The __log_wait_for_space function sits in a loop checkpointing transactions
until there is sufficient space free in the journal. However, if there are
no transactions to be processed (e.g. because the free space calculation is
wrong due to a corrupted filesystem) it will never progress.
Check for space being required when no transactions are outstanding and
abort the journal instead of endlessly looping.
This patch fixes the bug reported by Sami Liedes at:
http://bugzilla.kernel.org/show_bug.cgi?id=10976
Signed-off-by: Duane Griffin <duaneg@dghda.com>
Tested-by: Sami Liedes <sliedes@cc.hut.fi>
---
diff --git a/fs/jbd/checkpoint.c b/fs/jbd/checkpoint.c
index a5432bb..9fac177 100644
--- a/fs/jbd/checkpoint.c
+++ b/fs/jbd/checkpoint.c
@@ -126,14 +126,29 @@ void __log_wait_for_space(journal_t *journal)
/*
* Test again, another process may have checkpointed while we
- * were waiting for the checkpoint lock
+ * were waiting for the checkpoint lock. If there are no
+ * outstanding transactions there is nothing to checkpoint and
+ * we can't make progress. Abort the journal in this case.
*/
spin_lock(&journal->j_state_lock);
+ spin_lock(&journal->j_list_lock);
nblocks = jbd_space_needed(journal);
if (__log_space_left(journal) < nblocks) {
+ int chkpt = journal->j_checkpoint_transactions != NULL;
+
+ spin_unlock(&journal->j_list_lock);
spin_unlock(&journal->j_state_lock);
- log_do_checkpoint(journal);
+ if (chkpt) {
+ log_do_checkpoint(journal);
+ } else {
+ printk(KERN_ERR "%s: no transactions\n",
+ __func__);
+ journal_abort(journal, 0);
+ }
+
spin_lock(&journal->j_state_lock);
+ } else {
+ spin_unlock(&journal->j_list_lock);
}
mutex_unlock(&journal->j_checkpoint_mutex);
}
--
