[openib-general] [PATCH] validate MADs issued from userspace for spec compliance C13-18.1.1

[Sean Hefty]

>> This should work if we can determine whether the SEND is a new operation or a
>> response to some other request.
>
>Isn't ib_response_mad doing this?

It should.  We just need to ensure that it identifies the MADs correctly.

>> After further testing, this patch breaks osmtest as a result of modifying the
>> TID for a SEND.
>
>What does the test do?

Hmm... I just reran the test, and it worked now.  Now I'm really confused as to
what the problem was.  The SM / SA classes don't use SENDs, so I was struggling
to understand the issue.  Maybr I'm hitting into some sort of SM conflict that
takes a while to resolve itself...

>> I could just ignore SENDs like the existing code did, but I'm
>> not convinced that that's the right thing to do.
>
>What does Jack's patch do?

Jack's patch operated beneath the MAD interface, so left the TIDs unchanged.  It
relied on user_mad to set the TIDs correctly.

- Sean