Re: [PATCH] KVM: nVMX: Rework event injection and recovery

[Gleb Natapov <gleb@redhat.com>]

On Wed, Feb 20, 2013 at 02:01:47PM +0100, Jan Kiszka wrote:
> This aligns VMX more with SVM regarding event injection and recovery for
> nested guests. The changes allow to inject interrupts directly from L0
> to L2.
> 
> One difference to SVM is that we always transfer the pending event
> injection into the architectural state of the VCPU and then drop it from
> there if it turns out that we left L2 to enter L1.
> 
> VMX and SVM are now identical in how they recover event injections from
> unperformed vmlaunch/vmresume: We detect that VM_ENTRY_INTR_INFO_FIELD
> still contains a valid event and, if yes, transfer the content into L1's
> idt_vectoring_info_field.
> 
> To avoid that we incorrectly leak an event into the architectural VCPU
> state that L1 wants to inject, we skip cancellation on nested run.
> 
> Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
> ---
> 
> Survived moderate testing here and (currently) makes sense to me, but
> please review very carefully. I wouldn't be surprised if I'm still
> missing some subtle corner case.
> 
>  arch/x86/kvm/vmx.c |   57 +++++++++++++++++++++++----------------------------
>  1 files changed, 26 insertions(+), 31 deletions(-)
> 
> diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
> index dd3a8a0..7d2fbd2 100644
> --- a/arch/x86/kvm/vmx.c
> +++ b/arch/x86/kvm/vmx.c
> @@ -6489,8 +6489,6 @@ static void __vmx_complete_interrupts(struct vcpu_vmx *vmx,
>  
>  static void vmx_complete_interrupts(struct vcpu_vmx *vmx)
>  {
> -	if (is_guest_mode(&vmx->vcpu))
> -		return;
>  	__vmx_complete_interrupts(vmx, vmx->idt_vectoring_info,
>  				  VM_EXIT_INSTRUCTION_LEN,
>  				  IDT_VECTORING_ERROR_CODE);
> @@ -6498,7 +6496,7 @@ static void vmx_complete_interrupts(struct vcpu_vmx *vmx)
>  
>  static void vmx_cancel_injection(struct kvm_vcpu *vcpu)
>  {
> -	if (is_guest_mode(vcpu))
> +	if (to_vmx(vcpu)->nested.nested_run_pending)
>  		return;
Why is this needed here?

>  	__vmx_complete_interrupts(to_vmx(vcpu),
>  				  vmcs_read32(VM_ENTRY_INTR_INFO_FIELD),
> @@ -6531,21 +6529,6 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
>  	struct vcpu_vmx *vmx = to_vmx(vcpu);
>  	unsigned long debugctlmsr;
>  
> -	if (is_guest_mode(vcpu) && !vmx->nested.nested_run_pending) {
> -		struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
> -		if (vmcs12->idt_vectoring_info_field &
> -				VECTORING_INFO_VALID_MASK) {
> -			vmcs_write32(VM_ENTRY_INTR_INFO_FIELD,
> -				vmcs12->idt_vectoring_info_field);
> -			vmcs_write32(VM_ENTRY_INSTRUCTION_LEN,
> -				vmcs12->vm_exit_instruction_len);
> -			if (vmcs12->idt_vectoring_info_field &
> -					VECTORING_INFO_DELIVER_CODE_MASK)
> -				vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE,
> -					vmcs12->idt_vectoring_error_code);
> -		}
> -	}
> -
>  	/* Record the guest's net vcpu time for enforced NMI injections. */
>  	if (unlikely(!cpu_has_virtual_nmis() && vmx->soft_vnmi_blocked))
>  		vmx->entry_time = ktime_get();
> @@ -6704,17 +6687,6 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
>  
>  	vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD);
>  
> -	if (is_guest_mode(vcpu)) {
> -		struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
> -		vmcs12->idt_vectoring_info_field = vmx->idt_vectoring_info;
> -		if (vmx->idt_vectoring_info & VECTORING_INFO_VALID_MASK) {
> -			vmcs12->idt_vectoring_error_code =
> -				vmcs_read32(IDT_VECTORING_ERROR_CODE);
> -			vmcs12->vm_exit_instruction_len =
> -				vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
> -		}
> -	}
> -
>  	vmx->loaded_vmcs->launched = 1;
>  
>  	vmx->exit_reason = vmcs_read32(VM_EXIT_REASON);
> @@ -7403,9 +7375,32 @@ void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
>  	vmcs12->vm_exit_instruction_len = vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
>  	vmcs12->vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
>  
> -	/* clear vm-entry fields which are to be cleared on exit */
> -	if (!(vmcs12->vm_exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY))
> +	/* drop what we picked up for L0 via vmx_complete_interrupts */
> +	vcpu->arch.nmi_injected = false;
> +	kvm_clear_exception_queue(vcpu);
> +	kvm_clear_interrupt_queue(vcpu);
> +
> +	if (!(vmcs12->vm_exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY) &&
> +	    vmcs12->vm_entry_intr_info_field & INTR_INFO_VALID_MASK) {
> +		/*
> +		 * Preserve the event that was supposed to be injected
> +		 * by emulating it would have been returned in
> +		 * IDT_VECTORING_INFO_FIELD.
> +		 */
> +		if (vmcs_read32(VM_ENTRY_INTR_INFO_FIELD) &
> +		    INTR_INFO_VALID_MASK) {
> +			vmcs12->idt_vectoring_info_field =
> +				vmcs12->vm_entry_intr_info_field;
> +			vmcs12->idt_vectoring_error_code =
> +				vmcs12->vm_entry_exception_error_code;
> +			vmcs12->vm_exit_instruction_len =
> +				vmcs12->vm_entry_instruction_len;
> +			vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0);
> +		}
> +
> +		/* clear vm-entry fields which are to be cleared on exit */
>  		vmcs12->vm_entry_intr_info_field &= ~INTR_INFO_VALID_MASK;
> +	}
>  }
>  
>  /*
> -- 
> 1.7.3.4

--
			Gleb.