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]

32 files changed, 1928 insertions, 389 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)
+{
+}
diff --git a/arch/arm64/include/asm/debug-monitors.h b/arch/arm64/include/asm/debug-monitors.h
index 6e9b5b36921c..7fb343779498 100644
--- a/arch/arm64/include/asm/debug-monitors.h
+++ b/arch/arm64/include/asm/debug-monitors.h
@@ -18,6 +18,15 @@
 
 #ifdef __KERNEL__
 
+/* Low-level stepping controls. */
+#define DBG_MDSCR_SS		(1 << 0)
+#define DBG_SPSR_SS		(1 << 21)
+
+/* MDSCR_EL1 enabling bits */
+#define DBG_MDSCR_KDE		(1 << 13)
+#define DBG_MDSCR_MDE		(1 << 15)
+#define DBG_MDSCR_MASK		~(DBG_MDSCR_KDE | DBG_MDSCR_MDE)
+
 #define	DBG_ESR_EVT(x)		(((x) >> 27) & 0x7)
 
 /* AArch64 */
@@ -73,11 +82,6 @@
 
 #define CACHE_FLUSH_IS_SAFE		1
 
-enum debug_el {
-	DBG_ACTIVE_EL0 = 0,
-	DBG_ACTIVE_EL1,
-};
-
 /* AArch32 */
 #define DBG_ESR_EVT_BKPT	0x4
 #define DBG_ESR_EVT_VECC	0x5
@@ -115,6 +119,11 @@ void unregister_break_hook(struct break_hook *hook);
 
 u8 debug_monitors_arch(void);
 
+enum debug_el {
+	DBG_ACTIVE_EL0 = 0,
+	DBG_ACTIVE_EL1,
+};
+
 void enable_debug_monitors(enum debug_el el);
 void disable_debug_monitors(enum debug_el el);
 
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 3d6903006a8a..cc83520459ed 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -76,9 +76,10 @@
  */
 #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)
+			 HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW)
 #define HCR_VIRT_EXCP_MASK (HCR_VA | HCR_VI | HCR_VF)
+#define HCR_INT_OVERRIDE   (HCR_FMO | HCR_IMO)
+
 
 /* Hyp System Control Register (SCTLR_EL2) bits */
 #define SCTLR_EL2_EE	(1 << 25)
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 9fcd54b1e16d..483842180f8f 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -18,6 +18,8 @@
 #ifndef __ARM_KVM_ASM_H__
 #define __ARM_KVM_ASM_H__
 
+#include <asm/virt.h>
+
 /*
  * 0 is reserved as an invalid value.
  * Order *must* be kept in sync with the hyp switch code.
@@ -43,14 +45,25 @@
 #define	AMAIR_EL1	19	/* Aux Memory Attribute Indirection Register */
 #define	CNTKCTL_EL1	20	/* Timer Control Register (EL1) */
 #define	PAR_EL1		21	/* Physical Address Register */
+#define MDSCR_EL1	22	/* Monitor Debug System Control Register */
+#define DBGBCR0_EL1	23	/* Debug Breakpoint Control Registers (0-15) */
+#define DBGBCR15_EL1	38
+#define DBGBVR0_EL1	39	/* Debug Breakpoint Value Registers (0-15) */
+#define DBGBVR15_EL1	54
+#define DBGWCR0_EL1	55	/* Debug Watchpoint Control Registers (0-15) */
+#define DBGWCR15_EL1	70
+#define DBGWVR0_EL1	71	/* Debug Watchpoint Value Registers (0-15) */
+#define DBGWVR15_EL1	86
+#define MDCCINT_EL1	87	/* Monitor Debug Comms Channel Interrupt Enable Reg */
+
 /* 32bit specific registers. Keep them at the end of the range */
-#define	DACR32_EL2	22	/* Domain Access Control Register */
-#define	IFSR32_EL2	23	/* Instruction Fault Status Register */
-#define	FPEXC32_EL2	24	/* Floating-Point Exception Control Register */
-#define	DBGVCR32_EL2	25	/* Debug Vector Catch Register */
-#define	TEECR32_EL1	26	/* ThumbEE Configuration Register */
-#define	TEEHBR32_EL1	27	/* ThumbEE Handler Base Register */
-#define	NR_SYS_REGS	28
+#define	DACR32_EL2	88	/* Domain Access Control Register */
+#define	IFSR32_EL2	89	/* Instruction Fault Status Register */
+#define	FPEXC32_EL2	90	/* Floating-Point Exception Control Register */
+#define	DBGVCR32_EL2	91	/* Debug Vector Catch Register */
+#define	TEECR32_EL1	92	/* ThumbEE Configuration Register */
+#define	TEEHBR32_EL1	93	/* ThumbEE Handler Base Register */
+#define	NR_SYS_REGS	94
 
 /* 32bit mapping */
 #define c0_MPIDR	(MPIDR_EL1 * 2)	/* MultiProcessor ID Register */
@@ -82,11 +95,23 @@
 #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)
+
+#define cp14_DBGDSCRext	(MDSCR_EL1 * 2)
+#define cp14_DBGBCR0	(DBGBCR0_EL1 * 2)
+#define cp14_DBGBVR0	(DBGBVR0_EL1 * 2)
+#define cp14_DBGBXVR0	(cp14_DBGBVR0 + 1)
+#define cp14_DBGWCR0	(DBGWCR0_EL1 * 2)
+#define cp14_DBGWVR0	(DBGWVR0_EL1 * 2)
+#define cp14_DBGDCCINT	(MDCCINT_EL1 * 2)
+
+#define NR_COPRO_REGS	(NR_SYS_REGS * 2)
 
 #define ARM_EXCEPTION_IRQ	  0
 #define ARM_EXCEPTION_TRAP	  1
 
+#define KVM_ARM64_DEBUG_DIRTY_SHIFT	0
+#define KVM_ARM64_DEBUG_DIRTY		(1 << KVM_ARM64_DEBUG_DIRTY_SHIFT)
+
 #ifndef __ASSEMBLY__
 struct kvm;
 struct kvm_vcpu;
@@ -96,13 +121,21 @@ extern char __kvm_hyp_init_end[];
 
 extern char __kvm_hyp_vector[];
 
-extern char __kvm_hyp_code_start[];
-extern char __kvm_hyp_code_end[];
+#define	__kvm_hyp_code_start	__hyp_text_start
+#define	__kvm_hyp_code_end	__hyp_text_end
 
 extern void __kvm_flush_vm_context(void);
 extern void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa);
 
 extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
+
+extern u64 __vgic_v3_get_ich_vtr_el2(void);
+
+extern char __save_vgic_v2_state[];
+extern char __restore_vgic_v2_state[];
+extern char __save_vgic_v3_state[];
+extern char __restore_vgic_v3_state[];
+
 #endif
 
 #endif /* __ARM_KVM_ASM_H__ */
diff --git a/arch/arm64/include/asm/kvm_coproc.h b/arch/arm64/include/asm/kvm_coproc.h
index 9a59301cd014..0b52377a6c11 100644
--- a/arch/arm64/include/asm/kvm_coproc.h
+++ b/arch/arm64/include/asm/kvm_coproc.h
@@ -39,7 +39,8 @@ void kvm_register_target_sys_reg_table(unsigned int target,
 				       struct kvm_sys_reg_target_table *table);
 
 int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu, struct kvm_run *run);
-int kvm_handle_cp14_access(struct kvm_vcpu *vcpu, struct kvm_run *run);
+int kvm_handle_cp14_32(struct kvm_vcpu *vcpu, struct kvm_run *run);
+int kvm_handle_cp14_64(struct kvm_vcpu *vcpu, struct kvm_run *run);
 int kvm_handle_cp15_32(struct kvm_vcpu *vcpu, struct kvm_run *run);
 int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run);
 int kvm_handle_sys_reg(struct kvm_vcpu *vcpu, struct kvm_run *run);
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index dd8ecfc3f995..fdc3e21abd8d 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -213,6 +213,17 @@ static inline unsigned long vcpu_data_guest_to_host(struct kvm_vcpu *vcpu,
 		default:
 			return be64_to_cpu(data);
 		}
+	} else {
+		switch (len) {
+		case 1:
+			return data & 0xff;
+		case 2:
+			return le16_to_cpu(data & 0xffff);
+		case 4:
+			return le32_to_cpu(data & 0xffffffff);
+		default:
+			return le64_to_cpu(data);
+		}
 	}
 
 	return data;		/* Leave LE untouched */
@@ -233,6 +244,17 @@ static inline unsigned long vcpu_data_host_to_guest(struct kvm_vcpu *vcpu,
 		default:
 			return cpu_to_be64(data);
 		}
+	} else {
+		switch (len) {
+		case 1:
+			return data & 0xff;
+		case 2:
+			return cpu_to_le16(data & 0xffff);
+		case 4:
+			return cpu_to_le32(data & 0xffffffff);
+		default:
+			return cpu_to_le64(data);
+		}
 	}
 
 	return data;		/* Leave LE untouched */
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 92242ce06309..e10c45a578e3 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -86,7 +86,7 @@ struct kvm_cpu_context {
 	struct kvm_regs	gp_regs;
 	union {
 		u64 sys_regs[NR_SYS_REGS];
-		u32 cp15[NR_CP15_REGS];
+		u32 copro[NR_COPRO_REGS];
 	};
 };
 
@@ -101,6 +101,9 @@ struct kvm_vcpu_arch {
 	/* Exception Information */
 	struct kvm_vcpu_fault_info fault;
 
+	/* Debug state */
+	u64 debug_flags;
+
 	/* Pointer to host CPU context */
 	kvm_cpu_context_t *host_cpu_context;
 
@@ -138,7 +141,20 @@ struct kvm_vcpu_arch {
 
 #define vcpu_gp_regs(v)		(&(v)->arch.ctxt.gp_regs)
 #define vcpu_sys_reg(v,r)	((v)->arch.ctxt.sys_regs[(r)])
-#define vcpu_cp15(v,r)		((v)->arch.ctxt.cp15[(r)])
+/*
+ * CP14 and CP15 live in the same array, as they are backed by the
+ * same system registers.
+ */
+#define vcpu_cp14(v,r)		((v)->arch.ctxt.copro[(r)])
+#define vcpu_cp15(v,r)		((v)->arch.ctxt.copro[(r)])
+
+#ifdef CONFIG_CPU_BIG_ENDIAN
+#define vcpu_cp15_64_high(v,r)	vcpu_cp15((v),(r))
+#define vcpu_cp15_64_low(v,r)	vcpu_cp15((v),(r) + 1)
+#else
+#define vcpu_cp15_64_high(v,r)	vcpu_cp15((v),(r) + 1)
+#define vcpu_cp15_64_low(v,r)	vcpu_cp15((v),(r))
+#endif
 
 struct kvm_vm_stat {
 	u32 remote_tlb_flush;
@@ -200,4 +216,32 @@ static inline void __cpu_init_hyp_mode(phys_addr_t boot_pgd_ptr,
 		     hyp_stack_ptr, vector_ptr);
 }
 
+struct vgic_sr_vectors {
+	void	*save_vgic;
+	void	*restore_vgic;
+};
+
+static inline void vgic_arch_setup(const struct vgic_params *vgic)
+{
+	extern struct vgic_sr_vectors __vgic_sr_vectors;
+
+	switch(vgic->type)
+	{
+	case VGIC_V2:
+		__vgic_sr_vectors.save_vgic	= __save_vgic_v2_state;
+		__vgic_sr_vectors.restore_vgic	= __restore_vgic_v2_state;
+		break;
+
+#ifdef CONFIG_ARM_GIC_V3
+	case VGIC_V3:
+		__vgic_sr_vectors.save_vgic	= __save_vgic_v3_state;
+		__vgic_sr_vectors.restore_vgic	= __restore_vgic_v3_state;
+		break;
+#endif
+
+	default:
+		BUG();
+	}
+}
+
 #endif /* __ARM64_KVM_HOST_H__ */
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 7d29847a893b..8e138c7c53ac 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -125,6 +125,21 @@ static inline void kvm_set_s2pmd_writable(pmd_t *pmd)
 #define kvm_pud_addr_end(addr, end)	pud_addr_end(addr, end)
 #define kvm_pmd_addr_end(addr, end)	pmd_addr_end(addr, 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)
+#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;
 
 #define kvm_flush_dcache_to_poc(a,l)	__flush_dcache_area((a), (l))
diff --git a/arch/arm64/include/asm/virt.h b/arch/arm64/include/asm/virt.h
index 215ad4649dd7..7a5df5252dd7 100644
--- a/arch/arm64/include/asm/virt.h
+++ b/arch/arm64/include/asm/virt.h
@@ -50,6 +50,10 @@ static inline bool is_hyp_mode_mismatched(void)
 	return __boot_cpu_mode[0] != __boot_cpu_mode[1];
 }
 
+/* The section containing the hypervisor text */
+extern char __hyp_text_start[];
+extern char __hyp_text_end[];
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* ! __ASM__VIRT_H */
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 646f888387cd..9a9fce090d58 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -120,6 +120,7 @@ int main(void)
   DEFINE(VCPU_ESR_EL2,		offsetof(struct kvm_vcpu, arch.fault.esr_el2));
   DEFINE(VCPU_FAR_EL2,		offsetof(struct kvm_vcpu, arch.fault.far_el2));
   DEFINE(VCPU_HPFAR_EL2,	offsetof(struct kvm_vcpu, arch.fault.hpfar_el2));
+  DEFINE(VCPU_DEBUG_FLAGS,	offsetof(struct kvm_vcpu, arch.debug_flags));
   DEFINE(VCPU_HCR_EL2,		offsetof(struct kvm_vcpu, arch.hcr_el2));
   DEFINE(VCPU_IRQ_LINES,	offsetof(struct kvm_vcpu, arch.irq_lines));
   DEFINE(VCPU_HOST_CONTEXT,	offsetof(struct kvm_vcpu, arch.host_cpu_context));
@@ -129,13 +130,24 @@ int main(void)
   DEFINE(KVM_TIMER_ENABLED,	offsetof(struct kvm, arch.timer.enabled));
   DEFINE(VCPU_KVM,		offsetof(struct kvm_vcpu, kvm));
   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_SAVE_FN,		offsetof(struct vgic_sr_vectors, save_vgic));
+  DEFINE(VGIC_RESTORE_FN,	offsetof(struct vgic_sr_vectors, restore_vgic));
+  DEFINE(VGIC_SR_VECTOR_SZ,	sizeof(struct vgic_sr_vectors));
+  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_V3_CPU_HCR,	offsetof(struct vgic_cpu, vgic_v3.vgic_hcr));
+  DEFINE(VGIC_V3_CPU_VMCR,	offsetof(struct vgic_cpu, vgic_v3.vgic_vmcr));
+  DEFINE(VGIC_V3_CPU_MISR,	offsetof(struct vgic_cpu, vgic_v3.vgic_misr));
+  DEFINE(VGIC_V3_CPU_EISR,	offsetof(struct vgic_cpu, vgic_v3.vgic_eisr));
+  DEFINE(VGIC_V3_CPU_ELRSR,	offsetof(struct vgic_cpu, vgic_v3.vgic_elrsr));
+  DEFINE(VGIC_V3_CPU_AP0R,	offsetof(struct vgic_cpu, vgic_v3.vgic_ap0r));
+  DEFINE(VGIC_V3_CPU_AP1R,	offsetof(struct vgic_cpu, vgic_v3.vgic_ap1r));
+  DEFINE(VGIC_V3_CPU_LR,	offsetof(struct vgic_cpu, vgic_v3.vgic_lr));
   DEFINE(VGIC_CPU_NR_LR,	offsetof(struct vgic_cpu, nr_lr));
   DEFINE(KVM_VTTBR,		offsetof(struct kvm, arch.vttbr));
   DEFINE(KVM_VGIC_VCTRL,	offsetof(struct kvm, arch.vgic.vctrl_base));
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index fe5b94078d82..b056369fd47d 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -30,15 +30,6 @@
 #include <asm/cputype.h>
 #include <asm/system_misc.h>
 
-/* Low-level stepping controls. */
-#define DBG_MDSCR_SS		(1 << 0)
-#define DBG_SPSR_SS		(1 << 21)
-
-/* MDSCR_EL1 enabling bits */
-#define DBG_MDSCR_KDE		(1 << 13)
-#define DBG_MDSCR_MDE		(1 << 15)
-#define DBG_MDSCR_MASK		~(DBG_MDSCR_KDE | DBG_MDSCR_MDE)
-
 /* Determine debug architecture. */
 u8 debug_monitors_arch(void)
 {
diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile
index 72a9fd583ad3..32a096174b94 100644
--- a/arch/arm64/kvm/Makefile
+++ b/arch/arm64/kvm/Makefile
@@ -20,4 +20,8 @@ kvm-$(CONFIG_KVM_ARM_HOST) += hyp.o hyp-init.o handle_exit.o
 kvm-$(CONFIG_KVM_ARM_HOST) += guest.o reset.o sys_regs.o sys_regs_generic_v8.o
 
 kvm-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic.o
+kvm-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic-v2.o
+kvm-$(CONFIG_KVM_ARM_VGIC) += vgic-v2-switch.o
+kvm-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic-v3.o
+kvm-$(CONFIG_KVM_ARM_VGIC) += vgic-v3-switch.o
 kvm-$(CONFIG_KVM_ARM_TIMER) += $(KVM)/arm/arch_timer.o
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index 60b5c31f3c10..8d1ec2887a26 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -136,13 +136,67 @@ static unsigned long num_core_regs(void)
 }
 
 /**
+ * ARM64 versions of the TIMER registers, always available on arm64
+ */
+
+#define NUM_TIMER_REGS 3
+
+static bool is_timer_reg(u64 index)
+{
+	switch (index) {
+	case KVM_REG_ARM_TIMER_CTL:
+	case KVM_REG_ARM_TIMER_CNT:
+	case KVM_REG_ARM_TIMER_CVAL:
+		return true;
+	}
+	return false;
+}
+
+static int copy_timer_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
+{
+	if (put_user(KVM_REG_ARM_TIMER_CTL, uindices))
+		return -EFAULT;
+	uindices++;
+	if (put_user(KVM_REG_ARM_TIMER_CNT, uindices))
+		return -EFAULT;
+	uindices++;
+	if (put_user(KVM_REG_ARM_TIMER_CVAL, uindices))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int set_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
+{
+	void __user *uaddr = (void __user *)(long)reg->addr;
+	u64 val;
+	int ret;
+
+	ret = copy_from_user(&val, uaddr, KVM_REG_SIZE(reg->id));
+	if (ret != 0)
+		return ret;
+
+	return kvm_arm_timer_set_reg(vcpu, reg->id, val);
+}
+
+static int get_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
+{
+	void __user *uaddr = (void __user *)(long)reg->addr;
+	u64 val;
+
+	val = kvm_arm_timer_get_reg(vcpu, reg->id);
+	return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id));
+}
+
+/**
  * kvm_arm_num_regs - how many registers do we present via KVM_GET_ONE_REG
  *
  * This is for all registers.
  */
 unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu)
 {
-	return num_core_regs() + kvm_arm_num_sys_reg_descs(vcpu);
+	return num_core_regs() + kvm_arm_num_sys_reg_descs(vcpu)
+                + NUM_TIMER_REGS;
 }
 
 /**
@@ -154,6 +208,7 @@ int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
 {
 	unsigned int i;
 	const u64 core_reg = KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE;
+	int ret;
 
 	for (i = 0; i < sizeof(struct kvm_regs) / sizeof(__u32); i++) {
 		if (put_user(core_reg | i, uindices))
@@ -161,6 +216,11 @@ int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
 		uindices++;
 	}
 
+	ret = copy_timer_indices(vcpu, uindices);
+	if (ret)
+		return ret;
+	uindices += NUM_TIMER_REGS;
+
 	return kvm_arm_copy_sys_reg_indices(vcpu, uindices);
 }
 
@@ -174,6 +234,9 @@ int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_CORE)
 		return get_core_reg(vcpu, reg);
 
+	if (is_timer_reg(reg->id))
+		return get_timer_reg(vcpu, reg);
+
 	return kvm_arm_sys_reg_get_reg(vcpu, reg);
 }
 
@@ -187,6 +250,9 @@ int kvm_arm_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_CORE)
 		return set_core_reg(vcpu, reg);
 
+	if (is_timer_reg(reg->id))
+		return set_timer_reg(vcpu, reg);
+
 	return kvm_arm_sys_reg_set_reg(vcpu, reg);
 }
 
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index 182415e1a952..e28be510380c 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -73,9 +73,9 @@ static exit_handle_fn arm_exit_handlers[] = {
 	[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,
+	[ESR_EL2_EC_CP14_MR]	= kvm_handle_cp14_32,
 	[ESR_EL2_EC_CP14_LS]	= kvm_handle_cp14_load_store,
-	[ESR_EL2_EC_CP14_64]	= kvm_handle_cp14_access,
+	[ESR_EL2_EC_CP14_64]	= kvm_handle_cp14_64,
 	[ESR_EL2_EC_HVC32]	= handle_hvc,
 	[ESR_EL2_EC_SMC32]	= handle_smc,
 	[ESR_EL2_EC_HVC64]	= handle_hvc,
diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S
index b0d1512acf08..b72aa9f9215c 100644
--- a/arch/arm64/kvm/hyp.S
+++ b/arch/arm64/kvm/hyp.S
@@ -16,11 +16,11 @@
  */
 
 #include <linux/linkage.h>
-#include <linux/irqchip/arm-gic.h>
 
 #include <asm/assembler.h>
 #include <asm/memory.h>
 #include <asm/asm-offsets.h>
+#include <asm/debug-monitors.h>
 #include <asm/fpsimdmacros.h>
 #include <asm/kvm.h>
 #include <asm/kvm_asm.h>
@@ -36,9 +36,6 @@
 	.pushsection	.hyp.text, "ax"
 	.align	PAGE_SHIFT
 
-__kvm_hyp_code_start:
-	.globl __kvm_hyp_code_start
-
 .macro save_common_regs
 	// x2: base address for cpu context
 	// x3: tmp register
@@ -215,6 +212,7 @@ __kvm_hyp_code_start:
 	mrs	x22, 	amair_el1
 	mrs	x23, 	cntkctl_el1
 	mrs	x24,	par_el1
+	mrs	x25,	mdscr_el1
 
 	stp	x4, x5, [x3]
 	stp	x6, x7, [x3, #16]
@@ -226,7 +224,202 @@ __kvm_hyp_code_start:
 	stp	x18, x19, [x3, #112]
 	stp	x20, x21, [x3, #128]
 	stp	x22, x23, [x3, #144]
-	str	x24, [x3, #160]
+	stp	x24, x25, [x3, #160]
+.endm
+
+.macro save_debug
+	// x2: base address for cpu context
+	// x3: tmp register
+
+	mrs	x26, id_aa64dfr0_el1
+	ubfx	x24, x26, #12, #4	// Extract BRPs
+	ubfx	x25, x26, #20, #4	// Extract WRPs
+	mov	w26, #15
+	sub	w24, w26, w24		// How many BPs to skip
+	sub	w25, w26, w25		// How many WPs to skip
+
+	add	x3, x2, #CPU_SYSREG_OFFSET(DBGBCR0_EL1)
+
+	adr	x26, 1f
+	add	x26, x26, x24, lsl #2
+	br	x26
+1:
+	mrs	x20, dbgbcr15_el1
+	mrs	x19, dbgbcr14_el1
+	mrs	x18, dbgbcr13_el1
+	mrs	x17, dbgbcr12_el1
+	mrs	x16, dbgbcr11_el1
+	mrs	x15, dbgbcr10_el1
+	mrs	x14, dbgbcr9_el1
+	mrs	x13, dbgbcr8_el1
+	mrs	x12, dbgbcr7_el1
+	mrs	x11, dbgbcr6_el1
+	mrs	x10, dbgbcr5_el1
+	mrs	x9, dbgbcr4_el1
+	mrs	x8, dbgbcr3_el1
+	mrs	x7, dbgbcr2_el1
+	mrs	x6, dbgbcr1_el1
+	mrs	x5, dbgbcr0_el1
+
+	adr	x26, 1f
+	add	x26, x26, x24, lsl #2
+	br	x26
+
+1:
+	str	x20, [x3, #(15 * 8)]
+	str	x19, [x3, #(14 * 8)]
+	str	x18, [x3, #(13 * 8)]
+	str	x17, [x3, #(12 * 8)]
+	str	x16, [x3, #(11 * 8)]
+	str	x15, [x3, #(10 * 8)]
+	str	x14, [x3, #(9 * 8)]
+	str	x13, [x3, #(8 * 8)]
+	str	x12, [x3, #(7 * 8)]
+	str	x11, [x3, #(6 * 8)]
+	str	x10, [x3, #(5 * 8)]
+	str	x9, [x3, #(4 * 8)]
+	str	x8, [x3, #(3 * 8)]
+	str	x7, [x3, #(2 * 8)]
+	str	x6, [x3, #(1 * 8)]
+	str	x5, [x3, #(0 * 8)]
+
+	add	x3, x2, #CPU_SYSREG_OFFSET(DBGBVR0_EL1)
+
+	adr	x26, 1f
+	add	x26, x26, x24, lsl #2
+	br	x26
+1:
+	mrs	x20, dbgbvr15_el1
+	mrs	x19, dbgbvr14_el1
+	mrs	x18, dbgbvr13_el1
+	mrs	x17, dbgbvr12_el1
+	mrs	x16, dbgbvr11_el1
+	mrs	x15, dbgbvr10_el1
+	mrs	x14, dbgbvr9_el1
+	mrs	x13, dbgbvr8_el1
+	mrs	x12, dbgbvr7_el1
+	mrs	x11, dbgbvr6_el1
+	mrs	x10, dbgbvr5_el1
+	mrs	x9, dbgbvr4_el1
+	mrs	x8, dbgbvr3_el1
+	mrs	x7, dbgbvr2_el1
+	mrs	x6, dbgbvr1_el1
+	mrs	x5, dbgbvr0_el1
+
+	adr	x26, 1f
+	add	x26, x26, x24, lsl #2
+	br	x26
+
+1:
+	str	x20, [x3, #(15 * 8)]
+	str	x19, [x3, #(14 * 8)]
+	str	x18, [x3, #(13 * 8)]
+	str	x17, [x3, #(12 * 8)]
+	str	x16, [x3, #(11 * 8)]
+	str	x15, [x3, #(10 * 8)]
+	str	x14, [x3, #(9 * 8)]
+	str	x13, [x3, #(8 * 8)]
+	str	x12, [x3, #(7 * 8)]
+	str	x11, [x3, #(6 * 8)]
+	str	x10, [x3, #(5 * 8)]
+	str	x9, [x3, #(4 * 8)]
+	str	x8, [x3, #(3 * 8)]
+	str	x7, [x3, #(2 * 8)]
+	str	x6, [x3, #(1 * 8)]
+	str	x5, [x3, #(0 * 8)]
+
+	add	x3, x2, #CPU_SYSREG_OFFSET(DBGWCR0_EL1)
+
+	adr	x26, 1f
+	add	x26, x26, x25, lsl #2
+	br	x26
+1:
+	mrs	x20, dbgwcr15_el1
+	mrs	x19, dbgwcr14_el1
+	mrs	x18, dbgwcr13_el1
+	mrs	x17, dbgwcr12_el1
+	mrs	x16, dbgwcr11_el1
+	mrs	x15, dbgwcr10_el1
+	mrs	x14, dbgwcr9_el1
+	mrs	x13, dbgwcr8_el1
+	mrs	x12, dbgwcr7_el1
+	mrs	x11, dbgwcr6_el1
+	mrs	x10, dbgwcr5_el1
+	mrs	x9, dbgwcr4_el1
+	mrs	x8, dbgwcr3_el1
+	mrs	x7, dbgwcr2_el1
+	mrs	x6, dbgwcr1_el1
+	mrs	x5, dbgwcr0_el1
+
+	adr	x26, 1f
+	add	x26, x26, x25, lsl #2
+	br	x26
+
+1:
+	str	x20, [x3, #(15 * 8)]
+	str	x19, [x3, #(14 * 8)]
+	str	x18, [x3, #(13 * 8)]
+	str	x17, [x3, #(12 * 8)]
+	str	x16, [x3, #(11 * 8)]
+	str	x15, [x3, #(10 * 8)]
+	str	x14, [x3, #(9 * 8)]
+	str	x13, [x3, #(8 * 8)]
+	str	x12, [x3, #(7 * 8)]
+	str	x11, [x3, #(6 * 8)]
+	str	x10, [x3, #(5 * 8)]
+	str	x9, [x3, #(4 * 8)]
+	str	x8, [x3, #(3 * 8)]
+	str	x7, [x3, #(2 * 8)]
+	str	x6, [x3, #(1 * 8)]
+	str	x5, [x3, #(0 * 8)]
+
+	add	x3, x2, #CPU_SYSREG_OFFSET(DBGWVR0_EL1)
+
+	adr	x26, 1f
+	add	x26, x26, x25, lsl #2
+	br	x26
+1:
+	mrs	x20, dbgwvr15_el1
+	mrs	x19, dbgwvr14_el1
+	mrs	x18, dbgwvr13_el1
+	mrs	x17, dbgwvr12_el1
+	mrs	x16, dbgwvr11_el1
+	mrs	x15, dbgwvr10_el1
+	mrs	x14, dbgwvr9_el1
+	mrs	x13, dbgwvr8_el1
+	mrs	x12, dbgwvr7_el1
+	mrs	x11, dbgwvr6_el1
+	mrs	x10, dbgwvr5_el1
+	mrs	x9, dbgwvr4_el1
+	mrs	x8, dbgwvr3_el1
+	mrs	x7, dbgwvr2_el1
+	mrs	x6, dbgwvr1_el1
+	mrs	x5, dbgwvr0_el1
+
+	adr	x26, 1f
+	add	x26, x26, x25, lsl #2
+	br	x26
+
+1:
+	str	x20, [x3, #(15 * 8)]
+	str	x19, [x3, #(14 * 8)]
+	str	x18, [x3, #(13 * 8)]
+	str	x17, [x3, #(12 * 8)]
+	str	x16, [x3, #(11 * 8)]
+	str	x15, [x3, #(10 * 8)]
+	str	x14, [x3, #(9 * 8)]
+	str	x13, [x3, #(8 * 8)]
+	str	x12, [x3, #(7 * 8)]
+	str	x11, [x3, #(6 * 8)]
+	str	x10, [x3, #(5 * 8)]
+	str	x9, [x3, #(4 * 8)]
+	str	x8, [x3, #(3 * 8)]
+	str	x7, [x3, #(2 * 8)]
+	str	x6, [x3, #(1 * 8)]
+	str	x5, [x3, #(0 * 8)]
+
+	mrs	x21, mdccint_el1
+	str	x21, [x2, #CPU_SYSREG_OFFSET(MDCCINT_EL1)]
 .endm
 
 .macro restore_sysregs
@@ -245,7 +438,7 @@ __kvm_hyp_code_start:
 	ldp	x18, x19, [x3, #112]
 	ldp	x20, x21, [x3, #128]
 	ldp	x22, x23, [x3, #144]
-	ldr	x24, [x3, #160]
+	ldp	x24, x25, [x3, #160]
 
 	msr	vmpidr_el2,	x4
 	msr	csselr_el1,	x5
@@ -268,6 +461,198 @@ __kvm_hyp_code_start:
 	msr	amair_el1,	x22
 	msr	cntkctl_el1,	x23
 	msr	par_el1,	x24
+	msr	mdscr_el1,	x25
+.endm
+
+.macro restore_debug
+	// x2: base address for cpu context
+	// x3: tmp register
+
+	mrs	x26, id_aa64dfr0_el1
+	ubfx	x24, x26, #12, #4	// Extract BRPs
+	ubfx	x25, x26, #20, #4	// Extract WRPs
+	mov	w26, #15
+	sub	w24, w26, w24		// How many BPs to skip
+	sub	w25, w26, w25		// How many WPs to skip
+
+	add	x3, x2, #CPU_SYSREG_OFFSET(DBGBCR0_EL1)
+
+	adr	x26, 1f
+	add	x26, x26, x24, lsl #2
+	br	x26
+1:
+	ldr	x20, [x3, #(15 * 8)]
+	ldr	x19, [x3, #(14 * 8)]
+	ldr	x18, [x3, #(13 * 8)]
+	ldr	x17, [x3, #(12 * 8)]
+	ldr	x16, [x3, #(11 * 8)]
+	ldr	x15, [x3, #(10 * 8)]
+	ldr	x14, [x3, #(9 * 8)]
+	ldr	x13, [x3, #(8 * 8)]
+	ldr	x12, [x3, #(7 * 8)]
+	ldr	x11, [x3, #(6 * 8)]
+	ldr	x10, [x3, #(5 * 8)]
+	ldr	x9, [x3, #(4 * 8)]
+	ldr	x8, [x3, #(3 * 8)]
+	ldr	x7, [x3, #(2 * 8)]
+	ldr	x6, [x3, #(1 * 8)]
+	ldr	x5, [x3, #(0 * 8)]
+
+	adr	x26, 1f
+	add	x26, x26, x24, lsl #2
+	br	x26
+1:
+	msr	dbgbcr15_el1, x20
+	msr	dbgbcr14_el1, x19
+	msr	dbgbcr13_el1, x18
+	msr	dbgbcr12_el1, x17
+	msr	dbgbcr11_el1, x16
+	msr	dbgbcr10_el1, x15
+	msr	dbgbcr9_el1, x14
+	msr	dbgbcr8_el1, x13
+	msr	dbgbcr7_el1, x12
+	msr	dbgbcr6_el1, x11
+	msr	dbgbcr5_el1, x10
+	msr	dbgbcr4_el1, x9
+	msr	dbgbcr3_el1, x8
+	msr	dbgbcr2_el1, x7
+	msr	dbgbcr1_el1, x6
+	msr	dbgbcr0_el1, x5
+
+	add	x3, x2, #CPU_SYSREG_OFFSET(DBGBVR0_EL1)
+
+	adr	x26, 1f
+	add	x26, x26, x24, lsl #2
+	br	x26
+1:
+	ldr	x20, [x3, #(15 * 8)]
+	ldr	x19, [x3, #(14 * 8)]
+	ldr	x18, [x3, #(13 * 8)]
+	ldr	x17, [x3, #(12 * 8)]
+	ldr	x16, [x3, #(11 * 8)]
+	ldr	x15, [x3, #(10 * 8)]
+	ldr	x14, [x3, #(9 * 8)]
+	ldr	x13, [x3, #(8 * 8)]
+	ldr	x12, [x3, #(7 * 8)]
+	ldr	x11, [x3, #(6 * 8)]
+	ldr	x10, [x3, #(5 * 8)]
+	ldr	x9, [x3, #(4 * 8)]
+	ldr	x8, [x3, #(3 * 8)]
+	ldr	x7, [x3, #(2 * 8)]
+	ldr	x6, [x3, #(1 * 8)]
+	ldr	x5, [x3, #(0 * 8)]
+
+	adr	x26, 1f
+	add	x26, x26, x24, lsl #2
+	br	x26
+1:
+	msr	dbgbvr15_el1, x20
+	msr	dbgbvr14_el1, x19
+	msr	dbgbvr13_el1, x18
+	msr	dbgbvr12_el1, x17
+	msr	dbgbvr11_el1, x16
+	msr	dbgbvr10_el1, x15
+	msr	dbgbvr9_el1, x14
+	msr	dbgbvr8_el1, x13
+	msr	dbgbvr7_el1, x12
+	msr	dbgbvr6_el1, x11
+	msr	dbgbvr5_el1, x10
+	msr	dbgbvr4_el1, x9
+	msr	dbgbvr3_el1, x8
+	msr	dbgbvr2_el1, x7
+	msr	dbgbvr1_el1, x6
+	msr	dbgbvr0_el1, x5
+
+	add	x3, x2, #CPU_SYSREG_OFFSET(DBGWCR0_EL1)
+
+	adr	x26, 1f
+	add	x26, x26, x25, lsl #2
+	br	x26
+1:
+	ldr	x20, [x3, #(15 * 8)]
+	ldr	x19, [x3, #(14 * 8)]
+	ldr	x18, [x3, #(13 * 8)]
+	ldr	x17, [x3, #(12 * 8)]
+	ldr	x16, [x3, #(11 * 8)]
+	ldr	x15, [x3, #(10 * 8)]
+	ldr	x14, [x3, #(9 * 8)]
+	ldr	x13, [x3, #(8 * 8)]
+	ldr	x12, [x3, #(7 * 8)]
+	ldr	x11, [x3, #(6 * 8)]
+	ldr	x10, [x3, #(5 * 8)]
+	ldr	x9, [x3, #(4 * 8)]
+	ldr	x8, [x3, #(3 * 8)]
+	ldr	x7, [x3, #(2 * 8)]
+	ldr	x6, [x3, #(1 * 8)]
+	ldr	x5, [x3, #(0 * 8)]
+
+	adr	x26, 1f
+	add	x26, x26, x25, lsl #2
+	br	x26
+1:
+	msr	dbgwcr15_el1, x20
+	msr	dbgwcr14_el1, x19
+	msr	dbgwcr13_el1, x18
+	msr	dbgwcr12_el1, x17
+	msr	dbgwcr11_el1, x16
+	msr	dbgwcr10_el1, x15
+	msr	dbgwcr9_el1, x14
+	msr	dbgwcr8_el1, x13
+	msr	dbgwcr7_el1, x12
+	msr	dbgwcr6_el1, x11
+	msr	dbgwcr5_el1, x10
+	msr	dbgwcr4_el1, x9
+	msr	dbgwcr3_el1, x8
+	msr	dbgwcr2_el1, x7
+	msr	dbgwcr1_el1, x6
+	msr	dbgwcr0_el1, x5
+
+	add	x3, x2, #CPU_SYSREG_OFFSET(DBGWVR0_EL1)
+
+	adr	x26, 1f
+	add	x26, x26, x25, lsl #2
+	br	x26
+1:
+	ldr	x20, [x3, #(15 * 8)]
+	ldr	x19, [x3, #(14 * 8)]
+	ldr	x18, [x3, #(13 * 8)]
+	ldr	x17, [x3, #(12 * 8)]
+	ldr	x16, [x3, #(11 * 8)]
+	ldr	x15, [x3, #(10 * 8)]
+	ldr	x14, [x3, #(9 * 8)]
+	ldr	x13, [x3, #(8 * 8)]
+	ldr	x12, [x3, #(7 * 8)]
+	ldr	x11, [x3, #(6 * 8)]
+	ldr	x10, [x3, #(5 * 8)]
+	ldr	x9, [x3, #(4 * 8)]
+	ldr	x8, [x3, #(3 * 8)]
+	ldr	x7, [x3, #(2 * 8)]
+	ldr	x6, [x3, #(1 * 8)]
+	ldr	x5, [x3, #(0 * 8)]
+
+	adr	x26, 1f
+	add	x26, x26, x25, lsl #2
+	br	x26
+1:
+	msr	dbgwvr15_el1, x20
+	msr	dbgwvr14_el1, x19
+	msr	dbgwvr13_el1, x18
+	msr	dbgwvr12_el1, x17
+	msr	dbgwvr11_el1, x16
+	msr	dbgwvr10_el1, x15
+	msr	dbgwvr9_el1, x14
+	msr	dbgwvr8_el1, x13
+	msr	dbgwvr7_el1, x12
+	msr	dbgwvr6_el1, x11
+	msr	dbgwvr5_el1, x10
+	msr	dbgwvr4_el1, x9
+	msr	dbgwvr3_el1, x8
+	msr	dbgwvr2_el1, x7
+	msr	dbgwvr1_el1, x6
+	msr	dbgwvr0_el1, x5
+
+	ldr	x21, [x2, #CPU_SYSREG_OFFSET(MDCCINT_EL1)]
+	msr	mdccint_el1, x21
 .endm
 
 .macro skip_32bit_state tmp, target
@@ -282,6 +667,35 @@ __kvm_hyp_code_start:
 	tbz	\tmp, #12, \target
 .endm
 
+.macro skip_debug_state tmp, target
+	ldr	\tmp, [x0, #VCPU_DEBUG_FLAGS]
+	tbz	\tmp, #KVM_ARM64_DEBUG_DIRTY_SHIFT, \target
+.endm
+
+.macro compute_debug_state target
+	// Compute debug state: If any of KDE, MDE or KVM_ARM64_DEBUG_DIRTY
+	// is set, we do a full save/restore cycle and disable trapping.
+	add	x25, x0, #VCPU_CONTEXT
+
+	// Check the state of MDSCR_EL1
+	ldr	x25, [x25, #CPU_SYSREG_OFFSET(MDSCR_EL1)]
+	and	x26, x25, #DBG_MDSCR_KDE
+	and	x25, x25, #DBG_MDSCR_MDE
+	adds	xzr, x25, x26
+	b.eq	9998f		// Nothing to see there
+
+	// If any interesting bits was set, we must set the flag
+	mov	x26, #KVM_ARM64_DEBUG_DIRTY
+	str	x26, [x0, #VCPU_DEBUG_FLAGS]
+	b	9999f		// Don't skip restore
+
+9998:
+	// Otherwise load the flags from memory in case we recently
+	// trapped
+	skip_debug_state x25, \target
+9999:
+.endm
+
 .macro save_guest_32bit_state
 	skip_32bit_state x3, 1f
 
@@ -297,10 +711,13 @@ __kvm_hyp_code_start:
 	mrs	x4, dacr32_el2
 	mrs	x5, ifsr32_el2
 	mrs	x6, fpexc32_el2
-	mrs	x7, dbgvcr32_el2
 	stp	x4, x5, [x3]
-	stp	x6, x7, [x3, #16]
+	str	x6, [x3, #16]
 
+	skip_debug_state x8, 2f
+	mrs	x7, dbgvcr32_el2
+	str	x7, [x3, #24]
+2:
 	skip_tee_state x8, 1f
 
 	add	x3, x2, #CPU_SYSREG_OFFSET(TEECR32_EL1)
@@ -323,12 +740,15 @@ __kvm_hyp_code_start:
 
 	add	x3, x2, #CPU_SYSREG_OFFSET(DACR32_EL2)
 	ldp	x4, x5, [x3]
-	ldp	x6, x7, [x3, #16]
+	ldr	x6, [x3, #16]
 	msr	dacr32_el2, x4
 	msr	ifsr32_el2, x5
 	msr	fpexc32_el2, x6
-	msr	dbgvcr32_el2, x7
 
+	skip_debug_state x8, 2f
+	ldr	x7, [x3, #24]
+	msr	dbgvcr32_el2, x7
+2:
 	skip_tee_state x8, 1f
 
 	add	x3, x2, #CPU_SYSREG_OFFSET(TEECR32_EL1)
@@ -339,11 +759,8 @@ __kvm_hyp_code_start:
 .endm
 
 .macro activate_traps
-	ldr	x2, [x0, #VCPU_IRQ_LINES]
-	ldr	x1, [x0, #VCPU_HCR_EL2]
-	orr	x2, x2, x1
-	msr	hcr_el2, x2
-
+	ldr     x2, [x0, #VCPU_HCR_EL2]
+	msr     hcr_el2, x2
 	ldr	x2, =(CPTR_EL2_TTA)
 	msr	cptr_el2, x2
 
@@ -353,6 +770,14 @@ __kvm_hyp_code_start:
 	mrs	x2, mdcr_el2
 	and	x2, x2, #MDCR_EL2_HPMN_MASK
 	orr	x2, x2, #(MDCR_EL2_TPM | MDCR_EL2_TPMCR)
+	orr	x2, x2, #(MDCR_EL2_TDRA | MDCR_EL2_TDOSA)
+
+	// Check for KVM_ARM64_DEBUG_DIRTY, and set debug to trap
+	// if not dirty.
+	ldr	x3, [x0, #VCPU_DEBUG_FLAGS]
+	tbnz	x3, #KVM_ARM64_DEBUG_DIRTY_SHIFT, 1f
+	orr	x2, x2,  #MDCR_EL2_TDA
+1:
 	msr	mdcr_el2, x2
 .endm
 
@@ -379,100 +804,33 @@ __kvm_hyp_code_start:
 .endm
 
 /*
- * Save the VGIC CPU state into memory
- * x0: Register pointing to VCPU struct
- * Do not corrupt x1!!!
+ * Call into the vgic backend for state saving
  */
 .macro save_vgic_state
-	/* Get VGIC VCTRL base into x2 */
-	ldr	x2, [x0, #VCPU_KVM]
-	kern_hyp_va	x2
-	ldr	x2, [x2, #KVM_VGIC_VCTRL]
-	kern_hyp_va	x2
-	cbz	x2, 2f		// disabled
-
-	/* Compute the address of struct vgic_cpu */
-	add	x3, x0, #VCPU_VGIC_CPU
-
-	/* Save all interesting registers */
-	ldr	w4, [x2, #GICH_HCR]
-	ldr	w5, [x2, #GICH_VMCR]
-	ldr	w6, [x2, #GICH_MISR]
-	ldr	w7, [x2, #GICH_EISR0]
-	ldr	w8, [x2, #GICH_EISR1]
-	ldr	w9, [x2, #GICH_ELRSR0]
-	ldr	w10, [x2, #GICH_ELRSR1]
-	ldr	w11, [x2, #GICH_APR]
-CPU_BE(	rev	w4,  w4  )
-CPU_BE(	rev	w5,  w5  )
-CPU_BE(	rev	w6,  w6  )
-CPU_BE(	rev	w7,  w7  )
-CPU_BE(	rev	w8,  w8  )
-CPU_BE(	rev	w9,  w9  )
-CPU_BE(	rev	w10, w10 )
-CPU_BE(	rev	w11, w11 )
-
-	str	w4, [x3, #VGIC_CPU_HCR]
-	str	w5, [x3, #VGIC_CPU_VMCR]
-	str	w6, [x3, #VGIC_CPU_MISR]
-	str	w7, [x3, #VGIC_CPU_EISR]
-	str	w8, [x3, #(VGIC_CPU_EISR + 4)]
-	str	w9, [x3, #VGIC_CPU_ELRSR]
-	str	w10, [x3, #(VGIC_CPU_ELRSR + 4)]
-	str	w11, [x3, #VGIC_CPU_APR]
-
-	/* Clear GICH_HCR */
-	str	wzr, [x2, #GICH_HCR]
-
-	/* Save list registers */
-	add	x2, x2, #GICH_LR0
-	ldr	w4, [x3, #VGIC_CPU_NR_LR]
-	add	x3, x3, #VGIC_CPU_LR
-1:	ldr	w5, [x2], #4
-CPU_BE(	rev	w5, w5 )
-	str	w5, [x3], #4
-	sub	w4, w4, #1
-	cbnz	w4, 1b
-2:
+	adr	x24, __vgic_sr_vectors
+	ldr	x24, [x24, VGIC_SAVE_FN]
+	kern_hyp_va	x24
+	blr	x24
+	mrs	x24, hcr_el2
+	mov	x25, #HCR_INT_OVERRIDE
+	neg	x25, x25
+	and	x24, x24, x25
+	msr	hcr_el2, x24
 .endm
 
 /*
- * Restore the VGIC CPU state from memory
- * x0: Register pointing to VCPU struct
+ * Call into the vgic backend for state restoring
  */
 .macro restore_vgic_state
-	/* Get VGIC VCTRL base into x2 */
-	ldr	x2, [x0, #VCPU_KVM]
-	kern_hyp_va	x2
-	ldr	x2, [x2, #KVM_VGIC_VCTRL]
-	kern_hyp_va	x2
-	cbz	x2, 2f		// disabled
-
-	/* Compute the address of struct vgic_cpu */
-	add	x3, x0, #VCPU_VGIC_CPU
-
-	/* We only restore a minimal set of registers */
-	ldr	w4, [x3, #VGIC_CPU_HCR]
-	ldr	w5, [x3, #VGIC_CPU_VMCR]
-	ldr	w6, [x3, #VGIC_CPU_APR]
-CPU_BE(	rev	w4, w4 )
-CPU_BE(	rev	w5, w5 )
-CPU_BE(	rev	w6, w6 )
-
-	str	w4, [x2, #GICH_HCR]
-	str	w5, [x2, #GICH_VMCR]
-	str	w6, [x2, #GICH_APR]
-
-	/* Restore list registers */
-	add	x2, x2, #GICH_LR0
-	ldr	w4, [x3, #VGIC_CPU_NR_LR]
-	add	x3, x3, #VGIC_CPU_LR
-1:	ldr	w5, [x3], #4
-CPU_BE(	rev	w5, w5 )
-	str	w5, [x2], #4
-	sub	w4, w4, #1
-	cbnz	w4, 1b
-2:
+	mrs	x24, hcr_el2
+	ldr	x25, [x0, #VCPU_IRQ_LINES]
+	orr	x24, x24, #HCR_INT_OVERRIDE
+	orr	x24, x24, x25
+	msr	hcr_el2, x24
+	adr	x24, __vgic_sr_vectors
+	ldr	x24, [x24, #VGIC_RESTORE_FN]
+	kern_hyp_va	x24
+	blr	x24
 .endm
 
 .macro save_timer_state
@@ -537,6 +895,14 @@ __restore_sysregs:
 	restore_sysregs
 	ret
 
+__save_debug:
+	save_debug
+	ret
+
+__restore_debug:
+	restore_debug
+	ret
+
 __save_fpsimd:
 	save_fpsimd
 	ret
@@ -568,6 +934,9 @@ ENTRY(__kvm_vcpu_run)
 	bl __save_fpsimd
 	bl __save_sysregs
 
+	compute_debug_state 1f
+	bl	__save_debug
+1:
 	activate_traps
 	activate_vm
 
@@ -579,6 +948,10 @@ ENTRY(__kvm_vcpu_run)
 
 	bl __restore_sysregs
 	bl __restore_fpsimd
+
+	skip_debug_state x3, 1f
+	bl	__restore_debug
+1:
 	restore_guest_32bit_state
 	restore_guest_regs
 
@@ -595,6 +968,10 @@ __kvm_vcpu_return:
 	save_guest_regs
 	bl __save_fpsimd
 	bl __save_sysregs
+
+	skip_debug_state x3, 1f
+	bl	__save_debug
+1:
 	save_guest_32bit_state
 
 	save_timer_state
@@ -609,6 +986,14 @@ __kvm_vcpu_return:
 
 	bl __restore_sysregs
 	bl __restore_fpsimd
+
+	skip_debug_state x3, 1f
+	// Clear the dirty flag for the next run, as all the state has
+	// already been saved. Note that we nuke the whole 64bit word.
+	// If we ever add more flags, we'll have to be more careful...
+	str	xzr, [x0, #VCPU_DEBUG_FLAGS]
+	bl	__restore_debug
+1:
 	restore_host_regs
 
 	mov	x0, x1
@@ -653,6 +1038,12 @@ ENTRY(__kvm_flush_vm_context)
 	ret
 ENDPROC(__kvm_flush_vm_context)
 
+	// struct vgic_sr_vectors __vgi_sr_vectors;
+	.align 3
+ENTRY(__vgic_sr_vectors)
+	.skip	VGIC_SR_VECTOR_SZ
+ENDPROC(__vgic_sr_vectors)
+
 __kvm_hyp_panic:
 	// Guess the context by looking at VTTBR:
 	// If zero, then we're already a host.
@@ -830,7 +1221,7 @@ 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]
 
@@ -880,7 +1271,4 @@ ENTRY(__kvm_hyp_vector)
 	ventry	el1_error_invalid		// Error 32-bit EL1
 ENDPROC(__kvm_hyp_vector)
 
-__kvm_hyp_code_end:
-	.globl	__kvm_hyp_code_end
-
 	.popsection
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index c59a1bdab5eb..5805e7c4a4dd 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -30,6 +30,7 @@
 #include <asm/kvm_mmu.h>
 #include <asm/cacheflush.h>
 #include <asm/cputype.h>
+#include <asm/debug-monitors.h>
 #include <trace/events/kvm.h>
 
 #include "sys_regs.h"
@@ -137,10 +138,11 @@ static bool access_vm_reg(struct kvm_vcpu *vcpu,
 	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;
+			vcpu_cp15_64_high(vcpu, r->reg) = val >> 32;
+		vcpu_cp15_64_low(vcpu, r->reg) = val & 0xffffffffUL;
 	}
+
 	return true;
 }
 
@@ -163,18 +165,9 @@ static bool access_sctlr(struct kvm_vcpu *vcpu,
 	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.
- *
- * Therefore we tell the guest we have 0 counters.  Unfortunately, we
- * must always support PMCCNTR (the cycle counter): we just RAZ/WI for
- * all PM registers, which doesn't crash the guest kernel at least.
- */
-static bool pm_fake(struct kvm_vcpu *vcpu,
-		    const struct sys_reg_params *p,
-		    const struct sys_reg_desc *r)
+static bool trap_raz_wi(struct kvm_vcpu *vcpu,
+			const struct sys_reg_params *p,
+			const struct sys_reg_desc *r)
 {
 	if (p->is_write)
 		return ignore_write(vcpu, p);
@@ -182,6 +175,73 @@ static bool pm_fake(struct kvm_vcpu *vcpu,
 		return read_zero(vcpu, p);
 }
 
+static bool trap_oslsr_el1(struct kvm_vcpu *vcpu,
+			   const struct sys_reg_params *p,
+			   const struct sys_reg_desc *r)
+{
+	if (p->is_write) {
+		return ignore_write(vcpu, p);
+	} else {
+		*vcpu_reg(vcpu, p->Rt) = (1 << 3);
+		return true;
+	}
+}
+
+static bool trap_dbgauthstatus_el1(struct kvm_vcpu *vcpu,
+				   const struct sys_reg_params *p,
+				   const struct sys_reg_desc *r)
+{
+	if (p->is_write) {
+		return ignore_write(vcpu, p);
+	} else {
+		u32 val;
+		asm volatile("mrs %0, dbgauthstatus_el1" : "=r" (val));
+		*vcpu_reg(vcpu, p->Rt) = val;
+		return true;
+	}
+}
+
+/*
+ * We want to avoid world-switching all the DBG registers all the
+ * time:
+ * 
+ * - If we've touched any debug register, it is likely that we're
+ *   going to touch more of them. It then makes sense to disable the
+ *   traps and start doing the save/restore dance
+ * - If debug is active (DBG_MDSCR_KDE or DBG_MDSCR_MDE set), it is
+ *   then mandatory to save/restore the registers, as the guest
+ *   depends on them.
+ * 
+ * For this, we use a DIRTY bit, indicating the guest has modified the
+ * debug registers, used as follow:
+ *
+ * On guest entry:
+ * - If the dirty bit is set (because we're coming back from trapping),
+ *   disable the traps, save host registers, restore guest registers.
+ * - If debug is actively in use (DBG_MDSCR_KDE or DBG_MDSCR_MDE set),
+ *   set the dirty bit, disable the traps, save host registers,
+ *   restore guest registers.
+ * - Otherwise, enable the traps
+ *
+ * On guest exit:
+ * - If the dirty bit is set, save guest registers, restore host
+ *   registers and clear the dirty bit. This ensure that the host can
+ *   now use the debug registers.
+ */
+static bool trap_debug_regs(struct kvm_vcpu *vcpu,
+			    const struct sys_reg_params *p,
+			    const struct sys_reg_desc *r)
+{
+	if (p->is_write) {
+		vcpu_sys_reg(vcpu, r->reg) = *vcpu_reg(vcpu, p->Rt);
+		vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY;
+	} else {
+		*vcpu_reg(vcpu, p->Rt) = vcpu_sys_reg(vcpu, r->reg);
+	}
+
+	return true;
+}
+
 static void reset_amair_el1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 {
 	u64 amair;
@@ -198,9 +258,39 @@ static void reset_mpidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 	vcpu_sys_reg(vcpu, MPIDR_EL1) = (1UL << 31) | (vcpu->vcpu_id & 0xff);
 }
 
+/* Silly macro to expand the DBG{BCR,BVR,WVR,WCR}n_EL1 registers in one go */
+#define DBG_BCR_BVR_WCR_WVR_EL1(n)					\
+	/* DBGBVRn_EL1 */						\
+	{ Op0(0b10), Op1(0b000), CRn(0b0000), CRm((n)), Op2(0b100),	\
+	  trap_debug_regs, reset_val, (DBGBVR0_EL1 + (n)), 0 },		\
+	/* DBGBCRn_EL1 */						\
+	{ Op0(0b10), Op1(0b000), CRn(0b0000), CRm((n)), Op2(0b101),	\
+	  trap_debug_regs, reset_val, (DBGBCR0_EL1 + (n)), 0 },		\
+	/* DBGWVRn_EL1 */						\
+	{ Op0(0b10), Op1(0b000), CRn(0b0000), CRm((n)), Op2(0b110),	\
+	  trap_debug_regs, reset_val, (DBGWVR0_EL1 + (n)), 0 },		\
+	/* DBGWCRn_EL1 */						\
+	{ Op0(0b10), Op1(0b000), CRn(0b0000), CRm((n)), Op2(0b111),	\
+	  trap_debug_regs, reset_val, (DBGWCR0_EL1 + (n)), 0 }
+
 /*
  * Architected system registers.
  * Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2
+ *
+ * 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.
+ *
+ * Therefore we tell the guest we have 0 counters.  Unfortunately, we
+ * must always support PMCCNTR (the cycle counter): we just RAZ/WI for
+ * all PM registers, which doesn't crash the guest kernel at least.
+ *
+ * Debug handling: We do trap most, if not all debug related system
+ * registers. The implementation is good enough to ensure that a guest
+ * can use these with minimal performance degradation. The drawback is
+ * that we don't implement any of the external debug, none of the
+ * OSlock protocol. This should be revisited if we ever encounter a
+ * more demanding guest...
  */
 static const struct sys_reg_desc sys_reg_descs[] = {
 	/* DC ISW */
@@ -213,12 +303,71 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ Op0(0b01), Op1(0b000), CRn(0b0111), CRm(0b1110), Op2(0b010),
 	  access_dcsw },
 
+	DBG_BCR_BVR_WCR_WVR_EL1(0),
+	DBG_BCR_BVR_WCR_WVR_EL1(1),
+	/* MDCCINT_EL1 */
+	{ Op0(0b10), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b000),
+	  trap_debug_regs, reset_val, MDCCINT_EL1, 0 },
+	/* MDSCR_EL1 */
+	{ Op0(0b10), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b010),
+	  trap_debug_regs, reset_val, MDSCR_EL1, 0 },
+	DBG_BCR_BVR_WCR_WVR_EL1(2),
+	DBG_BCR_BVR_WCR_WVR_EL1(3),
+	DBG_BCR_BVR_WCR_WVR_EL1(4),
+	DBG_BCR_BVR_WCR_WVR_EL1(5),
+	DBG_BCR_BVR_WCR_WVR_EL1(6),
+	DBG_BCR_BVR_WCR_WVR_EL1(7),
+	DBG_BCR_BVR_WCR_WVR_EL1(8),
+	DBG_BCR_BVR_WCR_WVR_EL1(9),
+	DBG_BCR_BVR_WCR_WVR_EL1(10),
+	DBG_BCR_BVR_WCR_WVR_EL1(11),
+	DBG_BCR_BVR_WCR_WVR_EL1(12),
+	DBG_BCR_BVR_WCR_WVR_EL1(13),
+	DBG_BCR_BVR_WCR_WVR_EL1(14),
+	DBG_BCR_BVR_WCR_WVR_EL1(15),
+
+	/* MDRAR_EL1 */
+	{ Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b000),
+	  trap_raz_wi },
+	/* OSLAR_EL1 */
+	{ Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b100),
+	  trap_raz_wi },
+	/* OSLSR_EL1 */
+	{ Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0001), Op2(0b100),
+	  trap_oslsr_el1 },
+	/* OSDLR_EL1 */
+	{ Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0011), Op2(0b100),
+	  trap_raz_wi },
+	/* DBGPRCR_EL1 */
+	{ Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0100), Op2(0b100),
+	  trap_raz_wi },
+	/* DBGCLAIMSET_EL1 */
+	{ Op0(0b10), Op1(0b000), CRn(0b0111), CRm(0b1000), Op2(0b110),
+	  trap_raz_wi },
+	/* DBGCLAIMCLR_EL1 */
+	{ Op0(0b10), Op1(0b000), CRn(0b0111), CRm(0b1001), Op2(0b110),
+	  trap_raz_wi },
+	/* DBGAUTHSTATUS_EL1 */
+	{ Op0(0b10), Op1(0b000), CRn(0b0111), CRm(0b1110), Op2(0b110),
+	  trap_dbgauthstatus_el1 },
+
 	/* TEECR32_EL1 */
 	{ Op0(0b10), Op1(0b010), CRn(0b0000), CRm(0b0000), Op2(0b000),
 	  NULL, reset_val, TEECR32_EL1, 0 },
 	/* TEEHBR32_EL1 */
 	{ Op0(0b10), Op1(0b010), CRn(0b0001), CRm(0b0000), Op2(0b000),
 	  NULL, reset_val, TEEHBR32_EL1, 0 },
+
+	/* MDCCSR_EL1 */
+	{ Op0(0b10), Op1(0b011), CRn(0b0000), CRm(0b0001), Op2(0b000),
+	  trap_raz_wi },
+	/* DBGDTR_EL0 */
+	{ Op0(0b10), Op1(0b011), CRn(0b0000), CRm(0b0100), Op2(0b000),
+	  trap_raz_wi },
+	/* DBGDTR[TR]X_EL0 */
+	{ Op0(0b10), Op1(0b011), CRn(0b0000), CRm(0b0101), Op2(0b000),
+	  trap_raz_wi },
+
 	/* DBGVCR32_EL2 */
 	{ Op0(0b10), Op1(0b100), CRn(0b0000), CRm(0b0111), Op2(0b000),
 	  NULL, reset_val, DBGVCR32_EL2, 0 },
@@ -260,10 +409,10 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 
 	/* PMINTENSET_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b1001), CRm(0b1110), Op2(0b001),
-	  pm_fake },
+	  trap_raz_wi },
 	/* PMINTENCLR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b1001), CRm(0b1110), Op2(0b010),
-	  pm_fake },
+	  trap_raz_wi },
 
 	/* MAIR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b1010), CRm(0b0010), Op2(0b000),
@@ -292,43 +441,43 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 
 	/* PMCR_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b000),
-	  pm_fake },
+	  trap_raz_wi },
 	/* PMCNTENSET_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b001),
-	  pm_fake },
+	  trap_raz_wi },
 	/* PMCNTENCLR_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b010),
-	  pm_fake },
+	  trap_raz_wi },
 	/* PMOVSCLR_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b011),
-	  pm_fake },
+	  trap_raz_wi },
 	/* PMSWINC_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b100),
-	  pm_fake },
+	  trap_raz_wi },
 	/* PMSELR_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b101),
-	  pm_fake },
+	  trap_raz_wi },
 	/* PMCEID0_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b110),
-	  pm_fake },
+	  trap_raz_wi },
 	/* PMCEID1_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b111),
-	  pm_fake },
+	  trap_raz_wi },
 	/* PMCCNTR_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1101), Op2(0b000),
-	  pm_fake },
+	  trap_raz_wi },
 	/* PMXEVTYPER_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1101), Op2(0b001),
-	  pm_fake },
+	  trap_raz_wi },
 	/* PMXEVCNTR_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1101), Op2(0b010),
-	  pm_fake },
+	  trap_raz_wi },
 	/* PMUSERENR_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1110), Op2(0b000),
-	  pm_fake },
+	  trap_raz_wi },
 	/* PMOVSSET_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1110), Op2(0b011),
-	  pm_fake },
+	  trap_raz_wi },
 
 	/* TPIDR_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1101), CRm(0b0000), Op2(0b010),
@@ -348,13 +497,161 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	  NULL, reset_val, FPEXC32_EL2, 0x70 },
 };
 
+static bool trap_dbgidr(struct kvm_vcpu *vcpu,
+			const struct sys_reg_params *p,
+			const struct sys_reg_desc *r)
+{
+	if (p->is_write) {
+		return ignore_write(vcpu, p);
+	} else {
+		u64 dfr = read_cpuid(ID_AA64DFR0_EL1);
+		u64 pfr = read_cpuid(ID_AA64PFR0_EL1);
+		u32 el3 = !!((pfr >> 12) & 0xf);
+
+		*vcpu_reg(vcpu, p->Rt) = ((((dfr >> 20) & 0xf) << 28) |
+					  (((dfr >> 12) & 0xf) << 24) |
+					  (((dfr >> 28) & 0xf) << 20) |
+					  (6 << 16) | (el3 << 14) | (el3 << 12));
+		return true;
+	}
+}
+
+static bool trap_debug32(struct kvm_vcpu *vcpu,
+			 const struct sys_reg_params *p,
+			 const struct sys_reg_desc *r)
+{
+	if (p->is_write) {
+		vcpu_cp14(vcpu, r->reg) = *vcpu_reg(vcpu, p->Rt);
+		vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY;
+	} else {
+		*vcpu_reg(vcpu, p->Rt) = vcpu_cp14(vcpu, r->reg);
+	}
+
+	return true;
+}
+
+#define DBG_BCR_BVR_WCR_WVR(n)					\
+	/* DBGBVRn */						\
+	{ Op1( 0), CRn( 0), CRm((n)), Op2( 4), trap_debug32,	\
+	  NULL, (cp14_DBGBVR0 + (n) * 2) },			\
+	/* DBGBCRn */						\
+	{ Op1( 0), CRn( 0), CRm((n)), Op2( 5), trap_debug32,	\
+	  NULL, (cp14_DBGBCR0 + (n) * 2) },			\
+	/* DBGWVRn */						\
+	{ Op1( 0), CRn( 0), CRm((n)), Op2( 6), trap_debug32,	\
+	  NULL, (cp14_DBGWVR0 + (n) * 2) },			\
+	/* DBGWCRn */						\
+	{ Op1( 0), CRn( 0), CRm((n)), Op2( 7), trap_debug32,	\
+	  NULL, (cp14_DBGWCR0 + (n) * 2) }
+
+#define DBGBXVR(n)						\
+	{ Op1( 0), CRn( 1), CRm((n)), Op2( 1), trap_debug32,	\
+	  NULL, cp14_DBGBXVR0 + n * 2 }
+
+/*
+ * Trapped cp14 registers. We generally ignore most of the external
+ * debug, on the principle that they don't really make sense to a
+ * guest. Revisit this one day, whould this principle change.
+ */
+static const struct sys_reg_desc cp14_regs[] = {
+	/* DBGIDR */
+	{ Op1( 0), CRn( 0), CRm( 0), Op2( 0), trap_dbgidr },
+	/* DBGDTRRXext */
+	{ Op1( 0), CRn( 0), CRm( 0), Op2( 2), trap_raz_wi },
+
+	DBG_BCR_BVR_WCR_WVR(0),
+	/* DBGDSCRint */
+	{ Op1( 0), CRn( 0), CRm( 1), Op2( 0), trap_raz_wi },
+	DBG_BCR_BVR_WCR_WVR(1),
+	/* DBGDCCINT */
+	{ Op1( 0), CRn( 0), CRm( 2), Op2( 0), trap_debug32 },
+	/* DBGDSCRext */
+	{ Op1( 0), CRn( 0), CRm( 2), Op2( 2), trap_debug32 },
+	DBG_BCR_BVR_WCR_WVR(2),
+	/* DBGDTR[RT]Xint */
+	{ Op1( 0), CRn( 0), CRm( 3), Op2( 0), trap_raz_wi },
+	/* DBGDTR[RT]Xext */
+	{ Op1( 0), CRn( 0), CRm( 3), Op2( 2), trap_raz_wi },
+	DBG_BCR_BVR_WCR_WVR(3),
+	DBG_BCR_BVR_WCR_WVR(4),
+	DBG_BCR_BVR_WCR_WVR(5),
+	/* DBGWFAR */
+	{ Op1( 0), CRn( 0), CRm( 6), Op2( 0), trap_raz_wi },
+	/* DBGOSECCR */
+	{ Op1( 0), CRn( 0), CRm( 6), Op2( 2), trap_raz_wi },
+	DBG_BCR_BVR_WCR_WVR(6),
+	/* DBGVCR */
+	{ Op1( 0), CRn( 0), CRm( 7), Op2( 0), trap_debug32 },
+	DBG_BCR_BVR_WCR_WVR(7),
+	DBG_BCR_BVR_WCR_WVR(8),
+	DBG_BCR_BVR_WCR_WVR(9),
+	DBG_BCR_BVR_WCR_WVR(10),
+	DBG_BCR_BVR_WCR_WVR(11),
+	DBG_BCR_BVR_WCR_WVR(12),
+	DBG_BCR_BVR_WCR_WVR(13),
+	DBG_BCR_BVR_WCR_WVR(14),
+	DBG_BCR_BVR_WCR_WVR(15),
+
+	/* DBGDRAR (32bit) */
+	{ Op1( 0), CRn( 1), CRm( 0), Op2( 0), trap_raz_wi },
+
+	DBGBXVR(0),
+	/* DBGOSLAR */
+	{ Op1( 0), CRn( 1), CRm( 0), Op2( 4), trap_raz_wi },
+	DBGBXVR(1),
+	/* DBGOSLSR */
+	{ Op1( 0), CRn( 1), CRm( 1), Op2( 4), trap_oslsr_el1 },
+	DBGBXVR(2),
+	DBGBXVR(3),
+	/* DBGOSDLR */
+	{ Op1( 0), CRn( 1), CRm( 3), Op2( 4), trap_raz_wi },
+	DBGBXVR(4),
+	/* DBGPRCR */
+	{ Op1( 0), CRn( 1), CRm( 4), Op2( 4), trap_raz_wi },
+	DBGBXVR(5),
+	DBGBXVR(6),
+	DBGBXVR(7),
+	DBGBXVR(8),
+	DBGBXVR(9),
+	DBGBXVR(10),
+	DBGBXVR(11),
+	DBGBXVR(12),
+	DBGBXVR(13),
+	DBGBXVR(14),
+	DBGBXVR(15),
+
+	/* DBGDSAR (32bit) */
+	{ Op1( 0), CRn( 2), CRm( 0), Op2( 0), trap_raz_wi },
+
+	/* DBGDEVID2 */
+	{ Op1( 0), CRn( 7), CRm( 0), Op2( 7), trap_raz_wi },
+	/* DBGDEVID1 */
+	{ Op1( 0), CRn( 7), CRm( 1), Op2( 7), trap_raz_wi },
+	/* DBGDEVID */
+	{ Op1( 0), CRn( 7), CRm( 2), Op2( 7), trap_raz_wi },
+	/* DBGCLAIMSET */
+	{ Op1( 0), CRn( 7), CRm( 8), Op2( 6), trap_raz_wi },
+	/* DBGCLAIMCLR */
+	{ Op1( 0), CRn( 7), CRm( 9), Op2( 6), trap_raz_wi },
+	/* DBGAUTHSTATUS */
+	{ Op1( 0), CRn( 7), CRm(14), Op2( 6), trap_dbgauthstatus_el1 },
+};
+
+/* Trapped cp14 64bit registers */
+static const struct sys_reg_desc cp14_64_regs[] = {
+	/* DBGDRAR (64bit) */
+	{ Op1( 0), CRm( 1), .access = trap_raz_wi },
+
+	/* DBGDSAR (64bit) */
+	{ Op1( 0), CRm( 2), .access = trap_raz_wi },
+};
+
 /*
  * 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 },
@@ -374,26 +671,30 @@ static const struct sys_reg_desc cp15_regs[] = {
 	{ 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 },
-	{ Op1( 0), CRn( 9), CRm(12), Op2( 3), pm_fake },
-	{ Op1( 0), CRn( 9), CRm(12), Op2( 5), pm_fake },
-	{ Op1( 0), CRn( 9), CRm(12), Op2( 6), pm_fake },
-	{ Op1( 0), CRn( 9), CRm(12), Op2( 7), pm_fake },
-	{ Op1( 0), CRn( 9), CRm(13), Op2( 0), pm_fake },
-	{ Op1( 0), CRn( 9), CRm(13), Op2( 1), pm_fake },
-	{ Op1( 0), CRn( 9), CRm(13), Op2( 2), pm_fake },
-	{ 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 },
+	/* PMU */
+	{ Op1( 0), CRn( 9), CRm(12), Op2( 0), trap_raz_wi },
+	{ Op1( 0), CRn( 9), CRm(12), Op2( 1), trap_raz_wi },
+	{ Op1( 0), CRn( 9), CRm(12), Op2( 2), trap_raz_wi },
+	{ Op1( 0), CRn( 9), CRm(12), Op2( 3), trap_raz_wi },
+	{ Op1( 0), CRn( 9), CRm(12), Op2( 5), trap_raz_wi },
+	{ Op1( 0), CRn( 9), CRm(12), Op2( 6), trap_raz_wi },
+	{ Op1( 0), CRn( 9), CRm(12), Op2( 7), trap_raz_wi },
+	{ Op1( 0), CRn( 9), CRm(13), Op2( 0), trap_raz_wi },
+	{ Op1( 0), CRn( 9), CRm(13), Op2( 1), trap_raz_wi },
+	{ Op1( 0), CRn( 9), CRm(13), Op2( 2), trap_raz_wi },
+	{ Op1( 0), CRn( 9), CRm(14), Op2( 0), trap_raz_wi },
+	{ Op1( 0), CRn( 9), CRm(14), Op2( 1), trap_raz_wi },
+	{ Op1( 0), CRn( 9), CRm(14), Op2( 2), trap_raz_wi },
 
 	{ 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 },
+};
 
+static const struct sys_reg_desc cp15_64_regs[] = {
+	{ Op1( 0), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, c2_TTBR0 },
 	{ Op1( 1), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, c2_TTBR1 },
 };
 
@@ -454,26 +755,29 @@ int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	return 1;
 }
 
-int kvm_handle_cp14_access(struct kvm_vcpu *vcpu, struct kvm_run *run)
-{
-	kvm_inject_undefined(vcpu);
-	return 1;
-}
-
-static void emulate_cp15(struct kvm_vcpu *vcpu,
-			 const struct sys_reg_params *params)
+/*
+ * emulate_cp --  tries to match a sys_reg access in a handling table, and
+ *                call the corresponding trap handler.
+ *
+ * @params: pointer to the descriptor of the access
+ * @table: array of trap descriptors
+ * @num: size of the trap descriptor array
+ *
+ * Return 0 if the access has been handled, and -1 if not.
+ */
+static int emulate_cp(struct kvm_vcpu *vcpu,
+		      const struct sys_reg_params *params,
+		      const struct sys_reg_desc *table,
+		      size_t num)
 {
-	size_t num;
-	const struct sys_reg_desc *table, *r;
+	const struct sys_reg_desc *r;
 
-	table = get_target_table(vcpu->arch.target, false, &num);
+	if (!table)
+		return -1;	/* Not handled */
 
-	/* Search target-specific then generic table. */
 	r = find_reg(params, table, num);
-	if (!r)
-		r = find_reg(params, cp15_regs, ARRAY_SIZE(cp15_regs));
 
-	if (likely(r)) {
+	if (r) {
 		/*
 		 * Not having an accessor means that we have
 		 * configured a trap that we don't know how to
@@ -485,22 +789,51 @@ static void emulate_cp15(struct kvm_vcpu *vcpu,
 		if (likely(r->access(vcpu, params, r))) {
 			/* Skip instruction, since it was emulated */
 			kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
-			return;
 		}
-		/* If access function fails, it should complain. */
+
+		/* Handled */
+		return 0;
 	}
 
-	kvm_err("Unsupported guest CP15 access at: %08lx\n", *vcpu_pc(vcpu));
+	/* Not handled */
+	return -1;
+}
+
+static void unhandled_cp_access(struct kvm_vcpu *vcpu,
+				struct sys_reg_params *params)
+{
+	u8 hsr_ec = kvm_vcpu_trap_get_class(vcpu);
+	int cp;
+
+	switch(hsr_ec) {
+	case ESR_EL2_EC_CP15_32:
+	case ESR_EL2_EC_CP15_64:
+		cp = 15;
+		break;
+	case ESR_EL2_EC_CP14_MR:
+	case ESR_EL2_EC_CP14_64:
+		cp = 14;
+		break;
+	default:
+		WARN_ON((cp = -1));
+	}
+
+	kvm_err("Unsupported guest CP%d access at: %08lx\n",
+		cp, *vcpu_pc(vcpu));
 	print_sys_reg_instr(params);
 	kvm_inject_undefined(vcpu);
 }
 
 /**
- * kvm_handle_cp15_64 -- handles a mrrc/mcrr trap on a guest CP15 access
+ * kvm_handle_cp_64 -- handles a mrrc/mcrr trap on a guest CP15 access
  * @vcpu: The VCPU pointer
  * @run:  The kvm_run struct
  */
-int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
+static int kvm_handle_cp_64(struct kvm_vcpu *vcpu,
+			    const struct sys_reg_desc *global,
+			    size_t nr_global,
+			    const struct sys_reg_desc *target_specific,
+			    size_t nr_specific)
 {
 	struct sys_reg_params params;
 	u32 hsr = kvm_vcpu_get_hsr(vcpu);
@@ -529,8 +862,14 @@ int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		*vcpu_reg(vcpu, params.Rt) = val;
 	}
 
-	emulate_cp15(vcpu, &params);
+	if (!emulate_cp(vcpu, &params, target_specific, nr_specific))
+		goto out;
+	if (!emulate_cp(vcpu, &params, global, nr_global))
+		goto out;
 
+	unhandled_cp_access(vcpu, &params);
+
+out:
 	/* Do the opposite hack for the read side */
 	if (!params.is_write) {
 		u64 val = *vcpu_reg(vcpu, params.Rt);
@@ -546,7 +885,11 @@ int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
  * @vcpu: The VCPU pointer
  * @run:  The kvm_run struct
  */
-int kvm_handle_cp15_32(struct kvm_vcpu *vcpu, struct kvm_run *run)
+static int kvm_handle_cp_32(struct kvm_vcpu *vcpu,
+			    const struct sys_reg_desc *global,
+			    size_t nr_global,
+			    const struct sys_reg_desc *target_specific,
+			    size_t nr_specific)
 {
 	struct sys_reg_params params;
 	u32 hsr = kvm_vcpu_get_hsr(vcpu);
@@ -561,10 +904,51 @@ int kvm_handle_cp15_32(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	params.Op1 = (hsr >> 14) & 0x7;
 	params.Op2 = (hsr >> 17) & 0x7;
 
-	emulate_cp15(vcpu, &params);
+	if (!emulate_cp(vcpu, &params, target_specific, nr_specific))
+		return 1;
+	if (!emulate_cp(vcpu, &params, global, nr_global))
+		return 1;
+
+	unhandled_cp_access(vcpu, &params);
 	return 1;
 }
 
+int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	const struct sys_reg_desc *target_specific;
+	size_t num;
+
+	target_specific = get_target_table(vcpu->arch.target, false, &num);
+	return kvm_handle_cp_64(vcpu,
+				cp15_64_regs, ARRAY_SIZE(cp15_64_regs),
+				target_specific, num);
+}
+
+int kvm_handle_cp15_32(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	const struct sys_reg_desc *target_specific;
+	size_t num;
+
+	target_specific = get_target_table(vcpu->arch.target, false, &num);
+	return kvm_handle_cp_32(vcpu,
+				cp15_regs, ARRAY_SIZE(cp15_regs),
+				target_specific, num);
+}
+
+int kvm_handle_cp14_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	return kvm_handle_cp_64(vcpu,
+				cp14_64_regs, ARRAY_SIZE(cp14_64_regs),
+				NULL, 0);
+}
+
+int kvm_handle_cp14_32(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	return kvm_handle_cp_32(vcpu,
+				cp14_regs, ARRAY_SIZE(cp14_regs),
+				NULL, 0);
+}
+
 static int emulate_sys_reg(struct kvm_vcpu *vcpu,
 			   const struct sys_reg_params *params)
 {
@@ -776,17 +1160,15 @@ static struct sys_reg_desc invariant_sys_regs[] = {
 	  NULL, get_ctr_el0 },
 };
 
-static int reg_from_user(void *val, const void __user *uaddr, u64 id)
+static int reg_from_user(u64 *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;
 }
 
-static int reg_to_user(void __user *uaddr, const void *val, u64 id)
+static int reg_to_user(void __user *uaddr, const u64 *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;
@@ -962,7 +1344,7 @@ 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;
@@ -1069,14 +1451,32 @@ int kvm_arm_copy_sys_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
 	return write_demux_regids(uindices);
 }
 
+static int check_sysreg_table(const struct sys_reg_desc *table, unsigned int n)
+{
+	unsigned int i;
+
+	for (i = 1; i < n; i++) {
+		if (cmp_sys_reg(&table[i-1], &table[i]) >= 0) {
+			kvm_err("sys_reg table %p out of order (%d)\n", table, i - 1);
+			return 1;
+		}
+	}
+
+	return 0;
+}
+
 void kvm_sys_reg_table_init(void)
 {
 	unsigned int i;
 	struct sys_reg_desc clidr;
 
 	/* Make sure tables are unique and in order. */
-	for (i = 1; i < ARRAY_SIZE(sys_reg_descs); i++)
-		BUG_ON(cmp_sys_reg(&sys_reg_descs[i-1], &sys_reg_descs[i]) >= 0);
+	BUG_ON(check_sysreg_table(sys_reg_descs, ARRAY_SIZE(sys_reg_descs)));
+	BUG_ON(check_sysreg_table(cp14_regs, ARRAY_SIZE(cp14_regs)));
+	BUG_ON(check_sysreg_table(cp14_64_regs, ARRAY_SIZE(cp14_64_regs)));
+	BUG_ON(check_sysreg_table(cp15_regs, ARRAY_SIZE(cp15_regs)));
+	BUG_ON(check_sysreg_table(cp15_64_regs, ARRAY_SIZE(cp15_64_regs)));
+	BUG_ON(check_sysreg_table(invariant_sys_regs, ARRAY_SIZE(invariant_sys_regs)));
 
 	/* We abuse the reset function to overwrite the table itself. */
 	for (i = 0; i < ARRAY_SIZE(invariant_sys_regs); i++)
diff --git a/arch/arm64/kvm/vgic-v2-switch.S b/arch/arm64/kvm/vgic-v2-switch.S
new file mode 100644
index 000000000000..ae211772f991
--- /dev/null
+++ b/arch/arm64/kvm/vgic-v2-switch.S
@@ -0,0 +1,133 @@
+/*
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/linkage.h>
+#include <linux/irqchip/arm-gic.h>
+
+#include <asm/assembler.h>
+#include <asm/memory.h>
+#include <asm/asm-offsets.h>
+#include <asm/kvm.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_arm.h>
+#include <asm/kvm_mmu.h>
+
+	.text
+	.pushsection	.hyp.text, "ax"
+
+/*
+ * Save the VGIC CPU state into memory
+ * x0: Register pointing to VCPU struct
+ * Do not corrupt x1!!!
+ */
+ENTRY(__save_vgic_v2_state)
+__save_vgic_v2_state:
+	/* Get VGIC VCTRL base into x2 */
+	ldr	x2, [x0, #VCPU_KVM]
+	kern_hyp_va	x2
+	ldr	x2, [x2, #KVM_VGIC_VCTRL]
+	kern_hyp_va	x2
+	cbz	x2, 2f		// disabled
+
+	/* Compute the address of struct vgic_cpu */
+	add	x3, x0, #VCPU_VGIC_CPU
+
+	/* Save all interesting registers */
+	ldr	w4, [x2, #GICH_HCR]
+	ldr	w5, [x2, #GICH_VMCR]
+	ldr	w6, [x2, #GICH_MISR]
+	ldr	w7, [x2, #GICH_EISR0]
+	ldr	w8, [x2, #GICH_EISR1]
+	ldr	w9, [x2, #GICH_ELRSR0]
+	ldr	w10, [x2, #GICH_ELRSR1]
+	ldr	w11, [x2, #GICH_APR]
+CPU_BE(	rev	w4,  w4  )
+CPU_BE(	rev	w5,  w5  )
+CPU_BE(	rev	w6,  w6  )
+CPU_BE(	rev	w7,  w7  )
+CPU_BE(	rev	w8,  w8  )
+CPU_BE(	rev	w9,  w9  )
+CPU_BE(	rev	w10, w10 )
+CPU_BE(	rev	w11, w11 )
+
+	str	w4, [x3, #VGIC_V2_CPU_HCR]
+	str	w5, [x3, #VGIC_V2_CPU_VMCR]
+	str	w6, [x3, #VGIC_V2_CPU_MISR]
+	str	w7, [x3, #VGIC_V2_CPU_EISR]
+	str	w8, [x3, #(VGIC_V2_CPU_EISR + 4)]
+	str	w9, [x3, #VGIC_V2_CPU_ELRSR]
+	str	w10, [x3, #(VGIC_V2_CPU_ELRSR + 4)]
+	str	w11, [x3, #VGIC_V2_CPU_APR]
+
+	/* Clear GICH_HCR */
+	str	wzr, [x2, #GICH_HCR]
+
+	/* Save list registers */
+	add	x2, x2, #GICH_LR0
+	ldr	w4, [x3, #VGIC_CPU_NR_LR]
+	add	x3, x3, #VGIC_V2_CPU_LR
+1:	ldr	w5, [x2], #4
+CPU_BE(	rev	w5, w5 )
+	str	w5, [x3], #4
+	sub	w4, w4, #1
+	cbnz	w4, 1b
+2:
+	ret
+ENDPROC(__save_vgic_v2_state)
+
+/*
+ * Restore the VGIC CPU state from memory
+ * x0: Register pointing to VCPU struct
+ */
+ENTRY(__restore_vgic_v2_state)
+__restore_vgic_v2_state:
+	/* Get VGIC VCTRL base into x2 */
+	ldr	x2, [x0, #VCPU_KVM]
+	kern_hyp_va	x2
+	ldr	x2, [x2, #KVM_VGIC_VCTRL]
+	kern_hyp_va	x2
+	cbz	x2, 2f		// disabled
+
+	/* Compute the address of struct vgic_cpu */
+	add	x3, x0, #VCPU_VGIC_CPU
+
+	/* We only restore a minimal set of registers */
+	ldr	w4, [x3, #VGIC_V2_CPU_HCR]
+	ldr	w5, [x3, #VGIC_V2_CPU_VMCR]
+	ldr	w6, [x3, #VGIC_V2_CPU_APR]
+CPU_BE(	rev	w4, w4 )
+CPU_BE(	rev	w5, w5 )
+CPU_BE(	rev	w6, w6 )
+
+	str	w4, [x2, #GICH_HCR]
+	str	w5, [x2, #GICH_VMCR]
+	str	w6, [x2, #GICH_APR]
+
+	/* Restore list registers */
+	add	x2, x2, #GICH_LR0
+	ldr	w4, [x3, #VGIC_CPU_NR_LR]
+	add	x3, x3, #VGIC_V2_CPU_LR
+1:	ldr	w5, [x3], #4
+CPU_BE(	rev	w5, w5 )
+	str	w5, [x2], #4
+	sub	w4, w4, #1
+	cbnz	w4, 1b
+2:
+	ret
+ENDPROC(__restore_vgic_v2_state)
+
+	.popsection
diff --git a/arch/arm64/kvm/vgic-v3-switch.S b/arch/arm64/kvm/vgic-v3-switch.S
new file mode 100644
index 000000000000..d16046999e06
--- /dev/null
+++ b/arch/arm64/kvm/vgic-v3-switch.S
@@ -0,0 +1,267 @@
+/*
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/linkage.h>
+#include <linux/irqchip/arm-gic-v3.h>
+
+#include <asm/assembler.h>
+#include <asm/memory.h>
+#include <asm/asm-offsets.h>
+#include <asm/kvm.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_arm.h>
+
+	.text
+	.pushsection	.hyp.text, "ax"
+
+/*
+ * We store LRs in reverse order to let the CPU deal with streaming
+ * access. Use this macro to make it look saner...
+ */
+#define LR_OFFSET(n)	(VGIC_V3_CPU_LR + (15 - n) * 8)
+
+/*
+ * Save the VGIC CPU state into memory
+ * x0: Register pointing to VCPU struct
+ * Do not corrupt x1!!!
+ */
+.macro	save_vgic_v3_state
+	// Compute the address of struct vgic_cpu
+	add	x3, x0, #VCPU_VGIC_CPU
+
+	// Make sure stores to the GIC via the memory mapped interface
+	// are now visible to the system register interface
+	dsb	st
+
+	// Save all interesting registers
+	mrs_s	x4, ICH_HCR_EL2
+	mrs_s	x5, ICH_VMCR_EL2
+	mrs_s	x6, ICH_MISR_EL2
+	mrs_s	x7, ICH_EISR_EL2
+	mrs_s	x8, ICH_ELSR_EL2
+
+	str	w4, [x3, #VGIC_V3_CPU_HCR]
+	str	w5, [x3, #VGIC_V3_CPU_VMCR]
+	str	w6, [x3, #VGIC_V3_CPU_MISR]
+	str	w7, [x3, #VGIC_V3_CPU_EISR]
+	str	w8, [x3, #VGIC_V3_CPU_ELRSR]
+
+	msr_s	ICH_HCR_EL2, xzr
+
+	mrs_s	x21, ICH_VTR_EL2
+	mvn	w22, w21
+	ubfiz	w23, w22, 2, 4	// w23 = (15 - ListRegs) * 4
+
+	adr	x24, 1f
+	add	x24, x24, x23
+	br	x24
+
+1:
+	mrs_s	x20, ICH_LR15_EL2
+	mrs_s	x19, ICH_LR14_EL2
+	mrs_s	x18, ICH_LR13_EL2
+	mrs_s	x17, ICH_LR12_EL2
+	mrs_s	x16, ICH_LR11_EL2
+	mrs_s	x15, ICH_LR10_EL2
+	mrs_s	x14, ICH_LR9_EL2
+	mrs_s	x13, ICH_LR8_EL2
+	mrs_s	x12, ICH_LR7_EL2
+	mrs_s	x11, ICH_LR6_EL2
+	mrs_s	x10, ICH_LR5_EL2
+	mrs_s	x9, ICH_LR4_EL2
+	mrs_s	x8, ICH_LR3_EL2
+	mrs_s	x7, ICH_LR2_EL2
+	mrs_s	x6, ICH_LR1_EL2
+	mrs_s	x5, ICH_LR0_EL2
+
+	adr	x24, 1f
+	add	x24, x24, x23
+	br	x24
+
+1:
+	str	x20, [x3, #LR_OFFSET(15)]
+	str	x19, [x3, #LR_OFFSET(14)]
+	str	x18, [x3, #LR_OFFSET(13)]
+	str	x17, [x3, #LR_OFFSET(12)]
+	str	x16, [x3, #LR_OFFSET(11)]
+	str	x15, [x3, #LR_OFFSET(10)]
+	str	x14, [x3, #LR_OFFSET(9)]
+	str	x13, [x3, #LR_OFFSET(8)]
+	str	x12, [x3, #LR_OFFSET(7)]
+	str	x11, [x3, #LR_OFFSET(6)]
+	str	x10, [x3, #LR_OFFSET(5)]
+	str	x9, [x3, #LR_OFFSET(4)]
+	str	x8, [x3, #LR_OFFSET(3)]
+	str	x7, [x3, #LR_OFFSET(2)]
+	str	x6, [x3, #LR_OFFSET(1)]
+	str	x5, [x3, #LR_OFFSET(0)]
+
+	tbnz	w21, #29, 6f	// 6 bits
+	tbz	w21, #30, 5f	// 5 bits
+				// 7 bits
+	mrs_s	x20, ICH_AP0R3_EL2
+	str	w20, [x3, #(VGIC_V3_CPU_AP0R + 3*4)]
+	mrs_s	x19, ICH_AP0R2_EL2
+	str	w19, [x3, #(VGIC_V3_CPU_AP0R + 2*4)]
+6:	mrs_s	x18, ICH_AP0R1_EL2
+	str	w18, [x3, #(VGIC_V3_CPU_AP0R + 1*4)]
+5:	mrs_s	x17, ICH_AP0R0_EL2
+	str	w17, [x3, #VGIC_V3_CPU_AP0R]
+
+	tbnz	w21, #29, 6f	// 6 bits
+	tbz	w21, #30, 5f	// 5 bits
+				// 7 bits
+	mrs_s	x20, ICH_AP1R3_EL2
+	str	w20, [x3, #(VGIC_V3_CPU_AP1R + 3*4)]
+	mrs_s	x19, ICH_AP1R2_EL2
+	str	w19, [x3, #(VGIC_V3_CPU_AP1R + 2*4)]
+6:	mrs_s	x18, ICH_AP1R1_EL2
+	str	w18, [x3, #(VGIC_V3_CPU_AP1R + 1*4)]
+5:	mrs_s	x17, ICH_AP1R0_EL2
+	str	w17, [x3, #VGIC_V3_CPU_AP1R]
+
+	// Restore SRE_EL1 access and re-enable SRE at EL1.
+	mrs_s	x5, ICC_SRE_EL2
+	orr	x5, x5, #ICC_SRE_EL2_ENABLE
+	msr_s	ICC_SRE_EL2, x5
+	isb
+	mov	x5, #1
+	msr_s	ICC_SRE_EL1, x5
+.endm
+
+/*
+ * Restore the VGIC CPU state from memory
+ * x0: Register pointing to VCPU struct
+ */
+.macro	restore_vgic_v3_state
+	// Disable SRE_EL1 access. Necessary, otherwise
+	// ICH_VMCR_EL2.VFIQEn becomes one, and FIQ happens...
+	msr_s	ICC_SRE_EL1, xzr
+	isb
+
+	// Compute the address of struct vgic_cpu
+	add	x3, x0, #VCPU_VGIC_CPU
+
+	// Restore all interesting registers
+	ldr	w4, [x3, #VGIC_V3_CPU_HCR]
+	ldr	w5, [x3, #VGIC_V3_CPU_VMCR]
+
+	msr_s	ICH_HCR_EL2, x4
+	msr_s	ICH_VMCR_EL2, x5
+
+	mrs_s	x21, ICH_VTR_EL2
+
+	tbnz	w21, #29, 6f	// 6 bits
+	tbz	w21, #30, 5f	// 5 bits
+				// 7 bits
+	ldr	w20, [x3, #(VGIC_V3_CPU_AP1R + 3*4)]
+	msr_s	ICH_AP1R3_EL2, x20
+	ldr	w19, [x3, #(VGIC_V3_CPU_AP1R + 2*4)]
+	msr_s	ICH_AP1R2_EL2, x19
+6:	ldr	w18, [x3, #(VGIC_V3_CPU_AP1R + 1*4)]
+	msr_s	ICH_AP1R1_EL2, x18
+5:	ldr	w17, [x3, #VGIC_V3_CPU_AP1R]
+	msr_s	ICH_AP1R0_EL2, x17
+
+	tbnz	w21, #29, 6f	// 6 bits
+	tbz	w21, #30, 5f	// 5 bits
+				// 7 bits
+	ldr	w20, [x3, #(VGIC_V3_CPU_AP0R + 3*4)]
+	msr_s	ICH_AP0R3_EL2, x20
+	ldr	w19, [x3, #(VGIC_V3_CPU_AP0R + 2*4)]
+	msr_s	ICH_AP0R2_EL2, x19
+6:	ldr	w18, [x3, #(VGIC_V3_CPU_AP0R + 1*4)]
+	msr_s	ICH_AP0R1_EL2, x18
+5:	ldr	w17, [x3, #VGIC_V3_CPU_AP0R]
+	msr_s	ICH_AP0R0_EL2, x17
+
+	and	w22, w21, #0xf
+	mvn	w22, w21
+	ubfiz	w23, w22, 2, 4	// w23 = (15 - ListRegs) * 4
+
+	adr	x24, 1f
+	add	x24, x24, x23
+	br	x24
+
+1:
+	ldr	x20, [x3, #LR_OFFSET(15)]
+	ldr	x19, [x3, #LR_OFFSET(14)]
+	ldr	x18, [x3, #LR_OFFSET(13)]
+	ldr	x17, [x3, #LR_OFFSET(12)]
+	ldr	x16, [x3, #LR_OFFSET(11)]
+	ldr	x15, [x3, #LR_OFFSET(10)]
+	ldr	x14, [x3, #LR_OFFSET(9)]
+	ldr	x13, [x3, #LR_OFFSET(8)]
+	ldr	x12, [x3, #LR_OFFSET(7)]
+	ldr	x11, [x3, #LR_OFFSET(6)]
+	ldr	x10, [x3, #LR_OFFSET(5)]
+	ldr	x9, [x3, #LR_OFFSET(4)]
+	ldr	x8, [x3, #LR_OFFSET(3)]
+	ldr	x7, [x3, #LR_OFFSET(2)]
+	ldr	x6, [x3, #LR_OFFSET(1)]
+	ldr	x5, [x3, #LR_OFFSET(0)]
+
+	adr	x24, 1f
+	add	x24, x24, x23
+	br	x24
+
+1:
+	msr_s	ICH_LR15_EL2, x20
+	msr_s	ICH_LR14_EL2, x19
+	msr_s	ICH_LR13_EL2, x18
+	msr_s	ICH_LR12_EL2, x17
+	msr_s	ICH_LR11_EL2, x16
+	msr_s	ICH_LR10_EL2, x15
+	msr_s	ICH_LR9_EL2,  x14
+	msr_s	ICH_LR8_EL2,  x13
+	msr_s	ICH_LR7_EL2,  x12
+	msr_s	ICH_LR6_EL2,  x11
+	msr_s	ICH_LR5_EL2,  x10
+	msr_s	ICH_LR4_EL2,   x9
+	msr_s	ICH_LR3_EL2,   x8
+	msr_s	ICH_LR2_EL2,   x7
+	msr_s	ICH_LR1_EL2,   x6
+	msr_s	ICH_LR0_EL2,   x5
+
+	// Ensure that the above will have reached the
+	// (re)distributors. This ensure the guest will read
+	// the correct values from the memory-mapped interface.
+	isb
+	dsb	sy
+
+	// Prevent the guest from touching the GIC system registers
+	mrs_s	x5, ICC_SRE_EL2
+	and	x5, x5, #~ICC_SRE_EL2_ENABLE
+	msr_s	ICC_SRE_EL2, x5
+.endm
+
+ENTRY(__save_vgic_v3_state)
+	save_vgic_v3_state
+	ret
+ENDPROC(__save_vgic_v3_state)
+
+ENTRY(__restore_vgic_v3_state)
+	restore_vgic_v3_state
+	ret
+ENDPROC(__restore_vgic_v3_state)
+
+ENTRY(__vgic_v3_get_ich_vtr_el2)
+	mrs_s	x0, ICH_VTR_EL2
+	ret
+ENDPROC(__vgic_v3_get_ich_vtr_el2)
+
+	.popsection