On Mon, 1 Nov 2004 15:01:26 -0800
Shirley Ma <[EMAIL PROTECTED]> wrote:
> I am using my unix account to send the patch. Hope it works.
>
> diff -urN access/mad.c access.patch2/mad.c
> --- access/mad.c 2004-11-01 14:51:41.356902216 -0800
> +++ access.patch2/mad.c 2004-11-01 14:53:37.003321288 -0800
> @@ -368,16 +368,15 @@
> struct ib_mad_agent_private *mad_agent_priv;
> struct ib_mad_port_private *port_priv;
>
> - cur_send_wr = send_wr;
> /* Validate supplied parameters */
> if (!mad_agent || !send_wr) {
> - *bad_send_wr = cur_send_wr;
> + *bad_send_wr = send_wr;
> return -EINVAL;
> }
>
> if (!mad_agent->send_handler ||
> (send_wr->wr.ud.timeout_ms && !mad_agent->recv_handler)) {
> - *bad_send_wr = cur_send_wr;
> + *bad_send_wr = send_wr;
> return -EINVAL;
> }
Patch looks good to me, and should be applied
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. As a minor optimization, we could make bad_send_wr
optional for cases where only a single work request is being posted.
- Sean
_______________________________________________
openib-general mailing list
[EMAIL PROTECTED]
http://openib.org/mailman/listinfo/openib-general
To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
