[ofa-general] possible librdmacm bug?

[Steve Wise]

Sean,

The Lamprey guys uncovered a potential bug in the RDMA CM:

If an application binds to address 0, port 0 via a call to
rdma_bind_addr(), and then calls rdma_get_src_addr(), the port number is
still 0 even though the RDMA CM chose a port during the bind operation.
However, If the application then calls rdma_listen() followed by another
rdma_get_src_addr() call, then the actual port number is correctly
returned.  

But it should be returned in the call to rdma_get_src_addr() immediately
after the bind succeeds, yes?

I poked around the code and couldn't see an obvious bug.  I'm still
looking.  Shall I open a bug in the ofa bugzilla for this?

Thanks,

Steve.