Re: [PATCH 19/28] nVMX: Exiting from L2 to L1

[Avi Kivity <avi@redhat.com>]

On 12/08/2010 07:09 PM, Nadav Har'El wrote:
> This patch implements nested_vmx_vmexit(), called when the nested L2 guest
> exits and we want to run its L1 parent and let it handle this exit.
>
> Note that this will not necessarily be called on every L2 exit. L0 may decide
> to handle a particular exit on its own, without L1's involvement; In that
> case, L0 will handle the exit, and resume running L2, without running L1 and
> without calling nested_vmx_vmexit(). The logic for deciding whether to handle
> a particular exit in L1 or in L0, i.e., whether to call nested_vmx_vmexit(),
> will appear in the next patch.
>
>
> +void prepare_vmcs12(struct kvm_vcpu *vcpu)
> +{
> +	struct vmcs_fields *vmcs12 = get_vmcs12_fields(vcpu);
> +
> +	/* update guest state fields: */
> +	vmcs12->guest_cr0 = vmcs12_guest_cr0(vcpu, vmcs12);
> +	vmcs12->guest_cr4 = vmcs12_guest_cr4(vcpu, vmcs12);
> +
> +	vmcs12->guest_dr7 = vmcs_readl(GUEST_DR7);
> +	vmcs12->guest_rsp = vmcs_readl(GUEST_RSP);
> +	vmcs12->guest_rip = vmcs_readl(GUEST_RIP);
> +	vmcs12->guest_rflags = vmcs_readl(GUEST_RFLAGS);

kvm_register_read() etc.

> +
> +static int nested_vmx_vmexit(struct kvm_vcpu *vcpu, bool is_interrupt)
> +{
> +	struct vcpu_vmx *vmx = to_vmx(vcpu);
> +	int efer_offset;
> +	struct vmcs_fields *vmcs01 = vmx->nested.vmcs01_fields;
> +
> +	if (!is_guest_mode(vcpu)) {
> +		printk(KERN_INFO "WARNING: %s called but not in nested mode\n",
> +		       __func__);
> +		return 0;
> +	}
> +
> +	sync_cached_regs_to_vmcs(vcpu);
> +
> +	prepare_vmcs12(vcpu);
> +
> +	if (is_interrupt)
> +		get_vmcs12_fields(vcpu)->vm_exit_reason =
> +			EXIT_REASON_EXTERNAL_INTERRUPT;
> +
> +	vmx->nested.current_vmcs12->launched = vmx->launched;
> +	vmx->nested.current_vmcs12->cpu = vcpu->cpu;
> +
> +	vmx->vmcs = vmx->nested.vmcs01;
> +	vcpu->cpu = vmx->nested.l1_state.cpu;
> +	vmx->launched = vmx->nested.l1_state.launched;
> +
> +	leave_guest_mode(vcpu);
> +
> +	vmx_vcpu_load(vcpu, get_cpu());
> +	put_cpu();
> +
> +	vcpu->arch.efer = vmx->nested.l1_state.efer;
> +	if ((vcpu->arch.efer&  EFER_LMA)&&
> +	    !(vcpu->arch.efer&  EFER_SCE))
> +		vcpu->arch.efer |= EFER_SCE;

set_efer() in x86.c for the side effects.

> +
> +	efer_offset = __find_msr_index(vmx, MSR_EFER);
> +	if (update_transition_efer(vmx, efer_offset))
> +		wrmsrl(MSR_EFER, vmx->guest_msrs[efer_offset].data);

Including this.

> +
> +	/*
> +	 * L2 perhaps switched to real mode and set vmx->rmode, but we're back
> +	 * in L1 and as it is running VMX, it can't be in real mode.
> +	 */
> +	vmx->rmode.vm86_active = 0;

L2 cannot be in real mode since vmx does not support it (except for 
unrestricted guest, in which case rmode.vm86_active would be clear).

> +
> +	/*
> +	 * If L1 set the HOST_* fields in the VMCS, when exiting from L2 to L1
> +	 * we need to return those, not L1's old values.
> +	 */
> +	vmcs_writel(GUEST_RIP, get_vmcs12_fields(vcpu)->host_rip);
> +	vmcs_writel(GUEST_RSP, get_vmcs12_fields(vcpu)->host_rsp);

kvm_register_write() etc.

> +	vmcs01->cr0_read_shadow = get_vmcs12_fields(vcpu)->host_cr0;
> +
> +	/*
> +	 * We're running a regular L1 guest again, so we do the regular KVM
> +	 * thing: run vmx_set_cr0 with the cr0 bits the guest thinks it has.
> +	 * vmx_set_cr0 might use slightly different bits on the new guest_cr0
> +	 * it sets, e.g., add TS when !fpu_active.
> +	 * Note that vmx_set_cr0 refers to rmode and efer set above.
> +	 */
> +	vmx_set_cr0(vcpu, guest_readable_cr0(vmcs01));

kvm_set_cr0() takes care of some extra stuff.  Why guest_readable_cr0?  
want vmcs12->host_cr0.

> +	/*
> +	 * If we did fpu_activate()/fpu_deactive() during l2's run, we need to
> +	 * apply the same changes to l1's vmcs. We just set cr0 correctly, but
> +	 * now we need to also update cr0_guest_host_mask and exception_bitmap.
> +	 */
> +	vmcs_write32(EXCEPTION_BITMAP,
> +		(vmcs01->exception_bitmap&  ~(1u<<NM_VECTOR)) |
> +			(vcpu->fpu_active ? 0 : (1u<<NM_VECTOR)));
> +	vcpu->arch.cr0_guest_owned_bits = (vcpu->fpu_active ? X86_CR0_TS : 0);
> +	vmcs_writel(CR0_GUEST_HOST_MASK, ~vcpu->arch.cr0_guest_owned_bits);

Should be a side effect of kvm_set_cr0().

> +
> +	vmx_set_cr4(vcpu, guest_readable_cr4(vmcs01));
> +	vcpu->arch.cr4_guest_owned_bits = ~vmcs01->cr4_guest_host_mask;

kvm_set_cr4(vmcs12->host_cr4)

> +
> +	if (enable_ept) {
> +		/* shadow page tables on EPT: */
> +		set_cr3_and_pdptrs(vcpu, get_vmcs12_fields(vcpu)->host_cr3);
> +	} else {
> +		/* shadow page tables on shadow page tables: */
> +		kvm_set_cr3(vcpu, vmx->nested.l1_arch_cr3);
> +		kvm_mmu_reset_context(vcpu);
> +		kvm_mmu_load(vcpu);
> +	}

kvm_set_cr3() should suffice in both cases.  
kvm_mmu_reset_context()/kvm_mmu_load() is probably unneeded.

> +
> +	kvm_register_write(vcpu, VCPU_REGS_RSP, vmcs01->guest_rsp);
> +	kvm_register_write(vcpu, VCPU_REGS_RIP, vmcs01->guest_rip);

vmcs12->host_rip

> +
> +	if (unlikely(vmx->fail)) {
> +		/*
> +		 * When L1 launches L2 and then we (L0) fail to launch L2,
> +		 * we nested_vmx_vmexit back to L1, but now should let it know
> +		 * that the VMLAUNCH failed - with the same error that we
> +		 * got when launching L2.
> +		 */
> +		vmx->fail = 0;
> +		nested_vmx_failValid(vcpu, vmcs_read32(VM_INSTRUCTION_ERROR));
> +	} else
> +		nested_vmx_succeed(vcpu);
> +
> +	return 0;
> +}
> +
>   static struct kvm_x86_ops vmx_x86_ops = {
>   	.cpu_has_kvm_support = cpu_has_kvm_support,
>   	.disabled_by_bios = vmx_disabled_by_bios,


-- 
error compiling committee.c: too many arguments to function