ext4/jbd2: don't wait (forever) for stale tid caused by wraparound

In the case where an inode has a very stale transaction id (tid) in
i_datasync_tid or i_sync_tid, it's possible that after a very large
(2**31) number of transactions, that the tid number space might wrap,
causing tid_geq()'s calculations to fail.

Commit deeeaf13 "jbd2: fix fsync() tid wraparound bug", later modified
by commit e7b04ac0 "jbd2: don't wake kjournald unnecessarily",
attempted to fix this problem, but it only avoided kjournald spinning
forever by fixing the logic in jbd2_log_start_commit().

Unfortunately, in the codepaths in fs/ext4/fsync.c and fs/ext4/inode.c
that might call jbd2_log_start_commit() with a stale tid, those
functions will subsequently call jbd2_log_wait_commit() with the same
stale tid, and then wait for a very long time.  To fix this, we
replace the calls to jbd2_log_start_commit() and
jbd2_log_wait_commit() with a call to a new function,
jbd2_complete_transaction(), which will correctly handle stale tid's.

As a bonus, jbd2_complete_transaction() will avoid locking
j_state_lock for writing unless a commit needs to be started.  This
should have a small (but probably not measurable) improvement for
ext4's scalability.

Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Reported-by: Ben Hutchings <ben@decadent.org.uk>
Reported-by: George Barnett <gbarnett@atlassian.com>
Cc: stable@vger.kernel.org


diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index 3278e64..e0ba8a4 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -166,8 +166,7 @@
 	if (journal->j_flags & JBD2_BARRIER &&
 	    !jbd2_trans_will_send_data_barrier(journal, commit_tid))
 		needs_barrier = true;
-	jbd2_log_start_commit(journal, commit_tid);
-	ret = jbd2_log_wait_commit(journal, commit_tid);
+	ret = jbd2_complete_transaction(journal, commit_tid);
 	if (needs_barrier) {
 		err = blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
 		if (!ret)
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 56ebd66..addba9e 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -210,8 +210,7 @@
 			journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
 			tid_t commit_tid = EXT4_I(inode)->i_datasync_tid;
 
-			jbd2_log_start_commit(journal, commit_tid);
-			jbd2_log_wait_commit(journal, commit_tid);
+			jbd2_complete_transaction(journal, commit_tid);
 			filemap_write_and_wait(&inode->i_data);
 		}
 		truncate_inode_pages(&inode->i_data, 0);
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index ed10991..886ec2f 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -710,6 +710,37 @@
 }
 
 /*
+ * When this function returns the transaction corresponding to tid
+ * will be completed.  If the transaction has currently running, start
+ * committing that transaction before waiting for it to complete.  If
+ * the transaction id is stale, it is by definition already completed,
+ * so just return SUCCESS.
+ */
+int jbd2_complete_transaction(journal_t *journal, tid_t tid)
+{
+	int	need_to_wait = 1;
+
+	read_lock(&journal->j_state_lock);
+	if (journal->j_running_transaction &&
+	    journal->j_running_transaction->t_tid == tid) {
+		if (journal->j_commit_request != tid) {
+			/* transaction not yet started, so request it */
+			read_unlock(&journal->j_state_lock);
+			jbd2_log_start_commit(journal, tid);
+			goto wait_commit;
+		}
+	} else if (!(journal->j_committing_transaction &&
+		     journal->j_committing_transaction->t_tid == tid))
+		need_to_wait = 0;
+	read_unlock(&journal->j_state_lock);
+	if (!need_to_wait)
+		return 0;
+wait_commit:
+	return jbd2_log_wait_commit(journal, tid);
+}
+EXPORT_SYMBOL(jbd2_complete_transaction);
+
+/*
  * Log buffer allocation routines:
  */
 
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 50e5a5e..f028975 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -1200,6 +1200,7 @@
 int jbd2_journal_start_commit(journal_t *journal, tid_t *tid);
 int jbd2_journal_force_commit_nested(journal_t *journal);
 int jbd2_log_wait_commit(journal_t *journal, tid_t tid);
+int jbd2_complete_transaction(journal_t *journal, tid_t tid);
 int jbd2_log_do_checkpoint(journal_t *journal);
 int jbd2_trans_will_send_data_barrier(journal_t *journal, tid_t tid);