diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 858aecf21db2..0d578c0f5749 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -2299,7 +2299,8 @@ should be created before this ioctl is invoked.
 
 Possible features:
 	- KVM_ARM_VCPU_POWER_OFF: Starts the CPU in a power-off state.
-	  Depends on KVM_CAP_ARM_PSCI.
+	  Depends on KVM_CAP_ARM_PSCI.  If not set, the CPU will be powered on
+	  and execute guest code when KVM_RUN is called.
 	- KVM_ARM_VCPU_EL1_32BIT: Starts the CPU in a 32bit mode.
 	  Depends on KVM_CAP_ARM_EL1_32BIT (arm64 only).
 
diff --git a/Makefile b/Makefile
index 597426cb6a4d..f78c2f2579f9 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
 VERSION = 3
 PATCHLEVEL = 12
-SUBLEVEL = 41
+SUBLEVEL = 42
 EXTRAVERSION =
 NAME = One Giant Leap for Frogkind
 
diff --git a/arch/arm/include/asm/kvm_arm.h b/arch/arm/include/asm/kvm_arm.h
index 64e96960de29..816db0bf2dd8 100644
--- a/arch/arm/include/asm/kvm_arm.h
+++ b/arch/arm/include/asm/kvm_arm.h
@@ -55,8 +55,10 @@
  * The bits we set in HCR:
  * TAC:		Trap ACTLR
  * TSC:		Trap SMC
+ * TVM:		Trap VM ops (until MMU and caches are on)
  * TSW:		Trap cache operations by set/way
  * TWI:		Trap WFI
+ * TWE:		Trap WFE
  * TIDCP:	Trap L2CTLR/L2ECTLR
  * BSU_IS:	Upgrade barriers to the inner shareable domain
  * FB:		Force broadcast of all maintainance operations
@@ -67,8 +69,7 @@
  */
 #define HCR_GUEST_MASK (HCR_TSC | HCR_TSW | HCR_TWI | HCR_VM | HCR_BSU_IS | \
 			HCR_FB | HCR_TAC | HCR_AMO | HCR_IMO | HCR_FMO | \
-			HCR_SWIO | HCR_TIDCP)
-#define HCR_VIRT_EXCP_MASK (HCR_VA | HCR_VI | HCR_VF)
+			HCR_TVM | HCR_TWE | HCR_SWIO | HCR_TIDCP)
 
 /* System Control Register (SCTLR) bits */
 #define SCTLR_TE	(1 << 30)
@@ -95,12 +96,12 @@
 #define TTBCR_IRGN1	(3 << 24)
 #define TTBCR_EPD1	(1 << 23)
 #define TTBCR_A1	(1 << 22)
-#define TTBCR_T1SZ	(3 << 16)
+#define TTBCR_T1SZ	(7 << 16)
 #define TTBCR_SH0	(3 << 12)
 #define TTBCR_ORGN0	(3 << 10)
 #define TTBCR_IRGN0	(3 << 8)
 #define TTBCR_EPD0	(1 << 7)
-#define TTBCR_T0SZ	3
+#define TTBCR_T0SZ	(7 << 0)
 #define HTCR_MASK	(TTBCR_T0SZ | TTBCR_IRGN0 | TTBCR_ORGN0 | TTBCR_SH0)
 
 /* Hyp System Trap Register */
@@ -208,6 +209,8 @@
 #define HSR_EC_DABT	(0x24)
 #define HSR_EC_DABT_HYP	(0x25)
 
+#define HSR_WFI_IS_WFE		(1U << 0)
+
 #define HSR_HVC_IMM_MASK	((1UL << 16) - 1)
 
 #define HSR_DABT_S1PTW		(1U << 7)
diff --git a/arch/arm/include/asm/kvm_asm.h b/arch/arm/include/asm/kvm_asm.h
index a2f43ddcc300..cdd3cf171cd1 100644
--- a/arch/arm/include/asm/kvm_asm.h
+++ b/arch/arm/include/asm/kvm_asm.h
@@ -48,7 +48,9 @@
 #define c13_TID_URO	26	/* Thread ID, User R/O */
 #define c13_TID_PRIV	27	/* Thread ID, Privileged */
 #define c14_CNTKCTL	28	/* Timer Control Register (PL1) */
-#define NR_CP15_REGS	29	/* Number of regs (incl. invalid) */
+#define c10_AMAIR0	29	/* Auxilary Memory Attribute Indirection Reg0 */
+#define c10_AMAIR1	30	/* Auxilary Memory Attribute Indirection Reg1 */
+#define NR_CP15_REGS	31	/* Number of regs (incl. invalid) */
 
 #define ARM_EXCEPTION_RESET	  0
 #define ARM_EXCEPTION_UNDEFINED   1
diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h
index a464e8d7b6c5..4adba055cfea 100644
--- a/arch/arm/include/asm/kvm_emulate.h
+++ b/arch/arm/include/asm/kvm_emulate.h
@@ -33,6 +33,11 @@ void kvm_inject_undefined(struct kvm_vcpu *vcpu);
 void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr);
 void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr);
 
+static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.hcr = HCR_GUEST_MASK;
+}
+
 static inline bool vcpu_mode_is_32bit(struct kvm_vcpu *vcpu)
 {
 	return 1;
@@ -157,4 +162,9 @@ static inline u32 kvm_vcpu_hvc_get_imm(struct kvm_vcpu *vcpu)
 	return kvm_vcpu_get_hsr(vcpu) & HSR_HVC_IMM_MASK;
 }
 
+static inline unsigned long kvm_vcpu_get_mpidr(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.cp15[c0_MPIDR];
+}
+
 #endif /* __ARM_KVM_EMULATE_H__ */
diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index 7d22517d8071..2e247b6ec2cc 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -47,7 +47,7 @@
 
 struct kvm_vcpu;
 u32 *kvm_vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num, u32 mode);
-int kvm_target_cpu(void);
+int __attribute_const__ kvm_target_cpu(void);
 int kvm_reset_vcpu(struct kvm_vcpu *vcpu);
 void kvm_reset_coprocs(struct kvm_vcpu *vcpu);
 
@@ -106,6 +106,12 @@ struct kvm_vcpu_arch {
 	/* The CPU type we expose to the VM */
 	u32 midr;
 
+	/* HYP trapping configuration */
+	u32 hcr;
+
+	/* Interrupt related fields */
+	u32 irq_lines;		/* IRQ and FIQ levels */
+
 	/* Exception Information */
 	struct kvm_vcpu_fault_info fault;
 
@@ -133,9 +139,6 @@ struct kvm_vcpu_arch {
 	/* IO related fields */
 	struct kvm_decode mmio_decode;
 
-	/* Interrupt related fields */
-	u32 irq_lines;		/* IRQ and FIQ levels */
-
 	/* Cache some mmu pages needed inside spinlock regions */
 	struct kvm_mmu_memory_cache mmu_page_cache;
 
diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index 9b28c41f4ba9..7a1d664fa13f 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -47,6 +47,7 @@ int create_hyp_io_mappings(void *from, void *to, phys_addr_t);
 void free_boot_hyp_pgd(void);
 void free_hyp_pgds(void);
 
+void stage2_unmap_vm(struct kvm *kvm);
 int kvm_alloc_stage2_pgd(struct kvm *kvm);
 void kvm_free_stage2_pgd(struct kvm *kvm);
 int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
@@ -72,17 +73,6 @@ static inline void kvm_set_pte(pte_t *pte, pte_t new_pte)
 	flush_pmd_entry(pte);
 }
 
-static inline bool kvm_is_write_fault(unsigned long hsr)
-{
-	unsigned long hsr_ec = hsr >> HSR_EC_SHIFT;
-	if (hsr_ec == HSR_EC_IABT)
-		return false;
-	else if ((hsr & HSR_ISV) && !(hsr & HSR_WNR))
-		return false;
-	else
-		return true;
-}
-
 static inline void kvm_clean_pgd(pgd_t *pgd)
 {
 	clean_dcache_area(pgd, PTRS_PER_S2_PGD * sizeof(pgd_t));
@@ -103,10 +93,46 @@ static inline void kvm_set_s2pte_writable(pte_t *pte)
 	pte_val(*pte) |= L_PTE_S2_RDWR;
 }
 
+/* Open coded p*d_addr_end that can deal with 64bit addresses */
+#define kvm_pgd_addr_end(addr, end)                                    \
+({	u64 __boundary = ((addr) + PGDIR_SIZE) & PGDIR_MASK;            \
+	(__boundary - 1 < (end) - 1)? __boundary: (end);                \
+})
+
+#define kvm_pud_addr_end(addr,end)             (end)
+
+#define kvm_pmd_addr_end(addr, end)                                    \
+({	u64 __boundary = ((addr) + PMD_SIZE) & PMD_MASK;                \
+	(__boundary - 1 < (end) - 1)? __boundary: (end);                \
+})
+
+#define kvm_pgd_index(addr)                    pgd_index(addr)
+
+static inline bool kvm_page_empty(void *ptr)
+{
+	struct page *ptr_page = virt_to_page(ptr);
+	return page_count(ptr_page) == 1;
+}
+
+
+#define kvm_pte_table_empty(ptep) kvm_page_empty(ptep)
+#define kvm_pmd_table_empty(pmdp) kvm_page_empty(pmdp)
+#define kvm_pud_table_empty(pudp) (0)
+
 struct kvm;
 
-static inline void coherent_icache_guest_page(struct kvm *kvm, gfn_t gfn)
+#define kvm_flush_dcache_to_poc(a,l)   __cpuc_flush_dcache_area((a), (l))
+
+static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu)
+{
+	return (vcpu->arch.cp15[c1_SCTLR] & 0b101) == 0b101;
+}
+
+static inline void coherent_cache_guest_page(struct kvm_vcpu *vcpu, hva_t hva,
+					    unsigned long size)
 {
+	if (!vcpu_has_cache_enabled(vcpu))
+		kvm_flush_dcache_to_poc((void *)hva, size);
 	/*
 	 * If we are going to insert an instruction page and the icache is
 	 * either VIPT or PIPT, there is a potential problem where the host
@@ -120,15 +146,14 @@ static inline void coherent_icache_guest_page(struct kvm *kvm, gfn_t gfn)
 	 * need any kind of flushing (DDI 0406C.b - Page B3-1392).
 	 */
 	if (icache_is_pipt()) {
-		unsigned long hva = gfn_to_hva(kvm, gfn);
-		__cpuc_coherent_user_range(hva, hva + PAGE_SIZE);
+		__cpuc_coherent_user_range(hva, hva + size);
 	} else if (!icache_is_vivt_asid_tagged()) {
 		/* any kind of VIPT cache */
 		__flush_icache_all();
 	}
 }
 
-#define kvm_flush_dcache_to_poc(a,l)	__cpuc_flush_dcache_area((a), (l))
+void stage2_flush_vm(struct kvm *kvm);
 
 #endif	/* !__ASSEMBLY__ */
 
diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c
index ded041711beb..85598b5d1efd 100644
--- a/arch/arm/kernel/asm-offsets.c
+++ b/arch/arm/kernel/asm-offsets.c
@@ -174,6 +174,7 @@ int main(void)
   DEFINE(VCPU_FIQ_REGS,		offsetof(struct kvm_vcpu, arch.regs.fiq_regs));
   DEFINE(VCPU_PC,		offsetof(struct kvm_vcpu, arch.regs.usr_regs.ARM_pc));
   DEFINE(VCPU_CPSR,		offsetof(struct kvm_vcpu, arch.regs.usr_regs.ARM_cpsr));
+  DEFINE(VCPU_HCR,		offsetof(struct kvm_vcpu, arch.hcr));
   DEFINE(VCPU_IRQ_LINES,	offsetof(struct kvm_vcpu, arch.irq_lines));
   DEFINE(VCPU_HSR,		offsetof(struct kvm_vcpu, arch.fault.hsr));
   DEFINE(VCPU_HxFAR,		offsetof(struct kvm_vcpu, arch.fault.hxfar));
diff --git a/arch/arm/kernel/hyp-stub.S b/arch/arm/kernel/hyp-stub.S
index 797b1a6a4906..6c3b5972d5c9 100644
--- a/arch/arm/kernel/hyp-stub.S
+++ b/arch/arm/kernel/hyp-stub.S
@@ -135,7 +135,7 @@ ENTRY(__hyp_stub_install_secondary)
 
 THUMB(	orr	r7, #(1 << 30)	)	@ HSCTLR.TE
 #ifdef CONFIG_CPU_BIG_ENDIAN
-	orr	r7, #(1 << 9)		@ HSCTLR.EE
+	orr	r7, r7, #(1 << 25)      @ HSCTLR.EE
 #endif
 	mcr	p15, 4, r7, c1, c0, 0	@ HSCTLR
 
diff --git a/arch/arm/kvm/Kconfig b/arch/arm/kvm/Kconfig
index ebf5015508b5..4be5bb150bdd 100644
--- a/arch/arm/kvm/Kconfig
+++ b/arch/arm/kvm/Kconfig
@@ -20,9 +20,10 @@ config KVM
 	bool "Kernel-based Virtual Machine (KVM) support"
 	select PREEMPT_NOTIFIERS
 	select ANON_INODES
+	select HAVE_KVM_CPU_RELAX_INTERCEPT
 	select KVM_MMIO
 	select KVM_ARM_HOST
-	depends on ARM_VIRT_EXT && ARM_LPAE
+	depends on ARM_VIRT_EXT && ARM_LPAE && !CPU_BIG_ENDIAN
 	---help---
 	  Support hosting virtualized guest machines. You will also
 	  need to select one or more of the processor modules below.
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 9c697db2787e..28b60461936e 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -17,6 +17,7 @@
  */
 
 #include <linux/cpu.h>
+#include <linux/cpu_pm.h>
 #include <linux/errno.h>
 #include <linux/err.h>
 #include <linux/kvm_host.h>
@@ -81,7 +82,7 @@ struct kvm_vcpu *kvm_arm_get_running_vcpu(void)
 /**
  * kvm_arm_get_running_vcpus - get the per-CPU array of currently running vcpus.
  */
-struct kvm_vcpu __percpu **kvm_get_running_vcpus(void)
+struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void)
 {
 	return &kvm_arm_running_vcpu;
 }
@@ -137,6 +138,8 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	if (ret)
 		goto out_free_stage2_pgd;
 
+	kvm_timer_init(kvm);
+
 	/* Mark the initial VMID generation invalid */
 	kvm->arch.vmid_gen = 0;
 
@@ -152,16 +155,6 @@ int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
 	return VM_FAULT_SIGBUS;
 }
 
-void kvm_arch_free_memslot(struct kvm_memory_slot *free,
-			   struct kvm_memory_slot *dont)
-{
-}
-
-int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
-{
-	return 0;
-}
-
 /**
  * kvm_arch_destroy_vm - destroy the VM data structure
  * @kvm:	pointer to the KVM struct
@@ -219,39 +212,17 @@ long kvm_arch_dev_ioctl(struct file *filp,
 	return -EINVAL;
 }
 
-void kvm_arch_memslots_updated(struct kvm *kvm)
-{
-}
-
-int kvm_arch_prepare_memory_region(struct kvm *kvm,
-				   struct kvm_memory_slot *memslot,
-				   struct kvm_userspace_memory_region *mem,
-				   enum kvm_mr_change change)
-{
-	return 0;
-}
-
-void kvm_arch_commit_memory_region(struct kvm *kvm,
-				   struct kvm_userspace_memory_region *mem,
-				   const struct kvm_memory_slot *old,
-				   enum kvm_mr_change change)
-{
-}
-
-void kvm_arch_flush_shadow_all(struct kvm *kvm)
-{
-}
-
-void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
-				   struct kvm_memory_slot *slot)
-{
-}
 
 struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
 {
 	int err;
 	struct kvm_vcpu *vcpu;
 
+	if (irqchip_in_kernel(kvm) && vgic_initialized(kvm)) {
+		err = -EBUSY;
+		goto out;
+	}
+
 	vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
 	if (!vcpu) {
 		err = -ENOMEM;
@@ -338,6 +309,13 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 {
+	/*
+	 * The arch-generic KVM code expects the cpu field of a vcpu to be -1
+	 * if the vcpu is no longer assigned to a cpu.  This is used for the
+	 * optimized make_all_cpus_request path.
+	 */
+	vcpu->cpu = -1;
+
 	kvm_arm_set_running_vcpu(NULL);
 }
 
@@ -452,15 +430,18 @@ static void update_vttbr(struct kvm *kvm)
 
 	/* update vttbr to be used with the new vmid */
 	pgd_phys = virt_to_phys(kvm->arch.pgd);
+	BUG_ON(pgd_phys & ~VTTBR_BADDR_MASK);
 	vmid = ((u64)(kvm->arch.vmid) << VTTBR_VMID_SHIFT) & VTTBR_VMID_MASK;
-	kvm->arch.vttbr = pgd_phys & VTTBR_BADDR_MASK;
-	kvm->arch.vttbr |= vmid;
+	kvm->arch.vttbr = pgd_phys | vmid;
 
 	spin_unlock(&kvm_vmid_lock);
 }
 
 static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu)
 {
+	struct kvm *kvm = vcpu->kvm;
+	int ret;
+
 	if (likely(vcpu->arch.has_run_once))
 		return 0;
 
@@ -470,21 +451,19 @@ static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu)
 	 * Initialize the VGIC before running a vcpu the first time on
 	 * this VM.
 	 */
-	if (irqchip_in_kernel(vcpu->kvm) &&
-	    unlikely(!vgic_initialized(vcpu->kvm))) {
-		int ret = kvm_vgic_init(vcpu->kvm);
+	if (unlikely(!vgic_initialized(vcpu->kvm))) {
+		ret = kvm_vgic_init(vcpu->kvm);
 		if (ret)
 			return ret;
 	}
 
 	/*
-	 * Handle the "start in power-off" case by calling into the
-	 * PSCI code.
+	 * Enable the arch timers only if we have an in-kernel VGIC
+	 * and it has been properly initialized, since we cannot handle
+	 * interrupts from the virtual timer with a userspace gic.
 	 */
-	if (test_and_clear_bit(KVM_ARM_VCPU_POWER_OFF, vcpu->arch.features)) {
-		*vcpu_reg(vcpu, 0) = KVM_PSCI_FN_CPU_OFF;
-		kvm_psci_call(vcpu);
-	}
+	if (irqchip_in_kernel(kvm) && vgic_initialized(kvm))
+		kvm_timer_enable(kvm);
 
 	return 0;
 }
@@ -699,6 +678,35 @@ int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level,
 	return -EINVAL;
 }
 
+static int kvm_arch_vcpu_ioctl_vcpu_init(struct kvm_vcpu *vcpu,
+					 struct kvm_vcpu_init *init)
+{
+	int ret;
+
+	ret = kvm_vcpu_set_target(vcpu, init);
+	if (ret)
+		return ret;
+
+	/*
+	 * Ensure a rebooted VM will fault in RAM pages and detect if the
+	 * guest MMU is turned off and flush the caches as needed.
+	 */
+	if (vcpu->arch.has_run_once)
+		stage2_unmap_vm(vcpu->kvm);
+
+	vcpu_reset_hcr(vcpu);
+
+	/*
+	 * Handle the "start in power-off" case by marking the VCPU as paused.
+	 */
+	if (test_bit(KVM_ARM_VCPU_POWER_OFF, vcpu->arch.features))
+		vcpu->arch.pause = true;
+	else
+		vcpu->arch.pause = false;
+
+	return 0;
+}
+
 long kvm_arch_vcpu_ioctl(struct file *filp,
 			 unsigned int ioctl, unsigned long arg)
 {
@@ -712,8 +720,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		if (copy_from_user(&init, argp, sizeof(init)))
 			return -EFAULT;
 
-		return kvm_vcpu_set_target(vcpu, &init);
-
+		return kvm_arch_vcpu_ioctl_vcpu_init(vcpu, &init);
 	}
 	case KVM_SET_ONE_REG:
 	case KVM_GET_ONE_REG: {
@@ -828,7 +835,8 @@ static int hyp_init_cpu_notify(struct notifier_block *self,
 	switch (action) {
 	case CPU_STARTING:
 	case CPU_STARTING_FROZEN:
-		cpu_init_hyp_mode(NULL);
+		if (__hyp_get_vectors() == hyp_default_vectors)
+			cpu_init_hyp_mode(NULL);
 		break;
 	}
 
@@ -839,6 +847,34 @@ static struct notifier_block hyp_init_cpu_nb = {
 	.notifier_call = hyp_init_cpu_notify,
 };
 
+#ifdef CONFIG_CPU_PM
+static int hyp_init_cpu_pm_notifier(struct notifier_block *self,
+				    unsigned long cmd,
+				    void *v)
+{
+	if (cmd == CPU_PM_EXIT &&
+	    __hyp_get_vectors() == hyp_default_vectors) {
+		cpu_init_hyp_mode(NULL);
+		return NOTIFY_OK;
+	}
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block hyp_init_cpu_pm_nb = {
+	.notifier_call = hyp_init_cpu_pm_notifier,
+};
+
+static void __init hyp_cpu_pm_init(void)
+{
+	cpu_pm_register_notifier(&hyp_init_cpu_pm_nb);
+}
+#else
+static inline void hyp_cpu_pm_init(void)
+{
+}
+#endif
+
 /**
  * Inits Hyp-mode on all online CPUs
  */
@@ -999,6 +1035,8 @@ int kvm_arch_init(void *opaque)
 		goto out_err;
 	}
 
+	hyp_cpu_pm_init();
+
 	kvm_coproc_table_init();
 	return 0;
 out_err:
diff --git a/arch/arm/kvm/coproc.c b/arch/arm/kvm/coproc.c
index db9cf692d4dd..4dc9256d48a3 100644
--- a/arch/arm/kvm/coproc.c
+++ b/arch/arm/kvm/coproc.c
@@ -23,6 +23,7 @@
 #include <asm/kvm_host.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_coproc.h>
+#include <asm/kvm_mmu.h>
 #include <asm/cacheflush.h>
 #include <asm/cputype.h>
 #include <trace/events/kvm.h>
@@ -113,6 +114,44 @@ done:
 }
 
 /*
+ * Generic accessor for VM registers. Only called as long as HCR_TVM
+ * is set.
+ */
+static bool access_vm_reg(struct kvm_vcpu *vcpu,
+			  const struct coproc_params *p,
+			  const struct coproc_reg *r)
+{
+	BUG_ON(!p->is_write);
+
+	vcpu->arch.cp15[r->reg] = *vcpu_reg(vcpu, p->Rt1);
+	if (p->is_64bit)
+		vcpu->arch.cp15[r->reg + 1] = *vcpu_reg(vcpu, p->Rt2);
+
+	return true;
+}
+
+/*
+ * SCTLR accessor. Only called as long as HCR_TVM is set.  If the
+ * guest enables the MMU, we stop trapping the VM sys_regs and leave
+ * it in complete control of the caches.
+ *
+ * Used by the cpu-specific code.
+ */
+bool access_sctlr(struct kvm_vcpu *vcpu,
+		  const struct coproc_params *p,
+		  const struct coproc_reg *r)
+{
+	access_vm_reg(vcpu, p, r);
+
+	if (vcpu_has_cache_enabled(vcpu)) {	/* MMU+Caches enabled? */
+		vcpu->arch.hcr &= ~HCR_TVM;
+		stage2_flush_vm(vcpu->kvm);
+	}
+
+	return true;
+}
+
+/*
  * We could trap ID_DFR0 and tell the guest we don't support performance
  * monitoring.  Unfortunately the patch to make the kernel check ID_DFR0 was
  * NAKed, so it will read the PMCR anyway.
@@ -157,33 +196,35 @@ static const struct coproc_reg cp15_regs[] = {
 	{ CRn( 0), CRm( 0), Op1( 2), Op2( 0), is32,
 			NULL, reset_unknown, c0_CSSELR },
 
-	/* TTBR0/TTBR1: swapped by interrupt.S. */
-	{ CRm64( 2), Op1( 0), is64, NULL, reset_unknown64, c2_TTBR0 },
-	{ CRm64( 2), Op1( 1), is64, NULL, reset_unknown64, c2_TTBR1 },
-
-	/* TTBCR: swapped by interrupt.S. */
+	/* TTBR0/TTBR1/TTBCR: swapped by interrupt.S. */
+	{ CRm64( 2), Op1( 0), is64, access_vm_reg, reset_unknown64, c2_TTBR0 },
+	{ CRn(2), CRm( 0), Op1( 0), Op2( 0), is32,
+			access_vm_reg, reset_unknown, c2_TTBR0 },
+	{ CRn(2), CRm( 0), Op1( 0), Op2( 1), is32,
+			access_vm_reg, reset_unknown, c2_TTBR1 },
 	{ CRn( 2), CRm( 0), Op1( 0), Op2( 2), is32,
-			NULL, reset_val, c2_TTBCR, 0x00000000 },
+			access_vm_reg, reset_val, c2_TTBCR, 0x00000000 },
+	{ CRm64( 2), Op1( 1), is64, access_vm_reg, reset_unknown64, c2_TTBR1 },
 
 	/* DACR: swapped by interrupt.S. */
 	{ CRn( 3), CRm( 0), Op1( 0), Op2( 0), is32,
-			NULL, reset_unknown, c3_DACR },
+			access_vm_reg, reset_unknown, c3_DACR },
 
 	/* DFSR/IFSR/ADFSR/AIFSR: swapped by interrupt.S. */
 	{ CRn( 5), CRm( 0), Op1( 0), Op2( 0), is32,
-			NULL, reset_unknown, c5_DFSR },
+			access_vm_reg, reset_unknown, c5_DFSR },
 	{ CRn( 5), CRm( 0), Op1( 0), Op2( 1), is32,
-			NULL, reset_unknown, c5_IFSR },
+			access_vm_reg, reset_unknown, c5_IFSR },
 	{ CRn( 5), CRm( 1), Op1( 0), Op2( 0), is32,
-			NULL, reset_unknown, c5_ADFSR },
+			access_vm_reg, reset_unknown, c5_ADFSR },
 	{ CRn( 5), CRm( 1), Op1( 0), Op2( 1), is32,
-			NULL, reset_unknown, c5_AIFSR },
+			access_vm_reg, reset_unknown, c5_AIFSR },
 
 	/* DFAR/IFAR: swapped by interrupt.S. */
 	{ CRn( 6), CRm( 0), Op1( 0), Op2( 0), is32,
-			NULL, reset_unknown, c6_DFAR },
+			access_vm_reg, reset_unknown, c6_DFAR },
 	{ CRn( 6), CRm( 0), Op1( 0), Op2( 2), is32,
-			NULL, reset_unknown, c6_IFAR },
+			access_vm_reg, reset_unknown, c6_IFAR },
 
 	/* PAR swapped by interrupt.S */
 	{ CRm64( 7), Op1( 0), is64, NULL, reset_unknown64, c7_PAR },
@@ -213,9 +254,15 @@ static const struct coproc_reg cp15_regs[] = {
 
 	/* PRRR/NMRR (aka MAIR0/MAIR1): swapped by interrupt.S. */
 	{ CRn(10), CRm( 2), Op1( 0), Op2( 0), is32,
-			NULL, reset_unknown, c10_PRRR},
+			access_vm_reg, reset_unknown, c10_PRRR},
 	{ CRn(10), CRm( 2), Op1( 0), Op2( 1), is32,
-			NULL, reset_unknown, c10_NMRR},
+			access_vm_reg, reset_unknown, c10_NMRR},
+
+	/* AMAIR0/AMAIR1: swapped by interrupt.S. */
+	{ CRn(10), CRm( 3), Op1( 0), Op2( 0), is32,
+			access_vm_reg, reset_unknown, c10_AMAIR0},
+	{ CRn(10), CRm( 3), Op1( 0), Op2( 1), is32,
+			access_vm_reg, reset_unknown, c10_AMAIR1},
 
 	/* VBAR: swapped by interrupt.S. */
 	{ CRn(12), CRm( 0), Op1( 0), Op2( 0), is32,
@@ -223,7 +270,7 @@ static const struct coproc_reg cp15_regs[] = {
 
 	/* CONTEXTIDR/TPIDRURW/TPIDRURO/TPIDRPRW: swapped by interrupt.S. */
 	{ CRn(13), CRm( 0), Op1( 0), Op2( 1), is32,
-			NULL, reset_val, c13_CID, 0x00000000 },
+			access_vm_reg, reset_val, c13_CID, 0x00000000 },
 	{ CRn(13), CRm( 0), Op1( 0), Op2( 2), is32,
 			NULL, reset_unknown, c13_TID_URW },
 	{ CRn(13), CRm( 0), Op1( 0), Op2( 3), is32,
@@ -323,7 +370,7 @@ int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
 	struct coproc_params params;
 
-	params.CRm = (kvm_vcpu_get_hsr(vcpu) >> 1) & 0xf;
+	params.CRn = (kvm_vcpu_get_hsr(vcpu) >> 1) & 0xf;
 	params.Rt1 = (kvm_vcpu_get_hsr(vcpu) >> 5) & 0xf;
 	params.is_write = ((kvm_vcpu_get_hsr(vcpu) & 1) == 0);
 	params.is_64bit = true;
@@ -331,7 +378,7 @@ int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	params.Op1 = (kvm_vcpu_get_hsr(vcpu) >> 16) & 0xf;
 	params.Op2 = 0;
 	params.Rt2 = (kvm_vcpu_get_hsr(vcpu) >> 10) & 0xf;
-	params.CRn = 0;
+	params.CRm = 0;
 
 	return emulate_cp15(vcpu, &params);
 }
@@ -574,7 +621,7 @@ static bool is_valid_cache(u32 val)
 	u32 level, ctype;
 
 	if (val >= CSSELR_MAX)
-		return -ENOENT;
+		return false;
 
 	/* Bottom bit is Instruction or Data bit.  Next 3 bits are level. */
         level = (val >> 1);
diff --git a/arch/arm/kvm/coproc.h b/arch/arm/kvm/coproc.h
index 0461d5c8d3de..1a44bbe39643 100644
--- a/arch/arm/kvm/coproc.h
+++ b/arch/arm/kvm/coproc.h
@@ -58,8 +58,8 @@ static inline void print_cp_instr(const struct coproc_params *p)
 {
 	/* Look, we even formatted it for you to paste into the table! */
 	if (p->is_64bit) {
-		kvm_pr_unimpl(" { CRm(%2lu), Op1(%2lu), is64, func_%s },\n",
-			      p->CRm, p->Op1, p->is_write ? "write" : "read");
+		kvm_pr_unimpl(" { CRm64(%2lu), Op1(%2lu), is64, func_%s },\n",
+			      p->CRn, p->Op1, p->is_write ? "write" : "read");
 	} else {
 		kvm_pr_unimpl(" { CRn(%2lu), CRm(%2lu), Op1(%2lu), Op2(%2lu), is32,"
 			      " func_%s },\n",
@@ -135,13 +135,13 @@ static inline int cmp_reg(const struct coproc_reg *i1,
 		return -1;
 	if (i1->CRn != i2->CRn)
 		return i1->CRn - i2->CRn;
-	if (i1->is_64 != i2->is_64)
-		return i2->is_64 - i1->is_64;
 	if (i1->CRm != i2->CRm)
 		return i1->CRm - i2->CRm;
 	if (i1->Op1 != i2->Op1)
 		return i1->Op1 - i2->Op1;
-	return i1->Op2 - i2->Op2;
+	if (i1->Op2 != i2->Op2)
+		return i1->Op2 - i2->Op2;
+	return i2->is_64 - i1->is_64;
 }
 
 
@@ -153,4 +153,8 @@ static inline int cmp_reg(const struct coproc_reg *i1,
 #define is64		.is_64 = true
 #define is32		.is_64 = false
 
+bool access_sctlr(struct kvm_vcpu *vcpu,
+		  const struct coproc_params *p,
+		  const struct coproc_reg *r);
+
 #endif /* __ARM_KVM_COPROC_LOCAL_H__ */
diff --git a/arch/arm/kvm/coproc_a15.c b/arch/arm/kvm/coproc_a15.c
index cf93472b9dd6..e6ec43ab5c41 100644
--- a/arch/arm/kvm/coproc_a15.c
+++ b/arch/arm/kvm/coproc_a15.c
@@ -27,14 +27,13 @@
 static void reset_mpidr(struct kvm_vcpu *vcpu, const struct coproc_reg *r)
 {
 	/*
-	 * Compute guest MPIDR:
-	 * (Even if we present only one VCPU to the guest on an SMP
-	 * host we don't set the U bit in the MPIDR, or vice versa, as
-	 * revealing the underlying hardware properties is likely to
-	 * be the best choice).
+	 * Compute guest MPIDR. We build a virtual cluster out of the
+	 * vcpu_id, but we read the 'U' bit from the underlying
+	 * hardware directly.
 	 */
-	vcpu->arch.cp15[c0_MPIDR] = (read_cpuid_mpidr() & ~MPIDR_LEVEL_MASK)
-		| (vcpu->vcpu_id & MPIDR_LEVEL_MASK);
+	vcpu->arch.cp15[c0_MPIDR] = ((read_cpuid_mpidr() & MPIDR_SMP_BITMASK) |
+				   ((vcpu->vcpu_id >> 2) << MPIDR_LEVEL_BITS) |
+				   (vcpu->vcpu_id & 3));
 }
 
 #include "coproc.h"
@@ -80,6 +79,10 @@ static void reset_l2ctlr(struct kvm_vcpu *vcpu, const struct coproc_reg *r)
 	asm volatile("mrc p15, 1, %0, c9, c0, 2\n" : "=r" (l2ctlr));
 	l2ctlr &= ~(3 << 24);
 	ncores = atomic_read(&vcpu->kvm->online_vcpus) - 1;
+	/* How many cores in the current cluster and the next ones */
+	ncores -= (vcpu->vcpu_id & ~3);
+	/* Cap it to the maximum number of cores in a single cluster */
+	ncores = min(ncores, 3U);
 	l2ctlr |= (ncores & 3) << 24;
 
 	vcpu->arch.cp15[c9_L2CTLR] = l2ctlr;
@@ -127,7 +130,7 @@ static const struct coproc_reg a15_regs[] = {
 
 	/* SCTLR: swapped by interrupt.S. */
 	{ CRn( 1), CRm( 0), Op1( 0), Op2( 0), is32,
-			NULL, reset_val, c1_SCTLR, 0x00C50078 },
+			access_sctlr, reset_val, c1_SCTLR, 0x00C50078 },
 	/* ACTLR: trapped by HCR.TAC bit. */
 	{ CRn( 1), CRm( 0), Op1( 0), Op2( 1), is32,
 			access_actlr, reset_actlr, c1_ACTLR },
diff --git a/arch/arm/kvm/handle_exit.c b/arch/arm/kvm/handle_exit.c
index df4c82d47ad7..ec4fa868a7ba 100644
--- a/arch/arm/kvm/handle_exit.c
+++ b/arch/arm/kvm/handle_exit.c
@@ -26,8 +26,6 @@
 
 #include "trace.h"
 
-#include "trace.h"
-
 typedef int (*exit_handle_fn)(struct kvm_vcpu *, struct kvm_run *);
 
 static int handle_svc_hyp(struct kvm_vcpu *vcpu, struct kvm_run *run)
@@ -73,23 +71,31 @@ static int handle_dabt_hyp(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 WFI or WFE instructions trapped in guests
  * @vcpu:	the vcpu pointer
  * @run:	the kvm_run structure pointer
  *
- * Simply sets the wait_for_interrupts flag on the vcpu structure, which will
- * halt execution of world-switches and schedule other host processes until
- * there is an incoming IRQ or FIQ to the VM.
+ * 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)
 {
 	trace_kvm_wfi(*vcpu_pc(vcpu));
-	kvm_vcpu_block(vcpu);
+	if (kvm_vcpu_get_hsr(vcpu) & HSR_WFI_IS_WFE)
+		kvm_vcpu_on_spin(vcpu);
+	else
+		kvm_vcpu_block(vcpu);
+
+	kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
+
 	return 1;
 }
 
 static exit_handle_fn arm_exit_handlers[] = {
-	[HSR_EC_WFI]		= kvm_handle_wfi,
+	[HSR_EC_WFI]		= kvm_handle_wfx,
 	[HSR_EC_CP15_32]	= kvm_handle_cp15_32,
 	[HSR_EC_CP15_64]	= kvm_handle_cp15_64,
 	[HSR_EC_CP14_MR]	= kvm_handle_cp14_access,
diff --git a/arch/arm/kvm/init.S b/arch/arm/kvm/init.S
index 1b9844d369cc..ee4f7447a1d3 100644
--- a/arch/arm/kvm/init.S
+++ b/arch/arm/kvm/init.S
@@ -98,6 +98,10 @@ __do_hyp_init:
 	mrc	p15, 0, r0, c10, c2, 1
 	mcr	p15, 4, r0, c10, c2, 1
 
+	@ Invalidate the stale TLBs from Bootloader
+	mcr	p15, 4, r0, c8, c7, 0	@ TLBIALLH
+	dsb	ish
+
 	@ Set the HSCTLR to:
 	@  - ARM/THUMB exceptions: Kernel config (Thumb-2 kernel)
 	@  - Endianness: Kernel config
diff --git a/arch/arm/kvm/interrupts.S b/arch/arm/kvm/interrupts.S
index ddc15539bad2..0d68d4073068 100644
--- a/arch/arm/kvm/interrupts.S
+++ b/arch/arm/kvm/interrupts.S
@@ -220,6 +220,10 @@ after_vfp_restore:
  * in Hyp mode (see init_hyp_mode in arch/arm/kvm/arm.c).  Return values are
  * passed in r0 and r1.
  *
+ * A function pointer with a value of 0xffffffff has a special meaning,
+ * and is used to implement __hyp_get_vectors in the same way as in
+ * arch/arm/kernel/hyp_stub.S.
+ *
  * The calling convention follows the standard AAPCS:
  *   r0 - r3: caller save
  *   r12:     caller save
@@ -363,6 +367,11 @@ hyp_hvc:
 host_switch_to_hyp:
 	pop	{r0, r1, r2}
 
+	/* Check for __hyp_get_vectors */
+	cmp	r0, #-1
+	mrceq	p15, 4, r0, c12, c0, 0	@ get HVBAR
+	beq	1f
+
 	push	{lr}
 	mrs	lr, SPSR
 	push	{lr}
@@ -378,7 +387,7 @@ THUMB(	orr	lr, #1)
 	pop	{lr}
 	msr	SPSR_csxf, lr
 	pop	{lr}
-	eret
+1:	eret
 
 guest_trap:
 	load_vcpu			@ Load VCPU pointer to r0
diff --git a/arch/arm/kvm/interrupts_head.S b/arch/arm/kvm/interrupts_head.S
index 6f18695a09cb..76af93025574 100644
--- a/arch/arm/kvm/interrupts_head.S
+++ b/arch/arm/kvm/interrupts_head.S
@@ -303,13 +303,17 @@ vcpu	.req	r0		@ vcpu pointer always in r0
 
 	mrc	p15, 0, r2, c14, c1, 0	@ CNTKCTL
 	mrrc	p15, 0, r4, r5, c7	@ PAR
+	mrc	p15, 0, r6, c10, c3, 0	@ AMAIR0
+	mrc	p15, 0, r7, c10, c3, 1	@ AMAIR1
 
 	.if \store_to_vcpu == 0
-	push	{r2,r4-r5}
+	push	{r2,r4-r7}
 	.else
 	str	r2, [vcpu, #CP15_OFFSET(c14_CNTKCTL)]
 	add	r12, vcpu, #CP15_OFFSET(c7_PAR)
 	strd	r4, r5, [r12]
+	str	r6, [vcpu, #CP15_OFFSET(c10_AMAIR0)]
+	str	r7, [vcpu, #CP15_OFFSET(c10_AMAIR1)]
 	.endif
 .endm
 
@@ -322,15 +326,19 @@ vcpu	.req	r0		@ vcpu pointer always in r0
  */
 .macro write_cp15_state read_from_vcpu
 	.if \read_from_vcpu == 0
-	pop	{r2,r4-r5}
+	pop	{r2,r4-r7}
 	.else
 	ldr	r2, [vcpu, #CP15_OFFSET(c14_CNTKCTL)]
 	add	r12, vcpu, #CP15_OFFSET(c7_PAR)
 	ldrd	r4, r5, [r12]
+	ldr	r6, [vcpu, #CP15_OFFSET(c10_AMAIR0)]
+	ldr	r7, [vcpu, #CP15_OFFSET(c10_AMAIR1)]
 	.endif
 
 	mcr	p15, 0, r2, c14, c1, 0	@ CNTKCTL
 	mcrr	p15, 0, r4, r5, c7	@ PAR
+	mcr	p15, 0, r6, c10, c3, 0	@ AMAIR0
+	mcr	p15, 0, r7, c10, c3, 1	@ AMAIR1
 
 	.if \read_from_vcpu == 0
 	pop	{r2-r12}
@@ -597,17 +605,14 @@ vcpu	.req	r0		@ vcpu pointer always in r0
 
 /* Enable/Disable: stage-2 trans., trap interrupts, trap wfi, trap smc */
 .macro configure_hyp_role operation
-	mrc	p15, 4, r2, c1, c1, 0	@ HCR
-	bic	r2, r2, #HCR_VIRT_EXCP_MASK
-	ldr	r3, =HCR_GUEST_MASK
 	.if \operation == vmentry
-	orr	r2, r2, r3
+	ldr	r2, [vcpu, #VCPU_HCR]
 	ldr	r3, [vcpu, #VCPU_IRQ_LINES]
 	orr	r2, r2, r3
 	.else
-	bic	r2, r2, r3
+	mov	r2, #0
 	.endif
-	mcr	p15, 4, r2, c1, c1, 0
+	mcr	p15, 4, r2, c1, c1, 0	@ HCR
 .endm
 
 .macro load_vcpu
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index fe59e4a19022..87a2769898ac 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -87,10 +87,13 @@ static void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc)
 	return p;
 }
 
-static bool page_empty(void *ptr)
+static void clear_pgd_entry(struct kvm *kvm, pgd_t *pgd, phys_addr_t addr)
 {
-	struct page *ptr_page = virt_to_page(ptr);
-	return page_count(ptr_page) == 1;
+	pud_t *pud_table __maybe_unused = pud_offset(pgd, 0);
+	pgd_clear(pgd);
+	kvm_tlb_flush_vmid_ipa(kvm, addr);
+	pud_free(NULL, pud_table);
+	put_page(virt_to_page(pgd));
 }
 
 static void clear_pud_entry(struct kvm *kvm, pud_t *pud, phys_addr_t addr)
@@ -111,55 +114,157 @@ static void clear_pmd_entry(struct kvm *kvm, pmd_t *pmd, phys_addr_t addr)
 	put_page(virt_to_page(pmd));
 }
 
-static void clear_pte_entry(struct kvm *kvm, pte_t *pte, phys_addr_t addr)
+static void unmap_ptes(struct kvm *kvm, pmd_t *pmd,
+		      phys_addr_t addr, phys_addr_t end)
 {
-	if (pte_present(*pte)) {
-		kvm_set_pte(pte, __pte(0));
-		put_page(virt_to_page(pte));
-		kvm_tlb_flush_vmid_ipa(kvm, addr);
-	}
+	phys_addr_t start_addr = addr;
+	pte_t *pte, *start_pte;
+
+	start_pte = pte = pte_offset_kernel(pmd, addr);
+	do {
+		if (!pte_none(*pte)) {
+			kvm_set_pte(pte, __pte(0));
+			put_page(virt_to_page(pte));
+			kvm_tlb_flush_vmid_ipa(kvm, addr);
+		}
+	} while (pte++, addr += PAGE_SIZE, addr != end);
+
+	if (kvm_pte_table_empty(start_pte))
+		clear_pmd_entry(kvm, pmd, start_addr);
+}
+
+static void unmap_pmds(struct kvm *kvm, pud_t *pud,
+		      phys_addr_t addr, phys_addr_t end)
+{
+	phys_addr_t next, start_addr = addr;
+	pmd_t *pmd, *start_pmd;
+
+	start_pmd = pmd = pmd_offset(pud, addr);
+	do {
+		next = kvm_pmd_addr_end(addr, end);
+		if (!pmd_none(*pmd)) {
+			unmap_ptes(kvm, pmd, addr, next);
+		}
+	} while (pmd++, addr = next, addr != end);
+
+	if (kvm_pmd_table_empty(start_pmd))
+		clear_pud_entry(kvm, pud, start_addr);
+}
+
+static void unmap_puds(struct kvm *kvm, pgd_t *pgd,
+		      phys_addr_t addr, phys_addr_t end)
+{
+	phys_addr_t next, start_addr = addr;
+	pud_t *pud, *start_pud;
+
+	start_pud = pud = pud_offset(pgd, addr);
+	do {
+		next = kvm_pud_addr_end(addr, end);
+		if (!pud_none(*pud)) {
+			unmap_pmds(kvm, pud, addr, next);
+		}
+	} while (pud++, addr = next, addr != end);
+
+	if (kvm_pud_table_empty(start_pud))
+		clear_pgd_entry(kvm, pgd, start_addr);
 }
 
+
 static void unmap_range(struct kvm *kvm, pgd_t *pgdp,
-			unsigned long long start, u64 size)
+		       phys_addr_t start, u64 size)
 {
 	pgd_t *pgd;
-	pud_t *pud;
-	pmd_t *pmd;
+	phys_addr_t addr = start, end = start + size;
+	phys_addr_t next;
+
+	pgd = pgdp + kvm_pgd_index(addr);
+	do {
+		next = kvm_pgd_addr_end(addr, end);
+		unmap_puds(kvm, pgd, addr, next);
+	} while (pgd++, addr = next, addr != end);
+}
+
+static void stage2_flush_ptes(struct kvm *kvm, pmd_t *pmd,
+			      phys_addr_t addr, phys_addr_t end)
+{
 	pte_t *pte;
-	unsigned long long addr = start, end = start + size;
-	u64 next;
 
-	while (addr < end) {
-		pgd = pgdp + pgd_index(addr);
-		pud = pud_offset(pgd, addr);
-		if (pud_none(*pud)) {
-			addr = pud_addr_end(addr, end);
-			continue;
+	pte = pte_offset_kernel(pmd, addr);
+	do {
+		if (!pte_none(*pte)) {
+			hva_t hva = gfn_to_hva(kvm, addr >> PAGE_SHIFT);
+			kvm_flush_dcache_to_poc((void*)hva, PAGE_SIZE);
 		}
+	} while (pte++, addr += PAGE_SIZE, addr != end);
+}
 
-		pmd = pmd_offset(pud, addr);
-		if (pmd_none(*pmd)) {
-			addr = pmd_addr_end(addr, end);
-			continue;
+static void stage2_flush_pmds(struct kvm *kvm, pud_t *pud,
+			      phys_addr_t addr, phys_addr_t end)
+{
+	pmd_t *pmd;
+	phys_addr_t next;
+
+	pmd = pmd_offset(pud, addr);
+	do {
+		next = kvm_pmd_addr_end(addr, end);
+		if (!pmd_none(*pmd)) {
+			stage2_flush_ptes(kvm, pmd, addr, next);
 		}
+	} while (pmd++, addr = next, addr != end);
+}
 
-		pte = pte_offset_kernel(pmd, addr);
-		clear_pte_entry(kvm, pte, addr);
-		next = addr + PAGE_SIZE;
-
-		/* If we emptied the pte, walk back up the ladder */
-		if (page_empty(pte)) {
-			clear_pmd_entry(kvm, pmd, addr);
-			next = pmd_addr_end(addr, end);
-			if (page_empty(pmd) && !page_empty(pud)) {
-				clear_pud_entry(kvm, pud, addr);
-				next = pud_addr_end(addr, end);
-			}
+static void stage2_flush_puds(struct kvm *kvm, pgd_t *pgd,
+			      phys_addr_t addr, phys_addr_t end)
+{
+	pud_t *pud;
+	phys_addr_t next;
+
+	pud = pud_offset(pgd, addr);
+	do {
+		next = kvm_pud_addr_end(addr, end);
+		if (!pud_none(*pud)) {
+			stage2_flush_pmds(kvm, pud, addr, next);
 		}
+	} while (pud++, addr = next, addr != end);
+}
 
-		addr = next;
-	}
+static void stage2_flush_memslot(struct kvm *kvm,
+				 struct kvm_memory_slot *memslot)
+{
+	phys_addr_t addr = memslot->base_gfn << PAGE_SHIFT;
+	phys_addr_t end = addr + PAGE_SIZE * memslot->npages;
+	phys_addr_t next;
+	pgd_t *pgd;
+
+	pgd = kvm->arch.pgd + kvm_pgd_index(addr);
+	do {
+		next = kvm_pgd_addr_end(addr, end);
+		stage2_flush_puds(kvm, pgd, addr, next);
+	} while (pgd++, addr = next, addr != end);
+}
+
+/**
+ * stage2_flush_vm - Invalidate cache for pages mapped in stage 2
+ * @kvm: The struct kvm pointer
+ *
+ * Go through the stage 2 page tables and invalidate any cache lines
+ * backing memory already mapped to the VM.
+ */
+void stage2_flush_vm(struct kvm *kvm)
+{
+	struct kvm_memslots *slots;
+	struct kvm_memory_slot *memslot;
+	int idx;
+
+	idx = srcu_read_lock(&kvm->srcu);
+	spin_lock(&kvm->mmu_lock);
+
+	slots = kvm_memslots(kvm);
+	kvm_for_each_memslot(memslot, slots)
+		stage2_flush_memslot(kvm, memslot);
+
+	spin_unlock(&kvm->mmu_lock);
+	srcu_read_unlock(&kvm->srcu, idx);
 }
 
 /**
@@ -423,6 +528,71 @@ static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size)
 	unmap_range(kvm, kvm->arch.pgd, start, size);
 }
 
+static void stage2_unmap_memslot(struct kvm *kvm,
+				 struct kvm_memory_slot *memslot)
+{
+	hva_t hva = memslot->userspace_addr;
+	phys_addr_t addr = memslot->base_gfn << PAGE_SHIFT;
+	phys_addr_t size = PAGE_SIZE * memslot->npages;
+	hva_t reg_end = hva + size;
+
+	/*
+	 * A memory region could potentially cover multiple VMAs, and any holes
+	 * between them, so iterate over all of them to find out if we should
+	 * unmap any of them.
+	 *
+	 *     +--------------------------------------------+
+	 * +---------------+----------------+   +----------------+
+	 * |   : VMA 1     |      VMA 2     |   |    VMA 3  :    |
+	 * +---------------+----------------+   +----------------+
+	 *     |               memory region                |
+	 *     +--------------------------------------------+
+	 */
+	do {
+		struct vm_area_struct *vma = find_vma(current->mm, hva);
+		hva_t vm_start, vm_end;
+
+		if (!vma || vma->vm_start >= reg_end)
+			break;
+
+		/*
+		 * Take the intersection of this VMA with the memory region
+		 */
+		vm_start = max(hva, vma->vm_start);
+		vm_end = min(reg_end, vma->vm_end);
+
+		if (!(vma->vm_flags & VM_PFNMAP)) {
+			gpa_t gpa = addr + (vm_start - memslot->userspace_addr);
+			unmap_stage2_range(kvm, gpa, vm_end - vm_start);
+		}
+		hva = vm_end;
+	} while (hva < reg_end);
+}
+
+/**
+ * stage2_unmap_vm - Unmap Stage-2 RAM mappings
+ * @kvm: The struct kvm pointer
+ *
+ * Go through the memregions and unmap any reguler RAM
+ * backing memory already mapped to the VM.
+ */
+void stage2_unmap_vm(struct kvm *kvm)
+{
+	struct kvm_memslots *slots;
+	struct kvm_memory_slot *memslot;
+	int idx;
+
+	idx = srcu_read_lock(&kvm->srcu);
+	spin_lock(&kvm->mmu_lock);
+
+	slots = kvm_memslots(kvm);
+	kvm_for_each_memslot(memslot, slots)
+		stage2_unmap_memslot(kvm, memslot);
+
+	spin_unlock(&kvm->mmu_lock);
+	srcu_read_unlock(&kvm->srcu, idx);
+}
+
 /**
  * kvm_free_stage2_pgd - free all stage-2 tables
  * @kvm:	The KVM struct pointer for the VM.
@@ -454,7 +624,7 @@ static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
 	pte_t *pte, old_pte;
 
 	/* Create 2nd stage page table mapping - Level 1 */
-	pgd = kvm->arch.pgd + pgd_index(addr);
+	pgd = kvm->arch.pgd + kvm_pgd_index(addr);
 	pud = pud_offset(pgd, addr);
 	if (pud_none(*pud)) {
 		if (!cache)
@@ -531,6 +701,19 @@ out:
 	return ret;
 }
 
+static bool kvm_is_write_fault(struct kvm_vcpu *vcpu)
+{
+	if (kvm_vcpu_trap_is_iabt(vcpu))
+		return false;
+
+	return kvm_vcpu_dabt_iswrite(vcpu);
+}
+
+static bool kvm_is_device_pfn(unsigned long pfn)
+{
+	return !pfn_valid(pfn);
+}
+
 static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 			  gfn_t gfn, struct kvm_memory_slot *memslot,
 			  unsigned long fault_status)
@@ -540,9 +723,11 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	int ret;
 	bool write_fault, writable;
 	unsigned long mmu_seq;
+	unsigned long hva = gfn_to_hva(vcpu->kvm, gfn);
 	struct kvm_mmu_memory_cache *memcache = &vcpu->arch.mmu_page_cache;
+	pgprot_t mem_type = PAGE_S2;
 
-	write_fault = kvm_is_write_fault(kvm_vcpu_get_hsr(vcpu));
+	write_fault = kvm_is_write_fault(vcpu);
 	if (fault_status == FSC_PERM && !write_fault) {
 		kvm_err("Unexpected L2 read permission error\n");
 		return -EFAULT;
@@ -569,8 +754,11 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	if (is_error_pfn(pfn))
 		return -EFAULT;
 
-	new_pte = pfn_pte(pfn, PAGE_S2);
-	coherent_icache_guest_page(vcpu->kvm, gfn);
+	if (kvm_is_device_pfn(pfn))
+		mem_type = PAGE_S2_DEVICE;
+
+	new_pte = pfn_pte(pfn, mem_type);
+	coherent_cache_guest_page(vcpu, hva, PAGE_SIZE);
 
 	spin_lock(&vcpu->kvm->mmu_lock);
 	if (mmu_notifier_retry(vcpu->kvm, mmu_seq))
@@ -579,7 +767,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		kvm_set_s2pte_writable(&new_pte);
 		kvm_set_pfn_dirty(pfn);
 	}
-	stage2_set_pte(vcpu->kvm, memcache, fault_ipa, &new_pte, false);
+	stage2_set_pte(vcpu->kvm, memcache, fault_ipa, &new_pte,
+		pgprot_val(mem_type) == pgprot_val(PAGE_S2_DEVICE));
 
 out_unlock:
 	spin_unlock(&vcpu->kvm->mmu_lock);
@@ -653,6 +842,9 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run)
 
 	memslot = gfn_to_memslot(vcpu->kvm, gfn);
 
+	/* Userspace should not be able to register out-of-bounds IPAs */
+	VM_BUG_ON(fault_ipa >= KVM_PHYS_SIZE);
+
 	ret = user_mem_abort(vcpu, fault_ipa, gfn, memslot, fault_status);
 	if (ret == 0)
 		ret = 1;
@@ -857,3 +1049,56 @@ out:
 	free_hyp_pgds();
 	return err;
 }
+
+void kvm_arch_commit_memory_region(struct kvm *kvm,
+				   struct kvm_userspace_memory_region *mem,
+				   const struct kvm_memory_slot *old,
+				   enum kvm_mr_change change)
+{
+	gpa_t gpa = old->base_gfn << PAGE_SHIFT;
+	phys_addr_t size = old->npages << PAGE_SHIFT;
+	if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) {
+		spin_lock(&kvm->mmu_lock);
+		unmap_stage2_range(kvm, gpa, size);
+		spin_unlock(&kvm->mmu_lock);
+	}
+}
+
+int kvm_arch_prepare_memory_region(struct kvm *kvm,
+				   struct kvm_memory_slot *memslot,
+				   struct kvm_userspace_memory_region *mem,
+				   enum kvm_mr_change change)
+{
+	/*
+	 * Prevent userspace from creating a memory region outside of the IPA
+	 * space addressable by the KVM guest IPA space.
+	 */
+	if (memslot->base_gfn + memslot->npages >=
+	    (KVM_PHYS_SIZE >> PAGE_SHIFT))
+		return -EFAULT;
+
+	return 0;
+}
+
+void kvm_arch_free_memslot(struct kvm_memory_slot *free,
+			   struct kvm_memory_slot *dont)
+{
+}
+
+int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
+{
+	return 0;
+}
+
+void kvm_arch_memslots_updated(struct kvm *kvm)
+{
+}
+
+void kvm_arch_flush_shadow_all(struct kvm *kvm)
+{
+}
+
+void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
+				   struct kvm_memory_slot *slot)
+{
+}
diff --git a/arch/arm/kvm/psci.c b/arch/arm/kvm/psci.c
index 86a693a02ba3..485387bc1826 100644
--- a/arch/arm/kvm/psci.c
+++ b/arch/arm/kvm/psci.c
@@ -18,6 +18,7 @@
 #include <linux/kvm_host.h>
 #include <linux/wait.h>
 
+#include <asm/cputype.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_psci.h>
 
@@ -34,26 +35,35 @@ static void kvm_psci_vcpu_off(struct kvm_vcpu *vcpu)
 static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
 {
 	struct kvm *kvm = source_vcpu->kvm;
-	struct kvm_vcpu *vcpu;
+	struct kvm_vcpu *vcpu = NULL, *tmp;
 	wait_queue_head_t *wq;
 	unsigned long cpu_id;
+	unsigned long mpidr;
 	phys_addr_t target_pc;
+	int i;
 
 	cpu_id = *vcpu_reg(source_vcpu, 1);
 	if (vcpu_mode_is_32bit(source_vcpu))
 		cpu_id &= ~((u32) 0);
 
-	if (cpu_id >= atomic_read(&kvm->online_vcpus))
+	kvm_for_each_vcpu(i, tmp, kvm) {
+		mpidr = kvm_vcpu_get_mpidr(tmp);
+		if ((mpidr & MPIDR_HWID_BITMASK)
+		     == (cpu_id & MPIDR_HWID_BITMASK)) {
+			vcpu = tmp;
+			break;
+		}
+	}
+
+	/*
+	 * Make sure the caller requested a valid CPU and that the CPU is
+	 * turned off.
+	 */
+	if (!vcpu || !vcpu->arch.pause)
 		return KVM_PSCI_RET_INVAL;
 
 	target_pc = *vcpu_reg(source_vcpu, 2);
 
-	vcpu = kvm_get_vcpu(kvm, cpu_id);
-
-	wq = kvm_arch_vcpu_wq(vcpu);
-	if (!waitqueue_active(wq))
-		return KVM_PSCI_RET_INVAL;
-
 	kvm_reset_vcpu(vcpu);
 
 	/* Gracefully handle Thumb2 entry point */
@@ -66,6 +76,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
 	vcpu->arch.pause = false;
 	smp_mb();		/* Make sure the above is visible */
 
+	wq = kvm_arch_vcpu_wq(vcpu);
 	wake_up_interruptible(wq);
 
 	return KVM_PSCI_RET_SUCCESS;
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index a5f28e2720c7..370300438558 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -18,6 +18,7 @@
 #ifndef __ARM64_KVM_ARM_H__
 #define __ARM64_KVM_ARM_H__
 
+#include <asm/memory.h>
 #include <asm/types.h>
 
 /* Hyp Configuration Register (HCR) bits */
@@ -62,7 +63,9 @@
  * RW:		64bit by default, can be overriden for 32bit VMs
  * TAC:		Trap ACTLR
  * TSC:		Trap SMC
+ * TVM:		Trap VM ops (until M+C set in SCTLR_EL1)
  * 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 +75,9 @@
  * 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_TVM | 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)
 
@@ -119,6 +123,17 @@
 #define VTCR_EL2_T0SZ_MASK	0x3f
 #define VTCR_EL2_T0SZ_40B	24
 
+/*
+ * We configure the Stage-2 page tables to always restrict the IPA space to be
+ * 40 bits wide (T0SZ = 24).  Systems with a PARange smaller than 40 bits are
+ * not known to exist and will break with this configuration.
+ *
+ * Note that when using 4K pages, we concatenate two first level page tables
+ * together.
+ *
+ * The magic numbers used for VTTBR_X in this patch can be found in Tables
+ * D4-23 and D4-25 in ARM DDI 0487A.b.
+ */
 #ifdef CONFIG_ARM64_64K_PAGES
 /*
  * Stage2 translation configuration:
@@ -148,9 +163,9 @@
 #endif
 
 #define VTTBR_BADDR_SHIFT (VTTBR_X - 1)
-#define VTTBR_BADDR_MASK  (((1LLU << (40 - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT)
-#define VTTBR_VMID_SHIFT  (48LLU)
-#define VTTBR_VMID_MASK	  (0xffLLU << VTTBR_VMID_SHIFT)
+#define VTTBR_BADDR_MASK  (((UL(1) << (PHYS_MASK_SHIFT - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT)
+#define VTTBR_VMID_SHIFT  (UL(48))
+#define VTTBR_VMID_MASK	  (UL(0xFF) << VTTBR_VMID_SHIFT)
 
 /* Hyp System Trap Register */
 #define HSTR_EL2_TTEE	(1 << 16)
@@ -173,13 +188,13 @@
 
 /* Exception Syndrome Register (ESR) bits */
 #define ESR_EL2_EC_SHIFT	(26)
-#define ESR_EL2_EC		(0x3fU << ESR_EL2_EC_SHIFT)
-#define ESR_EL2_IL		(1U << 25)
+#define ESR_EL2_EC		(UL(0x3f) << ESR_EL2_EC_SHIFT)
+#define ESR_EL2_IL		(UL(1) << 25)
 #define ESR_EL2_ISS		(ESR_EL2_IL - 1)
 #define ESR_EL2_ISV_SHIFT	(24)
-#define ESR_EL2_ISV		(1U << ESR_EL2_ISV_SHIFT)
+#define ESR_EL2_ISV		(UL(1) << ESR_EL2_ISV_SHIFT)
 #define ESR_EL2_SAS_SHIFT	(22)
-#define ESR_EL2_SAS		(3U << ESR_EL2_SAS_SHIFT)
+#define ESR_EL2_SAS		(UL(3) << ESR_EL2_SAS_SHIFT)
 #define ESR_EL2_SSE		(1 << 21)
 #define ESR_EL2_SRT_SHIFT	(16)
 #define ESR_EL2_SRT_MASK	(0x1f << ESR_EL2_SRT_SHIFT)
@@ -193,16 +208,16 @@
 #define ESR_EL2_FSC_TYPE	(0x3c)
 
 #define ESR_EL2_CV_SHIFT	(24)
-#define ESR_EL2_CV		(1U << ESR_EL2_CV_SHIFT)
+#define ESR_EL2_CV		(UL(1) << ESR_EL2_CV_SHIFT)
 #define ESR_EL2_COND_SHIFT	(20)
-#define ESR_EL2_COND		(0xfU << ESR_EL2_COND_SHIFT)
+#define ESR_EL2_COND		(UL(0xf) << ESR_EL2_COND_SHIFT)
 
 
 #define FSC_FAULT	(0x04)
 #define FSC_PERM	(0x0c)
 
 /* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */
-#define HPFAR_MASK	(~0xFUL)
+#define HPFAR_MASK	(~UL(0xf))
 
 #define ESR_EL2_EC_UNKNOWN	(0x00)
 #define ESR_EL2_EC_WFI		(0x01)
@@ -242,4 +257,6 @@
 
 #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_asm.h b/arch/arm64/include/asm/kvm_asm.h
index b25763bc0ec4..9fcd54b1e16d 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -79,7 +79,8 @@
 #define c13_TID_URW	(TPIDR_EL0 * 2)	/* Thread ID, User R/W */
 #define c13_TID_URO	(TPIDRRO_EL0 * 2)/* Thread ID, User R/O */
 #define c13_TID_PRIV	(TPIDR_EL1 * 2)	/* Thread ID, Privileged */
-#define c10_AMAIR	(AMAIR_EL1 * 2)	/* Aux Memory Attr Indirection Reg */
+#define c10_AMAIR0	(AMAIR_EL1 * 2)	/* Aux Memory Attr Indirection Reg */
+#define c10_AMAIR1	(c10_AMAIR0 + 1)/* Aux Memory Attr Indirection Reg */
 #define c14_CNTKCTL	(CNTKCTL_EL1 * 2) /* Timer Control Register (PL1) */
 #define NR_CP15_REGS	(NR_SYS_REGS * 2)
 
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index eec073875218..2b01e2bdb7ef 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -38,6 +38,13 @@ void kvm_inject_undefined(struct kvm_vcpu *vcpu);
 void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr);
 void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr);
 
+static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.hcr_el2 = HCR_GUEST_FLAGS;
+	if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features))
+		vcpu->arch.hcr_el2 &= ~HCR_RW;
+}
+
 static inline unsigned long *vcpu_pc(const struct kvm_vcpu *vcpu)
 {
 	return (unsigned long *)&vcpu_gp_regs(vcpu)->regs.pc;
@@ -177,4 +184,9 @@ static inline u8 kvm_vcpu_trap_get_fault(const struct kvm_vcpu *vcpu)
 	return kvm_vcpu_get_hsr(vcpu) & ESR_EL2_FSC_TYPE;
 }
 
+static inline unsigned long kvm_vcpu_get_mpidr(struct kvm_vcpu *vcpu)
+{
+	return vcpu_sys_reg(vcpu, MPIDR_EL1);
+}
+
 #endif /* __ARM64_KVM_EMULATE_H__ */
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 0859a4ddd1e7..ca18e3faedd7 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -42,7 +42,7 @@
 #define KVM_PAGES_PER_HPAGE(x)	(1UL<<31)
 
 struct kvm_vcpu;
-int kvm_target_cpu(void);
+int __attribute_const__ kvm_target_cpu(void);
 int kvm_reset_vcpu(struct kvm_vcpu *vcpu);
 int kvm_arch_dev_ioctl_check_extension(long ext);
 
@@ -176,7 +176,7 @@ static inline int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
 }
 
 struct kvm_vcpu *kvm_arm_get_running_vcpu(void);
-struct kvm_vcpu __percpu **kvm_get_running_vcpus(void);
+struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void);
 
 u64 kvm_call_hyp(void *hypfn, ...);
 
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index efe609c6a3c9..0c661b823576 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -59,10 +59,9 @@
 #define KERN_TO_HYP(kva)	((unsigned long)kva - PAGE_OFFSET + HYP_PAGE_OFFSET)
 
 /*
- * Align KVM with the kernel's view of physical memory. Should be
- * 40bit IPA, with PGD being 8kB aligned in the 4KB page configuration.
+ * We currently only support a 40bit IPA.
  */
-#define KVM_PHYS_SHIFT	PHYS_MASK_SHIFT
+#define KVM_PHYS_SHIFT	(40)
 #define KVM_PHYS_SIZE	(1UL << KVM_PHYS_SHIFT)
 #define KVM_PHYS_MASK	(KVM_PHYS_SIZE - 1UL)
 
@@ -75,6 +74,7 @@ int create_hyp_io_mappings(void *from, void *to, phys_addr_t);
 void free_boot_hyp_pgd(void);
 void free_hyp_pgds(void);
 
+void stage2_unmap_vm(struct kvm *kvm);
 int kvm_alloc_stage2_pgd(struct kvm *kvm);
 void kvm_free_stage2_pgd(struct kvm *kvm);
 int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
@@ -92,20 +92,6 @@ void kvm_clear_hyp_idmap(void);
 
 #define	kvm_set_pte(ptep, pte)		set_pte(ptep, pte)
 
-static inline bool kvm_is_write_fault(unsigned long esr)
-{
-	unsigned long esr_ec = esr >> ESR_EL2_EC_SHIFT;
-
-	if (esr_ec == ESR_EL2_EC_IABT)
-		return false;
-
-	if ((esr & ESR_EL2_ISV) && !(esr & ESR_EL2_WNR))
-		return false;
-
-	return true;
-}
-
-static inline void kvm_clean_dcache_area(void *addr, size_t size) {}
 static inline void kvm_clean_pgd(pgd_t *pgd) {}
 static inline void kvm_clean_pmd_entry(pmd_t *pmd) {}
 static inline void kvm_clean_pte(pte_t *pte) {}
@@ -116,20 +102,50 @@ static inline void kvm_set_s2pte_writable(pte_t *pte)
 	pte_val(*pte) |= PTE_S2_RDWR;
 }
 
+#define kvm_pgd_addr_end(addr, end)    pgd_addr_end(addr, end)
+#define kvm_pud_addr_end(addr, end)    pud_addr_end(addr, end)
+#define kvm_pmd_addr_end(addr, end)    pmd_addr_end(addr, end)
+
+#define kvm_pgd_index(addr)    (((addr) >> PGDIR_SHIFT) & (PTRS_PER_S2_PGD - 1))
+
+static inline bool kvm_page_empty(void *ptr)
+{
+	struct page *ptr_page = virt_to_page(ptr);
+	return page_count(ptr_page) == 1;
+}
+
+#define kvm_pte_table_empty(ptep) kvm_page_empty(ptep)
+#ifndef CONFIG_ARM64_64K_PAGES
+#define kvm_pmd_table_empty(pmdp) kvm_page_empty(pmdp)
+#else
+#define kvm_pmd_table_empty(pmdp) (0)
+#endif
+#define kvm_pud_table_empty(pudp) (0)
+
 struct kvm;
 
-static inline void coherent_icache_guest_page(struct kvm *kvm, gfn_t gfn)
+#define kvm_flush_dcache_to_poc(a,l)   __flush_dcache_area((a), (l))
+
+static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu)
 {
+	return (vcpu_sys_reg(vcpu, SCTLR_EL1) & 0b101) == 0b101;
+}
+
+static inline void coherent_cache_guest_page(struct kvm_vcpu *vcpu, hva_t hva,
+					    unsigned long size)
+{
+	if (!vcpu_has_cache_enabled(vcpu))
+		kvm_flush_dcache_to_poc((void *)hva, size);
+
 	if (!icache_is_aliasing()) {		/* PIPT */
-		unsigned long hva = gfn_to_hva(kvm, gfn);
-		flush_icache_range(hva, hva + PAGE_SIZE);
+		flush_icache_range(hva, hva + size);
 	} else if (!icache_is_aivivt()) {	/* non ASID-tagged VIVT */
 		/* any kind of VIPT cache */
 		__flush_icache_all();
 	}
 }
 
-#define kvm_flush_dcache_to_poc(a,l)	__flush_dcache_area((a), (l))
+void stage2_flush_vm(struct kvm *kvm);
 
 #endif /* __ASSEMBLY__ */
 #endif /* __ARM64_KVM_MMU_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/guest.c b/arch/arm64/kvm/guest.c
index 2c3ff67a8ecb..6ee53bb29fa8 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -38,7 +38,6 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 
 int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 {
-	vcpu->arch.hcr_el2 = HCR_GUEST_FLAGS;
 	return 0;
 }
 
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index 9beaca033437..ab1ec62dd3e5 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -39,29 +39,36 @@ static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run)
 
 static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
-	if (kvm_psci_call(vcpu))
-		return 1;
-
 	kvm_inject_undefined(vcpu);
 	return 1;
 }
 
 /**
- * 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);
+
+	kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(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,
diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp-init.S
index ba84e6705e20..e9c87e5402c7 100644
--- a/arch/arm64/kvm/hyp-init.S
+++ b/arch/arm64/kvm/hyp-init.S
@@ -74,6 +74,10 @@ __do_hyp_init:
 	msr	mair_el2, x4
 	isb
 
+	/* Invalidate the stale TLBs from Bootloader */
+	tlbi    alle2
+	dsb     sy
+
 	mov	x4, #SCTLR_EL2_FLAGS
 	msr	sctlr_el2, x4
 	isb
diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S
index 1ac0bbbdddb2..a255167baf6a 100644
--- a/arch/arm64/kvm/hyp.S
+++ b/arch/arm64/kvm/hyp.S
@@ -616,10 +616,17 @@ ENTRY(__kvm_tlb_flush_vmid_ipa)
 	 * Instead, we invalidate Stage-2 for this IPA, and the
 	 * whole of Stage-1. Weep...
 	 */
+	lsr	x1, x1, #12
 	tlbi	ipas2e1is, x1
-	dsb	sy
+	/*
+	 * We have to ensure completion of the invalidation at Stage-2,
+	 * since a table walk on another CPU could refill a TLB with a
+	 * complete (S1 + S2) walk based on the old Stage-2 mapping if
+	 * the Stage-1 invalidation happened first.
+	 */
+	dsb	ish
 	tlbi	vmalle1is
-	dsb	sy
+	dsb	ish
 	isb
 
 	msr	vttbr_el2, xzr
@@ -630,7 +637,7 @@ ENTRY(__kvm_flush_vm_context)
 	dsb	ishst
 	tlbi	alle1is
 	ic	ialluis
-	dsb	sy
+	dsb	ish
 	ret
 ENDPROC(__kvm_flush_vm_context)
 
@@ -681,6 +688,24 @@ __hyp_panic_str:
 
 	.align	2
 
+/*
+ * u64 kvm_call_hyp(void *hypfn, ...);
+ *
+ * This is not really a variadic function in the classic C-way and care must
+ * be taken when calling this to ensure parameters are passed in registers
+ * only, since the stack will change between the caller and the callee.
+ *
+ * Call the function with the first argument containing a pointer to the
+ * function you wish to call in Hyp mode, and subsequent arguments will be
+ * passed as x0, x1, and x2 (a maximum of 3 arguments in addition to the
+ * function pointer can be passed).  The function being called must be mapped
+ * in Hyp mode (see init_hyp_mode in arch/arm/kvm/arm.c).  Return values are
+ * passed in r0 and r1.
+ *
+ * A function pointer with a value of 0 has a special meaning, and is
+ * used to implement __hyp_get_vectors in the same way as in
+ * arch/arm64/kernel/hyp_stub.S.
+ */
 ENTRY(kvm_call_hyp)
 	hvc	#0
 	ret
@@ -724,7 +749,12 @@ el1_sync:					// Guest trapped into EL2
 	pop	x2, x3
 	pop	x0, x1
 
-	push	lr, xzr
+	/* Check for __hyp_get_vectors */
+	cbnz	x0, 1f
+	mrs	x0, vbar_el2
+	b	2f
+
+1:	push	lr, xzr
 
 	/*
 	 * Compute the function address in EL2, and shuffle the parameters.
@@ -737,7 +767,7 @@ el1_sync:					// Guest trapped into EL2
 	blr	lr
 
 	pop	lr, xzr
-	eret
+2:	eret
 
 el1_trap:
 	/*
@@ -788,7 +818,7 @@ el1_trap:
 	mrs	x2, far_el2
 
 2:	mrs	x0, tpidr_el2
-	str	x1, [x0, #VCPU_ESR_EL2]
+	str	w1, [x0, #VCPU_ESR_EL2]
 	str	x2, [x0, #VCPU_FAR_EL2]
 	str	x3, [x0, #VCPU_HPFAR_EL2]
 
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index 70a7816535cd..0b4326578985 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -90,7 +90,6 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 			if (!cpu_has_32bit_el1())
 				return -EINVAL;
 			cpu_reset = &default_regs_reset32;
-			vcpu->arch.hcr_el2 &= ~HCR_RW;
 		} else {
 			cpu_reset = &default_regs_reset;
 		}
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 02e9d09e1d80..7691b2563d27 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -27,6 +27,7 @@
 #include <asm/kvm_host.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_coproc.h>
+#include <asm/kvm_mmu.h>
 #include <asm/cacheflush.h>
 #include <asm/cputype.h>
 #include <trace/events/kvm.h>
@@ -121,6 +122,48 @@ done:
 }
 
 /*
+ * Generic accessor for VM registers. Only called as long as HCR_TVM
+ * is set.
+ */
+static bool access_vm_reg(struct kvm_vcpu *vcpu,
+			  const struct sys_reg_params *p,
+			  const struct sys_reg_desc *r)
+{
+	unsigned long val;
+
+	BUG_ON(!p->is_write);
+
+	val = *vcpu_reg(vcpu, p->Rt);
+	if (!p->is_aarch32) {
+		vcpu_sys_reg(vcpu, r->reg) = val;
+	} else {
+		vcpu_cp15(vcpu, r->reg) = val & 0xffffffffUL;
+		if (!p->is_32bit)
+			vcpu_cp15(vcpu, r->reg + 1) = val >> 32;
+	}
+	return true;
+}
+
+/*
+ * SCTLR_EL1 accessor. Only called as long as HCR_TVM is set.  If the
+ * guest enables the MMU, we stop trapping the VM sys_regs and leave
+ * it in complete control of the caches.
+ */
+static bool access_sctlr(struct kvm_vcpu *vcpu,
+			 const struct sys_reg_params *p,
+			 const struct sys_reg_desc *r)
+{
+	access_vm_reg(vcpu, p, r);
+
+	if (vcpu_has_cache_enabled(vcpu)) {	/* MMU+Caches enabled? */
+		vcpu->arch.hcr_el2 &= ~HCR_TVM;
+		stage2_flush_vm(vcpu->kvm);
+	}
+
+	return true;
+}
+
+/*
  * We could trap ID_DFR0 and tell the guest we don't support performance
  * monitoring.  Unfortunately the patch to make the kernel check ID_DFR0 was
  * NAKed, so it will read the PMCR anyway.
@@ -185,32 +228,32 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	  NULL, reset_mpidr, MPIDR_EL1 },
 	/* SCTLR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b000),
-	  NULL, reset_val, SCTLR_EL1, 0x00C50078 },
+	  access_sctlr, reset_val, SCTLR_EL1, 0x00C50078 },
 	/* CPACR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b010),
 	  NULL, reset_val, CPACR_EL1, 0 },
 	/* TTBR0_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b0010), CRm(0b0000), Op2(0b000),
-	  NULL, reset_unknown, TTBR0_EL1 },
+	  access_vm_reg, reset_unknown, TTBR0_EL1 },
 	/* TTBR1_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b0010), CRm(0b0000), Op2(0b001),
-	  NULL, reset_unknown, TTBR1_EL1 },
+	  access_vm_reg, reset_unknown, TTBR1_EL1 },
 	/* TCR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b0010), CRm(0b0000), Op2(0b010),
-	  NULL, reset_val, TCR_EL1, 0 },
+	  access_vm_reg, reset_val, TCR_EL1, 0 },
 
 	/* AFSR0_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b0101), CRm(0b0001), Op2(0b000),
-	  NULL, reset_unknown, AFSR0_EL1 },
+	  access_vm_reg, reset_unknown, AFSR0_EL1 },
 	/* AFSR1_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b0101), CRm(0b0001), Op2(0b001),
-	  NULL, reset_unknown, AFSR1_EL1 },
+	  access_vm_reg, reset_unknown, AFSR1_EL1 },
 	/* ESR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b0101), CRm(0b0010), Op2(0b000),
-	  NULL, reset_unknown, ESR_EL1 },
+	  access_vm_reg, reset_unknown, ESR_EL1 },
 	/* FAR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b0110), CRm(0b0000), Op2(0b000),
-	  NULL, reset_unknown, FAR_EL1 },
+	  access_vm_reg, reset_unknown, FAR_EL1 },
 	/* PAR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b0111), CRm(0b0100), Op2(0b000),
 	  NULL, reset_unknown, PAR_EL1 },
@@ -224,17 +267,17 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 
 	/* MAIR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b1010), CRm(0b0010), Op2(0b000),
-	  NULL, reset_unknown, MAIR_EL1 },
+	  access_vm_reg, reset_unknown, MAIR_EL1 },
 	/* AMAIR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b1010), CRm(0b0011), Op2(0b000),
-	  NULL, reset_amair_el1, AMAIR_EL1 },
+	  access_vm_reg, reset_amair_el1, AMAIR_EL1 },
 
 	/* VBAR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b1100), CRm(0b0000), Op2(0b000),
 	  NULL, reset_val, VBAR_EL1, 0 },
 	/* CONTEXTIDR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b1101), CRm(0b0000), Op2(0b001),
-	  NULL, reset_val, CONTEXTIDR_EL1, 0 },
+	  access_vm_reg, reset_val, CONTEXTIDR_EL1, 0 },
 	/* TPIDR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b1101), CRm(0b0000), Op2(0b100),
 	  NULL, reset_unknown, TPIDR_EL1 },
@@ -305,14 +348,32 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	  NULL, reset_val, FPEXC32_EL2, 0x70 },
 };
 
-/* Trapped cp15 registers */
+/*
+ * Trapped cp15 registers. TTBR0/TTBR1 get a double encoding,
+ * depending on the way they are accessed (as a 32bit or a 64bit
+ * register).
+ */
 static const struct sys_reg_desc cp15_regs[] = {
+	{ Op1( 0), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, c2_TTBR0 },
+	{ Op1( 0), CRn( 1), CRm( 0), Op2( 0), access_sctlr, NULL, c1_SCTLR },
+	{ Op1( 0), CRn( 2), CRm( 0), Op2( 0), access_vm_reg, NULL, c2_TTBR0 },
+	{ Op1( 0), CRn( 2), CRm( 0), Op2( 1), access_vm_reg, NULL, c2_TTBR1 },
+	{ Op1( 0), CRn( 2), CRm( 0), Op2( 2), access_vm_reg, NULL, c2_TTBCR },
+	{ Op1( 0), CRn( 3), CRm( 0), Op2( 0), access_vm_reg, NULL, c3_DACR },
+	{ Op1( 0), CRn( 5), CRm( 0), Op2( 0), access_vm_reg, NULL, c5_DFSR },
+	{ Op1( 0), CRn( 5), CRm( 0), Op2( 1), access_vm_reg, NULL, c5_IFSR },
+	{ Op1( 0), CRn( 5), CRm( 1), Op2( 0), access_vm_reg, NULL, c5_ADFSR },
+	{ Op1( 0), CRn( 5), CRm( 1), Op2( 1), access_vm_reg, NULL, c5_AIFSR },
+	{ Op1( 0), CRn( 6), CRm( 0), Op2( 0), access_vm_reg, NULL, c6_DFAR },
+	{ Op1( 0), CRn( 6), CRm( 0), Op2( 2), access_vm_reg, NULL, c6_IFAR },
+
 	/*
 	 * DC{C,I,CI}SW operations:
 	 */
 	{ Op1( 0), CRn( 7), CRm( 6), Op2( 2), access_dcsw },
 	{ Op1( 0), CRn( 7), CRm(10), Op2( 2), access_dcsw },
 	{ Op1( 0), CRn( 7), CRm(14), Op2( 2), access_dcsw },
+
 	{ Op1( 0), CRn( 9), CRm(12), Op2( 0), pm_fake },
 	{ Op1( 0), CRn( 9), CRm(12), Op2( 1), pm_fake },
 	{ Op1( 0), CRn( 9), CRm(12), Op2( 2), pm_fake },
@@ -326,6 +387,14 @@ static const struct sys_reg_desc cp15_regs[] = {
 	{ Op1( 0), CRn( 9), CRm(14), Op2( 0), pm_fake },
 	{ Op1( 0), CRn( 9), CRm(14), Op2( 1), pm_fake },
 	{ Op1( 0), CRn( 9), CRm(14), Op2( 2), pm_fake },
+
+	{ Op1( 0), CRn(10), CRm( 2), Op2( 0), access_vm_reg, NULL, c10_PRRR },
+	{ Op1( 0), CRn(10), CRm( 2), Op2( 1), access_vm_reg, NULL, c10_NMRR },
+	{ Op1( 0), CRn(10), CRm( 3), Op2( 0), access_vm_reg, NULL, c10_AMAIR0 },
+	{ Op1( 0), CRn(10), CRm( 3), Op2( 1), access_vm_reg, NULL, c10_AMAIR1 },
+	{ Op1( 0), CRn(13), CRm( 0), Op2( 1), access_vm_reg, NULL, c13_CID },
+
+	{ Op1( 1), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, c2_TTBR1 },
 };
 
 /* Target specific emulation tables */
@@ -437,6 +506,8 @@ int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	u32 hsr = kvm_vcpu_get_hsr(vcpu);
 	int Rt2 = (hsr >> 10) & 0xf;
 
+	params.is_aarch32 = true;
+	params.is_32bit = false;
 	params.CRm = (hsr >> 1) & 0xf;
 	params.Rt = (hsr >> 5) & 0xf;
 	params.is_write = ((hsr & 1) == 0);
@@ -480,6 +551,8 @@ int kvm_handle_cp15_32(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	struct sys_reg_params params;
 	u32 hsr = kvm_vcpu_get_hsr(vcpu);
 
+	params.is_aarch32 = true;
+	params.is_32bit = true;
 	params.CRm = (hsr >> 1) & 0xf;
 	params.Rt  = (hsr >> 5) & 0xf;
 	params.is_write = ((hsr & 1) == 0);
@@ -549,6 +622,8 @@ int kvm_handle_sys_reg(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	struct sys_reg_params params;
 	unsigned long esr = kvm_vcpu_get_hsr(vcpu);
 
+	params.is_aarch32 = false;
+	params.is_32bit = false;
 	params.Op0 = (esr >> 20) & 3;
 	params.Op1 = (esr >> 14) & 0x7;
 	params.CRn = (esr >> 10) & 0xf;
@@ -761,7 +836,7 @@ static bool is_valid_cache(u32 val)
 	u32 level, ctype;
 
 	if (val >= CSSELR_MAX)
-		return -ENOENT;
+		return false;
 
 	/* Bottom bit is Instruction or Data bit.  Next 3 bits are level. */
 	level = (val >> 1);
@@ -887,7 +962,7 @@ static unsigned int num_demux_regs(void)
 
 static int write_demux_regids(u64 __user *uindices)
 {
-	u64 val = KVM_REG_ARM | KVM_REG_SIZE_U32 | KVM_REG_ARM_DEMUX;
+	u64 val = KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_DEMUX;
 	unsigned int i;
 
 	val |= KVM_REG_ARM_DEMUX_ID_CCSIDR;
diff --git a/arch/arm64/kvm/sys_regs.h b/arch/arm64/kvm/sys_regs.h
index d50d3722998e..d411e251412c 100644
--- a/arch/arm64/kvm/sys_regs.h
+++ b/arch/arm64/kvm/sys_regs.h
@@ -30,6 +30,8 @@ struct sys_reg_params {
 	u8	Op2;
 	u8	Rt;
 	bool	is_write;
+	bool	is_aarch32;
+	bool	is_32bit;	/* Only valid if is_aarch32 is true */
 };
 
 struct sys_reg_desc {
diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h
index 6d9aeddc09bf..327b155e7cc9 100644
--- a/include/kvm/arm_arch_timer.h
+++ b/include/kvm/arm_arch_timer.h
@@ -60,7 +60,8 @@ struct arch_timer_cpu {
 
 #ifdef CONFIG_KVM_ARM_TIMER
 int kvm_timer_hyp_init(void);
-int kvm_timer_init(struct kvm *kvm);
+void kvm_timer_enable(struct kvm *kvm);
+void kvm_timer_init(struct kvm *kvm);
 void kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu,
 			  const struct kvm_irq_level *irq);
 void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu);
@@ -73,11 +74,8 @@ static inline int kvm_timer_hyp_init(void)
 	return 0;
 };
 
-static inline int kvm_timer_init(struct kvm *kvm)
-{
-	return 0;
-}
-
+static inline void kvm_timer_enable(struct kvm *kvm) {}
+static inline void kvm_timer_init(struct kvm *kvm) {}
 static inline void kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu,
 					const struct kvm_irq_level *irq) {}
 static inline void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu) {}
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index 7e2d15837b02..a15ae2a820b9 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -171,6 +171,11 @@ static inline int kvm_vgic_set_addr(struct kvm *kvm, unsigned long type, u64 add
 	return 0;
 }
 
+static inline int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write)
+{
+	return -ENXIO;
+}
+
 static inline int kvm_vgic_init(struct kvm *kvm)
 {
 	return 0;
diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c
index c2e1ef4604e8..52b4225da32d 100644
--- a/virt/kvm/arm/arch_timer.c
+++ b/virt/kvm/arm/arch_timer.c
@@ -61,12 +61,14 @@ static void timer_disarm(struct arch_timer_cpu *timer)
 
 static void kvm_timer_inject_irq(struct kvm_vcpu *vcpu)
 {
+	int ret;
 	struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
 
 	timer->cntv_ctl |= ARCH_TIMER_CTRL_IT_MASK;
-	kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id,
-			    timer->irq->irq,
-			    timer->irq->level);
+	ret = kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id,
+				  timer->irq->irq,
+				  timer->irq->level);
+	WARN_ON(ret);
 }
 
 static irqreturn_t kvm_arch_timer_handler(int irq, void *dev_id)
@@ -273,12 +275,24 @@ void kvm_timer_vcpu_terminate(struct kvm_vcpu *vcpu)
 	timer_disarm(timer);
 }
 
-int kvm_timer_init(struct kvm *kvm)
+void kvm_timer_enable(struct kvm *kvm)
 {
-	if (timecounter && wqueue) {
-		kvm->arch.timer.cntvoff = kvm_phys_timer_read();
+	if (kvm->arch.timer.enabled)
+		return;
+
+	/*
+	 * There is a potential race here between VCPUs starting for the first
+	 * time, which may be enabling the timer multiple times.  That doesn't
+	 * hurt though, because we're just setting a variable to the same
+	 * variable that it already was.  The important thing is that all
+	 * VCPUs have the enabled variable set, before entering the guest, if
+	 * the arch timers are enabled.
+	 */
+	if (timecounter && wqueue)
 		kvm->arch.timer.enabled = 1;
-	}
+}
 
-	return 0;
+void kvm_timer_init(struct kvm *kvm)
+{
+	kvm->arch.timer.cntvoff = kvm_phys_timer_read();
 }
diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
index b001dbff0f38..ecea20153b42 100644
--- a/virt/kvm/arm/vgic.c
+++ b/virt/kvm/arm/vgic.c
@@ -543,11 +543,10 @@ static bool handle_mmio_cfg_reg(struct kvm_vcpu *vcpu,
 	u32 val;
 	u32 *reg;
 
-	offset >>= 1;
 	reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_cfg,
-				  vcpu->vcpu_id, offset);
+				  vcpu->vcpu_id, offset >> 1);
 
-	if (offset & 2)
+	if (offset & 4)
 		val = *reg >> 16;
 	else
 		val = *reg & 0xffff;
@@ -556,13 +555,13 @@ static bool handle_mmio_cfg_reg(struct kvm_vcpu *vcpu,
 	vgic_reg_access(mmio, &val, offset,
 			ACCESS_READ_VALUE | ACCESS_WRITE_VALUE);
 	if (mmio->is_write) {
-		if (offset < 4) {
+		if (offset < 8) {
 			*reg = ~0U; /* Force PPIs/SGIs to 1 */
 			return false;
 		}
 
 		val = vgic_cfg_compress(val);
-		if (offset & 2) {
+		if (offset & 4) {
 			*reg &= 0xffff;
 			*reg |= val << 16;
 		} else {
@@ -882,6 +881,7 @@ static bool vgic_queue_irq(struct kvm_vcpu *vcpu, u8 sgi_source_id, int irq)
 			  lr, irq, vgic_cpu->vgic_lr[lr]);
 		BUG_ON(!test_bit(lr, vgic_cpu->lr_used));
 		vgic_cpu->vgic_lr[lr] |= GICH_LR_PENDING_BIT;
+		__clear_bit(lr, (unsigned long *)vgic_cpu->vgic_elrsr);
 		return true;
 	}
 
@@ -895,6 +895,7 @@ static bool vgic_queue_irq(struct kvm_vcpu *vcpu, u8 sgi_source_id, int irq)
 	vgic_cpu->vgic_lr[lr] = MK_LR_PEND(sgi_source_id, irq);
 	vgic_cpu->vgic_irq_lr_map[irq] = lr;
 	set_bit(lr, vgic_cpu->lr_used);
+	__clear_bit(lr, (unsigned long *)vgic_cpu->vgic_elrsr);
 
 	if (!vgic_irq_is_edge(vcpu, irq))
 		vgic_cpu->vgic_lr[lr] |= GICH_LR_EOI;
@@ -1049,6 +1050,14 @@ static bool vgic_process_maintenance(struct kvm_vcpu *vcpu)
 	if (vgic_cpu->vgic_misr & GICH_MISR_U)
 		vgic_cpu->vgic_hcr &= ~GICH_HCR_UIE;
 
+	/*
+	 * In the next iterations of the vcpu loop, if we sync the vgic state
+	 * after flushing it, but before entering the guest (this happens for
+	 * pending signals and vmid rollovers), then make sure we don't pick
+	 * up any old maintenance interrupts here.
+	 */
+	memset(vgic_cpu->vgic_eisr, 0, sizeof(vgic_cpu->vgic_eisr[0]) * 2);
+
 	return level_pending;
 }
 
@@ -1227,7 +1236,8 @@ out:
 int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int irq_num,
 			bool level)
 {
-	if (vgic_update_irq_state(kvm, cpuid, irq_num, level))
+	if (likely(vgic_initialized(kvm)) &&
+	    vgic_update_irq_state(kvm, cpuid, irq_num, level))
 		vgic_kick_vcpus(kvm);
 
 	return 0;
@@ -1244,15 +1254,19 @@ static irqreturn_t vgic_maintenance_handler(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
+/**
+ * kvm_vgic_vcpu_init - Initialize per-vcpu VGIC state
+ * @vcpu: pointer to the vcpu struct
+ *
+ * Initialize the vgic_cpu struct and vgic_dist struct fields pertaining to
+ * this vcpu and enable the VGIC for this VCPU
+ */
 int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
 {
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
 	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
 	int i;
 
-	if (!irqchip_in_kernel(vcpu->kvm))
-		return 0;
-
 	if (vcpu->vcpu_id >= VGIC_MAX_CPUS)
 		return -EBUSY;
 
@@ -1362,17 +1376,33 @@ int kvm_vgic_hyp_init(void)
 		goto out_unmap;
 	}
 
-	kvm_info("%s@%llx IRQ%d\n", vgic_node->name,
-		 vctrl_res.start, vgic_maint_irq);
-	on_each_cpu(vgic_init_maintenance_interrupt, NULL, 1);
-
 	if (of_address_to_resource(vgic_node, 3, &vcpu_res)) {
 		kvm_err("Cannot obtain VCPU resource\n");
 		ret = -ENXIO;
 		goto out_unmap;
 	}
+
+	if (!PAGE_ALIGNED(vcpu_res.start)) {
+		kvm_err("GICV physical address 0x%llx not page aligned\n",
+			(unsigned long long)vcpu_res.start);
+		ret = -ENXIO;
+		goto out_unmap;
+	}
+
+	if (!PAGE_ALIGNED(resource_size(&vcpu_res))) {
+		kvm_err("GICV size 0x%llx not a multiple of page size 0x%lx\n",
+			(unsigned long long)resource_size(&vcpu_res),
+			PAGE_SIZE);
+		ret = -ENXIO;
+		goto out_unmap;
+	}
+
 	vgic_vcpu_base = vcpu_res.start;
 
+	kvm_info("%s@%llx IRQ%d\n", vgic_node->name,
+		 vctrl_res.start, vgic_maint_irq);
+	on_each_cpu(vgic_init_maintenance_interrupt, NULL, 1);
+
 	goto out;
 
 out_unmap:
@@ -1384,10 +1414,22 @@ out:
 	return ret;
 }
 
+/**
+ * kvm_vgic_init - Initialize global VGIC state before running any VCPUs
+ * @kvm: pointer to the kvm struct
+ *
+ * Map the virtual CPU interface into the VM before running any VCPUs.  We
+ * can't do this at creation time, because user space must first set the
+ * virtual CPU interface address in the guest physical address space.  Also
+ * initialize the ITARGETSRn regs to 0 on the emulated distributor.
+ */
 int kvm_vgic_init(struct kvm *kvm)
 {
 	int ret = 0, i;
 
+	if (!irqchip_in_kernel(kvm))
+		return 0;
+
 	mutex_lock(&kvm->lock);
 
 	if (vgic_initialized(kvm))
@@ -1410,7 +1452,6 @@ int kvm_vgic_init(struct kvm *kvm)
 	for (i = VGIC_NR_PRIVATE_IRQS; i < VGIC_NR_IRQS; i += 4)
 		vgic_set_target_reg(kvm, 0, i);
 
-	kvm_timer_init(kvm);
 	kvm->arch.vgic.ready = true;
 out:
 	mutex_unlock(&kvm->lock);
@@ -1438,7 +1479,7 @@ out:
 	return ret;
 }
 
-static bool vgic_ioaddr_overlap(struct kvm *kvm)
+static int vgic_ioaddr_overlap(struct kvm *kvm)
 {
 	phys_addr_t dist = kvm->arch.vgic.vgic_dist_base;
 	phys_addr_t cpu = kvm->arch.vgic.vgic_cpu_base;
@@ -1461,10 +1502,11 @@ static int vgic_ioaddr_assign(struct kvm *kvm, phys_addr_t *ioaddr,
 	if (addr + size < addr)
 		return -EINVAL;
 
+	*ioaddr = addr;
 	ret = vgic_ioaddr_overlap(kvm);
 	if (ret)
-		return ret;
-	*ioaddr = addr;
+		*ioaddr = VGIC_ADDR_UNDEF;
+
 	return ret;
 }