svm_copy_lbrs() always marks VMCB_LBR dirty in the destination VMCB.
However, nested_svm_vmexit() uses it to copy LBRs to vmcb12, and
clearing clean bits in vmcb12 is not architecturally defined.

Move vmcb_mark_dirty() to callers and drop it for vmcb12.

This also facilitates incoming refactoring that does not pass the entire
VMCB to svm_copy_lbrs().

Fixes: d20c796ca370 ("KVM: x86: nSVM: implement nested LBR virtualization")
Cc: stable@vger.kernel.org
Signed-off-by: Yosry Ahmed <yosry.ahmed@linux.dev>
---
 arch/x86/kvm/svm/nested.c | 7 +++++--
 arch/x86/kvm/svm/svm.c    | 2 --
 2 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index de90b104a0dd..a31f3be1e16e 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -714,6 +714,7 @@ static void nested_vmcb02_prepare_save(struct vcpu_svm *svm, struct vmcb *vmcb12
 	} else {
 		svm_copy_lbrs(vmcb02, vmcb01);
 	}
+	vmcb_mark_dirty(vmcb02, VMCB_LBR);
 	svm_update_lbrv(&svm->vcpu);
 }
 
@@ -1232,10 +1233,12 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
 		kvm_make_request(KVM_REQ_EVENT, &svm->vcpu);
 
 	if (unlikely(guest_cpu_cap_has(vcpu, X86_FEATURE_LBRV) &&
-		     (svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK)))
+		     (svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK))) {
 		svm_copy_lbrs(vmcb12, vmcb02);
-	else
+	} else {
 		svm_copy_lbrs(vmcb01, vmcb02);
+		vmcb_mark_dirty(vmcb01, VMCB_LBR);
+	}
 
 	svm_update_lbrv(vcpu);
 
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 5f0136dbdde6..98cbd7c7beed 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -848,8 +848,6 @@ void svm_copy_lbrs(struct vmcb *to_vmcb, struct vmcb *from_vmcb)
 	to_vmcb->save.br_to		= from_vmcb->save.br_to;
 	to_vmcb->save.last_excp_from	= from_vmcb->save.last_excp_from;
 	to_vmcb->save.last_excp_to	= from_vmcb->save.last_excp_to;
-
-	vmcb_mark_dirty(to_vmcb, VMCB_LBR);
 }
 
 static void __svm_enable_lbrv(struct kvm_vcpu *vcpu)
-- 
2.53.0.rc2.204.g2597b5adb4-goog