Re: [PATCH v2 2/3] block: fix ordering between checking QUEUE_FLAG_QUIESCED and adding requests

[Muchun Song]

> On Sep 11, 2024, at 11:54, Ming Lei <ming.lei@xxxxxxxxxx> wrote:
> 
> On Tue, Sep 10, 2024 at 07:22:16AM -0600, Jens Axboe wrote:
>> On 9/3/24 2:16 AM, Muchun Song wrote:
>>> Supposing the following scenario.
>>> 
>>> CPU0                                        CPU1
>>> 
>>> blk_mq_insert_request()         1) store    blk_mq_unquiesce_queue()
>>> blk_mq_run_hw_queue()                       blk_queue_flag_clear(QUEUE_FLAG_QUIESCED)   3) store
>>>    if (blk_queue_quiesced())   2) load         blk_mq_run_hw_queues()
>>>        return                                      blk_mq_run_hw_queue()
>>>    blk_mq_sched_dispatch_requests()                    if (!blk_mq_hctx_has_pending()) 4) load
>>>                                                           return
>>> 
>>> The full memory barrier should be inserted between 1) and 2), as well as
>>> between 3) and 4) to make sure that either CPU0 sees QUEUE_FLAG_QUIESCED is
>>> cleared or CPU1 sees dispatch list or setting of bitmap of software queue.
>>> Otherwise, either CPU will not re-run the hardware queue causing starvation.
>>> 
>>> So the first solution is to 1) add a pair of memory barrier to fix the
>>> problem, another solution is to 2) use hctx->queue->queue_lock to synchronize
>>> QUEUE_FLAG_QUIESCED. Here, we chose 2) to fix it since memory barrier is not
>>> easy to be maintained.
>> 
>> Same comment here, 72-74 chars wide please.
>> 
>>> diff --git a/block/blk-mq.c b/block/blk-mq.c
>>> index b2d0f22de0c7f..ac39f2a346a52 100644
>>> --- a/block/blk-mq.c
>>> +++ b/block/blk-mq.c
>>> @@ -2202,6 +2202,24 @@ void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs)
>>> }
>>> EXPORT_SYMBOL(blk_mq_delay_run_hw_queue);
>>> 
>>> +static inline bool blk_mq_hw_queue_need_run(struct blk_mq_hw_ctx *hctx)
>>> +{
>>> + 	bool need_run;
>>> +
>>> + 	/*
>>> + 	 * When queue is quiesced, we may be switching io scheduler, or
>>> + 	 * updating nr_hw_queues, or other things, and we can't run queue
>>> + 	 * any more, even blk_mq_hctx_has_pending() can't be called safely.
>>> + 	 *
>>> + 	 * And queue will be rerun in blk_mq_unquiesce_queue() if it is
>>> + 	 * quiesced.
>>> + 	 */
>>> + 	__blk_mq_run_dispatch_ops(hctx->queue, false,
>>> + 		need_run = !blk_queue_quiesced(hctx->queue) &&
>>> +       	blk_mq_hctx_has_pending(hctx));
>>> + 	return need_run;
>>> +}
>> 
>> This __blk_mq_run_dispatch_ops() is also way too wide, why didn't you
>> just break it like where you copied it from?
>> 
>>> +
>>> /**
>>>  * blk_mq_run_hw_queue - Start to run a hardware queue.
>>>  * @hctx: Pointer to the hardware queue to run.
>>> @@ -2222,20 +2240,23 @@ void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
>>> 
>>> might_sleep_if(!async && hctx->flags & BLK_MQ_F_BLOCKING);
>>> 
>>> - 	/*
>>> - 	 * When queue is quiesced, we may be switching io scheduler, or
>>> - 	 * updating nr_hw_queues, or other things, and we can't run queue
>>> - 	 * any more, even __blk_mq_hctx_has_pending() can't be called safely.
>>> - 	 *
>>> - 	 * And queue will be rerun in blk_mq_unquiesce_queue() if it is
>>> - 	 * quiesced.
>>> - 	 */
>>> - 	__blk_mq_run_dispatch_ops(hctx->queue, false,
>>> - 		need_run = !blk_queue_quiesced(hctx->queue) &&
>>> - 		blk_mq_hctx_has_pending(hctx));
>>> + 	need_run = blk_mq_hw_queue_need_run(hctx);
>>> + 	if (!need_run) {
>>> + 		unsigned long flags;
>>> 
>>> - 	if (!need_run)
>>> - 		return;
>>> + 	/*
>>> + 	 * synchronize with blk_mq_unquiesce_queue(), becuase we check
>>> + 	 * if hw queue is quiesced locklessly above, we need the use
>>> + 	 * ->queue_lock to make sure we see the up-to-date status to
>>> + 	 * not miss rerunning the hw queue.
>>> + 	 */
>>> + 	spin_lock_irqsave(&hctx->queue->queue_lock, flags);
>>> + 	need_run = blk_mq_hw_queue_need_run(hctx);
>>> + 	spin_unlock_irqrestore(&hctx->queue->queue_lock, flags);
>>> +
>>> + 	if (!need_run)
>>> + 		return;
>>> + }
>> 
>> Is this not solvable on the unquiesce side instead? It's rather a shame
>> to add overhead to the fast path to avoid a race with something that's
>> super unlikely, like quisce.
> 
> Yeah, it can be solved by adding synchronize_rcu()/srcu() in unquiesce
> side, but SCSI may call it in non-sleepable context via scsi_internal_device_unblock_nowait().

Hi Ming and Jens,

I use call_srcu/call_rcu to make it non-sleepable. Does this make sense to you?

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 12bf38bec1044..86cdff28b2ce6 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -247,6 +247,13 @@ void blk_mq_quiesce_queue(struct request_queue *q)
 }
 EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue);

+static void blk_mq_run_hw_queues_rcu(struct rcu_head *rh)
+{
+       struct request_queue *q = container_of(rh, struct request_queue,
+                                              rcu_head);
+       blk_mq_run_hw_queues(q, true);
+}
+
 /*
  * blk_mq_unquiesce_queue() - counterpart of blk_mq_quiesce_queue()
  * @q: request queue.
@@ -269,8 +276,13 @@ void blk_mq_unquiesce_queue(struct request_queue *q)
        spin_unlock_irqrestore(&q->queue_lock, flags);

        /* dispatch requests which are inserted during quiescing */
-       if (run_queue)
-               blk_mq_run_hw_queues(q, true);
+       if (run_queue) {
+               if (q->tag_set->flags & BLK_MQ_F_BLOCKING)
+                       call_srcu(q->tag_set->srcu, &q->rcu_head,
+                                 blk_mq_run_hw_queues_rcu);
+               else
+                       call_rcu(&q->rcu_head, blk_mq_run_hw_queues_rcu);
+       }
 }
 EXPORT_SYMBOL_GPL(blk_mq_unquiesce_queue);

> 
> 
> Thanks,
> Ming