diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 6742414..8959ebb 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -546,7 +546,6 @@
 	struct kvm_s390_sie_block *sie_block;
 	unsigned int      host_acrs[NUM_ACRS];
 	struct fpu	  host_fpregs;
-	struct fpu	  guest_fpregs;
 	struct kvm_s390_local_interrupt local_int;
 	struct hrtimer    ckc_timer;
 	struct kvm_s390_pgm_info pgm;
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 797dbc4..4af21c7 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -1244,7 +1244,6 @@
 
 	if (vcpu->kvm->arch.use_cmma)
 		kvm_s390_vcpu_unsetup_cmma(vcpu);
-	kfree(vcpu->arch.guest_fpregs.fprs);
 	free_page((unsigned long)(vcpu->arch.sie_block));
 
 	kvm_vcpu_uninit(vcpu);
@@ -1424,44 +1423,18 @@
 	return 0;
 }
 
-/*
- * Backs up the current FP/VX register save area on a particular
- * destination.  Used to switch between different register save
- * areas.
- */
-static inline void save_fpu_to(struct fpu *dst)
-{
-	dst->fpc = current->thread.fpu.fpc;
-	dst->regs = current->thread.fpu.regs;
-}
-
-/*
- * Switches the FP/VX register save area from which to lazy
- * restore register contents.
- */
-static inline void load_fpu_from(struct fpu *from)
-{
-	current->thread.fpu.fpc = from->fpc;
-	current->thread.fpu.regs = from->regs;
-}
-
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	/* Save host register state */
 	save_fpu_regs();
-	save_fpu_to(&vcpu->arch.host_fpregs);
+	vcpu->arch.host_fpregs.fpc = current->thread.fpu.fpc;
+	vcpu->arch.host_fpregs.regs = current->thread.fpu.regs;
 
-	if (test_kvm_facility(vcpu->kvm, 129)) {
-		current->thread.fpu.fpc = vcpu->run->s.regs.fpc;
-		/*
-		 * Use the register save area in the SIE-control block
-		 * for register restore and save in kvm_arch_vcpu_put()
-		 */
-		current->thread.fpu.vxrs =
-			(__vector128 *)&vcpu->run->s.regs.vrs;
-	} else
-		load_fpu_from(&vcpu->arch.guest_fpregs);
-
+	/* Depending on MACHINE_HAS_VX, data stored to vrs either
+	 * has vector register or floating point register format.
+	 */
+	current->thread.fpu.regs = vcpu->run->s.regs.vrs;
+	current->thread.fpu.fpc = vcpu->run->s.regs.fpc;
 	if (test_fp_ctl(current->thread.fpu.fpc))
 		/* User space provided an invalid FPC, let's clear it */
 		current->thread.fpu.fpc = 0;
@@ -1477,19 +1450,13 @@
 	atomic_andnot(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
 	gmap_disable(vcpu->arch.gmap);
 
+	/* Save guest register state */
 	save_fpu_regs();
+	vcpu->run->s.regs.fpc = current->thread.fpu.fpc;
 
-	if (test_kvm_facility(vcpu->kvm, 129))
-		/*
-		 * kvm_arch_vcpu_load() set up the register save area to
-		 * the &vcpu->run->s.regs.vrs and, thus, the vector registers
-		 * are already saved.  Only the floating-point control must be
-		 * copied.
-		 */
-		vcpu->run->s.regs.fpc = current->thread.fpu.fpc;
-	else
-		save_fpu_to(&vcpu->arch.guest_fpregs);
-	load_fpu_from(&vcpu->arch.host_fpregs);
+	/* Restore host register state */
+	current->thread.fpu.fpc = vcpu->arch.host_fpregs.fpc;
+	current->thread.fpu.regs = vcpu->arch.host_fpregs.regs;
 
 	save_access_regs(vcpu->run->s.regs.acrs);
 	restore_access_regs(vcpu->arch.host_acrs);
@@ -1507,8 +1474,9 @@
 	memset(vcpu->arch.sie_block->gcr, 0, 16 * sizeof(__u64));
 	vcpu->arch.sie_block->gcr[0]  = 0xE0UL;
 	vcpu->arch.sie_block->gcr[14] = 0xC2000000UL;
-	vcpu->arch.guest_fpregs.fpc = 0;
-	asm volatile("lfpc %0" : : "Q" (vcpu->arch.guest_fpregs.fpc));
+	/* make sure the new fpc will be lazily loaded */
+	save_fpu_regs();
+	current->thread.fpu.fpc = 0;
 	vcpu->arch.sie_block->gbea = 1;
 	vcpu->arch.sie_block->pp = 0;
 	vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
@@ -1649,27 +1617,14 @@
 	vcpu->arch.local_int.wq = &vcpu->wq;
 	vcpu->arch.local_int.cpuflags = &vcpu->arch.sie_block->cpuflags;
 
-	/*
-	 * Allocate a save area for floating-point registers.  If the vector
-	 * extension is available, register contents are saved in the SIE
-	 * control block.  The allocated save area is still required in
-	 * particular places, for example, in kvm_s390_vcpu_store_status().
-	 */
-	vcpu->arch.guest_fpregs.fprs = kzalloc(sizeof(freg_t) * __NUM_FPRS,
-					       GFP_KERNEL);
-	if (!vcpu->arch.guest_fpregs.fprs)
-		goto out_free_sie_block;
-
 	rc = kvm_vcpu_init(vcpu, kvm, id);
 	if (rc)
-		goto out_free_fprs;
+		goto out_free_sie_block;
 	VM_EVENT(kvm, 3, "create cpu %d at 0x%pK, sie block at 0x%pK", id, vcpu,
 		 vcpu->arch.sie_block);
 	trace_kvm_s390_create_vcpu(id, vcpu, vcpu->arch.sie_block);
 
 	return vcpu;
-out_free_fprs:
-	kfree(vcpu->arch.guest_fpregs.fprs);
 out_free_sie_block:
 	free_page((unsigned long)(vcpu->arch.sie_block));
 out_free_cpu:
@@ -1882,19 +1837,27 @@
 
 int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 {
+	/* make sure the new values will be lazily loaded */
+	save_fpu_regs();
 	if (test_fp_ctl(fpu->fpc))
 		return -EINVAL;
-	memcpy(vcpu->arch.guest_fpregs.fprs, &fpu->fprs, sizeof(fpu->fprs));
-	vcpu->arch.guest_fpregs.fpc = fpu->fpc;
-	save_fpu_regs();
-	load_fpu_from(&vcpu->arch.guest_fpregs);
+	current->thread.fpu.fpc = fpu->fpc;
+	if (MACHINE_HAS_VX)
+		convert_fp_to_vx(current->thread.fpu.vxrs, (freg_t *)fpu->fprs);
+	else
+		memcpy(current->thread.fpu.fprs, &fpu->fprs, sizeof(fpu->fprs));
 	return 0;
 }
 
 int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 {
-	memcpy(&fpu->fprs, vcpu->arch.guest_fpregs.fprs, sizeof(fpu->fprs));
-	fpu->fpc = vcpu->arch.guest_fpregs.fpc;
+	/* make sure we have the latest values */
+	save_fpu_regs();
+	if (MACHINE_HAS_VX)
+		convert_vx_to_fp((freg_t *)fpu->fprs, current->thread.fpu.vxrs);
+	else
+		memcpy(fpu->fprs, current->thread.fpu.fprs, sizeof(fpu->fprs));
+	fpu->fpc = current->thread.fpu.fpc;
 	return 0;
 }
 
@@ -2399,6 +2362,7 @@
 int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long gpa)
 {
 	unsigned char archmode = 1;
+	freg_t fprs[NUM_FPRS];
 	unsigned int px;
 	u64 clkcomp;
 	int rc;
@@ -2414,8 +2378,16 @@
 		gpa = px;
 	} else
 		gpa -= __LC_FPREGS_SAVE_AREA;
-	rc = write_guest_abs(vcpu, gpa + __LC_FPREGS_SAVE_AREA,
-			     vcpu->arch.guest_fpregs.fprs, 128);
+
+	/* manually convert vector registers if necessary */
+	if (MACHINE_HAS_VX) {
+		convert_vx_to_fp(fprs, current->thread.fpu.vxrs);
+		rc = write_guest_abs(vcpu, gpa + __LC_FPREGS_SAVE_AREA,
+				     fprs, 128);
+	} else {
+		rc = write_guest_abs(vcpu, gpa + __LC_FPREGS_SAVE_AREA,
+				     vcpu->run->s.regs.vrs, 128);
+	}
 	rc |= write_guest_abs(vcpu, gpa + __LC_GPREGS_SAVE_AREA,
 			      vcpu->run->s.regs.gprs, 128);
 	rc |= write_guest_abs(vcpu, gpa + __LC_PSW_SAVE_AREA,
@@ -2423,7 +2395,7 @@
 	rc |= write_guest_abs(vcpu, gpa + __LC_PREFIX_SAVE_AREA,
 			      &px, 4);
 	rc |= write_guest_abs(vcpu, gpa + __LC_FP_CREG_SAVE_AREA,
-			      &vcpu->arch.guest_fpregs.fpc, 4);
+			      &vcpu->run->s.regs.fpc, 4);
 	rc |= write_guest_abs(vcpu, gpa + __LC_TOD_PROGREG_SAVE_AREA,
 			      &vcpu->arch.sie_block->todpr, 4);
 	rc |= write_guest_abs(vcpu, gpa + __LC_CPU_TIMER_SAVE_AREA,
@@ -2446,19 +2418,7 @@
 	 * it into the save area
 	 */
 	save_fpu_regs();
-	if (test_kvm_facility(vcpu->kvm, 129)) {
-		/*
-		 * If the vector extension is available, the vector registers
-		 * which overlaps with floating-point registers are saved in
-		 * the SIE-control block.  Hence, extract the floating-point
-		 * registers and the FPC value and store them in the
-		 * guest_fpregs structure.
-		 */
-		vcpu->arch.guest_fpregs.fpc = current->thread.fpu.fpc;
-		convert_vx_to_fp(vcpu->arch.guest_fpregs.fprs,
-				 current->thread.fpu.vxrs);
-	} else
-		save_fpu_to(&vcpu->arch.guest_fpregs);
+	vcpu->run->s.regs.fpc = current->thread.fpu.fpc;
 	save_access_regs(vcpu->run->s.regs.acrs);
 
 	return kvm_s390_store_status_unloaded(vcpu, addr);