linux-kernel - Re: [PATCH v2 5/5] KVM: SVM: allow AVIC to co-exist with a nested guest running

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]

Date:   Wed, 5 Jan 2022 21:56:31 +0000
From:   Sean Christopherson <seanjc@...gle.com>
To:     Maxim Levitsky <mlevitsk@...hat.com>
Cc:     kvm@...r.kernel.org, Jim Mattson <jmattson@...gle.com>,
        Thomas Gleixner <tglx@...utronix.de>,
        Joerg Roedel <joro@...tes.org>,
        "maintainer:X86 ARCHITECTURE (32-BIT AND 64-BIT)" <x86@...nel.org>,
        Vitaly Kuznetsov <vkuznets@...hat.com>,
        Borislav Petkov <bp@...en8.de>, linux-kernel@...r.kernel.org,
        Paolo Bonzini <pbonzini@...hat.com>,
        Dave Hansen <dave.hansen@...ux.intel.com>,
        "H. Peter Anvin" <hpa@...or.com>,
        Wanpeng Li <wanpengli@...cent.com>,
        Ingo Molnar <mingo@...hat.com>
Subject: Re: [PATCH v2 5/5] KVM: SVM: allow AVIC to co-exist with a nested
 guest running

On Mon, Dec 13, 2021, Maxim Levitsky wrote:
> @@ -1486,6 +1485,12 @@ struct kvm_x86_ops {
>  	int (*complete_emulated_msr)(struct kvm_vcpu *vcpu, int err);
>  
>  	void (*vcpu_deliver_sipi_vector)(struct kvm_vcpu *vcpu, u8 vector);
> +
> +	/*
> +	 * Returns false if for some reason APICv (e.g guest mode)
> +	 * must be inhibited on this vCPU

Comment is wrong, code returns 'true' if AVIC is inhibited due to is_guest_mode().
Even better, rename the hook to something that's more self-documenting.

vcpu_is_apicv_inhibited() jumps to mind, but that's a bad name since it's not
called by kvm_vcpu_apicv_active().  Maybe vcpu_has_apicv_inhibit_condition()?

> +	 */
> +	bool (*apicv_check_inhibit)(struct kvm_vcpu *vcpu);
>  };
>  
>  struct kvm_x86_nested_ops {
> diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
> index 34f62da2fbadd..5a8304938f51e 100644
> --- a/arch/x86/kvm/svm/avic.c
> +++ b/arch/x86/kvm/svm/avic.c
> @@ -734,6 +734,11 @@ int svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec)
>  	return 0;
>  }
>  
> +bool avic_is_vcpu_inhibited(struct kvm_vcpu *vcpu)

This should follow whatever wording we decide on for the kvm_x86_ops hook.  In
isolation, this name is too close to kvm_vcpu_apicv_active() and could be wrongly
assumed to mean that APICv is not inhibited for _any_ reason on this vCPU if it
returns false.

> +{
> +	return is_guest_mode(vcpu);
> +}
> +
>  bool svm_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu)
>  {
>  	return false;

...

> @@ -4486,6 +4493,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
>  	.complete_emulated_msr = svm_complete_emulated_msr,
>  
>  	.vcpu_deliver_sipi_vector = svm_vcpu_deliver_sipi_vector,
> +	.apicv_check_inhibit = avic_is_vcpu_inhibited,

This can technically be NULL if nested=0.

>  };
>  
>  /*
> diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
> index daa8ca84afccd..545684ea37353 100644
> --- a/arch/x86/kvm/svm/svm.h
> +++ b/arch/x86/kvm/svm/svm.h
> @@ -590,6 +590,7 @@ void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap);
>  void svm_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr);
>  void svm_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr);
>  int svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec);
> +bool avic_is_vcpu_inhibited(struct kvm_vcpu *vcpu);
>  bool svm_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu);
>  int svm_update_pi_irte(struct kvm *kvm, unsigned int host_irq,
>  		       uint32_t guest_irq, bool set);
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index 81a74d86ee5eb..125599855af47 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -9161,6 +9161,10 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit)
>  		r = kvm_check_nested_events(vcpu);
>  		if (r < 0)
>  			goto out;
> +
> +		/* Nested VM exit might need to update APICv status */
> +		if (kvm_check_request(KVM_REQ_APICV_UPDATE, vcpu))
> +			kvm_vcpu_update_apicv(vcpu);
>  	}
>  
>  	/* try to inject new event if pending */
> @@ -9538,6 +9542,10 @@ void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu)
>  	down_read(&vcpu->kvm->arch.apicv_update_lock);
>  
>  	activate = kvm_apicv_activated(vcpu->kvm);
> +
> +	if (kvm_x86_ops.apicv_check_inhibit)
> +		activate = activate && !kvm_x86_ops.apicv_check_inhibit(vcpu);

Might as well use Use static_call().  This would also be a candidate for
DEFINE_STATIC_CALL_RET0, though that's overkill if this is the only call site.

> +
>  	if (vcpu->arch.apicv_active == activate)
>  		goto out;
>  
> @@ -9935,7 +9943,10 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
>  		 * per-VM state, and responsing vCPUs must wait for the update
>  		 * to complete before servicing KVM_REQ_APICV_UPDATE.
>  		 */
> -		WARN_ON_ONCE(kvm_apicv_activated(vcpu->kvm) != kvm_vcpu_apicv_active(vcpu));
> +		if (!is_guest_mode(vcpu))
> +			WARN_ON_ONCE(kvm_apicv_activated(vcpu->kvm) != kvm_vcpu_apicv_active(vcpu));
> +		else
> +			WARN_ON(kvm_vcpu_apicv_active(vcpu));

Won't this fire on VMX?

>  
>  		exit_fastpath = static_call(kvm_x86_run)(vcpu);
>  		if (likely(exit_fastpath != EXIT_FASTPATH_REENTER_GUEST))
> -- 
> 2.26.3
>