inode.c

来自「Linux Kernel 2.6.9 for OMAP1710」· C语言 代码 · 共 1,950 行 · 第 1/5 页

// read direct item
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_prepare_write, 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_prepare_write expects to
** be able to do i/o on the buffers returned, unless an error value
** is also returned.
** 
** So, this allows block_prepare_write 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,
					 unsigned long max_blocks,
					 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 = (1 << inode->i_blkbits);

    ret = reiserfs_get_block(inode, iblock, bh_result,
                             create | GET_BLOCK_NO_DANGLE) ;

    /* don't allow direct io onto tail pages */
    if (ret == 0 && 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) {
        lock_kernel();
        reiserfs_commit_for_inode(inode);
        REISERFS_I(inode)->i_flags &= ~i_pack_on_close_mask;
        unlock_kernel();
    }
    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_CACHE_SIZE - 1) ;
    tail_end = (tail_start | (bh_result->b_size - 1)) + 1 ;

    index = tail_offset >> PAGE_CACHE_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_sem.
    **
    ** 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_prepare_write
    ** won't trigger a get_block in this case.
    */
    fix_tail_page_for_writing(tail_page) ;
    retval = reiserfs_prepare_write(NULL, tail_page, tail_start, tail_end);
    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) ;
	page_cache_release(tail_page) ;
    }
out:
    return retval ;
}

static inline int _allocate_block(struct reiserfs_transaction_handle *th,
			   long block,
                           struct inode *inode, 
			   b_blocknr_t *allocated_block_nr, 
			   struct path * path,
			   int flags) {
  
#ifdef REISERFS_PREALLOCATE
    if (!(flags & GET_BLOCK_NO_ISEM)) {
	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;
    b_blocknr_t allocated_block_nr = 0;// b_blocknr_t is (unsigned) 32 bit int
    INITIALIZE_PATH(path);
    int pos_in_item;
    struct cpu_key key;
    struct buffer_head * bh, * unbh = NULL;
    struct item_head * ih, tmp_ih;
    __u32 * 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 that 3 balancings. */
    int jbegin_count = JOURNAL_PER_BALANCE_CNT * 3 + 1;
    int version;
    int dangle = 1;
    loff_t new_offset = (((loff_t)block) << inode->i_sb->s_blocksize_bits) + 1 ;

				/* bad.... */
    reiserfs_write_lock(inode->i_sb);
    version = get_inode_item_key_version (inode);

    if (block < 0) {
	reiserfs_write_unlock(inode->i_sb);
	return -EIO;
    }

    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 = get_ih (&path);
    item = get_item (&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);

	if (repeat == NO_DISK_SPACE || repeat == QUOTA_EXCEEDED) {
	    /* 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
	    */
	    SB_JOURNAL(inode->i_sb)->j_next_async_flush = 1;
	    restart_transaction(th, inode, &path) ;
	    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, inode->i_sb, bh);
	    reiserfs_update_sd(th, inode) ;
	}
	set_block_dev_mapped(bh_result, unfm_ptr, inode);
	pathrelse (&path);
	if (!dangle && th)
	    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 0;
    }

    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)) {
	    __u32 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 */);

	    if (cpu_key_k_offset (&key) == 1) {
		/* we are going to add 'block'-th block to the file. Use
		   allocated block for that */
		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);
		goto failure; // retval == -ENOSPC, -EDQUOT or -EIO or -EEXIST
	    }
	    //mark_tail_converted (inode);
	} 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;
	    if (tail_offset == cpu_key_k_offset (&key)) {
		/* direct item we just found fits into block we have
                   to map. Convert it into unformatted node: use
                   bh_result for the conversion */
		set_block_dev_mapped (bh_result, allocated_block_nr, inode);
		unbh = bh_result;
		done = 1;
	    } else {
		/* we have to padd 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
		 */
		if (th->t_refcount == 1) {
		    reiserfs_end_persistent_transaction(th);
		    th = NULL;
		}

		retval = convert_tail_for_hole(inode, bh_result, tail_offset) ;
		if (retval) {
		    if ( retval != -ENOSPC )
			reiserfs_warning (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)