Re: [PATCH v2 0/3] new ib_drain_qp() API

[Bart Van Assche <bart.vanassche-XdAiOPVOjttBDgjK7y7TUQ@public.gmane.org>]

On 02/11/16 02:46, Sagi Grimberg wrote:
>>> I'd suggest to look at the CQ context and act accordingly, something
>>> like:
>>>
>>>      if (cq->poll_ctx == IB_POLL_DIRECT) {
>>>          while (!wait_for_completion_timeout(&sdrain.done,
>>>                  mescs_to_jiffies(100))
>>>              ib_process_cq_direct(cq, 1024)
>>>      } else {
>>>          wait_for_completion(&sdrain.done);
>>>      }
>>>
>>> Thoughts?
>>
>> Hello Sagi,
>>
>> The above code will only work as expected if the caller won't call
>> ib_process_cq_direct() for the same queue from another context.
>
> Why? ib_poll_cq is safe from multiple contexts. Is it because the
> completion structures are on stack? because if so we can easily move
> them to the cq...

Hello Sagi,

The srp_send_done() function accesses the ch->free_tx list without 
locking. This is safe because all existing 
ib_process_cq_direct(ch->send_cq, ...) calls occur while holding 
ch->lock. The approach suggested above breaks that assumption.

Bart.
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html