Merge tag 'kvm-arm-for-3.17' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into kvm

KVM/ARM New features for 3.17 include:
 - Fixes and code refactoring for stage2 kvm MMU unmap_range
 - Support unmapping IPAs on deleting memslots for arm and arm64
 - Support MMIO mappings in stage2 faults
 - KVM VGIC v2 emulation on GICv3 hardware
 - Big-Endian support for arm/arm64 (guest and host)
 - Debug Architecture support for arm64 (arm32 is on Christoffer's todo list)

Conflicts:
	virt/kvm/arm/vgic.c [last minute cherry-pick from 3.17 to 3.16]

15 files changed, 320 insertions, 171 deletions

diff --git a/arch/arm/include/asm/kvm_asm.h b/arch/arm/include/asm/kvm_asm.h
index 53b3c4a50d5c..3a67bec72d0c 100644
--- a/arch/arm/include/asm/kvm_asm.h
+++ b/arch/arm/include/asm/kvm_asm.h
@@ -61,6 +61,24 @@
 #define ARM_EXCEPTION_FIQ	  6
 #define ARM_EXCEPTION_HVC	  7
 
+/*
+ * The rr_lo_hi macro swaps a pair of registers depending on
+ * current endianness. It is used in conjunction with ldrd and strd
+ * instructions that load/store a 64-bit value from/to memory to/from
+ * a pair of registers which are used with the mrrc and mcrr instructions.
+ * If used with the ldrd/strd instructions, the a1 parameter is the first
+ * source/destination register and the a2 parameter is the second
+ * source/destination register. Note that the ldrd/strd instructions
+ * already swap the bytes within the words correctly according to the
+ * endianness setting, but the order of the registers need to be effectively
+ * swapped when used with the mrrc/mcrr instructions.
+ */
+#ifdef CONFIG_CPU_ENDIAN_BE8
+#define rr_lo_hi(a1, a2) a2, a1
+#else
+#define rr_lo_hi(a1, a2) a1, a2
+#endif
+
 #ifndef __ASSEMBLY__
 struct kvm;
 struct kvm_vcpu;
diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h
index 0fa90c962ac8..69b746955fca 100644
--- a/arch/arm/include/asm/kvm_emulate.h
+++ b/arch/arm/include/asm/kvm_emulate.h
@@ -185,9 +185,16 @@ static inline unsigned long vcpu_data_guest_to_host(struct kvm_vcpu *vcpu,
 		default:
 			return be32_to_cpu(data);
 		}
+	} else {
+		switch (len) {
+		case 1:
+			return data & 0xff;
+		case 2:
+			return le16_to_cpu(data & 0xffff);
+		default:
+			return le32_to_cpu(data);
+		}
 	}
-
-	return data;		/* Leave LE untouched */
 }
 
 static inline unsigned long vcpu_data_host_to_guest(struct kvm_vcpu *vcpu,
@@ -203,9 +210,16 @@ static inline unsigned long vcpu_data_host_to_guest(struct kvm_vcpu *vcpu,
 		default:
 			return cpu_to_be32(data);
 		}
+	} else {
+		switch (len) {
+		case 1:
+			return data & 0xff;
+		case 2:
+			return cpu_to_le16(data & 0xffff);
+		default:
+			return cpu_to_le32(data);
+		}
 	}
-
-	return data;		/* Leave LE untouched */
 }
 
 #endif /* __ARM_KVM_EMULATE_H__ */
diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index 193ceaf01bfd..6dfb404f6c46 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -225,10 +225,12 @@ static inline int kvm_arch_dev_ioctl_check_extension(long ext)
 	return 0;
 }
 
+static inline void vgic_arch_setup(const struct vgic_params *vgic)
+{
+	BUG_ON(vgic->type != VGIC_V2);
+}
+
 int kvm_perf_init(void);
 int kvm_perf_teardown(void);
 
-u64 kvm_arm_timer_get_reg(struct kvm_vcpu *, u64 regid);
-int kvm_arm_timer_set_reg(struct kvm_vcpu *, u64 regid, u64 value);
-
 #endif /* __ARM_KVM_HOST_H__ */
diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index 5c7aa3c1519f..5cc0b0f5f72f 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -127,6 +127,18 @@ static inline void kvm_set_s2pmd_writable(pmd_t *pmd)
 	(__boundary - 1 < (end) - 1)? __boundary: (end);		\
 })
 
+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;
 
 #define kvm_flush_dcache_to_poc(a,l)	__cpuc_flush_dcache_area((a), (l))
diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c
index 85598b5d1efd..713e807621d2 100644
--- a/arch/arm/kernel/asm-offsets.c
+++ b/arch/arm/kernel/asm-offsets.c
@@ -182,13 +182,13 @@ int main(void)
   DEFINE(VCPU_HYP_PC,		offsetof(struct kvm_vcpu, arch.fault.hyp_pc));
 #ifdef CONFIG_KVM_ARM_VGIC
   DEFINE(VCPU_VGIC_CPU,		offsetof(struct kvm_vcpu, arch.vgic_cpu));
-  DEFINE(VGIC_CPU_HCR,		offsetof(struct vgic_cpu, vgic_hcr));
-  DEFINE(VGIC_CPU_VMCR,		offsetof(struct vgic_cpu, vgic_vmcr));
-  DEFINE(VGIC_CPU_MISR,		offsetof(struct vgic_cpu, vgic_misr));
-  DEFINE(VGIC_CPU_EISR,		offsetof(struct vgic_cpu, vgic_eisr));
-  DEFINE(VGIC_CPU_ELRSR,	offsetof(struct vgic_cpu, vgic_elrsr));
-  DEFINE(VGIC_CPU_APR,		offsetof(struct vgic_cpu, vgic_apr));
-  DEFINE(VGIC_CPU_LR,		offsetof(struct vgic_cpu, vgic_lr));
+  DEFINE(VGIC_V2_CPU_HCR,	offsetof(struct vgic_cpu, vgic_v2.vgic_hcr));
+  DEFINE(VGIC_V2_CPU_VMCR,	offsetof(struct vgic_cpu, vgic_v2.vgic_vmcr));
+  DEFINE(VGIC_V2_CPU_MISR,	offsetof(struct vgic_cpu, vgic_v2.vgic_misr));
+  DEFINE(VGIC_V2_CPU_EISR,	offsetof(struct vgic_cpu, vgic_v2.vgic_eisr));
+  DEFINE(VGIC_V2_CPU_ELRSR,	offsetof(struct vgic_cpu, vgic_v2.vgic_elrsr));
+  DEFINE(VGIC_V2_CPU_APR,	offsetof(struct vgic_cpu, vgic_v2.vgic_apr));
+  DEFINE(VGIC_V2_CPU_LR,	offsetof(struct vgic_cpu, vgic_v2.vgic_lr));
   DEFINE(VGIC_CPU_NR_LR,	offsetof(struct vgic_cpu, nr_lr));
 #ifdef CONFIG_KVM_ARM_TIMER
   DEFINE(VCPU_TIMER_CNTV_CTL,	offsetof(struct kvm_vcpu, arch.timer_cpu.cntv_ctl));
diff --git a/arch/arm/kernel/hyp-stub.S b/arch/arm/kernel/hyp-stub.S
index 797b1a6a4906..7e666cfda634 100644
--- a/arch/arm/kernel/hyp-stub.S
+++ b/arch/arm/kernel/hyp-stub.S
@@ -134,9 +134,7 @@ ENTRY(__hyp_stub_install_secondary)
 	mcr	p15, 4, r7, c1, c1, 3	@ HSTR
 
 THUMB(	orr	r7, #(1 << 30)	)	@ HSCTLR.TE
-#ifdef CONFIG_CPU_BIG_ENDIAN
-	orr	r7, #(1 << 9)		@ HSCTLR.EE
-#endif
+ARM_BE8(orr	r7, r7, #(1 << 25))     @ HSCTLR.EE
 	mcr	p15, 4, r7, c1, c0, 0	@ HSCTLR
 
 	mrc	p15, 4, r7, c1, c1, 1	@ HDCR
diff --git a/arch/arm/kvm/Kconfig b/arch/arm/kvm/Kconfig
index 4be5bb150bdd..466bd299b1a8 100644
--- a/arch/arm/kvm/Kconfig
+++ b/arch/arm/kvm/Kconfig
@@ -23,7 +23,7 @@ config KVM
 	select HAVE_KVM_CPU_RELAX_INTERCEPT
 	select KVM_MMIO
 	select KVM_ARM_HOST
-	depends on ARM_VIRT_EXT && ARM_LPAE && !CPU_BIG_ENDIAN
+	depends on ARM_VIRT_EXT && ARM_LPAE
 	---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/Makefile b/arch/arm/kvm/Makefile
index 789bca9e64a7..f7057ed045b6 100644
--- a/arch/arm/kvm/Makefile
+++ b/arch/arm/kvm/Makefile
@@ -21,4 +21,5 @@ obj-y += kvm-arm.o init.o interrupts.o
 obj-y += arm.o handle_exit.o guest.o mmu.o emulate.o reset.o
 obj-y += coproc.o coproc_a15.o coproc_a7.o mmio.o psci.o perf.o
 obj-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic.o
+obj-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic-v2.o
 obj-$(CONFIG_KVM_ARM_TIMER) += $(KVM)/arm/arch_timer.o
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 3c82b37c0f9e..d7424ef80354 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -155,16 +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 *kvm, struct kvm_memory_slot *free,
-			   struct kvm_memory_slot *dont)
-{
-}
-
-int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
-			    unsigned long npages)
-{
-	return 0;
-}
 
 /**
  * kvm_arch_destroy_vm - destroy the VM data structure
@@ -225,33 +215,6 @@ 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)
 {
diff --git a/arch/arm/kvm/coproc.c b/arch/arm/kvm/coproc.c
index c58a35116f63..37a0fe1bb9bb 100644
--- a/arch/arm/kvm/coproc.c
+++ b/arch/arm/kvm/coproc.c
@@ -44,6 +44,31 @@ static u32 cache_levels;
 /* CSSELR values; used to index KVM_REG_ARM_DEMUX_ID_CCSIDR */
 #define CSSELR_MAX 12
 
+/*
+ * kvm_vcpu_arch.cp15 holds cp15 registers as an array of u32, but some
+ * of cp15 registers can be viewed either as couple of two u32 registers
+ * or one u64 register. Current u64 register encoding is that least
+ * significant u32 word is followed by most significant u32 word.
+ */
+static inline void vcpu_cp15_reg64_set(struct kvm_vcpu *vcpu,
+				       const struct coproc_reg *r,
+				       u64 val)
+{
+	vcpu->arch.cp15[r->reg] = val & 0xffffffff;
+	vcpu->arch.cp15[r->reg + 1] = val >> 32;
+}
+
+static inline u64 vcpu_cp15_reg64_get(struct kvm_vcpu *vcpu,
+				      const struct coproc_reg *r)
+{
+	u64 val;
+
+	val = vcpu->arch.cp15[r->reg + 1];
+	val = val << 32;
+	val = val | vcpu->arch.cp15[r->reg];
+	return val;
+}
+
 int kvm_handle_cp10_id(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
 	kvm_inject_undefined(vcpu);
@@ -682,17 +707,23 @@ static struct coproc_reg invariant_cp15[] = {
 	{ CRn( 0), CRm( 0), Op1( 1), Op2( 7), is32, NULL, get_AIDR },
 };
 
+/*
+ * Reads a register value from a userspace address to a kernel
+ * variable. Make sure that register size matches sizeof(*__val).
+ */
 static int reg_from_user(void *val, const void __user *uaddr, u64 id)
 {
-	/* This Just Works because we are little endian. */
 	if (copy_from_user(val, uaddr, KVM_REG_SIZE(id)) != 0)
 		return -EFAULT;
 	return 0;
 }
 
+/*
+ * Writes a register value to a userspace address from a kernel variable.
+ * Make sure that register size matches sizeof(*__val).
+ */
 static int reg_to_user(void __user *uaddr, const void *val, u64 id)
 {
-	/* This Just Works because we are little endian. */
 	if (copy_to_user(uaddr, val, KVM_REG_SIZE(id)) != 0)
 		return -EFAULT;
 	return 0;
@@ -702,6 +733,7 @@ static int get_invariant_cp15(u64 id, void __user *uaddr)
 {
 	struct coproc_params params;
 	const struct coproc_reg *r;
+	int ret;
 
 	if (!index_to_params(id, &params))
 		return -ENOENT;
@@ -710,7 +742,15 @@ static int get_invariant_cp15(u64 id, void __user *uaddr)
 	if (!r)
 		return -ENOENT;
 
-	return reg_to_user(uaddr, &r->val, id);
+	ret = -ENOENT;
+	if (KVM_REG_SIZE(id) == 4) {
+		u32 val = r->val;
+
+		ret = reg_to_user(uaddr, &val, id);
+	} else if (KVM_REG_SIZE(id) == 8) {
+		ret = reg_to_user(uaddr, &r->val, id);
+	}
+	return ret;
 }
 
 static int set_invariant_cp15(u64 id, void __user *uaddr)
@@ -718,7 +758,7 @@ static int set_invariant_cp15(u64 id, void __user *uaddr)
 	struct coproc_params params;
 	const struct coproc_reg *r;
 	int err;
-	u64 val = 0; /* Make sure high bits are 0 for 32-bit regs */
+	u64 val;
 
 	if (!index_to_params(id, &params))
 		return -ENOENT;
@@ -726,7 +766,16 @@ static int set_invariant_cp15(u64 id, void __user *uaddr)
 	if (!r)
 		return -ENOENT;
 
-	err = reg_from_user(&val, uaddr, id);
+	err = -ENOENT;
+	if (KVM_REG_SIZE(id) == 4) {
+		u32 val32;
+
+		err = reg_from_user(&val32, uaddr, id);
+		if (!err)
+			val = val32;
+	} else if (KVM_REG_SIZE(id) == 8) {
+		err = reg_from_user(&val, uaddr, id);
+	}
 	if (err)
 		return err;
 
@@ -1004,6 +1053,7 @@ int kvm_arm_coproc_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 {
 	const struct coproc_reg *r;
 	void __user *uaddr = (void __user *)(long)reg->addr;
+	int ret;
 
 	if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_DEMUX)
 		return demux_c15_get(reg->id, uaddr);
@@ -1015,14 +1065,24 @@ int kvm_arm_coproc_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	if (!r)
 		return get_invariant_cp15(reg->id, uaddr);
 
-	/* Note: copies two regs if size is 64 bit. */
-	return reg_to_user(uaddr, &vcpu->arch.cp15[r->reg], reg->id);
+	ret = -ENOENT;
+	if (KVM_REG_SIZE(reg->id) == 8) {
+		u64 val;
+
+		val = vcpu_cp15_reg64_get(vcpu, r);
+		ret = reg_to_user(uaddr, &val, reg->id);
+	} else if (KVM_REG_SIZE(reg->id) == 4) {
+		ret = reg_to_user(uaddr, &vcpu->arch.cp15[r->reg], reg->id);
+	}
+
+	return ret;
 }
 
 int kvm_arm_coproc_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 {
 	const struct coproc_reg *r;
 	void __user *uaddr = (void __user *)(long)reg->addr;
+	int ret;
 
 	if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_DEMUX)
 		return demux_c15_set(reg->id, uaddr);
@@ -1034,8 +1094,18 @@ int kvm_arm_coproc_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	if (!r)
 		return set_invariant_cp15(reg->id, uaddr);
 
-	/* Note: copies two regs if size is 64 bit */
-	return reg_from_user(&vcpu->arch.cp15[r->reg], uaddr, reg->id);
+	ret = -ENOENT;
+	if (KVM_REG_SIZE(reg->id) == 8) {
+		u64 val;
+
+		ret = reg_from_user(&val, uaddr, reg->id);
+		if (!ret)
+			vcpu_cp15_reg64_set(vcpu, r, val);
+	} else if (KVM_REG_SIZE(reg->id) == 4) {
+		ret = reg_from_user(&vcpu->arch.cp15[r->reg], uaddr, reg->id);
+	}
+
+	return ret;
 }
 
 static unsigned int num_demux_regs(void)
diff --git a/arch/arm/kvm/guest.c b/arch/arm/kvm/guest.c
index b23a59c1c522..986e625b5dbd 100644
--- a/arch/arm/kvm/guest.c
+++ b/arch/arm/kvm/guest.c
@@ -124,16 +124,6 @@ static bool is_timer_reg(u64 index)
 	return false;
 }
 
-int kvm_arm_timer_set_reg(struct kvm_vcpu *vcpu, u64 regid, u64 value)
-{
-	return 0;
-}
-
-u64 kvm_arm_timer_get_reg(struct kvm_vcpu *vcpu, u64 regid)
-{
-	return 0;
-}
-
 #else
 
 #define NUM_TIMER_REGS 3
diff --git a/arch/arm/kvm/init.S b/arch/arm/kvm/init.S
index 1b9844d369cc..2cc14dfad049 100644
--- a/arch/arm/kvm/init.S
+++ b/arch/arm/kvm/init.S
@@ -71,7 +71,7 @@ __do_hyp_init:
 	bne	phase2			@ Yes, second stage init
 
 	@ Set the HTTBR to point to the hypervisor PGD pointer passed
-	mcrr	p15, 4, r2, r3, c2
+	mcrr	p15, 4, rr_lo_hi(r2, r3), c2
 
 	@ Set the HTCR and VTCR to the same shareability and cacheability
 	@ settings as the non-secure TTBCR and with T0SZ == 0.
@@ -137,7 +137,7 @@ phase2:
 	mov	pc, r0
 
 target:	@ We're now in the trampoline code, switch page tables
-	mcrr	p15, 4, r2, r3, c2
+	mcrr	p15, 4, rr_lo_hi(r2, r3), c2
 	isb
 
 	@ Invalidate the old TLBs
diff --git a/arch/arm/kvm/interrupts.S b/arch/arm/kvm/interrupts.S
index 0d68d4073068..01dcb0e752d9 100644
--- a/arch/arm/kvm/interrupts.S
+++ b/arch/arm/kvm/interrupts.S
@@ -52,7 +52,7 @@ ENTRY(__kvm_tlb_flush_vmid_ipa)
 	dsb	ishst
 	add	r0, r0, #KVM_VTTBR
 	ldrd	r2, r3, [r0]
-	mcrr	p15, 6, r2, r3, c2	@ Write VTTBR
+	mcrr	p15, 6, rr_lo_hi(r2, r3), c2	@ Write VTTBR
 	isb
 	mcr     p15, 0, r0, c8, c3, 0	@ TLBIALLIS (rt ignored)
 	dsb	ish
@@ -135,7 +135,7 @@ ENTRY(__kvm_vcpu_run)
 	ldr	r1, [vcpu, #VCPU_KVM]
 	add	r1, r1, #KVM_VTTBR
 	ldrd	r2, r3, [r1]
-	mcrr	p15, 6, r2, r3, c2	@ Write VTTBR
+	mcrr	p15, 6, rr_lo_hi(r2, r3), c2	@ Write VTTBR
 
 	@ We're all done, just restore the GPRs and go to the guest
 	restore_guest_regs
@@ -199,8 +199,13 @@ after_vfp_restore:
 
 	restore_host_regs
 	clrex				@ Clear exclusive monitor
+#ifndef CONFIG_CPU_ENDIAN_BE8
 	mov	r0, r1			@ Return the return code
 	mov	r1, #0			@ Clear upper bits in return value
+#else
+	@ r1 already has return code
+	mov	r0, #0			@ Clear upper bits in return value
+#endif /* CONFIG_CPU_ENDIAN_BE8 */
 	bx	lr			@ return to IOCTL
 
 /********************************************************************
diff --git a/arch/arm/kvm/interrupts_head.S b/arch/arm/kvm/interrupts_head.S
index 76af93025574..98c8c5b9a87f 100644
--- a/arch/arm/kvm/interrupts_head.S
+++ b/arch/arm/kvm/interrupts_head.S
@@ -1,4 +1,5 @@
 #include <linux/irqchip/arm-gic.h>
+#include <asm/assembler.h>
 
 #define VCPU_USR_REG(_reg_nr)	(VCPU_USR_REGS + (_reg_nr * 4))
 #define VCPU_USR_SP		(VCPU_USR_REG(13))
@@ -420,15 +421,23 @@ vcpu	.req	r0		@ vcpu pointer always in r0
 	ldr	r8, [r2, #GICH_ELRSR0]
 	ldr	r9, [r2, #GICH_ELRSR1]
 	ldr	r10, [r2, #GICH_APR]
-
-	str	r3, [r11, #VGIC_CPU_HCR]
-	str	r4, [r11, #VGIC_CPU_VMCR]
-	str	r5, [r11, #VGIC_CPU_MISR]
-	str	r6, [r11, #VGIC_CPU_EISR]
-	str	r7, [r11, #(VGIC_CPU_EISR + 4)]
-	str	r8, [r11, #VGIC_CPU_ELRSR]
-	str	r9, [r11, #(VGIC_CPU_ELRSR + 4)]
-	str	r10, [r11, #VGIC_CPU_APR]
+ARM_BE8(rev	r3, r3	)
+ARM_BE8(rev	r4, r4	)
+ARM_BE8(rev	r5, r5	)
+ARM_BE8(rev	r6, r6	)
+ARM_BE8(rev	r7, r7	)
+ARM_BE8(rev	r8, r8	)
+ARM_BE8(rev	r9, r9	)
+ARM_BE8(rev	r10, r10	)
+
+	str	r3, [r11, #VGIC_V2_CPU_HCR]
+	str	r4, [r11, #VGIC_V2_CPU_VMCR]
+	str	r5, [r11, #VGIC_V2_CPU_MISR]
+	str	r6, [r11, #VGIC_V2_CPU_EISR]
+	str	r7, [r11, #(VGIC_V2_CPU_EISR + 4)]
+	str	r8, [r11, #VGIC_V2_CPU_ELRSR]
+	str	r9, [r11, #(VGIC_V2_CPU_ELRSR + 4)]
+	str	r10, [r11, #VGIC_V2_CPU_APR]
 
 	/* Clear GICH_HCR */
 	mov	r5, #0
@@ -436,9 +445,10 @@ vcpu	.req	r0		@ vcpu pointer always in r0
 
 	/* Save list registers */
 	add	r2, r2, #GICH_LR0
-	add	r3, r11, #VGIC_CPU_LR
+	add	r3, r11, #VGIC_V2_CPU_LR
 	ldr	r4, [r11, #VGIC_CPU_NR_LR]
 1:	ldr	r6, [r2], #4
+ARM_BE8(rev	r6, r6	)
 	str	r6, [r3], #4
 	subs	r4, r4, #1
 	bne	1b
@@ -463,9 +473,12 @@ vcpu	.req	r0		@ vcpu pointer always in r0
 	add	r11, vcpu, #VCPU_VGIC_CPU
 
 	/* We only restore a minimal set of registers */
-	ldr	r3, [r11, #VGIC_CPU_HCR]
-	ldr	r4, [r11, #VGIC_CPU_VMCR]
-	ldr	r8, [r11, #VGIC_CPU_APR]
+	ldr	r3, [r11, #VGIC_V2_CPU_HCR]
+	ldr	r4, [r11, #VGIC_V2_CPU_VMCR]
+	ldr	r8, [r11, #VGIC_V2_CPU_APR]
+ARM_BE8(rev	r3, r3	)
+ARM_BE8(rev	r4, r4	)
+ARM_BE8(rev	r8, r8	)
 
 	str	r3, [r2, #GICH_HCR]
 	str	r4, [r2, #GICH_VMCR]
@@ -473,9 +486,10 @@ vcpu	.req	r0		@ vcpu pointer always in r0
 
 	/* Restore list registers */
 	add	r2, r2, #GICH_LR0
-	add	r3, r11, #VGIC_CPU_LR
+	add	r3, r11, #VGIC_V2_CPU_LR
 	ldr	r4, [r11, #VGIC_CPU_NR_LR]
 1:	ldr	r6, [r3], #4
+ARM_BE8(rev	r6, r6  )
 	str	r6, [r2], #4
 	subs	r4, r4, #1
 	bne	1b
@@ -506,7 +520,7 @@ vcpu	.req	r0		@ vcpu pointer always in r0
 	mcr	p15, 0, r2, c14, c3, 1	@ CNTV_CTL
 	isb
 
-	mrrc	p15, 3, r2, r3, c14	@ CNTV_CVAL
+	mrrc	p15, 3, rr_lo_hi(r2, r3), c14	@ CNTV_CVAL
 	ldr	r4, =VCPU_TIMER_CNTV_CVAL
 	add	r5, vcpu, r4
 	strd	r2, r3, [r5]
@@ -546,12 +560,12 @@ vcpu	.req	r0		@ vcpu pointer always in r0
 
 	ldr	r2, [r4, #KVM_TIMER_CNTVOFF]
 	ldr	r3, [r4, #(KVM_TIMER_CNTVOFF + 4)]
-	mcrr	p15, 4, r2, r3, c14	@ CNTVOFF
+	mcrr	p15, 4, rr_lo_hi(r2, r3), c14	@ CNTVOFF
 
 	ldr	r4, =VCPU_TIMER_CNTV_CVAL
 	add	r5, vcpu, r4
 	ldrd	r2, r3, [r5]
-	mcrr	p15, 3, r2, r3, c14	@ CNTV_CVAL
+	mcrr	p15, 3, rr_lo_hi(r2, r3), c14	@ CNTV_CVAL
 	isb
 
 	ldr	r2, [vcpu, #VCPU_TIMER_CNTV_CTL]
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index 16f804938b8f..16e7994bf347 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -90,104 +90,115 @@ 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)
 {
-	if (pud_huge(*pud)) {
-		pud_clear(pud);
-		kvm_tlb_flush_vmid_ipa(kvm, addr);
-	} else {
-		pmd_t *pmd_table = pmd_offset(pud, 0);
-		pud_clear(pud);
-		kvm_tlb_flush_vmid_ipa(kvm, addr);
-		pmd_free(NULL, pmd_table);
-	}
+	pmd_t *pmd_table = pmd_offset(pud, 0);
+	VM_BUG_ON(pud_huge(*pud));
+	pud_clear(pud);
+	kvm_tlb_flush_vmid_ipa(kvm, addr);
+	pmd_free(NULL, pmd_table);
 	put_page(virt_to_page(pud));
 }
 
 static void clear_pmd_entry(struct kvm *kvm, pmd_t *pmd, phys_addr_t addr)
 {
-	if (kvm_pmd_huge(*pmd)) {
-		pmd_clear(pmd);
-		kvm_tlb_flush_vmid_ipa(kvm, addr);
-	} else {
-		pte_t *pte_table = pte_offset_kernel(pmd, 0);
-		pmd_clear(pmd);
-		kvm_tlb_flush_vmid_ipa(kvm, addr);
-		pte_free_kernel(NULL, pte_table);
-	}
+	pte_t *pte_table = pte_offset_kernel(pmd, 0);
+	VM_BUG_ON(kvm_pmd_huge(*pmd));
+	pmd_clear(pmd);
+	kvm_tlb_flush_vmid_ipa(kvm, addr);
+	pte_free_kernel(NULL, pte_table);
 	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_range(struct kvm *kvm, pgd_t *pgdp,
-			unsigned long long start, u64 size)
+static void unmap_pmds(struct kvm *kvm, pud_t *pud,
+		       phys_addr_t addr, phys_addr_t end)
 {
-	pgd_t *pgd;
-	pud_t *pud;
-	pmd_t *pmd;
-	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);
-		pte = NULL;
-		if (pud_none(*pud)) {
-			addr = kvm_pud_addr_end(addr, end);
-			continue;
-		}
+	phys_addr_t next, start_addr = addr;
+	pmd_t *pmd, *start_pmd;
 
-		if (pud_huge(*pud)) {
-			/*
-			 * If we are dealing with a huge pud, just clear it and
-			 * move on.
-			 */
-			clear_pud_entry(kvm, pud, addr);
-			addr = kvm_pud_addr_end(addr, end);
-			continue;
+	start_pmd = pmd = pmd_offset(pud, addr);
+	do {
+		next = kvm_pmd_addr_end(addr, end);
+		if (!pmd_none(*pmd)) {
+			if (kvm_pmd_huge(*pmd)) {
+				pmd_clear(pmd);
+				kvm_tlb_flush_vmid_ipa(kvm, addr);
+				put_page(virt_to_page(pmd));
+			} else {
+				unmap_ptes(kvm, pmd, addr, next);
+			}
 		}
+	} while (pmd++, addr = next, addr != end);
 
-		pmd = pmd_offset(pud, addr);
-		if (pmd_none(*pmd)) {
-			addr = kvm_pmd_addr_end(addr, end);
-			continue;
-		}
+	if (kvm_pmd_table_empty(start_pmd))
+		clear_pud_entry(kvm, pud, start_addr);
+}
 
-		if (!kvm_pmd_huge(*pmd)) {
-			pte = pte_offset_kernel(pmd, addr);
-			clear_pte_entry(kvm, pte, addr);
-			next = addr + PAGE_SIZE;
-		}
+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;
 
-		/*
-		 * If the pmd entry is to be cleared, walk back up the ladder
-		 */
-		if (kvm_pmd_huge(*pmd) || (pte && page_empty(pte))) {
-			clear_pmd_entry(kvm, pmd, addr);
-			next = kvm_pmd_addr_end(addr, end);
-			if (page_empty(pmd) && !page_empty(pud)) {
-				clear_pud_entry(kvm, pud, addr);
-				next = kvm_pud_addr_end(addr, end);
+	start_pud = pud = pud_offset(pgd, addr);
+	do {
+		next = kvm_pud_addr_end(addr, end);
+		if (!pud_none(*pud)) {
+			if (pud_huge(*pud)) {
+				pud_clear(pud);
+				kvm_tlb_flush_vmid_ipa(kvm, addr);
+				put_page(virt_to_page(pud));
+			} else {
+				unmap_pmds(kvm, pud, addr, next);
 			}
 		}
+	} while (pud++, addr = next, addr != end);
 
-		addr = next;
-	}
+	if (kvm_pud_table_empty(start_pud))
+		clear_pgd_entry(kvm, pgd, start_addr);
+}
+
+
+static void unmap_range(struct kvm *kvm, pgd_t *pgdp,
+			phys_addr_t start, u64 size)
+{
+	pgd_t *pgd;
+	phys_addr_t addr = start, end = start + size;
+	phys_addr_t next;
+
+	pgd = pgdp + 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,
@@ -748,6 +759,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	struct kvm_mmu_memory_cache *memcache = &vcpu->arch.mmu_page_cache;
 	struct vm_area_struct *vma;
 	pfn_t pfn;
+	pgprot_t mem_type = PAGE_S2;
 
 	write_fault = kvm_is_write_fault(kvm_vcpu_get_hsr(vcpu));
 	if (fault_status == FSC_PERM && !write_fault) {
@@ -798,6 +810,9 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	if (is_error_pfn(pfn))
 		return -EFAULT;
 
+	if (kvm_is_mmio_pfn(pfn))
+		mem_type = PAGE_S2_DEVICE;
+
 	spin_lock(&kvm->mmu_lock);
 	if (mmu_notifier_retry(kvm, mmu_seq))
 		goto out_unlock;
@@ -805,7 +820,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		hugetlb = transparent_hugepage_adjust(&pfn, &fault_ipa);
 
 	if (hugetlb) {
-		pmd_t new_pmd = pfn_pmd(pfn, PAGE_S2);
+		pmd_t new_pmd = pfn_pmd(pfn, mem_type);
 		new_pmd = pmd_mkhuge(new_pmd);
 		if (writable) {
 			kvm_set_s2pmd_writable(&new_pmd);
@@ -814,13 +829,14 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		coherent_cache_guest_page(vcpu, hva & PMD_MASK, PMD_SIZE);
 		ret = stage2_set_pmd_huge(kvm, memcache, fault_ipa, &new_pmd);
 	} else {
-		pte_t new_pte = pfn_pte(pfn, PAGE_S2);
+		pte_t new_pte = pfn_pte(pfn, mem_type);
 		if (writable) {
 			kvm_set_s2pte_writable(&new_pte);
 			kvm_set_pfn_dirty(pfn);
 		}
 		coherent_cache_guest_page(vcpu, hva, PAGE_SIZE);
-		ret = stage2_set_pte(kvm, memcache, fault_ipa, &new_pte, false);
+		ret = stage2_set_pte(kvm, memcache, fault_ipa, &new_pte,
+				     mem_type == PAGE_S2_DEVICE);
 	}
 
 
@@ -1100,3 +1116,49 @@ 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)
+{
+	return 0;
+}
+
+void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
+			   struct kvm_memory_slot *dont)
+{
+}
+
+int kvm_arch_create_memslot(struct kvm *kvm, 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)
+{
+}