3 files changed, 36 insertions, 1 deletions

diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 846306c3a887..ba434d9ac720 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -35,7 +35,7 @@
 #include <linux/rcupdate.h>
 #include <linux/sched/clock.h>
 #include <linux/rculist.h>
-
+#include <linux/delay.h>
 #include <trace/events/bcache.h>
 
 /*
@@ -659,12 +659,25 @@ static int mca_reap(struct btree *b, unsigned int min_order, bool flush)
 		up(&b->io_mutex);
 	}
 
+retry:
 	/*
 	 * BTREE_NODE_dirty might be cleared in btree_flush_btree() by
 	 * __bch_btree_node_write(). To avoid an extra flush, acquire
 	 * b->write_lock before checking BTREE_NODE_dirty bit.
 	 */
 	mutex_lock(&b->write_lock);
+	/*
+	 * If this btree node is selected in btree_flush_write() by journal
+	 * code, delay and retry until the node is flushed by journal code
+	 * and BTREE_NODE_journal_flush bit cleared by btree_flush_write().
+	 */
+	if (btree_node_journal_flush(b)) {
+		pr_debug("bnode %p is flushing by journal, retry", b);
+		mutex_unlock(&b->write_lock);
+		udelay(1);
+		goto retry;
+	}
+
 	if (btree_node_dirty(b))
 		__bch_btree_node_write(b, &cl);
 	mutex_unlock(&b->write_lock);
@@ -1081,7 +1094,20 @@ static void btree_node_free(struct btree *b)
 
 	BUG_ON(b == b->c->root);
 
+retry:
 	mutex_lock(&b->write_lock);
+	/*
+	 * If the btree node is selected and flushing in btree_flush_write(),
+	 * delay and retry until the BTREE_NODE_journal_flush bit cleared,
+	 * then it is safe to free the btree node here. Otherwise this btree
+	 * node will be in race condition.
+	 */
+	if (btree_node_journal_flush(b)) {
+		mutex_unlock(&b->write_lock);
+		pr_debug("bnode %p journal_flush set, retry", b);
+		udelay(1);
+		goto retry;
+	}
 
 	if (btree_node_dirty(b)) {
 		btree_complete_write(b, btree_current_write(b));
diff --git a/drivers/md/bcache/btree.h b/drivers/md/bcache/btree.h
index d1c72ef64edf..76cfd121a486 100644
--- a/drivers/md/bcache/btree.h
+++ b/drivers/md/bcache/btree.h
@@ -158,11 +158,13 @@ enum btree_flags {
 	BTREE_NODE_io_error,
 	BTREE_NODE_dirty,
 	BTREE_NODE_write_idx,
+	BTREE_NODE_journal_flush,
 };
 
 BTREE_FLAG(io_error);
 BTREE_FLAG(dirty);
 BTREE_FLAG(write_idx);
+BTREE_FLAG(journal_flush);
 
 static inline struct btree_write *btree_current_write(struct btree *b)
 {
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index 1218e3cada3c..a1e3e1fcea6e 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -430,6 +430,7 @@ static void btree_flush_write(struct cache_set *c)
 retry:
 	best = NULL;
 
+	mutex_lock(&c->bucket_lock);
 	for_each_cached_btree(b, c, i)
 		if (btree_current_write(b)->journal) {
 			if (!best)
@@ -442,15 +443,21 @@ retry:
 		}
 
 	b = best;
+	if (b)
+		set_btree_node_journal_flush(b);
+	mutex_unlock(&c->bucket_lock);
+
 	if (b) {
 		mutex_lock(&b->write_lock);
 		if (!btree_current_write(b)->journal) {
+			clear_bit(BTREE_NODE_journal_flush, &b->flags);
 			mutex_unlock(&b->write_lock);
 			/* We raced */
 			goto retry;
 		}
 
 		__bch_btree_node_write(b, NULL);
+		clear_bit(BTREE_NODE_journal_flush, &b->flags);
 		mutex_unlock(&b->write_lock);
 	}
 }