Re: [PATCH v2 1/3] KVM: nSVM: restore the L1 host state prior to resuming a nested guest on SMM exit

[Sean Christopherson <seanjc@google.com>]

On Mon, Aug 23, 2021, Maxim Levitsky wrote:
> If the guest is entered prior to restoring the host save area,
> the guest entry code might see incorrect L1 state (e.g paging state).
> 
> Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
> ---
>  arch/x86/kvm/svm/svm.c | 23 +++++++++++++----------
>  1 file changed, 13 insertions(+), 10 deletions(-)
> 
> diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
> index 1a70e11f0487..ea7a4dacd42f 100644
> --- a/arch/x86/kvm/svm/svm.c
> +++ b/arch/x86/kvm/svm/svm.c
> @@ -4347,27 +4347,30 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
>  					 gpa_to_gfn(vmcb12_gpa), &map) == -EINVAL)
>  				return 1;
>  
> -			if (svm_allocate_nested(svm))
> +			if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr),
> +					 &map_save) == -EINVAL)
>  				return 1;

Returning here will neglect to unmap "map".

>  
> -			vmcb12 = map.hva;
> -
> -			nested_load_control_from_vmcb12(svm, &vmcb12->control);
> -
> -			ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12);
> -			kvm_vcpu_unmap(vcpu, &map, true);
> +			if (svm_allocate_nested(svm))
> +				return 1;

Ditto here for both "map" and "map_save", though it looks like there's a
pre-existing bug if svm_allocate_nested() fails.  If you add a prep cleanup patch
to remove the statement nesting (between the bug fix and this patch), it will make
handling this a lot easier, e.g.

static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
{
	struct vcpu_svm *svm = to_svm(vcpu);
	struct kvm_host_map map, map_save;
	u64 saved_efer, vmcb12_gpa;
	struct vmcb *vmcb12;
	int ret;

	if (!guest_cpuid_has(vcpu, X86_FEATURE_LM))
		return 0;

	/* Non-zero if SMI arrived while vCPU was in guest mode. */
	if (!GET_SMSTATE(u64, smstate, 0x7ed8))
		return 0;

	if (!guest_cpuid_has(vcpu, X86_FEATURE_SVM))
		return 1;

	saved_efer = GET_SMSTATE(u64, smstate, 0x7ed0);
	if (!(saved_efer & EFER_SVME))
		return 1;

	vmcb12_gpa = GET_SMSTATE(u64, smstate, 0x7ee0);
	if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmcb12_gpa), &map) == -EINVAL)
		return 1;

	ret = 1;
	if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr), &map_save) == -EINVAL)
		goto unmap_map;

	if (svm_allocate_nested(svm))
		goto unmap_save;

	/*
	 * Restore L1 host state from L1 HSAVE area as VMCB01 was
	 * used during SMM (see svm_enter_smm())
	 */

	svm_copy_vmrun_state(&svm->vmcb01.ptr->save,
				map_save.hva + 0x400);

	/*
	 * Restore L2 state
	 */

	vmcb12 = map.hva;
	nested_load_control_from_vmcb12(svm, &vmcb12->control);
	ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12);

unmap_save;
	kvm_vcpu_unmap(vcpu, &map_save, true);
unmap_map:
	kvm_vcpu_unmap(vcpu, &map, true);
	return 1;
}