1 files changed, 89 insertions, 79 deletions

diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index f661d80474be..4b2f609f376d 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -58,6 +58,7 @@ static struct page *__get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index,
 		.rw = READ_SYNC | REQ_META | REQ_PRIO,
 		.blk_addr = index,
 		.encrypted_page = NULL,
+		.is_meta = is_meta,
 	};
 
 	if (unlikely(!is_meta))
@@ -74,8 +75,10 @@ repeat:
 	fio.page = page;
 
 	if (f2fs_submit_page_bio(&fio)) {
-		f2fs_put_page(page, 1);
-		goto repeat;
+		memset(page_address(page), 0, PAGE_SIZE);
+		f2fs_stop_checkpoint(sbi);
+		f2fs_bug_on(sbi, 1);
+		return page;
 	}
 
 	lock_page(page);
@@ -106,7 +109,8 @@ struct page *get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index)
 	return __get_meta_page(sbi, index, false);
 }
 
-bool is_valid_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type)
+bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
+					block_t blkaddr, int type)
 {
 	switch (type) {
 	case META_NAT:
@@ -126,8 +130,20 @@ bool is_valid_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type)
 			return false;
 		break;
 	case META_POR:
+	case DATA_GENERIC:
 		if (unlikely(blkaddr >= MAX_BLKADDR(sbi) ||
-			blkaddr < MAIN_BLKADDR(sbi)))
+			blkaddr < MAIN_BLKADDR(sbi))) {
+			if (type == DATA_GENERIC) {
+				f2fs_msg(sbi->sb, KERN_WARNING,
+					"access invalid blkaddr:%u", blkaddr);
+				WARN_ON(1);
+			}
+			return false;
+		}
+		break;
+	case META_GENERIC:
+		if (unlikely(blkaddr < SEG0_BLKADDR(sbi) ||
+			blkaddr >= MAIN_BLKADDR(sbi)))
 			return false;
 		break;
 	default:
@@ -151,6 +167,7 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
 		.type = META,
 		.rw = sync ? (READ_SYNC | REQ_META | REQ_PRIO) : READA,
 		.encrypted_page = NULL,
+		.is_meta = (type != META_POR),
 	};
 
 	if (unlikely(type == META_POR))
@@ -158,7 +175,7 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
 
 	for (; nrpages-- > 0; blkno++) {
 
-		if (!is_valid_blkaddr(sbi, blkno, type))
+		if (!f2fs_is_valid_blkaddr(sbi, blkno, type))
 			goto out;
 
 		switch (type) {
@@ -601,54 +618,73 @@ static void write_orphan_inodes(struct f2fs_sb_info *sbi, block_t start_blk)
 	}
 }
 
-static struct page *validate_checkpoint(struct f2fs_sb_info *sbi,
-				block_t cp_addr, unsigned long long *version)
+static int get_checkpoint_version(struct f2fs_sb_info *sbi, block_t cp_addr,
+		struct f2fs_checkpoint **cp_block, struct page **cp_page,
+		unsigned long long *version)
 {
-	struct page *cp_page_1, *cp_page_2 = NULL;
 	unsigned long blk_size = sbi->blocksize;
-	struct f2fs_checkpoint *cp_block;
-	unsigned long long cur_version = 0, pre_version = 0;
-	size_t crc_offset;
+	size_t crc_offset = 0;
 	__u32 crc = 0;
 
-	/* Read the 1st cp block in this CP pack */
-	cp_page_1 = get_meta_page(sbi, cp_addr);
+	*cp_page = get_meta_page(sbi, cp_addr);
+	*cp_block = (struct f2fs_checkpoint *)page_address(*cp_page);
 
-	/* get the version number */
-	cp_block = (struct f2fs_checkpoint *)page_address(cp_page_1);
-	crc_offset = le32_to_cpu(cp_block->checksum_offset);
-	if (crc_offset >= blk_size)
-		goto invalid_cp1;
-
-	crc = le32_to_cpu(*((__le32 *)((unsigned char *)cp_block + crc_offset)));
-	if (!f2fs_crc_valid(crc, cp_block, crc_offset))
-		goto invalid_cp1;
+	crc_offset = le32_to_cpu((*cp_block)->checksum_offset);
+	if (crc_offset >= blk_size) {
+		f2fs_put_page(*cp_page, 1);
+		f2fs_msg(sbi->sb, KERN_WARNING,
+			"invalid crc_offset: %zu", crc_offset);
+		return -EINVAL;
+	}
 
-	pre_version = cur_cp_version(cp_block);
+	crc = le32_to_cpu(*((__le32 *)((unsigned char *)*cp_block
+							+ crc_offset)));
+	if (!f2fs_crc_valid(crc, *cp_block, crc_offset)) {
+		f2fs_put_page(*cp_page, 1);
+		f2fs_msg(sbi->sb, KERN_WARNING, "invalid crc value");
+		return -EINVAL;
+	}
 
-	/* Read the 2nd cp block in this CP pack */
-	cp_addr += le32_to_cpu(cp_block->cp_pack_total_block_count) - 1;
-	cp_page_2 = get_meta_page(sbi, cp_addr);
+	*version = cur_cp_version(*cp_block);
+	return 0;
+}
 
-	cp_block = (struct f2fs_checkpoint *)page_address(cp_page_2);
-	crc_offset = le32_to_cpu(cp_block->checksum_offset);
-	if (crc_offset >= blk_size)
-		goto invalid_cp2;
+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;
 
-	crc = le32_to_cpu(*((__le32 *)((unsigned char *)cp_block + crc_offset)));
-	if (!f2fs_crc_valid(crc, cp_block, crc_offset))
-		goto invalid_cp2;
+	err = get_checkpoint_version(sbi, cp_addr, &cp_block,
+					&cp_page_1, version);
+	if (err)
+		return NULL;
+
+	if (le32_to_cpu(cp_block->cp_pack_total_block_count) >
+					sbi->blocks_per_seg) {
+		f2fs_msg(sbi->sb, KERN_WARNING,
+			"invalid cp_pack_total_block_count:%u",
+			le32_to_cpu(cp_block->cp_pack_total_block_count));
+		goto invalid_cp;
+	}
+	pre_version = *version;
 
-	cur_version = cur_cp_version(cp_block);
+	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_cp;
+	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:
+invalid_cp:
 	f2fs_put_page(cp_page_1, 1);
 	return NULL;
 }
@@ -696,6 +732,15 @@ int get_valid_checkpoint(struct f2fs_sb_info *sbi)
 	cp_block = (struct f2fs_checkpoint *)page_address(cur_page);
 	memcpy(sbi->ckpt, cp_block, blk_size);
 
+	if (cur_page == cp1)
+		sbi->cur_cp_pack = 1;
+	else
+		sbi->cur_cp_pack = 2;
+
+	/* Sanity checking of checkpoint */
+	if (sanity_check_ckpt(sbi))
+		goto free_fail_no_cp;
+
 	if (cp_blks <= 1)
 		goto done;
 
@@ -717,6 +762,9 @@ done:
 	f2fs_put_page(cp2, 1);
 	return 0;
 
+free_fail_no_cp:
+	f2fs_put_page(cp1, 1);
+	f2fs_put_page(cp2, 1);
 fail_no_cp:
 	kfree(sbi->ckpt);
 	return -EINVAL;
@@ -767,24 +815,6 @@ out:
 	f2fs_trace_pid(page);
 }
 
-void add_dirty_dir_inode(struct inode *inode)
-{
-	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	struct inode_entry *new =
-			f2fs_kmem_cache_alloc(inode_entry_slab, GFP_NOFS);
-	int ret = 0;
-
-	new->inode = inode;
-	INIT_LIST_HEAD(&new->list);
-
-	spin_lock(&sbi->dir_inode_lock);
-	ret = __add_dirty_inode(inode, new);
-	spin_unlock(&sbi->dir_inode_lock);
-
-	if (ret)
-		kmem_cache_free(inode_entry_slab, new);
-}
-
 void remove_dirty_dir_inode(struct inode *inode)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
@@ -807,12 +837,6 @@ void remove_dirty_dir_inode(struct inode *inode)
 	stat_dec_dirty_dir(sbi);
 	spin_unlock(&sbi->dir_inode_lock);
 	kmem_cache_free(inode_entry_slab, entry);
-
-	/* Only from the recovery routine */
-	if (is_inode_flag_set(F2FS_I(inode), FI_DELAY_IPUT)) {
-		clear_inode_flag(F2FS_I(inode), FI_DELAY_IPUT);
-		iput(inode);
-	}
 }
 
 void sync_dirty_dir_inodes(struct f2fs_sb_info *sbi)
@@ -922,7 +946,6 @@ static void wait_on_all_pages_writeback(struct f2fs_sb_info *sbi)
 static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 {
 	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
-	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	unsigned long orphan_num = sbi->im[ORPHAN_INO].ino_num;
 	nid_t last_nid = nm_i->next_scan_nid;
@@ -931,15 +954,6 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	__u32 crc32 = 0;
 	int i;
 	int cp_payload_blks = __cp_payload(sbi);
-	block_t discard_blk = NEXT_FREE_BLKADDR(sbi, curseg);
-	bool invalidate = false;
-
-	/*
-	 * This avoids to conduct wrong roll-forward operations and uses
-	 * metapages, so should be called prior to sync_meta_pages below.
-	 */
-	if (discard_next_dnode(sbi, discard_blk))
-		invalidate = true;
 
 	/* Flush all the NAT/SIT pages */
 	while (get_pages(sbi, F2FS_DIRTY_META)) {
@@ -1016,6 +1030,9 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	if (is_sbi_flag_set(sbi, SBI_NEED_FSCK))
 		set_ckpt_flags(ckpt, CP_FSCK_FLAG);
 
+	/* set this flag to activate crc|cp_ver for recovery */
+	set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG);
+
 	/* update SIT/NAT bitmap */
 	get_sit_bitmap(sbi, __bitmap_ptr(sbi, SIT_BITMAP));
 	get_nat_bitmap(sbi, __bitmap_ptr(sbi, NAT_BITMAP));
@@ -1025,7 +1042,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 				le32_to_cpu(ckpt->checksum_offset)))
 				= cpu_to_le32(crc32);
 
-	start_blk = __start_cp_addr(sbi);
+	start_blk = __start_cp_next_addr(sbi);
 
 	/* need to wait for end_io results */
 	wait_on_all_pages_writeback(sbi);
@@ -1073,14 +1090,6 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	/* wait for previous submitted meta pages writeback */
 	wait_on_all_pages_writeback(sbi);
 
-	/*
-	 * invalidate meta page which is used temporarily for zeroing out
-	 * block at the end of warm node chain.
-	 */
-	if (invalidate)
-		invalidate_mapping_pages(META_MAPPING(sbi), discard_blk,
-								discard_blk);
-
 	release_dirty_inode(sbi);
 
 	if (unlikely(f2fs_cp_error(sbi)))
@@ -1088,6 +1097,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 
 	clear_prefree_segments(sbi, cpc);
 	clear_sbi_flag(sbi, SBI_IS_DIRTY);
+	__set_cp_next_pack(sbi);
 }
 
 /*