[openib-general] [PATCH 3/4] IB CM: register and handle COMM_EST events on a QP

[Or Gerlitz]

Sean Hefty wrote:
>> +/**
>> + * ib_cm_establish - Forces a connection state to established.
>> + * @cm_id: Connection identifier to transition to established.
>> + *
>> + * This routine should be invoked by users who receive messages on a
>> + * connected QP before an RTU has been received.
>> + */
>> +int ib_cm_establish(struct ib_cm_id *cm_id);
>>
>> As with your patch ib_cm_establish is now called internally from within
>> the CM with the suggested solution good for both user and kernel space
>> connections/qps, how about removing it from the API?
> 
> I thought about removing it, but it changes the ABI, and existing users may
> still want to call ib_cm_establish() after processing a receive completion.
> This will let them immediately send a response without waiting for either the
> RTU or the COMM_EST event.

there are three types of CM/VERBS consumers:

1) work over the CM/VERBS
2) work over the CMA/VERBS with the CMA doing the QP state changes
3) work over the CMA/VERBS with the ULP doing the QP state changes

Your patch provides ***full*** solution for type 2 consumers. Type 3 
consumers can't call ib_cm_establish since they don't interact with the 
CM, as for type 1 consumers, looking on the CM code i was not able to 
convince myself that calling ib_cm_establish along with modifying the qp 
state to RTS would provide a full solution for them, what do you think?

Or.