[PATCH 1/4] f2fs: cover large section in sanity check of super

[PATCH 1/4] f2fs: cover large section in sanity check of super

[Jaegeuk Kim]

This patch fixes the bug which does not cover a large section case when checking
the sanity of superblock.
If f2fs detects misalignment, it will fix the superblock during the mount time,
so it doesn't need to trigger fsck.f2fs further.

Reported-by: Matthias Prager <linux@matthiasprager.de>
Reported-by: David Gnedt <david.gnedt@davizone.at>
Cc: stable 4.5+ <stable@vger.kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/super.c | 102 ++++++++++++++++++++++++++++++++++++--------------------
 1 file changed, 65 insertions(+), 37 deletions(-)

diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 15bb81f..5afb4a6 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -984,9 +984,25 @@ static loff_t max_file_blocks(void)
 	return result;
 }
 
+static int __f2fs_commit_super(struct buffer_head *bh,
+			struct f2fs_super_block *super)
+{
+	lock_buffer(bh);
+	if (super)
+		memcpy(bh->b_data + F2FS_SUPER_OFFSET, super, sizeof(*super));
+	set_buffer_uptodate(bh);
+	set_buffer_dirty(bh);
+	unlock_buffer(bh);
+
+	/* it's rare case, we can do fua all the time */
+	return __sync_dirty_buffer(bh, WRITE_FLUSH_FUA);
+}
+
 static inline bool sanity_check_area_boundary(struct super_block *sb,
-					struct f2fs_super_block *raw_super)
+					struct buffer_head *bh)
 {
+	struct f2fs_super_block *raw_super = (struct f2fs_super_block *)
+					(bh->b_data + F2FS_SUPER_OFFSET);
 	u32 segment0_blkaddr = le32_to_cpu(raw_super->segment0_blkaddr);
 	u32 cp_blkaddr = le32_to_cpu(raw_super->cp_blkaddr);
 	u32 sit_blkaddr = le32_to_cpu(raw_super->sit_blkaddr);
@@ -1000,6 +1016,10 @@ static inline bool sanity_check_area_boundary(struct super_block *sb,
 	u32 segment_count_main = le32_to_cpu(raw_super->segment_count_main);
 	u32 segment_count = le32_to_cpu(raw_super->segment_count);
 	u32 log_blocks_per_seg = le32_to_cpu(raw_super->log_blocks_per_seg);
+	u64 main_end_blkaddr = main_blkaddr +
+				(segment_count_main << log_blocks_per_seg);
+	u64 seg_end_blkaddr = segment0_blkaddr +
+				(segment_count << log_blocks_per_seg);
 
 	if (segment0_blkaddr != cp_blkaddr) {
 		f2fs_msg(sb, KERN_INFO,
@@ -1044,22 +1064,45 @@ static inline bool sanity_check_area_boundary(struct super_block *sb,
 		return true;
 	}
 
-	if (main_blkaddr + (segment_count_main << log_blocks_per_seg) !=
-		segment0_blkaddr + (segment_count << log_blocks_per_seg)) {
+	if (main_end_blkaddr > seg_end_blkaddr) {
 		f2fs_msg(sb, KERN_INFO,
-			"Wrong MAIN_AREA boundary, start(%u) end(%u) blocks(%u)",
+			"Wrong MAIN_AREA boundary, start(%u) end(%u) block(%u)",
 			main_blkaddr,
-			segment0_blkaddr + (segment_count << log_blocks_per_seg),
+			segment0_blkaddr +
+				(segment_count << log_blocks_per_seg),
 			segment_count_main << log_blocks_per_seg);
 		return true;
+	} else if (main_end_blkaddr < seg_end_blkaddr) {
+		int err = 0;
+		char *res;
+
+		/* fix in-memory information all the time */
+		raw_super->segment_count = cpu_to_le32((main_end_blkaddr -
+				segment0_blkaddr) >> log_blocks_per_seg);
+
+		if (f2fs_readonly(sb) || bdev_read_only(sb->s_bdev)) {
+			res = "internally";
+		} else {
+			err = __f2fs_commit_super(bh, NULL);
+			res = err ? "failed" : "done";
+		}
+		f2fs_msg(sb, KERN_INFO,
+			"Fix alignment : %s, start(%u) end(%u) block(%u)",
+			res, main_blkaddr,
+			segment0_blkaddr +
+				(segment_count << log_blocks_per_seg),
+			segment_count_main << log_blocks_per_seg);
+		if (err)
+			return true;
 	}
-
 	return false;
 }
 
 static int sanity_check_raw_super(struct super_block *sb,
-			struct f2fs_super_block *raw_super)
+				struct buffer_head *bh)
 {
+	struct f2fs_super_block *raw_super = (struct f2fs_super_block *)
+					(bh->b_data + F2FS_SUPER_OFFSET);
 	unsigned int blocksize;
 
 	if (F2FS_SUPER_MAGIC != le32_to_cpu(raw_super->magic)) {
@@ -1126,7 +1169,7 @@ static int sanity_check_raw_super(struct super_block *sb,
 	}
 
 	/* check CP/SIT/NAT/SSA/MAIN_AREA area boundary */
-	if (sanity_check_area_boundary(sb, raw_super))
+	if (sanity_check_area_boundary(sb, bh))
 		return 1;
 
 	return 0;
@@ -1202,7 +1245,7 @@ static int read_raw_super_block(struct super_block *sb,
 {
 	int block;
 	struct buffer_head *bh;
-	struct f2fs_super_block *super, *buf;
+	struct f2fs_super_block *super;
 	int err = 0;
 
 	super = kzalloc(sizeof(struct f2fs_super_block), GFP_KERNEL);
@@ -1218,11 +1261,8 @@ static int read_raw_super_block(struct super_block *sb,
 			continue;
 		}
 
-		buf = (struct f2fs_super_block *)
-				(bh->b_data + F2FS_SUPER_OFFSET);
-
 		/* sanity checking of raw super */
-		if (sanity_check_raw_super(sb, buf)) {
+		if (sanity_check_raw_super(sb, bh)) {
 			f2fs_msg(sb, KERN_ERR,
 				"Can't find valid F2FS filesystem in %dth superblock",
 				block + 1);
@@ -1232,7 +1272,8 @@ static int read_raw_super_block(struct super_block *sb,
 		}
 
 		if (!*raw_super) {
-			memcpy(super, buf, sizeof(*super));
+			memcpy(super, bh->b_data + F2FS_SUPER_OFFSET,
+							sizeof(*super));
 			*valid_super_block = block;
 			*raw_super = super;
 		}
@@ -1252,42 +1293,29 @@ static int read_raw_super_block(struct super_block *sb,
 	return err;
 }
 
-static int __f2fs_commit_super(struct f2fs_sb_info *sbi, int block)
+int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover)
 {
-	struct f2fs_super_block *super = F2FS_RAW_SUPER(sbi);
 	struct buffer_head *bh;
 	int err;
 
-	bh = sb_getblk(sbi->sb, block);
+	/* write back-up superblock first */
+	bh = sb_getblk(sbi->sb, sbi->valid_super_block ? 0: 1);
 	if (!bh)
 		return -EIO;
-
-	lock_buffer(bh);
-	memcpy(bh->b_data + F2FS_SUPER_OFFSET, super, sizeof(*super));
-	set_buffer_uptodate(bh);
-	set_buffer_dirty(bh);
-	unlock_buffer(bh);
-
-	/* it's rare case, we can do fua all the time */
-	err = __sync_dirty_buffer(bh, WRITE_FLUSH_FUA);
+	err = __f2fs_commit_super(bh, F2FS_RAW_SUPER(sbi));
 	brelse(bh);
 
-	return err;
-}
-
-int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover)
-{
-	int err;
-
-	/* write back-up superblock first */
-	err = __f2fs_commit_super(sbi, sbi->valid_super_block ? 0 : 1);
-
 	/* if we are in recovery path, skip writing valid superblock */
 	if (recover || err)
 		return err;
 
 	/* write current valid superblock */
-	return __f2fs_commit_super(sbi, sbi->valid_super_block);
+	bh = sb_getblk(sbi->sb, sbi->valid_super_block);
+	if (!bh)
+		return -EIO;
+	err = __f2fs_commit_super(bh, F2FS_RAW_SUPER(sbi));
+	brelse(bh);
+	return err;
 }
 
 static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
-- 
2.6.3

[PATCH 2/4] f2fs: give RO message when recovering superblock

[Jaegeuk Kim]

When one of superblocks is missing, f2fs recovers it with the valid one.
But, even if f2fs is mounted as RO, we'd better notify that too.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/super.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 5afb4a6..742fc48 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -1298,6 +1298,9 @@ int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover)
 	struct buffer_head *bh;
 	int err;
 
+	if (f2fs_readonly(sbi->sb) || bdev_read_only(sbi->sb->s_bdev))
+		return -EROFS;
+
 	/* write back-up superblock first */
 	bh = sb_getblk(sbi->sb, sbi->valid_super_block ? 0: 1);
 	if (!bh)
@@ -1565,7 +1568,7 @@ try_onemore:
 	kfree(options);
 
 	/* recover broken superblock */
-	if (recovery && !f2fs_readonly(sb) && !bdev_read_only(sb->s_bdev)) {
+	if (recovery) {
 		err = f2fs_commit_super(sbi, true);
 		f2fs_msg(sb, KERN_INFO,
 			"Try to recover %dth superblock, ret: %ld",
-- 
2.6.3

[PATCH 3/4] f2fs: recover superblock at RW remounts

[Jaegeuk Kim]

This patch adds a sbi flag, SBI_NEED_SB_WRITE, which indicates it needs to
recover superblock when (re)mounting as RW. This is set only when f2fs is
mounted as RO.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/f2fs.h  |  1 +
 fs/f2fs/super.c | 36 +++++++++++++++++++++++++++---------
 2 files changed, 28 insertions(+), 9 deletions(-)

diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index bbe2cd1..286e917 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -672,6 +672,7 @@ enum {
 	SBI_IS_CLOSE,				/* specify unmounting */
 	SBI_NEED_FSCK,				/* need fsck.f2fs to fix */
 	SBI_POR_DOING,				/* recovery is doing or not */
+	SBI_NEED_SB_WRITE,			/* need to recover superblock */
 };
 
 enum {
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 742fc48..5718187 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -796,6 +796,15 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 		set_sbi_flag(sbi, SBI_IS_DIRTY);
 	}
 
+	/* recover superblocks we couldn't write due to previous RO mount */
+	if (!(*flags & MS_RDONLY) && is_sbi_flag_set(sbi, SBI_NEED_SB_WRITE)) {
+		err = f2fs_commit_super(sbi, false);
+		f2fs_msg(sb, KERN_INFO,
+			"Try to recover all the superblocks, ret: %d", err);
+		if (!err)
+			clear_sbi_flag(sbi, SBI_NEED_SB_WRITE);
+	}
+
 	sync_filesystem(sb);
 
 	sbi->mount_opt.opt = 0;
@@ -852,8 +861,9 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 	}
 skip:
 	/* Update the POSIXACL Flag */
-	 sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
+	sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
 		(test_opt(sbi, POSIX_ACL) ? MS_POSIXACL : 0);
+
 	return 0;
 restore_gc:
 	if (need_restart_gc) {
@@ -998,11 +1008,12 @@ static int __f2fs_commit_super(struct buffer_head *bh,
 	return __sync_dirty_buffer(bh, WRITE_FLUSH_FUA);
 }
 
-static inline bool sanity_check_area_boundary(struct super_block *sb,
+static inline bool sanity_check_area_boundary(struct f2fs_sb_info *sbi,
 					struct buffer_head *bh)
 {
 	struct f2fs_super_block *raw_super = (struct f2fs_super_block *)
 					(bh->b_data + F2FS_SUPER_OFFSET);
+	struct super_block *sb = sbi->sb;
 	u32 segment0_blkaddr = le32_to_cpu(raw_super->segment0_blkaddr);
 	u32 cp_blkaddr = le32_to_cpu(raw_super->cp_blkaddr);
 	u32 sit_blkaddr = le32_to_cpu(raw_super->sit_blkaddr);
@@ -1081,6 +1092,7 @@ static inline bool sanity_check_area_boundary(struct super_block *sb,
 				segment0_blkaddr) >> log_blocks_per_seg);
 
 		if (f2fs_readonly(sb) || bdev_read_only(sb->s_bdev)) {
+			set_sbi_flag(sbi, SBI_NEED_SB_WRITE);
 			res = "internally";
 		} else {
 			err = __f2fs_commit_super(bh, NULL);
@@ -1098,11 +1110,12 @@ static inline bool sanity_check_area_boundary(struct super_block *sb,
 	return false;
 }
 
-static int sanity_check_raw_super(struct super_block *sb,
+static int sanity_check_raw_super(struct f2fs_sb_info *sbi,
 				struct buffer_head *bh)
 {
 	struct f2fs_super_block *raw_super = (struct f2fs_super_block *)
 					(bh->b_data + F2FS_SUPER_OFFSET);
+	struct super_block *sb = sbi->sb;
 	unsigned int blocksize;
 
 	if (F2FS_SUPER_MAGIC != le32_to_cpu(raw_super->magic)) {
@@ -1169,7 +1182,7 @@ static int sanity_check_raw_super(struct super_block *sb,
 	}
 
 	/* check CP/SIT/NAT/SSA/MAIN_AREA area boundary */
-	if (sanity_check_area_boundary(sb, bh))
+	if (sanity_check_area_boundary(sbi, bh))
 		return 1;
 
 	return 0;
@@ -1239,10 +1252,11 @@ static void init_sb_info(struct f2fs_sb_info *sbi)
  * to get the first valid one. If any one of them is broken, we pass
  * them recovery flag back to the caller.
  */
-static int read_raw_super_block(struct super_block *sb,
+static int read_raw_super_block(struct f2fs_sb_info *sbi,
 			struct f2fs_super_block **raw_super,
 			int *valid_super_block, int *recovery)
 {
+	struct super_block *sb = sbi->sb;
 	int block;
 	struct buffer_head *bh;
 	struct f2fs_super_block *super;
@@ -1262,7 +1276,7 @@ static int read_raw_super_block(struct super_block *sb,
 		}
 
 		/* sanity checking of raw super */
-		if (sanity_check_raw_super(sb, bh)) {
+		if (sanity_check_raw_super(sbi, bh)) {
 			f2fs_msg(sb, KERN_ERR,
 				"Can't find valid F2FS filesystem in %dth superblock",
 				block + 1);
@@ -1298,8 +1312,11 @@ int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover)
 	struct buffer_head *bh;
 	int err;
 
-	if (f2fs_readonly(sbi->sb) || bdev_read_only(sbi->sb->s_bdev))
+	if ((recover && f2fs_readonly(sbi->sb)) ||
+				bdev_read_only(sbi->sb->s_bdev)) {
+		set_sbi_flag(sbi, SBI_NEED_SB_WRITE);
 		return -EROFS;
+	}
 
 	/* write back-up superblock first */
 	bh = sb_getblk(sbi->sb, sbi->valid_super_block ? 0: 1);
@@ -1343,6 +1360,8 @@ try_onemore:
 	if (!sbi)
 		return -ENOMEM;
 
+	sbi->sb = sb;
+
 	/* Load the checksum driver */
 	sbi->s_chksum_driver = crypto_alloc_shash("crc32", 0, 0);
 	if (IS_ERR(sbi->s_chksum_driver)) {
@@ -1358,7 +1377,7 @@ try_onemore:
 		goto free_sbi;
 	}
 
-	err = read_raw_super_block(sb, &raw_super, &valid_super_block,
+	err = read_raw_super_block(sbi, &raw_super, &valid_super_block,
 								&recovery);
 	if (err)
 		goto free_sbi;
@@ -1393,7 +1412,6 @@ try_onemore:
 	memcpy(sb->s_uuid, raw_super->uuid, sizeof(raw_super->uuid));
 
 	/* init f2fs-specific super block info */
-	sbi->sb = sb;
 	sbi->raw_super = raw_super;
 	sbi->valid_super_block = valid_super_block;
 	mutex_init(&sbi->gc_mutex);
-- 
2.6.3

[PATCH 4/4] f2fs: give -EINVAL for norecovery and rw mount

[Jaegeuk Kim]

Once detecting something to recover, f2fs should stop mounting, given norecovery
and rw mount options.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/f2fs.h     |  2 +-
 fs/f2fs/recovery.c | 11 +++++++----
 fs/f2fs/super.c    | 14 ++++++++++++--
 3 files changed, 20 insertions(+), 7 deletions(-)

diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 286e917..5dcc04e 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -1907,7 +1907,7 @@ void build_gc_manager(struct f2fs_sb_info *);
 /*
  * recovery.c
  */
-int recover_fsync_data(struct f2fs_sb_info *);
+int recover_fsync_data(struct f2fs_sb_info *, bool);
 bool space_for_roll_forward(struct f2fs_sb_info *);
 
 /*
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index 0b30cd2..e87f071 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -551,12 +551,13 @@ next:
 	return err;
 }
 
-int recover_fsync_data(struct f2fs_sb_info *sbi)
+int recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
 {
 	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
 	struct list_head inode_list;
 	block_t blkaddr;
 	int err;
+	int ret = 0;
 	bool need_writecp = false;
 
 	fsync_entry_slab = f2fs_kmem_cache_create("f2fs_fsync_inode_entry",
@@ -573,11 +574,13 @@ int recover_fsync_data(struct f2fs_sb_info *sbi)
 
 	/* step #1: find fsynced inode numbers */
 	err = find_fsync_dnodes(sbi, &inode_list);
-	if (err)
+	if (err || list_empty(&inode_list))
 		goto out;
 
-	if (list_empty(&inode_list))
+	if (check_only) {
+		ret = 1;
 		goto out;
+	}
 
 	need_writecp = true;
 
@@ -625,5 +628,5 @@ out:
 	} else {
 		mutex_unlock(&sbi->cp_mutex);
 	}
-	return err;
+	return ret ? ret: err;
 }
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 5718187..abc0d75 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -1562,14 +1562,24 @@ try_onemore:
 		if (need_fsck)
 			set_sbi_flag(sbi, SBI_NEED_FSCK);
 
-		err = recover_fsync_data(sbi);
-		if (err) {
+		err = recover_fsync_data(sbi, false);
+		if (err < 0) {
 			need_fsck = true;
 			f2fs_msg(sb, KERN_ERR,
 				"Cannot recover all fsync data errno=%ld", err);
 			goto free_kobj;
 		}
+	} else {
+		err = recover_fsync_data(sbi, true);
+
+		if (!f2fs_readonly(sb) && err > 0) {
+			err = -EINVAL;
+			f2fs_msg(sb, KERN_ERR,
+				"Need to recover fsync data");
+			goto free_kobj;
+		}
 	}
+
 	/* recover_fsync_data() cleared this already */
 	clear_sbi_flag(sbi, SBI_POR_DOING);
 
-- 
2.6.3