[ofa-general] Re: [PATCH] IB/core: Add comletion flag for send with invalidate

[Roland Dreier]

Never mind... I see that this is for the corresponding receive on the
other side.  But:

 > +			/*
 > +			 * TBD: maybe we should just call this ieth_val
 > +			 */
 > +			wc->imm_data = be32_to_cpu(cqe->immed_rss_invalid);

I think we should make the wc->imm_data handling a union like with did
for the work request structure.

If we call it ieth_val I think it's too hard for anyone to understand,
and it is IB-specific (iWARP has no IETH of course).

 - R.