On Mon, 2004-11-01 at 18:06, Sean Hefty wrote: > It raises an issue with the current code, though. There are checks for > a valid mad_agent, valid_wr, but not a valid *bad_send_wr. I'm > wondering if we should convert these checks to BUG_ON, or add in a check > for a *bad_send_wr.
I don't think this is an "or". A check for *bad_send_wr should be added (which might be changed based on the below question). I will post a patch for this. IMO these should be BUG_ON but just errors as these are localized coding errors in some client. > As a minor optimization, we could make bad_send_wr > optional for cases where only a single work request is being posted. If *bad_send_wr is to be validated, the only time when NULL is allowed is when there is only one send_wr. Wouldn't this nullify any savings (unless the validation is removed) ? -- Hal _______________________________________________ openib-general mailing list [EMAIL PROTECTED] http://openib.org/mailman/listinfo/openib-general To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
