[PATCH] nvmet-rdma: Release connections synchronously

[Bart Van Assche]

On 5/17/23 00:42, Sagi Grimberg wrote:
> On 5/11/23 18:03, Bart Van Assche wrote:
>> @@ -1582,11 +1566,6 @@ static int nvmet_rdma_queue_connect(struct 
>> rdma_cm_id *cm_id,
>>           goto put_device;
>>       }
>> -    if (queue->host_qid == 0) {
>> -        /* Let inflight controller teardown complete */
>> -        flush_workqueue(nvmet_wq);
>> -    }
>> -
>>       ret = nvmet_rdma_cm_accept(cm_id, queue, &event->param.conn);
>>       if (ret) {
>>           /*
> 
> You could have simply removed this hunk alone to make lockdep quiet on
> this, without the need to rework the async queue removal.
> 
> The flush here was added to prevent a reset/connect/disconnect storm
> causing the target to run out of resources (which we have seen reports
> about in the distant past). What prevents it now?
> 
> And you both reworked the teardown, and still removed the flush, I don't
> get why both are needed.

Hi Sagi,

My understanding is that the above flush_workqueue() call waits for 
prior release_work to complete. If the release_work instance is removed, 
I don't think that the above flush_workqueue() call is still necessary.

This patch prevents that the target runs out of resources by releasing 
connections synchronously instead of asynchronously.

Does the above answer your questions?

Bart.