Don't worry about p2p_type if peer2peer itself is not requested
in the first place.
Signed-off-by: Kumar Sanghvi
---
drivers/infiniband/hw/cxgb4/cm.c |2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4
Hi Arlin,
Did you get a chance to look into this further?
Also, will you be releasing a new version of dapl with the two patches
provided earlier to OFED-1.5.4 ?
Thanks,
Kumar.
On 11/22/2011 12:41 PM, Kumar Sanghvi wrote:
Hi Arlin,
On 11/22/2011 01:51 AM, Davis, Arlin R wrote:
Can you
Fix logic so that we don't retry with MPAv1 once we have
done that already.
Else, we end up retrying with MPAv1 even when its not needed
on getting peer aborts - and this could lead to kernel panic.
Signed-off-by: Kumar Sanghvi
---
drivers/infiniband/hw/cxgb4/cm.c |4 +++-
1 files ch
Hi Arlin,
On 11/22/2011 01:51 AM, Davis, Arlin R wrote:
Can you send me your scripts so I can attempt to duplicate?
Find attached the script with this mail.
Did this test setup run successfully before OFED 1.5.4 RC3 release?
I am not sure when it stopped working.
However, we have been runnin
Hi,
On 11/19/2011 05:18 AM, Davis, Arlin R wrote:
#0 dapl_llist_remove_entry (head=0x636960, entry=0x70004bf8) at
[...]
You should have seen a message like "WARNING: overflow event on EVD".
It appears that the default dapltest server allocates too small of a CR EVD for
many client
Hi All,
I am trying to debug a segfault observed on dapltest-server with OFED-1.5.4.
I am using the daily-build OFED-1.5.4-2016-0600 for this test.
The test setup involves 4 machines connected via switch.
1 machine acts as dapltest-server while rest 3 machines act as dapltest clients.
We are
Hi Roland,
On Fri, Oct 28, 2011 at 10:59:47 -0700, Roland Dreier wrote:
> On Thu, Oct 20, 2011 at 10:18 AM, Felix Marti wrote:
> > Don't add stuff to the t4fw_interface.h, that is owned by firmware.
>
> Vipul, do you plan to respin to handle Felix's comment?
>
> - R.
Vipul is on leave, so repl
From: Tom Tucker
The QP needs to be moved to error before telling the firwmare
to shutdown the queue. Otherwise, the application can submit
WR that will never get fetched by the hardware and never
flushed by the driver.
Signed-off-by: Kumar Sanghvi
---
drivers/infiniband/hw/cxgb4/qp.c |4
ld be active.
Such problem was reported by Parav Pandit for
iw_cxgb4 driver. Based on discussion between Parav Pandit and Steve Wise,
this patch aims to correct above problem by serializing the calls to cq's
comp_handler using a spin_lock.
Signed-off-by: Kumar Sanghvi
---
drivers/infiniban
it
Signed-off-by: Kumar Sanghvi
---
drivers/infiniband/hw/cxgb4/cq.c |1 +
drivers/infiniband/hw/cxgb4/ev.c | 10 --
drivers/infiniband/hw/cxgb4/iw_cxgb4.h |1 +
drivers/infiniband/hw/cxgb4/qp.c | 15 +--
4 files changed, 23 insertions(+), 4 deletion
On Thu, Oct 20, 2011 at 12:30:08 -0500, Steve Wise wrote:
> On 10/20/2011 12:25 PM, parav.pan...@emulex.com wrote:
> >You are right, cq_lock will result into dead lock.
> >Should there be a additional compl_handler spin_lock?
> >I was measuring performance impact for adding it, and, irq_save() and
At the time when peer closes connection, iw_cxgb4 will not
send a cq event if ibqp.uobject exists. In that case, its possible
for user application to get blocked in ibv_get_cq_event.
To resolve this, call the cq's comp_handler to unblock any read
from ibv_get_cq_event.
Signed-off-by:
Hi Roland,
On Mon, Oct 03, 2011 at 20:19:31 +0530, Kumar Sanghvi wrote:
> Hi Roland,
>
> On 09/25/2011 08:17 PM, Kumar Sanghvi wrote:
> >This series adds support for MPA V2 Enhanced RDMA Negotiation
> >protocol.
> >Details about the protocol are available a
Hi Roland,
On 09/25/2011 08:17 PM, Kumar Sanghvi wrote:
This series adds support for MPA V2 Enhanced RDMA Negotiation
protocol.
Details about the protocol are available at below IETF Draft:
http://www.ietf.org/id/draft-ietf-storm-mpa-peer-connect-06.txt
To brief on MPA V2:
1) It allows two
As part of MPAv2 Enhanced RDMA Negotiation, pass max supported
ird/ord values upwards for the time-being in iw-cxgb3 and
amso1100.
Signed-off-by: Kumar Sanghvi
---
drivers/infiniband/hw/amso1100/c2_ae.c |5 +
drivers/infiniband/hw/amso1100/c2_intr.c |5 +
drivers/infiniband/hw
responder perspective:
-process_mpa_request
-send_mpa_reply
-c4iw_accept_cr
-passes ird/ord to upper layers
Signed-off-by: Kumar Sanghvi
---
drivers/infiniband/hw/cxgb4/cm.c | 469 +---
drivers/infiniband/hw/cxgb4/iw_cxgb4.h | 22 ++-
drivers/infiniband/hw/cxgb4
Updates iw_cm_event to support propagating the ird/or
values upwards to the application
Signed-off-by: Kumar Sanghvi
---
drivers/infiniband/core/cma.c |8 ++--
include/rdma/iw_cm.h |2 ++
2 files changed, 8 insertions(+), 2 deletions(-)
diff --git a/drivers/infiniband/core
Intel and Chelsio, using basic test tools like
rping and rdma_bw.
---
Kumar Sanghvi (3):
iw_cm: Propagate ird/ord values upwards
iw_cxgb4: Add support for MPA V2 Enhanced RDMA Negotiation
amso1100/iw_cxgb3: Minimal MPAv2 support
Tatyana (1):
RDMA/nes: Adds support for MPA frame Version 2
18 matches
Mail list logo
