blk-mq: unify hctx delay_work and run_work

The only difference between ->run_work and ->delay_work, is that
the latter is used to defer running a queue. This is done by
marking the queue stopped, and scheduling ->delay_work to run
sometime in the future. While the queue is stopped, direct runs
or runs through ->run_work will not run the queue.

If we combine the handlers, then we need to handle two things:

1) If a delayed/stopped run is scheduled, then we should not run
   the queue before that has been completed.
2) If a queue is delayed/stopped, the handler needs to restart
   the queue. Normally a run of a queue with the stopped bit set
   would be a no-op.

Case 1 is handled by modifying a currently pending queue run
to the deadline set by the caller of blk_mq_delay_queue().
Subsequent attempts to queue a queue run will find the work
item already pending, and direct runs will see a stopped queue
as before.

Case 2 is handled by adding a new bit, BLK_MQ_S_START_ON_RUN,
that tells the work handler that it should clear a stopped
queue and run the handler.

Reviewed-by: Bart Van Assche <Bart.VanAssche@sandisk.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
diff --git a/block/blk-core.c b/block/blk-core.c
index 64b6e58..24886b6 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -268,10 +268,8 @@
 		struct blk_mq_hw_ctx *hctx;
 		int i;
 
-		queue_for_each_hw_ctx(q, hctx, i) {
+		queue_for_each_hw_ctx(q, hctx, i)
 			cancel_delayed_work_sync(&hctx->run_work);
-			cancel_delayed_work_sync(&hctx->delay_work);
-		}
 	} else {
 		cancel_delayed_work_sync(&q->delay_work);
 	}
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 5c68fce..a0bdf63 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1221,7 +1221,6 @@
 void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx)
 {
 	cancel_delayed_work_sync(&hctx->run_work);
-	cancel_delayed_work(&hctx->delay_work);
 	set_bit(BLK_MQ_S_STOPPED, &hctx->state);
 }
 EXPORT_SYMBOL(blk_mq_stop_hw_queue);
@@ -1279,27 +1278,39 @@
 	struct blk_mq_hw_ctx *hctx;
 
 	hctx = container_of(work, struct blk_mq_hw_ctx, run_work.work);
+
+	/*
+	 * If we are stopped, don't run the queue. The exception is if
+	 * BLK_MQ_S_START_ON_RUN is set. For that case, we auto-clear
+	 * the STOPPED bit and run it.
+	 */
+	if (test_bit(BLK_MQ_S_STOPPED, &hctx->state)) {
+		if (!test_bit(BLK_MQ_S_START_ON_RUN, &hctx->state))
+			return;
+
+		clear_bit(BLK_MQ_S_START_ON_RUN, &hctx->state);
+		clear_bit(BLK_MQ_S_STOPPED, &hctx->state);
+	}
+
 	__blk_mq_run_hw_queue(hctx);
 }
 
-static void blk_mq_delay_work_fn(struct work_struct *work)
-{
-	struct blk_mq_hw_ctx *hctx;
-
-	hctx = container_of(work, struct blk_mq_hw_ctx, delay_work.work);
-
-	if (test_and_clear_bit(BLK_MQ_S_STOPPED, &hctx->state))
-		__blk_mq_run_hw_queue(hctx);
-}
 
 void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs)
 {
 	if (unlikely(!blk_mq_hw_queue_mapped(hctx)))
 		return;
 
+	/*
+	 * Stop the hw queue, then modify currently delayed work.
+	 * This should prevent us from running the queue prematurely.
+	 * Mark the queue as auto-clearing STOPPED when it runs.
+	 */
 	blk_mq_stop_hw_queue(hctx);
-	kblockd_schedule_delayed_work_on(blk_mq_hctx_next_cpu(hctx),
-			&hctx->delay_work, msecs_to_jiffies(msecs));
+	set_bit(BLK_MQ_S_START_ON_RUN, &hctx->state);
+	kblockd_mod_delayed_work_on(blk_mq_hctx_next_cpu(hctx),
+					&hctx->run_work,
+					msecs_to_jiffies(msecs));
 }
 EXPORT_SYMBOL(blk_mq_delay_queue);
 
@@ -1885,7 +1896,6 @@
 		node = hctx->numa_node = set->numa_node;
 
 	INIT_DELAYED_WORK(&hctx->run_work, blk_mq_run_work_fn);
-	INIT_DELAYED_WORK(&hctx->delay_work, blk_mq_delay_work_fn);
 	spin_lock_init(&hctx->lock);
 	INIT_LIST_HEAD(&hctx->dispatch);
 	hctx->queue = q;
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index c7cc903..f3e5e1d 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -51,8 +51,6 @@
 
 	atomic_t		nr_active;
 
-	struct delayed_work	delay_work;
-
 	struct hlist_node	cpuhp_dead;
 	struct kobject		kobj;
 
@@ -168,6 +166,7 @@
 	BLK_MQ_S_TAG_ACTIVE	= 1,
 	BLK_MQ_S_SCHED_RESTART	= 2,
 	BLK_MQ_S_TAG_WAITING	= 3,
+	BLK_MQ_S_START_ON_RUN	= 4,
 
 	BLK_MQ_MAX_DEPTH	= 10240,