bcache: Move journal work to new flush wq

stable inclusion
from stable-5.10.20
commit 695185fce22928dfc9bacd7d7eb976c9ec2fcef3
bugzilla: 50608

--------------------------------

commit afe78ab4 upstream.

This is potentially long running and not latency sensitive, let's get
it out of the way of other latency sensitive events.

As observed in the previous commit, the `system_wq` comes easily
congested by bcache, and this fixes a few more stalls I was observing
every once in a while.

Let's not make this `WQ_MEM_RECLAIM` as it showed to reduce performance
of boot and file system operations in my tests. Also, without
`WQ_MEM_RECLAIM`, I no longer see desktop stalls. This matches the
previous behavior as `system_wq` also does no memory reclaim:

> // workqueue.c:
> system_wq = alloc_workqueue("events", 0, 0);

Cc: Coly Li <colyli@suse.de>
Cc: stable@vger.kernel.org # 5.4+
Signed-off-by: NKai Krakow <kai@kaishome.de>
Signed-off-by: NColy Li <colyli@suse.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: NChen Jun <chenjun102@huawei.com>
Acked-by: NXie XiuQi <xiexiuqi@huawei.com>
Signed-off-by: NZheng Zengkai <zhengzengkai@huawei.com>

drivers/md/bcache/bcache.h

@@ -1001,6 +1001,7 @@ void bch_write_bdev_super(struct cached_dev *dc, struct closure *parent);
 
 extern struct workqueue_struct *bcache_wq;
 extern struct workqueue_struct *bch_journal_wq;
+extern struct workqueue_struct *bch_flush_wq;
 extern struct mutex bch_register_lock;
 extern struct list_head bch_cache_sets;
 

drivers/md/bcache/journal.c

@@ -932,8 +932,8 @@ atomic_t *bch_journal(struct cache_set *c,
 		journal_try_write(c);
 	} else if (!w->dirty) {
 		w->dirty = true;
-		schedule_delayed_work(&c->journal.work,
-				      msecs_to_jiffies(c->journal_delay_ms));
+		queue_delayed_work(bch_flush_wq, &c->journal.work,
+				   msecs_to_jiffies(c->journal_delay_ms));
 		spin_unlock(&c->journal.lock);
 	} else {
 		spin_unlock(&c->journal.lock);

drivers/md/bcache/super.c

@@ -49,6 +49,7 @@ static int bcache_major;
 static DEFINE_IDA(bcache_device_idx);
 static wait_queue_head_t unregister_wait;
 struct workqueue_struct *bcache_wq;
+struct workqueue_struct *bch_flush_wq;
 struct workqueue_struct *bch_journal_wq;
 
 
@@ -2833,6 +2834,8 @@ static void bcache_exit(void)
 		destroy_workqueue(bcache_wq);
 	if (bch_journal_wq)
 		destroy_workqueue(bch_journal_wq);
+	if (bch_flush_wq)
+		destroy_workqueue(bch_flush_wq);
 	bch_btree_exit();
 
 	if (bcache_major)
@@ -2896,6 +2899,19 @@ static int __init bcache_init(void)
 	if (!bcache_wq)
 		goto err;
 
+	/*
+	 * Let's not make this `WQ_MEM_RECLAIM` for the following reasons:
+	 *
+	 * 1. It used `system_wq` before which also does no memory reclaim.
+	 * 2. With `WQ_MEM_RECLAIM` desktop stalls, increased boot times, and
+	 *    reduced throughput can be observed.
+	 *
+	 * We still want to user our own queue to not congest the `system_wq`.
+	 */
+	bch_flush_wq = alloc_workqueue("bch_flush", 0, 0);
+	if (!bch_flush_wq)
+		goto err;
+
 	bch_journal_wq = alloc_workqueue("bch_journal", WQ_MEM_RECLAIM, 0);
 	if (!bch_journal_wq)
 		goto err;