Re: [PATCH] KVM: VMX: Enable MSR-BASED TPR shadow even if w/o APICv

[...] > >> Btw, I heard from Tianyu from Intel, you said there was a x2apic bug >> in kvm forum and the bug maybe in kvm, I guess I meet the same bug >> when run a windows guest(server version of windows 7, 2008 or 2012) w/ >> x2apic enabled in guest and -machine q35,kernel_irqchip=spit -device >>

Re: [PATCH] KVM: VMX: Enable MSR-BASED TPR shadow even if w/o APICv

[...] > >> Btw, I heard from Tianyu from Intel, you said there was a x2apic bug >> in kvm forum and the bug maybe in kvm, I guess I meet the same bug >> when run a windows guest(server version of windows 7, 2008 or 2012) w/ >> x2apic enabled in guest and -machine q35,kernel_irqchip=spit -device >>

Re: [PATCH] KVM: VMX: Enable MSR-BASED TPR shadow even if w/o APICv

2016-09-19 21:44 GMT+08:00 Radim Krčmář : > 2016-09-18 14:53+0800, Wanpeng Li: >> 2016-09-15 23:58 GMT+08:00 Radim Krčmář : >>> 2016-09-15 15:05+0800, Wanpeng Li: 2016-09-14 20:03 GMT+08:00 Radim Krčmář : > 2016-09-14 11:40+0200,

Re: [PATCH] KVM: VMX: Enable MSR-BASED TPR shadow even if w/o APICv

2016-09-19 21:44 GMT+08:00 Radim Krčmář : > 2016-09-18 14:53+0800, Wanpeng Li: >> 2016-09-15 23:58 GMT+08:00 Radim Krčmář : >>> 2016-09-15 15:05+0800, Wanpeng Li: 2016-09-14 20:03 GMT+08:00 Radim Krčmář : > 2016-09-14 11:40+0200, Paolo Bonzini: >> On 14/09/2016 09:58, Wanpeng Li

Re: [PATCH] KVM: VMX: Enable MSR-BASED TPR shadow even if w/o APICv

2016-09-18 14:53+0800, Wanpeng Li: > 2016-09-15 23:58 GMT+08:00 Radim Krčmář : >> 2016-09-15 15:05+0800, Wanpeng Li: >>> 2016-09-14 20:03 GMT+08:00 Radim Krčmář : 2016-09-14 11:40+0200, Paolo Bonzini: > On 14/09/2016 09:58, Wanpeng Li wrote: >>

Re: [PATCH] KVM: VMX: Enable MSR-BASED TPR shadow even if w/o APICv

2016-09-18 14:53+0800, Wanpeng Li: > 2016-09-15 23:58 GMT+08:00 Radim Krčmář : >> 2016-09-15 15:05+0800, Wanpeng Li: >>> 2016-09-14 20:03 GMT+08:00 Radim Krčmář : 2016-09-14 11:40+0200, Paolo Bonzini: > On 14/09/2016 09:58, Wanpeng Li wrote: >> From: Wanpeng Li >> >> I

Re: [PATCH] KVM: VMX: Enable MSR-BASED TPR shadow even if w/o APICv

2016-09-18 14:53 GMT+08:00 Wanpeng Li : > 2016-09-15 23:58 GMT+08:00 Radim Krčmář : >> 2016-09-15 15:05+0800, Wanpeng Li: >>> 2016-09-14 20:03 GMT+08:00 Radim Krčmář : 2016-09-14 11:40+0200, Paolo Bonzini: > On 14/09/2016 09:58,

Re: [PATCH] KVM: VMX: Enable MSR-BASED TPR shadow even if w/o APICv

2016-09-18 14:53 GMT+08:00 Wanpeng Li : > 2016-09-15 23:58 GMT+08:00 Radim Krčmář : >> 2016-09-15 15:05+0800, Wanpeng Li: >>> 2016-09-14 20:03 GMT+08:00 Radim Krčmář : 2016-09-14 11:40+0200, Paolo Bonzini: > On 14/09/2016 09:58, Wanpeng Li wrote: >> From: Wanpeng Li >> >> I

Re: [PATCH] KVM: VMX: Enable MSR-BASED TPR shadow even if w/o APICv

2016-09-15 23:58 GMT+08:00 Radim Krčmář : > 2016-09-15 15:05+0800, Wanpeng Li: >> 2016-09-14 20:03 GMT+08:00 Radim Krčmář : >>> 2016-09-14 11:40+0200, Paolo Bonzini: On 14/09/2016 09:58, Wanpeng Li wrote: > From: Wanpeng Li

Re: [PATCH] KVM: VMX: Enable MSR-BASED TPR shadow even if w/o APICv

2016-09-15 23:58 GMT+08:00 Radim Krčmář : > 2016-09-15 15:05+0800, Wanpeng Li: >> 2016-09-14 20:03 GMT+08:00 Radim Krčmář : >>> 2016-09-14 11:40+0200, Paolo Bonzini: On 14/09/2016 09:58, Wanpeng Li wrote: > From: Wanpeng Li > > I observed that kvmvapic(to optimize flexpriority=N

Re: [PATCH] KVM: VMX: Enable MSR-BASED TPR shadow even if w/o APICv

On 09/15/2016 07:25 AM, Wanpeng Li wrote: > 2016-09-15 12:08 GMT+08:00 Mika Penttilä : >> On 09/14/2016 10:58 AM, Wanpeng Li wrote: >>> From: Wanpeng Li >>> >>> I observed that kvmvapic(to optimize flexpriority=N or AMD) is used >>> to boost TPR

Re: [PATCH] KVM: VMX: Enable MSR-BASED TPR shadow even if w/o APICv

On 09/15/2016 07:25 AM, Wanpeng Li wrote: > 2016-09-15 12:08 GMT+08:00 Mika Penttilä : >> On 09/14/2016 10:58 AM, Wanpeng Li wrote: >>> From: Wanpeng Li >>> >>> I observed that kvmvapic(to optimize flexpriority=N or AMD) is used >>> to boost TPR access when testing kvm-unit-test/eventinj.flat tpr

Re: [PATCH] KVM: VMX: Enable MSR-BASED TPR shadow even if w/o APICv

2016-09-15 15:05+0800, Wanpeng Li: > 2016-09-14 20:03 GMT+08:00 Radim Krčmář : >> 2016-09-14 11:40+0200, Paolo Bonzini: >>> On 14/09/2016 09:58, Wanpeng Li wrote: From: Wanpeng Li I observed that kvmvapic(to optimize flexpriority=N or

Re: [PATCH] KVM: VMX: Enable MSR-BASED TPR shadow even if w/o APICv

2016-09-15 15:05+0800, Wanpeng Li: > 2016-09-14 20:03 GMT+08:00 Radim Krčmář : >> 2016-09-14 11:40+0200, Paolo Bonzini: >>> On 14/09/2016 09:58, Wanpeng Li wrote: From: Wanpeng Li I observed that kvmvapic(to optimize flexpriority=N or AMD) is used to boost TPR access when

Re: [PATCH] KVM: VMX: Enable MSR-BASED TPR shadow even if w/o APICv

2016-09-14 20:03 GMT+08:00 Radim Krčmář : > 2016-09-14 11:40+0200, Paolo Bonzini: >> On 14/09/2016 09:58, Wanpeng Li wrote: >>> From: Wanpeng Li >>> >>> I observed that kvmvapic(to optimize flexpriority=N or AMD) is used >>> to boost TPR access when

Re: [PATCH] KVM: VMX: Enable MSR-BASED TPR shadow even if w/o APICv

2016-09-14 20:03 GMT+08:00 Radim Krčmář : > 2016-09-14 11:40+0200, Paolo Bonzini: >> On 14/09/2016 09:58, Wanpeng Li wrote: >>> From: Wanpeng Li >>> >>> I observed that kvmvapic(to optimize flexpriority=N or AMD) is used >>> to boost TPR access when testing kvm-unit-test/eventinj.flat tpr case

Re: [PATCH] KVM: VMX: Enable MSR-BASED TPR shadow even if w/o APICv

2016-09-15 14:29 GMT+08:00 Paolo Bonzini : > > > On 15/09/2016 03:19, Wanpeng Li wrote: >> 2016-09-14 20:03 GMT+08:00 Radim Krčmář : >>> 2016-09-14 11:40+0200, Paolo Bonzini: On 14/09/2016 09:58, Wanpeng Li wrote: > From: Wanpeng Li

Re: [PATCH] KVM: VMX: Enable MSR-BASED TPR shadow even if w/o APICv

2016-09-15 14:29 GMT+08:00 Paolo Bonzini : > > > On 15/09/2016 03:19, Wanpeng Li wrote: >> 2016-09-14 20:03 GMT+08:00 Radim Krčmář : >>> 2016-09-14 11:40+0200, Paolo Bonzini: On 14/09/2016 09:58, Wanpeng Li wrote: > From: Wanpeng Li > > I observed that kvmvapic(to optimize

Re: [PATCH] KVM: VMX: Enable MSR-BASED TPR shadow even if w/o APICv

On 15/09/2016 06:08, Mika Penttilä wrote: > On 09/14/2016 10:58 AM, Wanpeng Li wrote: >> From: Wanpeng Li >> >> I observed that kvmvapic(to optimize flexpriority=N or AMD) is used >> to boost TPR access when testing kvm-unit-test/eventinj.flat tpr case >> on my haswell

Re: [PATCH] KVM: VMX: Enable MSR-BASED TPR shadow even if w/o APICv

On 15/09/2016 06:08, Mika Penttilä wrote: > On 09/14/2016 10:58 AM, Wanpeng Li wrote: >> From: Wanpeng Li >> >> I observed that kvmvapic(to optimize flexpriority=N or AMD) is used >> to boost TPR access when testing kvm-unit-test/eventinj.flat tpr case >> on my haswell desktop (w/

Re: [PATCH] KVM: VMX: Enable MSR-BASED TPR shadow even if w/o APICv

On 15/09/2016 03:19, Wanpeng Li wrote: > 2016-09-14 20:03 GMT+08:00 Radim Krčmář : >> 2016-09-14 11:40+0200, Paolo Bonzini: >>> On 14/09/2016 09:58, Wanpeng Li wrote: From: Wanpeng Li I observed that kvmvapic(to optimize flexpriority=N

Re: [PATCH] KVM: VMX: Enable MSR-BASED TPR shadow even if w/o APICv

On 15/09/2016 03:19, Wanpeng Li wrote: > 2016-09-14 20:03 GMT+08:00 Radim Krčmář : >> 2016-09-14 11:40+0200, Paolo Bonzini: >>> On 14/09/2016 09:58, Wanpeng Li wrote: From: Wanpeng Li I observed that kvmvapic(to optimize flexpriority=N or AMD) is used to boost TPR access

Re: [PATCH] KVM: VMX: Enable MSR-BASED TPR shadow even if w/o APICv

2016-09-15 12:08 GMT+08:00 Mika Penttilä : > On 09/14/2016 10:58 AM, Wanpeng Li wrote: >> From: Wanpeng Li >> >> I observed that kvmvapic(to optimize flexpriority=N or AMD) is used >> to boost TPR access when testing kvm-unit-test/eventinj.flat

Re: [PATCH] KVM: VMX: Enable MSR-BASED TPR shadow even if w/o APICv

2016-09-15 12:08 GMT+08:00 Mika Penttilä : > On 09/14/2016 10:58 AM, Wanpeng Li wrote: >> From: Wanpeng Li >> >> I observed that kvmvapic(to optimize flexpriority=N or AMD) is used >> to boost TPR access when testing kvm-unit-test/eventinj.flat tpr case >> on my haswell desktop (w/ flexpriority,

Re: [PATCH] KVM: VMX: Enable MSR-BASED TPR shadow even if w/o APICv

On 09/14/2016 10:58 AM, Wanpeng Li wrote: > From: Wanpeng Li > > I observed that kvmvapic(to optimize flexpriority=N or AMD) is used > to boost TPR access when testing kvm-unit-test/eventinj.flat tpr case > on my haswell desktop (w/ flexpriority, w/o APICv). Commit

Re: [PATCH] KVM: VMX: Enable MSR-BASED TPR shadow even if w/o APICv

On 09/14/2016 10:58 AM, Wanpeng Li wrote: > From: Wanpeng Li > > I observed that kvmvapic(to optimize flexpriority=N or AMD) is used > to boost TPR access when testing kvm-unit-test/eventinj.flat tpr case > on my haswell desktop (w/ flexpriority, w/o APICv). Commit (8d14695f9542 > x86, apicv:

Re: [PATCH] KVM: VMX: Enable MSR-BASED TPR shadow even if w/o APICv

2016-09-14 20:03 GMT+08:00 Radim Krčmář : > 2016-09-14 11:40+0200, Paolo Bonzini: >> On 14/09/2016 09:58, Wanpeng Li wrote: >>> From: Wanpeng Li >>> >>> I observed that kvmvapic(to optimize flexpriority=N or AMD) is used >>> to boost TPR access when

Re: [PATCH] KVM: VMX: Enable MSR-BASED TPR shadow even if w/o APICv

2016-09-14 20:03 GMT+08:00 Radim Krčmář : > 2016-09-14 11:40+0200, Paolo Bonzini: >> On 14/09/2016 09:58, Wanpeng Li wrote: >>> From: Wanpeng Li >>> >>> I observed that kvmvapic(to optimize flexpriority=N or AMD) is used >>> to boost TPR access when testing kvm-unit-test/eventinj.flat tpr case

Re: [PATCH] KVM: VMX: Enable MSR-BASED TPR shadow even if w/o APICv

2016-09-15 8:07 GMT+08:00 Wanpeng Li : > 2016-09-14 17:40 GMT+08:00 Paolo Bonzini : >> >> >> On 14/09/2016 09:58, Wanpeng Li wrote: >>> From: Wanpeng Li >>> >>> I observed that kvmvapic(to optimize flexpriority=N or AMD) is used

Re: [PATCH] KVM: VMX: Enable MSR-BASED TPR shadow even if w/o APICv

2016-09-15 8:07 GMT+08:00 Wanpeng Li : > 2016-09-14 17:40 GMT+08:00 Paolo Bonzini : >> >> >> On 14/09/2016 09:58, Wanpeng Li wrote: >>> From: Wanpeng Li >>> >>> I observed that kvmvapic(to optimize flexpriority=N or AMD) is used >>> to boost TPR access when testing kvm-unit-test/eventinj.flat tpr

Re: [PATCH] KVM: VMX: Enable MSR-BASED TPR shadow even if w/o APICv

2016-09-14 17:40 GMT+08:00 Paolo Bonzini : > > > On 14/09/2016 09:58, Wanpeng Li wrote: >> From: Wanpeng Li >> >> I observed that kvmvapic(to optimize flexpriority=N or AMD) is used >> to boost TPR access when testing kvm-unit-test/eventinj.flat tpr

Re: [PATCH] KVM: VMX: Enable MSR-BASED TPR shadow even if w/o APICv

2016-09-14 17:40 GMT+08:00 Paolo Bonzini : > > > On 14/09/2016 09:58, Wanpeng Li wrote: >> From: Wanpeng Li >> >> I observed that kvmvapic(to optimize flexpriority=N or AMD) is used >> to boost TPR access when testing kvm-unit-test/eventinj.flat tpr case >> on my haswell desktop (w/ flexpriority,

Re: [PATCH] KVM: VMX: Enable MSR-BASED TPR shadow even if w/o APICv

2016-09-14 11:40+0200, Paolo Bonzini: > On 14/09/2016 09:58, Wanpeng Li wrote: >> From: Wanpeng Li >> >> I observed that kvmvapic(to optimize flexpriority=N or AMD) is used >> to boost TPR access when testing kvm-unit-test/eventinj.flat tpr case >> on my haswell desktop

Re: [PATCH] KVM: VMX: Enable MSR-BASED TPR shadow even if w/o APICv

2016-09-14 11:40+0200, Paolo Bonzini: > On 14/09/2016 09:58, Wanpeng Li wrote: >> From: Wanpeng Li >> >> I observed that kvmvapic(to optimize flexpriority=N or AMD) is used >> to boost TPR access when testing kvm-unit-test/eventinj.flat tpr case >> on my haswell desktop (w/ flexpriority, w/o

Re: [PATCH] KVM: VMX: Enable MSR-BASED TPR shadow even if w/o APICv

On 14/09/2016 09:58, Wanpeng Li wrote: > From: Wanpeng Li > > I observed that kvmvapic(to optimize flexpriority=N or AMD) is used > to boost TPR access when testing kvm-unit-test/eventinj.flat tpr case > on my haswell desktop (w/ flexpriority, w/o APICv). Commit

Re: [PATCH] KVM: VMX: Enable MSR-BASED TPR shadow even if w/o APICv

On 14/09/2016 09:58, Wanpeng Li wrote: > From: Wanpeng Li > > I observed that kvmvapic(to optimize flexpriority=N or AMD) is used > to boost TPR access when testing kvm-unit-test/eventinj.flat tpr case > on my haswell desktop (w/ flexpriority, w/o APICv). Commit (8d14695f9542 > x86, apicv:

[PATCH] KVM: VMX: Enable MSR-BASED TPR shadow even if w/o APICv

From: Wanpeng Li I observed that kvmvapic(to optimize flexpriority=N or AMD) is used to boost TPR access when testing kvm-unit-test/eventinj.flat tpr case on my haswell desktop (w/ flexpriority, w/o APICv). Commit (8d14695f9542 x86, apicv: add virtual x2apic support)

[PATCH] KVM: VMX: Enable MSR-BASED TPR shadow even if w/o APICv

From: Wanpeng Li I observed that kvmvapic(to optimize flexpriority=N or AMD) is used to boost TPR access when testing kvm-unit-test/eventinj.flat tpr case on my haswell desktop (w/ flexpriority, w/o APICv). Commit (8d14695f9542 x86, apicv: add virtual x2apic support) disable virtual x2apic