Re: [PATCH 3/3] KVM: Add capability to not exit on PAUSE

["Michael S. Tsirkin" <mst@redhat.com>]

On Sat, Nov 25, 2017 at 02:09:33PM +0100, Jan H. Schönherr wrote:
> Allow to disable pause loop exit/pause filtering on a per VM basis.
> 
> If some VMs have dedicated host CPUs, they won't be negatively affected
> due to needlessly intercepted PAUSE instructions.
> 
> Signed-off-by: Jan H. Schönherr <jschoenh@amazon.de>

Nice, thanks!

> ---
> Note: AMD code paths are only compile tested
> ---
>  Documentation/virtual/kvm/api.txt |  8 ++++++++
>  arch/x86/include/asm/kvm_host.h   |  1 +
>  arch/x86/kvm/svm.c                |  3 ++-
>  arch/x86/kvm/vmx.c                | 17 +++++++++++++----
>  arch/x86/kvm/x86.c                |  5 +++++
>  arch/x86/kvm/x86.h                |  5 +++++
>  include/uapi/linux/kvm.h          |  1 +
>  7 files changed, 35 insertions(+), 5 deletions(-)
> 
> diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
> index c06bb41..42a54d1 100644
> --- a/Documentation/virtual/kvm/api.txt
> +++ b/Documentation/virtual/kvm/api.txt
> @@ -4184,6 +4184,14 @@ This capability indicates that a guest using HLT to stop a virtual CPU will not
>  cause a VM exit. As such, time spent while a virtual CPU is halted in this way
>  will then be accounted for as guest running time on the host.
>  
> +7.15 KVM_CAP_X86_GUEST_PAUSE
> +
> +Architectures: x86
> +Parameters: none
> +Returns: 0 on success
> +
> +This capability indicates that a guest using PAUSE will not cause a VM exit.
> +
>  8. Other capabilities.
>  ----------------------
>  
> diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
> index 3197c2d..0d4ea32 100644
> --- a/arch/x86/include/asm/kvm_host.h
> +++ b/arch/x86/include/asm/kvm_host.h
> @@ -782,6 +782,7 @@ struct kvm_arch {
>  	gpa_t wall_clock;
>  
>  	bool hlt_in_guest;
> +	bool pause_in_guest;
>  	bool mwait_in_guest;
>  
>  	bool ept_identity_pagetable_done;
> diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
> index c135b98..a5eb60a 100644
> --- a/arch/x86/kvm/svm.c
> +++ b/arch/x86/kvm/svm.c
> @@ -1314,7 +1314,8 @@ static void init_vmcb(struct vcpu_svm *svm)
>  	svm->nested.vmcb = 0;
>  	svm->vcpu.arch.hflags = 0;
>  
> -	if (boot_cpu_has(X86_FEATURE_PAUSEFILTER)) {
> +	if (boot_cpu_has(X86_FEATURE_PAUSEFILTER) &&
> +	    !kvm_pause_in_guest(svm->vcpu.kvm)) {
>  		control->pause_filter_count = 3000;
>  		set_intercept(svm, INTERCEPT_PAUSE);
>  	}
> diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
> index 1b67433..5f8c33b 100644
> --- a/arch/x86/kvm/vmx.c
> +++ b/arch/x86/kvm/vmx.c
> @@ -5352,7 +5352,7 @@ static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx)
>  	}
>  	if (!enable_unrestricted_guest)
>  		exec_control &= ~SECONDARY_EXEC_UNRESTRICTED_GUEST;
> -	if (!ple_gap)
> +	if (kvm_pause_in_guest(vmx->vcpu.kvm))
>  		exec_control &= ~SECONDARY_EXEC_PAUSE_LOOP_EXITING;
>  	if (!kvm_vcpu_apicv_active(vcpu))
>  		exec_control &= ~(SECONDARY_EXEC_APIC_REGISTER_VIRT |
> @@ -5519,7 +5519,7 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx)
>  		vmcs_write64(POSTED_INTR_DESC_ADDR, __pa((&vmx->pi_desc)));
>  	}
>  
> -	if (ple_gap) {
> +	if (!kvm_pause_in_guest(vmx->vcpu.kvm)) {
>  		vmcs_write32(PLE_GAP, ple_gap);
>  		vmx->ple_window = ple_window;
>  		vmx->ple_window_dirty = true;
> @@ -6975,7 +6975,7 @@ static __exit void hardware_unsetup(void)
>   */
>  static int handle_pause(struct kvm_vcpu *vcpu)
>  {
> -	if (ple_gap)
> +	if (!kvm_pause_in_guest(vcpu->kvm))
>  		grow_ple_window(vcpu);
>  
>  	/*
> @@ -9730,6 +9730,13 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
>  	return ERR_PTR(err);
>  }
>  
> +static int vmx_vm_init(struct kvm *kvm)
> +{
> +	if (!ple_gap)
> +		kvm->arch.pause_in_guest = true;
> +	return 0;
> +}
> +
>  static void __init vmx_check_processor_compat(void *rtn)
>  {
>  	struct vmcs_config vmcs_conf;
> @@ -11793,7 +11800,7 @@ static void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu)
>  
>  static void vmx_sched_in(struct kvm_vcpu *vcpu, int cpu)
>  {
> -	if (ple_gap)
> +	if (!kvm_pause_in_guest(vcpu->kvm))
>  		shrink_ple_window(vcpu);
>  }
>  
> @@ -12152,6 +12159,8 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
>  	.cpu_has_accelerated_tpr = report_flexpriority,
>  	.cpu_has_high_real_mode_segbase = vmx_has_high_real_mode_segbase,
>  
> +	.vm_init = vmx_vm_init,
> +
>  	.vcpu_create = vmx_create_vcpu,
>  	.vcpu_free = vmx_free_vcpu,
>  	.vcpu_reset = vmx_vcpu_reset,
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index f17c520..e13df00 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -2756,6 +2756,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
>   	case KVM_CAP_SPLIT_IRQCHIP:
>  	case KVM_CAP_IMMEDIATE_EXIT:
>  	case KVM_CAP_X86_GUEST_HLT:
> +	case KVM_CAP_X86_GUEST_PAUSE:
>  		r = 1;
>  		break;
>  	case KVM_CAP_ADJUST_CLOCK:
> @@ -4073,6 +4074,10 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
>  		kvm->arch.hlt_in_guest = true;
>  		r = 0;
>  		break;
> +	case KVM_CAP_X86_GUEST_PAUSE:
> +		kvm->arch.pause_in_guest = true;
> +		r = 0;
> +		break;
>  	default:
>  		r = -EINVAL;
>  		break;
> diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
> index b2066aa..56297c4 100644
> --- a/arch/x86/kvm/x86.h
> +++ b/arch/x86/kvm/x86.h
> @@ -271,4 +271,9 @@ static inline bool kvm_hlt_in_guest(struct kvm *kvm)
>  	return kvm->arch.hlt_in_guest;
>  }
>  
> +static inline bool kvm_pause_in_guest(struct kvm *kvm)
> +{
> +	return kvm->arch.pause_in_guest;
> +}
> +
>  #endif
> diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
> index ff8f266..bc2b654 100644
> --- a/include/uapi/linux/kvm.h
> +++ b/include/uapi/linux/kvm.h
> @@ -933,6 +933,7 @@ struct kvm_ppc_resize_hpt {
>  #define KVM_CAP_HYPERV_VP_INDEX 149
>  #define KVM_CAP_S390_AIS_MIGRATION 150
>  #define KVM_CAP_X86_GUEST_HLT 151
> +#define KVM_CAP_X86_GUEST_PAUSE 152
>  
>  #ifdef KVM_CAP_IRQ_ROUTING
>  
> -- 
> 2.3.1.dirty