[openib-general] [PATCH] librdmacm: fix bug causing failure to work with partial membership pkey

[Sean Hefty]

>My understanding is that when an IPoIB broadcast domain contains both
>partial and full members (*) attempts to communicate between two partial
>members would silently fail, does this silence is something you think we
>should work to change?

I'm looking at this from a different view than just ipoib multicast groups.  For
example, can two users of the ib_cm successfully establish a connection, but not
actually be able to transfer data between each other?  This seems possible,
though unlikely.  This is the type of silent failure I'm referring to.

Without this patch, two clients that try to connect using the librdmacm will
fail.  That failure is reported to the user.  With this patch, the connection
would be created, but I don't think that it guarantees that communication can
actually occur.  I don't want to mask a configuration issue.

>My thinking is that if in the end of this thread we are willing to move
>forward without changing ib_find_cached_pkey() then this patch should be
>merged.

I'm still unsure about where the cause of this problem lies.  It may be that the
kernel rdma_cm or rdma_ucm needs to change if we decide the ib_find_cached_pkey
is correct.

- Sean