On (Mon) Mar 30 2009 [16:55:05], Avi Kivity wrote: > Amit Shah wrote: >> On (Mon) Mar 30 2009 [10:07:58], Avi Kivity wrote: >> >> >>>> 1. perfctr wrmsr warning when booting 64bit RHEl5.3 >>>> https://sourceforge.net/tracker/?func=detail&aid=2721640&group_id=180599&atid=893831 >>>> >>> This is the architectural performance counting msr which was enabled >>> in 4f76231 (KVM: x86: Ignore reads to EVNTSEL MSRs). Amit, can you >>> check if appropriate cpuid leaf 10 reporting will fix this? >>> >> >> We already report 0s for the cpuid leaf 10; we need to report 0x3f in >> EBX for leaf 10 to denote events corresponding to the bits aren't >> available. >> >> I checked and it didn't help (we can't rely on guests to abide by cpuid >> flags) >> > > I see this in the code: > >> /* >> * Check whether the Architectural PerfMon supports >> * Unhalted Core Cycles Event or not. >> * NOTE: Corresponding bit = 0 in ebx indicates event present. >> */ >> cpuid(10, &(eax.full), &ebx, &unused, &unused); >> if ((eax.split.mask_length < >> (ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX+1)) || >> (ebx & ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT)) >> return 0; >> > > So I think it can be done. Only if the guest kernel (or module accessing those registers) look at the cpuid output, right? I checked this for the Kaspersky AV on Windows, the crash bug I was solving and that program doesn't seem to check cpuid. RHEL 5.3 is based on 2.6.18 and this patch appears to have entered in 2.6.21. I saw this on 5.3 as well. Amit -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
