On Monday 18 July 2011 19:39, Roland Dreier wrote:
> On Mon, Jul 18, 2011 at 9:35 AM, Hefty, Sean wrote:
> >> - if (ret && !IS_ERR(id_priv->cm_id.ib)) {
> >> + if (ret && !IS_ERR(id)) {
> >> ib_destroy_cm_id(id_priv->cm_id.ib);
> >
> > I would change the above line to ib_dest
On Mon, Jul 18, 2011 at 12:20:01PM -0700, Roland Dreier wrote:
> > Why is that test even in libmlx4?
>
> We need some way for userspace drivers to know which devices to bind.
Hum, for some reason I thought it was already keying off the sysfs
driver entry:
$ readlink class/infiniband_verbs/uverbs
Thanks, applied.
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
> There seems to be disagreement about whether to return 0, -ENOSYS or
> -EOPNOTSUPP for not supported functionality. Does the patch below make sense ?
> Note: I don't have all the hardware necessary to test the patch below.
This makes sense to me, so I went ahead and applied it for 3.1 (minus
the
>>> What about the new CX3 device ID patch?
>
>> Did I ever get a final version of the libmthca and kernel patches?
>
> CX3 is using libmlx4 and not libmthca.
> Vlad sent a patch on 1/19/11:
> http://www.spinics.net/lists/linux-rdma/msg07237.html
Sorry, I meant libmlx4 of course.
So that patch in
> Why is that test even in libmlx4?
We need some way for userspace drivers to know which devices to bind.
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.htm
> See net-next-2.6, I already took care of this stuff last night during my
> neigh layer cleanups.
I see the changes. Thanks!
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.o
From: "Hefty, Sean"
Date: Mon, 18 Jul 2011 18:29:46 +
> Reported by Dave Miller:
>
> In drivers/infiniband/core/addr.c:
>
> neigh = dst->neighbour;
> if (!neigh || !(neigh->nud_state & NUD_VALID)) {
> neigh_event_send(dst->neighbour, NULL);
> ret = -E
Reported by Dave Miller:
In drivers/infiniband/core/addr.c:
neigh = dst->neighbour;
if (!neigh || !(neigh->nud_state & NUD_VALID)) {
neigh_event_send(dst->neighbour, NULL);
ret = -ENODATA;
goto put;
}
neigh_event_send() can
Devesh Sharma wrote,
>Hello List,
>Kindly someone help me on this. I need to know about promiscuous mode
>support in IPoIB and have a confusion if it is possible at all on
>IPoIB stack. If yes then How?
I am not sure that it is supported, but Eli would know for sure.
--
To unsubscribe from this
On Mon, Jul 18, 2011 at 08:42:25AM +, Tziporet Koren wrote:
> CX3 is using libmlx4 and not libmthca.
> Vlad sent a patch on 1/19/11:
> http://www.spinics.net/lists/linux-rdma/msg07237.html
> Is contain adding several device IDs including CX3
Why is that test even in libmlx4?
Maybe this is a
On Mon, Jul 18, 2011 at 9:35 AM, Hefty, Sean wrote:
>> - if (ret && !IS_ERR(id_priv->cm_id.ib)) {
>> + if (ret && !IS_ERR(id)) {
>> ib_destroy_cm_id(id_priv->cm_id.ib);
>
> I would change the above line to ib_destroy_cm_id(id) to align the destroy
> call with the if statemen
> Avoid assigning an IS_ERR value to the cm id pointer in the cma_id object.
> This fixes a few anomalies in the error flow, and eliminates the need to
> test for the IS_ERR value every time we wish to determine if the cma_id object
> has a cm device associated with it.
>
> Also, eliminate the now
Signed-off-by: Hal Rosenstock
---
diff --git a/doc/todo b/doc/todo
index bbb9698..8a5ff14 100644
--- a/doc/todo
+++ b/doc/todo
@@ -8,20 +8,18 @@
5 051207 - Client reregistration is indicated before SA is
ready to accept subscriptions
6 060109 - Use LID routing for lig
to accomodate IBA extended link speeds
Also, some other cosmetic changes (formatting, etc.)
Signed-off-by: Hal Rosenstock
---
diff --git a/include/iba/ib_types.h b/include/iba/ib_types.h
index b713f33..ea08f51 100644
--- a/include/iba/ib_types.h
+++ b/include/iba/ib_types.h
@@ -1,6 +1,6 @@
/*
Hello List,
Kindly someone help me on this. I need to know about promiscuous mode
support in IPoIB and have a confusion if it is possible at all on
IPoIB stack. If yes then How?
On Fri, Jun 24, 2011 at 11:19 AM, Devesh Sharma wrote:
> Hello list,
>
> does IPoIB supports promiscuous mode? Is it p
>> What about the new CX3 device ID patch?
> Did I ever get a final version of the libmthca and kernel patches?
CX3 is using libmlx4 and not libmthca.
Vlad sent a patch on 1/19/11:
http://www.spinics.net/lists/linux-rdma/msg07237.html
Is contain adding several device IDs including CX3
Do you
17 matches
Mail list logo