Hi Corey, Thanks for the review.
>> IPMI folks: the IPMI driver could do with a little review, as it's >> not a conventional BT/KCS/SMI SI, in that the low-level send/recv >> interface will handle the entire message at once. > > Handling the entire message at once should be fine, as that's what > this driver level is designed to do for the message handler. That > part all looks correct. The code itself looks good, but I have a > couple of high-level comments. > > The driver at this level can receive more than one message to handle > at a time, so it needs some sort of queue. This is to allow multiple > users and to allow the message handler to send its own commands while > other commands are going on. You might argue that the queuing should > be done in ipmi_msghandler, and you would probably be right. Ah, that's what I'd been assuming was being done - I missed the xmit_list in the si_intf code. It'd be great if this could be in the generic msghandler code, otherwise I'd just be duplicating the si_intf logic. > I'll look at doing that. If that is the case, then your NULL check > for current message should probably be a BUG_ON(). OK, I'll update this when the msghandler bit is implemented. > Do you need to handle any BMC flags? Particularly incoming events? Not at this stage - we may in future though. Cheers, Jeremy _______________________________________________ Linuxppc-dev mailing list Linuxppc-dev@lists.ozlabs.org https://lists.ozlabs.org/listinfo/linuxppc-dev
