Copy the LBRv2 state on nested VMRUN and #VMEXIT just like the legacy
LBR state. If L1 enables V_LBR for L2, L2 has its own LBRv2 state in
vmcb12. If L1 does not enable V_LBR, L2 uses the LBRv2 state of L1.

Add svm_copy_lbrs_v2() macro to copy this state. Keep it separate from
svm_copy_lbrs(), because the LBR stack is 256 bytes and KVM copies it
only when LBRv2 is supported.

Signed-off-by: Shivansh Dhiman <shivansh.dhiman@amd.com>
---

Changes in v2:
* New patch.

---
 arch/x86/kvm/svm/nested.c | 28 +++++++++++++++++++++++++++-
 arch/x86/kvm/svm/svm.h    | 18 ++++++++++++++++++
 2 files changed, 45 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index af0ef678433d..b356a091e320 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -608,6 +608,9 @@ static void __nested_copy_vmcb_save_to_cache(struct vmcb_save_area_cached *to,
 	to->g_pat = from->g_pat;
 
 	svm_copy_lbrs(to, from);
+
+	if (kvm_cpu_cap_has(X86_FEATURE_AMD_LBR_V2))
+		svm_copy_lbrs_v2(to, from);
 }
 
 void nested_copy_vmcb_save_to_cache(struct vcpu_svm *svm,
@@ -819,8 +822,17 @@ static void nested_vmcb02_prepare_save(struct vcpu_svm *svm)
 		 */
 		svm_copy_lbrs(&vmcb02->save, save);
 		vmcb02->save.dbgctl &= svm_get_supported_debugctl(vcpu);
+
+		if (guest_cpu_cap_has(vcpu, X86_FEATURE_AMD_LBR_V2)) {
+			svm_copy_lbrs_v2(&vmcb02->save, save);
+			vmcb02->save.dbg_extn_cfg &= ~DBG_EXTN_CFG_RESERVED_BITS;
+			vmcb02->save.lbr_select &= ~LBR_SELECT_RESERVED_BITS;
+		}
 	} else {
 		svm_copy_lbrs(&vmcb02->save, &vmcb01->save);
+
+		if (guest_cpu_cap_has(vcpu, X86_FEATURE_AMD_LBR_V2))
+			svm_copy_lbrs_v2(&vmcb02->save, &vmcb01->save);
 	}
 	vmcb_mark_dirty(vmcb02, VMCB_LBR);
 	svm_update_lbrv(&svm->vcpu);
@@ -1236,6 +1248,12 @@ void svm_copy_vmrun_state(struct kvm_vcpu *vcpu, struct vmcb_save_area *to_save,
 		svm_copy_lbrs(to_save, from_save);
 		to_save->dbgctl &= svm_get_supported_debugctl(vcpu);
 	}
+
+	if (kvm_cpu_cap_has(X86_FEATURE_AMD_LBR_V2)) {
+		svm_copy_lbrs_v2(to_save, from_save);
+		to_save->dbg_extn_cfg &= ~DBG_EXTN_CFG_RESERVED_BITS;
+		to_save->lbr_select &= ~LBR_SELECT_RESERVED_BITS;
+	}
 }
 
 void svm_copy_vmloadsave_state(struct vmcb *to_vmcb, struct vmcb *from_vmcb)
@@ -1305,9 +1323,13 @@ static int nested_svm_vmexit_update_vmcb12(struct kvm_vcpu *vcpu)
 	if (guest_cpu_cap_has(vcpu, X86_FEATURE_NRIPS))
 		vmcb12->control.next_rip  = vmcb02->control.next_rip;
 
-	if (svm->nested.ctl.misc_ctl2 & SVM_MISC2_ENABLE_V_LBR)
+	if (svm->nested.ctl.misc_ctl2 & SVM_MISC2_ENABLE_V_LBR) {
 		svm_copy_lbrs(&vmcb12->save, &vmcb02->save);
 
+		if (guest_cpu_cap_has(vcpu, X86_FEATURE_AMD_LBR_V2))
+			svm_copy_lbrs_v2(&vmcb12->save, &vmcb02->save);
+	}
+
 	vmcb12->control.event_inj	  = 0;
 	vmcb12->control.event_inj_err	  = 0;
 	vmcb12->control.int_ctl           = svm->nested.ctl.int_ctl;
@@ -1384,6 +1406,10 @@ void nested_svm_vmexit(struct vcpu_svm *svm)
 
 	if (!(svm->nested.ctl.misc_ctl2 & SVM_MISC2_ENABLE_V_LBR)) {
 		svm_copy_lbrs(&vmcb01->save, &vmcb02->save);
+
+		if (guest_cpu_cap_has(vcpu, X86_FEATURE_AMD_LBR_V2))
+			svm_copy_lbrs_v2(&vmcb01->save, &vmcb02->save);
+
 		vmcb_mark_dirty(vmcb01, VMCB_LBR);
 	}
 
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 72f19053fb4c..01be2fc05d70 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -176,6 +176,12 @@ struct vmcb_save_area_cached {
 	u64 br_to;
 	u64 last_excp_from;
 	u64 last_excp_to;
+	u64 dbg_extn_cfg;
+	struct {
+		u64 lbr_stack_from;
+		u64 lbr_stack_to;
+	} lbr[SVM_LBR_V2_STACK_SIZE];
+	u64 lbr_select;
 };
 
 struct vmcb_ctrl_area_cached {
@@ -820,6 +826,18 @@ do {								\
 	(to)->last_excp_to	= (from)->last_excp_to;		\
 } while (0)
 
+/*
+ * Kept separate from svm_copy_lbrs() as the branch record stack is 256 bytes,
+ * i.e. is only worth copying when LBR v2 is exposed to the guest.
+ */
+#define svm_copy_lbrs_v2(to, from)					\
+do {									\
+	BUILD_BUG_ON(sizeof((to)->lbr) != sizeof((from)->lbr));		\
+	(to)->dbg_extn_cfg	= (from)->dbg_extn_cfg;			\
+	(to)->lbr_select	= (from)->lbr_select;			\
+	memcpy((to)->lbr, (from)->lbr, sizeof((to)->lbr));		\
+} while (0)
+
 void svm_vcpu_free_msrpm(void *msrpm);
 void svm_enable_lbrv(struct kvm_vcpu *vcpu);
 void svm_update_lbrv(struct kvm_vcpu *vcpu);
-- 
2.43.0