Erroneous MCE taint on Some CPU Processors

This document (7008578) is provided subject to the disclaimer at the end of this document.

Environment

SUSE Linux Enterprise Server 10 Service Pack 3
SUSE Linux Enterprise Server 10 Service Pack 4
SUSE Linux Enterprise Server 11 Service Pack 1

Situation

Partner Engineering has seen new systems with processors that report Machine Check Exceptions (MCE). These are errors on the hardware that are correctable by the hardware, so it is not causing the OS a problem. SLES 11 SP1 and SLES 10 SP3 capture and log these errors. The problem is the errors are tainting the kernel with an MCE taint (M). Processors known to report these MCEs are:

Xeon Model Numbers: E7-8800, E7-4800 and E7-2800
AMD Model Numbers: 6180 SE

Run `cat /proc/cpuinfo | grep -i "model name"` to confirm.

Resolution

Partner Engineering does not think this is a compatibility problem between the hardware and the OS, it is working as "currently" designed. So, they are YES Certifying systems with the MCE taint. Engineering is also working on an upstream fix to avoid the taint.

Since it is difficult to tell if the MCE taint is erroneous or indicative of other hardware failures, it is recommended that you run your vendor's hardware diagnostic procedure to confirm.

Disclaimer

This Support Knowledgebase provides a valuable tool for SUSE customers and parties interested in our products and solutions to acquire information, ideas and learn from one another. Materials are provided for informational, personal or non-commercial use within your organization and are presented "AS IS" WITHOUT WARRANTY OF ANY KIND.