/* 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);
unsigned long block_group;
int bit;
struct buffer_head *bitmap_bh = NULL;
struct inode *inode = NULL;
/* Error cases - e2fsck has already cleaned up for us */
if (ino > max_ino) {
ext4_warning(sb, __FUNCTION__,
"bad orphan ino %lu! e2fsck was run?", ino);
goto out;
}
block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb);
bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb);
bitmap_bh = read_inode_bitmap(sb, block_group);
if (!bitmap_bh) {
ext4_warning(sb, __FUNCTION__,
"inode bitmap error for orphan %lu", ino);
goto out;
}
/* 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) ||
!(inode = iget(sb, ino)) || is_bad_inode(inode) ||
NEXT_ORPHAN(inode) > max_ino) {
ext4_warning(sb, __FUNCTION__,
"bad orphan inode %lu! e2fsck was run?", ino);
printk(KERN_NOTICE "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));
printk(KERN_NOTICE "inode=%p\n", inode);
if (inode) {
printk(KERN_NOTICE "is_bad_inode(inode)=%d\n",
is_bad_inode(inode));
printk(KERN_NOTICE "NEXT_ORPHAN(inode)=%u\n",
NEXT_ORPHAN(inode));
printk(KERN_NOTICE "max_ino=%lu\n", max_ino);
}
/* Avoid freeing blocks if we got a bad deleted inode */
if (inode && inode->i_nlink == 0)
inode->i_blocks = 0;
iput(inode);
inode = NULL;
}
out:
brelse(bitmap_bh);
return inode;
}
unsigned long ext4_count_free_inodes (struct super_block * sb)
{
unsigned long desc_count;
struct ext4_group_desc *gdp;
int i;
#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 < EXT4_SB(sb)->s_groups_count; i++) {
gdp = ext4_get_group_desc (sb, i, NULL);
if (!gdp)
continue;
desc_count += le16_to_cpu(gdp->bg_free_inodes_count);
brelse(bitmap_bh);
bitmap_bh = read_inode_bitmap(sb, i);
if (!bitmap_bh)
continue;
x = ext4_count_free(bitmap_bh, EXT4_INODES_PER_GROUP(sb) / 8);
printk("group %d: stored = %d, counted = %lu\n",
i, le16_to_cpu(gdp->bg_free_inodes_count), x);
bitmap_count += x;
}
brelse(bitmap_bh);
printk("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 < EXT4_SB(sb)->s_groups_count; i++) {
gdp = ext4_get_group_desc (sb, i, NULL);
if (!gdp)
continue;
desc_count += le16_to_cpu(gdp->bg_free_inodes_count);
cond_resched();
}
return desc_count;
#endif
}
int ext4_ext_migrate(struct inode *inode)
{
handle_t *handle;
int retval = 0, i;
__le32 *i_data;
struct ext4_inode_info *ei;
struct inode *tmp_inode = NULL;
struct migrate_struct lb;
unsigned long max_entries;
__u32 goal;
uid_t owner[2];
/*
* If the filesystem does not support extents, or the inode
* already is extent-based, error out.
*/
if (!EXT4_HAS_INCOMPAT_FEATURE(inode->i_sb,
EXT4_FEATURE_INCOMPAT_EXTENTS) ||
(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
return -EINVAL;
if (S_ISLNK(inode->i_mode) && inode->i_blocks == 0)
/*
* don't migrate fast symlink
*/
return retval;
/*
* Worst case we can touch the allocation bitmaps, a bgd
* block, and a block to link in the orphan list. We do need
* need to worry about credits for modifying the quota inode.
*/
handle = ext4_journal_start(inode, EXT4_HT_MIGRATE,
4 + EXT4_MAXQUOTAS_TRANS_BLOCKS(inode->i_sb));
if (IS_ERR(handle)) {
retval = PTR_ERR(handle);
return retval;
}
goal = (((inode->i_ino - 1) / EXT4_INODES_PER_GROUP(inode->i_sb)) *
EXT4_INODES_PER_GROUP(inode->i_sb)) + 1;
owner[0] = i_uid_read(inode);
owner[1] = i_gid_read(inode);
tmp_inode = ext4_new_inode(handle, inode->i_sb->s_root->d_inode,
S_IFREG, NULL, goal, owner);
if (IS_ERR(tmp_inode)) {
retval = PTR_ERR(tmp_inode);
ext4_journal_stop(handle);
return retval;
}
i_size_write(tmp_inode, i_size_read(inode));
/*
* Set the i_nlink to zero so it will be deleted later
* when we drop inode reference.
*/
clear_nlink(tmp_inode);
ext4_ext_tree_init(handle, tmp_inode);
ext4_orphan_add(handle, tmp_inode);
ext4_journal_stop(handle);
/*
* start with one credit accounted for
* superblock modification.
*
* For the tmp_inode we already have committed the
* trascation that created the inode. Later as and
* when we add extents we extent the journal
*/
/*
* Even though we take i_mutex we can still cause block
* allocation via mmap write to holes. If we have allocated
* new blocks we fail migrate. New block allocation will
* clear EXT4_STATE_EXT_MIGRATE flag. The flag is updated
* with i_data_sem held to prevent racing with block
* allocation.
*/
down_read((&EXT4_I(inode)->i_data_sem));
ext4_set_inode_state(inode, EXT4_STATE_EXT_MIGRATE);
up_read((&EXT4_I(inode)->i_data_sem));
handle = ext4_journal_start(inode, EXT4_HT_MIGRATE, 1);
if (IS_ERR(handle)) {
/*
* It is impossible to update on-disk structures without
* a handle, so just rollback in-core changes and live other
* work to orphan_list_cleanup()
*/
ext4_orphan_del(NULL, tmp_inode);
retval = PTR_ERR(handle);
goto out;
}
ei = EXT4_I(inode);
i_data = ei->i_data;
memset(&lb, 0, sizeof(lb));
/* 32 bit block address 4 bytes */
max_entries = inode->i_sb->s_blocksize >> 2;
for (i = 0; i < EXT4_NDIR_BLOCKS; i++) {
if (i_data[i]) {
retval = update_extent_range(handle, tmp_inode,
le32_to_cpu(i_data[i]), &lb);
if (retval)
goto err_out;
} else
lb.curr_block++;
}
if (i_data[EXT4_IND_BLOCK]) {
retval = update_ind_extent_range(handle, tmp_inode,
le32_to_cpu(i_data[EXT4_IND_BLOCK]), &lb);
if (retval)
goto err_out;
} else
lb.curr_block += max_entries;
if (i_data[EXT4_DIND_BLOCK]) {
retval = update_dind_extent_range(handle, tmp_inode,
le32_to_cpu(i_data[EXT4_DIND_BLOCK]), &lb);
if (retval)
goto err_out;
} else
lb.curr_block += max_entries * max_entries;
if (i_data[EXT4_TIND_BLOCK]) {
retval = update_tind_extent_range(handle, tmp_inode,
le32_to_cpu(i_data[EXT4_TIND_BLOCK]), &lb);
if (retval)
goto err_out;
}
/*
* Build the last extent
*/
retval = finish_range(handle, tmp_inode, &lb);
err_out:
if (retval)
/*
* Failure case delete the extent information with the
* tmp_inode
*/
free_ext_block(handle, tmp_inode);
else {
retval = ext4_ext_swap_inode_data(handle, inode, tmp_inode);
if (retval)
/*
* if we fail to swap inode data free the extent
* details of the tmp inode
*/
free_ext_block(handle, tmp_inode);
}
/* We mark the tmp_inode dirty via ext4_ext_tree_init. */
if (ext4_journal_extend(handle, 1) != 0)
ext4_journal_restart(handle, 1);
/*
* Mark the tmp_inode as of size zero
*/
i_size_write(tmp_inode, 0);
/*
* set the i_blocks count to zero
* so that the ext4_delete_inode does the
* right job
*
* We don't need to take the i_lock because
* the inode is not visible to user space.
*/
tmp_inode->i_blocks = 0;
/* Reset the extent details */
ext4_ext_tree_init(handle, tmp_inode);
ext4_journal_stop(handle);
out:
unlock_new_inode(tmp_inode);
iput(tmp_inode);
return retval;
}
int ext4_ext_migrate(struct inode *inode)
{
handle_t *handle;
int retval = 0, i;
__le32 *i_data;
ext4_lblk_t blk_count = 0;
struct ext4_inode_info *ei;
struct inode *tmp_inode = NULL;
struct list_blocks_struct lb;
unsigned long max_entries;
__u32 goal;
/*
* If the filesystem does not support extents, or the inode
* already is extent-based, error out.
*/
if (!EXT4_HAS_INCOMPAT_FEATURE(inode->i_sb,
EXT4_FEATURE_INCOMPAT_EXTENTS) ||
(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL))
return -EINVAL;
if (S_ISLNK(inode->i_mode) && inode->i_blocks == 0)
/*
* don't migrate fast symlink
*/
return retval;
handle = ext4_journal_start(inode,
EXT4_DATA_TRANS_BLOCKS(inode->i_sb) +
EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 +
EXT4_MAXQUOTAS_INIT_BLOCKS(inode->i_sb)
+ 1);
if (IS_ERR(handle)) {
retval = PTR_ERR(handle);
return retval;
}
goal = (((inode->i_ino - 1) / EXT4_INODES_PER_GROUP(inode->i_sb)) *
EXT4_INODES_PER_GROUP(inode->i_sb)) + 1;
tmp_inode = ext4_new_inode(handle, inode->i_sb->s_root->d_inode,
S_IFREG, 0, goal);
if (IS_ERR(tmp_inode)) {
retval = -ENOMEM;
ext4_journal_stop(handle);
return retval;
}
i_size_write(tmp_inode, i_size_read(inode));
/*
* We don't want the inode to be reclaimed
* if we got interrupted in between. We have
* this tmp inode carrying reference to the
* data blocks of the original file. We set
* the i_nlink to zero at the last stage after
* switching the original file to extent format
*/
tmp_inode->i_nlink = 1;
ext4_ext_tree_init(handle, tmp_inode);
ext4_orphan_add(handle, tmp_inode);
ext4_journal_stop(handle);
/*
* start with one credit accounted for
* superblock modification.
*
* For the tmp_inode we already have commited the
* trascation that created the inode. Later as and
* when we add extents we extent the journal
*/
/*
* Even though we take i_mutex we can still cause block
* allocation via mmap write to holes. If we have allocated
* new blocks we fail migrate. New block allocation will
* clear EXT4_STATE_EXT_MIGRATE flag. The flag is updated
* with i_data_sem held to prevent racing with block
* allocation.
*/
down_read((&EXT4_I(inode)->i_data_sem));
EXT4_I(inode)->i_state |= EXT4_STATE_EXT_MIGRATE;
up_read((&EXT4_I(inode)->i_data_sem));
handle = ext4_journal_start(inode, 1);
ei = EXT4_I(inode);
i_data = ei->i_data;
memset(&lb, 0, sizeof(lb));
/* 32 bit block address 4 bytes */
max_entries = inode->i_sb->s_blocksize >> 2;
for (i = 0; i < EXT4_NDIR_BLOCKS; i++, blk_count++) {
if (i_data[i]) {
retval = update_extent_range(handle, tmp_inode,
le32_to_cpu(i_data[i]),
blk_count, &lb);
if (retval)
goto err_out;
}
}
if (i_data[EXT4_IND_BLOCK]) {
retval = update_ind_extent_range(handle, tmp_inode,
le32_to_cpu(i_data[EXT4_IND_BLOCK]),
&blk_count, &lb);
if (retval)
goto err_out;
} else
blk_count += max_entries;
if (i_data[EXT4_DIND_BLOCK]) {
retval = update_dind_extent_range(handle, tmp_inode,
le32_to_cpu(i_data[EXT4_DIND_BLOCK]),
&blk_count, &lb);
if (retval)
goto err_out;
} else
blk_count += max_entries * max_entries;
if (i_data[EXT4_TIND_BLOCK]) {
retval = update_tind_extent_range(handle, tmp_inode,
le32_to_cpu(i_data[EXT4_TIND_BLOCK]),
&blk_count, &lb);
if (retval)
goto err_out;
}
/*
* Build the last extent
*/
retval = finish_range(handle, tmp_inode, &lb);
err_out:
if (retval)
/*
* Failure case delete the extent information with the
* tmp_inode
*/
free_ext_block(handle, tmp_inode);
else {
retval = ext4_ext_swap_inode_data(handle, inode, tmp_inode);
if (retval)
/*
* if we fail to swap inode data free the extent
* details of the tmp inode
*/
free_ext_block(handle, tmp_inode);
}
/* We mark the tmp_inode dirty via ext4_ext_tree_init. */
if (ext4_journal_extend(handle, 1) != 0)
ext4_journal_restart(handle, 1);
/*
* Mark the tmp_inode as of size zero
*/
i_size_write(tmp_inode, 0);
/*
* set the i_blocks count to zero
* so that the ext4_delete_inode does the
* right job
*
* We don't need to take the i_lock because
* the inode is not visible to user space.
*/
tmp_inode->i_blocks = 0;
/* Reset the extent details */
ext4_ext_tree_init(handle, tmp_inode);
/*
* Set the i_nlink to zero so that
* generic_drop_inode really deletes the
* inode
*/
tmp_inode->i_nlink = 0;
ext4_journal_stop(handle);
unlock_new_inode(tmp_inode);
iput(tmp_inode);
return retval;
}
/*
* 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;
unsigned long block_group;
unsigned long bit;
struct ext4_group_desc * gdp;
struct ext4_super_block * es;
struct ext4_sb_info *sbi;
int fatal = 0, err;
if (atomic_read(&inode->i_count) > 1) {
printk ("ext4_free_inode: inode has count=%d\n",
atomic_read(&inode->i_count));
return;
}
if (inode->i_nlink) {
printk ("ext4_free_inode: inode has nlink=%d\n",
inode->i_nlink);
return;
}
if (!sb) {
printk("ext4_free_inode: inode on nonexistent device\n");
return;
}
sbi = EXT4_SB(sb);
ino = inode->i_ino;
ext4_debug ("freeing inode %lu\n", ino);
/*
* Note: we must free any quota before locking the superblock,
* as writing the quota to disk may need the lock as well.
*/
DQUOT_INIT(inode);
ext4_xattr_delete_inode(handle, inode);
DQUOT_FREE_INODE(inode);
DQUOT_DROP(inode);
is_directory = S_ISDIR(inode->i_mode);
/* Do this BEFORE marking the inode not in use or returning an error */
clear_inode (inode);
es = EXT4_SB(sb)->s_es;
if (ino < EXT4_FIRST_INO(sb) || ino > le32_to_cpu(es->s_inodes_count)) {
ext4_error (sb, "ext4_free_inode",
"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 = read_inode_bitmap(sb, block_group);
if (!bitmap_bh)
goto error_return;
BUFFER_TRACE(bitmap_bh, "get_write_access");
fatal = ext4_journal_get_write_access(handle, bitmap_bh);
if (fatal)
goto error_return;
/* Ok, now we can actually update the inode bitmaps.. */
if (!ext4_clear_bit_atomic(sb_bgl_lock(sbi, block_group),
bit, bitmap_bh->b_data))
ext4_error (sb, "ext4_free_inode",
"bit already cleared for inode %lu", ino);
else {
gdp = ext4_get_group_desc (sb, block_group, &bh2);
BUFFER_TRACE(bh2, "get_write_access");
fatal = ext4_journal_get_write_access(handle, bh2);
if (fatal) goto error_return;
if (gdp) {
spin_lock(sb_bgl_lock(sbi, block_group));
gdp->bg_free_inodes_count = cpu_to_le16(
le16_to_cpu(gdp->bg_free_inodes_count) + 1);
if (is_directory)
gdp->bg_used_dirs_count = cpu_to_le16(
le16_to_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 ext4_journal_dirty_metadata");
err = ext4_journal_dirty_metadata(handle, bh2);
if (!fatal) fatal = err;
}
BUFFER_TRACE(bitmap_bh, "call ext4_journal_dirty_metadata");
err = ext4_journal_dirty_metadata(handle, bitmap_bh);
if (!fatal)
fatal = err;
sb->s_dirt = 1;
error_return:
brelse(bitmap_bh);
ext4_std_error(sb, fatal);
}
/*
* 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(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 ext4_group_desc * gdp = NULL;
struct ext4_super_block * es;
struct ext4_inode_info *ei;
struct ext4_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 = EXT4_I(inode);
sbi = EXT4_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 = ext4_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 = ext4_find_next_zero_bit((unsigned long *)
bitmap_bh->b_data, EXT4_INODES_PER_GROUP(sb), ino);
if (ino < EXT4_INODES_PER_GROUP(sb)) {
BUFFER_TRACE(bitmap_bh, "get_write_access");
err = ext4_journal_get_write_access(handle, bitmap_bh);
if (err)
goto fail;
if (!ext4_set_bit_atomic(sb_bgl_lock(sbi, group),
ino, bitmap_bh->b_data)) {
/* we won it */
BUFFER_TRACE(bitmap_bh,
"call ext4_journal_dirty_metadata");
err = ext4_journal_dirty_metadata(handle,
bitmap_bh);
if (err)
goto fail;
goto got;
}
/* we lost it */
jbd2_journal_release_buffer(handle, bitmap_bh);
if (++ino < EXT4_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 * EXT4_INODES_PER_GROUP(sb) + 1;
if (ino < EXT4_FIRST_INO(sb) || ino > le32_to_cpu(es->s_inodes_count)) {
ext4_error (sb, "ext4_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 = ext4_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 ext4_journal_dirty_metadata");
err = ext4_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_blocks = 0;
inode->i_mtime = inode->i_atime = inode->i_ctime = ei->i_crtime =
ext4_current_time(inode);
memset(ei->i_data, 0, sizeof(ei->i_data));
ei->i_dir_start_lookup = 0;
ei->i_disksize = 0;
ei->i_flags = EXT4_I(dir)->i_flags & ~EXT4_INDEX_FL;
if (S_ISLNK(mode))
ei->i_flags &= ~(EXT4_IMMUTABLE_FL|EXT4_APPEND_FL);
/* dirsync only applies to directories */
if (!S_ISDIR(mode))
ei->i_flags &= ~EXT4_DIRSYNC_FL;
#ifdef EXT4_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;
ext4_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 = EXT4_STATE_NEW;
ei->i_extra_isize = EXT4_SB(sb)->s_want_extra_isize;
ret = inode;
if(DQUOT_ALLOC_INODE(inode)) {
err = -EDQUOT;
goto fail_drop;
}
err = ext4_init_acl(handle, inode, dir);
if (err)
goto fail_free_drop;
err = ext4_init_security(handle,inode, dir);
if (err)
goto fail_free_drop;
err = ext4_mark_inode_dirty(handle, inode);
if (err) {
ext4_std_error(sb, err);
goto fail_free_drop;
}
if (test_opt(sb, EXTENTS)) {
EXT4_I(inode)->i_flags |= EXT4_EXTENTS_FL;
ext4_ext_tree_init(handle, inode);
if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) {
err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh);
if (err) goto fail;
EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS);
BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "call ext4_journal_dirty_metadata");
err = ext4_journal_dirty_metadata(handle, EXT4_SB(sb)->s_sbh);
}
}
ext4_debug("allocating inode %lu\n", inode->i_ino);
goto really_out;
fail:
ext4_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;
iput(inode);
brelse(bitmap_bh);
return ERR_PTR(err);
}
static int find_group_orlov(struct super_block *sb, struct inode *parent)
{
int parent_group = EXT4_I(parent)->i_block_group;
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_super_block *es = sbi->s_es;
int ngroups = sbi->s_groups_count;
int inodes_per_group = EXT4_INODES_PER_GROUP(sb);
unsigned int freei, avefreei;
ext4_fsblk_t freeb, avefreeb;
ext4_fsblk_t blocks_per_dir;
unsigned int ndirs;
int max_debt, max_dirs, min_inodes;
ext4_grpblk_t min_blocks;
int group = -1, i;
struct ext4_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;
do_div(avefreeb, ngroups);
ndirs = percpu_counter_read_positive(&sbi->s_dirs_counter);
if ((parent == sb->s_root->d_inode) ||
(EXT4_I(parent)->i_flags & EXT4_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 = ext4_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 = ext4_blocks_count(es) - freeb;
do_div(blocks_per_dir, ndirs);
max_dirs = ndirs / ngroups + inodes_per_group / 16;
min_inodes = avefreei - inodes_per_group / 4;
min_blocks = avefreeb - EXT4_BLOCKS_PER_GROUP(sb) / 4;
max_debt = EXT4_BLOCKS_PER_GROUP(sb);
max_debt /= max_t(int, 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 = ext4_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 = ext4_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;
}
