inode.c

来自「Linux Kernel 2.6.9 for OMAP1710」· C语言 代码 · 共 2,219 行 · 第 1/5 页

		/* Reader: end */
		if (!p->key)
			goto no_block;
	}
	return NULL;

changed:
	brelse(bh);
	*err = -EAGAIN;
	goto no_block;
failure:
	*err = -EIO;
no_block:
	return p;
}

/**
 *	ext3_find_near - find a place for allocation with sufficient locality
 *	@inode: owner
 *	@ind: descriptor of indirect block.
 *
 *	This function returns the prefered place for block allocation.
 *	It is used when heuristic for sequential allocation fails.
 *	Rules are:
 *	  + if there is a block to the left of our position - allocate near it.
 *	  + if pointer will live in indirect block - allocate near that block.
 *	  + if pointer will live in inode - allocate in the same
 *	    cylinder group. 
 *
 * In the latter case we colour the starting block by the callers PID to
 * prevent it from clashing with concurrent allocations for a different inode
 * in the same block group.   The PID is used here so that functionally related
 * files will be close-by on-disk.
 *
 *	Caller must make sure that @ind is valid and will stay that way.
 */

static unsigned long ext3_find_near(struct inode *inode, Indirect *ind)
{
	struct ext3_inode_info *ei = EXT3_I(inode);
	__le32 *start = ind->bh ? (__le32*) ind->bh->b_data : ei->i_data;
	__le32 *p;
	unsigned long bg_start;
	unsigned long colour;

	/* Try to find previous block */
	for (p = ind->p - 1; p >= start; p--)
		if (*p)
			return le32_to_cpu(*p);

	/* No such thing, so let's try location of indirect block */
	if (ind->bh)
		return ind->bh->b_blocknr;

	/*
	 * It is going to be refered from inode itself? OK, just put it into
	 * the same cylinder group then.
	 */
	bg_start = (ei->i_block_group * EXT3_BLOCKS_PER_GROUP(inode->i_sb)) +
		le32_to_cpu(EXT3_SB(inode->i_sb)->s_es->s_first_data_block);
	colour = (current->pid % 16) *
			(EXT3_BLOCKS_PER_GROUP(inode->i_sb) / 16);
	return bg_start + colour;
}

/**
 *	ext3_find_goal - find a prefered place for allocation.
 *	@inode: owner
 *	@block:  block we want
 *	@chain:  chain of indirect blocks
 *	@partial: pointer to the last triple within a chain
 *	@goal:	place to store the result.
 *
 *	Normally this function find the prefered place for block allocation,
 *	stores it in *@goal and returns zero. If the branch had been changed
 *	under us we return -EAGAIN.
 */

static int ext3_find_goal(struct inode *inode, long block, Indirect chain[4],
			  Indirect *partial, unsigned long *goal)
{
	struct ext3_inode_info *ei = EXT3_I(inode);
	/* Writer: ->i_next_alloc* */
	if (block == ei->i_next_alloc_block + 1) {
		ei->i_next_alloc_block++;
		ei->i_next_alloc_goal++;
	}
	/* Writer: end */
	/* Reader: pointers, ->i_next_alloc* */
	if (verify_chain(chain, partial)) {
		/*
		 * try the heuristic for sequential allocation,
		 * failing that at least try to get decent locality.
		 */
		if (block == ei->i_next_alloc_block)
			*goal = ei->i_next_alloc_goal;
		if (!*goal)
			*goal = ext3_find_near(inode, partial);
		return 0;
	}
	/* Reader: end */
	return -EAGAIN;
}

/**
 *	ext3_alloc_branch - allocate and set up a chain of blocks.
 *	@inode: owner
 *	@num: depth of the chain (number of blocks to allocate)
 *	@offsets: offsets (in the blocks) to store the pointers to next.
 *	@branch: place to store the chain in.
 *
 *	This function allocates @num blocks, zeroes out all but the last one,
 *	links them into chain and (if we are synchronous) writes them to disk.
 *	In other words, it prepares a branch that can be spliced onto the
 *	inode. It stores the information about that chain in the branch[], in
 *	the same format as ext3_get_branch() would do. We are calling it after
 *	we had read the existing part of chain and partial points to the last
 *	triple of that (one with zero ->key). Upon the exit we have the same
 *	picture as after the successful ext3_get_block(), excpet that in one
 *	place chain is disconnected - *branch->p is still zero (we did not
 *	set the last link), but branch->key contains the number that should
 *	be placed into *branch->p to fill that gap.
 *
 *	If allocation fails we free all blocks we've allocated (and forget
 *	their buffer_heads) and return the error value the from failed
 *	ext3_alloc_block() (normally -ENOSPC). Otherwise we set the chain
 *	as described above and return 0.
 */

static int ext3_alloc_branch(handle_t *handle, struct inode *inode,
			     int num,
			     unsigned long goal,
			     int *offsets,
			     Indirect *branch)
{
	int blocksize = inode->i_sb->s_blocksize;
	int n = 0, keys = 0;
	int err = 0;
	int i;
	int parent = ext3_alloc_block(handle, inode, goal, &err);

	branch[0].key = cpu_to_le32(parent);
	if (parent) {
		for (n = 1; n < num; n++) {
			struct buffer_head *bh;
			/* Allocate the next block */
			int nr = ext3_alloc_block(handle, inode, parent, &err);
			if (!nr)
				break;
			branch[n].key = cpu_to_le32(nr);
			keys = n+1;

			/*
			 * Get buffer_head for parent block, zero it out
			 * and set the pointer to new one, then send
			 * parent to disk.  
			 */
			bh = sb_getblk(inode->i_sb, parent);
			branch[n].bh = bh;
			lock_buffer(bh);
			BUFFER_TRACE(bh, "call get_create_access");
			err = ext3_journal_get_create_access(handle, bh);
			if (err) {
				unlock_buffer(bh);
				brelse(bh);
				break;
			}

			memset(bh->b_data, 0, blocksize);
			branch[n].p = (__le32*) bh->b_data + offsets[n];
			*branch[n].p = branch[n].key;
			BUFFER_TRACE(bh, "marking uptodate");
			set_buffer_uptodate(bh);
			unlock_buffer(bh);

			BUFFER_TRACE(bh, "call ext3_journal_dirty_metadata");
			err = ext3_journal_dirty_metadata(handle, bh);
			if (err)
				break;

			parent = nr;
		}
	}
	if (n == num)
		return 0;

	/* Allocation failed, free what we already allocated */
	for (i = 1; i < keys; i++) {
		BUFFER_TRACE(branch[i].bh, "call journal_forget");
		ext3_journal_forget(handle, branch[i].bh);
	}
	for (i = 0; i < keys; i++)
		ext3_free_blocks(handle, inode, le32_to_cpu(branch[i].key), 1);
	return err;
}

/**
 *	ext3_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
 *		ext3_alloc_branch)
 *	@where: location of missing link
 *	@num:   number of blocks we are adding
 *
 *	This function verifies that chain (up to the missing link) had not
 *	changed, 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. Otherwise (== chain had been changed)
 *	we free the new blocks (forgetting their buffer_heads, indeed) and
 *	return -EAGAIN.
 */

static int ext3_splice_branch(handle_t *handle, struct inode *inode, long block,
			      Indirect chain[4], Indirect *where, int num)
{
	int i;
	int err = 0;
	struct ext3_inode_info *ei = EXT3_I(inode);

	/*
	 * If we're splicing into a [td]indirect block (as opposed to the
	 * inode) then we need to get write access to the [td]indirect block
	 * before the splice.
	 */
	if (where->bh) {
		BUFFER_TRACE(where->bh, "get_write_access");
		err = ext3_journal_get_write_access(handle, where->bh);
		if (err)
			goto err_out;
	}
	/* Verify that place we are splicing to is still there and vacant */

	/* Writer: pointers, ->i_next_alloc* */
	if (!verify_chain(chain, where-1) || *where->p)
		/* Writer: end */
		goto changed;

	/* That's it */

	*where->p = where->key;
	ei->i_next_alloc_block = block;
	ei->i_next_alloc_goal = le32_to_cpu(where[num-1].key);
	/* Writer: end */

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

	inode->i_ctime = CURRENT_TIME;
	ext3_mark_inode_dirty(handle, inode);

	/* had we spliced it onto indirect block? */
	if (where->bh) {
		/*
		 * akpm: If we spliced it onto an indirect block, we haven't
		 * altered the inode.  Note however that if it is being spliced
		 * onto an indirect block at the very end of the file (the
		 * file is growing) then we *will* alter the inode to reflect
		 * the new i_size.  But that is not done here - it is done in
		 * generic_commit_write->__mark_inode_dirty->ext3_dirty_inode.
		 */
		jbd_debug(5, "splicing indirect only\n");
		BUFFER_TRACE(where->bh, "call ext3_journal_dirty_metadata");
		err = ext3_journal_dirty_metadata(handle, where->bh);
		if (err) 
			goto err_out;
	} else {
		/*
		 * OK, we spliced it into the inode itself on a direct block.
		 * Inode was dirtied above.
		 */
		jbd_debug(5, "splicing direct\n");
	}
	return err;

changed:
	/*
	 * AKPM: if where[i].bh isn't part of the current updating
	 * transaction then we explode nastily.  Test this code path.
	 */
	jbd_debug(1, "the chain changed: try again\n");
	err = -EAGAIN;

err_out:
	for (i = 1; i < num; i++) {
		BUFFER_TRACE(where[i].bh, "call journal_forget");
		ext3_journal_forget(handle, where[i].bh);
	}
	/* For the normal collision cleanup case, we free up the blocks.
	 * On genuine filesystem errors we don't even think about doing
	 * that. */
	if (err == -EAGAIN)
		for (i = 0; i < num; i++)
			ext3_free_blocks(handle, inode, 
					 le32_to_cpu(where[i].key), 1);
	return err;
}

/*
 * 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.
 *
 * akpm: `handle' can be NULL if create == 0.
 *
 * The BKL may not be held on entry here.  Be sure to take it early.
 */

static int
ext3_get_block_handle(handle_t *handle, struct inode *inode, sector_t iblock,
		struct buffer_head *bh_result, int create, int extend_disksize)
{
	int err = -EIO;
	int offsets[4];
	Indirect chain[4];
	Indirect *partial;
	unsigned long goal;
	int left;
	int boundary = 0;
	int depth = ext3_block_to_path(inode, iblock, offsets, &boundary);
	struct ext3_inode_info *ei = EXT3_I(inode);

	J_ASSERT(handle != NULL || create == 0);

	if (depth == 0)
		goto out;

reread:
	partial = ext3_get_branch(inode, depth, offsets, chain, &err);

	/* Simplest case - block found, no allocation needed */
	if (!partial) {
		clear_buffer_new(bh_result);
got_it:
		map_bh(bh_result, inode->i_sb, le32_to_cpu(chain[depth-1].key));
		if (boundary)
			set_buffer_boundary(bh_result);
		/* Clean up and exit */
		partial = chain+depth-1; /* the whole chain */
		goto cleanup;
	}

	/* Next simple case - plain lookup or failed read of indirect block */
	if (!create || err == -EIO) {
cleanup:
		while (partial > chain) {
			BUFFER_TRACE(partial->bh, "call brelse");
			brelse(partial->bh);
			partial--;
		}
		BUFFER_TRACE(bh_result, "returned");
out:
		return err;
	}

	/*
	 * Indirect block might be removed by truncate while we were
	 * reading it. Handling of that case (forget what we've got and
	 * reread) is taken out of the main path.
	 */
	if (err == -EAGAIN)
		goto changed;

	goal = 0;
	down(&ei->truncate_sem);
	if (ext3_find_goal(inode, iblock, chain, partial, &goal) < 0) {
		up(&ei->truncate_sem);
		goto changed;
	}

	left = (chain + depth) - partial;

	/*
	 * Block out ext3_truncate while we alter the tree
	 */
	err = ext3_alloc_branch(handle, inode, left, goal,
					offsets+(partial-chain), partial);

	/* The ext3_splice_branch call will free and forget any buffers
	 * on the new chain if there is a failure, but that risks using
	 * up transaction credits, especially for bitmaps where the
	 * credits cannot be returned.  Can we handle this somehow?  We
	 * may need to return -EAGAIN upwards in the worst case.  --sct */
	if (!err)
		err = ext3_splice_branch(handle, inode, iblock, chain,
					 partial, left);
	/* i_disksize growing is protected by truncate_sem
	 * don't forget to protect it if you're about to implement
	 * concurrent ext3_get_block() -bzzz */
	if (!err && extend_disksize && inode->i_size > ei->i_disksize)
		ei->i_disksize = inode->i_size;
	up(&ei->truncate_sem);
	if (err == -EAGAIN)
		goto changed;
	if (err)
		goto cleanup;

	set_buffer_new(bh_result);
	goto got_it;

changed:
	while (partial > chain) {
		jbd_debug(1, "buffer chain changed, retrying\n");
		BUFFER_TRACE(partial->bh, "brelsing");
		brelse(partial->bh);
		partial--;
	}
	goto reread;
}

static int ext3_get_block(struct inode *inode, sector_t iblock,
			struct buffer_head *bh_result, int create)
{
	handle_t *handle = NULL;
	int ret;

	if (create) {
		handle = ext3_journal_current_handle();
		J_ASSERT(handle != 0);
	}
	ret = ext3_get_block_handle(handle, inode, iblock,
				bh_result, create, 1);
	return ret;
}

#define DIO_CREDITS (EXT3_RESERVE_TRANS_BLOCKS + 32)

static int
ext3_direct_io_get_blocks(struct inode *inode, sector_t iblock,
		unsigned long max_blocks, struct buffer_head *bh_result,
		int create)
{
	handle_t *handle = journal_current_handle();
	int ret = 0;

	if (!handle)
		goto get_block;		/* A read */