Re: [PATCH 1/3] KVM: x86: optimization: cache physical address width to avoid excessive enumerations of CPUID entries

[Paolo Bonzini <pbonzini@redhat.com>]

On 29/03/2015 22:56, Eugene Korenevsky wrote:
> cpuid_maxphyaddr() which performs lot of memory accesses is called extensively
> across KVM, especially in nVMX code.
> This patch adds cached value of maxphyaddr to vcpu.arch to reduce the pressure onto
> CPU cache and simplify the code of cpuid_maxphyaddr() callers. The cached value is
> initialized in kvm_arch_vcpu_init() and reloaded every time CPUID is updated by
> usermode. It is obvious that these reloads occur infrequently.
> 
> Signed-off-by: Eugene Korenevsky <ekorenevsky@gmail.com>
> ---
>  arch/x86/include/asm/kvm_host.h |  4 +++-
>  arch/x86/kvm/cpuid.c            | 33 ++++++++++++++++++---------------
>  arch/x86/kvm/cpuid.h            |  6 ++++++
>  arch/x86/kvm/x86.c              |  2 ++
>  4 files changed, 29 insertions(+), 16 deletions(-)
> 
> diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
> index a236e39..2362a60 100644
> --- a/arch/x86/include/asm/kvm_host.h
> +++ b/arch/x86/include/asm/kvm_host.h
> @@ -431,6 +431,9 @@ struct kvm_vcpu_arch {
>  
>  	int cpuid_nent;
>  	struct kvm_cpuid_entry2 cpuid_entries[KVM_MAX_CPUID_ENTRIES];
> +
> +	int maxphyaddr;
> +
>  	/* emulate context */
>  
>  	struct x86_emulate_ctxt emulate_ctxt;
> @@ -1128,7 +1131,6 @@ int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end)
>  int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end);
>  int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);
>  void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
> -int cpuid_maxphyaddr(struct kvm_vcpu *vcpu);
>  int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v);
>  int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu);
>  int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu);
> diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
> index 8a80737..59b69f6 100644
> --- a/arch/x86/kvm/cpuid.c
> +++ b/arch/x86/kvm/cpuid.c
> @@ -104,6 +104,9 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu)
>  		((best->eax & 0xff00) >> 8) != 0)
>  		return -EINVAL;
>  
> +	/* Update physical-address width */
> +	vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu);
> +
>  	kvm_pmu_cpuid_update(vcpu);
>  	return 0;
>  }
> @@ -135,6 +138,21 @@ static void cpuid_fix_nx_cap(struct kvm_vcpu *vcpu)
>  	}
>  }
>  
> +int cpuid_query_maxphyaddr(struct kvm_vcpu *vcpu)
> +{
> +	struct kvm_cpuid_entry2 *best;
> +
> +	best = kvm_find_cpuid_entry(vcpu, 0x80000000, 0);
> +	if (!best || best->eax < 0x80000008)
> +		goto not_found;
> +	best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0);
> +	if (best)
> +		return best->eax & 0xff;
> +not_found:
> +	return 36;
> +}
> +EXPORT_SYMBOL_GPL(cpuid_query_maxphyaddr);
> +
>  /* when an old userspace process fills a new kernel module */
>  int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu,
>  			     struct kvm_cpuid *cpuid,
> @@ -757,21 +775,6 @@ struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu,
>  }
>  EXPORT_SYMBOL_GPL(kvm_find_cpuid_entry);
>  
> -int cpuid_maxphyaddr(struct kvm_vcpu *vcpu)
> -{
> -	struct kvm_cpuid_entry2 *best;
> -
> -	best = kvm_find_cpuid_entry(vcpu, 0x80000000, 0);
> -	if (!best || best->eax < 0x80000008)
> -		goto not_found;
> -	best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0);
> -	if (best)
> -		return best->eax & 0xff;
> -not_found:
> -	return 36;
> -}
> -EXPORT_SYMBOL_GPL(cpuid_maxphyaddr);
> -
>  /*
>   * If no match is found, check whether we exceed the vCPU's limit
>   * and return the content of the highest valid _standard_ leaf instead.
> diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
> index 4452eed..78b61b4 100644
> --- a/arch/x86/kvm/cpuid.h
> +++ b/arch/x86/kvm/cpuid.h
> @@ -20,6 +20,12 @@ int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu,
>  			      struct kvm_cpuid_entry2 __user *entries);
>  void kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, u32 *ecx, u32 *edx);
>  
> +int cpuid_query_maxphyaddr(struct kvm_vcpu *vcpu);
> +
> +static inline int cpuid_maxphyaddr(struct kvm_vcpu *vcpu)
> +{
> +	return vcpu->arch.maxphyaddr;
> +}
>  
>  static inline bool guest_cpuid_has_xsave(struct kvm_vcpu *vcpu)
>  {
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index bd7a70b..084e1d5 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -7289,6 +7289,8 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
>  	vcpu->arch.guest_supported_xcr0 = 0;
>  	vcpu->arch.guest_xstate_size = XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET;
>  
> +	vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu);
> +
>  	kvm_async_pf_hash_reset(vcpu);
>  	kvm_pmu_init(vcpu);
>  
> 

Applied series, thanks.

Paolo