1 files changed, 47 insertions, 6 deletions

diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 773f5fdad25f..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>
 
 /*
@@ -613,6 +613,10 @@ static void mca_data_alloc(struct btree *b, struct bkey *k, gfp_t gfp)
 static struct btree *mca_bucket_alloc(struct cache_set *c,
 				      struct bkey *k, gfp_t gfp)
 {
+	/*
+	 * kzalloc() is necessary here for initialization,
+	 * see code comments in bch_btree_keys_init().
+	 */
 	struct btree *b = kzalloc(sizeof(struct btree), gfp);
 
 	if (!b)
@@ -655,7 +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);
@@ -778,10 +800,15 @@ void bch_btree_cache_free(struct cache_set *c)
 	while (!list_empty(&c->btree_cache)) {
 		b = list_first_entry(&c->btree_cache, struct btree, list);
 
-		if (btree_node_dirty(b))
+		/*
+		 * This function is called by cache_set_free(), no I/O
+		 * request on cache now, it is unnecessary to acquire
+		 * b->write_lock before clearing BTREE_NODE_dirty anymore.
+		 */
+		if (btree_node_dirty(b)) {
 			btree_complete_write(b, btree_current_write(b));
-		clear_bit(BTREE_NODE_dirty, &b->flags);
-
+			clear_bit(BTREE_NODE_dirty, &b->flags);
+		}
 		mca_data_free(b);
 	}
 
@@ -1067,11 +1094,25 @@ 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))
+	if (btree_node_dirty(b)) {
 		btree_complete_write(b, btree_current_write(b));
-	clear_bit(BTREE_NODE_dirty, &b->flags);
+		clear_bit(BTREE_NODE_dirty, &b->flags);
+	}
 
 	mutex_unlock(&b->write_lock);