Revert "bcache: Kill btree_io_wq"

commit 9f233ffe02e5cef611100cd8c5bcf4de26ca7bef upstream.

This reverts commit 56b30770b27d54d68ad51eccc6d888282b568cee.

With the btree using the `system_wq`, I seem to see a lot more desktop
latency than I should.

After some more investigation, it looks like the original assumption
of 56b3077 no longer is true, and bcache has a very high potential of
congesting the `system_wq`. In turn, this introduces laggy desktop
performance, IO stalls (at least with btrfs), and input events may be
delayed.

So let's revert this. It's important to note that the semantics of
using `system_wq` previously mean that `btree_io_wq` should be created
before and destroyed after other bcache wqs to keep the same
assumptions.

Cc: Coly Li <colyli@suse.de>
Cc: stable@vger.kernel.org # 5.4+
Signed-off-by: Kai Krakow <kai@kaishome.de>
Signed-off-by: Coly Li <colyli@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

3 files changed, 25 insertions, 2 deletions

diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index 859567ad3db4..830ca66c284a 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -1027,5 +1027,7 @@ void bch_debug_exit(void);
 void bch_debug_init(void);
 void bch_request_exit(void);
 int bch_request_init(void);
+void bch_btree_exit(void);
+int bch_btree_init(void);
 
 #endif /* _BCACHE_H */
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 8d06105fc9ff..1108460880fd 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -99,6 +99,8 @@
 #define PTR_HASH(c, k)							\
 	(((k)->ptr[0] >> c->bucket_bits) | PTR_GEN(k, 0))
 
+static struct workqueue_struct *btree_io_wq;
+
 #define insert_lock(s, b)	((b)->level <= (s)->lock)
 
 /*
@@ -366,7 +368,7 @@ static void __btree_node_write_done(struct closure *cl)
 	btree_complete_write(b, w);
 
 	if (btree_node_dirty(b))
-		schedule_delayed_work(&b->work, 30 * HZ);
+		queue_delayed_work(btree_io_wq, &b->work, 30 * HZ);
 
 	closure_return_with_destructor(cl, btree_node_write_unlock);
 }
@@ -539,7 +541,7 @@ static void bch_btree_leaf_dirty(struct btree *b, atomic_t *journal_ref)
 	BUG_ON(!i->keys);
 
 	if (!btree_node_dirty(b))
-		schedule_delayed_work(&b->work, 30 * HZ);
+		queue_delayed_work(btree_io_wq, &b->work, 30 * HZ);
 
 	set_btree_node_dirty(b);
 
@@ -2659,3 +2661,18 @@ void bch_keybuf_init(struct keybuf *buf)
 	spin_lock_init(&buf->lock);
 	array_allocator_init(&buf->freelist);
 }
+
+void bch_btree_exit(void)
+{
+	if (btree_io_wq)
+		destroy_workqueue(btree_io_wq);
+}
+
+int __init bch_btree_init(void)
+{
+	btree_io_wq = create_singlethread_workqueue("bch_btree_io");
+	if (!btree_io_wq)
+		return -ENOMEM;
+
+	return 0;
+}
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 63f5ce18311b..a1b010c78304 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -2652,6 +2652,7 @@ static void bcache_exit(void)
 		destroy_workqueue(bcache_wq);
 	if (bch_journal_wq)
 		destroy_workqueue(bch_journal_wq);
+	bch_btree_exit();
 
 	if (bcache_major)
 		unregister_blkdev(bcache_major, "bcache");
@@ -2707,6 +2708,9 @@ static int __init bcache_init(void)
 		return bcache_major;
 	}
 
+	if (bch_btree_init())
+		goto err;
+
 	bcache_wq = alloc_workqueue("bcache", WQ_MEM_RECLAIM, 0);
 	if (!bcache_wq)
 		goto err;