Re: [kvm-devel] Could not start KVM 24

2007-05-27 Thread Dor Laor
>I have used KVM 16 in x86_64 OpenSUSE 10.2 without problems. >I have recently downloaded and installed x86_64 RPMs of KVM 24. >But I could not start it: > >#qemu-kvm >open /dev/kvm: No such file or directory >Could not initialize KVM, will disable KVM support > >I have Intel VT enabled in my PC an

[kvm-devel] Could not start KVM 24

2007-05-27 Thread ymed
Hello! I have used KVM 16 in x86_64 OpenSUSE 10.2 without problems. I have recently downloaded and installed x86_64 RPMs of KVM 24. But I could not start it: #qemu-kvm open /dev/kvm: No such file or directory Could not initialize KVM, will disable KVM support I have Intel VT enabled in my PC and

[kvm-devel] Kernel panic when loading kvm-amd

2007-05-27 Thread Pär Andersson
Hi. I am getting a kernel panic when loading the kvm-amd module. I have talked a little about this with aliguori on IRC and according to him the panic occurs when KVM enables EFER.SVME. Computer information: AMD Athlon64 X2 4400+, 65nm, Brisbane. Abit KN9 motherboard (nforce4) Ubuntu 7.04 x86_6

Re: [kvm-devel] [PATCH 4/9] KVM: Adds ability to preempt an executing VCPU

2007-05-27 Thread Avi Kivity
Gregory Haskins wrote: > static void kvm_vcpu_irqsink_init(struct kvm_vcpu *vcpu) > diff --git a/drivers/kvm/svm.c b/drivers/kvm/svm.c > index a9d917a..c79bfc0 100644 > --- a/drivers/kvm/svm.c > +++ b/drivers/kvm/svm.c > @@ -1544,9 +1544,43 @@ static int svm_vcpu_run(struct kvm_vcpu *vcpu, struct

[kvm-devel] [ANNOUNCE] kvm-26 release

2007-05-27 Thread Avi Kivity
This is a minor release for compile fixes while we hash out the apic-on-amd problems. Changes since kvm-25: - implement wbinvd emulation, triggered by Windows Vista - compile fixes (Markus Rechberger, me) Notes: If you use the modules from kvm-26, you can use any version of Linux from 2.6.9 u

Re: [kvm-devel] [PATCH 0/7] KVM: Suspend and cpu hotplug fixes

2007-05-27 Thread Avi Kivity
Avi Kivity wrote: > I estimate that that take_cpu_down will run for about a millisecond if > there are a few hundred vcpus which have last run on the dying cpu (and > that's an extreme case, which is not expected in normal operation). I measured vmclear time on an uncached vmcs (which would be all