gfs2: add some much needed cleanup for log flushes that fail

When a log flush fails due to io errors, it signals the failure but does
not clean up after itself very well. This is because buffers are added to
the transaction tr_buf and tr_databuf queue, but the io error causes
gfs2_log_flush to bypass the "after_commit" functions responsible for
dequeueing the bd elements. If the bd elements are added to the ail list
before the error, function ail_drain takes care of dequeueing them.
But if they haven't gotten that far, the elements are forgotten and
make the transactions unable to be freed.

This patch introduces new function trans_drain which drains the bd
elements from the transaction so they can be freed properly.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>

2 files changed, 32 insertions, 0 deletions

diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index a58333e3980d..3763c9ff1406 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -902,6 +902,36 @@ static void empty_ail1_list(struct gfs2_sbd *sdp)
 }
 
 /**
+ * drain_bd - drain the buf and databuf queue for a failed transaction
+ * @tr: the transaction to drain
+ *
+ * When this is called, we're taking an error exit for a log write that failed
+ * but since we bypassed the after_commit functions, we need to remove the
+ * items from the buf and databuf queue.
+ */
+static void trans_drain(struct gfs2_trans *tr)
+{
+	struct gfs2_bufdata *bd;
+	struct list_head *head;
+
+	if (!tr)
+		return;
+
+	head = &tr->tr_buf;
+	while (!list_empty(head)) {
+		bd = list_first_entry(head, struct gfs2_bufdata, bd_list);
+		list_del_init(&bd->bd_list);
+		kmem_cache_free(gfs2_bufdata_cachep, bd);
+	}
+	head = &tr->tr_databuf;
+	while (!list_empty(head)) {
+		bd = list_first_entry(head, struct gfs2_bufdata, bd_list);
+		list_del_init(&bd->bd_list);
+		kmem_cache_free(gfs2_bufdata_cachep, bd);
+	}
+}
+
+/**
  * gfs2_log_flush - flush incore transaction(s)
  * @sdp: the filesystem
  * @gl: The glock structure to flush.  If NULL, flush the whole incore log
@@ -1005,6 +1035,7 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl, u32 flags)
 
 out:
 	if (gfs2_withdrawn(sdp)) {
+		trans_drain(tr);
 		/**
 		 * If the tr_list is empty, we're withdrawing during a log
 		 * flush that targets a transaction, but the transaction was
diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c
index e1c7eb6eb00a..6d4bf7ea7b3b 100644
--- a/fs/gfs2/trans.c
+++ b/fs/gfs2/trans.c
@@ -67,6 +67,7 @@ int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks,
 		tr->tr_reserved += gfs2_struct2blk(sdp, revokes);
 	INIT_LIST_HEAD(&tr->tr_databuf);
 	INIT_LIST_HEAD(&tr->tr_buf);
+	INIT_LIST_HEAD(&tr->tr_list);
 	INIT_LIST_HEAD(&tr->tr_ail1_list);
 	INIT_LIST_HEAD(&tr->tr_ail2_list);