[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [PATCH V2 0/3] improve -overcommit cpu-pm=on|off
From: |
Igor Mammedov |
Subject: |
Re: [PATCH V2 0/3] improve -overcommit cpu-pm=on|off |
Date: |
Wed, 29 May 2024 14:46:34 +0200 |
On Tue, 28 May 2024 11:16:59 -0700
"Chen, Zide" <zide.chen@intel.com> wrote:
> On 5/28/2024 2:23 AM, Igor Mammedov wrote:
> > On Fri, 24 May 2024 13:00:14 -0700
> > Zide Chen <zide.chen@intel.com> wrote:
> >
> >> Currently, if running "-overcommit cpu-pm=on" on hosts that don't
> >> have MWAIT support, the MWAIT/MONITOR feature is advertised to the
> >> guest and executing MWAIT/MONITOR on the guest triggers #UD.
> >
> > this is missing proper description how do you trigger issue
> > with reproducer and detailed description why guest sees MWAIT
> > when it's not supported by host.
>
> If "overcommit cpu-pm=on" and "-cpu hpst" are present, as shown in the
it's bette to provide full QEMU CLI and host/guest kernels used and what
hardware was used if it's relevant so others can reproduce problem.
> following, CPUID_EXT_MONITOR is set after x86_cpu_filter_features(), so
> that it doesn't have a chance to check MWAIT against host features and
> will be advertised to the guest regardless of whether it's supported by
> the host or not.
>
> x86_cpu_realizefn()
> x86_cpu_filter_features()
> cpu_exec_realizefn()
> kvm_cpu_realizefn
> host_cpu_realizefn
> host_cpu_enable_cpu_pm
> env->features[FEAT_1_ECX] |= CPUID_EXT_MONITOR;
>
>
> If it's not supported by the host, executing MONITOR or MWAIT
> instructions from the guest triggers #UD, no matter MWAIT_EXITING
> control is set or not.
If I recall right, kvm was able to emulate mwait/monitor.
So question is why it leads to exception instead?
- Re: [PATCH V2 3/3] target/i386: Move host_cpu_enable_cpu_pm into kvm_cpu_realizefn(), (continued)
- Re: [PATCH V2 0/3] improve -overcommit cpu-pm=on|off, Igor Mammedov, 2024/05/28
- Re: [PATCH V2 0/3] improve -overcommit cpu-pm=on|off, Chen, Zide, 2024/05/28
- Re: [PATCH V2 0/3] improve -overcommit cpu-pm=on|off,
Igor Mammedov <=
- Re: [PATCH V2 0/3] improve -overcommit cpu-pm=on|off, Chen, Zide, 2024/05/29
- Re: [PATCH V2 0/3] improve -overcommit cpu-pm=on|off, Zhao Liu, 2024/05/30
- Re: [PATCH V2 0/3] improve -overcommit cpu-pm=on|off, Igor Mammedov, 2024/05/30
- Re: [PATCH V2 0/3] improve -overcommit cpu-pm=on|off, Sean Christopherson, 2024/05/30
- Re: [PATCH V2 0/3] improve -overcommit cpu-pm=on|off, Igor Mammedov, 2024/05/30
- Re: [PATCH V2 0/3] improve -overcommit cpu-pm=on|off, Chen, Zide, 2024/05/30