[openib-general] opensm crash with topspin HCA

[Hal Rosenstock]

On Thu, 2006-11-02 at 13:33, Viswanath Krishnamurthy wrote:
> 
> When we run opensm (OFED) release and if a Topspin HCA is in the IB
> network, opensm crashes in umad_receiver with NULL pointer exception. 
> The transaction ID is zero is the MAD'S from topspin HCA on windows.
> The crashes seems to random in umad_receiver. 

What OpenSM version ? 

There was a problem like this fixed back at the end of August:

r8920 | halr | 2006-08-14 09:09:28 -0400 (Mon, 14 Aug 2006) | 11 lines

OpenSM/osm_vendor_ibumad.c: In get_madw, check for TID 0 (resolves
NULL ptr crash with Cisco stack)

This change fixes an OSM crash when working with Cisco's stack.
Cisco's stack doesn't follow the same TID convention when generating transaction
 id which in some bad flow revealed this bug in the get_madw lookup.

The bug was in get_madw which does not detect lookup of its reserved "free" entr
y of key==0.

Signed-off-by: Yevgeny Kliteynik <kliteyn at mellanox.co.il>
Signed-off-by: Hal Rosenstock <halr at voltaire.com>

-- Hal

> 
> 
> 
> HCA found:
> 
>         hca_id=InfiniHost0
> 
>         vendor_id=0x02C9
> 
>         vendor_part_id=0x5A44
> 
>         hw_ver=0xA0
> 
>         fw_ver=0x400060000
> 
> 
> 
> 
> ______________________________________________________________________
> 
> _______________________________________________
> openib-general mailing list
> openib-general at openib.org
> http://openib.org/mailman/listinfo/openib-general
> 
> To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general