Something went wrong. Try again.
(I'm so sorry!) Linux kernel mirror (for testing) git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
kernel os linux
Something went wrong. Try again.
12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394959697989910010110210310410510610710810911011111211311411511611711811912012112212312412512612712812913013113213313413513613713813914014114214314414514614714814915015115215315415515615715815916016116216316416516616716816917017117217317417517617717817918018118218318418518618718818919019119219319419519619719819920020120220320420520620720820921021121221321421521621721821922022122222322422522622722822923023123223323423523623723823924024124224324424524624724824925025125225325425525625725825926026126226326426526626726826927027127227327427527627727827928028128228328428528628728828929029129229329429529629729829930030130230330430530630730830931031131231331431531631731831932032132232332432532632732832933033133233333433533633733833934034134234334434534634734834935035135235335435535635735835936036136236336436536636736836937037137237337437537637737837938038138238338438538638738838939039139239339439539639739839940040140240340440540640740840941041141241341441541641741841942042142242342442542642742842943043143243343443543643743843944044144244344444544644744844945045145245345445545645745845946046146246346446546646746846947047147247347447547647747847948048148248348448548648748848949049149249349449549649749849950050150250350450550650750850951051151251351451551651751851952052152252352452552652752852953053153253353453553653753853954054154254354454554654754854955055155255355455555655755855956056156256356456556656756856957057157257357457557657757857958058158258358458558658758858959059159259359459559659759859960060160260360460560660760860961061161261361461561661761861962062162262362462562662762862963063163263363463563663763863964064164264364464564664764864965065165265365465565665765865966066166266366466566666766866967067167267367467567667767867968068168268368468568668768868969069169269369469569669769869970070170270370470570670770870971071171271371471571671771871972072172272372472572672772872973073173273373473573673773873974074174274374474574674774874975075175275375475575675775875976076176276376476576676776876977077177277377477577677777877978078178278378478578678778878979079179279379479579679779879980080180280380480580680780880981081181281381481581681781881982082182282382482582682782882983083183283383483583683783883984084184284384484584684784884985085185285385485585685785885986086186286386486586686786886987087187287387487587687787887988088188288388488588688788888989089189289389489589689789889990090190290390490590690790890991091191291391491591691791891992092192292392492592692792892993093193293393493593693793893994094194294394494594694794894995095195295395495595695795895996096196296396496596696796896997097197297397497597697797897998098198298398498598698798898999099199299399499599699799899910001001100210031004100510061007100810091010101110121013101410151016101710181019102010211022102310241025102610271028102910301031103210331034103510361037103810391040104110421043104410451046104710481049105010511052105310541055105610571058105910601061106210631064106510661067106810691070107110721073107410751076107710781079108010811082108310841085108610871088108910901091109210931094109510961097109810991100110111021103110411051106110711081109111011111112111311141115111611171118111911201121112211231124112511261127112811291130113111321133113411351136113711381139114011411142114311441145114611471148114911501151115211531154115511561157115811591160116111621163116411651166116711681169117011711172117311741175117611771178117911801181118211831184118511861187118811891190119111921193119411951196119711981199120012011202120312041205120612071208120912101211121212131214121512161217121812191220122112221223122412251226122712281229123012311232123312341235123612371238123912401241124212431244124512461247124812491250125112521253125412551256125712581259126012611262126312641265126612671268126912701271127212731274127512761277127812791280128112821283128412851286128712881289129012911292129312941295129612971298129913001301130213031304130513061307130813091310131113121313131413151316131713181319132013211322132313241325132613271328132913301331133213331334133513361337133813391340134113421343134413451346134713481349135013511352135313541355135613571358135913601361136213631364136513661367136813691370137113721373137413751376137713781379138013811382138313841385138613871388138913901391139213931394139513961397139813991400140114021403140414051406140714081409141014111412141314141415141614171418141914201421142214231424142514261427142814291430143114321433143414351436143714381439144014411442144314441445144614471448144914501451145214531454145514561457145814591460146114621463146414651466146714681469147014711472147314741475147614771478147914801481148214831484148514861487148814891490149114921493149414951496149714981499150015011502150315041505150615071508150915101511151215131514151515161517151815191520152115221523152415251526152715281529153015311532153315341535153615371538153915401541154215431544154515461547154815491550155115521553155415551556155715581559156015611562156315641565156615671568156915701571157215731574157515761577157815791580158115821583158415851586158715881589159015911592159315941595159615971598159916001601160216031604160516061607160816091610161116121613161416151616161716181619162016211622162316241625162616271628162916301631163216331634// SPDX-License-Identifier: GPL-2.0/* * linux/fs/ext4/ialloc.c * * Copyright (C) 1992, 1993, 1994, 1995 * Remy Card (card@masi.ibp.fr) * Laboratoire MASI - Institut Blaise Pascal * Universite Pierre et Marie Curie (Paris VI) * * BSD ufs-inspired inode and directory allocation by * Stephen Tweedie (sct@redhat.com), 1993 * Big-endian to little-endian byte-swapping/bitmaps by * David S. Miller (davem@caip.rutgers.edu), 1995 */
#include <linux/time.h>#include <linux/fs.h>#include <linux/stat.h>#include <linux/string.h>#include <linux/quotaops.h>#include <linux/buffer_head.h>#include <linux/random.h>#include <linux/bitops.h>#include <linux/blkdev.h>#include <linux/cred.h>
#include <asm/byteorder.h>
#include "ext4.h"#include "ext4_jbd2.h"#include "xattr.h"#include "acl.h"
#include <trace/events/ext4.h>
/* * ialloc.c contains the inodes allocation and deallocation routines */
/* * The free inodes are managed by bitmaps. A file system contains several * blocks groups. Each group contains 1 bitmap block for blocks, 1 bitmap * block for inodes, N blocks for the inode table and data blocks. * * The file system contains group descriptors which are located after the * super block. Each descriptor contains the number of the bitmap block and * the free blocks count in the block. */
/* * To avoid calling the atomic setbit hundreds or thousands of times, we only * need to use it within a single byte (to ensure we get endianness right). * We can use memset for the rest of the bitmap as there are no other users. */void ext4_mark_bitmap_end(int start_bit, int end_bit, char *bitmap){ int i;
if (start_bit >= end_bit) return;
ext4_debug("mark end bits +%d through +%d used\n", start_bit, end_bit); for (i = start_bit; i < ((start_bit + 7) & ~7UL); i++) ext4_set_bit(i, bitmap); if (i < end_bit) memset(bitmap + (i >> 3), 0xff, (end_bit - i) >> 3);}
void ext4_end_bitmap_read(struct bio *bio){ struct buffer_head *bh; bool uptodate = bio_endio_bh(bio, &bh);
if (uptodate) { set_buffer_uptodate(bh); set_bitmap_uptodate(bh); } unlock_buffer(bh);}
static int ext4_validate_inode_bitmap(struct super_block *sb, struct ext4_group_desc *desc, ext4_group_t block_group, struct buffer_head *bh){ ext4_fsblk_t blk; struct ext4_group_info *grp;
if (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY) return 0;
if (buffer_verified(bh)) return 0;
grp = ext4_get_group_info(sb, block_group); if (!grp || EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) return -EFSCORRUPTED;
ext4_lock_group(sb, block_group); if (buffer_verified(bh)) goto verified; blk = ext4_inode_bitmap(sb, desc); if (!ext4_inode_bitmap_csum_verify(sb, desc, bh) || ext4_simulate_fail(sb, EXT4_SIM_IBITMAP_CRC)) { ext4_unlock_group(sb, block_group); ext4_error(sb, "Corrupt inode bitmap - block_group = %u, " "inode_bitmap = %llu", block_group, blk); ext4_mark_group_bitmap_corrupted(sb, block_group, EXT4_GROUP_INFO_IBITMAP_CORRUPT); return -EFSBADCRC; } set_buffer_verified(bh);verified: ext4_unlock_group(sb, block_group); return 0;}
/* * Read the inode allocation bitmap for a given block_group, reading * into the specified slot in the superblock's bitmap cache. * * Return buffer_head of bitmap on success, or an ERR_PTR on error. */static struct buffer_head *ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group){ struct ext4_group_desc *desc; struct ext4_sb_info *sbi = EXT4_SB(sb); struct buffer_head *bh = NULL; ext4_fsblk_t bitmap_blk; int err;
desc = ext4_get_group_desc(sb, block_group, NULL); if (!desc) return ERR_PTR(-EFSCORRUPTED);
bitmap_blk = ext4_inode_bitmap(sb, desc); if ((bitmap_blk <= le32_to_cpu(sbi->s_es->s_first_data_block)) || (bitmap_blk >= ext4_blocks_count(sbi->s_es))) { ext4_error(sb, "Invalid inode bitmap blk %llu in " "block_group %u", bitmap_blk, block_group); ext4_mark_group_bitmap_corrupted(sb, block_group, EXT4_GROUP_INFO_IBITMAP_CORRUPT); return ERR_PTR(-EFSCORRUPTED); } bh = sb_getblk(sb, bitmap_blk); if (unlikely(!bh)) { ext4_warning(sb, "Cannot read inode bitmap - " "block_group = %u, inode_bitmap = %llu", block_group, bitmap_blk); return ERR_PTR(-ENOMEM); } if (bitmap_uptodate(bh)) goto verify;
lock_buffer(bh); if (bitmap_uptodate(bh)) { unlock_buffer(bh); goto verify; }
ext4_lock_group(sb, block_group); if (ext4_has_group_desc_csum(sb) && (desc->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT))) { if (block_group == 0) { ext4_unlock_group(sb, block_group); unlock_buffer(bh); ext4_error(sb, "Inode bitmap for bg 0 marked " "uninitialized"); err = -EFSCORRUPTED; goto out; } memset(bh->b_data, 0, (EXT4_INODES_PER_GROUP(sb) + 7) / 8); ext4_mark_bitmap_end(EXT4_INODES_PER_GROUP(sb), sb->s_blocksize * 8, bh->b_data); set_bitmap_uptodate(bh); set_buffer_uptodate(bh); set_buffer_verified(bh); ext4_unlock_group(sb, block_group); unlock_buffer(bh); return bh; } ext4_unlock_group(sb, block_group);
if (buffer_uptodate(bh)) { /* * if not uninit if bh is uptodate, * bitmap is also uptodate */ set_bitmap_uptodate(bh); unlock_buffer(bh); goto verify; } /* * submit the buffer_head for reading */ trace_ext4_load_inode_bitmap(sb, block_group); ext4_read_bh(bh, REQ_META | REQ_PRIO, ext4_end_bitmap_read, ext4_simulate_fail(sb, EXT4_SIM_IBITMAP_EIO)); if (!buffer_uptodate(bh)) { put_bh(bh); ext4_error_err(sb, EIO, "Cannot read inode bitmap - " "block_group = %u, inode_bitmap = %llu", block_group, bitmap_blk); ext4_mark_group_bitmap_corrupted(sb, block_group, EXT4_GROUP_INFO_IBITMAP_CORRUPT); return ERR_PTR(-EIO); }
verify: err = ext4_validate_inode_bitmap(sb, desc, block_group, bh); if (err) goto out; return bh;out: put_bh(bh); return ERR_PTR(err);}
/* * NOTE! When we get the inode, we're the only people * that have access to it, and as such there are no * race conditions we have to worry about. The inode * is not on the hash-lists, and it cannot be reached * through the filesystem because the directory entry * has been deleted earlier. * * HOWEVER: we must make sure that we get no aliases, * which means that we have to call "clear_inode()" * _before_ we mark the inode not in use in the inode * bitmaps. Otherwise a newly created file might use * the same inode number (not actually the same pointer * though), and then we'd have two inodes sharing the * same inode number and space on the harddisk. */void ext4_free_inode(handle_t *handle, struct inode *inode){ struct super_block *sb = inode->i_sb; int is_directory; unsigned long ino; struct buffer_head *bitmap_bh = NULL; struct buffer_head *bh2; ext4_group_t block_group; unsigned long bit; struct ext4_group_desc *gdp; struct ext4_super_block *es; struct ext4_sb_info *sbi; int fatal = 0, err, count, cleared; struct ext4_group_info *grp;
if (!sb) { printk(KERN_ERR "EXT4-fs: %s:%d: inode on " "nonexistent device\n", __func__, __LINE__); return; } if (icount_read_once(inode) > 1) { ext4_msg(sb, KERN_ERR, "%s:%d: inode #%llu: count=%d", __func__, __LINE__, inode->i_ino, icount_read_once(inode)); return; } if (inode->i_nlink) { ext4_msg(sb, KERN_ERR, "%s:%d: inode #%llu: nlink=%d\n", __func__, __LINE__, inode->i_ino, inode->i_nlink); return; } sbi = EXT4_SB(sb);
ino = inode->i_ino; ext4_debug("freeing inode %lu\n", ino); trace_ext4_free_inode(inode);
dquot_initialize(inode); dquot_free_inode(inode);
is_directory = S_ISDIR(inode->i_mode);
/* Do this BEFORE marking the inode not in use or returning an error */ ext4_clear_inode(inode);
es = sbi->s_es; if (ino < EXT4_FIRST_INO(sb) || ino > le32_to_cpu(es->s_inodes_count)) { ext4_error(sb, "reserved or nonexistent inode %lu", ino); goto error_return; } block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb); bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb); bitmap_bh = ext4_read_inode_bitmap(sb, block_group); /* Don't bother if the inode bitmap is corrupt. */ if (IS_ERR(bitmap_bh)) { fatal = PTR_ERR(bitmap_bh); bitmap_bh = NULL; goto error_return; } if (!(sbi->s_mount_state & EXT4_FC_REPLAY)) { grp = ext4_get_group_info(sb, block_group); if (!grp || unlikely(EXT4_MB_GRP_IBITMAP_CORRUPT(grp))) { fatal = -EFSCORRUPTED; goto error_return; } }
BUFFER_TRACE(bitmap_bh, "get_write_access"); fatal = ext4_journal_get_write_access(handle, sb, bitmap_bh, EXT4_JTR_NONE); if (fatal) goto error_return;
fatal = -ESRCH; gdp = ext4_get_group_desc(sb, block_group, &bh2); if (gdp) { BUFFER_TRACE(bh2, "get_write_access"); fatal = ext4_journal_get_write_access(handle, sb, bh2, EXT4_JTR_NONE); } ext4_lock_group(sb, block_group); cleared = ext4_test_and_clear_bit(bit, bitmap_bh->b_data); if (fatal || !cleared) { ext4_unlock_group(sb, block_group); goto out; }
count = ext4_free_inodes_count(sb, gdp) + 1; ext4_free_inodes_set(sb, gdp, count); if (is_directory) { count = ext4_used_dirs_count(sb, gdp) - 1; ext4_used_dirs_set(sb, gdp, count); if (percpu_counter_initialized(&sbi->s_dirs_counter)) percpu_counter_dec(&sbi->s_dirs_counter); } ext4_inode_bitmap_csum_set(sb, gdp, bitmap_bh); ext4_group_desc_csum_set(sb, block_group, gdp); ext4_unlock_group(sb, block_group);
if (percpu_counter_initialized(&sbi->s_freeinodes_counter)) percpu_counter_inc(&sbi->s_freeinodes_counter); if (sbi->s_log_groups_per_flex) { struct flex_groups *fg;
fg = sbi_array_rcu_deref(sbi, s_flex_groups, ext4_flex_group(sbi, block_group)); atomic_inc(&fg->free_inodes); if (is_directory) atomic_dec(&fg->used_dirs); } BUFFER_TRACE(bh2, "call ext4_handle_dirty_metadata"); fatal = ext4_handle_dirty_metadata(handle, NULL, bh2);out: if (cleared) { BUFFER_TRACE(bitmap_bh, "call ext4_handle_dirty_metadata"); err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh); if (!fatal) fatal = err; } else { ext4_error(sb, "bit already cleared for inode %lu", ino); ext4_mark_group_bitmap_corrupted(sb, block_group, EXT4_GROUP_INFO_IBITMAP_CORRUPT); }
error_return: brelse(bitmap_bh); ext4_std_error(sb, fatal);}
struct orlov_stats { __u64 free_clusters; __u32 free_inodes; __u32 used_dirs;};
/* * Helper function for Orlov's allocator; returns critical information * for a particular block group or flex_bg. If flex_size is 1, then g * is a block group number; otherwise it is flex_bg number. */static void get_orlov_stats(struct super_block *sb, ext4_group_t g, int flex_size, struct orlov_stats *stats){ struct ext4_group_desc *desc;
if (flex_size > 1) { struct flex_groups *fg = sbi_array_rcu_deref(EXT4_SB(sb), s_flex_groups, g); stats->free_inodes = atomic_read(&fg->free_inodes); stats->free_clusters = atomic64_read(&fg->free_clusters); stats->used_dirs = atomic_read(&fg->used_dirs); return; }
desc = ext4_get_group_desc(sb, g, NULL); if (desc) { stats->free_inodes = ext4_free_inodes_count(sb, desc); stats->free_clusters = ext4_free_group_clusters(sb, desc); stats->used_dirs = ext4_used_dirs_count(sb, desc); } else { stats->free_inodes = 0; stats->free_clusters = 0; stats->used_dirs = 0; }}
/* * Orlov's allocator for directories. * * We always try to spread first-level directories. * * If there are blockgroups with both free inodes and free clusters counts * not worse than average we return one with smallest directory count. * Otherwise we simply return a random group. * * For the rest rules look so: * * It's OK to put directory into a group unless * it has too many directories already (max_dirs) or * it has too few free inodes left (min_inodes) or * it has too few free clusters left (min_clusters) or * Parent's group is preferred, if it doesn't satisfy these * conditions we search cyclically through the rest. If none * of the groups look good we just look for a group with more * free inodes than average (starting at parent's group). */
static int find_group_orlov(struct super_block *sb, struct inode *parent, ext4_group_t *group, umode_t mode, const struct qstr *qstr){ ext4_group_t parent_group = EXT4_I(parent)->i_block_group; struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_group_t real_ngroups = ext4_get_groups_count(sb); int inodes_per_group = EXT4_INODES_PER_GROUP(sb); unsigned int freei, avefreei, grp_free; ext4_fsblk_t freec, avefreec; unsigned int ndirs; int max_dirs, min_inodes; ext4_grpblk_t min_clusters; ext4_group_t i, grp, g, ngroups; struct ext4_group_desc *desc; struct orlov_stats stats; int flex_size = ext4_flex_bg_size(sbi); struct dx_hash_info hinfo;
ngroups = real_ngroups; if (flex_size > 1) { ngroups = (real_ngroups + flex_size - 1) >> sbi->s_log_groups_per_flex; parent_group >>= sbi->s_log_groups_per_flex; }
freei = percpu_counter_read_positive(&sbi->s_freeinodes_counter); avefreei = freei / ngroups; freec = percpu_counter_read_positive(&sbi->s_freeclusters_counter); avefreec = freec; do_div(avefreec, ngroups); ndirs = percpu_counter_read_positive(&sbi->s_dirs_counter);
if (S_ISDIR(mode) && ((parent == d_inode(sb->s_root)) || (ext4_test_inode_flag(parent, EXT4_INODE_TOPDIR)))) { int best_ndir = inodes_per_group; int ret = -1;
if (qstr) { hinfo.hash_version = DX_HASH_HALF_MD4; hinfo.seed = sbi->s_hash_seed; ext4fs_dirhash(parent, qstr->name, qstr->len, &hinfo); parent_group = hinfo.hash % ngroups; } else parent_group = get_random_u32_below(ngroups); for (i = 0; i < ngroups; i++) { g = (parent_group + i) % ngroups; get_orlov_stats(sb, g, flex_size, &stats); if (!stats.free_inodes) continue; if (stats.used_dirs >= best_ndir) continue; if (stats.free_inodes < avefreei) continue; if (stats.free_clusters < avefreec) continue; grp = g; ret = 0; best_ndir = stats.used_dirs; } if (ret) goto fallback; found_flex_bg: if (flex_size == 1) { *group = grp; return 0; }
/* * We pack inodes at the beginning of the flexgroup's * inode tables. Block allocation decisions will do * something similar, although regular files will * start at 2nd block group of the flexgroup. See * ext4_ext_find_goal() and ext4_find_near(). */ grp *= flex_size; for (i = 0; i < flex_size; i++) { if (grp+i >= real_ngroups) break; desc = ext4_get_group_desc(sb, grp+i, NULL); if (desc && ext4_free_inodes_count(sb, desc)) { *group = grp+i; return 0; } } goto fallback; }
max_dirs = ndirs / ngroups + inodes_per_group*flex_size / 16; min_inodes = avefreei - inodes_per_group*flex_size / 4; if (min_inodes < 1) min_inodes = 1; min_clusters = avefreec - EXT4_CLUSTERS_PER_GROUP(sb)*flex_size / 4; if (min_clusters < 0) min_clusters = 0;
/* * Start looking in the flex group where we last allocated an * inode for this parent directory */ if (EXT4_I(parent)->i_last_alloc_group != ~0) { parent_group = EXT4_I(parent)->i_last_alloc_group; if (flex_size > 1) parent_group >>= sbi->s_log_groups_per_flex; }
for (i = 0; i < ngroups; i++) { grp = (parent_group + i) % ngroups; get_orlov_stats(sb, grp, flex_size, &stats); if (stats.used_dirs >= max_dirs) continue; if (stats.free_inodes < min_inodes) continue; if (stats.free_clusters < min_clusters) continue; goto found_flex_bg; }
fallback: ngroups = real_ngroups; avefreei = freei / ngroups;fallback_retry: parent_group = EXT4_I(parent)->i_block_group; for (i = 0; i < ngroups; i++) { grp = (parent_group + i) % ngroups; desc = ext4_get_group_desc(sb, grp, NULL); if (desc) { grp_free = ext4_free_inodes_count(sb, desc); if (grp_free && grp_free >= avefreei) { *group = grp; return 0; } } }
if (avefreei) { /* * The free-inodes counter is approximate, and for really small * filesystems the above test can fail to find any blockgroups */ avefreei = 0; goto fallback_retry; }
return -1;}
static int find_group_other(struct super_block *sb, struct inode *parent, ext4_group_t *group, umode_t mode){ ext4_group_t parent_group = EXT4_I(parent)->i_block_group; ext4_group_t i, last, ngroups = ext4_get_groups_count(sb); struct ext4_group_desc *desc; int flex_size = ext4_flex_bg_size(EXT4_SB(sb));
/* * Try to place the inode is the same flex group as its * parent. If we can't find space, use the Orlov algorithm to * find another flex group, and store that information in the * parent directory's inode information so that use that flex * group for future allocations. */ if (flex_size > 1) { int retry = 0;
try_again: parent_group &= ~(flex_size-1); last = parent_group + flex_size; if (last > ngroups) last = ngroups; for (i = parent_group; i < last; i++) { desc = ext4_get_group_desc(sb, i, NULL); if (desc && ext4_free_inodes_count(sb, desc)) { *group = i; return 0; } } if (!retry && EXT4_I(parent)->i_last_alloc_group != ~0) { retry = 1; parent_group = EXT4_I(parent)->i_last_alloc_group; goto try_again; } /* * If this didn't work, use the Orlov search algorithm * to find a new flex group; we pass in the mode to * avoid the topdir algorithms. */ *group = parent_group + flex_size; if (*group > ngroups) *group = 0; return find_group_orlov(sb, parent, group, mode, NULL); }
/* * Try to place the inode in its parent directory */ *group = parent_group; desc = ext4_get_group_desc(sb, *group, NULL); if (desc && ext4_free_inodes_count(sb, desc) && ext4_free_group_clusters(sb, desc)) return 0;
/* * We're going to place this inode in a different blockgroup from its * parent. We want to cause files in a common directory to all land in * the same blockgroup. But we want files which are in a different * directory which shares a blockgroup with our parent to land in a * different blockgroup. * * So add our directory's i_ino into the starting point for the hash. */ *group = (*group + (unsigned int)parent->i_ino) % ngroups;
/* * Use a quadratic hash to find a group with a free inode and some free * blocks. */ for (i = 1; i < ngroups; i <<= 1) { *group += i; if (*group >= ngroups) *group -= ngroups; desc = ext4_get_group_desc(sb, *group, NULL); if (desc && ext4_free_inodes_count(sb, desc) && ext4_free_group_clusters(sb, desc)) return 0; }
/* * That failed: try linear search for a free inode, even if that group * has no free blocks. */ *group = parent_group; for (i = 0; i < ngroups; i++) { if (++*group >= ngroups) *group = 0; desc = ext4_get_group_desc(sb, *group, NULL); if (desc && ext4_free_inodes_count(sb, desc)) return 0; }
return -1;}
/* * In no journal mode, if an inode has recently been deleted, we want * to avoid reusing it until we're reasonably sure the inode table * block has been written back to disk. (Yes, these values are * somewhat arbitrary...) */#define RECENTCY_MIN 60#define RECENTCY_DIRTY 300
static int recently_deleted(struct super_block *sb, ext4_group_t group, int ino){ struct ext4_group_desc *gdp; struct ext4_inode *raw_inode; struct buffer_head *bh; int inodes_per_block = EXT4_SB(sb)->s_inodes_per_block; int offset, ret = 0; int recentcy = RECENTCY_MIN; u32 dtime, now;
gdp = ext4_get_group_desc(sb, group, NULL); if (unlikely(!gdp)) return 0;
/* Inode was never used in this filesystem? */ if (ext4_has_group_desc_csum(sb) && (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT) || ino >= EXT4_INODES_PER_GROUP(sb) - ext4_itable_unused_count(sb, gdp))) return 0;
bh = sb_find_get_block(sb, ext4_inode_table(sb, gdp) + (ino / inodes_per_block)); if (!bh || !buffer_uptodate(bh)) /* * If the block is not in the buffer cache, then it * must have been written out, or, most unlikely, is * being migrated - false failure should be OK here. */ goto out;
offset = (ino % inodes_per_block) * EXT4_INODE_SIZE(sb); raw_inode = (struct ext4_inode *) (bh->b_data + offset);
/* i_dtime is only 32 bits on disk, but we only care about relative * times in the range of a few minutes (i.e. long enough to sync a * recently-deleted inode to disk), so using the low 32 bits of the * clock (a 68 year range) is enough, see time_before32() */ dtime = le32_to_cpu(raw_inode->i_dtime); now = ktime_get_real_seconds(); if (buffer_dirty(bh)) recentcy += RECENTCY_DIRTY;
if (dtime && time_before32(dtime, now) && time_before32(now, dtime + recentcy)) ret = 1;out: brelse(bh); return ret;}
static int find_inode_bit(struct super_block *sb, ext4_group_t group, struct buffer_head *bitmap, unsigned long *ino){ bool check_recently_deleted = EXT4_SB(sb)->s_journal == NULL; unsigned long recently_deleted_ino = EXT4_INODES_PER_GROUP(sb);
next: *ino = ext4_find_next_zero_bit((unsigned long *) bitmap->b_data, EXT4_INODES_PER_GROUP(sb), *ino); if (*ino >= EXT4_INODES_PER_GROUP(sb)) goto not_found;
if (check_recently_deleted && recently_deleted(sb, group, *ino)) { recently_deleted_ino = *ino; *ino = *ino + 1; if (*ino < EXT4_INODES_PER_GROUP(sb)) goto next; goto not_found; } return 1;not_found: if (recently_deleted_ino >= EXT4_INODES_PER_GROUP(sb)) return 0; /* * Not reusing recently deleted inodes is mostly a preference. We don't * want to report ENOSPC or skew allocation patterns because of that. * So return even recently deleted inode if we could find better in the * given range. */ *ino = recently_deleted_ino; return 1;}
int ext4_mark_inode_used(struct super_block *sb, int ino){ unsigned long max_ino = le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count); struct buffer_head *inode_bitmap_bh = NULL, *group_desc_bh = NULL; struct ext4_group_desc *gdp; ext4_group_t group; int bit; int err;
if (ino < EXT4_FIRST_INO(sb) || ino > max_ino) return -EFSCORRUPTED;
group = (ino - 1) / EXT4_INODES_PER_GROUP(sb); bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb); inode_bitmap_bh = ext4_read_inode_bitmap(sb, group); if (IS_ERR(inode_bitmap_bh)) return PTR_ERR(inode_bitmap_bh);
if (ext4_test_bit(bit, inode_bitmap_bh->b_data)) { err = 0; goto out; }
gdp = ext4_get_group_desc(sb, group, &group_desc_bh); if (!gdp) { err = -EINVAL; goto out; }
ext4_set_bit(bit, inode_bitmap_bh->b_data);
BUFFER_TRACE(inode_bitmap_bh, "call ext4_handle_dirty_metadata"); err = ext4_handle_dirty_metadata(NULL, NULL, inode_bitmap_bh); if (err) { ext4_std_error(sb, err); goto out; } err = sync_dirty_buffer(inode_bitmap_bh); if (err) { ext4_std_error(sb, err); goto out; }
/* We may have to initialize the block bitmap if it isn't already */ if (ext4_has_group_desc_csum(sb) && gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) { struct buffer_head *block_bitmap_bh;
block_bitmap_bh = ext4_read_block_bitmap(sb, group); if (IS_ERR(block_bitmap_bh)) { err = PTR_ERR(block_bitmap_bh); goto out; }
BUFFER_TRACE(block_bitmap_bh, "dirty block bitmap"); err = ext4_handle_dirty_metadata(NULL, NULL, block_bitmap_bh); sync_dirty_buffer(block_bitmap_bh);
/* recheck and clear flag under lock if we still need to */ ext4_lock_group(sb, group); if (ext4_has_group_desc_csum(sb) && (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) { gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT); ext4_free_group_clusters_set(sb, gdp, ext4_free_clusters_after_init(sb, group, gdp)); ext4_block_bitmap_csum_set(sb, gdp, block_bitmap_bh); ext4_group_desc_csum_set(sb, group, gdp); } ext4_unlock_group(sb, group); brelse(block_bitmap_bh);
if (err) { ext4_std_error(sb, err); goto out; } }
/* Update the relevant bg descriptor fields */ if (ext4_has_group_desc_csum(sb)) { int free;
ext4_lock_group(sb, group); /* while we modify the bg desc */ free = EXT4_INODES_PER_GROUP(sb) - ext4_itable_unused_count(sb, gdp); if (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) { gdp->bg_flags &= cpu_to_le16(~EXT4_BG_INODE_UNINIT); free = 0; }
/* * Check the relative inode number against the last used * relative inode number in this group. if it is greater * we need to update the bg_itable_unused count */ if (bit >= free) ext4_itable_unused_set(sb, gdp, (EXT4_INODES_PER_GROUP(sb) - bit - 1)); } else { ext4_lock_group(sb, group); }
ext4_free_inodes_set(sb, gdp, ext4_free_inodes_count(sb, gdp) - 1); if (ext4_has_group_desc_csum(sb)) { ext4_inode_bitmap_csum_set(sb, gdp, inode_bitmap_bh); ext4_group_desc_csum_set(sb, group, gdp); }
ext4_unlock_group(sb, group); err = ext4_handle_dirty_metadata(NULL, NULL, group_desc_bh); sync_dirty_buffer(group_desc_bh);out: brelse(inode_bitmap_bh); return err;}
static int ext4_xattr_credits_for_new_inode(struct inode *dir, mode_t mode, bool encrypt){ struct super_block *sb = dir->i_sb; int nblocks = 0;#ifdef CONFIG_EXT4_FS_POSIX_ACL struct posix_acl *p = get_inode_acl(dir, ACL_TYPE_DEFAULT);
if (IS_ERR(p)) return PTR_ERR(p); if (p) { int acl_size = p->a_count * sizeof(ext4_acl_entry);
nblocks += (S_ISDIR(mode) ? 2 : 1) * __ext4_xattr_set_credits(sb, NULL /* inode */, NULL /* block_bh */, acl_size, true /* is_create */); posix_acl_release(p); }#endif
#ifdef CONFIG_SECURITY { int num_security_xattrs = 1;
#ifdef CONFIG_INTEGRITY num_security_xattrs++;#endif /* * We assume that security xattrs are never more than 1k. * In practice they are under 128 bytes. */ nblocks += num_security_xattrs * __ext4_xattr_set_credits(sb, NULL /* inode */, NULL /* block_bh */, 1024, true /* is_create */); }#endif if (encrypt) nblocks += __ext4_xattr_set_credits(sb, NULL /* inode */, NULL /* block_bh */, FSCRYPT_SET_CONTEXT_MAX_SIZE, true /* is_create */); return nblocks;}
/* * There are two policies for allocating an inode. If the new inode is * a directory, then a forward search is made for a block group with both * free space and a low directory-to-inode ratio; if that fails, then of * the groups with above-average free space, that group with the fewest * directories already is chosen. * * For other inodes, search forward from the parent directory's block * group to find a free inode. */struct inode *__ext4_new_inode(const struct mnt_idmap *idmap, handle_t *handle, struct inode *dir, umode_t mode, const struct qstr *qstr, __u32 goal, uid_t *owner, __u32 i_flags, int handle_type, unsigned int line_no, int nblocks){ struct super_block *sb; struct buffer_head *inode_bitmap_bh = NULL; struct buffer_head *group_desc_bh; ext4_group_t ngroups, group = 0; unsigned long ino = 0; struct inode *inode; struct ext4_group_desc *gdp = NULL; struct ext4_inode_info *ei; struct ext4_sb_info *sbi; int ret2, err; struct inode *ret; ext4_group_t i; ext4_group_t flex_group; struct ext4_group_info *grp = NULL; bool encrypt = false;
/* Cannot create files in a deleted directory */ if (!dir || !dir->i_nlink) return ERR_PTR(-EPERM);
sb = dir->i_sb; sbi = EXT4_SB(sb);
ret2 = ext4_emergency_state(sb); if (unlikely(ret2)) return ERR_PTR(ret2);
ngroups = ext4_get_groups_count(sb); trace_ext4_request_inode(dir, mode); inode = new_inode(sb); if (!inode) return ERR_PTR(-ENOMEM); ei = EXT4_I(inode);
/* * Initialize owners and quota early so that we don't have to account * for quota initialization worst case in standard inode creating * transaction */ if (owner) { inode->i_mode = mode; i_uid_write(inode, owner[0]); i_gid_write(inode, owner[1]); } else if (test_opt(sb, GRPID)) { inode->i_mode = mode; inode_fsuid_set(inode, idmap); inode->i_gid = dir->i_gid; } else inode_init_owner(idmap, inode, dir, mode);
if (ext4_has_feature_project(sb) && ext4_test_inode_flag(dir, EXT4_INODE_PROJINHERIT)) ei->i_projid = EXT4_I(dir)->i_projid; else ei->i_projid = make_kprojid(&init_user_ns, EXT4_DEF_PROJID);
if (!(i_flags & EXT4_EA_INODE_FL)) { err = fscrypt_prepare_new_inode(dir, inode, &encrypt); if (err) goto out; if (encrypt) i_flags |= EXT4_ENCRYPT_FL; }
err = dquot_initialize(inode); if (err) goto out;
if (!handle && sbi->s_journal && !(i_flags & EXT4_EA_INODE_FL)) { ret2 = ext4_xattr_credits_for_new_inode(dir, mode, encrypt); if (ret2 < 0) { err = ret2; goto out; } nblocks += ret2; }
if (!goal) goal = sbi->s_inode_goal;
if (goal && goal <= le32_to_cpu(sbi->s_es->s_inodes_count)) { group = (goal - 1) / EXT4_INODES_PER_GROUP(sb); ino = (goal - 1) % EXT4_INODES_PER_GROUP(sb); ret2 = 0; goto got_group; }
if (S_ISDIR(mode)) ret2 = find_group_orlov(sb, dir, &group, mode, qstr); else ret2 = find_group_other(sb, dir, &group, mode);
got_group: EXT4_I(dir)->i_last_alloc_group = group; err = -ENOSPC; if (ret2 == -1) goto out;
/* * Normally we will only go through one pass of this loop, * unless we get unlucky and it turns out the group we selected * had its last inode grabbed by someone else. */ for (i = 0; i < ngroups; i++, ino = 0) { err = -EIO;
gdp = ext4_get_group_desc(sb, group, &group_desc_bh); if (!gdp) goto out;
/* * Check free inodes count before loading bitmap. */ if (ext4_free_inodes_count(sb, gdp) == 0) goto next_group;
if (!(sbi->s_mount_state & EXT4_FC_REPLAY)) { grp = ext4_get_group_info(sb, group); /* * Skip groups with already-known suspicious inode * tables */ if (!grp || EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) goto next_group; }
brelse(inode_bitmap_bh); inode_bitmap_bh = ext4_read_inode_bitmap(sb, group); /* Skip groups with suspicious inode tables */ if (IS_ERR(inode_bitmap_bh)) { inode_bitmap_bh = NULL; goto next_group; } if (!(sbi->s_mount_state & EXT4_FC_REPLAY) && EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) goto next_group;
ret2 = find_inode_bit(sb, group, inode_bitmap_bh, &ino); if (!ret2) goto next_group;
if (group == 0 && (ino + 1) < EXT4_FIRST_INO(sb)) { ext4_error(sb, "reserved inode found cleared - " "inode=%lu", ino + 1); ext4_mark_group_bitmap_corrupted(sb, group, EXT4_GROUP_INFO_IBITMAP_CORRUPT); goto next_group; }
if ((!(sbi->s_mount_state & EXT4_FC_REPLAY)) && !handle) { BUG_ON(nblocks <= 0); handle = __ext4_journal_start_sb(NULL, dir->i_sb, line_no, handle_type, nblocks, 0, ext4_trans_default_revoke_credits(sb)); if (IS_ERR(handle)) { err = PTR_ERR(handle); ext4_std_error(sb, err); goto out; } } BUFFER_TRACE(inode_bitmap_bh, "get_write_access"); err = ext4_journal_get_write_access(handle, sb, inode_bitmap_bh, EXT4_JTR_NONE); if (err) { ext4_std_error(sb, err); goto out; } ext4_lock_group(sb, group); ret2 = ext4_test_and_set_bit(ino, inode_bitmap_bh->b_data); if (ret2) { /* Someone already took the bit. Repeat the search * with lock held. */ ret2 = find_inode_bit(sb, group, inode_bitmap_bh, &ino); if (ret2) { ext4_set_bit(ino, inode_bitmap_bh->b_data); ret2 = 0; } else { ret2 = 1; /* we didn't grab the inode */ } } ext4_unlock_group(sb, group); ino++; /* the inode bitmap is zero-based */ if (!ret2) goto got; /* we grabbed the inode! */
next_group: if (++group == ngroups) group = 0; } err = -ENOSPC; goto out;
got: BUFFER_TRACE(inode_bitmap_bh, "call ext4_handle_dirty_metadata"); err = ext4_handle_dirty_metadata(handle, NULL, inode_bitmap_bh); if (err) { ext4_std_error(sb, err); goto out; }
BUFFER_TRACE(group_desc_bh, "get_write_access"); err = ext4_journal_get_write_access(handle, sb, group_desc_bh, EXT4_JTR_NONE); if (err) { ext4_std_error(sb, err); goto out; }
/* We may have to initialize the block bitmap if it isn't already */ if (ext4_has_group_desc_csum(sb) && gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) { struct buffer_head *block_bitmap_bh;
block_bitmap_bh = ext4_read_block_bitmap(sb, group); if (IS_ERR(block_bitmap_bh)) { err = PTR_ERR(block_bitmap_bh); goto out; } BUFFER_TRACE(block_bitmap_bh, "get block bitmap access"); err = ext4_journal_get_write_access(handle, sb, block_bitmap_bh, EXT4_JTR_NONE); if (err) { brelse(block_bitmap_bh); ext4_std_error(sb, err); goto out; }
BUFFER_TRACE(block_bitmap_bh, "dirty block bitmap"); err = ext4_handle_dirty_metadata(handle, NULL, block_bitmap_bh);
/* recheck and clear flag under lock if we still need to */ ext4_lock_group(sb, group); if (ext4_has_group_desc_csum(sb) && (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) { gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT); ext4_free_group_clusters_set(sb, gdp, ext4_free_clusters_after_init(sb, group, gdp)); ext4_block_bitmap_csum_set(sb, gdp, block_bitmap_bh); ext4_group_desc_csum_set(sb, group, gdp); } ext4_unlock_group(sb, group); brelse(block_bitmap_bh);
if (err) { ext4_std_error(sb, err); goto out; } }
/* Update the relevant bg descriptor fields */ if (ext4_has_group_desc_csum(sb)) { int free; struct ext4_group_info *grp = NULL;
if (!(sbi->s_mount_state & EXT4_FC_REPLAY)) { grp = ext4_get_group_info(sb, group); if (!grp) { err = -EFSCORRUPTED; goto out; } down_read(&grp->alloc_sem); /* * protect vs itable * lazyinit */ } ext4_lock_group(sb, group); /* while we modify the bg desc */ free = EXT4_INODES_PER_GROUP(sb) - ext4_itable_unused_count(sb, gdp); if (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) { gdp->bg_flags &= cpu_to_le16(~EXT4_BG_INODE_UNINIT); free = 0; } /* * Check the relative inode number against the last used * relative inode number in this group. if it is greater * we need to update the bg_itable_unused count */ if (ino > free) ext4_itable_unused_set(sb, gdp, (EXT4_INODES_PER_GROUP(sb) - ino)); if (!(sbi->s_mount_state & EXT4_FC_REPLAY)) up_read(&grp->alloc_sem); } else { ext4_lock_group(sb, group); }
ext4_free_inodes_set(sb, gdp, ext4_free_inodes_count(sb, gdp) - 1); if (S_ISDIR(mode)) { ext4_used_dirs_set(sb, gdp, ext4_used_dirs_count(sb, gdp) + 1); if (sbi->s_log_groups_per_flex) { ext4_group_t f = ext4_flex_group(sbi, group);
atomic_inc(&sbi_array_rcu_deref(sbi, s_flex_groups, f)->used_dirs); } } if (ext4_has_group_desc_csum(sb)) { ext4_inode_bitmap_csum_set(sb, gdp, inode_bitmap_bh); ext4_group_desc_csum_set(sb, group, gdp); } ext4_unlock_group(sb, group);
BUFFER_TRACE(group_desc_bh, "call ext4_handle_dirty_metadata"); err = ext4_handle_dirty_metadata(handle, NULL, group_desc_bh); if (err) { ext4_std_error(sb, err); goto out; }
percpu_counter_dec(&sbi->s_freeinodes_counter); if (S_ISDIR(mode)) percpu_counter_inc(&sbi->s_dirs_counter);
if (sbi->s_log_groups_per_flex) { flex_group = ext4_flex_group(sbi, group); atomic_dec(&sbi_array_rcu_deref(sbi, s_flex_groups, flex_group)->free_inodes); }
inode->i_ino = ino + group * EXT4_INODES_PER_GROUP(sb); /* This is the optimal IO size (for stat), not the fs block size */ inode->i_blocks = 0; simple_inode_init_ts(inode); ei->i_crtime = inode_get_mtime(inode);
memset(ei->i_data, 0, sizeof(ei->i_data)); ei->i_dir_start_lookup = 0; ei->i_disksize = 0;
/* Don't inherit extent flag from directory, amongst others. */ ei->i_flags = ext4_mask_flags(mode, EXT4_I(dir)->i_flags & EXT4_FL_INHERITED); ei->i_flags |= i_flags; ei->i_file_acl = 0; ei->i_dtime = 0; ei->i_block_group = group; ei->i_last_alloc_group = ~0;
ext4_set_inode_flags(inode, true); if (IS_DIRSYNC(inode)) ext4_handle_sync(handle); if (insert_inode_locked(inode) < 0) { /* * Likely a bitmap corruption causing inode to be allocated * twice. */ err = -EIO; ext4_error(sb, "failed to insert inode %llu: doubly allocated?", inode->i_ino); ext4_mark_group_bitmap_corrupted(sb, group, EXT4_GROUP_INFO_IBITMAP_CORRUPT); goto out; } inode->i_generation = get_random_u32();
/* Precompute checksum seed for inode metadata */ if (ext4_has_feature_metadata_csum(sb)) { __u32 csum; __le32 inum = cpu_to_le32(inode->i_ino); __le32 gen = cpu_to_le32(inode->i_generation); csum = ext4_chksum(sbi->s_csum_seed, (__u8 *)&inum, sizeof(inum)); ei->i_csum_seed = ext4_chksum(csum, (__u8 *)&gen, sizeof(gen)); }
ext4_set_inode_state(inode, EXT4_STATE_NEW);
ei->i_extra_isize = sbi->s_want_extra_isize; ei->i_inline_off = 0; if (ext4_has_feature_inline_data(sb) && /* Encrypted inodes cannot have inline data */ !(ei->i_flags & EXT4_ENCRYPT_FL) && (!(ei->i_flags & (EXT4_DAX_FL|EXT4_EA_INODE_FL)) || S_ISDIR(mode))) ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); ret = inode; err = dquot_alloc_inode(inode); if (err) goto fail_drop;
/* * Since the encryption xattr will always be unique, create it first so * that it's less likely to end up in an external xattr block and * prevent its deduplication. */ if (encrypt) { err = fscrypt_set_context(inode, handle); if (err) goto fail_free_drop; }
if (!(ei->i_flags & EXT4_EA_INODE_FL)) { err = ext4_init_acl(handle, inode, dir); if (err) goto fail_free_drop;
err = ext4_init_security(handle, inode, dir, qstr); if (err) goto fail_free_drop; }
if (ext4_has_feature_extents(sb)) { /* set extent flag only for directory, file and normal symlink*/ if (S_ISDIR(mode) || S_ISREG(mode) || S_ISLNK(mode)) { ext4_set_inode_flag(inode, EXT4_INODE_EXTENTS); ext4_ext_tree_init(handle, inode); } }
ext4_enable_buffered_iomap(inode); ext4_set_inode_mapping_order(inode);
ext4_update_inode_fsync_trans(handle, inode, 1);
err = ext4_mark_inode_dirty(handle, inode); if (err) { ext4_std_error(sb, err); goto fail_free_drop; }
ext4_debug("allocating inode %llu\n", inode->i_ino); trace_ext4_allocate_inode(inode, dir, mode); brelse(inode_bitmap_bh); return ret;
fail_free_drop: dquot_free_inode(inode);fail_drop: clear_nlink(inode); unlock_new_inode(inode);out: dquot_drop(inode); inode->i_flags |= S_NOQUOTA; iput(inode); brelse(inode_bitmap_bh); return ERR_PTR(err);}
/* Verify that we are loading a valid orphan from disk */struct inode *ext4_orphan_get(struct super_block *sb, unsigned long ino){ unsigned long max_ino = le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count); ext4_group_t block_group; int bit; struct buffer_head *bitmap_bh = NULL; struct inode *inode = NULL; int err = -EFSCORRUPTED;
if (ino < EXT4_FIRST_INO(sb) || ino > max_ino) goto bad_orphan;
block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb); bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb); bitmap_bh = ext4_read_inode_bitmap(sb, block_group); if (IS_ERR(bitmap_bh)) return ERR_CAST(bitmap_bh);
/* Having the inode bit set should be a 100% indicator that this * is a valid orphan (no e2fsck run on fs). Orphans also include * inodes that were being truncated, so we can't check i_nlink==0. */ if (!ext4_test_bit(bit, bitmap_bh->b_data)) goto bad_orphan;
inode = ext4_iget(sb, ino, EXT4_IGET_NORMAL); if (IS_ERR(inode)) { err = PTR_ERR(inode); ext4_error_err(sb, -err, "couldn't read orphan inode %lu (err %d)", ino, err); brelse(bitmap_bh); return inode; }
/* * If the orphans has i_nlinks > 0 then it should be able to * be truncated, otherwise it won't be removed from the orphan * list during processing and an infinite loop will result. * Similarly, it must not be a bad inode. */ if ((inode->i_nlink && !ext4_can_truncate(inode)) || is_bad_inode(inode)) goto bad_orphan;
if (NEXT_ORPHAN(inode) > max_ino) goto bad_orphan; brelse(bitmap_bh); return inode;
bad_orphan: ext4_error(sb, "bad orphan inode %lu", ino); if (bitmap_bh) printk(KERN_ERR "ext4_test_bit(bit=%d, block=%llu) = %d\n", bit, (unsigned long long)bitmap_bh->b_blocknr, ext4_test_bit(bit, bitmap_bh->b_data)); if (inode) { printk(KERN_ERR "is_bad_inode(inode)=%d\n", is_bad_inode(inode)); printk(KERN_ERR "NEXT_ORPHAN(inode)=%u\n", NEXT_ORPHAN(inode)); printk(KERN_ERR "max_ino=%lu\n", max_ino); printk(KERN_ERR "i_nlink=%u\n", inode->i_nlink); /* Avoid freeing blocks if we got a bad deleted inode */ if (inode->i_nlink == 0) inode->i_blocks = 0; iput(inode); } brelse(bitmap_bh); return ERR_PTR(err);}
unsigned long ext4_count_free_inodes(struct super_block *sb){ unsigned long desc_count; struct ext4_group_desc *gdp; ext4_group_t i, ngroups = ext4_get_groups_count(sb);#ifdef EXT4FS_DEBUG struct ext4_super_block *es; unsigned long bitmap_count, x; struct buffer_head *bitmap_bh = NULL;
es = EXT4_SB(sb)->s_es; desc_count = 0; bitmap_count = 0; gdp = NULL; for (i = 0; i < ngroups; i++) { gdp = ext4_get_group_desc(sb, i, NULL); if (!gdp) continue; desc_count += ext4_free_inodes_count(sb, gdp); brelse(bitmap_bh); bitmap_bh = ext4_read_inode_bitmap(sb, i); if (IS_ERR(bitmap_bh)) { bitmap_bh = NULL; continue; }
x = ext4_count_free(bitmap_bh->b_data, EXT4_INODES_PER_GROUP(sb) / 8); printk(KERN_DEBUG "group %lu: stored = %d, counted = %lu\n", (unsigned long) i, ext4_free_inodes_count(sb, gdp), x); bitmap_count += x; } brelse(bitmap_bh); printk(KERN_DEBUG "ext4_count_free_inodes: " "stored = %u, computed = %lu, %lu\n", le32_to_cpu(es->s_free_inodes_count), desc_count, bitmap_count); return desc_count;#else desc_count = 0; for (i = 0; i < ngroups; i++) { gdp = ext4_get_group_desc(sb, i, NULL); if (!gdp) continue; desc_count += ext4_free_inodes_count(sb, gdp); cond_resched(); } return desc_count;#endif}
/* Called at mount-time, super-block is locked */unsigned long ext4_count_dirs(struct super_block * sb){ unsigned long count = 0; ext4_group_t i, ngroups = ext4_get_groups_count(sb);
for (i = 0; i < ngroups; i++) { struct ext4_group_desc *gdp = ext4_get_group_desc(sb, i, NULL); if (!gdp) continue; count += ext4_used_dirs_count(sb, gdp); } return count;}
/* * Zeroes not yet zeroed inode table - just write zeroes through the whole * inode table. Must be called without any spinlock held. The only place * where it is called from on active part of filesystem is ext4lazyinit * thread, so we do not need any special locks, however we have to prevent * inode allocation from the current group, so we take alloc_sem lock, to * block ext4_new_inode() until we are finished. */int ext4_init_inode_table(struct super_block *sb, ext4_group_t group, int barrier){ struct ext4_group_info *grp = ext4_get_group_info(sb, group); struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_group_desc *gdp = NULL; struct buffer_head *group_desc_bh; handle_t *handle; ext4_fsblk_t blk; int num, ret = 0, used_blks = 0; unsigned long used_inos = 0;
gdp = ext4_get_group_desc(sb, group, &group_desc_bh); if (!gdp || !grp) goto out;
/* * We do not need to lock this, because we are the only one * handling this flag. */ if (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED)) goto out;
handle = ext4_journal_start_sb(sb, EXT4_HT_MISC, 1); if (IS_ERR(handle)) { ret = PTR_ERR(handle); goto out; }
down_write(&grp->alloc_sem); /* * If inode bitmap was already initialized there may be some * used inodes so we need to skip blocks with used inodes in * inode table. */ if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT))) { used_inos = EXT4_INODES_PER_GROUP(sb) - ext4_itable_unused_count(sb, gdp); used_blks = DIV_ROUND_UP(used_inos, sbi->s_inodes_per_block);
/* Bogus inode unused count? */ if (used_blks < 0 || used_blks > sbi->s_itb_per_group) { ext4_error(sb, "Something is wrong with group %u: " "used itable blocks: %d; " "itable unused count: %u", group, used_blks, ext4_itable_unused_count(sb, gdp)); ret = 1; goto err_out; }
used_inos += group * EXT4_INODES_PER_GROUP(sb); /* * Are there some uninitialized inodes in the inode table * before the first normal inode? */ if ((used_blks != sbi->s_itb_per_group) && (used_inos < EXT4_FIRST_INO(sb))) { ext4_error(sb, "Something is wrong with group %u: " "itable unused count: %u; " "itables initialized count: %ld", group, ext4_itable_unused_count(sb, gdp), used_inos); ret = 1; goto err_out; } }
blk = ext4_inode_table(sb, gdp) + used_blks; num = sbi->s_itb_per_group - used_blks;
BUFFER_TRACE(group_desc_bh, "get_write_access"); ret = ext4_journal_get_write_access(handle, sb, group_desc_bh, EXT4_JTR_NONE); if (ret) goto err_out;
/* * Skip zeroout if the inode table is full. But we set the ZEROED * flag anyway, because obviously, when it is full it does not need * further zeroing. */ if (unlikely(num == 0)) goto skip_zeroout;
ext4_debug("going to zero out inode table in group %d\n", group); ret = sb_issue_zeroout(sb, blk, num, GFP_NOFS); if (ret < 0) goto err_out; if (barrier) blkdev_issue_flush(sb->s_bdev);
skip_zeroout: ext4_lock_group(sb, group); gdp->bg_flags |= cpu_to_le16(EXT4_BG_INODE_ZEROED); ext4_group_desc_csum_set(sb, group, gdp); ext4_unlock_group(sb, group);
BUFFER_TRACE(group_desc_bh, "call ext4_handle_dirty_metadata"); ret = ext4_handle_dirty_metadata(handle, NULL, group_desc_bh);
err_out: up_write(&grp->alloc_sem); ext4_journal_stop(handle);out: return ret;}