Re: [PATCH] IB/core: Don't drain the receive queue for srq attached queue-pair

[Steve Wise <swise-7bPotxP6k4+P2YhJcF5u+vpXobYPEAuW@public.gmane.org>]

On 4/26/2016 12:27 PM, Bart Van Assche wrote:
>>>>> Conversely, I would think that a consumer that uses SRQ
>>>>> would want a similar drain mechanism to guarantee there
>>>>> are no more posted Receives for the associated QP, and
>>>>> thus it is safe to destroy it.
>>>>
>>>> I don't think there is anything now that handles draining an SRQ, nor
>>>> ensuring a QP's RQEs are completed/consumed from its SRQ when draining
>>>> the QP.  Sounds like work is needed here.
>>>>
>>>> But are there any kernel SRQ consumers at this point?
>>>
>>> I think the following two:
>>>
>>> $ git grep -nHE '(ib|rdma)_create_srq' drivers/infiniband/ulp
>>> drivers/infiniband/ulp/ipoib/ipoib_cm.c:1521:    priv->cm.srq =
>>> ib_create_srq(priv->pd, &srq_init_attr);
>>> drivers/infiniband/ulp/srpt/ib_srpt.c:2723:    sdev->srq =
>>> ib_create_srq(sdev->pd, &srq_attr);
>>
>> If we make the requirement that the ib_drain_rq() caller must consume
>> all completions for all QPs attached to an SRQ if they are outstanding,
>> then I think we can modify ib_drain_rq() to post the drain recv WR to
>> the SRQ.  It should work, right?
>
> At least the ib_srpt driver already guarantees that no further receive
> completions will be generated before ib_destroy_qp() is called. But
> posting an additional receive WR on the SRQ from inside ib_drain_rq()
> shouldn't hurt.

Actually, after thinking more about this, posting anything to the SRQ 
will not force it to complete.  The only reason that works for a QP with 
an RQ is that the QP is in ERR state and thus the RECV WR gets completed 
with FLUSHED status.

So SRQ drain would require some other method...

Steve.



--
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