[openib-general] ib_mthca "NOP command failed to generate interrupt (IRQ 169), aborting."

[Don.Albert at Bull.com]

I am attempting to update the Linux kernel and the OpenIB stack to the 
latest versions and have run into a problem with the driver for the HCA.

Machine:        EM64T
HCA :           Mellanox Technologies MT25208 InfiniHost III Ex (Tavor 
compatibility mode) (rev a0)
Old Kernel:             2.6.14  New Kernel              2.6.15.6
Old OpenIB revision:    3929    New OpenIB revision:    5685

Booting with the old kernel and version of the mthca driver works.   I see 
in the "dmesg" log:

ib_mthca: Mellanox InfiniBand HCA driver v0.06 (June 23, 2005)
ib_mthca: Initializing 0000:06:00.0
ACPI: PCI Interrupt 0000:06:00.0[A] -> GSI 16 (level, low) -> IRQ 169
PCI: Setting latency timer of device 0000:06:00.0 to 64
ib_mthca 0000:06:00.0: HCA FW version 4.6.0 is old (4.7.0 is current).
ib_mthca 0000:06:00.0: If you have problems, try updating your HCA FW.

When I try to boot with the newer kernel and driver,  I get the following:

ib_mthca: Mellanox InfiniBand HCA driver v0.08 (February 14, 2006)
ib_mthca: Initializing 0000:06:00.0
ACPI: PCI Interrupt 0000:06:00.0[A] -> GSI 16 (level, low) -> IRQ 169
PCI: Setting latency timer of device 0000:06:00.0 to 64
ib_mthca 0000:06:00.0: HCA FW version 4.6.0 is old (4.7.400 is current).
ib_mthca 0000:06:00.0: If you have problems, try updating your HCA FW.
ib_mthca 0000:06:00.0: NOP command failed to generate interrupt (IRQ 169), 
aborting.
ib_mthca 0000:06:00.0: BIOS or ACPI interrupt routing problem?
ACPI: PCI interrupt for device 0000:06:00.0 disabled
ib_mthca: probe of 0000:06:00.0 failed with error -16

I see that the HCA firmware is old,  but is that the problem here,  or is 
there some other change that could be causing this? 

-Don Albert-
Bull HN Information Systems
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.openfabrics.org/pipermail/general/attachments/20060313/a04484e1/attachment.html>