Kernel messages when high CAN bus load

[markus.ribler]

Hi all,
We observed repeatedly kernel messages as soon CAN bus load reaches a certain level.

Kernel messages (timestamps omitted):
pcieport 0000:00:02.0: AER: Corrected error received: id=0010
pcieport 0000:00:02.0: PCIe Bus Error: severity=Corrected, type=Data Link Layer, id=0010(Receiver ID)
pcieport 0000:00:02.0: device [8086:6f04] error status/mask=00000040/00002000
pcieport 0000:00:02.0: [ 6] Bad TLP

Can bus load generation:
> cangen can0 -g 1 (Kernel messages every 5 sec)
> cangen can0 -g 0 -i (Kernel messages 8 times per sec)

We have several identical PCs and the effect can be reproduced on each machine.

We use:
Ubuntu 16.04
Kernel 4.15.0-36 with mainline driver 'peak_pciefd.ko' (provided by ubuntu)
Mainboard: Supermicro X10SRA with Xeon E5

What is the reason for these messages?

Regards,
Markus Ribler

[M.Maidhof]

Hi,

which PEAK hardware do you use on that system, please tell us the serialnumber of that PCAN card. Next, please send us the relevant outputs of dmesg showing the firmware of the PCAN card.

regards

Michael

[markus.ribler]

Hi Michael,

Here the dmesg of peak_pciefd:

[ 10.081897] peak_pciefd 0000:02:00.0: 4x CAN-FD PCAN-PCIe FPGA v3.2.1:
[ 10.082181] peak_pciefd 0000:02:00.0: can0 at reg_base=0x (ptrval) irq=26
[ 10.082513] peak_pciefd 0000:02:00.0: can1 at reg_base=0x (ptrval) irq=26
[ 10.082844] peak_pciefd 0000:02:00.0: can2 at reg_base=0x (ptrval) irq=26
[ 10.083169] peak_pciefd 0000:02:00.0: can3 at reg_base=0x (ptrval) irq=26

On the label (back of the card):

IPEH-004040 00656

We have about 30 of these cards and kernel messages I mentioned have been observed also on other (same PC HW) systems. Also the number of kernel messages per seconds depends on the load on the CAN bus.

Regards,
Markus Ribler
FPT Motorenforschung AG

[M.Maidhof]

Hi,

thanks for the info. Please contact us by email (linux@) to be able to provide you some more files for further tests.

regards

Michael