extents.c

linux 内核源代码

		/*
		 * truncate to zero freed all the tree,
		 * so we need to correct eh_depth
		 */
		err = ext4_ext_get_access(handle, inode, path);
		if (err == 0) {
			ext_inode_hdr(inode)->eh_depth = 0;
			ext_inode_hdr(inode)->eh_max =
				cpu_to_le16(ext4_ext_space_root(inode));
			err = ext4_ext_dirty(handle, inode, path);
		}
	}
out:
	ext4_ext_tree_changed(inode);
	ext4_ext_drop_refs(path);
	kfree(path);
	ext4_journal_stop(handle);

	return err;
}

/*
 * called at mount time
 */
void ext4_ext_init(struct super_block *sb)
{
	/*
	 * possible initialization would be here
	 */

	if (test_opt(sb, EXTENTS)) {
		printk("EXT4-fs: file extents enabled");
#ifdef AGGRESSIVE_TEST
		printk(", aggressive tests");
#endif
#ifdef CHECK_BINSEARCH
		printk(", check binsearch");
#endif
#ifdef EXTENTS_STATS
		printk(", stats");
#endif
		printk("\n");
#ifdef EXTENTS_STATS
		spin_lock_init(&EXT4_SB(sb)->s_ext_stats_lock);
		EXT4_SB(sb)->s_ext_min = 1 << 30;
		EXT4_SB(sb)->s_ext_max = 0;
#endif
	}
}

/*
 * called at umount time
 */
void ext4_ext_release(struct super_block *sb)
{
	if (!test_opt(sb, EXTENTS))
		return;

#ifdef EXTENTS_STATS
	if (EXT4_SB(sb)->s_ext_blocks && EXT4_SB(sb)->s_ext_extents) {
		struct ext4_sb_info *sbi = EXT4_SB(sb);
		printk(KERN_ERR "EXT4-fs: %lu blocks in %lu extents (%lu ave)\n",
			sbi->s_ext_blocks, sbi->s_ext_extents,
			sbi->s_ext_blocks / sbi->s_ext_extents);
		printk(KERN_ERR "EXT4-fs: extents: %lu min, %lu max, max depth %lu\n",
			sbi->s_ext_min, sbi->s_ext_max, sbi->s_depth_max);
	}
#endif
}

/*
 * This function is called by ext4_ext_get_blocks() if someone tries to write
 * to an uninitialized extent. It may result in splitting the uninitialized
 * extent into multiple extents (upto three - one initialized and two
 * uninitialized).
 * There are three possibilities:
 *   a> There is no split required: Entire extent should be initialized
 *   b> Splits in two extents: Write is happening at either end of the extent
 *   c> Splits in three extents: Somone is writing in middle of the extent
 */
int ext4_ext_convert_to_initialized(handle_t *handle, struct inode *inode,
					struct ext4_ext_path *path,
					ext4_fsblk_t iblock,
					unsigned long max_blocks)
{
	struct ext4_extent *ex, newex;
	struct ext4_extent *ex1 = NULL;
	struct ext4_extent *ex2 = NULL;
	struct ext4_extent *ex3 = NULL;
	struct ext4_extent_header *eh;
	unsigned int allocated, ee_block, ee_len, depth;
	ext4_fsblk_t newblock;
	int err = 0;
	int ret = 0;

	depth = ext_depth(inode);
	eh = path[depth].p_hdr;
	ex = path[depth].p_ext;
	ee_block = le32_to_cpu(ex->ee_block);
	ee_len = ext4_ext_get_actual_len(ex);
	allocated = ee_len - (iblock - ee_block);
	newblock = iblock - ee_block + ext_pblock(ex);
	ex2 = ex;

	/* ex1: ee_block to iblock - 1 : uninitialized */
	if (iblock > ee_block) {
		ex1 = ex;
		ex1->ee_len = cpu_to_le16(iblock - ee_block);
		ext4_ext_mark_uninitialized(ex1);
		ex2 = &newex;
	}
	/*
	 * for sanity, update the length of the ex2 extent before
	 * we insert ex3, if ex1 is NULL. This is to avoid temporary
	 * overlap of blocks.
	 */
	if (!ex1 && allocated > max_blocks)
		ex2->ee_len = cpu_to_le16(max_blocks);
	/* ex3: to ee_block + ee_len : uninitialised */
	if (allocated > max_blocks) {
		unsigned int newdepth;
		ex3 = &newex;
		ex3->ee_block = cpu_to_le32(iblock + max_blocks);
		ext4_ext_store_pblock(ex3, newblock + max_blocks);
		ex3->ee_len = cpu_to_le16(allocated - max_blocks);
		ext4_ext_mark_uninitialized(ex3);
		err = ext4_ext_insert_extent(handle, inode, path, ex3);
		if (err)
			goto out;
		/*
		 * The depth, and hence eh & ex might change
		 * as part of the insert above.
		 */
		newdepth = ext_depth(inode);
		if (newdepth != depth) {
			depth = newdepth;
			path = ext4_ext_find_extent(inode, iblock, NULL);
			if (IS_ERR(path)) {
				err = PTR_ERR(path);
				path = NULL;
				goto out;
			}
			eh = path[depth].p_hdr;
			ex = path[depth].p_ext;
			if (ex2 != &newex)
				ex2 = ex;
		}
		allocated = max_blocks;
	}
	/*
	 * If there was a change of depth as part of the
	 * insertion of ex3 above, we need to update the length
	 * of the ex1 extent again here
	 */
	if (ex1 && ex1 != ex) {
		ex1 = ex;
		ex1->ee_len = cpu_to_le16(iblock - ee_block);
		ext4_ext_mark_uninitialized(ex1);
		ex2 = &newex;
	}
	/* ex2: iblock to iblock + maxblocks-1 : initialised */
	ex2->ee_block = cpu_to_le32(iblock);
	ext4_ext_store_pblock(ex2, newblock);
	ex2->ee_len = cpu_to_le16(allocated);
	if (ex2 != ex)
		goto insert;
	err = ext4_ext_get_access(handle, inode, path + depth);
	if (err)
		goto out;
	/*
	 * New (initialized) extent starts from the first block
	 * in the current extent. i.e., ex2 == ex
	 * We have to see if it can be merged with the extent
	 * on the left.
	 */
	if (ex2 > EXT_FIRST_EXTENT(eh)) {
		/*
		 * To merge left, pass "ex2 - 1" to try_to_merge(),
		 * since it merges towards right _only_.
		 */
		ret = ext4_ext_try_to_merge(inode, path, ex2 - 1);
		if (ret) {
			err = ext4_ext_correct_indexes(handle, inode, path);
			if (err)
				goto out;
			depth = ext_depth(inode);
			ex2--;
		}
	}
	/*
	 * Try to Merge towards right. This might be required
	 * only when the whole extent is being written to.
	 * i.e. ex2 == ex and ex3 == NULL.
	 */
	if (!ex3) {
		ret = ext4_ext_try_to_merge(inode, path, ex2);
		if (ret) {
			err = ext4_ext_correct_indexes(handle, inode, path);
			if (err)
				goto out;
		}
	}
	/* Mark modified extent as dirty */
	err = ext4_ext_dirty(handle, inode, path + depth);
	goto out;
insert:
	err = ext4_ext_insert_extent(handle, inode, path, &newex);
out:
	return err ? err : allocated;
}

int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
			ext4_fsblk_t iblock,
			unsigned long max_blocks, struct buffer_head *bh_result,
			int create, int extend_disksize)
{
	struct ext4_ext_path *path = NULL;
	struct ext4_extent_header *eh;
	struct ext4_extent newex, *ex;
	ext4_fsblk_t goal, newblock;
	int err = 0, depth, ret;
	unsigned long allocated = 0;

	__clear_bit(BH_New, &bh_result->b_state);
	ext_debug("blocks %d/%lu requested for inode %u\n", (int) iblock,
			max_blocks, (unsigned) inode->i_ino);
	mutex_lock(&EXT4_I(inode)->truncate_mutex);

	/* check in cache */
	goal = ext4_ext_in_cache(inode, iblock, &newex);
	if (goal) {
		if (goal == EXT4_EXT_CACHE_GAP) {
			if (!create) {
				/*
				 * block isn't allocated yet and
				 * user doesn't want to allocate it
				 */
				goto out2;
			}
			/* we should allocate requested block */
		} else if (goal == EXT4_EXT_CACHE_EXTENT) {
			/* block is already allocated */
			newblock = iblock
				   - le32_to_cpu(newex.ee_block)
				   + ext_pblock(&newex);
			/* number of remaining blocks in the extent */
			allocated = le16_to_cpu(newex.ee_len) -
					(iblock - le32_to_cpu(newex.ee_block));
			goto out;
		} else {
			BUG();
		}
	}

	/* find extent for this block */
	path = ext4_ext_find_extent(inode, iblock, NULL);
	if (IS_ERR(path)) {
		err = PTR_ERR(path);
		path = NULL;
		goto out2;
	}

	depth = ext_depth(inode);

	/*
	 * consistent leaf must not be empty;
	 * this situation is possible, though, _during_ tree modification;
	 * this is why assert can't be put in ext4_ext_find_extent()
	 */
	BUG_ON(path[depth].p_ext == NULL && depth != 0);
	eh = path[depth].p_hdr;

	ex = path[depth].p_ext;
	if (ex) {
		unsigned long ee_block = le32_to_cpu(ex->ee_block);
		ext4_fsblk_t ee_start = ext_pblock(ex);
		unsigned short ee_len;

		/*
		 * Uninitialized extents are treated as holes, except that
		 * we split out initialized portions during a write.
		 */
		ee_len = ext4_ext_get_actual_len(ex);
		/* if found extent covers block, simply return it */
		if (iblock >= ee_block && iblock < ee_block + ee_len) {
			newblock = iblock - ee_block + ee_start;
			/* number of remaining blocks in the extent */
			allocated = ee_len - (iblock - ee_block);
			ext_debug("%d fit into %lu:%d -> %llu\n", (int) iblock,
					ee_block, ee_len, newblock);

			/* Do not put uninitialized extent in the cache */
			if (!ext4_ext_is_uninitialized(ex)) {
				ext4_ext_put_in_cache(inode, ee_block,
							ee_len, ee_start,
							EXT4_EXT_CACHE_EXTENT);
				goto out;
			}
			if (create == EXT4_CREATE_UNINITIALIZED_EXT)
				goto out;
			if (!create)
				goto out2;

			ret = ext4_ext_convert_to_initialized(handle, inode,
								path, iblock,
								max_blocks);
			if (ret <= 0)
				goto out2;
			else
				allocated = ret;
			goto outnew;
		}
	}

	/*
	 * requested block isn't allocated yet;
	 * we couldn't try to create block if create flag is zero
	 */
	if (!create) {
		/*
		 * put just found gap into cache to speed up
		 * subsequent requests
		 */
		ext4_ext_put_gap_in_cache(inode, path, iblock);
		goto out2;
	}
	/*
	 * Okay, we need to do block allocation.  Lazily initialize the block
	 * allocation info here if necessary.
	 */
	if (S_ISREG(inode->i_mode) && (!EXT4_I(inode)->i_block_alloc_info))
		ext4_init_block_alloc_info(inode);

	/* allocate new block */
	goal = ext4_ext_find_goal(inode, path, iblock);

	/*
	 * See if request is beyond maximum number of blocks we can have in
	 * a single extent. For an initialized extent this limit is
	 * EXT_INIT_MAX_LEN and for an uninitialized extent this limit is
	 * EXT_UNINIT_MAX_LEN.
	 */
	if (max_blocks > EXT_INIT_MAX_LEN &&
	    create != EXT4_CREATE_UNINITIALIZED_EXT)
		max_blocks = EXT_INIT_MAX_LEN;
	else if (max_blocks > EXT_UNINIT_MAX_LEN &&
		 create == EXT4_CREATE_UNINITIALIZED_EXT)
		max_blocks = EXT_UNINIT_MAX_LEN;

	/* Check if we can really insert (iblock)::(iblock+max_blocks) extent */
	newex.ee_block = cpu_to_le32(iblock);
	newex.ee_len = cpu_to_le16(max_blocks);
	err = ext4_ext_check_overlap(inode, &newex, path);
	if (err)
		allocated = le16_to_cpu(newex.ee_len);
	else
		allocated = max_blocks;
	newblock = ext4_new_blocks(handle, inode, goal, &allocated, &err);
	if (!newblock)
		goto out2;
	ext_debug("allocate new block: goal %llu, found %llu/%lu\n",
			goal, newblock, allocated);

	/* try to insert new extent into found leaf and return */
	ext4_ext_store_pblock(&newex, newblock);
	newex.ee_len = cpu_to_le16(allocated);
	if (create == EXT4_CREATE_UNINITIALIZED_EXT)  /* Mark uninitialized */
		ext4_ext_mark_uninitialized(&newex);
	err = ext4_ext_insert_extent(handle, inode, path, &newex);
	if (err) {
		/* free data blocks we just allocated */
		ext4_free_blocks(handle, inode, ext_pblock(&newex),
					le16_to_cpu(newex.ee_len));
		goto out2;
	}

	if (extend_disksize && inode->i_size > EXT4_I(inode)->i_disksize)
		EXT4_I(inode)->i_disksize = inode->i_size;

	/* previous routine could use block we allocated */
	newblock = ext_pblock(&newex);
outnew:
	__set_bit(BH_New, &bh_result->b_state);

	/* Cache only when it is _not_ an uninitialized extent */
	if (create != EXT4_CREATE_UNINITIALIZED_EXT)
		ext4_ext_put_in_cache(inode, iblock, allocated, newblock,
						EXT4_EXT_CACHE_EXTENT);
out:
	if (allocated > max_blocks)
		allocated = max_blocks;
	ext4_ext_show_leaf(inode, path);
	__set_bit(BH_Mapped, &bh_result->b_state);
	bh_result->b_bdev = inode->i_sb->s_bdev;
	bh_result->b_blocknr = newblock;
out2:
	if (path) {
		ext4_ext_drop_refs(path);
		kfree(path);
	}
	mutex_unlock(&EXT4_I(inode)->truncate_mutex);

	return err ? err : allocated;
}

void ext4_ext_truncate(struct inode * inode, struct page *page)
{
	struct address_space *mapping = inode->i_mapping;
	struct super_block *sb = inode->i_sb;
	unsigned long last_block;
	handle_t *handle;
	int err = 0;

	/*
	 * probably first extent we're gonna free will be last in block
	 */
	err = ext4_writepage_trans_blocks(inode) + 3;
	handle = ext4_journal_start(inode, err);
	if (IS_ERR(handle)) {
		if (page) {
			clear_highpage(page);
			flush_dcache_page(page);
			unlock_page(page);
			page_cache_release(page);
		}
		return;
	}

	if (page)
		ext4_block_truncate_page(handle, page, mapping, inode->i_size);

	mutex_lock(&EXT4_I(inode)->truncate_mutex);
	ext4_ext_invalidate_cache(inode);

	/*
	 * TODO: optimization is possible here.
	 * Probably we need not scan at all,
	 * because page truncation is enough.
	 */
	if (ext4_orphan_add(handle, inode))
		goto out_stop;

	/* we have to know where to truncate from in crash case */
	EXT4_I(inode)->i_disksize = inode->i_size;
	ext4_mark_inode_dirty(handle, inode);

	last_block = (inode->i_size + sb->s_blocksize - 1)
			>> EXT4_BLOCK_SIZE_BITS(sb);
	err = ext4_ext_remove_space(inode, last_block);

	/* In a multi-transaction truncate, we only make the final
	 * transaction synchronous.
	 */
	if (IS_SYNC(inode))
		handle->h_sync = 1;

out_stop:
	/*
	 * If this was a simple ftruncate() and the file will remain alive,
	 * then we need to clear up the orphan record which we created above.
	 * However, if this was a real unlink then we were called by
	 * ext4_delete_inode(), and we allow that function to clean up the
	 * orphan info for us.
	 */
	if (inode->i_nlink)
		ext4_orphan_del(handle, inode);

	mutex_unlock(&EXT4_I(inode)->truncate_mutex);
	ext4_journal_stop(handle);
}

/*
 * ext4_ext_writepage_trans_blocks:
 * calculate max number of blocks we could modify
 * in order to allocate new block for an inode
 */
int ext4_ext_writepage_trans_blocks(struct inode *inode, int num)
{
	int needed;

	needed = ext4_ext_calc_credits_for_insert(inode, NULL);

	/* caller wants to allocate num blocks, but note it includes sb */
	needed = needed * num - (num - 1);

#ifdef CONFIG_QUOTA
	needed += 2 * EXT4_QUOTA_TRANS_BLOCKS(inode->i_sb);
#endif

	return needed;
}

/*
 * preallocate space for a file. This implements ext4's fallocate inode
 * operation, which gets called from sys_fallocate system call.
 * For block-mapped files, posix_fallocate should fall back to the method
 * of writing zeroes to the required new blocks (the same behavior which is
 * expected for file systems which do not support fallocate() system call).
 */
long ext4_fallocate(struct inode *inode, int mode, loff_t offset, loff_t len)
{
	handle_t *handl