[openib-general] Some Missing Features from mthca/user MAD access

[Roland Dreier]

> I know, I was thinking about modifying the f_ops and calling
> back to the original. A bit ugly ...

Keep in mind that we should be implementing solutions that are
acceptable upstream...

> Yes, I think it is. It involves catching CTRL-C in the application
> and other such horror, and it never works 100%.
> And what about running to opensms on the same HCA?
> I think it is clearly kernel's job to handle synchronisation and do cleanups
> when application exits.

OK, we can have a file for controlling capability bits.

> After consideration, I think the proper way is add a reference count
> and clean is_sm when it falls to 0.
> This way runnning two opensms on the same HCA and two different
> HCAs in the same subnet behaves the same.

I don't understand this.  IsSM is per-port, so what does it mean for the
reference count of IsSM for a port to be 2?  Two SMs are running on that
port?

> To do this, I think either and ioctl on umad, or
> a flag to open to set this bit is not too bad though.

I don't like either the ioctl() or a magic flag for open().  I'm
trying to decide
between a special issm file, or changing the umad file interface to put a
command code in the structure that is passed via write() (this would also
let us add a mechanism for canceling MADs).

 - R.