KVM: x86: move vm_destroy callback at end of kvm_arch_destroy_vm

TDX needs to free the TDR control structures last, after all paging structures
have been torn down; move the vm_destroy callback at a suitable place.
The new place is also okay for AMD; the main difference is that the
MMU has been torn down and, if anything, that is better done before
the SNP ASID is released.

Extracted from a patch by Yan Zhao.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 4b64ab350bcd4d122adbe9416523bec692e5fc4f..bd2b71d4e64f0876cfb616c35a231f10d325ca9d 100644 (file)
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -12880,7 +12880,6 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
        }
        kvm_unload_vcpu_mmus(kvm);
        kvm_destroy_vcpus(kvm);
-       kvm_x86_call(vm_destroy)(kvm);
        kvm_free_msr_filter(srcu_dereference_check(kvm->arch.msr_filter, &kvm->srcu, 1));
        kvm_pic_destroy(kvm);
        kvm_ioapic_destroy(kvm);
@@ -12890,6 +12889,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
        kvm_page_track_cleanup(kvm);
        kvm_xen_destroy_vm(kvm);
        kvm_hv_destroy_vm(kvm);
+       kvm_x86_call(vm_destroy)(kvm);
 }
 
 static void memslot_rmap_free(struct kvm_memory_slot *slot)