f2fs系列文章——cp pack的组成

    f2fs将分区分为super block、cp pack、sit、nat、ssa、main area四个区域，除了cp pack外，其他的区域的组成都比较简单，基本只有一种数据结构，只有cp pack由于承载了check point的功能，所以其组成比较复杂，这篇文章就cp pack的组成来详细讲述。

    cp pack是由f2fs_checkpoint、sit_version_bitmap、nat_version_bitmap、orphan inode、data summary、node summary（可能没有）、f2fs_checkpoint来组成。下面将从mount和do_checkpoint两个方位来对cp pack的组成进行详细讲述。

    下面是在do_checkpoint的时候关于cp pack的写入过程

static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
{

	...

	start_blk = __start_cp_addr(sbi);

	...

	update_meta_page(sbi, ckpt, start_blk++);

	for (i = 1; i < 1 + cp_payload_blks; i++)
		update_meta_page(sbi, (char *)ckpt + i * F2FS_BLKSIZE, start_blk++);

	if (orphan_num) {
		write_orphan_inodes(sbi, start_blk);
		start_blk += orphan_blocks;
	}

	write_data_summaries(sbi, start_blk);
	start_blk += data_sum_blocks;

	...

	if (__remain_node_summaries(cpc->reason)) {
		write_node_summaries(sbi, start_blk);
		start_blk += NR_CURSEG_NODE_TYPE;
	}

	update_meta_page(sbi, ckpt, start_blk);

	...

}

        下面是关于mount时候的读入过程。

int get_valid_checkpoint(struct f2fs_sb_info *sbi)
{
	struct f2fs_checkpoint *cp_block;
	struct f2fs_super_block *fsb = sbi->raw_super;
	struct page *cp1, *cp2, *cur_page;
	unsigned long blk_size = sbi->blocksize;
	unsigned long long cp1_version = 0, cp2_version = 0;
	unsigned long long cp_start_blk_no;
	unsigned int cp_blks = 1 + __cp_payload(sbi);
	block_t cp_blk_no;
	int i;

	sbi->ckpt = kzalloc(cp_blks * blk_size, GFP_KERNEL);
	if (!sbi->ckpt)
		return -ENOMEM;

	cp_start_blk_no = le32_to_cpu(fsb->cp_blkaddr);
	cp1 = validate_checkpoint(sbi, cp_start_blk_no, &cp1_version);

	cp_start_blk_no += ((unsigned long long)1) << le32_to_cpu(fsb->log_blocks_per_seg);
	cp2 = validate_checkpoint(sbi, cp_start_blk_no, &cp2_version);

	if (cp1 && cp2) {
		if (ver_after(cp2_version, cp1_version))
			cur_page = cp2;
		else
			cur_page = cp1;
	} else if (cp1) {
		cur_page = cp1;
	} else if (cp2) {
		cur_page = cp2;
	} else {
		goto fail_no_cp;
	}

	cp_block = (struct f2fs_checkpoint *)page_address(cur_page);
	memcpy(sbi->ckpt, cp_block, blk_size);

	if (sanity_check_ckpt(sbi))
		goto fail_no_cp;

	if (cp_blks <= 1)
		goto done;

	cp_blk_no = le32_to_cpu(fsb->cp_blkaddr);
	if (cur_page == cp2)
		cp_blk_no += 1 << le32_to_cpu(fsb->log_blocks_per_seg);

	for (i = 1; i < cp_blks; i++) {
		void *sit_bitmap_ptr;
		unsigned char *ckpt = (unsigned char *)sbi->ckpt;
		cur_page = get_meta_page(sbi, cp_blk_no + i);
		sit_bitmap_ptr = page_address(cur_page);
		memcpy(ckpt + i * blk_size, sit_bitmap_ptr, blk_size);
		f2fs_put_page(cur_page, 1);
	}
done:
	f2fs_put_page(cp1, 1);
	f2fs_put_page(cp2, 1);
	return 0;

fail_no_cp:
	kfree(sbi->ckpt);
	return -EINVAL;
}

static struct page *validate_checkpoint(struct f2fs_sb_info *sbi,
				block_t cp_addr, unsigned long long *version)
{
	struct page *cp_page_1 = NULL, *cp_page_2 = NULL;
	struct f2fs_checkpoint *cp_block = NULL;
	unsigned long long cur_version = 0, pre_version = 0;
	int err;

	err = get_checkpoint_version(sbi, cp_addr, &cp_block, &cp_page_1, version);
	if (err)
		goto invalid_cp1;
	pre_version = *version;

	cp_addr += le32_to_cpu(cp_block->cp_pack_total_block_count) - 1;
	err = get_checkpoint_version(sbi, cp_addr, &cp_block, &cp_page_2, version);
	if (err)
		goto invalid_cp2;
	cur_version = *version;

	if (cur_version == pre_version) {
		*version = cur_version;
		f2fs_put_page(cp_page_2, 1);
		return cp_page_1;
	}
invalid_cp2:
	f2fs_put_page(cp_page_2, 1);
invalid_cp1:
	f2fs_put_page(cp_page_1, 1);
	return NULL;
}

int recover_orphan_inodes(struct f2fs_sb_info *sbi)
{
	block_t start_blk, orphan_blocks, i, j;
	int err;

	if (!is_set_ckpt_flags(sbi, CP_ORPHAN_PRESENT_FLAG))
		return 0;

	start_blk = __start_cp_addr(sbi) + 1 + __cp_payload(sbi);
	orphan_blocks = __start_sum_addr(sbi) - 1 - __cp_payload(sbi);

	ra_meta_pages(sbi, start_blk, orphan_blocks, META_CP, true);

	for (i = 0; i < orphan_blocks; i++) {
		struct page *page = get_meta_page(sbi, start_blk + i);
		struct f2fs_orphan_block *orphan_blk;

		orphan_blk = (struct f2fs_orphan_block *)page_address(page);
		for (j = 0; j < le32_to_cpu(orphan_blk->entry_count); j++) {
			nid_t ino = le32_to_cpu(orphan_blk->ino[j]);
			err = recover_orphan_inode(sbi, ino);
			if (err) {
				f2fs_put_page(page, 1);
				return err;
			}
		}
		f2fs_put_page(page, 1);
	}

	clear_ckpt_flags(sbi, CP_ORPHAN_PRESENT_FLAG);
	return 0;
}

static int restore_curseg_summaries(struct f2fs_sb_info *sbi)
{
	int type = CURSEG_HOT_DATA;
	int err;

	if (is_set_ckpt_flags(sbi, CP_COMPACT_SUM_FLAG)) {
		int npages = npages_for_summary_flush(sbi, true);

		if (npages >= 2)
			ra_meta_pages(sbi, start_sum_block(sbi), npages, META_CP, true);

		if (read_compacted_summaries(sbi))
			return -EINVAL;
		type = CURSEG_HOT_NODE;
	}

	if (__exist_node_summaries(sbi))
		ra_meta_pages(sbi, sum_blk_addr(sbi, NR_CURSEG_TYPE, type),
					NR_CURSEG_TYPE - type, META_CP, true);

	for (; type <= CURSEG_COLD_NODE; type++) {
		err = read_normal_summaries(sbi, type);
		if (err)
			return err;
	}

	return 0;
}

static int read_compacted_summaries(struct f2fs_sb_info *sbi)
{
	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
	struct curseg_info *seg_i;
	unsigned char *kaddr;
	struct page *page;
	block_t start;
	int i, j, offset;

	start = start_sum_block(sbi);

	page = get_meta_page(sbi, start++);
	kaddr = (unsigned char *)page_address(page);

	seg_i = CURSEG_I(sbi, CURSEG_HOT_DATA);
	memcpy(seg_i->journal, kaddr, SUM_JOURNAL_SIZE);

	seg_i = CURSEG_I(sbi, CURSEG_COLD_DATA);
	memcpy(seg_i->journal, kaddr + SUM_JOURNAL_SIZE, SUM_JOURNAL_SIZE);
	offset = 2 * SUM_JOURNAL_SIZE;

	for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) {
		unsigned short blk_off;
		unsigned int segno;

		seg_i = CURSEG_I(sbi, i);
		segno = le32_to_cpu(ckpt->cur_data_segno[i]);
		blk_off = le16_to_cpu(ckpt->cur_data_blkoff[i]);
		seg_i->next_segno = segno;
		reset_curseg(sbi, i, 0);
		seg_i->alloc_type = ckpt->alloc_type[i];
		seg_i->next_blkoff = blk_off;

		if (seg_i->alloc_type == SSR)
			blk_off = sbi->blocks_per_seg;

		for (j = 0; j < blk_off; j++) {
			struct f2fs_summary *s;
			s = (struct f2fs_summary *)(kaddr + offset);
			seg_i->sum_blk->entries[j] = *s;
			offset += SUMMARY_SIZE;
			if (offset + SUMMARY_SIZE <= PAGE_SIZE - SUM_FOOTER_SIZE)
				continue;

			f2fs_put_page(page, 1);
			page = NULL;

			page = get_meta_page(sbi, start++);
			kaddr = (unsigned char *)page_address(page);
			offset = 0;
		}
	}
	f2fs_put_page(page, 1);
	return 0;
}

static int read_normal_summaries(struct f2fs_sb_info *sbi, int type)
{
	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
	struct f2fs_summary_block *sum;
	struct curseg_info *curseg;
	struct page *new;
	unsigned short blk_off;
	unsigned int segno = 0;
	block_t blk_addr = 0;

	if (IS_DATASEG(type)) {
		segno = le32_to_cpu(ckpt->cur_data_segno[type]);
		blk_off = le16_to_cpu(ckpt->cur_data_blkoff[type - CURSEG_HOT_DATA]);
		if (__exist_node_summaries(sbi))
			blk_addr = sum_blk_addr(sbi, NR_CURSEG_TYPE, type);
		else
			blk_addr = sum_blk_addr(sbi, NR_CURSEG_DATA_TYPE, type);
	} else {
		segno = le32_to_cpu(ckpt->cur_node_segno[type - CURSEG_HOT_NODE]);
		blk_off = le16_to_cpu(ckpt->cur_node_blkoff[type - CURSEG_HOT_NODE]);
		if (__exist_node_summaries(sbi))
			blk_addr = sum_blk_addr(sbi, NR_CURSEG_NODE_TYPE, type - CURSEG_HOT_NODE);
		else
			blk_addr = GET_SUM_BLOCK(sbi, segno);
	}

	new = get_meta_page(sbi, blk_addr);
	sum = (struct f2fs_summary_block *)page_address(new);

	if (IS_NODESEG(type)) {
		if (__exist_node_summaries(sbi)) {
			struct f2fs_summary *ns = &sum->entries[0];
			int i;
			for (i = 0; i < sbi->blocks_per_seg; i++, ns++) {
				ns->version = 0;
				ns->ofs_in_node = 0;
			}
		} else {
			int err;

			err = restore_node_summary(sbi, segno, sum);
			if (err) {
				f2fs_put_page(new, 1);
				return err;
			}
		}
	}

	curseg = CURSEG_I(sbi, type);
	mutex_lock(&curseg->curseg_mutex);

	down_write(&curseg->journal_rwsem);
	memcpy(curseg->journal, &sum->journal, SUM_JOURNAL_SIZE);
	up_write(&curseg->journal_rwsem);

	memcpy(curseg->sum_blk->entries, sum->entries, SUM_ENTRY_SIZE);
	memcpy(&curseg->sum_blk->footer, &sum->footer, SUM_FOOTER_SIZE);
	curseg->next_segno = segno;
	reset_curseg(sbi, type, 0);
	curseg->alloc_type = ckpt->alloc_type[type];
	curseg->next_blkoff = blk_off;
	mutex_unlock(&curseg->curseg_mutex);
	f2fs_put_page(new, 1);
	return 0;
}

        以上是关于各部分的写入和读入过程，我们从上面可以看出各个部分的起始地址和长度的计算过程。

sba_checkpoint = f2fs_super_block->cp_blkaddr

sba_sit_version_bitmap = f2fs_super_block->cp_blkaddr+ F2FS_BLKSIZE （cp_payload > 0）

                                      =&(f2fs_checkpoint -> sit_nat_version_bitmap) （cp_payload= 0）

sba_nat_version_bitmap = &(f2fs_checkpoint-> sit_nat_version_bitmap) （cp_payload > 0）

                                        = &(f2fs_checkpoint -> sit_nat_version_bitmap)

                                        + sit_ver_bitmap_bytesize （cp_payload= 0）

sba_orphan_inode = f2fs_super_block->cp_blkaddr+ 1 + cp_payload

sba_summary = f2fs_checkpoint->cp_pack_start_sum

sba_checkpoint2 = f2fs_super_block->cp_blkaddr

                            + f2fs_checkpoint->cp_pack_total_block_count- 1

length_checkpoint = sizeof(structf2fs_checkpoint)

length_sit_version_bitmap = f2fs_checkpoint->sit_ver_bitmap_bytesize

length_nat_version_bitmap = f2fs_checkpoint->nat_ver_bitmap_bytesize

length_orphan_inode = f2fs_checkpoint->cp_pack_start_sum- 1 - cp_payload

length_summary = cp_block->cp_pack_total_block_count)- 1

- f2fs_checkpoint->cp_pack_start_sum

length_checkpoint2 = sizeof(structf2fs_checkpoint)