Re: [PATCH] kvm: tracing: Fix unmatched kvm_entry and kvm_exit events

2021-01-21 Thread Paolo Bonzini
On 23/12/20 15:45, Dario Faggioli wrote: From: Lorenzo Brescia On VMX, if we exit and then re-enter immediately without leaving the vmx_vcpu_run() function, the kvm_entry event is not logged. That means we will see one (or more) kvm_exit, without its (their) corresponding kvm_entry, as shown he

Re: [PATCH] kvm: tracing: Fix unmatched kvm_entry and kvm_exit events

2021-01-18 Thread Paolo Bonzini
On 23/12/20 15:45, Dario Faggioli wrote: From: Lorenzo Brescia On VMX, if we exit and then re-enter immediately without leaving the vmx_vcpu_run() function, the kvm_entry event is not logged. That means we will see one (or more) kvm_exit, without its (their) corresponding kvm_entry, as shown he

Re: [PATCH] kvm: tracing: Fix unmatched kvm_entry and kvm_exit events

2021-01-15 Thread Dario Faggioli
On Wed, 2020-12-23 at 14:45 +, Dario Faggioli wrote: > From: Lorenzo Brescia > > On VMX, if we exit and then re-enter immediately without leaving > the vmx_vcpu_run() function, the kvm_entry event is not logged. > That means we will see one (or more) kvm_exit, without its (their) > correspond

[PATCH] kvm: tracing: Fix unmatched kvm_entry and kvm_exit events

2020-12-23 Thread Dario Faggioli
From: Lorenzo Brescia On VMX, if we exit and then re-enter immediately without leaving the vmx_vcpu_run() function, the kvm_entry event is not logged. That means we will see one (or more) kvm_exit, without its (their) corresponding kvm_entry, as shown here: CPU-1979 [002] 89.871187: kvm_entry: