[PATCH 3.4 017/125] ext4, jbd2: ensure entering into panic after recording an error in superblock

[lizf]

From: Daeho Jeong <daeho.jeong@xxxxxxxxxxx>

3.4.113-rc1 review patch.  If anyone has any objections, please let me know.

------------------


commit 4327ba52afd03fc4b5afa0ee1d774c9c5b0e85c5 upstream.

If a EXT4 filesystem utilizes JBD2 journaling and an error occurs, the
journaling will be aborted first and the error number will be recorded
into JBD2 superblock and, finally, the system will enter into the
panic state in "errors=panic" option.  But, in the rare case, this
sequence is little twisted like the below figure and it will happen
that the system enters into panic state, which means the system reset
in mobile environment, before completion of recording an error in the
journal superblock. In this case, e2fsck cannot recognize that the
filesystem failure occurred in the previous run and the corruption
wouldn't be fixed.

Task A                        Task B
ext4_handle_error()
-> jbd2_journal_abort()
  -> __journal_abort_soft()
    -> __jbd2_journal_abort_hard()
    | -> journal->j_flags |= JBD2_ABORT;
    |
    |                         __ext4_abort()
    |                         -> jbd2_journal_abort()
    |                         | -> __journal_abort_soft()
    |                         |   -> if (journal->j_flags & JBD2_ABORT)
    |                         |           return;
    |                         -> panic()
    |
    -> jbd2_journal_update_sb_errno()

Tested-by: Hobin Woo <hobin.woo@xxxxxxxxxxx>
Signed-off-by: Daeho Jeong <daeho.jeong@xxxxxxxxxxx>
Signed-off-by: Theodore Ts'o <tytso@xxxxxxx>
Signed-off-by: Zefan Li <lizefan@xxxxxxxxxx>
---
 fs/ext4/super.c      | 12 ++++++++++--
 fs/jbd2/journal.c    |  6 +++++-
 include/linux/jbd2.h |  1 +
 3 files changed, 16 insertions(+), 3 deletions(-)

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 3de888c3..5862518 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -483,9 +483,13 @@ static void ext4_handle_error(struct super_block *sb)
 		ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
 		sb->s_flags |= MS_RDONLY;
 	}
-	if (test_opt(sb, ERRORS_PANIC))
+	if (test_opt(sb, ERRORS_PANIC)) {
+		if (EXT4_SB(sb)->s_journal &&
+		  !(EXT4_SB(sb)->s_journal->j_flags & JBD2_REC_ERR))
+			return;
 		panic("EXT4-fs (device %s): panic forced after error\n",
 			sb->s_id);
+	}
 }
 
 void __ext4_error(struct super_block *sb, const char *function,
@@ -659,8 +663,12 @@ void __ext4_abort(struct super_block *sb, const char *function,
 			jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO);
 		save_error_info(sb, function, line);
 	}
-	if (test_opt(sb, ERRORS_PANIC))
+	if (test_opt(sb, ERRORS_PANIC)) {
+		if (EXT4_SB(sb)->s_journal &&
+		  !(EXT4_SB(sb)->s_journal->j_flags & JBD2_REC_ERR))
+			return;
 		panic("EXT4-fs panic from previous error\n");
+	}
 }
 
 void ext4_msg(struct super_block *sb, const char *prefix, const char *fmt, ...)
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index a327944..2e3063c 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -1921,8 +1921,12 @@ static void __journal_abort_soft (journal_t *journal, int errno)
 
 	__jbd2_journal_abort_hard(journal);
 
-	if (errno)
+	if (errno) {
 		jbd2_journal_update_sb_errno(journal);
+		write_lock(&journal->j_state_lock);
+		journal->j_flags |= JBD2_REC_ERR;
+		write_unlock(&journal->j_state_lock);
+	}
 }
 
 /**
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 2179d78..ee8090f 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -954,6 +954,7 @@ struct journal_s
 #define JBD2_ABORT_ON_SYNCDATA_ERR	0x040	/* Abort the journal on file
 						 * data write error in ordered
 						 * mode */
+#define JBD2_REC_ERR	0x080	/* The errno in the sb has been recorded */
 
 /*
  * Function declarations for the journaling transaction and buffer
-- 
1.9.1