[PATCH 0/2] nvme: sanitize KATO handling

[Chao Leng]

On 2021/2/24 15:20, Chao Leng wrote:
> 
> 
> On 2021/2/24 15:06, Hannes Reinecke wrote:
>> On 2/24/21 7:42 AM, Chao Leng wrote:
>>>
>>>
>>> On 2021/2/23 20:07, Hannes Reinecke wrote:
>>>> Hi all,
>>>>
>>>> one of our customer had been running into a deadlock trying to terminate
>>>> outstanding KATO commands during reset.
>>>> Looking closer at it, I found that we never actually _track_ if a KATO
>>>> command is submitted, so we might happily be sending several KATO commands
>>>> to the same controller simultaneously.
>>> Can you explain how can send KATO commands simultaneously?
>>
>> Sure.
>> Call nvme_start_keep_alive() on a dead connection.
>> Just _after_ the KATO request has been sent,
>> call nvme_start_keep_alive() again.
> Call nvme_start_keep_alive() again? why?
> Now just nvme_start_ctrl call nvme_start_keep_alive().
> The ka_work will be canceled sync before start reconnection.
> Did I miss something?And all flight request will be canceled before start reconnection.
Is the request hang on block?
>>
>> You now have an expired KATO command, and the new KATO command, both are active and sent to the controller.
>>
>> Cheers,
>>
>> Hannes
> 
> _______________________________________________
> Linux-nvme mailing list
> Linux-nvme at lists.infradead.org
> http://lists.infradead.org/mailman/listinfo/linux-nvme
> .