static int find_group_orlov(struct super_block *sb, struct inode *parent)
{
int parent_group = EXT3_I(parent)->i_block_group;
struct ext3_sb_info *sbi = EXT3_SB(sb);
struct ext3_super_block *es = sbi->s_es;
int ngroups = sbi->s_groups_count;
int inodes_per_group = EXT3_INODES_PER_GROUP(sb);
int freei, avefreei;
int freeb, avefreeb;
int blocks_per_dir, ndirs;
int max_debt, max_dirs, min_blocks, min_inodes;
int group = -1, i;
struct ext3_group_desc *desc;
struct buffer_head *bh;
freei = percpu_counter_read_positive(&sbi->s_freeinodes_counter);
avefreei = freei / ngroups;
freeb = percpu_counter_read_positive(&sbi->s_freeblocks_counter);
avefreeb = freeb / ngroups;
ndirs = percpu_counter_read_positive(&sbi->s_dirs_counter);
if ((parent == sb->s_root->d_inode) ||
(EXT3_I(parent)->i_flags & EXT3_TOPDIR_FL)) {
int best_ndir = inodes_per_group;
int best_group = -1;
get_random_bytes(&group, sizeof(group));
parent_group = (unsigned)group % ngroups;
for (i = 0; i < ngroups; i++) {
group = (parent_group + i) % ngroups;
desc = ext3_get_group_desc (sb, group, &bh);
if (!desc || !desc->bg_free_inodes_count)
continue;
if (le16_to_cpu(desc->bg_used_dirs_count) >= best_ndir)
continue;
if (le16_to_cpu(desc->bg_free_inodes_count) < avefreei)
continue;
if (le16_to_cpu(desc->bg_free_blocks_count) < avefreeb)
continue;
best_group = group;
best_ndir = le16_to_cpu(desc->bg_used_dirs_count);
}
if (best_group >= 0)
return best_group;
goto fallback;
}
blocks_per_dir = (le32_to_cpu(es->s_blocks_count) - freeb) / ndirs;
max_dirs = ndirs / ngroups + inodes_per_group / 16;
min_inodes = avefreei - inodes_per_group / 4;
min_blocks = avefreeb - EXT3_BLOCKS_PER_GROUP(sb) / 4;
max_debt = EXT3_BLOCKS_PER_GROUP(sb) / max(blocks_per_dir, BLOCK_COST);
if (max_debt * INODE_COST > inodes_per_group)
max_debt = inodes_per_group / INODE_COST;
if (max_debt > 255)
max_debt = 255;
if (max_debt == 0)
max_debt = 1;
for (i = 0; i < ngroups; i++) {
group = (parent_group + i) % ngroups;
desc = ext3_get_group_desc (sb, group, &bh);
if (!desc || !desc->bg_free_inodes_count)
continue;
if (le16_to_cpu(desc->bg_used_dirs_count) >= max_dirs)
continue;
if (le16_to_cpu(desc->bg_free_inodes_count) < min_inodes)
continue;
if (le16_to_cpu(desc->bg_free_blocks_count) < min_blocks)
continue;
return group;
}
fallback:
for (i = 0; i < ngroups; i++) {
group = (parent_group + i) % ngroups;
desc = ext3_get_group_desc (sb, group, &bh);
if (!desc || !desc->bg_free_inodes_count)
continue;
if (le16_to_cpu(desc->bg_free_inodes_count) >= avefreei)
return group;
}
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;
}
return -1;
}
/*
* 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 ext3_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;
unsigned long block_group;
unsigned long bit;
struct ext3_group_desc * gdp;
struct ext3_super_block * es;
struct ext3_sb_info *sbi;
int fatal = 0, err;
if (atomic_read(&inode->i_count) > 1) {
printk ("ext3_free_inode: inode has count=%d\n",
atomic_read(&inode->i_count));
return;
}
if (inode->i_nlink) {
printk ("ext3_free_inode: inode has nlink=%d\n",
inode->i_nlink);
return;
}
if (!sb) {
printk("ext3_free_inode: inode on nonexistent device\n");
return;
}
sbi = EXT3_SB(sb);
ino = inode->i_ino;
ext3_debug ("freeing inode %lu\n", ino);
is_directory = S_ISDIR(inode->i_mode);
es = EXT3_SB(sb)->s_es;
if (ino < EXT3_FIRST_INO(sb) || ino > le32_to_cpu(es->s_inodes_count)) {
ext3_error (sb, "ext3_free_inode",
"reserved or nonexistent inode %lu", ino);
goto error_return;
}
block_group = (ino - 1) / EXT3_INODES_PER_GROUP(sb);
bit = (ino - 1) % EXT3_INODES_PER_GROUP(sb);
bitmap_bh = read_inode_bitmap(sb, block_group);
if (!bitmap_bh)
goto error_return;
BUFFER_TRACE(bitmap_bh, "get_write_access");
fatal = ext3_journal_get_write_access(handle, bitmap_bh);
if (fatal)
goto error_return;
/* Ok, now we can actually update the inode bitmaps.. */
if (!ext3_clear_bit_atomic(sb_bgl_lock(sbi, block_group),
bit, bitmap_bh->b_data))
ext3_error (sb, "ext3_free_inode",
"bit already cleared for inode %lu", ino);
else {
gdp = ext3_get_group_desc (sb, block_group, &bh2);
BUFFER_TRACE(bh2, "get_write_access");
fatal = ext3_journal_get_write_access(handle, bh2);
if (fatal) goto error_return;
if (gdp) {
spin_lock(sb_bgl_lock(sbi, block_group));
le16_add_cpu(&gdp->bg_free_inodes_count, 1);
if (is_directory)
le16_add_cpu(&gdp->bg_used_dirs_count, -1);
spin_unlock(sb_bgl_lock(sbi, block_group));
percpu_counter_inc(&sbi->s_freeinodes_counter);
if (is_directory)
percpu_counter_dec(&sbi->s_dirs_counter);
}
BUFFER_TRACE(bh2, "call ext3_journal_dirty_metadata");
err = ext3_journal_dirty_metadata(handle, bh2);
if (!fatal) fatal = err;
}
BUFFER_TRACE(bitmap_bh, "call ext3_journal_dirty_metadata");
err = ext3_journal_dirty_metadata(handle, bitmap_bh);
if (!fatal)
fatal = err;
error_return:
brelse(bitmap_bh);
ext3_std_error(sb, fatal);
}
static int find_group_orlov(struct super_block *sb, struct inode *parent)
{
int parent_group = EXT3_I(parent)->i_block_group;
struct ext3_sb_info *sbi = EXT3_SB(sb);
int ngroups = sbi->s_groups_count;
int inodes_per_group = EXT3_INODES_PER_GROUP(sb);
unsigned int freei, avefreei;
ext3_fsblk_t freeb, avefreeb;
unsigned int ndirs;
int max_dirs, min_inodes;
ext3_grpblk_t min_blocks;
int group = -1, i;
struct ext3_group_desc *desc;
freei = percpu_counter_read_positive(&sbi->s_freeinodes_counter);
avefreei = freei / ngroups;
freeb = percpu_counter_read_positive(&sbi->s_freeblocks_counter);
avefreeb = freeb / ngroups;
ndirs = percpu_counter_read_positive(&sbi->s_dirs_counter);
if ((parent == sb->s_root->d_inode) ||
(EXT3_I(parent)->i_flags & EXT3_TOPDIR_FL)) {
int best_ndir = inodes_per_group;
int best_group = -1;
group = prandom_u32();
parent_group = (unsigned)group % ngroups;
for (i = 0; i < ngroups; i++) {
group = (parent_group + i) % ngroups;
desc = ext3_get_group_desc (sb, group, NULL);
if (!desc || !desc->bg_free_inodes_count)
continue;
if (le16_to_cpu(desc->bg_used_dirs_count) >= best_ndir)
continue;
if (le16_to_cpu(desc->bg_free_inodes_count) < avefreei)
continue;
if (le16_to_cpu(desc->bg_free_blocks_count) < avefreeb)
continue;
best_group = group;
best_ndir = le16_to_cpu(desc->bg_used_dirs_count);
}
if (best_group >= 0)
return best_group;
goto fallback;
}
max_dirs = ndirs / ngroups + inodes_per_group / 16;
min_inodes = avefreei - inodes_per_group / 4;
min_blocks = avefreeb - EXT3_BLOCKS_PER_GROUP(sb) / 4;
for (i = 0; i < ngroups; i++) {
group = (parent_group + i) % ngroups;
desc = ext3_get_group_desc (sb, group, NULL);
if (!desc || !desc->bg_free_inodes_count)
continue;
if (le16_to_cpu(desc->bg_used_dirs_count) >= max_dirs)
continue;
if (le16_to_cpu(desc->bg_free_inodes_count) < min_inodes)
continue;
if (le16_to_cpu(desc->bg_free_blocks_count) < min_blocks)
continue;
return group;
}
fallback:
for (i = 0; i < ngroups; i++) {
group = (parent_group + i) % ngroups;
desc = ext3_get_group_desc (sb, group, NULL);
if (!desc || !desc->bg_free_inodes_count)
continue;
if (le16_to_cpu(desc->bg_free_inodes_count) >= avefreei)
return group;
}
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;
}
return -1;
}
/*
* 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 *ext3_new_inode(handle_t *handle, struct inode * dir, int mode)
{
struct super_block *sb;
struct buffer_head *bitmap_bh = NULL;
struct buffer_head *bh2;
int group;
unsigned long ino = 0;
struct inode * inode;
struct ext3_group_desc * gdp = NULL;
struct ext3_super_block * es;
struct ext3_inode_info *ei;
struct ext3_sb_info *sbi;
int err = 0;
struct inode *ret;
int i;
/* Cannot create files in a deleted directory */
if (!dir || !dir->i_nlink)
return ERR_PTR(-EPERM);
sb = dir->i_sb;
inode = new_inode(sb);
if (!inode)
return ERR_PTR(-ENOMEM);
ei = EXT3_I(inode);
sbi = EXT3_SB(sb);
es = sbi->s_es;
if (S_ISDIR(mode)) {
if (test_opt (sb, OLDALLOC))
group = find_group_dir(sb, dir);
else
group = find_group_orlov(sb, dir);
} else
group = find_group_other(sb, dir);
err = -ENOSPC;
if (group == -1)
goto out;
for (i = 0; i < sbi->s_groups_count; i++) {
err = -EIO;
gdp = ext3_get_group_desc(sb, group, &bh2);
if (!gdp)
goto fail;
brelse(bitmap_bh);
bitmap_bh = read_inode_bitmap(sb, group);
if (!bitmap_bh)
goto fail;
ino = 0;
repeat_in_this_group:
ino = ext3_find_next_zero_bit((unsigned long *)
bitmap_bh->b_data, EXT3_INODES_PER_GROUP(sb), ino);
if (ino < EXT3_INODES_PER_GROUP(sb)) {
BUFFER_TRACE(bitmap_bh, "get_write_access");
err = ext3_journal_get_write_access(handle, bitmap_bh);
if (err)
goto fail;
if (!ext3_set_bit_atomic(sb_bgl_lock(sbi, group),
ino, bitmap_bh->b_data)) {
/* we won it */
BUFFER_TRACE(bitmap_bh,
"call ext3_journal_dirty_metadata");
err = ext3_journal_dirty_metadata(handle,
bitmap_bh);
if (err)
goto fail;
goto got;
}
/* we lost it */
journal_release_buffer(handle, bitmap_bh);
if (++ino < EXT3_INODES_PER_GROUP(sb))
goto repeat_in_this_group;
}
/*
* This case is possible in concurrent environment. It is very
* rare. We cannot repeat the find_group_xxx() call because
* that will simply return the same blockgroup, because the
* group descriptor metadata has not yet been updated.
* So we just go onto the next blockgroup.
*/
if (++group == sbi->s_groups_count)
group = 0;
}
err = -ENOSPC;
goto out;
got:
ino += group * EXT3_INODES_PER_GROUP(sb) + 1;
if (ino < EXT3_FIRST_INO(sb) || ino > le32_to_cpu(es->s_inodes_count)) {
ext3_error (sb, "ext3_new_inode",
"reserved inode or inode > inodes count - "
"block_group = %d, inode=%lu", group, ino);
err = -EIO;
goto fail;
}
BUFFER_TRACE(bh2, "get_write_access");
err = ext3_journal_get_write_access(handle, bh2);
if (err) goto fail;
spin_lock(sb_bgl_lock(sbi, group));
le16_add_cpu(&gdp->bg_free_inodes_count, -1);
if (S_ISDIR(mode)) {
le16_add_cpu(&gdp->bg_used_dirs_count, 1);
}
spin_unlock(sb_bgl_lock(sbi, group));
BUFFER_TRACE(bh2, "call ext3_journal_dirty_metadata");
err = ext3_journal_dirty_metadata(handle, bh2);
if (err) goto fail;
percpu_counter_dec(&sbi->s_freeinodes_counter);
if (S_ISDIR(mode))
percpu_counter_inc(&sbi->s_dirs_counter);
if (test_opt(sb, GRPID)) {
inode->i_mode = mode;
inode->i_uid = current_fsuid();
inode->i_gid = dir->i_gid;
} else
inode_init_owner(inode, dir, mode);
inode->i_ino = ino;
/* This is the optimal IO size (for stat), not the fs block size */
inode->i_blocks = 0;
inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC;
memset(ei->i_data, 0, sizeof(ei->i_data));
ei->i_dir_start_lookup = 0;
ei->i_disksize = 0;
ei->i_flags =
ext3_mask_flags(mode, EXT3_I(dir)->i_flags & EXT3_FL_INHERITED);
#ifdef EXT3_FRAGMENTS
ei->i_faddr = 0;
ei->i_frag_no = 0;
ei->i_frag_size = 0;
#endif
ei->i_file_acl = 0;
ei->i_dir_acl = 0;
ei->i_dtime = 0;
ei->i_block_alloc_info = NULL;
ei->i_block_group = group;
ext3_set_inode_flags(inode);
if (IS_DIRSYNC(inode))
handle->h_sync = 1;
if (insert_inode_locked(inode) < 0) {
err = -EINVAL;
goto fail_drop;
}
spin_lock(&sbi->s_next_gen_lock);
inode->i_generation = sbi->s_next_generation++;
spin_unlock(&sbi->s_next_gen_lock);
ei->i_state_flags = 0;
ext3_set_inode_state(inode, EXT3_STATE_NEW);
ei->i_extra_isize =
(EXT3_INODE_SIZE(inode->i_sb) > EXT3_GOOD_OLD_INODE_SIZE) ?
sizeof(struct ext3_inode) - EXT3_GOOD_OLD_INODE_SIZE : 0;
ret = inode;
dquot_initialize(inode);
err = dquot_alloc_inode(inode);
if (err)
goto fail_drop;
err = ext3_init_acl(handle, inode, dir);
if (err)
goto fail_free_drop;
err = ext3_init_security(handle,inode, dir);
if (err)
goto fail_free_drop;
err = ext3_mark_inode_dirty(handle, inode);
if (err) {
ext3_std_error(sb, err);
goto fail_free_drop;
}
ext3_debug("allocating inode %lu\n", inode->i_ino);
goto really_out;
fail:
ext3_std_error(sb, err);
out:
iput(inode);
ret = ERR_PTR(err);
really_out:
brelse(bitmap_bh);
return ret;
fail_free_drop:
dquot_free_inode(inode);
fail_drop:
dquot_drop(inode);
inode->i_flags |= S_NOQUOTA;
inode->i_nlink = 0;
unlock_new_inode(inode);
iput(inode);
brelse(bitmap_bh);
return ERR_PTR(err);
}
/*
* 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 *ext3_new_inode(handle_t *handle, struct inode * dir, int mode)
{
struct super_block *sb;
struct buffer_head *bitmap_bh = NULL;
struct buffer_head *bh2;
int group;
unsigned long ino = 0;
struct inode * inode;
struct ext3_group_desc * gdp = NULL;
struct ext3_super_block * es;
struct ext3_inode_info *ei;
struct ext3_sb_info *sbi;
int err = 0;
struct inode *ret;
int i;
/* Cannot create files in a deleted directory */
if (!dir || !dir->i_nlink)
return ERR_PTR(-EPERM);
sb = dir->i_sb;
inode = new_inode(sb);
if (!inode)
return ERR_PTR(-ENOMEM);
ei = EXT3_I(inode);
sbi = EXT3_SB(sb);
es = sbi->s_es;
if (S_ISDIR(mode)) {
if (test_opt (sb, OLDALLOC))
group = find_group_dir(sb, dir);
else
group = find_group_orlov(sb, dir);
} else
group = find_group_other(sb, dir);
err = -ENOSPC;
if (group == -1)
goto out;
for (i = 0; i < sbi->s_groups_count; i++) {
gdp = ext3_get_group_desc(sb, group, &bh2);
err = -EIO;
brelse(bitmap_bh);
bitmap_bh = read_inode_bitmap(sb, group);
if (!bitmap_bh)
goto fail;
ino = 0;
repeat_in_this_group:
ino = ext3_find_next_zero_bit((unsigned long *)
bitmap_bh->b_data, EXT3_INODES_PER_GROUP(sb), ino);
if (ino < EXT3_INODES_PER_GROUP(sb)) {
int credits = 0;
BUFFER_TRACE(bitmap_bh, "get_write_access");
err = ext3_journal_get_write_access_credits(handle,
bitmap_bh, &credits);
if (err)
goto fail;
if (!ext3_set_bit_atomic(sb_bgl_lock(sbi, group),
ino, bitmap_bh->b_data)) {
/* we won it */
BUFFER_TRACE(bitmap_bh,
"call ext3_journal_dirty_metadata");
err = ext3_journal_dirty_metadata(handle,
bitmap_bh);
if (err)
goto fail;
goto got;
}
/* we lost it */
journal_release_buffer(handle, bitmap_bh, credits);
if (++ino < EXT3_INODES_PER_GROUP(sb))
goto repeat_in_this_group;
}
/*
* This case is possible in concurrent environment. It is very
* rare. We cannot repeat the find_group_xxx() call because
* that will simply return the same blockgroup, because the
* group descriptor metadata has not yet been updated.
* So we just go onto the next blockgroup.
*/
if (++group == sbi->s_groups_count)
group = 0;
}
err = -ENOSPC;
goto out;
got:
ino += group * EXT3_INODES_PER_GROUP(sb) + 1;
if (ino < EXT3_FIRST_INO(sb) || ino > le32_to_cpu(es->s_inodes_count)) {
ext3_error (sb, "ext3_new_inode",
"reserved inode or inode > inodes count - "
"block_group = %d, inode=%lu", group, ino);
err = -EIO;
goto fail;
}
BUFFER_TRACE(bh2, "get_write_access");
err = ext3_journal_get_write_access(handle, bh2);
if (err) goto fail;
spin_lock(sb_bgl_lock(sbi, group));
gdp->bg_free_inodes_count =
cpu_to_le16(le16_to_cpu(gdp->bg_free_inodes_count) - 1);
if (S_ISDIR(mode)) {
gdp->bg_used_dirs_count =
cpu_to_le16(le16_to_cpu(gdp->bg_used_dirs_count) + 1);
}
spin_unlock(sb_bgl_lock(sbi, group));
BUFFER_TRACE(bh2, "call ext3_journal_dirty_metadata");
err = ext3_journal_dirty_metadata(handle, bh2);
if (err) goto fail;
percpu_counter_dec(&sbi->s_freeinodes_counter);
if (S_ISDIR(mode))
percpu_counter_inc(&sbi->s_dirs_counter);
sb->s_dirt = 1;
inode->i_uid = current->fsuid;
if (test_opt (sb, GRPID))
inode->i_gid = dir->i_gid;
else if (dir->i_mode & S_ISGID) {
inode->i_gid = dir->i_gid;
if (S_ISDIR(mode))
mode |= S_ISGID;
} else
inode->i_gid = current->fsgid;
inode->i_mode = mode;
inode->i_ino = ino;
/* This is the optimal IO size (for stat), not the fs block size */
inode->i_blksize = PAGE_SIZE;
inode->i_blocks = 0;
inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
memset(ei->i_data, 0, sizeof(ei->i_data));
ei->i_next_alloc_block = 0;
ei->i_next_alloc_goal = 0;
ei->i_dir_start_lookup = 0;
ei->i_disksize = 0;
ei->i_flags = EXT3_I(dir)->i_flags & ~EXT3_INDEX_FL;
if (S_ISLNK(mode))
ei->i_flags &= ~(EXT3_IMMUTABLE_FL|EXT3_APPEND_FL);
/* dirsync only applies to directories */
if (!S_ISDIR(mode))
ei->i_flags &= ~EXT3_DIRSYNC_FL;
#ifdef EXT3_FRAGMENTS
ei->i_faddr = 0;
ei->i_frag_no = 0;
ei->i_frag_size = 0;
#endif
ei->i_file_acl = 0;
ei->i_dir_acl = 0;
ei->i_dtime = 0;
#ifdef EXT3_PREALLOCATE
ei->i_prealloc_block = 0;
ei->i_prealloc_count = 0;
#endif
ei->i_block_group = group;
ext3_set_inode_flags(inode);
if (IS_DIRSYNC(inode))
handle->h_sync = 1;
insert_inode_hash(inode);
spin_lock(&sbi->s_next_gen_lock);
inode->i_generation = sbi->s_next_generation++;
spin_unlock(&sbi->s_next_gen_lock);
ei->i_state = EXT3_STATE_NEW;
ret = inode;
if(DQUOT_ALLOC_INODE(inode)) {
DQUOT_DROP(inode);
err = -EDQUOT;
goto fail2;
}
err = ext3_init_acl(handle, inode, dir);
if (err) {
DQUOT_FREE_INODE(inode);
goto fail2;
}
err = ext3_mark_inode_dirty(handle, inode);
if (err) {
ext3_std_error(sb, err);
DQUOT_FREE_INODE(inode);
goto fail2;
}
ext3_debug("allocating inode %lu\n", inode->i_ino);
goto really_out;
fail:
ext3_std_error(sb, err);
out:
iput(inode);
ret = ERR_PTR(err);
really_out:
brelse(bitmap_bh);
return ret;
fail2:
inode->i_flags |= S_NOQUOTA;
inode->i_nlink = 0;
iput(inode);
brelse(bitmap_bh);
return ERR_PTR(err);
}