public inbox for linux-rdma@vger.kernel.org
 help / color / mirror / Atom feed
* help with IB_WC_MW_BIND_ERR
@ 2014-05-20 18:55 Chuck Lever
       [not found] ` <B34C7243-DCF8-472B-B156-9B8791F0F475-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
  0 siblings, 1 reply; 4+ messages in thread
From: Chuck Lever @ 2014-05-20 18:55 UTC (permalink / raw)
  To: linux-rdma

Hi-

What does it mean when a LOCAL_INV work request fails with a
IB_WC_MW_BIND_ERR completion?

--
Chuck Lever
chuck[dot]lever[at]oracle[dot]com



--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

^ permalink raw reply	[flat|nested] 4+ messages in thread

* Re: help with IB_WC_MW_BIND_ERR
       [not found] ` <B34C7243-DCF8-472B-B156-9B8791F0F475-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
@ 2014-05-20 19:39   ` Wendy Cheng
       [not found]     ` <CABgxfbHu8Wga6tX7iPyNb0aZaVY7XizAY_jpJW6+Nk2H9Gva5w-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
  2014-06-26 19:07   ` Shirley Ma
  1 sibling, 1 reply; 4+ messages in thread
From: Wendy Cheng @ 2014-05-20 19:39 UTC (permalink / raw)
  To: Chuck Lever; +Cc: linux-rdma

On Tue, May 20, 2014 at 11:55 AM, Chuck Lever <chuck.lever-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org> wrote:
> Hi-
>
> What does it mean when a LOCAL_INV work request fails with a
> IB_WC_MW_BIND_ERR completion?
>

Mapping an IB error code has been a great pain (at least for me)
unless you have access to the HCA firmware. In this case, I think it
implies memory protection error (registration issues).... say in cxgb4
driver, it is associated with invalidate shared MR or invalidate bound
memory window (with a QP):

                case T4_ERR_INVALIDATE_SHARED_MR:
                case T4_ERR_INVALIDATE_MR_WITH_MW_BOUND:
                        wc->status = IB_WC_MW_BIND_ERR;
                        break;

"drivers/infiniband/hw/cxgb4/cq.c" line 654 of 898 --72%-- col 11-25

You'll probably need to mention the HCA name so the firmware people,
if they are reading this, could pinpoint the exact cause.

-- Wendy
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

^ permalink raw reply	[flat|nested] 4+ messages in thread

* Re: help with IB_WC_MW_BIND_ERR
       [not found]     ` <CABgxfbHu8Wga6tX7iPyNb0aZaVY7XizAY_jpJW6+Nk2H9Gva5w-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
@ 2014-05-20 19:50       ` Chuck Lever
  0 siblings, 0 replies; 4+ messages in thread
From: Chuck Lever @ 2014-05-20 19:50 UTC (permalink / raw)
  To: Wendy Cheng; +Cc: linux-rdma


On May 20, 2014, at 3:39 PM, Wendy Cheng <s.wendy.cheng-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org> wrote:

> On Tue, May 20, 2014 at 11:55 AM, Chuck Lever <chuck.lever-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org> wrote:
>> Hi-
>> 
>> What does it mean when a LOCAL_INV work request fails with a
>> IB_WC_MW_BIND_ERR completion?
>> 
> 
> Mapping an IB error code has been a great pain (at least for me)
> unless you have access to the HCA firmware. In this case, I think it
> implies memory protection error (registration issues).... say in cxgb4
> driver, it is associated with invalidate shared MR or invalidate bound
> memory window (with a QP):
> 
>                case T4_ERR_INVALIDATE_SHARED_MR:
>                case T4_ERR_INVALIDATE_MR_WITH_MW_BOUND:
>                        wc->status = IB_WC_MW_BIND_ERR;
>                        break;
> 
> "drivers/infiniband/hw/cxgb4/cq.c" line 654 of 898 --72%-- col 11-25
> 
> You'll probably need to mention the HCA name so the firmware people,
> if they are reading this, could pinpoint the exact cause.

Thanks. ConnectX-2, mlx4 provider.

The IB architecture spec lists five conditions that could result in an
IB_WC_MW_BIND_ERR completion of LOCAL_INV:

1. Memory access was attempted on an L_Key or R_Key that is in the
   Invalid State;

2. Memory Region could not be Invalidated, because it is a Shared
   Memory Region;

3. Memory Region can not be invalidated because it has bound Memory
   Window; or

4. Memory Region could not be Invalidated, because it was created
   through a Register Memory Region or Reregister Memory Region.

5. Memory Window could not be Invalidated, because it was a Type 1
   Memory Window.

This is with FRMR and the MR is not shared (I think?). So I expect I’m
dealing with condition 1. But I can’t seem to make any more headway on
confirming that, or how it got that way.

--
Chuck Lever
chuck[dot]lever[at]oracle[dot]com



--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

^ permalink raw reply	[flat|nested] 4+ messages in thread

* Re: help with IB_WC_MW_BIND_ERR
       [not found] ` <B34C7243-DCF8-472B-B156-9B8791F0F475-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
  2014-05-20 19:39   ` Wendy Cheng
@ 2014-06-26 19:07   ` Shirley Ma
  1 sibling, 0 replies; 4+ messages in thread
From: Shirley Ma @ 2014-06-26 19:07 UTC (permalink / raw)
  To: Chuck Lever, linux-rdma, Or Gerlitz, eli-VPRAkNaXOzVWk0Htik3J/w

Hello Eli, Or,

Do you know who can help on this? NFSoRDMA hits this error case with Mellanox ConnectX-2 HCAs.

Thanks
Shirley

On 05/20/2014 11:55 AM, Chuck Lever wrote:
> Hi-
> 
> What does it mean when a LOCAL_INV work request fails with a
> IB_WC_MW_BIND_ERR completion?
> 
> --
> Chuck Lever
> chuck[dot]lever[at]oracle[dot]com
> 
> 
> 
> --
> To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
> the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> 
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

^ permalink raw reply	[flat|nested] 4+ messages in thread

end of thread, other threads:[~2014-06-26 19:07 UTC | newest]

Thread overview: 4+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2014-05-20 18:55 help with IB_WC_MW_BIND_ERR Chuck Lever
     [not found] ` <B34C7243-DCF8-472B-B156-9B8791F0F475-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
2014-05-20 19:39   ` Wendy Cheng
     [not found]     ` <CABgxfbHu8Wga6tX7iPyNb0aZaVY7XizAY_jpJW6+Nk2H9Gva5w-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2014-05-20 19:50       ` Chuck Lever
2014-06-26 19:07   ` Shirley Ma

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox