[openib-general] SMI Patch

[Hal Rosenstock]

Hi,

I have a patch which I think fixes the SMI issues for an end node. There
is more to be done for switch support but this hopefully is sufficient
for SM support. Can you please validate it before I check it in ? I'm a
little gun shy about breaking the tree after last week's debacle. If it
works in your configurations, I will check it in.

Thanks.

-- Hal

Index: smi.c
===================================================================
--- smi.c	(revision 1247)
+++ smi.c	(working copy)
@@ -98,6 +98,9 @@
 		}
 
 		/* C14-13:4 -- hop_ptr = 0 -> should have gone to SM */
+		if (hop_ptr == 0)
+			return 1;
+
 		/* C14-13:5 -- Check for unreasonable hop pointer */
 		return 0;
 	}
Index: mad.c
===================================================================
--- mad.c	(revision 1245)
+++ mad.c	(working copy)
@@ -1121,7 +1121,7 @@
 					    port_priv->device->phys_port_cnt))
 			goto out;
 		if (!smi_check_forward_dr_smp(smp))
-			goto out;
+			goto local;
 		if (!smi_handle_dr_smp_send(smp,
 					    port_priv->device->node_type,
 					    port_priv->port_num))
@@ -1132,6 +1132,7 @@
 			goto out;
 	}
 
+local:
 	/* Give driver "right of first refusal" on incoming MAD */
 	if (port_priv->device->process_mad) {
 		int ret;