Beispiel #1
0
/*
 * Set the access or default ACL of an inode.
 *
 * inode->i_mutex: down unless called from ext3_new_inode
 */
static int
ext3_set_acl(handle_t *handle, struct inode *inode, int type,
	     struct posix_acl *acl)
{
	int name_index;
	void *value = NULL;
	size_t size = 0;
	int error;

	if (S_ISLNK(inode->i_mode))
		return -EOPNOTSUPP;

	switch(type) {
		case ACL_TYPE_ACCESS:
			name_index = EXT3_XATTR_INDEX_POSIX_ACL_ACCESS;
			if (acl) {
				mode_t mode = inode->i_mode;
				error = posix_acl_equiv_mode(acl, &mode);
				if (error < 0)
					return error;
				else {
					inode->i_mode = mode;
					inode->i_ctime = CURRENT_TIME_SEC;
					ext3_mark_inode_dirty(handle, inode);
					if (error == 0)
						acl = NULL;
				}
			}
			break;

		case ACL_TYPE_DEFAULT:
			name_index = EXT3_XATTR_INDEX_POSIX_ACL_DEFAULT;
			if (!S_ISDIR(inode->i_mode))
				return acl ? -EACCES : 0;
			break;

		default:
			return -EINVAL;
	}
	if (acl) {
		value = ext3_acl_to_disk(acl, &size);
		if (IS_ERR(value))
			return (int)PTR_ERR(value);
	}

	error = ext3_xattr_set_handle(handle, inode, name_index, "",
				      value, size, 0);

	kfree(value);

	if (!error)
		set_cached_acl(inode, type, acl);

	return error;
}
/*
 * 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));
	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_SEC;

	memset(ei->i_data, 0, sizeof(ei->i_data));
	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;
	ei->i_block_alloc_info = NULL;
	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;
	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;
	if(DQUOT_ALLOC_INODE(inode)) {
		err = -EDQUOT;
		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;
	iput(inode);
	brelse(bitmap_bh);
	return ERR_PTR(err);
}
Beispiel #3
0
/*
 * 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,
				const struct inode * dir, int mode)
{
	struct super_block * sb;
	struct buffer_head * bh;
	struct buffer_head * bh2;
	int i, j, avefreei;
	struct inode * inode;
	int bitmap_nr;
	struct ext3_group_desc * gdp;
	struct ext3_group_desc * tmp;
	struct ext3_super_block * es;
	int err = 0;

	/* 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);
	init_rwsem(&inode->u.ext3_i.truncate_sem);

	lock_super (sb);
	es = sb->u.ext3_sb.s_es;
repeat:
	gdp = NULL;
	i = 0;

	if (S_ISDIR(mode)) {
		avefreei = le32_to_cpu(es->s_free_inodes_count) /
			sb->u.ext3_sb.s_groups_count;
		if (!gdp) {
			for (j = 0; j < sb->u.ext3_sb.s_groups_count; j++) {
				struct buffer_head *temp_buffer;
				tmp = ext3_get_group_desc (sb, j, &temp_buffer);
				if (tmp &&
				    le16_to_cpu(tmp->bg_free_inodes_count) &&
				    le16_to_cpu(tmp->bg_free_inodes_count) >=
							avefreei) {
					if (!gdp || (le16_to_cpu(tmp->bg_free_blocks_count) >
						le16_to_cpu(gdp->bg_free_blocks_count))) {
						i = j;
						gdp = tmp;
						bh2 = temp_buffer;
					}
				}
			}
		}
	} else {
		/*
		 * Try to place the inode in its parent directory
		 */
		i = dir->u.ext3_i.i_block_group;
		tmp = ext3_get_group_desc (sb, i, &bh2);
		if (tmp && le16_to_cpu(tmp->bg_free_inodes_count))
			gdp = tmp;
		else
		{
			/*
			 * Use a quadratic hash to find a group with a
			 * free inode
			 */
			for (j = 1; j < sb->u.ext3_sb.s_groups_count; j <<= 1) {
				i += j;
				if (i >= sb->u.ext3_sb.s_groups_count)
					i -= sb->u.ext3_sb.s_groups_count;
				tmp = ext3_get_group_desc (sb, i, &bh2);
				if (tmp &&
				    le16_to_cpu(tmp->bg_free_inodes_count)) {
					gdp = tmp;
					break;
				}
			}
		}
		if (!gdp) {
			/*
			 * That failed: try linear search for a free inode
			 */
			i = dir->u.ext3_i.i_block_group + 1;
			for (j = 2; j < sb->u.ext3_sb.s_groups_count; j++) {
				if (++i >= sb->u.ext3_sb.s_groups_count)
					i = 0;
				tmp = ext3_get_group_desc (sb, i, &bh2);
				if (tmp &&
				    le16_to_cpu(tmp->bg_free_inodes_count)) {
					gdp = tmp;
					break;
				}
			}
		}
	}

	err = -ENOSPC;
	if (!gdp)
		goto fail;

	err = -EIO;
	bitmap_nr = load_inode_bitmap (sb, i);
	if (bitmap_nr < 0)
		goto fail;

	bh = sb->u.ext3_sb.s_inode_bitmap[bitmap_nr];

	if ((j = ext3_find_first_zero_bit ((unsigned long *) bh->b_data,
				      EXT3_INODES_PER_GROUP(sb))) <
	    EXT3_INODES_PER_GROUP(sb)) {
		BUFFER_TRACE(bh, "get_write_access");
		err = ext3_journal_get_write_access(handle, bh);
		if (err) goto fail;
		
		if (ext3_set_bit (j, bh->b_data)) {
			ext3_error (sb, "ext3_new_inode",
				      "bit already set for inode %d", j);
			goto repeat;
		}
		BUFFER_TRACE(bh, "call ext3_journal_dirty_metadata");
		err = ext3_journal_dirty_metadata(handle, bh);
		if (err) goto fail;
	} else {
		if (le16_to_cpu(gdp->bg_free_inodes_count) != 0) {
			ext3_error (sb, "ext3_new_inode",
				    "Free inodes count corrupted in group %d",
				    i);
			/* Is it really ENOSPC? */
			err = -ENOSPC;
			if (sb->s_flags & MS_RDONLY)
				goto fail;

			BUFFER_TRACE(bh2, "get_write_access");
			err = ext3_journal_get_write_access(handle, bh2);
			if (err) goto fail;
			gdp->bg_free_inodes_count = 0;
			BUFFER_TRACE(bh2, "call ext3_journal_dirty_metadata");
			err = ext3_journal_dirty_metadata(handle, bh2);
			if (err) goto fail;
		}
		goto repeat;
	}
	j += i * EXT3_INODES_PER_GROUP(sb) + 1;
	if (j < EXT3_FIRST_INO(sb) || j > le32_to_cpu(es->s_inodes_count)) {
		ext3_error (sb, "ext3_new_inode",
			    "reserved inode or inode > inodes count - "
			    "block_group = %d,inode=%d", i, j);
		err = -EIO;
		goto fail;
	}

	BUFFER_TRACE(bh2, "get_write_access");
	err = ext3_journal_get_write_access(handle, bh2);
	if (err) goto fail;
	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);
	BUFFER_TRACE(bh2, "call ext3_journal_dirty_metadata");
	err = ext3_journal_dirty_metadata(handle, bh2);
	if (err) goto fail;
	
	BUFFER_TRACE(sb->u.ext3_sb.s_sbh, "get_write_access");
	err = ext3_journal_get_write_access(handle, sb->u.ext3_sb.s_sbh);
	if (err) goto fail;
	es->s_free_inodes_count =
		cpu_to_le32(le32_to_cpu(es->s_free_inodes_count) - 1);
	BUFFER_TRACE(sb->u.ext3_sb.s_sbh, "call ext3_journal_dirty_metadata");
	err = ext3_journal_dirty_metadata(handle, sb->u.ext3_sb.s_sbh);
	sb->s_dirt = 1;
	if (err) goto fail;

	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 = j;
	/* 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;
	inode->u.ext3_i.i_flags = dir->u.ext3_i.i_flags & ~EXT3_INDEX_FL;
	if (S_ISLNK(mode))
		inode->u.ext3_i.i_flags &= ~(EXT3_IMMUTABLE_FL|EXT3_APPEND_FL);
#ifdef EXT3_FRAGMENTS
	inode->u.ext3_i.i_faddr = 0;
	inode->u.ext3_i.i_frag_no = 0;
	inode->u.ext3_i.i_frag_size = 0;
#endif
	inode->u.ext3_i.i_file_acl = 0;
	inode->u.ext3_i.i_dir_acl = 0;
	inode->u.ext3_i.i_dtime = 0;
	INIT_LIST_HEAD(&inode->u.ext3_i.i_orphan);
#ifdef EXT3_PREALLOCATE
	inode->u.ext3_i.i_prealloc_count = 0;
#endif
	inode->u.ext3_i.i_block_group = i;
	
	if (inode->u.ext3_i.i_flags & EXT3_SYNC_FL)
		inode->i_flags |= S_SYNC;
	if (IS_SYNC(inode))
		handle->h_sync = 1;
	insert_inode_hash(inode);
	inode->i_generation = sb->u.ext3_sb.s_next_generation++;

	inode->u.ext3_i.i_state = EXT3_STATE_NEW;
	err = ext3_mark_inode_dirty(handle, inode);
	if (err) goto fail;
	
	unlock_super (sb);
	if(DQUOT_ALLOC_INODE(inode)) {
		DQUOT_DROP(inode);
		inode->i_flags |= S_NOQUOTA;
		inode->i_nlink = 0;
		iput(inode);
		return ERR_PTR(-EDQUOT);
	}
	ext3_debug ("allocating inode %lu\n", inode->i_ino);
	return inode;

fail:
	unlock_super(sb);
	iput(inode);
	ext3_std_error(sb, err);
	return ERR_PTR(err);
}
Beispiel #4
0
/*
 * Called at inode eviction from icache
 */
void ext3_evict_inode (struct inode *inode)
{
	struct ext3_inode_info *ei = EXT3_I(inode);
	struct ext3_block_alloc_info *rsv;
	handle_t *handle;
	int want_delete = 0;

	trace_ext3_evict_inode(inode);
	if (!inode->i_nlink && !is_bad_inode(inode)) {
		dquot_initialize(inode);
		want_delete = 1;
	}

	/*
	 * When journalling data dirty buffers are tracked only in the journal.
	 * So although mm thinks everything is clean and ready for reaping the
	 * inode might still have some pages to write in the running
	 * transaction or waiting to be checkpointed. Thus calling
	 * journal_invalidatepage() (via truncate_inode_pages()) to discard
	 * these buffers can cause data loss. Also even if we did not discard
	 * these buffers, we would have no way to find them after the inode
	 * is reaped and thus user could see stale data if he tries to read
	 * them before the transaction is checkpointed. So be careful and
	 * force everything to disk here... We use ei->i_datasync_tid to
	 * store the newest transaction containing inode's data.
	 *
	 * Note that directories do not have this problem because they don't
	 * use page cache.
	 *
	 * The s_journal check handles the case when ext3_get_journal() fails
	 * and puts the journal inode.
	 */
	if (inode->i_nlink && ext3_should_journal_data(inode) &&
	    EXT3_SB(inode->i_sb)->s_journal &&
	    (S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode)) &&
	    inode->i_ino != EXT3_JOURNAL_INO) {
		tid_t commit_tid = atomic_read(&ei->i_datasync_tid);
		journal_t *journal = EXT3_SB(inode->i_sb)->s_journal;

		log_start_commit(journal, commit_tid);
		log_wait_commit(journal, commit_tid);
		filemap_write_and_wait(&inode->i_data);
	}
	truncate_inode_pages(&inode->i_data, 0);

	ext3_discard_reservation(inode);
	rsv = ei->i_block_alloc_info;
	ei->i_block_alloc_info = NULL;
	if (unlikely(rsv))
		kfree(rsv);

	if (!want_delete)
		goto no_delete;

	handle = start_transaction(inode);
	if (IS_ERR(handle)) {
		/*
		 * If we're going to skip the normal cleanup, we still need to
		 * make sure that the in-core orphan linked list is properly
		 * cleaned up.
		 */
		ext3_orphan_del(NULL, inode);
		goto no_delete;
	}

	if (IS_SYNC(inode))
		handle->h_sync = 1;
	inode->i_size = 0;
	if (inode->i_blocks)
		ext3_truncate(inode);
	/*
	 * Kill off the orphan record created when the inode lost the last
	 * link.  Note that ext3_orphan_del() has to be able to cope with the
	 * deletion of a non-existent orphan - ext3_truncate() could
	 * have removed the record.
	 */
	ext3_orphan_del(handle, inode);
	ei->i_dtime = get_seconds();

	/*
	 * One subtle ordering requirement: if anything has gone wrong
	 * (transaction abort, IO errors, whatever), then we can still
	 * do these next steps (the fs will already have been marked as
	 * having errors), but we can't free the inode if the mark_dirty
	 * fails.
	 */
	if (ext3_mark_inode_dirty(handle, inode)) {
		/* If that failed, just dquot_drop() and be done with that */
		dquot_drop(inode);
		clear_inode(inode);
	} else {
		ext3_xattr_delete_inode(handle, inode);
		dquot_free_inode(inode);
		dquot_drop(inode);
		clear_inode(inode);
		ext3_free_inode(handle, inode);
	}
	ext3_journal_stop(handle);
	return;
no_delete:
	clear_inode(inode);
	dquot_drop(inode);
}
/*
 * inode->i_sem: down, or inode is just being initialized
 * BKL: held
 */
static int
ext3_do_set_acl(handle_t *handle, struct inode *inode, int type,
		struct posix_acl *acl)
{
	struct ext3_inode_info *ei = EXT3_I(inode);
	int name_index;
	void *value = NULL;
	size_t size;
	int error;

	if (S_ISLNK(inode->i_mode))
		return -ENODATA;

	switch(type) {
		case ACL_TYPE_ACCESS:
			name_index = EXT3_XATTR_INDEX_POSIX_ACL_ACCESS;
			if (acl) {
				mode_t mode = inode->i_mode;
				error = posix_acl_equiv_mode(acl, &mode);
				if (error < 0)
					return error;
				else {
					inode->i_mode = mode;
					ext3_mark_inode_dirty(handle, inode);
					if (error == 0)
						acl = NULL;
				}
			}
			break;

		case ACL_TYPE_DEFAULT:
			name_index = EXT3_XATTR_INDEX_POSIX_ACL_DEFAULT;
			if (!S_ISDIR(inode->i_mode))
				return acl ? -EACCES : 0;
			break;

		default:
			return -EINVAL;
	}
 	if (acl) {
		if (acl->a_count > EXT3_ACL_MAX_ENTRIES)
			return -EINVAL;
		value = ext3_acl_to_disk(acl, &size);
		if (IS_ERR(value))
			return (int)PTR_ERR(value);
	}

	error = ext3_xattr_set_handle(handle, inode, name_index, "",
				      value, size, 0);

	if (value)
		kfree(value);
	if (!error) {
		switch(type) {
			case ACL_TYPE_ACCESS:
				if (ei->i_acl != EXT3_ACL_NOT_CACHED)
					posix_acl_release(ei->i_acl);
				ei->i_acl = posix_acl_dup(acl);
				break;

			case ACL_TYPE_DEFAULT:
				if (ei->i_default_acl != EXT3_ACL_NOT_CACHED)
					posix_acl_release(ei->i_default_acl);
				ei->i_default_acl = posix_acl_dup(acl);
				break;
		}
	}
	return error;
}
Beispiel #6
0
/*
 * 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,
			     const struct qstr *qstr, umode_t 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;
	trace_ext3_request_inode(dir, mode);
	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))
		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) {
		/*
		 * Likely a bitmap corruption causing inode to be allocated
		 * twice.
		 */
		err = -EIO;
		goto fail;
	}
	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);

	/* See comment in ext3_iget for explanation */
	if (ino >= EXT3_FIRST_INO(sb) + 1 &&
	    EXT3_INODE_SIZE(sb) > EXT3_GOOD_OLD_INODE_SIZE) {
		ei->i_extra_isize =
			sizeof(struct ext3_inode) - EXT3_GOOD_OLD_INODE_SIZE;
	} else {
		ei->i_extra_isize = 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, qstr);
	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);
	trace_ext3_allocate_inode(inode, dir, mode);
	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;
	clear_nlink(inode);
	unlock_new_inode(inode);
	iput(inode);
	brelse(bitmap_bh);
	return ERR_PTR(err);
}