Something went wrong. Try again.
Linux kernel mirror (for testing) git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
Something went wrong. Try again.
123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773774775776777778779780781782783784785786787788789790791792793794795796797798799800801802803804805806807808809810811812813814815816817818819820821822823824825826827828829830831832833834835836837838839840841842843844845846847848849850851852853854855856857858859860861862863864865866867868869870871872873874875876877878879880881882883884885886887888889890891892893894895896897898899900901902903904905906907908909910911912913914915916917918919920921922923924925926927928929930931932933934935936937938939940941942943944945946947948949950951952953954955956957958959960961962963964965966967968969970971972973974975976977978979980981982983984985986987988989990991992993994995996997998999100010011002100310041005100610071008100910101011101210131014101510161017101810191020102110221023102410251026102710281029103010311032103310341035103610371038103910401041104210431044104510461047104810491050105110521053105410551056105710581059106010611062106310641065106610671068106910701071107210731074107510761077107810791080108110821083108410851086108710881089109010911092109310941095109610971098109911001101110211031104110511061107110811091110111111121113111411151116111711181119112011211122112311241125112611271128112911301131113211331134113511361137113811391140114111421143114411451146114711481149115011511152115311541155115611571158115911601161116211631164116511661167116811691170117111721173117411751176117711781179118011811182118311841185118611871188118911901191119211931194119511961197119811991200120112021203120412051206120712081209121012111212121312141215121612171218121912201221122212231224122512261227122812291230123112321233123412351236123712381239124012411242124312441245124612471248124912501251125212531254125512561257125812591260126112621263126412651266126712681269127012711272127312741275127612771278127912801281128212831284128512861287128812891290129112921293129412951296129712981299130013011302130313041305130613071308130913101311131213131314131513161317131813191320132113221323132413251326132713281329133013311332133313341335133613371338133913401341134213431344134513461347134813491350135113521353135413551356135713581359136013611362136313641365136613671368136913701371137213731374137513761377137813791380138113821383138413851386138713881389139013911392139313941395139613971398139914001401140214031404140514061407140814091410141114121413141414151416141714181419142014211422142314241425142614271428142914301431143214331434143514361437143814391440144114421443144414451446144714481449145014511452145314541455145614571458145914601461146214631464146514661467146814691470147114721473147414751476147714781479148014811482148314841485148614871488148914901491149214931494149514961497149814991500150115021503150415051506150715081509151015111512151315141515151615171518151915201521152215231524152515261527152815291530153115321533153415351536153715381539154015411542154315441545154615471548154915501551155215531554155515561557155815591560156115621563156415651566156715681569157015711572157315741575157615771578157915801581158215831584158515861587158815891590159115921593159415951596159715981599160016011602160316041605160616071608160916101611161216131614161516161617161816191620162116221623162416251626162716281629163016311632163316341635163616371638163916401641164216431644164516461647164816491650165116521653165416551656165716581659166016611662166316641665166616671668166916701671167216731674167516761677167816791680168116821683168416851686168716881689169016911692169316941695169616971698169917001701170217031704170517061707170817091710171117121713171417151716171717181719172017211722172317241725172617271728172917301731173217331734173517361737173817391740174117421743174417451746174717481749175017511752175317541755175617571758175917601761176217631764176517661767176817691770177117721773177417751776177717781779178017811782178317841785178617871788178917901791179217931794179517961797179817991800180118021803180418051806180718081809181018111812181318141815181618171818181918201821182218231824182518261827182818291830183118321833183418351836183718381839184018411842184318441845184618471848184918501851185218531854185518561857185818591860186118621863186418651866186718681869187018711872187318741875187618771878187918801881188218831884188518861887188818891890189118921893189418951896189718981899190019011902190319041905190619071908190919101911191219131914191519161917191819191920192119221923192419251926192719281929193019311932193319341935193619371938193919401941194219431944194519461947194819491950195119521953195419551956195719581959196019611962196319641965196619671968196919701971197219731974197519761977197819791980198119821983198419851986198719881989199019911992199319941995199619971998199920002001// SPDX-License-Identifier: LGPL-2.1/* * Copyright (c) 2012 Taobao. * Written by Tao Ma <boyu.mt@taobao.com> */
#include <linux/iomap.h>#include <linux/fiemap.h>#include <linux/namei.h>#include <linux/iversion.h>#include <linux/sched/mm.h>
#include "ext4_jbd2.h"#include "ext4.h"#include "xattr.h"#include "truncate.h"
#define EXT4_XATTR_SYSTEM_DATA "data"#define EXT4_MIN_INLINE_DATA_SIZE ((sizeof(__le32) * EXT4_N_BLOCKS))#define EXT4_INLINE_DOTDOT_OFFSET 2#define EXT4_INLINE_DOTDOT_SIZE 4
static int ext4_da_convert_inline_data_to_extent(struct address_space *mapping, struct inode *inode, void **fsdata);
static int ext4_get_inline_size(struct inode *inode){ if (EXT4_I(inode)->i_inline_off) return EXT4_I(inode)->i_inline_size;
return 0;}
static int get_max_inline_xattr_value_size(struct inode *inode, struct ext4_iloc *iloc){ struct ext4_xattr_ibody_header *header; struct ext4_xattr_entry *entry; struct ext4_inode *raw_inode; void *end; int free, min_offs;
if (!EXT4_INODE_HAS_XATTR_SPACE(inode)) return 0;
min_offs = EXT4_SB(inode->i_sb)->s_inode_size - EXT4_GOOD_OLD_INODE_SIZE - EXT4_I(inode)->i_extra_isize - sizeof(struct ext4_xattr_ibody_header);
/* * We need to subtract another sizeof(__u32) since an in-inode xattr * needs an empty 4 bytes to indicate the gap between the xattr entry * and the name/value pair. */ if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR)) return EXT4_XATTR_SIZE(min_offs - EXT4_XATTR_LEN(strlen(EXT4_XATTR_SYSTEM_DATA)) - EXT4_XATTR_ROUND - sizeof(__u32));
raw_inode = ext4_raw_inode(iloc); header = IHDR(inode, raw_inode); entry = IFIRST(header); end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size;
/* Compute min_offs. */ while (!IS_LAST_ENTRY(entry)) { void *next = EXT4_XATTR_NEXT(entry);
if (next >= end) { EXT4_ERROR_INODE(inode, "corrupt xattr in inline inode"); return 0; } if (!entry->e_value_inum && entry->e_value_size) { size_t offs = le16_to_cpu(entry->e_value_offs); if (offs < min_offs) min_offs = offs; } entry = next; } free = min_offs - ((void *)entry - (void *)IFIRST(header)) - sizeof(__u32);
if (EXT4_I(inode)->i_inline_off) { entry = (struct ext4_xattr_entry *) ((void *)raw_inode + EXT4_I(inode)->i_inline_off);
free += EXT4_XATTR_SIZE(le32_to_cpu(entry->e_value_size)); goto out; }
free -= EXT4_XATTR_LEN(strlen(EXT4_XATTR_SYSTEM_DATA));
if (free > EXT4_XATTR_ROUND) free = EXT4_XATTR_SIZE(free - EXT4_XATTR_ROUND); else free = 0;
out: return free;}
/* * Get the maximum size we now can store in an inode. * If we can't find the space for a xattr entry, don't use the space * of the extents since we have no space to indicate the inline data. */int ext4_get_max_inline_size(struct inode *inode){ int error, max_inline_size; struct ext4_iloc iloc;
if (EXT4_I(inode)->i_extra_isize == 0) return 0;
error = ext4_get_inode_loc(inode, &iloc); if (error) { ext4_error_inode_err(inode, __func__, __LINE__, 0, -error, "can't get inode location %llu", inode->i_ino); return 0; }
down_read(&EXT4_I(inode)->xattr_sem); max_inline_size = get_max_inline_xattr_value_size(inode, &iloc); up_read(&EXT4_I(inode)->xattr_sem);
brelse(iloc.bh);
if (!max_inline_size) return 0;
return max_inline_size + EXT4_MIN_INLINE_DATA_SIZE;}
/* * this function does not take xattr_sem, which is OK because it is * currently only used in a code path coming form ext4_iget, before * the new inode has been unlocked */int ext4_find_inline_data_nolock(struct inode *inode){ struct ext4_xattr_ibody_find is = { .s = { .not_found = -ENODATA, }, }; struct ext4_xattr_info i = { .name_index = EXT4_XATTR_INDEX_SYSTEM, .name = EXT4_XATTR_SYSTEM_DATA, }; int error;
if (EXT4_I(inode)->i_extra_isize == 0) return 0;
error = ext4_get_inode_loc(inode, &is.iloc); if (error) return error;
error = ext4_xattr_ibody_find(inode, &i, &is); if (error) goto out;
if (!is.s.not_found) { if (is.s.here->e_value_inum) { EXT4_ERROR_INODE(inode, "inline data xattr refers " "to an external xattr inode"); error = -EFSCORRUPTED; goto out; } EXT4_I(inode)->i_inline_off = (u16)((void *)is.s.here - (void *)ext4_raw_inode(&is.iloc)); EXT4_I(inode)->i_inline_size = EXT4_MIN_INLINE_DATA_SIZE + le32_to_cpu(is.s.here->e_value_size); }out: brelse(is.iloc.bh); return error;}
static int ext4_read_inline_data(struct inode *inode, void *buffer, unsigned int len, struct ext4_iloc *iloc){ struct ext4_xattr_entry *entry; struct ext4_xattr_ibody_header *header; int cp_len = 0; struct ext4_inode *raw_inode;
if (!len) return 0;
BUG_ON(len > EXT4_I(inode)->i_inline_size);
cp_len = min_t(unsigned int, len, EXT4_MIN_INLINE_DATA_SIZE);
raw_inode = ext4_raw_inode(iloc); memcpy(buffer, (void *)(raw_inode->i_block), cp_len);
len -= cp_len; buffer += cp_len;
if (!len) goto out;
header = IHDR(inode, raw_inode); entry = (struct ext4_xattr_entry *)((void *)raw_inode + EXT4_I(inode)->i_inline_off); len = min_t(unsigned int, len, (unsigned int)le32_to_cpu(entry->e_value_size));
memcpy(buffer, (void *)IFIRST(header) + le16_to_cpu(entry->e_value_offs), len); cp_len += len;
out: return cp_len;}
/* * write the buffer to the inline inode. * If 'create' is set, we don't need to do the extra copy in the xattr * value since it is already handled by ext4_xattr_ibody_set. * That saves us one memcpy. */static void ext4_write_inline_data(struct inode *inode, struct ext4_iloc *iloc, void *buffer, loff_t pos, unsigned int len){ struct ext4_xattr_entry *entry; struct ext4_xattr_ibody_header *header; struct ext4_inode *raw_inode; int cp_len = 0;
if (unlikely(ext4_emergency_state(inode->i_sb))) return;
BUG_ON(!EXT4_I(inode)->i_inline_off); BUG_ON(pos + len > EXT4_I(inode)->i_inline_size);
raw_inode = ext4_raw_inode(iloc); buffer += pos;
if (pos < EXT4_MIN_INLINE_DATA_SIZE) { cp_len = pos + len > EXT4_MIN_INLINE_DATA_SIZE ? EXT4_MIN_INLINE_DATA_SIZE - pos : len; memcpy((void *)raw_inode->i_block + pos, buffer, cp_len);
len -= cp_len; buffer += cp_len; pos += cp_len; }
if (!len) return;
pos -= EXT4_MIN_INLINE_DATA_SIZE; header = IHDR(inode, raw_inode); entry = (struct ext4_xattr_entry *)((void *)raw_inode + EXT4_I(inode)->i_inline_off);
memcpy((void *)IFIRST(header) + le16_to_cpu(entry->e_value_offs) + pos, buffer, len);}
static int ext4_create_inline_data(handle_t *handle, struct inode *inode, unsigned len){ int error; void *value = NULL; struct ext4_xattr_ibody_find is = { .s = { .not_found = -ENODATA, }, }; struct ext4_xattr_info i = { .name_index = EXT4_XATTR_INDEX_SYSTEM, .name = EXT4_XATTR_SYSTEM_DATA, };
error = ext4_get_inode_loc(inode, &is.iloc); if (error) return error;
BUFFER_TRACE(is.iloc.bh, "get_write_access"); error = ext4_journal_get_write_access(handle, inode->i_sb, is.iloc.bh, EXT4_JTR_NONE); if (error) goto out;
if (len > EXT4_MIN_INLINE_DATA_SIZE) { value = EXT4_ZERO_XATTR_VALUE; len -= EXT4_MIN_INLINE_DATA_SIZE; } else { value = ""; len = 0; }
/* Insert the xttr entry. */ i.value = value; i.value_len = len;
error = ext4_xattr_ibody_find(inode, &i, &is); if (error) goto out;
if (!is.s.not_found) { EXT4_ERROR_INODE(inode, "unexpected inline data xattr"); error = -EFSCORRUPTED; goto out; }
error = ext4_xattr_ibody_set(handle, inode, &i, &is); if (error) { if (error == -ENOSPC) ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); goto out; }
memset((void *)ext4_raw_inode(&is.iloc)->i_block, 0, EXT4_MIN_INLINE_DATA_SIZE);
EXT4_I(inode)->i_inline_off = (u16)((void *)is.s.here - (void *)ext4_raw_inode(&is.iloc)); EXT4_I(inode)->i_inline_size = len + EXT4_MIN_INLINE_DATA_SIZE; ext4_clear_inode_flag(inode, EXT4_INODE_EXTENTS); ext4_set_inode_flag(inode, EXT4_INODE_INLINE_DATA); get_bh(is.iloc.bh); error = ext4_mark_iloc_dirty(handle, inode, &is.iloc);
out: brelse(is.iloc.bh); return error;}
static int ext4_update_inline_data(handle_t *handle, struct inode *inode, unsigned int len){ int error; void *value = NULL; struct ext4_xattr_ibody_find is = { .s = { .not_found = -ENODATA, }, }; struct ext4_xattr_info i = { .name_index = EXT4_XATTR_INDEX_SYSTEM, .name = EXT4_XATTR_SYSTEM_DATA, };
/* If the old space is ok, write the data directly. */ if (len <= EXT4_I(inode)->i_inline_size) return 0;
error = ext4_get_inode_loc(inode, &is.iloc); if (error) return error;
error = ext4_xattr_ibody_find(inode, &i, &is); if (error) goto out;
if (is.s.not_found) { EXT4_ERROR_INODE(inode, "missing inline data xattr"); error = -EFSCORRUPTED; goto out; }
len -= EXT4_MIN_INLINE_DATA_SIZE; value = kzalloc(len, GFP_NOFS); if (!value) { error = -ENOMEM; goto out; }
error = ext4_xattr_ibody_get(inode, i.name_index, i.name, value, len); if (error < 0) goto out;
BUFFER_TRACE(is.iloc.bh, "get_write_access"); error = ext4_journal_get_write_access(handle, inode->i_sb, is.iloc.bh, EXT4_JTR_NONE); if (error) goto out;
/* Update the xattr entry. */ i.value = value; i.value_len = len;
error = ext4_xattr_ibody_set(handle, inode, &i, &is); if (error) goto out;
EXT4_I(inode)->i_inline_off = (u16)((void *)is.s.here - (void *)ext4_raw_inode(&is.iloc)); EXT4_I(inode)->i_inline_size = EXT4_MIN_INLINE_DATA_SIZE + le32_to_cpu(is.s.here->e_value_size); ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); get_bh(is.iloc.bh); error = ext4_mark_iloc_dirty(handle, inode, &is.iloc);
out: kfree(value); brelse(is.iloc.bh); return error;}
static int ext4_prepare_inline_data(handle_t *handle, struct inode *inode, loff_t len){ int ret, size, no_expand; struct ext4_inode_info *ei = EXT4_I(inode);
if (!ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) return -ENOSPC;
size = ext4_get_max_inline_size(inode); if (size < len) return -ENOSPC;
ext4_write_lock_xattr(inode, &no_expand); /* * ei->i_inline_size may have changed since the initial check * if other xattrs were added. Recalculate to ensure * ext4_update_inline_data() validates against current capacity. */ (void) ext4_find_inline_data_nolock(inode); if (ei->i_inline_off) ret = ext4_update_inline_data(handle, inode, len); else ret = ext4_create_inline_data(handle, inode, len);
ext4_write_unlock_xattr(inode, &no_expand); return ret;}
static int ext4_destroy_inline_data_nolock(handle_t *handle, struct inode *inode){ struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_xattr_ibody_find is = { .s = { .not_found = 0, }, }; struct ext4_xattr_info i = { .name_index = EXT4_XATTR_INDEX_SYSTEM, .name = EXT4_XATTR_SYSTEM_DATA, .value = NULL, .value_len = 0, }; int error;
if (!ei->i_inline_off) return 0;
down_write(&ei->i_data_sem);
error = ext4_get_inode_loc(inode, &is.iloc); if (error) { up_write(&ei->i_data_sem); return error; }
error = ext4_xattr_ibody_find(inode, &i, &is); if (error) goto out;
BUFFER_TRACE(is.iloc.bh, "get_write_access"); error = ext4_journal_get_write_access(handle, inode->i_sb, is.iloc.bh, EXT4_JTR_NONE); if (error) goto out;
error = ext4_xattr_ibody_set(handle, inode, &i, &is); if (error) goto out;
memset((void *)ext4_raw_inode(&is.iloc)->i_block, 0, EXT4_MIN_INLINE_DATA_SIZE); memset(ei->i_data, 0, EXT4_MIN_INLINE_DATA_SIZE);
if (ext4_has_feature_extents(inode->i_sb)) { if (S_ISDIR(inode->i_mode) || S_ISREG(inode->i_mode) || S_ISLNK(inode->i_mode)) { ext4_set_inode_flag(inode, EXT4_INODE_EXTENTS); ext4_ext_tree_init(handle, inode); } } ext4_clear_inode_flag(inode, EXT4_INODE_INLINE_DATA);
get_bh(is.iloc.bh); error = ext4_mark_iloc_dirty(handle, inode, &is.iloc);
EXT4_I(inode)->i_inline_off = 0; EXT4_I(inode)->i_inline_size = 0; ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);out: brelse(is.iloc.bh); if (error == -ENODATA) error = 0; up_write(&ei->i_data_sem); return error;}
static int ext4_read_inline_folio(struct inode *inode, struct folio *folio){ void *kaddr; int ret = 0; size_t len; struct ext4_iloc iloc;
BUG_ON(!folio_test_locked(folio)); BUG_ON(!ext4_has_inline_data(inode)); BUG_ON(folio->index);
if (!EXT4_I(inode)->i_inline_off) { ext4_warning(inode->i_sb, "inode %llu doesn't have inline data.", inode->i_ino); goto out; }
ret = ext4_get_inode_loc(inode, &iloc); if (ret) goto out;
len = min_t(size_t, ext4_get_inline_size(inode), i_size_read(inode));
if (len > PAGE_SIZE) { ext4_error_inode(inode, __func__, __LINE__, 0, "inline size %zu exceeds PAGE_SIZE", len); ret = -EFSCORRUPTED; brelse(iloc.bh); goto out; }
kaddr = kmap_local_folio(folio, 0); ret = ext4_read_inline_data(inode, kaddr, len, &iloc); kaddr = folio_zero_tail(folio, len, kaddr + len); kunmap_local(kaddr); folio_mark_uptodate(folio); brelse(iloc.bh);
out: return ret;}
int ext4_readpage_inline(struct inode *inode, struct folio *folio){ int ret = 0;
down_read(&EXT4_I(inode)->xattr_sem); if (!ext4_has_inline_data(inode)) { up_read(&EXT4_I(inode)->xattr_sem); return -EAGAIN; }
/* * Current inline data can only exist in the 1st page, * So for all the other pages, just set them uptodate. */ if (!folio->index) ret = ext4_read_inline_folio(inode, folio); else if (!folio_test_uptodate(folio)) { folio_zero_segment(folio, 0, folio_size(folio)); folio_mark_uptodate(folio); }
up_read(&EXT4_I(inode)->xattr_sem);
folio_unlock(folio); return ret >= 0 ? 0 : ret;}
static int ext4_convert_inline_data_to_extent(struct address_space *mapping, struct inode *inode){ int ret, needed_blocks, no_expand; handle_t *handle = NULL; int retries = 0, sem_held = 0; struct folio *folio = NULL; unsigned from, to; struct ext4_iloc iloc;
if (!ext4_has_inline_data(inode)) { /* * clear the flag so that no new write * will trap here again. */ ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); return 0; }
needed_blocks = ext4_chunk_trans_extent(inode, 1);
ret = ext4_get_inode_loc(inode, &iloc); if (ret) return ret;
retry: handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, needed_blocks); if (IS_ERR(handle)) { ret = PTR_ERR(handle); handle = NULL; goto out; }
/* We cannot recurse into the filesystem as the transaction is already * started */ folio = __filemap_get_folio(mapping, 0, FGP_WRITEBEGIN | FGP_NOFS, mapping_gfp_mask(mapping)); if (IS_ERR(folio)) { ret = PTR_ERR(folio); goto out_nofolio; }
ext4_write_lock_xattr(inode, &no_expand); sem_held = 1; /* If some one has already done this for us, just exit. */ if (!ext4_has_inline_data(inode)) { ret = 0; goto out; }
from = 0; to = ext4_get_inline_size(inode); if (!folio_test_uptodate(folio)) { ret = ext4_read_inline_folio(inode, folio); if (ret < 0) goto out; }
ext4_fc_track_inode(handle, inode); ret = ext4_destroy_inline_data_nolock(handle, inode); if (ret) goto out;
if (ext4_should_dioread_nolock(inode)) { ret = ext4_block_write_begin(handle, folio, from, to, ext4_get_block_unwritten); } else ret = ext4_block_write_begin(handle, folio, from, to, ext4_get_block); clear_buffer_new(folio_buffers(folio));
if (!ret && ext4_should_journal_data(inode)) { ret = ext4_walk_page_buffers(handle, inode, folio_buffers(folio), from, to, NULL, do_journal_get_write_access); }
if (ret) { folio_unlock(folio); folio_put(folio); folio = NULL; ext4_orphan_add(handle, inode); ext4_write_unlock_xattr(inode, &no_expand); sem_held = 0; ext4_journal_stop(handle); handle = NULL; ext4_truncate_failed_write(inode); /* * If truncate failed early the inode might * still be on the orphan list; we need to * make sure the inode is removed from the * orphan list in that case. */ if (inode->i_nlink) ext4_orphan_del(NULL, inode); }
if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) goto retry;
if (folio) block_commit_write(folio, from, to);out: if (folio) { folio_unlock(folio); folio_put(folio); }out_nofolio: if (sem_held) ext4_write_unlock_xattr(inode, &no_expand); if (handle) ext4_journal_stop(handle); brelse(iloc.bh); return ret;}
/* * Prepare the write for the inline data. * If the data can be written into the inode, we just read * the page and make it uptodate, and start the journal. * Otherwise read the page, makes it dirty so that it can be * handle in writepages(the i_disksize update is left to the * normal ext4_da_write_end). */int ext4_generic_write_inline_data(struct address_space *mapping, struct inode *inode, loff_t pos, unsigned len, struct folio **foliop, void **fsdata, bool da){ int ret; handle_t *handle; struct folio *folio; struct ext4_iloc iloc; int retries = 0;
ret = ext4_get_inode_loc(inode, &iloc); if (ret) return ret;
retry_journal: handle = ext4_journal_start(inode, EXT4_HT_INODE, 1); if (IS_ERR(handle)) { ret = PTR_ERR(handle); goto out_release_bh; }
ret = ext4_prepare_inline_data(handle, inode, pos + len); if (ret && ret != -ENOSPC) goto out_stop_journal;
if (ret == -ENOSPC) { ext4_journal_stop(handle); if (!da) { brelse(iloc.bh); /* Retry inside */ return ext4_convert_inline_data_to_extent(mapping, inode); }
ret = ext4_da_convert_inline_data_to_extent(mapping, inode, fsdata); if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) goto retry_journal; goto out_release_bh; }
folio = __filemap_get_folio(mapping, 0, FGP_WRITEBEGIN | FGP_NOFS, mapping_gfp_mask(mapping)); if (IS_ERR(folio)) { ret = PTR_ERR(folio); goto out_stop_journal; }
down_read(&EXT4_I(inode)->xattr_sem); /* Someone else had converted it to extent */ if (!ext4_has_inline_data(inode)) { ret = 0; goto out_release_folio; }
if (!folio_test_uptodate(folio)) { ret = ext4_read_inline_folio(inode, folio); if (ret < 0) goto out_release_folio; }
ret = ext4_journal_get_write_access(handle, inode->i_sb, iloc.bh, EXT4_JTR_NONE); if (ret) goto out_release_folio; *foliop = folio; up_read(&EXT4_I(inode)->xattr_sem); brelse(iloc.bh); return 1;
out_release_folio: up_read(&EXT4_I(inode)->xattr_sem); folio_unlock(folio); folio_put(folio);out_stop_journal: ext4_journal_stop(handle);out_release_bh: brelse(iloc.bh); return ret;}
/* * Try to write data in the inode. * If the inode has inline data, check whether the new write can be * in the inode also. If not, create the page the handle, move the data * to the page make it update and let the later codes create extent for it. */int ext4_try_to_write_inline_data(struct address_space *mapping, struct inode *inode, loff_t pos, unsigned len, struct folio **foliop){ if (pos + len > ext4_get_max_inline_size(inode)) return ext4_convert_inline_data_to_extent(mapping, inode); return ext4_generic_write_inline_data(mapping, inode, pos, len, foliop, NULL, false);}
int ext4_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len, unsigned copied, struct folio *folio){ handle_t *handle = ext4_journal_current_handle(); int no_expand; void *kaddr; struct ext4_iloc iloc; int ret = 0, ret2;
if (unlikely(copied < len) && !folio_test_uptodate(folio)) copied = 0;
if (likely(copied)) { ret = ext4_get_inode_loc(inode, &iloc); if (ret) { folio_unlock(folio); folio_put(folio); ext4_std_error(inode->i_sb, ret); goto out; } ext4_write_lock_xattr(inode, &no_expand); BUG_ON(!ext4_has_inline_data(inode));
/* * ei->i_inline_off may have changed since * ext4_write_begin() called * ext4_try_to_write_inline_data() */ (void) ext4_find_inline_data_nolock(inode);
kaddr = kmap_local_folio(folio, 0); ext4_write_inline_data(inode, &iloc, kaddr, pos, copied); kunmap_local(kaddr); folio_mark_uptodate(folio); /* clear dirty flag so that writepages wouldn't work for us. */ folio_clear_dirty(folio);
ext4_write_unlock_xattr(inode, &no_expand); brelse(iloc.bh);
/* * It's important to update i_size while still holding folio * lock: page writeout could otherwise come in and zero * beyond i_size. */ ext4_update_inode_size(inode, pos + copied); } folio_unlock(folio); folio_put(folio);
/* * Don't mark the inode dirty under folio lock. First, it unnecessarily * makes the holding time of folio lock longer. Second, it forces lock * ordering of folio lock and transaction start for journaling * filesystems. */ if (likely(copied)) mark_inode_dirty(inode);out: /* * If we didn't copy as much data as expected, we need to trim back * size of xattr containing inline data. */ if (pos + len > inode->i_size && ext4_can_truncate(inode)) ext4_orphan_add(handle, inode);
ret2 = ext4_journal_stop(handle); if (!ret) ret = ret2; if (pos + len > inode->i_size) { ext4_truncate_failed_write(inode); /* * If truncate failed early the inode might still be * on the orphan list; we need to make sure the inode * is removed from the orphan list in that case. */ if (inode->i_nlink) ext4_orphan_del(NULL, inode); } return ret ? ret : copied;}
/* * Try to make the page cache and handle ready for the inline data case. * We can call this function in 2 cases: * 1. The inode is created and the first write exceeds inline size. We can * clear the inode state safely. * 2. The inode has inline data, then we need to read the data, make it * update and dirty so that ext4_da_writepages can handle it. We don't * need to start the journal since the file's metadata isn't changed now. */static int ext4_da_convert_inline_data_to_extent(struct address_space *mapping, struct inode *inode, void **fsdata){ int ret = 0, inline_size; struct folio *folio;
folio = __filemap_get_folio(mapping, 0, FGP_WRITEBEGIN, mapping_gfp_mask(mapping)); if (IS_ERR(folio)) return PTR_ERR(folio);
down_read(&EXT4_I(inode)->xattr_sem); if (!ext4_has_inline_data(inode)) { ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); goto out; }
inline_size = ext4_get_inline_size(inode);
if (!folio_test_uptodate(folio)) { ret = ext4_read_inline_folio(inode, folio); if (ret < 0) goto out; }
ret = ext4_block_write_begin(NULL, folio, 0, inline_size, ext4_da_get_block_prep); if (ret) { up_read(&EXT4_I(inode)->xattr_sem); folio_unlock(folio); folio_put(folio); ext4_truncate_failed_write(inode); return ret; }
clear_buffer_new(folio_buffers(folio)); folio_mark_dirty(folio); folio_mark_uptodate(folio); ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); *fsdata = (void *)CONVERT_INLINE_DATA;
out: up_read(&EXT4_I(inode)->xattr_sem); if (folio) { folio_unlock(folio); folio_put(folio); } return ret;}
#ifdef INLINE_DIR_DEBUGvoid ext4_show_inline_dir(struct inode *dir, struct buffer_head *bh, void *inline_start, int inline_size){ int offset; unsigned short de_len; struct ext4_dir_entry_2 *de = inline_start; void *dlimit = inline_start + inline_size;
trace_printk("inode %llu\n", dir->i_ino); offset = 0; while ((void *)de < dlimit) { de_len = ext4_rec_len_from_disk(de->rec_len, inline_size); trace_printk("de: off %u rlen %u name %.*s nlen %u ino %u\n", offset, de_len, de->name_len, de->name, de->name_len, le32_to_cpu(de->inode)); if (ext4_check_dir_entry(dir, NULL, de, bh, inline_start, inline_size, offset)) BUG();
offset += de_len; de = (struct ext4_dir_entry_2 *) ((char *) de + de_len); }}#else#define ext4_show_inline_dir(dir, bh, inline_start, inline_size)#endif
/* * Add a new entry into a inline dir. * It will return -ENOSPC if no space is available, and -EIO * and -EEXIST if directory entry already exists. */static int ext4_add_dirent_to_inline(handle_t *handle, struct ext4_filename *fname, struct inode *dir, struct inode *inode, struct ext4_iloc *iloc, void *inline_start, int inline_size){ int err; struct ext4_dir_entry_2 *de;
err = ext4_find_dest_de(dir, iloc->bh, inline_start, inline_size, fname, &de); if (err) return err;
BUFFER_TRACE(iloc->bh, "get_write_access"); err = ext4_journal_get_write_access(handle, dir->i_sb, iloc->bh, EXT4_JTR_NONE); if (err) return err; ext4_insert_dentry(dir, inode, de, inline_size, fname);
ext4_show_inline_dir(dir, iloc->bh, inline_start, inline_size);
/* * XXX shouldn't update any times until successful * completion of syscall, but too many callers depend * on this. * * XXX similarly, too many callers depend on * ext4_new_inode() setting the times, but error * recovery deletes the inode, so the worst that can * happen is that the times are slightly out of date * and/or different from the directory change time. */ inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); ext4_update_dx_flag(dir); inode_inc_iversion(dir); return 1;}
static void *ext4_get_inline_xattr_pos(struct inode *inode, struct ext4_iloc *iloc){ struct ext4_xattr_entry *entry; struct ext4_xattr_ibody_header *header;
BUG_ON(!EXT4_I(inode)->i_inline_off);
header = IHDR(inode, ext4_raw_inode(iloc)); entry = (struct ext4_xattr_entry *)((void *)ext4_raw_inode(iloc) + EXT4_I(inode)->i_inline_off);
return (void *)IFIRST(header) + le16_to_cpu(entry->e_value_offs);}
/* Set the final de to cover the whole block. */void ext4_update_final_de(void *de_buf, int old_size, int new_size){ struct ext4_dir_entry_2 *de, *prev_de; void *limit; int de_len;
de = de_buf; if (old_size) { limit = de_buf + old_size; do { prev_de = de; de_len = ext4_rec_len_from_disk(de->rec_len, old_size); de_buf += de_len; de = de_buf; } while (de_buf < limit);
prev_de->rec_len = ext4_rec_len_to_disk(de_len + new_size - old_size, new_size); } else { /* this is just created, so create an empty entry. */ de->inode = 0; de->rec_len = ext4_rec_len_to_disk(new_size, new_size); }}
static int ext4_update_inline_dir(handle_t *handle, struct inode *dir, struct ext4_iloc *iloc){ int ret; int old_size = EXT4_I(dir)->i_inline_size - EXT4_MIN_INLINE_DATA_SIZE; int new_size = get_max_inline_xattr_value_size(dir, iloc);
if (new_size - old_size <= ext4_dir_rec_len(1, NULL)) return -ENOSPC;
ret = ext4_update_inline_data(handle, dir, new_size + EXT4_MIN_INLINE_DATA_SIZE); if (ret) return ret;
ext4_update_final_de(ext4_get_inline_xattr_pos(dir, iloc), old_size, EXT4_I(dir)->i_inline_size - EXT4_MIN_INLINE_DATA_SIZE); dir->i_size = EXT4_I(dir)->i_disksize = EXT4_I(dir)->i_inline_size; return 0;}
static void ext4_restore_inline_data(handle_t *handle, struct inode *inode, struct ext4_iloc *iloc, void *buf, int inline_size){ int ret;
ret = ext4_create_inline_data(handle, inode, inline_size); if (ret) { ext4_msg(inode->i_sb, KERN_EMERG, "error restoring inline_data for inode -- potential data loss! (inode %llu, error %d)", inode->i_ino, ret); return; } ext4_write_inline_data(inode, iloc, buf, 0, inline_size); ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);}
static int ext4_convert_inline_data_nolock(handle_t *handle, struct inode *inode, struct ext4_iloc *iloc){ int error; void *buf = NULL; struct buffer_head *data_bh = NULL; struct ext4_map_blocks map; int inline_size;
inline_size = ext4_get_inline_size(inode); buf = kmalloc(inline_size, GFP_NOFS); if (!buf) { error = -ENOMEM; goto out; }
error = ext4_read_inline_data(inode, buf, inline_size, iloc); if (error < 0) goto out;
/* * Make sure the inline directory entries pass checks before we try to * convert them, so that we avoid touching stuff that needs fsck. */ if (S_ISDIR(inode->i_mode)) { error = ext4_check_all_de(inode, iloc->bh, buf + EXT4_INLINE_DOTDOT_SIZE, inline_size - EXT4_INLINE_DOTDOT_SIZE); if (error) goto out; }
error = ext4_destroy_inline_data_nolock(handle, inode); if (error) goto out;
map.m_lblk = 0; map.m_len = 1; map.m_flags = 0; error = ext4_map_blocks(handle, inode, &map, EXT4_GET_BLOCKS_CREATE); if (error < 0) goto out_restore; if (!(map.m_flags & EXT4_MAP_MAPPED)) { error = -EIO; goto out_restore; }
data_bh = sb_getblk(inode->i_sb, map.m_pblk); if (!data_bh) { error = -ENOMEM; goto out_restore; }
lock_buffer(data_bh); error = ext4_journal_get_create_access(handle, inode->i_sb, data_bh, EXT4_JTR_NONE); if (error) { unlock_buffer(data_bh); error = -EIO; goto out_restore; } memset(data_bh->b_data, 0, inode->i_sb->s_blocksize);
if (!S_ISDIR(inode->i_mode)) { memcpy(data_bh->b_data, buf, inline_size); set_buffer_uptodate(data_bh); unlock_buffer(data_bh); error = ext4_handle_dirty_metadata(handle, inode, data_bh); } else { unlock_buffer(data_bh); inode->i_size = inode->i_sb->s_blocksize; i_size_write(inode, inode->i_sb->s_blocksize); EXT4_I(inode)->i_disksize = inode->i_sb->s_blocksize;
error = ext4_init_dirblock(handle, inode, data_bh, le32_to_cpu(((struct ext4_dir_entry_2 *)buf)->inode), buf + EXT4_INLINE_DOTDOT_SIZE, inline_size - EXT4_INLINE_DOTDOT_SIZE); if (!error) error = ext4_mark_inode_dirty(handle, inode); }
out_restore: if (error) ext4_restore_inline_data(handle, inode, iloc, buf, inline_size);
out: brelse(data_bh); kfree(buf); return error;}
/* * Try to add the new entry to the inline data. * If succeeds, return 0. If not, extended the inline dir and copied data to * the new created block. */int ext4_try_add_inline_entry(handle_t *handle, struct ext4_filename *fname, struct inode *dir, struct inode *inode){ int ret, ret2, inline_size, no_expand; void *inline_start; struct ext4_iloc iloc;
ret = ext4_get_inode_loc(dir, &iloc); if (ret) return ret;
ext4_write_lock_xattr(dir, &no_expand); if (!ext4_has_inline_data(dir)) goto out;
inline_start = (void *)ext4_raw_inode(&iloc)->i_block + EXT4_INLINE_DOTDOT_SIZE; inline_size = EXT4_MIN_INLINE_DATA_SIZE - EXT4_INLINE_DOTDOT_SIZE;
ret = ext4_add_dirent_to_inline(handle, fname, dir, inode, &iloc, inline_start, inline_size); if (ret != -ENOSPC) goto out;
/* check whether it can be inserted to inline xattr space. */ inline_size = EXT4_I(dir)->i_inline_size - EXT4_MIN_INLINE_DATA_SIZE; if (!inline_size) { /* Try to use the xattr space.*/ ret = ext4_update_inline_dir(handle, dir, &iloc); if (ret && ret != -ENOSPC) goto out;
inline_size = EXT4_I(dir)->i_inline_size - EXT4_MIN_INLINE_DATA_SIZE; }
if (inline_size) { inline_start = ext4_get_inline_xattr_pos(dir, &iloc);
ret = ext4_add_dirent_to_inline(handle, fname, dir, inode, &iloc, inline_start, inline_size);
if (ret != -ENOSPC) goto out; }
/* * The inline space is filled up, so create a new block for it. * As the extent tree will be created, we have to save the inline * dir first. */ ret = ext4_convert_inline_data_nolock(handle, dir, &iloc);
out: ext4_write_unlock_xattr(dir, &no_expand); ret2 = ext4_mark_inode_dirty(handle, dir); if (unlikely(ret2 && !ret)) ret = ret2; brelse(iloc.bh); return ret;}
/* * This function fills a red-black tree with information from an * inlined dir. It returns the number directory entries loaded * into the tree. If there is an error it is returned in err. */int ext4_inlinedir_to_tree(struct file *dir_file, struct inode *dir, ext4_lblk_t block, struct dx_hash_info *hinfo, __u32 start_hash, __u32 start_minor_hash, int *has_inline_data){ int err = 0, count = 0; unsigned int parent_ino; int pos; struct ext4_dir_entry_2 *de; struct inode *inode = file_inode(dir_file); int ret, inline_size = 0; struct ext4_iloc iloc; void *dir_buf = NULL; struct ext4_dir_entry_2 fake; struct fscrypt_str tmp_str;
ret = ext4_get_inode_loc(inode, &iloc); if (ret) return ret;
down_read(&EXT4_I(inode)->xattr_sem); if (!ext4_has_inline_data(inode)) { up_read(&EXT4_I(inode)->xattr_sem); *has_inline_data = 0; goto out; }
inline_size = ext4_get_inline_size(inode); dir_buf = kmalloc(inline_size, GFP_NOFS); if (!dir_buf) { ret = -ENOMEM; up_read(&EXT4_I(inode)->xattr_sem); goto out; }
ret = ext4_read_inline_data(inode, dir_buf, inline_size, &iloc); up_read(&EXT4_I(inode)->xattr_sem); if (ret < 0) goto out;
pos = 0; parent_ino = le32_to_cpu(((struct ext4_dir_entry_2 *)dir_buf)->inode); while (pos < inline_size) { /* * As inlined dir doesn't store any information about '.' and * only the inode number of '..' is stored, we have to handle * them differently. */ if (pos == 0) { fake.inode = cpu_to_le32(inode->i_ino); fake.name_len = 1; memcpy(fake.name, ".", 2); fake.rec_len = ext4_rec_len_to_disk( ext4_dir_rec_len(fake.name_len, NULL), inline_size); ext4_set_de_type(inode->i_sb, &fake, S_IFDIR); de = &fake; pos = EXT4_INLINE_DOTDOT_OFFSET; } else if (pos == EXT4_INLINE_DOTDOT_OFFSET) { fake.inode = cpu_to_le32(parent_ino); fake.name_len = 2; memcpy(fake.name, "..", 3); fake.rec_len = ext4_rec_len_to_disk( ext4_dir_rec_len(fake.name_len, NULL), inline_size); ext4_set_de_type(inode->i_sb, &fake, S_IFDIR); de = &fake; pos = EXT4_INLINE_DOTDOT_SIZE; } else { de = (struct ext4_dir_entry_2 *)(dir_buf + pos); pos += ext4_rec_len_from_disk(de->rec_len, inline_size); if (ext4_check_dir_entry(inode, dir_file, de, iloc.bh, dir_buf, inline_size, pos)) { ret = count; goto out; } }
if (ext4_hash_in_dirent(dir)) { hinfo->hash = EXT4_DIRENT_HASH(de); hinfo->minor_hash = EXT4_DIRENT_MINOR_HASH(de); } else { err = ext4fs_dirhash(dir, de->name, de->name_len, hinfo); if (err) { ret = err; goto out; } } if ((hinfo->hash < start_hash) || ((hinfo->hash == start_hash) && (hinfo->minor_hash < start_minor_hash))) continue; if (de->inode == 0) continue; tmp_str.name = de->name; tmp_str.len = de->name_len; err = ext4_htree_store_dirent(dir_file, hinfo->hash, hinfo->minor_hash, de, &tmp_str); if (err) { ret = err; goto out; } count++; } ret = count;out: kfree(dir_buf); brelse(iloc.bh); return ret;}
/* * So this function is called when the volume is mkfsed with * dir_index disabled. In order to keep f_pos persistent * after we convert from an inlined dir to a blocked based, * we just pretend that we are a normal dir and return the * offset as if '.' and '..' really take place. * */int ext4_read_inline_dir(struct file *file, struct dir_context *ctx, int *has_inline_data){ unsigned int offset, parent_ino; int i; struct ext4_dir_entry_2 *de; struct super_block *sb; struct inode *inode = file_inode(file); int ret, inline_size = 0; struct ext4_iloc iloc; void *dir_buf = NULL; int dotdot_offset, dotdot_size, extra_offset, extra_size; struct dir_private_info *info = file->private_data;
ret = ext4_get_inode_loc(inode, &iloc); if (ret) return ret;
down_read(&EXT4_I(inode)->xattr_sem); if (!ext4_has_inline_data(inode)) { up_read(&EXT4_I(inode)->xattr_sem); *has_inline_data = 0; goto out; }
inline_size = ext4_get_inline_size(inode); dir_buf = kmalloc(inline_size, GFP_NOFS); if (!dir_buf) { ret = -ENOMEM; up_read(&EXT4_I(inode)->xattr_sem); goto out; }
ret = ext4_read_inline_data(inode, dir_buf, inline_size, &iloc); up_read(&EXT4_I(inode)->xattr_sem); if (ret < 0) goto out;
ret = 0; sb = inode->i_sb; parent_ino = le32_to_cpu(((struct ext4_dir_entry_2 *)dir_buf)->inode); offset = ctx->pos;
/* * dotdot_offset and dotdot_size is the real offset and * size for ".." and "." if the dir is block based while * the real size for them are only EXT4_INLINE_DOTDOT_SIZE. * So we will use extra_offset and extra_size to indicate them * during the inline dir iteration. */ dotdot_offset = ext4_dir_rec_len(1, NULL); dotdot_size = dotdot_offset + ext4_dir_rec_len(2, NULL); extra_offset = dotdot_size - EXT4_INLINE_DOTDOT_SIZE; extra_size = extra_offset + inline_size;
/* * If the cookie has changed since the last call to * readdir(2), then we might be pointing to an invalid * dirent right now. Scan from the start of the inline * dir to make sure. */ if (!inode_eq_iversion(inode, info->cookie)) { for (i = 0; i < extra_size && i < offset;) { /* * "." is with offset 0 and * ".." is dotdot_offset. */ if (!i) { i = dotdot_offset; continue; } else if (i == dotdot_offset) { i = dotdot_size; continue; } /* for other entry, the real offset in * the buf has to be tuned accordingly. */ de = (struct ext4_dir_entry_2 *) (dir_buf + i - extra_offset); /* It's too expensive to do a full * dirent test each time round this * loop, but we do have to test at * least that it is non-zero. A * failure will be detected in the * dirent test below. */ if (ext4_rec_len_from_disk(de->rec_len, extra_size) < ext4_dir_rec_len(1, NULL)) break; i += ext4_rec_len_from_disk(de->rec_len, extra_size); } offset = i; ctx->pos = offset; info->cookie = inode_query_iversion(inode); }
while (ctx->pos < extra_size) { if (ctx->pos == 0) { if (!dir_emit(ctx, ".", 1, inode->i_ino, DT_DIR)) goto out; ctx->pos = dotdot_offset; continue; }
if (ctx->pos == dotdot_offset) { if (!dir_emit(ctx, "..", 2, parent_ino, DT_DIR)) goto out; ctx->pos = dotdot_size; continue; }
de = (struct ext4_dir_entry_2 *) (dir_buf + ctx->pos - extra_offset); if (ext4_check_dir_entry(inode, file, de, iloc.bh, dir_buf, extra_size, ctx->pos)) goto out; if (le32_to_cpu(de->inode)) { if (!dir_emit(ctx, de->name, de->name_len, le32_to_cpu(de->inode), get_dtype(sb, de->file_type))) goto out; } ctx->pos += ext4_rec_len_from_disk(de->rec_len, extra_size); }out: kfree(dir_buf); brelse(iloc.bh); return ret;}
void *ext4_read_inline_link(struct inode *inode){ struct ext4_iloc iloc; int ret, inline_size; void *link;
ret = ext4_get_inode_loc(inode, &iloc); if (ret) return ERR_PTR(ret);
ret = -ENOMEM; inline_size = ext4_get_inline_size(inode); link = kmalloc(inline_size + 1, GFP_NOFS); if (!link) goto out;
ret = ext4_read_inline_data(inode, link, inline_size, &iloc); if (ret < 0) { kfree(link); goto out; } nd_terminate_link(link, inode->i_size, ret);out: if (ret < 0) link = ERR_PTR(ret); brelse(iloc.bh); return link;}
struct buffer_head *ext4_get_first_inline_block(struct inode *inode, struct ext4_dir_entry_2 **parent_de, int *retval){ struct ext4_iloc iloc;
*retval = ext4_get_inode_loc(inode, &iloc); if (*retval) return NULL;
*parent_de = (struct ext4_dir_entry_2 *)ext4_raw_inode(&iloc)->i_block;
return iloc.bh;}
/* * Try to create the inline data for the new dir. * If it succeeds, return 0, otherwise return the error. * In case of ENOSPC, the caller should create the normal disk layout dir. */int ext4_try_create_inline_dir(handle_t *handle, struct inode *parent, struct inode *inode){ int ret, inline_size = EXT4_MIN_INLINE_DATA_SIZE; struct ext4_iloc iloc; struct ext4_dir_entry_2 *de;
ret = ext4_get_inode_loc(inode, &iloc); if (ret) return ret;
ret = ext4_prepare_inline_data(handle, inode, inline_size); if (ret) goto out;
/* * For inline dir, we only save the inode information for the ".." * and create a fake dentry to cover the left space. */ de = (struct ext4_dir_entry_2 *)ext4_raw_inode(&iloc)->i_block; de->inode = cpu_to_le32(parent->i_ino); de = (struct ext4_dir_entry_2 *)((void *)de + EXT4_INLINE_DOTDOT_SIZE); de->inode = 0; de->rec_len = ext4_rec_len_to_disk( inline_size - EXT4_INLINE_DOTDOT_SIZE, inline_size); set_nlink(inode, 2); inode->i_size = EXT4_I(inode)->i_disksize = inline_size;out: brelse(iloc.bh); return ret;}
struct buffer_head *ext4_find_inline_entry(struct inode *dir, struct ext4_filename *fname, struct ext4_dir_entry_2 **res_dir, int *has_inline_data){ struct ext4_xattr_ibody_find is = { .s = { .not_found = -ENODATA, }, }; struct ext4_xattr_info i = { .name_index = EXT4_XATTR_INDEX_SYSTEM, .name = EXT4_XATTR_SYSTEM_DATA, }; int ret; void *inline_start; int inline_size;
ret = ext4_get_inode_loc(dir, &is.iloc); if (ret) return ERR_PTR(ret);
down_read(&EXT4_I(dir)->xattr_sem);
ret = ext4_xattr_ibody_find(dir, &i, &is); if (ret) goto out;
if (!ext4_has_inline_data(dir)) { *has_inline_data = 0; goto out; }
inline_start = (void *)ext4_raw_inode(&is.iloc)->i_block + EXT4_INLINE_DOTDOT_SIZE; inline_size = EXT4_MIN_INLINE_DATA_SIZE - EXT4_INLINE_DOTDOT_SIZE; ret = ext4_search_dir(is.iloc.bh, inline_start, inline_size, dir, fname, 0, res_dir); if (ret == 1) goto out_find; if (ret < 0) goto out;
if (ext4_get_inline_size(dir) == EXT4_MIN_INLINE_DATA_SIZE) goto out;
inline_start = ext4_get_inline_xattr_pos(dir, &is.iloc); inline_size = ext4_get_inline_size(dir) - EXT4_MIN_INLINE_DATA_SIZE;
ret = ext4_search_dir(is.iloc.bh, inline_start, inline_size, dir, fname, 0, res_dir); if (ret == 1) goto out_find;
out: brelse(is.iloc.bh); if (ret < 0) is.iloc.bh = ERR_PTR(ret); else is.iloc.bh = NULL;out_find: up_read(&EXT4_I(dir)->xattr_sem); return is.iloc.bh;}
int ext4_delete_inline_entry(handle_t *handle, struct inode *dir, struct ext4_dir_entry_2 *de_del, struct buffer_head *bh, int *has_inline_data){ int err, inline_size, no_expand; struct ext4_iloc iloc; void *inline_start;
err = ext4_get_inode_loc(dir, &iloc); if (err) return err;
ext4_write_lock_xattr(dir, &no_expand); if (!ext4_has_inline_data(dir)) { *has_inline_data = 0; goto out; }
if ((void *)de_del - ((void *)ext4_raw_inode(&iloc)->i_block) < EXT4_MIN_INLINE_DATA_SIZE) { inline_start = (void *)ext4_raw_inode(&iloc)->i_block + EXT4_INLINE_DOTDOT_SIZE; inline_size = EXT4_MIN_INLINE_DATA_SIZE - EXT4_INLINE_DOTDOT_SIZE; } else { inline_start = ext4_get_inline_xattr_pos(dir, &iloc); inline_size = ext4_get_inline_size(dir) - EXT4_MIN_INLINE_DATA_SIZE; }
BUFFER_TRACE(bh, "get_write_access"); err = ext4_journal_get_write_access(handle, dir->i_sb, bh, EXT4_JTR_NONE); if (err) goto out;
err = ext4_generic_delete_entry(dir, de_del, bh, inline_start, inline_size, 0); if (err) goto out;
ext4_show_inline_dir(dir, iloc.bh, inline_start, inline_size);out: ext4_write_unlock_xattr(dir, &no_expand); if (likely(err == 0)) err = ext4_mark_inode_dirty(handle, dir); brelse(iloc.bh); if (err != -ENOENT) ext4_std_error(dir->i_sb, err); return err;}
/* * Get the inline dentry at offset. */static inline struct ext4_dir_entry_2 *ext4_get_inline_entry(struct inode *inode, struct ext4_iloc *iloc, unsigned int offset, void **inline_start, int *inline_size){ void *inline_pos;
BUG_ON(offset > ext4_get_inline_size(inode));
if (offset < EXT4_MIN_INLINE_DATA_SIZE) { inline_pos = (void *)ext4_raw_inode(iloc)->i_block; *inline_size = EXT4_MIN_INLINE_DATA_SIZE; } else { inline_pos = ext4_get_inline_xattr_pos(inode, iloc); offset -= EXT4_MIN_INLINE_DATA_SIZE; *inline_size = ext4_get_inline_size(inode) - EXT4_MIN_INLINE_DATA_SIZE; }
if (inline_start) *inline_start = inline_pos; return (struct ext4_dir_entry_2 *)(inline_pos + offset);}
bool empty_inline_dir(struct inode *dir, int *has_inline_data){ int err, inline_size; struct ext4_iloc iloc; size_t inline_len; void *inline_pos; unsigned int offset; struct ext4_dir_entry_2 *de; bool ret = false;
err = ext4_get_inode_loc(dir, &iloc); if (err) { EXT4_ERROR_INODE_ERR(dir, -err, "error %d getting inode %llu block", err, dir->i_ino); return false; }
down_read(&EXT4_I(dir)->xattr_sem); if (!ext4_has_inline_data(dir)) { *has_inline_data = 0; ret = true; goto out; }
de = (struct ext4_dir_entry_2 *)ext4_raw_inode(&iloc)->i_block; if (!le32_to_cpu(de->inode)) { ext4_warning(dir->i_sb, "bad inline directory (dir #%llu) - no `..'", dir->i_ino); goto out; }
inline_len = ext4_get_inline_size(dir); offset = EXT4_INLINE_DOTDOT_SIZE; while (offset < inline_len) { de = ext4_get_inline_entry(dir, &iloc, offset, &inline_pos, &inline_size); if (ext4_check_dir_entry(dir, NULL, de, iloc.bh, inline_pos, inline_size, offset)) { ext4_warning(dir->i_sb, "bad inline directory (dir #%llu) - " "inode %u, rec_len %u, name_len %d" "inline size %d", dir->i_ino, le32_to_cpu(de->inode), le16_to_cpu(de->rec_len), de->name_len, inline_size); goto out; } if (le32_to_cpu(de->inode)) { goto out; } offset += ext4_rec_len_from_disk(de->rec_len, inline_size); }
ret = true;out: up_read(&EXT4_I(dir)->xattr_sem); brelse(iloc.bh); return ret;}
int ext4_destroy_inline_data(handle_t *handle, struct inode *inode){ int ret, no_expand;
ext4_write_lock_xattr(inode, &no_expand); ret = ext4_destroy_inline_data_nolock(handle, inode); ext4_write_unlock_xattr(inode, &no_expand);
return ret;}
int ext4_inline_data_iomap(struct inode *inode, struct iomap *iomap){ __u64 addr; int error = -EAGAIN; struct ext4_iloc iloc;
down_read(&EXT4_I(inode)->xattr_sem); if (!ext4_has_inline_data(inode)) goto out;
error = ext4_get_inode_loc(inode, &iloc); if (error) goto out;
addr = (__u64)iloc.bh->b_blocknr << inode->i_sb->s_blocksize_bits; addr += (char *)ext4_raw_inode(&iloc) - iloc.bh->b_data; addr += offsetof(struct ext4_inode, i_block);
brelse(iloc.bh);
iomap->addr = addr; iomap->offset = 0; iomap->length = min_t(loff_t, ext4_get_inline_size(inode), i_size_read(inode)); iomap->type = IOMAP_INLINE; iomap->flags = 0;
out: up_read(&EXT4_I(inode)->xattr_sem); return error;}
int ext4_inline_data_truncate(struct inode *inode, int *has_inline){ handle_t *handle; int inline_size, value_len, needed_blocks, no_expand, err = 0; size_t i_size; void *value = NULL; struct ext4_xattr_ibody_find is = { .s = { .not_found = -ENODATA, }, }; struct ext4_xattr_info i = { .name_index = EXT4_XATTR_INDEX_SYSTEM, .name = EXT4_XATTR_SYSTEM_DATA, };
needed_blocks = ext4_chunk_trans_extent(inode, 1); handle = ext4_journal_start(inode, EXT4_HT_INODE, needed_blocks); if (IS_ERR(handle)) return PTR_ERR(handle);
ext4_write_lock_xattr(inode, &no_expand); if (!ext4_has_inline_data(inode)) { ext4_write_unlock_xattr(inode, &no_expand); *has_inline = 0; ext4_journal_stop(handle); return 0; }
if ((err = ext4_orphan_add(handle, inode)) != 0) goto out;
if ((err = ext4_get_inode_loc(inode, &is.iloc)) != 0) goto out;
down_write(&EXT4_I(inode)->i_data_sem); i_size = inode->i_size; inline_size = ext4_get_inline_size(inode); EXT4_I(inode)->i_disksize = i_size;
if (i_size < inline_size) { /* * if there's inline data to truncate and this file was * converted to extents after that inline data was written, * the extent status cache must be cleared to avoid leaving * behind stale delayed allocated extent entries */ if (!ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS);
/* Clear the content in the xattr space. */ if (inline_size > EXT4_MIN_INLINE_DATA_SIZE) { if ((err = ext4_xattr_ibody_find(inode, &i, &is)) != 0) goto out_error;
if (is.s.not_found) { EXT4_ERROR_INODE(inode, "missing inline data xattr"); err = -EFSCORRUPTED; goto out_error; }
value_len = le32_to_cpu(is.s.here->e_value_size); value = kmalloc(value_len, GFP_NOFS); if (!value) { err = -ENOMEM; goto out_error; }
err = ext4_xattr_ibody_get(inode, i.name_index, i.name, value, value_len); if (err <= 0) goto out_error;
i.value = value; i.value_len = i_size > EXT4_MIN_INLINE_DATA_SIZE ? i_size - EXT4_MIN_INLINE_DATA_SIZE : 0; err = ext4_xattr_ibody_set(handle, inode, &i, &is); if (err) goto out_error; }
/* Clear the content within i_blocks. */ if (i_size < EXT4_MIN_INLINE_DATA_SIZE) { void *p = (void *) ext4_raw_inode(&is.iloc)->i_block; memset(p + i_size, 0, EXT4_MIN_INLINE_DATA_SIZE - i_size); }
EXT4_I(inode)->i_inline_size = i_size < EXT4_MIN_INLINE_DATA_SIZE ? EXT4_MIN_INLINE_DATA_SIZE : i_size; }
out_error: up_write(&EXT4_I(inode)->i_data_sem);out: brelse(is.iloc.bh); ext4_write_unlock_xattr(inode, &no_expand); kfree(value); if (inode->i_nlink) ext4_orphan_del(handle, inode);
if (err == 0) { inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); err = ext4_mark_inode_dirty(handle, inode); if (IS_SYNC(inode)) ext4_handle_sync(handle); } ext4_journal_stop(handle); return err;}
int ext4_convert_inline_data(struct inode *inode){ int error, needed_blocks, no_expand; handle_t *handle; struct ext4_iloc iloc;
if (!ext4_has_inline_data(inode)) { ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); return 0; } else if (!ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) { /* * Inode has inline data but EXT4_STATE_MAY_INLINE_DATA is * cleared. This means we are in the middle of moving of * inline data to delay allocated block. Just force writeout * here to finish conversion. */ error = filemap_flush(inode->i_mapping); if (error) return error; if (!ext4_has_inline_data(inode)) return 0; }
needed_blocks = ext4_chunk_trans_extent(inode, 1);
iloc.bh = NULL; error = ext4_get_inode_loc(inode, &iloc); if (error) return error;
handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, needed_blocks); if (IS_ERR(handle)) { error = PTR_ERR(handle); goto out_free; }
ext4_write_lock_xattr(inode, &no_expand); if (ext4_has_inline_data(inode)) error = ext4_convert_inline_data_nolock(handle, inode, &iloc); ext4_write_unlock_xattr(inode, &no_expand); ext4_journal_stop(handle);out_free: brelse(iloc.bh); return error;}