Re: [PATCH 1/3] Provide VM capability to disable PMU virtualization for individual VMs

[Like Xu <like.xu.linux@gmail.com>]

Hi David,

Thanks for coming to address this.

Please modify the patch(es) subject to follow the convention.

On 20/1/2022 2:28 am, David Dunn wrote:
> When PMU virtualization is enabled via the module parameter, usermode
> can disable PMU virtualization on individual VMs using this new
> capability.

Will the user space fail or be notified when the enable_pmu say no ?

> 
> This provides a uniform way to disable PMU virtualization on x86.  Since
> AMD doesn't have a CPUID bit for PMU support, disabling PMU

Not entirely absent, such as PERFCTR_CORE.

> virtualization requires some other state to indicate whether the PMU
> related MSRs are ignored.

Not just ignored, but made to disappear altogether.

> 
> Since KVM_GET_SUPPORTED_CPUID reports the maximal CPUID information
> based on module parameters, usermode will need to adjust CPUID when
> disabling PMU virtualization on individual VMs.  On Intel CPUs, the
> change to PMU enablement will not alter existing until SET_CPUID2 is
> invoked.

Please clarify. Do we have a requirement for the order in which the
SET_CPUID2 and ioctl_enable_cap interfaces are called?

> 
> Signed-off-by: David Dunn <daviddunn@google.com>
> ---
>   arch/x86/include/asm/kvm_host.h |  1 +
>   arch/x86/kvm/svm/pmu.c          |  2 +-
>   arch/x86/kvm/vmx/pmu_intel.c    |  2 +-
>   arch/x86/kvm/x86.c              | 11 +++++++++++
>   include/uapi/linux/kvm.h        |  1 +
>   tools/include/uapi/linux/kvm.h  |  1 +
>   6 files changed, 16 insertions(+), 2 deletions(-)
> 
> diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
> index 682ad02a4e58..5cdcd4a7671b 100644
> --- a/arch/x86/include/asm/kvm_host.h
> +++ b/arch/x86/include/asm/kvm_host.h
> @@ -1232,6 +1232,7 @@ struct kvm_arch {
>   	hpa_t	hv_root_tdp;
>   	spinlock_t hv_root_tdp_lock;
>   #endif
> +	bool enable_pmu;

The name makes it difficult to distinguish the scope of access to the variable.
Try storing it via "pmu->version == 0".

>   };
>   
>   struct kvm_vm_stat {
> diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c
> index 5aa45f13b16d..605bcfb55625 100644
> --- a/arch/x86/kvm/svm/pmu.c
> +++ b/arch/x86/kvm/svm/pmu.c
> @@ -101,7 +101,7 @@ static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr,
>   {
>   	struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu);
>   
> -	if (!enable_pmu)
> +	if (!enable_pmu || !vcpu->kvm->arch.enable_pmu)
>   		return NULL;
>   
>   	switch (msr) {
> diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
> index 466d18fc0c5d..4c3885765027 100644
> --- a/arch/x86/kvm/vmx/pmu_intel.c
> +++ b/arch/x86/kvm/vmx/pmu_intel.c
> @@ -487,7 +487,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
>   	pmu->reserved_bits = 0xffffffff00200000ull;
>   
>   	entry = kvm_find_cpuid_entry(vcpu, 0xa, 0);
> -	if (!entry || !enable_pmu)
> +	if (!entry || !vcpu->kvm->arch.enable_pmu || !enable_pmu)
>   		return;
>   	eax.full = entry->eax;
>   	edx.full = entry->edx;
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index 55518b7d3b96..9b640c5bb4f6 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -4326,6 +4326,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
>   		if (r < sizeof(struct kvm_xsave))
>   			r = sizeof(struct kvm_xsave);
>   		break;
> +	case KVM_CAP_ENABLE_PMU:
> +		r = enable_pmu;
> +		break;
>   	}
>   	default:
>   		break;
> @@ -5937,6 +5940,13 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
>   		kvm->arch.exit_on_emulation_error = cap->args[0];
>   		r = 0;
>   		break;
> +	case KVM_CAP_ENABLE_PMU:
> +		r = -EINVAL;
> +		if (!enable_pmu || cap->args[0] & ~1)
> +			break;
> +		kvm->arch.enable_pmu = cap->args[0];
> +		r = 0;
> +		break;
>   	default:
>   		r = -EINVAL;
>   		break;
> @@ -11562,6 +11572,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
>   	raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);
>   
>   	kvm->arch.guest_can_read_msr_platform_info = true;
> +	kvm->arch.enable_pmu = true;
>   
>   #if IS_ENABLED(CONFIG_HYPERV)
>   	spin_lock_init(&kvm->arch.hv_root_tdp_lock);
> diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
> index 9563d294f181..37cbcdffe773 100644
> --- a/include/uapi/linux/kvm.h
> +++ b/include/uapi/linux/kvm.h
> @@ -1133,6 +1133,7 @@ struct kvm_ppc_resize_hpt {
>   #define KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM 206
>   #define KVM_CAP_VM_GPA_BITS 207
>   #define KVM_CAP_XSAVE2 208
> +#define KVM_CAP_ENABLE_PMU 209

Rename it to KVM_CAP_PMU_CAPABILITY and use the bit 0 for *DISABLE_PMU*.

>   
>   #ifdef KVM_CAP_IRQ_ROUTING
>   
> diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
> index f066637ee206..e71712c71ab1 100644
> --- a/tools/include/uapi/linux/kvm.h
> +++ b/tools/include/uapi/linux/kvm.h
> @@ -1132,6 +1132,7 @@ struct kvm_ppc_resize_hpt {
>   #define KVM_CAP_ARM_MTE 205
>   #define KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM 206
>   #define KVM_CAP_XSAVE2 207
> +#define KVM_CAP_ENABLE_PMU 209
>   
>   #ifdef KVM_CAP_IRQ_ROUTING
>