Bugzilla – Bug 1789
powernow-k8 transitions fail in xen dom0
Last modified: 2012-11-22 13:12:13 CST
I am filing this upstream from a report in the redhat bugzilla [1]. When using Fedora 16 as Dom0 with some CPUs (I'm using 2x Dual Core AMD Opteron(tm) Processor 865 HE), the system log is flooded with messages (several per second) like the following: kernel: [ 1.226209] powernow-k8: fid trans failed, fid 0x2, curr 0x0 kernel: [ 1.226271] powernow-k8: transition frequency failed While the system is still running with these errors, the console is pretty much useless and all of the extra messages make the signal/noise ratio in the system log very low. According to the kernel maintainers, this is an issue with Xen and not the kernel [2]. At the time of this report, I am using the following Fedora packages: kernel-3.1.0-0.rc8.git0.1.fc16.x86_64 xen-4.1.1-6 [1] https://bugzilla.redhat.com/show_bug.cgi?id=739159 [2] https://bugzilla.redhat.com/show_bug.cgi?id=739159#c6
Copying what I said on the RH BZ: Tim, Thanks for posting it in the Xen BZ. The issue is .. well, it is a long explanation, so skip to the end for summary if you don't want to read technical jargon. On AMD with Xen, the cpuidle is set to use the halt one (this is b/c the halt ends up doing a yield hypercall) - look in setup.c - and the hypervisor does the appropiate halt operation (MWAIT, halt, etc, or schedules another guest on the CPU). Anyhow, to not have the cpuidle trying to activate, the "boot_option_idle_override" is set. Therefore, the ACPI _PSS driver (processor.ko) ends up bailing out, b/c of that parameter. As such the "older" AMD pstate driver is invoked (powernow-k8), and the older driver attempts to use ACPI _PSD - but only if in UP mode, or it attempts to use the voltage tables - which are k8 or earlier. To detect that, it use the MSR (sadly not CPUID values), which Xen traps and returns 00, which the powernow-k8 driver interprets as "buggy hardware - can't use". Which is exactly what you are seeing. I believe (and sadly I don't have the hardware to check this - but I think I saw the somebody using it) if you were running on K8 hardware - it ought to work. Solution: Have the ACPI processor driver cooperate with Xen. Patches are in the queue for it (if you are really interested look in oss.oracle.com/kwilk/xen.git #devel/acpi-cpufreq.v2 - but they are not yet upstream-able material. Actually, they are quite ugly). Other solution: The "easy" option for right now would be to do what Dave suggest until the upstream patches are ready and reviewed.
This bug is still persistent. I have compiled xen 4.2 from source on FC 17 on AMD Turion X52 cores kernel version 3.3.4-5.fc17.x86_64 dmesg shows a lot of powernow-k8: transition frequency failed and CPUs is running nostop on full power