[openib-general][PATCH][SRP] bug fixes & fmr supported,

[Roland Dreier]

Thanks, I haven't read all the FMR stuff through yet, but a few quick comments:

    > + support more than default 8 luns per target. Should we have max_luns
    > as module param? How about cmds_per_lun, max_sectors, max_targets as
    > module params as well

I think it makes more sense to handle this the same way I handled
max_sectors: make it a per-target parameter passed in when connecting
to the target.  We could make cmds_per_lun a similar parameter, but
are there likely to be any SRP targets that need this to be limited?
Also, what is max_targets?

    > + fix the srp_free_iu free NULL pointer - due to srp_connect_target fail
    > with target->state other than PORT(DLID)_REDIRECT

Yes, good catch.

    > + fix the bug of reuse the iu while it's still in_use

I think I see the bug: a send may complete and have its IU recycled
before the corresponding command is completed, and end up screwing
things up.  Is this right?

If so I would prefer to fix things in a slightly different way.
Rather than a TX ring, we should just keep a list of free IUs ready to
send and only add IUs to the end of the list when we're really done
with the IU.

    > + support FMR - srp_map_fmr (if map_fmr failed then fall back to normal
    > indirect mode using global r_key)

This is good to have.  I still need to read the code.

 - R.