inode.c

嵌入式系统设计与实例开发实验教材二源码 多线程应用程序设计 串行端口程序设计 AD接口实验 CAN总线通信实验 GPS通信实验 Linux内核移植与编译实验 IC卡读写实验 SD驱动使

	/* bget() all the buffers */
	if (order_data) {
		if (!page->buffers)
			create_empty_buffers(page,
				inode->i_dev, inode->i_sb->s_blocksize);
		page_buffers = page->buffers;
		walk_page_buffers(handle, page_buffers, 0,
				PAGE_CACHE_SIZE, NULL, bget_one);
	}

	ret = block_write_full_page(page, ext3_get_block);

	/*
	 * The page can become unlocked at any point now, and
	 * truncate can then come in and change things.  So we
	 * can't touch *page from now on.  But *page_buffers is
	 * safe due to elevated refcount.
	 */

	handle = ext3_journal_current_handle();
	lock_kernel();

	/* And attach them to the current transaction */
	if (order_data) {
		err = walk_page_buffers(handle, page_buffers,
			0, PAGE_CACHE_SIZE, NULL, journal_dirty_async_data);
		if (!ret)
			ret = err;
	}

	err = ext3_journal_stop(handle, inode);
	if (!ret)
		ret = err;
	unlock_kernel();
	return ret;

out_fail:
	
	unlock_kernel();
	SetPageDirty(page);
	UnlockPage(page);
	return ret;
}

static int ext3_readpage(struct file *file, struct page *page)
{
	return block_read_full_page(page,ext3_get_block);
}


static int ext3_flushpage(struct page *page, unsigned long offset)
{
	journal_t *journal = EXT3_JOURNAL(page->mapping->host);
	return journal_flushpage(journal, page, offset);
}

static int ext3_releasepage(struct page *page, int wait)
{
	journal_t *journal = EXT3_JOURNAL(page->mapping->host);
	return journal_try_to_free_buffers(journal, page, wait);
}


struct address_space_operations ext3_aops = {
	readpage:	ext3_readpage,		/* BKL not held.  Don't need */
	writepage:	ext3_writepage,		/* BKL not held.  We take it */
	sync_page:	block_sync_page,
	prepare_write:	ext3_prepare_write,	/* BKL not held.  We take it */
	commit_write:	ext3_commit_write,	/* BKL not held.  We take it */
	bmap:		ext3_bmap,		/* BKL held */
	flushpage:	ext3_flushpage,		/* BKL not held.  Don't need */
	releasepage:	ext3_releasepage,	/* BKL not held.  Don't need */
};

/*
 * ext3_block_truncate_page() zeroes out a mapping from file offset `from'
 * up to the end of the block which corresponds to `from'.
 * This required during truncate. We need to physically zero the tail end
 * of that block so it doesn't yield old data if the file is later grown.
 */
static int ext3_block_truncate_page(handle_t *handle,
		struct address_space *mapping, loff_t from)
{
	unsigned long index = from >> PAGE_CACHE_SHIFT;
	unsigned offset = from & (PAGE_CACHE_SIZE-1);
	unsigned blocksize, iblock, length, pos;
	struct inode *inode = mapping->host;
	struct page *page;
	struct buffer_head *bh;
	int err;

	blocksize = inode->i_sb->s_blocksize;
	length = offset & (blocksize - 1);

	/* Block boundary? Nothing to do */
	if (!length)
		return 0;

	length = blocksize - length;
	iblock = index << (PAGE_CACHE_SHIFT - inode->i_sb->s_blocksize_bits);

	page = grab_cache_page(mapping, index);
	err = -ENOMEM;
	if (!page)
		goto out;

	if (!page->buffers)
		create_empty_buffers(page, inode->i_dev, blocksize);

	/* Find the buffer that contains "offset" */
	bh = page->buffers;
	pos = blocksize;
	while (offset >= pos) {
		bh = bh->b_this_page;
		iblock++;
		pos += blocksize;
	}

	err = 0;
	if (!buffer_mapped(bh)) {
		/* Hole? Nothing to do */
		if (buffer_uptodate(bh))
			goto unlock;
		ext3_get_block(inode, iblock, bh, 0);
		/* Still unmapped? Nothing to do */
		if (!buffer_mapped(bh))
			goto unlock;
	}

	/* Ok, it's mapped. Make sure it's up-to-date */
	if (Page_Uptodate(page))
		set_bit(BH_Uptodate, &bh->b_state);

	if (!buffer_uptodate(bh)) {
		err = -EIO;
		ll_rw_block(READ, 1, &bh);
		wait_on_buffer(bh);
		/* Uhhuh. Read error. Complain and punt. */
		if (!buffer_uptodate(bh))
			goto unlock;
	}

	if (ext3_should_journal_data(inode)) {
		BUFFER_TRACE(bh, "get write access");
		err = ext3_journal_get_write_access(handle, bh);
		if (err)
			goto unlock;
	}
	
	memset(kmap(page) + offset, 0, length);
	flush_dcache_page(page);
	kunmap(page);

	BUFFER_TRACE(bh, "zeroed end of block");

	err = 0;
	if (ext3_should_journal_data(inode)) {
		err = ext3_journal_dirty_metadata(handle, bh);
	} else {
		if (ext3_should_order_data(inode))
			err = ext3_journal_dirty_data(handle, bh, 0);
		__mark_buffer_dirty(bh);
	}

unlock:
	UnlockPage(page);
	page_cache_release(page);
out:
	return err;
}

/*
 * Probably it should be a library function... search for first non-zero word
 * or memcmp with zero_page, whatever is better for particular architecture.
 * Linus?
 */
static inline int all_zeroes(u32 *p, u32 *q)
{
	while (p < q)
		if (*p++)
			return 0;
	return 1;
}

/**
 *	ext3_find_shared - find the indirect blocks for partial truncation.
 *	@inode:	  inode in question
 *	@depth:	  depth of the affected branch
 *	@offsets: offsets of pointers in that branch (see ext3_block_to_path)
 *	@chain:	  place to store the pointers to partial indirect blocks
 *	@top:	  place to the (detached) top of branch
 *
 *	This is a helper function used by ext3_truncate().
 *
 *	When we do truncate() we may have to clean the ends of several
 *	indirect blocks but leave the blocks themselves alive. Block is
 *	partially truncated if some data below the new i_size is refered
 *	from it (and it is on the path to the first completely truncated
 *	data block, indeed).  We have to free the top of that path along
 *	with everything to the right of the path. Since no allocation
 *	past the truncation point is possible until ext3_truncate()
 *	finishes, we may safely do the latter, but top of branch may
 *	require special attention - pageout below the truncation point
 *	might try to populate it.
 *
 *	We atomically detach the top of branch from the tree, store the
 *	block number of its root in *@top, pointers to buffer_heads of
 *	partially truncated blocks - in @chain[].bh and pointers to
 *	their last elements that should not be removed - in
 *	@chain[].p. Return value is the pointer to last filled element
 *	of @chain.
 *
 *	The work left to caller to do the actual freeing of subtrees:
 *		a) free the subtree starting from *@top
 *		b) free the subtrees whose roots are stored in
 *			(@chain[i].p+1 .. end of @chain[i].bh->b_data)
 *		c) free the subtrees growing from the inode past the @chain[0].
 *			(no partially truncated stuff there).  */

static Indirect *ext3_find_shared(struct inode *inode,
				int depth,
				int offsets[4],
				Indirect chain[4],
				u32 *top)
{
	Indirect *partial, *p;
	int k, err;

	*top = 0;
	/* Make k index the deepest non-null offest + 1 */
	for (k = depth; k > 1 && !offsets[k-1]; k--)
		;
	partial = ext3_get_branch(inode, k, offsets, chain, &err);
	/* Writer: pointers */
	if (!partial)
		partial = chain + k-1;
	/*
	 * If the branch acquired continuation since we've looked at it -
	 * fine, it should all survive and (new) top doesn't belong to us.
	 */
	if (!partial->key && *partial->p)
		/* Writer: end */
		goto no_top;
	for (p=partial; p>chain && all_zeroes((u32*)p->bh->b_data,p->p); p--)
		;
	/*
	 * OK, we've found the last block that must survive. The rest of our
	 * branch should be detached before unlocking. However, if that rest
	 * of branch is all ours and does not grow immediately from the inode
	 * it's easier to cheat and just decrement partial->p.
	 */
	if (p == chain + k - 1 && p > chain) {
		p->p--;
	} else {
		*top = *p->p;
		/* Nope, don't do this in ext3.  Must leave the tree intact */
#if 0
		*p->p = 0;
#endif
	}
	/* Writer: end */

	while(partial > p)
	{
		brelse(partial->bh);
		partial--;
	}
no_top:
	return partial;
}

/*
 * Zero a number of block pointers in either an inode or an indirect block.
 * If we restart the transaction we must again get write access to the
 * indirect block for further modification.
 *
 * We release `count' blocks on disk, but (last - first) may be greater
 * than `count' because there can be holes in there.
 */
static void
ext3_clear_blocks(handle_t *handle, struct inode *inode, struct buffer_head *bh,
		unsigned long block_to_free, unsigned long count,
		u32 *first, u32 *last)
{
	u32 *p;
	if (try_to_extend_transaction(handle, inode)) {
		if (bh) {
			BUFFER_TRACE(bh, "call ext3_journal_dirty_metadata");
			ext3_journal_dirty_metadata(handle, bh);
		}
		ext3_mark_inode_dirty(handle, inode);
		ext3_journal_test_restart(handle, inode);
		BUFFER_TRACE(bh, "get_write_access");
		ext3_journal_get_write_access(handle, bh);
	}

	/*
	 * Any buffers which are on the journal will be in memory. We find
	 * them on the hash table so journal_revoke() will run journal_forget()
	 * on them.  We've already detached each block from the file, so
	 * bforget() in journal_forget() should be safe.
	 *
	 * AKPM: turn on bforget in journal_forget()!!!
	 */
	for (p = first; p < last; p++) {
		u32 nr = le32_to_cpu(*p);
		if (nr) {
			struct buffer_head *bh;

			*p = 0;
			bh = sb_get_hash_table(inode->i_sb, nr);
			ext3_forget(handle, 0, inode, bh, nr);
		}
	}

	ext3_free_blocks(handle, inode, block_to_free, count);
}

/**
 * ext3_free_data - free a list of data blocks
 * @handle:	handle for this transaction
 * @inode:	inode we are dealing with
 * @this_bh:	indirect buffer_head which contains *@first and *@last
 * @first:	array of block numbers
 * @last:	points immediately past the end of array
 *
 * We are freeing all blocks refered from that array (numbers are stored as
 * little-endian 32-bit) and updating @inode->i_blocks appropriately.
 *
 * We accumulate contiguous runs of blocks to free.  Conveniently, if these
 * blocks are contiguous then releasing them at one time will only affect one
 * or two bitmap blocks (+ group descriptor(s) and superblock) and we won't
 * actually use a lot of journal space.
 *
 * @this_bh will be %NULL if @first and @last point into the inode's direct
 * block pointers.
 */
static void ext3_free_data(handle_t *handle, struct inode *inode,
			   struct buffer_head *this_bh, u32 *first, u32 *last)
{
	unsigned long block_to_free = 0;    /* Starting block # of a run */
	unsigned long count = 0;	    /* Number of blocks in the run */ 
	u32 *block_to_free_p = NULL;	    /* Pointer into inode/ind
					       corresponding to
					       block_to_free */
	unsigned long nr;		    /* Current block # */
	u32 *p;				    /* Pointer into inode/ind
					       for current block */
	int err;

	if (this_bh) {				/* For indirect block */
		BUFFER_TRACE(this_bh, "get_write_access");
		err = ext3_journal_get_write_access(handle, this_bh);
		/* Important: if we can't update the indirect pointers
		 * to the blocks, we can't free them. */
		if (err)
			return;
	}

	for (p = first; p < last; p++) {
		nr = le32_to_cpu(*p);
		if (nr) {
			/* accumulate blocks to free if they're contiguous */
			if (count == 0) {
				block_to_free = nr;
				block_to_free_p = p;
				count = 1;
			} else if (nr == block_to_free + count) {
				count++;
			} else {
				ext3_clear_blocks(handle, inode, this_bh, 
						  block_to_free,
						  count, block_to_free_p, p);
				block_to_free = nr;
				block_to_free_p = p;
				count = 1;
			}
		}
	}

	if (count > 0)
		ext3_clear_blocks(handle, inode, this_bh, block_to_free,
				  count, block_to_free_p, p);

	if (this_bh) {
		BUFFER_TRACE(this_bh, "call ext3_journal_dirty_metadata");
		ext3_journal_dirty_metadata(handle, this_bh);
	}
}

/**
 *	ext3_free_branches - free an array of branches
 *	@handle: JBD handle for this transaction
 *	@inode:	inode we are dealing with
 *	@parent_bh: the buffer_head which contains *@first and *@last
 *	@first:	array of block numbers
 *	@last:	pointer immediately past the end of array
 *	@depth:	depth of the branches to free
 *
 *	We are freeing all blocks refered from these branches (numbers are
 *	stored as little-endian 32-bit) and updating @inode->i_blocks
 *	appropriately.
 */
static void ext3_free_branches(handle_t *handle, struct inode *inode,
			       struct buffer_head *parent_bh,
			       u32 *first, u32 *last, int depth)
{
	unsigned long nr;
	u32 *p;

	if (is_handle_aborted(handle))
		return;
	
	if (depth--) {
		struct buffer_head *bh;
		int addr_per_block = EXT3_ADDR_PER_BLOCK(inode->i_sb);
		p = last;
		while (--p >= first) {
			nr = le32_to_cpu(*p);
			if (!nr)
				continue;		/* A hole */

			/* Go read the buffer for the next level down */
			bh = sb_bread(inode->i_sb, nr);

			/*
			 * A read failure? Report error and clear slot
			 * (should be rare).
			 */