Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/cmarinas/linux-aarch64

Pull ARM64 update from Catalin Marinas:
 "Main features:
   - Ticket-based spinlock implementation and lockless lockref support
   - Big endian support
   - CPU hotplug support, currently for PSCI (Power State Coordination
     Interface) capable firmware
   - Virtual address space extended to 42-bit in the 64K page
     configuration (maximum VA space with 2 levels of page tables)
   - Compat (AArch32) kuser helpers updated to ARMv8 (make use of
     load-acquire/store-release instructions)
   - Code cleanup, defconfig update and minor fixes"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/cmarinas/linux-aarch64: (43 commits)
  ARM64: /proc/interrupts: display IPIs of online CPUs only
  arm64: locks: Remove CONFIG_GENERIC_LOCKBREAK
  arm64: KVM: vgic: byteswap GICv2 access on world switch if BE
  arm64: KVM: initialize HYP mode following the kernel endianness
  arm64: compat: Clear the IT state independent of the 32-bit ARM or Thumb-2 mode
  arm64: Use 42-bit address space with 64K pages
  arm64: module: ensure instruction is little-endian before manipulation
  arm64: defconfig: Enable CONFIG_PREEMPT by default
  arm64: fix access to preempt_count from assembly code
  arm64: move enabling of GIC before CPUs are set online
  arm64: use generic RW_DATA_SECTION macro in linker script
  arm64: Slightly improve the warning on CPU0 enable-method
  ARM64: simplify cpu_read_bootcpu_ops using OF/DT helper
  ARM64: DT: define ARM64 specific arch_match_cpu_phys_id
  arm64: allow ioremap_cache() to use existing RAM mappings
  arm64: update 32-bit kuser helpers to ARMv8
  arm64: perf: fix event number mask
  arm64: kconfig: allow CPU_BIG_ENDIAN to be selected
  arm64: Fix the endianness of arch_spinlock_t
  arm64: big-endian: write CPU holding pen address as LE
  ...

46 files changed, 878 insertions, 354 deletions

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index c04454876bcb..ce6ae9497492 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1,6 +1,7 @@
 config ARM64
 	def_bool y
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
+	select ARCH_USE_CMPXCHG_LOCKREF
 	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select ARCH_WANT_COMPAT_IPC_PARSE_VERSION
 	select ARCH_WANT_FRAME_POINTERS
@@ -61,10 +62,6 @@ config LOCKDEP_SUPPORT
 config TRACE_IRQFLAGS_SUPPORT
 	def_bool y
 
-config GENERIC_LOCKBREAK
-	def_bool y
-	depends on SMP && PREEMPT
-
 config RWSEM_GENERIC_SPINLOCK
 	def_bool y
 
@@ -138,6 +135,11 @@ config ARM64_64K_PAGES
 	  look-up. AArch32 emulation is not available when this feature
 	  is enabled.
 
+config CPU_BIG_ENDIAN
+       bool "Build big-endian kernel"
+       help
+         Say Y if you plan on running a kernel in big-endian mode.
+
 config SMP
 	bool "Symmetric Multi-Processing"
 	select USE_GENERIC_SMP_HELPERS
@@ -160,6 +162,13 @@ config NR_CPUS
 	default "8" if ARCH_XGENE
 	default "4"
 
+config HOTPLUG_CPU
+	bool "Support for hot-pluggable CPUs"
+	depends on SMP
+	help
+	  Say Y here to experiment with turning CPUs off and on.  CPUs
+	  can be controlled through /sys/devices/system/cpu.
+
 source kernel/Kconfig.preempt
 
 config HZ
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index d90cf79f233a..2fceb71ac3b7 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -20,9 +20,15 @@ LIBGCC 		:= $(shell $(CC) $(KBUILD_CFLAGS) -print-libgcc-file-name)
 KBUILD_DEFCONFIG := defconfig
 
 KBUILD_CFLAGS	+= -mgeneral-regs-only
+ifeq ($(CONFIG_CPU_BIG_ENDIAN), y)
+KBUILD_CPPFLAGS	+= -mbig-endian
+AS		+= -EB
+LD		+= -EB
+else
 KBUILD_CPPFLAGS	+= -mlittle-endian
 AS		+= -EL
 LD		+= -EL
+endif
 
 comma = ,
 
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 31c81e9b792e..84139be62ae6 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -26,7 +26,7 @@ CONFIG_MODULE_UNLOAD=y
 CONFIG_ARCH_VEXPRESS=y
 CONFIG_ARCH_XGENE=y
 CONFIG_SMP=y
-CONFIG_PREEMPT_VOLUNTARY=y
+CONFIG_PREEMPT=y
 CONFIG_CMDLINE="console=ttyAMA0"
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 CONFIG_COMPAT=y
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index 5aceb83b3f5c..fd3e3924041b 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -115,3 +115,34 @@ lr	.req	x30		// link register
 	.align	7
 	b	\label
 	.endm
+
+/*
+ * Select code when configured for BE.
+ */
+#ifdef CONFIG_CPU_BIG_ENDIAN
+#define CPU_BE(code...) code
+#else
+#define CPU_BE(code...)
+#endif
+
+/*
+ * Select code when configured for LE.
+ */
+#ifdef CONFIG_CPU_BIG_ENDIAN
+#define CPU_LE(code...)
+#else
+#define CPU_LE(code...) code
+#endif
+
+/*
+ * Define a macro that constructs a 64-bit value by concatenating two
+ * 32-bit registers. Note that on big endian systems the order of the
+ * registers is swapped.
+ */
+#ifndef CONFIG_CPU_BIG_ENDIAN
+	.macro	regs_to_64, rd, lbits, hbits
+#else
+	.macro	regs_to_64, rd, hbits, lbits
+#endif
+	orr	\rd, \lbits, \hbits, lsl #32
+	.endm
diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h
index 8a8ce0e73a38..3914c0dcd09c 100644
--- a/arch/arm64/include/asm/cmpxchg.h
+++ b/arch/arm64/include/asm/cmpxchg.h
@@ -173,4 +173,6 @@ static inline unsigned long __cmpxchg_mb(volatile void *ptr, unsigned long old,
 #define cmpxchg64(ptr,o,n)		cmpxchg((ptr),(o),(n))
 #define cmpxchg64_local(ptr,o,n)	cmpxchg_local((ptr),(o),(n))
 
+#define cmpxchg64_relaxed(ptr,o,n)	cmpxchg_local((ptr),(o),(n))
+
 #endif	/* __ASM_CMPXCHG_H */
diff --git a/arch/arm64/include/asm/compat.h b/arch/arm64/include/asm/compat.h
index 899af807ef0f..fda2704b3f9f 100644
--- a/arch/arm64/include/asm/compat.h
+++ b/arch/arm64/include/asm/compat.h
@@ -26,7 +26,11 @@
 #include <linux/ptrace.h>
 
 #define COMPAT_USER_HZ		100
+#ifdef __AARCH64EB__
+#define COMPAT_UTS_MACHINE	"armv8b\0\0"
+#else
 #define COMPAT_UTS_MACHINE	"armv8l\0\0"
+#endif
 
 typedef u32		compat_size_t;
 typedef s32		compat_ssize_t;
@@ -73,13 +77,23 @@ struct compat_timeval {
 };
 
 struct compat_stat {
+#ifdef __AARCH64EB__
+	short		st_dev;
+	short		__pad1;
+#else
 	compat_dev_t	st_dev;
+#endif
 	compat_ino_t	st_ino;
 	compat_mode_t	st_mode;
 	compat_ushort_t	st_nlink;
 	__compat_uid16_t	st_uid;
 	__compat_gid16_t	st_gid;
+#ifdef __AARCH64EB__
+	short		st_rdev;
+	short		__pad2;
+#else
 	compat_dev_t	st_rdev;
+#endif
 	compat_off_t	st_size;
 	compat_off_t	st_blksize;
 	compat_off_t	st_blocks;
diff --git a/arch/arm64/include/asm/cpu_ops.h b/arch/arm64/include/asm/cpu_ops.h
new file mode 100644
index 000000000000..c4cdb5e5b73d
--- /dev/null
+++ b/arch/arm64/include/asm/cpu_ops.h
@@ -0,0 +1,59 @@
+/*
+ * Copyright (C) 2013 ARM Ltd.
+ *
+ * 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/>.
+ */
+#ifndef __ASM_CPU_OPS_H
+#define __ASM_CPU_OPS_H
+
+#include <linux/init.h>
+#include <linux/threads.h>
+
+struct device_node;
+
+/**
+ * struct cpu_operations - Callback operations for hotplugging CPUs.
+ *
+ * @name:	Name of the property as appears in a devicetree cpu node's
+ *		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_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.
+ * @cpu_boot:	Boots a cpu into the kernel.
+ * @cpu_postboot: Optionally, perform any post-boot cleanup or necesary
+ *		synchronisation. Called from the cpu being booted.
+ * @cpu_disable: Prepares a cpu to die. May fail for some mechanism-specific
+ * 		reason, which will cause the hot unplug to be aborted. Called
+ * 		from the cpu to be killed.
+ * @cpu_die:	Makes a cpu leave the kernel. Must not fail. Called from the
+ *		cpu being killed.
+ */
+struct cpu_operations {
+	const char	*name;
+	int		(*cpu_init)(struct device_node *, unsigned int);
+	int		(*cpu_prepare)(unsigned int);
+	int		(*cpu_boot)(unsigned int);
+	void		(*cpu_postboot)(void);
+#ifdef CONFIG_HOTPLUG_CPU
+	int		(*cpu_disable)(unsigned int cpu);
+	void		(*cpu_die)(unsigned int cpu);
+#endif
+};
+
+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);
+
+#endif /* ifndef __ASM_CPU_OPS_H */
diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h
index e7fa87f9201b..01d3aab64b79 100644
--- a/arch/arm64/include/asm/elf.h
+++ b/arch/arm64/include/asm/elf.h
@@ -90,11 +90,24 @@ typedef struct user_fpsimd_state elf_fpregset_t;
  * These are used to set parameters in the core dumps.
  */
 #define ELF_CLASS	ELFCLASS64
+#ifdef __AARCH64EB__
+#define ELF_DATA	ELFDATA2MSB
+#else
 #define ELF_DATA	ELFDATA2LSB
+#endif
 #define ELF_ARCH	EM_AARCH64
 
+/*
+ * This yields a string that ld.so will use to load implementation
+ * specific libraries for optimization.  This is more specific in
+ * intent than poking at uname or /proc/cpuinfo.
+ */
 #define ELF_PLATFORM_SIZE	16
+#ifdef __AARCH64EB__
+#define ELF_PLATFORM		("aarch64_be")
+#else
 #define ELF_PLATFORM		("aarch64")
+#endif
 
 /*
  * This is used to ensure we don't load something for the wrong architecture.
@@ -149,7 +162,12 @@ extern unsigned long arch_randomize_brk(struct mm_struct *mm);
 #define arch_randomize_brk arch_randomize_brk
 
 #ifdef CONFIG_COMPAT
+
+#ifdef __AARCH64EB__
+#define COMPAT_ELF_PLATFORM		("v8b")
+#else
 #define COMPAT_ELF_PLATFORM		("v8l")
+#endif
 
 #define COMPAT_ELF_ET_DYN_BASE		(randomize_et_dyn(2 * TASK_SIZE_32 / 3))
 
diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h
index 1d12f89140ba..b56e5b5df881 100644
--- a/arch/arm64/include/asm/io.h
+++ b/arch/arm64/include/asm/io.h
@@ -224,6 +224,7 @@ extern void __memset_io(volatile void __iomem *, int, size_t);
  */
 extern void __iomem *__ioremap(phys_addr_t phys_addr, size_t size, pgprot_t prot);
 extern void __iounmap(volatile void __iomem *addr);
+extern void __iomem *ioremap_cache(phys_addr_t phys_addr, size_t size);
 
 #define PROT_DEFAULT		(PTE_TYPE_PAGE | PTE_AF | PTE_DIRTY)
 #define PROT_DEVICE_nGnRE	(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_DEVICE_nGnRE))
@@ -233,7 +234,6 @@ extern void __iounmap(volatile void __iomem *addr);
 #define ioremap(addr, size)		__ioremap((addr), (size), __pgprot(PROT_DEVICE_nGnRE))
 #define ioremap_nocache(addr, size)	__ioremap((addr), (size), __pgprot(PROT_DEVICE_nGnRE))
 #define ioremap_wc(addr, size)		__ioremap((addr), (size), __pgprot(PROT_NORMAL_NC))
-#define ioremap_cached(addr, size)	__ioremap((addr), (size), __pgprot(PROT_NORMAL))
 #define iounmap				__iounmap
 
 #define PROT_SECT_DEFAULT	(PMD_TYPE_SECT | PMD_SECT_AF)
diff --git a/arch/arm64/include/asm/irq.h b/arch/arm64/include/asm/irq.h
index 0332fc077f6e..e1f7ecdde11f 100644
--- a/arch/arm64/include/asm/irq.h
+++ b/arch/arm64/include/asm/irq.h
@@ -4,6 +4,7 @@
 #include <asm-generic/irq.h>
 
 extern void (*handle_arch_irq)(struct pt_regs *);
+extern void migrate_irqs(void);
 extern void set_handle_irq(void (*handle_irq)(struct pt_regs *));
 
 #endif
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 20925bcf4e2a..37762175896f 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -33,18 +33,23 @@
 #define UL(x) _AC(x, UL)
 
 /*
- * PAGE_OFFSET - the virtual address of the start of the kernel image.
+ * PAGE_OFFSET - the virtual address of the start of the kernel image (top
+ *		 (VA_BITS - 1))
  * VA_BITS - the maximum number of bits for virtual addresses.
  * TASK_SIZE - the maximum size of a user space task.
  * TASK_UNMAPPED_BASE - the lower boundary of the mmap VM area.
  * The module space lives between the addresses given by TASK_SIZE
  * and PAGE_OFFSET - it must be within 128MB of the kernel text.
  */
-#define PAGE_OFFSET		UL(0xffffffc000000000)
+#ifdef CONFIG_ARM64_64K_PAGES
+#define VA_BITS			(42)
+#else
+#define VA_BITS			(39)
+#endif
+#define PAGE_OFFSET		(UL(0xffffffffffffffff) << (VA_BITS - 1))
 #define MODULES_END		(PAGE_OFFSET)
 #define MODULES_VADDR		(MODULES_END - SZ_64M)
 #define EARLYCON_IOBASE		(MODULES_VADDR - SZ_4M)
-#define VA_BITS			(39)
 #define TASK_SIZE_64		(UL(1) << VA_BITS)
 
 #ifdef CONFIG_COMPAT
diff --git a/arch/arm64/include/asm/pgtable-2level-hwdef.h b/arch/arm64/include/asm/pgtable-2level-hwdef.h
index 0a8ed3f94e93..2593b490c56a 100644
--- a/arch/arm64/include/asm/pgtable-2level-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-2level-hwdef.h
@@ -21,10 +21,10 @@
  * 8192 entries of 8 bytes each, occupying a 64KB page. Levels 0 and 1 are not
  * used. The 2nd level table (PGD for Linux) can cover a range of 4TB, each
  * entry representing 512MB. The user and kernel address spaces are limited to
- * 512GB and therefore we only use 1024 entries in the PGD.
+ * 4TB in the 64KB page configuration.
  */
 #define PTRS_PER_PTE		8192
-#define PTRS_PER_PGD		1024
+#define PTRS_PER_PGD		8192
 
 /*
  * PGDIR_SHIFT determines the size a top-level page table entry can map.
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index f0bebc5e22cd..17bd3af0a117 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -33,7 +33,7 @@
 /*
  * VMALLOC and SPARSEMEM_VMEMMAP ranges.
  */
-#define VMALLOC_START		UL(0xffffff8000000000)
+#define VMALLOC_START		(UL(0xffffffffffffffff) << VA_BITS)
 #define VMALLOC_END		(PAGE_OFFSET - UL(0x400000000) - SZ_64K)
 
 #define vmemmap			((struct page *)(VMALLOC_END + SZ_64K))
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index ab239b2c456f..45b20cd6cbca 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -107,6 +107,11 @@ static inline void compat_start_thread(struct pt_regs *regs, unsigned long pc,
 	regs->pstate = COMPAT_PSR_MODE_USR;
 	if (pc & 1)
 		regs->pstate |= COMPAT_PSR_T_BIT;
+
+#ifdef __AARCH64EB__
+	regs->pstate |= COMPAT_PSR_E_BIT;
+#endif
+
 	regs->compat_sp = sp;
 }
 #endif
diff --git a/arch/arm64/include/asm/psci.h b/arch/arm64/include/asm/psci.h
index 0604237ecd99..e5312ea0ec1a 100644
--- a/arch/arm64/include/asm/psci.h
+++ b/arch/arm64/include/asm/psci.h
@@ -14,25 +14,6 @@
 #ifndef __ASM_PSCI_H
 #define __ASM_PSCI_H
 
-#define PSCI_POWER_STATE_TYPE_STANDBY		0
-#define PSCI_POWER_STATE_TYPE_POWER_DOWN	1
-
-struct psci_power_state {
-	u16	id;
-	u8	type;
-	u8	affinity_level;
-};
-
-struct psci_operations {
-	int (*cpu_suspend)(struct psci_power_state state,
-			   unsigned long entry_point);
-	int (*cpu_off)(struct psci_power_state state);
-	int (*cpu_on)(unsigned long cpuid, unsigned long entry_point);
-	int (*migrate)(unsigned long cpuid);
-};
-
-extern struct psci_operations psci_ops;
-
 int psci_init(void);
 
 #endif /* __ASM_PSCI_H */
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index 0dacbbf9458b..0e7fa4963735 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -42,6 +42,7 @@
 #define COMPAT_PSR_MODE_UND	0x0000001b
 #define COMPAT_PSR_MODE_SYS	0x0000001f
 #define COMPAT_PSR_T_BIT	0x00000020
+#define COMPAT_PSR_E_BIT	0x00000200
 #define COMPAT_PSR_F_BIT	0x00000040
 #define COMPAT_PSR_I_BIT	0x00000080
 #define COMPAT_PSR_A_BIT	0x00000100
diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h
index 4b8023c5d146..a498f2cd2c2a 100644
--- a/arch/arm64/include/asm/smp.h
+++ b/arch/arm64/include/asm/smp.h
@@ -60,21 +60,14 @@ struct secondary_data {
 	void *stack;
 };
 extern struct secondary_data secondary_data;
-extern void secondary_holding_pen(void);
-extern volatile unsigned long secondary_holding_pen_release;
+extern void secondary_entry(void);
 
 extern void arch_send_call_function_single_ipi(int cpu);
 extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
 
-struct device_node;
+extern int __cpu_disable(void);
 
-struct smp_enable_ops {
-	const char	*name;
-	int		(*init_cpu)(struct device_node *, int);
-	int		(*prepare_cpu)(int);
-};
-
-extern const struct smp_enable_ops smp_spin_table_ops;
-extern const struct smp_enable_ops smp_psci_ops;
+extern void __cpu_die(unsigned int cpu);
+extern void cpu_die(void);
 
 #endif /* ifndef __ASM_SMP_H */
diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h
index 0defa0728a9b..3d5cf064d7a1 100644
--- a/arch/arm64/include/asm/spinlock.h
+++ b/arch/arm64/include/asm/spinlock.h
@@ -22,17 +22,10 @@
 /*
  * Spinlock implementation.
  *
- * The old value is read exclusively and the new one, if unlocked, is written
- * exclusively. In case of failure, the loop is restarted.
- *
  * The memory barriers are implicit with the load-acquire and store-release
  * instructions.
- *
- * Unlocked value: 0
- * Locked value: 1
  */
 
-#define arch_spin_is_locked(x)		((x)->lock != 0)
 #define arch_spin_unlock_wait(lock) \
 	do { while (arch_spin_is_locked(lock)) cpu_relax(); } while (0)
 
@@ -41,32 +34,51 @@
 static inline void arch_spin_lock(arch_spinlock_t *lock)
 {
 	unsigned int tmp;
+	arch_spinlock_t lockval, newval;
 
 	asm volatile(
-	"	sevl\n"
-	"1:	wfe\n"
-	"2:	ldaxr	%w0, %1\n"
-	"	cbnz	%w0, 1b\n"
-	"	stxr	%w0, %w2, %1\n"
-	"	cbnz	%w0, 2b\n"
-	: "=&r" (tmp), "+Q" (lock->lock)
-	: "r" (1)
-	: "cc", "memory");
+	/* Atomically increment the next ticket. */
+"	prfm	pstl1strm, %3\n"
+"1:	ldaxr	%w0, %3\n"
+"	add	%w1, %w0, %w5\n"
+"	stxr	%w2, %w1, %3\n"
+"	cbnz	%w2, 1b\n"
+	/* Did we get the lock? */
+"	eor	%w1, %w0, %w0, ror #16\n"
+"	cbz	%w1, 3f\n"
+	/*
+	 * No: spin on the owner. Send a local event to avoid missing an
+	 * unlock before the exclusive load.
+	 */
+"	sevl\n"
+"2:	wfe\n"
+"	ldaxrh	%w2, %4\n"
+"	eor	%w1, %w2, %w0, lsr #16\n"
+"	cbnz	%w1, 2b\n"
+	/* We got the lock. Critical section starts here. */
+"3:"
+	: "=&r" (lockval), "=&r" (newval), "=&r" (tmp), "+Q" (*lock)
+	: "Q" (lock->owner), "I" (1 << TICKET_SHIFT)
+	: "memory");
 }
 
 static inline int arch_spin_trylock(arch_spinlock_t *lock)
 {
 	unsigned int tmp;
+	arch_spinlock_t lockval;
 
 	asm volatile(
-	"2:	ldaxr	%w0, %1\n"
-	"	cbnz	%w0, 1f\n"
-	"	stxr	%w0, %w2, %1\n"
-	"	cbnz	%w0, 2b\n"
-	"1:\n"
-	: "=&r" (tmp), "+Q" (lock->lock)
-	: "r" (1)
-	: "cc", "memory");
+"	prfm	pstl1strm, %2\n"
+"1:	ldaxr	%w0, %2\n"
+"	eor	%w1, %w0, %w0, ror #16\n"
+"	cbnz	%w1, 2f\n"
+"	add	%w0, %w0, %3\n"
+"	stxr	%w1, %w0, %2\n"
+"	cbnz	%w1, 1b\n"
+"2:"
+	: "=&r" (lockval), "=&r" (tmp), "+Q" (*lock)
+	: "I" (1 << TICKET_SHIFT)
+	: "memory");
 
 	return !tmp;
 }
@@ -74,9 +86,28 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock)
 static inline void arch_spin_unlock(arch_spinlock_t *lock)
 {
 	asm volatile(
-	"	stlr	%w1, %0\n"
-	: "=Q" (lock->lock) : "r" (0) : "memory");
+"	stlrh	%w1, %0\n"
+	: "=Q" (lock->owner)
+	: "r" (lock->owner + 1)
+	: "memory");
+}
+
+static inline int arch_spin_value_unlocked(arch_spinlock_t lock)
+{
+	return lock.owner == lock.next;
+}
+
+static inline int arch_spin_is_locked(arch_spinlock_t *lock)
+{
+	return !arch_spin_value_unlocked(ACCESS_ONCE(*lock));
+}
+
+static inline int arch_spin_is_contended(arch_spinlock_t *lock)
+{
+	arch_spinlock_t lockval = ACCESS_ONCE(*lock);
+	return (lockval.next - lockval.owner) > 1;
 }
+#define arch_spin_is_contended	arch_spin_is_contended
 
 /*
  * Write lock implementation.
diff --git a/arch/arm64/include/asm/spinlock_types.h b/arch/arm64/include/asm/spinlock_types.h
index 9a494346efed..b8d383665f56 100644
--- a/arch/arm64/include/asm/spinlock_types.h
+++ b/arch/arm64/include/asm/spinlock_types.h
@@ -20,14 +20,19 @@
 # error "please don't include this file directly"
 #endif
 
-/* We only require natural alignment for exclusive accesses. */
-#define __lock_aligned
+#define TICKET_SHIFT	16
 
 typedef struct {
-	volatile unsigned int lock;
-} arch_spinlock_t;
+#ifdef __AARCH64EB__
+	u16 next;
+	u16 owner;
+#else
+	u16 owner;
+	u16 next;
+#endif
+} __aligned(4) arch_spinlock_t;
 
-#define __ARCH_SPIN_LOCK_UNLOCKED	{ 0 }
+#define __ARCH_SPIN_LOCK_UNLOCKED	{ 0 , 0 }
 
 typedef struct {
 	volatile unsigned int lock;
diff --git a/arch/arm64/include/asm/syscall.h b/arch/arm64/include/asm/syscall.h
index 89c047f9a971..70ba9d4ee978 100644
--- a/arch/arm64/include/asm/syscall.h
+++ b/arch/arm64/include/asm/syscall.h
@@ -59,6 +59,9 @@ static inline void syscall_get_arguments(struct task_struct *task,
 					 unsigned int i, unsigned int n,
 					 unsigned long *args)
 {
+	if (n == 0)
+		return;
+
 	if (i + n > SYSCALL_MAX_ARGS) {
 		unsigned long *args_bad = args + SYSCALL_MAX_ARGS - i;
 		unsigned int n_bad = n + i - SYSCALL_MAX_ARGS;
@@ -82,6 +85,9 @@ static inline void syscall_set_arguments(struct task_struct *task,
 					 unsigned int i, unsigned int n,
 					 const unsigned long *args)
 {
+	if (n == 0)
+		return;
+
 	if (i + n > SYSCALL_MAX_ARGS) {
 		pr_warning("%s called with max args %d, handling only %d\n",
 			   __func__, i + n, SYSCALL_MAX_ARGS);
diff --git a/arch/arm64/include/asm/virt.h b/arch/arm64/include/asm/virt.h
index 26e310c54344..130e2be952cf 100644
--- a/arch/arm64/include/asm/virt.h
+++ b/arch/arm64/include/asm/virt.h
@@ -18,7 +18,8 @@
 #ifndef __ASM__VIRT_H
 #define __ASM__VIRT_H
 
-#define BOOT_CPU_MODE_EL2	(0x0e12b007)
+#define BOOT_CPU_MODE_EL1	(0xe11)
+#define BOOT_CPU_MODE_EL2	(0xe12)
 
 #ifndef __ASSEMBLY__
 #include <asm/cacheflush.h>
diff --git a/arch/arm64/include/uapi/asm/byteorder.h b/arch/arm64/include/uapi/asm/byteorder.h
index 2b92046aafc5..dc19e9537f0d 100644
--- a/arch/arm64/include/uapi/asm/byteorder.h
+++ b/arch/arm64/include/uapi/asm/byteorder.h
@@ -16,6 +16,10 @@
 #ifndef __ASM_BYTEORDER_H
 #define __ASM_BYTEORDER_H
 
+#ifdef __AARCH64EB__
+#include <linux/byteorder/big_endian.h>
+#else
 #include <linux/byteorder/little_endian.h>
+#endif
 
 #endif	/* __ASM_BYTEORDER_H */
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 7b4b564961d4..5ba2fd43a75b 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -9,12 +9,12 @@ AFLAGS_head.o		:= -DTEXT_OFFSET=$(TEXT_OFFSET)
 arm64-obj-y		:= cputable.o debug-monitors.o entry.o irq.o fpsimd.o	\
 			   entry-fpsimd.o process.o ptrace.o setup.o signal.o	\
 			   sys.o stacktrace.o time.o traps.o io.o vdso.o	\
-			   hyp-stub.o psci.o
+			   hyp-stub.o psci.o cpu_ops.o
 
 arm64-obj-$(CONFIG_COMPAT)		+= sys32.o kuser32.o signal32.o 	\
 					   sys_compat.o
 arm64-obj-$(CONFIG_MODULES)		+= arm64ksyms.o module.o
-arm64-obj-$(CONFIG_SMP)			+= smp.o smp_spin_table.o smp_psci.o
+arm64-obj-$(CONFIG_SMP)			+= smp.o smp_spin_table.o
 arm64-obj-$(CONFIG_HW_PERF_EVENTS)	+= perf_event.o
 arm64-obj-$(CONFIG_HAVE_HW_BREAKPOINT)+= hw_breakpoint.o
 arm64-obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
diff --git a/arch/arm64/kernel/arm64ksyms.c b/arch/arm64/kernel/arm64ksyms.c
index 41b4f626d554..e7ee770c0697 100644
--- a/arch/arm64/kernel/arm64ksyms.c
+++ b/arch/arm64/kernel/arm64ksyms.c
@@ -39,6 +39,7 @@ EXPORT_SYMBOL(clear_page);
 EXPORT_SYMBOL(__copy_from_user);
 EXPORT_SYMBOL(__copy_to_user);
 EXPORT_SYMBOL(__clear_user);
+EXPORT_SYMBOL(__copy_in_user);
 
 	/* physical memory */
 EXPORT_SYMBOL(memstart_addr);
diff --git a/arch/arm64/kernel/cpu_ops.c b/arch/arm64/kernel/cpu_ops.c
new file mode 100644
index 000000000000..d62d12fb36c8
--- /dev/null
+++ b/arch/arm64/kernel/cpu_ops.c
@@ -0,0 +1,87 @@
+/*
+ * CPU kernel entry/exit control
+ *
+ * Copyright (C) 2013 ARM Ltd.
+ *
+ * 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 <asm/cpu_ops.h>
+#include <asm/smp_plat.h>
+#include <linux/errno.h>
+#include <linux/of.h>
+#include <linux/string.h>
+
+extern const struct cpu_operations smp_spin_table_ops;
+extern const struct cpu_operations cpu_psci_ops;
+
+const struct cpu_operations *cpu_ops[NR_CPUS];
+
+static const struct cpu_operations *supported_cpu_ops[] __initconst = {
+#ifdef CONFIG_SMP
+	&smp_spin_table_ops,
+	&cpu_psci_ops,
+#endif
+	NULL,
+};
+
+static const struct cpu_operations * __init cpu_get_ops(const char *name)
+{
+	const struct cpu_operations **ops = supported_cpu_ops;
+
+	while (*ops) {
+		if (!strcmp(name, (*ops)->name))
+			return *ops;
+
+		ops++;
+	}
+
+	return NULL;
+}
+
+/*
+ * Read a cpu's enable method from the device tree and record it in cpu_ops.
+ */
+int __init cpu_read_ops(struct device_node *dn, int cpu)
+{
+	const char *enable_method = of_get_property(dn, "enable-method", NULL);
+	if (!enable_method) {
+		/*
+		 * The boot CPU may not have an enable method (e.g. when
+		 * spin-table is used for secondaries). Don't warn spuriously.
+		 */
+		if (cpu != 0)
+			pr_err("%s: missing enable-method property\n",
+				dn->full_name);
+		return -ENOENT;
+	}
+
+	cpu_ops[cpu] = cpu_get_ops(enable_method);
+	if (!cpu_ops[cpu]) {
+		pr_warn("%s: unsupported enable-method property: %s\n",
+			dn->full_name, enable_method);
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+void __init cpu_read_bootcpu_ops(void)
+{
+	struct device_node *dn = of_get_cpu_node(0, NULL);
+	if (!dn) {
+		pr_err("Failed to find device node for boot cpu\n");
+		return;
+	}
+	cpu_read_ops(dn, 0);
+}
diff --git a/arch/arm64/kernel/cputable.c b/arch/arm64/kernel/cputable.c
index 63cfc4a43f4e..fd3993cb060f 100644
--- a/arch/arm64/kernel/cputable.c
+++ b/arch/arm64/kernel/cputable.c
@@ -22,7 +22,7 @@
 
 extern unsigned long __cpu_setup(void);
 
-struct cpu_info __initdata cpu_table[] = {
+struct cpu_info cpu_table[] = {
 	{
 		.cpu_id_val	= 0x000f0000,
 		.cpu_id_mask	= 0x000f0000,
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 3881fd115ebb..e1166145ca29 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -311,14 +311,14 @@ el1_irq:
 #endif
 #ifdef CONFIG_PREEMPT
 	get_thread_info tsk
-	ldr	x24, [tsk, #TI_PREEMPT]		// get preempt count
-	add	x0, x24, #1			// increment it
-	str	x0, [tsk, #TI_PREEMPT]
+	ldr	w24, [tsk, #TI_PREEMPT]		// get preempt count
+	add	w0, w24, #1			// increment it
+	str	w0, [tsk, #TI_PREEMPT]
 #endif
 	irq_handler
 #ifdef CONFIG_PREEMPT
-	str	x24, [tsk, #TI_PREEMPT]		// restore preempt count
-	cbnz	x24, 1f				// preempt count != 0
+	str	w24, [tsk, #TI_PREEMPT]		// restore preempt count
+	cbnz	w24, 1f				// preempt count != 0
 	ldr	x0, [tsk, #TI_FLAGS]		// get flags
 	tbz	x0, #TIF_NEED_RESCHED, 1f	// needs rescheduling?
 	bl	el1_preempt
@@ -509,15 +509,15 @@ el0_irq_naked:
 #endif
 	get_thread_info tsk
 #ifdef CONFIG_PREEMPT
-	ldr	x24, [tsk, #TI_PREEMPT]		// get preempt count
-	add	x23, x24, #1			// increment it
-	str	x23, [tsk, #TI_PREEMPT]
+	ldr	w24, [tsk, #TI_PREEMPT]		// get preempt count
+	add	w23, w24, #1			// increment it
+	str	w23, [tsk, #TI_PREEMPT]
 #endif
 	irq_handler
 #ifdef CONFIG_PREEMPT
-	ldr	x0, [tsk, #TI_PREEMPT]
-	str	x24, [tsk, #TI_PREEMPT]
-	cmp	x0, x23
+	ldr	w0, [tsk, #TI_PREEMPT]
+	str	w24, [tsk, #TI_PREEMPT]
+	cmp	w0, w23
 	b.eq	1f
 	mov	x1, #0
 	str	x1, [x1]			// BUG
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 7090c126797c..7009387348b7 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -123,8 +123,9 @@
 
 ENTRY(stext)
 	mov	x21, x0				// x21=FDT
+	bl	el2_setup			// Drop to EL1, w20=cpu_boot_mode
 	bl	__calc_phys_offset		// x24=PHYS_OFFSET, x28=PHYS_OFFSET-PAGE_OFFSET
-	bl	el2_setup			// Drop to EL1
+	bl	set_cpu_boot_mode_flag
 	mrs	x22, midr_el1			// x22=cpuid
 	mov	x0, x22
 	bl	lookup_processor_type
@@ -150,21 +151,30 @@ ENDPROC(stext)
 /*
  * If we're fortunate enough to boot at EL2, ensure that the world is
  * sane before dropping to EL1.
+ *
+ * Returns either BOOT_CPU_MODE_EL1 or BOOT_CPU_MODE_EL2 in x20 if
+ * booted in EL1 or EL2 respectively.
  */
 ENTRY(el2_setup)
 	mrs	x0, CurrentEL
 	cmp	x0, #PSR_MODE_EL2t
 	ccmp	x0, #PSR_MODE_EL2h, #0x4, ne
-	ldr	x0, =__boot_cpu_mode		// Compute __boot_cpu_mode
-	add	x0, x0, x28
-	b.eq	1f
-	str	wzr, [x0]			// Remember we don't have EL2...
+	b.ne	1f
+	mrs	x0, sctlr_el2
+CPU_BE(	orr	x0, x0, #(1 << 25)	)	// Set the EE bit for EL2
+CPU_LE(	bic	x0, x0, #(1 << 25)	)	// Clear the EE bit for EL2
+	msr	sctlr_el2, x0
+	b	2f
+1:	mrs	x0, sctlr_el1
+CPU_BE(	orr	x0, x0, #(3 << 24)	)	// Set the EE and E0E bits for EL1
+CPU_LE(	bic	x0, x0, #(3 << 24)	)	// Clear the EE and E0E bits for EL1
+	msr	sctlr_el1, x0
+	mov	w20, #BOOT_CPU_MODE_EL1		// This cpu booted in EL1
+	isb
 	ret
 
 	/* Hyp configuration. */
-1:	ldr	w1, =BOOT_CPU_MODE_EL2
-	str	w1, [x0, #4]			// This CPU has EL2
-	mov	x0, #(1 << 31)			// 64-bit EL1
+2:	mov	x0, #(1 << 31)			// 64-bit EL1
 	msr	hcr_el2, x0
 
 	/* Generic timers. */
@@ -181,7 +191,8 @@ ENTRY(el2_setup)
 
 	/* sctlr_el1 */
 	mov	x0, #0x0800			// Set/clear RES{1,0} bits
-	movk	x0, #0x30d0, lsl #16
+CPU_BE(	movk	x0, #0x33d0, lsl #16	)	// Set EE and E0E on BE systems
+CPU_LE(	movk	x0, #0x30d0, lsl #16	)	// Clear EE and E0E on LE systems
 	msr	sctlr_el1, x0
 
 	/* Coprocessor traps. */
@@ -204,10 +215,25 @@ ENTRY(el2_setup)
 		      PSR_MODE_EL1h)
 	msr	spsr_el2, x0
 	msr	elr_el2, lr
+	mov	w20, #BOOT_CPU_MODE_EL2		// This CPU booted in EL2
 	eret
 ENDPROC(el2_setup)
 
 /*
+ * Sets the __boot_cpu_mode flag depending on the CPU boot mode passed
+ * in x20. See arch/arm64/include/asm/virt.h for more info.
+ */
+ENTRY(set_cpu_boot_mode_flag)
+	ldr	x1, =__boot_cpu_mode		// Compute __boot_cpu_mode
+	add	x1, x1, x28
+	cmp	w20, #BOOT_CPU_MODE_EL2
+	b.ne	1f
+	add	x1, x1, #4
+1:	str	w20, [x1]			// This CPU has booted in EL1
+	ret
+ENDPROC(set_cpu_boot_mode_flag)
+
+/*
  * We need to find out the CPU boot mode long after boot, so we need to
  * store it in a writable variable.
  *
@@ -225,7 +251,6 @@ ENTRY(__boot_cpu_mode)
 	.quad	PAGE_OFFSET
 
 #ifdef CONFIG_SMP
-	.pushsection    .smp.pen.text, "ax"
 	.align	3
 1:	.quad	.
 	.quad	secondary_holding_pen_release
@@ -235,8 +260,9 @@ ENTRY(__boot_cpu_mode)
 	 * cores are held until we're ready for them to initialise.
 	 */
 ENTRY(secondary_holding_pen)
-	bl	__calc_phys_offset		// x24=phys offset
-	bl	el2_setup			// Drop to EL1
+	bl	el2_setup			// Drop to EL1, w20=cpu_boot_mode
+	bl	__calc_phys_offset		// x24=PHYS_OFFSET, x28=PHYS_OFFSET-PAGE_OFFSET
+	bl	set_cpu_boot_mode_flag
 	mrs	x0, mpidr_el1
 	ldr     x1, =MPIDR_HWID_BITMASK
 	and	x0, x0, x1
@@ -250,7 +276,16 @@ pen:	ldr	x4, [x3]
 	wfe
 	b	pen
 ENDPROC(secondary_holding_pen)
-	.popsection
+
+	/*
+	 * Secondary entry point that jumps straight into the kernel. Only to
+	 * be used where CPUs are brought online dynamically by the kernel.
+	 */
+ENTRY(secondary_entry)
+	bl	__calc_phys_offset		// x2=phys offset
+	bl	el2_setup			// Drop to EL1
+	b	secondary_startup
+ENDPROC(secondary_entry)
 
 ENTRY(secondary_startup)
 	/*
diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c
index ecb3354292ed..473e5dbf8f39 100644
--- a/arch/arm64/kernel/irq.c
+++ b/arch/arm64/kernel/irq.c
@@ -81,3 +81,64 @@ void __init init_IRQ(void)
 	if (!handle_arch_irq)
 		panic("No interrupt controller found.");
 }
+
+#ifdef CONFIG_HOTPLUG_CPU
+static bool migrate_one_irq(struct irq_desc *desc)
+{
+	struct irq_data *d = irq_desc_get_irq_data(desc);
+	const struct cpumask *affinity = d->affinity;
+	struct irq_chip *c;
+	bool ret = false;
+
+	/*
+	 * If this is a per-CPU interrupt, or the affinity does not
+	 * include this CPU, then we have nothing to do.
+	 */
+	if (irqd_is_per_cpu(d) || !cpumask_test_cpu(smp_processor_id(), affinity))
+		return false;
+
+	if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) {
+		affinity = cpu_online_mask;
+		ret = true;
+	}
+
+	c = irq_data_get_irq_chip(d);
+	if (!c->irq_set_affinity)
+		pr_debug("IRQ%u: unable to set affinity\n", d->irq);
+	else if (c->irq_set_affinity(d, affinity, true) == IRQ_SET_MASK_OK && ret)
+		cpumask_copy(d->affinity, affinity);
+
+	return ret;
+}
+
+/*
+ * The current CPU has been marked offline.  Migrate IRQs off this CPU.
+ * If the affinity settings do not allow other CPUs, force them onto any
+ * available CPU.
+ *
+ * Note: we must iterate over all IRQs, whether they have an attached
+ * action structure or not, as we need to get chained interrupts too.
+ */
+void migrate_irqs(void)
+{
+	unsigned int i;
+	struct irq_desc *desc;
+	unsigned long flags;
+
+	local_irq_save(flags);
+
+	for_each_irq_desc(i, desc) {
+		bool affinity_broken;
+
+		raw_spin_lock(&desc->lock);
+		affinity_broken = migrate_one_irq(desc);
+		raw_spin_unlock(&desc->lock);
+
+		if (affinity_broken)
+			pr_warn_ratelimited("IRQ%u no longer affine to CPU%u\n",
+					    i, smp_processor_id());
+	}
+
+	local_irq_restore(flags);
+}
+#endif /* CONFIG_HOTPLUG_CPU */
diff --git a/arch/arm64/kernel/kuser32.S b/arch/arm64/kernel/kuser32.S
index 8b69ecb1d8bc..63c48ffdf230 100644
--- a/arch/arm64/kernel/kuser32.S
+++ b/arch/arm64/kernel/kuser32.S
@@ -27,6 +27,9 @@
  *
  * See Documentation/arm/kernel_user_helpers.txt for formal definitions.
  */
+
+#include <asm/unistd32.h>
+
 	.align	5
 	.globl	__kuser_helper_start
 __kuser_helper_start:
@@ -35,33 +38,30 @@ __kuser_cmpxchg64:			// 0xffff0f60
 	.inst	0xe92d00f0		//	push		{r4, r5, r6, r7}
 	.inst	0xe1c040d0		//	ldrd		r4, r5, [r0]
 	.inst	0xe1c160d0		//	ldrd		r6, r7, [r1]
-	.inst	0xf57ff05f		//	dmb		sy
-	.inst	0xe1b20f9f		// 1:	ldrexd		r0, r1, [r2]
+	.inst	0xe1b20e9f		// 1:	ldaexd		r0, r1, [r2]
 	.inst	0xe0303004		//	eors		r3, r0, r4
 	.inst	0x00313005		//	eoreqs		r3, r1, r5
-	.inst	0x01a23f96		//	strexdeq	r3, r6, [r2]
+	.inst	0x01a23e96		//	stlexdeq	r3, r6, [r2]
 	.inst	0x03330001		//	teqeq		r3, #1
 	.inst	0x0afffff9		//	beq		1b
-	.inst	0xf57ff05f		//	dmb		sy
 	.inst	0xe2730000		//	rsbs		r0, r3, #0
 	.inst	0xe8bd00f0		//	pop		{r4, r5, r6, r7}
 	.inst	0xe12fff1e		//	bx		lr
 
 	.align	5
 __kuser_memory_barrier:			// 0xffff0fa0
-	.inst	0xf57ff05f		//	dmb		sy
+	.inst	0xf57ff05b		//	dmb		ish
 	.inst	0xe12fff1e		//	bx		lr
 
 	.align	5
 __kuser_cmpxchg:			// 0xffff0fc0
-	.inst	0xf57ff05f		//	dmb		sy
-	.inst	0xe1923f9f		// 1:	ldrex		r3, [r2]
+	.inst	0xe1923e9f		// 1:	ldaex		r3, [r2]
 	.inst	0xe0533000		//	subs		r3, r3, r0
-	.inst	0x01823f91		//	strexeq	r3, r1, [r2]
+	.inst	0x01823e91		//	stlexeq		r3, r1, [r2]
 	.inst	0x03330001		//	teqeq		r3, #1
 	.inst	0x0afffffa		//	beq		1b
 	.inst	0xe2730000		//	rsbs		r0, r3, #0
-	.inst	0xeaffffef		//	b		<__kuser_memory_barrier>
+	.inst	0xe12fff1e		//	bx		lr
 
 	.align	5
 __kuser_get_tls:			// 0xffff0fe0
@@ -75,3 +75,42 @@ __kuser_helper_version:			// 0xffff0ffc
 	.word	((__kuser_helper_end - __kuser_helper_start) >> 5)
 	.globl	__kuser_helper_end
 __kuser_helper_end:
+
+/*
+ * AArch32 sigreturn code
+ *
+ * For ARM syscalls, the syscall number has to be loaded into r7.
+ * We do not support an OABI userspace.
+ *
+ * For Thumb syscalls, we also pass the syscall number via r7. We therefore
+ * need two 16-bit instructions.
+ */
+	.globl __aarch32_sigret_code_start
+__aarch32_sigret_code_start:
+
+	/*
+	 * ARM Code
+	 */
+	.byte	__NR_compat_sigreturn, 0x70, 0xa0, 0xe3	// mov	r7, #__NR_compat_sigreturn
+	.byte	__NR_compat_sigreturn, 0x00, 0x00, 0xef	// svc	#__NR_compat_sigreturn
+
+	/*
+	 * Thumb code
+	 */
+	.byte	__NR_compat_sigreturn, 0x27			// svc	#__NR_compat_sigreturn
+	.byte	__NR_compat_sigreturn, 0xdf			// mov	r7, #__NR_compat_sigreturn
+
+	/*
+	 * ARM code
+	 */
+	.byte	__NR_compat_rt_sigreturn, 0x70, 0xa0, 0xe3	// mov	r7, #__NR_compat_rt_sigreturn
+	.byte	__NR_compat_rt_sigreturn, 0x00, 0x00, 0xef	// svc	#__NR_compat_rt_sigreturn
+
+	/*
+	 * Thumb code
+	 */
+	.byte	__NR_compat_rt_sigreturn, 0x27			// svc	#__NR_compat_rt_sigreturn
+	.byte	__NR_compat_rt_sigreturn, 0xdf			// mov	r7, #__NR_compat_rt_sigreturn
+
+        .globl __aarch32_sigret_code_end
+__aarch32_sigret_code_end:
diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c
index ca0e3d55da99..2c28a6cf93e6 100644
--- a/arch/arm64/kernel/module.c
+++ b/arch/arm64/kernel/module.c
@@ -111,6 +111,9 @@ static u32 encode_insn_immediate(enum aarch64_imm_type type, u32 insn, u64 imm)
 	u32 immlo, immhi, lomask, himask, mask;
 	int shift;
 
+	/* The instruction stream is always little endian. */
+	insn = le32_to_cpu(insn);
+
 	switch (type) {
 	case INSN_IMM_MOVNZ:
 		/*
@@ -179,7 +182,7 @@ static u32 encode_insn_immediate(enum aarch64_imm_type type, u32 insn, u64 imm)
 	insn &= ~(mask << shift);
 	insn |= (imm & mask) << shift;
 
-	return insn;
+	return cpu_to_le32(insn);
 }
 
 static int reloc_insn_movw(enum aarch64_reloc_op op, void *place, u64 val,
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index cea1594ff933..5d14470452ac 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -784,8 +784,8 @@ static const unsigned armv8_pmuv3_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 /*
  * PMXEVTYPER: Event selection reg
  */
-#define	ARMV8_EVTYPE_MASK	0xc80000ff	/* Mask for writable bits */
-#define	ARMV8_EVTYPE_EVENT	0xff		/* Mask for EVENT bits */
+#define	ARMV8_EVTYPE_MASK	0xc80003ff	/* Mask for writable bits */
+#define	ARMV8_EVTYPE_EVENT	0x3ff		/* Mask for EVENT bits */
 
 /*
  * Event filters for PMUv3
@@ -1175,7 +1175,8 @@ static void armv8pmu_reset(void *info)
 static int armv8_pmuv3_map_event(struct perf_event *event)
 {
 	return map_cpu_event(event, &armv8_pmuv3_perf_map,
-				&armv8_pmuv3_perf_cache_map, 0xFF);
+				&armv8_pmuv3_perf_cache_map,
+				ARMV8_EVTYPE_EVENT);
 }
 
 static struct arm_pmu armv8pmu = {
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 7ae8a1f00c3c..de17c89985db 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -102,6 +102,13 @@ void arch_cpu_idle(void)
 	local_irq_enable();
 }
 
+#ifdef CONFIG_HOTPLUG_CPU
+void arch_cpu_idle_dead(void)
+{
+       cpu_die();
+}
+#endif
+
 void machine_shutdown(void)
 {
 #ifdef CONFIG_SMP
diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c
index 14f73c445ff5..4f97db3d7363 100644
--- a/arch/arm64/kernel/psci.c
+++ b/arch/arm64/kernel/psci.c
@@ -17,12 +17,32 @@
 
 #include <linux/init.h>
 #include <linux/of.h>
+#include <linux/smp.h>
 
 #include <asm/compiler.h>
+#include <asm/cpu_ops.h>
 #include <asm/errno.h>
 #include <asm/psci.h>
+#include <asm/smp_plat.h>
 
-struct psci_operations psci_ops;
+#define PSCI_POWER_STATE_TYPE_STANDBY		0
+#define PSCI_POWER_STATE_TYPE_POWER_DOWN	1
+
+struct psci_power_state {
+	u16	id;
+	u8	type;
+	u8	affinity_level;
+};
+
+struct psci_operations {
+	int (*cpu_suspend)(struct psci_power_state state,
+			   unsigned long entry_point);
+	int (*cpu_off)(struct psci_power_state state);
+	int (*cpu_on)(unsigned long cpuid, unsigned long entry_point);
+	int (*migrate)(unsigned long cpuid);
+};
+
+static struct psci_operations psci_ops;
 
 static int (*invoke_psci_fn)(u64, u64, u64, u64);
 
@@ -209,3 +229,68 @@ out_put_node:
 	of_node_put(np);
 	return err;
 }
+
+#ifdef CONFIG_SMP
+
+static int __init cpu_psci_cpu_init(struct device_node *dn, unsigned int cpu)
+{
+	return 0;
+}
+
+static int __init cpu_psci_cpu_prepare(unsigned int cpu)
+{
+	if (!psci_ops.cpu_on) {
+		pr_err("no cpu_on method, not booting CPU%d\n", cpu);
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+static int cpu_psci_cpu_boot(unsigned int cpu)
+{
+	int err = psci_ops.cpu_on(cpu_logical_map(cpu), __pa(secondary_entry));
+	if (err)
+		pr_err("psci: failed to boot CPU%d (%d)\n", cpu, err);
+
+	return err;
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+static int cpu_psci_cpu_disable(unsigned int cpu)
+{
+	/* Fail early if we don't have CPU_OFF support */
+	if (!psci_ops.cpu_off)
+		return -EOPNOTSUPP;
+	return 0;
+}
+
+static void cpu_psci_cpu_die(unsigned int cpu)
+{
+	int ret;
+	/*
+	 * There are no known implementations of PSCI actually using the
+	 * power state field, pass a sensible default for now.
+	 */
+	struct psci_power_state state = {
+		.type = PSCI_POWER_STATE_TYPE_POWER_DOWN,
+	};
+
+	ret = psci_ops.cpu_off(state);
+
+	pr_crit("psci: unable to power off CPU%u (%d)\n", cpu, ret);
+}
+#endif
+
+const struct cpu_operations cpu_psci_ops = {
+	.name		= "psci",
+	.cpu_init	= cpu_psci_cpu_init,
+	.cpu_prepare	= cpu_psci_cpu_prepare,
+	.cpu_boot	= cpu_psci_cpu_boot,
+#ifdef CONFIG_HOTPLUG_CPU
+	.cpu_disable	= cpu_psci_cpu_disable,
+	.cpu_die	= cpu_psci_cpu_die,
+#endif
+};
+
+#endif
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 055cfb80e05c..9cf30f49610d 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -45,6 +45,7 @@
 #include <asm/cputype.h>
 #include <asm/elf.h>
 #include <asm/cputable.h>
+#include <asm/cpu_ops.h>
 #include <asm/sections.h>
 #include <asm/setup.h>
 #include <asm/smp_plat.h>
@@ -97,6 +98,11 @@ void __init early_print(const char *str, ...)
 	printk("%s", buf);
 }
 
+bool arch_match_cpu_phys_id(int cpu, u64 phys_id)
+{
+	return phys_id == cpu_logical_map(cpu);
+}
+
 static void __init setup_processor(void)
 {
 	struct cpu_info *cpu_info;
@@ -118,7 +124,7 @@ static void __init setup_processor(void)
 	printk("CPU: %s [%08x] revision %d\n",
 	       cpu_name, read_cpuid_id(), read_cpuid_id() & 15);
 
-	sprintf(init_utsname()->machine, "aarch64");
+	sprintf(init_utsname()->machine, ELF_PLATFORM);
 	elf_hwcap = 0;
 }
 
@@ -264,6 +270,7 @@ void __init setup_arch(char **cmdline_p)
 	psci_init();
 
 	cpu_logical_map(0) = read_cpuid_mpidr() & MPIDR_HWID_BITMASK;
+	cpu_read_bootcpu_ops();
 #ifdef CONFIG_SMP
 	smp_init_cpus();
 #endif
diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index e393174fe859..e51bbe79f5b5 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -100,34 +100,6 @@ struct compat_rt_sigframe {
 
 #define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
 
-/*
- * For ARM syscalls, the syscall number has to be loaded into r7.
- * We do not support an OABI userspace.
- */
-#define MOV_R7_NR_SIGRETURN	(0xe3a07000 | __NR_compat_sigreturn)
-#define SVC_SYS_SIGRETURN	(0xef000000 | __NR_compat_sigreturn)
-#define MOV_R7_NR_RT_SIGRETURN	(0xe3a07000 | __NR_compat_rt_sigreturn)
-#define SVC_SYS_RT_SIGRETURN	(0xef000000 | __NR_compat_rt_sigreturn)
-
-/*
- * For Thumb syscalls, we also pass the syscall number via r7. We therefore
- * need two 16-bit instructions.
- */
-#define SVC_THUMB_SIGRETURN	(((0xdf00 | __NR_compat_sigreturn) << 16) | \
-				   0x2700 | __NR_compat_sigreturn)
-#define SVC_THUMB_RT_SIGRETURN	(((0xdf00 | __NR_compat_rt_sigreturn) << 16) | \
-				   0x2700 | __NR_compat_rt_sigreturn)
-
-const compat_ulong_t aarch32_sigret_code[6] = {
-	/*
-	 * AArch32 sigreturn code.
-	 * We don't construct an OABI SWI - instead we just set the imm24 field
-	 * to the EABI syscall number so that we create a sane disassembly.
-	 */
-	MOV_R7_NR_SIGRETURN,    SVC_SYS_SIGRETURN,    SVC_THUMB_SIGRETURN,
-	MOV_R7_NR_RT_SIGRETURN, SVC_SYS_RT_SIGRETURN, SVC_THUMB_RT_SIGRETURN,
-};
-
 static inline int put_sigset_t(compat_sigset_t __user *uset, sigset_t *set)
 {
 	compat_sigset_t	cset;
@@ -474,12 +446,13 @@ static void compat_setup_return(struct pt_regs *regs, struct k_sigaction *ka,
 	/* Check if the handler is written for ARM or Thumb */
 	thumb = handler & 1;
 
-	if (thumb) {
+	if (thumb)
 		spsr |= COMPAT_PSR_T_BIT;
-		spsr &= ~COMPAT_PSR_IT_MASK;
-	} else {
+	else
 		spsr &= ~COMPAT_PSR_T_BIT;
-	}
+
+	/* The IT state must be cleared for both ARM and Thumb-2 */
+	spsr &= ~COMPAT_PSR_IT_MASK;
 
 	if (ka->sa.sa_flags & SA_RESTORER) {
 		retcode = ptr_to_compat(ka->sa.sa_restorer);
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 78db90dcc910..a5aeefab03c3 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -39,6 +39,7 @@
 #include <asm/atomic.h>
 #include <asm/cacheflush.h>
 #include <asm/cputype.h>
+#include <asm/cpu_ops.h>
 #include <asm/mmu_context.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -54,7 +55,6 @@
  * where to place its SVC stack
  */
 struct secondary_data secondary_data;
-volatile unsigned long secondary_holding_pen_release = INVALID_HWID;
 
 enum ipi_msg_type {
 	IPI_RESCHEDULE,
@@ -63,61 +63,16 @@ enum ipi_msg_type {
 	IPI_CPU_STOP,
 };
 
-static DEFINE_RAW_SPINLOCK(boot_lock);
-
-/*
- * Write secondary_holding_pen_release in a way that is guaranteed to be
- * visible to all observers, irrespective of whether they're taking part
- * in coherency or not.  This is necessary for the hotplug code to work
- * reliably.
- */
-static void write_pen_release(u64 val)
-{
-	void *start = (void *)&secondary_holding_pen_release;
-	unsigned long size = sizeof(secondary_holding_pen_release);
-
-	secondary_holding_pen_release = val;
-	__flush_dcache_area(start, size);
-}
-
 /*
  * Boot a secondary CPU, and assign it the specified idle task.
  * This also gives us the initial stack to use for this CPU.
  */
 static int boot_secondary(unsigned int cpu, struct task_struct *idle)
 {
-	unsigned long timeout;
-
-	/*
-	 * Set synchronisation state between this boot processor
-	 * and the secondary one
-	 */
-	raw_spin_lock(&boot_lock);
-
-	/*
-	 * Update the pen release flag.
-	 */
-	write_pen_release(cpu_logical_map(cpu));
-
-	/*
-	 * Send an event, causing the secondaries to read pen_release.
-	 */
-	sev();
-
-	timeout = jiffies + (1 * HZ);
-	while (time_before(jiffies, timeout)) {
-		if (secondary_holding_pen_release == INVALID_HWID)
-			break;
-		udelay(10);
-	}
-
-	/*
-	 * Now the secondary core is starting up let it run its
-	 * calibrations, then wait for it to finish
-	 */
-	raw_spin_unlock(&boot_lock);
+	if (cpu_ops[cpu]->cpu_boot)
+		return cpu_ops[cpu]->cpu_boot(cpu);
 
-	return secondary_holding_pen_release != INVALID_HWID ? -ENOSYS : 0;
+	return -EOPNOTSUPP;
 }
 
 static DECLARE_COMPLETION(cpu_running);
@@ -187,17 +142,13 @@ asmlinkage void secondary_start_kernel(void)
 	preempt_disable();
 	trace_hardirqs_off();
 
-	/*
-	 * Let the primary processor know we're out of the
-	 * pen, then head off into the C entry point
-	 */
-	write_pen_release(INVALID_HWID);
+	if (cpu_ops[cpu]->cpu_postboot)
+		cpu_ops[cpu]->cpu_postboot();
 
 	/*
-	 * Synchronise with the boot thread.
+	 * Enable GIC and timers.
 	 */
-	raw_spin_lock(&boot_lock);
-	raw_spin_unlock(&boot_lock);
+	notify_cpu_starting(cpu);
 
 	/*
 	 * OK, now it's safe to let the boot CPU continue.  Wait for
@@ -207,11 +158,6 @@ asmlinkage void secondary_start_kernel(void)
 	set_cpu_online(cpu, true);
 	complete(&cpu_running);
 
-	/*
-	 * Enable GIC and timers.
-	 */
-	notify_cpu_starting(cpu);
-
 	local_irq_enable();
 	local_fiq_enable();
 
@@ -221,39 +167,113 @@ asmlinkage void secondary_start_kernel(void)
 	cpu_startup_entry(CPUHP_ONLINE);
 }
 
-void __init smp_cpus_done(unsigned int max_cpus)
+#ifdef CONFIG_HOTPLUG_CPU
+static int op_cpu_disable(unsigned int cpu)
 {
-	pr_info("SMP: Total of %d processors activated.\n", num_online_cpus());
+	/*
+	 * If we don't have a cpu_die method, abort before we reach the point
+	 * of no return. CPU0 may not have an cpu_ops, so test for it.
+	 */
+	if (!cpu_ops[cpu] || !cpu_ops[cpu]->cpu_die)
+		return -EOPNOTSUPP;
+
+	/*
+	 * We may need to abort a hot unplug for some other mechanism-specific
+	 * reason.
+	 */
+	if (cpu_ops[cpu]->cpu_disable)
+		return cpu_ops[cpu]->cpu_disable(cpu);
+
+	return 0;
 }
 
-void __init smp_prepare_boot_cpu(void)
+/*
+ * __cpu_disable runs on the processor to be shutdown.
+ */
+int __cpu_disable(void)
 {
-}
+	unsigned int cpu = smp_processor_id();
+	int ret;
 
-static void (*smp_cross_call)(const struct cpumask *, unsigned int);
+	ret = op_cpu_disable(cpu);
+	if (ret)
+		return ret;
 
-static const struct smp_enable_ops *enable_ops[] __initconst = {
-	&smp_spin_table_ops,
-	&smp_psci_ops,
-	NULL,
-};
+	/*
+	 * Take this CPU offline.  Once we clear this, we can't return,
+	 * and we must not schedule until we're ready to give up the cpu.
+	 */
+	set_cpu_online(cpu, false);
+
+	/*
+	 * OK - migrate IRQs away from this CPU
+	 */
+	migrate_irqs();
 
-static const struct smp_enable_ops *smp_enable_ops[NR_CPUS];
+	/*
+	 * Remove this CPU from the vm mask set of all processes.
+	 */
+	clear_tasks_mm_cpumask(cpu);
 
-static const struct smp_enable_ops * __init smp_get_enable_ops(const char *name)
-{
-	const struct smp_enable_ops **ops = enable_ops;
+	return 0;
+}
 
-	while (*ops) {
-		if (!strcmp(name, (*ops)->name))
-			return *ops;
+static DECLARE_COMPLETION(cpu_died);
 
-		ops++;
+/*
+ * called on the thread which is asking for a CPU to be shutdown -
+ * waits until shutdown has completed, or it is timed out.
+ */
+void __cpu_die(unsigned int cpu)
+{
+	if (!wait_for_completion_timeout(&cpu_died, msecs_to_jiffies(5000))) {
+		pr_crit("CPU%u: cpu didn't die\n", cpu);
+		return;
 	}
+	pr_notice("CPU%u: shutdown\n", cpu);
+}
+
+/*
+ * Called from the idle thread for the CPU which has been shutdown.
+ *
+ * Note that we disable IRQs here, but do not re-enable them
+ * before returning to the caller. This is also the behaviour
+ * of the other hotplug-cpu capable cores, so presumably coming
+ * out of idle fixes this.
+ */
+void cpu_die(void)
+{
+	unsigned int cpu = smp_processor_id();
+
+	idle_task_exit();
 
-	return NULL;
+	local_irq_disable();
+
+	/* Tell __cpu_die() that this CPU is now safe to dispose of */
+	complete(&cpu_died);
+
+	/*
+	 * Actually shutdown the CPU. This must never fail. The specific hotplug
+	 * mechanism must perform all required cache maintenance to ensure that
+	 * no dirty lines are lost in the process of shutting down the CPU.
+	 */
+	cpu_ops[cpu]->cpu_die(cpu);
+
+	BUG();
+}
+#endif
+
+void __init smp_cpus_done(unsigned int max_cpus)
+{
+	pr_info("SMP: Total of %d processors activated.\n", num_online_cpus());
 }
 
+void __init smp_prepare_boot_cpu(void)
+{
+}
+
+static void (*smp_cross_call)(const struct cpumask *, unsigned int);
+
 /*
  * Enumerate the possible CPU set from the device tree and build the
  * cpu logical map array containing MPIDR values related to logical
@@ -261,9 +281,8 @@ static const struct smp_enable_ops * __init smp_get_enable_ops(const char *name)
  */
 void __init smp_init_cpus(void)
 {
-	const char *enable_method;
 	struct device_node *dn = NULL;
-	int i, cpu = 1;
+	unsigned int i, cpu = 1;
 	bool bootcpu_valid = false;
 
 	while ((dn = of_find_node_by_type(dn, "cpu"))) {
@@ -332,25 +351,10 @@ void __init smp_init_cpus(void)
 		if (cpu >= NR_CPUS)
 			goto next;
 
-		/*
-		 * We currently support only the "spin-table" enable-method.
-		 */
-		enable_method = of_get_property(dn, "enable-method", NULL);
-		if (!enable_method) {
-			pr_err("%s: missing enable-method property\n",
-				dn->full_name);
+		if (cpu_read_ops(dn, cpu) != 0)
 			goto next;
-		}
-
-		smp_enable_ops[cpu] = smp_get_enable_ops(enable_method);
-
-		if (!smp_enable_ops[cpu]) {
-			pr_err("%s: invalid enable-method property: %s\n",
-			       dn->full_name, enable_method);
-			goto next;
-		}
 
-		if (smp_enable_ops[cpu]->init_cpu(dn, cpu))
+		if (cpu_ops[cpu]->cpu_init(dn, cpu))
 			goto next;
 
 		pr_debug("cpu logical map 0x%llx\n", hwid);
@@ -380,8 +384,8 @@ next:
 
 void __init smp_prepare_cpus(unsigned int max_cpus)
 {
-	int cpu, err;
-	unsigned int ncores = num_possible_cpus();
+	int err;
+	unsigned int cpu, ncores = num_possible_cpus();
 
 	/*
 	 * are we trying to boot more cores than exist?
@@ -408,10 +412,10 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 		if (cpu == smp_processor_id())
 			continue;
 
-		if (!smp_enable_ops[cpu])
+		if (!cpu_ops[cpu])
 			continue;
 
-		err = smp_enable_ops[cpu]->prepare_cpu(cpu);
+		err = cpu_ops[cpu]->cpu_prepare(cpu);
 		if (err)
 			continue;
 
@@ -451,7 +455,7 @@ void show_ipi_list(struct seq_file *p, int prec)
 	for (i = 0; i < NR_IPI; i++) {
 		seq_printf(p, "%*s%u:%s", prec - 1, "IPI", i + IPI_RESCHEDULE,
 			   prec >= 4 ? " " : "");
-		for_each_present_cpu(cpu)
+		for_each_online_cpu(cpu)
 			seq_printf(p, "%10u ",
 				   __get_irq_stat(cpu, ipi_irqs[i]));
 		seq_printf(p, "      %s\n", ipi_types[i]);
diff --git a/arch/arm64/kernel/smp_psci.c b/arch/arm64/kernel/smp_psci.c
deleted file mode 100644
index 0c533301be77..000000000000
--- a/arch/arm64/kernel/smp_psci.c
+++ /dev/null
@@ -1,53 +0,0 @@
-/*
- * PSCI SMP initialisation
- *
- * Copyright (C) 2013 ARM Ltd.
- *
- * 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/init.h>
-#include <linux/of.h>
-#include <linux/smp.h>
-
-#include <asm/psci.h>
-#include <asm/smp_plat.h>
-
-static int __init smp_psci_init_cpu(struct device_node *dn, int cpu)
-{
-	return 0;
-}
-
-static int __init smp_psci_prepare_cpu(int cpu)
-{
-	int err;
-
-	if (!psci_ops.cpu_on) {
-		pr_err("psci: no cpu_on method, not booting CPU%d\n", cpu);
-		return -ENODEV;
-	}
-
-	err = psci_ops.cpu_on(cpu_logical_map(cpu), __pa(secondary_holding_pen));
-	if (err) {
-		pr_err("psci: failed to boot CPU%d (%d)\n", cpu, err);
-		return err;
-	}
-
-	return 0;
-}
-
-const struct smp_enable_ops smp_psci_ops __initconst = {
-	.name		= "psci",
-	.init_cpu	= smp_psci_init_cpu,
-	.prepare_cpu	= smp_psci_prepare_cpu,
-};
diff --git a/arch/arm64/kernel/smp_spin_table.c b/arch/arm64/kernel/smp_spin_table.c
index 7c35fa682f76..44c22805d2e2 100644
--- a/arch/arm64/kernel/smp_spin_table.c
+++ b/arch/arm64/kernel/smp_spin_table.c
@@ -16,15 +16,39 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/delay.h>
 #include <linux/init.h>
 #include <linux/of.h>
 #include <linux/smp.h>
 
 #include <asm/cacheflush.h>
+#include <asm/cpu_ops.h>
+#include <asm/cputype.h>
+#include <asm/smp_plat.h>
+
+extern void secondary_holding_pen(void);
+volatile unsigned long secondary_holding_pen_release = INVALID_HWID;
 
 static phys_addr_t cpu_release_addr[NR_CPUS];
+static DEFINE_RAW_SPINLOCK(boot_lock);
+
+/*
+ * Write secondary_holding_pen_release in a way that is guaranteed to be
+ * visible to all observers, irrespective of whether they're taking part
+ * in coherency or not.  This is necessary for the hotplug code to work
+ * reliably.
+ */
+static void write_pen_release(u64 val)
+{
+	void *start = (void *)&secondary_holding_pen_release;
+	unsigned long size = sizeof(secondary_holding_pen_release);
 
-static int __init smp_spin_table_init_cpu(struct device_node *dn, int cpu)
+	secondary_holding_pen_release = val;
+	__flush_dcache_area(start, size);
+}
+
+
+static int smp_spin_table_cpu_init(struct device_node *dn, unsigned int cpu)
 {
 	/*
 	 * Determine the address from which the CPU is polling.
@@ -40,7 +64,7 @@ static int __init smp_spin_table_init_cpu(struct device_node *dn, int cpu)
 	return 0;
 }
 
-static int __init smp_spin_table_prepare_cpu(int cpu)
+static int smp_spin_table_cpu_prepare(unsigned int cpu)
 {
 	void **release_addr;
 
@@ -48,7 +72,16 @@ static int __init smp_spin_table_prepare_cpu(int cpu)
 		return -ENODEV;
 
 	release_addr = __va(cpu_release_addr[cpu]);
-	release_addr[0] = (void *)__pa(secondary_holding_pen);
+
+	/*
+	 * We write the release address as LE regardless of the native
+	 * endianess of the kernel. Therefore, any boot-loaders that
+	 * read this address need to convert this address to the
+	 * boot-loader's endianess before jumping. This is mandated by
+	 * the boot protocol.
+	 */
+	release_addr[0] = (void *) cpu_to_le64(__pa(secondary_holding_pen));
+
 	__flush_dcache_area(release_addr, sizeof(release_addr[0]));
 
 	/*
@@ -59,8 +92,60 @@ static int __init smp_spin_table_prepare_cpu(int cpu)
 	return 0;
 }
 
-const struct smp_enable_ops smp_spin_table_ops __initconst = {
+static int smp_spin_table_cpu_boot(unsigned int cpu)
+{
+	unsigned long timeout;
+
+	/*
+	 * Set synchronisation state between this boot processor
+	 * and the secondary one
+	 */
+	raw_spin_lock(&boot_lock);
+
+	/*
+	 * Update the pen release flag.
+	 */
+	write_pen_release(cpu_logical_map(cpu));
+
+	/*
+	 * Send an event, causing the secondaries to read pen_release.
+	 */
+	sev();
+
+	timeout = jiffies + (1 * HZ);
+	while (time_before(jiffies, timeout)) {
+		if (secondary_holding_pen_release == INVALID_HWID)
+			break;
+		udelay(10);
+	}
+
+	/*
+	 * Now the secondary core is starting up let it run its
+	 * calibrations, then wait for it to finish
+	 */
+	raw_spin_unlock(&boot_lock);
+
+	return secondary_holding_pen_release != INVALID_HWID ? -ENOSYS : 0;
+}
+
+void smp_spin_table_cpu_postboot(void)
+{
+	/*
+	 * Let the primary processor know we're out of the pen.
+	 */
+	write_pen_release(INVALID_HWID);
+
+	/*
+	 * Synchronise with the boot thread.
+	 */
+	raw_spin_lock(&boot_lock);
+	raw_spin_unlock(&boot_lock);
+}
+
+const struct cpu_operations smp_spin_table_ops = {
 	.name		= "spin-table",
-	.init_cpu 	= smp_spin_table_init_cpu,
-	.prepare_cpu	= smp_spin_table_prepare_cpu,
+	.cpu_init	= smp_spin_table_cpu_init,
+	.cpu_prepare	= smp_spin_table_cpu_prepare,
+	.cpu_boot	= smp_spin_table_cpu_boot,
+	.cpu_postboot	= smp_spin_table_cpu_postboot,
 };
diff --git a/arch/arm64/kernel/sys32.S b/arch/arm64/kernel/sys32.S
index a1b19ed7467c..423a5b3fc2be 100644
--- a/arch/arm64/kernel/sys32.S
+++ b/arch/arm64/kernel/sys32.S
@@ -59,48 +59,48 @@ ENDPROC(compat_sys_fstatfs64_wrapper)
  * extension.
  */
 compat_sys_pread64_wrapper:
-	orr	x3, x4, x5, lsl #32
+	regs_to_64	x3, x4, x5
 	b	sys_pread64
 ENDPROC(compat_sys_pread64_wrapper)
 
 compat_sys_pwrite64_wrapper:
-	orr	x3, x4, x5, lsl #32
+	regs_to_64	x3, x4, x5
 	b	sys_pwrite64
 ENDPROC(compat_sys_pwrite64_wrapper)
 
 compat_sys_truncate64_wrapper:
-	orr	x1, x2, x3, lsl #32
+	regs_to_64	x1, x2, x3
 	b	sys_truncate
 ENDPROC(compat_sys_truncate64_wrapper)
 
 compat_sys_ftruncate64_wrapper:
-	orr	x1, x2, x3, lsl #32
+	regs_to_64	x1, x2, x3
 	b	sys_ftruncate
 ENDPROC(compat_sys_ftruncate64_wrapper)
 
 compat_sys_readahead_wrapper:
-	orr	x1, x2, x3, lsl #32
+	regs_to_64	x1, x2, x3
 	mov	w2, w4
 	b	sys_readahead
 ENDPROC(compat_sys_readahead_wrapper)
 
 compat_sys_fadvise64_64_wrapper:
 	mov	w6, w1
-	orr	x1, x2, x3, lsl #32
-	orr	x2, x4, x5, lsl #32
+	regs_to_64	x1, x2, x3
+	regs_to_64	x2, x4, x5
 	mov	w3, w6
 	b	sys_fadvise64_64
 ENDPROC(compat_sys_fadvise64_64_wrapper)
 
 compat_sys_sync_file_range2_wrapper:
-	orr	x2, x2, x3, lsl #32
-	orr	x3, x4, x5, lsl #32
+	regs_to_64	x2, x2, x3
+	regs_to_64	x3, x4, x5
 	b	sys_sync_file_range2
 ENDPROC(compat_sys_sync_file_range2_wrapper)
 
 compat_sys_fallocate_wrapper:
-	orr	x2, x2, x3, lsl #32
-	orr	x3, x4, x5, lsl #32
+	regs_to_64	x2, x2, x3
+	regs_to_64	x3, x4, x5
 	b	sys_fallocate
 ENDPROC(compat_sys_fallocate_wrapper)
 
diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c
index 6a389dc1bd49..65d40cf6945a 100644
--- a/arch/arm64/kernel/vdso.c
+++ b/arch/arm64/kernel/vdso.c
@@ -58,7 +58,10 @@ static struct page *vectors_page[1];
 static int alloc_vectors_page(void)
 {
 	extern char __kuser_helper_start[], __kuser_helper_end[];
+	extern char __aarch32_sigret_code_start[], __aarch32_sigret_code_end[];
+
 	int kuser_sz = __kuser_helper_end - __kuser_helper_start;
+	int sigret_sz = __aarch32_sigret_code_end - __aarch32_sigret_code_start;
 	unsigned long vpage;
 
 	vpage = get_zeroed_page(GFP_ATOMIC);
@@ -72,7 +75,7 @@ static int alloc_vectors_page(void)
 
 	/* sigreturn code */
 	memcpy((void *)vpage + AARCH32_KERN_SIGRET_CODE_OFFSET,
-		aarch32_sigret_code, sizeof(aarch32_sigret_code));
+               __aarch32_sigret_code_start, sigret_sz);
 
 	flush_icache_range(vpage, vpage + PAGE_SIZE);
 	vectors_page[0] = virt_to_page(vpage);
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index f8ab9d8e2ea3..5161ad992091 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -54,7 +54,6 @@ SECTIONS
 	}
 	.text : {			/* Real text segment		*/
 		_stext = .;		/* Text and read-only data	*/
-			*(.smp.pen.text)
 			__exception_text_start = .;
 			*(.exception.text)
 			__exception_text_end = .;
@@ -97,30 +96,13 @@ SECTIONS
 	PERCPU_SECTION(64)
 
 	__init_end = .;
-	. = ALIGN(THREAD_SIZE);
-	__data_loc = .;
-
-	.data : AT(__data_loc) {
-		_data = .;		/* address in memory */
-		_sdata = .;
-
-		/*
-		 * first, the init task union, aligned
-		 * to an 8192 byte boundary.
-		 */
-		INIT_TASK_DATA(THREAD_SIZE)
-		NOSAVE_DATA
-		CACHELINE_ALIGNED_DATA(64)
-		READ_MOSTLY_DATA(64)
-
-		/*
-		 * and the usual data section
-		 */
-		DATA_DATA
-		CONSTRUCTORS
-
-		_edata = .;
-	}
+
+	. = ALIGN(PAGE_SIZE);
+	_data = .;
+	__data_loc = _data - LOAD_OFFSET;
+	_sdata = .;
+	RW_DATA_SECTION(64, PAGE_SIZE, THREAD_SIZE)
+	_edata = .;
 	_edata_loc = __data_loc + SIZEOF(.data);
 
 	BSS_SECTION(0, 0, 0)
diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp-init.S
index ba84e6705e20..2b0244d65c16 100644
--- a/arch/arm64/kvm/hyp-init.S
+++ b/arch/arm64/kvm/hyp-init.S
@@ -74,7 +74,10 @@ __do_hyp_init:
 	msr	mair_el2, x4
 	isb
 
-	mov	x4, #SCTLR_EL2_FLAGS
+	mrs	x4, sctlr_el2
+	and	x4, x4, #SCTLR_EL2_EE	// preserve endianness of EL2
+	ldr	x5, =SCTLR_EL2_FLAGS
+	orr	x4, x4, x5
 	msr	sctlr_el2, x4
 	isb
 
diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S
index 1ac0bbbdddb2..3b47c36e10ff 100644
--- a/arch/arm64/kvm/hyp.S
+++ b/arch/arm64/kvm/hyp.S
@@ -403,6 +403,14 @@ __kvm_hyp_code_start:
 	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]
@@ -421,6 +429,7 @@ __kvm_hyp_code_start:
 	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
@@ -446,6 +455,9 @@ __kvm_hyp_code_start:
 	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]
@@ -456,6 +468,7 @@ __kvm_hyp_code_start:
 	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
diff --git a/arch/arm64/mm/ioremap.c b/arch/arm64/mm/ioremap.c
index 1725cd6db37a..2bb1d586664c 100644
--- a/arch/arm64/mm/ioremap.c
+++ b/arch/arm64/mm/ioremap.c
@@ -77,8 +77,24 @@ EXPORT_SYMBOL(__ioremap);
 
 void __iounmap(volatile void __iomem *io_addr)
 {
-	void *addr = (void *)(PAGE_MASK & (unsigned long)io_addr);
+	unsigned long addr = (unsigned long)io_addr & PAGE_MASK;
 
-	vunmap(addr);
+	/*
+	 * We could get an address outside vmalloc range in case
+	 * of ioremap_cache() reusing a RAM mapping.
+	 */
+	if (VMALLOC_START <= addr && addr < VMALLOC_END)
+		vunmap((void *)addr);
 }
 EXPORT_SYMBOL(__iounmap);
+
+void __iomem *ioremap_cache(phys_addr_t phys_addr, size_t size)
+{
+	/* For normal memory we already have a cacheable mapping. */
+	if (pfn_valid(__phys_to_pfn(phys_addr)))
+		return (void __iomem *)__phys_to_virt(phys_addr);
+
+	return __ioremap_caller(phys_addr, size, __pgprot(PROT_NORMAL),
+				__builtin_return_address(0));
+}
+EXPORT_SYMBOL(ioremap_cache);
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index b1b31bbc967b..421b99fd635d 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -162,9 +162,9 @@ ENDPROC(__cpu_setup)
 	 *       CE0      XWHW CZ     ME TEEA S
 	 * .... .IEE .... NEAI TE.I ..AD DEN0 ACAM
 	 * 0011 0... 1101 ..0. ..0. 10.. .... .... < hardware reserved
-	 * .... .100 .... 01.1 11.1 ..01 0001 1101 < software settings
+	 * .... .1.. .... 01.1 11.1 ..01 0001 1101 < software settings
 	 */
 	.type	crval, #object
 crval:
-	.word	0x030802e2			// clear
+	.word	0x000802e2			// clear
 	.word	0x0405d11d			// set