[openib-general] [PATCH] Initial checkin of userspace MAD access

[Roland Dreier]

    Johannes> Does the device name need to have the HCA driver name in
    Johannes> it? Also, the u in umad is implied.

Good point, I'll change the docs to suggest no "u."

    Johannes> Wouldn't it be more appropriate to do something like
    Johannes> this:

    Johannes> /dev/infiniband/hca0/mad1

Maybe, but:
 - How does userspace know which device hca0 corresponds to?  Right
   now, mthca0 can be looked up under /sys/class/infiniband.
 - Do we need to do switch0 etc. for switches?

Of course the mthca driver could be updated to register itself using
hcaN names instead of mthcaN names, which would solve things fairly
transparently.

    Johannes> or maybe even:

    Johannes> /dev/ib/hca0/mad1

I don't like /dev/ib/ because I think "ib" is a little generic.  So I
prefer the more verbose but unambiguous "infiniband" name.

 - Roland