ext4: Save error information to the superblock for analysis

Save number of file system errors, and the time function name, line
number, block number, and inode number of the first and most recent
errors reported on the file system in the superblock.
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>

fs/ext4/block_validity.c

@@ -229,16 +229,20 @@ int ext4_data_block_valid(struct ext4_sb_info *sbi, ext4_fsblk_t start_blk,
 
 	if ((start_blk <= le32_to_cpu(sbi->s_es->s_first_data_block)) ||
 	    (start_blk + count < start_blk) ||
-	    (start_blk + count > ext4_blocks_count(sbi->s_es)))
+	    (start_blk + count > ext4_blocks_count(sbi->s_es))) {
+		sbi->s_es->s_last_error_block = cpu_to_le64(start_blk);
 		return 0;
+	}
 	while (n) {
 		entry = rb_entry(n, struct ext4_system_zone, node);
 		if (start_blk + count - 1 < entry->start_blk)
 			n = n->rb_left;
 		else if (start_blk >= (entry->start_blk + entry->count))
 			n = n->rb_right;
-		else
+		else {
+			sbi->s_es->s_last_error_block = cpu_to_le64(start_blk);
 			return 0;
+		}
 	}
 	return 1;
 }

fs/ext4/ext4.h

@@ -1011,9 +1011,24 @@ struct ext4_super_block {
 					      snapshot's future use */
 	__le32	s_snapshot_list;	/* inode number of the head of the
 					   on-disk snapshot list */
-	__u32   s_reserved[155];        /* Padding to the end of the block */
+#define EXT4_S_ERR_START offsetof(struct ext4_super_block, s_error_count)
+	__le32	s_error_count;		/* number of fs errors */
+	__le32	s_first_error_time;	/* first time an error happened */
+	__le32	s_first_error_ino;	/* inode involved in first error */
+	__le64	s_first_error_block;	/* block involved of first error */
+	__u8	s_first_error_func[32];	/* function where the error happened */
+	__le32	s_first_error_line;	/* line number where error happened */
+	__le32	s_last_error_time;	/* most recent time of an error */
+	__le32	s_last_error_ino;	/* inode involved in last error */
+	__le32	s_last_error_line;	/* line number where error happened */
+	__le64	s_last_error_block;	/* block involved of last error */
+	__u8	s_last_error_func[32];	/* function where the error happened */
+#define EXT4_S_ERR_END offsetof(struct ext4_super_block, s_reserved)
+	__le32   s_reserved[128];        /* Padding to the end of the block */
 };
 
+#define EXT4_S_ERR_LEN (EXT4_S_ERR_END - EXT4_S_ERR_START)
+
 #ifdef __KERNEL__
 
 /*

fs/ext4/ext4_jbd2.c

@@ -134,6 +134,11 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line,
 		if (inode && inode_needs_sync(inode)) {
 			sync_dirty_buffer(bh);
 			if (buffer_req(bh) && !buffer_uptodate(bh)) {
+				struct ext4_super_block *es;
+
+				es = EXT4_SB(inode->i_sb)->s_es;
+				es->s_last_error_block =
+					cpu_to_le64(bh->b_blocknr);
 				ext4_error_inode(inode, where, line,
 						 bh->b_blocknr,
 					"IO error syncing itable block");

fs/ext4/inode.c

@@ -341,6 +341,7 @@ static int __ext4_check_blockref(const char *function, unsigned int line,
 				 struct inode *inode,
 				 __le32 *p, unsigned int max)
 {
+	struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es;
 	__le32 *bref = p;
 	unsigned int blk;
 
@@ -349,6 +350,7 @@ static int __ext4_check_blockref(const char *function, unsigned int line,
 		if (blk &&
 		    unlikely(!ext4_data_block_valid(EXT4_SB(inode->i_sb),
 						    blk, 1))) {
+			es->s_last_error_block = cpu_to_le64(blk);
 			ext4_error_inode(inode, function, line, blk,
 					 "invalid block");
 			return -EIO;

fs/ext4/super.c

@@ -307,6 +307,35 @@ void ext4_journal_abort_handle(const char *caller, unsigned int line,
 	jbd2_journal_abort_handle(handle);
 }
 
+static void __save_error_info(struct super_block *sb, const char *func,
+			    unsigned int line)
+{
+	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
+
+	EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
+	es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
+	es->s_last_error_time = cpu_to_le32(get_seconds());
+	strncpy(es->s_last_error_func, func, sizeof(es->s_last_error_func));
+	es->s_last_error_line = cpu_to_le32(line);
+	if (!es->s_first_error_time) {
+		es->s_first_error_time = es->s_last_error_time;
+		strncpy(es->s_first_error_func, func,
+			sizeof(es->s_first_error_func));
+		es->s_first_error_line = cpu_to_le32(line);
+		es->s_first_error_ino = es->s_last_error_ino;
+		es->s_first_error_block = es->s_last_error_block;
+	}
+	es->s_error_count = cpu_to_le32(le32_to_cpu(es->s_error_count) + 1);
+}
+
+static void save_error_info(struct super_block *sb, const char *func,
+			    unsigned int line)
+{
+	__save_error_info(sb, func, line);
+	ext4_commit_super(sb, 1);
+}
+
+
 /* Deal with the reporting of failure conditions on a filesystem such as
  * inconsistencies detected or read IO failures.
  *
@@ -324,11 +353,6 @@ void ext4_journal_abort_handle(const char *caller, unsigned int line,
 
 static void ext4_handle_error(struct super_block *sb)
 {
-	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
-
-	EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
-	es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
-
 	if (sb->s_flags & MS_RDONLY)
 		return;
 
@@ -343,7 +367,6 @@ static void ext4_handle_error(struct super_block *sb)
 		ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
 		sb->s_flags |= MS_RDONLY;
 	}
-	ext4_commit_super(sb, 1);
 	if (test_opt(sb, ERRORS_PANIC))
 		panic("EXT4-fs (device %s): panic forced after error\n",
 			sb->s_id);
@@ -369,7 +392,11 @@ void ext4_error_inode(struct inode *inode, const char *function,
 		      const char *fmt, ...)
 {
 	va_list args;
+	struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es;
 
+	es->s_last_error_ino = cpu_to_le32(inode->i_ino);
+	es->s_last_error_block = cpu_to_le64(block);
+	save_error_info(inode->i_sb, function, line);
 	va_start(args, fmt);
 	printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: inode #%lu: ",
 	       inode->i_sb->s_id, function, line, inode->i_ino);
@@ -387,9 +414,13 @@ void ext4_error_file(struct file *file, const char *function,
 		     unsigned int line, const char *fmt, ...)
 {
 	va_list args;
+	struct ext4_super_block *es;
 	struct inode *inode = file->f_dentry->d_inode;
 	char pathname[80], *path;
 
+	es = EXT4_SB(inode->i_sb)->s_es;
+	es->s_last_error_ino = cpu_to_le32(inode->i_ino);
+	save_error_info(inode->i_sb, function, line);
 	va_start(args, fmt);
 	path = d_path(&(file->f_path), pathname, sizeof(pathname));
 	if (!path)
@@ -459,6 +490,7 @@ void __ext4_std_error(struct super_block *sb, const char *function,
 	errstr = ext4_decode_error(sb, errno, nbuf);
 	printk(KERN_CRIT "EXT4-fs error (device %s) in %s:%d: %s\n",
 	       sb->s_id, function, line, errstr);
+	save_error_info(sb, function, line);
 
 	ext4_handle_error(sb);
 }
@@ -478,6 +510,7 @@ void __ext4_abort(struct super_block *sb, const char *function,
 {
 	va_list args;
 
+	save_error_info(sb, function, line);
 	va_start(args, fmt);
 	printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: ", sb->s_id,
 	       function, line);
@@ -485,18 +518,16 @@ void __ext4_abort(struct super_block *sb, const char *function,
 	printk("\n");
 	va_end(args);
 
+	if ((sb->s_flags & MS_RDONLY) == 0) {
+		ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
+		sb->s_flags |= MS_RDONLY;
+		EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED;
+		if (EXT4_SB(sb)->s_journal)
+			jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO);
+		save_error_info(sb, function, line);
+	}
 	if (test_opt(sb, ERRORS_PANIC))
 		panic("EXT4-fs panic from previous error\n");
-
-	if (sb->s_flags & MS_RDONLY)
-		return;
-
-	ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
-	EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
-	sb->s_flags |= MS_RDONLY;
-	EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED;
-	if (EXT4_SB(sb)->s_journal)
-		jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO);
 }
 
 void ext4_msg (struct super_block * sb, const char *prefix,
@@ -534,6 +565,9 @@ __acquires(bitlock)
 	va_list args;
 	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
 
+	es->s_last_error_ino = cpu_to_le32(ino);
+	es->s_last_error_block = cpu_to_le64(block);
+	__save_error_info(sb, function, line);
 	va_start(args, fmt);
 	printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: group %u",
 	       sb->s_id, function, line, grp);
@@ -546,11 +580,10 @@ __acquires(bitlock)
 	va_end(args);
 
 	if (test_opt(sb, ERRORS_CONT)) {
-		EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
-		es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
 		ext4_commit_super(sb, 0);
 		return;
 	}
+
 	ext4_unlock_group(sb, grp);
 	ext4_handle_error(sb);
 	/*
@@ -3332,8 +3365,17 @@ static int ext4_load_journal(struct super_block *sb,
 
 	if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER))
 		err = jbd2_journal_wipe(journal, !really_read_only);
-	if (!err)
+	if (!err) {
+		char *save = kmalloc(EXT4_S_ERR_LEN, GFP_KERNEL);
+		if (save)
+			memcpy(save, ((char *) es) +
+			       EXT4_S_ERR_START, EXT4_S_ERR_LEN);
 		err = jbd2_journal_load(journal);
+		if (save)
+			memcpy(((char *) es) + EXT4_S_ERR_START,
+			       save, EXT4_S_ERR_LEN);
+		kfree(save);
+	}
 
 	if (err) {
 		ext4_msg(sb, KERN_ERR, "error loading journal");