Re: [PATCH v3 2/5] KVM: nVMX: Rework event injection and recovery

[Gleb Natapov <gleb@redhat.com>]

On Sun, Mar 24, 2013 at 07:44:45PM +0100, Jan Kiszka wrote:
> From: Jan Kiszka <jan.kiszka@siemens.com>
> 
> The basic idea is to always transfer the pending event injection on
> vmexit into the architectural state of the VCPU and then drop it from
> there if it turns out that we left L2 to enter L1, i.e. if we enter
> prepare_vmcs12.
> 
> vmcs12_save_pending_events takes care to transfer pending L0 events into
> the queue of L1. That is mandatory as L1 may decide to switch the guest
> state completely, invalidating or preserving the pending events for
> later injection (including on a different node, once we support
> migration).
> 
> This concept is based on the rule that a pending vmlaunch/vmresume is
> not canceled. Otherwise, we would risk to lose injected events or leak
> them into the wrong queues. Encode this rule via a WARN_ON_ONCE at the
> entry of nested_vmx_vmexit.
> 
> Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
> ---
>  arch/x86/kvm/vmx.c |   90 +++++++++++++++++++++++++++++++++------------------
>  1 files changed, 58 insertions(+), 32 deletions(-)
> 
> diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
> index 8827b3b..9d9ff74 100644
> --- a/arch/x86/kvm/vmx.c
> +++ b/arch/x86/kvm/vmx.c
> @@ -6493,8 +6493,6 @@ static void __vmx_complete_interrupts(struct kvm_vcpu *vcpu,
>  
>  static void vmx_complete_interrupts(struct vcpu_vmx *vmx)
>  {
> -	if (is_guest_mode(&vmx->vcpu))
> -		return;
>  	__vmx_complete_interrupts(&vmx->vcpu, vmx->idt_vectoring_info,
>  				  VM_EXIT_INSTRUCTION_LEN,
>  				  IDT_VECTORING_ERROR_CODE);
> @@ -6502,8 +6500,6 @@ static void vmx_complete_interrupts(struct vcpu_vmx *vmx)
>  
>  static void vmx_cancel_injection(struct kvm_vcpu *vcpu)
>  {
> -	if (is_guest_mode(vcpu))
> -		return;
>  	__vmx_complete_interrupts(vcpu,
>  				  vmcs_read32(VM_ENTRY_INTR_INFO_FIELD),
>  				  VM_ENTRY_INSTRUCTION_LEN,
> @@ -6535,21 +6531,6 @@ 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();
> @@ -6708,17 +6689,6 @@ 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);
> @@ -7325,6 +7295,48 @@ vmcs12_guest_cr4(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
>  			vcpu->arch.cr4_guest_owned_bits));
>  }
>  
> +static void vmcs12_save_pending_event(struct kvm_vcpu *vcpu,
> +				       struct vmcs12 *vmcs12)
> +{
> +	u32 idt_vectoring;
> +	unsigned int nr;
> +
> +	if (vcpu->arch.exception.pending) {
> +		nr = vcpu->arch.exception.nr;
> +		idt_vectoring = nr | VECTORING_INFO_VALID_MASK;
> +
> +		if (kvm_exception_is_soft(nr)) {
> +			vmcs12->vm_exit_instruction_len =
> +				vcpu->arch.event_exit_inst_len;
> +			idt_vectoring |= INTR_TYPE_SOFT_EXCEPTION;
> +		} else
> +			idt_vectoring |= INTR_TYPE_HARD_EXCEPTION;
> +
> +		if (vcpu->arch.exception.has_error_code) {
> +			idt_vectoring |= VECTORING_INFO_DELIVER_CODE_MASK;
> +			vmcs12->idt_vectoring_error_code =
> +				vcpu->arch.exception.error_code;
> +		}
> +
> +		vmcs12->idt_vectoring_info_field = idt_vectoring;
> +	} else if (vcpu->arch.nmi_pending) {
> +		vmcs12->idt_vectoring_info_field =
> +			INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK | NMI_VECTOR;
> +	} else if (vcpu->arch.interrupt.pending) {
> +		nr = vcpu->arch.interrupt.nr;
> +		idt_vectoring = nr | VECTORING_INFO_VALID_MASK;
> +
> +		if (vcpu->arch.interrupt.soft) {
> +			idt_vectoring |= INTR_TYPE_SOFT_INTR;
> +			vmcs12->vm_entry_instruction_len =
> +				vcpu->arch.event_exit_inst_len;
> +		} else
> +			idt_vectoring |= INTR_TYPE_EXT_INTR;
> +
> +		vmcs12->idt_vectoring_info_field = idt_vectoring;
> +	}
> +}
> +
>  /*
>   * prepare_vmcs12 is part of what we need to do when the nested L2 guest exits
>   * and we want to prepare to run its L1 parent. L1 keeps a vmcs for L2 (vmcs12),
> @@ -7416,9 +7428,20 @@ static 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))
> -		vmcs12->vm_entry_intr_info_field &= ~INTR_INFO_VALID_MASK;
Why have you dropped this? Where is it cleaned now?

> +		/*
> +		 * Transfer the event that L0 or L1 may wanted to inject into
> +		 * L2 to IDT_VECTORING_INFO_FIELD.
> +		 */
> +		vmcs12_save_pending_event(vcpu, vmcs12);
> +
> +	/*
> +	 * Drop what we picked up for L2 via vmx_complete_interrupts. It is
> +	 * preserved above and would only end up incorrectly in L1.
> +	 */
> +	vcpu->arch.nmi_injected = false;
> +	kvm_clear_exception_queue(vcpu);
> +	kvm_clear_interrupt_queue(vcpu);
>  }
>  
>  /*
> @@ -7518,6 +7541,9 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu)
>  	int cpu;
>  	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
>  
> +	/* trying to cancel vmlaunch/vmresume is a bug */
> +	WARN_ON_ONCE(vmx->nested.nested_run_pending);
> +
>  	leave_guest_mode(vcpu);
>  	prepare_vmcs12(vcpu, vmcs12);
>  
> -- 
> 1.7.3.4

--
			Gleb.