext4_pending_tree *tree = &EXT4_I(inode)->i_pending_tree; struct rb_node *node; ext4_lblk_t first_lclu, last_lclu; bool left_delayed, right_delayed, count_pending; struct extent_status *es; if (sbi->s_cluster_ratio > 1) { /* count any remaining partial cluster */ if (rc->partial) rc->ndelayed++; if (rc->ndelayed == 0) return 0; first_lclu = EXT4_B2C(sbi, rc->first_do_lblk); last_lclu = EXT4_B2C(sbi, rc->last_do_lblk); /* * decrease the delayed count by the number of clusters at the * ends of the range that still contain delayed blocks - * these clusters still need to be reserved */ left_delayed = right_delayed = false; es = rc->left_es; while (es && ext4_es_end(es) >= EXT4_LBLK_CMASK(sbi, rc->first_do_lblk)) { if (ext4_es_is_delayed(es)) { rc->ndelayed--; left_delayed = true; break; } node = rb_prev(&es->rb_node); if (!node) break; es = rb_entry(node, struct extent_status, rb_node); } if (right_es && (!left_delayed || first_lclu != last_lclu)) { if (end < ext4_es_end(right_es)) { es = right_es; } else { node = rb_next(&right_es->rb_node); es = node ? rb_entry(node, struct extent_status, rb_node) : NULL; } while (es && es->es_lblk <= EXT4_LBLK_CFILL(sbi, rc->last_do_lblk)) { if (ext4_es_is_delayed(es)) { rc->ndelayed--; right_delayed = true; break; } node = rb_next(&es->rb_node); if (!node) break; es = rb_entry(node, struct extent_status, rb_node); } } /* * Determine the block range that should be searched for * pending reservations, if any. Clusters on the ends of the * original removed range containing delayed blocks are * excluded. They've already been accounted for and it's not * possible to determine if an associated pending reservation * should be released with the information available in the * extents status tree. */ if (first_lclu == last_lclu) { if (left_delayed | right_delayed) count_pending = false; else count_pending = true; } else { if (left_delayed) first_lclu++; if (right_delayed) last_lclu--; if (first_lclu <= last_lclu) count_pending = true; else count_pending = false; } /* * a pending reservation found between first_lclu and last_lclu * represents an allocated cluster that contained at least one * delayed block, so the delayed total must be reduced by one * for each pending reservation found and released */ if (count_pending) { pr = __pr_tree_search(&tree->root, first_lclu); while (pr && pr->lclu <= last_lclu) { rc->ndelayed--; node = rb_next(&pr->rb_node); rb_erase(&pr->rb_node, &tree->root); __free_pending(pr); if (!node) break; pr = rb_entry(node, struct pending_reservation, rb_node); } } } return rc->ndelayed; } /* * __es_remove_extent - removes block range from extent status tree * * @inode - file containing range * @lblk - first block in range * @end - last block in range * @reserved - number of cluster reservations released * @prealloc - pre-allocated es to avoid memory allocation failures * * If @reserved is not NULL and delayed allocation is enabled, counts * block/cluster reservations freed by removing range and if bigalloc * enabled cancels pending reservations as needed. Returns 0 on success, * error code on failure. */ static int __es_remove_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t end, int *reserved, struct extent_status *prealloc) { struct ext4_es_tree *tree = &EXT4_I(inode)->i_es_tree; struct rb_node *node; struct extent_status *es; struct extent_status orig_es; ext4_lblk_t len1, len2; ext4_fsblk_t block; int err = 0; bool count_reserved = true; struct rsvd_count rc; if (reserved == NULL || !test_opt(inode->i_sb, DELALLOC)) count_reserved = false; es = __es_tree_search(&tree->root, lblk); if (!es) goto out; if (es->es_lblk > end) goto out; /* Simply invalidate cache_es. */ tree->cache_es = NULL; if (count_reserved) init_rsvd(inode, lblk, es, &rc); orig_es.es_lblk = es->es_lblk; orig_es.es_len = es->es_len; orig_es.es_pblk = es->es_pblk; len1 = lblk > es->es_lblk ? lblk - es->es_lblk : 0; len2 = ext4_es_end(es) > end ? ext4_es_end(es) - end : 0; if (len1 > 0) es->es_len = len1; if (len2 > 0) { if (len1 > 0) { struct extent_status newes; newes.es_lblk = end + 1; newes.es_len = len2; block = 0x7FDEADBEEFULL; if (ext4_es_is_written(&orig_es) || ext4_es_is_unwritten(&orig_es)) block = ext4_es_pblock(&orig_es) + orig_es.es_len - len2; ext4_es_store_pblock_status(&newes, block, ext4_es_status(&orig_es)); err = __es_insert_extent(inode, &newes, prealloc); if (err) { if (!ext4_es_must_keep(&newes)) return 0; es->es_lblk = orig_es.es_lblk; es->es_len = orig_es.es_len; goto out; } } else { es->es_lblk = end + 1; es->es_len = len2; if (ext4_es_is_written(es) || ext4_es_is_unwritten(es)) { block = orig_es.es_pblk + orig_es.es_len - len2; ext4_es_store_pblock(es, block); } } if (count_reserved) count_rsvd(inode, orig_es.es_lblk + len1, orig_es.es_len - len1 - len2, &orig_es, &rc); goto out_get_reserved; } if (len1 > 0) { if (count_reserved) count_rsvd(inode, lblk, orig_es.es_len - len1, &orig_es, &rc); node = rb_next(&es->rb_node); if (node) es = rb_entry(node, struct extent_status, rb_node); else es = NULL; } while (es && ext4_es_end(es) <= end) { if (count_reserved) count_rsvd(inode, es->es_lblk, es->es_len, es, &rc); node = rb_next(&es->rb_node); rb_erase(&es->rb_node, &tree->root); ext4_es_free_extent(inode, es); if (!node) { es = NULL; break; } es = rb_entry(node, struct extent_status, rb_node); } if (es && es->es_lblk < end + 1) { ext4_lblk_t orig_len = es->es_len; len1 = ext4_es_end(es) - end; if (count_reserved) count_rsvd(inode, es->es_lblk, orig_len - len1, es, &rc); es->es_lblk = end + 1; es->es_len = len1; if (ext4_es_is_written(es) || ext4_es_is_unwritten(es)) { block = es->es_pblk + orig_len - len1; ext4_es_store_pblock(es, block); } } out_get_reserved: if (count_reserved) *reserved = get_rsvd(inode, end, es, &rc); out: return err; } /* * ext4_es_remove_extent - removes block range from extent status tree * * @inode - file containing range * @lblk - first block in range * @len - number of blocks to remove * * Reduces block/cluster reservation count and for bigalloc cancels pending * reservations as needed. */ void ext4_es_remove_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len) { ext4_lblk_t end; int err = 0; int reserved = 0; struct extent_status *es = NULL; if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) return; trace_ext4_es_remove_extent(inode, lblk, len); es_debug("remove [%u/%u) from extent status tree of inode %lu\n", lblk, len, inode->i_ino); if (!len) return; end = lblk + len - 1; BUG_ON(end < lblk); retry: if (err && !es) es = __es_alloc_extent(true); /* * ext4_clear_inode() depends on us taking i_es_lock unconditionally * so that we are sure __es_shrink() is done with the inode before it * is reclaimed. */ write_lock(&EXT4_I(inode)->i_es_lock); err = __es_remove_extent(inode, lblk, end, &reserved, es); /* Free preallocated extent if it didn't get used. */ if (es) { if (!es->es_len) __es_free_extent(es); es = NULL; } write_unlock(&EXT4_I(inode)->i_es_lock); if (err) goto retry; ext4_es_print_tree(inode); ext4_da_release_space(inode, reserved); return; } static int __es_shrink(struct ext4_sb_info *sbi, int nr_to_scan, struct ext4_inode_info *locked_ei) { struct ext4_inode_info *ei; struct ext4_es_stats *es_stats; ktime_t start_time; u64 scan_time; int nr_to_walk; int nr_shrunk = 0; int retried = 0, nr_skipped = 0; es_stats = &sbi->s_es_stats; start_time = ktime_get(); retry: spin_lock(&sbi->s_es_lock); nr_to_walk = sbi->s_es_nr_inode; while (nr_to_walk-- > 0) { if (list_empty(&sbi->s_es_list)) { spin_unlock(&sbi->s_es_lock); goto out; } ei = list_first_entry(&sbi->s_es_list, struct ext4_inode_info, i_es_list); /* Move the inode to the tail */ list_move_tail(&ei->i_es_list, &sbi->s_es_list); /* * Normally we try hard to avoid shrinking precached inodes, * but we will as a last resort. */ if (!retried && ext4_test_inode_state(&ei->vfs_inode, EXT4_STATE_EXT_PRECACHED)) { nr_skipped++; continue; } if (ei == locked_ei || !write_trylock(&ei->i_es_lock)) { nr_skipped++; continue; } /* * Now we hold i_es_lock which protects us from inode reclaim * freeing inode under us */ spin_unlock(&sbi->s_es_lock); nr_shrunk += es_reclaim_extents(ei, &nr_to_scan); write_unlock(&ei->i_es_lock); if (nr_to_scan <= 0) goto out; spin_lock(&sbi->s_es_lock); } spin_unlock(&sbi->s_es_lock); /* * If we skipped any inodes, and we weren't able to make any * forward progress, try again to scan precached inodes. */ if ((nr_shrunk == 0) && nr_skipped && !retried) { retried++; goto retry; } if (locked_ei && nr_shrunk == 0) nr_shrunk = es_reclaim_extents(locked_ei, &nr_to_scan); out: scan_time = ktime_to_ns(ktime_sub(ktime_get(), start_time)); if (likely(es_stats->es_stats_scan_time)) es_stats->es_stats_scan_time = (scan_time + es_stats->es_stats_scan_time*3) / 4; else es_stats->es_stats_scan_time = scan_time; if (scan_time > es_stats->es_stats_max_scan_time) es_stats->es_stats_max_scan_time = scan_time; if (likely(es_stats->es_stats_shrunk)) es_stats->es_stats_shrunk = (nr_shrunk + es_stats->es_stats_shrunk*3) / 4; else es_stats->es_stats_shrunk = nr_shrunk; trace_ext4_es_shrink(sbi->s_sb, nr_shrunk, scan_time, nr_skipped, retried); return nr_shrunk; } static unsigned long ext4_es_count(struct shrinker *shrink, struct shrink_control *sc) { unsigned long nr; struct ext4_sb_info *sbi; sbi = shrink->private_data; nr = percpu_counter_read_positive(&sbi->s_es_stats.es_stats_shk_cnt); trace_ext4_es_shrink_count(sbi->s_sb, sc->nr_to_scan, nr); return nr; } static unsigned long ext4_es_scan(struct shrinker *shrink, struct shrink_control *sc) { struct ext4_sb_info *sbi = shrink->private_data; int nr_to_scan = sc->nr_to_scan; int ret, nr_shrunk; ret = percpu_counter_read_positive(&sbi->s_es_stats.es_stats_shk_cnt); trace_ext4_es_shrink_scan_enter(sbi->s_sb, nr_to_scan, ret); nr_shrunk = __es_shrink(sbi, nr_to_scan, NULL); ret = percpu_counter_read_positive(&sbi->s_es_stats.es_stats_shk_cnt); trace_ext4_es_shrink_scan_exit(sbi->s_sb, nr_shrunk, ret); return nr_shrunk; } int ext4_seq_es_shrinker_info_show(struct seq_file *seq, void *v) { struct ext4_sb_info *sbi = EXT4_SB((struct super_block *) seq->private); struct ext4_es_stats *es_stats = &sbi->s_es_stats; struct ext4_inode_info *ei, *max = NULL; unsigned int inode_cnt = 0; if (v != SEQ_START_TOKEN) return 0; /* here we just find an inode that has the max nr. of objects */ spin_lock(&sbi->s_es_lock); list_for_each_entry(ei, &sbi->s_es_list, i_es_list) { inode_cnt++; if (max && max->i_es_all_nr < ei->i_es_all_nr) max = ei; else if (!max) max = ei; } spin_unlock(&sbi->s_es_lock); seq_printf(seq, "stats:\n %lld objects\n %lld reclaimable objects\n", percpu_counter_sum_positive(&es_stats->es_stats_all_cnt), percpu_counter_sum_positive(&es_stats->es_stats_shk_cnt)); seq_printf(seq, " %lld/%lld cache hits/misses\n", percpu_counter_sum_positive(&es_stats->es_stats_cache_hits), percpu_counter_sum_positive(&es_stats->es_stats_cache_misses)); if (inode_cnt) seq_printf(seq, " %d inodes on list\n", inode_cnt); seq_printf(seq, "average:\n %llu us scan time\n", div_u64(es_stats->es_stats_scan_time, 1000)); seq_printf(seq, " %lu shrunk objects\n", es_stats->es_stats_shrunk); if (inode_cnt) seq_printf(seq, "maximum:\n %lu inode (%u objects, %u reclaimable)\n" " %llu us max scan time\n", max->vfs_inode.i_ino, max->i_es_all_nr, max->i_es_shk_nr, div_u64(es_stats->es_stats_max_scan_time, 1000)); return 0; } int ext4_es_register_shrinker(struct ext4_sb_info *sbi) { int err; /* Make sure we have enough bits for physical block number */ BUILD_BUG_ON(ES_SHIFT < 48); INIT_LIST_HEAD(&sbi->s_es_list); sbi->s_es_nr_inode = 0; spin_lock_init(&sbi->s_es_lock); sbi->s_es_stats.es_stats_shrunk = 0; err = percpu_counter_init(&sbi->s_es_stats.es_stats_cache_hits, 0, GFP_KERNEL); if (err) return err; err = percpu_counter_init(&sbi->s_es_stats.es_stats_cache_misses, 0, GFP_KERNEL); if (err) goto err1; sbi->s_es_stats.es_stats_scan_time = 0; sbi->s_es_stats.es_stats_max_scan_time = 0; err = percpu_counter_init(&sbi->s_es_stats.es_stats_all_cnt, 0, GFP_KERNEL); if (err) goto err2; err = percpu_counter_init(&sbi->s_es_stats.es_stats_shk_cnt, 0, GFP_KERNEL); if (err) goto err3; sbi->s_es_shrinker = shrinker_alloc(0, "ext4-es:%s", sbi->s_sb->s_id); if (!sbi->s_es_shrinker) { err = -ENOMEM; goto err4; } sbi->s_es_shrinker->scan_objects = ext4_es_scan; sbi->s_es_shrinker->count_objects = ext4_es_count; sbi->s_es_shrinker->private_data = sbi; shrinker_register(sbi->s_es_shrinker); return 0; err4: percpu_counter_destroy(&sbi->s_es_stats.es_stats_shk_cnt); err3: percpu_counter_destroy(&sbi->s_es_stats.es_stats_all_cnt); err2: percpu_counter_destroy(&sbi->s_es_stats.es_stats_cache_misses); err1: percpu_counter_destroy(&sbi->s_es_stats.es_stats_cache_hits); return err; } void ext4_es_unregister_shrinker(struct ext4_sb_info *sbi) { percpu_counter_destroy(&sbi->s_es_stats.es_stats_cache_hits); percpu_counter_destroy(&sbi->s_es_stats.es_stats_cache_misses); percpu_counter_destroy(&sbi->s_es_stats.es_stats_all_cnt); percpu_counter_destroy(&sbi->s_es_stats.es_stats_shk_cnt); shrinker_free(sbi->s_es_shrinker); } /* * Shrink extents in given inode from ei->i_es_shrink_lblk till end. Scan at * most *nr_to_scan extents, update *nr_to_scan accordingly. * * Return 0 if we hit end of tree / interval, 1 if we exhausted nr_to_scan. * Increment *nr_shrunk by the number of reclaimed extents. Also update * ei->i_es_shrink_lblk to where we should continue scanning. */ static int es_do_reclaim_extents(struct ext4_inode_info *ei, ext4_lblk_t end, int *nr_to_scan, int *nr_shrunk) { struct inode *inode = &ei->vfs_inode; struct ext4_es_tree *tree = &ei->i_es_tree; struct extent_status *es; struct rb_node *node; es = __es_tree_search(&tree->root, ei->i_es_shrink_lblk); if (!es) goto out_wrap; while (*nr_to_scan > 0) { if (es->es_lblk > end) { ei->i_es_shrink_lblk = end + 1; return 0; } (*nr_to_scan)--; node = rb_next(&es->rb_node); if (ext4_es_must_keep(es)) goto next; if (ext4_es_is_referenced(es)) { ext4_es_clear_referenced(es); goto next; } rb_erase(&es->rb_node, &tree->root); ext4_es_free_extent(inode, es); (*nr_shrunk)++; next: if (!node) goto out_wrap; es = rb_entry(node, struct extent_status, rb_node); } ei->i_es_shrink_lblk = es->es_lblk; return 1; out_wrap: ei->i_es_shrink_lblk = 0; return 0; } static int es_reclaim_extents(struct ext4_inode_info *ei, int *nr_to_scan) { struct inode *inode = &ei->vfs_inode; int nr_shrunk = 0; ext4_lblk_t start = ei->i_es_shrink_lblk; static DEFINE_RATELIMIT_STATE(_rs, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); if (ei->i_es_shk_nr == 0) return 0; if (ext4_test_inode_state(inode, EXT4_STATE_EXT_PRECACHED) && __ratelimit(&_rs)) ext4_warning(inode->i_sb, "forced shrink of precached extents"); if (!es_do_reclaim_extents(ei, EXT_MAX_BLOCKS, nr_to_scan, &nr_shrunk) && start != 0) es_do_reclaim_extents(ei, start - 1, nr_to_scan, &nr_shrunk); ei->i_es_tree.cache_es = NULL; return nr_shrunk; } /* * Called to support EXT4_IOC_CLEAR_ES_CACHE. We can only remove * discretionary entries from the extent status cache. (Some entries * must be present for proper operations.) */ void ext4_clear_inode_es(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); struct extent_status *es; struct ext4_es_tree *tree; struct rb_node *node; write_lock(&ei->i_es_lock); tree = &EXT4_I(inode)->i_es_tree; tree->cache_es = NULL; node = rb_first(&tree->root); while (node) { es = rb_entry(node, struct extent_status, rb_node); node = rb_next(node); if (!ext4_es_must_keep(es)) { rb_erase(&es->rb_node, &tree->root); ext4_es_free_extent(inode, es); } } ext4_clear_inode_state(inode, EXT4_STATE_EXT_PRECACHED); write_unlock(&ei->i_es_lock); } #ifdef ES_DEBUG__ static void ext4_print_pending_tree(struct inode *inode) { struct ext4_pending_tree *tree; struct rb_node *node; struct pending_reservation *pr; printk(KERN_DEBUG "pending reservations for inode %lu:", inode->i_ino); tree = &EXT4_I(inode)->i_pending_tree; node = rb_first(&tree->root); while (node) { pr = rb_entry(node, struct pending_reservation, rb_node); printk(KERN_DEBUG " %u", pr->lclu); node = rb_next(node); } printk(KERN_DEBUG "\n"); } #else #define ext4_print_pending_tree(inode) #endif int __init ext4_init_pending(void) { ext4_pending_cachep = KMEM_CACHE(pending_reservation, SLAB_RECLAIM_ACCOUNT); if (ext4_pending_cachep == NULL) return -ENOMEM; return 0; } void ext4_exit_pending(void) { kmem_cache_destroy(ext4_pending_cachep); } void ext4_init_pending_tree(struct ext4_pending_tree *tree) { tree->root = RB_ROOT; } /* * __get_pending - retrieve a pointer to a pending reservation * * @inode - file containing the pending cluster reservation * @lclu - logical cluster of interest * * Returns a pointer to a pending reservation if it's a member of * the set, and NULL if not. Must be called holding i_es_lock. */ static struct pending_reservation *__get_pending(struct inode *inode, ext4_lblk_t lclu) { struct ext4_pending_tree *tree; struct rb_node *node; struct pending_reservation *pr = NULL; tree = &EXT4_I(inode)->i_pending_tree; node = (&tree->root)->rb_node; while (node) { pr = rb_entry(node, struct pending_reservation, rb_node); if (lclu < pr->lclu) node = node->rb_left; else if (lclu > pr->lclu) node = node->rb_right; else if (lclu == pr->lclu) return pr; } return NULL; } /* * __insert_pending - adds a pending cluster reservation to the set of * pending reservations * * @inode - file containing the cluster * @lblk - logical block in the cluster to be added * @prealloc - preallocated pending entry * * Returns 1 on successful insertion and -ENOMEM on failure. If the * pending reservation is already in the set, returns successfully. */ static int __insert_pending(struct inode *inode, ext4_lblk_t lblk, struct pending_reservation **prealloc) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_pending_tree *tree = &EXT4_I(inode)->i_pending_tree; struct rb_node **p = &tree->root.rb_node; struct rb_node *parent = NULL; struct pending_reservation *pr; ext4_lblk_t lclu; int ret = 0; lclu = EXT4_B2C(sbi, lblk); /* search to find parent for insertion */ while (*p) { parent = *p; pr = rb_entry(parent, struct pending_reservation, rb_node); if (lclu < pr->lclu) { p = &(*p)->rb_left; } else if (lclu > pr->lclu) { p = &(*p)->rb_right; } else { /* pending reservation already inserted */ goto out; } } if (likely(*prealloc == NULL)) { pr = __alloc_pending(false); if (!pr) { ret = -ENOMEM; goto out; } } else { pr = *prealloc; *prealloc = NULL; } pr->lclu = lclu; rb_link_node(&pr->rb_node, parent, p); rb_insert_color(&pr->rb_node, &tree->root); ret = 1; out: return ret; } /* * __remove_pending - removes a pending cluster reservation from the set * of pending reservations * * @inode - file containing the cluster * @lblk - logical block in the pending cluster reservation to be removed * * Returns successfully if pending reservation is not a member of the set. */ static void __remove_pending(struct inode *inode, ext4_lblk_t lblk) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct pending_reservation *pr; struct ext4_pending_tree *tree; pr = __get_pending(inode, EXT4_B2C(sbi, lblk)); if (pr != NULL) { tree = &EXT4_I(inode)->i_pending_tree; rb_erase(&pr->rb_node, &tree->root); __free_pending(pr); } } /* * ext4_remove_pending - removes a pending cluster reservation from the set * of pending reservations * * @inode - file containing the cluster * @lblk - logical block in the pending cluster reservation to be removed * * Locking for external use of __remove_pending. */ void ext4_remove_pending(struct inode *inode, ext4_lblk_t lblk) { struct ext4_inode_info *ei = EXT4_I(inode); write_lock(&ei->i_es_lock); __remove_pending(inode, lblk); write_unlock(&ei->i_es_lock); } /* * ext4_is_pending - determine whether a cluster has a pending reservation * on it * * @inode - file containing the cluster * @lblk - logical block in the cluster * * Returns true if there's a pending reservation for the cluster in the * set of pending reservations, and false if not. */ bool ext4_is_pending(struct inode *inode, ext4_lblk_t lblk) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_inode_info *ei = EXT4_I(inode); bool ret; read_lock(&ei->i_es_lock); ret = (bool)(__get_pending(inode, EXT4_B2C(sbi, lblk)) != NULL); read_unlock(&ei->i_es_lock); return ret; } /* * ext4_es_insert_delayed_extent - adds some delayed blocks to the extents * status tree, adding a pending reservation * where needed * * @inode - file containing the newly added block * @lblk - start logical block to be added * @len - length of blocks to be added * @lclu_allocated/end_allocated - indicates whether a physical cluster has * been allocated for the logical cluster * that contains the start/end block. Note that * end_allocated should always be set to false * if the start and the end block are in the * same cluster */ void ext4_es_insert_delayed_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len, bool lclu_allocated, bool end_allocated) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct extent_status newes; ext4_lblk_t end = lblk + len - 1; int err1 = 0, err2 = 0, err3 = 0; struct extent_status *es1 = NULL; struct extent_status *es2 = NULL; struct pending_reservation *pr1 = NULL; struct pending_reservation *pr2 = NULL; if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) return; es_debug("add [%u/%u) delayed to extent status tree of inode %lu\n", lblk, len, inode->i_ino); if (!len) return; WARN_ON_ONCE((EXT4_B2C(sbi, lblk) == EXT4_B2C(sbi, end)) && end_allocated); newes.es_lblk = lblk; newes.es_len = len; ext4_es_store_pblock_status(&newes, ~0, EXTENT_STATUS_DELAYED); trace_ext4_es_insert_delayed_extent(inode, &newes, lclu_allocated, end_allocated); ext4_es_insert_extent_check(inode, &newes); retry: if (err1 && !es1) es1 = __es_alloc_extent(true); if ((err1 || err2) && !es2) es2 = __es_alloc_extent(true); if (err1 || err2 || err3 < 0) { if (lclu_allocated && !pr1) pr1 = __alloc_pending(true); if (end_allocated && !pr2) pr2 = __alloc_pending(true); } write_lock(&EXT4_I(inode)->i_es_lock); err1 = __es_remove_extent(inode, lblk, end, NULL, es1); if (err1 != 0) goto error; /* Free preallocated extent if it didn't get used. */ if (es1) { if (!es1->es_len) __es_free_extent(es1); es1 = NULL; } err2 = __es_insert_extent(inode, &newes, es2); if (err2 != 0) goto error; /* Free preallocated extent if it didn't get used. */ if (es2) { if (!es2->es_len) __es_free_extent(es2); es2 = NULL; } if (lclu_allocated) { err3 = __insert_pending(inode, lblk, &pr1); if (err3 < 0) goto error; if (pr1) { __free_pending(pr1); pr1 = NULL; } } if (end_allocated) { err3 = __insert_pending(inode, end, &pr2); if (err3 < 0) goto error; if (pr2) { __free_pending(pr2); pr2 = NULL; } } error: write_unlock(&EXT4_I(inode)->i_es_lock); if (err1 || err2 || err3 < 0) goto retry; ext4_es_print_tree(inode); ext4_print_pending_tree(inode); return; } /* * __revise_pending - makes, cancels, or leaves unchanged pending cluster * reservations for a specified block range depending * upon the presence or absence of delayed blocks * outside the range within clusters at the ends of the * range * * @inode - file containing the range * @lblk - logical block defining the start of range * @len - length of range in blocks * @prealloc - preallocated pending entry * * Used after a newly allocated extent is added to the extents status tree. * Requires that the extents in the range have either written or unwritten * status. Must be called while holding i_es_lock. Returns number of new * inserts pending cluster on insert pendings, returns 0 on remove pendings, * return -ENOMEM on failure. */ static int __revise_pending(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len, struct pending_reservation **prealloc) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); ext4_lblk_t end = lblk + len - 1; ext4_lblk_t first, last; bool f_del = false, l_del = false; int pendings = 0; int ret = 0; if (len == 0) return 0; /* * Two cases - block range within single cluster and block range * spanning two or more clusters. Note that a cluster belonging * to a range starting and/or ending on a cluster boundary is treated * as if it does not contain a delayed extent. The new range may * have allocated space for previously delayed blocks out to the * cluster boundary, requiring that any pre-existing pending * reservation be canceled. Because this code only looks at blocks * outside the range, it should revise pending reservations * correctly even if the extent represented by the range can't be * inserted in the extents status tree due to ENOSPC. */ if (EXT4_B2C(sbi, lblk) == EXT4_B2C(sbi, end)) { first = EXT4_LBLK_CMASK(sbi, lblk); if (first != lblk) f_del = __es_scan_range(inode, &ext4_es_is_delayed, first, lblk - 1); if (f_del) { ret = __insert_pending(inode, first, prealloc); if (ret < 0) goto out; pendings += ret; } else { last = EXT4_LBLK_CMASK(sbi, end) + sbi->s_cluster_ratio - 1; if (last != end) l_del = __es_scan_range(inode, &ext4_es_is_delayed, end + 1, last); if (l_del) { ret = __insert_pending(inode, last, prealloc); if (ret < 0) goto out; pendings += ret; } else __remove_pending(inode, last); } } else { first = EXT4_LBLK_CMASK(sbi, lblk); if (first != lblk) f_del = __es_scan_range(inode, &ext4_es_is_delayed, first, lblk - 1); if (f_del) { ret = __insert_pending(inode, first, prealloc); if (ret < 0) goto out; pendings += ret; } else __remove_pending(inode, first); last = EXT4_LBLK_CMASK(sbi, end) + sbi->s_cluster_ratio - 1; if (last != end) l_del = __es_scan_range(inode, &ext4_es_is_delayed, end + 1, last); if (l_del) { ret = __insert_pending(inode, last, prealloc); if (ret < 0) goto out; pendings += ret; } else __remove_pending(inode, last); } out: return (ret < 0) ? ret : pendings; }
Information contained on this website is for historical information purposes only and does not indicate or represent copyright ownership.
Created with Cregit http://github.com/cregit/cregit
Version 2.0-RC1