[ofa-general] mthca issues -need help

Boris Shpolyansky boris at mellanox.com
Fri Apr 13 14:42:10 PDT 2007


Pradeep,

I guess you need to upgrade FW first to the latest 3.5.0 revision -
this might solve the issue and save everybody's time.

You can download FW image from Mellanox web site.

Please, verify your Board ID (PSID) first using mstflint tool:

	mstflint -d <PCI device> q

You should obtain your PCI device from lspci, for instance:

[root at lt ~]# lspci | grep InfiniBand
03:00.0 InfiniBand: Mellanox Technologies MT25204 [InfiniHost III Lx
HCA] (rev 20)

Then pick the right FW image file based on the PSID.

Burn FW using mstflint utility - the instructions are on Mellanox web
site.
'mstflint -h' is also helpful.

Regards,
Boris Shpolyansky
Sr. Member of Technical Staff
Applications
Mellanox Technologies Inc.
2900 Stender Way
Santa Clara, CA 95054
Tel.: (408) 916 0014
Fax: (408) 970 3403
Cell: (408) 834 9365
www.mellanox.com

-----Original Message-----
From: general-bounces at lists.openfabrics.org
[mailto:general-bounces at lists.openfabrics.org] On Behalf Of Pradeep
Satyanarayana
Sent: Friday, April 13, 2007 2:33 PM
To: Roland Dreier
Cc: Michael S. Tsirkin; general at lists.openfabrics.org
Subject: Re: [ofa-general] mthca issues -need help

Please see details below.

Pradeep
pradeep at us.ibm.com

Roland Dreier <rdreier at cisco.com> wrote on 04/13/2007 02:01:41 PM:

>  > 1. I am using linux-2.6.21-rc5 and I see this Oops when I modprobe

> > ib_mthca (on ppc64)
> 
> Can you give more details of your platform?  Also, the output of 
> "lspci -vv -d 15b3:" might be helpful (I'm curious where the BARs
are).
> 
I am using a p575 (4 CPU) with 1.9GHz and has PCI-X slots, using about
8GB RAM currently. 
This OOps was seen using an MT23108. I am not sure what additional
details you would like. 
Here is the output of lspci:


# lspci -vv -d 15b3:
0002:d8:01.0 PCI bridge: Mellanox Technologies MT23108 PCI Bridge (rev
a1) (prog-if 00 [Normal decode])
        Control: I/O+ Mem+ BusMaster+ SpecCycle- MemWINV- VGASnoop- 
ParErr+ Stepping- SERR+ FastB2B-
        Status: Cap+ 66MHz+ UDF- FastB2B- ParErr- DEVSEL=medium >TAbort-
<TAbort- <MAbort- >SERR- <PERR-
        Latency: 144, Cache Line Size: 128 bytes
        Bus: primary=d8, secondary=d9, subordinate=d9, sec-latency=128
        Memory behind bridge: c0000000-c08fffff
        Secondary status: 66MHz+ FastB2B- ParErr- DEVSEL=medium >TAbort-
<TAbort- <MAbort- <SERR- <PERR-
        BridgeCtl: Parity- SERR- NoISA- VGA- MAbort- >Reset- FastB2B-
        Capabilities: [70] PCI-X bridge device
                Secondary Status: 64bit+ 133MHz+ SCD- USC- SCO- SRD-
Freq=133MHz
                Status: Dev=d8:01.0 64bit+ 133MHz+ SCD- USC- SCO- SRD-
                Upstream: Capacity=512 CommitmentLimit=512
                Downstream: Capacity=128 CommitmentLimit=128

0002:d9:00.0 InfiniBand: Mellanox Technologies MT23108 InfiniHost (rev
a1)
        Subsystem: Mellanox Technologies MT23108 InfiniHost
        Control: I/O- Mem+ BusMaster+ SpecCycle- MemWINV- VGASnoop-
ParErr- Stepping- SERR+ FastB2B-
        Status: Cap+ 66MHz+ UDF- FastB2B- ParErr- DEVSEL=medium >TAbort-
<TAbort- <MAbort- >SERR- <PERR-
        Latency: 144, Cache Line Size: 128 bytes
        Interrupt: pin A routed to IRQ 121
        Region 0: Memory at 400c0800000 (64-bit, non-prefetchable)
[size=1M]
        Region 2: Memory at 400c0000000 (64-bit, prefetchable) [size=8M]
        Capabilities: [40] MSI-X: Enable- Mask- TabSize=32
                Vector table: BAR=0 offset=00082000
                PBA: BAR=0 offset=00082200
        Capabilities: [50] Vital Product Data
        Capabilities: [60] Message Signalled Interrupts: 64bit+
Queue=0/5
Enable-
                Address: 0000000000000000  Data: 0000
        Capabilities: [70] PCI-X non-bridge device
                Command: DPERE- ERO- RBC=4096 OST=2
                Status: Dev=d9:00.0 64bit+ 133MHz+ SCD- USC- DC=simple
DMMRBC=4096 DMOST=2 DMCRS=8 RSCEM- 266MHz- 533MHz-



>  > 2. The above may or may not be a bug and as indicated in the 
> message
I 
>  > wanted to upgrade (the FW). However, I found that the  > latest 
> firmware is 3.5.0 and not 3.4.0 as the message seems to
indicate. I 
>  > wanted to use IPOIB CM -so which one should I upgrade to -  > 
> presumably 3.5.0?
> 
> The FW versions in the driver have not been kept up to date.  I'll 
> queue a patch for 2.6.22 that updates the latest FW information to 
> what is current right now.
> 
Yes, I saw your next mail with the patch for this. Thanks!

>  - R.

_______________________________________________
general mailing list
general at lists.openfabrics.org
http://lists.openfabrics.org/cgi-bin/mailman/listinfo/general

To unsubscribe, please visit
http://openib.org/mailman/listinfo/openib-general



More information about the general mailing list