inode.c

linux 内核源代码

			 */
			for (i=1; i < num; i++)
				*(branch[n].p + i) = cpu_to_le32(++current_block);
		}
		set_buffer_uptodate(bh);
		unlock_buffer(bh);
		mark_buffer_dirty_inode(bh, inode);
		/* We used to sync bh here if IS_SYNC(inode).
		 * But we now rely upon generic_osync_inode()
		 * and b_inode_buffers.  But not for directories.
		 */
		if (S_ISDIR(inode->i_mode) && IS_DIRSYNC(inode))
			sync_dirty_buffer(bh);
	}
	*blks = num;
	return err;
}

/**
 * ext2_splice_branch - splice the allocated branch onto inode.
 * @inode: owner
 * @block: (logical) number of block we are adding
 * @chain: chain of indirect blocks (with a missing link - see
 *	ext2_alloc_branch)
 * @where: location of missing link
 * @num:   number of indirect blocks we are adding
 * @blks:  number of direct blocks we are adding
 *
 * This function fills the missing link and does all housekeeping needed in
 * inode (->i_blocks, etc.). In case of success we end up with the full
 * chain to new block and return 0.
 */
static void ext2_splice_branch(struct inode *inode,
			long block, Indirect *where, int num, int blks)
{
	int i;
	struct ext2_block_alloc_info *block_i;
	ext2_fsblk_t current_block;

	block_i = EXT2_I(inode)->i_block_alloc_info;

	/* XXX LOCKING probably should have i_meta_lock ?*/
	/* That's it */

	*where->p = where->key;

	/*
	 * Update the host buffer_head or inode to point to more just allocated
	 * direct blocks blocks
	 */
	if (num == 0 && blks > 1) {
		current_block = le32_to_cpu(where->key) + 1;
		for (i = 1; i < blks; i++)
			*(where->p + i ) = cpu_to_le32(current_block++);
	}

	/*
	 * update the most recently allocated logical & physical block
	 * in i_block_alloc_info, to assist find the proper goal block for next
	 * allocation
	 */
	if (block_i) {
		block_i->last_alloc_logical_block = block + blks - 1;
		block_i->last_alloc_physical_block =
				le32_to_cpu(where[num].key) + blks - 1;
	}

	/* We are done with atomic stuff, now do the rest of housekeeping */

	/* had we spliced it onto indirect block? */
	if (where->bh)
		mark_buffer_dirty_inode(where->bh, inode);

	inode->i_ctime = CURRENT_TIME_SEC;
	mark_inode_dirty(inode);
}

/*
 * Allocation strategy is simple: if we have to allocate something, we will
 * have to go the whole way to leaf. So let's do it before attaching anything
 * to tree, set linkage between the newborn blocks, write them if sync is
 * required, recheck the path, free and repeat if check fails, otherwise
 * set the last missing link (that will protect us from any truncate-generated
 * removals - all blocks on the path are immune now) and possibly force the
 * write on the parent block.
 * That has a nice additional property: no special recovery from the failed
 * allocations is needed - we simply release blocks and do not touch anything
 * reachable from inode.
 *
 * `handle' can be NULL if create == 0.
 *
 * The BKL may not be held on entry here.  Be sure to take it early.
 * return > 0, # of blocks mapped or allocated.
 * return = 0, if plain lookup failed.
 * return < 0, error case.
 */
static int ext2_get_blocks(struct inode *inode,
			   sector_t iblock, unsigned long maxblocks,
			   struct buffer_head *bh_result,
			   int create)
{
	int err = -EIO;
	int offsets[4];
	Indirect chain[4];
	Indirect *partial;
	ext2_fsblk_t goal;
	int indirect_blks;
	int blocks_to_boundary = 0;
	int depth;
	struct ext2_inode_info *ei = EXT2_I(inode);
	int count = 0;
	ext2_fsblk_t first_block = 0;

	depth = ext2_block_to_path(inode,iblock,offsets,&blocks_to_boundary);

	if (depth == 0)
		return (err);
reread:
	partial = ext2_get_branch(inode, depth, offsets, chain, &err);

	/* Simplest case - block found, no allocation needed */
	if (!partial) {
		first_block = le32_to_cpu(chain[depth - 1].key);
		clear_buffer_new(bh_result); /* What's this do? */
		count++;
		/*map more blocks*/
		while (count < maxblocks && count <= blocks_to_boundary) {
			ext2_fsblk_t blk;

			if (!verify_chain(chain, partial)) {
				/*
				 * Indirect block might be removed by
				 * truncate while we were reading it.
				 * Handling of that case: forget what we've
				 * got now, go to reread.
				 */
				count = 0;
				goto changed;
			}
			blk = le32_to_cpu(*(chain[depth-1].p + count));
			if (blk == first_block + count)
				count++;
			else
				break;
		}
		goto got_it;
	}

	/* Next simple case - plain lookup or failed read of indirect block */
	if (!create || err == -EIO)
		goto cleanup;

	mutex_lock(&ei->truncate_mutex);

	/*
	 * Okay, we need to do block allocation.  Lazily initialize the block
	 * allocation info here if necessary
	*/
	if (S_ISREG(inode->i_mode) && (!ei->i_block_alloc_info))
		ext2_init_block_alloc_info(inode);

	goal = ext2_find_goal(inode, iblock, chain, partial);

	/* the number of blocks need to allocate for [d,t]indirect blocks */
	indirect_blks = (chain + depth) - partial - 1;
	/*
	 * Next look up the indirect map to count the totoal number of
	 * direct blocks to allocate for this branch.
	 */
	count = ext2_blks_to_allocate(partial, indirect_blks,
					maxblocks, blocks_to_boundary);
	/*
	 * XXX ???? Block out ext2_truncate while we alter the tree
	 */
	err = ext2_alloc_branch(inode, indirect_blks, &count, goal,
				offsets + (partial - chain), partial);

	if (err) {
		mutex_unlock(&ei->truncate_mutex);
		goto cleanup;
	}

	if (ext2_use_xip(inode->i_sb)) {
		/*
		 * we need to clear the block
		 */
		err = ext2_clear_xip_target (inode,
			le32_to_cpu(chain[depth-1].key));
		if (err) {
			mutex_unlock(&ei->truncate_mutex);
			goto cleanup;
		}
	}

	ext2_splice_branch(inode, iblock, partial, indirect_blks, count);
	mutex_unlock(&ei->truncate_mutex);
	set_buffer_new(bh_result);
got_it:
	map_bh(bh_result, inode->i_sb, le32_to_cpu(chain[depth-1].key));
	if (count > blocks_to_boundary)
		set_buffer_boundary(bh_result);
	err = count;
	/* Clean up and exit */
	partial = chain + depth - 1;	/* the whole chain */
cleanup:
	while (partial > chain) {
		brelse(partial->bh);
		partial--;
	}
	return err;
changed:
	while (partial > chain) {
		brelse(partial->bh);
		partial--;
	}
	goto reread;
}

int ext2_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create)
{
	unsigned max_blocks = bh_result->b_size >> inode->i_blkbits;
	int ret = ext2_get_blocks(inode, iblock, max_blocks,
			      bh_result, create);
	if (ret > 0) {
		bh_result->b_size = (ret << inode->i_blkbits);
		ret = 0;
	}
	return ret;

}

static int ext2_writepage(struct page *page, struct writeback_control *wbc)
{
	return block_write_full_page(page, ext2_get_block, wbc);
}

static int ext2_readpage(struct file *file, struct page *page)
{
	return mpage_readpage(page, ext2_get_block);
}

static int
ext2_readpages(struct file *file, struct address_space *mapping,
		struct list_head *pages, unsigned nr_pages)
{
	return mpage_readpages(mapping, pages, nr_pages, ext2_get_block);
}

int __ext2_write_begin(struct file *file, struct address_space *mapping,
		loff_t pos, unsigned len, unsigned flags,
		struct page **pagep, void **fsdata)
{
	return block_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
							ext2_get_block);
}

static int
ext2_write_begin(struct file *file, struct address_space *mapping,
		loff_t pos, unsigned len, unsigned flags,
		struct page **pagep, void **fsdata)
{
	*pagep = NULL;
	return __ext2_write_begin(file, mapping, pos, len, flags, pagep,fsdata);
}

static int
ext2_nobh_write_begin(struct file *file, struct address_space *mapping,
		loff_t pos, unsigned len, unsigned flags,
		struct page **pagep, void **fsdata)
{
	/*
	 * Dir-in-pagecache still uses ext2_write_begin. Would have to rework
	 * directory handling code to pass around offsets rather than struct
	 * pages in order to make this work easily.
	 */
	return nobh_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
							ext2_get_block);
}

static int ext2_nobh_writepage(struct page *page,
			struct writeback_control *wbc)
{
	return nobh_writepage(page, ext2_get_block, wbc);
}

static sector_t ext2_bmap(struct address_space *mapping, sector_t block)
{
	return generic_block_bmap(mapping,block,ext2_get_block);
}

static ssize_t
ext2_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
			loff_t offset, unsigned long nr_segs)
{
	struct file *file = iocb->ki_filp;
	struct inode *inode = file->f_mapping->host;

	return blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov,
				offset, nr_segs, ext2_get_block, NULL);
}

static int
ext2_writepages(struct address_space *mapping, struct writeback_control *wbc)
{
	return mpage_writepages(mapping, wbc, ext2_get_block);
}

const struct address_space_operations ext2_aops = {
	.readpage		= ext2_readpage,
	.readpages		= ext2_readpages,
	.writepage		= ext2_writepage,
	.sync_page		= block_sync_page,
	.write_begin		= ext2_write_begin,
	.write_end		= generic_write_end,
	.bmap			= ext2_bmap,
	.direct_IO		= ext2_direct_IO,
	.writepages		= ext2_writepages,
	.migratepage		= buffer_migrate_page,
};

const struct address_space_operations ext2_aops_xip = {
	.bmap			= ext2_bmap,
	.get_xip_page		= ext2_get_xip_page,
};

const struct address_space_operations ext2_nobh_aops = {
	.readpage		= ext2_readpage,
	.readpages		= ext2_readpages,
	.writepage		= ext2_nobh_writepage,
	.sync_page		= block_sync_page,
	.write_begin		= ext2_nobh_write_begin,
	.write_end		= nobh_write_end,
	.bmap			= ext2_bmap,
	.direct_IO		= ext2_direct_IO,
	.writepages		= ext2_writepages,
	.migratepage		= buffer_migrate_page,
};

/*
 * 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(__le32 *p, __le32 *q)
{
	while (p < q)
		if (*p++)
			return 0;
	return 1;
}

/**
 *	ext2_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 ext2_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 ext2_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 ext2_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].p
 *			(no partially truncated stuff there).
 */

static Indirect *ext2_find_shared(struct inode *inode,
				int depth,
				int offsets[4],
				Indirect chain[4],
				__le32 *top)
{
	Indirect *partial, *p;
	int k, err;

	*top = 0;
	for (k = depth; k > 1 && !offsets[k-1]; k--)
		;
	partial = ext2_get_branch(inode, k, offsets, chain, &err);
	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.
	 */
	write_lock(&EXT2_I(inode)->i_meta_lock);
	if (!partial->key && *partial->p) {
		write_unlock(&EXT2_I(inode)->i_meta_lock);
		goto no_top;
	}
	for (p=partial; p>chain && all_zeroes((__le32*)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;
		*p->p = 0;
	}
	write_unlock(&EXT2_I(inode)->i_meta_lock);

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

/**
 *	ext2_free_data - free a list of data blocks
 *	@inode:	inode we are dealing with
 *	@p:	array of block numbers
 *	@q:	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.
 */
static inline void ext2_free_data(struct inode *inode, __le32 *p, __le32 *q)
{
	unsigned long block_to_free = 0, count = 0;
	unsigned long nr;

	for ( ; p < q ; p++) {
		nr = le32_to_cpu(*p);
		if (nr) {
			*p = 0;
			/* accumulate blocks to free if they're contiguous */
			if (count == 0)
				goto free_this;
			else if (block_to_free == nr - count)
				count++;
			else {
				mark_inode_dirty(inode);
				ext2_free_blocks (inode, block_to_free, count);
			free_this:
				block_to_free = nr;
				count = 1;
			}
		}
	}
	if (count > 0) {
		mark_inode_dirty(inode);
		ext2_free_blocks (inode, block_to_free, count);
	}
}

/**
 *	ext2_free_branches - free an array of branches
 *	@inode:	inode we are dealing with
 *	@p:	array of block numbers
 *	@q:	pointer immediately past the end of array
 *	@depth:	depth of the branches to free
 *