[openib-general] [PATCH RFC] return qp pointer as part of ib_wc

[Or Gerlitz]

Michael S. Tsirkin wrote:
>> This sentence refers to your use case description, not to what this 
>> patch is doing. And again, when SRQ is used, the IB consumer can not 
>> stick a per QP context to the WR on post recv time b/c you can't tell on 
>> behalf of which QP the SRQ would consume the WR, is it clearer now?

> OK, but how does this refer to the use case description?

it comes to say that your multiple QPs per CQ use case description is in 
away not accurate since you actually have SRQ per multiple QPs and this 
is the point why with the current IB API you must have to maintain an 
association between wc->QPN to QP structure, anyway:

>>> All my patch does is, put struct ib_qp * instead of qp_num in ib_wc -
>>> this is more useful for ULPs and turns out not to have extra cost
>>> for low-level drivers.

>> sure, it makes sense to me, it can help any IB ULP that uses SRQ or uses 
>> the same CQ to report completions from multiple QPs.

> And that's exactly what IPoIB CM does.

does in the code which is not posted.


>>> To detect stale (unused) connections and remove them.
>>> I have not pushed this code yet.

>> So you don't really have a use case which is based on code that can be 
>> reviewed (or can it be reviewed from your openfabrics GIT?)

> Well, I did note the patch is untested.
> I'm testing the code in question, and plan to push to openfabrics RSN.
> I'll post a patch as well.

OK

>> that the logic you suggest comes into play when wc->status is not 
>> success as i have guessed.

> No, I want to have an LRU list of pages.

OK