Merge branch 'topic/enum-info-cleanup' into for-next

this is a series of patches to just convert the plain info callback
for enum ctl elements to snd_ctl_elem_info().  Also, it includes the
extension of snd_ctl_elem_info(), for catching the unexpected string
cut-off and handling the zero items.

28 files changed, 682 insertions, 254 deletions

diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index 0b3fcf86e6ba..dc770bd4f5a5 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -9,8 +9,9 @@ generic-y += current.h
 generic-y += delay.h
 generic-y += div64.h
 generic-y += dma.h
-generic-y += emergency-restart.h
+generic-y += dma-contiguous.h
 generic-y += early_ioremap.h
+generic-y += emergency-restart.h
 generic-y += errno.h
 generic-y += ftrace.h
 generic-y += hash.h
@@ -29,6 +30,7 @@ generic-y += mman.h
 generic-y += msgbuf.h
 generic-y += mutex.h
 generic-y += pci.h
+generic-y += pci-bridge.h
 generic-y += poll.h
 generic-y += preempt.h
 generic-y += resource.h
diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h
index 9400596a0f39..f19097134b02 100644
--- a/arch/arm64/include/asm/arch_timer.h
+++ b/arch/arm64/include/asm/arch_timer.h
@@ -104,37 +104,6 @@ static inline void arch_timer_set_cntkctl(u32 cntkctl)
 	asm volatile("msr	cntkctl_el1, %0" : : "r" (cntkctl));
 }
 
-static inline void arch_counter_set_user_access(void)
-{
-	u32 cntkctl = arch_timer_get_cntkctl();
-
-	/* Disable user access to the timers and the physical counter */
-	/* Also disable virtual event stream */
-	cntkctl &= ~(ARCH_TIMER_USR_PT_ACCESS_EN
-			| ARCH_TIMER_USR_VT_ACCESS_EN
-			| ARCH_TIMER_VIRT_EVT_EN
-			| ARCH_TIMER_USR_PCT_ACCESS_EN);
-
-	/* Enable user access to the virtual counter */
-	cntkctl |= ARCH_TIMER_USR_VCT_ACCESS_EN;
-
-	arch_timer_set_cntkctl(cntkctl);
-}
-
-static inline void arch_timer_evtstrm_enable(int divider)
-{
-	u32 cntkctl = arch_timer_get_cntkctl();
-	cntkctl &= ~ARCH_TIMER_EVT_TRIGGER_MASK;
-	/* Set the divider and enable virtual event stream */
-	cntkctl |= (divider << ARCH_TIMER_EVT_TRIGGER_SHIFT)
-			| ARCH_TIMER_VIRT_EVT_EN;
-	arch_timer_set_cntkctl(cntkctl);
-	elf_hwcap |= HWCAP_EVTSTRM;
-#ifdef CONFIG_COMPAT
-	compat_elf_hwcap |= COMPAT_HWCAP_EVTSTRM;
-#endif
-}
-
 static inline u64 arch_counter_get_cntvct(void)
 {
 	u64 cval;
diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h
index 65f1569ac96e..7047051ded40 100644
--- a/arch/arm64/include/asm/atomic.h
+++ b/arch/arm64/include/asm/atomic.h
@@ -35,7 +35,7 @@
  * strex/ldrex monitor on some implementations. The reason we can use it for
  * atomic_set() is the clrex or dummy strex done on every exception return.
  */
-#define atomic_read(v)	(*(volatile int *)&(v)->counter)
+#define atomic_read(v)	ACCESS_ONCE((v)->counter)
 #define atomic_set(v,i)	(((v)->counter) = (i))
 
 /*
@@ -43,69 +43,51 @@
  * store exclusive to ensure that these are atomic.  We may loop
  * to ensure that the update happens.
  */
-static inline void atomic_add(int i, atomic_t *v)
-{
-	unsigned long tmp;
-	int result;
-
-	asm volatile("// atomic_add\n"
-"1:	ldxr	%w0, %2\n"
-"	add	%w0, %w0, %w3\n"
-"	stxr	%w1, %w0, %2\n"
-"	cbnz	%w1, 1b"
-	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
-	: "Ir" (i));
-}
-
-static inline int atomic_add_return(int i, atomic_t *v)
-{
-	unsigned long tmp;
-	int result;
-
-	asm volatile("// atomic_add_return\n"
-"1:	ldxr	%w0, %2\n"
-"	add	%w0, %w0, %w3\n"
-"	stlxr	%w1, %w0, %2\n"
-"	cbnz	%w1, 1b"
-	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
-	: "Ir" (i)
-	: "memory");
-
-	smp_mb();
-	return result;
-}
-
-static inline void atomic_sub(int i, atomic_t *v)
-{
-	unsigned long tmp;
-	int result;
 
-	asm volatile("// atomic_sub\n"
-"1:	ldxr	%w0, %2\n"
-"	sub	%w0, %w0, %w3\n"
-"	stxr	%w1, %w0, %2\n"
-"	cbnz	%w1, 1b"
-	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
-	: "Ir" (i));
+#define ATOMIC_OP(op, asm_op)						\
+static inline void atomic_##op(int i, atomic_t *v)			\
+{									\
+	unsigned long tmp;						\
+	int result;							\
+									\
+	asm volatile("// atomic_" #op "\n"				\
+"1:	ldxr	%w0, %2\n"						\
+"	" #asm_op "	%w0, %w0, %w3\n"				\
+"	stxr	%w1, %w0, %2\n"						\
+"	cbnz	%w1, 1b"						\
+	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)		\
+	: "Ir" (i));							\
+}									\
+
+#define ATOMIC_OP_RETURN(op, asm_op)					\
+static inline int atomic_##op##_return(int i, atomic_t *v)		\
+{									\
+	unsigned long tmp;						\
+	int result;							\
+									\
+	asm volatile("// atomic_" #op "_return\n"			\
+"1:	ldxr	%w0, %2\n"						\
+"	" #asm_op "	%w0, %w0, %w3\n"				\
+"	stlxr	%w1, %w0, %2\n"						\
+"	cbnz	%w1, 1b"						\
+	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)		\
+	: "Ir" (i)							\
+	: "memory");							\
+									\
+	smp_mb();							\
+	return result;							\
 }
 
-static inline int atomic_sub_return(int i, atomic_t *v)
-{
-	unsigned long tmp;
-	int result;
+#define ATOMIC_OPS(op, asm_op)						\
+	ATOMIC_OP(op, asm_op)						\
+	ATOMIC_OP_RETURN(op, asm_op)
 
-	asm volatile("// atomic_sub_return\n"
-"1:	ldxr	%w0, %2\n"
-"	sub	%w0, %w0, %w3\n"
-"	stlxr	%w1, %w0, %2\n"
-"	cbnz	%w1, 1b"
-	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
-	: "Ir" (i)
-	: "memory");
+ATOMIC_OPS(add, add)
+ATOMIC_OPS(sub, sub)
 
-	smp_mb();
-	return result;
-}
+#undef ATOMIC_OPS
+#undef ATOMIC_OP_RETURN
+#undef ATOMIC_OP
 
 static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new)
 {
@@ -157,72 +139,53 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
  */
 #define ATOMIC64_INIT(i) { (i) }
 
-#define atomic64_read(v)	(*(volatile long *)&(v)->counter)
+#define atomic64_read(v)	ACCESS_ONCE((v)->counter)
 #define atomic64_set(v,i)	(((v)->counter) = (i))
 
-static inline void atomic64_add(u64 i, atomic64_t *v)
-{
-	long result;
-	unsigned long tmp;
-
-	asm volatile("// atomic64_add\n"
-"1:	ldxr	%0, %2\n"
-"	add	%0, %0, %3\n"
-"	stxr	%w1, %0, %2\n"
-"	cbnz	%w1, 1b"
-	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
-	: "Ir" (i));
+#define ATOMIC64_OP(op, asm_op)						\
+static inline void atomic64_##op(long i, atomic64_t *v)			\
+{									\
+	long result;							\
+	unsigned long tmp;						\
+									\
+	asm volatile("// atomic64_" #op "\n"				\
+"1:	ldxr	%0, %2\n"						\
+"	" #asm_op "	%0, %0, %3\n"					\
+"	stxr	%w1, %0, %2\n"						\
+"	cbnz	%w1, 1b"						\
+	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)		\
+	: "Ir" (i));							\
+}									\
+
+#define ATOMIC64_OP_RETURN(op, asm_op)					\
+static inline long atomic64_##op##_return(long i, atomic64_t *v)	\
+{									\
+	long result;							\
+	unsigned long tmp;						\
+									\
+	asm volatile("// atomic64_" #op "_return\n"			\
+"1:	ldxr	%0, %2\n"						\
+"	" #asm_op "	%0, %0, %3\n"					\
+"	stlxr	%w1, %0, %2\n"						\
+"	cbnz	%w1, 1b"						\
+	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)		\
+	: "Ir" (i)							\
+	: "memory");							\
+									\
+	smp_mb();							\
+	return result;							\
 }
 
-static inline long atomic64_add_return(long i, atomic64_t *v)
-{
-	long result;
-	unsigned long tmp;
+#define ATOMIC64_OPS(op, asm_op)					\
+	ATOMIC64_OP(op, asm_op)						\
+	ATOMIC64_OP_RETURN(op, asm_op)
 
-	asm volatile("// atomic64_add_return\n"
-"1:	ldxr	%0, %2\n"
-"	add	%0, %0, %3\n"
-"	stlxr	%w1, %0, %2\n"
-"	cbnz	%w1, 1b"
-	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
-	: "Ir" (i)
-	: "memory");
+ATOMIC64_OPS(add, add)
+ATOMIC64_OPS(sub, sub)
 
-	smp_mb();
-	return result;
-}
-
-static inline void atomic64_sub(u64 i, atomic64_t *v)
-{
-	long result;
-	unsigned long tmp;
-
-	asm volatile("// atomic64_sub\n"
-"1:	ldxr	%0, %2\n"
-"	sub	%0, %0, %3\n"
-"	stxr	%w1, %0, %2\n"
-"	cbnz	%w1, 1b"
-	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
-	: "Ir" (i));
-}
-
-static inline long atomic64_sub_return(long i, atomic64_t *v)
-{
-	long result;
-	unsigned long tmp;
-
-	asm volatile("// atomic64_sub_return\n"
-"1:	ldxr	%0, %2\n"
-"	sub	%0, %0, %3\n"
-"	stlxr	%w1, %0, %2\n"
-"	cbnz	%w1, 1b"
-	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
-	: "Ir" (i)
-	: "memory");
-
-	smp_mb();
-	return result;
-}
+#undef ATOMIC64_OPS
+#undef ATOMIC64_OP_RETURN
+#undef ATOMIC64_OP
 
 static inline long atomic64_cmpxchg(atomic64_t *ptr, long old, long new)
 {
diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h
index f2defe1c380c..689b6379188c 100644
--- a/arch/arm64/include/asm/cacheflush.h
+++ b/arch/arm64/include/asm/cacheflush.h
@@ -148,4 +148,8 @@ static inline void flush_cache_vunmap(unsigned long start, unsigned long end)
 {
 }
 
+int set_memory_ro(unsigned long addr, int numpages);
+int set_memory_rw(unsigned long addr, int numpages);
+int set_memory_x(unsigned long addr, int numpages);
+int set_memory_nx(unsigned long addr, int numpages);
 #endif
diff --git a/arch/arm64/include/asm/cachetype.h b/arch/arm64/include/asm/cachetype.h
index 7a2e0762cb40..4c631a0a3609 100644
--- a/arch/arm64/include/asm/cachetype.h
+++ b/arch/arm64/include/asm/cachetype.h
@@ -39,6 +39,26 @@
 
 extern unsigned long __icache_flags;
 
+#define CCSIDR_EL1_LINESIZE_MASK	0x7
+#define CCSIDR_EL1_LINESIZE(x)		((x) & CCSIDR_EL1_LINESIZE_MASK)
+
+#define CCSIDR_EL1_NUMSETS_SHIFT	13
+#define CCSIDR_EL1_NUMSETS_MASK		(0x7fff << CCSIDR_EL1_NUMSETS_SHIFT)
+#define CCSIDR_EL1_NUMSETS(x) \
+	(((x) & CCSIDR_EL1_NUMSETS_MASK) >> CCSIDR_EL1_NUMSETS_SHIFT)
+
+extern u64 __attribute_const__ icache_get_ccsidr(void);
+
+static inline int icache_get_linesize(void)
+{
+	return 16 << CCSIDR_EL1_LINESIZE(icache_get_ccsidr());
+}
+
+static inline int icache_get_numsets(void)
+{
+	return 1 + CCSIDR_EL1_NUMSETS(icache_get_ccsidr());
+}
+
 /*
  * Whilst the D-side always behaves as PIPT on AArch64, aliasing is
  * permitted in the I-cache.
diff --git a/arch/arm64/include/asm/cpu_ops.h b/arch/arm64/include/asm/cpu_ops.h
index d7b4b38a8e86..6f8e2ef9094a 100644
--- a/arch/arm64/include/asm/cpu_ops.h
+++ b/arch/arm64/include/asm/cpu_ops.h
@@ -28,6 +28,8 @@ struct device_node;
  *		enable-method property.
  * @cpu_init:	Reads any data necessary for a specific enable-method from the
  *		devicetree, for a given cpu node and proposed logical id.
+ * @cpu_init_idle: Reads any data necessary to initialize CPU idle states from
+ *		devicetree, for a given cpu node and proposed logical id.
  * @cpu_prepare: Early one-time preparation step for a cpu. If there is a
  *		mechanism for doing so, tests whether it is possible to boot
  *		the given CPU.
@@ -47,6 +49,7 @@ struct device_node;
 struct cpu_operations {
 	const char	*name;
 	int		(*cpu_init)(struct device_node *, unsigned int);
+	int		(*cpu_init_idle)(struct device_node *, unsigned int);
 	int		(*cpu_prepare)(unsigned int);
 	int		(*cpu_boot)(unsigned int);
 	void		(*cpu_postboot)(void);
@@ -61,7 +64,7 @@ struct cpu_operations {
 };
 
 extern const struct cpu_operations *cpu_ops[NR_CPUS];
-extern int __init cpu_read_ops(struct device_node *dn, int cpu);
-extern void __init cpu_read_bootcpu_ops(void);
+int __init cpu_read_ops(struct device_node *dn, int cpu);
+void __init cpu_read_bootcpu_ops(void);
 
 #endif /* ifndef __ASM_CPU_OPS_H */
diff --git a/arch/arm64/include/asm/cpuidle.h b/arch/arm64/include/asm/cpuidle.h
new file mode 100644
index 000000000000..b52a9932e2b1
--- /dev/null
+++ b/arch/arm64/include/asm/cpuidle.h
@@ -0,0 +1,13 @@
+#ifndef __ASM_CPUIDLE_H
+#define __ASM_CPUIDLE_H
+
+#ifdef CONFIG_CPU_IDLE
+extern int cpu_init_idle(unsigned int cpu);
+#else
+static inline int cpu_init_idle(unsigned int cpu)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+
+#endif
diff --git a/arch/arm64/include/asm/debug-monitors.h b/arch/arm64/include/asm/debug-monitors.h
index 7fb343779498..40ec68aa6870 100644
--- a/arch/arm64/include/asm/debug-monitors.h
+++ b/arch/arm64/include/asm/debug-monitors.h
@@ -48,11 +48,13 @@
 /*
  * #imm16 values used for BRK instruction generation
  * Allowed values for kgbd are 0x400 - 0x7ff
+ * 0x100: for triggering a fault on purpose (reserved)
  * 0x400: for dynamic BRK instruction
  * 0x401: for compile time BRK instruction
  */
-#define KGDB_DYN_DGB_BRK_IMM		0x400
-#define KDBG_COMPILED_DBG_BRK_IMM	0x401
+#define FAULT_BRK_IMM			0x100
+#define KGDB_DYN_DBG_BRK_IMM		0x400
+#define KGDB_COMPILED_DBG_BRK_IMM	0x401
 
 /*
  * BRK instruction encoding
@@ -61,24 +63,30 @@
 #define AARCH64_BREAK_MON	0xd4200000
 
 /*
+ * BRK instruction for provoking a fault on purpose
+ * Unlike kgdb, #imm16 value with unallocated handler is used for faulting.
+ */
+#define AARCH64_BREAK_FAULT	(AARCH64_BREAK_MON | (FAULT_BRK_IMM << 5))
+
+/*
  * Extract byte from BRK instruction
  */
-#define KGDB_DYN_DGB_BRK_INS_BYTE(x) \
+#define KGDB_DYN_DBG_BRK_INS_BYTE(x) \
 	((((AARCH64_BREAK_MON) & 0xffe0001f) >> (x * 8)) & 0xff)
 
 /*
  * Extract byte from BRK #imm16
  */
-#define KGBD_DYN_DGB_BRK_IMM_BYTE(x) \
-	(((((KGDB_DYN_DGB_BRK_IMM) & 0xffff) << 5) >> (x * 8)) & 0xff)
+#define KGBD_DYN_DBG_BRK_IMM_BYTE(x) \
+	(((((KGDB_DYN_DBG_BRK_IMM) & 0xffff) << 5) >> (x * 8)) & 0xff)
 
-#define KGDB_DYN_DGB_BRK_BYTE(x) \
-	(KGDB_DYN_DGB_BRK_INS_BYTE(x) | KGBD_DYN_DGB_BRK_IMM_BYTE(x))
+#define KGDB_DYN_DBG_BRK_BYTE(x) \
+	(KGDB_DYN_DBG_BRK_INS_BYTE(x) | KGBD_DYN_DBG_BRK_IMM_BYTE(x))
 
-#define  KGDB_DYN_BRK_INS_BYTE0  KGDB_DYN_DGB_BRK_BYTE(0)
-#define  KGDB_DYN_BRK_INS_BYTE1  KGDB_DYN_DGB_BRK_BYTE(1)
-#define  KGDB_DYN_BRK_INS_BYTE2  KGDB_DYN_DGB_BRK_BYTE(2)
-#define  KGDB_DYN_BRK_INS_BYTE3  KGDB_DYN_DGB_BRK_BYTE(3)
+#define  KGDB_DYN_BRK_INS_BYTE0  KGDB_DYN_DBG_BRK_BYTE(0)
+#define  KGDB_DYN_BRK_INS_BYTE1  KGDB_DYN_DBG_BRK_BYTE(1)
+#define  KGDB_DYN_BRK_INS_BYTE2  KGDB_DYN_DBG_BRK_BYTE(2)
+#define  KGDB_DYN_BRK_INS_BYTE3  KGDB_DYN_DBG_BRK_BYTE(3)
 
 #define CACHE_FLUSH_IS_SAFE		1
 
diff --git a/arch/arm64/include/asm/dma-contiguous.h b/arch/arm64/include/asm/dma-contiguous.h
deleted file mode 100644
index 14c4c0ca7f2a..000000000000
--- a/arch/arm64/include/asm/dma-contiguous.h
+++ /dev/null
@@ -1,28 +0,0 @@
-/*
- * Copyright (c) 2013, The Linux Foundation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only 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.
- */
-
-#ifndef _ASM_DMA_CONTIGUOUS_H
-#define _ASM_DMA_CONTIGUOUS_H
-
-#ifdef __KERNEL__
-#ifdef CONFIG_DMA_CMA
-
-#include <linux/types.h>
-
-static inline void
-dma_contiguous_early_fixup(phys_addr_t base, unsigned long size) { }
-
-#endif
-#endif
-
-#endif
diff --git a/arch/arm64/include/asm/dma-mapping.h b/arch/arm64/include/asm/dma-mapping.h
index dc82e52acdb3..adeae3f6f0fc 100644
--- a/arch/arm64/include/asm/dma-mapping.h
+++ b/arch/arm64/include/asm/dma-mapping.h
@@ -52,6 +52,13 @@ static inline void set_dma_ops(struct device *dev, struct dma_map_ops *ops)
 	dev->archdata.dma_ops = ops;
 }
 
+static inline int set_arch_dma_coherent_ops(struct device *dev)
+{
+	set_dma_ops(dev, &coherent_swiotlb_dma_ops);
+	return 0;
+}
+#define set_arch_dma_coherent_ops	set_arch_dma_coherent_ops
+
 #include <asm-generic/dma-mapping-common.h>
 
 static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
diff --git a/arch/arm64/include/asm/hardirq.h b/arch/arm64/include/asm/hardirq.h
index 0be67821f9ce..e8a3268a891c 100644
--- a/arch/arm64/include/asm/hardirq.h
+++ b/arch/arm64/include/asm/hardirq.h
@@ -47,8 +47,6 @@ static inline void ack_bad_irq(unsigned int irq)
 	irq_err_count++;
 }
 
-extern void handle_IRQ(unsigned int, struct pt_regs *);
-
 /*
  * No arch-specific IRQ flags.
  */
diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h
index dc1f73b13e74..56a9e63b6c33 100644
--- a/arch/arm64/include/asm/insn.h
+++ b/arch/arm64/include/asm/insn.h
@@ -2,6 +2,8 @@
  * Copyright (C) 2013 Huawei Ltd.
  * Author: Jiang Liu <liuj97@gmail.com>
  *
+ * Copyright (C) 2014 Zi Shen Lim <zlim.lnx@gmail.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.
@@ -64,12 +66,155 @@ enum aarch64_insn_imm_type {
 	AARCH64_INSN_IMM_14,
 	AARCH64_INSN_IMM_12,
 	AARCH64_INSN_IMM_9,
+	AARCH64_INSN_IMM_7,
+	AARCH64_INSN_IMM_6,
+	AARCH64_INSN_IMM_S,
+	AARCH64_INSN_IMM_R,
 	AARCH64_INSN_IMM_MAX
 };
 
+enum aarch64_insn_register_type {
+	AARCH64_INSN_REGTYPE_RT,
+	AARCH64_INSN_REGTYPE_RN,
+	AARCH64_INSN_REGTYPE_RT2,
+	AARCH64_INSN_REGTYPE_RM,
+	AARCH64_INSN_REGTYPE_RD,
+	AARCH64_INSN_REGTYPE_RA,
+};
+
+enum aarch64_insn_register {
+	AARCH64_INSN_REG_0  = 0,
+	AARCH64_INSN_REG_1  = 1,
+	AARCH64_INSN_REG_2  = 2,
+	AARCH64_INSN_REG_3  = 3,
+	AARCH64_INSN_REG_4  = 4,
+	AARCH64_INSN_REG_5  = 5,
+	AARCH64_INSN_REG_6  = 6,
+	AARCH64_INSN_REG_7  = 7,
+	AARCH64_INSN_REG_8  = 8,
+	AARCH64_INSN_REG_9  = 9,
+	AARCH64_INSN_REG_10 = 10,
+	AARCH64_INSN_REG_11 = 11,
+	AARCH64_INSN_REG_12 = 12,
+	AARCH64_INSN_REG_13 = 13,
+	AARCH64_INSN_REG_14 = 14,
+	AARCH64_INSN_REG_15 = 15,
+	AARCH64_INSN_REG_16 = 16,
+	AARCH64_INSN_REG_17 = 17,
+	AARCH64_INSN_REG_18 = 18,
+	AARCH64_INSN_REG_19 = 19,
+	AARCH64_INSN_REG_20 = 20,
+	AARCH64_INSN_REG_21 = 21,
+	AARCH64_INSN_REG_22 = 22,
+	AARCH64_INSN_REG_23 = 23,
+	AARCH64_INSN_REG_24 = 24,
+	AARCH64_INSN_REG_25 = 25,
+	AARCH64_INSN_REG_26 = 26,
+	AARCH64_INSN_REG_27 = 27,
+	AARCH64_INSN_REG_28 = 28,
+	AARCH64_INSN_REG_29 = 29,
+	AARCH64_INSN_REG_FP = 29, /* Frame pointer */
+	AARCH64_INSN_REG_30 = 30,
+	AARCH64_INSN_REG_LR = 30, /* Link register */
+	AARCH64_INSN_REG_ZR = 31, /* Zero: as source register */
+	AARCH64_INSN_REG_SP = 31  /* Stack pointer: as load/store base reg */
+};
+
+enum aarch64_insn_variant {
+	AARCH64_INSN_VARIANT_32BIT,
+	AARCH64_INSN_VARIANT_64BIT
+};
+
+enum aarch64_insn_condition {
+	AARCH64_INSN_COND_EQ = 0x0, /* == */
+	AARCH64_INSN_COND_NE = 0x1, /* != */
+	AARCH64_INSN_COND_CS = 0x2, /* unsigned >= */
+	AARCH64_INSN_COND_CC = 0x3, /* unsigned < */
+	AARCH64_INSN_COND_MI = 0x4, /* < 0 */
+	AARCH64_INSN_COND_PL = 0x5, /* >= 0 */
+	AARCH64_INSN_COND_VS = 0x6, /* overflow */
+	AARCH64_INSN_COND_VC = 0x7, /* no overflow */
+	AARCH64_INSN_COND_HI = 0x8, /* unsigned > */
+	AARCH64_INSN_COND_LS = 0x9, /* unsigned <= */
+	AARCH64_INSN_COND_GE = 0xa, /* signed >= */
+	AARCH64_INSN_COND_LT = 0xb, /* signed < */
+	AARCH64_INSN_COND_GT = 0xc, /* signed > */
+	AARCH64_INSN_COND_LE = 0xd, /* signed <= */
+	AARCH64_INSN_COND_AL = 0xe, /* always */
+};
+
 enum aarch64_insn_branch_type {
 	AARCH64_INSN_BRANCH_NOLINK,
 	AARCH64_INSN_BRANCH_LINK,
+	AARCH64_INSN_BRANCH_RETURN,
+	AARCH64_INSN_BRANCH_COMP_ZERO,
+	AARCH64_INSN_BRANCH_COMP_NONZERO,
+};
+
+enum aarch64_insn_size_type {
+	AARCH64_INSN_SIZE_8,
+	AARCH64_INSN_SIZE_16,
+	AARCH64_INSN_SIZE_32,
+	AARCH64_INSN_SIZE_64,
+};
+
+enum aarch64_insn_ldst_type {
+	AARCH64_INSN_LDST_LOAD_REG_OFFSET,
+	AARCH64_INSN_LDST_STORE_REG_OFFSET,
+	AARCH64_INSN_LDST_LOAD_PAIR_PRE_INDEX,
+	AARCH64_INSN_LDST_STORE_PAIR_PRE_INDEX,
+	AARCH64_INSN_LDST_LOAD_PAIR_POST_INDEX,
+	AARCH64_INSN_LDST_STORE_PAIR_POST_INDEX,
+};
+
+enum aarch64_insn_adsb_type {
+	AARCH64_INSN_ADSB_ADD,
+	AARCH64_INSN_ADSB_SUB,
+	AARCH64_INSN_ADSB_ADD_SETFLAGS,
+	AARCH64_INSN_ADSB_SUB_SETFLAGS
+};
+
+enum aarch64_insn_movewide_type {
+	AARCH64_INSN_MOVEWIDE_ZERO,
+	AARCH64_INSN_MOVEWIDE_KEEP,
+	AARCH64_INSN_MOVEWIDE_INVERSE
+};
+
+enum aarch64_insn_bitfield_type {
+	AARCH64_INSN_BITFIELD_MOVE,
+	AARCH64_INSN_BITFIELD_MOVE_UNSIGNED,
+	AARCH64_INSN_BITFIELD_MOVE_SIGNED
+};
+
+enum aarch64_insn_data1_type {
+	AARCH64_INSN_DATA1_REVERSE_16,
+	AARCH64_INSN_DATA1_REVERSE_32,
+	AARCH64_INSN_DATA1_REVERSE_64,
+};
+
+enum aarch64_insn_data2_type {
+	AARCH64_INSN_DATA2_UDIV,
+	AARCH64_INSN_DATA2_SDIV,
+	AARCH64_INSN_DATA2_LSLV,
+	AARCH64_INSN_DATA2_LSRV,
+	AARCH64_INSN_DATA2_ASRV,
+	AARCH64_INSN_DATA2_RORV,
+};
+
+enum aarch64_insn_data3_type {
+	AARCH64_INSN_DATA3_MADD,
+	AARCH64_INSN_DATA3_MSUB,
+};
+
+enum aarch64_insn_logic_type {
+	AARCH64_INSN_LOGIC_AND,
+	AARCH64_INSN_LOGIC_BIC,
+	AARCH64_INSN_LOGIC_ORR,
+	AARCH64_INSN_LOGIC_ORN,
+	AARCH64_INSN_LOGIC_EOR,
+	AARCH64_INSN_LOGIC_EON,
+	AARCH64_INSN_LOGIC_AND_SETFLAGS,
+	AARCH64_INSN_LOGIC_BIC_SETFLAGS
 };
 
 #define	__AARCH64_INSN_FUNCS(abbr, mask, val)	\
@@ -78,13 +223,58 @@ static __always_inline bool aarch64_insn_is_##abbr(u32 code) \
 static __always_inline u32 aarch64_insn_get_##abbr##_value(void) \
 { return (val); }
 
+__AARCH64_INSN_FUNCS(str_reg,	0x3FE0EC00, 0x38206800)
+__AARCH64_INSN_FUNCS(ldr_reg,	0x3FE0EC00, 0x38606800)
+__AARCH64_INSN_FUNCS(stp_post,	0x7FC00000, 0x28800000)
+__AARCH64_INSN_FUNCS(ldp_post,	0x7FC00000, 0x28C00000)
+__AARCH64_INSN_FUNCS(stp_pre,	0x7FC00000, 0x29800000)
+__AARCH64_INSN_FUNCS(ldp_pre,	0x7FC00000, 0x29C00000)
+__AARCH64_INSN_FUNCS(add_imm,	0x7F000000, 0x11000000)
+__AARCH64_INSN_FUNCS(adds_imm,	0x7F000000, 0x31000000)
+__AARCH64_INSN_FUNCS(sub_imm,	0x7F000000, 0x51000000)
+__AARCH64_INSN_FUNCS(subs_imm,	0x7F000000, 0x71000000)
+__AARCH64_INSN_FUNCS(movn,	0x7F800000, 0x12800000)
+__AARCH64_INSN_FUNCS(sbfm,	0x7F800000, 0x13000000)
+__AARCH64_INSN_FUNCS(bfm,	0x7F800000, 0x33000000)
+__AARCH64_INSN_FUNCS(movz,	0x7F800000, 0x52800000)
+__AARCH64_INSN_FUNCS(ubfm,	0x7F800000, 0x53000000)
+__AARCH64_INSN_FUNCS(movk,	0x7F800000, 0x72800000)
+__AARCH64_INSN_FUNCS(add,	0x7F200000, 0x0B000000)
+__AARCH64_INSN_FUNCS(adds,	0x7F200000, 0x2B000000)
+__AARCH64_INSN_FUNCS(sub,	0x7F200000, 0x4B000000)
+__AARCH64_INSN_FUNCS(subs,	0x7F200000, 0x6B000000)
+__AARCH64_INSN_FUNCS(madd,	0x7FE08000, 0x1B000000)
+__AARCH64_INSN_FUNCS(msub,	0x7FE08000, 0x1B008000)
+__AARCH64_INSN_FUNCS(udiv,	0x7FE0FC00, 0x1AC00800)
+__AARCH64_INSN_FUNCS(sdiv,	0x7FE0FC00, 0x1AC00C00)
+__AARCH64_INSN_FUNCS(lslv,	0x7FE0FC00, 0x1AC02000)
+__AARCH64_INSN_FUNCS(lsrv,	0x7FE0FC00, 0x1AC02400)
+__AARCH64_INSN_FUNCS(asrv,	0x7FE0FC00, 0x1AC02800)
+__AARCH64_INSN_FUNCS(rorv,	0x7FE0FC00, 0x1AC02C00)
+__AARCH64_INSN_FUNCS(rev16,	0x7FFFFC00, 0x5AC00400)
+__AARCH64_INSN_FUNCS(rev32,	0x7FFFFC00, 0x5AC00800)
+__AARCH64_INSN_FUNCS(rev64,	0x7FFFFC00, 0x5AC00C00)
+__AARCH64_INSN_FUNCS(and,	0x7F200000, 0x0A000000)
+__AARCH64_INSN_FUNCS(bic,	0x7F200000, 0x0A200000)
+__AARCH64_INSN_FUNCS(orr,	0x7F200000, 0x2A000000)
+__AARCH64_INSN_FUNCS(orn,	0x7F200000, 0x2A200000)
+__AARCH64_INSN_FUNCS(eor,	0x7F200000, 0x4A000000)
+__AARCH64_INSN_FUNCS(eon,	0x7F200000, 0x4A200000)
+__AARCH64_INSN_FUNCS(ands,	0x7F200000, 0x6A000000)
+__AARCH64_INSN_FUNCS(bics,	0x7F200000, 0x6A200000)
 __AARCH64_INSN_FUNCS(b,		0xFC000000, 0x14000000)
 __AARCH64_INSN_FUNCS(bl,	0xFC000000, 0x94000000)
+__AARCH64_INSN_FUNCS(cbz,	0xFE000000, 0x34000000)
+__AARCH64_INSN_FUNCS(cbnz,	0xFE000000, 0x35000000)
+__AARCH64_INSN_FUNCS(bcond,	0xFF000010, 0x54000000)
 __AARCH64_INSN_FUNCS(svc,	0xFFE0001F, 0xD4000001)
 __AARCH64_INSN_FUNCS(hvc,	0xFFE0001F, 0xD4000002)
 __AARCH64_INSN_FUNCS(smc,	0xFFE0001F, 0xD4000003)
 __AARCH64_INSN_FUNCS(brk,	0xFFE0001F, 0xD4200000)
 __AARCH64_INSN_FUNCS(hint,	0xFFFFF01F, 0xD503201F)
+__AARCH64_INSN_FUNCS(br,	0xFFFFFC1F, 0xD61F0000)
+__AARCH64_INSN_FUNCS(blr,	0xFFFFFC1F, 0xD63F0000)
+__AARCH64_INSN_FUNCS(ret,	0xFFFFFC1F, 0xD65F0000)
 
 #undef	__AARCH64_INSN_FUNCS
 
@@ -97,8 +287,67 @@ u32 aarch64_insn_encode_immediate(enum aarch64_insn_imm_type type,
 				  u32 insn, u64 imm);
 u32 aarch64_insn_gen_branch_imm(unsigned long pc, unsigned long addr,
 				enum aarch64_insn_branch_type type);
+u32 aarch64_insn_gen_comp_branch_imm(unsigned long pc, unsigned long addr,
+				     enum aarch64_insn_register reg,
+				     enum aarch64_insn_variant variant,
+				     enum aarch64_insn_branch_type type);
+u32 aarch64_insn_gen_cond_branch_imm(unsigned long pc, unsigned long addr,
+				     enum aarch64_insn_condition cond);
 u32 aarch64_insn_gen_hint(enum aarch64_insn_hint_op op);
 u32 aarch64_insn_gen_nop(void);
+u32 aarch64_insn_gen_branch_reg(enum aarch64_insn_register reg,
+				enum aarch64_insn_branch_type type);
+u32 aarch64_insn_gen_load_store_reg(enum aarch64_insn_register reg,
+				    enum aarch64_insn_register base,
+				    enum aarch64_insn_register offset,
+				    enum aarch64_insn_size_type size,
+				    enum aarch64_insn_ldst_type type);
+u32 aarch64_insn_gen_load_store_pair(enum aarch64_insn_register reg1,
+				     enum aarch64_insn_register reg2,
+				     enum aarch64_insn_register base,
+				     int offset,
+				     enum aarch64_insn_variant variant,
+				     enum aarch64_insn_ldst_type type);
+u32 aarch64_insn_gen_add_sub_imm(enum aarch64_insn_register dst,
+				 enum aarch64_insn_register src,
+				 int imm, enum aarch64_insn_variant variant,
+				 enum aarch64_insn_adsb_type type);
+u32 aarch64_insn_gen_bitfield(enum aarch64_insn_register dst,
+			      enum aarch64_insn_register src,
+			      int immr, int imms,
+			      enum aarch64_insn_variant variant,
+			      enum aarch64_insn_bitfield_type type);
+u32 aarch64_insn_gen_movewide(enum aarch64_insn_register dst,
+			      int imm, int shift,
+			      enum aarch64_insn_variant variant,
+			      enum aarch64_insn_movewide_type type);
+u32 aarch64_insn_gen_add_sub_shifted_reg(enum aarch64_insn_register dst,
+					 enum aarch64_insn_register src,
+					 enum aarch64_insn_register reg,
+					 int shift,
+					 enum aarch64_insn_variant variant,
+					 enum aarch64_insn_adsb_type type);
+u32 aarch64_insn_gen_data1(enum aarch64_insn_register dst,
+			   enum aarch64_insn_register src,
+			   enum aarch64_insn_variant variant,
+			   enum aarch64_insn_data1_type type);
+u32 aarch64_insn_gen_data2(enum aarch64_insn_register dst,
+			   enum aarch64_insn_register src,
+			   enum aarch64_insn_register reg,
+			   enum aarch64_insn_variant variant,
+			   enum aarch64_insn_data2_type type);
+u32 aarch64_insn_gen_data3(enum aarch64_insn_register dst,
+			   enum aarch64_insn_register src,
+			   enum aarch64_insn_register reg1,
+			   enum aarch64_insn_register reg2,
+			   enum aarch64_insn_variant variant,
+			   enum aarch64_insn_data3_type type);
+u32 aarch64_insn_gen_logical_shifted_reg(enum aarch64_insn_register dst,
+					 enum aarch64_insn_register src,
+					 enum aarch64_insn_register reg,
+					 int shift,
+					 enum aarch64_insn_variant variant,
+					 enum aarch64_insn_logic_type type);
 
 bool aarch64_insn_hotpatch_safe(u32 old_insn, u32 new_insn);
 
diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h
index e0ecdcf6632d..79f1d519221f 100644
--- a/arch/arm64/include/asm/io.h
+++ b/arch/arm64/include/asm/io.h
@@ -121,7 +121,8 @@ static inline u64 __raw_readq(const volatile void __iomem *addr)
 /*
  *  I/O port access primitives.
  */
-#define IO_SPACE_LIMIT		0xffff
+#define arch_has_dev_port()	(1)
+#define IO_SPACE_LIMIT		(SZ_32M - 1)
 #define PCI_IOBASE		((void __iomem *)(MODULES_VADDR - SZ_32M))
 
 static inline u8 inb(unsigned long addr)
@@ -243,7 +244,7 @@ extern void __iomem *ioremap_cache(phys_addr_t phys_addr, size_t size);
  * (PHYS_OFFSET and PHYS_MASK taken into account).
  */
 #define ARCH_HAS_VALID_PHYS_ADDR_RANGE
-extern int valid_phys_addr_range(unsigned long addr, size_t size);
+extern int valid_phys_addr_range(phys_addr_t addr, size_t size);
 extern int valid_mmap_phys_addr_range(unsigned long pfn, size_t size);
 
 extern int devmem_is_allowed(unsigned long pfn);
diff --git a/arch/arm64/include/asm/irq_work.h b/arch/arm64/include/asm/irq_work.h
new file mode 100644
index 000000000000..8e24ef3f7c82
--- /dev/null
+++ b/arch/arm64/include/asm/irq_work.h
@@ -0,0 +1,11 @@
+#ifndef __ASM_IRQ_WORK_H
+#define __ASM_IRQ_WORK_H
+
+#include <asm/smp.h>
+
+static inline bool arch_irq_work_has_interrupt(void)
+{
+	return !!__smp_cross_call;
+}
+
+#endif /* __ASM_IRQ_WORK_H */
diff --git a/arch/arm64/include/asm/kgdb.h b/arch/arm64/include/asm/kgdb.h
index 3c8aafc1082f..f69f69c8120c 100644
--- a/arch/arm64/include/asm/kgdb.h
+++ b/arch/arm64/include/asm/kgdb.h
@@ -29,7 +29,7 @@
 
 static inline void arch_kgdb_breakpoint(void)
 {
-	asm ("brk %0" : : "I" (KDBG_COMPILED_DBG_BRK_IMM));
+	asm ("brk %0" : : "I" (KGDB_COMPILED_DBG_BRK_IMM));
 }
 
 extern void kgdb_handle_bus_error(void);
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index cc83520459ed..7fd3e27e3ccc 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -122,6 +122,17 @@
 #define VTCR_EL2_T0SZ_MASK	0x3f
 #define VTCR_EL2_T0SZ_40B	24
 
+/*
+ * We configure the Stage-2 page tables to always restrict the IPA space to be
+ * 40 bits wide (T0SZ = 24).  Systems with a PARange smaller than 40 bits are
+ * not known to exist and will break with this configuration.
+ *
+ * Note that when using 4K pages, we concatenate two first level page tables
+ * together.
+ *
+ * The magic numbers used for VTTBR_X in this patch can be found in Tables
+ * D4-23 and D4-25 in ARM DDI 0487A.b.
+ */
 #ifdef CONFIG_ARM64_64K_PAGES
 /*
  * Stage2 translation configuration:
@@ -149,7 +160,7 @@
 #endif
 
 #define VTTBR_BADDR_SHIFT (VTTBR_X - 1)
-#define VTTBR_BADDR_MASK  (((1LLU << (40 - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT)
+#define VTTBR_BADDR_MASK  (((1LLU << (PHYS_MASK_SHIFT - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT)
 #define VTTBR_VMID_SHIFT  (48LLU)
 #define VTTBR_VMID_MASK	  (0xffLLU << VTTBR_VMID_SHIFT)
 
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index fdc3e21abd8d..5674a55b5518 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -174,6 +174,11 @@ static inline bool kvm_vcpu_trap_is_iabt(const struct kvm_vcpu *vcpu)
 
 static inline u8 kvm_vcpu_trap_get_fault(const struct kvm_vcpu *vcpu)
 {
+	return kvm_vcpu_get_hsr(vcpu) & ESR_EL2_FSC;
+}
+
+static inline u8 kvm_vcpu_trap_get_fault_type(const struct kvm_vcpu *vcpu)
+{
 	return kvm_vcpu_get_hsr(vcpu) & ESR_EL2_FSC_TYPE;
 }
 
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index e10c45a578e3..2012c4ba8d67 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -22,6 +22,8 @@
 #ifndef __ARM64_KVM_HOST_H__
 #define __ARM64_KVM_HOST_H__
 
+#include <linux/types.h>
+#include <linux/kvm_types.h>
 #include <asm/kvm.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_mmio.h>
@@ -41,8 +43,7 @@
 
 #define KVM_VCPU_MAX_FEATURES 3
 
-struct kvm_vcpu;
-int kvm_target_cpu(void);
+int __attribute_const__ kvm_target_cpu(void);
 int kvm_reset_vcpu(struct kvm_vcpu *vcpu);
 int kvm_arch_dev_ioctl_check_extension(long ext);
 
@@ -164,25 +165,23 @@ struct kvm_vcpu_stat {
 	u32 halt_wakeup;
 };
 
-struct kvm_vcpu_init;
 int kvm_vcpu_set_target(struct kvm_vcpu *vcpu,
 			const struct kvm_vcpu_init *init);
 int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init);
 unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu);
 int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices);
-struct kvm_one_reg;
 int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg);
 int kvm_arm_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg);
 
 #define KVM_ARCH_WANT_MMU_NOTIFIER
-struct kvm;
 int kvm_unmap_hva(struct kvm *kvm, unsigned long hva);
 int kvm_unmap_hva_range(struct kvm *kvm,
 			unsigned long start, unsigned long end);
 void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
 
 /* We do not have shadow page tables, hence the empty hooks */
-static inline int kvm_age_hva(struct kvm *kvm, unsigned long hva)
+static inline int kvm_age_hva(struct kvm *kvm, unsigned long start,
+			      unsigned long end)
 {
 	return 0;
 }
@@ -192,8 +191,13 @@ static inline int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
 	return 0;
 }
 
+static inline void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm,
+							 unsigned long address)
+{
+}
+
 struct kvm_vcpu *kvm_arm_get_running_vcpu(void);
-struct kvm_vcpu __percpu **kvm_get_running_vcpus(void);
+struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void);
 
 u64 kvm_call_hyp(void *hypfn, ...);
 
@@ -244,4 +248,10 @@ static inline void vgic_arch_setup(const struct vgic_params *vgic)
 	}
 }
 
+static inline void kvm_arch_hardware_disable(void) {}
+static inline void kvm_arch_hardware_unsetup(void) {}
+static inline void kvm_arch_sync_events(struct kvm *kvm) {}
+static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {}
+static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
+
 #endif /* __ARM64_KVM_HOST_H__ */
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 8e138c7c53ac..0caf7a59f6a1 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -41,6 +41,18 @@
  */
 #define TRAMPOLINE_VA		(HYP_PAGE_OFFSET_MASK & PAGE_MASK)
 
+/*
+ * KVM_MMU_CACHE_MIN_PAGES is the number of stage2 page table translation
+ * levels in addition to the PGD and potentially the PUD which are
+ * pre-allocated (we pre-allocate the fake PGD and the PUD when the Stage-2
+ * tables use one level of tables less than the kernel.
+ */
+#ifdef CONFIG_ARM64_64K_PAGES
+#define KVM_MMU_CACHE_MIN_PAGES	1
+#else
+#define KVM_MMU_CACHE_MIN_PAGES	2
+#endif
+
 #ifdef __ASSEMBLY__
 
 /*
@@ -53,23 +65,19 @@
 
 #else
 
+#include <asm/pgalloc.h>
 #include <asm/cachetype.h>
 #include <asm/cacheflush.h>
 
 #define KERN_TO_HYP(kva)	((unsigned long)kva - PAGE_OFFSET + HYP_PAGE_OFFSET)
 
 /*
- * Align KVM with the kernel's view of physical memory. Should be
- * 40bit IPA, with PGD being 8kB aligned in the 4KB page configuration.
+ * We currently only support a 40bit IPA.
  */
-#define KVM_PHYS_SHIFT	PHYS_MASK_SHIFT
+#define KVM_PHYS_SHIFT	(40)
 #define KVM_PHYS_SIZE	(1UL << KVM_PHYS_SHIFT)
 #define KVM_PHYS_MASK	(KVM_PHYS_SIZE - 1UL)
 
-/* Make sure we get the right size, and thus the right alignment */
-#define PTRS_PER_S2_PGD (1 << (KVM_PHYS_SHIFT - PGDIR_SHIFT))
-#define S2_PGD_ORDER	get_order(PTRS_PER_S2_PGD * sizeof(pgd_t))
-
 int create_hyp_mappings(void *from, void *to);
 int create_hyp_io_mappings(void *from, void *to, phys_addr_t);
 void free_boot_hyp_pgd(void);
@@ -78,7 +86,7 @@ void free_hyp_pgds(void);
 int kvm_alloc_stage2_pgd(struct kvm *kvm);
 void kvm_free_stage2_pgd(struct kvm *kvm);
 int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
-			  phys_addr_t pa, unsigned long size);
+			  phys_addr_t pa, unsigned long size, bool writable);
 
 int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run);
 
@@ -93,20 +101,8 @@ void kvm_clear_hyp_idmap(void);
 #define	kvm_set_pte(ptep, pte)		set_pte(ptep, pte)
 #define	kvm_set_pmd(pmdp, pmd)		set_pmd(pmdp, pmd)
 
-static inline bool kvm_is_write_fault(unsigned long esr)
-{
-	unsigned long esr_ec = esr >> ESR_EL2_EC_SHIFT;
-
-	if (esr_ec == ESR_EL2_EC_IABT)
-		return false;
-
-	if ((esr & ESR_EL2_ISV) && !(esr & ESR_EL2_WNR))
-		return false;
-
-	return true;
-}
-
 static inline void kvm_clean_pgd(pgd_t *pgd) {}
+static inline void kvm_clean_pmd(pmd_t *pmd) {}
 static inline void kvm_clean_pmd_entry(pmd_t *pmd) {}
 static inline void kvm_clean_pte(pte_t *pte) {}
 static inline void kvm_clean_pte_entry(pte_t *pte) {}
@@ -125,19 +121,116 @@ 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)
 
+/*
+ * In the case where PGDIR_SHIFT is larger than KVM_PHYS_SHIFT, we can address
+ * the entire IPA input range with a single pgd entry, and we would only need
+ * one pgd entry.  Note that in this case, the pgd is actually not used by
+ * the MMU for Stage-2 translations, but is merely a fake pgd used as a data
+ * structure for the kernel pgtable macros to work.
+ */
+#if PGDIR_SHIFT > KVM_PHYS_SHIFT
+#define PTRS_PER_S2_PGD_SHIFT	0
+#else
+#define PTRS_PER_S2_PGD_SHIFT	(KVM_PHYS_SHIFT - PGDIR_SHIFT)
+#endif
+#define PTRS_PER_S2_PGD		(1 << PTRS_PER_S2_PGD_SHIFT)
+#define S2_PGD_ORDER		get_order(PTRS_PER_S2_PGD * sizeof(pgd_t))
+
+/*
+ * If we are concatenating first level stage-2 page tables, we would have less
+ * than or equal to 16 pointers in the fake PGD, because that's what the
+ * architecture allows.  In this case, (4 - CONFIG_ARM64_PGTABLE_LEVELS)
+ * represents the first level for the host, and we add 1 to go to the next
+ * level (which uses contatenation) for the stage-2 tables.
+ */
+#if PTRS_PER_S2_PGD <= 16
+#define KVM_PREALLOC_LEVEL	(4 - CONFIG_ARM64_PGTABLE_LEVELS + 1)
+#else
+#define KVM_PREALLOC_LEVEL	(0)
+#endif
+
+/**
+ * kvm_prealloc_hwpgd - allocate inital table for VTTBR
+ * @kvm:	The KVM struct pointer for the VM.
+ * @pgd:	The kernel pseudo pgd
+ *
+ * When the kernel uses more levels of page tables than the guest, we allocate
+ * a fake PGD and pre-populate it to point to the next-level page table, which
+ * will be the real initial page table pointed to by the VTTBR.
+ *
+ * When KVM_PREALLOC_LEVEL==2, we allocate a single page for the PMD and
+ * the kernel will use folded pud.  When KVM_PREALLOC_LEVEL==1, we
+ * allocate 2 consecutive PUD pages.
+ */
+static inline int kvm_prealloc_hwpgd(struct kvm *kvm, pgd_t *pgd)
+{
+	unsigned int i;
+	unsigned long hwpgd;
+
+	if (KVM_PREALLOC_LEVEL == 0)
+		return 0;
+
+	hwpgd = __get_free_pages(GFP_KERNEL | __GFP_ZERO, PTRS_PER_S2_PGD_SHIFT);
+	if (!hwpgd)
+		return -ENOMEM;
+
+	for (i = 0; i < PTRS_PER_S2_PGD; i++) {
+		if (KVM_PREALLOC_LEVEL == 1)
+			pgd_populate(NULL, pgd + i,
+				     (pud_t *)hwpgd + i * PTRS_PER_PUD);
+		else if (KVM_PREALLOC_LEVEL == 2)
+			pud_populate(NULL, pud_offset(pgd, 0) + i,
+				     (pmd_t *)hwpgd + i * PTRS_PER_PMD);
+	}
+
+	return 0;
+}
+
+static inline void *kvm_get_hwpgd(struct kvm *kvm)
+{
+	pgd_t *pgd = kvm->arch.pgd;
+	pud_t *pud;
+
+	if (KVM_PREALLOC_LEVEL == 0)
+		return pgd;
+
+	pud = pud_offset(pgd, 0);
+	if (KVM_PREALLOC_LEVEL == 1)
+		return pud;
+
+	BUG_ON(KVM_PREALLOC_LEVEL != 2);
+	return pmd_offset(pud, 0);
+}
+
+static inline void kvm_free_hwpgd(struct kvm *kvm)
+{
+	if (KVM_PREALLOC_LEVEL > 0) {
+		unsigned long hwpgd = (unsigned long)kvm_get_hwpgd(kvm);
+		free_pages(hwpgd, PTRS_PER_S2_PGD_SHIFT);
+	}
+}
+
 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)
+#define kvm_pte_table_empty(kvm, ptep) kvm_page_empty(ptep)
+
+#ifdef __PAGETABLE_PMD_FOLDED
+#define kvm_pmd_table_empty(kvm, pmdp) (0)
+#else
+#define kvm_pmd_table_empty(kvm, pmdp) \
+	(kvm_page_empty(pmdp) && (!(kvm) || KVM_PREALLOC_LEVEL < 2))
+#endif
+
+#ifdef __PAGETABLE_PUD_FOLDED
+#define kvm_pud_table_empty(kvm, pudp) (0)
 #else
-#define kvm_pmd_table_empty(pmdp) (0)
+#define kvm_pud_table_empty(kvm, pudp) \
+	(kvm_page_empty(pudp) && (!(kvm) || KVM_PREALLOC_LEVEL < 1))
 #endif
-#define kvm_pud_table_empty(pudp) (0)
 
 
 struct kvm;
diff --git a/arch/arm64/include/asm/pci.h b/arch/arm64/include/asm/pci.h
new file mode 100644
index 000000000000..872ba939fcb2
--- /dev/null
+++ b/arch/arm64/include/asm/pci.h
@@ -0,0 +1,37 @@
+#ifndef __ASM_PCI_H
+#define __ASM_PCI_H
+#ifdef __KERNEL__
+
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/dma-mapping.h>
+
+#include <asm/io.h>
+#include <asm-generic/pci-bridge.h>
+#include <asm-generic/pci-dma-compat.h>
+
+#define PCIBIOS_MIN_IO		0x1000
+#define PCIBIOS_MIN_MEM		0
+
+/*
+ * Set to 1 if the kernel should re-assign all PCI bus numbers
+ */
+#define pcibios_assign_all_busses() \
+	(pci_has_flag(PCI_REASSIGN_ALL_BUS))
+
+/*
+ * PCI address space differs from physical memory address space
+ */
+#define PCI_DMA_BUS_IS_PHYS	(0)
+
+extern int isa_dma_bridge_buggy;
+
+#ifdef CONFIG_PCI
+static inline int pci_proc_domain(struct pci_bus *bus)
+{
+	return 1;
+}
+#endif  /* CONFIG_PCI */
+
+#endif  /* __KERNEL__ */
+#endif  /* __ASM_PCI_H */
diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h
index 453a179469a3..5279e5733386 100644
--- a/arch/arm64/include/asm/percpu.h
+++ b/arch/arm64/include/asm/percpu.h
@@ -26,13 +26,13 @@ static inline void set_my_cpu_offset(unsigned long off)
 static inline unsigned long __my_cpu_offset(void)
 {
 	unsigned long off;
-	register unsigned long *sp asm ("sp");
 
 	/*
 	 * We want to allow caching the value, so avoid using volatile and
 	 * instead use a fake stack read to hazard against barrier().
 	 */
-	asm("mrs %0, tpidr_el1" : "=r" (off) : "Q" (*sp));
+	asm("mrs %0, tpidr_el1" : "=r" (off) :
+		"Q" (*(const unsigned long *)current_stack_pointer));
 
 	return off;
 }
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index ffe1ba0506d1..41a43bf26492 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -79,7 +79,7 @@ extern void __pgd_error(const char *file, int line, unsigned long val);
 #define PAGE_HYP_DEVICE		__pgprot(PROT_DEVICE_nGnRE | PTE_HYP)
 
 #define PAGE_S2			__pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_NORMAL) | PTE_S2_RDONLY)
-#define PAGE_S2_DEVICE		__pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_DEVICE_nGnRE) | PTE_S2_RDWR | PTE_UXN)
+#define PAGE_S2_DEVICE		__pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_DEVICE_nGnRE) | PTE_S2_RDONLY | PTE_UXN)
 
 #define PAGE_NONE		__pgprot(((_PAGE_DEFAULT) & ~PTE_TYPE_MASK) | PTE_PROT_NONE | PTE_PXN | PTE_UXN)
 #define PAGE_SHARED		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE)
@@ -149,46 +149,51 @@ extern struct page *empty_zero_page;
 #define pte_valid_not_user(pte) \
 	((pte_val(pte) & (PTE_VALID | PTE_USER)) == PTE_VALID)
 
-static inline pte_t pte_wrprotect(pte_t pte)
+static inline pte_t clear_pte_bit(pte_t pte, pgprot_t prot)
 {
-	pte_val(pte) &= ~PTE_WRITE;
+	pte_val(pte) &= ~pgprot_val(prot);
 	return pte;
 }
 
-static inline pte_t pte_mkwrite(pte_t pte)
+static inline pte_t set_pte_bit(pte_t pte, pgprot_t prot)
 {
-	pte_val(pte) |= PTE_WRITE;
+	pte_val(pte) |= pgprot_val(prot);
 	return pte;
 }
 
+static inline pte_t pte_wrprotect(pte_t pte)
+{
+	return clear_pte_bit(pte, __pgprot(PTE_WRITE));
+}
+
+static inline pte_t pte_mkwrite(pte_t pte)
+{
+	return set_pte_bit(pte, __pgprot(PTE_WRITE));
+}
+
 static inline pte_t pte_mkclean(pte_t pte)
 {
-	pte_val(pte) &= ~PTE_DIRTY;
-	return pte;
+	return clear_pte_bit(pte, __pgprot(PTE_DIRTY));
 }
 
 static inline pte_t pte_mkdirty(pte_t pte)
 {
-	pte_val(pte) |= PTE_DIRTY;
-	return pte;
+	return set_pte_bit(pte, __pgprot(PTE_DIRTY));
 }
 
 static inline pte_t pte_mkold(pte_t pte)
 {
-	pte_val(pte) &= ~PTE_AF;
-	return pte;
+	return clear_pte_bit(pte, __pgprot(PTE_AF));
 }
 
 static inline pte_t pte_mkyoung(pte_t pte)
 {
-	pte_val(pte) |= PTE_AF;
-	return pte;
+	return set_pte_bit(pte, __pgprot(PTE_AF));
 }
 
 static inline pte_t pte_mkspecial(pte_t pte)
 {
-	pte_val(pte) |= PTE_SPECIAL;
-	return pte;
+	return set_pte_bit(pte, __pgprot(PTE_SPECIAL));
 }
 
 static inline void set_pte(pte_t *ptep, pte_t pte)
@@ -239,6 +244,16 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 
 #define __HAVE_ARCH_PTE_SPECIAL
 
+static inline pte_t pud_pte(pud_t pud)
+{
+	return __pte(pud_val(pud));
+}
+
+static inline pmd_t pud_pmd(pud_t pud)
+{
+	return __pmd(pud_val(pud));
+}
+
 static inline pte_t pmd_pte(pmd_t pmd)
 {
 	return __pte(pmd_val(pmd));
@@ -256,7 +271,13 @@ static inline pmd_t pte_pmd(pte_t pte)
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 #define pmd_trans_huge(pmd)	(pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT))
 #define pmd_trans_splitting(pmd)	pte_special(pmd_pte(pmd))
-#endif
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+#define __HAVE_ARCH_PMDP_SPLITTING_FLUSH
+struct vm_area_struct;
+void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address,
+			  pmd_t *pmdp);
+#endif /* CONFIG_HAVE_RCU_TABLE_FREE */
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 #define pmd_young(pmd)		pte_young(pmd_pte(pmd))
 #define pmd_wrprotect(pmd)	pte_pmd(pte_wrprotect(pmd_pte(pmd)))
@@ -277,6 +298,7 @@ static inline pmd_t pte_pmd(pte_t pte)
 #define mk_pmd(page,prot)	pfn_pmd(page_to_pfn(page),prot)
 
 #define pmd_page(pmd)           pfn_to_page(__phys_to_pfn(pmd_val(pmd) & PHYS_MASK))
+#define pud_write(pud)		pte_write(pud_pte(pud))
 #define pud_pfn(pud)		(((pud_val(pud) & PUD_MASK) & PHYS_MASK) >> PAGE_SHIFT)
 
 #define set_pmd_at(mm, addr, pmdp, pmd)	set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd))
@@ -296,6 +318,8 @@ static inline int has_transparent_hugepage(void)
 	__pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_DEVICE_nGnRnE) | PTE_PXN | PTE_UXN)
 #define pgprot_writecombine(prot) \
 	__pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_NORMAL_NC) | PTE_PXN | PTE_UXN)
+#define pgprot_device(prot) \
+	__pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_DEVICE_nGnRE) | PTE_PXN | PTE_UXN)
 #define __HAVE_PHYS_MEM_ACCESS_PROT
 struct file;
 extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
@@ -376,6 +400,8 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
 	return (pmd_t *)pud_page_vaddr(*pud) + pmd_index(addr);
 }
 
+#define pud_page(pud)           pmd_page(pud_pmd(pud))
+
 #endif	/* CONFIG_ARM64_PGTABLE_LEVELS > 2 */
 
 #if CONFIG_ARM64_PGTABLE_LEVELS > 3
diff --git a/arch/arm64/include/asm/proc-fns.h b/arch/arm64/include/asm/proc-fns.h
index 0c657bb54597..9a8fd84f8fb2 100644
--- a/arch/arm64/include/asm/proc-fns.h
+++ b/arch/arm64/include/asm/proc-fns.h
@@ -32,6 +32,8 @@ extern void cpu_cache_off(void);
 extern void cpu_do_idle(void);
 extern void cpu_do_switch_mm(unsigned long pgd_phys, struct mm_struct *mm);
 extern void cpu_reset(unsigned long addr) __attribute__((noreturn));
+void cpu_soft_restart(phys_addr_t cpu_reset,
+		unsigned long addr) __attribute__((noreturn));
 extern void cpu_do_suspend(struct cpu_suspend_ctx *ptr);
 extern u64 cpu_do_resume(phys_addr_t ptr, u64 idmap_ttbr);
 
diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h
index a498f2cd2c2a..780f82c827b6 100644
--- a/arch/arm64/include/asm/smp.h
+++ b/arch/arm64/include/asm/smp.h
@@ -48,6 +48,8 @@ extern void smp_init_cpus(void);
  */
 extern void set_smp_cross_call(void (*)(const struct cpumask *, unsigned int));
 
+extern void (*__smp_cross_call)(const struct cpumask *, unsigned int);
+
 /*
  * Called from the secondary holding pen, this is the secondary CPU entry point.
  */
diff --git a/arch/arm64/include/asm/suspend.h b/arch/arm64/include/asm/suspend.h
index e9c149c042e0..456d67c1f0fa 100644
--- a/arch/arm64/include/asm/suspend.h
+++ b/arch/arm64/include/asm/suspend.h
@@ -21,6 +21,7 @@ struct sleep_save_sp {
 	phys_addr_t save_ptr_stash_phys;
 };
 
+extern int __cpu_suspend(unsigned long arg, int (*fn)(unsigned long));
 extern void cpu_resume(void);
 extern int cpu_suspend(unsigned long);
 
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index 45108d802f5e..459bf8e53208 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -69,14 +69,19 @@ struct thread_info {
 #define init_stack		(init_thread_union.stack)
 
 /*
+ * how to get the current stack pointer from C
+ */
+register unsigned long current_stack_pointer asm ("sp");
+
+/*
  * how to get the thread information struct from C
  */
 static inline struct thread_info *current_thread_info(void) __attribute_const__;
 
 static inline struct thread_info *current_thread_info(void)
 {
-	register unsigned long sp asm ("sp");
-	return (struct thread_info *)(sp & ~(THREAD_SIZE - 1));
+	return (struct thread_info *)
+		(current_stack_pointer & ~(THREAD_SIZE - 1));
 }
 
 #define thread_saved_pc(tsk)	\
diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h
index 62731ef9749a..a82c0c5c8b52 100644
--- a/arch/arm64/include/asm/tlb.h
+++ b/arch/arm64/include/asm/tlb.h
@@ -23,6 +23,20 @@
 
 #include <asm-generic/tlb.h>
 
+#include <linux/pagemap.h>
+#include <linux/swap.h>
+
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+
+#define tlb_remove_entry(tlb, entry)	tlb_remove_table(tlb, entry)
+static inline void __tlb_remove_table(void *_table)
+{
+	free_page_and_swap_cache((struct page *)_table);
+}
+#else
+#define tlb_remove_entry(tlb, entry)	tlb_remove_page(tlb, entry)
+#endif /* CONFIG_HAVE_RCU_TABLE_FREE */
+
 /*
  * There's three ways the TLB shootdown code is used:
  *  1. Unmapping a range of vmas.  See zap_page_range(), unmap_region().
@@ -88,7 +102,7 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
 {
 	pgtable_page_dtor(pte);
 	tlb_add_flush(tlb, addr);
-	tlb_remove_page(tlb, pte);
+	tlb_remove_entry(tlb, pte);
 }
 
 #if CONFIG_ARM64_PGTABLE_LEVELS > 2
@@ -96,7 +110,7 @@ static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
 				  unsigned long addr)
 {
 	tlb_add_flush(tlb, addr);
-	tlb_remove_page(tlb, virt_to_page(pmdp));
+	tlb_remove_entry(tlb, virt_to_page(pmdp));
 }
 #endif
 
@@ -105,7 +119,7 @@ static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pudp,
 				  unsigned long addr)
 {
 	tlb_add_flush(tlb, addr);
-	tlb_remove_page(tlb, virt_to_page(pudp));
+	tlb_remove_entry(tlb, virt_to_page(pudp));
 }
 #endif
 
diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h
index e633ff8cdec8..8e38878c87c6 100644
--- a/arch/arm64/include/uapi/asm/kvm.h
+++ b/arch/arm64/include/uapi/asm/kvm.h
@@ -37,6 +37,7 @@
 
 #define __KVM_HAVE_GUEST_DEBUG
 #define __KVM_HAVE_IRQ_LINE
+#define __KVM_HAVE_READONLY_MEM
 
 #define KVM_REG_SIZE(id)						\
 	(1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT))
@@ -159,6 +160,7 @@ struct kvm_arch_memory_slot {
 #define   KVM_DEV_ARM_VGIC_CPUID_MASK	(0xffULL << KVM_DEV_ARM_VGIC_CPUID_SHIFT)
 #define   KVM_DEV_ARM_VGIC_OFFSET_SHIFT	0
 #define   KVM_DEV_ARM_VGIC_OFFSET_MASK	(0xffffffffULL << KVM_DEV_ARM_VGIC_OFFSET_SHIFT)
+#define KVM_DEV_ARM_VGIC_GRP_NR_IRQS	3
 
 /* KVM_IRQ_LINE irq field index values */
 #define KVM_ARM_IRQ_TYPE_SHIFT		24