linux-kernel - Re: [PATCH 1/2] KVM: x86: Snapshot host's MSR_IA32_ARCH

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <02d97490-9e59-8e78-8a54-0139d316d3b7@intel.com>
Date:   Thu, 8 Jun 2023 11:12:41 +0800
From:   Xiaoyao Li <xiaoyao.li@...el.com>
To:     Sean Christopherson <seanjc@...gle.com>,
        Paolo Bonzini <pbonzini@...hat.com>
Cc:     kvm@...r.kernel.org, linux-kernel@...r.kernel.org,
        Chao Gao <chao.gao@...el.com>,
        Pawan Gupta <pawan.kumar.gupta@...ux.intel.com>
Subject: Re: [PATCH 1/2] KVM: x86: Snapshot host's MSR_IA32_ARCH_CAPABILITIES

On 6/7/2023 8:43 AM, Sean Christopherson wrote:
> Snapshot the host's MSR_IA32_ARCH_CAPABILITIES, if it's supported, instead
> of reading the MSR every time KVM wants to query the host state, e.g. when
> initializing the default value during vCPU creation.  The paths that query
> ARCH_CAPABILITIES aren't particularly performance sensitive, but creating
> vCPUs is a frequent enough operation that burning 8 bytes is a good
> trade-off.
> 
> Alternatively, KVM could add a field in kvm_caps and thus skip the
> on-demand calculations entirely, but a pure snapshot isn't possible due to
> the way KVM handles the l1tf_vmx_mitigation module param.  And unlike the
> other "supported" fields in kvm_caps, KVM doesn't enforce the "supported"
> value, i.e. KVM treats ARCH_CAPABILITIES like a CPUID leaf and lets
> userspace advertise whatever it wants.  Those problems are solvable, but
> it's not clear there is real benefit versus snapshotting the host value,
> and grabbing the host value will allow additional cleanup of KVM's
> FB_CLEAR_CTRL code.

Reviewed-by: Xiaoyao Li <xiaoyao.li@...el.com>

> Link: https://lore.kernel.org/all/20230524061634.54141-2-chao.gao@intel.com
> Cc: Chao Gao <chao.gao@...el.com>
> Cc: Xiaoyao Li <xiaoyao.li@...el.com>
> Signed-off-by: Sean Christopherson <seanjc@...gle.com>
> ---
>   arch/x86/kvm/vmx/vmx.c | 22 ++++++----------------
>   arch/x86/kvm/x86.c     | 13 +++++++------
>   arch/x86/kvm/x86.h     |  1 +
>   3 files changed, 14 insertions(+), 22 deletions(-)
> 
> diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
> index 2d9d155691a7..42d1148f933c 100644
> --- a/arch/x86/kvm/vmx/vmx.c
> +++ b/arch/x86/kvm/vmx/vmx.c
> @@ -255,14 +255,9 @@ static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf)
>   		return 0;
>   	}
>   
> -	if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) {
> -		u64 msr;
> -
> -		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, msr);
> -		if (msr & ARCH_CAP_SKIP_VMENTRY_L1DFLUSH) {
> -			l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_NOT_REQUIRED;
> -			return 0;
> -		}
> +	if (host_arch_capabilities & ARCH_CAP_SKIP_VMENTRY_L1DFLUSH) {
> +		l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_NOT_REQUIRED;
> +		return 0;
>   	}
>   
>   	/* If set to auto use the default l1tf mitigation method */
> @@ -373,15 +368,10 @@ static int vmentry_l1d_flush_get(char *s, const struct kernel_param *kp)
>   
>   static void vmx_setup_fb_clear_ctrl(void)
>   {
> -	u64 msr;
> -
> -	if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES) &&
> +	if ((host_arch_capabilities & ARCH_CAP_FB_CLEAR_CTRL) &&
>   	    !boot_cpu_has_bug(X86_BUG_MDS) &&
> -	    !boot_cpu_has_bug(X86_BUG_TAA)) {
> -		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, msr);
> -		if (msr & ARCH_CAP_FB_CLEAR_CTRL)
> -			vmx_fb_clear_ctrl_available = true;
> -	}
> +	    !boot_cpu_has_bug(X86_BUG_TAA))
> +		vmx_fb_clear_ctrl_available = true;
>   }
>   
>   static __always_inline void vmx_disable_fb_clear(struct vcpu_vmx *vmx)
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index 7c7be4815eaa..7c2e796fa460 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -237,6 +237,9 @@ EXPORT_SYMBOL_GPL(enable_apicv);
>   u64 __read_mostly host_xss;
>   EXPORT_SYMBOL_GPL(host_xss);
>   
> +u64 __read_mostly host_arch_capabilities;
> +EXPORT_SYMBOL_GPL(host_arch_capabilities);
> +
>   const struct _kvm_stats_desc kvm_vm_stats_desc[] = {
>   	KVM_GENERIC_VM_STATS(),
>   	STATS_DESC_COUNTER(VM, mmu_shadow_zapped),
> @@ -1612,12 +1615,7 @@ static bool kvm_is_immutable_feature_msr(u32 msr)
>   
>   static u64 kvm_get_arch_capabilities(void)
>   {
> -	u64 data = 0;
> -
> -	if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) {
> -		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, data);
> -		data &= KVM_SUPPORTED_ARCH_CAP;
> -	}
> +	u64 data = host_arch_capabilities & KVM_SUPPORTED_ARCH_CAP;
>   
>   	/*
>   	 * If nx_huge_pages is enabled, KVM's shadow paging will ensure that
> @@ -9492,6 +9490,9 @@ static int __kvm_x86_vendor_init(struct kvm_x86_init_ops *ops)
>   
>   	kvm_init_pmu_capability(ops->pmu_ops);
>   
> +	if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES))
> +		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, host_arch_capabilities);
> +
>   	r = ops->hardware_setup();
>   	if (r != 0)
>   		goto out_mmu_exit;
> diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
> index 82e3dafc5453..1e7be1f6ab29 100644
> --- a/arch/x86/kvm/x86.h
> +++ b/arch/x86/kvm/x86.h
> @@ -323,6 +323,7 @@ fastpath_t handle_fastpath_set_msr_irqoff(struct kvm_vcpu *vcpu);
>   
>   extern u64 host_xcr0;
>   extern u64 host_xss;
> +extern u64 host_arch_capabilities;
>   
>   extern struct kvm_caps kvm_caps;
>