[ofa-general] [PATCH] libmlx4: Fix the value of the pkey_index in the completion

Dotan Barak dotanb at dev.mellanox.co.il
Mon Jan 14 01:31:26 PST 2008


Sasha Khapyorsky wrote:
> Hi Dotan,
>
> On 14:49 Mon 07 Jan     , Dotan Barak wrote:
>   
>>  Dotan Barak wrote:
>>     
>>> Yevgeny Kliteynik wrote:
>>>       
>>>> Dotan Barak wrote:
>>>>         
>>>>> Or Gerlitz wrote:
>>>>>           
>>>>>> Dotan Barak wrote:
>>>>>>             
>>>>>>> Fix the value of the pkey_index in the completion to get a valid value 
>>>>>>> for GSI QPs.
>>>>>>>               
>>>>>> Is libmthca fine in that respect?
>>>>>>             
>>>>> As much as i know, everything is fine with mthca/libmthca.
>>>>>
>>>>> We saw several problems only in ConnectX (because of the new low level 
>>>>> driver).
>>>>>
>>>>> Right now, we are doing some more checks to check the mlx4_0 low level 
>>>>> driver as well as the IB core.
>>>>> After that we'll check the mthca low level driver too.
>>>>>           
>>>> Currently OpenSM doesn't support any non-default pkey
>>>> (or any pkey at index other than 0) in sa queries.
>>>> When a request is received, opensm doesn't extract the
>>>> right pkey from the mad header - it replaces it with a
>>>> default pkey, and when a response is sent, OpenSM always
>>>> uses pkey at index 0.
>>>>
>>>> -- Yevgeny
>>>>         
>>> FYI: after several testings it seems that mthca low level driver don't have 
>>> this problem.
>>>
>>> Dotan
>>>
>>>       
>>  Just to make sure that everything is clear: I checked that the mthca low 
>>  level driver can extract
>>  the right pkey_index in the completion of GSI QP.
>>
>>  The problem that Yevgeny mentioned exists in the openSM and i opened a bug 
>>  on this issue.
>>     
>
> I tried mthca connected back-to-back (between ports 1 and 2). When
> non-default P_Key value is configured (at any index, full membership on
> both ports pkey tables and no 0xffff), saquery is timed out and trap 257
> (Bad P_Key) is reported to OpenSM.
>
> I'm using kernel 2.6.24-rc7-gcdf71a10 and FW 3.2.000. Could this be old
> FW issue?
>   
This is a really old FW and you should consider updating it ...

What exactly did you do (and how)?

I have troubles to set the pkey table in the subnet to not use the 
default pkey.

Dotan




More information about the general mailing list