Re: [PATCH v4] KVM: nVMX: Fully support of nested VMX preemption timer

[Gleb Natapov <gleb@redhat.com>]

On Mon, Sep 16, 2013 at 01:49:41PM +0800, Arthur Chunqi Li wrote:
> On Sun, Sep 15, 2013 at 8:31 PM, Gleb Natapov <gleb@redhat.com> wrote:
> > On Fri, Sep 06, 2013 at 10:04:51AM +0800, Arthur Chunqi Li wrote:
> >> This patch contains the following two changes:
> >> 1. Fix the bug in nested preemption timer support. If vmexit L2->L0
> >> with some reasons not emulated by L1, preemption timer value should
> >> be save in such exits.
> >> 2. Add support of "Save VMX-preemption timer value" VM-Exit controls
> >> to nVMX.
> >>
> >> With this patch, nested VMX preemption timer features are fully
> >> supported.
> >>
> >> Signed-off-by: Arthur Chunqi Li <yzt356@gmail.com>
> >> ---
> >> ChangeLog to v3:
> >> Move nested_adjust_preemption_timer to the latest place just before vmenter.
> >> Some minor changes.
> >>
> >>  arch/x86/include/uapi/asm/msr-index.h |    1 +
> >>  arch/x86/kvm/vmx.c                    |   49 +++++++++++++++++++++++++++++++--
> >>  2 files changed, 48 insertions(+), 2 deletions(-)
> >>
> >> diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/uapi/asm/msr-index.h
> >> index bb04650..b93e09a 100644
> >> --- a/arch/x86/include/uapi/asm/msr-index.h
> >> +++ b/arch/x86/include/uapi/asm/msr-index.h
> >> @@ -536,6 +536,7 @@
> >>
> >>  /* MSR_IA32_VMX_MISC bits */
> >>  #define MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS (1ULL << 29)
> >> +#define MSR_IA32_VMX_MISC_PREEMPTION_TIMER_SCALE   0x1F
> >>  /* AMD-V MSRs */
> >>
> >>  #define MSR_VM_CR                       0xc0010114
> >> diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
> >> index 1f1da43..f364d16 100644
> >> --- a/arch/x86/kvm/vmx.c
> >> +++ b/arch/x86/kvm/vmx.c
> >> @@ -374,6 +374,8 @@ struct nested_vmx {
> >>        */
> >>       struct page *apic_access_page;
> >>       u64 msr_ia32_feature_control;
> >> +     /* Set if vmexit is L2->L1 */
> >> +     bool nested_vmx_exit;
> > Do not see why it is needed, see bellow.
> >
> >>  };
> >>
> >>  #define POSTED_INTR_ON  0
> >> @@ -2204,7 +2206,17 @@ static __init void nested_vmx_setup_ctls_msrs(void)
> >>  #ifdef CONFIG_X86_64
> >>               VM_EXIT_HOST_ADDR_SPACE_SIZE |
> >>  #endif
> >> -             VM_EXIT_LOAD_IA32_PAT | VM_EXIT_SAVE_IA32_PAT;
> >> +             VM_EXIT_LOAD_IA32_PAT | VM_EXIT_SAVE_IA32_PAT |
> >> +             VM_EXIT_SAVE_VMX_PREEMPTION_TIMER;
> >> +     if (!(nested_vmx_pinbased_ctls_high &
> >> +                             PIN_BASED_VMX_PREEMPTION_TIMER) ||
> >> +                     !(nested_vmx_exit_ctls_high &
> >> +                             VM_EXIT_SAVE_VMX_PREEMPTION_TIMER)) {
> >> +             nested_vmx_exit_ctls_high &=
> >> +                     (~VM_EXIT_SAVE_VMX_PREEMPTION_TIMER);
> >> +             nested_vmx_pinbased_ctls_high &=
> >> +                     (~PIN_BASED_VMX_PREEMPTION_TIMER);
> >> +     }
> >>       nested_vmx_exit_ctls_high |= (VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR |
> >>                                     VM_EXIT_LOAD_IA32_EFER);
> >>
> >> @@ -6707,6 +6719,24 @@ static void vmx_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2)
> >>       *info2 = vmcs_read32(VM_EXIT_INTR_INFO);
> >>  }
> >>
> >> +static void nested_adjust_preemption_timer(struct kvm_vcpu *vcpu)
> >> +{
> >> +     u64 delta_tsc_l1;
> >> +     u32 preempt_val_l1, preempt_val_l2, preempt_scale;
> >> +
> >> +     preempt_scale = native_read_msr(MSR_IA32_VMX_MISC) &
> >> +                     MSR_IA32_VMX_MISC_PREEMPTION_TIMER_SCALE;
> >> +     preempt_val_l2 = vmcs_read32(VMX_PREEMPTION_TIMER_VALUE);
> >> +     delta_tsc_l1 = kvm_x86_ops->read_l1_tsc(vcpu,
> >> +                     native_read_tsc()) - vcpu->arch.last_guest_tsc;
> >> +     preempt_val_l1 = delta_tsc_l1 >> preempt_scale;
> >> +     if (preempt_val_l2 <= preempt_val_l1)
> >> +             preempt_val_l2 = 0;
> >> +     else
> >> +             preempt_val_l2 -= preempt_val_l1;
> >> +     vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, preempt_val_l2);
> >> +}
> >> +
> >>  /*
> >>   * The guest has exited.  See if we can fix it or if we need userspace
> >>   * assistance.
> >> @@ -6736,9 +6766,11 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
> >>               vmx->nested.nested_run_pending = 0;
> >>
> >>       if (is_guest_mode(vcpu) && nested_vmx_exit_handled(vcpu)) {
> >> +             vmx->nested.nested_vmx_exit = true;
> >>               nested_vmx_vmexit(vcpu);
> >>               return 1;
> >>       }
> >> +     vmx->nested.nested_vmx_exit = false;
> >>
> >>       if (exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY) {
> >>               vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY;
> >> @@ -7132,6 +7164,8 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
> >>       debugctlmsr = get_debugctlmsr();
> >>
> >>       vmx->__launched = vmx->loaded_vmcs->launched;
> >> +     if (is_guest_mode(vcpu) && !(vmx->nested.nested_vmx_exit))
> > How is_guest_mode() and nested_vmx_exi can be both true? The only place
> > nested_vmx_exit is set to true is just before call to
> > nested_vmx_vmexit(). The firs thing nested_vmx_vmexit() does is makes
> > is_guest_mode() false. To enter guest mode again at least one other
> > vmexit from L1 to L0 is needed at which point nested_vmx_exit will be
> > reset to false again.
> >
> > If you want to avoid calling nested_adjust_preemption_timer() during
> > vmlaunch/vmresume emulation (and it looks like this is what you are
> > trying to achieve here) you can check nested_run_pending.
> Besides vmlaunch/vmresume emulation, every exit from L2->L1 should not
> call nested_adjust_preemption_timer(), this function is just used to
> adjust preemption timer when L2->L0->L2. Can nested_run_pending
> distinguish this?
> 
On L2->L1 exit is_guest_mode() will be false during vmx_vcpu_run().
On L1->L2 entry nested_run_pending will be true. On L0->L2 entry
is_guest_mode() == true && nested_run_pending == false.

--
			Gleb.