diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h
index 708e4d8a647f..0fa90c962ac8 100644
--- a/arch/arm/include/asm/kvm_emulate.h
+++ b/arch/arm/include/asm/kvm_emulate.h
@@ -162,4 +162,50 @@ static inline unsigned long kvm_vcpu_get_mpidr(struct kvm_vcpu *vcpu)
 	return vcpu->arch.cp15[c0_MPIDR];
 }
 
+static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu)
+{
+	*vcpu_cpsr(vcpu) |= PSR_E_BIT;
+}
+
+static inline bool kvm_vcpu_is_be(struct kvm_vcpu *vcpu)
+{
+	return !!(*vcpu_cpsr(vcpu) & PSR_E_BIT);
+}
+
+static inline unsigned long vcpu_data_guest_to_host(struct kvm_vcpu *vcpu,
+						    unsigned long data,
+						    unsigned int len)
+{
+	if (kvm_vcpu_is_be(vcpu)) {
+		switch (len) {
+		case 1:
+			return data & 0xff;
+		case 2:
+			return be16_to_cpu(data & 0xffff);
+		default:
+			return be32_to_cpu(data);
+		}
+	}
+
+	return data;		/* Leave LE untouched */
+}
+
+static inline unsigned long vcpu_data_host_to_guest(struct kvm_vcpu *vcpu,
+						    unsigned long data,
+						    unsigned int len)
+{
+	if (kvm_vcpu_is_be(vcpu)) {
+		switch (len) {
+		case 1:
+			return data & 0xff;
+		case 2:
+			return cpu_to_be16(data & 0xffff);
+		default:
+			return cpu_to_be32(data);
+		}
+	}
+
+	return data;		/* Leave LE untouched */
+}
+
 #endif /* __ARM_KVM_EMULATE_H__ */
diff --git a/arch/arm/kvm/mmio.c b/arch/arm/kvm/mmio.c
index 0c25d9487d53..4cb5a93182e9 100644
--- a/arch/arm/kvm/mmio.c
+++ b/arch/arm/kvm/mmio.c
@@ -23,6 +23,68 @@
 
 #include "trace.h"
 
+static void mmio_write_buf(char *buf, unsigned int len, unsigned long data)
+{
+	void *datap = NULL;
+	union {
+		u8	byte;
+		u16	hword;
+		u32	word;
+		u64	dword;
+	} tmp;
+
+	switch (len) {
+	case 1:
+		tmp.byte	= data;
+		datap		= &tmp.byte;
+		break;
+	case 2:
+		tmp.hword	= data;
+		datap		= &tmp.hword;
+		break;
+	case 4:
+		tmp.word	= data;
+		datap		= &tmp.word;
+		break;
+	case 8:
+		tmp.dword	= data;
+		datap		= &tmp.dword;
+		break;
+	}
+
+	memcpy(buf, datap, len);
+}
+
+static unsigned long mmio_read_buf(char *buf, unsigned int len)
+{
+	unsigned long data = 0;
+	union {
+		u16	hword;
+		u32	word;
+		u64	dword;
+	} tmp;
+
+	switch (len) {
+	case 1:
+		data = buf[0];
+		break;
+	case 2:
+		memcpy(&tmp.hword, buf, len);
+		data = tmp.hword;
+		break;
+	case 4:
+		memcpy(&tmp.word, buf, len);
+		data = tmp.word;
+		break;
+	case 8:
+		memcpy(&tmp.dword, buf, len);
+		data = tmp.dword;
+		break;
+	}
+
+	return data;
+}
+
 /**
  * kvm_handle_mmio_return -- Handle MMIO loads after user space emulation
  * @vcpu: The VCPU pointer
@@ -33,28 +95,27 @@
  */
 int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
-	unsigned long *dest;
+	unsigned long data;
 	unsigned int len;
 	int mask;
 
 	if (!run->mmio.is_write) {
-		dest = vcpu_reg(vcpu, vcpu->arch.mmio_decode.rt);
-		*dest = 0;
-
 		len = run->mmio.len;
 		if (len > sizeof(unsigned long))
 			return -EINVAL;
 
-		memcpy(dest, run->mmio.data, len);
-
-		trace_kvm_mmio(KVM_TRACE_MMIO_READ, len, run->mmio.phys_addr,
-				*((u64 *)run->mmio.data));
+		data = mmio_read_buf(run->mmio.data, len);
 
 		if (vcpu->arch.mmio_decode.sign_extend &&
 		    len < sizeof(unsigned long)) {
 			mask = 1U << ((len * 8) - 1);
-			*dest = (*dest ^ mask) - mask;
+			data = (data ^ mask) - mask;
 		}
+
+		trace_kvm_mmio(KVM_TRACE_MMIO_READ, len, run->mmio.phys_addr,
+			       data);
+		data = vcpu_data_host_to_guest(vcpu, data, len);
+		*vcpu_reg(vcpu, vcpu->arch.mmio_decode.rt) = data;
 	}
 
 	return 0;
@@ -105,6 +166,7 @@ int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		 phys_addr_t fault_ipa)
 {
 	struct kvm_exit_mmio mmio;
+	unsigned long data;
 	unsigned long rt;
 	int ret;
 
@@ -125,13 +187,15 @@ int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run,
 	}
 
 	rt = vcpu->arch.mmio_decode.rt;
+	data = vcpu_data_guest_to_host(vcpu, *vcpu_reg(vcpu, rt), mmio.len);
+
 	trace_kvm_mmio((mmio.is_write) ? KVM_TRACE_MMIO_WRITE :
 					 KVM_TRACE_MMIO_READ_UNSATISFIED,
 			mmio.len, fault_ipa,
-			(mmio.is_write) ? *vcpu_reg(vcpu, rt) : 0);
+			(mmio.is_write) ? data : 0);
 
 	if (mmio.is_write)
-		memcpy(mmio.data, vcpu_reg(vcpu, rt), mmio.len);
+		mmio_write_buf(mmio.data, mmio.len, data);
 
 	if (vgic_handle_mmio(vcpu, run, &mmio))
 		return 1;
diff --git a/arch/arm/kvm/psci.c b/arch/arm/kvm/psci.c
index 311263124acf..0881bf169fbc 100644
--- a/arch/arm/kvm/psci.c
+++ b/arch/arm/kvm/psci.c
@@ -71,6 +71,10 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
 		vcpu_set_thumb(vcpu);
 	}
 
+	/* Propagate caller endianness */
+	if (kvm_vcpu_is_be(source_vcpu))
+		kvm_vcpu_set_be(vcpu);
+
 	*vcpu_pc(vcpu) = target_pc;
 	vcpu->arch.pause = false;
 	smp_mb();		/* Make sure the above is visible */
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index a5f28e2720c7..c98ef4771c73 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -63,6 +63,7 @@
  * TAC:		Trap ACTLR
  * TSC:		Trap SMC
  * TSW:		Trap cache operations by set/way
+ * TWE:		Trap WFE
  * TWI:		Trap WFI
  * TIDCP:	Trap L2CTLR/L2ECTLR
  * BSU_IS:	Upgrade barriers to the inner shareable domain
@@ -72,8 +73,9 @@
  * FMO:		Override CPSR.F and enable signaling with VF
  * SWIO:	Turn set/way invalidates into set/way clean+invalidate
  */
-#define HCR_GUEST_FLAGS (HCR_TSC | HCR_TSW | HCR_TWI | HCR_VM | HCR_BSU_IS | \
-			 HCR_FB | HCR_TAC | HCR_AMO | HCR_IMO | HCR_FMO | \
+#define HCR_GUEST_FLAGS (HCR_TSC | HCR_TSW | HCR_TWE | HCR_TWI | HCR_VM | \
+			 HCR_BSU_IS | HCR_FB | HCR_TAC | \
+			 HCR_AMO | HCR_IMO | HCR_FMO | \
 			 HCR_SWIO | HCR_TIDCP | HCR_RW)
 #define HCR_VIRT_EXCP_MASK (HCR_VA | HCR_VI | HCR_VF)
 
@@ -242,4 +244,6 @@
 
 #define ESR_EL2_EC_xABT_xFSR_EXTABT	0x10
 
+#define ESR_EL2_EC_WFI_ISS_WFE	(1 << 0)
+
 #endif /* __ARM64_KVM_ARM_H__ */
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 6df93cdc652b..dd8ecfc3f995 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -182,4 +182,60 @@ static inline unsigned long kvm_vcpu_get_mpidr(struct kvm_vcpu *vcpu)
 	return vcpu_sys_reg(vcpu, MPIDR_EL1);
 }
 
+static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu)
+{
+	if (vcpu_mode_is_32bit(vcpu))
+		*vcpu_cpsr(vcpu) |= COMPAT_PSR_E_BIT;
+	else
+		vcpu_sys_reg(vcpu, SCTLR_EL1) |= (1 << 25);
+}
+
+static inline bool kvm_vcpu_is_be(struct kvm_vcpu *vcpu)
+{
+	if (vcpu_mode_is_32bit(vcpu))
+		return !!(*vcpu_cpsr(vcpu) & COMPAT_PSR_E_BIT);
+
+	return !!(vcpu_sys_reg(vcpu, SCTLR_EL1) & (1 << 25));
+}
+
+static inline unsigned long vcpu_data_guest_to_host(struct kvm_vcpu *vcpu,
+						    unsigned long data,
+						    unsigned int len)
+{
+	if (kvm_vcpu_is_be(vcpu)) {
+		switch (len) {
+		case 1:
+			return data & 0xff;
+		case 2:
+			return be16_to_cpu(data & 0xffff);
+		case 4:
+			return be32_to_cpu(data & 0xffffffff);
+		default:
+			return be64_to_cpu(data);
+		}
+	}
+
+	return data;		/* Leave LE untouched */
+}
+
+static inline unsigned long vcpu_data_host_to_guest(struct kvm_vcpu *vcpu,
+						    unsigned long data,
+						    unsigned int len)
+{
+	if (kvm_vcpu_is_be(vcpu)) {
+		switch (len) {
+		case 1:
+			return data & 0xff;
+		case 2:
+			return cpu_to_be16(data & 0xffff);
+		case 4:
+			return cpu_to_be32(data & 0xffffffff);
+		default:
+			return cpu_to_be64(data);
+		}
+	}
+
+	return data;		/* Leave LE untouched */
+}
+
 #endif /* __ARM64_KVM_EMULATE_H__ */
diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index 21e90820bd23..4480ab339a00 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -21,6 +21,7 @@ config KVM
 	select MMU_NOTIFIER
 	select PREEMPT_NOTIFIERS
 	select ANON_INODES
+	select HAVE_KVM_CPU_RELAX_INTERCEPT
 	select KVM_MMIO
 	select KVM_ARM_HOST
 	select KVM_ARM_VGIC
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index 9beaca033437..8da56067c304 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -47,21 +47,29 @@ static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run)
 }
 
 /**
- * kvm_handle_wfi - handle a wait-for-interrupts instruction executed by a guest
+ * kvm_handle_wfx - handle a wait-for-interrupts or wait-for-event
+ *		    instruction executed by a guest
+ *
  * @vcpu:	the vcpu pointer
  *
- * Simply call kvm_vcpu_block(), which will halt execution of
+ * WFE: Yield the CPU and come back to this vcpu when the scheduler
+ * decides to.
+ * WFI: Simply call kvm_vcpu_block(), which will halt execution of
  * world-switches and schedule other host processes until there is an
  * incoming IRQ or FIQ to the VM.
  */
-static int kvm_handle_wfi(struct kvm_vcpu *vcpu, struct kvm_run *run)
+static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
-	kvm_vcpu_block(vcpu);
+	if (kvm_vcpu_get_hsr(vcpu) & ESR_EL2_EC_WFI_ISS_WFE)
+		kvm_vcpu_on_spin(vcpu);
+	else
+		kvm_vcpu_block(vcpu);
+
 	return 1;
 }
 
 static exit_handle_fn arm_exit_handlers[] = {
-	[ESR_EL2_EC_WFI]	= kvm_handle_wfi,
+	[ESR_EL2_EC_WFI]	= kvm_handle_wfx,
 	[ESR_EL2_EC_CP15_32]	= kvm_handle_cp15_32,
 	[ESR_EL2_EC_CP15_64]	= kvm_handle_cp15_64,
 	[ESR_EL2_EC_CP14_MR]	= kvm_handle_cp14_access,