[ofa-general] [PATCH v2] IB/mlx4: Add send with invalidate support

[Eli Cohen]

On Sun, 2008-05-18 at 08:59 +0300, Or Gerlitz wrote:
> Is it correct that "cqe->immed_rss_invalid" equals 
> "wr->ex.invalidate_rkey" that was provided at the sender? if yes, any 
> reason not to have the same/similar union (imm_data/invalidate_rkey) 
> also for the work completion structure?
No reason for them to be different. Roland already suggested to use a
union here although he defines the union locally inside the containing
struct thus he has two definitions for the same union. Roland do you
intend to commit that?