[openib-general] Re: [PATCH] ib_mad: prevent duplicateoutstanding MADtransactions with same TID

[Sean Hefty]

Michael S. Tsirkin wrote:
> Okay. But, note this affects ACKs as well as ABORTs (with multi-packet
> requests):
> 
> Host A sends an RMPP request message to host B with TID=3
> Host B sends an RMPP request message to host A with TID=3.
> Now if A generates an RMPP response it has TID=3.
> 
> If B sends ACK, host A has no idea which transaction is being ACKed.

Bah... can we distinguish which transaction is being ACKed by the response bit?

There's a slight difference between the ACK and abort.  ACKs always match with 
sends, whereas an abort can match with a send or receive.

> What kind of spec change do you envision?

Maybe having the abort carry whether a send or receive is being aborted?  We may 
need to start with identifying which stop/abort codes can match with sends and 
receives, then creating two codes.

- Sean