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

[Michael S. Tsirkin]

> 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:

I'm sorry, you lost me here. Was something supposed to come after the column?

Anyway, at some point you said you see the point of the patch. If that's still so,
there's no reason to argue about wording, that's all the use case was supposed to
provide.

-- 
MST