[ofa-general] ibv_rc_pingpong hangs with forks

[Roland Dreier]

 > The attached modification to ibv_rc_pingpong makes it never complete.
 > 
 > Forking seems to do something bad. I noticed that forking right after
 > ibv_post_recv() "cancels" the posted WR (as if it was never issued):
 > sender keeps retrying.
 > 
 > Is it expected behavior or a bug?

Yes, forking is expected to cause issues.  Do things work better if you
set the environment variable IBV_FORK_SAFE=1 ?

 - R.