/*
   * Copyright 2000 by Hans Reiser, licensing governed by reiserfs/README
   */

  #include <linux/time.h>
  #include <linux/fs.h>

  #include "reiserfs.h"

  #include "acl.h"

  #include "xattr.h"

  #include <linux/exportfs.h>

  #include <linux/pagemap.h>
  #include <linux/highmem.h>

  #include <linux/slab.h>

  #include <linux/uaccess.h>

  #include <asm/unaligned.h>
  #include <linux/buffer_head.h>
  #include <linux/mpage.h>
  #include <linux/writeback.h>
  #include <linux/quotaops.h>

  #include <linux/swap.h>

  #include <linux/uio.h>

  #include <linux/bio.h>

  int reiserfs_commit_write(struct file *f, struct page *page,
  			  unsigned from, unsigned to);

  void reiserfs_evict_inode(struct inode *inode)

  {

  	/*
  	 * We need blocks for transaction + (user+group) quota
  	 * update (possibly delete)
  	 */

  	int jbegin_count =
  	    JOURNAL_PER_BALANCE_CNT * 2 +
  	    2 * REISERFS_QUOTA_INIT_BLOCKS(inode->i_sb);
  	struct reiserfs_transaction_handle th;

  	int err;

  	if (!inode->i_nlink && !is_bad_inode(inode))

  		dquot_initialize(inode);

  	truncate_inode_pages_final(&inode->i_data);

  	if (inode->i_nlink)
  		goto no_delete;

  	/*
  	 * The = 0 happens when we abort creating a new inode
  	 * for some reason like lack of space..
  	 * also handles bad_inode case
  	 */
  	if (!(inode->i_state & I_NEW) && INODE_PKEY(inode)->k_objectid != 0) {

  		reiserfs_delete_xattrs(inode);

  		reiserfs_write_lock(inode->i_sb);

  		if (journal_begin(&th, inode->i_sb, jbegin_count))

  			goto out;

  		reiserfs_update_inode_transaction(inode);

  		reiserfs_discard_prealloc(&th, inode);

  		err = reiserfs_delete_object(&th, inode);

  		/*
  		 * Do quota update inside a transaction for journaled quotas.
  		 * We must do that after delete_object so that quota updates
  		 * go into the same transaction as stat data deletion
  		 */

  		if (!err) {
  			int depth = reiserfs_write_unlock_nested(inode->i_sb);

  			dquot_free_inode(inode);

  			reiserfs_write_lock_nested(inode->i_sb, depth);
  		}

  		if (journal_end(&th))

  			goto out;

  		/*
  		 * check return value from reiserfs_delete_object after

  		 * ending the transaction
  		 */
  		if (err)
  		    goto out;

  		/*
  		 * all items of file are deleted, so we can remove
  		 * "save" link
  		 * we can't do anything about an error here
  		 */
  		remove_save_link(inode, 0 /* not truncate */);

  out:

  		reiserfs_write_unlock(inode->i_sb);

  	} else {
  		/* no object items are in the tree */
  		;
  	}

  
  	/* note this must go after the journal_end to prevent deadlock */
  	clear_inode(inode);

  	dquot_drop(inode);

  	inode->i_blocks = 0;

  	return;

  
  no_delete:

  	clear_inode(inode);

  	dquot_drop(inode);

  }

  static void _make_cpu_key(struct cpu_key *key, int version, __u32 dirid,
  			  __u32 objectid, loff_t offset, int type, int length)

  {

  	key->version = version;

  	key->on_disk_key.k_dir_id = dirid;
  	key->on_disk_key.k_objectid = objectid;
  	set_cpu_key_k_offset(key, offset);
  	set_cpu_key_k_type(key, type);
  	key->key_length = length;

  }

  /*
   * take base of inode_key (it comes from inode always) (dirid, objectid)
   * and version from an inode, set offset and type of key
   */

  void make_cpu_key(struct cpu_key *key, struct inode *inode, loff_t offset,
  		  int type, int length)

  {

  	_make_cpu_key(key, get_inode_item_key_version(inode),
  		      le32_to_cpu(INODE_PKEY(inode)->k_dir_id),
  		      le32_to_cpu(INODE_PKEY(inode)->k_objectid), offset, type,
  		      length);

  }

  /* when key is 0, do not set version and short key */

  inline void make_le_item_head(struct item_head *ih, const struct cpu_key *key,
  			      int version,
  			      loff_t offset, int type, int length,
  			      int entry_count /*or ih_free_space */ )

  {

  	if (key) {
  		ih->ih_key.k_dir_id = cpu_to_le32(key->on_disk_key.k_dir_id);
  		ih->ih_key.k_objectid =
  		    cpu_to_le32(key->on_disk_key.k_objectid);
  	}
  	put_ih_version(ih, version);
  	set_le_ih_k_offset(ih, offset);
  	set_le_ih_k_type(ih, type);
  	put_ih_item_len(ih, length);
  	/*    set_ih_free_space (ih, 0); */

  	/*
  	 * for directory items it is entry count, for directs and stat
  	 * datas - 0xffff, for indirects - 0
  	 */

  	put_ih_entry_count(ih, entry_count);

  }

  /*
   * FIXME: we might cache recently accessed indirect item
   * Ugh.  Not too eager for that....
   * I cut the code until such time as I see a convincing argument (benchmark).
   * I don't want a bloated inode struct..., and I don't like code complexity....
   */

  /*
   * cutting the code is fine, since it really isn't in use yet and is easy
   * to add back in.  But, Vladimir has a really good idea here.  Think
   * about what happens for reading a file.  For each page,
   * The VFS layer calls reiserfs_readpage, who searches the tree to find
   * an indirect item.  This indirect item has X number of pointers, where
   * X is a big number if we've done the block allocation right.  But,
   * we only use one or two of these pointers during each call to readpage,
   * needlessly researching again later on.
   *
   * The size of the cache could be dynamic based on the size of the file.
   *
   * I'd also like to see us cache the location the stat data item, since
   * we are needlessly researching for that frequently.
   *
   * --chris
   */
  
  /*
   * If this page has a file tail in it, and
   * it was read in by get_block_create_0, the page data is valid,
   * but tail is still sitting in a direct item, and we can't write to
   * it.  So, look through this page, and check all the mapped buffers
   * to make sure they have valid block numbers.  Any that don't need
   * to be unmapped, so that __block_write_begin will correctly call
   * reiserfs_get_block to convert the tail into an unformatted node
   */

  static inline void fix_tail_page_for_writing(struct page *page)
  {
  	struct buffer_head *head, *next, *bh;
  
  	if (page && page_has_buffers(page)) {
  		head = page_buffers(page);
  		bh = head;
  		do {
  			next = bh->b_this_page;
  			if (buffer_mapped(bh) && bh->b_blocknr == 0) {
  				reiserfs_unmap_buffer(bh);
  			}
  			bh = next;
  		} while (bh != head);
  	}

  }

  /*
   * reiserfs_get_block does not need to allocate a block only if it has been
   * done already or non-hole position has been found in the indirect item
   */

  static inline int allocation_needed(int retval, b_blocknr_t allocated,
  				    struct item_head *ih,
  				    __le32 * item, int pos_in_item)

  {

  	if (allocated)
  		return 0;
  	if (retval == POSITION_FOUND && is_indirect_le_ih(ih) &&
  	    get_block_num(item, pos_in_item))
  		return 0;
  	return 1;

  }

  static inline int indirect_item_found(int retval, struct item_head *ih)

  {

  	return (retval == POSITION_FOUND) && is_indirect_le_ih(ih);

  }

  static inline void set_block_dev_mapped(struct buffer_head *bh,
  					b_blocknr_t block, struct inode *inode)

  {
  	map_bh(bh, inode->i_sb, block);
  }

  /*
   * files which were created in the earlier version can not be longer,
   * than 2 gb
   */

  static int file_capable(struct inode *inode, sector_t block)

  {

  	/* it is new file. */
  	if (get_inode_item_key_version(inode) != KEY_FORMAT_3_5 ||
  	    /* old file, but 'block' is inside of 2gb */
  	    block < (1 << (31 - inode->i_sb->s_blocksize_bits)))

  		return 1;

  	return 0;

  }

  static int restart_transaction(struct reiserfs_transaction_handle *th,
  			       struct inode *inode, struct treepath *path)

  {
  	struct super_block *s = th->t_super;

  	int err;
  
  	BUG_ON(!th->t_trans_id);
  	BUG_ON(!th->t_refcount);

  	pathrelse(path);

  	/* we cannot restart while nested */
  	if (th->t_refcount > 1) {
  		return 0;
  	}

  	reiserfs_update_sd(th, inode);

  	err = journal_end(th);

  	if (!err) {
  		err = journal_begin(th, s, JOURNAL_PER_BALANCE_CNT * 6);
  		if (!err)
  			reiserfs_update_inode_transaction(inode);
  	}
  	return err;

  }

  /*
   * it is called by get_block when create == 0. Returns block number
   * for 'block'-th logical block of file. When it hits direct item it
   * returns 0 (being called from bmap) or read direct item into piece
   * of page (bh_result)
   * Please improve the english/clarity in the comment above, as it is
   * hard to understand.
   */

  static int _get_block_create_0(struct inode *inode, sector_t block,

  			       struct buffer_head *bh_result, int args)

  {

  	INITIALIZE_PATH(path);
  	struct cpu_key key;
  	struct buffer_head *bh;
  	struct item_head *ih, tmp_ih;

  	b_blocknr_t blocknr;

  	char *p = NULL;
  	int chars;
  	int ret;
  	int result;
  	int done = 0;
  	unsigned long offset;

  	/* prepare the key to look for the 'block'-th block of file */

  	make_cpu_key(&key, inode,
  		     (loff_t) block * inode->i_sb->s_blocksize + 1, TYPE_ANY,
  		     3);

  	result = search_for_position_by_key(inode->i_sb, &key, &path);
  	if (result != POSITION_FOUND) {
  		pathrelse(&path);
  		if (p)
  			kunmap(bh_result->b_page);
  		if (result == IO_ERROR)
  			return -EIO;

  		/*
  		 * We do not return -ENOENT if there is a hole but page is
  		 * uptodate, because it means that there is some MMAPED data
  		 * associated with it that is yet to be written to disk.
  		 */

  		if ((args & GET_BLOCK_NO_HOLE)
  		    && !PageUptodate(bh_result->b_page)) {
  			return -ENOENT;
  		}
  		return 0;
  	}

  	bh = get_last_bh(&path);

  	ih = tp_item_head(&path);

  	if (is_indirect_le_ih(ih)) {

  		__le32 *ind_item = (__le32 *) ih_item_body(bh, ih);

  		/*
  		 * FIXME: here we could cache indirect item or part of it in
  		 * the inode to avoid search_by_key in case of subsequent
  		 * access to file
  		 */

  		blocknr = get_block_num(ind_item, path.pos_in_item);
  		ret = 0;
  		if (blocknr) {
  			map_bh(bh_result, inode->i_sb, blocknr);
  			if (path.pos_in_item ==
  			    ((ih_item_len(ih) / UNFM_P_SIZE) - 1)) {
  				set_buffer_boundary(bh_result);
  			}
  		} else

  			/*
  			 * We do not return -ENOENT if there is a hole but
  			 * page is uptodate, because it means that there is
  			 * some MMAPED data associated with it that is
  			 * yet to be written to disk.
  			 */

  		if ((args & GET_BLOCK_NO_HOLE)
  			    && !PageUptodate(bh_result->b_page)) {
  			ret = -ENOENT;
  		}
  
  		pathrelse(&path);
  		if (p)
  			kunmap(bh_result->b_page);
  		return ret;
  	}

  	/* requested data are in direct item(s) */

  	if (!(args & GET_BLOCK_READ_DIRECT)) {

  		/*
  		 * we are called by bmap. FIXME: we can not map block of file
  		 * when it is stored in direct item(s)
  		 */

  		pathrelse(&path);
  		if (p)
  			kunmap(bh_result->b_page);
  		return -ENOENT;
  	}

  	/*
  	 * if we've got a direct item, and the buffer or page was uptodate,
  	 * we don't want to pull data off disk again.  skip to the
  	 * end, where we map the buffer and return

  	 */
  	if (buffer_uptodate(bh_result)) {
  		goto finished;
  	} else
  		/*

  		 * grab_tail_page can trigger calls to reiserfs_get_block on
  		 * up to date pages without any buffers.  If the page is up
  		 * to date, we don't want read old data off disk.  Set the up
  		 * to date bit on the buffer instead and jump to the end

  		 */
  	if (!bh_result->b_page || PageUptodate(bh_result->b_page)) {

  		set_buffer_uptodate(bh_result);

  		goto finished;
  	}

  	/* read file tail into part of page */

  	offset = (cpu_key_k_offset(&key) - 1) & (PAGE_SIZE - 1);

  	copy_item_head(&tmp_ih, ih);

  	/*
  	 * we only want to kmap if we are reading the tail into the page.
  	 * this is not the common case, so we don't kmap until we are
  	 * sure we need to.  But, this means the item might move if
  	 * kmap schedules

  	 */

  	if (!p)

  		p = (char *)kmap(bh_result->b_page);

  	p += offset;
  	memset(p, 0, inode->i_sb->s_blocksize);
  	do {
  		if (!is_direct_le_ih(ih)) {
  			BUG();
  		}

  		/*
  		 * make sure we don't read more bytes than actually exist in
  		 * the file.  This can happen in odd cases where i_size isn't
  		 * correct, and when direct item padding results in a few
  		 * extra bytes at the end of the direct item

  		 */
  		if ((le_ih_k_offset(ih) + path.pos_in_item) > inode->i_size)
  			break;
  		if ((le_ih_k_offset(ih) - 1 + ih_item_len(ih)) > inode->i_size) {
  			chars =
  			    inode->i_size - (le_ih_k_offset(ih) - 1) -
  			    path.pos_in_item;
  			done = 1;
  		} else {
  			chars = ih_item_len(ih) - path.pos_in_item;
  		}

  		memcpy(p, ih_item_body(bh, ih) + path.pos_in_item, chars);

  
  		if (done)
  			break;
  
  		p += chars;

  		/*
  		 * we done, if read direct item is not the last item of
  		 * node FIXME: we could try to check right delimiting key
  		 * to see whether direct item continues in the right
  		 * neighbor or rely on i_size
  		 */

  		if (PATH_LAST_POSITION(&path) != (B_NR_ITEMS(bh) - 1))

  			break;

  		/* update key to look for the next piece */

  		set_cpu_key_k_offset(&key, cpu_key_k_offset(&key) + chars);
  		result = search_for_position_by_key(inode->i_sb, &key, &path);
  		if (result != POSITION_FOUND)

  			/* i/o error most likely */

  			break;
  		bh = get_last_bh(&path);

  		ih = tp_item_head(&path);

  	} while (1);
  
  	flush_dcache_page(bh_result->b_page);
  	kunmap(bh_result->b_page);

  finished:

  	pathrelse(&path);
  
  	if (result == IO_ERROR)
  		return -EIO;

  	/*
  	 * this buffer has valid data, but isn't valid for io.  mapping it to

  	 * block #0 tells the rest of reiserfs it just has a tail in it
  	 */
  	map_bh(bh_result, inode->i_sb, 0);
  	set_buffer_uptodate(bh_result);
  	return 0;
  }

  /*
   * this is called to create file map. So, _get_block_create_0 will not
   * read direct item
   */

  static int reiserfs_bmap(struct inode *inode, sector_t block,
  			 struct buffer_head *bh_result, int create)

  {

  	if (!file_capable(inode, block))
  		return -EFBIG;
  
  	reiserfs_write_lock(inode->i_sb);
  	/* do not read the direct item */
  	_get_block_create_0(inode, block, bh_result, 0);
  	reiserfs_write_unlock(inode->i_sb);
  	return 0;

  }

  /*
   * special version of get_block that is only used by grab_tail_page right
   * now.  It is sent to __block_write_begin, and when you try to get a
   * block past the end of the file (or a block from a hole) it returns
   * -ENOENT instead of a valid buffer.  __block_write_begin expects to
   * be able to do i/o on the buffers returned, unless an error value
   * is also returned.
   *
   * So, this allows __block_write_begin to be used for reading a single block
   * in a page.  Where it does not produce a valid page for holes, or past the
   * end of the file.  This turns out to be exactly what we need for reading
   * tails for conversion.
   *
   * The point of the wrapper is forcing a certain value for create, even
   * though the VFS layer is calling this function with create==1.  If you
   * don't want to send create == GET_BLOCK_NO_HOLE to reiserfs_get_block,
   * don't use this function.

  */

  static int reiserfs_get_block_create_0(struct inode *inode, sector_t block,
  				       struct buffer_head *bh_result,
  				       int create)
  {
  	return reiserfs_get_block(inode, block, bh_result, GET_BLOCK_NO_HOLE);

  }

  /*
   * This is special helper for reiserfs_get_block in case we are executing
   * direct_IO request.
   */

  static int reiserfs_get_blocks_direct_io(struct inode *inode,
  					 sector_t iblock,

  					 struct buffer_head *bh_result,
  					 int create)
  {

  	int ret;
  
  	bh_result->b_page = NULL;

  	/*
  	 * We set the b_size before reiserfs_get_block call since it is
  	 * referenced in convert_tail_for_hole() that may be called from
  	 * reiserfs_get_block()
  	 */

  	bh_result->b_size = i_blocksize(inode);

  
  	ret = reiserfs_get_block(inode, iblock, bh_result,
  				 create | GET_BLOCK_NO_DANGLE);
  	if (ret)
  		goto out;
  
  	/* don't allow direct io onto tail pages */
  	if (buffer_mapped(bh_result) && bh_result->b_blocknr == 0) {

  		/*
  		 * make sure future calls to the direct io funcs for this
  		 * offset in the file fail by unmapping the buffer

  		 */
  		clear_buffer_mapped(bh_result);
  		ret = -EINVAL;
  	}

  
  	/*
  	 * Possible unpacked tail. Flush the data before pages have
  	 * disappeared
  	 */

  	if (REISERFS_I(inode)->i_flags & i_pack_on_close_mask) {
  		int err;

  
  		reiserfs_write_lock(inode->i_sb);

  		err = reiserfs_commit_for_inode(inode);
  		REISERFS_I(inode)->i_flags &= ~i_pack_on_close_mask;

  
  		reiserfs_write_unlock(inode->i_sb);

  		if (err < 0)
  			ret = err;
  	}

  out:

  	return ret;
  }

  
  /*

   * helper function for when reiserfs_get_block is called for a hole
   * but the file tail is still in a direct item
   * bh_result is the buffer head for the hole
   * tail_offset is the offset of the start of the tail in the file
   *
   * This calls prepare_write, which will start a new transaction
   * you should not be in a transaction, or have any paths held when you
   * call this.
   */

  static int convert_tail_for_hole(struct inode *inode,
  				 struct buffer_head *bh_result,
  				 loff_t tail_offset)
  {
  	unsigned long index;
  	unsigned long tail_end;
  	unsigned long tail_start;
  	struct page *tail_page;
  	struct page *hole_page = bh_result->b_page;
  	int retval = 0;
  
  	if ((tail_offset & (bh_result->b_size - 1)) != 1)
  		return -EIO;
  
  	/* always try to read until the end of the block */

  	tail_start = tail_offset & (PAGE_SIZE - 1);

  	tail_end = (tail_start | (bh_result->b_size - 1)) + 1;

  	index = tail_offset >> PAGE_SHIFT;

  	/*
  	 * hole_page can be zero in case of direct_io, we are sure
  	 * that we cannot get here if we write with O_DIRECT into tail page
  	 */

  	if (!hole_page || index != hole_page->index) {
  		tail_page = grab_cache_page(inode->i_mapping, index);
  		retval = -ENOMEM;
  		if (!tail_page) {
  			goto out;
  		}
  	} else {
  		tail_page = hole_page;
  	}

  	/*
  	 * we don't have to make sure the conversion did not happen while
  	 * we were locking the page because anyone that could convert
  	 * must first take i_mutex.
  	 *
  	 * We must fix the tail page for writing because it might have buffers
  	 * that are mapped, but have a block number of 0.  This indicates tail
  	 * data that has been read directly into the page, and
  	 * __block_write_begin won't trigger a get_block in this case.

  	 */
  	fix_tail_page_for_writing(tail_page);

  	retval = __reiserfs_write_begin(tail_page, tail_start,
  				      tail_end - tail_start);

  	if (retval)
  		goto unlock;
  
  	/* tail conversion might change the data in the page */
  	flush_dcache_page(tail_page);
  
  	retval = reiserfs_commit_write(NULL, tail_page, tail_start, tail_end);

  unlock:

  	if (tail_page != hole_page) {
  		unlock_page(tail_page);

  		put_page(tail_page);

  	}

  out:

  	return retval;

  }
  
  static inline int _allocate_block(struct reiserfs_transaction_handle *th,

  				  sector_t block,

  				  struct inode *inode,
  				  b_blocknr_t * allocated_block_nr,

  				  struct treepath *path, int flags)

  {
  	BUG_ON(!th->t_trans_id);

  #ifdef REISERFS_PREALLOCATE

  	if (!(flags & GET_BLOCK_NO_IMUX)) {

  		return reiserfs_new_unf_blocknrs2(th, inode, allocated_block_nr,
  						  path, block);
  	}

  #endif

  	return reiserfs_new_unf_blocknrs(th, inode, allocated_block_nr, path,
  					 block);

  }

  int reiserfs_get_block(struct inode *inode, sector_t block,
  		       struct buffer_head *bh_result, int create)

  {

  	int repeat, retval = 0;

  	/* b_blocknr_t is (unsigned) 32 bit int*/
  	b_blocknr_t allocated_block_nr = 0;

  	INITIALIZE_PATH(path);
  	int pos_in_item;
  	struct cpu_key key;
  	struct buffer_head *bh, *unbh = NULL;
  	struct item_head *ih, tmp_ih;
  	__le32 *item;
  	int done;
  	int fs_gen;
  	struct reiserfs_transaction_handle *th = NULL;

  	/*
  	 * space reserved in transaction batch:
  	 * . 3 balancings in direct->indirect conversion
  	 * . 1 block involved into reiserfs_update_sd()
  	 * XXX in practically impossible worst case direct2indirect()
  	 * can incur (much) more than 3 balancings.
  	 * quota update for user, group
  	 */

  	int jbegin_count =
  	    JOURNAL_PER_BALANCE_CNT * 3 + 1 +
  	    2 * REISERFS_QUOTA_TRANS_BLOCKS(inode->i_sb);
  	int version;
  	int dangle = 1;
  	loff_t new_offset =
  	    (((loff_t) block) << inode->i_sb->s_blocksize_bits) + 1;

  	reiserfs_write_lock(inode->i_sb);

  	version = get_inode_item_key_version(inode);

  	if (!file_capable(inode, block)) {

  		reiserfs_write_unlock(inode->i_sb);

  		return -EFBIG;
  	}

  	/*
  	 * if !create, we aren't changing the FS, so we don't need to
  	 * log anything, so we don't need to start a transaction

  	 */
  	if (!(create & GET_BLOCK_CREATE)) {
  		int ret;
  		/* find number of block-th logical block of the file */
  		ret = _get_block_create_0(inode, block, bh_result,
  					  create | GET_BLOCK_READ_DIRECT);

  		reiserfs_write_unlock(inode->i_sb);

  		return ret;
  	}

  	/*
  	 * if we're already in a transaction, make sure to close
  	 * any new transactions we start in this func
  	 */
  	if ((create & GET_BLOCK_NO_DANGLE) ||
  	    reiserfs_transaction_running(inode->i_sb))
  		dangle = 0;

  	/*
  	 * If file is of such a size, that it might have a tail and
  	 * tails are enabled  we should mark it as possibly needing
  	 * tail packing on close

  	 */
  	if ((have_large_tails(inode->i_sb)
  	     && inode->i_size < i_block_size(inode) * 4)
  	    || (have_small_tails(inode->i_sb)
  		&& inode->i_size < i_block_size(inode)))
  		REISERFS_I(inode)->i_flags |= i_pack_on_close_mask;
  
  	/* set the key of the first byte in the 'block'-th block of file */
  	make_cpu_key(&key, inode, new_offset, TYPE_ANY, 3 /*key length */ );
  	if ((new_offset + inode->i_sb->s_blocksize - 1) > inode->i_size) {

  start_trans:

  		th = reiserfs_persistent_transaction(inode->i_sb, jbegin_count);
  		if (!th) {
  			retval = -ENOMEM;

  			goto failure;
  		}

  		reiserfs_update_inode_transaction(inode);
  	}

  research:

  	retval = search_for_position_by_key(inode->i_sb, &key, &path);

  	if (retval == IO_ERROR) {

  		retval = -EIO;
  		goto failure;
  	}
  
  	bh = get_last_bh(&path);

  	ih = tp_item_head(&path);
  	item = tp_item_body(&path);

  	pos_in_item = path.pos_in_item;

  	fs_gen = get_generation(inode->i_sb);
  	copy_item_head(&tmp_ih, ih);
  
  	if (allocation_needed
  	    (retval, allocated_block_nr, ih, item, pos_in_item)) {
  		/* we have to allocate block for the unformatted node */
  		if (!th) {
  			pathrelse(&path);
  			goto start_trans;
  		}
  
  		repeat =
  		    _allocate_block(th, block, inode, &allocated_block_nr,
  				    &path, create);

  		/*
  		 * restart the transaction to give the journal a chance to free
  		 * some blocks.  releases the path, so we have to go back to
  		 * research if we succeed on the second try
  		 */

  		if (repeat == NO_DISK_SPACE || repeat == QUOTA_EXCEEDED) {

  			SB_JOURNAL(inode->i_sb)->j_next_async_flush = 1;
  			retval = restart_transaction(th, inode, &path);
  			if (retval)
  				goto failure;
  			repeat =
  			    _allocate_block(th, block, inode,
  					    &allocated_block_nr, NULL, create);
  
  			if (repeat != NO_DISK_SPACE && repeat != QUOTA_EXCEEDED) {
  				goto research;
  			}
  			if (repeat == QUOTA_EXCEEDED)
  				retval = -EDQUOT;
  			else
  				retval = -ENOSPC;
  			goto failure;
  		}
  
  		if (fs_changed(fs_gen, inode->i_sb)
  		    && item_moved(&tmp_ih, &path)) {
  			goto research;
  		}
  	}
  
  	if (indirect_item_found(retval, ih)) {
  		b_blocknr_t unfm_ptr;

  		/*
  		 * 'block'-th block is in the file already (there is
  		 * corresponding cell in some indirect item). But it may be
  		 * zero unformatted node pointer (hole)
  		 */

  		unfm_ptr = get_block_num(item, pos_in_item);
  		if (unfm_ptr == 0) {
  			/* use allocated block to plug the hole */
  			reiserfs_prepare_for_journal(inode->i_sb, bh, 1);
  			if (fs_changed(fs_gen, inode->i_sb)
  			    && item_moved(&tmp_ih, &path)) {
  				reiserfs_restore_prepared_buffer(inode->i_sb,
  								 bh);
  				goto research;
  			}
  			set_buffer_new(bh_result);
  			if (buffer_dirty(bh_result)
  			    && reiserfs_data_ordered(inode->i_sb))
  				reiserfs_add_ordered_list(inode, bh_result);
  			put_block_num(item, pos_in_item, allocated_block_nr);
  			unfm_ptr = allocated_block_nr;

  			journal_mark_dirty(th, bh);

  			reiserfs_update_sd(th, inode);
  		}
  		set_block_dev_mapped(bh_result, unfm_ptr, inode);
  		pathrelse(&path);
  		retval = 0;
  		if (!dangle && th)
  			retval = reiserfs_end_persistent_transaction(th);

  		reiserfs_write_unlock(inode->i_sb);

  		/*
  		 * the item was found, so new blocks were not added to the file
  		 * there is no need to make sure the inode is updated with this
  		 * transaction

  		 */
  		return retval;
  	}
  
  	if (!th) {
  		pathrelse(&path);
  		goto start_trans;
  	}

  	/*
  	 * desired position is not found or is in the direct item. We have
  	 * to append file with holes up to 'block'-th block converting
  	 * direct items to indirect one if necessary
  	 */

  	done = 0;
  	do {
  		if (is_statdata_le_ih(ih)) {
  			__le32 unp = 0;
  			struct cpu_key tmp_key;
  
  			/* indirect item has to be inserted */
  			make_le_item_head(&tmp_ih, &key, version, 1,
  					  TYPE_INDIRECT, UNFM_P_SIZE,
  					  0 /* free_space */ );

  			/*
  			 * we are going to add 'block'-th block to the file.
  			 * Use allocated block for that
  			 */

  			if (cpu_key_k_offset(&key) == 1) {

  				unp = cpu_to_le32(allocated_block_nr);
  				set_block_dev_mapped(bh_result,
  						     allocated_block_nr, inode);
  				set_buffer_new(bh_result);
  				done = 1;
  			}

  			tmp_key = key;	/* ;) */

  			set_cpu_key_k_offset(&tmp_key, 1);
  			PATH_LAST_POSITION(&path)++;
  
  			retval =
  			    reiserfs_insert_item(th, &path, &tmp_key, &tmp_ih,
  						 inode, (char *)&unp);
  			if (retval) {
  				reiserfs_free_block(th, inode,
  						    allocated_block_nr, 1);

  				/*
  				 * retval == -ENOSPC, -EDQUOT or -EIO
  				 * or -EEXIST
  				 */
  				goto failure;

  			}

  		} else if (is_direct_le_ih(ih)) {
  			/* direct item has to be converted */
  			loff_t tail_offset;
  
  			tail_offset =
  			    ((le_ih_k_offset(ih) -
  			      1) & ~(inode->i_sb->s_blocksize - 1)) + 1;

  
  			/*
  			 * direct item we just found fits into block we have
  			 * to map. Convert it into unformatted node: use
  			 * bh_result for the conversion
  			 */

  			if (tail_offset == cpu_key_k_offset(&key)) {

  				set_block_dev_mapped(bh_result,
  						     allocated_block_nr, inode);
  				unbh = bh_result;
  				done = 1;
  			} else {

  				/*
  				 * we have to pad file tail stored in direct
  				 * item(s) up to block size and convert it
  				 * to unformatted node. FIXME: this should
  				 * also get into page cache
  				 */

  
  				pathrelse(&path);
  				/*
  				 * ugly, but we can only end the transaction if
  				 * we aren't nested
  				 */
  				BUG_ON(!th->t_refcount);
  				if (th->t_refcount == 1) {
  					retval =
  					    reiserfs_end_persistent_transaction
  					    (th);
  					th = NULL;
  					if (retval)
  						goto failure;
  				}
  
  				retval =
  				    convert_tail_for_hole(inode, bh_result,
  							  tail_offset);
  				if (retval) {
  					if (retval != -ENOSPC)

  						reiserfs_error(inode->i_sb,
  							"clm-6004",
  							"convert tail failed "
  							"inode %lu, error %d",
  							inode->i_ino,
  							retval);

  					if (allocated_block_nr) {

  						/*
  						 * the bitmap, the super,
  						 * and the stat data == 3
  						 */

  						if (!th)
  							th = reiserfs_persistent_transaction(inode->i_sb, 3);
  						if (th)
  							reiserfs_free_block(th,
  									    inode,
  									    allocated_block_nr,
  									    1);
  					}
  					goto failure;
  				}
  				goto research;
  			}
  			retval =
  			    direct2indirect(th, inode, &path, unbh,
  					    tail_offset);
  			if (retval) {
  				reiserfs_unmap_buffer(unbh);
  				reiserfs_free_block(th, inode,
  						    allocated_block_nr, 1);
  				goto failure;
  			}

  			/*
  			 * it is important the set_buffer_uptodate is done
  			 * after the direct2indirect.  The buffer might
  			 * contain valid data newer than the data on disk
  			 * (read by readpage, changed, and then sent here by
  			 * writepage).  direct2indirect needs to know if unbh
  			 * was already up to date, so it can decide if the
  			 * data in unbh needs to be replaced with data from
  			 * the disk

  			 */
  			set_buffer_uptodate(unbh);

  			/*
  			 * unbh->b_page == NULL in case of DIRECT_IO request,
  			 * this means buffer will disappear shortly, so it
  			 * should not be added to

  			 */
  			if (unbh->b_page) {

  				/*
  				 * we've converted the tail, so we must
  				 * flush unbh before the transaction commits

  				 */
  				reiserfs_add_tail_list(inode, unbh);

  				/*
  				 * mark it dirty now to prevent commit_write
  				 * from adding this buffer to the inode's
  				 * dirty buffer list

  				 */
  				/*

  				 * AKPM: changed __mark_buffer_dirty to
  				 * mark_buffer_dirty().  It's still atomic,
  				 * but it sets the page dirty too, which makes
  				 * it eligible for writeback at any time by the
  				 * VM (which was also the case with
  				 * __mark_buffer_dirty())

  				 */
  				mark_buffer_dirty(unbh);
  			}
  		} else {

  			/*
  			 * append indirect item with holes if needed, when
  			 * appending pointer to 'block'-th block use block,
  			 * which is already allocated
  			 */

  			struct cpu_key tmp_key;

  			/*
  			 * We use this in case we need to allocate
  			 * only one block which is a fastpath
  			 */
  			unp_t unf_single = 0;

  			unp_t *un;
  			__u64 max_to_insert =
  			    MAX_ITEM_LEN(inode->i_sb->s_blocksize) /
  			    UNFM_P_SIZE;
  			__u64 blocks_needed;
  
  			RFALSE(pos_in_item != ih_item_len(ih) / UNFM_P_SIZE,
  			       "vs-804: invalid position for append");

  			/*
  			 * indirect item has to be appended,
  			 * set up key of that position
  			 * (key type is unimportant)
  			 */

  			make_cpu_key(&tmp_key, inode,
  				     le_key_k_offset(version,

  						     &ih->ih_key) +

  				     op_bytes_number(ih,
  						     inode->i_sb->s_blocksize),

  				     TYPE_INDIRECT, 3);

  			RFALSE(cpu_key_k_offset(&tmp_key) > cpu_key_k_offset(&key),
  			       "green-805: invalid offset");

  			blocks_needed =
  			    1 +
  			    ((cpu_key_k_offset(&key) -
  			      cpu_key_k_offset(&tmp_key)) >> inode->i_sb->
  			     s_blocksize_bits);

  
  			if (blocks_needed == 1) {
  				un = &unf_single;
  			} else {

  				un = kcalloc(min(blocks_needed, max_to_insert),
  					     UNFM_P_SIZE, GFP_NOFS);

  				if (!un) {
  					un = &unf_single;
  					blocks_needed = 1;
  					max_to_insert = 0;

  				}

  			}
  			if (blocks_needed <= max_to_insert) {

  				/*
  				 * we are going to add target block to
  				 * the file. Use allocated block for that
  				 */

  				un[blocks_needed - 1] =
  				    cpu_to_le32(allocated_block_nr);
  				set_block_dev_mapped(bh_result,
  						     allocated_block_nr, inode);
  				set_buffer_new(bh_result);
  				done = 1;
  			} else {
  				/* paste hole to the indirect item */

  				/*

  				 * If kcalloc failed, max_to_insert becomes

  				 * zero and it means we only have space for
  				 * one block
  				 */

  				blocks_needed =
  				    max_to_insert ? max_to_insert : 1;
  			}
  			retval =
  			    reiserfs_paste_into_item(th, &path, &tmp_key, inode,
  						     (char *)un,
  						     UNFM_P_SIZE *
  						     blocks_needed);
  
  			if (blocks_needed != 1)
  				kfree(un);
  
  			if (retval) {
  				reiserfs_free_block(th, inode,
  						    allocated_block_nr, 1);
  				goto failure;
  			}
  			if (!done) {

  				/*
  				 * We need to mark new file size in case
  				 * this function will be interrupted/aborted
  				 * later on. And we may do this only for
  				 * holes.
  				 */

  				inode->i_size +=
  				    inode->i_sb->s_blocksize * blocks_needed;
  			}
  		}

  		if (done == 1)
  			break;

  		/*
  		 * this loop could log more blocks than we had originally
  		 * asked for.  So, we have to allow the transaction to end
  		 * if it is too big or too full.  Update the inode so things
  		 * are consistent if we crash before the function returns
  		 * release the path so that anybody waiting on the path before
  		 * ending their transaction will be able to continue.

  		 */
  		if (journal_transaction_should_end(th, th->t_blocks_allocated)) {
  			retval = restart_transaction(th, inode, &path);
  			if (retval)
  				goto failure;
  		}

  		/*
  		 * inserting indirect pointers for a hole can take a
  		 * long time.  reschedule if needed and also release the write
  		 * lock for others.

  		 */

  		reiserfs_cond_resched(inode->i_sb);

  		retval = search_for_position_by_key(inode->i_sb, &key, &path);
  		if (retval == IO_ERROR) {
  			retval = -EIO;
  			goto failure;
  		}
  		if (retval == POSITION_FOUND) {

  			reiserfs_warning(inode->i_sb, "vs-825",

  					 "%K should not be found", &key);
  			retval = -EEXIST;
  			if (allocated_block_nr)
  				reiserfs_free_block(th, inode,
  						    allocated_block_nr, 1);
  			pathrelse(&path);
  			goto failure;
  		}
  		bh = get_last_bh(&path);

  		ih = tp_item_head(&path);
  		item = tp_item_body(&path);

  		pos_in_item = path.pos_in_item;
  	} while (1);
  
  	retval = 0;

  failure:

  	if (th && (!dangle || (retval && !th->t_trans_id))) {
  		int err;
  		if (th->t_trans_id)
  			reiserfs_update_sd(th, inode);
  		err = reiserfs_end_persistent_transaction(th);
  		if (err)
  			retval = err;
  	}

  	reiserfs_write_unlock(inode->i_sb);

  	reiserfs_check_path(&path);
  	return retval;

  }

  static void reiserfs_readahead(struct readahead_control *rac)

  {

  	mpage_readahead(rac, reiserfs_get_block);

  }

  /*
   * Compute real number of used bytes by file
   * Following three functions can go away when we'll have enough space in
   * stat item

   */
  static int real_space_diff(struct inode *inode, int sd_size)
  {

  	int bytes;
  	loff_t blocksize = inode->i_sb->s_blocksize;
  
  	if (S_ISLNK(inode->i_mode) || S_ISDIR(inode->i_mode))
  		return sd_size;

  	/*
  	 * End of file is also in full block with indirect reference, so round
  	 * up to the next block.
  	 *
  	 * there is just no way to know if the tail is actually packed
  	 * on the file, so we have to assume it isn't.  When we pack the
  	 * tail, we add 4 bytes to pretend there really is an unformatted
  	 * node pointer

  	 */
  	bytes =
  	    ((inode->i_size +
  	      (blocksize - 1)) >> inode->i_sb->s_blocksize_bits) * UNFM_P_SIZE +
  	    sd_size;
  	return bytes;

  }
  
  static inline loff_t to_real_used_space(struct inode *inode, ulong blocks,

  					int sd_size)

  {

  	if (S_ISLNK(inode->i_mode) || S_ISDIR(inode->i_mode)) {
  		return inode->i_size +
  		    (loff_t) (real_space_diff(inode, sd_size));
  	}
  	return ((loff_t) real_space_diff(inode, sd_size)) +
  	    (((loff_t) blocks) << 9);

  }
  
  /* Compute number of blocks used by file in ReiserFS counting */
  static inline ulong to_fake_used_blocks(struct inode *inode, int sd_size)
  {

  	loff_t bytes = inode_get_bytes(inode);
  	loff_t real_space = real_space_diff(inode, sd_size);
  
  	/* keeps fsck and non-quota versions of reiserfs happy */
  	if (S_ISLNK(inode->i_mode) || S_ISDIR(inode->i_mode)) {
  		bytes += (loff_t) 511;
  	}

  	/*
  	 * files from before the quota patch might i_blocks such that
  	 * bytes < real_space.  Deal with that here to prevent it from
  	 * going negative.

  	 */
  	if (bytes < real_space)
  		return 0;
  	return (bytes - real_space) >> 9;

  }

  /*
   * BAD: new directories have stat data of new type and all other items
   * of old type. Version stored in the inode says about body items, so
   * in update_stat_data we can not rely on inode, but have to check
   * item version directly
   */

  /* called by read_locked_inode */

  static void init_inode(struct inode *inode, struct treepath *path)

  {

  	struct buffer_head *bh;
  	struct item_head *ih;
  	__u32 rdev;

  
  	bh = PATH_PLAST_BUFFER(path);

  	ih = tp_item_head(path);

  	copy_key(INODE_PKEY(inode), &ih->ih_key);

  	INIT_LIST_HEAD(&REISERFS_I(inode)->i_prealloc_list);

  	REISERFS_I(inode)->i_flags = 0;
  	REISERFS_I(inode)->i_prealloc_block = 0;
  	REISERFS_I(inode)->i_prealloc_count = 0;
  	REISERFS_I(inode)->i_trans_id = 0;
  	REISERFS_I(inode)->i_jl = NULL;

  	reiserfs_init_xattr_rwsem(inode);

  
  	if (stat_data_v1(ih)) {
  		struct stat_data_v1 *sd =

  		    (struct stat_data_v1 *)ih_item_body(bh, ih);

  		unsigned long blocks;
  
  		set_inode_item_key_version(inode, KEY_FORMAT_3_5);
  		set_inode_sd_version(inode, STAT_DATA_V1);
  		inode->i_mode = sd_v1_mode(sd);

  		set_nlink(inode, sd_v1_nlink(sd));

  		i_uid_write(inode, sd_v1_uid(sd));
  		i_gid_write(inode, sd_v1_gid(sd));

  		inode->i_size = sd_v1_size(sd);
  		inode->i_atime.tv_sec = sd_v1_atime(sd);
  		inode->i_mtime.tv_sec = sd_v1_mtime(sd);
  		inode->i_ctime.tv_sec = sd_v1_ctime(sd);
  		inode->i_atime.tv_nsec = 0;
  		inode->i_ctime.tv_nsec = 0;
  		inode->i_mtime.tv_nsec = 0;
  
  		inode->i_blocks = sd_v1_blocks(sd);
  		inode->i_generation = le32_to_cpu(INODE_PKEY(inode)->k_dir_id);
  		blocks = (inode->i_size + 511) >> 9;
  		blocks = _ROUND_UP(blocks, inode->i_sb->s_blocksize >> 9);

  
  		/*
  		 * there was a bug in <=3.5.23 when i_blocks could take
  		 * negative values. Starting from 3.5.17 this value could
  		 * even be stored in stat data. For such files we set
  		 * i_blocks based on file size. Just 2 notes: this can be
  		 * wrong for sparse files. On-disk value will be only
  		 * updated if file's inode will ever change
  		 */

  		if (inode->i_blocks > blocks) {

  			inode->i_blocks = blocks;
  		}

  		rdev = sd_v1_rdev(sd);
  		REISERFS_I(inode)->i_first_direct_byte =
  		    sd_v1_first_direct_byte(sd);

  
  		/*
  		 * an early bug in the quota code can give us an odd
  		 * number for the block count.  This is incorrect, fix it here.

  		 */
  		if (inode->i_blocks & 1) {
  			inode->i_blocks++;
  		}
  		inode_set_bytes(inode,
  				to_real_used_space(inode, inode->i_blocks,
  						   SD_V1_SIZE));

  		/*
  		 * nopack is initially zero for v1 objects. For v2 objects,
  		 * nopack is initialised from sd_attrs
  		 */

  		REISERFS_I(inode)->i_flags &= ~i_nopack_mask;
  	} else {

  		/*
  		 * new stat data found, but object may have old items
  		 * (directories and symlinks)
  		 */

  		struct stat_data *sd = (struct stat_data *)ih_item_body(bh, ih);

  
  		inode->i_mode = sd_v2_mode(sd);

  		set_nlink(inode, sd_v2_nlink(sd));

  		i_uid_write(inode, sd_v2_uid(sd));

  		inode->i_size = sd_v2_size(sd);

  		i_gid_write(inode, sd_v2_gid(sd));

  		inode->i_mtime.tv_sec = sd_v2_mtime(sd);
  		inode->i_atime.tv_sec = sd_v2_atime(sd);
  		inode->i_ctime.tv_sec = sd_v2_ctime(sd);
  		inode->i_ctime.tv_nsec = 0;
  		inode->i_mtime.tv_nsec = 0;
  		inode->i_atime.tv_nsec = 0;
  		inode->i_blocks = sd_v2_blocks(sd);
  		rdev = sd_v2_rdev(sd);
  		if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode))
  			inode->i_generation =
  			    le32_to_cpu(INODE_PKEY(inode)->k_dir_id);
  		else
  			inode->i_generation = sd_v2_generation(sd);

  		if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
  			set_inode_item_key_version(inode, KEY_FORMAT_3_5);
  		else
  			set_inode_item_key_version(inode, KEY_FORMAT_3_6);
  		REISERFS_I(inode)->i_first_direct_byte = 0;
  		set_inode_sd_version(inode, STAT_DATA_V2);
  		inode_set_bytes(inode,
  				to_real_used_space(inode, inode->i_blocks,
  						   SD_V2_SIZE));

  		/*
  		 * read persistent inode attributes from sd and initialise
  		 * generic inode flags from them
  		 */

  		REISERFS_I(inode)->i_attrs = sd_v2_attrs(sd);
  		sd_attrs_to_i_attrs(sd_v2_attrs(sd), inode);
  	}
  
  	pathrelse(path);
  	if (S_ISREG(inode->i_mode)) {
  		inode->i_op = &reiserfs_file_inode_operations;
  		inode->i_fop = &reiserfs_file_operations;
  		inode->i_mapping->a_ops = &reiserfs_address_space_operations;
  	} else if (S_ISDIR(inode->i_mode)) {
  		inode->i_op = &reiserfs_dir_inode_operations;
  		inode->i_fop = &reiserfs_dir_operations;
  	} else if (S_ISLNK(inode->i_mode)) {
  		inode->i_op = &reiserfs_symlink_inode_operations;

  		inode_nohighmem(inode);

  		inode->i_mapping->a_ops = &reiserfs_address_space_operations;
  	} else {
  		inode->i_blocks = 0;
  		inode->i_op = &reiserfs_special_inode_operations;
  		init_special_inode(inode, inode->i_mode, new_decode_dev(rdev));
  	}
  }

  /* update new stat data with inode fields */

  static void inode2sd(void *sd, struct inode *inode, loff_t size)

  {

  	struct stat_data *sd_v2 = (struct stat_data *)sd;

  
  	set_sd_v2_mode(sd_v2, inode->i_mode);
  	set_sd_v2_nlink(sd_v2, inode->i_nlink);

  	set_sd_v2_uid(sd_v2, i_uid_read(inode));

  	set_sd_v2_size(sd_v2, size);

  	set_sd_v2_gid(sd_v2, i_gid_read(inode));

  	set_sd_v2_mtime(sd_v2, inode->i_mtime.tv_sec);
  	set_sd_v2_atime(sd_v2, inode->i_atime.tv_sec);
  	set_sd_v2_ctime(sd_v2, inode->i_ctime.tv_sec);
  	set_sd_v2_blocks(sd_v2, to_fake_used_blocks(inode, SD_V2_SIZE));
  	if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode))
  		set_sd_v2_rdev(sd_v2, new_encode_dev(inode->i_rdev));
  	else
  		set_sd_v2_generation(sd_v2, inode->i_generation);

  	set_sd_v2_attrs(sd_v2, REISERFS_I(inode)->i_attrs);

  }

  /* used to copy inode's fields to old stat data */

  static void inode2sd_v1(void *sd, struct inode *inode, loff_t size)

  {

  	struct stat_data_v1 *sd_v1 = (struct stat_data_v1 *)sd;
  
  	set_sd_v1_mode(sd_v1, inode->i_mode);

  	set_sd_v1_uid(sd_v1, i_uid_read(inode));
  	set_sd_v1_gid(sd_v1, i_gid_read(inode));

  	set_sd_v1_nlink(sd_v1, inode->i_nlink);
  	set_sd_v1_size(sd_v1, size);
  	set_sd_v1_atime(sd_v1, inode->i_atime.tv_sec);
  	set_sd_v1_ctime(sd_v1, inode->i_ctime.tv_sec);
  	set_sd_v1_mtime(sd_v1, inode->i_mtime.tv_sec);
  
  	if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode))
  		set_sd_v1_rdev(sd_v1, new_encode_dev(inode->i_rdev));
  	else
  		set_sd_v1_blocks(sd_v1, to_fake_used_blocks(inode, SD_V1_SIZE));

  	/* Sigh. i_first_direct_byte is back */

  	set_sd_v1_first_direct_byte(sd_v1,
  				    REISERFS_I(inode)->i_first_direct_byte);
  }

  /*
   * NOTE, you must prepare the buffer head before sending it here,
   * and then log it after the call
   */

  static void update_stat_data(struct treepath *path, struct inode *inode,

  			     loff_t size)

  {

  	struct buffer_head *bh;
  	struct item_head *ih;
  
  	bh = PATH_PLAST_BUFFER(path);

  	ih = tp_item_head(path);

  
  	if (!is_statdata_le_ih(ih))

  		reiserfs_panic(inode->i_sb, "vs-13065", "key %k, found item %h",

  			       INODE_PKEY(inode), ih);

  	/* path points to old stat data */

  	if (stat_data_v1(ih)) {

  		inode2sd_v1(ih_item_body(bh, ih), inode, size);

  	} else {

  		inode2sd(ih_item_body(bh, ih), inode, size);

  	}

  	return;
  }

  void reiserfs_update_sd_size(struct reiserfs_transaction_handle *th,
  			     struct inode *inode, loff_t size)

  {

  	struct cpu_key key;
  	INITIALIZE_PATH(path);
  	struct buffer_head *bh;
  	int fs_gen;
  	struct item_head *ih, tmp_ih;
  	int retval;
  
  	BUG_ON(!th->t_trans_id);

  	/* key type is unimportant */
  	make_cpu_key(&key, inode, SD_OFFSET, TYPE_STAT_DATA, 3);

  
  	for (;;) {
  		int pos;
  		/* look for the object's stat data */
  		retval = search_item(inode->i_sb, &key, &path);
  		if (retval == IO_ERROR) {

  			reiserfs_error(inode->i_sb, "vs-13050",
  				       "i/o failure occurred trying to "
  				       "update %K stat data", &key);

  			return;
  		}
  		if (retval == ITEM_NOT_FOUND) {
  			pos = PATH_LAST_POSITION(&path);
  			pathrelse(&path);
  			if (inode->i_nlink == 0) {
  				/*reiserfs_warning (inode->i_sb, "vs-13050: reiserfs_update_sd: i_nlink == 0, stat data not found"); */
  				return;
  			}

  			reiserfs_warning(inode->i_sb, "vs-13060",
  					 "stat data of object %k (nlink == %d) "
  					 "not found (pos %d)",

  					 INODE_PKEY(inode), inode->i_nlink,
  					 pos);
  			reiserfs_check_path(&path);
  			return;
  		}

  		/*
  		 * sigh, prepare_for_journal might schedule.  When it
  		 * schedules the FS might change.  We have to detect that,
  		 * and loop back to the search if the stat data item has moved

  		 */
  		bh = get_last_bh(&path);

  		ih = tp_item_head(&path);

  		copy_item_head(&tmp_ih, ih);
  		fs_gen = get_generation(inode->i_sb);
  		reiserfs_prepare_for_journal(inode->i_sb, bh, 1);

  
  		/* Stat_data item has been moved after scheduling. */

  		if (fs_changed(fs_gen, inode->i_sb)
  		    && item_moved(&tmp_ih, &path)) {
  			reiserfs_restore_prepared_buffer(inode->i_sb, bh);

  			continue;

  		}
  		break;
  	}
  	update_stat_data(&path, inode, size);

  	journal_mark_dirty(th, bh);

  	pathrelse(&path);
  	return;

  }

  /*
   * reiserfs_read_locked_inode is called to read the inode off disk, and it
   * does a make_bad_inode when things go wrong.  But, we need to make sure
   * and clear the key in the private portion of the inode, otherwise a
   * corresponding iput might try to delete whatever object the inode last
   * represented.
   */

  static void reiserfs_make_bad_inode(struct inode *inode)
  {
  	memset(INODE_PKEY(inode), 0, KEY_SIZE);
  	make_bad_inode(inode);

  }

  /*
   * initially this function was derived from minix or ext2's analog and
   * evolved as the prototype did
   */

  int reiserfs_init_locked_inode(struct inode *inode, void *p)

  {

  	struct reiserfs_iget_args *args = (struct reiserfs_iget_args *)p;
  	inode->i_ino = args->objectid;
  	INODE_PKEY(inode)->k_dir_id = cpu_to_le32(args->dirid);
  	return 0;

  }

  /*
   * looks for stat data in the tree, and fills up the fields of in-core
   * inode stat data fields
   */

  void reiserfs_read_locked_inode(struct inode *inode,
  				struct reiserfs_iget_args *args)

  {

  	INITIALIZE_PATH(path_to_sd);
  	struct cpu_key key;
  	unsigned long dirino;
  	int retval;
  
  	dirino = args->dirid;

  	/*
  	 * set version 1, version 2 could be used too, because stat data
  	 * key is the same in both versions
  	 */

  	_make_cpu_key(&key, KEY_FORMAT_3_5, dirino, inode->i_ino, 0, 0, 3);

  
  	/* look for the object's stat data */
  	retval = search_item(inode->i_sb, &key, &path_to_sd);
  	if (retval == IO_ERROR) {

  		reiserfs_error(inode->i_sb, "vs-13070",
  			       "i/o failure occurred trying to find "
  			       "stat data of %K", &key);

  		reiserfs_make_bad_inode(inode);
  		return;
  	}

  
  	/* a stale NFS handle can trigger this without it being an error */

  	if (retval != ITEM_FOUND) {

  		pathrelse(&path_to_sd);
  		reiserfs_make_bad_inode(inode);

  		clear_nlink(inode);

  		return;
  	}
  
  	init_inode(inode, &path_to_sd);

  	/*
  	 * It is possible that knfsd is trying to access inode of a file
  	 * that is being removed from the disk by some other thread. As we
  	 * update sd on unlink all that is required is to check for nlink
  	 * here. This bug was first found by Sizif when debugging
  	 * SquidNG/Butterfly, forgotten, and found again after Philippe
  	 * Gramoulle <philippe.gramoulle@mmania.com> reproduced it.
  
  	 * More logical fix would require changes in fs/inode.c:iput() to
  	 * remove inode from hash-table _after_ fs cleaned disk stuff up and
  	 * in iget() to return NULL if I_FREEING inode is found in
  	 * hash-table.
  	 */
  
  	/*
  	 * Currently there is one place where it's ok to meet inode with
  	 * nlink==0: processing of open-unlinked and half-truncated files
  	 * during mount (fs/reiserfs/super.c:finish_unfinished()).
  	 */

  	if ((inode->i_nlink == 0) &&
  	    !REISERFS_SB(inode->i_sb)->s_is_unlinked_ok) {

  		reiserfs_warning(inode->i_sb, "vs-13075",

  				 "dead inode read from disk %K. "
  				 "This is likely to be race with knfsd. Ignore",
  				 &key);
  		reiserfs_make_bad_inode(inode);
  	}

  	/* init inode should be relsing */
  	reiserfs_check_path(&path_to_sd);

  	/*
  	 * Stat data v1 doesn't support ACLs.
  	 */
  	if (get_inode_sd_version(inode) == STAT_DATA_V1)
  		cache_no_acl(inode);

  }

  /*

   * reiserfs_find_actor() - "find actor" reiserfs supplies to iget5_locked().
   *
   * @inode:    inode from hash table to check
   * @opaque:   "cookie" passed to iget5_locked(). This is &reiserfs_iget_args.
   *
   * This function is called by iget5_locked() to distinguish reiserfs inodes
   * having the same inode numbers. Such inodes can only exist due to some
   * error condition. One of them should be bad. Inodes with identical
   * inode numbers (objectids) are distinguished by parent directory ids.
   *
   */

  int reiserfs_find_actor(struct inode *inode, void *opaque)

  {

  	struct reiserfs_iget_args *args;

  	args = opaque;
  	/* args is already in CPU order */
  	return (inode->i_ino == args->objectid) &&
  	    (le32_to_cpu(INODE_PKEY(inode)->k_dir_id) == args->dirid);

  }

  struct inode *reiserfs_iget(struct super_block *s, const struct cpu_key *key)

  {

  	struct inode *inode;
  	struct reiserfs_iget_args args;

  	int depth;

  
  	args.objectid = key->on_disk_key.k_objectid;
  	args.dirid = key->on_disk_key.k_dir_id;

  	depth = reiserfs_write_unlock_nested(s);

  	inode = iget5_locked(s, key->on_disk_key.k_objectid,
  			     reiserfs_find_actor, reiserfs_init_locked_inode,
  			     (void *)(&args));

  	reiserfs_write_lock_nested(s, depth);

  	if (!inode)
  		return ERR_PTR(-ENOMEM);
  
  	if (inode->i_state & I_NEW) {
  		reiserfs_read_locked_inode(inode, &args);
  		unlock_new_inode(inode);
  	}
  
  	if (comp_short_keys(INODE_PKEY(inode), key) || is_bad_inode(inode)) {
  		/* either due to i/o error or a stale NFS handle */
  		iput(inode);
  		inode = NULL;
  	}
  	return inode;

  }

  static struct dentry *reiserfs_get_dentry(struct super_block *sb,
  	u32 objectid, u32 dir_id, u32 generation)

  {

  	struct cpu_key key;

  	struct inode *inode;

  	key.on_disk_key.k_objectid = objectid;
  	key.on_disk_key.k_dir_id = dir_id;

  	reiserfs_write_lock(sb);
  	inode = reiserfs_iget(sb, &key);

  	if (inode && !IS_ERR(inode) && generation != 0 &&
  	    generation != inode->i_generation) {

  		iput(inode);
  		inode = NULL;
  	}
  	reiserfs_write_unlock(sb);

  
  	return d_obtain_alias(inode);

  }

  struct dentry *reiserfs_fh_to_dentry(struct super_block *sb, struct fid *fid,
  		int fh_len, int fh_type)

  {

  	/*
  	 * fhtype happens to reflect the number of u32s encoded.

  	 * due to a bug in earlier code, fhtype might indicate there
  	 * are more u32s then actually fitted.
  	 * so if fhtype seems to be more than len, reduce fhtype.
  	 * Valid types are:
  	 *   2 - objectid + dir_id - legacy support
  	 *   3 - objectid + dir_id + generation
  	 *   4 - objectid + dir_id + objectid and dirid of parent - legacy
  	 *   5 - objectid + dir_id + generation + objectid and dirid of parent
  	 *   6 - as above plus generation of directory
  	 * 6 does not fit in NFSv2 handles
  	 */

  	if (fh_type > fh_len) {
  		if (fh_type != 6 || fh_len != 5)

  			reiserfs_warning(sb, "reiserfs-13077",

  				"nfsd/reiserfs, fhtype=%d, len=%d - odd",
  				fh_type, fh_len);

  		fh_type = fh_len;

  	}

  	if (fh_len < 2)
  		return NULL;

  	return reiserfs_get_dentry(sb, fid->raw[0], fid->raw[1],
  		(fh_type == 3 || fh_type >= 5) ? fid->raw[2] : 0);
  }

  struct dentry *reiserfs_fh_to_parent(struct super_block *sb, struct fid *fid,
  		int fh_len, int fh_type)
  {

  	if (fh_type > fh_len)
  		fh_type = fh_len;

  	if (fh_type < 4)
  		return NULL;
  
  	return reiserfs_get_dentry(sb,
  		(fh_type >= 5) ? fid->raw[3] : fid->raw[2],
  		(fh_type >= 5) ? fid->raw[4] : fid->raw[3],
  		(fh_type == 6) ? fid->raw[5] : 0);

  }

  int reiserfs_encode_fh(struct inode *inode, __u32 * data, int *lenp,
  		       struct inode *parent)

  {

  	int maxlen = *lenp;

  	if (parent && (maxlen < 5)) {

  		*lenp = 5;

  		return FILEID_INVALID;

  	} else if (maxlen < 3) {
  		*lenp = 3;

  		return FILEID_INVALID;

  	}

  
  	data[0] = inode->i_ino;
  	data[1] = le32_to_cpu(INODE_PKEY(inode)->k_dir_id);
  	data[2] = inode->i_generation;
  	*lenp = 3;

  	if (parent) {
  		data[3] = parent->i_ino;
  		data[4] = le32_to_cpu(INODE_PKEY(parent)->k_dir_id);
  		*lenp = 5;
  		if (maxlen >= 6) {
  			data[5] = parent->i_generation;
  			*lenp = 6;
  		}

  	}

  	return *lenp;
  }

  /*
   * looks for stat data, then copies fields to it, marks the buffer
   * containing stat data as dirty
   */
  /*
   * reiserfs inodes are never really dirty, since the dirty inode call
   * always logs them.  This call allows the VFS inode marking routines
   * to properly mark inodes for datasync and such, but only actually
   * does something when called for a synchronous update.
   */

  int reiserfs_write_inode(struct inode *inode, struct writeback_control *wbc)

  {
  	struct reiserfs_transaction_handle th;
  	int jbegin_count = 1;

  	if (sb_rdonly(inode->i_sb))

  		return -EROFS;

  	/*
  	 * memory pressure can sometimes initiate write_inode calls with
  	 * sync == 1,
  	 * these cases are just when the system needs ram, not when the
  	 * inode needs to reach disk for safety, and they can safely be
  	 * ignored because the altered inode has already been logged.

  	 */

  	if (wbc->sync_mode == WB_SYNC_ALL && !(current->flags & PF_MEMALLOC)) {

  		reiserfs_write_lock(inode->i_sb);
  		if (!journal_begin(&th, inode->i_sb, jbegin_count)) {
  			reiserfs_update_sd(&th, inode);

  			journal_end_sync(&th);

  		}
  		reiserfs_write_unlock(inode->i_sb);
  	}
  	return 0;

  }

  /*
   * stat data of new object is inserted already, this inserts the item
   * containing "." and ".." entries
   */

  static int reiserfs_new_directory(struct reiserfs_transaction_handle *th,
  				  struct inode *inode,

  				  struct item_head *ih, struct treepath *path,

  				  struct inode *dir)

  {

  	struct super_block *sb = th->t_super;
  	char empty_dir[EMPTY_DIR_SIZE];
  	char *body = empty_dir;
  	struct cpu_key key;
  	int retval;
  
  	BUG_ON(!th->t_trans_id);
  
  	_make_cpu_key(&key, KEY_FORMAT_3_5, le32_to_cpu(ih->ih_key.k_dir_id),
  		      le32_to_cpu(ih->ih_key.k_objectid), DOT_OFFSET,
  		      TYPE_DIRENTRY, 3 /*key length */ );

  	/*
  	 * compose item head for new item. Directories consist of items of
  	 * old type (ITEM_VERSION_1). Do not set key (second arg is 0), it
  	 * is done by reiserfs_new_inode
  	 */

  	if (old_format_only(sb)) {
  		make_le_item_head(ih, NULL, KEY_FORMAT_3_5, DOT_OFFSET,
  				  TYPE_DIRENTRY, EMPTY_DIR_SIZE_V1, 2);
  
  		make_empty_dir_item_v1(body, ih->ih_key.k_dir_id,
  				       ih->ih_key.k_objectid,
  				       INODE_PKEY(dir)->k_dir_id,
  				       INODE_PKEY(dir)->k_objectid);
  	} else {
  		make_le_item_head(ih, NULL, KEY_FORMAT_3_5, DOT_OFFSET,
  				  TYPE_DIRENTRY, EMPTY_DIR_SIZE, 2);
  
  		make_empty_dir_item(body, ih->ih_key.k_dir_id,
  				    ih->ih_key.k_objectid,
  				    INODE_PKEY(dir)->k_dir_id,
  				    INODE_PKEY(dir)->k_objectid);
  	}
  
  	/* look for place in the tree for new item */
  	retval = search_item(sb, &key, path);
  	if (retval == IO_ERROR) {

  		reiserfs_error(sb, "vs-13080",
  			       "i/o failure occurred creating new directory");

  		return -EIO;
  	}
  	if (retval == ITEM_FOUND) {
  		pathrelse(path);

  		reiserfs_warning(sb, "vs-13070",

  				 "object with this key exists (%k)",
  				 &(ih->ih_key));
  		return -EEXIST;
  	}

  	/* insert item, that is empty directory item */
  	return reiserfs_insert_item(th, path, &key, ih, inode, body);
  }

  /*
   * stat data of object has been inserted, this inserts the item
   * containing the body of symlink
   */
  static int reiserfs_new_symlink(struct reiserfs_transaction_handle *th,
  				struct inode *inode,

  				struct item_head *ih,

  				struct treepath *path, const char *symname,

  				int item_len)

  {

  	struct super_block *sb = th->t_super;
  	struct cpu_key key;
  	int retval;
  
  	BUG_ON(!th->t_trans_id);
  
  	_make_cpu_key(&key, KEY_FORMAT_3_5,
  		      le32_to_cpu(ih->ih_key.k_dir_id),
  		      le32_to_cpu(ih->ih_key.k_objectid),
  		      1, TYPE_DIRECT, 3 /*key length */ );
  
  	make_le_item_head(ih, NULL, KEY_FORMAT_3_5, 1, TYPE_DIRECT, item_len,
  			  0 /*free_space */ );
  
  	/* look for place in the tree for new item */
  	retval = search_item(sb, &key, path);
  	if (retval == IO_ERROR) {

  		reiserfs_error(sb, "vs-13080",
  			       "i/o failure occurred creating new symlink");

  		return -EIO;
  	}
  	if (retval == ITEM_FOUND) {
  		pathrelse(path);

  		reiserfs_warning(sb, "vs-13080",

  				 "object with this key exists (%k)",
  				 &(ih->ih_key));
  		return -EEXIST;
  	}

  	/* insert item, that is body of symlink */
  	return reiserfs_insert_item(th, path, &key, ih, inode, symname);
  }

  /*
   * inserts the stat data into the tree, and then calls
   * reiserfs_new_directory (to insert ".", ".." item if new object is
   * directory) or reiserfs_new_symlink (to insert symlink body if new
   * object is symlink) or nothing (if new object is regular file)
  
   * NOTE! uid and gid must already be set in the inode.  If we return
   * non-zero due to an error, we have to drop the quota previously allocated
   * for the fresh inode.  This can only be done outside a transaction, so
   * if we return non-zero, we also end the transaction.
   *
   * @th: active transaction handle
   * @dir: parent directory for new inode
   * @mode: mode of new inode
   * @symname: symlink contents if inode is symlink
   * @isize: 0 for regular file, EMPTY_DIR_SIZE for dirs, strlen(symname) for
   *         symlinks
   * @inode: inode to be filled
   * @security: optional security context to associate with this inode
   */

  int reiserfs_new_inode(struct reiserfs_transaction_handle *th,

  		       struct inode *dir, umode_t mode, const char *symname,

  		       /* 0 for regular, EMTRY_DIR_SIZE for dirs,

  		          strlen (symname) for symlinks) */
  		       loff_t i_size, struct dentry *dentry,

  		       struct inode *inode,
  		       struct reiserfs_security_handle *security)

  {

  	struct super_block *sb = dir->i_sb;

  	struct reiserfs_iget_args args;

  	INITIALIZE_PATH(path_to_key);
  	struct cpu_key key;
  	struct item_head ih;
  	struct stat_data sd;
  	int retval;
  	int err;

  	int depth;

  
  	BUG_ON(!th->t_trans_id);

  	depth = reiserfs_write_unlock_nested(sb);

  	err = dquot_alloc_inode(inode);

  	reiserfs_write_lock_nested(sb, depth);

  	if (err)

  		goto out_end_trans;

  	if (!dir->i_nlink) {

  		err = -EPERM;
  		goto out_bad_inode;
  	}

  	/* item head of new item */
  	ih.ih_key.k_dir_id = reiserfs_choose_packing(dir);
  	ih.ih_key.k_objectid = cpu_to_le32(reiserfs_get_unused_objectid(th));
  	if (!ih.ih_key.k_objectid) {
  		err = -ENOMEM;
  		goto out_bad_inode;
  	}

  	args.objectid = inode->i_ino = le32_to_cpu(ih.ih_key.k_objectid);

  	if (old_format_only(sb))
  		make_le_item_head(&ih, NULL, KEY_FORMAT_3_5, SD_OFFSET,
  				  TYPE_STAT_DATA, SD_V1_SIZE, MAX_US_INT);
  	else
  		make_le_item_head(&ih, NULL, KEY_FORMAT_3_6, SD_OFFSET,
  				  TYPE_STAT_DATA, SD_SIZE, MAX_US_INT);

  	memcpy(INODE_PKEY(inode), &ih.ih_key, KEY_SIZE);

  	args.dirid = le32_to_cpu(ih.ih_key.k_dir_id);

  	depth = reiserfs_write_unlock_nested(inode->i_sb);

  	err = insert_inode_locked4(inode, args.objectid,
  			     reiserfs_find_actor, &args);

  	reiserfs_write_lock_nested(inode->i_sb, depth);

  	if (err) {

  		err = -EINVAL;
  		goto out_bad_inode;
  	}

  	if (old_format_only(sb))

  		/*
  		 * not a perfect generation count, as object ids can be reused,
  		 * but this is as good as reiserfs can do right now.
  		 * note that the private part of inode isn't filled in yet,
  		 * we have to use the directory.

  		 */
  		inode->i_generation = le32_to_cpu(INODE_PKEY(dir)->k_objectid);
  	else

  #if defined( USE_INODE_GENERATION_COUNTER )

  		inode->i_generation =
  		    le32_to_cpu(REISERFS_SB(sb)->s_rs->s_inode_generation);

  #else

  		inode->i_generation = ++event;

  #endif

  	/* fill stat data */

  	set_nlink(inode, (S_ISDIR(mode) ? 2 : 1));

  
  	/* uid and gid must already be set by the caller for quota init */

  	inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);

  	inode->i_size = i_size;
  	inode->i_blocks = 0;
  	inode->i_bytes = 0;
  	REISERFS_I(inode)->i_first_direct_byte = S_ISLNK(mode) ? 1 :
  	    U32_MAX /*NO_BYTES_IN_DIRECT_ITEM */ ;

  	INIT_LIST_HEAD(&REISERFS_I(inode)->i_prealloc_list);

  	REISERFS_I(inode)->i_flags = 0;
  	REISERFS_I(inode)->i_prealloc_block = 0;
  	REISERFS_I(inode)->i_prealloc_count = 0;
  	REISERFS_I(inode)->i_trans_id = 0;
  	REISERFS_I(inode)->i_jl = NULL;
  	REISERFS_I(inode)->i_attrs =
  	    REISERFS_I(dir)->i_attrs & REISERFS_INHERIT_MASK;
  	sd_attrs_to_i_attrs(REISERFS_I(inode)->i_attrs, inode);

  	reiserfs_init_xattr_rwsem(inode);

  	/* key to search for correct place for new stat data */
  	_make_cpu_key(&key, KEY_FORMAT_3_6, le32_to_cpu(ih.ih_key.k_dir_id),
  		      le32_to_cpu(ih.ih_key.k_objectid), SD_OFFSET,
  		      TYPE_STAT_DATA, 3 /*key length */ );
  
  	/* find proper place for inserting of stat data */
  	retval = search_item(sb, &key, &path_to_key);
  	if (retval == IO_ERROR) {
  		err = -EIO;
  		goto out_bad_inode;
  	}
  	if (retval == ITEM_FOUND) {
  		pathrelse(&path_to_key);
  		err = -EEXIST;
  		goto out_bad_inode;
  	}
  	if (old_format_only(sb)) {

  		/* i_uid or i_gid is too big to be stored in stat data v3.5 */

  		if (i_uid_read(inode) & ~0xffff || i_gid_read(inode) & ~0xffff) {

  			pathrelse(&path_to_key);

  			err = -EINVAL;
  			goto out_bad_inode;
  		}
  		inode2sd_v1(&sd, inode, inode->i_size);
  	} else {
  		inode2sd(&sd, inode, inode->i_size);
  	}

  	/*
  	 * store in in-core inode the key of stat data and version all
  	 * object items will have (directory items will have old offset
  	 * format, other new objects will consist of new items)
  	 */

  	if (old_format_only(sb) || S_ISDIR(mode) || S_ISLNK(mode))
  		set_inode_item_key_version(inode, KEY_FORMAT_3_5);
  	else
  		set_inode_item_key_version(inode, KEY_FORMAT_3_6);
  	if (old_format_only(sb))
  		set_inode_sd_version(inode, STAT_DATA_V1);
  	else
  		set_inode_sd_version(inode, STAT_DATA_V2);
  
  	/* insert the stat data into the tree */

  #ifdef DISPLACE_NEW_PACKING_LOCALITIES

  	if (REISERFS_I(dir)->new_packing_locality)
  		th->displace_new_blocks = 1;

  #endif

  	retval =
  	    reiserfs_insert_item(th, &path_to_key, &key, &ih, inode,
  				 (char *)(&sd));
  	if (retval) {
  		err = retval;
  		reiserfs_check_path(&path_to_key);
  		goto out_bad_inode;
  	}

  #ifdef DISPLACE_NEW_PACKING_LOCALITIES

  	if (!th->displace_new_blocks)
  		REISERFS_I(dir)->new_packing_locality = 0;

  #endif

  	if (S_ISDIR(mode)) {
  		/* insert item with "." and ".." */
  		retval =
  		    reiserfs_new_directory(th, inode, &ih, &path_to_key, dir);
  	}
  
  	if (S_ISLNK(mode)) {
  		/* insert body of symlink */
  		if (!old_format_only(sb))
  			i_size = ROUND_UP(i_size);
  		retval =
  		    reiserfs_new_symlink(th, inode, &ih, &path_to_key, symname,
  					 i_size);
  	}
  	if (retval) {
  		err = retval;
  		reiserfs_check_path(&path_to_key);

  		journal_end(th);

  		goto out_inserted_sd;
  	}