diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 7f4783525144..55eb8dec2a77 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -873,7 +873,7 @@ static int __guestcopy(struct kvm_vcpu *vcpu, u64 guestdest, void *from,
  * KVM_S390_STORE_STATUS_NOADDR: -> 0x1200 on 64 bit
  * KVM_S390_STORE_STATUS_PREFIXED: -> prefix
  */
-int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr)
+int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long addr)
 {
 	unsigned char archmode = 1;
 	int prefix;
@@ -891,15 +891,6 @@ int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr)
 	} else
 		prefix = 0;
 
-	/*
-	 * The guest FPRS and ACRS are in the host FPRS/ACRS due to the lazy
-	 * copying in vcpu load/put. Lets update our copies before we save
-	 * it into the save area
-	 */
-	save_fp_ctl(&vcpu->arch.guest_fpregs.fpc);
-	save_fp_regs(vcpu->arch.guest_fpregs.fprs);
-	save_access_regs(vcpu->run->s.regs.acrs);
-
 	if (__guestcopy(vcpu, addr + offsetof(struct save_area, fp_regs),
 			vcpu->arch.guest_fpregs.fprs, 128, prefix))
 		return -EFAULT;
@@ -944,6 +935,20 @@ int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr)
 	return 0;
 }
 
+int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr)
+{
+	/*
+	 * The guest FPRS and ACRS are in the host FPRS/ACRS due to the lazy
+	 * copying in vcpu load/put. Lets update our copies before we save
+	 * it into the save area
+	 */
+	save_fp_ctl(&vcpu->arch.guest_fpregs.fpc);
+	save_fp_regs(vcpu->arch.guest_fpregs.fprs);
+	save_access_regs(vcpu->run->s.regs.acrs);
+
+	return kvm_s390_store_status_unloaded(vcpu, addr);
+}
+
 static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
 				     struct kvm_enable_cap *cap)
 {
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index fcd25b4bc7af..36f6b1890d4b 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -145,8 +145,8 @@ int kvm_s390_handle_eb(struct kvm_vcpu *vcpu);
 int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu);
 
 /* implemented in kvm-s390.c */
-int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu,
-				 unsigned long addr);
+int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long addr);
+int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr);
 void s390_vcpu_block(struct kvm_vcpu *vcpu);
 void s390_vcpu_unblock(struct kvm_vcpu *vcpu);
 void exit_sie(struct kvm_vcpu *vcpu);
diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c
index bec398c57acf..6805601262e0 100644
--- a/arch/s390/kvm/sigp.c
+++ b/arch/s390/kvm/sigp.c
@@ -130,6 +130,7 @@ unlock:
 static int __inject_sigp_stop(struct kvm_s390_local_interrupt *li, int action)
 {
 	struct kvm_s390_interrupt_info *inti;
+	int rc = SIGP_CC_ORDER_CODE_ACCEPTED;
 
 	inti = kzalloc(sizeof(*inti), GFP_ATOMIC);
 	if (!inti)
@@ -139,6 +140,8 @@ static int __inject_sigp_stop(struct kvm_s390_local_interrupt *li, int action)
 	spin_lock_bh(&li->lock);
 	if ((atomic_read(li->cpuflags) & CPUSTAT_STOPPED)) {
 		kfree(inti);
+		if ((action & ACTION_STORE_ON_STOP) != 0)
+			rc = -ESHUTDOWN;
 		goto out;
 	}
 	list_add_tail(&inti->list, &li->list);
@@ -150,7 +153,7 @@ static int __inject_sigp_stop(struct kvm_s390_local_interrupt *li, int action)
 out:
 	spin_unlock_bh(&li->lock);
 
-	return SIGP_CC_ORDER_CODE_ACCEPTED;
+	return rc;
 }
 
 static int __sigp_stop(struct kvm_vcpu *vcpu, u16 cpu_addr, int action)
@@ -174,6 +177,16 @@ static int __sigp_stop(struct kvm_vcpu *vcpu, u16 cpu_addr, int action)
 unlock:
 	spin_unlock(&fi->lock);
 	VCPU_EVENT(vcpu, 4, "sent sigp stop to cpu %x", cpu_addr);
+
+	if ((action & ACTION_STORE_ON_STOP) != 0 && rc == -ESHUTDOWN) {
+		/* If the CPU has already been stopped, we still have
+		 * to save the status when doing stop-and-store. This
+		 * has to be done after unlocking all spinlocks. */
+		struct kvm_vcpu *dst_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr);
+		rc = kvm_s390_store_status_unloaded(dst_vcpu,
+						KVM_S390_STORE_STATUS_NOADDR);
+	}
+
 	return rc;
 }