Re: [PATCH 3/4] KVM: x86: inject nested page faults on emulated instructions

[Gleb Natapov <gleb@kernel.org>]

On Thu, Sep 04, 2014 at 07:44:51PM +0200, Paolo Bonzini wrote:
> Il 04/09/2014 17:05, Gleb Natapov ha scritto:
> >> > 
> >> > If you do that, KVM gets down to the "if (writeback)" and writes the 
> >> > ctxt->eip from L2 into the L1 EIP.
> > Heh, that's a bummer. We should not write back if an instruction caused a vmexit.
> > 
> 
> You're right, that works.
Looks good!

Reviewed-by: Gleb Natapov <gleb@kernel.org>

> 
> Paolo
> 
> -------------- 8< -------------
> Subject: [PATCH] KVM: x86: skip writeback on injection of nested exception
> 
> If a nested page fault happens during emulation, we will inject a vmexit,
> not a page fault.  However because writeback happens after the injection,
> we will write ctxt->eip from L2 into the L1 EIP.  We do not write back
> if an instruction caused an interception vmexit---do the same for page
> faults.
> 
> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
> ---
>  arch/x86/include/asm/kvm_host.h |  1 -
>  arch/x86/kvm/x86.c              | 15 ++++++++++-----
>  2 files changed, 10 insertions(+), 6 deletions(-)
> 
> diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
> index 08cc299..c989651 100644
> --- a/arch/x86/include/asm/kvm_host.h
> +++ b/arch/x86/include/asm/kvm_host.h
> @@ -893,7 +893,6 @@ void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault);
>  int kvm_read_guest_page_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
>  			    gfn_t gfn, void *data, int offset, int len,
>  			    u32 access);
> -void kvm_propagate_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault);
>  bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl);
>  
>  static inline int __kvm_irq_line_state(unsigned long *irq_state,
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index e4ed85e..3541946 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -408,12 +408,14 @@ void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault)
>  }
>  EXPORT_SYMBOL_GPL(kvm_inject_page_fault);
>  
> -void kvm_propagate_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault)
> +static bool kvm_propagate_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault)
>  {
>  	if (mmu_is_nested(vcpu) && !fault->nested_page_fault)
>  		vcpu->arch.nested_mmu.inject_page_fault(vcpu, fault);
>  	else
>  		vcpu->arch.mmu.inject_page_fault(vcpu, fault);
> +
> +	return fault->nested_page_fault;
>  }
>  
>  void kvm_inject_nmi(struct kvm_vcpu *vcpu)
> @@ -4929,16 +4931,18 @@ static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask)
>  	}
>  }
>  
> -static void inject_emulated_exception(struct kvm_vcpu *vcpu)
> +static bool inject_emulated_exception(struct kvm_vcpu *vcpu)
>  {
>  	struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt;
>  	if (ctxt->exception.vector == PF_VECTOR)
> -		kvm_propagate_fault(vcpu, &ctxt->exception);
> -	else if (ctxt->exception.error_code_valid)
> +		return kvm_propagate_fault(vcpu, &ctxt->exception);
> +
> +	if (ctxt->exception.error_code_valid)
>  		kvm_queue_exception_e(vcpu, ctxt->exception.vector,
>  				      ctxt->exception.error_code);
>  	else
>  		kvm_queue_exception(vcpu, ctxt->exception.vector);
> +	return false;
>  }
>  
>  static void init_emulate_ctxt(struct kvm_vcpu *vcpu)
> @@ -5300,8 +5304,9 @@ restart:
>  	}
>  
>  	if (ctxt->have_exception) {
> -		inject_emulated_exception(vcpu);
>  		r = EMULATE_DONE;
> +		if (inject_emulated_exception(vcpu))
> +			return r;
>  	} else if (vcpu->arch.pio.count) {
>  		if (!vcpu->arch.pio.in) {
>  			/* FIXME: return into emulator if single-stepping.  */
> -- 
> 1.9.3
> 
> 

--
			Gleb.