Re: [PATCH v2 07/21] KVM: x86: Add a framework for enabling KVM-governed x86 features

[Zeng Guang]

On 7/29/2023 9:15 AM, Sean Christopherson wrote:
> Introduce yet another X86_FEATURE flag framework to manage and cache KVM
> governed features (for lack of a better name).  "Governed" in this case
> means that KVM has some level of involvement and/or vested interest in
> whether or not an X86_FEATURE can be used by the guest.  The intent of the
> framework is twofold: to simplify caching of guest CPUID flags that KVM
> needs to frequently query, and to add clarity to such caching, e.g. it
> isn't immediately obvious that SVM's bundle of flags for "optional nested
> SVM features" track whether or not a flag is exposed to L1.
>
> Begrudgingly define KVM_MAX_NR_GOVERNED_FEATURES for the size of the
> bitmap to avoid exposing governed_features.h in arch/x86/include/asm/, but
> add a FIXME to call out that it can and should be cleaned up once
> "struct kvm_vcpu_arch" is no longer expose to the kernel at large.
>
> Signed-off-by: Sean Christopherson <seanjc@xxxxxxxxxx>
> ---
>   arch/x86/include/asm/kvm_host.h  | 19 +++++++++++++
>   arch/x86/kvm/cpuid.c             |  4 +++
>   arch/x86/kvm/cpuid.h             | 46 ++++++++++++++++++++++++++++++++
>   arch/x86/kvm/governed_features.h |  9 +++++++
>   4 files changed, 78 insertions(+)
>   create mode 100644 arch/x86/kvm/governed_features.h
>
> diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
> index dad9331c5270..007fa8bfd634 100644
> --- a/arch/x86/include/asm/kvm_host.h
> +++ b/arch/x86/include/asm/kvm_host.h
> @@ -831,6 +831,25 @@ struct kvm_vcpu_arch {
>   	struct kvm_cpuid_entry2 *cpuid_entries;
>   	struct kvm_hypervisor_cpuid kvm_cpuid;
>   
> +	/*
> +	 * FIXME: Drop this macro and use KVM_NR_GOVERNED_FEATURES directly
> +	 * when "struct kvm_vcpu_arch" is no longer defined in an
> +	 * arch/x86/include/asm header.  The max is mostly arbitrary, i.e.
> +	 * can be increased as necessary.
> +	 */
> +#define KVM_MAX_NR_GOVERNED_FEATURES BITS_PER_LONG
> +
> +	/*
> +	 * Track whether or not the guest is allowed to use features that are
> +	 * governed by KVM, where "governed" means KVM needs to manage state
> +	 * and/or explicitly enable the feature in hardware.  Typically, but
> +	 * not always, governed features can be used by the guest if and only
> +	 * if both KVM and userspace want to expose the feature to the guest.
> +	 */
> +	struct {
> +		DECLARE_BITMAP(enabled, KVM_MAX_NR_GOVERNED_FEATURES);
> +	} governed_features;
> +
>   	u64 reserved_gpa_bits;
>   	int maxphyaddr;
>   
> diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
> index 7f4d13383cf2..ef826568c222 100644
> --- a/arch/x86/kvm/cpuid.c
> +++ b/arch/x86/kvm/cpuid.c
> @@ -313,6 +313,10 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
>   	struct kvm_lapic *apic = vcpu->arch.apic;
>   	struct kvm_cpuid_entry2 *best;
>   
> +	BUILD_BUG_ON(KVM_NR_GOVERNED_FEATURES > KVM_MAX_NR_GOVERNED_FEATURES);
> +	bitmap_zero(vcpu->arch.governed_features.enabled,
> +		    KVM_MAX_NR_GOVERNED_FEATURES);
> +
>   	best = kvm_find_cpuid_entry(vcpu, 1);
>   	if (best && apic) {
>   		if (cpuid_entry_has(best, X86_FEATURE_TSC_DEADLINE_TIMER))
> diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
> index b1658c0de847..3000fbe97678 100644
> --- a/arch/x86/kvm/cpuid.h
> +++ b/arch/x86/kvm/cpuid.h
> @@ -232,4 +232,50 @@ static __always_inline bool guest_pv_has(struct kvm_vcpu *vcpu,
>   	return vcpu->arch.pv_cpuid.features & (1u << kvm_feature);
>   }
>   
> +enum kvm_governed_features {
> +#define KVM_GOVERNED_FEATURE(x) KVM_GOVERNED_##x,
> +#include "governed_features.h"
> +	KVM_NR_GOVERNED_FEATURES
> +};
> +
> +static __always_inline int kvm_governed_feature_index(unsigned int x86_feature)
> +{
> +	switch (x86_feature) {
> +#define KVM_GOVERNED_FEATURE(x) case x: return KVM_GOVERNED_##x;
> +#include "governed_features.h"
> +	default:
> +		return -1;
> +	}
> +}
> +
> +static __always_inline int kvm_is_governed_feature(unsigned int x86_feature)
> +{
> +	return kvm_governed_feature_index(x86_feature) >= 0;
> +}
> +

I think it proper to return a bool, not "int" instead.