jbd: Write journal superblock with WRITE_FUA after checkpointing

If journal superblock is written only in disk's caches and other transaction
starts reusing space of the transaction cleaned from the log, it can happen
blocks of a new transaction reach the disk before journal superblock. When
power failure happens in such case, subsequent journal replay would still try
to replay the old transaction but some of it's blocks may be already
overwritten by the new transaction. For this reason we must use WRITE_FUA when
updating log tail and we must first write new log tail to disk and update
in-memory information only after that.

Signed-off-by: Jan Kara <jack@suse.cz>

1 files changed, 6 insertions, 3 deletions

diff --git a/include/trace/events/jbd.h b/include/trace/events/jbd.h
index d9658a940a39..da6f2591c25e 100644
--- a/include/trace/events/jbd.h
+++ b/include/trace/events/jbd.h
@@ -170,19 +170,22 @@ TRACE_EVENT(jbd_cleanup_journal_tail,
 );
 
 TRACE_EVENT(journal_write_superblock,
-        TP_PROTO(journal_t *journal),
+        TP_PROTO(journal_t *journal, int write_op),
 
-        TP_ARGS(journal),
+        TP_ARGS(journal, write_op),
 
         TP_STRUCT__entry(
                 __field(        dev_t,  dev                     )
+                __field(        int,    write_op                )
         ),
 
         TP_fast_assign(
                 __entry->dev            = journal->j_fs_dev->bd_dev;
+                __entry->write_op       = write_op;
         ),
 
-        TP_printk("dev %d,%d", MAJOR(__entry->dev), MINOR(__entry->dev))
+        TP_printk("dev %d,%d write_op %x", MAJOR(__entry->dev),
+                  MINOR(__entry->dev), __entry->write_op)
 );
 
 #endif /* _TRACE_JBD_H */