diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index dd03d5e01a94..32564b017ba0 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -335,6 +335,7 @@ static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
 static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {}
 
 static inline void kvm_arm_init_debug(void) {}
+static inline void kvm_arm_vcpu_init_debug(struct kvm_vcpu *vcpu) {}
 static inline void kvm_arm_setup_debug(struct kvm_vcpu *vcpu) {}
 static inline void kvm_arm_clear_debug(struct kvm_vcpu *vcpu) {}
 static inline void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu) {}
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index dfa6dc4575be..697702a1a1ff 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -552,6 +552,7 @@ static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
 static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {}
 
 void kvm_arm_init_debug(void);
+void kvm_arm_vcpu_init_debug(struct kvm_vcpu *vcpu);
 void kvm_arm_setup_debug(struct kvm_vcpu *vcpu);
 void kvm_arm_clear_debug(struct kvm_vcpu *vcpu);
 void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu);
diff --git a/arch/arm64/kvm/debug.c b/arch/arm64/kvm/debug.c
index dbc890511631..2484b2cca74b 100644
--- a/arch/arm64/kvm/debug.c
+++ b/arch/arm64/kvm/debug.c
@@ -68,6 +68,64 @@ void kvm_arm_init_debug(void)
 	__this_cpu_write(mdcr_el2, kvm_call_hyp_ret(__kvm_get_mdcr_el2));
 }
 
+/**
+ * kvm_arm_setup_mdcr_el2 - configure vcpu mdcr_el2 value
+ *
+ * @vcpu:	the vcpu pointer
+ *
+ * This ensures we will trap access to:
+ *  - Performance monitors (MDCR_EL2_TPM/MDCR_EL2_TPMCR)
+ *  - Debug ROM Address (MDCR_EL2_TDRA)
+ *  - OS related registers (MDCR_EL2_TDOSA)
+ *  - Statistical profiler (MDCR_EL2_TPMS/MDCR_EL2_E2PB)
+ *  - Self-hosted Trace Filter controls (MDCR_EL2_TTRF)
+ */
+static void kvm_arm_setup_mdcr_el2(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * This also clears MDCR_EL2_E2PB_MASK to disable guest access
+	 * to the profiling buffer.
+	 */
+	vcpu->arch.mdcr_el2 = __this_cpu_read(mdcr_el2) & MDCR_EL2_HPMN_MASK;
+	vcpu->arch.mdcr_el2 |= (MDCR_EL2_TPM |
+				MDCR_EL2_TPMS |
+				MDCR_EL2_TTRF |
+				MDCR_EL2_TPMCR |
+				MDCR_EL2_TDRA |
+				MDCR_EL2_TDOSA);
+
+	/* Is the VM being debugged by userspace? */
+	if (vcpu->guest_debug)
+		/* Route all software debug exceptions to EL2 */
+		vcpu->arch.mdcr_el2 |= MDCR_EL2_TDE;
+
+	/*
+	 * Trap debug register access when one of the following is true:
+	 *  - Userspace is using the hardware to debug the guest
+	 *  (KVM_GUESTDBG_USE_HW is set).
+	 *  - The guest is not using debug (KVM_ARM64_DEBUG_DIRTY is clear).
+	 */
+	if ((vcpu->guest_debug & KVM_GUESTDBG_USE_HW) ||
+	    !(vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY))
+		vcpu->arch.mdcr_el2 |= MDCR_EL2_TDA;
+
+	trace_kvm_arm_set_dreg32("MDCR_EL2", vcpu->arch.mdcr_el2);
+}
+
+/**
+ * kvm_arm_vcpu_init_debug - setup vcpu debug traps
+ *
+ * @vcpu:	the vcpu pointer
+ *
+ * Set vcpu initial mdcr_el2 value.
+ */
+void kvm_arm_vcpu_init_debug(struct kvm_vcpu *vcpu)
+{
+	preempt_disable();
+	kvm_arm_setup_mdcr_el2(vcpu);
+	preempt_enable();
+}
+
 /**
  * kvm_arm_reset_debug_ptr - reset the debug ptr to point to the vcpu state
  */
@@ -83,13 +141,7 @@ void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu)
  * @vcpu:	the vcpu pointer
  *
  * This is called before each entry into the hypervisor to setup any
- * debug related registers. Currently this just ensures we will trap
- * access to:
- *  - Performance monitors (MDCR_EL2_TPM/MDCR_EL2_TPMCR)
- *  - Debug ROM Address (MDCR_EL2_TDRA)
- *  - OS related registers (MDCR_EL2_TDOSA)
- *  - Statistical profiler (MDCR_EL2_TPMS/MDCR_EL2_E2PB)
- *  - Self-hosted Trace Filter controls (MDCR_EL2_TTRF)
+ * debug related registers.
  *
  * Additionally, KVM only traps guest accesses to the debug registers if
  * the guest is not actively using them (see the KVM_ARM64_DEBUG_DIRTY
@@ -101,28 +153,14 @@ void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu)
 
 void kvm_arm_setup_debug(struct kvm_vcpu *vcpu)
 {
-	bool trap_debug = !(vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY);
 	unsigned long mdscr, orig_mdcr_el2 = vcpu->arch.mdcr_el2;
 
 	trace_kvm_arm_setup_debug(vcpu, vcpu->guest_debug);
 
-	/*
-	 * This also clears MDCR_EL2_E2PB_MASK to disable guest access
-	 * to the profiling buffer.
-	 */
-	vcpu->arch.mdcr_el2 = __this_cpu_read(mdcr_el2) & MDCR_EL2_HPMN_MASK;
-	vcpu->arch.mdcr_el2 |= (MDCR_EL2_TPM |
-				MDCR_EL2_TPMS |
-				MDCR_EL2_TTRF |
-				MDCR_EL2_TPMCR |
-				MDCR_EL2_TDRA |
-				MDCR_EL2_TDOSA);
+	kvm_arm_setup_mdcr_el2(vcpu);
 
 	/* Is Guest debugging in effect? */
 	if (vcpu->guest_debug) {
-		/* Route all software debug exceptions to EL2 */
-		vcpu->arch.mdcr_el2 |= MDCR_EL2_TDE;
-
 		/* Save guest debug state */
 		save_guest_debug_regs(vcpu);
 
@@ -176,7 +214,6 @@ void kvm_arm_setup_debug(struct kvm_vcpu *vcpu)
 
 			vcpu->arch.debug_ptr = &vcpu->arch.external_debug_state;
 			vcpu->arch.flags |= KVM_ARM64_DEBUG_DIRTY;
-			trap_debug = true;
 
 			trace_kvm_arm_set_regset("BKPTS", get_num_brps(),
 						&vcpu->arch.debug_ptr->dbg_bcr[0],
@@ -191,10 +228,6 @@ void kvm_arm_setup_debug(struct kvm_vcpu *vcpu)
 	BUG_ON(!vcpu->guest_debug &&
 		vcpu->arch.debug_ptr != &vcpu->arch.vcpu_debug_state);
 
-	/* Trap debug register access */
-	if (trap_debug)
-		vcpu->arch.mdcr_el2 |= MDCR_EL2_TDA;
-
 	/* If KDE or MDE are set, perform a full save/restore cycle. */
 	if (vcpu_read_sys_reg(vcpu, MDSCR_EL1) & (DBG_MDSCR_KDE | DBG_MDSCR_MDE))
 		vcpu->arch.flags |= KVM_ARM64_DEBUG_DIRTY;
@@ -203,7 +236,6 @@ void kvm_arm_setup_debug(struct kvm_vcpu *vcpu)
 	if (has_vhe() && orig_mdcr_el2 != vcpu->arch.mdcr_el2)
 		write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2);
 
-	trace_kvm_arm_set_dreg32("MDCR_EL2", vcpu->arch.mdcr_el2);
 	trace_kvm_arm_set_dreg32("MDSCR_EL1", vcpu_read_sys_reg(vcpu, MDSCR_EL1));
 }
 
diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c
index 2e7d2b3f2907..4af85605730e 100644
--- a/virt/kvm/arm/arm.c
+++ b/virt/kvm/arm/arm.c
@@ -579,6 +579,8 @@ static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu)
 
 	vcpu->arch.has_run_once = true;
 
+	kvm_arm_vcpu_init_debug(vcpu);
+
 	if (likely(irqchip_in_kernel(kvm))) {
 		/*
 		 * Map the VGIC hardware resources before running a vcpu the