[ofa-general] Re: [PATCH] core/cm: improve requestmessage interpretation of subnet local fields

[Sean Hefty]

>But using this hop limit this was is just a convention we have
>adopted. There is nothing in IBA that allows the active side to send a
>REQ with invalid GIDs/etc in any situation. The passive side should
>always be able to form a correct GRH based on any REQ.

I don't think TC and FL need to be valid, though I can't say off the top of my
head if that would break the connection.