jbd2: clear revoked flag on buffers before a new transaction started

Currently, we clear revoked flag only when a block is reused.  However,
this can tigger a false journal error.  Consider a situation when a block
is used as a meta block and is deleted(revoked) in ordered mode, then the
block is allocated as a data block to a file.  At this moment, user changes
the file's journal mode from ordered to journaled and truncates the file.
The block will be considered re-revoked by journal because it has revoked
flag still pending from the last transaction and an assertion triggers.

We fix the problem by keeping the revoked status more uptodate - we clear
revoked flag when switching revoke tables to reflect there is no revoked
buffers in current transaction any more.
Signed-off-by: Yongqiang Yang <xiaoqiangnk@gmail.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>

fs/jbd2/commit.c

@@ -429,6 +429,12 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 
 	jbd_debug(3, "JBD2: commit phase 1\n");
 
+	/*
+	 * Clear revoked flag to reflect there is no revoked buffers
+	 * in the next transaction which is going to be started.
+	 */
+	jbd2_clear_buffer_revoked_flags(journal);
+
 	/*
 	 * Switch to a new revoke table.
 	 */

fs/jbd2/revoke.c

@@ -47,6 +47,10 @@
  *   overwriting the new data.  We don't even need to clear the revoke
  *   bit here.
  *
+ * We cache revoke status of a buffer in the current transaction in b_states
+ * bits.  As the name says, revokevalid flag indicates that the cached revoke
+ * status of a buffer is valid and we can rely on the cached status.
+ *
  * Revoke information on buffers is a tri-state value:
  *
  * RevokeValid clear:	no cached revoke status, need to look it up
@@ -478,6 +482,36 @@ int jbd2_journal_cancel_revoke(handle_t *handle, struct journal_head *jh)
 	return did_revoke;
 }
 
+/*
+ * journal_clear_revoked_flag clears revoked flag of buffers in
+ * revoke table to reflect there is no revoked buffers in the next
+ * transaction which is going to be started.
+ */
+void jbd2_clear_buffer_revoked_flags(journal_t *journal)
+{
+	struct jbd2_revoke_table_s *revoke = journal->j_revoke;
+	int i = 0;
+
+	for (i = 0; i < revoke->hash_size; i++) {
+		struct list_head *hash_list;
+		struct list_head *list_entry;
+		hash_list = &revoke->hash_table[i];
+
+		list_for_each(list_entry, hash_list) {
+			struct jbd2_revoke_record_s *record;
+			struct buffer_head *bh;
+			record = (struct jbd2_revoke_record_s *)list_entry;
+			bh = __find_get_block(journal->j_fs_dev,
+					      record->blocknr,
+					      journal->j_blocksize);
+			if (bh) {
+				clear_buffer_revoked(bh);
+				__brelse(bh);
+			}
+		}
+	}
+}
+
 /* journal_switch_revoke table select j_revoke for next transaction
  * we do not want to suspend any processing until all revokes are
  * written -bzzz

include/linux/jbd2.h

@@ -1151,6 +1151,7 @@ extern int	jbd2_journal_set_revoke(journal_t *, unsigned long long, tid_t);
 extern int	jbd2_journal_test_revoke(journal_t *, unsigned long long, tid_t);
 extern void	jbd2_journal_clear_revoke(journal_t *);
 extern void	jbd2_journal_switch_revoke_table(journal_t *journal);
+extern void	jbd2_clear_buffer_revoked_flags(journal_t *journal);
 
 /*
  * The log thread user interface: