Initial import

209 files changed, 22306 insertions, 0 deletions

diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild
new file mode 100644
index 000000000..3c4596d0c
--- /dev/null
+++ b/arch/arm/include/asm/Kbuild
@@ -0,0 +1,39 @@
+
+
+generic-y += bitsperlong.h
+generic-y += cputime.h
+generic-y += current.h
+generic-y += emergency-restart.h
+generic-y += errno.h
+generic-y += exec.h
+generic-y += ioctl.h
+generic-y += ipcbuf.h
+generic-y += irq_regs.h
+generic-y += kdebug.h
+generic-y += local.h
+generic-y += local64.h
+generic-y += mcs_spinlock.h
+generic-y += msgbuf.h
+generic-y += param.h
+generic-y += parport.h
+generic-y += poll.h
+generic-y += preempt.h
+generic-y += resource.h
+generic-y += rwsem.h
+generic-y += scatterlist.h
+generic-y += seccomp.h
+generic-y += sections.h
+generic-y += segment.h
+generic-y += sembuf.h
+generic-y += serial.h
+generic-y += shmbuf.h
+generic-y += siginfo.h
+generic-y += simd.h
+generic-y += sizes.h
+generic-y += socket.h
+generic-y += sockios.h
+generic-y += termbits.h
+generic-y += termios.h
+generic-y += timex.h
+generic-y += trace_clock.h
+generic-y += unaligned.h
diff --git a/arch/arm/include/asm/arch_timer.h b/arch/arm/include/asm/arch_timer.h
new file mode 100644
index 000000000..d4ebf5679
--- /dev/null
+++ b/arch/arm/include/asm/arch_timer.h
@@ -0,0 +1,113 @@
+#ifndef __ASMARM_ARCH_TIMER_H
+#define __ASMARM_ARCH_TIMER_H
+
+#include <asm/barrier.h>
+#include <asm/errno.h>
+#include <linux/clocksource.h>
+#include <linux/init.h>
+#include <linux/types.h>
+
+#include <clocksource/arm_arch_timer.h>
+
+#ifdef CONFIG_ARM_ARCH_TIMER
+int arch_timer_arch_init(void);
+
+/*
+ * These register accessors are marked inline so the compiler can
+ * nicely work out which register we want, and chuck away the rest of
+ * the code. At least it does so with a recent GCC (4.6.3).
+ */
+static __always_inline
+void arch_timer_reg_write_cp15(int access, enum arch_timer_reg reg, u32 val)
+{
+	if (access == ARCH_TIMER_PHYS_ACCESS) {
+		switch (reg) {
+		case ARCH_TIMER_REG_CTRL:
+			asm volatile("mcr p15, 0, %0, c14, c2, 1" : : "r" (val));
+			break;
+		case ARCH_TIMER_REG_TVAL:
+			asm volatile("mcr p15, 0, %0, c14, c2, 0" : : "r" (val));
+			break;
+		}
+	} else if (access == ARCH_TIMER_VIRT_ACCESS) {
+		switch (reg) {
+		case ARCH_TIMER_REG_CTRL:
+			asm volatile("mcr p15, 0, %0, c14, c3, 1" : : "r" (val));
+			break;
+		case ARCH_TIMER_REG_TVAL:
+			asm volatile("mcr p15, 0, %0, c14, c3, 0" : : "r" (val));
+			break;
+		}
+	}
+
+	isb();
+}
+
+static __always_inline
+u32 arch_timer_reg_read_cp15(int access, enum arch_timer_reg reg)
+{
+	u32 val = 0;
+
+	if (access == ARCH_TIMER_PHYS_ACCESS) {
+		switch (reg) {
+		case ARCH_TIMER_REG_CTRL:
+			asm volatile("mrc p15, 0, %0, c14, c2, 1" : "=r" (val));
+			break;
+		case ARCH_TIMER_REG_TVAL:
+			asm volatile("mrc p15, 0, %0, c14, c2, 0" : "=r" (val));
+			break;
+		}
+	} else if (access == ARCH_TIMER_VIRT_ACCESS) {
+		switch (reg) {
+		case ARCH_TIMER_REG_CTRL:
+			asm volatile("mrc p15, 0, %0, c14, c3, 1" : "=r" (val));
+			break;
+		case ARCH_TIMER_REG_TVAL:
+			asm volatile("mrc p15, 0, %0, c14, c3, 0" : "=r" (val));
+			break;
+		}
+	}
+
+	return val;
+}
+
+static inline u32 arch_timer_get_cntfrq(void)
+{
+	u32 val;
+	asm volatile("mrc p15, 0, %0, c14, c0, 0" : "=r" (val));
+	return val;
+}
+
+static inline u64 arch_counter_get_cntpct(void)
+{
+	u64 cval;
+
+	isb();
+	asm volatile("mrrc p15, 0, %Q0, %R0, c14" : "=r" (cval));
+	return cval;
+}
+
+static inline u64 arch_counter_get_cntvct(void)
+{
+	u64 cval;
+
+	isb();
+	asm volatile("mrrc p15, 1, %Q0, %R0, c14" : "=r" (cval));
+	return cval;
+}
+
+static inline u32 arch_timer_get_cntkctl(void)
+{
+	u32 cntkctl;
+	asm volatile("mrc p15, 0, %0, c14, c1, 0" : "=r" (cntkctl));
+	return cntkctl;
+}
+
+static inline void arch_timer_set_cntkctl(u32 cntkctl)
+{
+	asm volatile("mcr p15, 0, %0, c14, c1, 0" : : "r" (cntkctl));
+}
+
+#endif
+
+#endif
diff --git a/arch/arm/include/asm/arm-cci.h b/arch/arm/include/asm/arm-cci.h
new file mode 100644
index 000000000..fe77f7ab7
--- /dev/null
+++ b/arch/arm/include/asm/arm-cci.h
@@ -0,0 +1,42 @@
+/*
+ * arch/arm/include/asm/arm-cci.h
+ *
+ * Copyright (C) 2015 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_ARM_CCI_H
+#define __ASM_ARM_CCI_H
+
+#ifdef CONFIG_MCPM
+#include <asm/mcpm.h>
+
+/*
+ * We don't have a reliable way of detecting whether,
+ * if we have access to secure-only registers, unless
+ * mcpm is registered.
+ */
+static inline bool platform_has_secure_cci_access(void)
+{
+	return mcpm_is_available();
+}
+
+#else
+static inline bool platform_has_secure_cci_access(void)
+{
+	return false;
+}
+#endif
+
+#endif
diff --git a/arch/arm/include/asm/asm-offsets.h b/arch/arm/include/asm/asm-offsets.h
new file mode 100644
index 000000000..d370ee36a
--- /dev/null
+++ b/arch/arm/include/asm/asm-offsets.h
@@ -0,0 +1 @@
+#include <generated/asm-offsets.h>
diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
new file mode 100644
index 000000000..186270b3e
--- /dev/null
+++ b/arch/arm/include/asm/assembler.h
@@ -0,0 +1,454 @@
+/*
+ *  arch/arm/include/asm/assembler.h
+ *
+ *  Copyright (C) 1996-2000 Russell King
+ *
+ * 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 file contains arm architecture specific defines
+ *  for the different processors.
+ *
+ *  Do not include any C declarations in this file - it is included by
+ *  assembler source.
+ */
+#ifndef __ASM_ASSEMBLER_H__
+#define __ASM_ASSEMBLER_H__
+
+#ifndef __ASSEMBLY__
+#error "Only include this from assembly code"
+#endif
+
+#include <asm/ptrace.h>
+#include <asm/domain.h>
+#include <asm/opcodes-virt.h>
+#include <asm/asm-offsets.h>
+#include <asm/page.h>
+#include <asm/thread_info.h>
+
+#define IOMEM(x)	(x)
+
+/*
+ * Endian independent macros for shifting bytes within registers.
+ */
+#ifndef __ARMEB__
+#define lspull          lsr
+#define lspush          lsl
+#define get_byte_0      lsl #0
+#define get_byte_1	lsr #8
+#define get_byte_2	lsr #16
+#define get_byte_3	lsr #24
+#define put_byte_0      lsl #0
+#define put_byte_1	lsl #8
+#define put_byte_2	lsl #16
+#define put_byte_3	lsl #24
+#else
+#define lspull          lsl
+#define lspush          lsr
+#define get_byte_0	lsr #24
+#define get_byte_1	lsr #16
+#define get_byte_2	lsr #8
+#define get_byte_3      lsl #0
+#define put_byte_0	lsl #24
+#define put_byte_1	lsl #16
+#define put_byte_2	lsl #8
+#define put_byte_3      lsl #0
+#endif
+
+/* Select code for any configuration running in BE8 mode */
+#ifdef CONFIG_CPU_ENDIAN_BE8
+#define ARM_BE8(code...) code
+#else
+#define ARM_BE8(code...)
+#endif
+
+/*
+ * Data preload for architectures that support it
+ */
+#if __LINUX_ARM_ARCH__ >= 5
+#define PLD(code...)	code
+#else
+#define PLD(code...)
+#endif
+
+/*
+ * This can be used to enable code to cacheline align the destination
+ * pointer when bulk writing to memory.  Experiments on StrongARM and
+ * XScale didn't show this a worthwhile thing to do when the cache is not
+ * set to write-allocate (this would need further testing on XScale when WA
+ * is used).
+ *
+ * On Feroceon there is much to gain however, regardless of cache mode.
+ */
+#ifdef CONFIG_CPU_FEROCEON
+#define CALGN(code...) code
+#else
+#define CALGN(code...)
+#endif
+
+/*
+ * Enable and disable interrupts
+ */
+#if __LINUX_ARM_ARCH__ >= 6
+	.macro	disable_irq_notrace
+	cpsid	i
+	.endm
+
+	.macro	enable_irq_notrace
+	cpsie	i
+	.endm
+#else
+	.macro	disable_irq_notrace
+	msr	cpsr_c, #PSR_I_BIT | SVC_MODE
+	.endm
+
+	.macro	enable_irq_notrace
+	msr	cpsr_c, #SVC_MODE
+	.endm
+#endif
+
+	.macro asm_trace_hardirqs_off
+#if defined(CONFIG_TRACE_IRQFLAGS)
+	stmdb   sp!, {r0-r3, ip, lr}
+	bl	trace_hardirqs_off
+	ldmia	sp!, {r0-r3, ip, lr}
+#endif
+	.endm
+
+	.macro asm_trace_hardirqs_on_cond, cond
+#if defined(CONFIG_TRACE_IRQFLAGS)
+	/*
+	 * actually the registers should be pushed and pop'd conditionally, but
+	 * after bl the flags are certainly clobbered
+	 */
+	stmdb   sp!, {r0-r3, ip, lr}
+	bl\cond	trace_hardirqs_on
+	ldmia	sp!, {r0-r3, ip, lr}
+#endif
+	.endm
+
+	.macro asm_trace_hardirqs_on
+	asm_trace_hardirqs_on_cond al
+	.endm
+
+	.macro disable_irq
+	disable_irq_notrace
+	asm_trace_hardirqs_off
+	.endm
+
+	.macro enable_irq
+	asm_trace_hardirqs_on
+	enable_irq_notrace
+	.endm
+/*
+ * Save the current IRQ state and disable IRQs.  Note that this macro
+ * assumes FIQs are enabled, and that the processor is in SVC mode.
+ */
+	.macro	save_and_disable_irqs, oldcpsr
+#ifdef CONFIG_CPU_V7M
+	mrs	\oldcpsr, primask
+#else
+	mrs	\oldcpsr, cpsr
+#endif
+	disable_irq
+	.endm
+
+	.macro	save_and_disable_irqs_notrace, oldcpsr
+	mrs	\oldcpsr, cpsr
+	disable_irq_notrace
+	.endm
+
+/*
+ * Restore interrupt state previously stored in a register.  We don't
+ * guarantee that this will preserve the flags.
+ */
+	.macro	restore_irqs_notrace, oldcpsr
+#ifdef CONFIG_CPU_V7M
+	msr	primask, \oldcpsr
+#else
+	msr	cpsr_c, \oldcpsr
+#endif
+	.endm
+
+	.macro restore_irqs, oldcpsr
+	tst	\oldcpsr, #PSR_I_BIT
+	asm_trace_hardirqs_on_cond eq
+	restore_irqs_notrace \oldcpsr
+	.endm
+
+/*
+ * Get current thread_info.
+ */
+	.macro	get_thread_info, rd
+ ARM(	mov	\rd, sp, lsr #THREAD_SIZE_ORDER + PAGE_SHIFT	)
+ THUMB(	mov	\rd, sp			)
+ THUMB(	lsr	\rd, \rd, #THREAD_SIZE_ORDER + PAGE_SHIFT	)
+	mov	\rd, \rd, lsl #THREAD_SIZE_ORDER + PAGE_SHIFT
+	.endm
+
+/*
+ * Increment/decrement the preempt count.
+ */
+#ifdef CONFIG_PREEMPT_COUNT
+	.macro	inc_preempt_count, ti, tmp
+	ldr	\tmp, [\ti, #TI_PREEMPT]	@ get preempt count
+	add	\tmp, \tmp, #1			@ increment it
+	str	\tmp, [\ti, #TI_PREEMPT]
+	.endm
+
+	.macro	dec_preempt_count, ti, tmp
+	ldr	\tmp, [\ti, #TI_PREEMPT]	@ get preempt count
+	sub	\tmp, \tmp, #1			@ decrement it
+	str	\tmp, [\ti, #TI_PREEMPT]
+	.endm
+
+	.macro	dec_preempt_count_ti, ti, tmp
+	get_thread_info \ti
+	dec_preempt_count \ti, \tmp
+	.endm
+#else
+	.macro	inc_preempt_count, ti, tmp
+	.endm
+
+	.macro	dec_preempt_count, ti, tmp
+	.endm
+
+	.macro	dec_preempt_count_ti, ti, tmp
+	.endm
+#endif
+
+#define USER(x...)				\
+9999:	x;					\
+	.pushsection __ex_table,"a";		\
+	.align	3;				\
+	.long	9999b,9001f;			\
+	.popsection
+
+#ifdef CONFIG_SMP
+#define ALT_SMP(instr...)					\
+9998:	instr
+/*
+ * Note: if you get assembler errors from ALT_UP() when building with
+ * CONFIG_THUMB2_KERNEL, you almost certainly need to use
+ * ALT_SMP( W(instr) ... )
+ */
+#define ALT_UP(instr...)					\
+	.pushsection ".alt.smp.init", "a"			;\
+	.long	9998b						;\
+9997:	instr							;\
+	.if . - 9997b == 2					;\
+		nop						;\
+	.endif							;\
+	.if . - 9997b != 4					;\
+		.error "ALT_UP() content must assemble to exactly 4 bytes";\
+	.endif							;\
+	.popsection
+#define ALT_UP_B(label)					\
+	.equ	up_b_offset, label - 9998b			;\
+	.pushsection ".alt.smp.init", "a"			;\
+	.long	9998b						;\
+	W(b)	. + up_b_offset					;\
+	.popsection
+#else
+#define ALT_SMP(instr...)
+#define ALT_UP(instr...) instr
+#define ALT_UP_B(label) b label
+#endif
+
+/*
+ * Instruction barrier
+ */
+	.macro	instr_sync
+#if __LINUX_ARM_ARCH__ >= 7
+	isb
+#elif __LINUX_ARM_ARCH__ == 6
+	mcr	p15, 0, r0, c7, c5, 4
+#endif
+	.endm
+
+/*
+ * SMP data memory barrier
+ */
+	.macro	smp_dmb mode
+#ifdef CONFIG_SMP
+#if __LINUX_ARM_ARCH__ >= 7
+	.ifeqs "\mode","arm"
+	ALT_SMP(dmb	ish)
+	.else
+	ALT_SMP(W(dmb)	ish)
+	.endif
+#elif __LINUX_ARM_ARCH__ == 6
+	ALT_SMP(mcr	p15, 0, r0, c7, c10, 5)	@ dmb
+#else
+#error Incompatible SMP platform
+#endif
+	.ifeqs "\mode","arm"
+	ALT_UP(nop)
+	.else
+	ALT_UP(W(nop))
+	.endif
+#endif
+	.endm
+
+#if defined(CONFIG_CPU_V7M)
+	/*
+	 * setmode is used to assert to be in svc mode during boot. For v7-M
+	 * this is done in __v7m_setup, so setmode can be empty here.
+	 */
+	.macro	setmode, mode, reg
+	.endm
+#elif defined(CONFIG_THUMB2_KERNEL)
+	.macro	setmode, mode, reg
+	mov	\reg, #\mode
+	msr	cpsr_c, \reg
+	.endm
+#else
+	.macro	setmode, mode, reg
+	msr	cpsr_c, #\mode
+	.endm
+#endif
+
+/*
+ * Helper macro to enter SVC mode cleanly and mask interrupts. reg is
+ * a scratch register for the macro to overwrite.
+ *
+ * This macro is intended for forcing the CPU into SVC mode at boot time.
+ * you cannot return to the original mode.
+ */
+.macro safe_svcmode_maskall reg:req
+#if __LINUX_ARM_ARCH__ >= 6 && !defined(CONFIG_CPU_V7M)
+	mrs	\reg , cpsr
+	eor	\reg, \reg, #HYP_MODE
+	tst	\reg, #MODE_MASK
+	bic	\reg , \reg , #MODE_MASK
+	orr	\reg , \reg , #PSR_I_BIT | PSR_F_BIT | SVC_MODE
+THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
+	bne	1f
+	orr	\reg, \reg, #PSR_A_BIT
+	adr	lr, BSYM(2f)
+	msr	spsr_cxsf, \reg
+	__MSR_ELR_HYP(14)
+	__ERET
+1:	msr	cpsr_c, \reg
+2:
+#else
+/*
+ * workaround for possibly broken pre-v6 hardware
+ * (akita, Sharp Zaurus C-1000, PXA270-based)
+ */
+	setmode	PSR_F_BIT | PSR_I_BIT | SVC_MODE, \reg
+#endif
+.endm
+
+/*
+ * STRT/LDRT access macros with ARM and Thumb-2 variants
+ */
+#ifdef CONFIG_THUMB2_KERNEL
+
+	.macro	usraccoff, instr, reg, ptr, inc, off, cond, abort, t=TUSER()
+9999:
+	.if	\inc == 1
+	\instr\cond\()b\()\t\().w \reg, [\ptr, #\off]
+	.elseif	\inc == 4
+	\instr\cond\()\t\().w \reg, [\ptr, #\off]
+	.else
+	.error	"Unsupported inc macro argument"
+	.endif
+
+	.pushsection __ex_table,"a"
+	.align	3
+	.long	9999b, \abort
+	.popsection
+	.endm
+
+	.macro	usracc, instr, reg, ptr, inc, cond, rept, abort
+	@ explicit IT instruction needed because of the label
+	@ introduced by the USER macro
+	.ifnc	\cond,al
+	.if	\rept == 1
+	itt	\cond
+	.elseif	\rept == 2
+	ittt	\cond
+	.else
+	.error	"Unsupported rept macro argument"
+	.endif
+	.endif
+
+	@ Slightly optimised to avoid incrementing the pointer twice
+	usraccoff \instr, \reg, \ptr, \inc, 0, \cond, \abort
+	.if	\rept == 2
+	usraccoff \instr, \reg, \ptr, \inc, \inc, \cond, \abort
+	.endif
+
+	add\cond \ptr, #\rept * \inc
+	.endm
+
+#else	/* !CONFIG_THUMB2_KERNEL */
+
+	.macro	usracc, instr, reg, ptr, inc, cond, rept, abort, t=TUSER()
+	.rept	\rept
+9999:
+	.if	\inc == 1
+	\instr\cond\()b\()\t \reg, [\ptr], #\inc
+	.elseif	\inc == 4
+	\instr\cond\()\t \reg, [\ptr], #\inc
+	.else
+	.error	"Unsupported inc macro argument"
+	.endif
+
+	.pushsection __ex_table,"a"
+	.align	3
+	.long	9999b, \abort
+	.popsection
+	.endr
+	.endm
+
+#endif	/* CONFIG_THUMB2_KERNEL */
+
+	.macro	strusr, reg, ptr, inc, cond=al, rept=1, abort=9001f
+	usracc	str, \reg, \ptr, \inc, \cond, \rept, \abort
+	.endm
+
+	.macro	ldrusr, reg, ptr, inc, cond=al, rept=1, abort=9001f
+	usracc	ldr, \reg, \ptr, \inc, \cond, \rept, \abort
+	.endm
+
+/* Utility macro for declaring string literals */
+	.macro	string name:req, string
+	.type \name , #object
+\name:
+	.asciz "\string"
+	.size \name , . - \name
+	.endm
+
+	.macro check_uaccess, addr:req, size:req, limit:req, tmp:req, bad:req
+#ifndef CONFIG_CPU_USE_DOMAINS
+	adds	\tmp, \addr, #\size - 1
+	sbcccs	\tmp, \tmp, \limit
+	bcs	\bad
+#endif
+	.endm
+
+	.irp	c,,eq,ne,cs,cc,mi,pl,vs,vc,hi,ls,ge,lt,gt,le,hs,lo
+	.macro	ret\c, reg
+#if __LINUX_ARM_ARCH__ < 6
+	mov\c	pc, \reg
+#else
+	.ifeqs	"\reg", "lr"
+	bx\c	\reg
+	.else
+	mov\c	pc, \reg
+	.endif
+#endif
+	.endm
+	.endr
+
+	.macro	ret.w, reg
+	ret	\reg
+#ifdef CONFIG_THUMB2_KERNEL
+	nop
+#endif
+	.endm
+
+#endif /* __ASM_ASSEMBLER_H__ */
diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h
new file mode 100644
index 000000000..e22c11970
--- /dev/null
+++ b/arch/arm/include/asm/atomic.h
@@ -0,0 +1,446 @@
+/*
+ *  arch/arm/include/asm/atomic.h
+ *
+ *  Copyright (C) 1996 Russell King.
+ *  Copyright (C) 2002 Deep Blue Solutions 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.
+ */
+#ifndef __ASM_ARM_ATOMIC_H
+#define __ASM_ARM_ATOMIC_H
+
+#include <linux/compiler.h>
+#include <linux/prefetch.h>
+#include <linux/types.h>
+#include <linux/irqflags.h>
+#include <asm/barrier.h>
+#include <asm/cmpxchg.h>
+
+#define ATOMIC_INIT(i)	{ (i) }
+
+#ifdef __KERNEL__
+
+/*
+ * On ARM, ordinary assignment (str instruction) doesn't clear the local
+ * 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)	ACCESS_ONCE((v)->counter)
+#define atomic_set(v,i)	(((v)->counter) = (i))
+
+#if __LINUX_ARM_ARCH__ >= 6
+
+/*
+ * ARMv6 UP and SMP safe atomic ops.  We use load exclusive and
+ * store exclusive to ensure that these are atomic.  We may loop
+ * to ensure that the update happens.
+ */
+
+#define ATOMIC_OP(op, c_op, asm_op)					\
+static inline void atomic_##op(int i, atomic_t *v)			\
+{									\
+	unsigned long tmp;						\
+	int result;							\
+									\
+	prefetchw(&v->counter);						\
+	__asm__ __volatile__("@ atomic_" #op "\n"			\
+"1:	ldrex	%0, [%3]\n"						\
+"	" #asm_op "	%0, %0, %4\n"					\
+"	strex	%1, %0, [%3]\n"						\
+"	teq	%1, #0\n"						\
+"	bne	1b"							\
+	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)		\
+	: "r" (&v->counter), "Ir" (i)					\
+	: "cc");							\
+}									\
+
+#define ATOMIC_OP_RETURN(op, c_op, asm_op)				\
+static inline int atomic_##op##_return(int i, atomic_t *v)		\
+{									\
+	unsigned long tmp;						\
+	int result;							\
+									\
+	smp_mb();							\
+	prefetchw(&v->counter);						\
+									\
+	__asm__ __volatile__("@ atomic_" #op "_return\n"		\
+"1:	ldrex	%0, [%3]\n"						\
+"	" #asm_op "	%0, %0, %4\n"					\
+"	strex	%1, %0, [%3]\n"						\
+"	teq	%1, #0\n"						\
+"	bne	1b"							\
+	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)		\
+	: "r" (&v->counter), "Ir" (i)					\
+	: "cc");							\
+									\
+	smp_mb();							\
+									\
+	return result;							\
+}
+
+static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new)
+{
+	int oldval;
+	unsigned long res;
+
+	smp_mb();
+	prefetchw(&ptr->counter);
+
+	do {
+		__asm__ __volatile__("@ atomic_cmpxchg\n"
+		"ldrex	%1, [%3]\n"
+		"mov	%0, #0\n"
+		"teq	%1, %4\n"
+		"strexeq %0, %5, [%3]\n"
+		    : "=&r" (res), "=&r" (oldval), "+Qo" (ptr->counter)
+		    : "r" (&ptr->counter), "Ir" (old), "r" (new)
+		    : "cc");
+	} while (res);
+
+	smp_mb();
+
+	return oldval;
+}
+
+static inline int __atomic_add_unless(atomic_t *v, int a, int u)
+{
+	int oldval, newval;
+	unsigned long tmp;
+
+	smp_mb();
+	prefetchw(&v->counter);
+
+	__asm__ __volatile__ ("@ atomic_add_unless\n"
+"1:	ldrex	%0, [%4]\n"
+"	teq	%0, %5\n"
+"	beq	2f\n"
+"	add	%1, %0, %6\n"
+"	strex	%2, %1, [%4]\n"
+"	teq	%2, #0\n"
+"	bne	1b\n"
+"2:"
+	: "=&r" (oldval), "=&r" (newval), "=&r" (tmp), "+Qo" (v->counter)
+	: "r" (&v->counter), "r" (u), "r" (a)
+	: "cc");
+
+	if (oldval != u)
+		smp_mb();
+
+	return oldval;
+}
+
+#else /* ARM_ARCH_6 */
+
+#ifdef CONFIG_SMP
+#error SMP not supported on pre-ARMv6 CPUs
+#endif
+
+#define ATOMIC_OP(op, c_op, asm_op)					\
+static inline void atomic_##op(int i, atomic_t *v)			\
+{									\
+	unsigned long flags;						\
+									\
+	raw_local_irq_save(flags);					\
+	v->counter c_op i;						\
+	raw_local_irq_restore(flags);					\
+}									\
+
+#define ATOMIC_OP_RETURN(op, c_op, asm_op)				\
+static inline int atomic_##op##_return(int i, atomic_t *v)		\
+{									\
+	unsigned long flags;						\
+	int val;							\
+									\
+	raw_local_irq_save(flags);					\
+	v->counter c_op i;						\
+	val = v->counter;						\
+	raw_local_irq_restore(flags);					\
+									\
+	return val;							\
+}
+
+static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
+{
+	int ret;
+	unsigned long flags;
+
+	raw_local_irq_save(flags);
+	ret = v->counter;
+	if (likely(ret == old))
+		v->counter = new;
+	raw_local_irq_restore(flags);
+
+	return ret;
+}
+
+static inline int __atomic_add_unless(atomic_t *v, int a, int u)
+{
+	int c, old;
+
+	c = atomic_read(v);
+	while (c != u && (old = atomic_cmpxchg((v), c, c + a)) != c)
+		c = old;
+	return c;
+}
+
+#endif /* __LINUX_ARM_ARCH__ */
+
+#define ATOMIC_OPS(op, c_op, asm_op)					\
+	ATOMIC_OP(op, c_op, asm_op)					\
+	ATOMIC_OP_RETURN(op, c_op, asm_op)
+
+ATOMIC_OPS(add, +=, add)
+ATOMIC_OPS(sub, -=, sub)
+
+#undef ATOMIC_OPS
+#undef ATOMIC_OP_RETURN
+#undef ATOMIC_OP
+
+#define atomic_xchg(v, new) (xchg(&((v)->counter), new))
+
+#define atomic_inc(v)		atomic_add(1, v)
+#define atomic_dec(v)		atomic_sub(1, v)
+
+#define atomic_inc_and_test(v)	(atomic_add_return(1, v) == 0)
+#define atomic_dec_and_test(v)	(atomic_sub_return(1, v) == 0)
+#define atomic_inc_return(v)    (atomic_add_return(1, v))
+#define atomic_dec_return(v)    (atomic_sub_return(1, v))
+#define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0)
+
+#define atomic_add_negative(i,v) (atomic_add_return(i, v) < 0)
+
+#ifndef CONFIG_GENERIC_ATOMIC64
+typedef struct {
+	long long counter;
+} atomic64_t;
+
+#define ATOMIC64_INIT(i) { (i) }
+
+#ifdef CONFIG_ARM_LPAE
+static inline long long atomic64_read(const atomic64_t *v)
+{
+	long long result;
+
+	__asm__ __volatile__("@ atomic64_read\n"
+"	ldrd	%0, %H0, [%1]"
+	: "=&r" (result)
+	: "r" (&v->counter), "Qo" (v->counter)
+	);
+
+	return result;
+}
+
+static inline void atomic64_set(atomic64_t *v, long long i)
+{
+	__asm__ __volatile__("@ atomic64_set\n"
+"	strd	%2, %H2, [%1]"
+	: "=Qo" (v->counter)
+	: "r" (&v->counter), "r" (i)
+	);
+}
+#else
+static inline long long atomic64_read(const atomic64_t *v)
+{
+	long long result;
+
+	__asm__ __volatile__("@ atomic64_read\n"
+"	ldrexd	%0, %H0, [%1]"
+	: "=&r" (result)
+	: "r" (&v->counter), "Qo" (v->counter)
+	);
+
+	return result;
+}
+
+static inline void atomic64_set(atomic64_t *v, long long i)
+{
+	long long tmp;
+
+	prefetchw(&v->counter);
+	__asm__ __volatile__("@ atomic64_set\n"
+"1:	ldrexd	%0, %H0, [%2]\n"
+"	strexd	%0, %3, %H3, [%2]\n"
+"	teq	%0, #0\n"
+"	bne	1b"
+	: "=&r" (tmp), "=Qo" (v->counter)
+	: "r" (&v->counter), "r" (i)
+	: "cc");
+}
+#endif
+
+#define ATOMIC64_OP(op, op1, op2)					\
+static inline void atomic64_##op(long long i, atomic64_t *v)		\
+{									\
+	long long result;						\
+	unsigned long tmp;						\
+									\
+	prefetchw(&v->counter);						\
+	__asm__ __volatile__("@ atomic64_" #op "\n"			\
+"1:	ldrexd	%0, %H0, [%3]\n"					\
+"	" #op1 " %Q0, %Q0, %Q4\n"					\
+"	" #op2 " %R0, %R0, %R4\n"					\
+"	strexd	%1, %0, %H0, [%3]\n"					\
+"	teq	%1, #0\n"						\
+"	bne	1b"							\
+	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)		\
+	: "r" (&v->counter), "r" (i)					\
+	: "cc");							\
+}									\
+
+#define ATOMIC64_OP_RETURN(op, op1, op2)				\
+static inline long long atomic64_##op##_return(long long i, atomic64_t *v) \
+{									\
+	long long result;						\
+	unsigned long tmp;						\
+									\
+	smp_mb();							\
+	prefetchw(&v->counter);						\
+									\
+	__asm__ __volatile__("@ atomic64_" #op "_return\n"		\
+"1:	ldrexd	%0, %H0, [%3]\n"					\
+"	" #op1 " %Q0, %Q0, %Q4\n"					\
+"	" #op2 " %R0, %R0, %R4\n"					\
+"	strexd	%1, %0, %H0, [%3]\n"					\
+"	teq	%1, #0\n"						\
+"	bne	1b"							\
+	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)		\
+	: "r" (&v->counter), "r" (i)					\
+	: "cc");							\
+									\
+	smp_mb();							\
+									\
+	return result;							\
+}
+
+#define ATOMIC64_OPS(op, op1, op2)					\
+	ATOMIC64_OP(op, op1, op2)					\
+	ATOMIC64_OP_RETURN(op, op1, op2)
+
+ATOMIC64_OPS(add, adds, adc)
+ATOMIC64_OPS(sub, subs, sbc)
+
+#undef ATOMIC64_OPS
+#undef ATOMIC64_OP_RETURN
+#undef ATOMIC64_OP
+
+static inline long long atomic64_cmpxchg(atomic64_t *ptr, long long old,
+					long long new)
+{
+	long long oldval;
+	unsigned long res;
+
+	smp_mb();
+	prefetchw(&ptr->counter);
+
+	do {
+		__asm__ __volatile__("@ atomic64_cmpxchg\n"
+		"ldrexd		%1, %H1, [%3]\n"
+		"mov		%0, #0\n"
+		"teq		%1, %4\n"
+		"teqeq		%H1, %H4\n"
+		"strexdeq	%0, %5, %H5, [%3]"
+		: "=&r" (res), "=&r" (oldval), "+Qo" (ptr->counter)
+		: "r" (&ptr->counter), "r" (old), "r" (new)
+		: "cc");
+	} while (res);
+
+	smp_mb();
+
+	return oldval;
+}
+
+static inline long long atomic64_xchg(atomic64_t *ptr, long long new)
+{
+	long long result;
+	unsigned long tmp;
+
+	smp_mb();
+	prefetchw(&ptr->counter);
+
+	__asm__ __volatile__("@ atomic64_xchg\n"
+"1:	ldrexd	%0, %H0, [%3]\n"
+"	strexd	%1, %4, %H4, [%3]\n"
+"	teq	%1, #0\n"
+"	bne	1b"
+	: "=&r" (result), "=&r" (tmp), "+Qo" (ptr->counter)
+	: "r" (&ptr->counter), "r" (new)
+	: "cc");
+
+	smp_mb();
+
+	return result;
+}
+
+static inline long long atomic64_dec_if_positive(atomic64_t *v)
+{
+	long long result;
+	unsigned long tmp;
+
+	smp_mb();
+	prefetchw(&v->counter);
+
+	__asm__ __volatile__("@ atomic64_dec_if_positive\n"
+"1:	ldrexd	%0, %H0, [%3]\n"
+"	subs	%Q0, %Q0, #1\n"
+"	sbc	%R0, %R0, #0\n"
+"	teq	%R0, #0\n"
+"	bmi	2f\n"
+"	strexd	%1, %0, %H0, [%3]\n"
+"	teq	%1, #0\n"
+"	bne	1b\n"
+"2:"
+	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)
+	: "r" (&v->counter)
+	: "cc");
+
+	smp_mb();
+
+	return result;
+}
+
+static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u)
+{
+	long long val;
+	unsigned long tmp;
+	int ret = 1;
+
+	smp_mb();
+	prefetchw(&v->counter);
+
+	__asm__ __volatile__("@ atomic64_add_unless\n"
+"1:	ldrexd	%0, %H0, [%4]\n"
+"	teq	%0, %5\n"
+"	teqeq	%H0, %H5\n"
+"	moveq	%1, #0\n"
+"	beq	2f\n"
+"	adds	%Q0, %Q0, %Q6\n"
+"	adc	%R0, %R0, %R6\n"
+"	strexd	%2, %0, %H0, [%4]\n"
+"	teq	%2, #0\n"
+"	bne	1b\n"
+"2:"
+	: "=&r" (val), "+r" (ret), "=&r" (tmp), "+Qo" (v->counter)
+	: "r" (&v->counter), "r" (u), "r" (a)
+	: "cc");
+
+	if (ret)
+		smp_mb();
+
+	return ret;
+}
+
+#define atomic64_add_negative(a, v)	(atomic64_add_return((a), (v)) < 0)
+#define atomic64_inc(v)			atomic64_add(1LL, (v))
+#define atomic64_inc_return(v)		atomic64_add_return(1LL, (v))
+#define atomic64_inc_and_test(v)	(atomic64_inc_return(v) == 0)
+#define atomic64_sub_and_test(a, v)	(atomic64_sub_return((a), (v)) == 0)
+#define atomic64_dec(v)			atomic64_sub(1LL, (v))
+#define atomic64_dec_return(v)		atomic64_sub_return(1LL, (v))
+#define atomic64_dec_and_test(v)	(atomic64_dec_return((v)) == 0)
+#define atomic64_inc_not_zero(v)	atomic64_add_unless((v), 1LL, 0LL)
+
+#endif /* !CONFIG_GENERIC_ATOMIC64 */
+#endif
+#endif
diff --git a/arch/arm/include/asm/auxvec.h b/arch/arm/include/asm/auxvec.h
new file mode 100644
index 000000000..fbd388c46
--- /dev/null
+++ b/arch/arm/include/asm/auxvec.h
@@ -0,0 +1 @@
+#include <uapi/asm/auxvec.h>
diff --git a/arch/arm/include/asm/bL_switcher.h b/arch/arm/include/asm/bL_switcher.h
new file mode 100644
index 000000000..1714800fa
--- /dev/null
+++ b/arch/arm/include/asm/bL_switcher.h
@@ -0,0 +1,77 @@
+/*
+ * arch/arm/include/asm/bL_switcher.h
+ *
+ * Created by:  Nicolas Pitre, April 2012
+ * Copyright:   (C) 2012-2013  Linaro Limited
+ *
+ * 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.
+ */
+
+#ifndef ASM_BL_SWITCHER_H
+#define ASM_BL_SWITCHER_H
+
+#include <linux/compiler.h>
+#include <linux/types.h>
+
+typedef void (*bL_switch_completion_handler)(void *cookie);
+
+int bL_switch_request_cb(unsigned int cpu, unsigned int new_cluster_id,
+			 bL_switch_completion_handler completer,
+			 void *completer_cookie);
+static inline int bL_switch_request(unsigned int cpu, unsigned int new_cluster_id)
+{
+	return bL_switch_request_cb(cpu, new_cluster_id, NULL, NULL);
+}
+
+/*
+ * Register here to be notified about runtime enabling/disabling of
+ * the switcher.
+ *
+ * The notifier chain is called with the switcher activation lock held:
+ * the switcher will not be enabled or disabled during callbacks.
+ * Callbacks must not call bL_switcher_{get,put}_enabled().
+ */
+#define BL_NOTIFY_PRE_ENABLE	0
+#define BL_NOTIFY_POST_ENABLE	1
+#define BL_NOTIFY_PRE_DISABLE	2
+#define BL_NOTIFY_POST_DISABLE	3
+
+#ifdef CONFIG_BL_SWITCHER
+
+int bL_switcher_register_notifier(struct notifier_block *nb);
+int bL_switcher_unregister_notifier(struct notifier_block *nb);
+
+/*
+ * Use these functions to temporarily prevent enabling/disabling of
+ * the switcher.
+ * bL_switcher_get_enabled() returns true if the switcher is currently
+ * enabled.  Each call to bL_switcher_get_enabled() must be followed
+ * by a call to bL_switcher_put_enabled().  These functions are not
+ * recursive.
+ */
+bool bL_switcher_get_enabled(void);
+void bL_switcher_put_enabled(void);
+
+int bL_switcher_trace_trigger(void);
+int bL_switcher_get_logical_index(u32 mpidr);
+
+#else
+static inline int bL_switcher_register_notifier(struct notifier_block *nb)
+{
+	return 0;
+}
+
+static inline int bL_switcher_unregister_notifier(struct notifier_block *nb)
+{
+	return 0;
+}
+
+static inline bool bL_switcher_get_enabled(void) { return false; }
+static inline void bL_switcher_put_enabled(void) { }
+static inline int bL_switcher_trace_trigger(void) { return 0; }
+static inline int bL_switcher_get_logical_index(u32 mpidr) { return -EUNATCH; }
+#endif /* CONFIG_BL_SWITCHER */
+
+#endif
diff --git a/arch/arm/include/asm/barrier.h b/arch/arm/include/asm/barrier.h
new file mode 100644
index 000000000..d2f81e6b8
--- /dev/null
+++ b/arch/arm/include/asm/barrier.h
@@ -0,0 +1,90 @@
+#ifndef __ASM_BARRIER_H
+#define __ASM_BARRIER_H
+
+#ifndef __ASSEMBLY__
+#include <asm/outercache.h>
+
+#define nop() __asm__ __volatile__("mov\tr0,r0\t@ nop\n\t");
+
+#if __LINUX_ARM_ARCH__ >= 7 ||		\
+	(__LINUX_ARM_ARCH__ == 6 && defined(CONFIG_CPU_32v6K))
+#define sev()	__asm__ __volatile__ ("sev" : : : "memory")
+#define wfe()	__asm__ __volatile__ ("wfe" : : : "memory")
+#define wfi()	__asm__ __volatile__ ("wfi" : : : "memory")
+#endif
+
+#if __LINUX_ARM_ARCH__ >= 7
+#define isb(option) __asm__ __volatile__ ("isb " #option : : : "memory")
+#define dsb(option) __asm__ __volatile__ ("dsb " #option : : : "memory")
+#define dmb(option) __asm__ __volatile__ ("dmb " #option : : : "memory")
+#elif defined(CONFIG_CPU_XSC3) || __LINUX_ARM_ARCH__ == 6
+#define isb(x) __asm__ __volatile__ ("mcr p15, 0, %0, c7, c5, 4" \
+				    : : "r" (0) : "memory")
+#define dsb(x) __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 4" \
+				    : : "r" (0) : "memory")
+#define dmb(x) __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 5" \
+				    : : "r" (0) : "memory")
+#elif defined(CONFIG_CPU_FA526)
+#define isb(x) __asm__ __volatile__ ("mcr p15, 0, %0, c7, c5, 4" \
+				    : : "r" (0) : "memory")
+#define dsb(x) __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 4" \
+				    : : "r" (0) : "memory")
+#define dmb(x) __asm__ __volatile__ ("" : : : "memory")
+#else
+#define isb(x) __asm__ __volatile__ ("" : : : "memory")
+#define dsb(x) __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 4" \
+				    : : "r" (0) : "memory")
+#define dmb(x) __asm__ __volatile__ ("" : : : "memory")
+#endif
+
+#ifdef CONFIG_ARCH_HAS_BARRIERS
+#include <mach/barriers.h>
+#elif defined(CONFIG_ARM_DMA_MEM_BUFFERABLE) || defined(CONFIG_SMP)
+#define mb()		do { dsb(); outer_sync(); } while (0)
+#define rmb()		dsb()
+#define wmb()		do { dsb(st); outer_sync(); } while (0)
+#define dma_rmb()	dmb(osh)
+#define dma_wmb()	dmb(oshst)
+#else
+#define mb()		barrier()
+#define rmb()		barrier()
+#define wmb()		barrier()
+#define dma_rmb()	barrier()
+#define dma_wmb()	barrier()
+#endif
+
+#ifndef CONFIG_SMP
+#define smp_mb()	barrier()
+#define smp_rmb()	barrier()
+#define smp_wmb()	barrier()
+#else
+#define smp_mb()	dmb(ish)
+#define smp_rmb()	smp_mb()
+#define smp_wmb()	dmb(ishst)
+#endif
+
+#define smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	ACCESS_ONCE(*p) = (v);						\
+} while (0)
+
+#define smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	___p1;								\
+})
+
+#define read_barrier_depends()		do { } while(0)
+#define smp_read_barrier_depends()	do { } while(0)
+
+#define set_mb(var, value)	do { var = value; smp_mb(); } while (0)
+
+#define smp_mb__before_atomic()	smp_mb()
+#define smp_mb__after_atomic()	smp_mb()
+
+#endif /* !__ASSEMBLY__ */
+#endif /* __ASM_BARRIER_H */
diff --git a/arch/arm/include/asm/bitops.h b/arch/arm/include/asm/bitops.h
new file mode 100644
index 000000000..56380995f
--- /dev/null
+++ b/arch/arm/include/asm/bitops.h
@@ -0,0 +1,349 @@
+/*
+ * Copyright 1995, Russell King.
+ * Various bits and pieces copyrights include:
+ *  Linus Torvalds (test_bit).
+ * Big endian support: Copyright 2001, Nicolas Pitre
+ *  reworked by rmk.
+ *
+ * bit 0 is the LSB of an "unsigned long" quantity.
+ *
+ * Please note that the code in this file should never be included
+ * from user space.  Many of these are not implemented in assembler
+ * since they would be too costly.  Also, they require privileged
+ * instructions (which are not available from user mode) to ensure
+ * that they are atomic.
+ */
+
+#ifndef __ASM_ARM_BITOPS_H
+#define __ASM_ARM_BITOPS_H
+
+#ifdef __KERNEL__
+
+#ifndef _LINUX_BITOPS_H
+#error only <linux/bitops.h> can be included directly
+#endif
+
+#include <linux/compiler.h>
+#include <linux/irqflags.h>
+#include <asm/barrier.h>
+
+/*
+ * These functions are the basis of our bit ops.
+ *
+ * First, the atomic bitops. These use native endian.
+ */
+static inline void ____atomic_set_bit(unsigned int bit, volatile unsigned long *p)
+{
+	unsigned long flags;
+	unsigned long mask = 1UL << (bit & 31);
+
+	p += bit >> 5;
+
+	raw_local_irq_save(flags);
+	*p |= mask;
+	raw_local_irq_restore(flags);
+}
+
+static inline void ____atomic_clear_bit(unsigned int bit, volatile unsigned long *p)
+{
+	unsigned long flags;
+	unsigned long mask = 1UL << (bit & 31);
+
+	p += bit >> 5;
+
+	raw_local_irq_save(flags);
+	*p &= ~mask;
+	raw_local_irq_restore(flags);
+}
+
+static inline void ____atomic_change_bit(unsigned int bit, volatile unsigned long *p)
+{
+	unsigned long flags;
+	unsigned long mask = 1UL << (bit & 31);
+
+	p += bit >> 5;
+
+	raw_local_irq_save(flags);
+	*p ^= mask;
+	raw_local_irq_restore(flags);
+}
+
+static inline int
+____atomic_test_and_set_bit(unsigned int bit, volatile unsigned long *p)
+{
+	unsigned long flags;
+	unsigned int res;
+	unsigned long mask = 1UL << (bit & 31);
+
+	p += bit >> 5;
+
+	raw_local_irq_save(flags);
+	res = *p;
+	*p = res | mask;
+	raw_local_irq_restore(flags);
+
+	return (res & mask) != 0;
+}
+
+static inline int
+____atomic_test_and_clear_bit(unsigned int bit, volatile unsigned long *p)
+{
+	unsigned long flags;
+	unsigned int res;
+	unsigned long mask = 1UL << (bit & 31);
+
+	p += bit >> 5;
+
+	raw_local_irq_save(flags);
+	res = *p;
+	*p = res & ~mask;
+	raw_local_irq_restore(flags);
+
+	return (res & mask) != 0;
+}
+
+static inline int
+____atomic_test_and_change_bit(unsigned int bit, volatile unsigned long *p)
+{
+	unsigned long flags;
+	unsigned int res;
+	unsigned long mask = 1UL << (bit & 31);
+
+	p += bit >> 5;
+
+	raw_local_irq_save(flags);
+	res = *p;
+	*p = res ^ mask;
+	raw_local_irq_restore(flags);
+
+	return (res & mask) != 0;
+}
+
+#include <asm-generic/bitops/non-atomic.h>
+
+/*
+ *  A note about Endian-ness.
+ *  -------------------------
+ *
+ * When the ARM is put into big endian mode via CR15, the processor
+ * merely swaps the order of bytes within words, thus:
+ *
+ *          ------------ physical data bus bits -----------
+ *          D31 ... D24  D23 ... D16  D15 ... D8  D7 ... D0
+ * little     byte 3       byte 2       byte 1      byte 0
+ * big        byte 0       byte 1       byte 2      byte 3
+ *
+ * This means that reading a 32-bit word at address 0 returns the same
+ * value irrespective of the endian mode bit.
+ *
+ * Peripheral devices should be connected with the data bus reversed in
+ * "Big Endian" mode.  ARM Application Note 61 is applicable, and is
+ * available from http://www.arm.com/.
+ *
+ * The following assumes that the data bus connectivity for big endian
+ * mode has been followed.
+ *
+ * Note that bit 0 is defined to be 32-bit word bit 0, not byte 0 bit 0.
+ */
+
+/*
+ * Native endian assembly bitops.  nr = 0 -> word 0 bit 0.
+ */
+extern void _set_bit(int nr, volatile unsigned long * p);
+extern void _clear_bit(int nr, volatile unsigned long * p);
+extern void _change_bit(int nr, volatile unsigned long * p);
+extern int _test_and_set_bit(int nr, volatile unsigned long * p);
+extern int _test_and_clear_bit(int nr, volatile unsigned long * p);
+extern int _test_and_change_bit(int nr, volatile unsigned long * p);
+
+/*
+ * Little endian assembly bitops.  nr = 0 -> byte 0 bit 0.
+ */
+extern int _find_first_zero_bit_le(const void * p, unsigned size);
+extern int _find_next_zero_bit_le(const void * p, int size, int offset);
+extern int _find_first_bit_le(const unsigned long *p, unsigned size);
+extern int _find_next_bit_le(const unsigned long *p, int size, int offset);
+
+/*
+ * Big endian assembly bitops.  nr = 0 -> byte 3 bit 0.
+ */
+extern int _find_first_zero_bit_be(const void * p, unsigned size);
+extern int _find_next_zero_bit_be(const void * p, int size, int offset);
+extern int _find_first_bit_be(const unsigned long *p, unsigned size);
+extern int _find_next_bit_be(const unsigned long *p, int size, int offset);
+
+#ifndef CONFIG_SMP
+/*
+ * The __* form of bitops are non-atomic and may be reordered.
+ */
+#define ATOMIC_BITOP(name,nr,p)			\
+	(__builtin_constant_p(nr) ? ____atomic_##name(nr, p) : _##name(nr,p))
+#else
+#define ATOMIC_BITOP(name,nr,p)		_##name(nr,p)
+#endif
+
+/*
+ * Native endian atomic definitions.
+ */
+#define set_bit(nr,p)			ATOMIC_BITOP(set_bit,nr,p)
+#define clear_bit(nr,p)			ATOMIC_BITOP(clear_bit,nr,p)
+#define change_bit(nr,p)		ATOMIC_BITOP(change_bit,nr,p)
+#define test_and_set_bit(nr,p)		ATOMIC_BITOP(test_and_set_bit,nr,p)
+#define test_and_clear_bit(nr,p)	ATOMIC_BITOP(test_and_clear_bit,nr,p)
+#define test_and_change_bit(nr,p)	ATOMIC_BITOP(test_and_change_bit,nr,p)
+
+#ifndef __ARMEB__
+/*
+ * These are the little endian, atomic definitions.
+ */
+#define find_first_zero_bit(p,sz)	_find_first_zero_bit_le(p,sz)
+#define find_next_zero_bit(p,sz,off)	_find_next_zero_bit_le(p,sz,off)
+#define find_first_bit(p,sz)		_find_first_bit_le(p,sz)
+#define find_next_bit(p,sz,off)		_find_next_bit_le(p,sz,off)
+
+#else
+/*
+ * These are the big endian, atomic definitions.
+ */
+#define find_first_zero_bit(p,sz)	_find_first_zero_bit_be(p,sz)
+#define find_next_zero_bit(p,sz,off)	_find_next_zero_bit_be(p,sz,off)
+#define find_first_bit(p,sz)		_find_first_bit_be(p,sz)
+#define find_next_bit(p,sz,off)		_find_next_bit_be(p,sz,off)
+
+#endif
+
+#if __LINUX_ARM_ARCH__ < 5
+
+#include <asm-generic/bitops/ffz.h>
+#include <asm-generic/bitops/__fls.h>
+#include <asm-generic/bitops/__ffs.h>
+#include <asm-generic/bitops/fls.h>
+#include <asm-generic/bitops/ffs.h>
+
+#else
+
+static inline int constant_fls(int x)
+{
+	int r = 32;
+
+	if (!x)
+		return 0;
+	if (!(x & 0xffff0000u)) {
+		x <<= 16;
+		r -= 16;
+	}
+	if (!(x & 0xff000000u)) {
+		x <<= 8;
+		r -= 8;
+	}
+	if (!(x & 0xf0000000u)) {
+		x <<= 4;
+		r -= 4;
+	}
+	if (!(x & 0xc0000000u)) {
+		x <<= 2;
+		r -= 2;
+	}
+	if (!(x & 0x80000000u)) {
+		x <<= 1;
+		r -= 1;
+	}
+	return r;
+}
+
+/*
+ * On ARMv5 and above those functions can be implemented around the
+ * clz instruction for much better code efficiency.  __clz returns
+ * the number of leading zeros, zero input will return 32, and
+ * 0x80000000 will return 0.
+ */
+static inline unsigned int __clz(unsigned int x)
+{
+	unsigned int ret;
+
+	asm("clz\t%0, %1" : "=r" (ret) : "r" (x));
+
+	return ret;
+}
+
+/*
+ * fls() returns zero if the input is zero, otherwise returns the bit
+ * position of the last set bit, where the LSB is 1 and MSB is 32.
+ */
+static inline int fls(int x)
+{
+	if (__builtin_constant_p(x))
+	       return constant_fls(x);
+
+	return 32 - __clz(x);
+}
+
+/*
+ * __fls() returns the bit position of the last bit set, where the
+ * LSB is 0 and MSB is 31.  Zero input is undefined.
+ */
+static inline unsigned long __fls(unsigned long x)
+{
+	return fls(x) - 1;
+}
+
+/*
+ * ffs() returns zero if the input was zero, otherwise returns the bit
+ * position of the first set bit, where the LSB is 1 and MSB is 32.
+ */
+static inline int ffs(int x)
+{
+	return fls(x & -x);
+}
+
+/*
+ * __ffs() returns the bit position of the first bit set, where the
+ * LSB is 0 and MSB is 31.  Zero input is undefined.
+ */
+static inline unsigned long __ffs(unsigned long x)
+{
+	return ffs(x) - 1;
+}
+
+#define ffz(x) __ffs( ~(x) )
+
+#endif
+
+#include <asm-generic/bitops/fls64.h>
+
+#include <asm-generic/bitops/sched.h>
+#include <asm-generic/bitops/hweight.h>
+#include <asm-generic/bitops/lock.h>
+
+#ifdef __ARMEB__
+
+static inline int find_first_zero_bit_le(const void *p, unsigned size)
+{
+	return _find_first_zero_bit_le(p, size);
+}
+#define find_first_zero_bit_le find_first_zero_bit_le
+
+static inline int find_next_zero_bit_le(const void *p, int size, int offset)
+{
+	return _find_next_zero_bit_le(p, size, offset);
+}
+#define find_next_zero_bit_le find_next_zero_bit_le
+
+static inline int find_next_bit_le(const void *p, int size, int offset)
+{
+	return _find_next_bit_le(p, size, offset);
+}
+#define find_next_bit_le find_next_bit_le
+
+#endif
+
+#include <asm-generic/bitops/le.h>
+
+/*
+ * Ext2 is defined to use little-endian byte ordering.
+ */
+#include <asm-generic/bitops/ext2-atomic-setbit.h>
+
+#endif /* __KERNEL__ */
+
+#endif /* _ARM_BITOPS_H */
diff --git a/arch/arm/include/asm/bitrev.h b/arch/arm/include/asm/bitrev.h
new file mode 100644
index 000000000..ec291c350
--- /dev/null
+++ b/arch/arm/include/asm/bitrev.h
@@ -0,0 +1,20 @@
+#ifndef __ASM_BITREV_H
+#define __ASM_BITREV_H
+
+static __always_inline __attribute_const__ u32 __arch_bitrev32(u32 x)
+{
+	__asm__ ("rbit %0, %1" : "=r" (x) : "r" (x));
+	return x;
+}
+
+static __always_inline __attribute_const__ u16 __arch_bitrev16(u16 x)
+{
+	return __arch_bitrev32((u32)x) >> 16;
+}
+
+static __always_inline __attribute_const__ u8 __arch_bitrev8(u8 x)
+{
+	return __arch_bitrev32((u32)x) >> 24;
+}
+
+#endif
diff --git a/arch/arm/include/asm/bug.h b/arch/arm/include/asm/bug.h
new file mode 100644
index 000000000..b274bde24
--- /dev/null
+++ b/arch/arm/include/asm/bug.h
@@ -0,0 +1,92 @@
+#ifndef _ASMARM_BUG_H
+#define _ASMARM_BUG_H
+
+#include <linux/linkage.h>
+#include <linux/types.h>
+#include <asm/opcodes.h>
+
+#ifdef CONFIG_BUG
+
+/*
+ * Use a suitable undefined instruction to use for ARM/Thumb2 bug handling.
+ * We need to be careful not to conflict with those used by other modules and
+ * the register_undef_hook() system.
+ */
+#ifdef CONFIG_THUMB2_KERNEL
+#define BUG_INSTR_VALUE 0xde02
+#define BUG_INSTR(__value) __inst_thumb16(__value)
+#else
+#define BUG_INSTR_VALUE 0xe7f001f2
+#define BUG_INSTR(__value) __inst_arm(__value)
+#endif
+
+
+#define BUG() _BUG(__FILE__, __LINE__, BUG_INSTR_VALUE)
+#define _BUG(file, line, value) __BUG(file, line, value)
+
+#ifdef CONFIG_DEBUG_BUGVERBOSE
+
+/*
+ * The extra indirection is to ensure that the __FILE__ string comes through
+ * OK. Many version of gcc do not support the asm %c parameter which would be
+ * preferable to this unpleasantness. We use mergeable string sections to
+ * avoid multiple copies of the string appearing in the kernel image.
+ */
+
+#define __BUG(__file, __line, __value)				\
+do {								\
+	asm volatile("1:\t" BUG_INSTR(__value) "\n"  \
+		".pushsection .rodata.str, \"aMS\", %progbits, 1\n" \
+		"2:\t.asciz " #__file "\n" 			\
+		".popsection\n" 				\
+		".pushsection __bug_table,\"a\"\n"		\
+		"3:\t.word 1b, 2b\n"				\
+		"\t.hword " #__line ", 0\n"			\
+		".popsection");					\
+	unreachable();						\
+} while (0)
+
+#else  /* not CONFIG_DEBUG_BUGVERBOSE */
+
+#define __BUG(__file, __line, __value)				\
+do {								\
+	asm volatile(BUG_INSTR(__value) "\n");			\
+	unreachable();						\
+} while (0)
+#endif  /* CONFIG_DEBUG_BUGVERBOSE */
+
+#define HAVE_ARCH_BUG
+#endif  /* CONFIG_BUG */
+
+#include <asm-generic/bug.h>
+
+struct pt_regs;
+void die(const char *msg, struct pt_regs *regs, int err);
+
+struct siginfo;
+void arm_notify_die(const char *str, struct pt_regs *regs, struct siginfo *info,
+		unsigned long err, unsigned long trap);
+
+#ifdef CONFIG_ARM_LPAE
+#define FAULT_CODE_ALIGNMENT	33
+#define FAULT_CODE_DEBUG	34
+#else
+#define FAULT_CODE_ALIGNMENT	1
+#define FAULT_CODE_DEBUG	2
+#endif
+
+void hook_fault_code(int nr, int (*fn)(unsigned long, unsigned int,
+				       struct pt_regs *),
+		     int sig, int code, const char *name);
+
+void hook_ifault_code(int nr, int (*fn)(unsigned long, unsigned int,
+				       struct pt_regs *),
+		     int sig, int code, const char *name);
+
+extern asmlinkage void c_backtrace(unsigned long fp, int pmode);
+
+struct mm_struct;
+extern void show_pte(struct mm_struct *mm, unsigned long addr);
+extern void __show_regs(struct pt_regs *);
+
+#endif
diff --git a/arch/arm/include/asm/bugs.h b/arch/arm/include/asm/bugs.h
new file mode 100644
index 000000000..a97f1ea70
--- /dev/null
+++ b/arch/arm/include/asm/bugs.h
@@ -0,0 +1,21 @@
+/*
+ *  arch/arm/include/asm/bugs.h
+ *
+ *  Copyright (C) 1995-2003 Russell King
+ *
+ * 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.
+ */
+#ifndef __ASM_BUGS_H
+#define __ASM_BUGS_H
+
+#ifdef CONFIG_MMU
+extern void check_writebuffer_bugs(void);
+
+#define check_bugs() check_writebuffer_bugs()
+#else
+#define check_bugs() do { } while (0)
+#endif
+
+#endif
diff --git a/arch/arm/include/asm/cache.h b/arch/arm/include/asm/cache.h
new file mode 100644
index 000000000..75fe66bc0
--- /dev/null
+++ b/arch/arm/include/asm/cache.h
@@ -0,0 +1,28 @@
+/*
+ *  arch/arm/include/asm/cache.h
+ */
+#ifndef __ASMARM_CACHE_H
+#define __ASMARM_CACHE_H
+
+#define L1_CACHE_SHIFT		CONFIG_ARM_L1_CACHE_SHIFT
+#define L1_CACHE_BYTES		(1 << L1_CACHE_SHIFT)
+
+/*
+ * Memory returned by kmalloc() may be used for DMA, so we must make
+ * sure that all such allocations are cache aligned. Otherwise,
+ * unrelated code may cause parts of the buffer to be read into the
+ * cache before the transfer is done, causing old data to be seen by
+ * the CPU.
+ */
+#define ARCH_DMA_MINALIGN	L1_CACHE_BYTES
+
+/*
+ * With EABI on ARMv5 and above we must have 64-bit aligned slab pointers.
+ */
+#if defined(CONFIG_AEABI) && (__LINUX_ARM_ARCH__ >= 5)
+#define ARCH_SLAB_MINALIGN 8
+#endif
+
+#define __read_mostly __attribute__((__section__(".data..read_mostly")))
+
+#endif
diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h
new file mode 100644
index 000000000..2d46862e7
--- /dev/null
+++ b/arch/arm/include/asm/cacheflush.h
@@ -0,0 +1,502 @@
+/*
+ *  arch/arm/include/asm/cacheflush.h
+ *
+ *  Copyright (C) 1999-2002 Russell King
+ *
+ * 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.
+ */
+#ifndef _ASMARM_CACHEFLUSH_H
+#define _ASMARM_CACHEFLUSH_H
+
+#include <linux/mm.h>
+
+#include <asm/glue-cache.h>
+#include <asm/shmparam.h>
+#include <asm/cachetype.h>
+#include <asm/outercache.h>
+
+#define CACHE_COLOUR(vaddr)	((vaddr & (SHMLBA - 1)) >> PAGE_SHIFT)
+
+/*
+ * This flag is used to indicate that the page pointed to by a pte is clean
+ * and does not require cleaning before returning it to the user.
+ */
+#define PG_dcache_clean PG_arch_1
+
+/*
+ *	MM Cache Management
+ *	===================
+ *
+ *	The arch/arm/mm/cache-*.S and arch/arm/mm/proc-*.S files
+ *	implement these methods.
+ *
+ *	Start addresses are inclusive and end addresses are exclusive;
+ *	start addresses should be rounded down, end addresses up.
+ *
+ *	See Documentation/cachetlb.txt for more information.
+ *	Please note that the implementation of these, and the required
+ *	effects are cache-type (VIVT/VIPT/PIPT) specific.
+ *
+ *	flush_icache_all()
+ *
+ *		Unconditionally clean and invalidate the entire icache.
+ *		Currently only needed for cache-v6.S and cache-v7.S, see
+ *		__flush_icache_all for the generic implementation.
+ *
+ *	flush_kern_all()
+ *
+ *		Unconditionally clean and invalidate the entire cache.
+ *
+ *     flush_kern_louis()
+ *
+ *             Flush data cache levels up to the level of unification
+ *             inner shareable and invalidate the I-cache.
+ *             Only needed from v7 onwards, falls back to flush_cache_all()
+ *             for all other processor versions.
+ *
+ *	flush_user_all()
+ *
+ *		Clean and invalidate all user space cache entries
+ *		before a change of page tables.
+ *
+ *	flush_user_range(start, end, flags)
+ *
+ *		Clean and invalidate a range of cache entries in the
+ *		specified address space before a change of page tables.
+ *		- start - user start address (inclusive, page aligned)
+ *		- end   - user end address   (exclusive, page aligned)
+ *		- flags - vma->vm_flags field
+ *
+ *	coherent_kern_range(start, end)
+ *
+ *		Ensure coherency between the Icache and the Dcache in the
+ *		region described by start, end.  If you have non-snooping
+ *		Harvard caches, you need to implement this function.
+ *		- start  - virtual start address
+ *		- end    - virtual end address
+ *
+ *	coherent_user_range(start, end)
+ *
+ *		Ensure coherency between the Icache and the Dcache in the
+ *		region described by start, end.  If you have non-snooping
+ *		Harvard caches, you need to implement this function.
+ *		- start  - virtual start address
+ *		- end    - virtual end address
+ *
+ *	flush_kern_dcache_area(kaddr, size)
+ *
+ *		Ensure that the data held in page is written back.
+ *		- kaddr  - page address
+ *		- size   - region size
+ *
+ *	DMA Cache Coherency
+ *	===================
+ *
+ *	dma_flush_range(start, end)
+ *
+ *		Clean and invalidate the specified virtual address range.
+ *		- start  - virtual start address
+ *		- end    - virtual end address
+ */
+
+struct cpu_cache_fns {
+	void (*flush_icache_all)(void);
+	void (*flush_kern_all)(void);
+	void (*flush_kern_louis)(void);
+	void (*flush_user_all)(void);
+	void (*flush_user_range)(unsigned long, unsigned long, unsigned int);
+
+	void (*coherent_kern_range)(unsigned long, unsigned long);
+	int  (*coherent_user_range)(unsigned long, unsigned long);
+	void (*flush_kern_dcache_area)(void *, size_t);
+
+	void (*dma_map_area)(const void *, size_t, int);
+	void (*dma_unmap_area)(const void *, size_t, int);
+
+	void (*dma_flush_range)(const void *, const void *);
+};
+
+/*
+ * Select the calling method
+ */
+#ifdef MULTI_CACHE
+
+extern struct cpu_cache_fns cpu_cache;
+
+#define __cpuc_flush_icache_all		cpu_cache.flush_icache_all
+#define __cpuc_flush_kern_all		cpu_cache.flush_kern_all
+#define __cpuc_flush_kern_louis		cpu_cache.flush_kern_louis
+#define __cpuc_flush_user_all		cpu_cache.flush_user_all
+#define __cpuc_flush_user_range		cpu_cache.flush_user_range
+#define __cpuc_coherent_kern_range	cpu_cache.coherent_kern_range
+#define __cpuc_coherent_user_range	cpu_cache.coherent_user_range
+#define __cpuc_flush_dcache_area	cpu_cache.flush_kern_dcache_area
+
+/*
+ * These are private to the dma-mapping API.  Do not use directly.
+ * Their sole purpose is to ensure that data held in the cache
+ * is visible to DMA, or data written by DMA to system memory is
+ * visible to the CPU.
+ */
+#define dmac_map_area			cpu_cache.dma_map_area
+#define dmac_unmap_area			cpu_cache.dma_unmap_area
+#define dmac_flush_range		cpu_cache.dma_flush_range
+
+#else
+
+extern void __cpuc_flush_icache_all(void);
+extern void __cpuc_flush_kern_all(void);
+extern void __cpuc_flush_kern_louis(void);
+extern void __cpuc_flush_user_all(void);
+extern void __cpuc_flush_user_range(unsigned long, unsigned long, unsigned int);
+extern void __cpuc_coherent_kern_range(unsigned long, unsigned long);
+extern int  __cpuc_coherent_user_range(unsigned long, unsigned long);
+extern void __cpuc_flush_dcache_area(void *, size_t);
+
+/*
+ * These are private to the dma-mapping API.  Do not use directly.
+ * Their sole purpose is to ensure that data held in the cache
+ * is visible to DMA, or data written by DMA to system memory is
+ * visible to the CPU.
+ */
+extern void dmac_map_area(const void *, size_t, int);
+extern void dmac_unmap_area(const void *, size_t, int);
+extern void dmac_flush_range(const void *, const void *);
+
+#endif
+
+/*
+ * Copy user data from/to a page which is mapped into a different
+ * processes address space.  Really, we want to allow our "user
+ * space" model to handle this.
+ */
+extern void copy_to_user_page(struct vm_area_struct *, struct page *,
+	unsigned long, void *, const void *, unsigned long);
+#define copy_from_user_page(vma, page, vaddr, dst, src, len) \
+	do {							\
+		memcpy(dst, src, len);				\
+	} while (0)
+
+/*
+ * Convert calls to our calling convention.
+ */
+
+/* Invalidate I-cache */
+#define __flush_icache_all_generic()					\
+	asm("mcr	p15, 0, %0, c7, c5, 0"				\
+	    : : "r" (0));
+
+/* Invalidate I-cache inner shareable */
+#define __flush_icache_all_v7_smp()					\
+	asm("mcr	p15, 0, %0, c7, c1, 0"				\
+	    : : "r" (0));
+
+/*
+ * Optimized __flush_icache_all for the common cases. Note that UP ARMv7
+ * will fall through to use __flush_icache_all_generic.
+ */
+#if (defined(CONFIG_CPU_V7) && \
+     (defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_V6K))) || \
+	defined(CONFIG_SMP_ON_UP)
+#define __flush_icache_preferred	__cpuc_flush_icache_all
+#elif __LINUX_ARM_ARCH__ >= 7 && defined(CONFIG_SMP)
+#define __flush_icache_preferred	__flush_icache_all_v7_smp
+#elif __LINUX_ARM_ARCH__ == 6 && defined(CONFIG_ARM_ERRATA_411920)
+#define __flush_icache_preferred	__cpuc_flush_icache_all
+#else
+#define __flush_icache_preferred	__flush_icache_all_generic
+#endif
+
+static inline void __flush_icache_all(void)
+{
+	__flush_icache_preferred();
+	dsb(ishst);
+}
+
+/*
+ * Flush caches up to Level of Unification Inner Shareable
+ */
+#define flush_cache_louis()		__cpuc_flush_kern_louis()
+
+#define flush_cache_all()		__cpuc_flush_kern_all()
+
+static inline void vivt_flush_cache_mm(struct mm_struct *mm)
+{
+	if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(mm)))
+		__cpuc_flush_user_all();
+}
+
+static inline void
+vivt_flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end)
+{
+	struct mm_struct *mm = vma->vm_mm;
+
+	if (!mm || cpumask_test_cpu(smp_processor_id(), mm_cpumask(mm)))
+		__cpuc_flush_user_range(start & PAGE_MASK, PAGE_ALIGN(end),
+					vma->vm_flags);
+}
+
+static inline void
+vivt_flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr, unsigned long pfn)
+{
+	struct mm_struct *mm = vma->vm_mm;
+
+	if (!mm || cpumask_test_cpu(smp_processor_id(), mm_cpumask(mm))) {
+		unsigned long addr = user_addr & PAGE_MASK;
+		__cpuc_flush_user_range(addr, addr + PAGE_SIZE, vma->vm_flags);
+	}
+}
+
+#ifndef CONFIG_CPU_CACHE_VIPT
+#define flush_cache_mm(mm) \
+		vivt_flush_cache_mm(mm)
+#define flush_cache_range(vma,start,end) \
+		vivt_flush_cache_range(vma,start,end)
+#define flush_cache_page(vma,addr,pfn) \
+		vivt_flush_cache_page(vma,addr,pfn)
+#else
+extern void flush_cache_mm(struct mm_struct *mm);
+extern void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end);
+extern void flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr, unsigned long pfn);
+#endif
+
+#define flush_cache_dup_mm(mm) flush_cache_mm(mm)
+
+/*
+ * flush_cache_user_range is used when we want to ensure that the
+ * Harvard caches are synchronised for the user space address range.
+ * This is used for the ARM private sys_cacheflush system call.
+ */
+#define flush_cache_user_range(s,e)	__cpuc_coherent_user_range(s,e)
+
+/*
+ * Perform necessary cache operations to ensure that data previously
+ * stored within this range of addresses can be executed by the CPU.
+ */
+#define flush_icache_range(s,e)		__cpuc_coherent_kern_range(s,e)
+
+/*
+ * Perform necessary cache operations to ensure that the TLB will
+ * see data written in the specified area.
+ */
+#define clean_dcache_area(start,size)	cpu_dcache_clean_area(start, size)
+
+/*
+ * flush_dcache_page is used when the kernel has written to the page
+ * cache page at virtual address page->virtual.
+ *
+ * If this page isn't mapped (ie, page_mapping == NULL), or it might
+ * have userspace mappings, then we _must_ always clean + invalidate
+ * the dcache entries associated with the kernel mapping.
+ *
+ * Otherwise we can defer the operation, and clean the cache when we are
+ * about to change to user space.  This is the same method as used on SPARC64.
+ * See update_mmu_cache for the user space part.
+ */
+#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
+extern void flush_dcache_page(struct page *);
+
+static inline void flush_kernel_vmap_range(void *addr, int size)
+{
+	if ((cache_is_vivt() || cache_is_vipt_aliasing()))
+	  __cpuc_flush_dcache_area(addr, (size_t)size);
+}
+static inline void invalidate_kernel_vmap_range(void *addr, int size)
+{
+	if ((cache_is_vivt() || cache_is_vipt_aliasing()))
+	  __cpuc_flush_dcache_area(addr, (size_t)size);
+}
+
+#define ARCH_HAS_FLUSH_ANON_PAGE
+static inline void flush_anon_page(struct vm_area_struct *vma,
+			 struct page *page, unsigned long vmaddr)
+{
+	extern void __flush_anon_page(struct vm_area_struct *vma,
+				struct page *, unsigned long);
+	if (PageAnon(page))
+		__flush_anon_page(vma, page, vmaddr);
+}
+
+#define ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE
+extern void flush_kernel_dcache_page(struct page *);
+
+#define flush_dcache_mmap_lock(mapping) \
+	spin_lock_irq(&(mapping)->tree_lock)
+#define flush_dcache_mmap_unlock(mapping) \
+	spin_unlock_irq(&(mapping)->tree_lock)
+
+#define flush_icache_user_range(vma,page,addr,len) \
+	flush_dcache_page(page)
+
+/*
+ * We don't appear to need to do anything here.  In fact, if we did, we'd
+ * duplicate cache flushing elsewhere performed by flush_dcache_page().
+ */
+#define flush_icache_page(vma,page)	do { } while (0)
+
+/*
+ * flush_cache_vmap() is used when creating mappings (eg, via vmap,
+ * vmalloc, ioremap etc) in kernel space for pages.  On non-VIPT
+ * caches, since the direct-mappings of these pages may contain cached
+ * data, we need to do a full cache flush to ensure that writebacks
+ * don't corrupt data placed into these pages via the new mappings.
+ */
+static inline void flush_cache_vmap(unsigned long start, unsigned long end)
+{
+	if (!cache_is_vipt_nonaliasing())
+		flush_cache_all();
+	else
+		/*
+		 * set_pte_at() called from vmap_pte_range() does not
+		 * have a DSB after cleaning the cache line.
+		 */
+		dsb(ishst);
+}
+
+static inline void flush_cache_vunmap(unsigned long start, unsigned long end)
+{
+	if (!cache_is_vipt_nonaliasing())
+		flush_cache_all();
+}
+
+/*
+ * Memory synchronization helpers for mixed cached vs non cached accesses.
+ *
+ * Some synchronization algorithms have to set states in memory with the
+ * cache enabled or disabled depending on the code path.  It is crucial
+ * to always ensure proper cache maintenance to update main memory right
+ * away in that case.
+ *
+ * Any cached write must be followed by a cache clean operation.
+ * Any cached read must be preceded by a cache invalidate operation.
+ * Yet, in the read case, a cache flush i.e. atomic clean+invalidate
+ * operation is needed to avoid discarding possible concurrent writes to the
+ * accessed memory.
+ *
+ * Also, in order to prevent a cached writer from interfering with an
+ * adjacent non-cached writer, each state variable must be located to
+ * a separate cache line.
+ */
+
+/*
+ * This needs to be >= the max cache writeback size of all
+ * supported platforms included in the current kernel configuration.
+ * This is used to align state variables to their own cache lines.
+ */
+#define __CACHE_WRITEBACK_ORDER 6  /* guessed from existing platforms */
+#define __CACHE_WRITEBACK_GRANULE (1 << __CACHE_WRITEBACK_ORDER)
+
+/*
+ * There is no __cpuc_clean_dcache_area but we use it anyway for
+ * code intent clarity, and alias it to __cpuc_flush_dcache_area.
+ */
+#define __cpuc_clean_dcache_area __cpuc_flush_dcache_area
+
+/*
+ * Ensure preceding writes to *p by this CPU are visible to
+ * subsequent reads by other CPUs:
+ */
+static inline void __sync_cache_range_w(volatile void *p, size_t size)
+{
+	char *_p = (char *)p;
+
+	__cpuc_clean_dcache_area(_p, size);
+	outer_clean_range(__pa(_p), __pa(_p + size));
+}
+
+/*
+ * Ensure preceding writes to *p by other CPUs are visible to
+ * subsequent reads by this CPU.  We must be careful not to
+ * discard data simultaneously written by another CPU, hence the
+ * usage of flush rather than invalidate operations.
+ */
+static inline void __sync_cache_range_r(volatile void *p, size_t size)
+{
+	char *_p = (char *)p;
+
+#ifdef CONFIG_OUTER_CACHE
+	if (outer_cache.flush_range) {
+		/*
+		 * Ensure dirty data migrated from other CPUs into our cache
+		 * are cleaned out safely before the outer cache is cleaned:
+		 */
+		__cpuc_clean_dcache_area(_p, size);
+
+		/* Clean and invalidate stale data for *p from outer ... */
+		outer_flush_range(__pa(_p), __pa(_p + size));
+	}
+#endif
+
+	/* ... and inner cache: */
+	__cpuc_flush_dcache_area(_p, size);
+}
+
+#define sync_cache_w(ptr) __sync_cache_range_w(ptr, sizeof *(ptr))
+#define sync_cache_r(ptr) __sync_cache_range_r(ptr, sizeof *(ptr))
+
+/*
+ * Disabling cache access for one CPU in an ARMv7 SMP system is tricky.
+ * To do so we must:
+ *
+ * - Clear the SCTLR.C bit to prevent further cache allocations
+ * - Flush the desired level of cache
+ * - Clear the ACTLR "SMP" bit to disable local coherency
+ *
+ * ... and so without any intervening memory access in between those steps,
+ * not even to the stack.
+ *
+ * WARNING -- After this has been called:
+ *
+ * - No ldrex/strex (and similar) instructions must be used.
+ * - The CPU is obviously no longer coherent with the other CPUs.
+ * - This is unlikely to work as expected if Linux is running non-secure.
+ *
+ * Note:
+ *
+ * - This is known to apply to several ARMv7 processor implementations,
+ *   however some exceptions may exist.  Caveat emptor.
+ *
+ * - The clobber list is dictated by the call to v7_flush_dcache_*.
+ *   fp is preserved to the stack explicitly prior disabling the cache
+ *   since adding it to the clobber list is incompatible with having
+ *   CONFIG_FRAME_POINTER=y.  ip is saved as well if ever r12-clobbering
+ *   trampoline are inserted by the linker and to keep sp 64-bit aligned.
+ */
+#define v7_exit_coherency_flush(level) \
+	asm volatile( \
+	".arch	armv7-a \n\t" \
+	"stmfd	sp!, {fp, ip} \n\t" \
+	"mrc	p15, 0, r0, c1, c0, 0	@ get SCTLR \n\t" \
+	"bic	r0, r0, #"__stringify(CR_C)" \n\t" \
+	"mcr	p15, 0, r0, c1, c0, 0	@ set SCTLR \n\t" \
+	"isb	\n\t" \
+	"bl	v7_flush_dcache_"__stringify(level)" \n\t" \
+	"mrc	p15, 0, r0, c1, c0, 1	@ get ACTLR \n\t" \
+	"bic	r0, r0, #(1 << 6)	@ disable local coherency \n\t" \
+	"mcr	p15, 0, r0, c1, c0, 1	@ set ACTLR \n\t" \
+	"isb	\n\t" \
+	"dsb	\n\t" \
+	"ldmfd	sp!, {fp, ip}" \
+	: : : "r0","r1","r2","r3","r4","r5","r6","r7", \
+	      "r9","r10","lr","memory" )
+
+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);
+
+#ifdef CONFIG_DEBUG_RODATA
+void mark_rodata_ro(void);
+void set_kernel_text_rw(void);
+void set_kernel_text_ro(void);
+#else
+static inline void set_kernel_text_rw(void) { }
+static inline void set_kernel_text_ro(void) { }
+#endif
+
+void flush_uprobe_xol_access(struct page *page, unsigned long uaddr,
+			     void *kaddr, unsigned long len);
+
+#endif
diff --git a/arch/arm/include/asm/cachetype.h b/arch/arm/include/asm/cachetype.h
new file mode 100644
index 000000000..7ea78144a
--- /dev/null
+++ b/arch/arm/include/asm/cachetype.h
@@ -0,0 +1,59 @@
+#ifndef __ASM_ARM_CACHETYPE_H
+#define __ASM_ARM_CACHETYPE_H
+
+#define CACHEID_VIVT			(1 << 0)
+#define CACHEID_VIPT_NONALIASING	(1 << 1)
+#define CACHEID_VIPT_ALIASING		(1 << 2)
+#define CACHEID_VIPT			(CACHEID_VIPT_ALIASING|CACHEID_VIPT_NONALIASING)
+#define CACHEID_ASID_TAGGED		(1 << 3)
+#define CACHEID_VIPT_I_ALIASING		(1 << 4)
+#define CACHEID_PIPT			(1 << 5)
+
+extern unsigned int cacheid;
+
+#define cache_is_vivt()			cacheid_is(CACHEID_VIVT)
+#define cache_is_vipt()			cacheid_is(CACHEID_VIPT)
+#define cache_is_vipt_nonaliasing()	cacheid_is(CACHEID_VIPT_NONALIASING)
+#define cache_is_vipt_aliasing()	cacheid_is(CACHEID_VIPT_ALIASING)
+#define icache_is_vivt_asid_tagged()	cacheid_is(CACHEID_ASID_TAGGED)
+#define icache_is_vipt_aliasing()	cacheid_is(CACHEID_VIPT_I_ALIASING)
+#define icache_is_pipt()		cacheid_is(CACHEID_PIPT)
+
+/*
+ * __LINUX_ARM_ARCH__ is the minimum supported CPU architecture
+ * Mask out support which will never be present on newer CPUs.
+ * - v6+ is never VIVT
+ * - v7+ VIPT never aliases on D-side
+ */
+#if __LINUX_ARM_ARCH__ >= 7
+#define __CACHEID_ARCH_MIN	(CACHEID_VIPT_NONALIASING |\
+				 CACHEID_ASID_TAGGED |\
+				 CACHEID_VIPT_I_ALIASING |\
+				 CACHEID_PIPT)
+#elif __LINUX_ARM_ARCH__ >= 6
+#define	__CACHEID_ARCH_MIN	(~CACHEID_VIVT)
+#else
+#define __CACHEID_ARCH_MIN	(~0)
+#endif
+
+/*
+ * Mask out support which isn't configured
+ */
+#if defined(CONFIG_CPU_CACHE_VIVT) && !defined(CONFIG_CPU_CACHE_VIPT)
+#define __CACHEID_ALWAYS	(CACHEID_VIVT)
+#define __CACHEID_NEVER		(~CACHEID_VIVT)
+#elif !defined(CONFIG_CPU_CACHE_VIVT) && defined(CONFIG_CPU_CACHE_VIPT)
+#define __CACHEID_ALWAYS	(0)
+#define __CACHEID_NEVER		(CACHEID_VIVT)
+#else
+#define __CACHEID_ALWAYS	(0)
+#define __CACHEID_NEVER		(0)
+#endif
+
+static inline unsigned int __attribute__((pure)) cacheid_is(unsigned int mask)
+{
+	return (__CACHEID_ALWAYS & mask) |
+	       (~__CACHEID_NEVER & __CACHEID_ARCH_MIN & mask & cacheid);
+}
+
+#endif
diff --git a/arch/arm/include/asm/checksum.h b/arch/arm/include/asm/checksum.h
new file mode 100644
index 000000000..523315115
--- /dev/null
+++ b/arch/arm/include/asm/checksum.h
@@ -0,0 +1,153 @@
+/*
+ *  arch/arm/include/asm/checksum.h
+ *
+ * IP checksum routines
+ *
+ * Copyright (C) Original authors of ../asm-i386/checksum.h
+ * Copyright (C) 1996-1999 Russell King
+ */
+#ifndef __ASM_ARM_CHECKSUM_H
+#define __ASM_ARM_CHECKSUM_H
+
+#include <linux/in6.h>
+
+/*
+ * computes the checksum of a memory block at buff, length len,
+ * and adds in "sum" (32-bit)
+ *
+ * returns a 32-bit number suitable for feeding into itself
+ * or csum_tcpudp_magic
+ *
+ * this function must be called with even lengths, except
+ * for the last fragment, which may be odd
+ *
+ * it's best to have buff aligned on a 32-bit boundary
+ */
+__wsum csum_partial(const void *buff, int len, __wsum sum);
+
+/*
+ * the same as csum_partial, but copies from src while it
+ * checksums, and handles user-space pointer exceptions correctly, when needed.
+ *
+ * here even more important to align src and dst on a 32-bit (or even
+ * better 64-bit) boundary
+ */
+
+__wsum
+csum_partial_copy_nocheck(const void *src, void *dst, int len, __wsum sum);
+
+__wsum
+csum_partial_copy_from_user(const void __user *src, void *dst, int len, __wsum sum, int *err_ptr);
+
+/*
+ * 	Fold a partial checksum without adding pseudo headers
+ */
+static inline __sum16 csum_fold(__wsum sum)
+{
+	__asm__(
+	"add	%0, %1, %1, ror #16	@ csum_fold"
+	: "=r" (sum)
+	: "r" (sum)
+	: "cc");
+	return (__force __sum16)(~(__force u32)sum >> 16);
+}
+
+/*
+ *	This is a version of ip_compute_csum() optimized for IP headers,
+ *	which always checksum on 4 octet boundaries.
+ */
+static inline __sum16
+ip_fast_csum(const void *iph, unsigned int ihl)
+{
+	unsigned int tmp1;
+	__wsum sum;
+
+	__asm__ __volatile__(
+	"ldr	%0, [%1], #4		@ ip_fast_csum		\n\
+	ldr	%3, [%1], #4					\n\
+	sub	%2, %2, #5					\n\
+	adds	%0, %0, %3					\n\
+	ldr	%3, [%1], #4					\n\
+	adcs	%0, %0, %3					\n\
+	ldr	%3, [%1], #4					\n\
+1:	adcs	%0, %0, %3					\n\
+	ldr	%3, [%1], #4					\n\
+	tst	%2, #15			@ do this carefully	\n\
+	subne	%2, %2, #1		@ without destroying	\n\
+	bne	1b			@ the carry flag	\n\
+	adcs	%0, %0, %3					\n\
+	adc	%0, %0, #0"
+	: "=r" (sum), "=r" (iph), "=r" (ihl), "=r" (tmp1)
+	: "1" (iph), "2" (ihl)
+	: "cc", "memory");
+	return csum_fold(sum);
+}
+
+static inline __wsum
+csum_tcpudp_nofold(__be32 saddr, __be32 daddr, unsigned short len,
+		   unsigned short proto, __wsum sum)
+{
+	u32 lenprot = len | proto << 16;
+	if (__builtin_constant_p(sum) && sum == 0) {
+		__asm__(
+		"adds	%0, %1, %2	@ csum_tcpudp_nofold0	\n\t"
+#ifdef __ARMEB__
+		"adcs	%0, %0, %3				\n\t"
+#else
+		"adcs	%0, %0, %3, ror #8			\n\t"
+#endif
+		"adc	%0, %0, #0"
+		: "=&r" (sum)
+		: "r" (daddr), "r" (saddr), "r" (lenprot)
+		: "cc");
+	} else {
+		__asm__(
+		"adds	%0, %1, %2	@ csum_tcpudp_nofold	\n\t"
+		"adcs	%0, %0, %3				\n\t"
+#ifdef __ARMEB__
+		"adcs	%0, %0, %4				\n\t"
+#else
+		"adcs	%0, %0, %4, ror #8			\n\t"
+#endif
+		"adc	%0, %0, #0"
+		: "=&r"(sum)
+		: "r" (sum), "r" (daddr), "r" (saddr), "r" (lenprot)
+		: "cc");
+	}
+	return sum;
+}	
+/*
+ * computes the checksum of the TCP/UDP pseudo-header
+ * returns a 16-bit checksum, already complemented
+ */
+static inline __sum16
+csum_tcpudp_magic(__be32 saddr, __be32 daddr, unsigned short len,
+		  unsigned short proto, __wsum sum)
+{
+	return csum_fold(csum_tcpudp_nofold(saddr, daddr, len, proto, sum));
+}
+
+
+/*
+ * this routine is used for miscellaneous IP-like checksums, mainly
+ * in icmp.c
+ */
+static inline __sum16
+ip_compute_csum(const void *buff, int len)
+{
+	return csum_fold(csum_partial(buff, len, 0));
+}
+
+#define _HAVE_ARCH_IPV6_CSUM
+extern __wsum
+__csum_ipv6_magic(const struct in6_addr *saddr, const struct in6_addr *daddr, __be32 len,
+		__be32 proto, __wsum sum);
+
+static inline __sum16
+csum_ipv6_magic(const struct in6_addr *saddr, const struct in6_addr *daddr, __u32 len,
+		unsigned short proto, __wsum sum)
+{
+	return csum_fold(__csum_ipv6_magic(saddr, daddr, htonl(len),
+					   htonl(proto), sum));
+}
+#endif
diff --git a/arch/arm/include/asm/clkdev.h b/arch/arm/include/asm/clkdev.h
new file mode 100644
index 000000000..4e8a4b27d
--- /dev/null
+++ b/arch/arm/include/asm/clkdev.h
@@ -0,0 +1,31 @@
+/*
+ *  arch/arm/include/asm/clkdev.h
+ *
+ *  Copyright (C) 2008 Russell King.
+ *
+ * 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.
+ *
+ * Helper for the clk API to assist looking up a struct clk.
+ */
+#ifndef __ASM_CLKDEV_H
+#define __ASM_CLKDEV_H
+
+#include <linux/slab.h>
+
+#ifndef CONFIG_COMMON_CLK
+#ifdef CONFIG_HAVE_MACH_CLKDEV
+#include <mach/clkdev.h>
+#else
+#define __clk_get(clk)	({ 1; })
+#define __clk_put(clk)	do { } while (0)
+#endif
+#endif
+
+static inline struct clk_lookup_alloc *__clkdev_alloc(size_t size)
+{
+	return kzalloc(size, GFP_KERNEL);
+}
+
+#endif
diff --git a/arch/arm/include/asm/cmpxchg.h b/arch/arm/include/asm/cmpxchg.h
new file mode 100644
index 000000000..abb2c3769
--- /dev/null
+++ b/arch/arm/include/asm/cmpxchg.h
@@ -0,0 +1,288 @@
+#ifndef __ASM_ARM_CMPXCHG_H
+#define __ASM_ARM_CMPXCHG_H
+
+#include <linux/irqflags.h>
+#include <linux/prefetch.h>
+#include <asm/barrier.h>
+
+#if defined(CONFIG_CPU_SA1100) || defined(CONFIG_CPU_SA110)
+/*
+ * On the StrongARM, "swp" is terminally broken since it bypasses the
+ * cache totally.  This means that the cache becomes inconsistent, and,
+ * since we use normal loads/stores as well, this is really bad.
+ * Typically, this causes oopsen in filp_close, but could have other,
+ * more disastrous effects.  There are two work-arounds:
+ *  1. Disable interrupts and emulate the atomic swap
+ *  2. Clean the cache, perform atomic swap, flush the cache
+ *
+ * We choose (1) since its the "easiest" to achieve here and is not
+ * dependent on the processor type.
+ *
+ * NOTE that this solution won't work on an SMP system, so explcitly
+ * forbid it here.
+ */
+#define swp_is_buggy
+#endif
+
+static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size)
+{
+	extern void __bad_xchg(volatile void *, int);
+	unsigned long ret;
+#ifdef swp_is_buggy
+	unsigned long flags;
+#endif
+#if __LINUX_ARM_ARCH__ >= 6
+	unsigned int tmp;
+#endif
+
+	smp_mb();
+	prefetchw((const void *)ptr);
+
+	switch (size) {
+#if __LINUX_ARM_ARCH__ >= 6
+	case 1:
+		asm volatile("@	__xchg1\n"
+		"1:	ldrexb	%0, [%3]\n"
+		"	strexb	%1, %2, [%3]\n"
+		"	teq	%1, #0\n"
+		"	bne	1b"
+			: "=&r" (ret), "=&r" (tmp)
+			: "r" (x), "r" (ptr)
+			: "memory", "cc");
+		break;
+	case 4:
+		asm volatile("@	__xchg4\n"
+		"1:	ldrex	%0, [%3]\n"
+		"	strex	%1, %2, [%3]\n"
+		"	teq	%1, #0\n"
+		"	bne	1b"
+			: "=&r" (ret), "=&r" (tmp)
+			: "r" (x), "r" (ptr)
+			: "memory", "cc");
+		break;
+#elif defined(swp_is_buggy)
+#ifdef CONFIG_SMP
+#error SMP is not supported on this platform
+#endif
+	case 1:
+		raw_local_irq_save(flags);
+		ret = *(volatile unsigned char *)ptr;
+		*(volatile unsigned char *)ptr = x;
+		raw_local_irq_restore(flags);
+		break;
+
+	case 4:
+		raw_local_irq_save(flags);
+		ret = *(volatile unsigned long *)ptr;
+		*(volatile unsigned long *)ptr = x;
+		raw_local_irq_restore(flags);
+		break;
+#else
+	case 1:
+		asm volatile("@	__xchg1\n"
+		"	swpb	%0, %1, [%2]"
+			: "=&r" (ret)
+			: "r" (x), "r" (ptr)
+			: "memory", "cc");
+		break;
+	case 4:
+		asm volatile("@	__xchg4\n"
+		"	swp	%0, %1, [%2]"
+			: "=&r" (ret)
+			: "r" (x), "r" (ptr)
+			: "memory", "cc");
+		break;
+#endif
+	default:
+		__bad_xchg(ptr, size), ret = 0;
+		break;
+	}
+	smp_mb();
+
+	return ret;
+}
+
+#define xchg(ptr,x) \
+	((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr))))
+
+#include <asm-generic/cmpxchg-local.h>
+
+#if __LINUX_ARM_ARCH__ < 6
+/* min ARCH < ARMv6 */
+
+#ifdef CONFIG_SMP
+#error "SMP is not supported on this platform"
+#endif
+
+/*
+ * cmpxchg_local and cmpxchg64_local are atomic wrt current CPU. Always make
+ * them available.
+ */
+#define cmpxchg_local(ptr, o, n)				  	       \
+	((__typeof__(*(ptr)))__cmpxchg_local_generic((ptr), (unsigned long)(o),\
+			(unsigned long)(n), sizeof(*(ptr))))
+#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
+
+#ifndef CONFIG_SMP
+#include <asm-generic/cmpxchg.h>
+#endif
+
+#else	/* min ARCH >= ARMv6 */
+
+extern void __bad_cmpxchg(volatile void *ptr, int size);
+
+/*
+ * cmpxchg only support 32-bits operands on ARMv6.
+ */
+
+static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
+				      unsigned long new, int size)
+{
+	unsigned long oldval, res;
+
+	prefetchw((const void *)ptr);
+
+	switch (size) {
+#ifndef CONFIG_CPU_V6	/* min ARCH >= ARMv6K */
+	case 1:
+		do {
+			asm volatile("@ __cmpxchg1\n"
+			"	ldrexb	%1, [%2]\n"
+			"	mov	%0, #0\n"
+			"	teq	%1, %3\n"
+			"	strexbeq %0, %4, [%2]\n"
+				: "=&r" (res), "=&r" (oldval)
+				: "r" (ptr), "Ir" (old), "r" (new)
+				: "memory", "cc");
+		} while (res);
+		break;
+	case 2:
+		do {
+			asm volatile("@ __cmpxchg1\n"
+			"	ldrexh	%1, [%2]\n"
+			"	mov	%0, #0\n"
+			"	teq	%1, %3\n"
+			"	strexheq %0, %4, [%2]\n"
+				: "=&r" (res), "=&r" (oldval)
+				: "r" (ptr), "Ir" (old), "r" (new)
+				: "memory", "cc");
+		} while (res);
+		break;
+#endif
+	case 4:
+		do {
+			asm volatile("@ __cmpxchg4\n"
+			"	ldrex	%1, [%2]\n"
+			"	mov	%0, #0\n"
+			"	teq	%1, %3\n"
+			"	strexeq %0, %4, [%2]\n"
+				: "=&r" (res), "=&r" (oldval)
+				: "r" (ptr), "Ir" (old), "r" (new)
+				: "memory", "cc");
+		} while (res);
+		break;
+	default:
+		__bad_cmpxchg(ptr, size);
+		oldval = 0;
+	}
+
+	return oldval;
+}
+
+static inline unsigned long __cmpxchg_mb(volatile void *ptr, unsigned long old,
+					 unsigned long new, int size)
+{
+	unsigned long ret;
+
+	smp_mb();
+	ret = __cmpxchg(ptr, old, new, size);
+	smp_mb();
+
+	return ret;
+}
+
+#define cmpxchg(ptr,o,n)						\
+	((__typeof__(*(ptr)))__cmpxchg_mb((ptr),			\
+					  (unsigned long)(o),		\
+					  (unsigned long)(n),		\
+					  sizeof(*(ptr))))
+
+static inline unsigned long __cmpxchg_local(volatile void *ptr,
+					    unsigned long old,
+					    unsigned long new, int size)
+{
+	unsigned long ret;
+
+	switch (size) {
+#ifdef CONFIG_CPU_V6	/* min ARCH == ARMv6 */
+	case 1:
+	case 2:
+		ret = __cmpxchg_local_generic(ptr, old, new, size);
+		break;
+#endif
+	default:
+		ret = __cmpxchg(ptr, old, new, size);
+	}
+
+	return ret;
+}
+
+static inline unsigned long long __cmpxchg64(unsigned long long *ptr,
+					     unsigned long long old,
+					     unsigned long long new)
+{
+	unsigned long long oldval;
+	unsigned long res;
+
+	prefetchw(ptr);
+
+	__asm__ __volatile__(
+"1:	ldrexd		%1, %H1, [%3]\n"
+"	teq		%1, %4\n"
+"	teqeq		%H1, %H4\n"
+"	bne		2f\n"
+"	strexd		%0, %5, %H5, [%3]\n"
+"	teq		%0, #0\n"
+"	bne		1b\n"
+"2:"
+	: "=&r" (res), "=&r" (oldval), "+Qo" (*ptr)
+	: "r" (ptr), "r" (old), "r" (new)
+	: "cc");
+
+	return oldval;
+}
+
+static inline unsigned long long __cmpxchg64_mb(unsigned long long *ptr,
+						unsigned long long old,
+						unsigned long long new)
+{
+	unsigned long long ret;
+
+	smp_mb();
+	ret = __cmpxchg64(ptr, old, new);
+	smp_mb();
+
+	return ret;
+}
+
+#define cmpxchg_local(ptr,o,n)						\
+	((__typeof__(*(ptr)))__cmpxchg_local((ptr),			\
+				       (unsigned long)(o),		\
+				       (unsigned long)(n),		\
+				       sizeof(*(ptr))))
+
+#define cmpxchg64(ptr, o, n)						\
+	((__typeof__(*(ptr)))__cmpxchg64_mb((ptr),			\
+					(unsigned long long)(o),	\
+					(unsigned long long)(n)))
+
+#define cmpxchg64_relaxed(ptr, o, n)					\
+	((__typeof__(*(ptr)))__cmpxchg64((ptr),				\
+					(unsigned long long)(o),	\
+					(unsigned long long)(n)))
+
+#define cmpxchg64_local(ptr, o, n)	cmpxchg64_relaxed((ptr), (o), (n))
+
+#endif	/* __LINUX_ARM_ARCH__ >= 6 */
+
+#endif /* __ASM_ARM_CMPXCHG_H */
diff --git a/arch/arm/include/asm/compiler.h b/arch/arm/include/asm/compiler.h
new file mode 100644
index 000000000..29fe85e59
--- /dev/null
+++ b/arch/arm/include/asm/compiler.h
@@ -0,0 +1,28 @@
+#ifndef __ASM_ARM_COMPILER_H
+#define __ASM_ARM_COMPILER_H
+
+/*
+ * This is used to ensure the compiler did actually allocate the register we
+ * asked it for some inline assembly sequences.  Apparently we can't trust
+ * the compiler from one version to another so a bit of paranoia won't hurt.
+ * This string is meant to be concatenated with the inline asm string and
+ * will cause compilation to stop on mismatch.
+ * (for details, see gcc PR 15089)
+ * For compatibility with clang, we have to specifically take the equivalence
+ * of 'r11' <-> 'fp' and 'r12' <-> 'ip' into account as well.
+ */
+#define __asmeq(x, y)				\
+	".ifnc " x "," y "; "			\
+	  ".ifnc " x y ",fpr11; " 		\
+	    ".ifnc " x y ",r11fp; "		\
+	      ".ifnc " x y ",ipr12; " 		\
+	        ".ifnc " x y ",r12ip; "		\
+	          ".err; "			\
+	        ".endif; "			\
+	      ".endif; "			\
+	    ".endif; "				\
+	  ".endif; "				\
+	".endif\n\t"
+
+
+#endif /* __ASM_ARM_COMPILER_H */
diff --git a/arch/arm/include/asm/cp15.h b/arch/arm/include/asm/cp15.h
new file mode 100644
index 000000000..c3f11524f
--- /dev/null
+++ b/arch/arm/include/asm/cp15.h
@@ -0,0 +1,119 @@
+#ifndef __ASM_ARM_CP15_H
+#define __ASM_ARM_CP15_H
+
+#include <asm/barrier.h>
+
+/*
+ * CR1 bits (CP#15 CR1)
+ */
+#define CR_M	(1 << 0)	/* MMU enable				*/
+#define CR_A	(1 << 1)	/* Alignment abort enable		*/
+#define CR_C	(1 << 2)	/* Dcache enable			*/
+#define CR_W	(1 << 3)	/* Write buffer enable			*/
+#define CR_P	(1 << 4)	/* 32-bit exception handler		*/
+#define CR_D	(1 << 5)	/* 32-bit data address range		*/
+#define CR_L	(1 << 6)	/* Implementation defined		*/
+#define CR_B	(1 << 7)	/* Big endian				*/
+#define CR_S	(1 << 8)	/* System MMU protection		*/
+#define CR_R	(1 << 9)	/* ROM MMU protection			*/
+#define CR_F	(1 << 10)	/* Implementation defined		*/
+#define CR_Z	(1 << 11)	/* Implementation defined		*/
+#define CR_I	(1 << 12)	/* Icache enable			*/
+#define CR_V	(1 << 13)	/* Vectors relocated to 0xffff0000	*/
+#define CR_RR	(1 << 14)	/* Round Robin cache replacement	*/
+#define CR_L4	(1 << 15)	/* LDR pc can set T bit			*/
+#define CR_DT	(1 << 16)
+#ifdef CONFIG_MMU
+#define CR_HA	(1 << 17)	/* Hardware management of Access Flag   */
+#else
+#define CR_BR	(1 << 17)	/* MPU Background region enable (PMSA)  */
+#endif
+#define CR_IT	(1 << 18)
+#define CR_ST	(1 << 19)
+#define CR_FI	(1 << 21)	/* Fast interrupt (lower latency mode)	*/
+#define CR_U	(1 << 22)	/* Unaligned access operation		*/
+#define CR_XP	(1 << 23)	/* Extended page tables			*/
+#define CR_VE	(1 << 24)	/* Vectored interrupts			*/
+#define CR_EE	(1 << 25)	/* Exception (Big) Endian		*/
+#define CR_TRE	(1 << 28)	/* TEX remap enable			*/
+#define CR_AFE	(1 << 29)	/* Access flag enable			*/
+#define CR_TE	(1 << 30)	/* Thumb exception enable		*/
+
+#ifndef __ASSEMBLY__
+
+#if __LINUX_ARM_ARCH__ >= 4
+#define vectors_high()	(get_cr() & CR_V)
+#else
+#define vectors_high()	(0)
+#endif
+
+#ifdef CONFIG_CPU_CP15
+
+extern unsigned long cr_alignment;	/* defined in entry-armv.S */
+
+static inline unsigned long get_cr(void)
+{
+	unsigned long val;
+	asm("mrc p15, 0, %0, c1, c0, 0	@ get CR" : "=r" (val) : : "cc");
+	return val;
+}
+
+static inline void set_cr(unsigned long val)
+{
+	asm volatile("mcr p15, 0, %0, c1, c0, 0	@ set CR"
+	  : : "r" (val) : "cc");
+	isb();
+}
+
+static inline unsigned int get_auxcr(void)
+{
+	unsigned int val;
+	asm("mrc p15, 0, %0, c1, c0, 1	@ get AUXCR" : "=r" (val));
+	return val;
+}
+
+static inline void set_auxcr(unsigned int val)
+{
+	asm volatile("mcr p15, 0, %0, c1, c0, 1	@ set AUXCR"
+	  : : "r" (val));
+	isb();
+}
+
+#define CPACC_FULL(n)		(3 << (n * 2))
+#define CPACC_SVC(n)		(1 << (n * 2))
+#define CPACC_DISABLE(n)	(0 << (n * 2))
+
+static inline unsigned int get_copro_access(void)
+{
+	unsigned int val;
+	asm("mrc p15, 0, %0, c1, c0, 2 @ get copro access"
+	  : "=r" (val) : : "cc");
+	return val;
+}
+
+static inline void set_copro_access(unsigned int val)
+{
+	asm volatile("mcr p15, 0, %0, c1, c0, 2 @ set copro access"
+	  : : "r" (val) : "cc");
+	isb();
+}
+
+#else /* ifdef CONFIG_CPU_CP15 */
+
+/*
+ * cr_alignment is tightly coupled to cp15 (at least in the minds of the
+ * developers). Yielding 0 for machines without a cp15 (and making it
+ * read-only) is fine for most cases and saves quite some #ifdeffery.
+ */
+#define cr_alignment	UL(0)
+
+static inline unsigned long get_cr(void)
+{
+	return 0;
+}
+
+#endif /* ifdef CONFIG_CPU_CP15 / else */
+
+#endif /* ifndef __ASSEMBLY__ */
+
+#endif
diff --git a/arch/arm/include/asm/cpu.h b/arch/arm/include/asm/cpu.h
new file mode 100644
index 000000000..2744f0602
--- /dev/null
+++ b/arch/arm/include/asm/cpu.h
@@ -0,0 +1,26 @@
+/*
+ *  arch/arm/include/asm/cpu.h
+ *
+ *  Copyright (C) 2004-2005 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.
+ */
+#ifndef __ASM_ARM_CPU_H
+#define __ASM_ARM_CPU_H
+
+#include <linux/percpu.h>
+#include <linux/cpu.h>
+
+struct cpuinfo_arm {
+	struct cpu	cpu;
+	u32		cpuid;
+#ifdef CONFIG_SMP
+	unsigned int	loops_per_jiffy;
+#endif
+};
+
+DECLARE_PER_CPU(struct cpuinfo_arm, cpu_data);
+
+#endif
diff --git a/arch/arm/include/asm/cpuidle.h b/arch/arm/include/asm/cpuidle.h
new file mode 100644
index 000000000..0f8424924
--- /dev/null
+++ b/arch/arm/include/asm/cpuidle.h
@@ -0,0 +1,51 @@
+#ifndef __ASM_ARM_CPUIDLE_H
+#define __ASM_ARM_CPUIDLE_H
+
+#include <asm/proc-fns.h>
+
+#ifdef CONFIG_CPU_IDLE
+extern int arm_cpuidle_simple_enter(struct cpuidle_device *dev,
+		struct cpuidle_driver *drv, int index);
+#else
+static inline int arm_cpuidle_simple_enter(struct cpuidle_device *dev,
+		struct cpuidle_driver *drv, int index) { return -ENODEV; }
+#endif
+
+/* Common ARM WFI state */
+#define ARM_CPUIDLE_WFI_STATE_PWR(p) {\
+	.enter                  = arm_cpuidle_simple_enter,\
+	.exit_latency           = 1,\
+	.target_residency       = 1,\
+	.power_usage		= p,\
+	.name                   = "WFI",\
+	.desc                   = "ARM WFI",\
+}
+
+/*
+ * in case power_specified == 1, give a default WFI power value needed
+ * by some governors
+ */
+#define ARM_CPUIDLE_WFI_STATE ARM_CPUIDLE_WFI_STATE_PWR(UINT_MAX)
+
+struct device_node;
+
+struct cpuidle_ops {
+	int (*suspend)(int cpu, unsigned long arg);
+	int (*init)(struct device_node *, int cpu);
+};
+
+struct of_cpuidle_method {
+	const char *method;
+	struct cpuidle_ops *ops;
+};
+
+#define CPUIDLE_METHOD_OF_DECLARE(name, _method, _ops)			\
+	static const struct of_cpuidle_method __cpuidle_method_of_table_##name \
+	__used __section(__cpuidle_method_of_table)			\
+	= { .method = _method, .ops = _ops }
+
+extern int arm_cpuidle_suspend(int index);
+
+extern int arm_cpuidle_init(int cpu);
+
+#endif
diff --git a/arch/arm/include/asm/cputype.h b/arch/arm/include/asm/cputype.h
new file mode 100644
index 000000000..85e374f87
--- /dev/null
+++ b/arch/arm/include/asm/cputype.h
@@ -0,0 +1,272 @@
+#ifndef __ASM_ARM_CPUTYPE_H
+#define __ASM_ARM_CPUTYPE_H
+
+#include <linux/stringify.h>
+#include <linux/kernel.h>
+
+#define CPUID_ID	0
+#define CPUID_CACHETYPE	1
+#define CPUID_TCM	2
+#define CPUID_TLBTYPE	3
+#define CPUID_MPUIR	4
+#define CPUID_MPIDR	5
+#define CPUID_REVIDR	6
+
+#ifdef CONFIG_CPU_V7M
+#define CPUID_EXT_PFR0	0x40
+#define CPUID_EXT_PFR1	0x44
+#define CPUID_EXT_DFR0	0x48
+#define CPUID_EXT_AFR0	0x4c
+#define CPUID_EXT_MMFR0	0x50
+#define CPUID_EXT_MMFR1	0x54
+#define CPUID_EXT_MMFR2	0x58
+#define CPUID_EXT_MMFR3	0x5c
+#define CPUID_EXT_ISAR0	0x60
+#define CPUID_EXT_ISAR1	0x64
+#define CPUID_EXT_ISAR2	0x68
+#define CPUID_EXT_ISAR3	0x6c
+#define CPUID_EXT_ISAR4	0x70
+#define CPUID_EXT_ISAR5	0x74
+#else
+#define CPUID_EXT_PFR0	"c1, 0"
+#define CPUID_EXT_PFR1	"c1, 1"
+#define CPUID_EXT_DFR0	"c1, 2"
+#define CPUID_EXT_AFR0	"c1, 3"
+#define CPUID_EXT_MMFR0	"c1, 4"
+#define CPUID_EXT_MMFR1	"c1, 5"
+#define CPUID_EXT_MMFR2	"c1, 6"
+#define CPUID_EXT_MMFR3	"c1, 7"
+#define CPUID_EXT_ISAR0	"c2, 0"
+#define CPUID_EXT_ISAR1	"c2, 1"
+#define CPUID_EXT_ISAR2	"c2, 2"
+#define CPUID_EXT_ISAR3	"c2, 3"
+#define CPUID_EXT_ISAR4	"c2, 4"
+#define CPUID_EXT_ISAR5	"c2, 5"
+#endif
+
+#define MPIDR_SMP_BITMASK (0x3 << 30)
+#define MPIDR_SMP_VALUE (0x2 << 30)
+
+#define MPIDR_MT_BITMASK (0x1 << 24)
+
+#define MPIDR_HWID_BITMASK 0xFFFFFF
+
+#define MPIDR_INVALID (~MPIDR_HWID_BITMASK)
+
+#define MPIDR_LEVEL_BITS 8
+#define MPIDR_LEVEL_MASK ((1 << MPIDR_LEVEL_BITS) - 1)
+
+#define MPIDR_AFFINITY_LEVEL(mpidr, level) \
+	((mpidr >> (MPIDR_LEVEL_BITS * level)) & MPIDR_LEVEL_MASK)
+
+#define ARM_CPU_IMP_ARM			0x41
+#define ARM_CPU_IMP_INTEL		0x69
+
+/* ARM implemented processors */
+#define ARM_CPU_PART_ARM1136		0x4100b360
+#define ARM_CPU_PART_ARM1156		0x4100b560
+#define ARM_CPU_PART_ARM1176		0x4100b760
+#define ARM_CPU_PART_ARM11MPCORE	0x4100b020
+#define ARM_CPU_PART_CORTEX_A8		0x4100c080
+#define ARM_CPU_PART_CORTEX_A9		0x4100c090
+#define ARM_CPU_PART_CORTEX_A5		0x4100c050
+#define ARM_CPU_PART_CORTEX_A7		0x4100c070
+#define ARM_CPU_PART_CORTEX_A12		0x4100c0d0
+#define ARM_CPU_PART_CORTEX_A17		0x4100c0e0
+#define ARM_CPU_PART_CORTEX_A15		0x4100c0f0
+#define ARM_CPU_PART_MASK		0xff00fff0
+
+#define ARM_CPU_XSCALE_ARCH_MASK	0xe000
+#define ARM_CPU_XSCALE_ARCH_V1		0x2000
+#define ARM_CPU_XSCALE_ARCH_V2		0x4000
+#define ARM_CPU_XSCALE_ARCH_V3		0x6000
+
+extern unsigned int processor_id;
+
+#ifdef CONFIG_CPU_CP15
+#define read_cpuid(reg)							\
+	({								\
+		unsigned int __val;					\
+		asm("mrc	p15, 0, %0, c0, c0, " __stringify(reg)	\
+		    : "=r" (__val)					\
+		    :							\
+		    : "cc");						\
+		__val;							\
+	})
+
+/*
+ * The memory clobber prevents gcc 4.5 from reordering the mrc before
+ * any is_smp() tests, which can cause undefined instruction aborts on
+ * ARM1136 r0 due to the missing extended CP15 registers.
+ */
+#define read_cpuid_ext(ext_reg)						\
+	({								\
+		unsigned int __val;					\
+		asm("mrc	p15, 0, %0, c0, " ext_reg		\
+		    : "=r" (__val)					\
+		    :							\
+		    : "memory");					\
+		__val;							\
+	})
+
+#elif defined(CONFIG_CPU_V7M)
+
+#include <asm/io.h>
+#include <asm/v7m.h>
+
+#define read_cpuid(reg)							\
+	({								\
+		WARN_ON_ONCE(1);					\
+		0;							\
+	})
+
+static inline unsigned int __attribute_const__ read_cpuid_ext(unsigned offset)
+{
+	return readl(BASEADDR_V7M_SCB + offset);
+}
+
+#else /* ifdef CONFIG_CPU_CP15 / elif defined (CONFIG_CPU_V7M) */
+
+/*
+ * read_cpuid and read_cpuid_ext should only ever be called on machines that
+ * have cp15 so warn on other usages.
+ */
+#define read_cpuid(reg)							\
+	({								\
+		WARN_ON_ONCE(1);					\
+		0;							\
+	})
+
+#define read_cpuid_ext(reg) read_cpuid(reg)
+
+#endif /* ifdef CONFIG_CPU_CP15 / else */
+
+#ifdef CONFIG_CPU_CP15
+/*
+ * The CPU ID never changes at run time, so we might as well tell the
+ * compiler that it's constant.  Use this function to read the CPU ID
+ * rather than directly reading processor_id or read_cpuid() directly.
+ */
+static inline unsigned int __attribute_const__ read_cpuid_id(void)
+{
+	return read_cpuid(CPUID_ID);
+}
+
+#elif defined(CONFIG_CPU_V7M)
+
+static inline unsigned int __attribute_const__ read_cpuid_id(void)
+{
+	return readl(BASEADDR_V7M_SCB + V7M_SCB_CPUID);
+}
+
+#else /* ifdef CONFIG_CPU_CP15 / elif defined(CONFIG_CPU_V7M) */
+
+static inline unsigned int __attribute_const__ read_cpuid_id(void)
+{
+	return processor_id;
+}
+
+#endif /* ifdef CONFIG_CPU_CP15 / else */
+
+static inline unsigned int __attribute_const__ read_cpuid_implementor(void)
+{
+	return (read_cpuid_id() & 0xFF000000) >> 24;
+}
+
+/*
+ * The CPU part number is meaningless without referring to the CPU
+ * implementer: implementers are free to define their own part numbers
+ * which are permitted to clash with other implementer part numbers.
+ */
+static inline unsigned int __attribute_const__ read_cpuid_part(void)
+{
+	return read_cpuid_id() & ARM_CPU_PART_MASK;
+}
+
+static inline unsigned int __attribute_const__ __deprecated read_cpuid_part_number(void)
+{
+	return read_cpuid_id() & 0xFFF0;
+}
+
+static inline unsigned int __attribute_const__ xscale_cpu_arch_version(void)
+{
+	return read_cpuid_id() & ARM_CPU_XSCALE_ARCH_MASK;
+}
+
+static inline unsigned int __attribute_const__ read_cpuid_cachetype(void)
+{
+	return read_cpuid(CPUID_CACHETYPE);
+}
+
+static inline unsigned int __attribute_const__ read_cpuid_tcmstatus(void)
+{
+	return read_cpuid(CPUID_TCM);
+}
+
+static inline unsigned int __attribute_const__ read_cpuid_mpidr(void)
+{
+	return read_cpuid(CPUID_MPIDR);
+}
+
+/*
+ * Intel's XScale3 core supports some v6 features (supersections, L2)
+ * but advertises itself as v5 as it does not support the v6 ISA.  For
+ * this reason, we need a way to explicitly test for this type of CPU.
+ */
+#ifndef CONFIG_CPU_XSC3
+#define cpu_is_xsc3()	0
+#else
+static inline int cpu_is_xsc3(void)
+{
+	unsigned int id;
+	id = read_cpuid_id() & 0xffffe000;
+	/* It covers both Intel ID and Marvell ID */
+	if ((id == 0x69056000) || (id == 0x56056000))
+		return 1;
+
+	return 0;
+}
+#endif
+
+#if !defined(CONFIG_CPU_XSCALE) && !defined(CONFIG_CPU_XSC3)
+#define	cpu_is_xscale()	0
+#else
+#define	cpu_is_xscale()	1
+#endif
+
+/*
+ * Marvell's PJ4 and PJ4B cores are based on V7 version,
+ * but require a specical sequence for enabling coprocessors.
+ * For this reason, we need a way to distinguish them.
+ */
+#if defined(CONFIG_CPU_PJ4) || defined(CONFIG_CPU_PJ4B)
+static inline int cpu_is_pj4(void)
+{
+	unsigned int id;
+
+	id = read_cpuid_id();
+	if ((id & 0xff0fff00) == 0x560f5800)
+		return 1;
+
+	return 0;
+}
+#else
+#define cpu_is_pj4()	0
+#endif
+
+static inline int __attribute_const__ cpuid_feature_extract_field(u32 features,
+								  int field)
+{
+	int feature = (features >> field) & 15;
+
+	/* feature registers are signed values */
+	if (feature > 8)
+		feature -= 16;
+
+	return feature;
+}
+
+#define cpuid_feature_extract(reg, field) \
+	cpuid_feature_extract_field(read_cpuid_ext(reg), field)
+
+#endif
diff --git a/arch/arm/include/asm/cti.h b/arch/arm/include/asm/cti.h
new file mode 100644
index 000000000..2381199ac
--- /dev/null
+++ b/arch/arm/include/asm/cti.h
@@ -0,0 +1,159 @@
+#ifndef __ASMARM_CTI_H
+#define __ASMARM_CTI_H
+
+#include	<asm/io.h>
+#include	<asm/hardware/coresight.h>
+
+/* The registers' definition is from section 3.2 of
+ * Embedded Cross Trigger Revision: r0p0
+ */
+#define		CTICONTROL		0x000
+#define		CTISTATUS		0x004
+#define		CTILOCK			0x008
+#define		CTIPROTECTION		0x00C
+#define		CTIINTACK		0x010
+#define		CTIAPPSET		0x014
+#define		CTIAPPCLEAR		0x018
+#define		CTIAPPPULSE		0x01c
+#define		CTIINEN			0x020
+#define		CTIOUTEN		0x0A0
+#define		CTITRIGINSTATUS		0x130
+#define		CTITRIGOUTSTATUS	0x134
+#define		CTICHINSTATUS		0x138
+#define		CTICHOUTSTATUS		0x13c
+#define		CTIPERIPHID0		0xFE0
+#define		CTIPERIPHID1		0xFE4
+#define		CTIPERIPHID2		0xFE8
+#define		CTIPERIPHID3		0xFEC
+#define		CTIPCELLID0		0xFF0
+#define		CTIPCELLID1		0xFF4
+#define		CTIPCELLID2		0xFF8
+#define		CTIPCELLID3		0xFFC
+
+/* The below are from section 3.6.4 of
+ * CoreSight v1.0 Architecture Specification
+ */
+#define		LOCKACCESS		0xFB0
+#define		LOCKSTATUS		0xFB4
+
+/**
+ * struct cti - cross trigger interface struct
+ * @base: mapped virtual address for the cti base
+ * @irq: irq number for the cti
+ * @trig_out_for_irq: triger out number which will cause
+ *	the @irq happen
+ *
+ * cti struct used to operate cti registers.
+ */
+struct cti {
+	void __iomem *base;
+	int irq;
+	int trig_out_for_irq;
+};
+
+/**
+ * cti_init - initialize the cti instance
+ * @cti: cti instance
+ * @base: mapped virtual address for the cti base
+ * @irq: irq number for the cti
+ * @trig_out: triger out number which will cause
+ *	the @irq happen
+ *
+ * called by machine code to pass the board dependent
+ * @base, @irq and @trig_out to cti.
+ */
+static inline void cti_init(struct cti *cti,
+	void __iomem *base, int irq, int trig_out)
+{
+	cti->base = base;
+	cti->irq  = irq;
+	cti->trig_out_for_irq = trig_out;
+}
+
+/**
+ * cti_map_trigger - use the @chan to map @trig_in to @trig_out
+ * @cti: cti instance
+ * @trig_in: trigger in number
+ * @trig_out: trigger out number
+ * @channel: channel number
+ *
+ * This function maps one trigger in of @trig_in to one trigger
+ * out of @trig_out using the channel @chan.
+ */
+static inline void cti_map_trigger(struct cti *cti,
+	int trig_in, int trig_out, int chan)
+{
+	void __iomem *base = cti->base;
+	unsigned long val;
+
+	val = __raw_readl(base + CTIINEN + trig_in * 4);
+	val |= BIT(chan);
+	__raw_writel(val, base + CTIINEN + trig_in * 4);
+
+	val = __raw_readl(base + CTIOUTEN + trig_out * 4);
+	val |= BIT(chan);
+	__raw_writel(val, base + CTIOUTEN + trig_out * 4);
+}
+
+/**
+ * cti_enable - enable the cti module
+ * @cti: cti instance
+ *
+ * enable the cti module
+ */
+static inline void cti_enable(struct cti *cti)
+{
+	__raw_writel(0x1, cti->base + CTICONTROL);
+}
+
+/**
+ * cti_disable - disable the cti module
+ * @cti: cti instance
+ *
+ * enable the cti module
+ */
+static inline void cti_disable(struct cti *cti)
+{
+	__raw_writel(0, cti->base + CTICONTROL);
+}
+
+/**
+ * cti_irq_ack - clear the cti irq
+ * @cti: cti instance
+ *
+ * clear the cti irq
+ */
+static inline void cti_irq_ack(struct cti *cti)
+{
+	void __iomem *base = cti->base;
+	unsigned long val;
+
+	val = __raw_readl(base + CTIINTACK);
+	val |= BIT(cti->trig_out_for_irq);
+	__raw_writel(val, base + CTIINTACK);
+}
+
+/**
+ * cti_unlock - unlock cti module
+ * @cti: cti instance
+ *
+ * unlock the cti module, or else any writes to the cti
+ * module is not allowed.
+ */
+static inline void cti_unlock(struct cti *cti)
+{
+	__raw_writel(CS_LAR_KEY, cti->base + LOCKACCESS);
+}
+
+/**
+ * cti_lock - lock cti module
+ * @cti: cti instance
+ *
+ * lock the cti module, so any writes to the cti
+ * module will be not allowed.
+ */
+static inline void cti_lock(struct cti *cti)
+{
+	__raw_writel(~CS_LAR_KEY, cti->base + LOCKACCESS);
+}
+#endif
diff --git a/arch/arm/include/asm/dcc.h b/arch/arm/include/asm/dcc.h
new file mode 100644
index 000000000..b74899de0
--- /dev/null
+++ b/arch/arm/include/asm/dcc.h
@@ -0,0 +1,41 @@
+/* Copyright (c) 2010, 2014 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.
+ */
+
+#include <asm/barrier.h>
+
+static inline u32 __dcc_getstatus(void)
+{
+	u32 __ret;
+	asm volatile("mrc p14, 0, %0, c0, c1, 0	@ read comms ctrl reg"
+		: "=r" (__ret) : : "cc");
+
+	return __ret;
+}
+
+static inline char __dcc_getchar(void)
+{
+	char __c;
+
+	asm volatile("mrc p14, 0, %0, c0, c5, 0	@ read comms data reg"
+		: "=r" (__c));
+	isb();
+
+	return __c;
+}
+
+static inline void __dcc_putchar(char c)
+{
+	asm volatile("mcr p14, 0, %0, c0, c5, 0	@ write a char"
+		: /* no output register */
+		: "r" (c));
+	isb();
+}
diff --git a/arch/arm/include/asm/delay.h b/arch/arm/include/asm/delay.h
new file mode 100644
index 000000000..dff714d88
--- /dev/null
+++ b/arch/arm/include/asm/delay.h
@@ -0,0 +1,72 @@
+/*
+ * Copyright (C) 1995-2004 Russell King
+ *
+ * Delay routines, using a pre-computed "loops_per_second" value.
+ */
+#ifndef __ASM_ARM_DELAY_H
+#define __ASM_ARM_DELAY_H
+
+#include <asm/memory.h>
+#include <asm/param.h>	/* HZ */
+
+#define MAX_UDELAY_MS	2
+#define UDELAY_MULT	((UL(2199023) * HZ) >> 11)
+#define UDELAY_SHIFT	30
+
+#ifndef __ASSEMBLY__
+
+struct delay_timer {
+	unsigned long (*read_current_timer)(void);
+	unsigned long freq;
+};
+
+extern struct arm_delay_ops {
+	void (*delay)(unsigned long);
+	void (*const_udelay)(unsigned long);
+	void (*udelay)(unsigned long);
+	unsigned long ticks_per_jiffy;
+} arm_delay_ops;
+
+#define __delay(n)		arm_delay_ops.delay(n)
+
+/*
+ * This function intentionally does not exist; if you see references to
+ * it, it means that you're calling udelay() with an out of range value.
+ *
+ * With currently imposed limits, this means that we support a max delay
+ * of 2000us. Further limits: HZ<=1000 and bogomips<=3355
+ */
+extern void __bad_udelay(void);
+
+/*
+ * division by multiplication: you don't have to worry about
+ * loss of precision.
+ *
+ * Use only for very small delays ( < 2 msec).  Should probably use a
+ * lookup table, really, as the multiplications take much too long with
+ * short delays.  This is a "reasonable" implementation, though (and the
+ * first constant multiplications gets optimized away if the delay is
+ * a constant)
+ */
+#define __udelay(n)		arm_delay_ops.udelay(n)
+#define __const_udelay(n)	arm_delay_ops.const_udelay(n)
+
+#define udelay(n)							\
+	(__builtin_constant_p(n) ?					\
+	  ((n) > (MAX_UDELAY_MS * 1000) ? __bad_udelay() :		\
+			__const_udelay((n) * UDELAY_MULT)) :		\
+	  __udelay(n))
+
+/* Loop-based definitions for assembly code. */
+extern void __loop_delay(unsigned long loops);
+extern void __loop_udelay(unsigned long usecs);
+extern void __loop_const_udelay(unsigned long);
+
+/* Delay-loop timer registration. */
+#define ARCH_HAS_READ_CURRENT_TIMER
+extern void register_current_timer_delay(const struct delay_timer *timer);
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* defined(_ARM_DELAY_H) */
+
diff --git a/arch/arm/include/asm/device.h b/arch/arm/include/asm/device.h
new file mode 100644
index 000000000..4111592f0
--- /dev/null
+++ b/arch/arm/include/asm/device.h
@@ -0,0 +1,37 @@
+/*
+ * Arch specific extensions to struct device
+ *
+ * This file is released under the GPLv2
+ */
+#ifndef ASMARM_DEVICE_H
+#define ASMARM_DEVICE_H
+
+struct dev_archdata {
+	struct dma_map_ops	*dma_ops;
+#ifdef CONFIG_DMABOUNCE
+	struct dmabounce_device_info *dmabounce;
+#endif
+#ifdef CONFIG_IOMMU_API
+	void *iommu; /* private IOMMU data */
+#endif
+#ifdef CONFIG_ARM_DMA_USE_IOMMU
+	struct dma_iommu_mapping	*mapping;
+#endif
+	bool dma_coherent;
+};
+
+struct omap_device;
+
+struct pdev_archdata {
+#ifdef CONFIG_ARCH_OMAP
+	struct omap_device *od;
+#endif
+};
+
+#ifdef CONFIG_ARM_DMA_USE_IOMMU
+#define to_dma_iommu_mapping(dev) ((dev)->archdata.mapping)
+#else
+#define to_dma_iommu_mapping(dev) NULL
+#endif
+
+#endif
diff --git a/arch/arm/include/asm/div64.h b/arch/arm/include/asm/div64.h
new file mode 100644
index 000000000..662c7bd06
--- /dev/null
+++ b/arch/arm/include/asm/div64.h
@@ -0,0 +1,227 @@
+#ifndef __ASM_ARM_DIV64
+#define __ASM_ARM_DIV64
+
+#include <linux/types.h>
+#include <asm/compiler.h>
+
+/*
+ * The semantics of do_div() are:
+ *
+ * uint32_t do_div(uint64_t *n, uint32_t base)
+ * {
+ * 	uint32_t remainder = *n % base;
+ * 	*n = *n / base;
+ * 	return remainder;
+ * }
+ *
+ * In other words, a 64-bit dividend with a 32-bit divisor producing
+ * a 64-bit result and a 32-bit remainder.  To accomplish this optimally
+ * we call a special __do_div64 helper with completely non standard
+ * calling convention for arguments and results (beware).
+ */
+
+#ifdef __ARMEB__
+#define __xh "r0"
+#define __xl "r1"
+#else
+#define __xl "r0"
+#define __xh "r1"
+#endif
+
+#define __do_div_asm(n, base)					\
+({								\
+	register unsigned int __base      asm("r4") = base;	\
+	register unsigned long long __n   asm("r0") = n;	\
+	register unsigned long long __res asm("r2");		\
+	register unsigned int __rem       asm(__xh);		\
+	asm(	__asmeq("%0", __xh)				\
+		__asmeq("%1", "r2")				\
+		__asmeq("%2", "r0")				\
+		__asmeq("%3", "r4")				\
+		"bl	__do_div64"				\
+		: "=r" (__rem), "=r" (__res)			\
+		: "r" (__n), "r" (__base)			\
+		: "ip", "lr", "cc");				\
+	n = __res;						\
+	__rem;							\
+})
+
+#if __GNUC__ < 4 || !defined(CONFIG_AEABI)
+
+/*
+ * gcc versions earlier than 4.0 are simply too problematic for the
+ * optimized implementation below. First there is gcc PR 15089 that
+ * tend to trig on more complex constructs, spurious .global __udivsi3
+ * are inserted even if none of those symbols are referenced in the
+ * generated code, and those gcc versions are not able to do constant
+ * propagation on long long values anyway.
+ */
+#define do_div(n, base) __do_div_asm(n, base)
+
+#elif __GNUC__ >= 4
+
+#include <asm/bug.h>
+
+/*
+ * If the divisor happens to be constant, we determine the appropriate
+ * inverse at compile time to turn the division into a few inline
+ * multiplications instead which is much faster. And yet only if compiling
+ * for ARMv4 or higher (we need umull/umlal) and if the gcc version is
+ * sufficiently recent to perform proper long long constant propagation.
+ * (It is unfortunate that gcc doesn't perform all this internally.)
+ */
+#define do_div(n, base)							\
+({									\
+	unsigned int __r, __b = (base);					\
+	if (!__builtin_constant_p(__b) || __b == 0 ||			\
+	    (__LINUX_ARM_ARCH__ < 4 && (__b & (__b - 1)) != 0)) {	\
+		/* non-constant divisor (or zero): slow path */		\
+		__r = __do_div_asm(n, __b);				\
+	} else if ((__b & (__b - 1)) == 0) {				\
+		/* Trivial: __b is constant and a power of 2 */		\
+		/* gcc does the right thing with this code.  */		\
+		__r = n;						\
+		__r &= (__b - 1);					\
+		n /= __b;						\
+	} else {							\
+		/* Multiply by inverse of __b: n/b = n*(p/b)/p       */	\
+		/* We rely on the fact that most of this code gets   */	\
+		/* optimized away at compile time due to constant    */	\
+		/* propagation and only a couple inline assembly     */	\
+		/* instructions should remain. Better avoid any      */	\
+		/* code construct that might prevent that.           */	\
+		unsigned long long __res, __x, __t, __m, __n = n;	\
+		unsigned int __c, __p, __z = 0;				\
+		/* preserve low part of n for reminder computation */	\
+		__r = __n;						\
+		/* determine number of bits to represent __b */		\
+		__p = 1 << __div64_fls(__b);				\
+		/* compute __m = ((__p << 64) + __b - 1) / __b */	\
+		__m = (~0ULL / __b) * __p;				\
+		__m += (((~0ULL % __b + 1) * __p) + __b - 1) / __b;	\
+		/* compute __res = __m*(~0ULL/__b*__b-1)/(__p << 64) */	\
+		__x = ~0ULL / __b * __b - 1;				\
+		__res = (__m & 0xffffffff) * (__x & 0xffffffff);	\
+		__res >>= 32;						\
+		__res += (__m & 0xffffffff) * (__x >> 32);		\
+		__t = __res;						\
+		__res += (__x & 0xffffffff) * (__m >> 32);		\
+		__t = (__res < __t) ? (1ULL << 32) : 0;			\
+		__res = (__res >> 32) + __t;				\
+		__res += (__m >> 32) * (__x >> 32);			\
+		__res /= __p;						\
+		/* Now sanitize and optimize what we've got. */		\
+		if (~0ULL % (__b / (__b & -__b)) == 0) {		\
+			/* those cases can be simplified with: */	\
+			__n /= (__b & -__b);				\
+			__m = ~0ULL / (__b / (__b & -__b));		\
+			__p = 1;					\
+			__c = 1;					\
+		} else if (__res != __x / __b) {			\
+			/* We can't get away without a correction    */	\
+			/* to compensate for bit truncation errors.  */	\
+			/* To avoid it we'd need an additional bit   */	\
+			/* to represent __m which would overflow it. */	\
+			/* Instead we do m=p/b and n/b=(n*m+m)/p.    */	\
+			__c = 1;					\
+			/* Compute __m = (__p << 64) / __b */		\
+			__m = (~0ULL / __b) * __p;			\
+			__m += ((~0ULL % __b + 1) * __p) / __b;		\
+		} else {						\
+			/* Reduce __m/__p, and try to clear bit 31   */	\
+			/* of __m when possible otherwise that'll    */	\
+			/* need extra overflow handling later.       */	\
+			unsigned int __bits = -(__m & -__m);		\
+			__bits |= __m >> 32;				\
+			__bits = (~__bits) << 1;			\
+			/* If __bits == 0 then setting bit 31 is     */	\
+			/* unavoidable.  Simply apply the maximum    */	\
+			/* possible reduction in that case.          */	\
+			/* Otherwise the MSB of __bits indicates the */	\
+			/* best reduction we should apply.           */	\
+			if (!__bits) {					\
+				__p /= (__m & -__m);			\
+				__m /= (__m & -__m);			\
+			} else {					\
+				__p >>= __div64_fls(__bits);		\
+				__m >>= __div64_fls(__bits);		\
+			}						\
+			/* No correction needed. */			\
+			__c = 0;					\
+		}							\
+		/* Now we have a combination of 2 conditions:        */	\
+		/* 1) whether or not we need a correction (__c), and */	\
+		/* 2) whether or not there might be an overflow in   */	\
+		/*    the cross product (__m & ((1<<63) | (1<<31)))  */	\
+		/* Select the best insn combination to perform the   */	\
+		/* actual __m * __n / (__p << 64) operation.         */	\
+		if (!__c) {						\
+			asm (	"umull	%Q0, %R0, %Q1, %Q2\n\t"		\
+				"mov	%Q0, #0"			\
+				: "=&r" (__res)				\
+				: "r" (__m), "r" (__n)			\
+				: "cc" );				\
+		} else if (!(__m & ((1ULL << 63) | (1ULL << 31)))) {	\
+			__res = __m;					\
+			asm (	"umlal	%Q0, %R0, %Q1, %Q2\n\t"		\
+				"mov	%Q0, #0"			\
+				: "+&r" (__res)				\
+				: "r" (__m), "r" (__n)			\
+				: "cc" );				\
+		} else {						\
+			asm (	"umull	%Q0, %R0, %Q1, %Q2\n\t"		\
+				"cmn	%Q0, %Q1\n\t"			\
+				"adcs	%R0, %R0, %R1\n\t"		\
+				"adc	%Q0, %3, #0"			\
+				: "=&r" (__res)				\
+				: "r" (__m), "r" (__n), "r" (__z)	\
+				: "cc" );				\
+		}							\
+		if (!(__m & ((1ULL << 63) | (1ULL << 31)))) {		\
+			asm (	"umlal	%R0, %Q0, %R1, %Q2\n\t"		\
+				"umlal	%R0, %Q0, %Q1, %R2\n\t"		\
+				"mov	%R0, #0\n\t"			\
+				"umlal	%Q0, %R0, %R1, %R2"		\
+				: "+&r" (__res)				\
+				: "r" (__m), "r" (__n)			\
+				: "cc" );				\
+		} else {						\
+			asm (	"umlal	%R0, %Q0, %R2, %Q3\n\t"		\
+				"umlal	%R0, %1, %Q2, %R3\n\t"		\
+				"mov	%R0, #0\n\t"			\
+				"adds	%Q0, %1, %Q0\n\t"		\
+				"adc	%R0, %R0, #0\n\t"		\
+				"umlal	%Q0, %R0, %R2, %R3"		\
+				: "+&r" (__res), "+&r" (__z)		\
+				: "r" (__m), "r" (__n)			\
+				: "cc" );				\
+		}							\
+		__res /= __p;						\
+		/* The reminder can be computed with 32-bit regs     */	\
+		/* only, and gcc is good at that.                    */	\
+		{							\
+			unsigned int __res0 = __res;			\
+			unsigned int __b0 = __b;			\
+			__r -= __res0 * __b0;				\
+		}							\
+		/* BUG_ON(__r >= __b || __res * __b + __r != n); */	\
+		n = __res;						\
+	}								\
+	__r;								\
+})
+
+/* our own fls implementation to make sure constant propagation is fine */
+#define __div64_fls(bits)						\
+({									\
+	unsigned int __left = (bits), __nr = 0;				\
+	if (__left & 0xffff0000) __nr += 16, __left >>= 16;		\
+	if (__left & 0x0000ff00) __nr +=  8, __left >>=  8;		\
+	if (__left & 0x000000f0) __nr +=  4, __left >>=  4;		\
+	if (__left & 0x0000000c) __nr +=  2, __left >>=  2;		\
+	if (__left & 0x00000002) __nr +=  1;				\
+	__nr;								\
+})
+
+#endif
+
+#endif
diff --git a/arch/arm/include/asm/dma-contiguous.h b/arch/arm/include/asm/dma-contiguous.h
new file mode 100644
index 000000000..4f8e9e551
--- /dev/null
+++ b/arch/arm/include/asm/dma-contiguous.h
@@ -0,0 +1,14 @@
+#ifndef ASMARM_DMA_CONTIGUOUS_H
+#define ASMARM_DMA_CONTIGUOUS_H
+
+#ifdef __KERNEL__
+#ifdef CONFIG_DMA_CMA
+
+#include <linux/types.h>
+
+void dma_contiguous_early_fixup(phys_addr_t base, unsigned long size);
+
+#endif
+#endif
+
+#endif
diff --git a/arch/arm/include/asm/dma-iommu.h b/arch/arm/include/asm/dma-iommu.h
new file mode 100644
index 000000000..2ef282f96
--- /dev/null
+++ b/arch/arm/include/asm/dma-iommu.h
@@ -0,0 +1,37 @@
+#ifndef ASMARM_DMA_IOMMU_H
+#define ASMARM_DMA_IOMMU_H
+
+#ifdef __KERNEL__
+
+#include <linux/mm_types.h>
+#include <linux/scatterlist.h>
+#include <linux/dma-debug.h>
+#include <linux/kmemcheck.h>
+#include <linux/kref.h>
+
+struct dma_iommu_mapping {
+	/* iommu specific data */
+	struct iommu_domain	*domain;
+
+	unsigned long		**bitmaps;	/* array of bitmaps */
+	unsigned int		nr_bitmaps;	/* nr of elements in array */
+	unsigned int		extensions;
+	size_t			bitmap_size;	/* size of a single bitmap */
+	size_t			bits;		/* per bitmap */
+	dma_addr_t		base;
+
+	spinlock_t		lock;
+	struct kref		kref;
+};
+
+struct dma_iommu_mapping *
+arm_iommu_create_mapping(struct bus_type *bus, dma_addr_t base, u64 size);
+
+void arm_iommu_release_mapping(struct dma_iommu_mapping *mapping);
+
+int arm_iommu_attach_device(struct device *dev,
+					struct dma_iommu_mapping *mapping);
+void arm_iommu_detach_device(struct device *dev);
+
+#endif /* __KERNEL__ */
+#endif
diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h
new file mode 100644
index 000000000..b52101d37
--- /dev/null
+++ b/arch/arm/include/asm/dma-mapping.h
@@ -0,0 +1,338 @@
+#ifndef ASMARM_DMA_MAPPING_H
+#define ASMARM_DMA_MAPPING_H
+
+#ifdef __KERNEL__
+
+#include <linux/mm_types.h>
+#include <linux/scatterlist.h>
+#include <linux/dma-attrs.h>
+#include <linux/dma-debug.h>
+
+#include <asm-generic/dma-coherent.h>
+#include <asm/memory.h>
+
+#include <xen/xen.h>
+#include <asm/xen/hypervisor.h>
+
+#define DMA_ERROR_CODE	(~0)
+extern struct dma_map_ops arm_dma_ops;
+extern struct dma_map_ops arm_coherent_dma_ops;
+
+static inline struct dma_map_ops *__generic_dma_ops(struct device *dev)
+{
+	if (dev && dev->archdata.dma_ops)
+		return dev->archdata.dma_ops;
+	return &arm_dma_ops;
+}
+
+static inline struct dma_map_ops *get_dma_ops(struct device *dev)
+{
+	if (xen_initial_domain())
+		return xen_dma_ops;
+	else
+		return __generic_dma_ops(dev);
+}
+
+static inline void set_dma_ops(struct device *dev, struct dma_map_ops *ops)
+{
+	BUG_ON(!dev);
+	dev->archdata.dma_ops = ops;
+}
+
+#include <asm-generic/dma-mapping-common.h>
+
+static inline int dma_set_mask(struct device *dev, u64 mask)
+{
+	return get_dma_ops(dev)->set_dma_mask(dev, mask);
+}
+
+#ifdef __arch_page_to_dma
+#error Please update to __arch_pfn_to_dma
+#endif
+
+/*
+ * dma_to_pfn/pfn_to_dma/dma_to_virt/virt_to_dma are architecture private
+ * functions used internally by the DMA-mapping API to provide DMA
+ * addresses. They must not be used by drivers.
+ */
+#ifndef __arch_pfn_to_dma
+static inline dma_addr_t pfn_to_dma(struct device *dev, unsigned long pfn)
+{
+	if (dev)
+		pfn -= dev->dma_pfn_offset;
+	return (dma_addr_t)__pfn_to_bus(pfn);
+}
+
+static inline unsigned long dma_to_pfn(struct device *dev, dma_addr_t addr)
+{
+	unsigned long pfn = __bus_to_pfn(addr);
+
+	if (dev)
+		pfn += dev->dma_pfn_offset;
+
+	return pfn;
+}
+
+static inline void *dma_to_virt(struct device *dev, dma_addr_t addr)
+{
+	if (dev) {
+		unsigned long pfn = dma_to_pfn(dev, addr);
+
+		return phys_to_virt(__pfn_to_phys(pfn));
+	}
+
+	return (void *)__bus_to_virt((unsigned long)addr);
+}
+
+static inline dma_addr_t virt_to_dma(struct device *dev, void *addr)
+{
+	if (dev)
+		return pfn_to_dma(dev, virt_to_pfn(addr));
+
+	return (dma_addr_t)__virt_to_bus((unsigned long)(addr));
+}
+
+#else
+static inline dma_addr_t pfn_to_dma(struct device *dev, unsigned long pfn)
+{
+	return __arch_pfn_to_dma(dev, pfn);
+}
+
+static inline unsigned long dma_to_pfn(struct device *dev, dma_addr_t addr)
+{
+	return __arch_dma_to_pfn(dev, addr);
+}
+
+static inline void *dma_to_virt(struct device *dev, dma_addr_t addr)
+{
+	return __arch_dma_to_virt(dev, addr);
+}
+
+static inline dma_addr_t virt_to_dma(struct device *dev, void *addr)
+{
+	return __arch_virt_to_dma(dev, addr);
+}
+#endif
+
+/* The ARM override for dma_max_pfn() */
+static inline unsigned long dma_max_pfn(struct device *dev)
+{
+	return PHYS_PFN_OFFSET + dma_to_pfn(dev, *dev->dma_mask);
+}
+#define dma_max_pfn(dev) dma_max_pfn(dev)
+
+#define arch_setup_dma_ops arch_setup_dma_ops
+extern void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
+			       struct iommu_ops *iommu, bool coherent);
+
+#define arch_teardown_dma_ops arch_teardown_dma_ops
+extern void arch_teardown_dma_ops(struct device *dev);
+
+/* do not use this function in a driver */
+static inline bool is_device_dma_coherent(struct device *dev)
+{
+	return dev->archdata.dma_coherent;
+}
+
+static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
+{
+	unsigned int offset = paddr & ~PAGE_MASK;
+	return pfn_to_dma(dev, __phys_to_pfn(paddr)) + offset;
+}
+
+static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dev_addr)
+{
+	unsigned int offset = dev_addr & ~PAGE_MASK;
+	return __pfn_to_phys(dma_to_pfn(dev, dev_addr)) + offset;
+}
+
+static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
+{
+	u64 limit, mask;
+
+	if (!dev->dma_mask)
+		return 0;
+
+	mask = *dev->dma_mask;
+
+	limit = (mask + 1) & ~mask;
+	if (limit && size > limit)
+		return 0;
+
+	if ((addr | (addr + size - 1)) & ~mask)
+		return 0;
+
+	return 1;
+}
+
+static inline void dma_mark_clean(void *addr, size_t size) { }
+
+/*
+ * DMA errors are defined by all-bits-set in the DMA address.
+ */
+static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
+{
+	debug_dma_mapping_error(dev, dma_addr);
+	return dma_addr == DMA_ERROR_CODE;
+}
+
+/*
+ * Dummy noncoherent implementation.  We don't provide a dma_cache_sync
+ * function so drivers using this API are highlighted with build warnings.
+ */
+static inline void *dma_alloc_noncoherent(struct device *dev, size_t size,
+		dma_addr_t *handle, gfp_t gfp)
+{
+	return NULL;
+}
+
+static inline void dma_free_noncoherent(struct device *dev, size_t size,
+		void *cpu_addr, dma_addr_t handle)
+{
+}
+
+extern int dma_supported(struct device *dev, u64 mask);
+
+extern int arm_dma_set_mask(struct device *dev, u64 dma_mask);
+
+/**
+ * arm_dma_alloc - allocate consistent memory for DMA
+ * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
+ * @size: required memory size
+ * @handle: bus-specific DMA address
+ * @attrs: optinal attributes that specific mapping properties
+ *
+ * Allocate some memory for a device for performing DMA.  This function
+ * allocates pages, and will return the CPU-viewed address, and sets @handle
+ * to be the device-viewed address.
+ */
+extern void *arm_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
+			   gfp_t gfp, struct dma_attrs *attrs);
+
+#define dma_alloc_coherent(d, s, h, f) dma_alloc_attrs(d, s, h, f, NULL)
+
+static inline void *dma_alloc_attrs(struct device *dev, size_t size,
+				       dma_addr_t *dma_handle, gfp_t flag,
+				       struct dma_attrs *attrs)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+	void *cpu_addr;
+	BUG_ON(!ops);
+
+	cpu_addr = ops->alloc(dev, size, dma_handle, flag, attrs);
+	debug_dma_alloc_coherent(dev, size, *dma_handle, cpu_addr);
+	return cpu_addr;
+}
+
+/**
+ * arm_dma_free - free memory allocated by arm_dma_alloc
+ * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
+ * @size: size of memory originally requested in dma_alloc_coherent
+ * @cpu_addr: CPU-view address returned from dma_alloc_coherent
+ * @handle: device-view address returned from dma_alloc_coherent
+ * @attrs: optinal attributes that specific mapping properties
+ *
+ * Free (and unmap) a DMA buffer previously allocated by
+ * arm_dma_alloc().
+ *
+ * References to memory and mappings associated with cpu_addr/handle
+ * during and after this call executing are illegal.
+ */
+extern void arm_dma_free(struct device *dev, size_t size, void *cpu_addr,
+			 dma_addr_t handle, struct dma_attrs *attrs);
+
+#define dma_free_coherent(d, s, c, h) dma_free_attrs(d, s, c, h, NULL)
+
+static inline void dma_free_attrs(struct device *dev, size_t size,
+				     void *cpu_addr, dma_addr_t dma_handle,
+				     struct dma_attrs *attrs)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+	BUG_ON(!ops);
+
+	debug_dma_free_coherent(dev, size, cpu_addr, dma_handle);
+	ops->free(dev, size, cpu_addr, dma_handle, attrs);
+}
+
+/**
+ * arm_dma_mmap - map a coherent DMA allocation into user space
+ * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
+ * @vma: vm_area_struct describing requested user mapping
+ * @cpu_addr: kernel CPU-view address returned from dma_alloc_coherent
+ * @handle: device-view address returned from dma_alloc_coherent
+ * @size: size of memory originally requested in dma_alloc_coherent
+ * @attrs: optinal attributes that specific mapping properties
+ *
+ * Map a coherent DMA buffer previously allocated by dma_alloc_coherent
+ * into user space.  The coherent DMA buffer must not be freed by the
+ * driver until the user space mapping has been released.
+ */
+extern int arm_dma_mmap(struct device *dev, struct vm_area_struct *vma,
+			void *cpu_addr, dma_addr_t dma_addr, size_t size,
+			struct dma_attrs *attrs);
+
+/*
+ * This can be called during early boot to increase the size of the atomic
+ * coherent DMA pool above the default value of 256KiB. It must be called
+ * before postcore_initcall.
+ */
+extern void __init init_dma_coherent_pool_size(unsigned long size);
+
+/*
+ * For SA-1111, IXP425, and ADI systems  the dma-mapping functions are "magic"
+ * and utilize bounce buffers as needed to work around limited DMA windows.
+ *
+ * On the SA-1111, a bug limits DMA to only certain regions of RAM.
+ * On the IXP425, the PCI inbound window is 64MB (256MB total RAM)
+ * On some ADI engineering systems, PCI inbound window is 32MB (12MB total RAM)
+ *
+ * The following are helper functions used by the dmabounce subystem
+ *
+ */
+
+/**
+ * dmabounce_register_dev
+ *
+ * @dev: valid struct device pointer
+ * @small_buf_size: size of buffers to use with small buffer pool
+ * @large_buf_size: size of buffers to use with large buffer pool (can be 0)
+ * @needs_bounce_fn: called to determine whether buffer needs bouncing
+ *
+ * This function should be called by low-level platform code to register
+ * a device as requireing DMA buffer bouncing. The function will allocate
+ * appropriate DMA pools for the device.
+ */
+extern int dmabounce_register_dev(struct device *, unsigned long,
+		unsigned long, int (*)(struct device *, dma_addr_t, size_t));
+
+/**
+ * dmabounce_unregister_dev
+ *
+ * @dev: valid struct device pointer
+ *
+ * This function should be called by low-level platform code when device
+ * that was previously registered with dmabounce_register_dev is removed
+ * from the system.
+ *
+ */
+extern void dmabounce_unregister_dev(struct device *);
+
+
+
+/*
+ * The scatter list versions of the above methods.
+ */
+extern int arm_dma_map_sg(struct device *, struct scatterlist *, int,
+		enum dma_data_direction, struct dma_attrs *attrs);
+extern void arm_dma_unmap_sg(struct device *, struct scatterlist *, int,
+		enum dma_data_direction, struct dma_attrs *attrs);
+extern void arm_dma_sync_sg_for_cpu(struct device *, struct scatterlist *, int,
+		enum dma_data_direction);
+extern void arm_dma_sync_sg_for_device(struct device *, struct scatterlist *, int,
+		enum dma_data_direction);
+extern int arm_dma_get_sgtable(struct device *dev, struct sg_table *sgt,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		struct dma_attrs *attrs);
+
+#endif /* __KERNEL__ */
+#endif
diff --git a/arch/arm/include/asm/dma.h b/arch/arm/include/asm/dma.h
new file mode 100644
index 000000000..99084431d
--- /dev/null
+++ b/arch/arm/include/asm/dma.h
@@ -0,0 +1,151 @@
+#ifndef __ASM_ARM_DMA_H
+#define __ASM_ARM_DMA_H
+
+/*
+ * This is the maximum virtual address which can be DMA'd from.
+ */
+#ifndef CONFIG_ZONE_DMA
+#define MAX_DMA_ADDRESS	0xffffffffUL
+#else
+#define MAX_DMA_ADDRESS	({ \
+	extern phys_addr_t arm_dma_zone_size; \
+	arm_dma_zone_size && arm_dma_zone_size < (0x10000000 - PAGE_OFFSET) ? \
+		(PAGE_OFFSET + arm_dma_zone_size) : 0xffffffffUL; })
+#endif
+
+#ifdef CONFIG_ISA_DMA_API
+/*
+ * This is used to support drivers written for the x86 ISA DMA API.
+ * It should not be re-used except for that purpose.
+ */
+#include <linux/spinlock.h>
+#include <asm/scatterlist.h>
+
+#include <mach/isa-dma.h>
+
+/*
+ * The DMA modes reflect the settings for the ISA DMA controller
+ */
+#define DMA_MODE_MASK	 0xcc
+
+#define DMA_MODE_READ	 0x44
+#define DMA_MODE_WRITE	 0x48
+#define DMA_MODE_CASCADE 0xc0
+#define DMA_AUTOINIT	 0x10
+
+extern raw_spinlock_t  dma_spin_lock;
+
+static inline unsigned long claim_dma_lock(void)
+{
+	unsigned long flags;
+	raw_spin_lock_irqsave(&dma_spin_lock, flags);
+	return flags;
+}
+
+static inline void release_dma_lock(unsigned long flags)
+{
+	raw_spin_unlock_irqrestore(&dma_spin_lock, flags);
+}
+
+/* Clear the 'DMA Pointer Flip Flop'.
+ * Write 0 for LSB/MSB, 1 for MSB/LSB access.
+ */
+#define clear_dma_ff(chan)
+
+/* Set only the page register bits of the transfer address.
+ *
+ * NOTE: This is an architecture specific function, and should
+ *       be hidden from the drivers
+ */
+extern void set_dma_page(unsigned int chan, char pagenr);
+
+/* Request a DMA channel
+ *
+ * Some architectures may need to do allocate an interrupt
+ */
+extern int  request_dma(unsigned int chan, const char * device_id);
+
+/* Free a DMA channel
+ *
+ * Some architectures may need to do free an interrupt
+ */
+extern void free_dma(unsigned int chan);
+
+/* Enable DMA for this channel
+ *
+ * On some architectures, this may have other side effects like
+ * enabling an interrupt and setting the DMA registers.
+ */
+extern void enable_dma(unsigned int chan);
+
+/* Disable DMA for this channel
+ *
+ * On some architectures, this may have other side effects like
+ * disabling an interrupt or whatever.
+ */
+extern void disable_dma(unsigned int chan);
+
+/* Test whether the specified channel has an active DMA transfer
+ */
+extern int dma_channel_active(unsigned int chan);
+
+/* Set the DMA scatter gather list for this channel
+ *
+ * This should not be called if a DMA channel is enabled,
+ * especially since some DMA architectures don't update the
+ * DMA address immediately, but defer it to the enable_dma().
+ */
+extern void set_dma_sg(unsigned int chan, struct scatterlist *sg, int nr_sg);
+
+/* Set the DMA address for this channel
+ *
+ * This should not be called if a DMA channel is enabled,
+ * especially since some DMA architectures don't update the
+ * DMA address immediately, but defer it to the enable_dma().
+ */
+extern void __set_dma_addr(unsigned int chan, void *addr);
+#define set_dma_addr(chan, addr)				\
+	__set_dma_addr(chan, (void *)__bus_to_virt(addr))
+
+/* Set the DMA byte count for this channel
+ *
+ * This should not be called if a DMA channel is enabled,
+ * especially since some DMA architectures don't update the
+ * DMA count immediately, but defer it to the enable_dma().
+ */
+extern void set_dma_count(unsigned int chan, unsigned long count);
+
+/* Set the transfer direction for this channel
+ *
+ * This should not be called if a DMA channel is enabled,
+ * especially since some DMA architectures don't update the
+ * DMA transfer direction immediately, but defer it to the
+ * enable_dma().
+ */
+extern void set_dma_mode(unsigned int chan, unsigned int mode);
+
+/* Set the transfer speed for this channel
+ */
+extern void set_dma_speed(unsigned int chan, int cycle_ns);
+
+/* Get DMA residue count. After a DMA transfer, this
+ * should return zero. Reading this while a DMA transfer is
+ * still in progress will return unpredictable results.
+ * If called before the channel has been used, it may return 1.
+ * Otherwise, it returns the number of _bytes_ left to transfer.
+ */
+extern int  get_dma_residue(unsigned int chan);
+
+#ifndef NO_DMA
+#define NO_DMA	255
+#endif
+
+#endif /* CONFIG_ISA_DMA_API */
+
+#ifdef CONFIG_PCI
+extern int isa_dma_bridge_buggy;
+#else
+#define isa_dma_bridge_buggy    (0)
+#endif
+
+#endif /* __ASM_ARM_DMA_H */
diff --git a/arch/arm/include/asm/domain.h b/arch/arm/include/asm/domain.h
new file mode 100644
index 000000000..6ddbe4464
--- /dev/null
+++ b/arch/arm/include/asm/domain.h
@@ -0,0 +1,109 @@
+/*
+ *  arch/arm/include/asm/domain.h
+ *
+ *  Copyright (C) 1999 Russell King.
+ *
+ * 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.
+ */
+#ifndef __ASM_PROC_DOMAIN_H
+#define __ASM_PROC_DOMAIN_H
+
+#ifndef __ASSEMBLY__
+#include <asm/barrier.h>
+#endif
+
+/*
+ * Domain numbers
+ *
+ *  DOMAIN_IO     - domain 2 includes all IO only
+ *  DOMAIN_USER   - domain 1 includes all user memory only
+ *  DOMAIN_KERNEL - domain 0 includes all kernel memory only
+ *
+ * The domain numbering depends on whether we support 36 physical
+ * address for I/O or not.  Addresses above the 32 bit boundary can
+ * only be mapped using supersections and supersections can only
+ * be set for domain 0.  We could just default to DOMAIN_IO as zero,
+ * but there may be systems with supersection support and no 36-bit
+ * addressing.  In such cases, we want to map system memory with
+ * supersections to reduce TLB misses and footprint.
+ *
+ * 36-bit addressing and supersections are only available on
+ * CPUs based on ARMv6+ or the Intel XSC3 core.
+ */
+#ifndef CONFIG_IO_36
+#define DOMAIN_KERNEL	0
+#define DOMAIN_TABLE	0
+#define DOMAIN_USER	1
+#define DOMAIN_IO	2
+#else
+#define DOMAIN_KERNEL	2
+#define DOMAIN_TABLE	2
+#define DOMAIN_USER	1
+#define DOMAIN_IO	0
+#endif
+
+/*
+ * Domain types
+ */
+#define DOMAIN_NOACCESS	0
+#define DOMAIN_CLIENT	1
+#ifdef CONFIG_CPU_USE_DOMAINS
+#define DOMAIN_MANAGER	3
+#else
+#define DOMAIN_MANAGER	1
+#endif
+
+#define domain_val(dom,type)	((type) << (2*(dom)))
+
+#ifndef __ASSEMBLY__
+
+#ifdef CONFIG_CPU_USE_DOMAINS
+static inline void set_domain(unsigned val)
+{
+	asm volatile(
+	"mcr	p15, 0, %0, c3, c0	@ set domain"
+	  : : "r" (val));
+	isb();
+}
+
+#define modify_domain(dom,type)					\
+	do {							\
+	struct thread_info *thread = current_thread_info();	\
+	unsigned int domain = thread->cpu_domain;		\
+	domain &= ~domain_val(dom, DOMAIN_MANAGER);		\
+	thread->cpu_domain = domain | domain_val(dom, type);	\
+	set_domain(thread->cpu_domain);				\
+	} while (0)
+
+#else
+static inline void set_domain(unsigned val) { }
+static inline void modify_domain(unsigned dom, unsigned type)	{ }
+#endif
+
+/*
+ * Generate the T (user) versions of the LDR/STR and related
+ * instructions (inline assembly)
+ */
+#ifdef CONFIG_CPU_USE_DOMAINS
+#define TUSER(instr)	#instr "t"
+#else
+#define TUSER(instr)	#instr
+#endif
+
+#else /* __ASSEMBLY__ */
+
+/*
+ * Generate the T (user) versions of the LDR/STR and related
+ * instructions
+ */
+#ifdef CONFIG_CPU_USE_DOMAINS
+#define TUSER(instr)	instr ## t
+#else
+#define TUSER(instr)	instr
+#endif
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* !__ASM_PROC_DOMAIN_H */
diff --git a/arch/arm/include/asm/ecard.h b/arch/arm/include/asm/ecard.h
new file mode 100644
index 000000000..eaea14676
--- /dev/null
+++ b/arch/arm/include/asm/ecard.h
@@ -0,0 +1,218 @@
+/*
+ * arch/arm/include/asm/ecard.h
+ *
+ * definitions for expansion cards
+ *
+ * This is a new system as from Linux 1.2.3
+ *
+ * Changelog:
+ *  11-12-1996	RMK	Further minor improvements
+ *  12-09-1997	RMK	Added interrupt enable/disable for card level
+ *
+ * Reference: Acorns Risc OS 3 Programmers Reference Manuals.
+ */
+
+#ifndef __ASM_ECARD_H
+#define __ASM_ECARD_H
+
+/*
+ * Currently understood cards (but not necessarily
+ * supported):
+ *                        Manufacturer  Product ID
+ */
+#define MANU_ACORN		0x0000
+#define PROD_ACORN_SCSI			0x0002
+#define PROD_ACORN_ETHER1		0x0003
+#define PROD_ACORN_MFM			0x000b
+
+#define MANU_ANT2		0x0011
+#define PROD_ANT_ETHER3			0x00a4
+
+#define MANU_ATOMWIDE		0x0017
+#define PROD_ATOMWIDE_3PSERIAL		0x0090
+
+#define MANU_IRLAM_INSTRUMENTS	0x001f
+#define MANU_IRLAM_INSTRUMENTS_ETHERN	0x5678
+
+#define MANU_OAK		0x0021
+#define PROD_OAK_SCSI			0x0058
+
+#define MANU_MORLEY		0x002b
+#define PROD_MORLEY_SCSI_UNCACHED	0x0067
+
+#define MANU_CUMANA		0x003a
+#define PROD_CUMANA_SCSI_2		0x003a
+#define PROD_CUMANA_SCSI_1		0x00a0
+
+#define MANU_ICS		0x003c
+#define PROD_ICS_IDE			0x00ae
+
+#define MANU_ICS2		0x003d
+#define PROD_ICS2_IDE			0x00ae
+
+#define MANU_SERPORT		0x003f
+#define PROD_SERPORT_DSPORT		0x00b9
+
+#define MANU_ARXE		0x0041
+#define PROD_ARXE_SCSI			0x00be
+
+#define MANU_I3			0x0046
+#define PROD_I3_ETHERLAN500		0x00d4
+#define PROD_I3_ETHERLAN600		0x00ec
+#define PROD_I3_ETHERLAN600A		0x011e
+
+#define MANU_ANT		0x0053
+#define PROD_ANT_ETHERM			0x00d8
+#define PROD_ANT_ETHERB			0x00e4
+
+#define MANU_ALSYSTEMS		0x005b
+#define PROD_ALSYS_SCSIATAPI		0x0107
+
+#define MANU_MCS		0x0063
+#define PROD_MCS_CONNECT32		0x0125
+
+#define MANU_EESOX		0x0064
+#define PROD_EESOX_SCSI2		0x008c
+
+#define MANU_YELLOWSTONE	0x0096
+#define PROD_YELLOWSTONE_RAPIDE32	0x0120
+
+#ifdef ECARD_C
+#define CONST
+#else
+#define CONST const
+#endif
+
+#define MAX_ECARDS	9
+
+struct ecard_id {			/* Card ID structure		*/
+	unsigned short	manufacturer;
+	unsigned short	product;
+	void		*data;
+};
+
+struct in_ecid {			/* Packed card ID information	*/
+	unsigned short	product;	/* Product code			*/
+	unsigned short	manufacturer;	/* Manufacturer code		*/
+	unsigned char	id:4;		/* Simple ID			*/
+	unsigned char	cd:1;		/* Chunk dir present		*/
+	unsigned char	is:1;		/* Interrupt status pointers	*/
+	unsigned char	w:2;		/* Width			*/
+	unsigned char	country;	/* Country			*/
+	unsigned char	irqmask;	/* IRQ mask			*/
+	unsigned char	fiqmask;	/* FIQ mask			*/
+	unsigned long	irqoff;		/* IRQ offset			*/
+	unsigned long	fiqoff;		/* FIQ offset			*/
+};
+
+typedef struct expansion_card ecard_t;
+typedef unsigned long *loader_t;
+
+typedef struct expansion_card_ops {	/* Card handler routines	*/
+	void (*irqenable)(ecard_t *ec, int irqnr);
+	void (*irqdisable)(ecard_t *ec, int irqnr);
+	int  (*irqpending)(ecard_t *ec);
+	void (*fiqenable)(ecard_t *ec, int fiqnr);
+	void (*fiqdisable)(ecard_t *ec, int fiqnr);
+	int  (*fiqpending)(ecard_t *ec);
+} expansioncard_ops_t;
+
+#define ECARD_NUM_RESOURCES	(6)
+
+#define ECARD_RES_IOCSLOW	(0)
+#define ECARD_RES_IOCMEDIUM	(1)
+#define ECARD_RES_IOCFAST	(2)
+#define ECARD_RES_IOCSYNC	(3)
+#define ECARD_RES_MEMC		(4)
+#define ECARD_RES_EASI		(5)
+
+#define ecard_resource_start(ec,nr)	((ec)->resource[nr].start)
+#define ecard_resource_end(ec,nr)	((ec)->resource[nr].end)
+#define ecard_resource_len(ec,nr)	((ec)->resource[nr].end - \
+					 (ec)->resource[nr].start + 1)
+#define ecard_resource_flags(ec,nr)	((ec)->resource[nr].flags)
+
+/*
+ * This contains all the info needed on an expansion card
+ */
+struct expansion_card {
+	struct expansion_card  *next;
+
+	struct device		dev;
+	struct resource		resource[ECARD_NUM_RESOURCES];
+
+	/* Public data */
+	void __iomem		*irqaddr;	/* address of IRQ register	*/
+	void __iomem		*fiqaddr;	/* address of FIQ register	*/
+	unsigned char		irqmask;	/* IRQ mask			*/
+	unsigned char		fiqmask;	/* FIQ mask			*/
+	unsigned char  		claimed;	/* Card claimed?		*/
+	unsigned char		easi;		/* EASI card			*/
+
+	void			*irq_data;	/* Data for use for IRQ by card	*/
+	void			*fiq_data;	/* Data for use for FIQ by card	*/
+	const expansioncard_ops_t *ops;		/* Enable/Disable Ops for card	*/
+
+	CONST unsigned int	slot_no;	/* Slot number			*/
+	CONST unsigned int	dma;		/* DMA number (for request_dma)	*/
+	CONST unsigned int	irq;		/* IRQ number (for request_irq)	*/
+	CONST unsigned int	fiq;		/* FIQ number (for request_irq)	*/
+	CONST struct in_ecid	cid;		/* Card Identification		*/
+
+	/* Private internal data */
+	const char		*card_desc;	/* Card description		*/
+	CONST loader_t		loader;		/* loader program */
+	u64			dma_mask;
+};
+
+void ecard_setirq(struct expansion_card *ec, const struct expansion_card_ops *ops, void *irq_data);
+
+struct in_chunk_dir {
+	unsigned int start_offset;
+	union {
+		unsigned char string[256];
+		unsigned char data[1];
+	} d;
+};
+
+/*
+ * Read a chunk from an expansion card
+ * cd : where to put read data
+ * ec : expansion card info struct
+ * id : id number to find
+ * num: (n+1)'th id to find.
+ */
+extern int ecard_readchunk (struct in_chunk_dir *cd, struct expansion_card *ec, int id, int num);
+
+/*
+ * Request and release ecard resources
+ */
+extern int ecard_request_resources(struct expansion_card *ec);
+extern void ecard_release_resources(struct expansion_card *ec);
+
+void __iomem *ecardm_iomap(struct expansion_card *ec, unsigned int res,
+			   unsigned long offset, unsigned long maxsize);
+#define ecardm_iounmap(__ec, __addr)	devm_iounmap(&(__ec)->dev, __addr)
+
+extern struct bus_type ecard_bus_type;
+
+#define ECARD_DEV(_d)	container_of((_d), struct expansion_card, dev)
+
+struct ecard_driver {
+	int			(*probe)(struct expansion_card *, const struct ecard_id *id);
+	void			(*remove)(struct expansion_card *);
+	void			(*shutdown)(struct expansion_card *);
+	const struct ecard_id	*id_table;
+	unsigned int		id;
+	struct device_driver	drv;
+};
+
+#define ECARD_DRV(_d)	container_of((_d), struct ecard_driver, drv)
+
+#define ecard_set_drvdata(ec,data)	dev_set_drvdata(&(ec)->dev, (data))
+#define ecard_get_drvdata(ec)		dev_get_drvdata(&(ec)->dev)
+
+int ecard_register_driver(struct ecard_driver *);
+void ecard_remove_driver(struct ecard_driver *);
+
+#endif
diff --git a/arch/arm/include/asm/edac.h b/arch/arm/include/asm/edac.h
new file mode 100644
index 000000000..0df7a2c1f
--- /dev/null
+++ b/arch/arm/include/asm/edac.h
@@ -0,0 +1,48 @@
+/*
+ * Copyright 2011 Calxeda, Inc.
+ * Based on PPC version Copyright 2007 MontaVista Software, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope 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_EDAC_H
+#define ASM_EDAC_H
+/*
+ * ECC atomic, DMA, SMP and interrupt safe scrub function.
+ * Implements the per arch atomic_scrub() that EDAC use for software
+ * ECC scrubbing.  It reads memory and then writes back the original
+ * value, allowing the hardware to detect and correct memory errors.
+ */
+static inline void atomic_scrub(void *va, u32 size)
+{
+#if __LINUX_ARM_ARCH__ >= 6
+	unsigned int *virt_addr = va;
+	unsigned int temp, temp2;
+	unsigned int i;
+
+	for (i = 0; i < size / sizeof(*virt_addr); i++, virt_addr++) {
+		/* Very carefully read and write to memory atomically
+		 * so we are interrupt, DMA and SMP safe.
+		 */
+		__asm__ __volatile__("\n"
+			"1:	ldrex	%0, [%2]\n"
+			"	strex	%1, %0, [%2]\n"
+			"	teq	%1, #0\n"
+			"	bne	1b\n"
+			: "=&r"(temp), "=&r"(temp2)
+			: "r"(virt_addr)
+			: "cc");
+	}
+#endif
+}
+
+#endif
diff --git a/arch/arm/include/asm/elf.h b/arch/arm/include/asm/elf.h
new file mode 100644
index 000000000..d2315ffd8
--- /dev/null
+++ b/arch/arm/include/asm/elf.h
@@ -0,0 +1,143 @@
+#ifndef __ASMARM_ELF_H
+#define __ASMARM_ELF_H
+
+#include <asm/auxvec.h>
+#include <asm/hwcap.h>
+#include <asm/vdso_datapage.h>
+
+/*
+ * ELF register definitions..
+ */
+#include <asm/ptrace.h>
+#include <asm/user.h>
+
+struct task_struct;
+
+typedef unsigned long elf_greg_t;
+typedef unsigned long elf_freg_t[3];
+
+#define ELF_NGREG (sizeof (struct pt_regs) / sizeof(elf_greg_t))
+typedef elf_greg_t elf_gregset_t[ELF_NGREG];
+
+typedef struct user_fp elf_fpregset_t;
+
+#define EF_ARM_EABI_MASK	0xff000000
+#define EF_ARM_EABI_UNKNOWN	0x00000000
+#define EF_ARM_EABI_VER1	0x01000000
+#define EF_ARM_EABI_VER2	0x02000000
+#define EF_ARM_EABI_VER3	0x03000000
+#define EF_ARM_EABI_VER4	0x04000000
+#define EF_ARM_EABI_VER5	0x05000000
+
+#define EF_ARM_BE8		0x00800000	/* ABI 4,5 */
+#define EF_ARM_LE8		0x00400000	/* ABI 4,5 */
+#define EF_ARM_MAVERICK_FLOAT	0x00000800	/* ABI 0 */
+#define EF_ARM_VFP_FLOAT	0x00000400	/* ABI 0 */
+#define EF_ARM_SOFT_FLOAT	0x00000200	/* ABI 0 */
+#define EF_ARM_OLD_ABI		0x00000100	/* ABI 0 */
+#define EF_ARM_NEW_ABI		0x00000080	/* ABI 0 */
+#define EF_ARM_ALIGN8		0x00000040	/* ABI 0 */
+#define EF_ARM_PIC		0x00000020	/* ABI 0 */
+#define EF_ARM_MAPSYMSFIRST	0x00000010	/* ABI 2 */
+#define EF_ARM_APCS_FLOAT	0x00000010	/* ABI 0, floats in fp regs */
+#define EF_ARM_DYNSYMSUSESEGIDX	0x00000008	/* ABI 2 */
+#define EF_ARM_APCS_26		0x00000008	/* ABI 0 */
+#define EF_ARM_SYMSARESORTED	0x00000004	/* ABI 1,2 */
+#define EF_ARM_INTERWORK	0x00000004	/* ABI 0 */
+#define EF_ARM_HASENTRY		0x00000002	/* All */
+#define EF_ARM_RELEXEC		0x00000001	/* All */
+
+#define R_ARM_NONE		0
+#define R_ARM_PC24		1
+#define R_ARM_ABS32		2
+#define R_ARM_CALL		28
+#define R_ARM_JUMP24		29
+#define R_ARM_TARGET1		38
+#define R_ARM_V4BX		40
+#define R_ARM_PREL31		42
+#define R_ARM_MOVW_ABS_NC	43
+#define R_ARM_MOVT_ABS		44
+
+#define R_ARM_THM_CALL		10
+#define R_ARM_THM_JUMP24	30
+#define R_ARM_THM_MOVW_ABS_NC	47
+#define R_ARM_THM_MOVT_ABS	48
+
+/*
+ * These are used to set parameters in the core dumps.
+ */
+#define ELF_CLASS	ELFCLASS32
+#ifdef __ARMEB__
+#define ELF_DATA	ELFDATA2MSB
+#else
+#define ELF_DATA	ELFDATA2LSB
+#endif
+#define ELF_ARCH	EM_ARM
+
+/*
+ * 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.
+ *
+ * For now we just provide a fairly general string that describes the
+ * processor family.  This could be made more specific later if someone
+ * implemented optimisations that require it.  26-bit CPUs give you
+ * "v1l" for ARM2 (no SWP) and "v2l" for anything else (ARM1 isn't
+ * supported).  32-bit CPUs give you "v3[lb]" for anything based on an
+ * ARM6 or ARM7 core and "armv4[lb]" for anything based on a StrongARM-1
+ * core.
+ */
+#define ELF_PLATFORM_SIZE 8
+#define ELF_PLATFORM	(elf_platform)
+
+extern char elf_platform[];
+
+struct elf32_hdr;
+
+/*
+ * This is used to ensure we don't load something for the wrong architecture.
+ */
+extern int elf_check_arch(const struct elf32_hdr *);
+#define elf_check_arch elf_check_arch
+
+#define vmcore_elf64_check_arch(x) (0)
+
+extern int arm_elf_read_implies_exec(const struct elf32_hdr *, int);
+#define elf_read_implies_exec(ex,stk) arm_elf_read_implies_exec(&(ex), stk)
+
+struct task_struct;
+int dump_task_regs(struct task_struct *t, elf_gregset_t *elfregs);
+#define ELF_CORE_COPY_TASK_REGS dump_task_regs
+
+#define CORE_DUMP_USE_REGSET
+#define ELF_EXEC_PAGESIZE	4096
+
+/* This is the location that an ET_DYN program is loaded if exec'ed.  Typical
+   use of this is to invoke "./ld.so someprog" to test out a new version of
+   the loader.  We need to make sure that it is out of the way of the program
+   that it will "exec", and that there is sufficient room for the brk.  */
+
+#define ELF_ET_DYN_BASE	(TASK_SIZE / 3 * 2)
+
+/* When the program starts, a1 contains a pointer to a function to be 
+   registered with atexit, as per the SVR4 ABI.  A value of 0 means we 
+   have no such handler.  */
+#define ELF_PLAT_INIT(_r, load_addr)	(_r)->ARM_r0 = 0
+
+extern void elf_set_personality(const struct elf32_hdr *);
+#define SET_PERSONALITY(ex)	elf_set_personality(&(ex))
+
+#ifdef CONFIG_MMU
+#ifdef CONFIG_VDSO
+#define ARCH_DLINFO						\
+do {								\
+	NEW_AUX_ENT(AT_SYSINFO_EHDR,				\
+		    (elf_addr_t)current->mm->context.vdso);	\
+} while (0)
+#endif
+#define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1
+struct linux_binprm;
+int arch_setup_additional_pages(struct linux_binprm *, int);
+#endif
+
+#endif
diff --git a/arch/arm/include/asm/entry-macro-multi.S b/arch/arm/include/asm/entry-macro-multi.S
new file mode 100644
index 000000000..469a2b30f
--- /dev/null
+++ b/arch/arm/include/asm/entry-macro-multi.S
@@ -0,0 +1,39 @@
+#include <asm/assembler.h>
+
+/*
+ * Interrupt handling.  Preserves r7, r8, r9
+ */
+	.macro	arch_irq_handler_default
+	get_irqnr_preamble r6, lr
+1:	get_irqnr_and_base r0, r2, r6, lr
+	movne	r1, sp
+	@
+	@ routine called with r0 = irq number, r1 = struct pt_regs *
+	@
+	adrne	lr, BSYM(1b)
+	bne	asm_do_IRQ
+
+#ifdef CONFIG_SMP
+	/*
+	 * XXX
+	 *
+	 * this macro assumes that irqstat (r2) and base (r6) are
+	 * preserved from get_irqnr_and_base above
+	 */
+	ALT_SMP(test_for_ipi r0, r2, r6, lr)
+	ALT_UP_B(9997f)
+	movne	r1, sp
+	adrne	lr, BSYM(1b)
+	bne	do_IPI
+#endif
+9997:
+	.endm
+
+	.macro	arch_irq_handler, symbol_name
+	.align	5
+	.global \symbol_name
+\symbol_name:
+	mov	r8, lr
+	arch_irq_handler_default
+	ret	r8
+	.endm
diff --git a/arch/arm/include/asm/exception.h b/arch/arm/include/asm/exception.h
new file mode 100644
index 000000000..5abaf5bbd
--- /dev/null
+++ b/arch/arm/include/asm/exception.h
@@ -0,0 +1,19 @@
+/*
+ * Annotations for marking C functions as exception handlers.
+ *
+ * These should only be used for C functions that are called from the low
+ * level exception entry code and not any intervening C code.
+ */
+#ifndef __ASM_ARM_EXCEPTION_H
+#define __ASM_ARM_EXCEPTION_H
+
+#include <linux/ftrace.h>
+
+#define __exception	__attribute__((section(".exception.text")))
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+#define __exception_irq_entry	__irq_entry
+#else
+#define __exception_irq_entry	__exception
+#endif
+
+#endif /* __ASM_ARM_EXCEPTION_H */
diff --git a/arch/arm/include/asm/fb.h b/arch/arm/include/asm/fb.h
new file mode 100644
index 000000000..d92e99cd8
--- /dev/null
+++ b/arch/arm/include/asm/fb.h
@@ -0,0 +1,19 @@
+#ifndef _ASM_FB_H_
+#define _ASM_FB_H_
+
+#include <linux/fb.h>
+#include <linux/fs.h>
+#include <asm/page.h>
+
+static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma,
+				unsigned long off)
+{
+	vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
+}
+
+static inline int fb_is_primary_device(struct fb_info *info)
+{
+	return 0;
+}
+
+#endif /* _ASM_FB_H_ */
diff --git a/arch/arm/include/asm/fiq.h b/arch/arm/include/asm/fiq.h
new file mode 100644
index 000000000..d493d0b74
--- /dev/null
+++ b/arch/arm/include/asm/fiq.h
@@ -0,0 +1,56 @@
+/*
+ *  arch/arm/include/asm/fiq.h
+ *
+ * Support for FIQ on ARM architectures.
+ * Written by Philip Blundell <philb@gnu.org>, 1998
+ * Re-written by Russell King
+ *
+ * NOTE: The FIQ mode registers are not magically preserved across
+ * suspend/resume.
+ *
+ * Drivers which require these registers to be preserved across power
+ * management operations must implement appropriate suspend/resume handlers to
+ * save and restore them.
+ */
+
+#ifndef __ASM_FIQ_H
+#define __ASM_FIQ_H
+
+#include <asm/ptrace.h>
+
+struct fiq_handler {
+	struct fiq_handler *next;
+	/* Name
+	 */
+	const char *name;
+	/* Called to ask driver to relinquish/
+	 * reacquire FIQ
+	 * return zero to accept, or -<errno>
+	 */
+	int (*fiq_op)(void *, int relinquish);
+	/* data for the relinquish/reacquire functions
+	 */
+	void *dev_id;
+};
+
+extern int claim_fiq(struct fiq_handler *f);
+extern void release_fiq(struct fiq_handler *f);
+extern void set_fiq_handler(void *start, unsigned int length);
+extern void enable_fiq(int fiq);
+extern void disable_fiq(int fiq);
+
+/* helpers defined in fiqasm.S: */
+extern void __set_fiq_regs(unsigned long const *regs);
+extern void __get_fiq_regs(unsigned long *regs);
+
+static inline void set_fiq_regs(struct pt_regs const *regs)
+{
+	__set_fiq_regs(&regs->ARM_r8);
+}
+
+static inline void get_fiq_regs(struct pt_regs *regs)
+{
+	__get_fiq_regs(&regs->ARM_r8);
+}
+
+#endif
diff --git a/arch/arm/include/asm/firmware.h b/arch/arm/include/asm/firmware.h
new file mode 100644
index 000000000..89aefe10d
--- /dev/null
+++ b/arch/arm/include/asm/firmware.h
@@ -0,0 +1,78 @@
+/*
+ * Copyright (C) 2012 Samsung Electronics.
+ * Kyungmin Park <kyungmin.park@samsung.com>
+ * Tomasz Figa <t.figa@samsung.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.
+ */
+
+#ifndef __ASM_ARM_FIRMWARE_H
+#define __ASM_ARM_FIRMWARE_H
+
+#include <linux/bug.h>
+
+/*
+ * struct firmware_ops
+ *
+ * A structure to specify available firmware operations.
+ *
+ * A filled up structure can be registered with register_firmware_ops().
+ */
+struct firmware_ops {
+	/*
+	 * Inform the firmware we intend to enter CPU idle mode
+	 */
+	int (*prepare_idle)(void);
+	/*
+	 * Enters CPU idle mode
+	 */
+	int (*do_idle)(unsigned long mode);
+	/*
+	 * Sets boot address of specified physical CPU
+	 */
+	int (*set_cpu_boot_addr)(int cpu, unsigned long boot_addr);
+	/*
+	 * Boots specified physical CPU
+	 */
+	int (*cpu_boot)(int cpu);
+	/*
+	 * Initializes L2 cache
+	 */
+	int (*l2x0_init)(void);
+	/*
+	 * Enter system-wide suspend.
+	 */
+	int (*suspend)(void);
+	/*
+	 * Restore state of privileged hardware after system-wide suspend.
+	 */
+	int (*resume)(void);
+};
+
+/* Global pointer for current firmware_ops structure, can't be NULL. */
+extern const struct firmware_ops *firmware_ops;
+
+/*
+ * call_firmware_op(op, ...)
+ *
+ * Checks if firmware operation is present and calls it,
+ * otherwise returns -ENOSYS
+ */
+#define call_firmware_op(op, ...)					\
+	((firmware_ops->op) ? firmware_ops->op(__VA_ARGS__) : (-ENOSYS))
+
+/*
+ * register_firmware_ops(ops)
+ *
+ * A function to register platform firmware_ops struct.
+ */
+static inline void register_firmware_ops(const struct firmware_ops *ops)
+{
+	BUG_ON(!ops);
+
+	firmware_ops = ops;
+}
+
+#endif
diff --git a/arch/arm/include/asm/fixmap.h b/arch/arm/include/asm/fixmap.h
new file mode 100644
index 000000000..0415eae1d
--- /dev/null
+++ b/arch/arm/include/asm/fixmap.h
@@ -0,0 +1,25 @@
+#ifndef _ASM_FIXMAP_H
+#define _ASM_FIXMAP_H
+
+#define FIXADDR_START		0xffc00000UL
+#define FIXADDR_END		0xfff00000UL
+#define FIXADDR_TOP		(FIXADDR_END - PAGE_SIZE)
+
+#include <asm/kmap_types.h>
+
+enum fixed_addresses {
+	FIX_KMAP_BEGIN,
+	FIX_KMAP_END = FIX_KMAP_BEGIN + (KM_TYPE_NR * NR_CPUS) - 1,
+
+	/* Support writing RO kernel text via kprobes, jump labels, etc. */
+	FIX_TEXT_POKE0,
+	FIX_TEXT_POKE1,
+
+	__end_of_fixed_addresses
+};
+
+void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t prot);
+
+#include <asm-generic/fixmap.h>
+
+#endif
diff --git a/arch/arm/include/asm/flat.h b/arch/arm/include/asm/flat.h
new file mode 100644
index 000000000..e847d2335
--- /dev/null
+++ b/arch/arm/include/asm/flat.h
@@ -0,0 +1,16 @@
+/*
+ * arch/arm/include/asm/flat.h -- uClinux flat-format executables
+ */
+
+#ifndef __ARM_FLAT_H__
+#define __ARM_FLAT_H__
+
+#define	flat_argvp_envp_on_stack()		1
+#define	flat_old_ram_flag(flags)		(flags)
+#define	flat_reloc_valid(reloc, size)		((reloc) <= (size))
+#define	flat_get_addr_from_rp(rp, relval, flags, persistent) ((void)persistent,get_unaligned(rp))
+#define	flat_put_addr_at_rp(rp, val, relval)	put_unaligned(val,rp)
+#define	flat_get_relocate_addr(rel)		(rel)
+#define	flat_set_persistent(relval, p)		0
+
+#endif /* __ARM_FLAT_H__ */
diff --git a/arch/arm/include/asm/floppy.h b/arch/arm/include/asm/floppy.h
new file mode 100644
index 000000000..f4882553f
--- /dev/null
+++ b/arch/arm/include/asm/floppy.h
@@ -0,0 +1,148 @@
+/*
+ *  arch/arm/include/asm/floppy.h
+ *
+ *  Copyright (C) 1996-2000 Russell King
+ *
+ * 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.
+ *
+ *  Note that we don't touch FLOPPY_DMA nor FLOPPY_IRQ here
+ */
+#ifndef __ASM_ARM_FLOPPY_H
+#define __ASM_ARM_FLOPPY_H
+#if 0
+#include <mach/floppy.h>
+#endif
+
+#define fd_outb(val,port)			\
+	do {					\
+		if ((port) == FD_DOR)		\
+			fd_setdor((val));	\
+		else				\
+			outb((val),(port));	\
+	} while(0)
+
+#define fd_inb(port)		inb((port))
+#define fd_request_irq()	request_irq(IRQ_FLOPPYDISK,floppy_interrupt,\
+					    0,"floppy",NULL)
+#define fd_free_irq()		free_irq(IRQ_FLOPPYDISK,NULL)
+#define fd_disable_irq()	disable_irq(IRQ_FLOPPYDISK)
+#define fd_enable_irq()		enable_irq(IRQ_FLOPPYDISK)
+
+static inline int fd_dma_setup(void *data, unsigned int length,
+			       unsigned int mode, unsigned long addr)
+{
+	set_dma_mode(DMA_FLOPPY, mode);
+	__set_dma_addr(DMA_FLOPPY, data);
+	set_dma_count(DMA_FLOPPY, length);
+	virtual_dma_port = addr;
+	enable_dma(DMA_FLOPPY);
+	return 0;
+}
+#define fd_dma_setup		fd_dma_setup
+
+#define fd_request_dma()	request_dma(DMA_FLOPPY,"floppy")
+#define fd_free_dma()		free_dma(DMA_FLOPPY)
+#define fd_disable_dma()	disable_dma(DMA_FLOPPY)
+
+/* need to clean up dma.h */
+#define DMA_FLOPPYDISK		DMA_FLOPPY
+
+/* Floppy_selects is the list of DOR's to select drive fd
+ *
+ * On initialisation, the floppy list is scanned, and the drives allocated
+ * in the order that they are found.  This is done by seeking the drive
+ * to a non-zero track, and then restoring it to track 0.  If an error occurs,
+ * then there is no floppy drive present.       [to be put back in again]
+ */
+static unsigned char floppy_selects[2][4] =
+{
+	{ 0x10, 0x21, 0x23, 0x33 },
+	{ 0x10, 0x21, 0x23, 0x33 }
+};
+
+#define fd_setdor(dor)								\
+do {										\
+	int new_dor = (dor);							\
+	if (new_dor & 0xf0)							\
+		new_dor = (new_dor & 0x0c) | floppy_selects[fdc][new_dor & 3];	\
+	else									\
+		new_dor &= 0x0c;						\
+	outb(new_dor, FD_DOR);							\
+} while (0)
+
+/*
+ * Someday, we'll automatically detect which drives are present...
+ */
+static inline void fd_scandrives (void)
+{
+#if 0
+	int floppy, drive_count;
+
+	fd_disable_irq();
+	raw_cmd = &default_raw_cmd;
+	raw_cmd->flags = FD_RAW_SPIN | FD_RAW_NEED_SEEK;
+	raw_cmd->track = 0;
+	raw_cmd->rate = ?;
+	drive_count = 0;
+	for (floppy = 0; floppy < 4; floppy ++) {
+		current_drive = drive_count;
+		/*
+		 * Turn on floppy motor
+		 */
+		if (start_motor(redo_fd_request))
+			continue;
+		/*
+		 * Set up FDC
+		 */
+		fdc_specify();
+		/*
+		 * Tell FDC to recalibrate
+		 */
+		output_byte(FD_RECALIBRATE);
+		LAST_OUT(UNIT(floppy));
+		/* wait for command to complete */
+		if (!successful) {
+			int i;
+			for (i = drive_count; i < 3; i--)
+				floppy_selects[fdc][i] = floppy_selects[fdc][i + 1];
+			floppy_selects[fdc][3] = 0;
+			floppy -= 1;
+		} else
+			drive_count++;
+	}
+#else
+	floppy_selects[0][0] = 0x10;
+	floppy_selects[0][1] = 0x21;
+	floppy_selects[0][2] = 0x23;
+	floppy_selects[0][3] = 0x33;
+#endif
+}
+
+#define FDC1 (0x3f0)
+
+#define FLOPPY0_TYPE 4
+#define FLOPPY1_TYPE 4
+
+#define N_FDC 1
+#define N_DRIVE 4
+
+#define CROSS_64KB(a,s) (0)
+
+/*
+ * This allows people to reverse the order of
+ * fd0 and fd1, in case their hardware is
+ * strangely connected (as some RiscPCs
+ * and A5000s seem to be).
+ */
+static void driveswap(int *ints, int dummy, int dummy2)
+{
+	floppy_selects[0][0] ^= floppy_selects[0][1];
+	floppy_selects[0][1] ^= floppy_selects[0][0];
+	floppy_selects[0][0] ^= floppy_selects[0][1];
+}
+
+#define EXTRA_FLOPPY_PARAMS ,{ "driveswap", &driveswap, NULL, 0, 0 }
+	
+#endif
diff --git a/arch/arm/include/asm/fncpy.h b/arch/arm/include/asm/fncpy.h
new file mode 100644
index 000000000..de5354746
--- /dev/null
+++ b/arch/arm/include/asm/fncpy.h
@@ -0,0 +1,94 @@
+/*
+ * arch/arm/include/asm/fncpy.h - helper macros for function body copying
+ *
+ * Copyright (C) 2011 Linaro Limited
+ *
+ * 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, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+/*
+ * These macros are intended for use when there is a need to copy a low-level
+ * function body into special memory.
+ *
+ * For example, when reconfiguring the SDRAM controller, the code doing the
+ * reconfiguration may need to run from SRAM.
+ *
+ * NOTE: that the copied function body must be entirely self-contained and
+ * position-independent in order for this to work properly.
+ *
+ * NOTE: in order for embedded literals and data to get referenced correctly,
+ * the alignment of functions must be preserved when copying.  To ensure this,
+ * the source and destination addresses for fncpy() must be aligned to a
+ * multiple of 8 bytes: you will be get a BUG() if this condition is not met.
+ * You will typically need a ".align 3" directive in the assembler where the
+ * function to be copied is defined, and ensure that your allocator for the
+ * destination buffer returns 8-byte-aligned pointers.
+ *
+ * Typical usage example:
+ *
+ * extern int f(args);
+ * extern uint32_t size_of_f;
+ * int (*copied_f)(args);
+ * void *sram_buffer;
+ *
+ * copied_f = fncpy(sram_buffer, &f, size_of_f);
+ *
+ * ... later, call the function: ...
+ *
+ * copied_f(args);
+ *
+ * The size of the function to be copied can't be determined from C:
+ * this must be determined by other means, such as adding assmbler directives
+ * in the file where f is defined.
+ */
+
+#ifndef __ASM_FNCPY_H
+#define __ASM_FNCPY_H
+
+#include <linux/types.h>
+#include <linux/string.h>
+
+#include <asm/bug.h>
+#include <asm/cacheflush.h>
+
+/*
+ * Minimum alignment requirement for the source and destination addresses
+ * for function copying.
+ */
+#define FNCPY_ALIGN 8
+
+#define fncpy(dest_buf, funcp, size) ({					\
+	uintptr_t __funcp_address;					\
+	typeof(funcp) __result;						\
+									\
+	asm("" : "=r" (__funcp_address) : "0" (funcp));			\
+									\
+	/*								\
+	 * Ensure alignment of source and destination addresses,	\
+	 * disregarding the function's Thumb bit:			\
+	 */								\
+	BUG_ON((uintptr_t)(dest_buf) & (FNCPY_ALIGN - 1) ||		\
+		(__funcp_address & ~(uintptr_t)1 & (FNCPY_ALIGN - 1)));	\
+									\
+	memcpy(dest_buf, (void const *)(__funcp_address & ~1), size);	\
+	flush_icache_range((unsigned long)(dest_buf),			\
+		(unsigned long)(dest_buf) + (size));			\
+									\
+	asm("" : "=r" (__result)					\
+		: "0" ((uintptr_t)(dest_buf) | (__funcp_address & 1)));	\
+									\
+	__result;							\
+})
+
+#endif /* !__ASM_FNCPY_H */
diff --git a/arch/arm/include/asm/fpstate.h b/arch/arm/include/asm/fpstate.h
new file mode 100644
index 000000000..3ad4c10d0
--- /dev/null
+++ b/arch/arm/include/asm/fpstate.h
@@ -0,0 +1,93 @@
+/*
+ *  arch/arm/include/asm/fpstate.h
+ *
+ *  Copyright (C) 1995 Russell King
+ *
+ * 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.
+ */
+
+#ifndef __ASM_ARM_FPSTATE_H
+#define __ASM_ARM_FPSTATE_H
+
+
+#ifndef __ASSEMBLY__
+
+/*
+ * VFP storage area has:
+ *  - FPEXC, FPSCR, FPINST and FPINST2.
+ *  - 16 or 32 double precision data registers
+ *  - an implementation-dependent word of state for FLDMX/FSTMX (pre-ARMv6)
+ * 
+ *  FPEXC will always be non-zero once the VFP has been used in this process.
+ */
+
+struct vfp_hard_struct {
+#ifdef CONFIG_VFPv3
+	__u64 fpregs[32];
+#else
+	__u64 fpregs[16];
+#endif
+#if __LINUX_ARM_ARCH__ < 6
+	__u32 fpmx_state;
+#endif
+	__u32 fpexc;
+	__u32 fpscr;
+	/*
+	 * VFP implementation specific state
+	 */
+	__u32 fpinst;
+	__u32 fpinst2;
+
+#ifdef CONFIG_SMP
+	__u32 cpu;
+#endif
+};
+
+union vfp_state {
+	struct vfp_hard_struct	hard;
+};
+
+extern void vfp_flush_thread(union vfp_state *);
+extern void vfp_release_thread(union vfp_state *);
+
+#define FP_HARD_SIZE 35
+
+struct fp_hard_struct {
+	unsigned int save[FP_HARD_SIZE];		/* as yet undefined */
+};
+
+#define FP_SOFT_SIZE 35
+
+struct fp_soft_struct {
+	unsigned int save[FP_SOFT_SIZE];		/* undefined information */
+};
+
+#define IWMMXT_SIZE	0x98
+
+struct iwmmxt_struct {
+	unsigned int save[IWMMXT_SIZE / sizeof(unsigned int)];
+};
+
+union fp_state {
+	struct fp_hard_struct	hard;
+	struct fp_soft_struct	soft;
+#ifdef CONFIG_IWMMXT
+	struct iwmmxt_struct	iwmmxt;
+#endif
+};
+
+#define FP_SIZE (sizeof(union fp_state) / sizeof(int))
+
+struct crunch_state {
+	unsigned int	mvdx[16][2];
+	unsigned int	mvax[4][3];
+	unsigned int	dspsc[2];
+};
+
+#define CRUNCH_SIZE	sizeof(struct crunch_state)
+
+#endif
+
+#endif
diff --git a/arch/arm/include/asm/ftrace.h b/arch/arm/include/asm/ftrace.h
new file mode 100644
index 000000000..bfe2a2f5a
--- /dev/null
+++ b/arch/arm/include/asm/ftrace.h
@@ -0,0 +1,59 @@
+#ifndef _ASM_ARM_FTRACE
+#define _ASM_ARM_FTRACE
+
+#ifdef CONFIG_FUNCTION_TRACER
+#define MCOUNT_ADDR		((unsigned long)(__gnu_mcount_nc))
+#define MCOUNT_INSN_SIZE	4 /* sizeof mcount call */
+
+#ifndef __ASSEMBLY__
+extern void mcount(void);
+extern void __gnu_mcount_nc(void);
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+struct dyn_arch_ftrace {
+#ifdef CONFIG_OLD_MCOUNT
+	bool	old_mcount;
+#endif
+};
+
+static inline unsigned long ftrace_call_adjust(unsigned long addr)
+{
+	/* With Thumb-2, the recorded addresses have the lsb set */
+	return addr & ~1;
+}
+
+extern void ftrace_caller_old(void);
+extern void ftrace_call_old(void);
+#endif
+
+#endif
+
+#endif
+
+#ifndef __ASSEMBLY__
+
+#if defined(CONFIG_FRAME_POINTER) && !defined(CONFIG_ARM_UNWIND)
+/*
+ * return_address uses walk_stackframe to do it's work.  If both
+ * CONFIG_FRAME_POINTER=y and CONFIG_ARM_UNWIND=y walk_stackframe uses unwind
+ * information.  For this to work in the function tracer many functions would
+ * have to be marked with __notrace.  So for now just depend on
+ * !CONFIG_ARM_UNWIND.
+ */
+
+void *return_address(unsigned int);
+
+#else
+
+static inline void *return_address(unsigned int level)
+{
+	return NULL;
+}
+
+#endif
+
+#define ftrace_return_address(n) return_address(n)
+
+#endif /* ifndef __ASSEMBLY__ */
+
+#endif /* _ASM_ARM_FTRACE */
diff --git a/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h
new file mode 100644
index 000000000..4e78065a1
--- /dev/null
+++ b/arch/arm/include/asm/futex.h
@@ -0,0 +1,166 @@
+#ifndef _ASM_ARM_FUTEX_H
+#define _ASM_ARM_FUTEX_H
+
+#ifdef __KERNEL__
+
+#include <linux/futex.h>
+#include <linux/uaccess.h>
+#include <asm/errno.h>
+
+#define __futex_atomic_ex_table(err_reg)			\
+	"3:\n"							\
+	"	.pushsection __ex_table,\"a\"\n"		\
+	"	.align	3\n"					\
+	"	.long	1b, 4f, 2b, 4f\n"			\
+	"	.popsection\n"					\
+	"	.pushsection .text.fixup,\"ax\"\n"		\
+	"	.align	2\n"					\
+	"4:	mov	%0, " err_reg "\n"			\
+	"	b	3b\n"					\
+	"	.popsection"
+
+#ifdef CONFIG_SMP
+
+#define __futex_atomic_op(insn, ret, oldval, tmp, uaddr, oparg)	\
+	smp_mb();						\
+	prefetchw(uaddr);					\
+	__asm__ __volatile__(					\
+	"1:	ldrex	%1, [%3]\n"				\
+	"	" insn "\n"					\
+	"2:	strex	%2, %0, [%3]\n"				\
+	"	teq	%2, #0\n"				\
+	"	bne	1b\n"					\
+	"	mov	%0, #0\n"				\
+	__futex_atomic_ex_table("%5")				\
+	: "=&r" (ret), "=&r" (oldval), "=&r" (tmp)		\
+	: "r" (uaddr), "r" (oparg), "Ir" (-EFAULT)		\
+	: "cc", "memory")
+
+static inline int
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+			      u32 oldval, u32 newval)
+{
+	int ret;
+	u32 val;
+
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
+		return -EFAULT;
+
+	smp_mb();
+	/* Prefetching cannot fault */
+	prefetchw(uaddr);
+	__asm__ __volatile__("@futex_atomic_cmpxchg_inatomic\n"
+	"1:	ldrex	%1, [%4]\n"
+	"	teq	%1, %2\n"
+	"	ite	eq	@ explicit IT needed for the 2b label\n"
+	"2:	strexeq	%0, %3, [%4]\n"
+	"	movne	%0, #0\n"
+	"	teq	%0, #0\n"
+	"	bne	1b\n"
+	__futex_atomic_ex_table("%5")
+	: "=&r" (ret), "=&r" (val)
+	: "r" (oldval), "r" (newval), "r" (uaddr), "Ir" (-EFAULT)
+	: "cc", "memory");
+	smp_mb();
+
+	*uval = val;
+	return ret;
+}
+
+#else /* !SMP, we can work around lack of atomic ops by disabling preemption */
+
+#include <linux/preempt.h>
+#include <asm/domain.h>
+
+#define __futex_atomic_op(insn, ret, oldval, tmp, uaddr, oparg)	\
+	__asm__ __volatile__(					\
+	"1:	" TUSER(ldr) "	%1, [%3]\n"			\
+	"	" insn "\n"					\
+	"2:	" TUSER(str) "	%0, [%3]\n"			\
+	"	mov	%0, #0\n"				\
+	__futex_atomic_ex_table("%5")				\
+	: "=&r" (ret), "=&r" (oldval), "=&r" (tmp)		\
+	: "r" (uaddr), "r" (oparg), "Ir" (-EFAULT)		\
+	: "cc", "memory")
+
+static inline int
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+			      u32 oldval, u32 newval)
+{
+	int ret = 0;
+	u32 val;
+
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
+		return -EFAULT;
+
+	__asm__ __volatile__("@futex_atomic_cmpxchg_inatomic\n"
+	"1:	" TUSER(ldr) "	%1, [%4]\n"
+	"	teq	%1, %2\n"
+	"	it	eq	@ explicit IT needed for the 2b label\n"
+	"2:	" TUSER(streq) "	%3, [%4]\n"
+	__futex_atomic_ex_table("%5")
+	: "+r" (ret), "=&r" (val)
+	: "r" (oldval), "r" (newval), "r" (uaddr), "Ir" (-EFAULT)
+	: "cc", "memory");
+
+	*uval = val;
+	return ret;
+}
+
+#endif /* !SMP */
+
+static inline int
+futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
+{
+	int op = (encoded_op >> 28) & 7;
+	int cmp = (encoded_op >> 24) & 15;
+	int oparg = (encoded_op << 8) >> 20;
+	int cmparg = (encoded_op << 20) >> 20;
+	int oldval = 0, ret, tmp;
+
+	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
+		oparg = 1 << oparg;
+
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
+		return -EFAULT;
+
+	pagefault_disable();	/* implies preempt_disable() */
+
+	switch (op) {
+	case FUTEX_OP_SET:
+		__futex_atomic_op("mov	%0, %4", ret, oldval, tmp, uaddr, oparg);
+		break;
+	case FUTEX_OP_ADD:
+		__futex_atomic_op("add	%0, %1, %4", ret, oldval, tmp, uaddr, oparg);
+		break;
+	case FUTEX_OP_OR:
+		__futex_atomic_op("orr	%0, %1, %4", ret, oldval, tmp, uaddr, oparg);
+		break;
+	case FUTEX_OP_ANDN:
+		__futex_atomic_op("and	%0, %1, %4", ret, oldval, tmp, uaddr, ~oparg);
+		break;
+	case FUTEX_OP_XOR:
+		__futex_atomic_op("eor	%0, %1, %4", ret, oldval, tmp, uaddr, oparg);
+		break;
+	default:
+		ret = -ENOSYS;
+	}
+
+	pagefault_enable();	/* subsumes preempt_enable() */
+
+	if (!ret) {
+		switch (cmp) {
+		case FUTEX_OP_CMP_EQ: ret = (oldval == cmparg); break;
+		case FUTEX_OP_CMP_NE: ret = (oldval != cmparg); break;
+		case FUTEX_OP_CMP_LT: ret = (oldval < cmparg); break;
+		case FUTEX_OP_CMP_GE: ret = (oldval >= cmparg); break;
+		case FUTEX_OP_CMP_LE: ret = (oldval <= cmparg); break;
+		case FUTEX_OP_CMP_GT: ret = (oldval > cmparg); break;
+		default: ret = -ENOSYS;
+		}
+	}
+	return ret;
+}
+
+#endif /* __KERNEL__ */
+#endif /* _ASM_ARM_FUTEX_H */
diff --git a/arch/arm/include/asm/glue-cache.h b/arch/arm/include/asm/glue-cache.h
new file mode 100644
index 000000000..a3c24cd5b
--- /dev/null
+++ b/arch/arm/include/asm/glue-cache.h
@@ -0,0 +1,166 @@
+/*
+ *  arch/arm/include/asm/glue-cache.h
+ *
+ *  Copyright (C) 1999-2002 Russell King
+ *
+ * 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.
+ */
+#ifndef ASM_GLUE_CACHE_H
+#define ASM_GLUE_CACHE_H
+
+#include <asm/glue.h>
+
+/*
+ *	Cache Model
+ *	===========
+ */
+#undef _CACHE
+#undef MULTI_CACHE
+
+#if defined(CONFIG_CPU_CACHE_V4)
+# ifdef _CACHE
+#  define MULTI_CACHE 1
+# else
+#  define _CACHE v4
+# endif
+#endif
+
+#if defined(CONFIG_CPU_ARM920T) || defined(CONFIG_CPU_ARM922T) || \
+    defined(CONFIG_CPU_ARM925T) || defined(CONFIG_CPU_ARM1020) || \
+    defined(CONFIG_CPU_ARM1026)
+# define MULTI_CACHE 1
+#endif
+
+#if defined(CONFIG_CPU_FA526)
+# ifdef _CACHE
+#  define MULTI_CACHE 1
+# else
+#  define _CACHE fa
+# endif
+#endif
+
+#if defined(CONFIG_CPU_ARM926T)
+# ifdef _CACHE
+#  define MULTI_CACHE 1
+# else
+#  define _CACHE arm926
+# endif
+#endif
+
+#if defined(CONFIG_CPU_ARM940T)
+# ifdef _CACHE
+#  define MULTI_CACHE 1
+# else
+#  define _CACHE arm940
+# endif
+#endif
+
+#if defined(CONFIG_CPU_ARM946E)
+# ifdef _CACHE
+#  define MULTI_CACHE 1
+# else
+#  define _CACHE arm946
+# endif
+#endif
+
+#if defined(CONFIG_CPU_CACHE_V4WB)
+# ifdef _CACHE
+#  define MULTI_CACHE 1
+# else
+#  define _CACHE v4wb
+# endif
+#endif
+
+#if defined(CONFIG_CPU_XSCALE)
+# ifdef _CACHE
+#  define MULTI_CACHE 1
+# else
+#  define _CACHE xscale
+# endif
+#endif
+
+#if defined(CONFIG_CPU_XSC3)
+# ifdef _CACHE
+#  define MULTI_CACHE 1
+# else
+#  define _CACHE xsc3
+# endif
+#endif
+
+#if defined(CONFIG_CPU_MOHAWK)
+# ifdef _CACHE
+#  define MULTI_CACHE 1
+# else
+#  define _CACHE mohawk
+# endif
+#endif
+
+#if defined(CONFIG_CPU_FEROCEON)
+# define MULTI_CACHE 1
+#endif
+
+#if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_V6K)
+# ifdef _CACHE
+#  define MULTI_CACHE 1
+# else
+#  define _CACHE v6
+# endif
+#endif
+
+#if defined(CONFIG_CPU_V7)
+# ifdef _CACHE
+#  define MULTI_CACHE 1
+# else
+#  define _CACHE v7
+# endif
+#endif
+
+#if defined(CONFIG_CPU_V7M)
+# ifdef _CACHE
+#  define MULTI_CACHE 1
+# else
+#  define _CACHE nop
+# endif
+#endif
+
+#if !defined(_CACHE) && !defined(MULTI_CACHE)
+#error Unknown cache maintenance model
+#endif
+
+#ifndef __ASSEMBLER__
+static inline void nop_flush_icache_all(void) { }
+static inline void nop_flush_kern_cache_all(void) { }
+static inline void nop_flush_kern_cache_louis(void) { }
+static inline void nop_flush_user_cache_all(void) { }
+static inline void nop_flush_user_cache_range(unsigned long a,
+		unsigned long b, unsigned int c) { }
+
+static inline void nop_coherent_kern_range(unsigned long a, unsigned long b) { }
+static inline int nop_coherent_user_range(unsigned long a,
+		unsigned long b) { return 0; }
+static inline void nop_flush_kern_dcache_area(void *a, size_t s) { }
+
+static inline void nop_dma_flush_range(const void *a, const void *b) { }
+
+static inline void nop_dma_map_area(const void *s, size_t l, int f) { }
+static inline void nop_dma_unmap_area(const void *s, size_t l, int f) { }
+#endif
+
+#ifndef MULTI_CACHE
+#define __cpuc_flush_icache_all		__glue(_CACHE,_flush_icache_all)
+#define __cpuc_flush_kern_all		__glue(_CACHE,_flush_kern_cache_all)
+#define __cpuc_flush_kern_louis		__glue(_CACHE,_flush_kern_cache_louis)
+#define __cpuc_flush_user_all		__glue(_CACHE,_flush_user_cache_all)
+#define __cpuc_flush_user_range		__glue(_CACHE,_flush_user_cache_range)
+#define __cpuc_coherent_kern_range	__glue(_CACHE,_coherent_kern_range)
+#define __cpuc_coherent_user_range	__glue(_CACHE,_coherent_user_range)
+#define __cpuc_flush_dcache_area	__glue(_CACHE,_flush_kern_dcache_area)
+
+#define dmac_map_area			__glue(_CACHE,_dma_map_area)
+#define dmac_unmap_area			__glue(_CACHE,_dma_unmap_area)
+#define dmac_flush_range		__glue(_CACHE,_dma_flush_range)
+#endif
+
+#endif
diff --git a/arch/arm/include/asm/glue-df.h b/arch/arm/include/asm/glue-df.h
new file mode 100644
index 000000000..04e18b656
--- /dev/null
+++ b/arch/arm/include/asm/glue-df.h
@@ -0,0 +1,102 @@
+/*
+ *  arch/arm/include/asm/glue-df.h
+ *
+ *  Copyright (C) 1997-1999 Russell King
+ *  Copyright (C) 2000-2002 Deep Blue Solutions 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.
+ */
+#ifndef ASM_GLUE_DF_H
+#define ASM_GLUE_DF_H
+
+#include <asm/glue.h>
+
+/*
+ *	Data Abort Model
+ *	================
+ *
+ *	We have the following to choose from:
+ *	  arm7		- ARM7 style
+ *	  v4_early	- ARMv4 without Thumb early abort handler
+ *	  v4t_late	- ARMv4 with Thumb late abort handler
+ *	  v4t_early	- ARMv4 with Thumb early abort handler
+ *	  v5t_early	- ARMv5 with Thumb early abort handler
+ *	  v5tj_early	- ARMv5 with Thumb and Java early abort handler
+ *	  xscale	- ARMv5 with Thumb with Xscale extensions
+ *	  v6_early	- ARMv6 generic early abort handler
+ *	  v7_early	- ARMv7 generic early abort handler
+ */
+#undef CPU_DABORT_HANDLER
+#undef MULTI_DABORT
+
+#ifdef CONFIG_CPU_ABRT_EV4
+# ifdef CPU_DABORT_HANDLER
+#  define MULTI_DABORT 1
+# else
+#  define CPU_DABORT_HANDLER v4_early_abort
+# endif
+#endif
+
+#ifdef CONFIG_CPU_ABRT_LV4T
+# ifdef CPU_DABORT_HANDLER
+#  define MULTI_DABORT 1
+# else
+#  define CPU_DABORT_HANDLER v4t_late_abort
+# endif
+#endif
+
+#ifdef CONFIG_CPU_ABRT_EV4T
+# ifdef CPU_DABORT_HANDLER
+#  define MULTI_DABORT 1
+# else
+#  define CPU_DABORT_HANDLER v4t_early_abort
+# endif
+#endif
+
+#ifdef CONFIG_CPU_ABRT_EV5T
+# ifdef CPU_DABORT_HANDLER
+#  define MULTI_DABORT 1
+# else
+#  define CPU_DABORT_HANDLER v5t_early_abort
+# endif
+#endif
+
+#ifdef CONFIG_CPU_ABRT_EV5TJ
+# ifdef CPU_DABORT_HANDLER
+#  define MULTI_DABORT 1
+# else
+#  define CPU_DABORT_HANDLER v5tj_early_abort
+# endif
+#endif
+
+#ifdef CONFIG_CPU_ABRT_EV6
+# ifdef CPU_DABORT_HANDLER
+#  define MULTI_DABORT 1
+# else
+#  define CPU_DABORT_HANDLER v6_early_abort
+# endif
+#endif
+
+#ifdef CONFIG_CPU_ABRT_EV7
+# ifdef CPU_DABORT_HANDLER
+#  define MULTI_DABORT 1
+# else
+#  define CPU_DABORT_HANDLER v7_early_abort
+# endif
+#endif
+
+#ifdef CONFIG_CPU_ABRT_NOMMU
+# ifdef CPU_DABORT_HANDLER
+#  define MULTI_DABORT 1
+# else
+#  define CPU_DABORT_HANDLER nommu_early_abort
+# endif
+#endif
+
+#ifndef CPU_DABORT_HANDLER
+#error Unknown data abort handler type
+#endif
+
+#endif
diff --git a/arch/arm/include/asm/glue-pf.h b/arch/arm/include/asm/glue-pf.h
new file mode 100644
index 000000000..d385f37c1
--- /dev/null
+++ b/arch/arm/include/asm/glue-pf.h
@@ -0,0 +1,57 @@
+/*
+ *  arch/arm/include/asm/glue-pf.h
+ *
+ *  Copyright (C) 1997-1999 Russell King
+ *  Copyright (C) 2000-2002 Deep Blue Solutions 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.
+ */
+#ifndef ASM_GLUE_PF_H
+#define ASM_GLUE_PF_H
+
+#include <asm/glue.h>
+
+/*
+ *	Prefetch Abort Model
+ *	================
+ *
+ *	We have the following to choose from:
+ *	  legacy	- no IFSR, no IFAR
+ *	  v6		- ARMv6: IFSR, no IFAR
+ *	  v7		- ARMv7: IFSR and IFAR
+ */
+
+#undef CPU_PABORT_HANDLER
+#undef MULTI_PABORT
+
+#ifdef CONFIG_CPU_PABRT_LEGACY
+# ifdef CPU_PABORT_HANDLER
+#  define MULTI_PABORT 1
+# else
+#  define CPU_PABORT_HANDLER legacy_pabort
+# endif
+#endif
+
+#ifdef CONFIG_CPU_PABRT_V6
+# ifdef CPU_PABORT_HANDLER
+#  define MULTI_PABORT 1
+# else
+#  define CPU_PABORT_HANDLER v6_pabort
+# endif
+#endif
+
+#ifdef CONFIG_CPU_PABRT_V7
+# ifdef CPU_PABORT_HANDLER
+#  define MULTI_PABORT 1
+# else
+#  define CPU_PABORT_HANDLER v7_pabort
+# endif
+#endif
+
+#ifndef CPU_PABORT_HANDLER
+#error Unknown prefetch abort handler type
+#endif
+
+#endif
diff --git a/arch/arm/include/asm/glue-proc.h b/arch/arm/include/asm/glue-proc.h
new file mode 100644
index 000000000..74be7c220
--- /dev/null
+++ b/arch/arm/include/asm/glue-proc.h
@@ -0,0 +1,264 @@
+/*
+ *  arch/arm/include/asm/glue-proc.h
+ *
+ *  Copyright (C) 1997-1999 Russell King
+ *  Copyright (C) 2000 Deep Blue Solutions 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.
+ */
+#ifndef ASM_GLUE_PROC_H
+#define ASM_GLUE_PROC_H
+
+#include <asm/glue.h>
+
+/*
+ * Work out if we need multiple CPU support
+ */
+#undef MULTI_CPU
+#undef CPU_NAME
+
+/*
+ * CPU_NAME - the prefix for CPU related functions
+ */
+
+#ifdef CONFIG_CPU_ARM7TDMI
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_arm7tdmi
+# endif
+#endif
+
+#ifdef CONFIG_CPU_ARM720T
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_arm720
+# endif
+#endif
+
+#ifdef CONFIG_CPU_ARM740T
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_arm740
+# endif
+#endif
+
+#ifdef CONFIG_CPU_ARM9TDMI
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_arm9tdmi
+# endif
+#endif
+
+#ifdef CONFIG_CPU_ARM920T
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_arm920
+# endif
+#endif
+
+#ifdef CONFIG_CPU_ARM922T
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_arm922
+# endif
+#endif
+
+#ifdef CONFIG_CPU_FA526
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_fa526
+# endif
+#endif
+
+#ifdef CONFIG_CPU_ARM925T
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_arm925
+# endif
+#endif
+
+#ifdef CONFIG_CPU_ARM926T
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_arm926
+# endif
+#endif
+
+#ifdef CONFIG_CPU_ARM940T
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_arm940
+# endif
+#endif
+
+#ifdef CONFIG_CPU_ARM946E
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_arm946
+# endif
+#endif
+
+#ifdef CONFIG_CPU_SA110
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_sa110
+# endif
+#endif
+
+#ifdef CONFIG_CPU_SA1100
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_sa1100
+# endif
+#endif
+
+#ifdef CONFIG_CPU_ARM1020
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_arm1020
+# endif
+#endif
+
+#ifdef CONFIG_CPU_ARM1020E
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_arm1020e
+# endif
+#endif
+
+#ifdef CONFIG_CPU_ARM1022
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_arm1022
+# endif
+#endif
+
+#ifdef CONFIG_CPU_ARM1026
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_arm1026
+# endif
+#endif
+
+#ifdef CONFIG_CPU_XSCALE
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_xscale
+# endif
+#endif
+
+#ifdef CONFIG_CPU_XSC3
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_xsc3
+# endif
+#endif
+
+#ifdef CONFIG_CPU_MOHAWK
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_mohawk
+# endif
+#endif
+
+#ifdef CONFIG_CPU_FEROCEON
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_feroceon
+# endif
+#endif
+
+#if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_V6K)
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_v6
+# endif
+#endif
+
+#ifdef CONFIG_CPU_V7M
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_v7m
+# endif
+#endif
+
+#ifdef CONFIG_CPU_PJ4B
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_pj4b
+# endif
+#endif
+
+#ifdef CONFIG_CPU_V7
+/*
+ * Cortex-A9 needs a different suspend/resume function, so we need
+ * multiple CPU support for ARMv7 anyway.
+ */
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+#endif
+
+#ifndef MULTI_CPU
+#define cpu_proc_init			__glue(CPU_NAME,_proc_init)
+#define cpu_proc_fin			__glue(CPU_NAME,_proc_fin)
+#define cpu_reset			__glue(CPU_NAME,_reset)
+#define cpu_do_idle			__glue(CPU_NAME,_do_idle)
+#define cpu_dcache_clean_area		__glue(CPU_NAME,_dcache_clean_area)
+#define cpu_do_switch_mm		__glue(CPU_NAME,_switch_mm)
+#define cpu_set_pte_ext			__glue(CPU_NAME,_set_pte_ext)
+#define cpu_suspend_size		__glue(CPU_NAME,_suspend_size)
+#define cpu_do_suspend			__glue(CPU_NAME,_do_suspend)
+#define cpu_do_resume			__glue(CPU_NAME,_do_resume)
+#endif
+
+#endif
diff --git a/arch/arm/include/asm/glue.h b/arch/arm/include/asm/glue.h
new file mode 100644
index 000000000..fbf71d75e
--- /dev/null
+++ b/arch/arm/include/asm/glue.h
@@ -0,0 +1,25 @@
+/*
+ *  arch/arm/include/asm/glue.h
+ *
+ *  Copyright (C) 1997-1999 Russell King
+ *  Copyright (C) 2000-2002 Deep Blue Solutions 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 file provides the glue to stick the processor-specific bits
+ *  into the kernel in an efficient manner.  The idea is to use branches
+ *  when we're only targeting one class of TLB, or indirect calls
+ *  when we're targeting multiple classes of TLBs.
+ */
+#ifdef __KERNEL__
+
+#ifdef __STDC__
+#define ____glue(name,fn)	name##fn
+#else
+#define ____glue(name,fn)	name/**/fn
+#endif
+#define __glue(name,fn)		____glue(name,fn)
+
+#endif
diff --git a/arch/arm/include/asm/gpio.h b/arch/arm/include/asm/gpio.h
new file mode 100644
index 000000000..504dcddeb
--- /dev/null
+++ b/arch/arm/include/asm/gpio.h
@@ -0,0 +1,25 @@
+#ifndef _ARCH_ARM_GPIO_H
+#define _ARCH_ARM_GPIO_H
+
+#if CONFIG_ARCH_NR_GPIO > 0
+#define ARCH_NR_GPIOS CONFIG_ARCH_NR_GPIO
+#endif
+
+/* Note: this may rely upon the value of ARCH_NR_GPIOS set in mach/gpio.h */
+#include <asm-generic/gpio.h>
+
+/* The trivial gpiolib dispatchers */
+#define gpio_get_value  __gpio_get_value
+#define gpio_set_value  __gpio_set_value
+#define gpio_cansleep   __gpio_cansleep
+
+/*
+ * Provide a default gpio_to_irq() which should satisfy every case.
+ * However, some platforms want to do this differently, so allow them
+ * to override it.
+ */
+#ifndef gpio_to_irq
+#define gpio_to_irq	__gpio_to_irq
+#endif
+
+#endif /* _ARCH_ARM_GPIO_H */
diff --git a/arch/arm/include/asm/hardirq.h b/arch/arm/include/asm/hardirq.h
new file mode 100644
index 000000000..fe3ea776d
--- /dev/null
+++ b/arch/arm/include/asm/hardirq.h
@@ -0,0 +1,32 @@
+#ifndef __ASM_HARDIRQ_H
+#define __ASM_HARDIRQ_H
+
+#include <linux/cache.h>
+#include <linux/threads.h>
+#include <asm/irq.h>
+
+#define NR_IPI	8
+
+typedef struct {
+	unsigned int __softirq_pending;
+#ifdef CONFIG_SMP
+	unsigned int ipi_irqs[NR_IPI];
+#endif
+} ____cacheline_aligned irq_cpustat_t;
+
+#include <linux/irq_cpustat.h>	/* Standard mappings for irq_cpustat_t above */
+
+#define __inc_irq_stat(cpu, member)	__IRQ_STAT(cpu, member)++
+#define __get_irq_stat(cpu, member)	__IRQ_STAT(cpu, member)
+
+#ifdef CONFIG_SMP
+u64 smp_irq_stat_cpu(unsigned int cpu);
+#else
+#define smp_irq_stat_cpu(cpu)	0
+#endif
+
+#define arch_irq_stat_cpu	smp_irq_stat_cpu
+
+#define __ARCH_IRQ_EXIT_IRQS_DISABLED	1
+
+#endif /* __ASM_HARDIRQ_H */
diff --git a/arch/arm/include/asm/hardware/arm_timer.h b/arch/arm/include/asm/hardware/arm_timer.h
new file mode 100644
index 000000000..d6030ff59
--- /dev/null
+++ b/arch/arm/include/asm/hardware/arm_timer.h
@@ -0,0 +1,35 @@
+#ifndef __ASM_ARM_HARDWARE_ARM_TIMER_H
+#define __ASM_ARM_HARDWARE_ARM_TIMER_H
+
+/*
+ * ARM timer implementation, found in Integrator, Versatile and Realview
+ * platforms.  Not all platforms support all registers and bits in these
+ * registers, so we mark them with A for Integrator AP, C for Integrator
+ * CP, V for Versatile and R for Realview.
+ *
+ * Integrator AP has 16-bit timers, Integrator CP, Versatile and Realview
+ * can have 16-bit or 32-bit selectable via a bit in the control register.
+ *
+ * Every SP804 contains two identical timers.
+ */
+#define TIMER_1_BASE	0x00
+#define TIMER_2_BASE	0x20
+
+#define TIMER_LOAD	0x00			/* ACVR rw */
+#define TIMER_VALUE	0x04			/* ACVR ro */
+#define TIMER_CTRL	0x08			/* ACVR rw */
+#define TIMER_CTRL_ONESHOT	(1 << 0)	/*  CVR */
+#define TIMER_CTRL_32BIT	(1 << 1)	/*  CVR */
+#define TIMER_CTRL_DIV1		(0 << 2)	/* ACVR */
+#define TIMER_CTRL_DIV16	(1 << 2)	/* ACVR */
+#define TIMER_CTRL_DIV256	(2 << 2)	/* ACVR */
+#define TIMER_CTRL_IE		(1 << 5)	/*   VR */
+#define TIMER_CTRL_PERIODIC	(1 << 6)	/* ACVR */
+#define TIMER_CTRL_ENABLE	(1 << 7)	/* ACVR */
+
+#define TIMER_INTCLR	0x0c			/* ACVR wo */
+#define TIMER_RIS	0x10			/*  CVR ro */
+#define TIMER_MIS	0x14			/*  CVR ro */
+#define TIMER_BGLOAD	0x18			/*  CVR rw */
+
+#endif
diff --git a/arch/arm/include/asm/hardware/cache-feroceon-l2.h b/arch/arm/include/asm/hardware/cache-feroceon-l2.h
new file mode 100644
index 000000000..12e1588dc
--- /dev/null
+++ b/arch/arm/include/asm/hardware/cache-feroceon-l2.h
@@ -0,0 +1,13 @@
+/*
+ * arch/arm/include/asm/hardware/cache-feroceon-l2.h
+ *
+ * Copyright (C) 2008 Marvell Semiconductor
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+extern void __init feroceon_l2_init(int l2_wt_override);
+extern int __init feroceon_of_init(void);
+
diff --git a/arch/arm/include/asm/hardware/cache-l2x0.h b/arch/arm/include/asm/hardware/cache-l2x0.h
new file mode 100644
index 000000000..3a5ec1c25
--- /dev/null
+++ b/arch/arm/include/asm/hardware/cache-l2x0.h
@@ -0,0 +1,181 @@
+/*
+ * arch/arm/include/asm/hardware/cache-l2x0.h
+ *
+ * Copyright (C) 2007 ARM Limited
+ *
+ * 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, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#ifndef __ASM_ARM_HARDWARE_L2X0_H
+#define __ASM_ARM_HARDWARE_L2X0_H
+
+#include <linux/errno.h>
+
+#define L2X0_CACHE_ID			0x000
+#define L2X0_CACHE_TYPE			0x004
+#define L2X0_CTRL			0x100
+#define L2X0_AUX_CTRL			0x104
+#define L310_TAG_LATENCY_CTRL		0x108
+#define L310_DATA_LATENCY_CTRL		0x10C
+#define L2X0_EVENT_CNT_CTRL		0x200
+#define L2X0_EVENT_CNT1_CFG		0x204
+#define L2X0_EVENT_CNT0_CFG		0x208
+#define L2X0_EVENT_CNT1_VAL		0x20C
+#define L2X0_EVENT_CNT0_VAL		0x210
+#define L2X0_INTR_MASK			0x214
+#define L2X0_MASKED_INTR_STAT		0x218
+#define L2X0_RAW_INTR_STAT		0x21C
+#define L2X0_INTR_CLEAR			0x220
+#define L2X0_CACHE_SYNC			0x730
+#define L2X0_DUMMY_REG			0x740
+#define L2X0_INV_LINE_PA		0x770
+#define L2X0_INV_WAY			0x77C
+#define L2X0_CLEAN_LINE_PA		0x7B0
+#define L2X0_CLEAN_LINE_IDX		0x7B8
+#define L2X0_CLEAN_WAY			0x7BC
+#define L2X0_CLEAN_INV_LINE_PA		0x7F0
+#define L2X0_CLEAN_INV_LINE_IDX		0x7F8
+#define L2X0_CLEAN_INV_WAY		0x7FC
+/*
+ * The lockdown registers repeat 8 times for L310, the L210 has only one
+ * D and one I lockdown register at 0x0900 and 0x0904.
+ */
+#define L2X0_LOCKDOWN_WAY_D_BASE	0x900
+#define L2X0_LOCKDOWN_WAY_I_BASE	0x904
+#define L2X0_LOCKDOWN_STRIDE		0x08
+#define L310_ADDR_FILTER_START		0xC00
+#define L310_ADDR_FILTER_END		0xC04
+#define L2X0_TEST_OPERATION		0xF00
+#define L2X0_LINE_DATA			0xF10
+#define L2X0_LINE_TAG			0xF30
+#define L2X0_DEBUG_CTRL			0xF40
+#define L310_PREFETCH_CTRL		0xF60
+#define L310_POWER_CTRL			0xF80
+#define   L310_DYNAMIC_CLK_GATING_EN	(1 << 1)
+#define   L310_STNDBY_MODE_EN		(1 << 0)
+
+/* Registers shifts and masks */
+#define L2X0_CACHE_ID_PART_MASK		(0xf << 6)
+#define L2X0_CACHE_ID_PART_L210		(1 << 6)
+#define L2X0_CACHE_ID_PART_L220		(2 << 6)
+#define L2X0_CACHE_ID_PART_L310		(3 << 6)
+#define L2X0_CACHE_ID_RTL_MASK          0x3f
+#define L210_CACHE_ID_RTL_R0P2_02	0x00
+#define L210_CACHE_ID_RTL_R0P1		0x01
+#define L210_CACHE_ID_RTL_R0P2_01	0x02
+#define L210_CACHE_ID_RTL_R0P3		0x03
+#define L210_CACHE_ID_RTL_R0P4		0x0b
+#define L210_CACHE_ID_RTL_R0P5		0x0f
+#define L220_CACHE_ID_RTL_R1P7_01REL0	0x06
+#define L310_CACHE_ID_RTL_R0P0		0x00
+#define L310_CACHE_ID_RTL_R1P0		0x02
+#define L310_CACHE_ID_RTL_R2P0		0x04
+#define L310_CACHE_ID_RTL_R3P0		0x05
+#define L310_CACHE_ID_RTL_R3P1		0x06
+#define L310_CACHE_ID_RTL_R3P1_50REL0	0x07
+#define L310_CACHE_ID_RTL_R3P2		0x08
+#define L310_CACHE_ID_RTL_R3P3		0x09
+
+/* L2C auxiliary control register - bits common to L2C-210/220/310 */
+#define L2C_AUX_CTRL_WAY_SIZE_SHIFT		17
+#define L2C_AUX_CTRL_WAY_SIZE_MASK		(7 << 17)
+#define L2C_AUX_CTRL_WAY_SIZE(n)		((n) << 17)
+#define L2C_AUX_CTRL_EVTMON_ENABLE		BIT(20)
+#define L2C_AUX_CTRL_PARITY_ENABLE		BIT(21)
+#define L2C_AUX_CTRL_SHARED_OVERRIDE		BIT(22)
+/* L2C-210/220 common bits */
+#define L2X0_AUX_CTRL_DATA_RD_LATENCY_SHIFT	0
+#define L2X0_AUX_CTRL_DATA_RD_LATENCY_MASK	(7 << 0)
+#define L2X0_AUX_CTRL_DATA_WR_LATENCY_SHIFT	3
+#define L2X0_AUX_CTRL_DATA_WR_LATENCY_MASK	(7 << 3)
+#define L2X0_AUX_CTRL_TAG_LATENCY_SHIFT		6
+#define L2X0_AUX_CTRL_TAG_LATENCY_MASK		(7 << 6)
+#define L2X0_AUX_CTRL_DIRTY_LATENCY_SHIFT	9
+#define L2X0_AUX_CTRL_DIRTY_LATENCY_MASK	(7 << 9)
+#define L2X0_AUX_CTRL_ASSOC_SHIFT		13
+#define L2X0_AUX_CTRL_ASSOC_MASK		(15 << 13)
+/* L2C-210 specific bits */
+#define L210_AUX_CTRL_WRAP_DISABLE		BIT(12)
+#define L210_AUX_CTRL_WA_OVERRIDE		BIT(23)
+#define L210_AUX_CTRL_EXCLUSIVE_ABORT		BIT(24)
+/* L2C-220 specific bits */
+#define L220_AUX_CTRL_EXCLUSIVE_CACHE		BIT(12)
+#define L220_AUX_CTRL_FWA_SHIFT			23
+#define L220_AUX_CTRL_FWA_MASK			(3 << 23)
+#define L220_AUX_CTRL_NS_LOCKDOWN		BIT(26)
+#define L220_AUX_CTRL_NS_INT_CTRL		BIT(27)
+/* L2C-310 specific bits */
+#define L310_AUX_CTRL_FULL_LINE_ZERO		BIT(0)	/* R2P0+ */
+#define L310_AUX_CTRL_HIGHPRIO_SO_DEV		BIT(10)	/* R2P0+ */
+#define L310_AUX_CTRL_STORE_LIMITATION		BIT(11)	/* R2P0+ */
+#define L310_AUX_CTRL_EXCLUSIVE_CACHE		BIT(12)
+#define L310_AUX_CTRL_ASSOCIATIVITY_16		BIT(16)
+#define L310_AUX_CTRL_CACHE_REPLACE_RR		BIT(25)	/* R2P0+ */
+#define L310_AUX_CTRL_NS_LOCKDOWN		BIT(26)
+#define L310_AUX_CTRL_NS_INT_CTRL		BIT(27)
+#define L310_AUX_CTRL_DATA_PREFETCH		BIT(28)
+#define L310_AUX_CTRL_INSTR_PREFETCH		BIT(29)
+#define L310_AUX_CTRL_EARLY_BRESP		BIT(30)	/* R2P0+ */
+
+#define L310_LATENCY_CTRL_SETUP(n)		((n) << 0)
+#define L310_LATENCY_CTRL_RD(n)			((n) << 4)
+#define L310_LATENCY_CTRL_WR(n)			((n) << 8)
+
+#define L310_ADDR_FILTER_EN		1
+
+#define L310_PREFETCH_CTRL_OFFSET_MASK		0x1f
+#define L310_PREFETCH_CTRL_DBL_LINEFILL_INCR	BIT(23)
+#define L310_PREFETCH_CTRL_PREFETCH_DROP	BIT(24)
+#define L310_PREFETCH_CTRL_DBL_LINEFILL_WRAP	BIT(27)
+#define L310_PREFETCH_CTRL_DATA_PREFETCH	BIT(28)
+#define L310_PREFETCH_CTRL_INSTR_PREFETCH	BIT(29)
+#define L310_PREFETCH_CTRL_DBL_LINEFILL		BIT(30)
+
+#define L2X0_CTRL_EN			1
+
+#define L2X0_WAY_SIZE_SHIFT		3
+
+#ifndef __ASSEMBLY__
+extern void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask);
+#if defined(CONFIG_CACHE_L2X0) && defined(CONFIG_OF)
+extern int l2x0_of_init(u32 aux_val, u32 aux_mask);
+#else
+static inline int l2x0_of_init(u32 aux_val, u32 aux_mask)
+{
+	return -ENODEV;
+}
+#endif
+
+struct l2x0_regs {
+	unsigned long phy_base;
+	unsigned long aux_ctrl;
+	/*
+	 * Whether the following registers need to be saved/restored
+	 * depends on platform
+	 */
+	unsigned long tag_latency;
+	unsigned long data_latency;
+	unsigned long filter_start;
+	unsigned long filter_end;
+	unsigned long prefetch_ctrl;
+	unsigned long pwr_ctrl;
+	unsigned long ctrl;
+	unsigned long aux2_ctrl;
+};
+
+extern struct l2x0_regs l2x0_saved_regs;
+
+#endif /* __ASSEMBLY__ */
+
+#endif
diff --git a/arch/arm/include/asm/hardware/cache-tauros2.h b/arch/arm/include/asm/hardware/cache-tauros2.h
new file mode 100644
index 000000000..295e2e401
--- /dev/null
+++ b/arch/arm/include/asm/hardware/cache-tauros2.h
@@ -0,0 +1,14 @@
+/*
+ * arch/arm/include/asm/hardware/cache-tauros2.h
+ *
+ * Copyright (C) 2008 Marvell Semiconductor
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#define CACHE_TAUROS2_PREFETCH_ON	(1 << 0)
+#define CACHE_TAUROS2_LINEFILL_BURST8	(1 << 1)
+
+extern void __init tauros2_init(unsigned int features);
diff --git a/arch/arm/include/asm/hardware/cp14.h b/arch/arm/include/asm/hardware/cp14.h
new file mode 100644
index 000000000..61576dc58
--- /dev/null
+++ b/arch/arm/include/asm/hardware/cp14.h
@@ -0,0 +1,542 @@
+/* Copyright (c) 2011-2012, 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_HARDWARE_CP14_H
+#define __ASM_HARDWARE_CP14_H
+
+#include <linux/types.h>
+
+/* Accessors for CP14 registers */
+#define dbg_read(reg)			RCP14_##reg()
+#define dbg_write(val, reg)		WCP14_##reg(val)
+#define etm_read(reg)			RCP14_##reg()
+#define etm_write(val, reg)		WCP14_##reg(val)
+
+/* MRC14 and MCR14 */
+#define MRC14(op1, crn, crm, op2)					\
+({									\
+u32 val;								\
+asm volatile("mrc p14, "#op1", %0, "#crn", "#crm", "#op2 : "=r" (val));	\
+val;									\
+})
+
+#define MCR14(val, op1, crn, crm, op2)					\
+({									\
+asm volatile("mcr p14, "#op1", %0, "#crn", "#crm", "#op2 : : "r" (val));\
+})
+
+/*
+ * Debug Registers
+ *
+ * Available only in DBGv7
+ * DBGECR, DBGDSCCR, DBGDSMCR, DBGDRCR
+ *
+ * Available only in DBGv7.1
+ * DBGBXVRm, DBGOSDLR, DBGDEVID2, DBGDEVID1
+ *
+ * Read only
+ * DBGDIDR, DBGDSCRint, DBGDTRRXint, DBGDRAR, DBGOSLSR, DBGOSSRR, DBGPRSR,
+ * DBGPRSR, DBGDSAR, DBGAUTHSTATUS, DBGDEVID2, DBGDEVID1, DBGDEVID
+ *
+ * Write only
+ * DBGDTRTXint, DBGOSLAR
+ */
+#define RCP14_DBGDIDR()			MRC14(0, c0, c0, 0)
+#define RCP14_DBGDSCRint()		MRC14(0, c0, c1, 0)
+#define RCP14_DBGDTRRXint()		MRC14(0, c0, c5, 0)
+#define RCP14_DBGWFAR()			MRC14(0, c0, c6, 0)
+#define RCP14_DBGVCR()			MRC14(0, c0, c7, 0)
+#define RCP14_DBGECR()			MRC14(0, c0, c9, 0)
+#define RCP14_DBGDSCCR()		MRC14(0, c0, c10, 0)
+#define RCP14_DBGDSMCR()		MRC14(0, c0, c11, 0)
+#define RCP14_DBGDTRRXext()		MRC14(0, c0, c0, 2)
+#define RCP14_DBGDSCRext()		MRC14(0, c0, c2, 2)
+#define RCP14_DBGDTRTXext()		MRC14(0, c0, c3, 2)
+#define RCP14_DBGDRCR()			MRC14(0, c0, c4, 2)
+#define RCP14_DBGBVR0()			MRC14(0, c0, c0, 4)
+#define RCP14_DBGBVR1()			MRC14(0, c0, c1, 4)
+#define RCP14_DBGBVR2()			MRC14(0, c0, c2, 4)
+#define RCP14_DBGBVR3()			MRC14(0, c0, c3, 4)
+#define RCP14_DBGBVR4()			MRC14(0, c0, c4, 4)
+#define RCP14_DBGBVR5()			MRC14(0, c0, c5, 4)
+#define RCP14_DBGBVR6()			MRC14(0, c0, c6, 4)
+#define RCP14_DBGBVR7()			MRC14(0, c0, c7, 4)
+#define RCP14_DBGBVR8()			MRC14(0, c0, c8, 4)
+#define RCP14_DBGBVR9()			MRC14(0, c0, c9, 4)
+#define RCP14_DBGBVR10()		MRC14(0, c0, c10, 4)
+#define RCP14_DBGBVR11()		MRC14(0, c0, c11, 4)
+#define RCP14_DBGBVR12()		MRC14(0, c0, c12, 4)
+#define RCP14_DBGBVR13()		MRC14(0, c0, c13, 4)
+#define RCP14_DBGBVR14()		MRC14(0, c0, c14, 4)
+#define RCP14_DBGBVR15()		MRC14(0, c0, c15, 4)
+#define RCP14_DBGBCR0()			MRC14(0, c0, c0, 5)
+#define RCP14_DBGBCR1()			MRC14(0, c0, c1, 5)
+#define RCP14_DBGBCR2()			MRC14(0, c0, c2, 5)
+#define RCP14_DBGBCR3()			MRC14(0, c0, c3, 5)
+#define RCP14_DBGBCR4()			MRC14(0, c0, c4, 5)
+#define RCP14_DBGBCR5()			MRC14(0, c0, c5, 5)
+#define RCP14_DBGBCR6()			MRC14(0, c0, c6, 5)
+#define RCP14_DBGBCR7()			MRC14(0, c0, c7, 5)
+#define RCP14_DBGBCR8()			MRC14(0, c0, c8, 5)
+#define RCP14_DBGBCR9()			MRC14(0, c0, c9, 5)
+#define RCP14_DBGBCR10()		MRC14(0, c0, c10, 5)
+#define RCP14_DBGBCR11()		MRC14(0, c0, c11, 5)
+#define RCP14_DBGBCR12()		MRC14(0, c0, c12, 5)
+#define RCP14_DBGBCR13()		MRC14(0, c0, c13, 5)
+#define RCP14_DBGBCR14()		MRC14(0, c0, c14, 5)
+#define RCP14_DBGBCR15()		MRC14(0, c0, c15, 5)
+#define RCP14_DBGWVR0()			MRC14(0, c0, c0, 6)
+#define RCP14_DBGWVR1()			MRC14(0, c0, c1, 6)
+#define RCP14_DBGWVR2()			MRC14(0, c0, c2, 6)
+#define RCP14_DBGWVR3()			MRC14(0, c0, c3, 6)
+#define RCP14_DBGWVR4()			MRC14(0, c0, c4, 6)
+#define RCP14_DBGWVR5()			MRC14(0, c0, c5, 6)
+#define RCP14_DBGWVR6()			MRC14(0, c0, c6, 6)
+#define RCP14_DBGWVR7()			MRC14(0, c0, c7, 6)
+#define RCP14_DBGWVR8()			MRC14(0, c0, c8, 6)
+#define RCP14_DBGWVR9()			MRC14(0, c0, c9, 6)
+#define RCP14_DBGWVR10()		MRC14(0, c0, c10, 6)
+#define RCP14_DBGWVR11()		MRC14(0, c0, c11, 6)
+#define RCP14_DBGWVR12()		MRC14(0, c0, c12, 6)
+#define RCP14_DBGWVR13()		MRC14(0, c0, c13, 6)
+#define RCP14_DBGWVR14()		MRC14(0, c0, c14, 6)
+#define RCP14_DBGWVR15()		MRC14(0, c0, c15, 6)
+#define RCP14_DBGWCR0()			MRC14(0, c0, c0, 7)
+#define RCP14_DBGWCR1()			MRC14(0, c0, c1, 7)
+#define RCP14_DBGWCR2()			MRC14(0, c0, c2, 7)
+#define RCP14_DBGWCR3()			MRC14(0, c0, c3, 7)
+#define RCP14_DBGWCR4()			MRC14(0, c0, c4, 7)
+#define RCP14_DBGWCR5()			MRC14(0, c0, c5, 7)
+#define RCP14_DBGWCR6()			MRC14(0, c0, c6, 7)
+#define RCP14_DBGWCR7()			MRC14(0, c0, c7, 7)
+#define RCP14_DBGWCR8()			MRC14(0, c0, c8, 7)
+#define RCP14_DBGWCR9()			MRC14(0, c0, c9, 7)
+#define RCP14_DBGWCR10()		MRC14(0, c0, c10, 7)
+#define RCP14_DBGWCR11()		MRC14(0, c0, c11, 7)
+#define RCP14_DBGWCR12()		MRC14(0, c0, c12, 7)
+#define RCP14_DBGWCR13()		MRC14(0, c0, c13, 7)
+#define RCP14_DBGWCR14()		MRC14(0, c0, c14, 7)
+#define RCP14_DBGWCR15()		MRC14(0, c0, c15, 7)
+#define RCP14_DBGDRAR()			MRC14(0, c1, c0, 0)
+#define RCP14_DBGBXVR0()		MRC14(0, c1, c0, 1)
+#define RCP14_DBGBXVR1()		MRC14(0, c1, c1, 1)
+#define RCP14_DBGBXVR2()		MRC14(0, c1, c2, 1)
+#define RCP14_DBGBXVR3()		MRC14(0, c1, c3, 1)
+#define RCP14_DBGBXVR4()		MRC14(0, c1, c4, 1)
+#define RCP14_DBGBXVR5()		MRC14(0, c1, c5, 1)
+#define RCP14_DBGBXVR6()		MRC14(0, c1, c6, 1)
+#define RCP14_DBGBXVR7()		MRC14(0, c1, c7, 1)
+#define RCP14_DBGBXVR8()		MRC14(0, c1, c8, 1)
+#define RCP14_DBGBXVR9()		MRC14(0, c1, c9, 1)
+#define RCP14_DBGBXVR10()		MRC14(0, c1, c10, 1)
+#define RCP14_DBGBXVR11()		MRC14(0, c1, c11, 1)
+#define RCP14_DBGBXVR12()		MRC14(0, c1, c12, 1)
+#define RCP14_DBGBXVR13()		MRC14(0, c1, c13, 1)
+#define RCP14_DBGBXVR14()		MRC14(0, c1, c14, 1)
+#define RCP14_DBGBXVR15()		MRC14(0, c1, c15, 1)
+#define RCP14_DBGOSLSR()		MRC14(0, c1, c1, 4)
+#define RCP14_DBGOSSRR()		MRC14(0, c1, c2, 4)
+#define RCP14_DBGOSDLR()		MRC14(0, c1, c3, 4)
+#define RCP14_DBGPRCR()			MRC14(0, c1, c4, 4)
+#define RCP14_DBGPRSR()			MRC14(0, c1, c5, 4)
+#define RCP14_DBGDSAR()			MRC14(0, c2, c0, 0)
+#define RCP14_DBGITCTRL()		MRC14(0, c7, c0, 4)
+#define RCP14_DBGCLAIMSET()		MRC14(0, c7, c8, 6)
+#define RCP14_DBGCLAIMCLR()		MRC14(0, c7, c9, 6)
+#define RCP14_DBGAUTHSTATUS()		MRC14(0, c7, c14, 6)
+#define RCP14_DBGDEVID2()		MRC14(0, c7, c0, 7)
+#define RCP14_DBGDEVID1()		MRC14(0, c7, c1, 7)
+#define RCP14_DBGDEVID()		MRC14(0, c7, c2, 7)
+
+#define WCP14_DBGDTRTXint(val)		MCR14(val, 0, c0, c5, 0)
+#define WCP14_DBGWFAR(val)		MCR14(val, 0, c0, c6, 0)
+#define WCP14_DBGVCR(val)		MCR14(val, 0, c0, c7, 0)
+#define WCP14_DBGECR(val)		MCR14(val, 0, c0, c9, 0)
+#define WCP14_DBGDSCCR(val)		MCR14(val, 0, c0, c10, 0)
+#define WCP14_DBGDSMCR(val)		MCR14(val, 0, c0, c11, 0)
+#define WCP14_DBGDTRRXext(val)		MCR14(val, 0, c0, c0, 2)
+#define WCP14_DBGDSCRext(val)		MCR14(val, 0, c0, c2, 2)
+#define WCP14_DBGDTRTXext(val)		MCR14(val, 0, c0, c3, 2)
+#define WCP14_DBGDRCR(val)		MCR14(val, 0, c0, c4, 2)
+#define WCP14_DBGBVR0(val)		MCR14(val, 0, c0, c0, 4)
+#define WCP14_DBGBVR1(val)		MCR14(val, 0, c0, c1, 4)
+#define WCP14_DBGBVR2(val)		MCR14(val, 0, c0, c2, 4)
+#define WCP14_DBGBVR3(val)		MCR14(val, 0, c0, c3, 4)
+#define WCP14_DBGBVR4(val)		MCR14(val, 0, c0, c4, 4)
+#define WCP14_DBGBVR5(val)		MCR14(val, 0, c0, c5, 4)
+#define WCP14_DBGBVR6(val)		MCR14(val, 0, c0, c6, 4)
+#define WCP14_DBGBVR7(val)		MCR14(val, 0, c0, c7, 4)
+#define WCP14_DBGBVR8(val)		MCR14(val, 0, c0, c8, 4)
+#define WCP14_DBGBVR9(val)		MCR14(val, 0, c0, c9, 4)
+#define WCP14_DBGBVR10(val)		MCR14(val, 0, c0, c10, 4)
+#define WCP14_DBGBVR11(val)		MCR14(val, 0, c0, c11, 4)
+#define WCP14_DBGBVR12(val)		MCR14(val, 0, c0, c12, 4)
+#define WCP14_DBGBVR13(val)		MCR14(val, 0, c0, c13, 4)
+#define WCP14_DBGBVR14(val)		MCR14(val, 0, c0, c14, 4)
+#define WCP14_DBGBVR15(val)		MCR14(val, 0, c0, c15, 4)
+#define WCP14_DBGBCR0(val)		MCR14(val, 0, c0, c0, 5)
+#define WCP14_DBGBCR1(val)		MCR14(val, 0, c0, c1, 5)
+#define WCP14_DBGBCR2(val)		MCR14(val, 0, c0, c2, 5)
+#define WCP14_DBGBCR3(val)		MCR14(val, 0, c0, c3, 5)
+#define WCP14_DBGBCR4(val)		MCR14(val, 0, c0, c4, 5)
+#define WCP14_DBGBCR5(val)		MCR14(val, 0, c0, c5, 5)
+#define WCP14_DBGBCR6(val)		MCR14(val, 0, c0, c6, 5)
+#define WCP14_DBGBCR7(val)		MCR14(val, 0, c0, c7, 5)
+#define WCP14_DBGBCR8(val)		MCR14(val, 0, c0, c8, 5)
+#define WCP14_DBGBCR9(val)		MCR14(val, 0, c0, c9, 5)
+#define WCP14_DBGBCR10(val)		MCR14(val, 0, c0, c10, 5)
+#define WCP14_DBGBCR11(val)		MCR14(val, 0, c0, c11, 5)
+#define WCP14_DBGBCR12(val)		MCR14(val, 0, c0, c12, 5)
+#define WCP14_DBGBCR13(val)		MCR14(val, 0, c0, c13, 5)
+#define WCP14_DBGBCR14(val)		MCR14(val, 0, c0, c14, 5)
+#define WCP14_DBGBCR15(val)		MCR14(val, 0, c0, c15, 5)
+#define WCP14_DBGWVR0(val)		MCR14(val, 0, c0, c0, 6)
+#define WCP14_DBGWVR1(val)		MCR14(val, 0, c0, c1, 6)
+#define WCP14_DBGWVR2(val)		MCR14(val, 0, c0, c2, 6)
+#define WCP14_DBGWVR3(val)		MCR14(val, 0, c0, c3, 6)
+#define WCP14_DBGWVR4(val)		MCR14(val, 0, c0, c4, 6)
+#define WCP14_DBGWVR5(val)		MCR14(val, 0, c0, c5, 6)
+#define WCP14_DBGWVR6(val)		MCR14(val, 0, c0, c6, 6)
+#define WCP14_DBGWVR7(val)		MCR14(val, 0, c0, c7, 6)
+#define WCP14_DBGWVR8(val)		MCR14(val, 0, c0, c8, 6)
+#define WCP14_DBGWVR9(val)		MCR14(val, 0, c0, c9, 6)
+#define WCP14_DBGWVR10(val)		MCR14(val, 0, c0, c10, 6)
+#define WCP14_DBGWVR11(val)		MCR14(val, 0, c0, c11, 6)
+#define WCP14_DBGWVR12(val)		MCR14(val, 0, c0, c12, 6)
+#define WCP14_DBGWVR13(val)		MCR14(val, 0, c0, c13, 6)
+#define WCP14_DBGWVR14(val)		MCR14(val, 0, c0, c14, 6)
+#define WCP14_DBGWVR15(val)		MCR14(val, 0, c0, c15, 6)
+#define WCP14_DBGWCR0(val)		MCR14(val, 0, c0, c0, 7)
+#define WCP14_DBGWCR1(val)		MCR14(val, 0, c0, c1, 7)
+#define WCP14_DBGWCR2(val)		MCR14(val, 0, c0, c2, 7)
+#define WCP14_DBGWCR3(val)		MCR14(val, 0, c0, c3, 7)
+#define WCP14_DBGWCR4(val)		MCR14(val, 0, c0, c4, 7)
+#define WCP14_DBGWCR5(val)		MCR14(val, 0, c0, c5, 7)
+#define WCP14_DBGWCR6(val)		MCR14(val, 0, c0, c6, 7)
+#define WCP14_DBGWCR7(val)		MCR14(val, 0, c0, c7, 7)
+#define WCP14_DBGWCR8(val)		MCR14(val, 0, c0, c8, 7)
+#define WCP14_DBGWCR9(val)		MCR14(val, 0, c0, c9, 7)
+#define WCP14_DBGWCR10(val)		MCR14(val, 0, c0, c10, 7)
+#define WCP14_DBGWCR11(val)		MCR14(val, 0, c0, c11, 7)
+#define WCP14_DBGWCR12(val)		MCR14(val, 0, c0, c12, 7)
+#define WCP14_DBGWCR13(val)		MCR14(val, 0, c0, c13, 7)
+#define WCP14_DBGWCR14(val)		MCR14(val, 0, c0, c14, 7)
+#define WCP14_DBGWCR15(val)		MCR14(val, 0, c0, c15, 7)
+#define WCP14_DBGBXVR0(val)		MCR14(val, 0, c1, c0, 1)
+#define WCP14_DBGBXVR1(val)		MCR14(val, 0, c1, c1, 1)
+#define WCP14_DBGBXVR2(val)		MCR14(val, 0, c1, c2, 1)
+#define WCP14_DBGBXVR3(val)		MCR14(val, 0, c1, c3, 1)
+#define WCP14_DBGBXVR4(val)		MCR14(val, 0, c1, c4, 1)
+#define WCP14_DBGBXVR5(val)		MCR14(val, 0, c1, c5, 1)
+#define WCP14_DBGBXVR6(val)		MCR14(val, 0, c1, c6, 1)
+#define WCP14_DBGBXVR7(val)		MCR14(val, 0, c1, c7, 1)
+#define WCP14_DBGBXVR8(val)		MCR14(val, 0, c1, c8, 1)
+#define WCP14_DBGBXVR9(val)		MCR14(val, 0, c1, c9, 1)
+#define WCP14_DBGBXVR10(val)		MCR14(val, 0, c1, c10, 1)
+#define WCP14_DBGBXVR11(val)		MCR14(val, 0, c1, c11, 1)
+#define WCP14_DBGBXVR12(val)		MCR14(val, 0, c1, c12, 1)
+#define WCP14_DBGBXVR13(val)		MCR14(val, 0, c1, c13, 1)
+#define WCP14_DBGBXVR14(val)		MCR14(val, 0, c1, c14, 1)
+#define WCP14_DBGBXVR15(val)		MCR14(val, 0, c1, c15, 1)
+#define WCP14_DBGOSLAR(val)		MCR14(val, 0, c1, c0, 4)
+#define WCP14_DBGOSSRR(val)		MCR14(val, 0, c1, c2, 4)
+#define WCP14_DBGOSDLR(val)		MCR14(val, 0, c1, c3, 4)
+#define WCP14_DBGPRCR(val)		MCR14(val, 0, c1, c4, 4)
+#define WCP14_DBGITCTRL(val)		MCR14(val, 0, c7, c0, 4)
+#define WCP14_DBGCLAIMSET(val)		MCR14(val, 0, c7, c8, 6)
+#define WCP14_DBGCLAIMCLR(val)		MCR14(val, 0, c7, c9, 6)
+
+/*
+ * ETM Registers
+ *
+ * Available only in ETMv3.3, 3.4, 3.5
+ * ETMASICCR, ETMTECR2, ETMFFRR, ETMVDEVR, ETMVDCR1, ETMVDCR2, ETMVDCR3,
+ * ETMDCVRn, ETMDCMRn
+ *
+ * Available only in ETMv3.5 as read only
+ * ETMIDR2
+ *
+ * Available only in ETMv3.5, PFTv1.0, 1.1
+ * ETMTSEVR, ETMVMIDCVR, ETMPDCR
+ *
+ * Read only
+ * ETMCCR, ETMSCR, ETMIDR, ETMCCER, ETMOSLSR
+ * ETMLSR, ETMAUTHSTATUS, ETMDEVID, ETMDEVTYPE, ETMPIDR4, ETMPIDR5, ETMPIDR6,
+ * ETMPIDR7, ETMPIDR0, ETMPIDR1, ETMPIDR2, ETMPIDR2, ETMPIDR3, ETMCIDR0,
+ * ETMCIDR1, ETMCIDR2, ETMCIDR3
+ *
+ * Write only
+ * ETMOSLAR, ETMLAR
+ * Note: ETMCCER[11] controls WO nature of certain regs. Refer ETM arch spec.
+ */
+#define RCP14_ETMCR()			MRC14(1, c0, c0, 0)
+#define RCP14_ETMCCR()			MRC14(1, c0, c1, 0)
+#define RCP14_ETMTRIGGER()		MRC14(1, c0, c2, 0)
+#define RCP14_ETMASICCR()		MRC14(1, c0, c3, 0)
+#define RCP14_ETMSR()			MRC14(1, c0, c4, 0)
+#define RCP14_ETMSCR()			MRC14(1, c0, c5, 0)
+#define RCP14_ETMTSSCR()		MRC14(1, c0, c6, 0)
+#define RCP14_ETMTECR2()		MRC14(1, c0, c7, 0)
+#define RCP14_ETMTEEVR()		MRC14(1, c0, c8, 0)
+#define RCP14_ETMTECR1()		MRC14(1, c0, c9, 0)
+#define RCP14_ETMFFRR()			MRC14(1, c0, c10, 0)
+#define RCP14_ETMFFLR()			MRC14(1, c0, c11, 0)
+#define RCP14_ETMVDEVR()		MRC14(1, c0, c12, 0)
+#define RCP14_ETMVDCR1()		MRC14(1, c0, c13, 0)
+#define RCP14_ETMVDCR2()		MRC14(1, c0, c14, 0)
+#define RCP14_ETMVDCR3()		MRC14(1, c0, c15, 0)
+#define RCP14_ETMACVR0()		MRC14(1, c0, c0, 1)
+#define RCP14_ETMACVR1()		MRC14(1, c0, c1, 1)
+#define RCP14_ETMACVR2()		MRC14(1, c0, c2, 1)
+#define RCP14_ETMACVR3()		MRC14(1, c0, c3, 1)
+#define RCP14_ETMACVR4()		MRC14(1, c0, c4, 1)
+#define RCP14_ETMACVR5()		MRC14(1, c0, c5, 1)
+#define RCP14_ETMACVR6()		MRC14(1, c0, c6, 1)
+#define RCP14_ETMACVR7()		MRC14(1, c0, c7, 1)
+#define RCP14_ETMACVR8()		MRC14(1, c0, c8, 1)
+#define RCP14_ETMACVR9()		MRC14(1, c0, c9, 1)
+#define RCP14_ETMACVR10()		MRC14(1, c0, c10, 1)
+#define RCP14_ETMACVR11()		MRC14(1, c0, c11, 1)
+#define RCP14_ETMACVR12()		MRC14(1, c0, c12, 1)
+#define RCP14_ETMACVR13()		MRC14(1, c0, c13, 1)
+#define RCP14_ETMACVR14()		MRC14(1, c0, c14, 1)
+#define RCP14_ETMACVR15()		MRC14(1, c0, c15, 1)
+#define RCP14_ETMACTR0()		MRC14(1, c0, c0, 2)
+#define RCP14_ETMACTR1()		MRC14(1, c0, c1, 2)
+#define RCP14_ETMACTR2()		MRC14(1, c0, c2, 2)
+#define RCP14_ETMACTR3()		MRC14(1, c0, c3, 2)
+#define RCP14_ETMACTR4()		MRC14(1, c0, c4, 2)
+#define RCP14_ETMACTR5()		MRC14(1, c0, c5, 2)
+#define RCP14_ETMACTR6()		MRC14(1, c0, c6, 2)
+#define RCP14_ETMACTR7()		MRC14(1, c0, c7, 2)
+#define RCP14_ETMACTR8()		MRC14(1, c0, c8, 2)
+#define RCP14_ETMACTR9()		MRC14(1, c0, c9, 2)
+#define RCP14_ETMACTR10()		MRC14(1, c0, c10, 2)
+#define RCP14_ETMACTR11()		MRC14(1, c0, c11, 2)
+#define RCP14_ETMACTR12()		MRC14(1, c0, c12, 2)
+#define RCP14_ETMACTR13()		MRC14(1, c0, c13, 2)
+#define RCP14_ETMACTR14()		MRC14(1, c0, c14, 2)
+#define RCP14_ETMACTR15()		MRC14(1, c0, c15, 2)
+#define RCP14_ETMDCVR0()		MRC14(1, c0, c0, 3)
+#define RCP14_ETMDCVR2()		MRC14(1, c0, c2, 3)
+#define RCP14_ETMDCVR4()		MRC14(1, c0, c4, 3)
+#define RCP14_ETMDCVR6()		MRC14(1, c0, c6, 3)
+#define RCP14_ETMDCVR8()		MRC14(1, c0, c8, 3)
+#define RCP14_ETMDCVR10()		MRC14(1, c0, c10, 3)
+#define RCP14_ETMDCVR12()		MRC14(1, c0, c12, 3)
+#define RCP14_ETMDCVR14()		MRC14(1, c0, c14, 3)
+#define RCP14_ETMDCMR0()		MRC14(1, c0, c0, 4)
+#define RCP14_ETMDCMR2()		MRC14(1, c0, c2, 4)
+#define RCP14_ETMDCMR4()		MRC14(1, c0, c4, 4)
+#define RCP14_ETMDCMR6()		MRC14(1, c0, c6, 4)
+#define RCP14_ETMDCMR8()		MRC14(1, c0, c8, 4)
+#define RCP14_ETMDCMR10()		MRC14(1, c0, c10, 4)
+#define RCP14_ETMDCMR12()		MRC14(1, c0, c12, 4)
+#define RCP14_ETMDCMR14()		MRC14(1, c0, c14, 4)
+#define RCP14_ETMCNTRLDVR0()		MRC14(1, c0, c0, 5)
+#define RCP14_ETMCNTRLDVR1()		MRC14(1, c0, c1, 5)
+#define RCP14_ETMCNTRLDVR2()		MRC14(1, c0, c2, 5)
+#define RCP14_ETMCNTRLDVR3()		MRC14(1, c0, c3, 5)
+#define RCP14_ETMCNTENR0()		MRC14(1, c0, c4, 5)
+#define RCP14_ETMCNTENR1()		MRC14(1, c0, c5, 5)
+#define RCP14_ETMCNTENR2()		MRC14(1, c0, c6, 5)
+#define RCP14_ETMCNTENR3()		MRC14(1, c0, c7, 5)
+#define RCP14_ETMCNTRLDEVR0()		MRC14(1, c0, c8, 5)
+#define RCP14_ETMCNTRLDEVR1()		MRC14(1, c0, c9, 5)
+#define RCP14_ETMCNTRLDEVR2()		MRC14(1, c0, c10, 5)
+#define RCP14_ETMCNTRLDEVR3()		MRC14(1, c0, c11, 5)
+#define RCP14_ETMCNTVR0()		MRC14(1, c0, c12, 5)
+#define RCP14_ETMCNTVR1()		MRC14(1, c0, c13, 5)
+#define RCP14_ETMCNTVR2()		MRC14(1, c0, c14, 5)
+#define RCP14_ETMCNTVR3()		MRC14(1, c0, c15, 5)
+#define RCP14_ETMSQ12EVR()		MRC14(1, c0, c0, 6)
+#define RCP14_ETMSQ21EVR()		MRC14(1, c0, c1, 6)
+#define RCP14_ETMSQ23EVR()		MRC14(1, c0, c2, 6)
+#define RCP14_ETMSQ31EVR()		MRC14(1, c0, c3, 6)
+#define RCP14_ETMSQ32EVR()		MRC14(1, c0, c4, 6)
+#define RCP14_ETMSQ13EVR()		MRC14(1, c0, c5, 6)
+#define RCP14_ETMSQR()			MRC14(1, c0, c7, 6)
+#define RCP14_ETMEXTOUTEVR0()		MRC14(1, c0, c8, 6)
+#define RCP14_ETMEXTOUTEVR1()		MRC14(1, c0, c9, 6)
+#define RCP14_ETMEXTOUTEVR2()		MRC14(1, c0, c10, 6)
+#define RCP14_ETMEXTOUTEVR3()		MRC14(1, c0, c11, 6)
+#define RCP14_ETMCIDCVR0()		MRC14(1, c0, c12, 6)
+#define RCP14_ETMCIDCVR1()		MRC14(1, c0, c13, 6)
+#define RCP14_ETMCIDCVR2()		MRC14(1, c0, c14, 6)
+#define RCP14_ETMCIDCMR()		MRC14(1, c0, c15, 6)
+#define RCP14_ETMIMPSPEC0()		MRC14(1, c0, c0, 7)
+#define RCP14_ETMIMPSPEC1()		MRC14(1, c0, c1, 7)
+#define RCP14_ETMIMPSPEC2()		MRC14(1, c0, c2, 7)
+#define RCP14_ETMIMPSPEC3()		MRC14(1, c0, c3, 7)
+#define RCP14_ETMIMPSPEC4()		MRC14(1, c0, c4, 7)
+#define RCP14_ETMIMPSPEC5()		MRC14(1, c0, c5, 7)
+#define RCP14_ETMIMPSPEC6()		MRC14(1, c0, c6, 7)
+#define RCP14_ETMIMPSPEC7()		MRC14(1, c0, c7, 7)
+#define RCP14_ETMSYNCFR()		MRC14(1, c0, c8, 7)
+#define RCP14_ETMIDR()			MRC14(1, c0, c9, 7)
+#define RCP14_ETMCCER()			MRC14(1, c0, c10, 7)
+#define RCP14_ETMEXTINSELR()		MRC14(1, c0, c11, 7)
+#define RCP14_ETMTESSEICR()		MRC14(1, c0, c12, 7)
+#define RCP14_ETMEIBCR()		MRC14(1, c0, c13, 7)
+#define RCP14_ETMTSEVR()		MRC14(1, c0, c14, 7)
+#define RCP14_ETMAUXCR()		MRC14(1, c0, c15, 7)
+#define RCP14_ETMTRACEIDR()		MRC14(1, c1, c0, 0)
+#define RCP14_ETMIDR2()			MRC14(1, c1, c2, 0)
+#define RCP14_ETMVMIDCVR()		MRC14(1, c1, c0, 1)
+#define RCP14_ETMOSLSR()		MRC14(1, c1, c1, 4)
+/* Not available in PFTv1.1 */
+#define RCP14_ETMOSSRR()		MRC14(1, c1, c2, 4)
+#define RCP14_ETMPDCR()			MRC14(1, c1, c4, 4)
+#define RCP14_ETMPDSR()			MRC14(1, c1, c5, 4)
+#define RCP14_ETMITCTRL()		MRC14(1, c7, c0, 4)
+#define RCP14_ETMCLAIMSET()		MRC14(1, c7, c8, 6)
+#define RCP14_ETMCLAIMCLR()		MRC14(1, c7, c9, 6)
+#define RCP14_ETMLSR()			MRC14(1, c7, c13, 6)
+#define RCP14_ETMAUTHSTATUS()		MRC14(1, c7, c14, 6)
+#define RCP14_ETMDEVID()		MRC14(1, c7, c2, 7)
+#define RCP14_ETMDEVTYPE()		MRC14(1, c7, c3, 7)
+#define RCP14_ETMPIDR4()		MRC14(1, c7, c4, 7)
+#define RCP14_ETMPIDR5()		MRC14(1, c7, c5, 7)
+#define RCP14_ETMPIDR6()		MRC14(1, c7, c6, 7)
+#define RCP14_ETMPIDR7()		MRC14(1, c7, c7, 7)
+#define RCP14_ETMPIDR0()		MRC14(1, c7, c8, 7)
+#define RCP14_ETMPIDR1()		MRC14(1, c7, c9, 7)
+#define RCP14_ETMPIDR2()		MRC14(1, c7, c10, 7)
+#define RCP14_ETMPIDR3()		MRC14(1, c7, c11, 7)
+#define RCP14_ETMCIDR0()		MRC14(1, c7, c12, 7)
+#define RCP14_ETMCIDR1()		MRC14(1, c7, c13, 7)
+#define RCP14_ETMCIDR2()		MRC14(1, c7, c14, 7)
+#define RCP14_ETMCIDR3()		MRC14(1, c7, c15, 7)
+
+#define WCP14_ETMCR(val)		MCR14(val, 1, c0, c0, 0)
+#define WCP14_ETMTRIGGER(val)		MCR14(val, 1, c0, c2, 0)
+#define WCP14_ETMASICCR(val)		MCR14(val, 1, c0, c3, 0)
+#define WCP14_ETMSR(val)		MCR14(val, 1, c0, c4, 0)
+#define WCP14_ETMTSSCR(val)		MCR14(val, 1, c0, c6, 0)
+#define WCP14_ETMTECR2(val)		MCR14(val, 1, c0, c7, 0)
+#define WCP14_ETMTEEVR(val)		MCR14(val, 1, c0, c8, 0)
+#define WCP14_ETMTECR1(val)		MCR14(val, 1, c0, c9, 0)
+#define WCP14_ETMFFRR(val)		MCR14(val, 1, c0, c10, 0)
+#define WCP14_ETMFFLR(val)		MCR14(val, 1, c0, c11, 0)
+#define WCP14_ETMVDEVR(val)		MCR14(val, 1, c0, c12, 0)
+#define WCP14_ETMVDCR1(val)		MCR14(val, 1, c0, c13, 0)
+#define WCP14_ETMVDCR2(val)		MCR14(val, 1, c0, c14, 0)
+#define WCP14_ETMVDCR3(val)		MCR14(val, 1, c0, c15, 0)
+#define WCP14_ETMACVR0(val)		MCR14(val, 1, c0, c0, 1)
+#define WCP14_ETMACVR1(val)		MCR14(val, 1, c0, c1, 1)
+#define WCP14_ETMACVR2(val)		MCR14(val, 1, c0, c2, 1)
+#define WCP14_ETMACVR3(val)		MCR14(val, 1, c0, c3, 1)
+#define WCP14_ETMACVR4(val)		MCR14(val, 1, c0, c4, 1)
+#define WCP14_ETMACVR5(val)		MCR14(val, 1, c0, c5, 1)
+#define WCP14_ETMACVR6(val)		MCR14(val, 1, c0, c6, 1)
+#define WCP14_ETMACVR7(val)		MCR14(val, 1, c0, c7, 1)
+#define WCP14_ETMACVR8(val)		MCR14(val, 1, c0, c8, 1)
+#define WCP14_ETMACVR9(val)		MCR14(val, 1, c0, c9, 1)
+#define WCP14_ETMACVR10(val)		MCR14(val, 1, c0, c10, 1)
+#define WCP14_ETMACVR11(val)		MCR14(val, 1, c0, c11, 1)
+#define WCP14_ETMACVR12(val)		MCR14(val, 1, c0, c12, 1)
+#define WCP14_ETMACVR13(val)		MCR14(val, 1, c0, c13, 1)
+#define WCP14_ETMACVR14(val)		MCR14(val, 1, c0, c14, 1)
+#define WCP14_ETMACVR15(val)		MCR14(val, 1, c0, c15, 1)
+#define WCP14_ETMACTR0(val)		MCR14(val, 1, c0, c0, 2)
+#define WCP14_ETMACTR1(val)		MCR14(val, 1, c0, c1, 2)
+#define WCP14_ETMACTR2(val)		MCR14(val, 1, c0, c2, 2)
+#define WCP14_ETMACTR3(val)		MCR14(val, 1, c0, c3, 2)
+#define WCP14_ETMACTR4(val)		MCR14(val, 1, c0, c4, 2)
+#define WCP14_ETMACTR5(val)		MCR14(val, 1, c0, c5, 2)
+#define WCP14_ETMACTR6(val)		MCR14(val, 1, c0, c6, 2)
+#define WCP14_ETMACTR7(val)		MCR14(val, 1, c0, c7, 2)
+#define WCP14_ETMACTR8(val)		MCR14(val, 1, c0, c8, 2)
+#define WCP14_ETMACTR9(val)		MCR14(val, 1, c0, c9, 2)
+#define WCP14_ETMACTR10(val)		MCR14(val, 1, c0, c10, 2)
+#define WCP14_ETMACTR11(val)		MCR14(val, 1, c0, c11, 2)
+#define WCP14_ETMACTR12(val)		MCR14(val, 1, c0, c12, 2)
+#define WCP14_ETMACTR13(val)		MCR14(val, 1, c0, c13, 2)
+#define WCP14_ETMACTR14(val)		MCR14(val, 1, c0, c14, 2)
+#define WCP14_ETMACTR15(val)		MCR14(val, 1, c0, c15, 2)
+#define WCP14_ETMDCVR0(val)		MCR14(val, 1, c0, c0, 3)
+#define WCP14_ETMDCVR2(val)		MCR14(val, 1, c0, c2, 3)
+#define WCP14_ETMDCVR4(val)		MCR14(val, 1, c0, c4, 3)
+#define WCP14_ETMDCVR6(val)		MCR14(val, 1, c0, c6, 3)
+#define WCP14_ETMDCVR8(val)		MCR14(val, 1, c0, c8, 3)
+#define WCP14_ETMDCVR10(val)		MCR14(val, 1, c0, c10, 3)
+#define WCP14_ETMDCVR12(val)		MCR14(val, 1, c0, c12, 3)
+#define WCP14_ETMDCVR14(val)		MCR14(val, 1, c0, c14, 3)
+#define WCP14_ETMDCMR0(val)		MCR14(val, 1, c0, c0, 4)
+#define WCP14_ETMDCMR2(val)		MCR14(val, 1, c0, c2, 4)
+#define WCP14_ETMDCMR4(val)		MCR14(val, 1, c0, c4, 4)
+#define WCP14_ETMDCMR6(val)		MCR14(val, 1, c0, c6, 4)
+#define WCP14_ETMDCMR8(val)		MCR14(val, 1, c0, c8, 4)
+#define WCP14_ETMDCMR10(val)		MCR14(val, 1, c0, c10, 4)
+#define WCP14_ETMDCMR12(val)		MCR14(val, 1, c0, c12, 4)
+#define WCP14_ETMDCMR14(val)		MCR14(val, 1, c0, c14, 4)
+#define WCP14_ETMCNTRLDVR0(val)		MCR14(val, 1, c0, c0, 5)
+#define WCP14_ETMCNTRLDVR1(val)		MCR14(val, 1, c0, c1, 5)
+#define WCP14_ETMCNTRLDVR2(val)		MCR14(val, 1, c0, c2, 5)
+#define WCP14_ETMCNTRLDVR3(val)		MCR14(val, 1, c0, c3, 5)
+#define WCP14_ETMCNTENR0(val)		MCR14(val, 1, c0, c4, 5)
+#define WCP14_ETMCNTENR1(val)		MCR14(val, 1, c0, c5, 5)
+#define WCP14_ETMCNTENR2(val)		MCR14(val, 1, c0, c6, 5)
+#define WCP14_ETMCNTENR3(val)		MCR14(val, 1, c0, c7, 5)
+#define WCP14_ETMCNTRLDEVR0(val)	MCR14(val, 1, c0, c8, 5)
+#define WCP14_ETMCNTRLDEVR1(val)	MCR14(val, 1, c0, c9, 5)
+#define WCP14_ETMCNTRLDEVR2(val)	MCR14(val, 1, c0, c10, 5)
+#define WCP14_ETMCNTRLDEVR3(val)	MCR14(val, 1, c0, c11, 5)
+#define WCP14_ETMCNTVR0(val)		MCR14(val, 1, c0, c12, 5)
+#define WCP14_ETMCNTVR1(val)		MCR14(val, 1, c0, c13, 5)
+#define WCP14_ETMCNTVR2(val)		MCR14(val, 1, c0, c14, 5)
+#define WCP14_ETMCNTVR3(val)		MCR14(val, 1, c0, c15, 5)
+#define WCP14_ETMSQ12EVR(val)		MCR14(val, 1, c0, c0, 6)
+#define WCP14_ETMSQ21EVR(val)		MCR14(val, 1, c0, c1, 6)
+#define WCP14_ETMSQ23EVR(val)		MCR14(val, 1, c0, c2, 6)
+#define WCP14_ETMSQ31EVR(val)		MCR14(val, 1, c0, c3, 6)
+#define WCP14_ETMSQ32EVR(val)		MCR14(val, 1, c0, c4, 6)
+#define WCP14_ETMSQ13EVR(val)		MCR14(val, 1, c0, c5, 6)
+#define WCP14_ETMSQR(val)		MCR14(val, 1, c0, c7, 6)
+#define WCP14_ETMEXTOUTEVR0(val)	MCR14(val, 1, c0, c8, 6)
+#define WCP14_ETMEXTOUTEVR1(val)	MCR14(val, 1, c0, c9, 6)
+#define WCP14_ETMEXTOUTEVR2(val)	MCR14(val, 1, c0, c10, 6)
+#define WCP14_ETMEXTOUTEVR3(val)	MCR14(val, 1, c0, c11, 6)
+#define WCP14_ETMCIDCVR0(val)		MCR14(val, 1, c0, c12, 6)
+#define WCP14_ETMCIDCVR1(val)		MCR14(val, 1, c0, c13, 6)
+#define WCP14_ETMCIDCVR2(val)		MCR14(val, 1, c0, c14, 6)
+#define WCP14_ETMCIDCMR(val)		MCR14(val, 1, c0, c15, 6)
+#define WCP14_ETMIMPSPEC0(val)		MCR14(val, 1, c0, c0, 7)
+#define WCP14_ETMIMPSPEC1(val)		MCR14(val, 1, c0, c1, 7)
+#define WCP14_ETMIMPSPEC2(val)		MCR14(val, 1, c0, c2, 7)
+#define WCP14_ETMIMPSPEC3(val)		MCR14(val, 1, c0, c3, 7)
+#define WCP14_ETMIMPSPEC4(val)		MCR14(val, 1, c0, c4, 7)
+#define WCP14_ETMIMPSPEC5(val)		MCR14(val, 1, c0, c5, 7)
+#define WCP14_ETMIMPSPEC6(val)		MCR14(val, 1, c0, c6, 7)
+#define WCP14_ETMIMPSPEC7(val)		MCR14(val, 1, c0, c7, 7)
+/* Can be read only in ETMv3.4, ETMv3.5 */
+#define WCP14_ETMSYNCFR(val)		MCR14(val, 1, c0, c8, 7)
+#define WCP14_ETMEXTINSELR(val)		MCR14(val, 1, c0, c11, 7)
+#define WCP14_ETMTESSEICR(val)		MCR14(val, 1, c0, c12, 7)
+#define WCP14_ETMEIBCR(val)		MCR14(val, 1, c0, c13, 7)
+#define WCP14_ETMTSEVR(val)		MCR14(val, 1, c0, c14, 7)
+#define WCP14_ETMAUXCR(val)		MCR14(val, 1, c0, c15, 7)
+#define WCP14_ETMTRACEIDR(val)		MCR14(val, 1, c1, c0, 0)
+#define WCP14_ETMIDR2(val)		MCR14(val, 1, c1, c2, 0)
+#define WCP14_ETMVMIDCVR(val)		MCR14(val, 1, c1, c0, 1)
+#define WCP14_ETMOSLAR(val)		MCR14(val, 1, c1, c0, 4)
+/* Not available in PFTv1.1 */
+#define WCP14_ETMOSSRR(val)		MCR14(val, 1, c1, c2, 4)
+#define WCP14_ETMPDCR(val)		MCR14(val, 1, c1, c4, 4)
+#define WCP14_ETMPDSR(val)		MCR14(val, 1, c1, c5, 4)
+#define WCP14_ETMITCTRL(val)		MCR14(val, 1, c7, c0, 4)
+#define WCP14_ETMCLAIMSET(val)		MCR14(val, 1, c7, c8, 6)
+#define WCP14_ETMCLAIMCLR(val)		MCR14(val, 1, c7, c9, 6)
+/* Writes to this from CP14 interface are ignored */
+#define WCP14_ETMLAR(val)		MCR14(val, 1, c7, c12, 6)
+
+#endif
diff --git a/arch/arm/include/asm/hardware/dec21285.h b/arch/arm/include/asm/hardware/dec21285.h
new file mode 100644
index 000000000..0d7552751
--- /dev/null
+++ b/arch/arm/include/asm/hardware/dec21285.h
@@ -0,0 +1,147 @@
+/*
+ *  arch/arm/include/asm/hardware/dec21285.h
+ *
+ *  Copyright (C) 1998 Russell King
+ *
+ * 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.
+ *
+ *  DC21285 registers
+ */
+#define DC21285_PCI_IACK		0x79000000
+#define DC21285_ARMCSR_BASE		0x42000000
+#define DC21285_PCI_TYPE_0_CONFIG	0x7b000000
+#define DC21285_PCI_TYPE_1_CONFIG	0x7a000000
+#define DC21285_OUTBOUND_WRITE_FLUSH	0x78000000
+#define DC21285_FLASH			0x41000000
+#define DC21285_PCI_IO			0x7c000000
+#define DC21285_PCI_MEM			0x80000000
+
+#ifndef __ASSEMBLY__
+#include <mach/hardware.h>
+#define DC21285_IO(x)		((volatile unsigned long *)(ARMCSR_BASE+(x)))
+#else
+#define DC21285_IO(x)		(x)
+#endif
+
+#define CSR_PCICMD		DC21285_IO(0x0004)
+#define CSR_CLASSREV		DC21285_IO(0x0008)
+#define CSR_PCICACHELINESIZE	DC21285_IO(0x000c)
+#define CSR_PCICSRBASE		DC21285_IO(0x0010)
+#define CSR_PCICSRIOBASE	DC21285_IO(0x0014)
+#define CSR_PCISDRAMBASE	DC21285_IO(0x0018)
+#define CSR_PCIROMBASE		DC21285_IO(0x0030)
+#define CSR_MBOX0		DC21285_IO(0x0050)
+#define CSR_MBOX1		DC21285_IO(0x0054)
+#define CSR_MBOX2		DC21285_IO(0x0058)
+#define CSR_MBOX3		DC21285_IO(0x005c)
+#define CSR_DOORBELL		DC21285_IO(0x0060)
+#define CSR_DOORBELL_SETUP	DC21285_IO(0x0064)
+#define CSR_ROMWRITEREG		DC21285_IO(0x0068)
+#define CSR_CSRBASEMASK		DC21285_IO(0x00f8)
+#define CSR_CSRBASEOFFSET	DC21285_IO(0x00fc)
+#define CSR_SDRAMBASEMASK	DC21285_IO(0x0100)
+#define CSR_SDRAMBASEOFFSET	DC21285_IO(0x0104)
+#define CSR_ROMBASEMASK		DC21285_IO(0x0108)
+#define CSR_SDRAMTIMING		DC21285_IO(0x010c)
+#define CSR_SDRAMADDRSIZE0	DC21285_IO(0x0110)
+#define CSR_SDRAMADDRSIZE1	DC21285_IO(0x0114)
+#define CSR_SDRAMADDRSIZE2	DC21285_IO(0x0118)
+#define CSR_SDRAMADDRSIZE3	DC21285_IO(0x011c)
+#define CSR_I2O_INFREEHEAD	DC21285_IO(0x0120)
+#define CSR_I2O_INPOSTTAIL	DC21285_IO(0x0124)
+#define CSR_I2O_OUTPOSTHEAD	DC21285_IO(0x0128)
+#define CSR_I2O_OUTFREETAIL	DC21285_IO(0x012c)
+#define CSR_I2O_INFREECOUNT	DC21285_IO(0x0130)
+#define CSR_I2O_OUTPOSTCOUNT	DC21285_IO(0x0134)
+#define CSR_I2O_INPOSTCOUNT	DC21285_IO(0x0138)
+#define CSR_SA110_CNTL		DC21285_IO(0x013c)
+#define SA110_CNTL_INITCMPLETE		(1 << 0)
+#define SA110_CNTL_ASSERTSERR		(1 << 1)
+#define SA110_CNTL_RXSERR		(1 << 3)
+#define SA110_CNTL_SA110DRAMPARITY	(1 << 4)
+#define SA110_CNTL_PCISDRAMPARITY	(1 << 5)
+#define SA110_CNTL_DMASDRAMPARITY	(1 << 6)
+#define SA110_CNTL_DISCARDTIMER		(1 << 8)
+#define SA110_CNTL_PCINRESET		(1 << 9)
+#define SA110_CNTL_I2O_256		(0 << 10)
+#define SA110_CNTL_I20_512		(1 << 10)
+#define SA110_CNTL_I2O_1024		(2 << 10)
+#define SA110_CNTL_I2O_2048		(3 << 10)
+#define SA110_CNTL_I2O_4096		(4 << 10)
+#define SA110_CNTL_I2O_8192		(5 << 10)
+#define SA110_CNTL_I2O_16384		(6 << 10)
+#define SA110_CNTL_I2O_32768		(7 << 10)
+#define SA110_CNTL_WATCHDOG		(1 << 13)
+#define SA110_CNTL_ROMWIDTH_UNDEF	(0 << 14)
+#define SA110_CNTL_ROMWIDTH_16		(1 << 14)
+#define SA110_CNTL_ROMWIDTH_32		(2 << 14)
+#define SA110_CNTL_ROMWIDTH_8		(3 << 14)
+#define SA110_CNTL_ROMACCESSTIME(x)	((x)<<16)
+#define SA110_CNTL_ROMBURSTTIME(x)	((x)<<20)
+#define SA110_CNTL_ROMTRISTATETIME(x)	((x)<<24)
+#define SA110_CNTL_XCSDIR(x)		((x)<<28)
+#define SA110_CNTL_PCICFN		(1 << 31)
+
+/*
+ * footbridge_cfn_mode() is used when we want
+ * to check whether we are the central function
+ */
+#define __footbridge_cfn_mode() (*CSR_SA110_CNTL & SA110_CNTL_PCICFN)
+#if defined(CONFIG_FOOTBRIDGE_HOST) && defined(CONFIG_FOOTBRIDGE_ADDIN)
+#define footbridge_cfn_mode() __footbridge_cfn_mode()
+#elif defined(CONFIG_FOOTBRIDGE_HOST)
+#define footbridge_cfn_mode() (1)
+#else
+#define footbridge_cfn_mode() (0)
+#endif
+
+#define CSR_PCIADDR_EXTN	DC21285_IO(0x0140)
+#define CSR_PREFETCHMEMRANGE	DC21285_IO(0x0144)
+#define CSR_XBUS_CYCLE		DC21285_IO(0x0148)
+#define CSR_XBUS_IOSTROBE	DC21285_IO(0x014c)
+#define CSR_DOORBELL_PCI	DC21285_IO(0x0150)
+#define CSR_DOORBELL_SA110	DC21285_IO(0x0154)
+#define CSR_UARTDR		DC21285_IO(0x0160)
+#define CSR_RXSTAT		DC21285_IO(0x0164)
+#define CSR_H_UBRLCR		DC21285_IO(0x0168)
+#define CSR_M_UBRLCR		DC21285_IO(0x016c)
+#define CSR_L_UBRLCR		DC21285_IO(0x0170)
+#define CSR_UARTCON		DC21285_IO(0x0174)
+#define CSR_UARTFLG		DC21285_IO(0x0178)
+#define CSR_IRQ_STATUS		DC21285_IO(0x0180)
+#define CSR_IRQ_RAWSTATUS	DC21285_IO(0x0184)
+#define CSR_IRQ_ENABLE		DC21285_IO(0x0188)
+#define CSR_IRQ_DISABLE		DC21285_IO(0x018c)
+#define CSR_IRQ_SOFT		DC21285_IO(0x0190)
+#define CSR_FIQ_STATUS		DC21285_IO(0x0280)
+#define CSR_FIQ_RAWSTATUS	DC21285_IO(0x0284)
+#define CSR_FIQ_ENABLE		DC21285_IO(0x0288)
+#define CSR_FIQ_DISABLE		DC21285_IO(0x028c)
+#define CSR_FIQ_SOFT		DC21285_IO(0x0290)
+#define CSR_TIMER1_LOAD		DC21285_IO(0x0300)
+#define CSR_TIMER1_VALUE	DC21285_IO(0x0304)
+#define CSR_TIMER1_CNTL		DC21285_IO(0x0308)
+#define CSR_TIMER1_CLR		DC21285_IO(0x030c)
+#define CSR_TIMER2_LOAD		DC21285_IO(0x0320)
+#define CSR_TIMER2_VALUE	DC21285_IO(0x0324)
+#define CSR_TIMER2_CNTL		DC21285_IO(0x0328)
+#define CSR_TIMER2_CLR		DC21285_IO(0x032c)
+#define CSR_TIMER3_LOAD		DC21285_IO(0x0340)
+#define CSR_TIMER3_VALUE	DC21285_IO(0x0344)
+#define CSR_TIMER3_CNTL		DC21285_IO(0x0348)
+#define CSR_TIMER3_CLR		DC21285_IO(0x034c)
+#define CSR_TIMER4_LOAD		DC21285_IO(0x0360)
+#define CSR_TIMER4_VALUE	DC21285_IO(0x0364)
+#define CSR_TIMER4_CNTL		DC21285_IO(0x0368)
+#define CSR_TIMER4_CLR		DC21285_IO(0x036c)
+
+#define TIMER_CNTL_ENABLE	(1 << 7)
+#define TIMER_CNTL_AUTORELOAD	(1 << 6)
+#define TIMER_CNTL_DIV1		(0)
+#define TIMER_CNTL_DIV16	(1 << 2)
+#define TIMER_CNTL_DIV256	(2 << 2)
+#define TIMER_CNTL_CNTEXT	(3 << 2)
+
+
diff --git a/arch/arm/include/asm/hardware/entry-macro-iomd.S b/arch/arm/include/asm/hardware/entry-macro-iomd.S
new file mode 100644
index 000000000..8c215acd9
--- /dev/null
+++ b/arch/arm/include/asm/hardware/entry-macro-iomd.S
@@ -0,0 +1,131 @@
+/*
+ * arch/arm/include/asm/hardware/entry-macro-iomd.S
+ *
+ * Low-level IRQ helper macros for IOC/IOMD based platforms
+ *
+ * This file is licensed under  the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+/* IOC / IOMD based hardware */
+#include <asm/hardware/iomd.h>
+
+		.macro	get_irqnr_and_base, irqnr, irqstat, base, tmp
+		ldrb	\irqstat, [\base, #IOMD_IRQREQB]	@ get high priority first
+		ldr	\tmp, =irq_prio_h
+		teq	\irqstat, #0
+#ifdef IOMD_BASE
+		ldreqb	\irqstat, [\base, #IOMD_DMAREQ]	@ get dma
+		addeq	\tmp, \tmp, #256		@ irq_prio_h table size
+		teqeq	\irqstat, #0
+		bne	2406f
+#endif
+		ldreqb	\irqstat, [\base, #IOMD_IRQREQA]	@ get low priority
+		addeq	\tmp, \tmp, #256		@ irq_prio_d table size
+		teqeq	\irqstat, #0
+#ifdef IOMD_IRQREQC
+		ldreqb	\irqstat, [\base, #IOMD_IRQREQC]
+		addeq	\tmp, \tmp, #256		@ irq_prio_l table size
+		teqeq	\irqstat, #0
+#endif
+#ifdef IOMD_IRQREQD
+		ldreqb	\irqstat, [\base, #IOMD_IRQREQD]
+		addeq	\tmp, \tmp, #256		@ irq_prio_lc table size
+		teqeq	\irqstat, #0
+#endif
+2406:		ldrneb	\irqnr, [\tmp, \irqstat]	@ get IRQ number
+		.endm
+
+/*
+ * Interrupt table (incorporates priority).  Please note that we
+ * rely on the order of these tables (see above code).
+ */
+		.align	5
+irq_prio_h:	.byte	 0, 8, 9, 8,10,10,10,10,11,11,11,11,10,10,10,10
+		.byte	12, 8, 9, 8,10,10,10,10,11,11,11,11,10,10,10,10
+		.byte	13,13,13,13,10,10,10,10,11,11,11,11,10,10,10,10
+		.byte	13,13,13,13,10,10,10,10,11,11,11,11,10,10,10,10
+		.byte	14,14,14,14,10,10,10,10,11,11,11,11,10,10,10,10
+		.byte	14,14,14,14,10,10,10,10,11,11,11,11,10,10,10,10
+		.byte	13,13,13,13,10,10,10,10,11,11,11,11,10,10,10,10
+		.byte	13,13,13,13,10,10,10,10,11,11,11,11,10,10,10,10
+		.byte	15,15,15,15,10,10,10,10,11,11,11,11,10,10,10,10
+		.byte	15,15,15,15,10,10,10,10,11,11,11,11,10,10,10,10
+		.byte	13,13,13,13,10,10,10,10,11,11,11,11,10,10,10,10
+		.byte	13,13,13,13,10,10,10,10,11,11,11,11,10,10,10,10
+		.byte	15,15,15,15,10,10,10,10,11,11,11,11,10,10,10,10
+		.byte	15,15,15,15,10,10,10,10,11,11,11,11,10,10,10,10
+		.byte	13,13,13,13,10,10,10,10,11,11,11,11,10,10,10,10
+		.byte	13,13,13,13,10,10,10,10,11,11,11,11,10,10,10,10
+#ifdef IOMD_BASE
+irq_prio_d:	.byte	 0,16,17,16,18,16,17,16,19,16,17,16,18,16,17,16
+		.byte	20,16,17,16,18,16,17,16,19,16,17,16,18,16,17,16
+		.byte	21,16,17,16,18,16,17,16,19,16,17,16,18,16,17,16
+		.byte	21,16,17,16,18,16,17,16,19,16,17,16,18,16,17,16
+		.byte	22,16,17,16,18,16,17,16,19,16,17,16,18,16,17,16
+		.byte	22,16,17,16,18,16,17,16,19,16,17,16,18,16,17,16
+		.byte	21,16,17,16,18,16,17,16,19,16,17,16,18,16,17,16
+		.byte	21,16,17,16,18,16,17,16,19,16,17,16,18,16,17,16
+		.byte	23,16,17,16,18,16,17,16,19,16,17,16,18,16,17,16
+		.byte	23,16,17,16,18,16,17,16,19,16,17,16,18,16,17,16
+		.byte	21,16,17,16,18,16,17,16,19,16,17,16,18,16,17,16
+		.byte	21,16,17,16,18,16,17,16,19,16,17,16,18,16,17,16
+		.byte	22,16,17,16,18,16,17,16,19,16,17,16,18,16,17,16
+		.byte	22,16,17,16,18,16,17,16,19,16,17,16,18,16,17,16
+		.byte	21,16,17,16,18,16,17,16,19,16,17,16,18,16,17,16
+		.byte	21,16,17,16,18,16,17,16,19,16,17,16,18,16,17,16
+#endif
+irq_prio_l:	.byte	 0, 0, 1, 0, 2, 2, 2, 2, 3, 3, 3, 3, 3, 3, 3, 3
+		.byte	 4, 0, 1, 0, 2, 2, 2, 2, 3, 3, 3, 3, 3, 3, 3, 3
+		.byte	 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5
+		.byte	 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5
+		.byte	 6, 6, 6, 6, 6, 6, 6, 6, 3, 3, 3, 3, 3, 3, 3, 3
+		.byte	 6, 6, 6, 6, 6, 6, 6, 6, 3, 3, 3, 3, 3, 3, 3, 3
+		.byte	 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5
+		.byte	 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5
+		.byte	 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7
+		.byte	 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7
+		.byte	 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7
+		.byte	 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7
+		.byte	 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7
+		.byte	 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7
+		.byte	 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7
+		.byte	 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7
+#ifdef IOMD_IRQREQC
+irq_prio_lc:	.byte	24,24,25,24,26,26,26,26,27,27,27,27,27,27,27,27
+		.byte	28,24,25,24,26,26,26,26,27,27,27,27,27,27,27,27
+		.byte	29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,29
+		.byte	29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,29
+		.byte	30,30,30,30,30,30,30,30,27,27,27,27,27,27,27,27
+		.byte	30,30,30,30,30,30,30,30,27,27,27,27,27,27,27,27
+		.byte	29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,29
+		.byte	29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,29
+		.byte	31,31,31,31,31,31,31,31,31,31,31,31,31,31,31,31
+		.byte	31,31,31,31,31,31,31,31,31,31,31,31,31,31,31,31
+		.byte	31,31,31,31,31,31,31,31,31,31,31,31,31,31,31,31
+		.byte	31,31,31,31,31,31,31,31,31,31,31,31,31,31,31,31
+		.byte	31,31,31,31,31,31,31,31,31,31,31,31,31,31,31,31
+		.byte	31,31,31,31,31,31,31,31,31,31,31,31,31,31,31,31
+		.byte	31,31,31,31,31,31,31,31,31,31,31,31,31,31,31,31
+		.byte	31,31,31,31,31,31,31,31,31,31,31,31,31,31,31,31
+#endif
+#ifdef IOMD_IRQREQD
+irq_prio_ld:	.byte	40,40,41,40,42,42,42,42,43,43,43,43,43,43,43,43
+		.byte	44,40,41,40,42,42,42,42,43,43,43,43,43,43,43,43
+		.byte	45,45,45,45,45,45,45,45,45,45,45,45,45,45,45,45
+		.byte	45,45,45,45,45,45,45,45,45,45,45,45,45,45,45,45
+		.byte	46,46,46,46,46,46,46,46,43,43,43,43,43,43,43,43
+		.byte	46,46,46,46,46,46,46,46,43,43,43,43,43,43,43,43
+		.byte	45,45,45,45,45,45,45,45,45,45,45,45,45,45,45,45
+		.byte	45,45,45,45,45,45,45,45,45,45,45,45,45,45,45,45
+		.byte	47,47,47,47,47,47,47,47,47,47,47,47,47,47,47,47
+		.byte	47,47,47,47,47,47,47,47,47,47,47,47,47,47,47,47
+		.byte	47,47,47,47,47,47,47,47,47,47,47,47,47,47,47,47
+		.byte	47,47,47,47,47,47,47,47,47,47,47,47,47,47,47,47
+		.byte	47,47,47,47,47,47,47,47,47,47,47,47,47,47,47,47
+		.byte	47,47,47,47,47,47,47,47,47,47,47,47,47,47,47,47
+		.byte	47,47,47,47,47,47,47,47,47,47,47,47,47,47,47,47
+		.byte	47,47,47,47,47,47,47,47,47,47,47,47,47,47,47,47
+#endif
+
diff --git a/arch/arm/include/asm/hardware/icst.h b/arch/arm/include/asm/hardware/icst.h
new file mode 100644
index 000000000..794220b08
--- /dev/null
+++ b/arch/arm/include/asm/hardware/icst.h
@@ -0,0 +1,59 @@
+/*
+ *  arch/arm/include/asm/hardware/icst.h
+ *
+ *  Copyright (C) 2003 Deep Blue Solutions, Ltd, 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 as
+ * published by the Free Software Foundation.
+ *
+ *  Support functions for calculating clocks/divisors for the ICST
+ *  clock generators.  See http://www.idt.com/ for more information
+ *  on these devices.
+ */
+#ifndef ASMARM_HARDWARE_ICST_H
+#define ASMARM_HARDWARE_ICST_H
+
+struct icst_params {
+	unsigned long	ref;
+	unsigned long	vco_max;	/* inclusive */
+	unsigned long	vco_min;	/* exclusive */
+	unsigned short	vd_min;		/* inclusive */
+	unsigned short	vd_max;		/* inclusive */
+	unsigned char	rd_min;		/* inclusive */
+	unsigned char	rd_max;		/* inclusive */
+	const unsigned char *s2div;	/* chip specific s2div array */
+	const unsigned char *idx2s;	/* chip specific idx2s array */
+};
+
+struct icst_vco {
+	unsigned short	v;
+	unsigned char	r;
+	unsigned char	s;
+};
+
+unsigned long icst_hz(const struct icst_params *p, struct icst_vco vco);
+struct icst_vco icst_hz_to_vco(const struct icst_params *p, unsigned long freq);
+
+/*
+ * ICST307 VCO frequency must be between 6MHz and 200MHz (3.3 or 5V).
+ * This frequency is pre-output divider.
+ */
+#define ICST307_VCO_MIN	6000000
+#define ICST307_VCO_MAX	200000000
+
+extern const unsigned char icst307_s2div[];
+extern const unsigned char icst307_idx2s[];
+
+/*
+ * ICST525 VCO frequency must be between 10MHz and 200MHz (3V) or 320MHz (5V).
+ * This frequency is pre-output divider.
+ */
+#define ICST525_VCO_MIN		10000000
+#define ICST525_VCO_MAX_3V	200000000
+#define ICST525_VCO_MAX_5V	320000000
+
+extern const unsigned char icst525_s2div[];
+extern const unsigned char icst525_idx2s[];
+
+#endif
diff --git a/arch/arm/include/asm/hardware/ioc.h b/arch/arm/include/asm/hardware/ioc.h
new file mode 100644
index 000000000..1f6b8013b
--- /dev/null
+++ b/arch/arm/include/asm/hardware/ioc.h
@@ -0,0 +1,72 @@
+/*
+ *  arch/arm/include/asm/hardware/ioc.h
+ *
+ *  Copyright (C) Russell King
+ *
+ * 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.
+ *
+ *  Use these macros to read/write the IOC.  All it does is perform the actual
+ *  read/write.
+ */
+#ifndef __ASMARM_HARDWARE_IOC_H
+#define __ASMARM_HARDWARE_IOC_H
+
+#ifndef __ASSEMBLY__
+
+/*
+ * We use __raw_base variants here so that we give the compiler the
+ * chance to keep IOC_BASE in a register.
+ */
+#define ioc_readb(off)		__raw_readb(IOC_BASE + (off))
+#define ioc_writeb(val,off)	__raw_writeb(val, IOC_BASE + (off))
+
+#endif
+
+#define IOC_CONTROL	(0x00)
+#define IOC_KARTTX	(0x04)
+#define IOC_KARTRX	(0x04)
+
+#define IOC_IRQSTATA	(0x10)
+#define IOC_IRQREQA	(0x14)
+#define IOC_IRQCLRA	(0x14)
+#define IOC_IRQMASKA	(0x18)
+
+#define IOC_IRQSTATB	(0x20)
+#define IOC_IRQREQB	(0x24)
+#define IOC_IRQMASKB	(0x28)
+
+#define IOC_FIQSTAT	(0x30)
+#define IOC_FIQREQ	(0x34)
+#define IOC_FIQMASK	(0x38)
+
+#define IOC_T0CNTL	(0x40)
+#define IOC_T0LTCHL	(0x40)
+#define IOC_T0CNTH	(0x44)
+#define IOC_T0LTCHH	(0x44)
+#define IOC_T0GO	(0x48)
+#define IOC_T0LATCH	(0x4c)
+
+#define IOC_T1CNTL	(0x50)
+#define IOC_T1LTCHL	(0x50)
+#define IOC_T1CNTH	(0x54)
+#define IOC_T1LTCHH	(0x54)
+#define IOC_T1GO	(0x58)
+#define IOC_T1LATCH	(0x5c)
+
+#define IOC_T2CNTL	(0x60)
+#define IOC_T2LTCHL	(0x60)
+#define IOC_T2CNTH	(0x64)
+#define IOC_T2LTCHH	(0x64)
+#define IOC_T2GO	(0x68)
+#define IOC_T2LATCH	(0x6c)
+
+#define IOC_T3CNTL	(0x70)
+#define IOC_T3LTCHL	(0x70)
+#define IOC_T3CNTH	(0x74)
+#define IOC_T3LTCHH	(0x74)
+#define IOC_T3GO	(0x78)
+#define IOC_T3LATCH	(0x7c)
+
+#endif
diff --git a/arch/arm/include/asm/hardware/iomd.h b/arch/arm/include/asm/hardware/iomd.h
new file mode 100644
index 000000000..f9ee69e4f
--- /dev/null
+++ b/arch/arm/include/asm/hardware/iomd.h
@@ -0,0 +1,185 @@
+/*
+ *  arch/arm/include/asm/hardware/iomd.h
+ *
+ *  Copyright (C) 1999 Russell King
+ *
+ * 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 file contains information out the IOMD ASIC used in the
+ *  Acorn RiscPC and subsequently integrated into the CLPS7500 chips.
+ */
+#ifndef __ASMARM_HARDWARE_IOMD_H
+#define __ASMARM_HARDWARE_IOMD_H
+
+
+#ifndef __ASSEMBLY__
+
+/*
+ * We use __raw_base variants here so that we give the compiler the
+ * chance to keep IOC_BASE in a register.
+ */
+#define iomd_readb(off)		__raw_readb(IOMD_BASE + (off))
+#define iomd_readl(off)		__raw_readl(IOMD_BASE + (off))
+#define iomd_writeb(val,off)	__raw_writeb(val, IOMD_BASE + (off))
+#define iomd_writel(val,off)	__raw_writel(val, IOMD_BASE + (off))
+
+#endif
+
+#define IOMD_CONTROL	(0x000)
+#define IOMD_KARTTX	(0x004)
+#define IOMD_KARTRX	(0x004)
+#define IOMD_KCTRL	(0x008)
+
+#define IOMD_IRQSTATA	(0x010)
+#define IOMD_IRQREQA	(0x014)
+#define IOMD_IRQCLRA	(0x014)
+#define IOMD_IRQMASKA	(0x018)
+
+#define IOMD_IRQSTATB	(0x020)
+#define IOMD_IRQREQB	(0x024)
+#define IOMD_IRQMASKB	(0x028)
+
+#define IOMD_FIQSTAT	(0x030)
+#define IOMD_FIQREQ	(0x034)
+#define IOMD_FIQMASK	(0x038)
+
+#define IOMD_T0CNTL	(0x040)
+#define IOMD_T0LTCHL	(0x040)
+#define IOMD_T0CNTH	(0x044)
+#define IOMD_T0LTCHH	(0x044)
+#define IOMD_T0GO	(0x048)
+#define IOMD_T0LATCH	(0x04c)
+
+#define IOMD_T1CNTL	(0x050)
+#define IOMD_T1LTCHL	(0x050)
+#define IOMD_T1CNTH	(0x054)
+#define IOMD_T1LTCHH	(0x054)
+#define IOMD_T1GO	(0x058)
+#define IOMD_T1LATCH	(0x05c)
+
+#define IOMD_ROMCR0	(0x080)
+#define IOMD_ROMCR1	(0x084)
+#ifdef CONFIG_ARCH_RPC
+#define IOMD_DRAMCR	(0x088)
+#endif
+#define IOMD_REFCR	(0x08C)
+
+#define IOMD_FSIZE	(0x090)
+#define IOMD_ID0	(0x094)
+#define IOMD_ID1	(0x098)
+#define IOMD_VERSION	(0x09C)
+
+#ifdef CONFIG_ARCH_RPC
+#define IOMD_MOUSEX	(0x0A0)
+#define IOMD_MOUSEY	(0x0A4)
+#endif
+
+#ifdef CONFIG_ARCH_RPC
+#define IOMD_DMATCR	(0x0C0)
+#endif
+#define IOMD_IOTCR	(0x0C4)
+#define IOMD_ECTCR	(0x0C8)
+#ifdef CONFIG_ARCH_RPC
+#define IOMD_DMAEXT	(0x0CC)
+#endif
+
+#ifdef CONFIG_ARCH_RPC
+#define DMA_EXT_IO0	1
+#define DMA_EXT_IO1	2
+#define DMA_EXT_IO2	4
+#define DMA_EXT_IO3	8
+
+#define IOMD_IO0CURA	(0x100)
+#define IOMD_IO0ENDA	(0x104)
+#define IOMD_IO0CURB	(0x108)
+#define IOMD_IO0ENDB	(0x10C)
+#define IOMD_IO0CR	(0x110)
+#define IOMD_IO0ST	(0x114)
+
+#define IOMD_IO1CURA	(0x120)
+#define IOMD_IO1ENDA	(0x124)
+#define IOMD_IO1CURB	(0x128)
+#define IOMD_IO1ENDB	(0x12C)
+#define IOMD_IO1CR	(0x130)
+#define IOMD_IO1ST	(0x134)
+
+#define IOMD_IO2CURA	(0x140)
+#define IOMD_IO2ENDA	(0x144)
+#define IOMD_IO2CURB	(0x148)
+#define IOMD_IO2ENDB	(0x14C)
+#define IOMD_IO2CR	(0x150)
+#define IOMD_IO2ST	(0x154)
+
+#define IOMD_IO3CURA	(0x160)
+#define IOMD_IO3ENDA	(0x164)
+#define IOMD_IO3CURB	(0x168)
+#define IOMD_IO3ENDB	(0x16C)
+#define IOMD_IO3CR	(0x170)
+#define IOMD_IO3ST	(0x174)
+#endif
+
+#define IOMD_SD0CURA	(0x180)
+#define IOMD_SD0ENDA	(0x184)
+#define IOMD_SD0CURB	(0x188)
+#define IOMD_SD0ENDB	(0x18C)
+#define IOMD_SD0CR	(0x190)
+#define IOMD_SD0ST	(0x194)
+
+#ifdef CONFIG_ARCH_RPC
+#define IOMD_SD1CURA	(0x1A0)
+#define IOMD_SD1ENDA	(0x1A4)
+#define IOMD_SD1CURB	(0x1A8)
+#define IOMD_SD1ENDB	(0x1AC)
+#define IOMD_SD1CR	(0x1B0)
+#define IOMD_SD1ST	(0x1B4)
+#endif
+
+#define IOMD_CURSCUR	(0x1C0)
+#define IOMD_CURSINIT	(0x1C4)
+
+#define IOMD_VIDCUR	(0x1D0)
+#define IOMD_VIDEND	(0x1D4)
+#define IOMD_VIDSTART	(0x1D8)
+#define IOMD_VIDINIT	(0x1DC)
+#define IOMD_VIDCR	(0x1E0)
+
+#define IOMD_DMASTAT	(0x1F0)
+#define IOMD_DMAREQ	(0x1F4)
+#define IOMD_DMAMASK	(0x1F8)
+
+#define DMA_END_S	(1 << 31)
+#define DMA_END_L	(1 << 30)
+
+#define DMA_CR_C	0x80
+#define DMA_CR_D	0x40
+#define DMA_CR_E	0x20
+
+#define DMA_ST_OFL	4
+#define DMA_ST_INT	2
+#define DMA_ST_AB	1
+
+/*
+ * DMA (MEMC) compatibility
+ */
+#define HALF_SAM	vram_half_sam
+#define VDMA_ALIGNMENT	(HALF_SAM * 2)
+#define VDMA_XFERSIZE	(HALF_SAM)
+#define VDMA_INIT	IOMD_VIDINIT
+#define VDMA_START	IOMD_VIDSTART
+#define VDMA_END	IOMD_VIDEND
+
+#ifndef __ASSEMBLY__
+extern unsigned int vram_half_sam;
+#define video_set_dma(start,end,offset)				\
+do {								\
+	outl (SCREEN_START + start, VDMA_START);		\
+	outl (SCREEN_START + end - VDMA_XFERSIZE, VDMA_END);	\
+	if (offset >= end - VDMA_XFERSIZE)			\
+		offset |= 0x40000000;				\
+	outl (SCREEN_START + offset, VDMA_INIT);		\
+} while (0)
+#endif
+
+#endif
diff --git a/arch/arm/include/asm/hardware/iop3xx-adma.h b/arch/arm/include/asm/hardware/iop3xx-adma.h
new file mode 100644
index 000000000..240b29ef1
--- /dev/null
+++ b/arch/arm/include/asm/hardware/iop3xx-adma.h
@@ -0,0 +1,932 @@
+/*
+ * Copyright © 2006, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope 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, write to the Free Software Foundation, Inc.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ */
+#ifndef _ADMA_H
+#define _ADMA_H
+#include <linux/types.h>
+#include <linux/io.h>
+#include <mach/hardware.h>
+#include <asm/hardware/iop_adma.h>
+
+/* Memory copy units */
+#define DMA_CCR(chan)		(chan->mmr_base + 0x0)
+#define DMA_CSR(chan)		(chan->mmr_base + 0x4)
+#define DMA_DAR(chan)		(chan->mmr_base + 0xc)
+#define DMA_NDAR(chan)		(chan->mmr_base + 0x10)
+#define DMA_PADR(chan)		(chan->mmr_base + 0x14)
+#define DMA_PUADR(chan)	(chan->mmr_base + 0x18)
+#define DMA_LADR(chan)		(chan->mmr_base + 0x1c)
+#define DMA_BCR(chan)		(chan->mmr_base + 0x20)
+#define DMA_DCR(chan)		(chan->mmr_base + 0x24)
+
+/* Application accelerator unit  */
+#define AAU_ACR(chan)		(chan->mmr_base + 0x0)
+#define AAU_ASR(chan)		(chan->mmr_base + 0x4)
+#define AAU_ADAR(chan)		(chan->mmr_base + 0x8)
+#define AAU_ANDAR(chan)	(chan->mmr_base + 0xc)
+#define AAU_SAR(src, chan)	(chan->mmr_base + (0x10 + ((src) << 2)))
+#define AAU_DAR(chan)		(chan->mmr_base + 0x20)
+#define AAU_ABCR(chan)		(chan->mmr_base + 0x24)
+#define AAU_ADCR(chan)		(chan->mmr_base + 0x28)
+#define AAU_SAR_EDCR(src_edc)	(chan->mmr_base + (0x02c + ((src_edc-4) << 2)))
+#define AAU_EDCR0_IDX	8
+#define AAU_EDCR1_IDX	17
+#define AAU_EDCR2_IDX	26
+
+#define DMA0_ID 0
+#define DMA1_ID 1
+#define AAU_ID 2
+
+struct iop3xx_aau_desc_ctrl {
+	unsigned int int_en:1;
+	unsigned int blk1_cmd_ctrl:3;
+	unsigned int blk2_cmd_ctrl:3;
+	unsigned int blk3_cmd_ctrl:3;
+	unsigned int blk4_cmd_ctrl:3;
+	unsigned int blk5_cmd_ctrl:3;
+	unsigned int blk6_cmd_ctrl:3;
+	unsigned int blk7_cmd_ctrl:3;
+	unsigned int blk8_cmd_ctrl:3;
+	unsigned int blk_ctrl:2;
+	unsigned int dual_xor_en:1;
+	unsigned int tx_complete:1;
+	unsigned int zero_result_err:1;
+	unsigned int zero_result_en:1;
+	unsigned int dest_write_en:1;
+};
+
+struct iop3xx_aau_e_desc_ctrl {
+	unsigned int reserved:1;
+	unsigned int blk1_cmd_ctrl:3;
+	unsigned int blk2_cmd_ctrl:3;
+	unsigned int blk3_cmd_ctrl:3;
+	unsigned int blk4_cmd_ctrl:3;
+	unsigned int blk5_cmd_ctrl:3;
+	unsigned int blk6_cmd_ctrl:3;
+	unsigned int blk7_cmd_ctrl:3;
+	unsigned int blk8_cmd_ctrl:3;
+	unsigned int reserved2:7;
+};
+
+struct iop3xx_dma_desc_ctrl {
+	unsigned int pci_transaction:4;
+	unsigned int int_en:1;
+	unsigned int dac_cycle_en:1;
+	unsigned int mem_to_mem_en:1;
+	unsigned int crc_data_tx_en:1;
+	unsigned int crc_gen_en:1;
+	unsigned int crc_seed_dis:1;
+	unsigned int reserved:21;
+	unsigned int crc_tx_complete:1;
+};
+
+struct iop3xx_desc_dma {
+	u32 next_desc;
+	union {
+		u32 pci_src_addr;
+		u32 pci_dest_addr;
+		u32 src_addr;
+	};
+	union {
+		u32 upper_pci_src_addr;
+		u32 upper_pci_dest_addr;
+	};
+	union {
+		u32 local_pci_src_addr;
+		u32 local_pci_dest_addr;
+		u32 dest_addr;
+	};
+	u32 byte_count;
+	union {
+		u32 desc_ctrl;
+		struct iop3xx_dma_desc_ctrl desc_ctrl_field;
+	};
+	u32 crc_addr;
+};
+
+struct iop3xx_desc_aau {
+	u32 next_desc;
+	u32 src[4];
+	u32 dest_addr;
+	u32 byte_count;
+	union {
+		u32 desc_ctrl;
+		struct iop3xx_aau_desc_ctrl desc_ctrl_field;
+	};
+	union {
+		u32 src_addr;
+		u32 e_desc_ctrl;
+		struct iop3xx_aau_e_desc_ctrl e_desc_ctrl_field;
+	} src_edc[31];
+};
+
+struct iop3xx_aau_gfmr {
+	unsigned int gfmr1:8;
+	unsigned int gfmr2:8;
+	unsigned int gfmr3:8;
+	unsigned int gfmr4:8;
+};
+
+struct iop3xx_desc_pq_xor {
+	u32 next_desc;
+	u32 src[3];
+	union {
+		u32 data_mult1;
+		struct iop3xx_aau_gfmr data_mult1_field;
+	};
+	u32 dest_addr;
+	u32 byte_count;
+	union {
+		u32 desc_ctrl;
+		struct iop3xx_aau_desc_ctrl desc_ctrl_field;
+	};
+	union {
+		u32 src_addr;
+		u32 e_desc_ctrl;
+		struct iop3xx_aau_e_desc_ctrl e_desc_ctrl_field;
+		u32 data_multiplier;
+		struct iop3xx_aau_gfmr data_mult_field;
+		u32 reserved;
+	} src_edc_gfmr[19];
+};
+
+struct iop3xx_desc_dual_xor {
+	u32 next_desc;
+	u32 src0_addr;
+	u32 src1_addr;
+	u32 h_src_addr;
+	u32 d_src_addr;
+	u32 h_dest_addr;
+	u32 byte_count;
+	union {
+		u32 desc_ctrl;
+		struct iop3xx_aau_desc_ctrl desc_ctrl_field;
+	};
+	u32 d_dest_addr;
+};
+
+union iop3xx_desc {
+	struct iop3xx_desc_aau *aau;
+	struct iop3xx_desc_dma *dma;
+	struct iop3xx_desc_pq_xor *pq_xor;
+	struct iop3xx_desc_dual_xor *dual_xor;
+	void *ptr;
+};
+
+/* No support for p+q operations */
+static inline int
+iop_chan_pq_slot_count(size_t len, int src_cnt, int *slots_per_op)
+{
+	BUG();
+	return 0;
+}
+
+static inline void
+iop_desc_init_pq(struct iop_adma_desc_slot *desc, int src_cnt,
+		  unsigned long flags)
+{
+	BUG();
+}
+
+static inline void
+iop_desc_set_pq_addr(struct iop_adma_desc_slot *desc, dma_addr_t *addr)
+{
+	BUG();
+}
+
+static inline void
+iop_desc_set_pq_src_addr(struct iop_adma_desc_slot *desc, int src_idx,
+			 dma_addr_t addr, unsigned char coef)
+{
+	BUG();
+}
+
+static inline int
+iop_chan_pq_zero_sum_slot_count(size_t len, int src_cnt, int *slots_per_op)
+{
+	BUG();
+	return 0;
+}
+
+static inline void
+iop_desc_init_pq_zero_sum(struct iop_adma_desc_slot *desc, int src_cnt,
+			  unsigned long flags)
+{
+	BUG();
+}
+
+static inline void
+iop_desc_set_pq_zero_sum_byte_count(struct iop_adma_desc_slot *desc, u32 len)
+{
+	BUG();
+}
+
+#define iop_desc_set_pq_zero_sum_src_addr iop_desc_set_pq_src_addr
+
+static inline void
+iop_desc_set_pq_zero_sum_addr(struct iop_adma_desc_slot *desc, int pq_idx,
+			      dma_addr_t *src)
+{
+	BUG();
+}
+
+static inline int iop_adma_get_max_xor(void)
+{
+	return 32;
+}
+
+static inline int iop_adma_get_max_pq(void)
+{
+	BUG();
+	return 0;
+}
+
+static inline u32 iop_chan_get_current_descriptor(struct iop_adma_chan *chan)
+{
+	int id = chan->device->id;
+
+	switch (id) {
+	case DMA0_ID:
+	case DMA1_ID:
+		return __raw_readl(DMA_DAR(chan));
+	case AAU_ID:
+		return __raw_readl(AAU_ADAR(chan));
+	default:
+		BUG();
+	}
+	return 0;
+}
+
+static inline void iop_chan_set_next_descriptor(struct iop_adma_chan *chan,
+						u32 next_desc_addr)
+{
+	int id = chan->device->id;
+
+	switch (id) {
+	case DMA0_ID:
+	case DMA1_ID:
+		__raw_writel(next_desc_addr, DMA_NDAR(chan));
+		break;
+	case AAU_ID:
+		__raw_writel(next_desc_addr, AAU_ANDAR(chan));
+		break;
+	}
+
+}
+
+#define IOP_ADMA_STATUS_BUSY (1 << 10)
+#define IOP_ADMA_ZERO_SUM_MAX_BYTE_COUNT (1024)
+#define IOP_ADMA_XOR_MAX_BYTE_COUNT (16 * 1024 * 1024)
+#define IOP_ADMA_MAX_BYTE_COUNT (16 * 1024 * 1024)
+
+static inline int iop_chan_is_busy(struct iop_adma_chan *chan)
+{
+	u32 status = __raw_readl(DMA_CSR(chan));
+	return (status & IOP_ADMA_STATUS_BUSY) ? 1 : 0;
+}
+
+static inline int iop_desc_is_aligned(struct iop_adma_desc_slot *desc,
+					int num_slots)
+{
+	/* num_slots will only ever be 1, 2, 4, or 8 */
+	return (desc->idx & (num_slots - 1)) ? 0 : 1;
+}
+
+/* to do: support large (i.e. > hw max) buffer sizes */
+static inline int iop_chan_memcpy_slot_count(size_t len, int *slots_per_op)
+{
+	*slots_per_op = 1;
+	return 1;
+}
+
+/* to do: support large (i.e. > hw max) buffer sizes */
+static inline int iop_chan_memset_slot_count(size_t len, int *slots_per_op)
+{
+	*slots_per_op = 1;
+	return 1;
+}
+
+static inline int iop3xx_aau_xor_slot_count(size_t len, int src_cnt,
+					int *slots_per_op)
+{
+	static const char slot_count_table[] = {
+						1, 1, 1, 1, /* 01 - 04 */
+						2, 2, 2, 2, /* 05 - 08 */
+						4, 4, 4, 4, /* 09 - 12 */
+						4, 4, 4, 4, /* 13 - 16 */
+						8, 8, 8, 8, /* 17 - 20 */
+						8, 8, 8, 8, /* 21 - 24 */
+						8, 8, 8, 8, /* 25 - 28 */
+						8, 8, 8, 8, /* 29 - 32 */
+					      };
+	*slots_per_op = slot_count_table[src_cnt - 1];
+	return *slots_per_op;
+}
+
+static inline int
+iop_chan_interrupt_slot_count(int *slots_per_op, struct iop_adma_chan *chan)
+{
+	switch (chan->device->id) {
+	case DMA0_ID:
+	case DMA1_ID:
+		return iop_chan_memcpy_slot_count(0, slots_per_op);
+	case AAU_ID:
+		return iop3xx_aau_xor_slot_count(0, 2, slots_per_op);
+	default:
+		BUG();
+	}
+	return 0;
+}
+
+static inline int iop_chan_xor_slot_count(size_t len, int src_cnt,
+						int *slots_per_op)
+{
+	int slot_cnt = iop3xx_aau_xor_slot_count(len, src_cnt, slots_per_op);
+
+	if (len <= IOP_ADMA_XOR_MAX_BYTE_COUNT)
+		return slot_cnt;
+
+	len -= IOP_ADMA_XOR_MAX_BYTE_COUNT;
+	while (len > IOP_ADMA_XOR_MAX_BYTE_COUNT) {
+		len -= IOP_ADMA_XOR_MAX_BYTE_COUNT;
+		slot_cnt += *slots_per_op;
+	}
+
+	slot_cnt += *slots_per_op;
+
+	return slot_cnt;
+}
+
+/* zero sum on iop3xx is limited to 1k at a time so it requires multiple
+ * descriptors
+ */
+static inline int iop_chan_zero_sum_slot_count(size_t len, int src_cnt,
+						int *slots_per_op)
+{
+	int slot_cnt = iop3xx_aau_xor_slot_count(len, src_cnt, slots_per_op);
+
+	if (len <= IOP_ADMA_ZERO_SUM_MAX_BYTE_COUNT)
+		return slot_cnt;
+
+	len -= IOP_ADMA_ZERO_SUM_MAX_BYTE_COUNT;
+	while (len > IOP_ADMA_ZERO_SUM_MAX_BYTE_COUNT) {
+		len -= IOP_ADMA_ZERO_SUM_MAX_BYTE_COUNT;
+		slot_cnt += *slots_per_op;
+	}
+
+	slot_cnt += *slots_per_op;
+
+	return slot_cnt;
+}
+
+static inline u32 iop_desc_get_byte_count(struct iop_adma_desc_slot *desc,
+					struct iop_adma_chan *chan)
+{
+	union iop3xx_desc hw_desc = { .ptr = desc->hw_desc, };
+
+	switch (chan->device->id) {
+	case DMA0_ID:
+	case DMA1_ID:
+		return hw_desc.dma->byte_count;
+	case AAU_ID:
+		return hw_desc.aau->byte_count;
+	default:
+		BUG();
+	}
+	return 0;
+}
+
+/* translate the src_idx to a descriptor word index */
+static inline int __desc_idx(int src_idx)
+{
+	static const int desc_idx_table[] = { 0, 0, 0, 0,
+					      0, 1, 2, 3,
+					      5, 6, 7, 8,
+					      9, 10, 11, 12,
+					      14, 15, 16, 17,
+					      18, 19, 20, 21,
+					      23, 24, 25, 26,
+					      27, 28, 29, 30,
+					    };
+
+	return desc_idx_table[src_idx];
+}
+
+static inline u32 iop_desc_get_src_addr(struct iop_adma_desc_slot *desc,
+					struct iop_adma_chan *chan,
+					int src_idx)
+{
+	union iop3xx_desc hw_desc = { .ptr = desc->hw_desc, };
+
+	switch (chan->device->id) {
+	case DMA0_ID:
+	case DMA1_ID:
+		return hw_desc.dma->src_addr;
+	case AAU_ID:
+		break;
+	default:
+		BUG();
+	}
+
+	if (src_idx < 4)
+		return hw_desc.aau->src[src_idx];
+	else
+		return hw_desc.aau->src_edc[__desc_idx(src_idx)].src_addr;
+}
+
+static inline void iop3xx_aau_desc_set_src_addr(struct iop3xx_desc_aau *hw_desc,
+					int src_idx, dma_addr_t addr)
+{
+	if (src_idx < 4)
+		hw_desc->src[src_idx] = addr;
+	else
+		hw_desc->src_edc[__desc_idx(src_idx)].src_addr = addr;
+}
+
+static inline void
+iop_desc_init_memcpy(struct iop_adma_desc_slot *desc, unsigned long flags)
+{
+	struct iop3xx_desc_dma *hw_desc = desc->hw_desc;
+	union {
+		u32 value;
+		struct iop3xx_dma_desc_ctrl field;
+	} u_desc_ctrl;
+
+	u_desc_ctrl.value = 0;
+	u_desc_ctrl.field.mem_to_mem_en = 1;
+	u_desc_ctrl.field.pci_transaction = 0xe; /* memory read block */
+	u_desc_ctrl.field.int_en = flags & DMA_PREP_INTERRUPT;
+	hw_desc->desc_ctrl = u_desc_ctrl.value;
+	hw_desc->upper_pci_src_addr = 0;
+	hw_desc->crc_addr = 0;
+}
+
+static inline void
+iop_desc_init_memset(struct iop_adma_desc_slot *desc, unsigned long flags)
+{
+	struct iop3xx_desc_aau *hw_desc = desc->hw_desc;
+	union {
+		u32 value;
+		struct iop3xx_aau_desc_ctrl field;
+	} u_desc_ctrl;
+
+	u_desc_ctrl.value = 0;
+	u_desc_ctrl.field.blk1_cmd_ctrl = 0x2; /* memory block fill */
+	u_desc_ctrl.field.dest_write_en = 1;
+	u_desc_ctrl.field.int_en = flags & DMA_PREP_INTERRUPT;
+	hw_desc->desc_ctrl = u_desc_ctrl.value;
+}
+
+static inline u32
+iop3xx_desc_init_xor(struct iop3xx_desc_aau *hw_desc, int src_cnt,
+		     unsigned long flags)
+{
+	int i, shift;
+	u32 edcr;
+	union {
+		u32 value;
+		struct iop3xx_aau_desc_ctrl field;
+	} u_desc_ctrl;
+
+	u_desc_ctrl.value = 0;
+	switch (src_cnt) {
+	case 25 ... 32:
+		u_desc_ctrl.field.blk_ctrl = 0x3; /* use EDCR[2:0] */
+		edcr = 0;
+		shift = 1;
+		for (i = 24; i < src_cnt; i++) {
+			edcr |= (1 << shift);
+			shift += 3;
+		}
+		hw_desc->src_edc[AAU_EDCR2_IDX].e_desc_ctrl = edcr;
+		src_cnt = 24;
+		/* fall through */
+	case 17 ... 24:
+		if (!u_desc_ctrl.field.blk_ctrl) {
+			hw_desc->src_edc[AAU_EDCR2_IDX].e_desc_ctrl = 0;
+			u_desc_ctrl.field.blk_ctrl = 0x3; /* use EDCR[2:0] */
+		}
+		edcr = 0;
+		shift = 1;
+		for (i = 16; i < src_cnt; i++) {
+			edcr |= (1 << shift);
+			shift += 3;
+		}
+		hw_desc->src_edc[AAU_EDCR1_IDX].e_desc_ctrl = edcr;
+		src_cnt = 16;
+		/* fall through */
+	case 9 ... 16:
+		if (!u_desc_ctrl.field.blk_ctrl)
+			u_desc_ctrl.field.blk_ctrl = 0x2; /* use EDCR0 */
+		edcr = 0;
+		shift = 1;
+		for (i = 8; i < src_cnt; i++) {
+			edcr |= (1 << shift);
+			shift += 3;
+		}
+		hw_desc->src_edc[AAU_EDCR0_IDX].e_desc_ctrl = edcr;
+		src_cnt = 8;
+		/* fall through */
+	case 2 ... 8:
+		shift = 1;
+		for (i = 0; i < src_cnt; i++) {
+			u_desc_ctrl.value |= (1 << shift);
+			shift += 3;
+		}
+
+		if (!u_desc_ctrl.field.blk_ctrl && src_cnt > 4)
+			u_desc_ctrl.field.blk_ctrl = 0x1; /* use mini-desc */
+	}
+
+	u_desc_ctrl.field.dest_write_en = 1;
+	u_desc_ctrl.field.blk1_cmd_ctrl = 0x7; /* direct fill */
+	u_desc_ctrl.field.int_en = flags & DMA_PREP_INTERRUPT;
+	hw_desc->desc_ctrl = u_desc_ctrl.value;
+
+	return u_desc_ctrl.value;
+}
+
+static inline void
+iop_desc_init_xor(struct iop_adma_desc_slot *desc, int src_cnt,
+		  unsigned long flags)
+{
+	iop3xx_desc_init_xor(desc->hw_desc, src_cnt, flags);
+}
+
+/* return the number of operations */
+static inline int
+iop_desc_init_zero_sum(struct iop_adma_desc_slot *desc, int src_cnt,
+		       unsigned long flags)
+{
+	int slot_cnt = desc->slot_cnt, slots_per_op = desc->slots_per_op;
+	struct iop3xx_desc_aau *hw_desc, *prev_hw_desc, *iter;
+	union {
+		u32 value;
+		struct iop3xx_aau_desc_ctrl field;
+	} u_desc_ctrl;
+	int i, j;
+
+	hw_desc = desc->hw_desc;
+
+	for (i = 0, j = 0; (slot_cnt -= slots_per_op) >= 0;
+		i += slots_per_op, j++) {
+		iter = iop_hw_desc_slot_idx(hw_desc, i);
+		u_desc_ctrl.value = iop3xx_desc_init_xor(iter, src_cnt, flags);
+		u_desc_ctrl.field.dest_write_en = 0;
+		u_desc_ctrl.field.zero_result_en = 1;
+		u_desc_ctrl.field.int_en = flags & DMA_PREP_INTERRUPT;
+		iter->desc_ctrl = u_desc_ctrl.value;
+
+		/* for the subsequent descriptors preserve the store queue
+		 * and chain them together
+		 */
+		if (i) {
+			prev_hw_desc =
+				iop_hw_desc_slot_idx(hw_desc, i - slots_per_op);
+			prev_hw_desc->next_desc =
+				(u32) (desc->async_tx.phys + (i << 5));
+		}
+	}
+
+	return j;
+}
+
+static inline void
+iop_desc_init_null_xor(struct iop_adma_desc_slot *desc, int src_cnt,
+		       unsigned long flags)
+{
+	struct iop3xx_desc_aau *hw_desc = desc->hw_desc;
+	union {
+		u32 value;
+		struct iop3xx_aau_desc_ctrl field;
+	} u_desc_ctrl;
+
+	u_desc_ctrl.value = 0;
+	switch (src_cnt) {
+	case 25 ... 32:
+		u_desc_ctrl.field.blk_ctrl = 0x3; /* use EDCR[2:0] */
+		hw_desc->src_edc[AAU_EDCR2_IDX].e_desc_ctrl = 0;
+		/* fall through */
+	case 17 ... 24:
+		if (!u_desc_ctrl.field.blk_ctrl) {
+			hw_desc->src_edc[AAU_EDCR2_IDX].e_desc_ctrl = 0;
+			u_desc_ctrl.field.blk_ctrl = 0x3; /* use EDCR[2:0] */
+		}
+		hw_desc->src_edc[AAU_EDCR1_IDX].e_desc_ctrl = 0;
+		/* fall through */
+	case 9 ... 16:
+		if (!u_desc_ctrl.field.blk_ctrl)
+			u_desc_ctrl.field.blk_ctrl = 0x2; /* use EDCR0 */
+		hw_desc->src_edc[AAU_EDCR0_IDX].e_desc_ctrl = 0;
+		/* fall through */
+	case 1 ... 8:
+		if (!u_desc_ctrl.field.blk_ctrl && src_cnt > 4)
+			u_desc_ctrl.field.blk_ctrl = 0x1; /* use mini-desc */
+	}
+
+	u_desc_ctrl.field.dest_write_en = 0;
+	u_desc_ctrl.field.int_en = flags & DMA_PREP_INTERRUPT;
+	hw_desc->desc_ctrl = u_desc_ctrl.value;
+}
+
+static inline void iop_desc_set_byte_count(struct iop_adma_desc_slot *desc,
+					struct iop_adma_chan *chan,
+					u32 byte_count)
+{
+	union iop3xx_desc hw_desc = { .ptr = desc->hw_desc, };
+
+	switch (chan->device->id) {
+	case DMA0_ID:
+	case DMA1_ID:
+		hw_desc.dma->byte_count = byte_count;
+		break;
+	case AAU_ID:
+		hw_desc.aau->byte_count = byte_count;
+		break;
+	default:
+		BUG();
+	}
+}
+
+static inline void
+iop_desc_init_interrupt(struct iop_adma_desc_slot *desc,
+			struct iop_adma_chan *chan)
+{
+	union iop3xx_desc hw_desc = { .ptr = desc->hw_desc, };
+
+	switch (chan->device->id) {
+	case DMA0_ID:
+	case DMA1_ID:
+		iop_desc_init_memcpy(desc, 1);
+		hw_desc.dma->byte_count = 0;
+		hw_desc.dma->dest_addr = 0;
+		hw_desc.dma->src_addr = 0;
+		break;
+	case AAU_ID:
+		iop_desc_init_null_xor(desc, 2, 1);
+		hw_desc.aau->byte_count = 0;
+		hw_desc.aau->dest_addr = 0;
+		hw_desc.aau->src[0] = 0;
+		hw_desc.aau->src[1] = 0;
+		break;
+	default:
+		BUG();
+	}
+}
+
+static inline void
+iop_desc_set_zero_sum_byte_count(struct iop_adma_desc_slot *desc, u32 len)
+{
+	int slots_per_op = desc->slots_per_op;
+	struct iop3xx_desc_aau *hw_desc = desc->hw_desc, *iter;
+	int i = 0;
+
+	if (len <= IOP_ADMA_ZERO_SUM_MAX_BYTE_COUNT) {
+		hw_desc->byte_count = len;
+	} else {
+		do {
+			iter = iop_hw_desc_slot_idx(hw_desc, i);
+			iter->byte_count = IOP_ADMA_ZERO_SUM_MAX_BYTE_COUNT;
+			len -= IOP_ADMA_ZERO_SUM_MAX_BYTE_COUNT;
+			i += slots_per_op;
+		} while (len > IOP_ADMA_ZERO_SUM_MAX_BYTE_COUNT);
+
+		iter = iop_hw_desc_slot_idx(hw_desc, i);
+		iter->byte_count = len;
+	}
+}
+
+static inline void iop_desc_set_dest_addr(struct iop_adma_desc_slot *desc,
+					struct iop_adma_chan *chan,
+					dma_addr_t addr)
+{
+	union iop3xx_desc hw_desc = { .ptr = desc->hw_desc, };
+
+	switch (chan->device->id) {
+	case DMA0_ID:
+	case DMA1_ID:
+		hw_desc.dma->dest_addr = addr;
+		break;
+	case AAU_ID:
+		hw_desc.aau->dest_addr = addr;
+		break;
+	default:
+		BUG();
+	}
+}
+
+static inline void iop_desc_set_memcpy_src_addr(struct iop_adma_desc_slot *desc,
+					dma_addr_t addr)
+{
+	struct iop3xx_desc_dma *hw_desc = desc->hw_desc;
+	hw_desc->src_addr = addr;
+}
+
+static inline void
+iop_desc_set_zero_sum_src_addr(struct iop_adma_desc_slot *desc, int src_idx,
+				dma_addr_t addr)
+{
+
+	struct iop3xx_desc_aau *hw_desc = desc->hw_desc, *iter;
+	int slot_cnt = desc->slot_cnt, slots_per_op = desc->slots_per_op;
+	int i;
+
+	for (i = 0; (slot_cnt -= slots_per_op) >= 0;
+		i += slots_per_op, addr += IOP_ADMA_ZERO_SUM_MAX_BYTE_COUNT) {
+		iter = iop_hw_desc_slot_idx(hw_desc, i);
+		iop3xx_aau_desc_set_src_addr(iter, src_idx, addr);
+	}
+}
+
+static inline void iop_desc_set_xor_src_addr(struct iop_adma_desc_slot *desc,
+					int src_idx, dma_addr_t addr)
+{
+
+	struct iop3xx_desc_aau *hw_desc = desc->hw_desc, *iter;
+	int slot_cnt = desc->slot_cnt, slots_per_op = desc->slots_per_op;
+	int i;
+
+	for (i = 0; (slot_cnt -= slots_per_op) >= 0;
+		i += slots_per_op, addr += IOP_ADMA_XOR_MAX_BYTE_COUNT) {
+		iter = iop_hw_desc_slot_idx(hw_desc, i);
+		iop3xx_aau_desc_set_src_addr(iter, src_idx, addr);
+	}
+}
+
+static inline void iop_desc_set_next_desc(struct iop_adma_desc_slot *desc,
+					u32 next_desc_addr)
+{
+	/* hw_desc->next_desc is the same location for all channels */
+	union iop3xx_desc hw_desc = { .ptr = desc->hw_desc, };
+
+	iop_paranoia(hw_desc.dma->next_desc);
+	hw_desc.dma->next_desc = next_desc_addr;
+}
+
+static inline u32 iop_desc_get_next_desc(struct iop_adma_desc_slot *desc)
+{
+	/* hw_desc->next_desc is the same location for all channels */
+	union iop3xx_desc hw_desc = { .ptr = desc->hw_desc, };
+	return hw_desc.dma->next_desc;
+}
+
+static inline void iop_desc_clear_next_desc(struct iop_adma_desc_slot *desc)
+{
+	/* hw_desc->next_desc is the same location for all channels */
+	union iop3xx_desc hw_desc = { .ptr = desc->hw_desc, };
+	hw_desc.dma->next_desc = 0;
+}
+
+static inline void iop_desc_set_block_fill_val(struct iop_adma_desc_slot *desc,
+						u32 val)
+{
+	struct iop3xx_desc_aau *hw_desc = desc->hw_desc;
+	hw_desc->src[0] = val;
+}
+
+static inline enum sum_check_flags
+iop_desc_get_zero_result(struct iop_adma_desc_slot *desc)
+{
+	struct iop3xx_desc_aau *hw_desc = desc->hw_desc;
+	struct iop3xx_aau_desc_ctrl desc_ctrl = hw_desc->desc_ctrl_field;
+
+	iop_paranoia(!(desc_ctrl.tx_complete && desc_ctrl.zero_result_en));
+	return desc_ctrl.zero_result_err << SUM_CHECK_P;
+}
+
+static inline void iop_chan_append(struct iop_adma_chan *chan)
+{
+	u32 dma_chan_ctrl;
+
+	dma_chan_ctrl = __raw_readl(DMA_CCR(chan));
+	dma_chan_ctrl |= 0x2;
+	__raw_writel(dma_chan_ctrl, DMA_CCR(chan));
+}
+
+static inline u32 iop_chan_get_status(struct iop_adma_chan *chan)
+{
+	return __raw_readl(DMA_CSR(chan));
+}
+
+static inline void iop_chan_disable(struct iop_adma_chan *chan)
+{
+	u32 dma_chan_ctrl = __raw_readl(DMA_CCR(chan));
+	dma_chan_ctrl &= ~1;
+	__raw_writel(dma_chan_ctrl, DMA_CCR(chan));
+}
+
+static inline void iop_chan_enable(struct iop_adma_chan *chan)
+{
+	u32 dma_chan_ctrl = __raw_readl(DMA_CCR(chan));
+
+	dma_chan_ctrl |= 1;
+	__raw_writel(dma_chan_ctrl, DMA_CCR(chan));
+}
+
+static inline void iop_adma_device_clear_eot_status(struct iop_adma_chan *chan)
+{
+	u32 status = __raw_readl(DMA_CSR(chan));
+	status &= (1 << 9);
+	__raw_writel(status, DMA_CSR(chan));
+}
+
+static inline void iop_adma_device_clear_eoc_status(struct iop_adma_chan *chan)
+{
+	u32 status = __raw_readl(DMA_CSR(chan));
+	status &= (1 << 8);
+	__raw_writel(status, DMA_CSR(chan));
+}
+
+static inline void iop_adma_device_clear_err_status(struct iop_adma_chan *chan)
+{
+	u32 status = __raw_readl(DMA_CSR(chan));
+
+	switch (chan->device->id) {
+	case DMA0_ID:
+	case DMA1_ID:
+		status &= (1 << 5) | (1 << 3) | (1 << 2) | (1 << 1);
+		break;
+	case AAU_ID:
+		status &= (1 << 5);
+		break;
+	default:
+		BUG();
+	}
+
+	__raw_writel(status, DMA_CSR(chan));
+}
+
+static inline int
+iop_is_err_int_parity(unsigned long status, struct iop_adma_chan *chan)
+{
+	return 0;
+}
+
+static inline int
+iop_is_err_mcu_abort(unsigned long status, struct iop_adma_chan *chan)
+{
+	return 0;
+}
+
+static inline int
+iop_is_err_int_tabort(unsigned long status, struct iop_adma_chan *chan)
+{
+	return 0;
+}
+
+static inline int
+iop_is_err_int_mabort(unsigned long status, struct iop_adma_chan *chan)
+{
+	return test_bit(5, &status);
+}
+
+static inline int
+iop_is_err_pci_tabort(unsigned long status, struct iop_adma_chan *chan)
+{
+	switch (chan->device->id) {
+	case DMA0_ID:
+	case DMA1_ID:
+		return test_bit(2, &status);
+	default:
+		return 0;
+	}
+}
+
+static inline int
+iop_is_err_pci_mabort(unsigned long status, struct iop_adma_chan *chan)
+{
+	switch (chan->device->id) {
+	case DMA0_ID:
+	case DMA1_ID:
+		return test_bit(3, &status);
+	default:
+		return 0;
+	}
+}
+
+static inline int
+iop_is_err_split_tx(unsigned long status, struct iop_adma_chan *chan)
+{
+	switch (chan->device->id) {
+	case DMA0_ID:
+	case DMA1_ID:
+		return test_bit(1, &status);
+	default:
+		return 0;
+	}
+}
+#endif /* _ADMA_H */
diff --git a/arch/arm/include/asm/hardware/iop3xx.h b/arch/arm/include/asm/hardware/iop3xx.h
new file mode 100644
index 000000000..2594a95ff
--- /dev/null
+++ b/arch/arm/include/asm/hardware/iop3xx.h
@@ -0,0 +1,312 @@
+/*
+ * arch/arm/include/asm/hardware/iop3xx.h
+ *
+ * Intel IOP32X and IOP33X register definitions
+ *
+ * Author: Rory Bolt <rorybolt@pacbell.net>
+ * Copyright (C) 2002 Rory Bolt
+ * Copyright (C) 2004 Intel Corp.
+ *
+ * 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.
+ */
+
+#ifndef __IOP3XX_H
+#define __IOP3XX_H
+
+/*
+ * IOP3XX GPIO handling
+ */
+#define IOP3XX_GPIO_LINE(x)	(x)
+
+#ifndef __ASSEMBLY__
+extern int init_atu;
+extern int iop3xx_get_init_atu(void);
+#endif
+
+
+/*
+ * IOP3XX processor registers
+ */
+#define IOP3XX_PERIPHERAL_PHYS_BASE	0xffffe000
+#define IOP3XX_PERIPHERAL_VIRT_BASE	0xfedfe000
+#define IOP3XX_PERIPHERAL_SIZE		0x00002000
+#define IOP3XX_PERIPHERAL_UPPER_PA (IOP3XX_PERIPHERAL_PHYS_BASE +\
+					IOP3XX_PERIPHERAL_SIZE - 1)
+#define IOP3XX_PERIPHERAL_UPPER_VA (IOP3XX_PERIPHERAL_VIRT_BASE +\
+					IOP3XX_PERIPHERAL_SIZE - 1)
+#define IOP3XX_PMMR_PHYS_TO_VIRT(addr) (u32) ((u32) (addr) -\
+					(IOP3XX_PERIPHERAL_PHYS_BASE\
+					- IOP3XX_PERIPHERAL_VIRT_BASE))
+#define IOP3XX_REG_ADDR(reg)		(IOP3XX_PERIPHERAL_VIRT_BASE + (reg))
+
+/* Address Translation Unit  */
+#define IOP3XX_ATUVID		(volatile u16 *)IOP3XX_REG_ADDR(0x0100)
+#define IOP3XX_ATUDID		(volatile u16 *)IOP3XX_REG_ADDR(0x0102)
+#define IOP3XX_ATUCMD		(volatile u16 *)IOP3XX_REG_ADDR(0x0104)
+#define IOP3XX_ATUSR		(volatile u16 *)IOP3XX_REG_ADDR(0x0106)
+#define IOP3XX_ATURID		(volatile u8  *)IOP3XX_REG_ADDR(0x0108)
+#define IOP3XX_ATUCCR		(volatile u32 *)IOP3XX_REG_ADDR(0x0109)
+#define IOP3XX_ATUCLSR		(volatile u8  *)IOP3XX_REG_ADDR(0x010c)
+#define IOP3XX_ATULT		(volatile u8  *)IOP3XX_REG_ADDR(0x010d)
+#define IOP3XX_ATUHTR		(volatile u8  *)IOP3XX_REG_ADDR(0x010e)
+#define IOP3XX_ATUBIST		(volatile u8  *)IOP3XX_REG_ADDR(0x010f)
+#define IOP3XX_IABAR0		(volatile u32 *)IOP3XX_REG_ADDR(0x0110)
+#define IOP3XX_IAUBAR0		(volatile u32 *)IOP3XX_REG_ADDR(0x0114)
+#define IOP3XX_IABAR1		(volatile u32 *)IOP3XX_REG_ADDR(0x0118)
+#define IOP3XX_IAUBAR1		(volatile u32 *)IOP3XX_REG_ADDR(0x011c)
+#define IOP3XX_IABAR2		(volatile u32 *)IOP3XX_REG_ADDR(0x0120)
+#define IOP3XX_IAUBAR2		(volatile u32 *)IOP3XX_REG_ADDR(0x0124)
+#define IOP3XX_ASVIR		(volatile u16 *)IOP3XX_REG_ADDR(0x012c)
+#define IOP3XX_ASIR		(volatile u16 *)IOP3XX_REG_ADDR(0x012e)
+#define IOP3XX_ERBAR		(volatile u32 *)IOP3XX_REG_ADDR(0x0130)
+#define IOP3XX_ATUILR		(volatile u8  *)IOP3XX_REG_ADDR(0x013c)
+#define IOP3XX_ATUIPR		(volatile u8  *)IOP3XX_REG_ADDR(0x013d)
+#define IOP3XX_ATUMGNT		(volatile u8  *)IOP3XX_REG_ADDR(0x013e)
+#define IOP3XX_ATUMLAT		(volatile u8  *)IOP3XX_REG_ADDR(0x013f)
+#define IOP3XX_IALR0		(volatile u32 *)IOP3XX_REG_ADDR(0x0140)
+#define IOP3XX_IATVR0		(volatile u32 *)IOP3XX_REG_ADDR(0x0144)
+#define IOP3XX_ERLR		(volatile u32 *)IOP3XX_REG_ADDR(0x0148)
+#define IOP3XX_ERTVR		(volatile u32 *)IOP3XX_REG_ADDR(0x014c)
+#define IOP3XX_IALR1		(volatile u32 *)IOP3XX_REG_ADDR(0x0150)
+#define IOP3XX_IALR2		(volatile u32 *)IOP3XX_REG_ADDR(0x0154)
+#define IOP3XX_IATVR2		(volatile u32 *)IOP3XX_REG_ADDR(0x0158)
+#define IOP3XX_OIOWTVR		(volatile u32 *)IOP3XX_REG_ADDR(0x015c)
+#define IOP3XX_OMWTVR0		(volatile u32 *)IOP3XX_REG_ADDR(0x0160)
+#define IOP3XX_OUMWTVR0		(volatile u32 *)IOP3XX_REG_ADDR(0x0164)
+#define IOP3XX_OMWTVR1		(volatile u32 *)IOP3XX_REG_ADDR(0x0168)
+#define IOP3XX_OUMWTVR1		(volatile u32 *)IOP3XX_REG_ADDR(0x016c)
+#define IOP3XX_OUDWTVR		(volatile u32 *)IOP3XX_REG_ADDR(0x0178)
+#define IOP3XX_ATUCR		(volatile u32 *)IOP3XX_REG_ADDR(0x0180)
+#define IOP3XX_PCSR		(volatile u32 *)IOP3XX_REG_ADDR(0x0184)
+#define IOP3XX_ATUISR		(volatile u32 *)IOP3XX_REG_ADDR(0x0188)
+#define IOP3XX_ATUIMR		(volatile u32 *)IOP3XX_REG_ADDR(0x018c)
+#define IOP3XX_IABAR3		(volatile u32 *)IOP3XX_REG_ADDR(0x0190)
+#define IOP3XX_IAUBAR3		(volatile u32 *)IOP3XX_REG_ADDR(0x0194)
+#define IOP3XX_IALR3		(volatile u32 *)IOP3XX_REG_ADDR(0x0198)
+#define IOP3XX_IATVR3		(volatile u32 *)IOP3XX_REG_ADDR(0x019c)
+#define IOP3XX_OCCAR		(volatile u32 *)IOP3XX_REG_ADDR(0x01a4)
+#define IOP3XX_OCCDR		(volatile u32 *)IOP3XX_REG_ADDR(0x01ac)
+#define IOP3XX_PDSCR		(volatile u32 *)IOP3XX_REG_ADDR(0x01bc)
+#define IOP3XX_PMCAPID		(volatile u8  *)IOP3XX_REG_ADDR(0x01c0)
+#define IOP3XX_PMNEXT		(volatile u8  *)IOP3XX_REG_ADDR(0x01c1)
+#define IOP3XX_APMCR		(volatile u16 *)IOP3XX_REG_ADDR(0x01c2)
+#define IOP3XX_APMCSR		(volatile u16 *)IOP3XX_REG_ADDR(0x01c4)
+#define IOP3XX_PCIXCAPID	(volatile u8  *)IOP3XX_REG_ADDR(0x01e0)
+#define IOP3XX_PCIXNEXT		(volatile u8  *)IOP3XX_REG_ADDR(0x01e1)
+#define IOP3XX_PCIXCMD		(volatile u16 *)IOP3XX_REG_ADDR(0x01e2)
+#define IOP3XX_PCIXSR		(volatile u32 *)IOP3XX_REG_ADDR(0x01e4)
+#define IOP3XX_PCIIRSR		(volatile u32 *)IOP3XX_REG_ADDR(0x01ec)
+#define IOP3XX_PCSR_OUT_Q_BUSY (1 << 15)
+#define IOP3XX_PCSR_IN_Q_BUSY	(1 << 14)
+#define IOP3XX_ATUCR_OUT_EN	(1 << 1)
+
+#define IOP3XX_INIT_ATU_DEFAULT 0
+#define IOP3XX_INIT_ATU_DISABLE -1
+#define IOP3XX_INIT_ATU_ENABLE	 1
+
+/* Messaging Unit  */
+#define IOP3XX_IMR0		(volatile u32 *)IOP3XX_REG_ADDR(0x0310)
+#define IOP3XX_IMR1		(volatile u32 *)IOP3XX_REG_ADDR(0x0314)
+#define IOP3XX_OMR0		(volatile u32 *)IOP3XX_REG_ADDR(0x0318)
+#define IOP3XX_OMR1		(volatile u32 *)IOP3XX_REG_ADDR(0x031c)
+#define IOP3XX_IDR		(volatile u32 *)IOP3XX_REG_ADDR(0x0320)
+#define IOP3XX_IISR		(volatile u32 *)IOP3XX_REG_ADDR(0x0324)
+#define IOP3XX_IIMR		(volatile u32 *)IOP3XX_REG_ADDR(0x0328)
+#define IOP3XX_ODR		(volatile u32 *)IOP3XX_REG_ADDR(0x032c)
+#define IOP3XX_OISR		(volatile u32 *)IOP3XX_REG_ADDR(0x0330)
+#define IOP3XX_OIMR		(volatile u32 *)IOP3XX_REG_ADDR(0x0334)
+#define IOP3XX_MUCR		(volatile u32 *)IOP3XX_REG_ADDR(0x0350)
+#define IOP3XX_QBAR		(volatile u32 *)IOP3XX_REG_ADDR(0x0354)
+#define IOP3XX_IFHPR		(volatile u32 *)IOP3XX_REG_ADDR(0x0360)
+#define IOP3XX_IFTPR		(volatile u32 *)IOP3XX_REG_ADDR(0x0364)
+#define IOP3XX_IPHPR		(volatile u32 *)IOP3XX_REG_ADDR(0x0368)
+#define IOP3XX_IPTPR		(volatile u32 *)IOP3XX_REG_ADDR(0x036c)
+#define IOP3XX_OFHPR		(volatile u32 *)IOP3XX_REG_ADDR(0x0370)
+#define IOP3XX_OFTPR		(volatile u32 *)IOP3XX_REG_ADDR(0x0374)
+#define IOP3XX_OPHPR		(volatile u32 *)IOP3XX_REG_ADDR(0x0378)
+#define IOP3XX_OPTPR		(volatile u32 *)IOP3XX_REG_ADDR(0x037c)
+#define IOP3XX_IAR		(volatile u32 *)IOP3XX_REG_ADDR(0x0380)
+
+/* DMA Controller  */
+#define IOP3XX_DMA_PHYS_BASE(chan) (IOP3XX_PERIPHERAL_PHYS_BASE + \
+					(0x400 + (chan << 6)))
+#define IOP3XX_DMA_UPPER_PA(chan)  (IOP3XX_DMA_PHYS_BASE(chan) + 0x27)
+
+/* Peripheral bus interface  */
+#define IOP3XX_PBCR		(volatile u32 *)IOP3XX_REG_ADDR(0x0680)
+#define IOP3XX_PBISR		(volatile u32 *)IOP3XX_REG_ADDR(0x0684)
+#define IOP3XX_PBBAR0		(volatile u32 *)IOP3XX_REG_ADDR(0x0688)
+#define IOP3XX_PBLR0		(volatile u32 *)IOP3XX_REG_ADDR(0x068c)
+#define IOP3XX_PBBAR1		(volatile u32 *)IOP3XX_REG_ADDR(0x0690)
+#define IOP3XX_PBLR1		(volatile u32 *)IOP3XX_REG_ADDR(0x0694)
+#define IOP3XX_PBBAR2		(volatile u32 *)IOP3XX_REG_ADDR(0x0698)
+#define IOP3XX_PBLR2		(volatile u32 *)IOP3XX_REG_ADDR(0x069c)
+#define IOP3XX_PBBAR3		(volatile u32 *)IOP3XX_REG_ADDR(0x06a0)
+#define IOP3XX_PBLR3		(volatile u32 *)IOP3XX_REG_ADDR(0x06a4)
+#define IOP3XX_PBBAR4		(volatile u32 *)IOP3XX_REG_ADDR(0x06a8)
+#define IOP3XX_PBLR4		(volatile u32 *)IOP3XX_REG_ADDR(0x06ac)
+#define IOP3XX_PBBAR5		(volatile u32 *)IOP3XX_REG_ADDR(0x06b0)
+#define IOP3XX_PBLR5		(volatile u32 *)IOP3XX_REG_ADDR(0x06b4)
+#define IOP3XX_PMBR0		(volatile u32 *)IOP3XX_REG_ADDR(0x06c0)
+#define IOP3XX_PMBR1		(volatile u32 *)IOP3XX_REG_ADDR(0x06e0)
+#define IOP3XX_PMBR2		(volatile u32 *)IOP3XX_REG_ADDR(0x06e4)
+
+/* Peripheral performance monitoring unit  */
+#define IOP3XX_GTMR		(volatile u32 *)IOP3XX_REG_ADDR(0x0700)
+#define IOP3XX_ESR		(volatile u32 *)IOP3XX_REG_ADDR(0x0704)
+#define IOP3XX_EMISR		(volatile u32 *)IOP3XX_REG_ADDR(0x0708)
+#define IOP3XX_GTSR		(volatile u32 *)IOP3XX_REG_ADDR(0x0710)
+/* PERCR0 DOESN'T EXIST - index from 1! */
+#define IOP3XX_PERCR0		(volatile u32 *)IOP3XX_REG_ADDR(0x0710)
+
+/* Timers  */
+#define IOP3XX_TU_TMR0		(volatile u32 *)IOP3XX_TIMER_REG(0x0000)
+#define IOP3XX_TU_TMR1		(volatile u32 *)IOP3XX_TIMER_REG(0x0004)
+#define IOP3XX_TU_TCR0		(volatile u32 *)IOP3XX_TIMER_REG(0x0008)
+#define IOP3XX_TU_TCR1		(volatile u32 *)IOP3XX_TIMER_REG(0x000c)
+#define IOP3XX_TU_TRR0		(volatile u32 *)IOP3XX_TIMER_REG(0x0010)
+#define IOP3XX_TU_TRR1		(volatile u32 *)IOP3XX_TIMER_REG(0x0014)
+#define IOP3XX_TU_TISR		(volatile u32 *)IOP3XX_TIMER_REG(0x0018)
+#define IOP3XX_TU_WDTCR		(volatile u32 *)IOP3XX_TIMER_REG(0x001c)
+#define IOP_TMR_EN	    0x02
+#define IOP_TMR_RELOAD	    0x04
+#define IOP_TMR_PRIVILEGED 0x08
+#define IOP_TMR_RATIO_1_1  0x00
+
+/* Watchdog timer definitions */
+#define IOP_WDTCR_EN_ARM        0x1e1e1e1e
+#define IOP_WDTCR_EN            0xe1e1e1e1
+/* iop3xx does not support stopping the watchdog, so we just re-arm */
+#define IOP_WDTCR_DIS_ARM	(IOP_WDTCR_EN_ARM)
+#define IOP_WDTCR_DIS		(IOP_WDTCR_EN)
+
+/* Application accelerator unit  */
+#define IOP3XX_AAU_PHYS_BASE (IOP3XX_PERIPHERAL_PHYS_BASE + 0x800)
+#define IOP3XX_AAU_UPPER_PA (IOP3XX_AAU_PHYS_BASE + 0xa7)
+
+/* I2C bus interface unit  */
+#define IOP3XX_ICR0		(volatile u32 *)IOP3XX_REG_ADDR(0x1680)
+#define IOP3XX_ISR0		(volatile u32 *)IOP3XX_REG_ADDR(0x1684)
+#define IOP3XX_ISAR0		(volatile u32 *)IOP3XX_REG_ADDR(0x1688)
+#define IOP3XX_IDBR0		(volatile u32 *)IOP3XX_REG_ADDR(0x168c)
+#define IOP3XX_IBMR0		(volatile u32 *)IOP3XX_REG_ADDR(0x1694)
+#define IOP3XX_ICR1		(volatile u32 *)IOP3XX_REG_ADDR(0x16a0)
+#define IOP3XX_ISR1		(volatile u32 *)IOP3XX_REG_ADDR(0x16a4)
+#define IOP3XX_ISAR1		(volatile u32 *)IOP3XX_REG_ADDR(0x16a8)
+#define IOP3XX_IDBR1		(volatile u32 *)IOP3XX_REG_ADDR(0x16ac)
+#define IOP3XX_IBMR1		(volatile u32 *)IOP3XX_REG_ADDR(0x16b4)
+
+
+/*
+ * IOP3XX I/O and Mem space regions for PCI autoconfiguration
+ */
+#define IOP3XX_PCI_LOWER_MEM_PA	0x80000000
+#define IOP3XX_PCI_MEM_WINDOW_SIZE	0x08000000
+
+#define IOP3XX_PCI_LOWER_IO_PA		0x90000000
+#define IOP3XX_PCI_LOWER_IO_BA		0x00000000
+
+#ifndef __ASSEMBLY__
+
+#include <linux/types.h>
+#include <linux/reboot.h>
+
+void iop3xx_map_io(void);
+void iop_init_cp6_handler(void);
+void iop_init_time(unsigned long tickrate);
+void iop3xx_restart(enum reboot_mode, const char *);
+
+static inline u32 read_tmr0(void)
+{
+	u32 val;
+	asm volatile("mrc p6, 0, %0, c0, c1, 0" : "=r" (val));
+	return val;
+}
+
+static inline void write_tmr0(u32 val)
+{
+	asm volatile("mcr p6, 0, %0, c0, c1, 0" : : "r" (val));
+}
+
+static inline void write_tmr1(u32 val)
+{
+	asm volatile("mcr p6, 0, %0, c1, c1, 0" : : "r" (val));
+}
+
+static inline u32 read_tcr0(void)
+{
+	u32 val;
+	asm volatile("mrc p6, 0, %0, c2, c1, 0" : "=r" (val));
+	return val;
+}
+
+static inline void write_tcr0(u32 val)
+{
+	asm volatile("mcr p6, 0, %0, c2, c1, 0" : : "r" (val));
+}
+
+static inline u32 read_tcr1(void)
+{
+	u32 val;
+	asm volatile("mrc p6, 0, %0, c3, c1, 0" : "=r" (val));
+	return val;
+}
+
+static inline void write_tcr1(u32 val)
+{
+	asm volatile("mcr p6, 0, %0, c3, c1, 0" : : "r" (val));
+}
+
+static inline void write_trr0(u32 val)
+{
+	asm volatile("mcr p6, 0, %0, c4, c1, 0" : : "r" (val));
+}
+
+static inline void write_trr1(u32 val)
+{
+	asm volatile("mcr p6, 0, %0, c5, c1, 0" : : "r" (val));
+}
+
+static inline void write_tisr(u32 val)
+{
+	asm volatile("mcr p6, 0, %0, c6, c1, 0" : : "r" (val));
+}
+
+static inline u32 read_wdtcr(void)
+{
+	u32 val;
+	asm volatile("mrc p6, 0, %0, c7, c1, 0":"=r" (val));
+	return val;
+}
+static inline void write_wdtcr(u32 val)
+{
+	asm volatile("mcr p6, 0, %0, c7, c1, 0"::"r" (val));
+}
+
+extern unsigned long get_iop_tick_rate(void);
+
+/* only iop13xx has these registers, we define these to present a
+ * common register interface for the iop_wdt driver.
+ */
+#define IOP_RCSR_WDT	(0)
+static inline u32 read_rcsr(void)
+{
+	return 0;
+}
+static inline void write_wdtsr(u32 val)
+{
+	do { } while (0);
+}
+
+extern struct platform_device iop3xx_dma_0_channel;
+extern struct platform_device iop3xx_dma_1_channel;
+extern struct platform_device iop3xx_aau_channel;
+extern struct platform_device iop3xx_i2c0_device;
+extern struct platform_device iop3xx_i2c1_device;
+
+#endif
+
+
+#endif
diff --git a/arch/arm/include/asm/hardware/iop_adma.h b/arch/arm/include/asm/hardware/iop_adma.h
new file mode 100644
index 000000000..250760e08
--- /dev/null
+++ b/arch/arm/include/asm/hardware/iop_adma.h
@@ -0,0 +1,119 @@
+/*
+ * Copyright © 2006, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope 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, write to the Free Software Foundation, Inc.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ */
+#ifndef IOP_ADMA_H
+#define IOP_ADMA_H
+#include <linux/types.h>
+#include <linux/dmaengine.h>
+#include <linux/interrupt.h>
+
+#define IOP_ADMA_SLOT_SIZE 32
+#define IOP_ADMA_THRESHOLD 4
+#ifdef DEBUG
+#define IOP_PARANOIA 1
+#else
+#define IOP_PARANOIA 0
+#endif
+#define iop_paranoia(x) BUG_ON(IOP_PARANOIA && (x))
+
+/**
+ * struct iop_adma_device - internal representation of an ADMA device
+ * @pdev: Platform device
+ * @id: HW ADMA Device selector
+ * @dma_desc_pool: base of DMA descriptor region (DMA address)
+ * @dma_desc_pool_virt: base of DMA descriptor region (CPU address)
+ * @common: embedded struct dma_device
+ */
+struct iop_adma_device {
+	struct platform_device *pdev;
+	int id;
+	dma_addr_t dma_desc_pool;
+	void *dma_desc_pool_virt;
+	struct dma_device common;
+};
+
+/**
+ * struct iop_adma_chan - internal representation of an ADMA device
+ * @pending: allows batching of hardware operations
+ * @lock: serializes enqueue/dequeue operations to the slot pool
+ * @mmr_base: memory mapped register base
+ * @chain: device chain view of the descriptors
+ * @device: parent device
+ * @common: common dmaengine channel object members
+ * @last_used: place holder for allocation to continue from where it left off
+ * @all_slots: complete domain of slots usable by the channel
+ * @slots_allocated: records the actual size of the descriptor slot pool
+ * @irq_tasklet: bottom half where iop_adma_slot_cleanup runs
+ */
+struct iop_adma_chan {
+	int pending;
+	spinlock_t lock; /* protects the descriptor slot pool */
+	void __iomem *mmr_base;
+	struct list_head chain;
+	struct iop_adma_device *device;
+	struct dma_chan common;
+	struct iop_adma_desc_slot *last_used;
+	struct list_head all_slots;
+	int slots_allocated;
+	struct tasklet_struct irq_tasklet;
+};
+
+/**
+ * struct iop_adma_desc_slot - IOP-ADMA software descriptor
+ * @slot_node: node on the iop_adma_chan.all_slots list
+ * @chain_node: node on the op_adma_chan.chain list
+ * @hw_desc: virtual address of the hardware descriptor chain
+ * @phys: hardware address of the hardware descriptor chain
+ * @group_head: first operation in a transaction
+ * @slot_cnt: total slots used in an transaction (group of operations)
+ * @slots_per_op: number of slots per operation
+ * @idx: pool index
+ * @tx_list: list of descriptors that are associated with one operation
+ * @async_tx: support for the async_tx api
+ * @group_list: list of slots that make up a multi-descriptor transaction
+ *	for example transfer lengths larger than the supported hw max
+ * @xor_check_result: result of zero sum
+ * @crc32_result: result crc calculation
+ */
+struct iop_adma_desc_slot {
+	struct list_head slot_node;
+	struct list_head chain_node;
+	void *hw_desc;
+	struct iop_adma_desc_slot *group_head;
+	u16 slot_cnt;
+	u16 slots_per_op;
+	u16 idx;
+	struct list_head tx_list;
+	struct dma_async_tx_descriptor async_tx;
+	union {
+		u32 *xor_check_result;
+		u32 *crc32_result;
+		u32 *pq_check_result;
+	};
+};
+
+struct iop_adma_platform_data {
+	int hw_id;
+	dma_cap_mask_t cap_mask;
+	size_t pool_size;
+};
+
+#define to_iop_sw_desc(addr_hw_desc) \
+	container_of(addr_hw_desc, struct iop_adma_desc_slot, hw_desc)
+#define iop_hw_desc_slot_idx(hw_desc, idx) \
+	( (void *) (((unsigned long) hw_desc) + ((idx) << 5)) )
+#endif
diff --git a/arch/arm/include/asm/hardware/it8152.h b/arch/arm/include/asm/hardware/it8152.h
new file mode 100644
index 000000000..d36a73d7c
--- /dev/null
+++ b/arch/arm/include/asm/hardware/it8152.h
@@ -0,0 +1,115 @@
+/*
+ * linux/include/arm/hardware/it8152.h
+ *
+ * Copyright Compulab Ltd., 2006,2007
+ * Mike Rapoport <mike@compulab.co.il>
+ *
+ * ITE 8152 companion chip register definitions
+ */
+
+#ifndef __ASM_HARDWARE_IT8152_H
+#define __ASM_HARDWARE_IT8152_H
+
+#include <mach/irqs.h>
+
+extern void __iomem *it8152_base_address;
+
+#define IT8152_IO_BASE			(it8152_base_address + 0x03e00000)
+#define IT8152_CFGREG_BASE		(it8152_base_address + 0x03f00000)
+
+#define __REG_IT8152(x)			(it8152_base_address + (x))
+
+#define IT8152_PCI_CFG_ADDR		__REG_IT8152(0x3f00800)
+#define IT8152_PCI_CFG_DATA		__REG_IT8152(0x3f00804)
+
+#define IT8152_INTC_LDCNIRR		__REG_IT8152(0x3f00300)
+#define IT8152_INTC_LDPNIRR		__REG_IT8152(0x3f00304)
+#define IT8152_INTC_LDCNIMR		__REG_IT8152(0x3f00308)
+#define IT8152_INTC_LDPNIMR		__REG_IT8152(0x3f0030C)
+#define IT8152_INTC_LDNITR		__REG_IT8152(0x3f00310)
+#define IT8152_INTC_LDNIAR		__REG_IT8152(0x3f00314)
+#define IT8152_INTC_LPCNIRR		__REG_IT8152(0x3f00320)
+#define IT8152_INTC_LPPNIRR		__REG_IT8152(0x3f00324)
+#define IT8152_INTC_LPCNIMR		__REG_IT8152(0x3f00328)
+#define IT8152_INTC_LPPNIMR		__REG_IT8152(0x3f0032C)
+#define IT8152_INTC_LPNITR		__REG_IT8152(0x3f00330)
+#define IT8152_INTC_LPNIAR		__REG_IT8152(0x3f00334)
+#define IT8152_INTC_PDCNIRR		__REG_IT8152(0x3f00340)
+#define IT8152_INTC_PDPNIRR		__REG_IT8152(0x3f00344)
+#define IT8152_INTC_PDCNIMR		__REG_IT8152(0x3f00348)
+#define IT8152_INTC_PDPNIMR		__REG_IT8152(0x3f0034C)
+#define IT8152_INTC_PDNITR		__REG_IT8152(0x3f00350)
+#define IT8152_INTC_PDNIAR		__REG_IT8152(0x3f00354)
+#define IT8152_INTC_INTC_TYPER		__REG_IT8152(0x3f003FC)
+
+#define IT8152_GPIO_GPDR		__REG_IT8152(0x3f00500)
+
+/*
+  Interrupt controller per register summary:
+  ---------------------------------------
+  LCDNIRR:
+  IT8152_LD_IRQ(8) PCICLK stop
+  IT8152_LD_IRQ(7) MCLK ready
+  IT8152_LD_IRQ(6) s/w
+  IT8152_LD_IRQ(5) UART
+  IT8152_LD_IRQ(4) GPIO
+  IT8152_LD_IRQ(3) TIMER 4
+  IT8152_LD_IRQ(2) TIMER 3
+  IT8152_LD_IRQ(1) TIMER 2
+  IT8152_LD_IRQ(0) TIMER 1
+
+  LPCNIRR:
+  IT8152_LP_IRQ(x) serial IRQ x
+
+  PCIDNIRR:
+  IT8152_PD_IRQ(14) PCISERR
+  IT8152_PD_IRQ(13) CPU/PCI bridge target abort (h2pTADR)
+  IT8152_PD_IRQ(12) CPU/PCI bridge master abort (h2pMADR)
+  IT8152_PD_IRQ(11) PCI INTD
+  IT8152_PD_IRQ(10) PCI INTC
+  IT8152_PD_IRQ(9)  PCI INTB
+  IT8152_PD_IRQ(8)  PCI INTA
+  IT8152_PD_IRQ(7)  serial INTD
+  IT8152_PD_IRQ(6)  serial INTC
+  IT8152_PD_IRQ(5)  serial INTB
+  IT8152_PD_IRQ(4)  serial INTA
+  IT8152_PD_IRQ(3)  serial IRQ IOCHK (IOCHKR)
+  IT8152_PD_IRQ(2)  chaining DMA (CDMAR)
+  IT8152_PD_IRQ(1)  USB (USBR)
+  IT8152_PD_IRQ(0)  Audio controller (ACR)
+ */
+#define IT8152_IRQ(x)   (IRQ_BOARD_START + (x))
+#define IT8152_LAST_IRQ	(IRQ_BOARD_START + 40)
+
+/* IRQ-sources in 3 groups - local devices, LPC (serial), and external PCI */
+#define IT8152_LD_IRQ_COUNT     9
+#define IT8152_LP_IRQ_COUNT     16
+#define IT8152_PD_IRQ_COUNT     15
+
+/* Priorities: */
+#define IT8152_PD_IRQ(i)        IT8152_IRQ(i)
+#define IT8152_LP_IRQ(i)        (IT8152_IRQ(i) + IT8152_PD_IRQ_COUNT)
+#define IT8152_LD_IRQ(i)        (IT8152_IRQ(i) + IT8152_PD_IRQ_COUNT + IT8152_LP_IRQ_COUNT)
+
+/* frequently used interrupts */
+#define IT8152_PCISERR		IT8152_PD_IRQ(14)
+#define IT8152_H2PTADR		IT8152_PD_IRQ(13)
+#define IT8152_H2PMAR		IT8152_PD_IRQ(12)
+#define IT8152_PCI_INTD		IT8152_PD_IRQ(11)
+#define IT8152_PCI_INTC		IT8152_PD_IRQ(10)
+#define IT8152_PCI_INTB		IT8152_PD_IRQ(9)
+#define IT8152_PCI_INTA		IT8152_PD_IRQ(8)
+#define IT8152_CDMA_INT		IT8152_PD_IRQ(2)
+#define IT8152_USB_INT		IT8152_PD_IRQ(1)
+#define IT8152_AUDIO_INT	IT8152_PD_IRQ(0)
+
+struct pci_dev;
+struct pci_sys_data;
+
+extern void it8152_irq_demux(unsigned int irq, struct irq_desc *desc);
+extern void it8152_init_irq(void);
+extern int it8152_pci_map_irq(const struct pci_dev *dev, u8 slot, u8 pin);
+extern int it8152_pci_setup(int nr, struct pci_sys_data *sys);
+extern struct pci_ops it8152_ops;
+
+#endif /* __ASM_HARDWARE_IT8152_H */
diff --git a/arch/arm/include/asm/hardware/locomo.h b/arch/arm/include/asm/hardware/locomo.h
new file mode 100644
index 000000000..74e51d6bd
--- /dev/null
+++ b/arch/arm/include/asm/hardware/locomo.h
@@ -0,0 +1,221 @@
+/*
+ * arch/arm/include/asm/hardware/locomo.h
+ *
+ * This file contains the definitions for the LoCoMo G/A Chip
+ *
+ * (C) Copyright 2004 John Lenz
+ *
+ * May be copied or modified under the terms of the GNU General Public
+ * License.  See linux/COPYING for more information.
+ *
+ * Based on sa1111.h
+ */
+#ifndef _ASM_ARCH_LOCOMO
+#define _ASM_ARCH_LOCOMO
+
+#define locomo_writel(val,addr)	({ *(volatile u16 *)(addr) = (val); })
+#define locomo_readl(addr)	(*(volatile u16 *)(addr))
+
+/* LOCOMO version */
+#define LOCOMO_VER	0x00
+
+/* Pin status */
+#define LOCOMO_ST	0x04
+
+/* Pin status */
+#define LOCOMO_C32K	0x08
+
+/* Interrupt controller */
+#define LOCOMO_ICR	0x0C
+
+/* MCS decoder for boot selecting */
+#define LOCOMO_MCSX0	0x10
+#define LOCOMO_MCSX1	0x14
+#define LOCOMO_MCSX2	0x18
+#define LOCOMO_MCSX3	0x1c
+
+/* Touch panel controller */
+#define LOCOMO_ASD	0x20		/* AD start delay */
+#define LOCOMO_HSD	0x28		/* HSYS delay */
+#define LOCOMO_HSC	0x2c		/* HSYS period */
+#define LOCOMO_TADC	0x30		/* tablet ADC clock */
+
+
+/* Long time timer */
+#define LOCOMO_LTC	0xd8		/* LTC interrupt setting */
+#define LOCOMO_LTINT	0xdc		/* LTC interrupt */
+
+/* DAC control signal for LCD (COMADJ ) */
+#define LOCOMO_DAC		0xe0
+/* DAC control */
+#define	LOCOMO_DAC_SCLOEB	0x08	/* SCL pin output data       */
+#define	LOCOMO_DAC_TEST		0x04	/* Test bit                  */
+#define	LOCOMO_DAC_SDA		0x02	/* SDA pin level (read-only) */
+#define	LOCOMO_DAC_SDAOEB	0x01	/* SDA pin output data       */
+
+/* SPI interface */
+#define LOCOMO_SPI	0x60
+#define LOCOMO_SPIMD	0x00		/* SPI mode setting */
+#define LOCOMO_SPICT	0x04		/* SPI mode control */
+#define LOCOMO_SPIST	0x08		/* SPI status */
+#define	LOCOMO_SPI_TEND	(1 << 3)	/* Transfer end bit */
+#define	LOCOMO_SPI_REND	(1 << 2)	/* Receive end bit */
+#define	LOCOMO_SPI_RFW	(1 << 1)	/* write buffer bit */
+#define	LOCOMO_SPI_RFR	(1)		/* read buffer bit */
+
+#define LOCOMO_SPIIS	0x10		/* SPI interrupt status */
+#define LOCOMO_SPIWE	0x14		/* SPI interrupt status write enable */
+#define LOCOMO_SPIIE	0x18		/* SPI interrupt enable */
+#define LOCOMO_SPIIR	0x1c		/* SPI interrupt request */
+#define LOCOMO_SPITD	0x20		/* SPI transfer data write */
+#define LOCOMO_SPIRD	0x24		/* SPI receive data read */
+#define LOCOMO_SPITS	0x28		/* SPI transfer data shift */
+#define LOCOMO_SPIRS	0x2C		/* SPI receive data shift */
+
+/* GPIO */
+#define LOCOMO_GPD		0x90	/* GPIO direction */
+#define LOCOMO_GPE		0x94	/* GPIO input enable */
+#define LOCOMO_GPL		0x98	/* GPIO level */
+#define LOCOMO_GPO		0x9c	/* GPIO out data setting */
+#define LOCOMO_GRIE		0xa0	/* GPIO rise detection */
+#define LOCOMO_GFIE		0xa4	/* GPIO fall detection */
+#define LOCOMO_GIS		0xa8	/* GPIO edge detection status */
+#define LOCOMO_GWE		0xac	/* GPIO status write enable */
+#define LOCOMO_GIE		0xb0	/* GPIO interrupt enable */
+#define LOCOMO_GIR		0xb4	/* GPIO interrupt request */
+#define	LOCOMO_GPIO(Nb)		(0x01 << (Nb))
+#define LOCOMO_GPIO_RTS		LOCOMO_GPIO(0)
+#define LOCOMO_GPIO_CTS		LOCOMO_GPIO(1)
+#define LOCOMO_GPIO_DSR		LOCOMO_GPIO(2)
+#define LOCOMO_GPIO_DTR		LOCOMO_GPIO(3)
+#define LOCOMO_GPIO_LCD_VSHA_ON	LOCOMO_GPIO(4)
+#define LOCOMO_GPIO_LCD_VSHD_ON	LOCOMO_GPIO(5)
+#define LOCOMO_GPIO_LCD_VEE_ON	LOCOMO_GPIO(6)
+#define LOCOMO_GPIO_LCD_MOD	LOCOMO_GPIO(7)
+#define LOCOMO_GPIO_DAC_ON	LOCOMO_GPIO(8)
+#define LOCOMO_GPIO_FL_VR	LOCOMO_GPIO(9)
+#define LOCOMO_GPIO_DAC_SDATA	LOCOMO_GPIO(10)
+#define LOCOMO_GPIO_DAC_SCK	LOCOMO_GPIO(11)
+#define LOCOMO_GPIO_DAC_SLOAD	LOCOMO_GPIO(12)
+#define LOCOMO_GPIO_CARD_DETECT LOCOMO_GPIO(13)
+#define LOCOMO_GPIO_WRITE_PROT  LOCOMO_GPIO(14)
+#define LOCOMO_GPIO_CARD_POWER  LOCOMO_GPIO(15)
+
+/* Start the definitions of the devices.  Each device has an initial
+ * base address and a series of offsets from that base address. */
+
+/* Keyboard controller */
+#define LOCOMO_KEYBOARD		0x40
+#define LOCOMO_KIB		0x00	/* KIB level */
+#define LOCOMO_KSC		0x04	/* KSTRB control */
+#define LOCOMO_KCMD		0x08	/* KSTRB command */
+#define LOCOMO_KIC		0x0c	/* Key interrupt */
+
+/* Front light adjustment controller */
+#define LOCOMO_FRONTLIGHT	0xc8
+#define LOCOMO_ALS		0x00	/* Adjust light cycle */
+#define LOCOMO_ALD		0x04	/* Adjust light duty */
+
+#define LOCOMO_ALC_EN		0x8000
+
+/* Backlight controller: TFT signal */
+#define LOCOMO_BACKLIGHT	0x38
+#define LOCOMO_TC		0x00		/* TFT control signal */
+#define LOCOMO_CPSD		0x04		/* CPS delay */
+
+/* Audio controller */
+#define LOCOMO_AUDIO		0x54
+#define LOCOMO_ACC		0x00	/* Audio clock */
+#define LOCOMO_PAIF		0xD0	/* PCM audio interface */
+/* Audio clock */
+#define	LOCOMO_ACC_XON		0x80
+#define	LOCOMO_ACC_XEN		0x40
+#define	LOCOMO_ACC_XSEL0	0x00
+#define	LOCOMO_ACC_XSEL1	0x20
+#define	LOCOMO_ACC_MCLKEN	0x10
+#define	LOCOMO_ACC_64FSEN	0x08
+#define	LOCOMO_ACC_CLKSEL000	0x00	/* mclk  2 */
+#define	LOCOMO_ACC_CLKSEL001	0x01	/* mclk  3 */
+#define	LOCOMO_ACC_CLKSEL010	0x02	/* mclk  4 */
+#define	LOCOMO_ACC_CLKSEL011	0x03	/* mclk  6 */
+#define	LOCOMO_ACC_CLKSEL100	0x04	/* mclk  8 */
+#define	LOCOMO_ACC_CLKSEL101	0x05	/* mclk 12 */
+/* PCM audio interface */
+#define	LOCOMO_PAIF_SCINV	0x20
+#define	LOCOMO_PAIF_SCEN	0x10
+#define	LOCOMO_PAIF_LRCRST	0x08
+#define	LOCOMO_PAIF_LRCEVE	0x04
+#define	LOCOMO_PAIF_LRCINV	0x02
+#define	LOCOMO_PAIF_LRCEN	0x01
+
+/* LED controller */
+#define LOCOMO_LED		0xe8
+#define LOCOMO_LPT0		0x00
+#define LOCOMO_LPT1		0x04
+/* LED control */
+#define LOCOMO_LPT_TOFH		0x80
+#define LOCOMO_LPT_TOFL		0x08
+#define LOCOMO_LPT_TOH(TOH)	((TOH & 0x7) << 4)
+#define LOCOMO_LPT_TOL(TOL)	((TOL & 0x7))
+
+extern struct bus_type locomo_bus_type;
+
+#define LOCOMO_DEVID_KEYBOARD	0
+#define LOCOMO_DEVID_FRONTLIGHT	1
+#define LOCOMO_DEVID_BACKLIGHT	2
+#define LOCOMO_DEVID_AUDIO	3
+#define LOCOMO_DEVID_LED	4
+#define LOCOMO_DEVID_UART	5
+#define LOCOMO_DEVID_SPI	6
+
+struct locomo_dev {
+	struct device	dev;
+	unsigned int	devid;
+	unsigned int	irq[1];
+
+	void		*mapbase;
+	unsigned long	length;
+
+	u64		dma_mask;
+};
+
+#define LOCOMO_DEV(_d)	container_of((_d), struct locomo_dev, dev)
+
+#define locomo_get_drvdata(d)	dev_get_drvdata(&(d)->dev)
+#define locomo_set_drvdata(d,p)	dev_set_drvdata(&(d)->dev, p)
+
+struct locomo_driver {
+	struct device_driver	drv;
+	unsigned int		devid;
+	int (*probe)(struct locomo_dev *);
+	int (*remove)(struct locomo_dev *);
+	int (*suspend)(struct locomo_dev *, pm_message_t);
+	int (*resume)(struct locomo_dev *);
+};
+
+#define LOCOMO_DRV(_d)	container_of((_d), struct locomo_driver, drv)
+
+#define LOCOMO_DRIVER_NAME(_ldev) ((_ldev)->dev.driver->name)
+
+void locomo_lcd_power(struct locomo_dev *, int, unsigned int);
+
+int locomo_driver_register(struct locomo_driver *);
+void locomo_driver_unregister(struct locomo_driver *);
+
+/* GPIO control functions */
+void locomo_gpio_set_dir(struct device *dev, unsigned int bits, unsigned int dir);
+int locomo_gpio_read_level(struct device *dev, unsigned int bits);
+int locomo_gpio_read_output(struct device *dev, unsigned int bits);
+void locomo_gpio_write(struct device *dev, unsigned int bits, unsigned int set);
+
+/* M62332 control function */
+void locomo_m62332_senddata(struct locomo_dev *ldev, unsigned int dac_data, int channel);
+
+/* Frontlight control */
+void locomo_frontlight_set(struct locomo_dev *dev, int duty, int vr, int bpwf);
+
+struct locomo_platform_data {
+	int	irq_base;	/* IRQ base for cascaded on-chip IRQs */
+};
+
+#endif
diff --git a/arch/arm/include/asm/hardware/memc.h b/arch/arm/include/asm/hardware/memc.h
new file mode 100644
index 000000000..42ba7c167
--- /dev/null
+++ b/arch/arm/include/asm/hardware/memc.h
@@ -0,0 +1,26 @@
+/*
+ *  arch/arm/include/asm/hardware/memc.h
+ *
+ *  Copyright (C) Russell King.
+ *
+ * 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.
+ */
+#define VDMA_ALIGNMENT	PAGE_SIZE
+#define VDMA_XFERSIZE	16
+#define VDMA_INIT	0
+#define VDMA_START	1
+#define VDMA_END	2
+
+#ifndef __ASSEMBLY__
+extern void memc_write(unsigned int reg, unsigned long val);
+
+#define video_set_dma(start,end,offset)				\
+do {								\
+	memc_write (VDMA_START, (start >> 2));			\
+	memc_write (VDMA_END, (end - VDMA_XFERSIZE) >> 2);	\
+	memc_write (VDMA_INIT, (offset >> 2));			\
+} while (0)
+
+#endif
diff --git a/arch/arm/include/asm/hardware/sa1111.h b/arch/arm/include/asm/hardware/sa1111.h
new file mode 100644
index 000000000..7c2bbc7f0
--- /dev/null
+++ b/arch/arm/include/asm/hardware/sa1111.h
@@ -0,0 +1,475 @@
+/*
+ * arch/arm/include/asm/hardware/sa1111.h
+ *
+ * Copyright (C) 2000 John G Dorsey <john+@cs.cmu.edu>
+ *
+ * This file contains definitions for the SA-1111 Companion Chip.
+ * (Structure and naming borrowed from SA-1101.h, by Peter Danielsson.)
+ *
+ * Macro that calculates real address for registers in the SA-1111
+ */
+
+#ifndef _ASM_ARCH_SA1111
+#define _ASM_ARCH_SA1111
+
+#include <mach/bitfield.h>
+
+/*
+ * The SA1111 is always located at virtual 0xf4000000, and is always
+ * "native" endian.
+ */
+
+#define SA1111_VBASE		0xf4000000
+
+/* Don't use these! */
+#define SA1111_p2v( x )         ((x) - SA1111_BASE + SA1111_VBASE)
+#define SA1111_v2p( x )         ((x) - SA1111_VBASE + SA1111_BASE)
+
+#ifndef __ASSEMBLY__
+#define _SA1111(x)	((x) + sa1111->resource.start)
+#endif
+
+#define sa1111_writel(val,addr)	__raw_writel(val, addr)
+#define sa1111_readl(addr)	__raw_readl(addr)
+
+/*
+ * 26 bits of the SA-1110 address bus are available to the SA-1111.
+ * Use these when feeding target addresses to the DMA engines.
+ */
+
+#define SA1111_ADDR_WIDTH	(26)
+#define SA1111_ADDR_MASK	((1<<SA1111_ADDR_WIDTH)-1)
+#define SA1111_DMA_ADDR(x)	((x)&SA1111_ADDR_MASK)
+
+/*
+ * Don't ask the (SAC) DMA engines to move less than this amount.
+ */
+
+#define SA1111_SAC_DMA_MIN_XFER	(0x800)
+
+/*
+ * System Bus Interface (SBI)
+ *
+ * Registers
+ *    SKCR	Control Register
+ *    SMCR	Shared Memory Controller Register
+ *    SKID	ID Register
+ */
+#define SA1111_SKCR	0x0000
+#define SA1111_SMCR	0x0004
+#define SA1111_SKID	0x0008
+
+#define SKCR_PLL_BYPASS	(1<<0)
+#define SKCR_RCLKEN	(1<<1)
+#define SKCR_SLEEP	(1<<2)
+#define SKCR_DOZE	(1<<3)
+#define SKCR_VCO_OFF	(1<<4)
+#define SKCR_SCANTSTEN	(1<<5)
+#define SKCR_CLKTSTEN	(1<<6)
+#define SKCR_RDYEN	(1<<7)
+#define SKCR_SELAC	(1<<8)
+#define SKCR_OPPC	(1<<9)
+#define SKCR_PLLTSTEN	(1<<10)
+#define SKCR_USBIOTSTEN	(1<<11)
+/*
+ * Don't believe the specs!  Take them, throw them outside.  Leave them
+ * there for a week.  Spit on them.  Walk on them.  Stamp on them.
+ * Pour gasoline over them and finally burn them.  Now think about coding.
+ *  - The October 1999 errata (278260-007) says its bit 13, 1 to enable.
+ *  - The Feb 2001 errata (278260-010) says that the previous errata
+ *    (278260-009) is wrong, and its bit actually 12, fixed in spec
+ *    278242-003.
+ *  - The SA1111 manual (278242) says bit 12, but 0 to enable.
+ *  - Reality is bit 13, 1 to enable.
+ *      -- rmk
+ */
+#define SKCR_OE_EN	(1<<13)
+
+#define SMCR_DTIM	(1<<0)
+#define SMCR_MBGE	(1<<1)
+#define SMCR_DRAC_0	(1<<2)
+#define SMCR_DRAC_1	(1<<3)
+#define SMCR_DRAC_2	(1<<4)
+#define SMCR_DRAC	Fld(3, 2)
+#define SMCR_CLAT	(1<<5)
+
+#define SKID_SIREV_MASK	(0x000000f0)
+#define SKID_MTREV_MASK (0x0000000f)
+#define SKID_ID_MASK	(0xffffff00)
+#define SKID_SA1111_ID	(0x690cc200)
+
+/*
+ * System Controller
+ *
+ * Registers
+ *    SKPCR	Power Control Register
+ *    SKCDR	Clock Divider Register
+ *    SKAUD	Audio Clock Divider Register
+ *    SKPMC	PS/2 Mouse Clock Divider Register
+ *    SKPTC	PS/2 Track Pad Clock Divider Register
+ *    SKPEN0	PWM0 Enable Register
+ *    SKPWM0	PWM0 Clock Register
+ *    SKPEN1	PWM1 Enable Register
+ *    SKPWM1	PWM1 Clock Register
+ */
+#define SA1111_SKPCR	0x0200
+#define SA1111_SKCDR	0x0204
+#define SA1111_SKAUD	0x0208
+#define SA1111_SKPMC	0x020c
+#define SA1111_SKPTC	0x0210
+#define SA1111_SKPEN0	0x0214
+#define SA1111_SKPWM0	0x0218
+#define SA1111_SKPEN1	0x021c
+#define SA1111_SKPWM1	0x0220
+
+#define SKPCR_UCLKEN	(1<<0)
+#define SKPCR_ACCLKEN	(1<<1)
+#define SKPCR_I2SCLKEN	(1<<2)
+#define SKPCR_L3CLKEN	(1<<3)
+#define SKPCR_SCLKEN	(1<<4)
+#define SKPCR_PMCLKEN	(1<<5)
+#define SKPCR_PTCLKEN	(1<<6)
+#define SKPCR_DCLKEN	(1<<7)
+#define SKPCR_PWMCLKEN	(1<<8)
+
+/* USB Host controller */
+#define SA1111_USB		0x0400
+
+/*
+ * Serial Audio Controller
+ *
+ * Registers
+ *    SACR0             Serial Audio Common Control Register
+ *    SACR1             Serial Audio Alternate Mode (I2C/MSB) Control Register
+ *    SACR2             Serial Audio AC-link Control Register
+ *    SASR0             Serial Audio I2S/MSB Interface & FIFO Status Register
+ *    SASR1             Serial Audio AC-link Interface & FIFO Status Register
+ *    SASCR             Serial Audio Status Clear Register
+ *    L3_CAR            L3 Control Bus Address Register
+ *    L3_CDR            L3 Control Bus Data Register
+ *    ACCAR             AC-link Command Address Register
+ *    ACCDR             AC-link Command Data Register
+ *    ACSAR             AC-link Status Address Register
+ *    ACSDR             AC-link Status Data Register
+ *    SADTCS            Serial Audio DMA Transmit Control/Status Register
+ *    SADTSA            Serial Audio DMA Transmit Buffer Start Address A
+ *    SADTCA            Serial Audio DMA Transmit Buffer Count Register A
+ *    SADTSB            Serial Audio DMA Transmit Buffer Start Address B
+ *    SADTCB            Serial Audio DMA Transmit Buffer Count Register B
+ *    SADRCS            Serial Audio DMA Receive Control/Status Register
+ *    SADRSA            Serial Audio DMA Receive Buffer Start Address A
+ *    SADRCA            Serial Audio DMA Receive Buffer Count Register A
+ *    SADRSB            Serial Audio DMA Receive Buffer Start Address B
+ *    SADRCB            Serial Audio DMA Receive Buffer Count Register B
+ *    SAITR             Serial Audio Interrupt Test Register
+ *    SADR              Serial Audio Data Register (16 x 32-bit)
+ */
+
+#define SA1111_SERAUDIO		0x0600
+
+/*
+ * These are offsets from the above base.
+ */
+#define SA1111_SACR0		0x00
+#define SA1111_SACR1		0x04
+#define SA1111_SACR2		0x08
+#define SA1111_SASR0		0x0c
+#define SA1111_SASR1		0x10
+#define SA1111_SASCR		0x18
+#define SA1111_L3_CAR		0x1c
+#define SA1111_L3_CDR		0x20
+#define SA1111_ACCAR		0x24
+#define SA1111_ACCDR		0x28
+#define SA1111_ACSAR		0x2c
+#define SA1111_ACSDR		0x30
+#define SA1111_SADTCS		0x34
+#define SA1111_SADTSA		0x38
+#define SA1111_SADTCA		0x3c
+#define SA1111_SADTSB		0x40
+#define SA1111_SADTCB		0x44
+#define SA1111_SADRCS		0x48
+#define SA1111_SADRSA		0x4c
+#define SA1111_SADRCA		0x50
+#define SA1111_SADRSB		0x54
+#define SA1111_SADRCB		0x58
+#define SA1111_SAITR		0x5c
+#define SA1111_SADR		0x80
+
+#ifndef CONFIG_ARCH_PXA
+
+#define SACR0_ENB	(1<<0)
+#define SACR0_BCKD	(1<<2)
+#define SACR0_RST	(1<<3)
+
+#define SACR1_AMSL	(1<<0)
+#define SACR1_L3EN	(1<<1)
+#define SACR1_L3MB	(1<<2)
+#define SACR1_DREC	(1<<3)
+#define SACR1_DRPL	(1<<4)
+#define SACR1_ENLBF	(1<<5)
+
+#define SACR2_TS3V	(1<<0)
+#define SACR2_TS4V	(1<<1)
+#define SACR2_WKUP	(1<<2)
+#define SACR2_DREC	(1<<3)
+#define SACR2_DRPL	(1<<4)
+#define SACR2_ENLBF	(1<<5)
+#define SACR2_RESET	(1<<6)
+
+#define SASR0_TNF	(1<<0)
+#define SASR0_RNE	(1<<1)
+#define SASR0_BSY	(1<<2)
+#define SASR0_TFS	(1<<3)
+#define SASR0_RFS	(1<<4)
+#define SASR0_TUR	(1<<5)
+#define SASR0_ROR	(1<<6)
+#define SASR0_L3WD	(1<<16)
+#define SASR0_L3RD	(1<<17)
+
+#define SASR1_TNF	(1<<0)
+#define SASR1_RNE	(1<<1)
+#define SASR1_BSY	(1<<2)
+#define SASR1_TFS	(1<<3)
+#define SASR1_RFS	(1<<4)
+#define SASR1_TUR	(1<<5)
+#define SASR1_ROR	(1<<6)
+#define SASR1_CADT	(1<<16)
+#define SASR1_SADR	(1<<17)
+#define SASR1_RSTO	(1<<18)
+#define SASR1_CLPM	(1<<19)
+#define SASR1_CRDY	(1<<20)
+#define SASR1_RS3V	(1<<21)
+#define SASR1_RS4V	(1<<22)
+
+#define SASCR_TUR	(1<<5)
+#define SASCR_ROR	(1<<6)
+#define SASCR_DTS	(1<<16)
+#define SASCR_RDD	(1<<17)
+#define SASCR_STO	(1<<18)
+
+#define SADTCS_TDEN	(1<<0)
+#define SADTCS_TDIE	(1<<1)
+#define SADTCS_TDBDA	(1<<3)
+#define SADTCS_TDSTA	(1<<4)
+#define SADTCS_TDBDB	(1<<5)
+#define SADTCS_TDSTB	(1<<6)
+#define SADTCS_TBIU	(1<<7)
+
+#define SADRCS_RDEN	(1<<0)
+#define SADRCS_RDIE	(1<<1)
+#define SADRCS_RDBDA	(1<<3)
+#define SADRCS_RDSTA	(1<<4)
+#define SADRCS_RDBDB	(1<<5)
+#define SADRCS_RDSTB	(1<<6)
+#define SADRCS_RBIU	(1<<7)
+
+#define SAD_CS_DEN	(1<<0)
+#define SAD_CS_DIE	(1<<1)	/* Not functional on metal 1 */
+#define SAD_CS_DBDA	(1<<3)	/* Not functional on metal 1 */
+#define SAD_CS_DSTA	(1<<4)
+#define SAD_CS_DBDB	(1<<5)	/* Not functional on metal 1 */
+#define SAD_CS_DSTB	(1<<6)
+#define SAD_CS_BIU	(1<<7)	/* Not functional on metal 1 */
+
+#define SAITR_TFS	(1<<0)
+#define SAITR_RFS	(1<<1)
+#define SAITR_TUR	(1<<2)
+#define SAITR_ROR	(1<<3)
+#define SAITR_CADT	(1<<4)
+#define SAITR_SADR	(1<<5)
+#define SAITR_RSTO	(1<<6)
+#define SAITR_TDBDA	(1<<8)
+#define SAITR_TDBDB	(1<<9)
+#define SAITR_RDBDA	(1<<10)
+#define SAITR_RDBDB	(1<<11)
+
+#endif  /* !CONFIG_ARCH_PXA */
+
+/*
+ * General-Purpose I/O Interface
+ *
+ * Registers
+ *    PA_DDR		GPIO Block A Data Direction
+ *    PA_DRR/PA_DWR	GPIO Block A Data Value Register (read/write)
+ *    PA_SDR		GPIO Block A Sleep Direction
+ *    PA_SSR		GPIO Block A Sleep State
+ *    PB_DDR		GPIO Block B Data Direction
+ *    PB_DRR/PB_DWR	GPIO Block B Data Value Register (read/write)
+ *    PB_SDR		GPIO Block B Sleep Direction
+ *    PB_SSR		GPIO Block B Sleep State
+ *    PC_DDR		GPIO Block C Data Direction
+ *    PC_DRR/PC_DWR	GPIO Block C Data Value Register (read/write)
+ *    PC_SDR		GPIO Block C Sleep Direction
+ *    PC_SSR		GPIO Block C Sleep State
+ */
+
+#define SA1111_GPIO	0x1000
+
+#define SA1111_GPIO_PADDR	(0x000)
+#define SA1111_GPIO_PADRR	(0x004)
+#define SA1111_GPIO_PADWR	(0x004)
+#define SA1111_GPIO_PASDR	(0x008)
+#define SA1111_GPIO_PASSR	(0x00c)
+#define SA1111_GPIO_PBDDR	(0x010)
+#define SA1111_GPIO_PBDRR	(0x014)
+#define SA1111_GPIO_PBDWR	(0x014)
+#define SA1111_GPIO_PBSDR	(0x018)
+#define SA1111_GPIO_PBSSR	(0x01c)
+#define SA1111_GPIO_PCDDR	(0x020)
+#define SA1111_GPIO_PCDRR	(0x024)
+#define SA1111_GPIO_PCDWR	(0x024)
+#define SA1111_GPIO_PCSDR	(0x028)
+#define SA1111_GPIO_PCSSR	(0x02c)
+
+#define GPIO_A0		(1 << 0)
+#define GPIO_A1		(1 << 1)
+#define GPIO_A2		(1 << 2)
+#define GPIO_A3		(1 << 3)
+
+#define GPIO_B0		(1 << 8)
+#define GPIO_B1		(1 << 9)
+#define GPIO_B2		(1 << 10)
+#define GPIO_B3		(1 << 11)
+#define GPIO_B4		(1 << 12)
+#define GPIO_B5		(1 << 13)
+#define GPIO_B6		(1 << 14)
+#define GPIO_B7		(1 << 15)
+
+#define GPIO_C0		(1 << 16)
+#define GPIO_C1		(1 << 17)
+#define GPIO_C2		(1 << 18)
+#define GPIO_C3		(1 << 19)
+#define GPIO_C4		(1 << 20)
+#define GPIO_C5		(1 << 21)
+#define GPIO_C6		(1 << 22)
+#define GPIO_C7		(1 << 23)
+
+/*
+ * Interrupt Controller
+ *
+ * Registers
+ *    INTTEST0		Test register 0
+ *    INTTEST1		Test register 1
+ *    INTEN0		Interrupt Enable register 0
+ *    INTEN1		Interrupt Enable register 1
+ *    INTPOL0		Interrupt Polarity selection 0
+ *    INTPOL1		Interrupt Polarity selection 1
+ *    INTTSTSEL		Interrupt source selection
+ *    INTSTATCLR0	Interrupt Status/Clear 0
+ *    INTSTATCLR1	Interrupt Status/Clear 1
+ *    INTSET0		Interrupt source set 0
+ *    INTSET1		Interrupt source set 1
+ *    WAKE_EN0		Wake-up source enable 0
+ *    WAKE_EN1		Wake-up source enable 1
+ *    WAKE_POL0		Wake-up polarity selection 0
+ *    WAKE_POL1		Wake-up polarity selection 1
+ */
+#define SA1111_INTC		0x1600
+
+/*
+ * These are offsets from the above base.
+ */
+#define SA1111_INTTEST0		0x0000
+#define SA1111_INTTEST1		0x0004
+#define SA1111_INTEN0		0x0008
+#define SA1111_INTEN1		0x000c
+#define SA1111_INTPOL0		0x0010
+#define SA1111_INTPOL1		0x0014
+#define SA1111_INTTSTSEL	0x0018
+#define SA1111_INTSTATCLR0	0x001c
+#define SA1111_INTSTATCLR1	0x0020
+#define SA1111_INTSET0		0x0024
+#define SA1111_INTSET1		0x0028
+#define SA1111_WAKEEN0		0x002c
+#define SA1111_WAKEEN1		0x0030
+#define SA1111_WAKEPOL0		0x0034
+#define SA1111_WAKEPOL1		0x0038
+
+/* PS/2 Trackpad and Mouse Interfaces */
+#define SA1111_KBD		0x0a00
+#define SA1111_MSE		0x0c00
+
+/* PCMCIA Interface */
+#define SA1111_PCMCIA		0x1600
+
+
+
+
+
+extern struct bus_type sa1111_bus_type;
+
+#define SA1111_DEVID_SBI	(1 << 0)
+#define SA1111_DEVID_SK		(1 << 1)
+#define SA1111_DEVID_USB	(1 << 2)
+#define SA1111_DEVID_SAC	(1 << 3)
+#define SA1111_DEVID_SSP	(1 << 4)
+#define SA1111_DEVID_PS2	(3 << 5)
+#define SA1111_DEVID_PS2_KBD	(1 << 5)
+#define SA1111_DEVID_PS2_MSE	(1 << 6)
+#define SA1111_DEVID_GPIO	(1 << 7)
+#define SA1111_DEVID_INT	(1 << 8)
+#define SA1111_DEVID_PCMCIA	(1 << 9)
+
+struct sa1111_dev {
+	struct device	dev;
+	unsigned int	devid;
+	struct resource	res;
+	void __iomem	*mapbase;
+	unsigned int	skpcr_mask;
+	unsigned int	irq[6];
+	u64		dma_mask;
+};
+
+#define SA1111_DEV(_d)	container_of((_d), struct sa1111_dev, dev)
+
+#define sa1111_get_drvdata(d)	dev_get_drvdata(&(d)->dev)
+#define sa1111_set_drvdata(d,p)	dev_set_drvdata(&(d)->dev, p)
+
+struct sa1111_driver {
+	struct device_driver	drv;
+	unsigned int		devid;
+	int (*probe)(struct sa1111_dev *);
+	int (*remove)(struct sa1111_dev *);
+	int (*suspend)(struct sa1111_dev *, pm_message_t);
+	int (*resume)(struct sa1111_dev *);
+	void (*shutdown)(struct sa1111_dev *);
+};
+
+#define SA1111_DRV(_d)	container_of((_d), struct sa1111_driver, drv)
+
+#define SA1111_DRIVER_NAME(_sadev) ((_sadev)->dev.driver->name)
+
+/*
+ * These frob the SKPCR register, and call platform specific
+ * enable/disable functions.
+ */
+int sa1111_enable_device(struct sa1111_dev *);
+void sa1111_disable_device(struct sa1111_dev *);
+
+unsigned int sa1111_pll_clock(struct sa1111_dev *);
+
+#define SA1111_AUDIO_ACLINK	0
+#define SA1111_AUDIO_I2S	1
+
+void sa1111_select_audio_mode(struct sa1111_dev *sadev, int mode);
+int sa1111_set_audio_rate(struct sa1111_dev *sadev, int rate);
+int sa1111_get_audio_rate(struct sa1111_dev *sadev);
+
+int sa1111_check_dma_bug(dma_addr_t addr);
+
+int sa1111_driver_register(struct sa1111_driver *);
+void sa1111_driver_unregister(struct sa1111_driver *);
+
+void sa1111_set_io_dir(struct sa1111_dev *sadev, unsigned int bits, unsigned int dir, unsigned int sleep_dir);
+void sa1111_set_io(struct sa1111_dev *sadev, unsigned int bits, unsigned int v);
+void sa1111_set_sleep_io(struct sa1111_dev *sadev, unsigned int bits, unsigned int v);
+
+struct sa1111_platform_data {
+	int	irq_base;	/* base for cascaded on-chip IRQs */
+	unsigned disable_devs;
+	void	*data;
+	int	(*enable)(void *, unsigned);
+	void	(*disable)(void *, unsigned);
+};
+
+#endif  /* _ASM_ARCH_SA1111 */
diff --git a/arch/arm/include/asm/hardware/scoop.h b/arch/arm/include/asm/hardware/scoop.h
new file mode 100644
index 000000000..58cdf5d84
--- /dev/null
+++ b/arch/arm/include/asm/hardware/scoop.h
@@ -0,0 +1,71 @@
+/*
+ *  Definitions for the SCOOP interface found on various Sharp PDAs
+ *
+ *  Copyright (c) 2004 Richard Purdie
+ *
+ *  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.
+ *
+ */
+
+#define SCOOP_MCR  0x00
+#define SCOOP_CDR  0x04
+#define SCOOP_CSR  0x08
+#define SCOOP_CPR  0x0C
+#define SCOOP_CCR  0x10
+#define SCOOP_IRR  0x14
+#define SCOOP_IRM  0x14
+#define SCOOP_IMR  0x18
+#define SCOOP_ISR  0x1C
+#define SCOOP_GPCR 0x20
+#define SCOOP_GPWR 0x24
+#define SCOOP_GPRR 0x28
+
+#define SCOOP_CPR_OUT	(1 << 7)
+#define SCOOP_CPR_SD_3V	(1 << 2)
+#define SCOOP_CPR_CF_XV	(1 << 1)
+#define SCOOP_CPR_CF_3V	(1 << 0)
+
+#define SCOOP_GPCR_PA22	(1 << 12)
+#define SCOOP_GPCR_PA21	(1 << 11)
+#define SCOOP_GPCR_PA20	(1 << 10)
+#define SCOOP_GPCR_PA19	(1 << 9)
+#define SCOOP_GPCR_PA18	(1 << 8)
+#define SCOOP_GPCR_PA17	(1 << 7)
+#define SCOOP_GPCR_PA16	(1 << 6)
+#define SCOOP_GPCR_PA15	(1 << 5)
+#define SCOOP_GPCR_PA14	(1 << 4)
+#define SCOOP_GPCR_PA13	(1 << 3)
+#define SCOOP_GPCR_PA12	(1 << 2)
+#define SCOOP_GPCR_PA11	(1 << 1)
+
+struct scoop_config {
+	unsigned short io_out;
+	unsigned short io_dir;
+	unsigned short suspend_clr;
+	unsigned short suspend_set;
+	int gpio_base;
+};
+
+/* Structure for linking scoop devices to PCMCIA sockets */
+struct scoop_pcmcia_dev {
+	struct device *dev;     /* Pointer to this socket's scoop device */
+	int	irq;                /* irq for socket */
+	int cd_irq;
+	const char *cd_irq_str;
+	unsigned char keep_vs;
+	unsigned char keep_rd;
+};
+
+struct scoop_pcmcia_config {
+	struct scoop_pcmcia_dev *devs;
+	int num_devs;
+	void (*power_ctrl)(struct device *scoop, unsigned short cpr, int nr);
+};
+
+extern struct scoop_pcmcia_config *platform_scoop_config;
+
+void reset_scoop(struct device *dev);
+unsigned short read_scoop_reg(struct device *dev, unsigned short reg);
+void write_scoop_reg(struct device *dev, unsigned short reg, unsigned short data);
diff --git a/arch/arm/include/asm/hardware/ssp.h b/arch/arm/include/asm/hardware/ssp.h
new file mode 100644
index 000000000..3b42e1819
--- /dev/null
+++ b/arch/arm/include/asm/hardware/ssp.h
@@ -0,0 +1,28 @@
+/*
+ *  ssp.h
+ *
+ *  Copyright (C) 2003 Russell King, 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 as
+ * published by the Free Software Foundation.
+ */
+#ifndef SSP_H
+#define SSP_H
+
+struct ssp_state {
+	unsigned int	cr0;
+	unsigned int	cr1;
+};
+
+int ssp_write_word(u16 data);
+int ssp_read_word(u16 *data);
+int ssp_flush(void);
+void ssp_enable(void);
+void ssp_disable(void);
+void ssp_save_state(struct ssp_state *ssp);
+void ssp_restore_state(struct ssp_state *ssp);
+int ssp_init(void);
+void ssp_exit(void);
+
+#endif
diff --git a/arch/arm/include/asm/hardware/timer-sp.h b/arch/arm/include/asm/hardware/timer-sp.h
new file mode 100644
index 000000000..bb28af7c3
--- /dev/null
+++ b/arch/arm/include/asm/hardware/timer-sp.h
@@ -0,0 +1,23 @@
+struct clk;
+
+void __sp804_clocksource_and_sched_clock_init(void __iomem *,
+					      const char *, struct clk *, int);
+void __sp804_clockevents_init(void __iomem *, unsigned int,
+			      struct clk *, const char *);
+
+static inline void sp804_clocksource_init(void __iomem *base, const char *name)
+{
+	__sp804_clocksource_and_sched_clock_init(base, name, NULL, 0);
+}
+
+static inline void sp804_clocksource_and_sched_clock_init(void __iomem *base,
+							  const char *name)
+{
+	__sp804_clocksource_and_sched_clock_init(base, name, NULL, 1);
+}
+
+static inline void sp804_clockevents_init(void __iomem *base, unsigned int irq, const char *name)
+{
+	__sp804_clockevents_init(base, irq, NULL, name);
+
+}
diff --git a/arch/arm/include/asm/highmem.h b/arch/arm/include/asm/highmem.h
new file mode 100644
index 000000000..535579511
--- /dev/null
+++ b/arch/arm/include/asm/highmem.h
@@ -0,0 +1,74 @@
+#ifndef _ASM_HIGHMEM_H
+#define _ASM_HIGHMEM_H
+
+#include <asm/kmap_types.h>
+
+#define PKMAP_BASE		(PAGE_OFFSET - PMD_SIZE)
+#define LAST_PKMAP		PTRS_PER_PTE
+#define LAST_PKMAP_MASK		(LAST_PKMAP - 1)
+#define PKMAP_NR(virt)		(((virt) - PKMAP_BASE) >> PAGE_SHIFT)
+#define PKMAP_ADDR(nr)		(PKMAP_BASE + ((nr) << PAGE_SHIFT))
+
+#define kmap_prot		PAGE_KERNEL
+
+#define flush_cache_kmaps() \
+	do { \
+		if (cache_is_vivt()) \
+			flush_cache_all(); \
+	} while (0)
+
+extern pte_t *pkmap_page_table;
+extern pte_t *fixmap_page_table;
+
+extern void *kmap_high(struct page *page);
+extern void kunmap_high(struct page *page);
+
+/*
+ * The reason for kmap_high_get() is to ensure that the currently kmap'd
+ * page usage count does not decrease to zero while we're using its
+ * existing virtual mapping in an atomic context.  With a VIVT cache this
+ * is essential to do, but with a VIPT cache this is only an optimization
+ * so not to pay the price of establishing a second mapping if an existing
+ * one can be used.  However, on platforms without hardware TLB maintenance
+ * broadcast, we simply cannot use ARCH_NEEDS_KMAP_HIGH_GET at all since
+ * the locking involved must also disable IRQs which is incompatible with
+ * the IPI mechanism used by global TLB operations.
+ */
+#define ARCH_NEEDS_KMAP_HIGH_GET
+#if defined(CONFIG_SMP) && defined(CONFIG_CPU_TLB_V6)
+#undef ARCH_NEEDS_KMAP_HIGH_GET
+#if defined(CONFIG_HIGHMEM) && defined(CONFIG_CPU_CACHE_VIVT)
+#error "The sum of features in your kernel config cannot be supported together"
+#endif
+#endif
+
+/*
+ * Needed to be able to broadcast the TLB invalidation for kmap.
+ */
+#ifdef CONFIG_ARM_ERRATA_798181
+#undef ARCH_NEEDS_KMAP_HIGH_GET
+#endif
+
+#ifdef ARCH_NEEDS_KMAP_HIGH_GET
+extern void *kmap_high_get(struct page *page);
+#else
+static inline void *kmap_high_get(struct page *page)
+{
+	return NULL;
+}
+#endif
+
+/*
+ * The following functions are already defined by <linux/highmem.h>
+ * when CONFIG_HIGHMEM is not set.
+ */
+#ifdef CONFIG_HIGHMEM
+extern void *kmap(struct page *page);
+extern void kunmap(struct page *page);
+extern void *kmap_atomic(struct page *page);
+extern void __kunmap_atomic(void *kvaddr);
+extern void *kmap_atomic_pfn(unsigned long pfn);
+extern struct page *kmap_atomic_to_page(const void *ptr);
+#endif
+
+#endif
diff --git a/arch/arm/include/asm/hugetlb-3level.h b/arch/arm/include/asm/hugetlb-3level.h
new file mode 100644
index 000000000..d4014fbe5
--- /dev/null
+++ b/arch/arm/include/asm/hugetlb-3level.h
@@ -0,0 +1,71 @@
+/*
+ * arch/arm/include/asm/hugetlb-3level.h
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ *
+ * Based on arch/x86/include/asm/hugetlb.h.
+ *
+ * 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, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#ifndef _ASM_ARM_HUGETLB_3LEVEL_H
+#define _ASM_ARM_HUGETLB_3LEVEL_H
+
+
+/*
+ * If our huge pte is non-zero then mark the valid bit.
+ * This allows pte_present(huge_ptep_get(ptep)) to return true for non-zero
+ * ptes.
+ * (The valid bit is automatically cleared by set_pte_at for PROT_NONE ptes).
+ */
+static inline pte_t huge_ptep_get(pte_t *ptep)
+{
+	pte_t retval = *ptep;
+	if (pte_val(retval))
+		pte_val(retval) |= L_PTE_VALID;
+	return retval;
+}
+
+static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+				   pte_t *ptep, pte_t pte)
+{
+	set_pte_at(mm, addr, ptep, pte);
+}
+
+static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
+					 unsigned long addr, pte_t *ptep)
+{
+	ptep_clear_flush(vma, addr, ptep);
+}
+
+static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
+					   unsigned long addr, pte_t *ptep)
+{
+	ptep_set_wrprotect(mm, addr, ptep);
+}
+
+static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
+					    unsigned long addr, pte_t *ptep)
+{
+	return ptep_get_and_clear(mm, addr, ptep);
+}
+
+static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
+					     unsigned long addr, pte_t *ptep,
+					     pte_t pte, int dirty)
+{
+	return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
+}
+
+#endif /* _ASM_ARM_HUGETLB_3LEVEL_H */
diff --git a/arch/arm/include/asm/hugetlb.h b/arch/arm/include/asm/hugetlb.h
new file mode 100644
index 000000000..1f1b1cd11
--- /dev/null
+++ b/arch/arm/include/asm/hugetlb.h
@@ -0,0 +1,84 @@
+/*
+ * arch/arm/include/asm/hugetlb.h
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ *
+ * Based on arch/x86/include/asm/hugetlb.h
+ *
+ * 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, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#ifndef _ASM_ARM_HUGETLB_H
+#define _ASM_ARM_HUGETLB_H
+
+#include <asm/page.h>
+#include <asm-generic/hugetlb.h>
+
+#include <asm/hugetlb-3level.h>
+
+static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
+					  unsigned long addr, unsigned long end,
+					  unsigned long floor,
+					  unsigned long ceiling)
+{
+	free_pgd_range(tlb, addr, end, floor, ceiling);
+}
+
+
+static inline int is_hugepage_only_range(struct mm_struct *mm,
+					 unsigned long addr, unsigned long len)
+{
+	return 0;
+}
+
+static inline int prepare_hugepage_range(struct file *file,
+					 unsigned long addr, unsigned long len)
+{
+	struct hstate *h = hstate_file(file);
+	if (len & ~huge_page_mask(h))
+		return -EINVAL;
+	if (addr & ~huge_page_mask(h))
+		return -EINVAL;
+	return 0;
+}
+
+static inline void hugetlb_prefault_arch_hook(struct mm_struct *mm)
+{
+}
+
+static inline int huge_pte_none(pte_t pte)
+{
+	return pte_none(pte);
+}
+
+static inline pte_t huge_pte_wrprotect(pte_t pte)
+{
+	return pte_wrprotect(pte);
+}
+
+static inline int arch_prepare_hugepage(struct page *page)
+{
+	return 0;
+}
+
+static inline void arch_release_hugepage(struct page *page)
+{
+}
+
+static inline void arch_clear_hugepage_flags(struct page *page)
+{
+	clear_bit(PG_dcache_clean, &page->flags);
+}
+
+#endif /* _ASM_ARM_HUGETLB_H */
diff --git a/arch/arm/include/asm/hw_breakpoint.h b/arch/arm/include/asm/hw_breakpoint.h
new file mode 100644
index 000000000..8e427c7b4
--- /dev/null
+++ b/arch/arm/include/asm/hw_breakpoint.h
@@ -0,0 +1,139 @@
+#ifndef _ARM_HW_BREAKPOINT_H
+#define _ARM_HW_BREAKPOINT_H
+
+#ifdef __KERNEL__
+
+struct task_struct;
+
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+
+struct arch_hw_breakpoint_ctrl {
+		u32 __reserved	: 9,
+		mismatch	: 1,
+				: 9,
+		len		: 8,
+		type		: 2,
+		privilege	: 2,
+		enabled		: 1;
+};
+
+struct arch_hw_breakpoint {
+	u32	address;
+	u32	trigger;
+	struct	arch_hw_breakpoint_ctrl step_ctrl;
+	struct	arch_hw_breakpoint_ctrl ctrl;
+};
+
+static inline u32 encode_ctrl_reg(struct arch_hw_breakpoint_ctrl ctrl)
+{
+	return (ctrl.mismatch << 22) | (ctrl.len << 5) | (ctrl.type << 3) |
+		(ctrl.privilege << 1) | ctrl.enabled;
+}
+
+static inline void decode_ctrl_reg(u32 reg,
+				   struct arch_hw_breakpoint_ctrl *ctrl)
+{
+	ctrl->enabled	= reg & 0x1;
+	reg >>= 1;
+	ctrl->privilege	= reg & 0x3;
+	reg >>= 2;
+	ctrl->type	= reg & 0x3;
+	reg >>= 2;
+	ctrl->len	= reg & 0xff;
+	reg >>= 17;
+	ctrl->mismatch	= reg & 0x1;
+}
+
+/* Debug architecture numbers. */
+#define ARM_DEBUG_ARCH_RESERVED	0	/* In case of ptrace ABI updates. */
+#define ARM_DEBUG_ARCH_V6	1
+#define ARM_DEBUG_ARCH_V6_1	2
+#define ARM_DEBUG_ARCH_V7_ECP14	3
+#define ARM_DEBUG_ARCH_V7_MM	4
+#define ARM_DEBUG_ARCH_V7_1	5
+#define ARM_DEBUG_ARCH_V8	6
+
+/* Breakpoint */
+#define ARM_BREAKPOINT_EXECUTE	0
+
+/* Watchpoints */
+#define ARM_BREAKPOINT_LOAD	1
+#define ARM_BREAKPOINT_STORE	2
+#define ARM_FSR_ACCESS_MASK	(1 << 11)
+
+/* Privilege Levels */
+#define ARM_BREAKPOINT_PRIV	1
+#define ARM_BREAKPOINT_USER	2
+
+/* Lengths */
+#define ARM_BREAKPOINT_LEN_1	0x1
+#define ARM_BREAKPOINT_LEN_2	0x3
+#define ARM_BREAKPOINT_LEN_4	0xf
+#define ARM_BREAKPOINT_LEN_8	0xff
+
+/* Limits */
+#define ARM_MAX_BRP		16
+#define ARM_MAX_WRP		16
+#define ARM_MAX_HBP_SLOTS	(ARM_MAX_BRP + ARM_MAX_WRP)
+
+/* DSCR method of entry bits. */
+#define ARM_DSCR_MOE(x)			((x >> 2) & 0xf)
+#define ARM_ENTRY_BREAKPOINT		0x1
+#define ARM_ENTRY_ASYNC_WATCHPOINT	0x2
+#define ARM_ENTRY_SYNC_WATCHPOINT	0xa
+
+/* DSCR monitor/halting bits. */
+#define ARM_DSCR_HDBGEN		(1 << 14)
+#define ARM_DSCR_MDBGEN		(1 << 15)
+
+/* OSLSR os lock model bits */
+#define ARM_OSLSR_OSLM0		(1 << 0)
+
+/* opcode2 numbers for the co-processor instructions. */
+#define ARM_OP2_BVR		4
+#define ARM_OP2_BCR		5
+#define ARM_OP2_WVR		6
+#define ARM_OP2_WCR		7
+
+/* Base register numbers for the debug registers. */
+#define ARM_BASE_BVR		64
+#define ARM_BASE_BCR		80
+#define ARM_BASE_WVR		96
+#define ARM_BASE_WCR		112
+
+/* Accessor macros for the debug registers. */
+#define ARM_DBG_READ(N, M, OP2, VAL) do {\
+	asm volatile("mrc p14, 0, %0, " #N "," #M ", " #OP2 : "=r" (VAL));\
+} while (0)
+
+#define ARM_DBG_WRITE(N, M, OP2, VAL) do {\
+	asm volatile("mcr p14, 0, %0, " #N "," #M ", " #OP2 : : "r" (VAL));\
+} while (0)
+
+struct notifier_block;
+struct perf_event;
+struct pmu;
+
+extern struct pmu perf_ops_bp;
+extern int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl,
+				  int *gen_len, int *gen_type);
+extern int arch_check_bp_in_kernelspace(struct perf_event *bp);
+extern int arch_validate_hwbkpt_settings(struct perf_event *bp);
+extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
+					   unsigned long val, void *data);
+
+extern u8 arch_get_debug_arch(void);
+extern u8 arch_get_max_wp_len(void);
+extern void clear_ptrace_hw_breakpoint(struct task_struct *tsk);
+
+int arch_install_hw_breakpoint(struct perf_event *bp);
+void arch_uninstall_hw_breakpoint(struct perf_event *bp);
+void hw_breakpoint_pmu_read(struct perf_event *bp);
+int hw_breakpoint_slots(int type);
+
+#else
+static inline void clear_ptrace_hw_breakpoint(struct task_struct *tsk) {}
+
+#endif	/* CONFIG_HAVE_HW_BREAKPOINT */
+#endif	/* __KERNEL__ */
+#endif	/* _ARM_HW_BREAKPOINT_H */
diff --git a/arch/arm/include/asm/hw_irq.h b/arch/arm/include/asm/hw_irq.h
new file mode 100644
index 000000000..af79da40a
--- /dev/null
+++ b/arch/arm/include/asm/hw_irq.h
@@ -0,0 +1,22 @@
+/*
+ * Nothing to see here yet
+ */
+#ifndef _ARCH_ARM_HW_IRQ_H
+#define _ARCH_ARM_HW_IRQ_H
+
+static inline void ack_bad_irq(int irq)
+{
+	extern unsigned long irq_err_count;
+	irq_err_count++;
+	pr_crit("unexpected IRQ trap at vector %02x\n", irq);
+}
+
+void set_irq_flags(unsigned int irq, unsigned int flags);
+
+#define IRQF_VALID	(1 << 0)
+#define IRQF_PROBE	(1 << 1)
+#define IRQF_NOAUTOEN	(1 << 2)
+
+#define ARCH_IRQ_INIT_FLAGS	(IRQ_NOREQUEST | IRQ_NOPROBE)
+
+#endif
diff --git a/arch/arm/include/asm/hwcap.h b/arch/arm/include/asm/hwcap.h
new file mode 100644
index 000000000..6e183fd26
--- /dev/null
+++ b/arch/arm/include/asm/hwcap.h
@@ -0,0 +1,15 @@
+#ifndef __ASMARM_HWCAP_H
+#define __ASMARM_HWCAP_H
+
+#include <uapi/asm/hwcap.h>
+
+#if !defined(__ASSEMBLY__)
+/*
+ * This yields a mask that user programs can use to figure out what
+ * instruction set this cpu supports.
+ */
+#define ELF_HWCAP	(elf_hwcap)
+#define ELF_HWCAP2	(elf_hwcap2)
+extern unsigned int elf_hwcap, elf_hwcap2;
+#endif
+#endif
diff --git a/arch/arm/include/asm/hypervisor.h b/arch/arm/include/asm/hypervisor.h
new file mode 100644
index 000000000..b90d9e523
--- /dev/null
+++ b/arch/arm/include/asm/hypervisor.h
@@ -0,0 +1,6 @@
+#ifndef _ASM_ARM_HYPERVISOR_H
+#define _ASM_ARM_HYPERVISOR_H
+
+#include <asm/xen/hypervisor.h>
+
+#endif
diff --git a/arch/arm/include/asm/ide.h b/arch/arm/include/asm/ide.h
new file mode 100644
index 000000000..b507ce8e5
--- /dev/null
+++ b/arch/arm/include/asm/ide.h
@@ -0,0 +1,23 @@
+/*
+ *  arch/arm/include/asm/ide.h
+ *
+ *  Copyright (C) 1994-1996  Linus Torvalds & authors
+ */
+
+/*
+ *  This file contains the ARM architecture specific IDE code.
+ */
+
+#ifndef __ASMARM_IDE_H
+#define __ASMARM_IDE_H
+
+#ifdef __KERNEL__
+
+#define __ide_mm_insw(port,addr,len)	readsw(port,addr,len)
+#define __ide_mm_insl(port,addr,len)	readsl(port,addr,len)
+#define __ide_mm_outsw(port,addr,len)	writesw(port,addr,len)
+#define __ide_mm_outsl(port,addr,len)	writesl(port,addr,len)
+
+#endif /* __KERNEL__ */
+
+#endif /* __ASMARM_IDE_H */
diff --git a/arch/arm/include/asm/idmap.h b/arch/arm/include/asm/idmap.h
new file mode 100644
index 000000000..bf863edb5
--- /dev/null
+++ b/arch/arm/include/asm/idmap.h
@@ -0,0 +1,14 @@
+#ifndef __ASM_IDMAP_H
+#define __ASM_IDMAP_H
+
+#include <linux/compiler.h>
+#include <asm/pgtable.h>
+
+/* Tag a function as requiring to be executed via an identity mapping. */
+#define __idmap __section(.idmap.text) noinline notrace
+
+extern pgd_t *idmap_pgd;
+
+void setup_mm_for_reboot(void);
+
+#endif	/* __ASM_IDMAP_H */
diff --git a/arch/arm/include/asm/insn.h b/arch/arm/include/asm/insn.h
new file mode 100644
index 000000000..e96065da4
--- /dev/null
+++ b/arch/arm/include/asm/insn.h
@@ -0,0 +1,29 @@
+#ifndef __ASM_ARM_INSN_H
+#define __ASM_ARM_INSN_H
+
+static inline unsigned long
+arm_gen_nop(void)
+{
+#ifdef CONFIG_THUMB2_KERNEL
+	return 0xf3af8000; /* nop.w */
+#else
+	return 0xe1a00000; /* mov r0, r0 */
+#endif
+}
+
+unsigned long
+__arm_gen_branch(unsigned long pc, unsigned long addr, bool link);
+
+static inline unsigned long
+arm_gen_branch(unsigned long pc, unsigned long addr)
+{
+	return __arm_gen_branch(pc, addr, false);
+}
+
+static inline unsigned long
+arm_gen_branch_link(unsigned long pc, unsigned long addr)
+{
+	return __arm_gen_branch(pc, addr, true);
+}
+
+#endif
diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h
new file mode 100644
index 000000000..db58deb00
--- /dev/null
+++ b/arch/arm/include/asm/io.h
@@ -0,0 +1,406 @@
+/*
+ *  arch/arm/include/asm/io.h
+ *
+ *  Copyright (C) 1996-2000 Russell King
+ *
+ * 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.
+ *
+ * Modifications:
+ *  16-Sep-1996	RMK	Inlined the inx/outx functions & optimised for both
+ *			constant addresses and variable addresses.
+ *  04-Dec-1997	RMK	Moved a lot of this stuff to the new architecture
+ *			specific IO header files.
+ *  27-Mar-1999	PJB	Second parameter of memcpy_toio is const..
+ *  04-Apr-1999	PJB	Added check_signature.
+ *  12-Dec-1999	RMK	More cleanups
+ *  18-Jun-2000 RMK	Removed virt_to_* and friends definitions
+ *  05-Oct-2004 BJD     Moved memory string functions to use void __iomem
+ */
+#ifndef __ASM_ARM_IO_H
+#define __ASM_ARM_IO_H
+
+#ifdef __KERNEL__
+
+#include <linux/types.h>
+#include <linux/blk_types.h>
+#include <asm/byteorder.h>
+#include <asm/memory.h>
+#include <asm-generic/pci_iomap.h>
+#include <xen/xen.h>
+
+/*
+ * ISA I/O bus memory addresses are 1:1 with the physical address.
+ */
+#define isa_virt_to_bus virt_to_phys
+#define isa_page_to_bus page_to_phys
+#define isa_bus_to_virt phys_to_virt
+
+/*
+ * Atomic MMIO-wide IO modify
+ */
+extern void atomic_io_modify(void __iomem *reg, u32 mask, u32 set);
+extern void atomic_io_modify_relaxed(void __iomem *reg, u32 mask, u32 set);
+
+/*
+ * Generic IO read/write.  These perform native-endian accesses.  Note
+ * that some architectures will want to re-define __raw_{read,write}w.
+ */
+void __raw_writesb(volatile void __iomem *addr, const void *data, int bytelen);
+void __raw_writesw(volatile void __iomem *addr, const void *data, int wordlen);
+void __raw_writesl(volatile void __iomem *addr, const void *data, int longlen);
+
+void __raw_readsb(const volatile void __iomem *addr, void *data, int bytelen);
+void __raw_readsw(const volatile void __iomem *addr, void *data, int wordlen);
+void __raw_readsl(const volatile void __iomem *addr, void *data, int longlen);
+
+#if __LINUX_ARM_ARCH__ < 6
+/*
+ * Half-word accesses are problematic with RiscPC due to limitations of
+ * the bus. Rather than special-case the machine, just let the compiler
+ * generate the access for CPUs prior to ARMv6.
+ */
+#define __raw_readw(a)         (__chk_io_ptr(a), *(volatile unsigned short __force *)(a))
+#define __raw_writew(v,a)      ((void)(__chk_io_ptr(a), *(volatile unsigned short __force *)(a) = (v)))
+#else
+/*
+ * When running under a hypervisor, we want to avoid I/O accesses with
+ * writeback addressing modes as these incur a significant performance
+ * overhead (the address generation must be emulated in software).
+ */
+#define __raw_writew __raw_writew
+static inline void __raw_writew(u16 val, volatile void __iomem *addr)
+{
+	asm volatile("strh %1, %0"
+		     : "+Q" (*(volatile u16 __force *)addr)
+		     : "r" (val));
+}
+
+#define __raw_readw __raw_readw
+static inline u16 __raw_readw(const volatile void __iomem *addr)
+{
+	u16 val;
+	asm volatile("ldrh %1, %0"
+		     : "+Q" (*(volatile u16 __force *)addr),
+		       "=r" (val));
+	return val;
+}
+#endif
+
+#define __raw_writeb __raw_writeb
+static inline void __raw_writeb(u8 val, volatile void __iomem *addr)
+{
+	asm volatile("strb %1, %0"
+		     : "+Qo" (*(volatile u8 __force *)addr)
+		     : "r" (val));
+}
+
+#define __raw_writel __raw_writel
+static inline void __raw_writel(u32 val, volatile void __iomem *addr)
+{
+	asm volatile("str %1, %0"
+		     : "+Qo" (*(volatile u32 __force *)addr)
+		     : "r" (val));
+}
+
+#define __raw_readb __raw_readb
+static inline u8 __raw_readb(const volatile void __iomem *addr)
+{
+	u8 val;
+	asm volatile("ldrb %1, %0"
+		     : "+Qo" (*(volatile u8 __force *)addr),
+		       "=r" (val));
+	return val;
+}
+
+#define __raw_readl __raw_readl
+static inline u32 __raw_readl(const volatile void __iomem *addr)
+{
+	u32 val;
+	asm volatile("ldr %1, %0"
+		     : "+Qo" (*(volatile u32 __force *)addr),
+		       "=r" (val));
+	return val;
+}
+
+/*
+ * Architecture ioremap implementation.
+ */
+#define MT_DEVICE		0
+#define MT_DEVICE_NONSHARED	1
+#define MT_DEVICE_CACHED	2
+#define MT_DEVICE_WC		3
+/*
+ * types 4 onwards can be found in asm/mach/map.h and are undefined
+ * for ioremap
+ */
+
+/*
+ * __arm_ioremap takes CPU physical address.
+ * __arm_ioremap_pfn takes a Page Frame Number and an offset into that page
+ * The _caller variety takes a __builtin_return_address(0) value for
+ * /proc/vmalloc to use - and should only be used in non-inline functions.
+ */
+extern void __iomem *__arm_ioremap_pfn_caller(unsigned long, unsigned long,
+	size_t, unsigned int, void *);
+extern void __iomem *__arm_ioremap_caller(phys_addr_t, size_t, unsigned int,
+	void *);
+
+extern void __iomem *__arm_ioremap_pfn(unsigned long, unsigned long, size_t, unsigned int);
+extern void __iomem *__arm_ioremap(phys_addr_t, size_t, unsigned int);
+extern void __iomem *__arm_ioremap_exec(phys_addr_t, size_t, bool cached);
+extern void __iounmap(volatile void __iomem *addr);
+extern void __arm_iounmap(volatile void __iomem *addr);
+
+extern void __iomem * (*arch_ioremap_caller)(phys_addr_t, size_t,
+	unsigned int, void *);
+extern void (*arch_iounmap)(volatile void __iomem *);
+
+/*
+ * Bad read/write accesses...
+ */
+extern void __readwrite_bug(const char *fn);
+
+/*
+ * A typesafe __io() helper
+ */
+static inline void __iomem *__typesafe_io(unsigned long addr)
+{
+	return (void __iomem *)addr;
+}
+
+#define IOMEM(x)	((void __force __iomem *)(x))
+
+/* IO barriers */
+#ifdef CONFIG_ARM_DMA_MEM_BUFFERABLE
+#include <asm/barrier.h>
+#define __iormb()		rmb()
+#define __iowmb()		wmb()
+#else
+#define __iormb()		do { } while (0)
+#define __iowmb()		do { } while (0)
+#endif
+
+/* PCI fixed i/o mapping */
+#define PCI_IO_VIRT_BASE	0xfee00000
+#define PCI_IOBASE		((void __iomem *)PCI_IO_VIRT_BASE)
+
+#if defined(CONFIG_PCI)
+void pci_ioremap_set_mem_type(int mem_type);
+#else
+static inline void pci_ioremap_set_mem_type(int mem_type) {}
+#endif
+
+extern int pci_ioremap_io(unsigned int offset, phys_addr_t phys_addr);
+
+/*
+ * Now, pick up the machine-defined IO definitions
+ */
+#ifdef CONFIG_NEED_MACH_IO_H
+#include <mach/io.h>
+#elif defined(CONFIG_PCI)
+#define IO_SPACE_LIMIT	((resource_size_t)0xfffff)
+#define __io(a)		__typesafe_io(PCI_IO_VIRT_BASE + ((a) & IO_SPACE_LIMIT))
+#else
+#define __io(a)		__typesafe_io((a) & IO_SPACE_LIMIT)
+#endif
+
+/*
+ * This is the limit of PC card/PCI/ISA IO space, which is by default
+ * 64K if we have PC card, PCI or ISA support.  Otherwise, default to
+ * zero to prevent ISA/PCI drivers claiming IO space (and potentially
+ * oopsing.)
+ *
+ * Only set this larger if you really need inb() et.al. to operate over
+ * a larger address space.  Note that SOC_COMMON ioremaps each sockets
+ * IO space area, and so inb() et.al. must be defined to operate as per
+ * readb() et.al. on such platforms.
+ */
+#ifndef IO_SPACE_LIMIT
+#if defined(CONFIG_PCMCIA_SOC_COMMON) || defined(CONFIG_PCMCIA_SOC_COMMON_MODULE)
+#define IO_SPACE_LIMIT ((resource_size_t)0xffffffff)
+#elif defined(CONFIG_PCI) || defined(CONFIG_ISA) || defined(CONFIG_PCCARD)
+#define IO_SPACE_LIMIT ((resource_size_t)0xffff)
+#else
+#define IO_SPACE_LIMIT ((resource_size_t)0)
+#endif
+#endif
+
+/*
+ *  IO port access primitives
+ *  -------------------------
+ *
+ * The ARM doesn't have special IO access instructions; all IO is memory
+ * mapped.  Note that these are defined to perform little endian accesses
+ * only.  Their primary purpose is to access PCI and ISA peripherals.
+ *
+ * Note that for a big endian machine, this implies that the following
+ * big endian mode connectivity is in place, as described by numerous
+ * ARM documents:
+ *
+ *    PCI:  D0-D7   D8-D15 D16-D23 D24-D31
+ *    ARM: D24-D31 D16-D23  D8-D15  D0-D7
+ *
+ * The machine specific io.h include defines __io to translate an "IO"
+ * address to a memory address.
+ *
+ * Note that we prevent GCC re-ordering or caching values in expressions
+ * by introducing sequence points into the in*() definitions.  Note that
+ * __raw_* do not guarantee this behaviour.
+ *
+ * The {in,out}[bwl] macros are for emulating x86-style PCI/ISA IO space.
+ */
+#ifdef __io
+#define outb(v,p)	({ __iowmb(); __raw_writeb(v,__io(p)); })
+#define outw(v,p)	({ __iowmb(); __raw_writew((__force __u16) \
+					cpu_to_le16(v),__io(p)); })
+#define outl(v,p)	({ __iowmb(); __raw_writel((__force __u32) \
+					cpu_to_le32(v),__io(p)); })
+
+#define inb(p)	({ __u8 __v = __raw_readb(__io(p)); __iormb(); __v; })
+#define inw(p)	({ __u16 __v = le16_to_cpu((__force __le16) \
+			__raw_readw(__io(p))); __iormb(); __v; })
+#define inl(p)	({ __u32 __v = le32_to_cpu((__force __le32) \
+			__raw_readl(__io(p))); __iormb(); __v; })
+
+#define outsb(p,d,l)		__raw_writesb(__io(p),d,l)
+#define outsw(p,d,l)		__raw_writesw(__io(p),d,l)
+#define outsl(p,d,l)		__raw_writesl(__io(p),d,l)
+
+#define insb(p,d,l)		__raw_readsb(__io(p),d,l)
+#define insw(p,d,l)		__raw_readsw(__io(p),d,l)
+#define insl(p,d,l)		__raw_readsl(__io(p),d,l)
+#endif
+
+/*
+ * String version of IO memory access ops:
+ */
+extern void _memcpy_fromio(void *, const volatile void __iomem *, size_t);
+extern void _memcpy_toio(volatile void __iomem *, const void *, size_t);
+extern void _memset_io(volatile void __iomem *, int, size_t);
+
+#define mmiowb()
+
+/*
+ *  Memory access primitives
+ *  ------------------------
+ *
+ * These perform PCI memory accesses via an ioremap region.  They don't
+ * take an address as such, but a cookie.
+ *
+ * Again, this are defined to perform little endian accesses.  See the
+ * IO port primitives for more information.
+ */
+#ifndef readl
+#define readb_relaxed(c) ({ u8  __r = __raw_readb(c); __r; })
+#define readw_relaxed(c) ({ u16 __r = le16_to_cpu((__force __le16) \
+					__raw_readw(c)); __r; })
+#define readl_relaxed(c) ({ u32 __r = le32_to_cpu((__force __le32) \
+					__raw_readl(c)); __r; })
+
+#define writeb_relaxed(v,c)	__raw_writeb(v,c)
+#define writew_relaxed(v,c)	__raw_writew((__force u16) cpu_to_le16(v),c)
+#define writel_relaxed(v,c)	__raw_writel((__force u32) cpu_to_le32(v),c)
+
+#define readb(c)		({ u8  __v = readb_relaxed(c); __iormb(); __v; })
+#define readw(c)		({ u16 __v = readw_relaxed(c); __iormb(); __v; })
+#define readl(c)		({ u32 __v = readl_relaxed(c); __iormb(); __v; })
+
+#define writeb(v,c)		({ __iowmb(); writeb_relaxed(v,c); })
+#define writew(v,c)		({ __iowmb(); writew_relaxed(v,c); })
+#define writel(v,c)		({ __iowmb(); writel_relaxed(v,c); })
+
+#define readsb(p,d,l)		__raw_readsb(p,d,l)
+#define readsw(p,d,l)		__raw_readsw(p,d,l)
+#define readsl(p,d,l)		__raw_readsl(p,d,l)
+
+#define writesb(p,d,l)		__raw_writesb(p,d,l)
+#define writesw(p,d,l)		__raw_writesw(p,d,l)
+#define writesl(p,d,l)		__raw_writesl(p,d,l)
+
+#define memset_io(c,v,l)	_memset_io(c,(v),(l))
+#define memcpy_fromio(a,c,l)	_memcpy_fromio((a),c,(l))
+#define memcpy_toio(c,a,l)	_memcpy_toio(c,(a),(l))
+
+#endif	/* readl */
+
+/*
+ * ioremap and friends.
+ *
+ * ioremap takes a PCI memory address, as specified in
+ * Documentation/io-mapping.txt.
+ *
+ */
+#define ioremap(cookie,size)		__arm_ioremap((cookie), (size), MT_DEVICE)
+#define ioremap_nocache(cookie,size)	__arm_ioremap((cookie), (size), MT_DEVICE)
+#define ioremap_cache(cookie,size)	__arm_ioremap((cookie), (size), MT_DEVICE_CACHED)
+#define ioremap_wc(cookie,size)		__arm_ioremap((cookie), (size), MT_DEVICE_WC)
+#define iounmap				__arm_iounmap
+
+/*
+ * io{read,write}{16,32}be() macros
+ */
+#define ioread16be(p)		({ __u16 __v = be16_to_cpu((__force __be16)__raw_readw(p)); __iormb(); __v; })
+#define ioread32be(p)		({ __u32 __v = be32_to_cpu((__force __be32)__raw_readl(p)); __iormb(); __v; })
+
+#define iowrite16be(v,p)	({ __iowmb(); __raw_writew((__force __u16)cpu_to_be16(v), p); })
+#define iowrite32be(v,p)	({ __iowmb(); __raw_writel((__force __u32)cpu_to_be32(v), p); })
+
+#ifndef ioport_map
+#define ioport_map ioport_map
+extern void __iomem *ioport_map(unsigned long port, unsigned int nr);
+#endif
+#ifndef ioport_unmap
+#define ioport_unmap ioport_unmap
+extern void ioport_unmap(void __iomem *addr);
+#endif
+
+struct pci_dev;
+
+#define pci_iounmap pci_iounmap
+extern void pci_iounmap(struct pci_dev *dev, void __iomem *addr);
+
+/*
+ * Convert a physical pointer to a virtual kernel pointer for /dev/mem
+ * access
+ */
+#define xlate_dev_mem_ptr(p)	__va(p)
+
+/*
+ * Convert a virtual cached pointer to an uncached pointer
+ */
+#define xlate_dev_kmem_ptr(p)	p
+
+#include <asm-generic/io.h>
+
+/*
+ * can the hardware map this into one segment or not, given no other
+ * constraints.
+ */
+#define BIOVEC_MERGEABLE(vec1, vec2)	\
+	((bvec_to_phys((vec1)) + (vec1)->bv_len) == bvec_to_phys((vec2)))
+
+struct bio_vec;
+extern bool xen_biovec_phys_mergeable(const struct bio_vec *vec1,
+				      const struct bio_vec *vec2);
+#define BIOVEC_PHYS_MERGEABLE(vec1, vec2)				\
+	(__BIOVEC_PHYS_MERGEABLE(vec1, vec2) &&				\
+	 (!xen_domain() || xen_biovec_phys_mergeable(vec1, vec2)))
+
+#ifdef CONFIG_MMU
+#define ARCH_HAS_VALID_PHYS_ADDR_RANGE
+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);
+#endif
+
+/*
+ * Register ISA memory and port locations for glibc iopl/inb/outb
+ * emulation.
+ */
+extern void register_isa_ports(unsigned int mmio, unsigned int io,
+			       unsigned int io_shift);
+
+#endif	/* __KERNEL__ */
+#endif	/* __ASM_ARM_IO_H */
diff --git a/arch/arm/include/asm/irq.h b/arch/arm/include/asm/irq.h
new file mode 100644
index 000000000..53c15dec7
--- /dev/null
+++ b/arch/arm/include/asm/irq.h
@@ -0,0 +1,41 @@
+#ifndef __ASM_ARM_IRQ_H
+#define __ASM_ARM_IRQ_H
+
+#define NR_IRQS_LEGACY	16
+
+#ifndef CONFIG_SPARSE_IRQ
+#include <mach/irqs.h>
+#else
+#define NR_IRQS NR_IRQS_LEGACY
+#endif
+
+#ifndef irq_canonicalize
+#define irq_canonicalize(i)	(i)
+#endif
+
+/*
+ * Use this value to indicate lack of interrupt
+ * capability
+ */
+#ifndef NO_IRQ
+#define NO_IRQ	((unsigned int)(-1))
+#endif
+
+#ifndef __ASSEMBLY__
+struct irqaction;
+struct pt_regs;
+extern void migrate_irqs(void);
+
+extern void asm_do_IRQ(unsigned int, struct pt_regs *);
+void handle_IRQ(unsigned int, struct pt_regs *);
+void init_IRQ(void);
+
+#ifdef CONFIG_MULTI_IRQ_HANDLER
+extern void (*handle_arch_irq)(struct pt_regs *);
+extern void set_handle_irq(void (*handle_irq)(struct pt_regs *));
+#endif
+
+#endif
+
+#endif
+
diff --git a/arch/arm/include/asm/irq_work.h b/arch/arm/include/asm/irq_work.h
new file mode 100644
index 000000000..712d03e59
--- /dev/null
+++ b/arch/arm/include/asm/irq_work.h
@@ -0,0 +1,11 @@
+#ifndef __ASM_ARM_IRQ_WORK_H
+#define __ASM_ARM_IRQ_WORK_H
+
+#include <asm/smp_plat.h>
+
+static inline bool arch_irq_work_has_interrupt(void)
+{
+	return is_smp();
+}
+
+#endif /* _ASM_ARM_IRQ_WORK_H */
diff --git a/arch/arm/include/asm/irqflags.h b/arch/arm/include/asm/irqflags.h
new file mode 100644
index 000000000..3b763d665
--- /dev/null
+++ b/arch/arm/include/asm/irqflags.h
@@ -0,0 +1,165 @@
+#ifndef __ASM_ARM_IRQFLAGS_H
+#define __ASM_ARM_IRQFLAGS_H
+
+#ifdef __KERNEL__
+
+#include <asm/ptrace.h>
+
+/*
+ * CPU interrupt mask handling.
+ */
+#ifdef CONFIG_CPU_V7M
+#define IRQMASK_REG_NAME_R "primask"
+#define IRQMASK_REG_NAME_W "primask"
+#define IRQMASK_I_BIT	1
+#else
+#define IRQMASK_REG_NAME_R "cpsr"
+#define IRQMASK_REG_NAME_W "cpsr_c"
+#define IRQMASK_I_BIT	PSR_I_BIT
+#endif
+
+#if __LINUX_ARM_ARCH__ >= 6
+
+static inline unsigned long arch_local_irq_save(void)
+{
+	unsigned long flags;
+
+	asm volatile(
+		"	mrs	%0, " IRQMASK_REG_NAME_R "	@ arch_local_irq_save\n"
+		"	cpsid	i"
+		: "=r" (flags) : : "memory", "cc");
+	return flags;
+}
+
+static inline void arch_local_irq_enable(void)
+{
+	asm volatile(
+		"	cpsie i			@ arch_local_irq_enable"
+		:
+		:
+		: "memory", "cc");
+}
+
+static inline void arch_local_irq_disable(void)
+{
+	asm volatile(
+		"	cpsid i			@ arch_local_irq_disable"
+		:
+		:
+		: "memory", "cc");
+}
+
+#define local_fiq_enable()  __asm__("cpsie f	@ __stf" : : : "memory", "cc")
+#define local_fiq_disable() __asm__("cpsid f	@ __clf" : : : "memory", "cc")
+#else
+
+/*
+ * Save the current interrupt enable state & disable IRQs
+ */
+static inline unsigned long arch_local_irq_save(void)
+{
+	unsigned long flags, temp;
+
+	asm volatile(
+		"	mrs	%0, cpsr	@ arch_local_irq_save\n"
+		"	orr	%1, %0, #128\n"
+		"	msr	cpsr_c, %1"
+		: "=r" (flags), "=r" (temp)
+		:
+		: "memory", "cc");
+	return flags;
+}
+
+/*
+ * Enable IRQs
+ */
+static inline void arch_local_irq_enable(void)
+{
+	unsigned long temp;
+	asm volatile(
+		"	mrs	%0, cpsr	@ arch_local_irq_enable\n"
+		"	bic	%0, %0, #128\n"
+		"	msr	cpsr_c, %0"
+		: "=r" (temp)
+		:
+		: "memory", "cc");
+}
+
+/*
+ * Disable IRQs
+ */
+static inline void arch_local_irq_disable(void)
+{
+	unsigned long temp;
+	asm volatile(
+		"	mrs	%0, cpsr	@ arch_local_irq_disable\n"
+		"	orr	%0, %0, #128\n"
+		"	msr	cpsr_c, %0"
+		: "=r" (temp)
+		:
+		: "memory", "cc");
+}
+
+/*
+ * Enable FIQs
+ */
+#define local_fiq_enable()					\
+	({							\
+		unsigned long temp;				\
+	__asm__ __volatile__(					\
+	"mrs	%0, cpsr		@ stf\n"		\
+"	bic	%0, %0, #64\n"					\
+"	msr	cpsr_c, %0"					\
+	: "=r" (temp)						\
+	:							\
+	: "memory", "cc");					\
+	})
+
+/*
+ * Disable FIQs
+ */
+#define local_fiq_disable()					\
+	({							\
+		unsigned long temp;				\
+	__asm__ __volatile__(					\
+	"mrs	%0, cpsr		@ clf\n"		\
+"	orr	%0, %0, #64\n"					\
+"	msr	cpsr_c, %0"					\
+	: "=r" (temp)						\
+	:							\
+	: "memory", "cc");					\
+	})
+
+#endif
+
+/*
+ * Save the current interrupt enable state.
+ */
+static inline unsigned long arch_local_save_flags(void)
+{
+	unsigned long flags;
+	asm volatile(
+		"	mrs	%0, " IRQMASK_REG_NAME_R "	@ local_save_flags"
+		: "=r" (flags) : : "memory", "cc");
+	return flags;
+}
+
+/*
+ * restore saved IRQ & FIQ state
+ */
+static inline void arch_local_irq_restore(unsigned long flags)
+{
+	asm volatile(
+		"	msr	" IRQMASK_REG_NAME_W ", %0	@ local_irq_restore"
+		:
+		: "r" (flags)
+		: "memory", "cc");
+}
+
+static inline int arch_irqs_disabled_flags(unsigned long flags)
+{
+	return flags & IRQMASK_I_BIT;
+}
+
+#endif /* ifdef __KERNEL__ */
+#endif /* ifndef __ASM_ARM_IRQFLAGS_H */
diff --git a/arch/arm/include/asm/jump_label.h b/arch/arm/include/asm/jump_label.h
new file mode 100644
index 000000000..5f337dc5c
--- /dev/null
+++ b/arch/arm/include/asm/jump_label.h
@@ -0,0 +1,39 @@
+#ifndef _ASM_ARM_JUMP_LABEL_H
+#define _ASM_ARM_JUMP_LABEL_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/types.h>
+
+#define JUMP_LABEL_NOP_SIZE 4
+
+#ifdef CONFIG_THUMB2_KERNEL
+#define JUMP_LABEL_NOP	"nop.w"
+#else
+#define JUMP_LABEL_NOP	"nop"
+#endif
+
+static __always_inline bool arch_static_branch(struct static_key *key)
+{
+	asm_volatile_goto("1:\n\t"
+		 JUMP_LABEL_NOP "\n\t"
+		 ".pushsection __jump_table,  \"aw\"\n\t"
+		 ".word 1b, %l[l_yes], %c0\n\t"
+		 ".popsection\n\t"
+		 : :  "i" (key) :  : l_yes);
+
+	return false;
+l_yes:
+	return true;
+}
+
+typedef u32 jump_label_t;
+
+struct jump_entry {
+	jump_label_t code;
+	jump_label_t target;
+	jump_label_t key;
+};
+
+#endif  /* __ASSEMBLY__ */
+#endif
diff --git a/arch/arm/include/asm/kexec.h b/arch/arm/include/asm/kexec.h
new file mode 100644
index 000000000..c2b9b4bde
--- /dev/null
+++ b/arch/arm/include/asm/kexec.h
@@ -0,0 +1,60 @@
+#ifndef _ARM_KEXEC_H
+#define _ARM_KEXEC_H
+
+#ifdef CONFIG_KEXEC
+
+/* Maximum physical address we can use pages from */
+#define KEXEC_SOURCE_MEMORY_LIMIT (-1UL)
+/* Maximum address we can reach in physical address mode */
+#define KEXEC_DESTINATION_MEMORY_LIMIT (-1UL)
+/* Maximum address we can use for the control code buffer */
+#define KEXEC_CONTROL_MEMORY_LIMIT (-1UL)
+
+#define KEXEC_CONTROL_PAGE_SIZE	4096
+
+#define KEXEC_ARCH KEXEC_ARCH_ARM
+
+#define KEXEC_ARM_ATAGS_OFFSET  0x1000
+#define KEXEC_ARM_ZIMAGE_OFFSET 0x8000
+
+#ifndef __ASSEMBLY__
+
+/**
+ * crash_setup_regs() - save registers for the panic kernel
+ * @newregs: registers are saved here
+ * @oldregs: registers to be saved (may be %NULL)
+ *
+ * Function copies machine registers from @oldregs to @newregs. If @oldregs is
+ * %NULL then current registers are stored there.
+ */
+static inline void crash_setup_regs(struct pt_regs *newregs,
+				    struct pt_regs *oldregs)
+{
+	if (oldregs) {
+		memcpy(newregs, oldregs, sizeof(*newregs));
+	} else {
+		__asm__ __volatile__ (
+			"stmia	%[regs_base], {r0-r12}\n\t"
+			"mov	%[_ARM_sp], sp\n\t"
+			"str	lr, %[_ARM_lr]\n\t"
+			"adr	%[_ARM_pc], 1f\n\t"
+			"mrs	%[_ARM_cpsr], cpsr\n\t"
+		"1:"
+			: [_ARM_pc] "=r" (newregs->ARM_pc),
+			  [_ARM_cpsr] "=r" (newregs->ARM_cpsr),
+			  [_ARM_sp] "=r" (newregs->ARM_sp),
+			  [_ARM_lr] "=o" (newregs->ARM_lr)
+			: [regs_base] "r" (&newregs->ARM_r0)
+			: "memory"
+		);
+	}
+}
+
+/* Function pointer to optional machine-specific reinitialization */
+extern void (*kexec_reinit)(void);
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* CONFIG_KEXEC */
+
+#endif /* _ARM_KEXEC_H */
diff --git a/arch/arm/include/asm/kgdb.h b/arch/arm/include/asm/kgdb.h
new file mode 100644
index 000000000..0a9d5dd93
--- /dev/null
+++ b/arch/arm/include/asm/kgdb.h
@@ -0,0 +1,106 @@
+/*
+ * ARM KGDB support
+ *
+ * Author: Deepak Saxena <dsaxena@mvista.com>
+ *
+ * Copyright (C) 2002 MontaVista Software Inc.
+ *
+ */
+
+#ifndef __ARM_KGDB_H__
+#define __ARM_KGDB_H__
+
+#include <linux/ptrace.h>
+#include <asm/opcodes.h>
+
+/*
+ * GDB assumes that we're a user process being debugged, so
+ * it will send us an SWI command to write into memory as the
+ * debug trap. When an SWI occurs, the next instruction addr is
+ * placed into R14_svc before jumping to the vector trap.
+ * This doesn't work for kernel debugging as we are already in SVC
+ * we would loose the kernel's LR, which is a bad thing. This
+ * is  bad thing.
+ *
+ * By doing this as an undefined instruction trap, we force a mode
+ * switch from SVC to UND mode, allowing us to save full kernel state.
+ *
+ * We also define a KGDB_COMPILED_BREAK which can be used to compile
+ * in breakpoints. This is important for things like sysrq-G and for
+ * the initial breakpoint from trap_init().
+ *
+ * Note to ARM HW designers: Add real trap support like SH && PPC to
+ * make our lives much much simpler. :)
+ */
+#define BREAK_INSTR_SIZE	4
+#define GDB_BREAKINST		0xef9f0001
+#define KGDB_BREAKINST		0xe7ffdefe
+#define KGDB_COMPILED_BREAK	0xe7ffdeff
+#define CACHE_FLUSH_IS_SAFE	1
+
+#ifndef	__ASSEMBLY__
+
+static inline void arch_kgdb_breakpoint(void)
+{
+	asm(__inst_arm(0xe7ffdeff));
+}
+
+extern void kgdb_handle_bus_error(void);
+extern int kgdb_fault_expected;
+
+#endif /* !__ASSEMBLY__ */
+
+/*
+ * From Kevin Hilman:
+ *
+ * gdb is expecting the following registers layout.
+ *
+ * r0-r15: 1 long word each
+ * f0-f7:  unused, 3 long words each !!
+ * fps:    unused, 1 long word
+ * cpsr:   1 long word
+ *
+ * Even though f0-f7 and fps are not used, they need to be
+ * present in the registers sent for correct processing in
+ * the host-side gdb.
+ *
+ * In particular, it is crucial that CPSR is in the right place,
+ * otherwise gdb will not be able to correctly interpret stepping over
+ * conditional branches.
+ */
+#define _GP_REGS		16
+#define _FP_REGS		8
+#define _EXTRA_REGS		2
+#define GDB_MAX_REGS		(_GP_REGS + (_FP_REGS * 3) + _EXTRA_REGS)
+#define DBG_MAX_REG_NUM		(_GP_REGS + _FP_REGS + _EXTRA_REGS)
+
+#define KGDB_MAX_NO_CPUS	1
+#define BUFMAX			400
+#define NUMREGBYTES		(DBG_MAX_REG_NUM << 2)
+#define NUMCRITREGBYTES		(32 << 2)
+
+#define _R0			0
+#define _R1			1
+#define _R2			2
+#define _R3			3
+#define _R4			4
+#define _R5			5
+#define _R6			6
+#define _R7			7
+#define _R8			8
+#define _R9			9
+#define _R10			10
+#define _FP			11
+#define _IP			12
+#define _SPT			13
+#define _LR			14
+#define _PC			15
+#define _CPSR			(GDB_MAX_REGS - 1)
+
+/*
+ * So that we can denote the end of a frame for tracing,
+ * in the simple case:
+ */
+#define CFI_END_FRAME(func)	__CFI_END_FRAME(_PC, _SPT, func)
+
+#endif /* __ASM_KGDB_H__ */
diff --git a/arch/arm/include/asm/kmap_types.h b/arch/arm/include/asm/kmap_types.h
new file mode 100644
index 000000000..83eb2f772
--- /dev/null
+++ b/arch/arm/include/asm/kmap_types.h
@@ -0,0 +1,9 @@
+#ifndef __ARM_KMAP_TYPES_H
+#define __ARM_KMAP_TYPES_H
+
+/*
+ * This is the "bare minimum".  AIO seems to require this.
+ */
+#define KM_TYPE_NR 16
+
+#endif
diff --git a/arch/arm/include/asm/kprobes.h b/arch/arm/include/asm/kprobes.h
new file mode 100644
index 000000000..3ea9be559
--- /dev/null
+++ b/arch/arm/include/asm/kprobes.h
@@ -0,0 +1,86 @@
+/*
+ * arch/arm/include/asm/kprobes.h
+ *
+ * Copyright (C) 2006, 2007 Motorola Inc.
+ *
+ * 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.
+ */
+
+#ifndef _ARM_KPROBES_H
+#define _ARM_KPROBES_H
+
+#include <linux/types.h>
+#include <linux/ptrace.h>
+#include <linux/notifier.h>
+
+#define __ARCH_WANT_KPROBES_INSN_SLOT
+#define MAX_INSN_SIZE			2
+
+#define flush_insn_slot(p)		do { } while (0)
+#define kretprobe_blacklist_size	0
+
+typedef u32 kprobe_opcode_t;
+struct kprobe;
+#include <asm/probes.h>
+
+#define	arch_specific_insn	arch_probes_insn
+
+struct prev_kprobe {
+	struct kprobe *kp;
+	unsigned int status;
+};
+
+/* per-cpu kprobe control block */
+struct kprobe_ctlblk {
+	unsigned int kprobe_status;
+	struct prev_kprobe prev_kprobe;
+	struct pt_regs jprobe_saved_regs;
+	char jprobes_stack[MAX_STACK_SIZE];
+};
+
+void arch_remove_kprobe(struct kprobe *);
+int kprobe_fault_handler(struct pt_regs *regs, unsigned int fsr);
+int kprobe_exceptions_notify(struct notifier_block *self,
+			     unsigned long val, void *data);
+
+/* optinsn template addresses */
+extern __visible kprobe_opcode_t optprobe_template_entry;
+extern __visible kprobe_opcode_t optprobe_template_val;
+extern __visible kprobe_opcode_t optprobe_template_call;
+extern __visible kprobe_opcode_t optprobe_template_end;
+extern __visible kprobe_opcode_t optprobe_template_sub_sp;
+extern __visible kprobe_opcode_t optprobe_template_add_sp;
+extern __visible kprobe_opcode_t optprobe_template_restore_begin;
+extern __visible kprobe_opcode_t optprobe_template_restore_orig_insn;
+extern __visible kprobe_opcode_t optprobe_template_restore_end;
+
+#define MAX_OPTIMIZED_LENGTH	4
+#define MAX_OPTINSN_SIZE				\
+	((unsigned long)&optprobe_template_end -	\
+	 (unsigned long)&optprobe_template_entry)
+#define RELATIVEJUMP_SIZE	4
+
+struct arch_optimized_insn {
+	/*
+	 * copy of the original instructions.
+	 * Different from x86, ARM kprobe_opcode_t is u32.
+	 */
+#define MAX_COPIED_INSN	DIV_ROUND_UP(RELATIVEJUMP_SIZE, sizeof(kprobe_opcode_t))
+	kprobe_opcode_t copied_insn[MAX_COPIED_INSN];
+	/* detour code buffer */
+	kprobe_opcode_t *insn;
+	/*
+	 * We always copy one instruction on ARM,
+	 * so size will always be 4, and unlike x86, there is no
+	 * need for a size field.
+	 */
+};
+
+#endif /* _ARM_KPROBES_H */
diff --git a/arch/arm/include/asm/kvm_arm.h b/arch/arm/include/asm/kvm_arm.h
new file mode 100644
index 000000000..d995821f1
--- /dev/null
+++ b/arch/arm/include/asm/kvm_arm.h
@@ -0,0 +1,221 @@
+/*
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Author: Christoffer Dall <c.dall@virtualopensystems.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ */
+
+#ifndef __ARM_KVM_ARM_H__
+#define __ARM_KVM_ARM_H__
+
+#include <linux/types.h>
+
+/* Hyp Configuration Register (HCR) bits */
+#define HCR_TGE		(1 << 27)
+#define HCR_TVM		(1 << 26)
+#define HCR_TTLB	(1 << 25)
+#define HCR_TPU		(1 << 24)
+#define HCR_TPC		(1 << 23)
+#define HCR_TSW		(1 << 22)
+#define HCR_TAC		(1 << 21)
+#define HCR_TIDCP	(1 << 20)
+#define HCR_TSC		(1 << 19)
+#define HCR_TID3	(1 << 18)
+#define HCR_TID2	(1 << 17)
+#define HCR_TID1	(1 << 16)
+#define HCR_TID0	(1 << 15)
+#define HCR_TWE		(1 << 14)
+#define HCR_TWI		(1 << 13)
+#define HCR_DC		(1 << 12)
+#define HCR_BSU		(3 << 10)
+#define HCR_BSU_IS	(1 << 10)
+#define HCR_FB		(1 << 9)
+#define HCR_VA		(1 << 8)
+#define HCR_VI		(1 << 7)
+#define HCR_VF		(1 << 6)
+#define HCR_AMO		(1 << 5)
+#define HCR_IMO		(1 << 4)
+#define HCR_FMO		(1 << 3)
+#define HCR_PTW		(1 << 2)
+#define HCR_SWIO	(1 << 1)
+#define HCR_VM		1
+
+/*
+ * The bits we set in HCR:
+ * TAC:		Trap ACTLR
+ * TSC:		Trap SMC
+ * TVM:		Trap VM ops (until MMU and caches are on)
+ * TSW:		Trap cache operations by set/way
+ * TWI:		Trap WFI
+ * TWE:		Trap WFE
+ * TIDCP:	Trap L2CTLR/L2ECTLR
+ * BSU_IS:	Upgrade barriers to the inner shareable domain
+ * FB:		Force broadcast of all maintainance operations
+ * AMO:		Override CPSR.A and enable signaling with VA
+ * IMO:		Override CPSR.I and enable signaling with VI
+ * FMO:		Override CPSR.F and enable signaling with VF
+ * SWIO:	Turn set/way invalidates into set/way clean+invalidate
+ */
+#define HCR_GUEST_MASK (HCR_TSC | HCR_TSW | HCR_TWI | HCR_VM | HCR_BSU_IS | \
+			HCR_FB | HCR_TAC | HCR_AMO | HCR_IMO | HCR_FMO | \
+			HCR_TVM | HCR_TWE | HCR_SWIO | HCR_TIDCP)
+
+/* System Control Register (SCTLR) bits */
+#define SCTLR_TE	(1 << 30)
+#define SCTLR_EE	(1 << 25)
+#define SCTLR_V		(1 << 13)
+
+/* Hyp System Control Register (HSCTLR) bits */
+#define HSCTLR_TE	(1 << 30)
+#define HSCTLR_EE	(1 << 25)
+#define HSCTLR_FI	(1 << 21)
+#define HSCTLR_WXN	(1 << 19)
+#define HSCTLR_I	(1 << 12)
+#define HSCTLR_C	(1 << 2)
+#define HSCTLR_A	(1 << 1)
+#define HSCTLR_M	1
+#define HSCTLR_MASK	(HSCTLR_M | HSCTLR_A | HSCTLR_C | HSCTLR_I | \
+			 HSCTLR_WXN | HSCTLR_FI | HSCTLR_EE | HSCTLR_TE)
+
+/* TTBCR and HTCR Registers bits */
+#define TTBCR_EAE	(1 << 31)
+#define TTBCR_IMP	(1 << 30)
+#define TTBCR_SH1	(3 << 28)
+#define TTBCR_ORGN1	(3 << 26)
+#define TTBCR_IRGN1	(3 << 24)
+#define TTBCR_EPD1	(1 << 23)
+#define TTBCR_A1	(1 << 22)
+#define TTBCR_T1SZ	(7 << 16)
+#define TTBCR_SH0	(3 << 12)
+#define TTBCR_ORGN0	(3 << 10)
+#define TTBCR_IRGN0	(3 << 8)
+#define TTBCR_EPD0	(1 << 7)
+#define TTBCR_T0SZ	(7 << 0)
+#define HTCR_MASK	(TTBCR_T0SZ | TTBCR_IRGN0 | TTBCR_ORGN0 | TTBCR_SH0)
+
+/* Hyp System Trap Register */
+#define HSTR_T(x)	(1 << x)
+#define HSTR_TTEE	(1 << 16)
+#define HSTR_TJDBX	(1 << 17)
+
+/* Hyp Coprocessor Trap Register */
+#define HCPTR_TCP(x)	(1 << x)
+#define HCPTR_TCP_MASK	(0x3fff)
+#define HCPTR_TASE	(1 << 15)
+#define HCPTR_TTA	(1 << 20)
+#define HCPTR_TCPAC	(1 << 31)
+
+/* Hyp Debug Configuration Register bits */
+#define HDCR_TDRA	(1 << 11)
+#define HDCR_TDOSA	(1 << 10)
+#define HDCR_TDA	(1 << 9)
+#define HDCR_TDE	(1 << 8)
+#define HDCR_HPME	(1 << 7)
+#define HDCR_TPM	(1 << 6)
+#define HDCR_TPMCR	(1 << 5)
+#define HDCR_HPMN_MASK	(0x1F)
+
+/*
+ * The architecture supports 40-bit IPA as input to the 2nd stage translations
+ * and PTRS_PER_S2_PGD becomes 1024, because each entry covers 1GB of address
+ * space.
+ */
+#define KVM_PHYS_SHIFT	(40)
+#define KVM_PHYS_SIZE	(1ULL << KVM_PHYS_SHIFT)
+#define KVM_PHYS_MASK	(KVM_PHYS_SIZE - 1ULL)
+#define PTRS_PER_S2_PGD	(1ULL << (KVM_PHYS_SHIFT - 30))
+#define S2_PGD_ORDER	get_order(PTRS_PER_S2_PGD * sizeof(pgd_t))
+
+/* Virtualization Translation Control Register (VTCR) bits */
+#define VTCR_SH0	(3 << 12)
+#define VTCR_ORGN0	(3 << 10)
+#define VTCR_IRGN0	(3 << 8)
+#define VTCR_SL0	(3 << 6)
+#define VTCR_S		(1 << 4)
+#define VTCR_T0SZ	(0xf)
+#define VTCR_MASK	(VTCR_SH0 | VTCR_ORGN0 | VTCR_IRGN0 | VTCR_SL0 | \
+			 VTCR_S | VTCR_T0SZ)
+#define VTCR_HTCR_SH	(VTCR_SH0 | VTCR_ORGN0 | VTCR_IRGN0)
+#define VTCR_SL_L2	(0 << 6)	/* Starting-level: 2 */
+#define VTCR_SL_L1	(1 << 6)	/* Starting-level: 1 */
+#define KVM_VTCR_SL0	VTCR_SL_L1
+/* stage-2 input address range defined as 2^(32-T0SZ) */
+#define KVM_T0SZ	(32 - KVM_PHYS_SHIFT)
+#define KVM_VTCR_T0SZ	(KVM_T0SZ & VTCR_T0SZ)
+#define KVM_VTCR_S	((KVM_VTCR_T0SZ << 1) & VTCR_S)
+
+/* Virtualization Translation Table Base Register (VTTBR) bits */
+#if KVM_VTCR_SL0 == VTCR_SL_L2	/* see ARM DDI 0406C: B4-1720 */
+#define VTTBR_X		(14 - KVM_T0SZ)
+#else
+#define VTTBR_X		(5 - KVM_T0SZ)
+#endif
+#define VTTBR_BADDR_SHIFT (VTTBR_X - 1)
+#define VTTBR_BADDR_MASK  (((1LLU << (40 - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT)
+#define VTTBR_VMID_SHIFT  (48LLU)
+#define VTTBR_VMID_MASK	  (0xffLLU << VTTBR_VMID_SHIFT)
+
+/* Hyp Syndrome Register (HSR) bits */
+#define HSR_EC_SHIFT	(26)
+#define HSR_EC		(0x3fU << HSR_EC_SHIFT)
+#define HSR_IL		(1U << 25)
+#define HSR_ISS		(HSR_IL - 1)
+#define HSR_ISV_SHIFT	(24)
+#define HSR_ISV		(1U << HSR_ISV_SHIFT)
+#define HSR_SRT_SHIFT	(16)
+#define HSR_SRT_MASK	(0xf << HSR_SRT_SHIFT)
+#define HSR_FSC		(0x3f)
+#define HSR_FSC_TYPE	(0x3c)
+#define HSR_SSE		(1 << 21)
+#define HSR_WNR		(1 << 6)
+#define HSR_CV_SHIFT	(24)
+#define HSR_CV		(1U << HSR_CV_SHIFT)
+#define HSR_COND_SHIFT	(20)
+#define HSR_COND	(0xfU << HSR_COND_SHIFT)
+
+#define FSC_FAULT	(0x04)
+#define FSC_ACCESS	(0x08)
+#define FSC_PERM	(0x0c)
+
+/* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */
+#define HPFAR_MASK	(~0xf)
+
+#define HSR_EC_UNKNOWN	(0x00)
+#define HSR_EC_WFI	(0x01)
+#define HSR_EC_CP15_32	(0x03)
+#define HSR_EC_CP15_64	(0x04)
+#define HSR_EC_CP14_MR	(0x05)
+#define HSR_EC_CP14_LS	(0x06)
+#define HSR_EC_CP_0_13	(0x07)
+#define HSR_EC_CP10_ID	(0x08)
+#define HSR_EC_JAZELLE	(0x09)
+#define HSR_EC_BXJ	(0x0A)
+#define HSR_EC_CP14_64	(0x0C)
+#define HSR_EC_SVC_HYP	(0x11)
+#define HSR_EC_HVC	(0x12)
+#define HSR_EC_SMC	(0x13)
+#define HSR_EC_IABT	(0x20)
+#define HSR_EC_IABT_HYP	(0x21)
+#define HSR_EC_DABT	(0x24)
+#define HSR_EC_DABT_HYP	(0x25)
+
+#define HSR_WFI_IS_WFE		(1U << 0)
+
+#define HSR_HVC_IMM_MASK	((1UL << 16) - 1)
+
+#define HSR_DABT_S1PTW		(1U << 7)
+#define HSR_DABT_CM		(1U << 8)
+#define HSR_DABT_EA		(1U << 9)
+
+#endif /* __ARM_KVM_ARM_H__ */
diff --git a/arch/arm/include/asm/kvm_asm.h b/arch/arm/include/asm/kvm_asm.h
new file mode 100644
index 000000000..25410b2d8
--- /dev/null
+++ b/arch/arm/include/asm/kvm_asm.h
@@ -0,0 +1,104 @@
+/*
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Author: Christoffer Dall <c.dall@virtualopensystems.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ */
+
+#ifndef __ARM_KVM_ASM_H__
+#define __ARM_KVM_ASM_H__
+
+/* 0 is reserved as an invalid value. */
+#define c0_MPIDR	1	/* MultiProcessor ID Register */
+#define c0_CSSELR	2	/* Cache Size Selection Register */
+#define c1_SCTLR	3	/* System Control Register */
+#define c1_ACTLR	4	/* Auxilliary Control Register */
+#define c1_CPACR	5	/* Coprocessor Access Control */
+#define c2_TTBR0	6	/* Translation Table Base Register 0 */
+#define c2_TTBR0_high	7	/* TTBR0 top 32 bits */
+#define c2_TTBR1	8	/* Translation Table Base Register 1 */
+#define c2_TTBR1_high	9	/* TTBR1 top 32 bits */
+#define c2_TTBCR	10	/* Translation Table Base Control R. */
+#define c3_DACR		11	/* Domain Access Control Register */
+#define c5_DFSR		12	/* Data Fault Status Register */
+#define c5_IFSR		13	/* Instruction Fault Status Register */
+#define c5_ADFSR	14	/* Auxilary Data Fault Status R */
+#define c5_AIFSR	15	/* Auxilary Instrunction Fault Status R */
+#define c6_DFAR		16	/* Data Fault Address Register */
+#define c6_IFAR		17	/* Instruction Fault Address Register */
+#define c7_PAR		18	/* Physical Address Register */
+#define c7_PAR_high	19	/* PAR top 32 bits */
+#define c9_L2CTLR	20	/* Cortex A15/A7 L2 Control Register */
+#define c10_PRRR	21	/* Primary Region Remap Register */
+#define c10_NMRR	22	/* Normal Memory Remap Register */
+#define c12_VBAR	23	/* Vector Base Address Register */
+#define c13_CID		24	/* Context ID Register */
+#define c13_TID_URW	25	/* Thread ID, User R/W */
+#define c13_TID_URO	26	/* Thread ID, User R/O */
+#define c13_TID_PRIV	27	/* Thread ID, Privileged */
+#define c14_CNTKCTL	28	/* Timer Control Register (PL1) */
+#define c10_AMAIR0	29	/* Auxilary Memory Attribute Indirection Reg0 */
+#define c10_AMAIR1	30	/* Auxilary Memory Attribute Indirection Reg1 */
+#define NR_CP15_REGS	31	/* Number of regs (incl. invalid) */
+
+#define ARM_EXCEPTION_RESET	  0
+#define ARM_EXCEPTION_UNDEFINED   1
+#define ARM_EXCEPTION_SOFTWARE    2
+#define ARM_EXCEPTION_PREF_ABORT  3
+#define ARM_EXCEPTION_DATA_ABORT  4
+#define ARM_EXCEPTION_IRQ	  5
+#define ARM_EXCEPTION_FIQ	  6
+#define ARM_EXCEPTION_HVC	  7
+
+/*
+ * The rr_lo_hi macro swaps a pair of registers depending on
+ * current endianness. It is used in conjunction with ldrd and strd
+ * instructions that load/store a 64-bit value from/to memory to/from
+ * a pair of registers which are used with the mrrc and mcrr instructions.
+ * If used with the ldrd/strd instructions, the a1 parameter is the first
+ * source/destination register and the a2 parameter is the second
+ * source/destination register. Note that the ldrd/strd instructions
+ * already swap the bytes within the words correctly according to the
+ * endianness setting, but the order of the registers need to be effectively
+ * swapped when used with the mrrc/mcrr instructions.
+ */
+#ifdef CONFIG_CPU_ENDIAN_BE8
+#define rr_lo_hi(a1, a2) a2, a1
+#else
+#define rr_lo_hi(a1, a2) a1, a2
+#endif
+
+#ifndef __ASSEMBLY__
+struct kvm;
+struct kvm_vcpu;
+
+extern char __kvm_hyp_init[];
+extern char __kvm_hyp_init_end[];
+
+extern char __kvm_hyp_exit[];
+extern char __kvm_hyp_exit_end[];
+
+extern char __kvm_hyp_vector[];
+
+extern char __kvm_hyp_code_start[];
+extern char __kvm_hyp_code_end[];
+
+extern void __kvm_flush_vm_context(void);
+extern void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa);
+extern void __kvm_tlb_flush_vmid(struct kvm *kvm);
+
+extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
+#endif
+
+#endif /* __ARM_KVM_ASM_H__ */
diff --git a/arch/arm/include/asm/kvm_coproc.h b/arch/arm/include/asm/kvm_coproc.h
new file mode 100644
index 000000000..4917c2f7e
--- /dev/null
+++ b/arch/arm/include/asm/kvm_coproc.h
@@ -0,0 +1,47 @@
+/*
+ * Copyright (C) 2012 Rusty Russell IBM Corporation
+ *
+ * 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, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ */
+
+#ifndef __ARM_KVM_COPROC_H__
+#define __ARM_KVM_COPROC_H__
+#include <linux/kvm_host.h>
+
+void kvm_reset_coprocs(struct kvm_vcpu *vcpu);
+
+struct kvm_coproc_target_table {
+	unsigned target;
+	const struct coproc_reg *table;
+	size_t num;
+};
+void kvm_register_target_coproc_table(struct kvm_coproc_target_table *table);
+
+int kvm_handle_cp10_id(struct kvm_vcpu *vcpu, struct kvm_run *run);
+int kvm_handle_cp_0_13_access(struct kvm_vcpu *vcpu, struct kvm_run *run);
+int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu, struct kvm_run *run);
+int kvm_handle_cp14_access(struct kvm_vcpu *vcpu, struct kvm_run *run);
+int kvm_handle_cp15_32(struct kvm_vcpu *vcpu, struct kvm_run *run);
+int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run);
+
+unsigned long kvm_arm_num_guest_msrs(struct kvm_vcpu *vcpu);
+int kvm_arm_copy_msrindices(struct kvm_vcpu *vcpu, u64 __user *uindices);
+void kvm_coproc_table_init(void);
+
+struct kvm_one_reg;
+int kvm_arm_copy_coproc_indices(struct kvm_vcpu *vcpu, u64 __user *uindices);
+int kvm_arm_coproc_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *);
+int kvm_arm_coproc_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *);
+unsigned long kvm_arm_num_coproc_regs(struct kvm_vcpu *vcpu);
+#endif /* __ARM_KVM_COPROC_H__ */
diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h
new file mode 100644
index 000000000..a9c80a2ea
--- /dev/null
+++ b/arch/arm/include/asm/kvm_emulate.h
@@ -0,0 +1,246 @@
+/*
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Author: Christoffer Dall <c.dall@virtualopensystems.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ */
+
+#ifndef __ARM_KVM_EMULATE_H__
+#define __ARM_KVM_EMULATE_H__
+
+#include <linux/kvm_host.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_mmio.h>
+#include <asm/kvm_arm.h>
+#include <asm/cputype.h>
+
+unsigned long *vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num);
+unsigned long *vcpu_spsr(struct kvm_vcpu *vcpu);
+
+bool kvm_condition_valid(struct kvm_vcpu *vcpu);
+void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr);
+void kvm_inject_undefined(struct kvm_vcpu *vcpu);
+void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr);
+void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr);
+
+static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.hcr = HCR_GUEST_MASK;
+}
+
+static inline unsigned long vcpu_get_hcr(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.hcr;
+}
+
+static inline void vcpu_set_hcr(struct kvm_vcpu *vcpu, unsigned long hcr)
+{
+	vcpu->arch.hcr = hcr;
+}
+
+static inline bool vcpu_mode_is_32bit(struct kvm_vcpu *vcpu)
+{
+	return 1;
+}
+
+static inline unsigned long *vcpu_pc(struct kvm_vcpu *vcpu)
+{
+	return &vcpu->arch.regs.usr_regs.ARM_pc;
+}
+
+static inline unsigned long *vcpu_cpsr(struct kvm_vcpu *vcpu)
+{
+	return &vcpu->arch.regs.usr_regs.ARM_cpsr;
+}
+
+static inline void vcpu_set_thumb(struct kvm_vcpu *vcpu)
+{
+	*vcpu_cpsr(vcpu) |= PSR_T_BIT;
+}
+
+static inline bool mode_has_spsr(struct kvm_vcpu *vcpu)
+{
+	unsigned long cpsr_mode = vcpu->arch.regs.usr_regs.ARM_cpsr & MODE_MASK;
+	return (cpsr_mode > USR_MODE && cpsr_mode < SYSTEM_MODE);
+}
+
+static inline bool vcpu_mode_priv(struct kvm_vcpu *vcpu)
+{
+	unsigned long cpsr_mode = vcpu->arch.regs.usr_regs.ARM_cpsr & MODE_MASK;
+	return cpsr_mode > USR_MODE;;
+}
+
+static inline u32 kvm_vcpu_get_hsr(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.fault.hsr;
+}
+
+static inline unsigned long kvm_vcpu_get_hfar(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.fault.hxfar;
+}
+
+static inline phys_addr_t kvm_vcpu_get_fault_ipa(struct kvm_vcpu *vcpu)
+{
+	return ((phys_addr_t)vcpu->arch.fault.hpfar & HPFAR_MASK) << 8;
+}
+
+static inline unsigned long kvm_vcpu_get_hyp_pc(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.fault.hyp_pc;
+}
+
+static inline bool kvm_vcpu_dabt_isvalid(struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_get_hsr(vcpu) & HSR_ISV;
+}
+
+static inline bool kvm_vcpu_dabt_iswrite(struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_get_hsr(vcpu) & HSR_WNR;
+}
+
+static inline bool kvm_vcpu_dabt_issext(struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_get_hsr(vcpu) & HSR_SSE;
+}
+
+static inline int kvm_vcpu_dabt_get_rd(struct kvm_vcpu *vcpu)
+{
+	return (kvm_vcpu_get_hsr(vcpu) & HSR_SRT_MASK) >> HSR_SRT_SHIFT;
+}
+
+static inline bool kvm_vcpu_dabt_isextabt(struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_get_hsr(vcpu) & HSR_DABT_EA;
+}
+
+static inline bool kvm_vcpu_dabt_iss1tw(struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_get_hsr(vcpu) & HSR_DABT_S1PTW;
+}
+
+/* Get Access Size from a data abort */
+static inline int kvm_vcpu_dabt_get_as(struct kvm_vcpu *vcpu)
+{
+	switch ((kvm_vcpu_get_hsr(vcpu) >> 22) & 0x3) {
+	case 0:
+		return 1;
+	case 1:
+		return 2;
+	case 2:
+		return 4;
+	default:
+		kvm_err("Hardware is weird: SAS 0b11 is reserved\n");
+		return -EFAULT;
+	}
+}
+
+/* This one is not specific to Data Abort */
+static inline bool kvm_vcpu_trap_il_is32bit(struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_get_hsr(vcpu) & HSR_IL;
+}
+
+static inline u8 kvm_vcpu_trap_get_class(struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_get_hsr(vcpu) >> HSR_EC_SHIFT;
+}
+
+static inline bool kvm_vcpu_trap_is_iabt(struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_trap_get_class(vcpu) == HSR_EC_IABT;
+}
+
+static inline u8 kvm_vcpu_trap_get_fault(struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_get_hsr(vcpu) & HSR_FSC;
+}
+
+static inline u8 kvm_vcpu_trap_get_fault_type(struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_get_hsr(vcpu) & HSR_FSC_TYPE;
+}
+
+static inline u32 kvm_vcpu_hvc_get_imm(struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_get_hsr(vcpu) & HSR_HVC_IMM_MASK;
+}
+
+static inline unsigned long kvm_vcpu_get_mpidr_aff(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.cp15[c0_MPIDR] & MPIDR_HWID_BITMASK;
+}
+
+static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu)
+{
+	*vcpu_cpsr(vcpu) |= PSR_E_BIT;
+}
+
+static inline bool kvm_vcpu_is_be(struct kvm_vcpu *vcpu)
+{
+	return !!(*vcpu_cpsr(vcpu) & PSR_E_BIT);
+}
+
+static inline unsigned long vcpu_data_guest_to_host(struct kvm_vcpu *vcpu,
+						    unsigned long data,
+						    unsigned int len)
+{
+	if (kvm_vcpu_is_be(vcpu)) {
+		switch (len) {
+		case 1:
+			return data & 0xff;
+		case 2:
+			return be16_to_cpu(data & 0xffff);
+		default:
+			return be32_to_cpu(data);
+		}
+	} else {
+		switch (len) {
+		case 1:
+			return data & 0xff;
+		case 2:
+			return le16_to_cpu(data & 0xffff);
+		default:
+			return le32_to_cpu(data);
+		}
+	}
+}
+
+static inline unsigned long vcpu_data_host_to_guest(struct kvm_vcpu *vcpu,
+						    unsigned long data,
+						    unsigned int len)
+{
+	if (kvm_vcpu_is_be(vcpu)) {
+		switch (len) {
+		case 1:
+			return data & 0xff;
+		case 2:
+			return cpu_to_be16(data & 0xffff);
+		default:
+			return cpu_to_be32(data);
+		}
+	} else {
+		switch (len) {
+		case 1:
+			return data & 0xff;
+		case 2:
+			return cpu_to_le16(data & 0xffff);
+		default:
+			return cpu_to_le32(data);
+		}
+	}
+}
+
+#endif /* __ARM_KVM_EMULATE_H__ */
diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
new file mode 100644
index 000000000..d71607c16
--- /dev/null
+++ b/arch/arm/include/asm/kvm_host.h
@@ -0,0 +1,239 @@
+/*
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Author: Christoffer Dall <c.dall@virtualopensystems.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ */
+
+#ifndef __ARM_KVM_HOST_H__
+#define __ARM_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>
+#include <asm/fpstate.h>
+#include <kvm/arm_arch_timer.h>
+
+#define __KVM_HAVE_ARCH_INTC_INITIALIZED
+
+#if defined(CONFIG_KVM_ARM_MAX_VCPUS)
+#define KVM_MAX_VCPUS CONFIG_KVM_ARM_MAX_VCPUS
+#else
+#define KVM_MAX_VCPUS 0
+#endif
+
+#define KVM_USER_MEM_SLOTS 32
+#define KVM_PRIVATE_MEM_SLOTS 4
+#define KVM_COALESCED_MMIO_PAGE_OFFSET 1
+#define KVM_HAVE_ONE_REG
+
+#define KVM_VCPU_MAX_FEATURES 2
+
+#include <kvm/arm_vgic.h>
+
+u32 *kvm_vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num, u32 mode);
+int __attribute_const__ kvm_target_cpu(void);
+int kvm_reset_vcpu(struct kvm_vcpu *vcpu);
+void kvm_reset_coprocs(struct kvm_vcpu *vcpu);
+
+struct kvm_arch {
+	/* VTTBR value associated with below pgd and vmid */
+	u64    vttbr;
+
+	/* Timer */
+	struct arch_timer_kvm	timer;
+
+	/*
+	 * Anything that is not used directly from assembly code goes
+	 * here.
+	 */
+
+	/* The VMID generation used for the virt. memory system */
+	u64    vmid_gen;
+	u32    vmid;
+
+	/* Stage-2 page table */
+	pgd_t *pgd;
+
+	/* Interrupt controller */
+	struct vgic_dist	vgic;
+	int max_vcpus;
+};
+
+#define KVM_NR_MEM_OBJS     40
+
+/*
+ * We don't want allocation failures within the mmu code, so we preallocate
+ * enough memory for a single page fault in a cache.
+ */
+struct kvm_mmu_memory_cache {
+	int nobjs;
+	void *objects[KVM_NR_MEM_OBJS];
+};
+
+struct kvm_vcpu_fault_info {
+	u32 hsr;		/* Hyp Syndrome Register */
+	u32 hxfar;		/* Hyp Data/Inst. Fault Address Register */
+	u32 hpfar;		/* Hyp IPA Fault Address Register */
+	u32 hyp_pc;		/* PC when exception was taken from Hyp mode */
+};
+
+typedef struct vfp_hard_struct kvm_cpu_context_t;
+
+struct kvm_vcpu_arch {
+	struct kvm_regs regs;
+
+	int target; /* Processor target */
+	DECLARE_BITMAP(features, KVM_VCPU_MAX_FEATURES);
+
+	/* System control coprocessor (cp15) */
+	u32 cp15[NR_CP15_REGS];
+
+	/* The CPU type we expose to the VM */
+	u32 midr;
+
+	/* HYP trapping configuration */
+	u32 hcr;
+
+	/* Interrupt related fields */
+	u32 irq_lines;		/* IRQ and FIQ levels */
+
+	/* Exception Information */
+	struct kvm_vcpu_fault_info fault;
+
+	/* Floating point registers (VFP and Advanced SIMD/NEON) */
+	struct vfp_hard_struct vfp_guest;
+
+	/* Host FP context */
+	kvm_cpu_context_t *host_cpu_context;
+
+	/* VGIC state */
+	struct vgic_cpu vgic_cpu;
+	struct arch_timer_cpu timer_cpu;
+
+	/*
+	 * Anything that is not used directly from assembly code goes
+	 * here.
+	 */
+
+	/* Don't run the guest on this vcpu */
+	bool pause;
+
+	/* IO related fields */
+	struct kvm_decode mmio_decode;
+
+	/* Cache some mmu pages needed inside spinlock regions */
+	struct kvm_mmu_memory_cache mmu_page_cache;
+
+	/* Detect first run of a vcpu */
+	bool has_run_once;
+};
+
+struct kvm_vm_stat {
+	u32 remote_tlb_flush;
+};
+
+struct kvm_vcpu_stat {
+	u32 halt_successful_poll;
+	u32 halt_wakeup;
+};
+
+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);
+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);
+u64 kvm_call_hyp(void *hypfn, ...);
+void force_vm_exit(const cpumask_t *mask);
+
+#define KVM_ARCH_WANT_MMU_NOTIFIER
+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);
+
+unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu);
+int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices);
+int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end);
+int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);
+
+/* We do not have shadow page tables, hence the empty hooks */
+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);
+
+int kvm_arm_copy_coproc_indices(struct kvm_vcpu *vcpu, u64 __user *uindices);
+unsigned long kvm_arm_num_coproc_regs(struct kvm_vcpu *vcpu);
+int kvm_arm_coproc_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *);
+int kvm_arm_coproc_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *);
+
+int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
+		int exception_index);
+
+static inline void __cpu_init_hyp_mode(phys_addr_t boot_pgd_ptr,
+				       phys_addr_t pgd_ptr,
+				       unsigned long hyp_stack_ptr,
+				       unsigned long vector_ptr)
+{
+	/*
+	 * Call initialization code, and switch to the full blown HYP
+	 * code. The init code doesn't need to preserve these
+	 * registers as r0-r3 are already callee saved according to
+	 * the AAPCS.
+	 * Note that we slightly misuse the prototype by casing the
+	 * stack pointer to a void *.
+	 *
+	 * We don't have enough registers to perform the full init in
+	 * one go.  Install the boot PGD first, and then install the
+	 * runtime PGD, stack pointer and vectors. The PGDs are always
+	 * passed as the third argument, in order to be passed into
+	 * r2-r3 to the init code (yes, this is compliant with the
+	 * PCS!).
+	 */
+
+	kvm_call_hyp(NULL, 0, boot_pgd_ptr);
+
+	kvm_call_hyp((void*)hyp_stack_ptr, vector_ptr, pgd_ptr);
+}
+
+static inline int kvm_arch_dev_ioctl_check_extension(long ext)
+{
+	return 0;
+}
+
+static inline void vgic_arch_setup(const struct vgic_params *vgic)
+{
+	BUG_ON(vgic->type != VGIC_V2);
+}
+
+int kvm_perf_init(void);
+int kvm_perf_teardown(void);
+
+void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot);
+
+struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr);
+
+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 /* __ARM_KVM_HOST_H__ */
diff --git a/arch/arm/include/asm/kvm_mmio.h b/arch/arm/include/asm/kvm_mmio.h
new file mode 100644
index 000000000..d8e90c8cb
--- /dev/null
+++ b/arch/arm/include/asm/kvm_mmio.h
@@ -0,0 +1,35 @@
+/*
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Author: Christoffer Dall <c.dall@virtualopensystems.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ */
+
+#ifndef __ARM_KVM_MMIO_H__
+#define __ARM_KVM_MMIO_H__
+
+#include <linux/kvm_host.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_arm.h>
+
+struct kvm_decode {
+	unsigned long rt;
+	bool sign_extend;
+};
+
+int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run);
+int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run,
+		 phys_addr_t fault_ipa);
+
+#endif	/* __ARM_KVM_MMIO_H__ */
diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
new file mode 100644
index 000000000..405aa1883
--- /dev/null
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -0,0 +1,284 @@
+/*
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Author: Christoffer Dall <c.dall@virtualopensystems.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ */
+
+#ifndef __ARM_KVM_MMU_H__
+#define __ARM_KVM_MMU_H__
+
+#include <asm/memory.h>
+#include <asm/page.h>
+
+/*
+ * We directly use the kernel VA for the HYP, as we can directly share
+ * the mapping (HTTBR "covers" TTBR1).
+ */
+#define HYP_PAGE_OFFSET_MASK	UL(~0)
+#define HYP_PAGE_OFFSET		PAGE_OFFSET
+#define KERN_TO_HYP(kva)	(kva)
+
+/*
+ * Our virtual mapping for the boot-time MMU-enable code. Must be
+ * shared across all the page-tables. Conveniently, we use the vectors
+ * page, where no kernel data will ever be shared with HYP.
+ */
+#define TRAMPOLINE_VA		UL(CONFIG_VECTORS_BASE)
+
+/*
+ * KVM_MMU_CACHE_MIN_PAGES is the number of stage2 page table translation levels.
+ */
+#define KVM_MMU_CACHE_MIN_PAGES	2
+
+#ifndef __ASSEMBLY__
+
+#include <linux/highmem.h>
+#include <asm/cacheflush.h>
+#include <asm/pgalloc.h>
+
+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);
+void free_hyp_pgds(void);
+
+void stage2_unmap_vm(struct kvm *kvm);
+int kvm_alloc_stage2_pgd(struct kvm *kvm);
+void kvm_free_stage2_pgd(struct kvm *kvm);
+int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
+			  phys_addr_t pa, unsigned long size, bool writable);
+
+int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run);
+
+void kvm_mmu_free_memory_caches(struct kvm_vcpu *vcpu);
+
+phys_addr_t kvm_mmu_get_httbr(void);
+phys_addr_t kvm_mmu_get_boot_httbr(void);
+phys_addr_t kvm_get_idmap_vector(void);
+int kvm_mmu_init(void);
+void kvm_clear_hyp_idmap(void);
+
+static inline void kvm_set_pmd(pmd_t *pmd, pmd_t new_pmd)
+{
+	*pmd = new_pmd;
+	flush_pmd_entry(pmd);
+}
+
+static inline void kvm_set_pte(pte_t *pte, pte_t new_pte)
+{
+	*pte = new_pte;
+	/*
+	 * flush_pmd_entry just takes a void pointer and cleans the necessary
+	 * cache entries, so we can reuse the function for ptes.
+	 */
+	flush_pmd_entry(pte);
+}
+
+static inline void kvm_clean_pgd(pgd_t *pgd)
+{
+	clean_dcache_area(pgd, PTRS_PER_S2_PGD * sizeof(pgd_t));
+}
+
+static inline void kvm_clean_pmd(pmd_t *pmd)
+{
+	clean_dcache_area(pmd, PTRS_PER_PMD * sizeof(pmd_t));
+}
+
+static inline void kvm_clean_pmd_entry(pmd_t *pmd)
+{
+	clean_pmd_entry(pmd);
+}
+
+static inline void kvm_clean_pte(pte_t *pte)
+{
+	clean_pte_table(pte);
+}
+
+static inline void kvm_set_s2pte_writable(pte_t *pte)
+{
+	pte_val(*pte) |= L_PTE_S2_RDWR;
+}
+
+static inline void kvm_set_s2pmd_writable(pmd_t *pmd)
+{
+	pmd_val(*pmd) |= L_PMD_S2_RDWR;
+}
+
+static inline void kvm_set_s2pte_readonly(pte_t *pte)
+{
+	pte_val(*pte) = (pte_val(*pte) & ~L_PTE_S2_RDWR) | L_PTE_S2_RDONLY;
+}
+
+static inline bool kvm_s2pte_readonly(pte_t *pte)
+{
+	return (pte_val(*pte) & L_PTE_S2_RDWR) == L_PTE_S2_RDONLY;
+}
+
+static inline void kvm_set_s2pmd_readonly(pmd_t *pmd)
+{
+	pmd_val(*pmd) = (pmd_val(*pmd) & ~L_PMD_S2_RDWR) | L_PMD_S2_RDONLY;
+}
+
+static inline bool kvm_s2pmd_readonly(pmd_t *pmd)
+{
+	return (pmd_val(*pmd) & L_PMD_S2_RDWR) == L_PMD_S2_RDONLY;
+}
+
+
+/* Open coded p*d_addr_end that can deal with 64bit addresses */
+#define kvm_pgd_addr_end(addr, end)					\
+({	u64 __boundary = ((addr) + PGDIR_SIZE) & PGDIR_MASK;		\
+	(__boundary - 1 < (end) - 1)? __boundary: (end);		\
+})
+
+#define kvm_pud_addr_end(addr,end)		(end)
+
+#define kvm_pmd_addr_end(addr, end)					\
+({	u64 __boundary = ((addr) + PMD_SIZE) & PMD_MASK;		\
+	(__boundary - 1 < (end) - 1)? __boundary: (end);		\
+})
+
+#define kvm_pgd_index(addr)			pgd_index(addr)
+
+static inline bool kvm_page_empty(void *ptr)
+{
+	struct page *ptr_page = virt_to_page(ptr);
+	return page_count(ptr_page) == 1;
+}
+
+#define kvm_pte_table_empty(kvm, ptep) kvm_page_empty(ptep)
+#define kvm_pmd_table_empty(kvm, pmdp) kvm_page_empty(pmdp)
+#define kvm_pud_table_empty(kvm, pudp) (0)
+
+#define KVM_PREALLOC_LEVEL	0
+
+static inline void *kvm_get_hwpgd(struct kvm *kvm)
+{
+	return kvm->arch.pgd;
+}
+
+static inline unsigned int kvm_get_hwpgd_size(void)
+{
+	return PTRS_PER_S2_PGD * sizeof(pgd_t);
+}
+
+struct kvm;
+
+#define kvm_flush_dcache_to_poc(a,l)	__cpuc_flush_dcache_area((a), (l))
+
+static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu)
+{
+	return (vcpu->arch.cp15[c1_SCTLR] & 0b101) == 0b101;
+}
+
+static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, pfn_t pfn,
+					       unsigned long size,
+					       bool ipa_uncached)
+{
+	/*
+	 * If we are going to insert an instruction page and the icache is
+	 * either VIPT or PIPT, there is a potential problem where the host
+	 * (or another VM) may have used the same page as this guest, and we
+	 * read incorrect data from the icache.  If we're using a PIPT cache,
+	 * we can invalidate just that page, but if we are using a VIPT cache
+	 * we need to invalidate the entire icache - damn shame - as written
+	 * in the ARM ARM (DDI 0406C.b - Page B3-1393).
+	 *
+	 * VIVT caches are tagged using both the ASID and the VMID and doesn't
+	 * need any kind of flushing (DDI 0406C.b - Page B3-1392).
+	 *
+	 * We need to do this through a kernel mapping (using the
+	 * user-space mapping has proved to be the wrong
+	 * solution). For that, we need to kmap one page at a time,
+	 * and iterate over the range.
+	 */
+
+	bool need_flush = !vcpu_has_cache_enabled(vcpu) || ipa_uncached;
+
+	VM_BUG_ON(size & ~PAGE_MASK);
+
+	if (!need_flush && !icache_is_pipt())
+		goto vipt_cache;
+
+	while (size) {
+		void *va = kmap_atomic_pfn(pfn);
+
+		if (need_flush)
+			kvm_flush_dcache_to_poc(va, PAGE_SIZE);
+
+		if (icache_is_pipt())
+			__cpuc_coherent_user_range((unsigned long)va,
+						   (unsigned long)va + PAGE_SIZE);
+
+		size -= PAGE_SIZE;
+		pfn++;
+
+		kunmap_atomic(va);
+	}
+
+vipt_cache:
+	if (!icache_is_pipt() && !icache_is_vivt_asid_tagged()) {
+		/* any kind of VIPT cache */
+		__flush_icache_all();
+	}
+}
+
+static inline void __kvm_flush_dcache_pte(pte_t pte)
+{
+	void *va = kmap_atomic(pte_page(pte));
+
+	kvm_flush_dcache_to_poc(va, PAGE_SIZE);
+
+	kunmap_atomic(va);
+}
+
+static inline void __kvm_flush_dcache_pmd(pmd_t pmd)
+{
+	unsigned long size = PMD_SIZE;
+	pfn_t pfn = pmd_pfn(pmd);
+
+	while (size) {
+		void *va = kmap_atomic_pfn(pfn);
+
+		kvm_flush_dcache_to_poc(va, PAGE_SIZE);
+
+		pfn++;
+		size -= PAGE_SIZE;
+
+		kunmap_atomic(va);
+	}
+}
+
+static inline void __kvm_flush_dcache_pud(pud_t pud)
+{
+}
+
+#define kvm_virt_to_phys(x)		virt_to_idmap((unsigned long)(x))
+
+void kvm_set_way_flush(struct kvm_vcpu *vcpu);
+void kvm_toggle_cache(struct kvm_vcpu *vcpu, bool was_enabled);
+
+static inline bool __kvm_cpu_uses_extended_idmap(void)
+{
+	return false;
+}
+
+static inline void __kvm_extend_hypmap(pgd_t *boot_hyp_pgd,
+				       pgd_t *hyp_pgd,
+				       pgd_t *merged_hyp_pgd,
+				       unsigned long hyp_idmap_start) { }
+
+#endif	/* !__ASSEMBLY__ */
+
+#endif /* __ARM_KVM_MMU_H__ */
diff --git a/arch/arm/include/asm/kvm_psci.h b/arch/arm/include/asm/kvm_psci.h
new file mode 100644
index 000000000..6bda945d3
--- /dev/null
+++ b/arch/arm/include/asm/kvm_psci.h
@@ -0,0 +1,27 @@
+/*
+ * Copyright (C) 2012 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __ARM_KVM_PSCI_H__
+#define __ARM_KVM_PSCI_H__
+
+#define KVM_ARM_PSCI_0_1	1
+#define KVM_ARM_PSCI_0_2	2
+
+int kvm_psci_version(struct kvm_vcpu *vcpu);
+int kvm_psci_call(struct kvm_vcpu *vcpu);
+
+#endif /* __ARM_KVM_PSCI_H__ */
diff --git a/arch/arm/include/asm/limits.h b/arch/arm/include/asm/limits.h
new file mode 100644
index 000000000..08d8c6600
--- /dev/null
+++ b/arch/arm/include/asm/limits.h
@@ -0,0 +1,11 @@
+#ifndef __ASM_PIPE_H
+#define __ASM_PIPE_H
+
+#ifndef PAGE_SIZE
+#include <asm/page.h>
+#endif
+
+#define PIPE_BUF	PAGE_SIZE
+
+#endif
+
diff --git a/arch/arm/include/asm/linkage.h b/arch/arm/include/asm/linkage.h
new file mode 100644
index 000000000..5a25632b1
--- /dev/null
+++ b/arch/arm/include/asm/linkage.h
@@ -0,0 +1,11 @@
+#ifndef __ASM_LINKAGE_H
+#define __ASM_LINKAGE_H
+
+#define __ALIGN .align 0
+#define __ALIGN_STR ".align 0"
+
+#define ENDPROC(name) \
+  .type name, %function; \
+  END(name)
+
+#endif
diff --git a/arch/arm/include/asm/mach-types.h b/arch/arm/include/asm/mach-types.h
new file mode 100644
index 000000000..948178cc6
--- /dev/null
+++ b/arch/arm/include/asm/mach-types.h
@@ -0,0 +1 @@
+#include <generated/mach-types.h>
diff --git a/arch/arm/include/asm/mach/arch.h b/arch/arm/include/asm/mach/arch.h
new file mode 100644
index 000000000..0406cb3f1
--- /dev/null
+++ b/arch/arm/include/asm/mach/arch.h
@@ -0,0 +1,101 @@
+/*
+ *  arch/arm/include/asm/mach/arch.h
+ *
+ *  Copyright (C) 2000 Russell King
+ *
+ * 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.
+ */
+
+#include <linux/types.h>
+
+#ifndef __ASSEMBLY__
+#include <linux/reboot.h>
+
+struct tag;
+struct pt_regs;
+struct smp_operations;
+#ifdef CONFIG_SMP
+#define smp_ops(ops) (&(ops))
+#define smp_init_ops(ops) (&(ops))
+#else
+#define smp_ops(ops) (struct smp_operations *)NULL
+#define smp_init_ops(ops) (bool (*)(void))NULL
+#endif
+
+struct machine_desc {
+	unsigned int		nr;		/* architecture number	*/
+	const char		*name;		/* architecture name	*/
+	unsigned long		atag_offset;	/* tagged list (relative) */
+	const char *const 	*dt_compat;	/* array of device tree
+						 * 'compatible' strings	*/
+
+	unsigned int		nr_irqs;	/* number of IRQs */
+
+#ifdef CONFIG_ZONE_DMA
+	phys_addr_t		dma_zone_size;	/* size of DMA-able area */
+#endif
+
+	unsigned int		video_start;	/* start of video RAM	*/
+	unsigned int		video_end;	/* end of video RAM	*/
+
+	unsigned char		reserve_lp0 :1;	/* never has lp0	*/
+	unsigned char		reserve_lp1 :1;	/* never has lp1	*/
+	unsigned char		reserve_lp2 :1;	/* never has lp2	*/
+	enum reboot_mode	reboot_mode;	/* default restart mode	*/
+	unsigned		l2c_aux_val;	/* L2 cache aux value	*/
+	unsigned		l2c_aux_mask;	/* L2 cache aux mask	*/
+	void			(*l2c_write_sec)(unsigned long, unsigned);
+	struct smp_operations	*smp;		/* SMP operations	*/
+	bool			(*smp_init)(void);
+	void			(*fixup)(struct tag *, char **);
+	void			(*dt_fixup)(void);
+	void			(*init_meminfo)(void);
+	void			(*reserve)(void);/* reserve mem blocks	*/
+	void			(*map_io)(void);/* IO mapping function	*/
+	void			(*init_early)(void);
+	void			(*init_irq)(void);
+	void			(*init_time)(void);
+	void			(*init_machine)(void);
+	void			(*init_late)(void);
+#ifdef CONFIG_MULTI_IRQ_HANDLER
+	void			(*handle_irq)(struct pt_regs *);
+#endif
+	void			(*restart)(enum reboot_mode, const char *);
+};
+
+/*
+ * Current machine - only accessible during boot.
+ */
+extern const struct machine_desc *machine_desc;
+
+/*
+ * Machine type table - also only accessible during boot
+ */
+extern const struct machine_desc __arch_info_begin[], __arch_info_end[];
+#define for_each_machine_desc(p)			\
+	for (p = __arch_info_begin; p < __arch_info_end; p++)
+
+/*
+ * Set of macros to define architecture features.  This is built into
+ * a table by the linker.
+ */
+#define MACHINE_START(_type,_name)			\
+static const struct machine_desc __mach_desc_##_type	\
+ __used							\
+ __attribute__((__section__(".arch.info.init"))) = {	\
+	.nr		= MACH_TYPE_##_type,		\
+	.name		= _name,
+
+#define MACHINE_END				\
+};
+
+#define DT_MACHINE_START(_name, _namestr)		\
+static const struct machine_desc __mach_desc_##_name	\
+ __used							\
+ __attribute__((__section__(".arch.info.init"))) = {	\
+	.nr		= ~0,				\
+	.name		= _namestr,
+
+#endif
diff --git a/arch/arm/include/asm/mach/dma.h b/arch/arm/include/asm/mach/dma.h
new file mode 100644
index 000000000..9e614a18e
--- /dev/null
+++ b/arch/arm/include/asm/mach/dma.h
@@ -0,0 +1,54 @@
+/*
+ *  arch/arm/include/asm/mach/dma.h
+ *
+ *  Copyright (C) 1998-2000 Russell King
+ *
+ * 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 header file describes the interface between the generic DMA handler
+ *  (dma.c) and the architecture-specific DMA backends (dma-*.c)
+ */
+
+struct dma_struct;
+typedef struct dma_struct dma_t;
+
+struct dma_ops {
+	int	(*request)(unsigned int, dma_t *);		/* optional */
+	void	(*free)(unsigned int, dma_t *);			/* optional */
+	void	(*enable)(unsigned int, dma_t *);		/* mandatory */
+	void 	(*disable)(unsigned int, dma_t *);		/* mandatory */
+	int	(*residue)(unsigned int, dma_t *);		/* optional */
+	int	(*setspeed)(unsigned int, dma_t *, int);	/* optional */
+	const char *type;
+};
+
+struct dma_struct {
+	void		*addr;		/* single DMA address		*/
+	unsigned long	count;		/* single DMA size		*/
+	struct scatterlist buf;		/* single DMA			*/
+	int		sgcount;	/* number of DMA SG		*/
+	struct scatterlist *sg;		/* DMA Scatter-Gather List	*/
+
+	unsigned int	active:1;	/* Transfer active		*/
+	unsigned int	invalid:1;	/* Address/Count changed	*/
+
+	unsigned int	dma_mode;	/* DMA mode			*/
+	int		speed;		/* DMA speed			*/
+
+	unsigned int	lock;		/* Device is allocated		*/
+	const char	*device_id;	/* Device name			*/
+
+	const struct dma_ops *d_ops;
+};
+
+/*
+ * isa_dma_add - add an ISA-style DMA channel
+ */
+extern int isa_dma_add(unsigned int, dma_t *dma);
+
+/*
+ * Add the ISA DMA controller.  Always takes channels 0-7.
+ */
+extern void isa_init_dma(void);
diff --git a/arch/arm/include/asm/mach/flash.h b/arch/arm/include/asm/mach/flash.h
new file mode 100644
index 000000000..4ca69fe2c
--- /dev/null
+++ b/arch/arm/include/asm/mach/flash.h
@@ -0,0 +1,39 @@
+/*
+ *  arch/arm/include/asm/mach/flash.h
+ *
+ *  Copyright (C) 2003 Russell King, 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 as
+ * published by the Free Software Foundation.
+ */
+#ifndef ASMARM_MACH_FLASH_H
+#define ASMARM_MACH_FLASH_H
+
+struct mtd_partition;
+struct mtd_info;
+
+/*
+ * map_name:	the map probe function name
+ * name:	flash device name (eg, as used with mtdparts=)
+ * width:	width of mapped device
+ * init:	method called at driver/device initialisation
+ * exit:	method called at driver/device removal
+ * set_vpp:	method called to enable or disable VPP
+ * mmcontrol:	method called to enable or disable Sync. Burst Read in OneNAND
+ * parts:	optional array of mtd_partitions for static partitioning
+ * nr_parts:	number of mtd_partitions for static partitoning
+ */
+struct flash_platform_data {
+	const char	*map_name;
+	const char	*name;
+	unsigned int	width;
+	int		(*init)(void);
+	void		(*exit)(void);
+	void		(*set_vpp)(int on);
+	void		(*mmcontrol)(struct mtd_info *mtd, int sync_read);
+	struct mtd_partition *parts;
+	unsigned int	nr_parts;
+};
+
+#endif
diff --git a/arch/arm/include/asm/mach/irq.h b/arch/arm/include/asm/mach/irq.h
new file mode 100644
index 000000000..2092ee1e1
--- /dev/null
+++ b/arch/arm/include/asm/mach/irq.h
@@ -0,0 +1,33 @@
+/*
+ *  arch/arm/include/asm/mach/irq.h
+ *
+ *  Copyright (C) 1995-2000 Russell King.
+ *
+ * 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.
+ */
+#ifndef __ASM_ARM_MACH_IRQ_H
+#define __ASM_ARM_MACH_IRQ_H
+
+#include <linux/irq.h>
+
+struct seq_file;
+
+/*
+ * This is internal.  Do not use it.
+ */
+extern void init_FIQ(int);
+extern int show_fiq_list(struct seq_file *, int);
+
+/*
+ * This is for easy migration, but should be changed in the source
+ */
+#define do_bad_IRQ(irq,desc)				\
+do {							\
+	raw_spin_lock(&desc->lock);			\
+	handle_bad_irq(irq, desc);			\
+	raw_spin_unlock(&desc->lock);			\
+} while(0)
+
+#endif
diff --git a/arch/arm/include/asm/mach/map.h b/arch/arm/include/asm/mach/map.h
new file mode 100644
index 000000000..f98c7f32c
--- /dev/null
+++ b/arch/arm/include/asm/mach/map.h
@@ -0,0 +1,65 @@
+/*
+ *  arch/arm/include/asm/map.h
+ *
+ *  Copyright (C) 1999-2000 Russell King
+ *
+ * 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.
+ *
+ *  Page table mapping constructs and function prototypes
+ */
+#ifndef __ASM_MACH_MAP_H
+#define __ASM_MACH_MAP_H
+
+#include <asm/io.h>
+
+struct map_desc {
+	unsigned long virtual;
+	unsigned long pfn;
+	unsigned long length;
+	unsigned int type;
+};
+
+/* types 0-3 are defined in asm/io.h */
+enum {
+	MT_UNCACHED = 4,
+	MT_CACHECLEAN,
+	MT_MINICLEAN,
+	MT_LOW_VECTORS,
+	MT_HIGH_VECTORS,
+	MT_MEMORY_RWX,
+	MT_MEMORY_RW,
+	MT_ROM,
+	MT_MEMORY_RWX_NONCACHED,
+	MT_MEMORY_RW_DTCM,
+	MT_MEMORY_RWX_ITCM,
+	MT_MEMORY_RW_SO,
+	MT_MEMORY_DMA_READY,
+};
+
+#ifdef CONFIG_MMU
+extern void iotable_init(struct map_desc *, int);
+extern void vm_reserve_area_early(unsigned long addr, unsigned long size,
+				  void *caller);
+
+#ifdef CONFIG_DEBUG_LL
+extern void debug_ll_addr(unsigned long *paddr, unsigned long *vaddr);
+extern void debug_ll_io_init(void);
+#else
+static inline void debug_ll_io_init(void) {}
+#endif
+
+struct mem_type;
+extern const struct mem_type *get_mem_type(unsigned int type);
+/*
+ * external interface to remap single page with appropriate type
+ */
+extern int ioremap_page(unsigned long virt, unsigned long phys,
+			const struct mem_type *mtype);
+#else
+#define iotable_init(map,num)	do { } while (0)
+#define vm_reserve_area_early(a,s,c)	do { } while (0)
+#endif
+
+#endif
diff --git a/arch/arm/include/asm/mach/pci.h b/arch/arm/include/asm/mach/pci.h
new file mode 100644
index 000000000..28b9bb359
--- /dev/null
+++ b/arch/arm/include/asm/mach/pci.h
@@ -0,0 +1,105 @@
+/*
+ *  arch/arm/include/asm/mach/pci.h
+ *
+ *  Copyright (C) 2000 Russell King
+ *
+ * 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.
+ */
+
+#ifndef __ASM_MACH_PCI_H
+#define __ASM_MACH_PCI_H
+
+#include <linux/ioport.h>
+
+struct pci_sys_data;
+struct pci_ops;
+struct pci_bus;
+struct device;
+
+struct hw_pci {
+#ifdef CONFIG_PCI_MSI
+	struct msi_controller *msi_ctrl;
+#endif
+	struct pci_ops	*ops;
+	int		nr_controllers;
+	void		**private_data;
+	int		(*setup)(int nr, struct pci_sys_data *);
+	struct pci_bus *(*scan)(int nr, struct pci_sys_data *);
+	void		(*preinit)(void);
+	void		(*postinit)(void);
+	u8		(*swizzle)(struct pci_dev *dev, u8 *pin);
+	int		(*map_irq)(const struct pci_dev *dev, u8 slot, u8 pin);
+	resource_size_t (*align_resource)(struct pci_dev *dev,
+					  const struct resource *res,
+					  resource_size_t start,
+					  resource_size_t size,
+					  resource_size_t align);
+};
+
+/*
+ * Per-controller structure
+ */
+struct pci_sys_data {
+#ifdef CONFIG_PCI_MSI
+	struct msi_controller *msi_ctrl;
+#endif
+	struct list_head node;
+	int		busnr;		/* primary bus number			*/
+	u64		mem_offset;	/* bus->cpu memory mapping offset	*/
+	unsigned long	io_offset;	/* bus->cpu IO mapping offset		*/
+	struct pci_bus	*bus;		/* PCI bus				*/
+	struct list_head resources;	/* root bus resources (apertures)       */
+	struct resource io_res;
+	char		io_res_name[12];
+					/* Bridge swizzling			*/
+	u8		(*swizzle)(struct pci_dev *, u8 *);
+					/* IRQ mapping				*/
+	int		(*map_irq)(const struct pci_dev *, u8, u8);
+					/* Resource alignement requirements	*/
+	resource_size_t (*align_resource)(struct pci_dev *dev,
+					  const struct resource *res,
+					  resource_size_t start,
+					  resource_size_t size,
+					  resource_size_t align);
+	void		*private_data;	/* platform controller private data	*/
+};
+
+/*
+ * Call this with your hw_pci struct to initialise the PCI system.
+ */
+void pci_common_init_dev(struct device *, struct hw_pci *);
+
+/*
+ * Compatibility wrapper for older platforms that do not care about
+ * passing the parent device.
+ */
+static inline void pci_common_init(struct hw_pci *hw)
+{
+	pci_common_init_dev(NULL, hw);
+}
+
+/*
+ * Setup early fixed I/O mapping.
+ */
+#if defined(CONFIG_PCI)
+extern void pci_map_io_early(unsigned long pfn);
+#else
+static inline void pci_map_io_early(unsigned long pfn) {}
+#endif
+
+/*
+ * PCI controllers
+ */
+extern struct pci_ops iop3xx_ops;
+extern int iop3xx_pci_setup(int nr, struct pci_sys_data *);
+extern void iop3xx_pci_preinit(void);
+extern void iop3xx_pci_preinit_cond(void);
+
+extern struct pci_ops dc21285_ops;
+extern int dc21285_setup(int nr, struct pci_sys_data *);
+extern void dc21285_preinit(void);
+extern void dc21285_postinit(void);
+
+#endif /* __ASM_MACH_PCI_H */
diff --git a/arch/arm/include/asm/mach/sharpsl_param.h b/arch/arm/include/asm/mach/sharpsl_param.h
new file mode 100644
index 000000000..7a24ecf04
--- /dev/null
+++ b/arch/arm/include/asm/mach/sharpsl_param.h
@@ -0,0 +1,37 @@
+/*
+ * Hardware parameter area specific to Sharp SL series devices
+ *
+ * Copyright (c) 2005 Richard Purdie
+ *
+ * Based on Sharp's 2.4 kernel patches
+ *
+ * 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.
+ *
+ */
+
+struct sharpsl_param_info {
+  unsigned int comadj_keyword;
+  unsigned int comadj;
+
+  unsigned int uuid_keyword;
+  unsigned char uuid[16];
+
+  unsigned int touch_keyword;
+  unsigned int touch_xp;
+  unsigned int touch_yp;
+  unsigned int touch_xd;
+  unsigned int touch_yd;
+
+  unsigned int adadj_keyword;
+  unsigned int adadj;
+
+  unsigned int phad_keyword;
+  unsigned int phadadj;
+} __attribute__((packed));
+
+
+extern struct sharpsl_param_info sharpsl_param;
+extern void sharpsl_save_param(void);
+
diff --git a/arch/arm/include/asm/mach/time.h b/arch/arm/include/asm/mach/time.h
new file mode 100644
index 000000000..0f79e4dec
--- /dev/null
+++ b/arch/arm/include/asm/mach/time.h
@@ -0,0 +1,19 @@
+/*
+ * arch/arm/include/asm/mach/time.h
+ *
+ * Copyright (C) 2004 MontaVista Software, Inc.
+ *
+ * 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.
+ */
+#ifndef __ASM_ARM_MACH_TIME_H
+#define __ASM_ARM_MACH_TIME_H
+
+extern void timer_tick(void);
+
+typedef void (*clock_access_fn)(struct timespec64 *);
+extern int register_persistent_clock(clock_access_fn read_boot,
+				     clock_access_fn read_persistent);
+
+#endif
diff --git a/arch/arm/include/asm/mc146818rtc.h b/arch/arm/include/asm/mc146818rtc.h
new file mode 100644
index 000000000..e8567bb99
--- /dev/null
+++ b/arch/arm/include/asm/mc146818rtc.h
@@ -0,0 +1,30 @@
+/*
+ * Machine dependent access functions for RTC registers.
+ */
+#ifndef _ASM_MC146818RTC_H
+#define _ASM_MC146818RTC_H
+
+#include <linux/io.h>
+#include <linux/kernel.h>
+
+#define RTC_IRQ BUILD_BUG_ON(1)
+
+#ifndef RTC_PORT
+#define RTC_PORT(x)	(0x70 + (x))
+#define RTC_ALWAYS_BCD	1	/* RTC operates in binary mode */
+#endif
+
+/*
+ * The yet supported machines all access the RTC index register via
+ * an ISA port access but the way to access the date register differs ...
+ */
+#define CMOS_READ(addr) ({ \
+outb_p((addr),RTC_PORT(0)); \
+inb_p(RTC_PORT(1)); \
+})
+#define CMOS_WRITE(val, addr) ({ \
+outb_p((addr),RTC_PORT(0)); \
+outb_p((val),RTC_PORT(1)); \
+})
+
+#endif /* _ASM_MC146818RTC_H */
diff --git a/arch/arm/include/asm/mcpm.h b/arch/arm/include/asm/mcpm.h
new file mode 100644
index 000000000..50b378f59
--- /dev/null
+++ b/arch/arm/include/asm/mcpm.h
@@ -0,0 +1,358 @@
+/*
+ * arch/arm/include/asm/mcpm.h
+ *
+ * Created by:  Nicolas Pitre, April 2012
+ * Copyright:   (C) 2012-2013  Linaro Limited
+ *
+ * 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.
+ */
+
+#ifndef MCPM_H
+#define MCPM_H
+
+/*
+ * Maximum number of possible clusters / CPUs per cluster.
+ *
+ * This should be sufficient for quite a while, while keeping the
+ * (assembly) code simpler.  When this starts to grow then we'll have
+ * to consider dynamic allocation.
+ */
+#define MAX_CPUS_PER_CLUSTER	4
+
+#ifdef CONFIG_MCPM_QUAD_CLUSTER
+#define MAX_NR_CLUSTERS		4
+#else
+#define MAX_NR_CLUSTERS		2
+#endif
+
+#ifndef __ASSEMBLY__
+
+#include <linux/types.h>
+#include <asm/cacheflush.h>
+
+/*
+ * Platform specific code should use this symbol to set up secondary
+ * entry location for processors to use when released from reset.
+ */
+extern void mcpm_entry_point(void);
+
+/*
+ * This is used to indicate where the given CPU from given cluster should
+ * branch once it is ready to re-enter the kernel using ptr, or NULL if it
+ * should be gated.  A gated CPU is held in a WFE loop until its vector
+ * becomes non NULL.
+ */
+void mcpm_set_entry_vector(unsigned cpu, unsigned cluster, void *ptr);
+
+/*
+ * This sets an early poke i.e a value to be poked into some address
+ * from very early assembly code before the CPU is ungated.  The
+ * address must be physical, and if 0 then nothing will happen.
+ */
+void mcpm_set_early_poke(unsigned cpu, unsigned cluster,
+			 unsigned long poke_phys_addr, unsigned long poke_val);
+
+/*
+ * CPU/cluster power operations API for higher subsystems to use.
+ */
+
+/**
+ * mcpm_is_available - returns whether MCPM is initialized and available
+ *
+ * This returns true or false accordingly.
+ */
+bool mcpm_is_available(void);
+
+/**
+ * mcpm_cpu_power_up - make given CPU in given cluster runable
+ *
+ * @cpu: CPU number within given cluster
+ * @cluster: cluster number for the CPU
+ *
+ * The identified CPU is brought out of reset.  If the cluster was powered
+ * down then it is brought up as well, taking care not to let the other CPUs
+ * in the cluster run, and ensuring appropriate cluster setup.
+ *
+ * Caller must ensure the appropriate entry vector is initialized with
+ * mcpm_set_entry_vector() prior to calling this.
+ *
+ * This must be called in a sleepable context.  However, the implementation
+ * is strongly encouraged to return early and let the operation happen
+ * asynchronously, especially when significant delays are expected.
+ *
+ * If the operation cannot be performed then an error code is returned.
+ */
+int mcpm_cpu_power_up(unsigned int cpu, unsigned int cluster);
+
+/**
+ * mcpm_cpu_power_down - power the calling CPU down
+ *
+ * The calling CPU is powered down.
+ *
+ * If this CPU is found to be the "last man standing" in the cluster
+ * then the cluster is prepared for power-down too.
+ *
+ * This must be called with interrupts disabled.
+ *
+ * On success this does not return.  Re-entry in the kernel is expected
+ * via mcpm_entry_point.
+ *
+ * This will return if mcpm_platform_register() has not been called
+ * previously in which case the caller should take appropriate action.
+ *
+ * On success, the CPU is not guaranteed to be truly halted until
+ * mcpm_wait_for_cpu_powerdown() subsequently returns non-zero for the
+ * specified cpu.  Until then, other CPUs should make sure they do not
+ * trash memory the target CPU might be executing/accessing.
+ */
+void mcpm_cpu_power_down(void);
+
+/**
+ * mcpm_wait_for_cpu_powerdown - wait for a specified CPU to halt, and
+ *	make sure it is powered off
+ *
+ * @cpu: CPU number within given cluster
+ * @cluster: cluster number for the CPU
+ *
+ * Call this function to ensure that a pending powerdown has taken
+ * effect and the CPU is safely parked before performing non-mcpm
+ * operations that may affect the CPU (such as kexec trashing the
+ * kernel text).
+ *
+ * It is *not* necessary to call this function if you only need to
+ * serialise a pending powerdown with mcpm_cpu_power_up() or a wakeup
+ * event.
+ *
+ * Do not call this function unless the specified CPU has already
+ * called mcpm_cpu_power_down() or has committed to doing so.
+ *
+ * @return:
+ *	- zero if the CPU is in a safely parked state
+ *	- nonzero otherwise (e.g., timeout)
+ */
+int mcpm_wait_for_cpu_powerdown(unsigned int cpu, unsigned int cluster);
+
+/**
+ * mcpm_cpu_suspend - bring the calling CPU in a suspended state
+ *
+ * @expected_residency: duration in microseconds the CPU is expected
+ *			to remain suspended, or 0 if unknown/infinity.
+ *
+ * The calling CPU is suspended.  The expected residency argument is used
+ * as a hint by the platform specific backend to implement the appropriate
+ * sleep state level according to the knowledge it has on wake-up latency
+ * for the given hardware.
+ *
+ * If this CPU is found to be the "last man standing" in the cluster
+ * then the cluster may be prepared for power-down too, if the expected
+ * residency makes it worthwhile.
+ *
+ * This must be called with interrupts disabled.
+ *
+ * On success this does not return.  Re-entry in the kernel is expected
+ * via mcpm_entry_point.
+ *
+ * This will return if mcpm_platform_register() has not been called
+ * previously in which case the caller should take appropriate action.
+ */
+void mcpm_cpu_suspend(u64 expected_residency);
+
+/**
+ * mcpm_cpu_powered_up - housekeeping workafter a CPU has been powered up
+ *
+ * This lets the platform specific backend code perform needed housekeeping
+ * work.  This must be called by the newly activated CPU as soon as it is
+ * fully operational in kernel space, before it enables interrupts.
+ *
+ * If the operation cannot be performed then an error code is returned.
+ */
+int mcpm_cpu_powered_up(void);
+
+/*
+ * Platform specific callbacks used in the implementation of the above API.
+ *
+ * cpu_powerup:
+ * Make given CPU runable. Called with MCPM lock held and IRQs disabled.
+ * The given cluster is assumed to be set up (cluster_powerup would have
+ * been called beforehand). Must return 0 for success or negative error code.
+ *
+ * cluster_powerup:
+ * Set up power for given cluster. Called with MCPM lock held and IRQs
+ * disabled. Called before first cpu_powerup when cluster is down. Must
+ * return 0 for success or negative error code.
+ *
+ * cpu_suspend_prepare:
+ * Special suspend configuration. Called on target CPU with MCPM lock held
+ * and IRQs disabled. This callback is optional. If provided, it is called
+ * before cpu_powerdown_prepare.
+ *
+ * cpu_powerdown_prepare:
+ * Configure given CPU for power down. Called on target CPU with MCPM lock
+ * held and IRQs disabled. Power down must be effective only at the next WFI instruction.
+ *
+ * cluster_powerdown_prepare:
+ * Configure given cluster for power down. Called on one CPU from target
+ * cluster with MCPM lock held and IRQs disabled. A cpu_powerdown_prepare
+ * for each CPU in the cluster has happened when this occurs.
+ *
+ * cpu_cache_disable:
+ * Clean and disable CPU level cache for the calling CPU. Called on with IRQs
+ * disabled only. The CPU is no longer cache coherent with the rest of the
+ * system when this returns.
+ *
+ * cluster_cache_disable:
+ * Clean and disable the cluster wide cache as well as the CPU level cache
+ * for the calling CPU. No call to cpu_cache_disable will happen for this
+ * CPU. Called with IRQs disabled and only when all the other CPUs are done
+ * with their own cpu_cache_disable. The cluster is no longer cache coherent
+ * with the rest of the system when this returns.
+ *
+ * cpu_is_up:
+ * Called on given CPU after it has been powered up or resumed. The MCPM lock
+ * is held and IRQs disabled. This callback is optional.
+ *
+ * cluster_is_up:
+ * Called by the first CPU to be powered up or resumed in given cluster.
+ * The MCPM lock is held and IRQs disabled. This callback is optional. If
+ * provided, it is called before cpu_is_up for that CPU.
+ *
+ * wait_for_powerdown:
+ * Wait until given CPU is powered down. This is called in sleeping context.
+ * Some reasonable timeout must be considered. Must return 0 for success or
+ * negative error code.
+ */
+struct mcpm_platform_ops {
+	int (*cpu_powerup)(unsigned int cpu, unsigned int cluster);
+	int (*cluster_powerup)(unsigned int cluster);
+	void (*cpu_suspend_prepare)(unsigned int cpu, unsigned int cluster);
+	void (*cpu_powerdown_prepare)(unsigned int cpu, unsigned int cluster);
+	void (*cluster_powerdown_prepare)(unsigned int cluster);
+	void (*cpu_cache_disable)(void);
+	void (*cluster_cache_disable)(void);
+	void (*cpu_is_up)(unsigned int cpu, unsigned int cluster);
+	void (*cluster_is_up)(unsigned int cluster);
+	int (*wait_for_powerdown)(unsigned int cpu, unsigned int cluster);
+
+	/* deprecated callbacks */
+	int (*power_up)(unsigned int cpu, unsigned int cluster);
+	void (*power_down)(void);
+	void (*suspend)(u64);
+	void (*powered_up)(void);
+};
+
+/**
+ * mcpm_platform_register - register platform specific power methods
+ *
+ * @ops: mcpm_platform_ops structure to register
+ *
+ * An error is returned if the registration has been done previously.
+ */
+int __init mcpm_platform_register(const struct mcpm_platform_ops *ops);
+
+/* Synchronisation structures for coordinating safe cluster setup/teardown: */
+
+/*
+ * When modifying this structure, make sure you update the MCPM_SYNC_ defines
+ * to match.
+ */
+struct mcpm_sync_struct {
+	/* individual CPU states */
+	struct {
+		s8 cpu __aligned(__CACHE_WRITEBACK_GRANULE);
+	} cpus[MAX_CPUS_PER_CLUSTER];
+
+	/* cluster state */
+	s8 cluster __aligned(__CACHE_WRITEBACK_GRANULE);
+
+	/* inbound-side state */
+	s8 inbound __aligned(__CACHE_WRITEBACK_GRANULE);
+};
+
+struct sync_struct {
+	struct mcpm_sync_struct clusters[MAX_NR_CLUSTERS];
+};
+
+void __mcpm_cpu_going_down(unsigned int cpu, unsigned int cluster);
+void __mcpm_cpu_down(unsigned int cpu, unsigned int cluster);
+void __mcpm_outbound_leave_critical(unsigned int cluster, int state);
+bool __mcpm_outbound_enter_critical(unsigned int this_cpu, unsigned int cluster);
+int __mcpm_cluster_state(unsigned int cluster);
+
+/**
+ * mcpm_sync_init - Initialize the cluster synchronization support
+ *
+ * @power_up_setup: platform specific function invoked during very
+ * 		    early CPU/cluster bringup stage.
+ *
+ * This prepares memory used by vlocks and the MCPM state machine used
+ * across CPUs that may have their caches active or inactive. Must be
+ * called only after a successful call to mcpm_platform_register().
+ *
+ * The power_up_setup argument is a pointer to assembly code called when
+ * the MMU and caches are still disabled during boot  and no stack space is
+ * available. The affinity level passed to that code corresponds to the
+ * resource that needs to be initialized (e.g. 1 for cluster level, 0 for
+ * CPU level).  Proper exclusion mechanisms are already activated at that
+ * point.
+ */
+int __init mcpm_sync_init(
+	void (*power_up_setup)(unsigned int affinity_level));
+
+/**
+ * mcpm_loopback - make a run through the MCPM low-level code
+ *
+ * @cache_disable: pointer to function performing cache disabling
+ *
+ * This exercises the MCPM machinery by soft resetting the CPU and branching
+ * to the MCPM low-level entry code before returning to the caller.
+ * The @cache_disable function must do the necessary cache disabling to
+ * let the regular kernel init code turn it back on as if the CPU was
+ * hotplugged in. The MCPM state machine is set as if the cluster was
+ * initialized meaning the power_up_setup callback passed to mcpm_sync_init()
+ * will be invoked for all affinity levels. This may be useful to initialize
+ * some resources such as enabling the CCI that requires the cache to be off, or simply for testing purposes.
+ */
+int __init mcpm_loopback(void (*cache_disable)(void));
+
+void __init mcpm_smp_set_ops(void);
+
+#else
+
+/* 
+ * asm-offsets.h causes trouble when included in .c files, and cacheflush.h
+ * cannot be included in asm files.  Let's work around the conflict like this.
+ */
+#include <asm/asm-offsets.h>
+#define __CACHE_WRITEBACK_GRANULE CACHE_WRITEBACK_GRANULE
+
+#endif /* ! __ASSEMBLY__ */
+
+/* Definitions for mcpm_sync_struct */
+#define CPU_DOWN		0x11
+#define CPU_COMING_UP		0x12
+#define CPU_UP			0x13
+#define CPU_GOING_DOWN		0x14
+
+#define CLUSTER_DOWN		0x21
+#define CLUSTER_UP		0x22
+#define CLUSTER_GOING_DOWN	0x23
+
+#define INBOUND_NOT_COMING_UP	0x31
+#define INBOUND_COMING_UP	0x32
+
+/*
+ * Offsets for the mcpm_sync_struct members, for use in asm.
+ * We don't want to make them global to the kernel via asm-offsets.c.
+ */
+#define MCPM_SYNC_CLUSTER_CPUS	0
+#define MCPM_SYNC_CPU_SIZE	__CACHE_WRITEBACK_GRANULE
+#define MCPM_SYNC_CLUSTER_CLUSTER \
+	(MCPM_SYNC_CLUSTER_CPUS + MCPM_SYNC_CPU_SIZE * MAX_CPUS_PER_CLUSTER)
+#define MCPM_SYNC_CLUSTER_INBOUND \
+	(MCPM_SYNC_CLUSTER_CLUSTER + __CACHE_WRITEBACK_GRANULE)
+#define MCPM_SYNC_CLUSTER_SIZE \
+	(MCPM_SYNC_CLUSTER_INBOUND + __CACHE_WRITEBACK_GRANULE)
+
+#endif
diff --git a/arch/arm/include/asm/mcs_spinlock.h b/arch/arm/include/asm/mcs_spinlock.h
new file mode 100644
index 000000000..f652ad658
--- /dev/null
+++ b/arch/arm/include/asm/mcs_spinlock.h
@@ -0,0 +1,23 @@
+#ifndef __ASM_MCS_LOCK_H
+#define __ASM_MCS_LOCK_H
+
+#ifdef CONFIG_SMP
+#include <asm/spinlock.h>
+
+/* MCS spin-locking. */
+#define arch_mcs_spin_lock_contended(lock)				\
+do {									\
+	/* Ensure prior stores are observed before we enter wfe. */	\
+	smp_mb();							\
+	while (!(smp_load_acquire(lock)))				\
+		wfe();							\
+} while (0)								\
+
+#define arch_mcs_spin_unlock_contended(lock)				\
+do {									\
+	smp_store_release(lock, 1);					\
+	dsb_sev();							\
+} while (0)
+
+#endif	/* CONFIG_SMP */
+#endif	/* __ASM_MCS_LOCK_H */
diff --git a/arch/arm/include/asm/memblock.h b/arch/arm/include/asm/memblock.h
new file mode 100644
index 000000000..bf47a6c11
--- /dev/null
+++ b/arch/arm/include/asm/memblock.h
@@ -0,0 +1,9 @@
+#ifndef _ASM_ARM_MEMBLOCK_H
+#define _ASM_ARM_MEMBLOCK_H
+
+struct machine_desc;
+
+void arm_memblock_init(const struct machine_desc *);
+phys_addr_t arm_memblock_steal(phys_addr_t size, phys_addr_t align);
+
+#endif
diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h
new file mode 100644
index 000000000..184def0e1
--- /dev/null
+++ b/arch/arm/include/asm/memory.h
@@ -0,0 +1,359 @@
+/*
+ *  arch/arm/include/asm/memory.h
+ *
+ *  Copyright (C) 2000-2002 Russell King
+ *  modification for nommu, Hyok S. Choi, 2004
+ *
+ * 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.
+ *
+ *  Note: this file should not be included by non-asm/.h files
+ */
+#ifndef __ASM_ARM_MEMORY_H
+#define __ASM_ARM_MEMORY_H
+
+#include <linux/compiler.h>
+#include <linux/const.h>
+#include <linux/types.h>
+#include <linux/sizes.h>
+
+#include <asm/cache.h>
+
+#ifdef CONFIG_NEED_MACH_MEMORY_H
+#include <mach/memory.h>
+#endif
+
+/*
+ * Allow for constants defined here to be used from assembly code
+ * by prepending the UL suffix only with actual C code compilation.
+ */
+#define UL(x) _AC(x, UL)
+
+/* PAGE_OFFSET - the virtual address of the start of the kernel image */
+#define PAGE_OFFSET		UL(CONFIG_PAGE_OFFSET)
+
+#ifdef CONFIG_MMU
+
+/*
+ * TASK_SIZE - the maximum size of a user space task.
+ * TASK_UNMAPPED_BASE - the lower boundary of the mmap VM area
+ */
+#define TASK_SIZE		(UL(CONFIG_PAGE_OFFSET) - UL(SZ_16M))
+#define TASK_UNMAPPED_BASE	ALIGN(TASK_SIZE / 3, SZ_16M)
+
+/*
+ * The maximum size of a 26-bit user space task.
+ */
+#define TASK_SIZE_26		(UL(1) << 26)
+
+/*
+ * The module space lives between the addresses given by TASK_SIZE
+ * and PAGE_OFFSET - it must be within 32MB of the kernel text.
+ */
+#ifndef CONFIG_THUMB2_KERNEL
+#define MODULES_VADDR		(PAGE_OFFSET - SZ_16M)
+#else
+/* smaller range for Thumb-2 symbols relocation (2^24)*/
+#define MODULES_VADDR		(PAGE_OFFSET - SZ_8M)
+#endif
+
+#if TASK_SIZE > MODULES_VADDR
+#error Top of user space clashes with start of module space
+#endif
+
+/*
+ * The highmem pkmap virtual space shares the end of the module area.
+ */
+#ifdef CONFIG_HIGHMEM
+#define MODULES_END		(PAGE_OFFSET - PMD_SIZE)
+#else
+#define MODULES_END		(PAGE_OFFSET)
+#endif
+
+/*
+ * The XIP kernel gets mapped at the bottom of the module vm area.
+ * Since we use sections to map it, this macro replaces the physical address
+ * with its virtual address while keeping offset from the base section.
+ */
+#define XIP_VIRT_ADDR(physaddr)  (MODULES_VADDR + ((physaddr) & 0x000fffff))
+
+/*
+ * Allow 16MB-aligned ioremap pages
+ */
+#define IOREMAP_MAX_ORDER	24
+
+#else /* CONFIG_MMU */
+
+/*
+ * The limitation of user task size can grow up to the end of free ram region.
+ * It is difficult to define and perhaps will never meet the original meaning
+ * of this define that was meant to.
+ * Fortunately, there is no reference for this in noMMU mode, for now.
+ */
+#define TASK_SIZE		UL(0xffffffff)
+
+#ifndef TASK_UNMAPPED_BASE
+#define TASK_UNMAPPED_BASE	UL(0x00000000)
+#endif
+
+#ifndef END_MEM
+#define END_MEM     		(UL(CONFIG_DRAM_BASE) + CONFIG_DRAM_SIZE)
+#endif
+
+/*
+ * The module can be at any place in ram in nommu mode.
+ */
+#define MODULES_END		(END_MEM)
+#define MODULES_VADDR		PAGE_OFFSET
+
+#define XIP_VIRT_ADDR(physaddr)  (physaddr)
+
+#endif /* !CONFIG_MMU */
+
+/*
+ * We fix the TCM memories max 32 KiB ITCM resp DTCM at these
+ * locations
+ */
+#ifdef CONFIG_HAVE_TCM
+#define ITCM_OFFSET	UL(0xfffe0000)
+#define DTCM_OFFSET	UL(0xfffe8000)
+#endif
+
+/*
+ * Convert a physical address to a Page Frame Number and back
+ */
+#define	__phys_to_pfn(paddr)	((unsigned long)((paddr) >> PAGE_SHIFT))
+#define	__pfn_to_phys(pfn)	((phys_addr_t)(pfn) << PAGE_SHIFT)
+
+/*
+ * Convert a page to/from a physical address
+ */
+#define page_to_phys(page)	(__pfn_to_phys(page_to_pfn(page)))
+#define phys_to_page(phys)	(pfn_to_page(__phys_to_pfn(phys)))
+
+/*
+ * Minimum guaranted alignment in pgd_alloc().  The page table pointers passed
+ * around in head.S and proc-*.S are shifted by this amount, in order to
+ * leave spare high bits for systems with physical address extension.  This
+ * does not fully accomodate the 40-bit addressing capability of ARM LPAE, but
+ * gives us about 38-bits or so.
+ */
+#ifdef CONFIG_ARM_LPAE
+#define ARCH_PGD_SHIFT		L1_CACHE_SHIFT
+#else
+#define ARCH_PGD_SHIFT		0
+#endif
+#define ARCH_PGD_MASK		((1 << ARCH_PGD_SHIFT) - 1)
+
+/*
+ * PLAT_PHYS_OFFSET is the offset (from zero) of the start of physical
+ * memory.  This is used for XIP and NoMMU kernels, and on platforms that don't
+ * have CONFIG_ARM_PATCH_PHYS_VIRT. Assembly code must always use
+ * PLAT_PHYS_OFFSET and not PHYS_OFFSET.
+ */
+#define PLAT_PHYS_OFFSET	UL(CONFIG_PHYS_OFFSET)
+
+#ifndef __ASSEMBLY__
+
+/*
+ * Physical vs virtual RAM address space conversion.  These are
+ * private definitions which should NOT be used outside memory.h
+ * files.  Use virt_to_phys/phys_to_virt/__pa/__va instead.
+ *
+ * PFNs are used to describe any physical page; this means
+ * PFN 0 == physical address 0.
+ */
+#if defined(__virt_to_phys)
+#define PHYS_OFFSET	PLAT_PHYS_OFFSET
+#define PHYS_PFN_OFFSET	((unsigned long)(PHYS_OFFSET >> PAGE_SHIFT))
+
+#define virt_to_pfn(kaddr) (__pa(kaddr) >> PAGE_SHIFT)
+
+#elif defined(CONFIG_ARM_PATCH_PHYS_VIRT)
+
+/*
+ * Constants used to force the right instruction encodings and shifts
+ * so that all we need to do is modify the 8-bit constant field.
+ */
+#define __PV_BITS_31_24	0x81000000
+#define __PV_BITS_7_0	0x81
+
+extern unsigned long __pv_phys_pfn_offset;
+extern u64 __pv_offset;
+extern void fixup_pv_table(const void *, unsigned long);
+extern const void *__pv_table_begin, *__pv_table_end;
+
+#define PHYS_OFFSET	((phys_addr_t)__pv_phys_pfn_offset << PAGE_SHIFT)
+#define PHYS_PFN_OFFSET	(__pv_phys_pfn_offset)
+
+#define virt_to_pfn(kaddr) \
+	((((unsigned long)(kaddr) - PAGE_OFFSET) >> PAGE_SHIFT) + \
+	 PHYS_PFN_OFFSET)
+
+#define __pv_stub(from,to,instr,type)			\
+	__asm__("@ __pv_stub\n"				\
+	"1:	" instr "	%0, %1, %2\n"		\
+	"	.pushsection .pv_table,\"a\"\n"		\
+	"	.long	1b\n"				\
+	"	.popsection\n"				\
+	: "=r" (to)					\
+	: "r" (from), "I" (type))
+
+#define __pv_stub_mov_hi(t)				\
+	__asm__ volatile("@ __pv_stub_mov\n"		\
+	"1:	mov	%R0, %1\n"			\
+	"	.pushsection .pv_table,\"a\"\n"		\
+	"	.long	1b\n"				\
+	"	.popsection\n"				\
+	: "=r" (t)					\
+	: "I" (__PV_BITS_7_0))
+
+#define __pv_add_carry_stub(x, y)			\
+	__asm__ volatile("@ __pv_add_carry_stub\n"	\
+	"1:	adds	%Q0, %1, %2\n"			\
+	"	adc	%R0, %R0, #0\n"			\
+	"	.pushsection .pv_table,\"a\"\n"		\
+	"	.long	1b\n"				\
+	"	.popsection\n"				\
+	: "+r" (y)					\
+	: "r" (x), "I" (__PV_BITS_31_24)		\
+	: "cc")
+
+static inline phys_addr_t __virt_to_phys(unsigned long x)
+{
+	phys_addr_t t;
+
+	if (sizeof(phys_addr_t) == 4) {
+		__pv_stub(x, t, "add", __PV_BITS_31_24);
+	} else {
+		__pv_stub_mov_hi(t);
+		__pv_add_carry_stub(x, t);
+	}
+	return t;
+}
+
+static inline unsigned long __phys_to_virt(phys_addr_t x)
+{
+	unsigned long t;
+
+	/*
+	 * 'unsigned long' cast discard upper word when
+	 * phys_addr_t is 64 bit, and makes sure that inline
+	 * assembler expression receives 32 bit argument
+	 * in place where 'r' 32 bit operand is expected.
+	 */
+	__pv_stub((unsigned long) x, t, "sub", __PV_BITS_31_24);
+	return t;
+}
+
+#else
+
+#define PHYS_OFFSET	PLAT_PHYS_OFFSET
+#define PHYS_PFN_OFFSET	((unsigned long)(PHYS_OFFSET >> PAGE_SHIFT))
+
+static inline phys_addr_t __virt_to_phys(unsigned long x)
+{
+	return (phys_addr_t)x - PAGE_OFFSET + PHYS_OFFSET;
+}
+
+static inline unsigned long __phys_to_virt(phys_addr_t x)
+{
+	return x - PHYS_OFFSET + PAGE_OFFSET;
+}
+
+#define virt_to_pfn(kaddr) \
+	((((unsigned long)(kaddr) - PAGE_OFFSET) >> PAGE_SHIFT) + \
+	 PHYS_PFN_OFFSET)
+
+#endif
+
+/*
+ * These are *only* valid on the kernel direct mapped RAM memory.
+ * Note: Drivers should NOT use these.  They are the wrong
+ * translation for translating DMA addresses.  Use the driver
+ * DMA support - see dma-mapping.h.
+ */
+#define virt_to_phys virt_to_phys
+static inline phys_addr_t virt_to_phys(const volatile void *x)
+{
+	return __virt_to_phys((unsigned long)(x));
+}
+
+#define phys_to_virt phys_to_virt
+static inline void *phys_to_virt(phys_addr_t x)
+{
+	return (void *)__phys_to_virt(x);
+}
+
+/*
+ * Drivers should NOT use these either.
+ */
+#define __pa(x)			__virt_to_phys((unsigned long)(x))
+#define __va(x)			((void *)__phys_to_virt((phys_addr_t)(x)))
+#define pfn_to_kaddr(pfn)	__va((pfn) << PAGE_SHIFT)
+
+extern phys_addr_t (*arch_virt_to_idmap)(unsigned long x);
+
+/*
+ * These are for systems that have a hardware interconnect supported alias of
+ * physical memory for idmap purposes.  Most cases should leave these
+ * untouched.
+ */
+static inline phys_addr_t __virt_to_idmap(unsigned long x)
+{
+	if (arch_virt_to_idmap)
+		return arch_virt_to_idmap(x);
+	else
+		return __virt_to_phys(x);
+}
+
+#define virt_to_idmap(x)	__virt_to_idmap((unsigned long)(x))
+
+/*
+ * Virtual <-> DMA view memory address translations
+ * Again, these are *only* valid on the kernel direct mapped RAM
+ * memory.  Use of these is *deprecated* (and that doesn't mean
+ * use the __ prefixed forms instead.)  See dma-mapping.h.
+ */
+#ifndef __virt_to_bus
+#define __virt_to_bus	__virt_to_phys
+#define __bus_to_virt	__phys_to_virt
+#define __pfn_to_bus(x)	__pfn_to_phys(x)
+#define __bus_to_pfn(x)	__phys_to_pfn(x)
+#endif
+
+#ifdef CONFIG_VIRT_TO_BUS
+#define virt_to_bus virt_to_bus
+static inline __deprecated unsigned long virt_to_bus(void *x)
+{
+	return __virt_to_bus((unsigned long)x);
+}
+
+#define bus_to_virt bus_to_virt
+static inline __deprecated void *bus_to_virt(unsigned long x)
+{
+	return (void *)__bus_to_virt(x);
+}
+#endif
+
+/*
+ * Conversion between a struct page and a physical address.
+ *
+ *  page_to_pfn(page)	convert a struct page * to a PFN number
+ *  pfn_to_page(pfn)	convert a _valid_ PFN number to struct page *
+ *
+ *  virt_to_page(k)	convert a _valid_ virtual address to struct page *
+ *  virt_addr_valid(k)	indicates whether a virtual address is valid
+ */
+#define ARCH_PFN_OFFSET		PHYS_PFN_OFFSET
+
+#define virt_to_page(kaddr)	pfn_to_page(virt_to_pfn(kaddr))
+#define virt_addr_valid(kaddr)	(((unsigned long)(kaddr) >= PAGE_OFFSET && (unsigned long)(kaddr) < (unsigned long)high_memory) \
+					&& pfn_valid(virt_to_pfn(kaddr)))
+
+#endif
+
+#include <asm-generic/memory_model.h>
+
+#endif
diff --git a/arch/arm/include/asm/mmu.h b/arch/arm/include/asm/mmu.h
new file mode 100644
index 000000000..a5b474210
--- /dev/null
+++ b/arch/arm/include/asm/mmu.h
@@ -0,0 +1,40 @@
+#ifndef __ARM_MMU_H
+#define __ARM_MMU_H
+
+#ifdef CONFIG_MMU
+
+typedef struct {
+#ifdef CONFIG_CPU_HAS_ASID
+	atomic64_t	id;
+#else
+	int		switch_pending;
+#endif
+	unsigned int	vmalloc_seq;
+	unsigned long	sigpage;
+#ifdef CONFIG_VDSO
+	unsigned long	vdso;
+#endif
+} mm_context_t;
+
+#ifdef CONFIG_CPU_HAS_ASID
+#define ASID_BITS	8
+#define ASID_MASK	((~0ULL) << ASID_BITS)
+#define ASID(mm)	((unsigned int)((mm)->context.id.counter & ~ASID_MASK))
+#else
+#define ASID(mm)	(0)
+#endif
+
+#else
+
+/*
+ * From nommu.h:
+ *  Copyright (C) 2002, David McCullough <davidm@snapgear.com>
+ *  modified for 2.6 by Hyok S. Choi <hyok.choi@samsung.com>
+ */
+typedef struct {
+	unsigned long	end_brk;
+} mm_context_t;
+
+#endif
+
+#endif
diff --git a/arch/arm/include/asm/mmu_context.h b/arch/arm/include/asm/mmu_context.h
new file mode 100644
index 000000000..9b32f76bb
--- /dev/null
+++ b/arch/arm/include/asm/mmu_context.h
@@ -0,0 +1,142 @@
+/*
+ *  arch/arm/include/asm/mmu_context.h
+ *
+ *  Copyright (C) 1996 Russell King.
+ *
+ * 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.
+ *
+ *  Changelog:
+ *   27-06-1996	RMK	Created
+ */
+#ifndef __ASM_ARM_MMU_CONTEXT_H
+#define __ASM_ARM_MMU_CONTEXT_H
+
+#include <linux/compiler.h>
+#include <linux/sched.h>
+#include <asm/cacheflush.h>
+#include <asm/cachetype.h>
+#include <asm/proc-fns.h>
+#include <asm/smp_plat.h>
+#include <asm-generic/mm_hooks.h>
+
+void __check_vmalloc_seq(struct mm_struct *mm);
+
+#ifdef CONFIG_CPU_HAS_ASID
+
+void check_and_switch_context(struct mm_struct *mm, struct task_struct *tsk);
+#define init_new_context(tsk,mm)	({ atomic64_set(&mm->context.id, 0); 0; })
+
+#ifdef CONFIG_ARM_ERRATA_798181
+void a15_erratum_get_cpumask(int this_cpu, struct mm_struct *mm,
+			     cpumask_t *mask);
+#else  /* !CONFIG_ARM_ERRATA_798181 */
+static inline void a15_erratum_get_cpumask(int this_cpu, struct mm_struct *mm,
+					   cpumask_t *mask)
+{
+}
+#endif /* CONFIG_ARM_ERRATA_798181 */
+
+#else	/* !CONFIG_CPU_HAS_ASID */
+
+#ifdef CONFIG_MMU
+
+static inline void check_and_switch_context(struct mm_struct *mm,
+					    struct task_struct *tsk)
+{
+	if (unlikely(mm->context.vmalloc_seq != init_mm.context.vmalloc_seq))
+		__check_vmalloc_seq(mm);
+
+	if (irqs_disabled())
+		/*
+		 * cpu_switch_mm() needs to flush the VIVT caches. To avoid
+		 * high interrupt latencies, defer the call and continue
+		 * running with the old mm. Since we only support UP systems
+		 * on non-ASID CPUs, the old mm will remain valid until the
+		 * finish_arch_post_lock_switch() call.
+		 */
+		mm->context.switch_pending = 1;
+	else
+		cpu_switch_mm(mm->pgd, mm);
+}
+
+#define finish_arch_post_lock_switch \
+	finish_arch_post_lock_switch
+static inline void finish_arch_post_lock_switch(void)
+{
+	struct mm_struct *mm = current->mm;
+
+	if (mm && mm->context.switch_pending) {
+		/*
+		 * Preemption must be disabled during cpu_switch_mm() as we
+		 * have some stateful cache flush implementations. Check
+		 * switch_pending again in case we were preempted and the
+		 * switch to this mm was already done.
+		 */
+		preempt_disable();
+		if (mm->context.switch_pending) {
+			mm->context.switch_pending = 0;
+			cpu_switch_mm(mm->pgd, mm);
+		}
+		preempt_enable_no_resched();
+	}
+}
+
+#endif	/* CONFIG_MMU */
+
+#define init_new_context(tsk,mm)	0
+
+#endif	/* CONFIG_CPU_HAS_ASID */
+
+#define destroy_context(mm)		do { } while(0)
+#define activate_mm(prev,next)		switch_mm(prev, next, NULL)
+
+/*
+ * This is called when "tsk" is about to enter lazy TLB mode.
+ *
+ * mm:  describes the currently active mm context
+ * tsk: task which is entering lazy tlb
+ * cpu: cpu number which is entering lazy tlb
+ *
+ * tsk->mm will be NULL
+ */
+static inline void
+enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
+{
+}
+
+/*
+ * This is the actual mm switch as far as the scheduler
+ * is concerned.  No registers are touched.  We avoid
+ * calling the CPU specific function when the mm hasn't
+ * actually changed.
+ */
+static inline void
+switch_mm(struct mm_struct *prev, struct mm_struct *next,
+	  struct task_struct *tsk)
+{
+#ifdef CONFIG_MMU
+	unsigned int cpu = smp_processor_id();
+
+	/*
+	 * __sync_icache_dcache doesn't broadcast the I-cache invalidation,
+	 * so check for possible thread migration and invalidate the I-cache
+	 * if we're new to this CPU.
+	 */
+	if (cache_ops_need_broadcast() &&
+	    !cpumask_empty(mm_cpumask(next)) &&
+	    !cpumask_test_cpu(cpu, mm_cpumask(next)))
+		__flush_icache_all();
+
+	if (!cpumask_test_and_set_cpu(cpu, mm_cpumask(next)) || prev != next) {
+		check_and_switch_context(next, tsk);
+		if (cache_is_vivt())
+			cpumask_clear_cpu(cpu, mm_cpumask(prev));
+	}
+#endif
+}
+
+#define deactivate_mm(tsk,mm)	do { } while (0)
+
+#endif
diff --git a/arch/arm/include/asm/module.h b/arch/arm/include/asm/module.h
new file mode 100644
index 000000000..ed690c49e
--- /dev/null
+++ b/arch/arm/include/asm/module.h
@@ -0,0 +1,49 @@
+#ifndef _ASM_ARM_MODULE_H
+#define _ASM_ARM_MODULE_H
+
+#include <asm-generic/module.h>
+
+struct unwind_table;
+
+#ifdef CONFIG_ARM_UNWIND
+enum {
+	ARM_SEC_INIT,
+	ARM_SEC_DEVINIT,
+	ARM_SEC_CORE,
+	ARM_SEC_EXIT,
+	ARM_SEC_DEVEXIT,
+	ARM_SEC_HOT,
+	ARM_SEC_UNLIKELY,
+	ARM_SEC_MAX,
+};
+
+struct mod_arch_specific {
+	struct unwind_table *unwind[ARM_SEC_MAX];
+};
+#endif
+
+/*
+ * Add the ARM architecture version to the version magic string
+ */
+#define MODULE_ARCH_VERMAGIC_ARMVSN "ARMv" __stringify(__LINUX_ARM_ARCH__) " "
+
+/* Add __virt_to_phys patching state as well */
+#ifdef CONFIG_ARM_PATCH_PHYS_VIRT
+#define MODULE_ARCH_VERMAGIC_P2V "p2v8 "
+#else
+#define MODULE_ARCH_VERMAGIC_P2V ""
+#endif
+
+/* Add instruction set architecture tag to distinguish ARM/Thumb kernels */
+#ifdef CONFIG_THUMB2_KERNEL
+#define MODULE_ARCH_VERMAGIC_ARMTHUMB "thumb2 "
+#else
+#define MODULE_ARCH_VERMAGIC_ARMTHUMB ""
+#endif
+
+#define MODULE_ARCH_VERMAGIC \
+	MODULE_ARCH_VERMAGIC_ARMVSN \
+	MODULE_ARCH_VERMAGIC_ARMTHUMB \
+	MODULE_ARCH_VERMAGIC_P2V
+
+#endif /* _ASM_ARM_MODULE_H */
diff --git a/arch/arm/include/asm/mpu.h b/arch/arm/include/asm/mpu.h
new file mode 100644
index 000000000..c3247cc2f
--- /dev/null
+++ b/arch/arm/include/asm/mpu.h
@@ -0,0 +1,76 @@
+#ifndef __ARM_MPU_H
+#define __ARM_MPU_H
+
+#ifdef CONFIG_ARM_MPU
+
+/* MPUIR layout */
+#define MPUIR_nU		1
+#define MPUIR_DREGION		8
+#define MPUIR_IREGION		16
+#define MPUIR_DREGION_SZMASK	(0xFF << MPUIR_DREGION)
+#define MPUIR_IREGION_SZMASK	(0xFF << MPUIR_IREGION)
+
+/* ID_MMFR0 data relevant to MPU */
+#define MMFR0_PMSA		(0xF << 4)
+#define MMFR0_PMSAv7		(3 << 4)
+
+/* MPU D/I Size Register fields */
+#define MPU_RSR_SZ		1
+#define MPU_RSR_EN		0
+
+/* The D/I RSR value for an enabled region spanning the whole of memory */
+#define MPU_RSR_ALL_MEM		63
+
+/* Individual bits in the DR/IR ACR */
+#define MPU_ACR_XN		(1 << 12)
+#define MPU_ACR_SHARED		(1 << 2)
+
+/* C, B and TEX[2:0] bits only have semantic meanings when grouped */
+#define MPU_RGN_CACHEABLE	0xB
+#define MPU_RGN_SHARED_CACHEABLE (MPU_RGN_CACHEABLE | MPU_ACR_SHARED)
+#define MPU_RGN_STRONGLY_ORDERED 0
+
+/* Main region should only be shared for SMP */
+#ifdef CONFIG_SMP
+#define MPU_RGN_NORMAL		(MPU_RGN_CACHEABLE | MPU_ACR_SHARED)
+#else
+#define MPU_RGN_NORMAL		MPU_RGN_CACHEABLE
+#endif
+
+/* Access permission bits of ACR (only define those that we use)*/
+#define MPU_AP_PL1RW_PL0RW	(0x3 << 8)
+#define MPU_AP_PL1RW_PL0R0	(0x2 << 8)
+#define MPU_AP_PL1RW_PL0NA	(0x1 << 8)
+
+/* For minimal static MPU region configurations */
+#define MPU_PROBE_REGION	0
+#define MPU_BG_REGION		1
+#define MPU_RAM_REGION		2
+#define MPU_VECTORS_REGION	3
+
+/* Maximum number of regions Linux is interested in */
+#define MPU_MAX_REGIONS		16
+
+#define MPU_DATA_SIDE		0
+#define MPU_INSTR_SIDE		1
+
+#ifndef __ASSEMBLY__
+
+struct mpu_rgn {
+	/* Assume same attributes for d/i-side  */
+	u32 drbar;
+	u32 drsr;
+	u32 dracr;
+};
+
+struct mpu_rgn_info {
+	u32 mpuir;
+	struct mpu_rgn rgns[MPU_MAX_REGIONS];
+};
+extern struct mpu_rgn_info mpu_rgn_info;
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* CONFIG_ARM_MPU */
+
+#endif
diff --git a/arch/arm/include/asm/mtd-xip.h b/arch/arm/include/asm/mtd-xip.h
new file mode 100644
index 000000000..d79d66d2c
--- /dev/null
+++ b/arch/arm/include/asm/mtd-xip.h
@@ -0,0 +1,23 @@
+/*
+ * MTD primitives for XIP support. Architecture specific functions
+ *
+ * Do not include this file directly. It's included from linux/mtd/xip.h
+ * 
+ * Author:	Nicolas Pitre
+ * Created:	Nov 2, 2004
+ * Copyright:	(C) 2004 MontaVista Software, Inc.
+ *
+ * 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.
+ */
+
+#ifndef __ARM_MTD_XIP_H__
+#define __ARM_MTD_XIP_H__
+
+#include <mach/mtd-xip.h>
+
+/* fill instruction prefetch */
+#define xip_iprefetch() 	do { asm volatile (".rep 8; nop; .endr"); } while (0)
+
+#endif /* __ARM_MTD_XIP_H__ */
diff --git a/arch/arm/include/asm/mutex.h b/arch/arm/include/asm/mutex.h
new file mode 100644
index 000000000..87c044910
--- /dev/null
+++ b/arch/arm/include/asm/mutex.h
@@ -0,0 +1,21 @@
+/*
+ * arch/arm/include/asm/mutex.h
+ *
+ * ARM optimized mutex locking primitives
+ *
+ * Please look into asm-generic/mutex-xchg.h for a formal definition.
+ */
+#ifndef _ASM_MUTEX_H
+#define _ASM_MUTEX_H
+/*
+ * On pre-ARMv6 hardware this results in a swp-based implementation,
+ * which is the most efficient. For ARMv6+, we have exclusive memory
+ * accessors and use atomic_dec to avoid the extra xchg operations
+ * on the locking slowpaths.
+ */
+#if __LINUX_ARM_ARCH__ < 6
+#include <asm-generic/mutex-xchg.h>
+#else
+#include <asm-generic/mutex-dec.h>
+#endif
+#endif	/* _ASM_MUTEX_H */
diff --git a/arch/arm/include/asm/neon.h b/arch/arm/include/asm/neon.h
new file mode 100644
index 000000000..8f730fe70
--- /dev/null
+++ b/arch/arm/include/asm/neon.h
@@ -0,0 +1,36 @@
+/*
+ * linux/arch/arm/include/asm/neon.h
+ *
+ * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * 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.
+ */
+
+#include <asm/hwcap.h>
+
+#define cpu_has_neon()		(!!(elf_hwcap & HWCAP_NEON))
+
+#ifdef __ARM_NEON__
+
+/*
+ * If you are affected by the BUILD_BUG below, it probably means that you are
+ * using NEON code /and/ calling the kernel_neon_begin() function from the same
+ * compilation unit. To prevent issues that may arise from GCC reordering or
+ * generating(1) NEON instructions outside of these begin/end functions, the
+ * only supported way of using NEON code in the kernel is by isolating it in a
+ * separate compilation unit, and calling it from another unit from inside a
+ * kernel_neon_begin/kernel_neon_end pair.
+ *
+ * (1) Current GCC (4.7) might generate NEON instructions at O3 level if
+ *     -mpfu=neon is set.
+ */
+
+#define kernel_neon_begin() \
+	BUILD_BUG_ON_MSG(1, "kernel_neon_begin() called from NEON code")
+
+#else
+void kernel_neon_begin(void);
+#endif
+void kernel_neon_end(void);
diff --git a/arch/arm/include/asm/nwflash.h b/arch/arm/include/asm/nwflash.h
new file mode 100644
index 000000000..04e5a557a
--- /dev/null
+++ b/arch/arm/include/asm/nwflash.h
@@ -0,0 +1,9 @@
+#ifndef _FLASH_H
+#define _FLASH_H
+
+#define FLASH_MINOR		 160	/* MAJOR is 10 - miscdevice */
+#define CMD_WRITE_DISABLE	 0
+#define CMD_WRITE_ENABLE	 0x28
+#define CMD_WRITE_BASE64K_ENABLE 0x47
+
+#endif /* _FLASH_H */
diff --git a/arch/arm/include/asm/opcodes-sec.h b/arch/arm/include/asm/opcodes-sec.h
new file mode 100644
index 000000000..bc3a91744
--- /dev/null
+++ b/arch/arm/include/asm/opcodes-sec.h
@@ -0,0 +1,24 @@
+/*
+ * 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.
+ *
+ * Copyright (C) 2012 ARM Limited
+ */
+
+#ifndef __ASM_ARM_OPCODES_SEC_H
+#define __ASM_ARM_OPCODES_SEC_H
+
+#include <asm/opcodes.h>
+
+#define __SMC(imm4) __inst_arm_thumb32(					\
+	0xE1600070 | (((imm4) & 0xF) << 0),				\
+	0xF7F08000 | (((imm4) & 0xF) << 16)				\
+)
+
+#endif /* __ASM_ARM_OPCODES_SEC_H */
diff --git a/arch/arm/include/asm/opcodes-virt.h b/arch/arm/include/asm/opcodes-virt.h
new file mode 100644
index 000000000..efcfdf92d
--- /dev/null
+++ b/arch/arm/include/asm/opcodes-virt.h
@@ -0,0 +1,39 @@
+/*
+ * opcodes-virt.h: Opcode definitions for the ARM virtualization extensions
+ * Copyright (C) 2012  Linaro Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * 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, write to the Free Software Foundation, Inc.,
+ * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+ */
+#ifndef __ASM_ARM_OPCODES_VIRT_H
+#define __ASM_ARM_OPCODES_VIRT_H
+
+#include <asm/opcodes.h>
+
+#define __HVC(imm16) __inst_arm_thumb32(				\
+	0xE1400070 | (((imm16) & 0xFFF0) << 4) | ((imm16) & 0x000F),	\
+	0xF7E08000 | (((imm16) & 0xF000) << 4) | ((imm16) & 0x0FFF)	\
+)
+
+#define __ERET	__inst_arm_thumb32(					\
+	0xE160006E,							\
+	0xF3DE8F00							\
+)
+
+#define __MSR_ELR_HYP(regnum)	__inst_arm_thumb32(			\
+	0xE12EF300 | regnum,						\
+	0xF3808E30 | (regnum << 16)					\
+)
+
+#endif /* ! __ASM_ARM_OPCODES_VIRT_H */
diff --git a/arch/arm/include/asm/opcodes.h b/arch/arm/include/asm/opcodes.h
new file mode 100644
index 000000000..e796c5985
--- /dev/null
+++ b/arch/arm/include/asm/opcodes.h
@@ -0,0 +1,231 @@
+/*
+ *  arch/arm/include/asm/opcodes.h
+ *
+ * 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.
+ */
+
+#ifndef __ASM_ARM_OPCODES_H
+#define __ASM_ARM_OPCODES_H
+
+#ifndef __ASSEMBLY__
+#include <linux/linkage.h>
+extern asmlinkage unsigned int arm_check_condition(u32 opcode, u32 psr);
+#endif
+
+#define ARM_OPCODE_CONDTEST_FAIL   0
+#define ARM_OPCODE_CONDTEST_PASS   1
+#define ARM_OPCODE_CONDTEST_UNCOND 2
+
+
+/*
+ * Assembler opcode byteswap helpers.
+ * These are only intended for use by this header: don't use them directly,
+ * because they will be suboptimal in most cases.
+ */
+#define ___asm_opcode_swab32(x) (	\
+	  (((x) << 24) & 0xFF000000)	\
+	| (((x) <<  8) & 0x00FF0000)	\
+	| (((x) >>  8) & 0x0000FF00)	\
+	| (((x) >> 24) & 0x000000FF)	\
+)
+#define ___asm_opcode_swab16(x) (	\
+	  (((x) << 8) & 0xFF00)		\
+	| (((x) >> 8) & 0x00FF)		\
+)
+#define ___asm_opcode_swahb32(x) (	\
+	  (((x) << 8) & 0xFF00FF00)	\
+	| (((x) >> 8) & 0x00FF00FF)	\
+)
+#define ___asm_opcode_swahw32(x) (	\
+	  (((x) << 16) & 0xFFFF0000)	\
+	| (((x) >> 16) & 0x0000FFFF)	\
+)
+#define ___asm_opcode_identity32(x) ((x) & 0xFFFFFFFF)
+#define ___asm_opcode_identity16(x) ((x) & 0xFFFF)
+
+
+/*
+ * Opcode byteswap helpers
+ *
+ * These macros help with converting instructions between a canonical integer
+ * format and in-memory representation, in an endianness-agnostic manner.
+ *
+ * __mem_to_opcode_*() convert from in-memory representation to canonical form.
+ * __opcode_to_mem_*() convert from canonical form to in-memory representation.
+ *
+ *
+ * Canonical instruction representation:
+ *
+ *	ARM:		0xKKLLMMNN
+ *	Thumb 16-bit:	0x0000KKLL, where KK < 0xE8
+ *	Thumb 32-bit:	0xKKLLMMNN, where KK >= 0xE8
+ *
+ * There is no way to distinguish an ARM instruction in canonical representation
+ * from a Thumb instruction (just as these cannot be distinguished in memory).
+ * Where this distinction is important, it needs to be tracked separately.
+ *
+ * Note that values in the range 0x0000E800..0xE7FFFFFF intentionally do not
+ * represent any valid Thumb-2 instruction.  For this range,
+ * __opcode_is_thumb32() and __opcode_is_thumb16() will both be false.
+ *
+ * The ___asm variants are intended only for use by this header, in situations
+ * involving inline assembler.  For .S files, the normal __opcode_*() macros
+ * should do the right thing.
+ */
+#ifdef __ASSEMBLY__
+
+#define ___opcode_swab32(x) ___asm_opcode_swab32(x)
+#define ___opcode_swab16(x) ___asm_opcode_swab16(x)
+#define ___opcode_swahb32(x) ___asm_opcode_swahb32(x)
+#define ___opcode_swahw32(x) ___asm_opcode_swahw32(x)
+#define ___opcode_identity32(x) ___asm_opcode_identity32(x)
+#define ___opcode_identity16(x) ___asm_opcode_identity16(x)
+
+#else /* ! __ASSEMBLY__ */
+
+#include <linux/types.h>
+#include <linux/swab.h>
+
+#define ___opcode_swab32(x) swab32(x)
+#define ___opcode_swab16(x) swab16(x)
+#define ___opcode_swahb32(x) swahb32(x)
+#define ___opcode_swahw32(x) swahw32(x)
+#define ___opcode_identity32(x) ((u32)(x))
+#define ___opcode_identity16(x) ((u16)(x))
+
+#endif /* ! __ASSEMBLY__ */
+
+
+#ifdef CONFIG_CPU_ENDIAN_BE8
+
+#define __opcode_to_mem_arm(x) ___opcode_swab32(x)
+#define __opcode_to_mem_thumb16(x) ___opcode_swab16(x)
+#define __opcode_to_mem_thumb32(x) ___opcode_swahb32(x)
+#define ___asm_opcode_to_mem_arm(x) ___asm_opcode_swab32(x)
+#define ___asm_opcode_to_mem_thumb16(x) ___asm_opcode_swab16(x)
+#define ___asm_opcode_to_mem_thumb32(x) ___asm_opcode_swahb32(x)
+
+#else /* ! CONFIG_CPU_ENDIAN_BE8 */
+
+#define __opcode_to_mem_arm(x) ___opcode_identity32(x)
+#define __opcode_to_mem_thumb16(x) ___opcode_identity16(x)
+#define ___asm_opcode_to_mem_arm(x) ___asm_opcode_identity32(x)
+#define ___asm_opcode_to_mem_thumb16(x) ___asm_opcode_identity16(x)
+#ifndef CONFIG_CPU_ENDIAN_BE32
+/*
+ * On BE32 systems, using 32-bit accesses to store Thumb instructions will not
+ * work in all cases, due to alignment constraints.  For now, a correct
+ * version is not provided for BE32.
+ */
+#define __opcode_to_mem_thumb32(x) ___opcode_swahw32(x)
+#define ___asm_opcode_to_mem_thumb32(x) ___asm_opcode_swahw32(x)
+#endif
+
+#endif /* ! CONFIG_CPU_ENDIAN_BE8 */
+
+#define __mem_to_opcode_arm(x) __opcode_to_mem_arm(x)
+#define __mem_to_opcode_thumb16(x) __opcode_to_mem_thumb16(x)
+#ifndef CONFIG_CPU_ENDIAN_BE32
+#define __mem_to_opcode_thumb32(x) __opcode_to_mem_thumb32(x)
+#endif
+
+/* Operations specific to Thumb opcodes */
+
+/* Instruction size checks: */
+#define __opcode_is_thumb32(x) (		\
+	   ((x) & 0xF8000000) == 0xE8000000	\
+	|| ((x) & 0xF0000000) == 0xF0000000	\
+)
+#define __opcode_is_thumb16(x) (					\
+	   ((x) & 0xFFFF0000) == 0					\
+	&& !(((x) & 0xF800) == 0xE800 || ((x) & 0xF000) == 0xF000)	\
+)
+
+/* Operations to construct or split 32-bit Thumb instructions: */
+#define __opcode_thumb32_first(x) (___opcode_identity16((x) >> 16))
+#define __opcode_thumb32_second(x) (___opcode_identity16(x))
+#define __opcode_thumb32_compose(first, second) (			\
+	  (___opcode_identity32(___opcode_identity16(first)) << 16)	\
+	| ___opcode_identity32(___opcode_identity16(second))		\
+)
+#define ___asm_opcode_thumb32_first(x) (___asm_opcode_identity16((x) >> 16))
+#define ___asm_opcode_thumb32_second(x) (___asm_opcode_identity16(x))
+#define ___asm_opcode_thumb32_compose(first, second) (			    \
+	  (___asm_opcode_identity32(___asm_opcode_identity16(first)) << 16) \
+	| ___asm_opcode_identity32(___asm_opcode_identity16(second))	    \
+)
+
+/*
+ * Opcode injection helpers
+ *
+ * In rare cases it is necessary to assemble an opcode which the
+ * assembler does not support directly, or which would normally be
+ * rejected because of the CFLAGS or AFLAGS used to build the affected
+ * file.
+ *
+ * Before using these macros, consider carefully whether it is feasible
+ * instead to change the build flags for your file, or whether it really
+ * makes sense to support old assembler versions when building that
+ * particular kernel feature.
+ *
+ * The macros defined here should only be used where there is no viable
+ * alternative.
+ *
+ *
+ * __inst_arm(x): emit the specified ARM opcode
+ * __inst_thumb16(x): emit the specified 16-bit Thumb opcode
+ * __inst_thumb32(x): emit the specified 32-bit Thumb opcode
+ *
+ * __inst_arm_thumb16(arm, thumb): emit either the specified arm or
+ *	16-bit Thumb opcode, depending on whether an ARM or Thumb-2
+ *	kernel is being built
+ *
+ * __inst_arm_thumb32(arm, thumb): emit either the specified arm or
+ *	32-bit Thumb opcode, depending on whether an ARM or Thumb-2
+ *	kernel is being built
+ *
+ *
+ * Note that using these macros directly is poor practice.  Instead, you
+ * should use them to define human-readable wrapper macros to encode the
+ * instructions that you care about.  In code which might run on ARMv7 or
+ * above, you can usually use the __inst_arm_thumb{16,32} macros to
+ * specify the ARM and Thumb alternatives at the same time.  This ensures
+ * that the correct opcode gets emitted depending on the instruction set
+ * used for the kernel build.
+ *
+ * Look at opcodes-virt.h for an example of how to use these macros.
+ */
+#include <linux/stringify.h>
+
+#define __inst_arm(x) ___inst_arm(___asm_opcode_to_mem_arm(x))
+#define __inst_thumb32(x) ___inst_thumb32(				\
+	___asm_opcode_to_mem_thumb16(___asm_opcode_thumb32_first(x)),	\
+	___asm_opcode_to_mem_thumb16(___asm_opcode_thumb32_second(x))	\
+)
+#define __inst_thumb16(x) ___inst_thumb16(___asm_opcode_to_mem_thumb16(x))
+
+#ifdef CONFIG_THUMB2_KERNEL
+#define __inst_arm_thumb16(arm_opcode, thumb_opcode) \
+	__inst_thumb16(thumb_opcode)
+#define __inst_arm_thumb32(arm_opcode, thumb_opcode) \
+	__inst_thumb32(thumb_opcode)
+#else
+#define __inst_arm_thumb16(arm_opcode, thumb_opcode) __inst_arm(arm_opcode)
+#define __inst_arm_thumb32(arm_opcode, thumb_opcode) __inst_arm(arm_opcode)
+#endif
+
+/* Helpers for the helpers.  Don't use these directly. */
+#ifdef __ASSEMBLY__
+#define ___inst_arm(x) .long x
+#define ___inst_thumb16(x) .short x
+#define ___inst_thumb32(first, second) .short first, second
+#else
+#define ___inst_arm(x) ".long " __stringify(x) "\n\t"
+#define ___inst_thumb16(x) ".short " __stringify(x) "\n\t"
+#define ___inst_thumb32(first, second) \
+	".short " __stringify(first) ", " __stringify(second) "\n\t"
+#endif
+
+#endif /* __ASM_ARM_OPCODES_H */
diff --git a/arch/arm/include/asm/outercache.h b/arch/arm/include/asm/outercache.h
new file mode 100644
index 000000000..563b92fc2
--- /dev/null
+++ b/arch/arm/include/asm/outercache.h
@@ -0,0 +1,149 @@
+/*
+ * arch/arm/include/asm/outercache.h
+ *
+ * Copyright (C) 2010 ARM Ltd.
+ * Written by Catalin Marinas <catalin.marinas@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#ifndef __ASM_OUTERCACHE_H
+#define __ASM_OUTERCACHE_H
+
+#include <linux/types.h>
+
+struct l2x0_regs;
+
+struct outer_cache_fns {
+	void (*inv_range)(unsigned long, unsigned long);
+	void (*clean_range)(unsigned long, unsigned long);
+	void (*flush_range)(unsigned long, unsigned long);
+	void (*flush_all)(void);
+	void (*disable)(void);
+#ifdef CONFIG_OUTER_CACHE_SYNC
+	void (*sync)(void);
+#endif
+	void (*resume)(void);
+
+	/* This is an ARM L2C thing */
+	void (*write_sec)(unsigned long, unsigned);
+	void (*configure)(const struct l2x0_regs *);
+};
+
+extern struct outer_cache_fns outer_cache;
+
+#ifdef CONFIG_OUTER_CACHE
+/**
+ * outer_inv_range - invalidate range of outer cache lines
+ * @start: starting physical address, inclusive
+ * @end: end physical address, exclusive
+ */
+static inline void outer_inv_range(phys_addr_t start, phys_addr_t end)
+{
+	if (outer_cache.inv_range)
+		outer_cache.inv_range(start, end);
+}
+
+/**
+ * outer_clean_range - clean dirty outer cache lines
+ * @start: starting physical address, inclusive
+ * @end: end physical address, exclusive
+ */
+static inline void outer_clean_range(phys_addr_t start, phys_addr_t end)
+{
+	if (outer_cache.clean_range)
+		outer_cache.clean_range(start, end);
+}
+
+/**
+ * outer_flush_range - clean and invalidate outer cache lines
+ * @start: starting physical address, inclusive
+ * @end: end physical address, exclusive
+ */
+static inline void outer_flush_range(phys_addr_t start, phys_addr_t end)
+{
+	if (outer_cache.flush_range)
+		outer_cache.flush_range(start, end);
+}
+
+/**
+ * outer_flush_all - clean and invalidate all cache lines in the outer cache
+ *
+ * Note: depending on implementation, this may not be atomic - it must
+ * only be called with interrupts disabled and no other active outer
+ * cache masters.
+ *
+ * It is intended that this function is only used by implementations
+ * needing to override the outer_cache.disable() method due to security.
+ * (Some implementations perform this as a clean followed by an invalidate.)
+ */
+static inline void outer_flush_all(void)
+{
+	if (outer_cache.flush_all)
+		outer_cache.flush_all();
+}
+
+/**
+ * outer_disable - clean, invalidate and disable the outer cache
+ *
+ * Disable the outer cache, ensuring that any data contained in the outer
+ * cache is pushed out to lower levels of system memory.  The note and
+ * conditions above concerning outer_flush_all() applies here.
+ */
+extern void outer_disable(void);
+
+/**
+ * outer_resume - restore the cache configuration and re-enable outer cache
+ *
+ * Restore any configuration that the cache had when previously enabled,
+ * and re-enable the outer cache.
+ */
+static inline void outer_resume(void)
+{
+	if (outer_cache.resume)
+		outer_cache.resume();
+}
+
+#else
+
+static inline void outer_inv_range(phys_addr_t start, phys_addr_t end)
+{ }
+static inline void outer_clean_range(phys_addr_t start, phys_addr_t end)
+{ }
+static inline void outer_flush_range(phys_addr_t start, phys_addr_t end)
+{ }
+static inline void outer_flush_all(void) { }
+static inline void outer_disable(void) { }
+static inline void outer_resume(void) { }
+
+#endif
+
+#ifdef CONFIG_OUTER_CACHE_SYNC
+/**
+ * outer_sync - perform a sync point for outer cache
+ *
+ * Ensure that all outer cache operations are complete and any store
+ * buffers are drained.
+ */
+static inline void outer_sync(void)
+{
+	if (outer_cache.sync)
+		outer_cache.sync();
+}
+#else
+static inline void outer_sync(void)
+{ }
+#endif
+
+#endif	/* __ASM_OUTERCACHE_H */
diff --git a/arch/arm/include/asm/page-nommu.h b/arch/arm/include/asm/page-nommu.h
new file mode 100644
index 000000000..d1b162a18
--- /dev/null
+++ b/arch/arm/include/asm/page-nommu.h
@@ -0,0 +1,46 @@
+/*
+ *  arch/arm/include/asm/page-nommu.h
+ *
+ *  Copyright (C) 2004 Hyok S. Choi
+ *
+ * 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.
+ */
+
+#ifndef _ASMARM_PAGE_NOMMU_H
+#define _ASMARM_PAGE_NOMMU_H
+
+#if !defined(CONFIG_SMALL_TASKS) && PAGE_SHIFT < 13
+#define KTHREAD_SIZE (8192)
+#else
+#define KTHREAD_SIZE PAGE_SIZE
+#endif
+ 
+#define get_user_page(vaddr)		__get_free_page(GFP_KERNEL)
+#define free_user_page(page, addr)	free_page(addr)
+
+#define clear_page(page)	memset((page), 0, PAGE_SIZE)
+#define copy_page(to,from)	memcpy((to), (from), PAGE_SIZE)
+
+#define clear_user_page(page, vaddr, pg)	clear_page(page)
+#define copy_user_page(to, from, vaddr, pg)	copy_page(to, from)
+
+/*
+ * These are used to make use of C type-checking..
+ */
+typedef unsigned long pte_t;
+typedef unsigned long pmd_t;
+typedef unsigned long pgd_t[2];
+typedef unsigned long pgprot_t;
+
+#define pte_val(x)      (x)
+#define pmd_val(x)      (x)
+#define pgd_val(x)	((x)[0])
+#define pgprot_val(x)   (x)
+
+#define __pte(x)        (x)
+#define __pmd(x)        (x)
+#define __pgprot(x)     (x)
+
+#endif
diff --git a/arch/arm/include/asm/page.h b/arch/arm/include/asm/page.h
new file mode 100644
index 000000000..4355f0ec4
--- /dev/null
+++ b/arch/arm/include/asm/page.h
@@ -0,0 +1,173 @@
+/*
+ *  arch/arm/include/asm/page.h
+ *
+ *  Copyright (C) 1995-2003 Russell King
+ *
+ * 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.
+ */
+#ifndef _ASMARM_PAGE_H
+#define _ASMARM_PAGE_H
+
+/* PAGE_SHIFT determines the page size */
+#define PAGE_SHIFT		12
+#define PAGE_SIZE		(_AC(1,UL) << PAGE_SHIFT)
+#define PAGE_MASK		(~((1 << PAGE_SHIFT) - 1))
+
+#ifndef __ASSEMBLY__
+
+#ifndef CONFIG_MMU
+
+#include <asm/page-nommu.h>
+
+#else
+
+#include <asm/glue.h>
+
+/*
+ *	User Space Model
+ *	================
+ *
+ *	This section selects the correct set of functions for dealing with
+ *	page-based copying and clearing for user space for the particular
+ *	processor(s) we're building for.
+ *
+ *	We have the following to choose from:
+ *	  v4wt		- ARMv4 with writethrough cache, without minicache
+ *	  v4wb		- ARMv4 with writeback cache, without minicache
+ *	  v4_mc		- ARMv4 with minicache
+ *	  xscale	- Xscale
+ *	  xsc3		- XScalev3
+ */
+#undef _USER
+#undef MULTI_USER
+
+#ifdef CONFIG_CPU_COPY_V4WT
+# ifdef _USER
+#  define MULTI_USER 1
+# else
+#  define _USER v4wt
+# endif
+#endif
+
+#ifdef CONFIG_CPU_COPY_V4WB
+# ifdef _USER
+#  define MULTI_USER 1
+# else
+#  define _USER v4wb
+# endif
+#endif
+
+#ifdef CONFIG_CPU_COPY_FEROCEON
+# ifdef _USER
+#  define MULTI_USER 1
+# else
+#  define _USER feroceon
+# endif
+#endif
+
+#ifdef CONFIG_CPU_COPY_FA
+# ifdef _USER
+#  define MULTI_USER 1
+# else
+#  define _USER fa
+# endif
+#endif
+
+#ifdef CONFIG_CPU_SA1100
+# ifdef _USER
+#  define MULTI_USER 1
+# else
+#  define _USER v4_mc
+# endif
+#endif
+
+#ifdef CONFIG_CPU_XSCALE
+# ifdef _USER
+#  define MULTI_USER 1
+# else
+#  define _USER xscale_mc
+# endif
+#endif
+
+#ifdef CONFIG_CPU_XSC3
+# ifdef _USER
+#  define MULTI_USER 1
+# else
+#  define _USER xsc3_mc
+# endif
+#endif
+
+#ifdef CONFIG_CPU_COPY_V6
+# define MULTI_USER 1
+#endif
+
+#if !defined(_USER) && !defined(MULTI_USER)
+#error Unknown user operations model
+#endif
+
+struct page;
+struct vm_area_struct;
+
+struct cpu_user_fns {
+	void (*cpu_clear_user_highpage)(struct page *page, unsigned long vaddr);
+	void (*cpu_copy_user_highpage)(struct page *to, struct page *from,
+			unsigned long vaddr, struct vm_area_struct *vma);
+};
+
+#ifdef MULTI_USER
+extern struct cpu_user_fns cpu_user;
+
+#define __cpu_clear_user_highpage	cpu_user.cpu_clear_user_highpage
+#define __cpu_copy_user_highpage	cpu_user.cpu_copy_user_highpage
+
+#else
+
+#define __cpu_clear_user_highpage	__glue(_USER,_clear_user_highpage)
+#define __cpu_copy_user_highpage	__glue(_USER,_copy_user_highpage)
+
+extern void __cpu_clear_user_highpage(struct page *page, unsigned long vaddr);
+extern void __cpu_copy_user_highpage(struct page *to, struct page *from,
+			unsigned long vaddr, struct vm_area_struct *vma);
+#endif
+
+#define clear_user_highpage(page,vaddr)		\
+	 __cpu_clear_user_highpage(page, vaddr)
+
+#define __HAVE_ARCH_COPY_USER_HIGHPAGE
+#define copy_user_highpage(to,from,vaddr,vma)	\
+	__cpu_copy_user_highpage(to, from, vaddr, vma)
+
+#define clear_page(page)	memset((void *)(page), 0, PAGE_SIZE)
+extern void copy_page(void *to, const void *from);
+
+#ifdef CONFIG_KUSER_HELPERS
+#define __HAVE_ARCH_GATE_AREA 1
+#endif
+
+#ifdef CONFIG_ARM_LPAE
+#include <asm/pgtable-3level-types.h>
+#else
+#include <asm/pgtable-2level-types.h>
+#endif
+
+#endif /* CONFIG_MMU */
+
+typedef struct page *pgtable_t;
+
+#ifdef CONFIG_HAVE_ARCH_PFN_VALID
+extern int pfn_valid(unsigned long);
+#endif
+
+#include <asm/memory.h>
+
+#endif /* !__ASSEMBLY__ */
+
+#define VM_DATA_DEFAULT_FLAGS \
+	(((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0) | \
+	 VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
+
+#include <asm-generic/getorder.h>
+
+#endif
diff --git a/arch/arm/include/asm/patch.h b/arch/arm/include/asm/patch.h
new file mode 100644
index 000000000..77e054c2f
--- /dev/null
+++ b/arch/arm/include/asm/patch.h
@@ -0,0 +1,17 @@
+#ifndef _ARM_KERNEL_PATCH_H
+#define _ARM_KERNEL_PATCH_H
+
+void patch_text(void *addr, unsigned int insn);
+void __patch_text_real(void *addr, unsigned int insn, bool remap);
+
+static inline void __patch_text(void *addr, unsigned int insn)
+{
+	__patch_text_real(addr, insn, true);
+}
+
+static inline void __patch_text_early(void *addr, unsigned int insn)
+{
+	__patch_text_real(addr, insn, false);
+}
+
+#endif
diff --git a/arch/arm/include/asm/pci.h b/arch/arm/include/asm/pci.h
new file mode 100644
index 000000000..585dc33a7
--- /dev/null
+++ b/arch/arm/include/asm/pci.h
@@ -0,0 +1,55 @@
+#ifndef ASMARM_PCI_H
+#define ASMARM_PCI_H
+
+#ifdef __KERNEL__
+#include <asm-generic/pci-dma-compat.h>
+#include <asm-generic/pci-bridge.h>
+
+#include <asm/mach/pci.h> /* for pci_sys_data */
+
+extern unsigned long pcibios_min_io;
+#define PCIBIOS_MIN_IO pcibios_min_io
+extern unsigned long pcibios_min_mem;
+#define PCIBIOS_MIN_MEM pcibios_min_mem
+
+static inline int pcibios_assign_all_busses(void)
+{
+	return pci_has_flag(PCI_REASSIGN_ALL_RSRC);
+}
+
+#ifdef CONFIG_PCI_DOMAINS
+static inline int pci_proc_domain(struct pci_bus *bus)
+{
+	return pci_domain_nr(bus);
+}
+#endif /* CONFIG_PCI_DOMAINS */
+
+/*
+ * The PCI address space does equal the physical memory address space.
+ * The networking and block device layers use this boolean for bounce
+ * buffer decisions.
+ */
+#define PCI_DMA_BUS_IS_PHYS     (1)
+
+#ifdef CONFIG_PCI
+static inline void pci_dma_burst_advice(struct pci_dev *pdev,
+					enum pci_dma_burst_strategy *strat,
+					unsigned long *strategy_parameter)
+{
+	*strat = PCI_DMA_BURST_INFINITY;
+	*strategy_parameter = ~0UL;
+}
+#endif
+
+#define HAVE_PCI_MMAP
+extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
+                               enum pci_mmap_state mmap_state, int write_combine);
+
+static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
+{
+	return channel ? 15 : 14;
+}
+
+#endif /* __KERNEL__ */
+ 
+#endif
diff --git a/arch/arm/include/asm/percpu.h b/arch/arm/include/asm/percpu.h
new file mode 100644
index 000000000..a89b4076c
--- /dev/null
+++ b/arch/arm/include/asm/percpu.h
@@ -0,0 +1,52 @@
+/*
+ * Copyright 2012 Calxeda, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope 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_ARM_PERCPU_H_
+#define _ASM_ARM_PERCPU_H_
+
+/*
+ * Same as asm-generic/percpu.h, except that we store the per cpu offset
+ * in the TPIDRPRW. TPIDRPRW only exists on V6K and V7
+ */
+#if defined(CONFIG_SMP) && !defined(CONFIG_CPU_V6)
+static inline void set_my_cpu_offset(unsigned long off)
+{
+	/* Set TPIDRPRW */
+	asm volatile("mcr p15, 0, %0, c13, c0, 4" : : "r" (off) : "memory");
+}
+
+static inline unsigned long __my_cpu_offset(void)
+{
+	unsigned long off;
+
+	/*
+	 * Read TPIDRPRW.
+	 * We want to allow caching the value, so avoid using volatile and
+	 * instead use a fake stack read to hazard against barrier().
+	 */
+	asm("mrc p15, 0, %0, c13, c0, 4" : "=r" (off)
+		: "Q" (*(const unsigned long *)current_stack_pointer));
+
+	return off;
+}
+#define __my_cpu_offset __my_cpu_offset()
+#else
+#define set_my_cpu_offset(x)	do {} while(0)
+
+#endif /* CONFIG_SMP */
+
+#include <asm-generic/percpu.h>
+
+#endif /* _ASM_ARM_PERCPU_H_ */
diff --git a/arch/arm/include/asm/perf_event.h b/arch/arm/include/asm/perf_event.h
new file mode 100644
index 000000000..d9cf138fd
--- /dev/null
+++ b/arch/arm/include/asm/perf_event.h
@@ -0,0 +1,22 @@
+/*
+ *  linux/arch/arm/include/asm/perf_event.h
+ *
+ *  Copyright (C) 2009 picoChip Designs Ltd, Jamie Iles
+ *
+ * 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.
+ *
+ */
+
+#ifndef __ARM_PERF_EVENT_H__
+#define __ARM_PERF_EVENT_H__
+
+#ifdef CONFIG_PERF_EVENTS
+struct pt_regs;
+extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
+extern unsigned long perf_misc_flags(struct pt_regs *regs);
+#define perf_misc_flags(regs)	perf_misc_flags(regs)
+#endif
+
+#endif /* __ARM_PERF_EVENT_H__ */
diff --git a/arch/arm/include/asm/pgalloc.h b/arch/arm/include/asm/pgalloc.h
new file mode 100644
index 000000000..19cfab526
--- /dev/null
+++ b/arch/arm/include/asm/pgalloc.h
@@ -0,0 +1,174 @@
+/*
+ *  arch/arm/include/asm/pgalloc.h
+ *
+ *  Copyright (C) 2000-2001 Russell King
+ *
+ * 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.
+ */
+#ifndef _ASMARM_PGALLOC_H
+#define _ASMARM_PGALLOC_H
+
+#include <linux/pagemap.h>
+
+#include <asm/domain.h>
+#include <asm/pgtable-hwdef.h>
+#include <asm/processor.h>
+#include <asm/cacheflush.h>
+#include <asm/tlbflush.h>
+
+#define check_pgt_cache()		do { } while (0)
+
+#ifdef CONFIG_MMU
+
+#define _PAGE_USER_TABLE	(PMD_TYPE_TABLE | PMD_BIT4 | PMD_DOMAIN(DOMAIN_USER))
+#define _PAGE_KERNEL_TABLE	(PMD_TYPE_TABLE | PMD_BIT4 | PMD_DOMAIN(DOMAIN_KERNEL))
+
+#ifdef CONFIG_ARM_LPAE
+
+static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
+{
+	return (pmd_t *)get_zeroed_page(GFP_KERNEL | __GFP_REPEAT);
+}
+
+static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
+{
+	BUG_ON((unsigned long)pmd & (PAGE_SIZE-1));
+	free_page((unsigned long)pmd);
+}
+
+static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
+{
+	set_pud(pud, __pud(__pa(pmd) | PMD_TYPE_TABLE));
+}
+
+#else	/* !CONFIG_ARM_LPAE */
+
+/*
+ * Since we have only two-level page tables, these are trivial
+ */
+#define pmd_alloc_one(mm,addr)		({ BUG(); ((pmd_t *)2); })
+#define pmd_free(mm, pmd)		do { } while (0)
+#define pud_populate(mm,pmd,pte)	BUG()
+
+#endif	/* CONFIG_ARM_LPAE */
+
+extern pgd_t *pgd_alloc(struct mm_struct *mm);
+extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
+
+#define PGALLOC_GFP	(GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO)
+
+static inline void clean_pte_table(pte_t *pte)
+{
+	clean_dcache_area(pte + PTE_HWTABLE_PTRS, PTE_HWTABLE_SIZE);
+}
+
+/*
+ * Allocate one PTE table.
+ *
+ * This actually allocates two hardware PTE tables, but we wrap this up
+ * into one table thus:
+ *
+ *  +------------+
+ *  | Linux pt 0 |
+ *  +------------+
+ *  | Linux pt 1 |
+ *  +------------+
+ *  |  h/w pt 0  |
+ *  +------------+
+ *  |  h/w pt 1  |
+ *  +------------+
+ */
+static inline pte_t *
+pte_alloc_one_kernel(struct mm_struct *mm, unsigned long addr)
+{
+	pte_t *pte;
+
+	pte = (pte_t *)__get_free_page(PGALLOC_GFP);
+	if (pte)
+		clean_pte_table(pte);
+
+	return pte;
+}
+
+static inline pgtable_t
+pte_alloc_one(struct mm_struct *mm, unsigned long addr)
+{
+	struct page *pte;
+
+#ifdef CONFIG_HIGHPTE
+	pte = alloc_pages(PGALLOC_GFP | __GFP_HIGHMEM, 0);
+#else
+	pte = alloc_pages(PGALLOC_GFP, 0);
+#endif
+	if (!pte)
+		return NULL;
+	if (!PageHighMem(pte))
+		clean_pte_table(page_address(pte));
+	if (!pgtable_page_ctor(pte)) {
+		__free_page(pte);
+		return NULL;
+	}
+	return pte;
+}
+
+/*
+ * Free one PTE table.
+ */
+static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
+{
+	if (pte)
+		free_page((unsigned long)pte);
+}
+
+static inline void pte_free(struct mm_struct *mm, pgtable_t pte)
+{
+	pgtable_page_dtor(pte);
+	__free_page(pte);
+}
+
+static inline void __pmd_populate(pmd_t *pmdp, phys_addr_t pte,
+				  pmdval_t prot)
+{
+	pmdval_t pmdval = (pte + PTE_HWTABLE_OFF) | prot;
+	pmdp[0] = __pmd(pmdval);
+#ifndef CONFIG_ARM_LPAE
+	pmdp[1] = __pmd(pmdval + 256 * sizeof(pte_t));
+#endif
+	flush_pmd_entry(pmdp);
+}
+
+/*
+ * Populate the pmdp entry with a pointer to the pte.  This pmd is part
+ * of the mm address space.
+ *
+ * Ensure that we always set both PMD entries.
+ */
+static inline void
+pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmdp, pte_t *ptep)
+{
+	/*
+	 * The pmd must be loaded with the physical address of the PTE table
+	 */
+	__pmd_populate(pmdp, __pa(ptep), _PAGE_KERNEL_TABLE);
+}
+
+static inline void
+pmd_populate(struct mm_struct *mm, pmd_t *pmdp, pgtable_t ptep)
+{
+	extern pmdval_t user_pmd_table;
+	pmdval_t prot;
+
+	if (__LINUX_ARM_ARCH__ >= 6 && !IS_ENABLED(CONFIG_ARM_LPAE))
+		prot = user_pmd_table;
+	else
+		prot = _PAGE_USER_TABLE;
+
+	__pmd_populate(pmdp, page_to_phys(ptep), prot);
+}
+#define pmd_pgtable(pmd) pmd_page(pmd)
+
+#endif /* CONFIG_MMU */
+
+#endif
diff --git a/arch/arm/include/asm/pgtable-2level-hwdef.h b/arch/arm/include/asm/pgtable-2level-hwdef.h
new file mode 100644
index 000000000..5e68278e9
--- /dev/null
+++ b/arch/arm/include/asm/pgtable-2level-hwdef.h
@@ -0,0 +1,95 @@
+/*
+ *  arch/arm/include/asm/pgtable-2level-hwdef.h
+ *
+ *  Copyright (C) 1995-2002 Russell King
+ *
+ * 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.
+ */
+#ifndef _ASM_PGTABLE_2LEVEL_HWDEF_H
+#define _ASM_PGTABLE_2LEVEL_HWDEF_H
+
+/*
+ * Hardware page table definitions.
+ *
+ * + Level 1 descriptor (PMD)
+ *   - common
+ */
+#define PMD_TYPE_MASK		(_AT(pmdval_t, 3) << 0)
+#define PMD_TYPE_FAULT		(_AT(pmdval_t, 0) << 0)
+#define PMD_TYPE_TABLE		(_AT(pmdval_t, 1) << 0)
+#define PMD_TYPE_SECT		(_AT(pmdval_t, 2) << 0)
+#define PMD_PXNTABLE		(_AT(pmdval_t, 1) << 2)     /* v7 */
+#define PMD_BIT4		(_AT(pmdval_t, 1) << 4)
+#define PMD_DOMAIN(x)		(_AT(pmdval_t, (x)) << 5)
+#define PMD_PROTECTION		(_AT(pmdval_t, 1) << 9)		/* v5 */
+/*
+ *   - section
+ */
+#define PMD_SECT_PXN    (_AT(pmdval_t, 1) << 0)     /* v7 */
+#define PMD_SECT_BUFFERABLE	(_AT(pmdval_t, 1) << 2)
+#define PMD_SECT_CACHEABLE	(_AT(pmdval_t, 1) << 3)
+#define PMD_SECT_XN		(_AT(pmdval_t, 1) << 4)		/* v6 */
+#define PMD_SECT_AP_WRITE	(_AT(pmdval_t, 1) << 10)
+#define PMD_SECT_AP_READ	(_AT(pmdval_t, 1) << 11)
+#define PMD_SECT_TEX(x)		(_AT(pmdval_t, (x)) << 12)	/* v5 */
+#define PMD_SECT_APX		(_AT(pmdval_t, 1) << 15)	/* v6 */
+#define PMD_SECT_S		(_AT(pmdval_t, 1) << 16)	/* v6 */
+#define PMD_SECT_nG		(_AT(pmdval_t, 1) << 17)	/* v6 */
+#define PMD_SECT_SUPER		(_AT(pmdval_t, 1) << 18)	/* v6 */
+#define PMD_SECT_AF		(_AT(pmdval_t, 0))
+
+#define PMD_SECT_UNCACHED	(_AT(pmdval_t, 0))
+#define PMD_SECT_BUFFERED	(PMD_SECT_BUFFERABLE)
+#define PMD_SECT_WT		(PMD_SECT_CACHEABLE)
+#define PMD_SECT_WB		(PMD_SECT_CACHEABLE | PMD_SECT_BUFFERABLE)
+#define PMD_SECT_MINICACHE	(PMD_SECT_TEX(1) | PMD_SECT_CACHEABLE)
+#define PMD_SECT_WBWA		(PMD_SECT_TEX(1) | PMD_SECT_CACHEABLE | PMD_SECT_BUFFERABLE)
+#define PMD_SECT_NONSHARED_DEV	(PMD_SECT_TEX(2))
+
+/*
+ *   - coarse table (not used)
+ */
+
+/*
+ * + Level 2 descriptor (PTE)
+ *   - common
+ */
+#define PTE_TYPE_MASK		(_AT(pteval_t, 3) << 0)
+#define PTE_TYPE_FAULT		(_AT(pteval_t, 0) << 0)
+#define PTE_TYPE_LARGE		(_AT(pteval_t, 1) << 0)
+#define PTE_TYPE_SMALL		(_AT(pteval_t, 2) << 0)
+#define PTE_TYPE_EXT		(_AT(pteval_t, 3) << 0)		/* v5 */
+#define PTE_BUFFERABLE		(_AT(pteval_t, 1) << 2)
+#define PTE_CACHEABLE		(_AT(pteval_t, 1) << 3)
+
+/*
+ *   - extended small page/tiny page
+ */
+#define PTE_EXT_XN		(_AT(pteval_t, 1) << 0)		/* v6 */
+#define PTE_EXT_AP_MASK		(_AT(pteval_t, 3) << 4)
+#define PTE_EXT_AP0		(_AT(pteval_t, 1) << 4)
+#define PTE_EXT_AP1		(_AT(pteval_t, 2) << 4)
+#define PTE_EXT_AP_UNO_SRO	(_AT(pteval_t, 0) << 4)
+#define PTE_EXT_AP_UNO_SRW	(PTE_EXT_AP0)
+#define PTE_EXT_AP_URO_SRW	(PTE_EXT_AP1)
+#define PTE_EXT_AP_URW_SRW	(PTE_EXT_AP1|PTE_EXT_AP0)
+#define PTE_EXT_TEX(x)		(_AT(pteval_t, (x)) << 6)	/* v5 */
+#define PTE_EXT_APX		(_AT(pteval_t, 1) << 9)		/* v6 */
+#define PTE_EXT_COHERENT	(_AT(pteval_t, 1) << 9)		/* XScale3 */
+#define PTE_EXT_SHARED		(_AT(pteval_t, 1) << 10)	/* v6 */
+#define PTE_EXT_NG		(_AT(pteval_t, 1) << 11)	/* v6 */
+
+/*
+ *   - small page
+ */
+#define PTE_SMALL_AP_MASK	(_AT(pteval_t, 0xff) << 4)
+#define PTE_SMALL_AP_UNO_SRO	(_AT(pteval_t, 0x00) << 4)
+#define PTE_SMALL_AP_UNO_SRW	(_AT(pteval_t, 0x55) << 4)
+#define PTE_SMALL_AP_URO_SRW	(_AT(pteval_t, 0xaa) << 4)
+#define PTE_SMALL_AP_URW_SRW	(_AT(pteval_t, 0xff) << 4)
+
+#define PHYS_MASK		(~0UL)
+
+#endif
diff --git a/arch/arm/include/asm/pgtable-2level-types.h b/arch/arm/include/asm/pgtable-2level-types.h
new file mode 100644
index 000000000..66cb5b0e8
--- /dev/null
+++ b/arch/arm/include/asm/pgtable-2level-types.h
@@ -0,0 +1,67 @@
+/*
+ * arch/arm/include/asm/pgtable-2level-types.h
+ *
+ * Copyright (C) 1995-2003 Russell King
+ *
+ * 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, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+#ifndef _ASM_PGTABLE_2LEVEL_TYPES_H
+#define _ASM_PGTABLE_2LEVEL_TYPES_H
+
+#include <asm/types.h>
+
+typedef u32 pteval_t;
+typedef u32 pmdval_t;
+
+#undef STRICT_MM_TYPECHECKS
+
+#ifdef STRICT_MM_TYPECHECKS
+/*
+ * These are used to make use of C type-checking..
+ */
+typedef struct { pteval_t pte; } pte_t;
+typedef struct { pmdval_t pmd; } pmd_t;
+typedef struct { pmdval_t pgd[2]; } pgd_t;
+typedef struct { pteval_t pgprot; } pgprot_t;
+
+#define pte_val(x)      ((x).pte)
+#define pmd_val(x)      ((x).pmd)
+#define pgd_val(x)	((x).pgd[0])
+#define pgprot_val(x)   ((x).pgprot)
+
+#define __pte(x)        ((pte_t) { (x) } )
+#define __pmd(x)        ((pmd_t) { (x) } )
+#define __pgprot(x)     ((pgprot_t) { (x) } )
+
+#else
+/*
+ * .. while these make it easier on the compiler
+ */
+typedef pteval_t pte_t;
+typedef pmdval_t pmd_t;
+typedef pmdval_t pgd_t[2];
+typedef pteval_t pgprot_t;
+
+#define pte_val(x)      (x)
+#define pmd_val(x)      (x)
+#define pgd_val(x)	((x)[0])
+#define pgprot_val(x)   (x)
+
+#define __pte(x)        (x)
+#define __pmd(x)        (x)
+#define __pgprot(x)     (x)
+
+#endif /* STRICT_MM_TYPECHECKS */
+
+#endif	/* _ASM_PGTABLE_2LEVEL_TYPES_H */
diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h
new file mode 100644
index 000000000..bfd662e49
--- /dev/null
+++ b/arch/arm/include/asm/pgtable-2level.h
@@ -0,0 +1,198 @@
+/*
+ *  arch/arm/include/asm/pgtable-2level.h
+ *
+ *  Copyright (C) 1995-2002 Russell King
+ *
+ * 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.
+ */
+#ifndef _ASM_PGTABLE_2LEVEL_H
+#define _ASM_PGTABLE_2LEVEL_H
+
+#define __PAGETABLE_PMD_FOLDED
+
+/*
+ * Hardware-wise, we have a two level page table structure, where the first
+ * level has 4096 entries, and the second level has 256 entries.  Each entry
+ * is one 32-bit word.  Most of the bits in the second level entry are used
+ * by hardware, and there aren't any "accessed" and "dirty" bits.
+ *
+ * Linux on the other hand has a three level page table structure, which can
+ * be wrapped to fit a two level page table structure easily - using the PGD
+ * and PTE only.  However, Linux also expects one "PTE" table per page, and
+ * at least a "dirty" bit.
+ *
+ * Therefore, we tweak the implementation slightly - we tell Linux that we
+ * have 2048 entries in the first level, each of which is 8 bytes (iow, two
+ * hardware pointers to the second level.)  The second level contains two
+ * hardware PTE tables arranged contiguously, preceded by Linux versions
+ * which contain the state information Linux needs.  We, therefore, end up
+ * with 512 entries in the "PTE" level.
+ *
+ * This leads to the page tables having the following layout:
+ *
+ *    pgd             pte
+ * |        |
+ * +--------+
+ * |        |       +------------+ +0
+ * +- - - - +       | Linux pt 0 |
+ * |        |       +------------+ +1024
+ * +--------+ +0    | Linux pt 1 |
+ * |        |-----> +------------+ +2048
+ * +- - - - + +4    |  h/w pt 0  |
+ * |        |-----> +------------+ +3072
+ * +--------+ +8    |  h/w pt 1  |
+ * |        |       +------------+ +4096
+ *
+ * See L_PTE_xxx below for definitions of bits in the "Linux pt", and
+ * PTE_xxx for definitions of bits appearing in the "h/w pt".
+ *
+ * PMD_xxx definitions refer to bits in the first level page table.
+ *
+ * The "dirty" bit is emulated by only granting hardware write permission
+ * iff the page is marked "writable" and "dirty" in the Linux PTE.  This
+ * means that a write to a clean page will cause a permission fault, and
+ * the Linux MM layer will mark the page dirty via handle_pte_fault().
+ * For the hardware to notice the permission change, the TLB entry must
+ * be flushed, and ptep_set_access_flags() does that for us.
+ *
+ * The "accessed" or "young" bit is emulated by a similar method; we only
+ * allow accesses to the page if the "young" bit is set.  Accesses to the
+ * page will cause a fault, and handle_pte_fault() will set the young bit
+ * for us as long as the page is marked present in the corresponding Linux
+ * PTE entry.  Again, ptep_set_access_flags() will ensure that the TLB is
+ * up to date.
+ *
+ * However, when the "young" bit is cleared, we deny access to the page
+ * by clearing the hardware PTE.  Currently Linux does not flush the TLB
+ * for us in this case, which means the TLB will retain the transation
+ * until either the TLB entry is evicted under pressure, or a context
+ * switch which changes the user space mapping occurs.
+ */
+#define PTRS_PER_PTE		512
+#define PTRS_PER_PMD		1
+#define PTRS_PER_PGD		2048
+
+#define PTE_HWTABLE_PTRS	(PTRS_PER_PTE)
+#define PTE_HWTABLE_OFF		(PTE_HWTABLE_PTRS * sizeof(pte_t))
+#define PTE_HWTABLE_SIZE	(PTRS_PER_PTE * sizeof(u32))
+
+/*
+ * PMD_SHIFT determines the size of the area a second-level page table can map
+ * PGDIR_SHIFT determines what a third-level page table entry can map
+ */
+#define PMD_SHIFT		21
+#define PGDIR_SHIFT		21
+
+#define PMD_SIZE		(1UL << PMD_SHIFT)
+#define PMD_MASK		(~(PMD_SIZE-1))
+#define PGDIR_SIZE		(1UL << PGDIR_SHIFT)
+#define PGDIR_MASK		(~(PGDIR_SIZE-1))
+
+/*
+ * section address mask and size definitions.
+ */
+#define SECTION_SHIFT		20
+#define SECTION_SIZE		(1UL << SECTION_SHIFT)
+#define SECTION_MASK		(~(SECTION_SIZE-1))
+
+/*
+ * ARMv6 supersection address mask and size definitions.
+ */
+#define SUPERSECTION_SHIFT	24
+#define SUPERSECTION_SIZE	(1UL << SUPERSECTION_SHIFT)
+#define SUPERSECTION_MASK	(~(SUPERSECTION_SIZE-1))
+
+#define USER_PTRS_PER_PGD	(TASK_SIZE / PGDIR_SIZE)
+
+/*
+ * "Linux" PTE definitions.
+ *
+ * We keep two sets of PTEs - the hardware and the linux version.
+ * This allows greater flexibility in the way we map the Linux bits
+ * onto the hardware tables, and allows us to have YOUNG and DIRTY
+ * bits.
+ *
+ * The PTE table pointer refers to the hardware entries; the "Linux"
+ * entries are stored 1024 bytes below.
+ */
+#define L_PTE_VALID		(_AT(pteval_t, 1) << 0)		/* Valid */
+#define L_PTE_PRESENT		(_AT(pteval_t, 1) << 0)
+#define L_PTE_YOUNG		(_AT(pteval_t, 1) << 1)
+#define L_PTE_DIRTY		(_AT(pteval_t, 1) << 6)
+#define L_PTE_RDONLY		(_AT(pteval_t, 1) << 7)
+#define L_PTE_USER		(_AT(pteval_t, 1) << 8)
+#define L_PTE_XN		(_AT(pteval_t, 1) << 9)
+#define L_PTE_SHARED		(_AT(pteval_t, 1) << 10)	/* shared(v6), coherent(xsc3) */
+#define L_PTE_NONE		(_AT(pteval_t, 1) << 11)
+
+/*
+ * These are the memory types, defined to be compatible with
+ * pre-ARMv6 CPUs cacheable and bufferable bits:   XXCB
+ */
+#define L_PTE_MT_UNCACHED	(_AT(pteval_t, 0x00) << 2)	/* 0000 */
+#define L_PTE_MT_BUFFERABLE	(_AT(pteval_t, 0x01) << 2)	/* 0001 */
+#define L_PTE_MT_WRITETHROUGH	(_AT(pteval_t, 0x02) << 2)	/* 0010 */
+#define L_PTE_MT_WRITEBACK	(_AT(pteval_t, 0x03) << 2)	/* 0011 */
+#define L_PTE_MT_MINICACHE	(_AT(pteval_t, 0x06) << 2)	/* 0110 (sa1100, xscale) */
+#define L_PTE_MT_WRITEALLOC	(_AT(pteval_t, 0x07) << 2)	/* 0111 */
+#define L_PTE_MT_DEV_SHARED	(_AT(pteval_t, 0x04) << 2)	/* 0100 */
+#define L_PTE_MT_DEV_NONSHARED	(_AT(pteval_t, 0x0c) << 2)	/* 1100 */
+#define L_PTE_MT_DEV_WC		(_AT(pteval_t, 0x09) << 2)	/* 1001 */
+#define L_PTE_MT_DEV_CACHED	(_AT(pteval_t, 0x0b) << 2)	/* 1011 */
+#define L_PTE_MT_VECTORS	(_AT(pteval_t, 0x0f) << 2)	/* 1111 */
+#define L_PTE_MT_MASK		(_AT(pteval_t, 0x0f) << 2)
+
+#ifndef __ASSEMBLY__
+
+/*
+ * The "pud_xxx()" functions here are trivial when the pmd is folded into
+ * the pud: the pud entry is never bad, always exists, and can't be set or
+ * cleared.
+ */
+#define pud_none(pud)		(0)
+#define pud_bad(pud)		(0)
+#define pud_present(pud)	(1)
+#define pud_clear(pudp)		do { } while (0)
+#define set_pud(pud,pudp)	do { } while (0)
+
+static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
+{
+	return (pmd_t *)pud;
+}
+
+#define pmd_large(pmd)		(pmd_val(pmd) & 2)
+#define pmd_bad(pmd)		(pmd_val(pmd) & 2)
+
+#define copy_pmd(pmdpd,pmdps)		\
+	do {				\
+		pmdpd[0] = pmdps[0];	\
+		pmdpd[1] = pmdps[1];	\
+		flush_pmd_entry(pmdpd);	\
+	} while (0)
+
+#define pmd_clear(pmdp)			\
+	do {				\
+		pmdp[0] = __pmd(0);	\
+		pmdp[1] = __pmd(0);	\
+		clean_pmd_entry(pmdp);	\
+	} while (0)
+
+/* we don't need complex calculations here as the pmd is folded into the pgd */
+#define pmd_addr_end(addr,end) (end)
+
+#define set_pte_ext(ptep,pte,ext) cpu_set_pte_ext(ptep,pte,ext)
+#define pte_special(pte)	(0)
+static inline pte_t pte_mkspecial(pte_t pte) { return pte; }
+
+/*
+ * We don't have huge page support for short descriptors, for the moment
+ * define empty stubs for use by pin_page_for_write.
+ */
+#define pmd_hugewillfault(pmd)	(0)
+#define pmd_thp_or_huge(pmd)	(0)
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_PGTABLE_2LEVEL_H */
diff --git a/arch/arm/include/asm/pgtable-3level-hwdef.h b/arch/arm/include/asm/pgtable-3level-hwdef.h
new file mode 100644
index 000000000..f8f1cff62
--- /dev/null
+++ b/arch/arm/include/asm/pgtable-3level-hwdef.h
@@ -0,0 +1,108 @@
+/*
+ * arch/arm/include/asm/pgtable-3level-hwdef.h
+ *
+ * Copyright (C) 2011 ARM Ltd.
+ * Author: Catalin Marinas <catalin.marinas@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+#ifndef _ASM_PGTABLE_3LEVEL_HWDEF_H
+#define _ASM_PGTABLE_3LEVEL_HWDEF_H
+
+/*
+ * Hardware page table definitions.
+ *
+ * + Level 1/2 descriptor
+ *   - common
+ */
+#define PMD_TYPE_MASK		(_AT(pmdval_t, 3) << 0)
+#define PMD_TYPE_FAULT		(_AT(pmdval_t, 0) << 0)
+#define PMD_TYPE_TABLE		(_AT(pmdval_t, 3) << 0)
+#define PMD_TYPE_SECT		(_AT(pmdval_t, 1) << 0)
+#define PMD_TABLE_BIT		(_AT(pmdval_t, 1) << 1)
+#define PMD_BIT4		(_AT(pmdval_t, 0))
+#define PMD_DOMAIN(x)		(_AT(pmdval_t, 0))
+#define PMD_APTABLE_SHIFT	(61)
+#define PMD_APTABLE		(_AT(pgdval_t, 3) << PGD_APTABLE_SHIFT)
+#define PMD_PXNTABLE		(_AT(pgdval_t, 1) << 59)
+
+/*
+ *   - section
+ */
+#define PMD_SECT_BUFFERABLE	(_AT(pmdval_t, 1) << 2)
+#define PMD_SECT_CACHEABLE	(_AT(pmdval_t, 1) << 3)
+#define PMD_SECT_USER		(_AT(pmdval_t, 1) << 6)		/* AP[1] */
+#define PMD_SECT_AP2		(_AT(pmdval_t, 1) << 7)		/* read only */
+#define PMD_SECT_S		(_AT(pmdval_t, 3) << 8)
+#define PMD_SECT_AF		(_AT(pmdval_t, 1) << 10)
+#define PMD_SECT_nG		(_AT(pmdval_t, 1) << 11)
+#define PMD_SECT_PXN		(_AT(pmdval_t, 1) << 53)
+#define PMD_SECT_XN		(_AT(pmdval_t, 1) << 54)
+#define PMD_SECT_AP_WRITE	(_AT(pmdval_t, 0))
+#define PMD_SECT_AP_READ	(_AT(pmdval_t, 0))
+#define PMD_SECT_AP1		(_AT(pmdval_t, 1) << 6)
+#define PMD_SECT_TEX(x)		(_AT(pmdval_t, 0))
+
+/*
+ * AttrIndx[2:0] encoding (mapping attributes defined in the MAIR* registers).
+ */
+#define PMD_SECT_UNCACHED	(_AT(pmdval_t, 0) << 2)	/* strongly ordered */
+#define PMD_SECT_BUFFERED	(_AT(pmdval_t, 1) << 2)	/* normal non-cacheable */
+#define PMD_SECT_WT		(_AT(pmdval_t, 2) << 2)	/* normal inner write-through */
+#define PMD_SECT_WB		(_AT(pmdval_t, 3) << 2)	/* normal inner write-back */
+#define PMD_SECT_WBWA		(_AT(pmdval_t, 7) << 2)	/* normal inner write-alloc */
+
+/*
+ * + Level 3 descriptor (PTE)
+ */
+#define PTE_TYPE_MASK		(_AT(pteval_t, 3) << 0)
+#define PTE_TYPE_FAULT		(_AT(pteval_t, 0) << 0)
+#define PTE_TYPE_PAGE		(_AT(pteval_t, 3) << 0)
+#define PTE_TABLE_BIT		(_AT(pteval_t, 1) << 1)
+#define PTE_BUFFERABLE		(_AT(pteval_t, 1) << 2)		/* AttrIndx[0] */
+#define PTE_CACHEABLE		(_AT(pteval_t, 1) << 3)		/* AttrIndx[1] */
+#define PTE_AP2			(_AT(pteval_t, 1) << 7)		/* AP[2] */
+#define PTE_EXT_SHARED		(_AT(pteval_t, 3) << 8)		/* SH[1:0], inner shareable */
+#define PTE_EXT_AF		(_AT(pteval_t, 1) << 10)	/* Access Flag */
+#define PTE_EXT_NG		(_AT(pteval_t, 1) << 11)	/* nG */
+#define PTE_EXT_PXN		(_AT(pteval_t, 1) << 53)	/* PXN */
+#define PTE_EXT_XN		(_AT(pteval_t, 1) << 54)	/* XN */
+
+/*
+ * 40-bit physical address supported.
+ */
+#define PHYS_MASK_SHIFT		(40)
+#define PHYS_MASK		((1ULL << PHYS_MASK_SHIFT) - 1)
+
+/*
+ * TTBR0/TTBR1 split (PAGE_OFFSET):
+ *   0x40000000: T0SZ = 2, T1SZ = 0 (not used)
+ *   0x80000000: T0SZ = 0, T1SZ = 1
+ *   0xc0000000: T0SZ = 0, T1SZ = 2
+ *
+ * Only use this feature if PHYS_OFFSET <= PAGE_OFFSET, otherwise
+ * booting secondary CPUs would end up using TTBR1 for the identity
+ * mapping set up in TTBR0.
+ */
+#if defined CONFIG_VMSPLIT_2G
+#define TTBR1_OFFSET	16			/* skip two L1 entries */
+#elif defined CONFIG_VMSPLIT_3G
+#define TTBR1_OFFSET	(4096 * (1 + 3))	/* only L2, skip pgd + 3*pmd */
+#else
+#define TTBR1_OFFSET	0
+#endif
+
+#define TTBR1_SIZE	(((PAGE_OFFSET >> 30) - 1) << 16)
+
+#endif
diff --git a/arch/arm/include/asm/pgtable-3level-types.h b/arch/arm/include/asm/pgtable-3level-types.h
new file mode 100644
index 000000000..921aa3025
--- /dev/null
+++ b/arch/arm/include/asm/pgtable-3level-types.h
@@ -0,0 +1,70 @@
+/*
+ * arch/arm/include/asm/pgtable-3level-types.h
+ *
+ * Copyright (C) 2011 ARM Ltd.
+ * Author: Catalin Marinas <catalin.marinas@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+#ifndef _ASM_PGTABLE_3LEVEL_TYPES_H
+#define _ASM_PGTABLE_3LEVEL_TYPES_H
+
+#include <asm/types.h>
+
+typedef u64 pteval_t;
+typedef u64 pmdval_t;
+typedef u64 pgdval_t;
+
+#undef STRICT_MM_TYPECHECKS
+
+#ifdef STRICT_MM_TYPECHECKS
+
+/*
+ * These are used to make use of C type-checking..
+ */
+typedef struct { pteval_t pte; } pte_t;
+typedef struct { pmdval_t pmd; } pmd_t;
+typedef struct { pgdval_t pgd; } pgd_t;
+typedef struct { pteval_t pgprot; } pgprot_t;
+
+#define pte_val(x)      ((x).pte)
+#define pmd_val(x)      ((x).pmd)
+#define pgd_val(x)	((x).pgd)
+#define pgprot_val(x)   ((x).pgprot)
+
+#define __pte(x)        ((pte_t) { (x) } )
+#define __pmd(x)        ((pmd_t) { (x) } )
+#define __pgd(x)	((pgd_t) { (x) } )
+#define __pgprot(x)     ((pgprot_t) { (x) } )
+
+#else	/* !STRICT_MM_TYPECHECKS */
+
+typedef pteval_t pte_t;
+typedef pmdval_t pmd_t;
+typedef pgdval_t pgd_t;
+typedef pteval_t pgprot_t;
+
+#define pte_val(x)	(x)
+#define pmd_val(x)	(x)
+#define pgd_val(x)	(x)
+#define pgprot_val(x)	(x)
+
+#define __pte(x)	(x)
+#define __pmd(x)	(x)
+#define __pgd(x)	(x)
+#define __pgprot(x)	(x)
+
+#endif	/* STRICT_MM_TYPECHECKS */
+
+#endif	/* _ASM_PGTABLE_3LEVEL_TYPES_H */
diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h
new file mode 100644
index 000000000..a745a2a53
--- /dev/null
+++ b/arch/arm/include/asm/pgtable-3level.h
@@ -0,0 +1,299 @@
+/*
+ * arch/arm/include/asm/pgtable-3level.h
+ *
+ * Copyright (C) 2011 ARM Ltd.
+ * Author: Catalin Marinas <catalin.marinas@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+#ifndef _ASM_PGTABLE_3LEVEL_H
+#define _ASM_PGTABLE_3LEVEL_H
+
+/*
+ * With LPAE, there are 3 levels of page tables. Each level has 512 entries of
+ * 8 bytes each, occupying a 4K page. The first level table covers a range of
+ * 512GB, each entry representing 1GB. Since we are limited to 4GB input
+ * address range, only 4 entries in the PGD are used.
+ *
+ * There are enough spare bits in a page table entry for the kernel specific
+ * state.
+ */
+#define PTRS_PER_PTE		512
+#define PTRS_PER_PMD		512
+#define PTRS_PER_PGD		4
+
+#define PTE_HWTABLE_PTRS	(0)
+#define PTE_HWTABLE_OFF		(0)
+#define PTE_HWTABLE_SIZE	(PTRS_PER_PTE * sizeof(u64))
+
+/*
+ * PGDIR_SHIFT determines the size a top-level page table entry can map.
+ */
+#define PGDIR_SHIFT		30
+
+/*
+ * PMD_SHIFT determines the size a middle-level page table entry can map.
+ */
+#define PMD_SHIFT		21
+
+#define PMD_SIZE		(1UL << PMD_SHIFT)
+#define PMD_MASK		(~((1 << PMD_SHIFT) - 1))
+#define PGDIR_SIZE		(1UL << PGDIR_SHIFT)
+#define PGDIR_MASK		(~((1 << PGDIR_SHIFT) - 1))
+
+/*
+ * section address mask and size definitions.
+ */
+#define SECTION_SHIFT		21
+#define SECTION_SIZE		(1UL << SECTION_SHIFT)
+#define SECTION_MASK		(~((1 << SECTION_SHIFT) - 1))
+
+#define USER_PTRS_PER_PGD	(PAGE_OFFSET / PGDIR_SIZE)
+
+/*
+ * Hugetlb definitions.
+ */
+#define HPAGE_SHIFT		PMD_SHIFT
+#define HPAGE_SIZE		(_AC(1, UL) << HPAGE_SHIFT)
+#define HPAGE_MASK		(~(HPAGE_SIZE - 1))
+#define HUGETLB_PAGE_ORDER	(HPAGE_SHIFT - PAGE_SHIFT)
+
+/*
+ * "Linux" PTE definitions for LPAE.
+ *
+ * These bits overlap with the hardware bits but the naming is preserved for
+ * consistency with the classic page table format.
+ */
+#define L_PTE_VALID		(_AT(pteval_t, 1) << 0)		/* Valid */
+#define L_PTE_PRESENT		(_AT(pteval_t, 3) << 0)		/* Present */
+#define L_PTE_USER		(_AT(pteval_t, 1) << 6)		/* AP[1] */
+#define L_PTE_SHARED		(_AT(pteval_t, 3) << 8)		/* SH[1:0], inner shareable */
+#define L_PTE_YOUNG		(_AT(pteval_t, 1) << 10)	/* AF */
+#define L_PTE_XN		(_AT(pteval_t, 1) << 54)	/* XN */
+#define L_PTE_DIRTY		(_AT(pteval_t, 1) << 55)
+#define L_PTE_SPECIAL		(_AT(pteval_t, 1) << 56)
+#define L_PTE_NONE		(_AT(pteval_t, 1) << 57)	/* PROT_NONE */
+#define L_PTE_RDONLY		(_AT(pteval_t, 1) << 58)	/* READ ONLY */
+
+#define L_PMD_SECT_VALID	(_AT(pmdval_t, 1) << 0)
+#define L_PMD_SECT_DIRTY	(_AT(pmdval_t, 1) << 55)
+#define L_PMD_SECT_SPLITTING	(_AT(pmdval_t, 1) << 56)
+#define L_PMD_SECT_NONE		(_AT(pmdval_t, 1) << 57)
+#define L_PMD_SECT_RDONLY	(_AT(pteval_t, 1) << 58)
+
+/*
+ * To be used in assembly code with the upper page attributes.
+ */
+#define L_PTE_XN_HIGH		(1 << (54 - 32))
+#define L_PTE_DIRTY_HIGH	(1 << (55 - 32))
+
+/*
+ * AttrIndx[2:0] encoding (mapping attributes defined in the MAIR* registers).
+ */
+#define L_PTE_MT_UNCACHED	(_AT(pteval_t, 0) << 2)	/* strongly ordered */
+#define L_PTE_MT_BUFFERABLE	(_AT(pteval_t, 1) << 2)	/* normal non-cacheable */
+#define L_PTE_MT_WRITETHROUGH	(_AT(pteval_t, 2) << 2)	/* normal inner write-through */
+#define L_PTE_MT_WRITEBACK	(_AT(pteval_t, 3) << 2)	/* normal inner write-back */
+#define L_PTE_MT_WRITEALLOC	(_AT(pteval_t, 7) << 2)	/* normal inner write-alloc */
+#define L_PTE_MT_DEV_SHARED	(_AT(pteval_t, 4) << 2)	/* device */
+#define L_PTE_MT_DEV_NONSHARED	(_AT(pteval_t, 4) << 2)	/* device */
+#define L_PTE_MT_DEV_WC		(_AT(pteval_t, 1) << 2)	/* normal non-cacheable */
+#define L_PTE_MT_DEV_CACHED	(_AT(pteval_t, 3) << 2)	/* normal inner write-back */
+#define L_PTE_MT_MASK		(_AT(pteval_t, 7) << 2)
+
+/*
+ * Software PGD flags.
+ */
+#define L_PGD_SWAPPER		(_AT(pgdval_t, 1) << 55)	/* swapper_pg_dir entry */
+
+/*
+ * 2nd stage PTE definitions for LPAE.
+ */
+#define L_PTE_S2_MT_UNCACHED		(_AT(pteval_t, 0x0) << 2) /* strongly ordered */
+#define L_PTE_S2_MT_WRITETHROUGH	(_AT(pteval_t, 0xa) << 2) /* normal inner write-through */
+#define L_PTE_S2_MT_WRITEBACK		(_AT(pteval_t, 0xf) << 2) /* normal inner write-back */
+#define L_PTE_S2_MT_DEV_SHARED		(_AT(pteval_t, 0x1) << 2) /* device */
+#define L_PTE_S2_MT_MASK		(_AT(pteval_t, 0xf) << 2)
+
+#define L_PTE_S2_RDONLY			(_AT(pteval_t, 1) << 6)   /* HAP[1]   */
+#define L_PTE_S2_RDWR			(_AT(pteval_t, 3) << 6)   /* HAP[2:1] */
+
+#define L_PMD_S2_RDONLY			(_AT(pmdval_t, 1) << 6)   /* HAP[1]   */
+#define L_PMD_S2_RDWR			(_AT(pmdval_t, 3) << 6)   /* HAP[2:1] */
+
+/*
+ * Hyp-mode PL2 PTE definitions for LPAE.
+ */
+#define L_PTE_HYP		L_PTE_USER
+
+#ifndef __ASSEMBLY__
+
+#define pud_none(pud)		(!pud_val(pud))
+#define pud_bad(pud)		(!(pud_val(pud) & 2))
+#define pud_present(pud)	(pud_val(pud))
+#define pmd_table(pmd)		((pmd_val(pmd) & PMD_TYPE_MASK) == \
+						 PMD_TYPE_TABLE)
+#define pmd_sect(pmd)		((pmd_val(pmd) & PMD_TYPE_MASK) == \
+						 PMD_TYPE_SECT)
+#define pmd_large(pmd)		pmd_sect(pmd)
+
+#define pud_clear(pudp)			\
+	do {				\
+		*pudp = __pud(0);	\
+		clean_pmd_entry(pudp);	\
+	} while (0)
+
+#define set_pud(pudp, pud)		\
+	do {				\
+		*pudp = pud;		\
+		flush_pmd_entry(pudp);	\
+	} while (0)
+
+static inline pmd_t *pud_page_vaddr(pud_t pud)
+{
+	return __va(pud_val(pud) & PHYS_MASK & (s32)PAGE_MASK);
+}
+
+/* Find an entry in the second-level page table.. */
+#define pmd_index(addr)		(((addr) >> PMD_SHIFT) & (PTRS_PER_PMD - 1))
+static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
+{
+	return (pmd_t *)pud_page_vaddr(*pud) + pmd_index(addr);
+}
+
+#define pmd_bad(pmd)		(!(pmd_val(pmd) & 2))
+
+#define copy_pmd(pmdpd,pmdps)		\
+	do {				\
+		*pmdpd = *pmdps;	\
+		flush_pmd_entry(pmdpd);	\
+	} while (0)
+
+#define pmd_clear(pmdp)			\
+	do {				\
+		*pmdp = __pmd(0);	\
+		clean_pmd_entry(pmdp);	\
+	} while (0)
+
+/*
+ * For 3 levels of paging the PTE_EXT_NG bit will be set for user address ptes
+ * that are written to a page table but not for ptes created with mk_pte.
+ *
+ * In hugetlb_no_page, a new huge pte (new_pte) is generated and passed to
+ * hugetlb_cow, where it is compared with an entry in a page table.
+ * This comparison test fails erroneously leading ultimately to a memory leak.
+ *
+ * To correct this behaviour, we mask off PTE_EXT_NG for any pte that is
+ * present before running the comparison.
+ */
+#define __HAVE_ARCH_PTE_SAME
+#define pte_same(pte_a,pte_b)	((pte_present(pte_a) ? pte_val(pte_a) & ~PTE_EXT_NG	\
+					: pte_val(pte_a))				\
+				== (pte_present(pte_b) ? pte_val(pte_b) & ~PTE_EXT_NG	\
+					: pte_val(pte_b)))
+
+#define set_pte_ext(ptep,pte,ext) cpu_set_pte_ext(ptep,__pte(pte_val(pte)|(ext)))
+
+#define pte_huge(pte)		(pte_val(pte) && !(pte_val(pte) & PTE_TABLE_BIT))
+#define pte_mkhuge(pte)		(__pte(pte_val(pte) & ~PTE_TABLE_BIT))
+
+#define pmd_isset(pmd, val)	((u32)(val) == (val) ? pmd_val(pmd) & (val) \
+						: !!(pmd_val(pmd) & (val)))
+#define pmd_isclear(pmd, val)	(!(pmd_val(pmd) & (val)))
+
+#define pmd_young(pmd)		(pmd_isset((pmd), PMD_SECT_AF))
+#define pte_special(pte)	(pte_isset((pte), L_PTE_SPECIAL))
+static inline pte_t pte_mkspecial(pte_t pte)
+{
+	pte_val(pte) |= L_PTE_SPECIAL;
+	return pte;
+}
+#define	__HAVE_ARCH_PTE_SPECIAL
+
+#define __HAVE_ARCH_PMD_WRITE
+#define pmd_write(pmd)		(pmd_isclear((pmd), L_PMD_SECT_RDONLY))
+#define pmd_dirty(pmd)		(pmd_isset((pmd), L_PMD_SECT_DIRTY))
+#define pud_page(pud)		pmd_page(__pmd(pud_val(pud)))
+#define pud_write(pud)		pmd_write(__pmd(pud_val(pud)))
+
+#define pmd_hugewillfault(pmd)	(!pmd_young(pmd) || !pmd_write(pmd))
+#define pmd_thp_or_huge(pmd)	(pmd_huge(pmd) || pmd_trans_huge(pmd))
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define pmd_trans_huge(pmd)	(pmd_val(pmd) && !pmd_table(pmd))
+#define pmd_trans_splitting(pmd) (pmd_isset((pmd), L_PMD_SECT_SPLITTING))
+
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+#define __HAVE_ARCH_PMDP_SPLITTING_FLUSH
+void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address,
+			  pmd_t *pmdp);
+#endif
+#endif
+
+#define PMD_BIT_FUNC(fn,op) \
+static inline pmd_t pmd_##fn(pmd_t pmd) { pmd_val(pmd) op; return pmd; }
+
+PMD_BIT_FUNC(wrprotect,	|= L_PMD_SECT_RDONLY);
+PMD_BIT_FUNC(mkold,	&= ~PMD_SECT_AF);
+PMD_BIT_FUNC(mksplitting, |= L_PMD_SECT_SPLITTING);
+PMD_BIT_FUNC(mkwrite,   &= ~L_PMD_SECT_RDONLY);
+PMD_BIT_FUNC(mkdirty,   |= L_PMD_SECT_DIRTY);
+PMD_BIT_FUNC(mkyoung,   |= PMD_SECT_AF);
+
+#define pmd_mkhuge(pmd)		(__pmd(pmd_val(pmd) & ~PMD_TABLE_BIT))
+
+#define pmd_pfn(pmd)		(((pmd_val(pmd) & PMD_MASK) & PHYS_MASK) >> PAGE_SHIFT)
+#define pfn_pmd(pfn,prot)	(__pmd(((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot)))
+#define mk_pmd(page,prot)	pfn_pmd(page_to_pfn(page),prot)
+
+/* represent a notpresent pmd by zero, this is used by pmdp_invalidate */
+static inline pmd_t pmd_mknotpresent(pmd_t pmd)
+{
+	return __pmd(0);
+}
+
+static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
+{
+	const pmdval_t mask = PMD_SECT_USER | PMD_SECT_XN | L_PMD_SECT_RDONLY |
+				L_PMD_SECT_VALID | L_PMD_SECT_NONE;
+	pmd_val(pmd) = (pmd_val(pmd) & ~mask) | (pgprot_val(newprot) & mask);
+	return pmd;
+}
+
+static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
+			      pmd_t *pmdp, pmd_t pmd)
+{
+	BUG_ON(addr >= TASK_SIZE);
+
+	/* create a faulting entry if PROT_NONE protected */
+	if (pmd_val(pmd) & L_PMD_SECT_NONE)
+		pmd_val(pmd) &= ~L_PMD_SECT_VALID;
+
+	if (pmd_write(pmd) && pmd_dirty(pmd))
+		pmd_val(pmd) &= ~PMD_SECT_AP2;
+	else
+		pmd_val(pmd) |= PMD_SECT_AP2;
+
+	*pmdp = __pmd(pmd_val(pmd) | PMD_SECT_nG);
+	flush_pmd_entry(pmdp);
+}
+
+static inline int has_transparent_hugepage(void)
+{
+	return 1;
+}
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_PGTABLE_3LEVEL_H */
diff --git a/arch/arm/include/asm/pgtable-hwdef.h b/arch/arm/include/asm/pgtable-hwdef.h
new file mode 100644
index 000000000..8426229ba
--- /dev/null
+++ b/arch/arm/include/asm/pgtable-hwdef.h
@@ -0,0 +1,19 @@
+/*
+ *  arch/arm/include/asm/pgtable-hwdef.h
+ *
+ *  Copyright (C) 1995-2002 Russell King
+ *
+ * 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.
+ */
+#ifndef _ASMARM_PGTABLE_HWDEF_H
+#define _ASMARM_PGTABLE_HWDEF_H
+
+#ifdef CONFIG_ARM_LPAE
+#include <asm/pgtable-3level-hwdef.h>
+#else
+#include <asm/pgtable-2level-hwdef.h>
+#endif
+
+#endif
diff --git a/arch/arm/include/asm/pgtable-nommu.h b/arch/arm/include/asm/pgtable-nommu.h
new file mode 100644
index 000000000..add094d09
--- /dev/null
+++ b/arch/arm/include/asm/pgtable-nommu.h
@@ -0,0 +1,114 @@
+/*
+ *  arch/arm/include/asm/pgtable-nommu.h
+ *
+ *  Copyright (C) 1995-2002 Russell King
+ *  Copyright (C) 2004  Hyok S. Choi
+ *
+ * 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.
+ */
+#ifndef _ASMARM_PGTABLE_NOMMU_H
+#define _ASMARM_PGTABLE_NOMMU_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/slab.h>
+#include <asm/processor.h>
+#include <asm/page.h>
+
+/*
+ * Trivial page table functions.
+ */
+#define pgd_present(pgd)	(1)
+#define pgd_none(pgd)		(0)
+#define pgd_bad(pgd)		(0)
+#define pgd_clear(pgdp)
+#define kern_addr_valid(addr)	(1)
+#define	pmd_offset(a, b)	((void *)0)
+/* FIXME */
+/*
+ * PMD_SHIFT determines the size of the area a second-level page table can map
+ * PGDIR_SHIFT determines what a third-level page table entry can map
+ */
+#define PGDIR_SHIFT		21
+
+#define PGDIR_SIZE		(1UL << PGDIR_SHIFT)
+#define PGDIR_MASK		(~(PGDIR_SIZE-1))
+/* FIXME */
+
+#define PAGE_NONE	__pgprot(0)
+#define PAGE_SHARED	__pgprot(0)
+#define PAGE_COPY	__pgprot(0)
+#define PAGE_READONLY	__pgprot(0)
+#define PAGE_KERNEL	__pgprot(0)
+
+#define swapper_pg_dir ((pgd_t *) 0)
+
+#define __swp_type(x)		(0)
+#define __swp_offset(x)		(0)
+#define __swp_entry(typ,off)	((swp_entry_t) { ((typ) | ((off) << 7)) })
+#define __pte_to_swp_entry(pte)	((swp_entry_t) { pte_val(pte) })
+#define __swp_entry_to_pte(x)	((pte_t) { (x).val })
+
+
+typedef pte_t *pte_addr_t;
+
+/*
+ * ZERO_PAGE is a global shared page that is always zero: used
+ * for zero-mapped memory areas etc..
+ */
+#define ZERO_PAGE(vaddr)	(virt_to_page(0))
+
+/*
+ * Mark the prot value as uncacheable and unbufferable.
+ */
+#define pgprot_noncached(prot)	__pgprot(0)
+#define pgprot_writecombine(prot) __pgprot(0)
+#define pgprot_dmacoherent(prot) __pgprot(0)
+
+
+/*
+ * These would be in other places but having them here reduces the diffs.
+ */
+extern unsigned int kobjsize(const void *objp);
+
+/*
+ * No page table caches to initialise.
+ */
+#define pgtable_cache_init()	do { } while (0)
+
+/*
+ * All 32bit addresses are effectively valid for vmalloc...
+ * Sort of meaningless for non-VM targets.
+ */
+#define	VMALLOC_START	0UL
+#define	VMALLOC_END	0xffffffffUL
+
+#define FIRST_USER_ADDRESS      0UL
+
+#include <asm-generic/pgtable.h>
+
+#else 
+
+/*
+ * dummy tlb and user structures.
+ */
+#define v3_tlb_fns	(0)
+#define v4_tlb_fns	(0)
+#define v4wb_tlb_fns	(0)
+#define v4wbi_tlb_fns	(0)
+#define v6wbi_tlb_fns	(0)
+#define v7wbi_tlb_fns	(0)
+
+#define v3_user_fns	(0)
+#define v4_user_fns	(0)
+#define v4_mc_user_fns	(0)
+#define v4wb_user_fns	(0)
+#define v4wt_user_fns	(0)
+#define v6_user_fns	(0)
+#define xscale_mc_user_fns (0)
+
+#endif /*__ASSEMBLY__*/
+
+#endif /* _ASMARM_PGTABLE_H */
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
new file mode 100644
index 000000000..f40354198
--- /dev/null
+++ b/arch/arm/include/asm/pgtable.h
@@ -0,0 +1,363 @@
+/*
+ *  arch/arm/include/asm/pgtable.h
+ *
+ *  Copyright (C) 1995-2002 Russell King
+ *
+ * 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.
+ */
+#ifndef _ASMARM_PGTABLE_H
+#define _ASMARM_PGTABLE_H
+
+#include <linux/const.h>
+#include <asm/proc-fns.h>
+
+#ifndef CONFIG_MMU
+
+#include <asm-generic/4level-fixup.h>
+#include <asm/pgtable-nommu.h>
+
+#else
+
+#include <asm-generic/pgtable-nopud.h>
+#include <asm/memory.h>
+#include <asm/pgtable-hwdef.h>
+
+
+#include <asm/tlbflush.h>
+
+#ifdef CONFIG_ARM_LPAE
+#include <asm/pgtable-3level.h>
+#else
+#include <asm/pgtable-2level.h>
+#endif
+
+/*
+ * Just any arbitrary offset to the start of the vmalloc VM area: the
+ * current 8MB value just means that there will be a 8MB "hole" after the
+ * physical memory until the kernel virtual memory starts.  That means that
+ * any out-of-bounds memory accesses will hopefully be caught.
+ * The vmalloc() routines leaves a hole of 4kB between each vmalloced
+ * area for the same reason. ;)
+ */
+#define VMALLOC_OFFSET		(8*1024*1024)
+#define VMALLOC_START		(((unsigned long)high_memory + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1))
+#define VMALLOC_END		0xff000000UL
+
+#define LIBRARY_TEXT_START	0x0c000000
+
+#ifndef __ASSEMBLY__
+extern void __pte_error(const char *file, int line, pte_t);
+extern void __pmd_error(const char *file, int line, pmd_t);
+extern void __pgd_error(const char *file, int line, pgd_t);
+
+#define pte_ERROR(pte)		__pte_error(__FILE__, __LINE__, pte)
+#define pmd_ERROR(pmd)		__pmd_error(__FILE__, __LINE__, pmd)
+#define pgd_ERROR(pgd)		__pgd_error(__FILE__, __LINE__, pgd)
+
+/*
+ * This is the lowest virtual address we can permit any user space
+ * mapping to be mapped at.  This is particularly important for
+ * non-high vector CPUs.
+ */
+#define FIRST_USER_ADDRESS	(PAGE_SIZE * 2)
+
+/*
+ * Use TASK_SIZE as the ceiling argument for free_pgtables() and
+ * free_pgd_range() to avoid freeing the modules pmd when LPAE is enabled (pmd
+ * page shared between user and kernel).
+ */
+#ifdef CONFIG_ARM_LPAE
+#define USER_PGTABLES_CEILING	TASK_SIZE
+#endif
+
+/*
+ * The pgprot_* and protection_map entries will be fixed up in runtime
+ * to include the cachable and bufferable bits based on memory policy,
+ * as well as any architecture dependent bits like global/ASID and SMP
+ * shared mapping bits.
+ */
+#define _L_PTE_DEFAULT	L_PTE_PRESENT | L_PTE_YOUNG
+
+extern pgprot_t		pgprot_user;
+extern pgprot_t		pgprot_kernel;
+extern pgprot_t		pgprot_hyp_device;
+extern pgprot_t		pgprot_s2;
+extern pgprot_t		pgprot_s2_device;
+
+#define _MOD_PROT(p, b)	__pgprot(pgprot_val(p) | (b))
+
+#define PAGE_NONE		_MOD_PROT(pgprot_user, L_PTE_XN | L_PTE_RDONLY | L_PTE_NONE)
+#define PAGE_SHARED		_MOD_PROT(pgprot_user, L_PTE_USER | L_PTE_XN)
+#define PAGE_SHARED_EXEC	_MOD_PROT(pgprot_user, L_PTE_USER)
+#define PAGE_COPY		_MOD_PROT(pgprot_user, L_PTE_USER | L_PTE_RDONLY | L_PTE_XN)
+#define PAGE_COPY_EXEC		_MOD_PROT(pgprot_user, L_PTE_USER | L_PTE_RDONLY)
+#define PAGE_READONLY		_MOD_PROT(pgprot_user, L_PTE_USER | L_PTE_RDONLY | L_PTE_XN)
+#define PAGE_READONLY_EXEC	_MOD_PROT(pgprot_user, L_PTE_USER | L_PTE_RDONLY)
+#define PAGE_KERNEL		_MOD_PROT(pgprot_kernel, L_PTE_XN)
+#define PAGE_KERNEL_EXEC	pgprot_kernel
+#define PAGE_HYP		_MOD_PROT(pgprot_kernel, L_PTE_HYP)
+#define PAGE_HYP_DEVICE		_MOD_PROT(pgprot_hyp_device, L_PTE_HYP)
+#define PAGE_S2			_MOD_PROT(pgprot_s2, L_PTE_S2_RDONLY)
+#define PAGE_S2_DEVICE		_MOD_PROT(pgprot_s2_device, L_PTE_S2_RDONLY)
+
+#define __PAGE_NONE		__pgprot(_L_PTE_DEFAULT | L_PTE_RDONLY | L_PTE_XN | L_PTE_NONE)
+#define __PAGE_SHARED		__pgprot(_L_PTE_DEFAULT | L_PTE_USER | L_PTE_XN)
+#define __PAGE_SHARED_EXEC	__pgprot(_L_PTE_DEFAULT | L_PTE_USER)
+#define __PAGE_COPY		__pgprot(_L_PTE_DEFAULT | L_PTE_USER | L_PTE_RDONLY | L_PTE_XN)
+#define __PAGE_COPY_EXEC	__pgprot(_L_PTE_DEFAULT | L_PTE_USER | L_PTE_RDONLY)
+#define __PAGE_READONLY		__pgprot(_L_PTE_DEFAULT | L_PTE_USER | L_PTE_RDONLY | L_PTE_XN)
+#define __PAGE_READONLY_EXEC	__pgprot(_L_PTE_DEFAULT | L_PTE_USER | L_PTE_RDONLY)
+
+#define __pgprot_modify(prot,mask,bits)		\
+	__pgprot((pgprot_val(prot) & ~(mask)) | (bits))
+
+#define pgprot_noncached(prot) \
+	__pgprot_modify(prot, L_PTE_MT_MASK, L_PTE_MT_UNCACHED)
+
+#define pgprot_writecombine(prot) \
+	__pgprot_modify(prot, L_PTE_MT_MASK, L_PTE_MT_BUFFERABLE)
+
+#define pgprot_stronglyordered(prot) \
+	__pgprot_modify(prot, L_PTE_MT_MASK, L_PTE_MT_UNCACHED)
+
+#ifdef CONFIG_ARM_DMA_MEM_BUFFERABLE
+#define pgprot_dmacoherent(prot) \
+	__pgprot_modify(prot, L_PTE_MT_MASK, L_PTE_MT_BUFFERABLE | L_PTE_XN)
+#define __HAVE_PHYS_MEM_ACCESS_PROT
+struct file;
+extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
+				     unsigned long size, pgprot_t vma_prot);
+#else
+#define pgprot_dmacoherent(prot) \
+	__pgprot_modify(prot, L_PTE_MT_MASK, L_PTE_MT_UNCACHED | L_PTE_XN)
+#endif
+
+#endif /* __ASSEMBLY__ */
+
+/*
+ * The table below defines the page protection levels that we insert into our
+ * Linux page table version.  These get translated into the best that the
+ * architecture can perform.  Note that on most ARM hardware:
+ *  1) We cannot do execute protection
+ *  2) If we could do execute protection, then read is implied
+ *  3) write implies read permissions
+ */
+#define __P000  __PAGE_NONE
+#define __P001  __PAGE_READONLY
+#define __P010  __PAGE_COPY
+#define __P011  __PAGE_COPY
+#define __P100  __PAGE_READONLY_EXEC
+#define __P101  __PAGE_READONLY_EXEC
+#define __P110  __PAGE_COPY_EXEC
+#define __P111  __PAGE_COPY_EXEC
+
+#define __S000  __PAGE_NONE
+#define __S001  __PAGE_READONLY
+#define __S010  __PAGE_SHARED
+#define __S011  __PAGE_SHARED
+#define __S100  __PAGE_READONLY_EXEC
+#define __S101  __PAGE_READONLY_EXEC
+#define __S110  __PAGE_SHARED_EXEC
+#define __S111  __PAGE_SHARED_EXEC
+
+#ifndef __ASSEMBLY__
+/*
+ * ZERO_PAGE is a global shared page that is always zero: used
+ * for zero-mapped memory areas etc..
+ */
+extern struct page *empty_zero_page;
+#define ZERO_PAGE(vaddr)	(empty_zero_page)
+
+
+extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
+
+/* to find an entry in a page-table-directory */
+#define pgd_index(addr)		((addr) >> PGDIR_SHIFT)
+
+#define pgd_offset(mm, addr)	((mm)->pgd + pgd_index(addr))
+
+/* to find an entry in a kernel page-table-directory */
+#define pgd_offset_k(addr)	pgd_offset(&init_mm, addr)
+
+#define pmd_none(pmd)		(!pmd_val(pmd))
+#define pmd_present(pmd)	(pmd_val(pmd))
+
+static inline pte_t *pmd_page_vaddr(pmd_t pmd)
+{
+	return __va(pmd_val(pmd) & PHYS_MASK & (s32)PAGE_MASK);
+}
+
+#define pmd_page(pmd)		pfn_to_page(__phys_to_pfn(pmd_val(pmd) & PHYS_MASK))
+
+#ifndef CONFIG_HIGHPTE
+#define __pte_map(pmd)		pmd_page_vaddr(*(pmd))
+#define __pte_unmap(pte)	do { } while (0)
+#else
+#define __pte_map(pmd)		(pte_t *)kmap_atomic(pmd_page(*(pmd)))
+#define __pte_unmap(pte)	kunmap_atomic(pte)
+#endif
+
+#define pte_index(addr)		(((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
+
+#define pte_offset_kernel(pmd,addr)	(pmd_page_vaddr(*(pmd)) + pte_index(addr))
+
+#define pte_offset_map(pmd,addr)	(__pte_map(pmd) + pte_index(addr))
+#define pte_unmap(pte)			__pte_unmap(pte)
+
+#define pte_pfn(pte)		((pte_val(pte) & PHYS_MASK) >> PAGE_SHIFT)
+#define pfn_pte(pfn,prot)	__pte(__pfn_to_phys(pfn) | pgprot_val(prot))
+
+#define pte_page(pte)		pfn_to_page(pte_pfn(pte))
+#define mk_pte(page,prot)	pfn_pte(page_to_pfn(page), prot)
+
+#define pte_clear(mm,addr,ptep)	set_pte_ext(ptep, __pte(0), 0)
+
+#define pte_isset(pte, val)	((u32)(val) == (val) ? pte_val(pte) & (val) \
+						: !!(pte_val(pte) & (val)))
+#define pte_isclear(pte, val)	(!(pte_val(pte) & (val)))
+
+#define pte_none(pte)		(!pte_val(pte))
+#define pte_present(pte)	(pte_isset((pte), L_PTE_PRESENT))
+#define pte_valid(pte)		(pte_isset((pte), L_PTE_VALID))
+#define pte_accessible(mm, pte)	(mm_tlb_flush_pending(mm) ? pte_present(pte) : pte_valid(pte))
+#define pte_write(pte)		(pte_isclear((pte), L_PTE_RDONLY))
+#define pte_dirty(pte)		(pte_isset((pte), L_PTE_DIRTY))
+#define pte_young(pte)		(pte_isset((pte), L_PTE_YOUNG))
+#define pte_exec(pte)		(pte_isclear((pte), L_PTE_XN))
+
+#define pte_valid_user(pte)	\
+	(pte_valid(pte) && pte_isset((pte), L_PTE_USER) && pte_young(pte))
+
+#if __LINUX_ARM_ARCH__ < 6
+static inline void __sync_icache_dcache(pte_t pteval)
+{
+}
+#else
+extern void __sync_icache_dcache(pte_t pteval);
+#endif
+
+static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
+			      pte_t *ptep, pte_t pteval)
+{
+	unsigned long ext = 0;
+
+	if (addr < TASK_SIZE && pte_valid_user(pteval)) {
+		if (!pte_special(pteval))
+			__sync_icache_dcache(pteval);
+		ext |= PTE_EXT_NG;
+	}
+
+	set_pte_ext(ptep, pteval, ext);
+}
+
+static inline pte_t clear_pte_bit(pte_t pte, pgprot_t prot)
+{
+	pte_val(pte) &= ~pgprot_val(prot);
+	return pte;
+}
+
+static inline pte_t set_pte_bit(pte_t pte, pgprot_t prot)
+{
+	pte_val(pte) |= pgprot_val(prot);
+	return pte;
+}
+
+static inline pte_t pte_wrprotect(pte_t pte)
+{
+	return set_pte_bit(pte, __pgprot(L_PTE_RDONLY));
+}
+
+static inline pte_t pte_mkwrite(pte_t pte)
+{
+	return clear_pte_bit(pte, __pgprot(L_PTE_RDONLY));
+}
+
+static inline pte_t pte_mkclean(pte_t pte)
+{
+	return clear_pte_bit(pte, __pgprot(L_PTE_DIRTY));
+}
+
+static inline pte_t pte_mkdirty(pte_t pte)
+{
+	return set_pte_bit(pte, __pgprot(L_PTE_DIRTY));
+}
+
+static inline pte_t pte_mkold(pte_t pte)
+{
+	return clear_pte_bit(pte, __pgprot(L_PTE_YOUNG));
+}
+
+static inline pte_t pte_mkyoung(pte_t pte)
+{
+	return set_pte_bit(pte, __pgprot(L_PTE_YOUNG));
+}
+
+static inline pte_t pte_mkexec(pte_t pte)
+{
+	return clear_pte_bit(pte, __pgprot(L_PTE_XN));
+}
+
+static inline pte_t pte_mknexec(pte_t pte)
+{
+	return set_pte_bit(pte, __pgprot(L_PTE_XN));
+}
+
+static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
+{
+	const pteval_t mask = L_PTE_XN | L_PTE_RDONLY | L_PTE_USER |
+		L_PTE_NONE | L_PTE_VALID;
+	pte_val(pte) = (pte_val(pte) & ~mask) | (pgprot_val(newprot) & mask);
+	return pte;
+}
+
+/*
+ * Encode and decode a swap entry.  Swap entries are stored in the Linux
+ * page tables as follows:
+ *
+ *   3 3 2 2 2 2 2 2 2 2 2 2 1 1 1 1 1 1 1 1 1 1
+ *   1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0
+ *   <--------------- offset ------------------------> < type -> 0 0
+ *
+ * This gives us up to 31 swap files and 128GB per swap file.  Note that
+ * the offset field is always non-zero.
+ */
+#define __SWP_TYPE_SHIFT	2
+#define __SWP_TYPE_BITS		5
+#define __SWP_TYPE_MASK		((1 << __SWP_TYPE_BITS) - 1)
+#define __SWP_OFFSET_SHIFT	(__SWP_TYPE_BITS + __SWP_TYPE_SHIFT)
+
+#define __swp_type(x)		(((x).val >> __SWP_TYPE_SHIFT) & __SWP_TYPE_MASK)
+#define __swp_offset(x)		((x).val >> __SWP_OFFSET_SHIFT)
+#define __swp_entry(type,offset) ((swp_entry_t) { ((type) << __SWP_TYPE_SHIFT) | ((offset) << __SWP_OFFSET_SHIFT) })
+
+#define __pte_to_swp_entry(pte)	((swp_entry_t) { pte_val(pte) })
+#define __swp_entry_to_pte(swp)	((pte_t) { (swp).val })
+
+/*
+ * It is an error for the kernel to have more swap files than we can
+ * encode in the PTEs.  This ensures that we know when MAX_SWAPFILES
+ * is increased beyond what we presently support.
+ */
+#define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > __SWP_TYPE_BITS)
+
+/* Needs to be defined here and not in linux/mm.h, as it is arch dependent */
+/* FIXME: this is not correct */
+#define kern_addr_valid(addr)	(1)
+
+#include <asm-generic/pgtable.h>
+
+/*
+ * We provide our own arch_get_unmapped_area to cope with VIPT caches.
+ */
+#define HAVE_ARCH_UNMAPPED_AREA
+#define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
+
+#define pgtable_cache_init() do { } while (0)
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* CONFIG_MMU */
+
+#endif /* _ASMARM_PGTABLE_H */
diff --git a/arch/arm/include/asm/pmu.h b/arch/arm/include/asm/pmu.h
new file mode 100644
index 000000000..675e4ab79
--- /dev/null
+++ b/arch/arm/include/asm/pmu.h
@@ -0,0 +1,163 @@
+/*
+ *  linux/arch/arm/include/asm/pmu.h
+ *
+ *  Copyright (C) 2009 picoChip Designs Ltd, Jamie Iles
+ *
+ * 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.
+ *
+ */
+
+#ifndef __ARM_PMU_H__
+#define __ARM_PMU_H__
+
+#include <linux/interrupt.h>
+#include <linux/perf_event.h>
+
+#include <asm/cputype.h>
+
+/*
+ * struct arm_pmu_platdata - ARM PMU platform data
+ *
+ * @handle_irq: an optional handler which will be called from the
+ *	interrupt and passed the address of the low level handler,
+ *	and can be used to implement any platform specific handling
+ *	before or after calling it.
+ * @runtime_resume: an optional handler which will be called by the
+ *	runtime PM framework following a call to pm_runtime_get().
+ *	Note that if pm_runtime_get() is called more than once in
+ *	succession this handler will only be called once.
+ * @runtime_suspend: an optional handler which will be called by the
+ *	runtime PM framework following a call to pm_runtime_put().
+ *	Note that if pm_runtime_get() is called more than once in
+ *	succession this handler will only be called following the
+ *	final call to pm_runtime_put() that actually disables the
+ *	hardware.
+ */
+struct arm_pmu_platdata {
+	irqreturn_t (*handle_irq)(int irq, void *dev,
+				  irq_handler_t pmu_handler);
+	int (*runtime_resume)(struct device *dev);
+	int (*runtime_suspend)(struct device *dev);
+};
+
+#ifdef CONFIG_HW_PERF_EVENTS
+
+/*
+ * The ARMv7 CPU PMU supports up to 32 event counters.
+ */
+#define ARMPMU_MAX_HWEVENTS		32
+
+#define HW_OP_UNSUPPORTED		0xFFFF
+#define C(_x)				PERF_COUNT_HW_CACHE_##_x
+#define CACHE_OP_UNSUPPORTED		0xFFFF
+
+#define PERF_MAP_ALL_UNSUPPORTED					\
+	[0 ... PERF_COUNT_HW_MAX - 1] = HW_OP_UNSUPPORTED
+
+#define PERF_CACHE_MAP_ALL_UNSUPPORTED					\
+[0 ... C(MAX) - 1] = {							\
+	[0 ... C(OP_MAX) - 1] = {					\
+		[0 ... C(RESULT_MAX) - 1] = CACHE_OP_UNSUPPORTED,	\
+	},								\
+}
+
+/* The events for a given PMU register set. */
+struct pmu_hw_events {
+	/*
+	 * The events that are active on the PMU for the given index.
+	 */
+	struct perf_event	*events[ARMPMU_MAX_HWEVENTS];
+
+	/*
+	 * A 1 bit for an index indicates that the counter is being used for
+	 * an event. A 0 means that the counter can be used.
+	 */
+	DECLARE_BITMAP(used_mask, ARMPMU_MAX_HWEVENTS);
+
+	/*
+	 * Hardware lock to serialize accesses to PMU registers. Needed for the
+	 * read/modify/write sequences.
+	 */
+	raw_spinlock_t		pmu_lock;
+
+	/*
+	 * When using percpu IRQs, we need a percpu dev_id. Place it here as we
+	 * already have to allocate this struct per cpu.
+	 */
+	struct arm_pmu		*percpu_pmu;
+};
+
+struct arm_pmu {
+	struct pmu	pmu;
+	cpumask_t	active_irqs;
+	int		*irq_affinity;
+	char		*name;
+	irqreturn_t	(*handle_irq)(int irq_num, void *dev);
+	void		(*enable)(struct perf_event *event);
+	void		(*disable)(struct perf_event *event);
+	int		(*get_event_idx)(struct pmu_hw_events *hw_events,
+					 struct perf_event *event);
+	void		(*clear_event_idx)(struct pmu_hw_events *hw_events,
+					 struct perf_event *event);
+	int		(*set_event_filter)(struct hw_perf_event *evt,
+					    struct perf_event_attr *attr);
+	u32		(*read_counter)(struct perf_event *event);
+	void		(*write_counter)(struct perf_event *event, u32 val);
+	void		(*start)(struct arm_pmu *);
+	void		(*stop)(struct arm_pmu *);
+	void		(*reset)(void *);
+	int		(*request_irq)(struct arm_pmu *, irq_handler_t handler);
+	void		(*free_irq)(struct arm_pmu *);
+	int		(*map_event)(struct perf_event *event);
+	int		num_events;
+	atomic_t	active_events;
+	struct mutex	reserve_mutex;
+	u64		max_period;
+	struct platform_device	*plat_device;
+	struct pmu_hw_events	__percpu *hw_events;
+	struct notifier_block	hotplug_nb;
+};
+
+#define to_arm_pmu(p) (container_of(p, struct arm_pmu, pmu))
+
+extern const struct dev_pm_ops armpmu_dev_pm_ops;
+
+int armpmu_register(struct arm_pmu *armpmu, int type);
+
+u64 armpmu_event_update(struct perf_event *event);
+
+int armpmu_event_set_period(struct perf_event *event);
+
+int armpmu_map_event(struct perf_event *event,
+		     const unsigned (*event_map)[PERF_COUNT_HW_MAX],
+		     const unsigned (*cache_map)[PERF_COUNT_HW_CACHE_MAX]
+						[PERF_COUNT_HW_CACHE_OP_MAX]
+						[PERF_COUNT_HW_CACHE_RESULT_MAX],
+		     u32 raw_event_mask);
+
+struct pmu_probe_info {
+	unsigned int cpuid;
+	unsigned int mask;
+	int (*init)(struct arm_pmu *);
+};
+
+#define PMU_PROBE(_cpuid, _mask, _fn)	\
+{					\
+	.cpuid = (_cpuid),		\
+	.mask = (_mask),		\
+	.init = (_fn),			\
+}
+
+#define ARM_PMU_PROBE(_cpuid, _fn) \
+	PMU_PROBE(_cpuid, ARM_CPU_PART_MASK, _fn)
+
+#define ARM_PMU_XSCALE_MASK	((0xff << 24) | ARM_CPU_XSCALE_ARCH_MASK)
+
+#define XSCALE_PMU_PROBE(_version, _fn) \
+	PMU_PROBE(ARM_CPU_IMP_INTEL << 24 | _version, ARM_PMU_XSCALE_MASK, _fn)
+
+#endif /* CONFIG_HW_PERF_EVENTS */
+
+#endif /* __ARM_PMU_H__ */
diff --git a/arch/arm/include/asm/probes.h b/arch/arm/include/asm/probes.h
new file mode 100644
index 000000000..1e5b9bb92
--- /dev/null
+++ b/arch/arm/include/asm/probes.h
@@ -0,0 +1,58 @@
+/*
+ * arch/arm/include/asm/probes.h
+ *
+ * Original contents copied from arch/arm/include/asm/kprobes.h
+ * which contains the following notice...
+ *
+ * Copyright (C) 2006, 2007 Motorola Inc.
+ *
+ * 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.
+ */
+
+#ifndef _ASM_PROBES_H
+#define _ASM_PROBES_H
+
+#ifndef __ASSEMBLY__
+
+typedef u32 probes_opcode_t;
+
+struct arch_probes_insn;
+typedef void (probes_insn_handler_t)(probes_opcode_t,
+				     struct arch_probes_insn *,
+				     struct pt_regs *);
+typedef unsigned long (probes_check_cc)(unsigned long);
+typedef void (probes_insn_singlestep_t)(probes_opcode_t,
+					struct arch_probes_insn *,
+					struct pt_regs *);
+typedef void (probes_insn_fn_t)(void);
+
+/* Architecture specific copy of original instruction. */
+struct arch_probes_insn {
+	probes_opcode_t			*insn;
+	probes_insn_handler_t		*insn_handler;
+	probes_check_cc			*insn_check_cc;
+	probes_insn_singlestep_t	*insn_singlestep;
+	probes_insn_fn_t		*insn_fn;
+	int				stack_space;
+	unsigned long			register_usage_flags;
+	bool				kprobe_direct_exec;
+};
+
+#endif /* __ASSEMBLY__ */
+
+/*
+ * We assume one instruction can consume at most 64 bytes stack, which is
+ * 'push {r0-r15}'. Instructions consume more or unknown stack space like
+ * 'str r0, [sp, #-80]' and 'str r0, [sp, r1]' should be prohibit to probe.
+ * Both kprobe and jprobe use this macro.
+ */
+#define MAX_STACK_SIZE			64
+
+#endif
diff --git a/arch/arm/include/asm/proc-fns.h b/arch/arm/include/asm/proc-fns.h
new file mode 100644
index 000000000..5324c1112
--- /dev/null
+++ b/arch/arm/include/asm/proc-fns.h
@@ -0,0 +1,160 @@
+/*
+ *  arch/arm/include/asm/proc-fns.h
+ *
+ *  Copyright (C) 1997-1999 Russell King
+ *  Copyright (C) 2000 Deep Blue Solutions 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.
+ */
+#ifndef __ASM_PROCFNS_H
+#define __ASM_PROCFNS_H
+
+#ifdef __KERNEL__
+
+#include <asm/glue-proc.h>
+#include <asm/page.h>
+
+#ifndef __ASSEMBLY__
+
+struct mm_struct;
+
+/*
+ * Don't change this structure - ASM code relies on it.
+ */
+extern struct processor {
+	/* MISC
+	 * get data abort address/flags
+	 */
+	void (*_data_abort)(unsigned long pc);
+	/*
+	 * Retrieve prefetch fault address
+	 */
+	unsigned long (*_prefetch_abort)(unsigned long lr);
+	/*
+	 * Set up any processor specifics
+	 */
+	void (*_proc_init)(void);
+	/*
+	 * Disable any processor specifics
+	 */
+	void (*_proc_fin)(void);
+	/*
+	 * Special stuff for a reset
+	 */
+	void (*reset)(unsigned long addr) __attribute__((noreturn));
+	/*
+	 * Idle the processor
+	 */
+	int (*_do_idle)(void);
+	/*
+	 * Processor architecture specific
+	 */
+	/*
+	 * clean a virtual address range from the
+	 * D-cache without flushing the cache.
+	 */
+	void (*dcache_clean_area)(void *addr, int size);
+
+	/*
+	 * Set the page table
+	 */
+	void (*switch_mm)(phys_addr_t pgd_phys, struct mm_struct *mm);
+	/*
+	 * Set a possibly extended PTE.  Non-extended PTEs should
+	 * ignore 'ext'.
+	 */
+#ifdef CONFIG_ARM_LPAE
+	void (*set_pte_ext)(pte_t *ptep, pte_t pte);
+#else
+	void (*set_pte_ext)(pte_t *ptep, pte_t pte, unsigned int ext);
+#endif
+
+	/* Suspend/resume */
+	unsigned int suspend_size;
+	void (*do_suspend)(void *);
+	void (*do_resume)(void *);
+} processor;
+
+#ifndef MULTI_CPU
+extern void cpu_proc_init(void);
+extern void cpu_proc_fin(void);
+extern int cpu_do_idle(void);
+extern void cpu_dcache_clean_area(void *, int);
+extern void cpu_do_switch_mm(phys_addr_t pgd_phys, struct mm_struct *mm);
+#ifdef CONFIG_ARM_LPAE
+extern void cpu_set_pte_ext(pte_t *ptep, pte_t pte);
+#else
+extern void cpu_set_pte_ext(pte_t *ptep, pte_t pte, unsigned int ext);
+#endif
+extern void cpu_reset(unsigned long addr) __attribute__((noreturn));
+
+/* These three are private to arch/arm/kernel/suspend.c */
+extern void cpu_do_suspend(void *);
+extern void cpu_do_resume(void *);
+#else
+#define cpu_proc_init			processor._proc_init
+#define cpu_proc_fin			processor._proc_fin
+#define cpu_reset			processor.reset
+#define cpu_do_idle			processor._do_idle
+#define cpu_dcache_clean_area		processor.dcache_clean_area
+#define cpu_set_pte_ext			processor.set_pte_ext
+#define cpu_do_switch_mm		processor.switch_mm
+
+/* These three are private to arch/arm/kernel/suspend.c */
+#define cpu_do_suspend			processor.do_suspend
+#define cpu_do_resume			processor.do_resume
+#endif
+
+extern void cpu_resume(void);
+
+#include <asm/memory.h>
+
+#ifdef CONFIG_MMU
+
+#define cpu_switch_mm(pgd,mm) cpu_do_switch_mm(virt_to_phys(pgd),mm)
+
+#ifdef CONFIG_ARM_LPAE
+
+#define cpu_get_ttbr(nr)					\
+	({							\
+		u64 ttbr;					\
+		__asm__("mrrc	p15, " #nr ", %Q0, %R0, c2"	\
+			: "=r" (ttbr));				\
+		ttbr;						\
+	})
+
+#define cpu_set_ttbr(nr, val)					\
+	do {							\
+		u64 ttbr = val;					\
+		__asm__("mcrr	p15, " #nr ", %Q0, %R0, c2"	\
+			: : "r" (ttbr));			\
+	} while (0)
+
+#define cpu_get_pgd()	\
+	({						\
+		u64 pg = cpu_get_ttbr(0);		\
+		pg &= ~(PTRS_PER_PGD*sizeof(pgd_t)-1);	\
+		(pgd_t *)phys_to_virt(pg);		\
+	})
+#else
+#define cpu_get_pgd()	\
+	({						\
+		unsigned long pg;			\
+		__asm__("mrc	p15, 0, %0, c2, c0, 0"	\
+			 : "=r" (pg) : : "cc");		\
+		pg &= ~0x3fff;				\
+		(pgd_t *)phys_to_virt(pg);		\
+	})
+#endif
+
+#else	/*!CONFIG_MMU */
+
+#define cpu_switch_mm(pgd,mm)	{ }
+
+#endif
+
+#endif /* __ASSEMBLY__ */
+#endif /* __KERNEL__ */
+#endif /* __ASM_PROCFNS_H */
diff --git a/arch/arm/include/asm/processor.h b/arch/arm/include/asm/processor.h
new file mode 100644
index 000000000..8a1e8e995
--- /dev/null
+++ b/arch/arm/include/asm/processor.h
@@ -0,0 +1,136 @@
+/*
+ *  arch/arm/include/asm/processor.h
+ *
+ *  Copyright (C) 1995-1999 Russell King
+ *
+ * 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.
+ */
+
+#ifndef __ASM_ARM_PROCESSOR_H
+#define __ASM_ARM_PROCESSOR_H
+
+/*
+ * Default implementation of macro that returns current
+ * instruction pointer ("program counter").
+ */
+#define current_text_addr() ({ __label__ _l; _l: &&_l;})
+
+#ifdef __KERNEL__
+
+#include <asm/hw_breakpoint.h>
+#include <asm/ptrace.h>
+#include <asm/types.h>
+#include <asm/unified.h>
+
+#ifdef __KERNEL__
+#define STACK_TOP	((current->personality & ADDR_LIMIT_32BIT) ? \
+			 TASK_SIZE : TASK_SIZE_26)
+#define STACK_TOP_MAX	TASK_SIZE
+#endif
+
+struct debug_info {
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+	struct perf_event	*hbp[ARM_MAX_HBP_SLOTS];
+#endif
+};
+
+struct thread_struct {
+							/* fault info	  */
+	unsigned long		address;
+	unsigned long		trap_no;
+	unsigned long		error_code;
+							/* debugging	  */
+	struct debug_info	debug;
+};
+
+#define INIT_THREAD  {	}
+
+#ifdef CONFIG_MMU
+#define nommu_start_thread(regs) do { } while (0)
+#else
+#define nommu_start_thread(regs) regs->ARM_r10 = current->mm->start_data
+#endif
+
+#define start_thread(regs,pc,sp)					\
+({									\
+	memset(regs->uregs, 0, sizeof(regs->uregs));			\
+	if (current->personality & ADDR_LIMIT_32BIT)			\
+		regs->ARM_cpsr = USR_MODE;				\
+	else								\
+		regs->ARM_cpsr = USR26_MODE;				\
+	if (elf_hwcap & HWCAP_THUMB && pc & 1)				\
+		regs->ARM_cpsr |= PSR_T_BIT;				\
+	regs->ARM_cpsr |= PSR_ENDSTATE;					\
+	regs->ARM_pc = pc & ~1;		/* pc */			\
+	regs->ARM_sp = sp;		/* sp */			\
+	nommu_start_thread(regs);					\
+})
+
+/* Forward declaration, a strange C thing */
+struct task_struct;
+
+/* Free all resources held by a thread. */
+extern void release_thread(struct task_struct *);
+
+unsigned long get_wchan(struct task_struct *p);
+
+#if __LINUX_ARM_ARCH__ == 6 || defined(CONFIG_ARM_ERRATA_754327)
+#define cpu_relax()			smp_mb()
+#else
+#define cpu_relax()			barrier()
+#endif
+
+#define cpu_relax_lowlatency()                cpu_relax()
+
+#define task_pt_regs(p) \
+	((struct pt_regs *)(THREAD_START_SP + task_stack_page(p)) - 1)
+
+#define KSTK_EIP(tsk)	task_pt_regs(tsk)->ARM_pc
+#define KSTK_ESP(tsk)	task_pt_regs(tsk)->ARM_sp
+
+#ifdef CONFIG_SMP
+#define __ALT_SMP_ASM(smp, up)						\
+	"9998:	" smp "\n"						\
+	"	.pushsection \".alt.smp.init\", \"a\"\n"		\
+	"	.long	9998b\n"					\
+	"	" up "\n"						\
+	"	.popsection\n"
+#else
+#define __ALT_SMP_ASM(smp, up)	up
+#endif
+
+/*
+ * Prefetching support - only ARMv5.
+ */
+#if __LINUX_ARM_ARCH__ >= 5
+
+#define ARCH_HAS_PREFETCH
+static inline void prefetch(const void *ptr)
+{
+	__asm__ __volatile__(
+		"pld\t%a0"
+		:: "p" (ptr));
+}
+
+#if __LINUX_ARM_ARCH__ >= 7 && defined(CONFIG_SMP)
+#define ARCH_HAS_PREFETCHW
+static inline void prefetchw(const void *ptr)
+{
+	__asm__ __volatile__(
+		".arch_extension	mp\n"
+		__ALT_SMP_ASM(
+			WASM(pldw)		"\t%a0",
+			WASM(pld)		"\t%a0"
+		)
+		:: "p" (ptr));
+}
+#endif
+#endif
+
+#define HAVE_ARCH_PICK_MMAP_LAYOUT
+
+#endif
+
+#endif /* __ASM_ARM_PROCESSOR_H */
diff --git a/arch/arm/include/asm/procinfo.h b/arch/arm/include/asm/procinfo.h
new file mode 100644
index 000000000..ca52e584e
--- /dev/null
+++ b/arch/arm/include/asm/procinfo.h
@@ -0,0 +1,49 @@
+/*
+ *  arch/arm/include/asm/procinfo.h
+ *
+ *  Copyright (C) 1996-1999 Russell King
+ *
+ * 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.
+ */
+#ifndef __ASM_PROCINFO_H
+#define __ASM_PROCINFO_H
+
+#ifdef __KERNEL__
+
+struct cpu_tlb_fns;
+struct cpu_user_fns;
+struct cpu_cache_fns;
+struct processor;
+
+/*
+ * Note!  struct processor is always defined if we're
+ * using MULTI_CPU, otherwise this entry is unused,
+ * but still exists.
+ *
+ * NOTE! The following structure is defined by assembly
+ * language, NOT C code.  For more information, check:
+ *  arch/arm/mm/proc-*.S and arch/arm/kernel/head.S
+ */
+struct proc_info_list {
+	unsigned int		cpu_val;
+	unsigned int		cpu_mask;
+	unsigned long		__cpu_mm_mmu_flags;	/* used by head.S */
+	unsigned long		__cpu_io_mmu_flags;	/* used by head.S */
+	unsigned long		__cpu_flush;		/* used by head.S */
+	const char		*arch_name;
+	const char		*elf_name;
+	unsigned int		elf_hwcap;
+	const char		*cpu_name;
+	struct processor	*proc;
+	struct cpu_tlb_fns	*tlb;
+	struct cpu_user_fns	*user;
+	struct cpu_cache_fns	*cache;
+};
+
+#else	/* __KERNEL__ */
+#include <asm/elf.h>
+#warning "Please include asm/elf.h instead"
+#endif	/* __KERNEL__ */
+#endif
diff --git a/arch/arm/include/asm/prom.h b/arch/arm/include/asm/prom.h
new file mode 100644
index 000000000..cd94ef2ef
--- /dev/null
+++ b/arch/arm/include/asm/prom.h
@@ -0,0 +1,29 @@
+/*
+ *  arch/arm/include/asm/prom.h
+ *
+ *  Copyright (C) 2009 Canonical Ltd. <jeremy.kerr@canonical.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.
+ *
+ */
+#ifndef __ASMARM_PROM_H
+#define __ASMARM_PROM_H
+
+#ifdef CONFIG_OF
+
+extern const struct machine_desc *setup_machine_fdt(unsigned int dt_phys);
+extern void __init arm_dt_init_cpu_maps(void);
+
+#else /* CONFIG_OF */
+
+static inline const struct machine_desc *setup_machine_fdt(unsigned int dt_phys)
+{
+	return NULL;
+}
+
+static inline void arm_dt_init_cpu_maps(void) { }
+
+#endif /* CONFIG_OF */
+#endif /* ASMARM_PROM_H */
diff --git a/arch/arm/include/asm/psci.h b/arch/arm/include/asm/psci.h
new file mode 100644
index 000000000..c25ef3ec6
--- /dev/null
+++ b/arch/arm/include/asm/psci.h
@@ -0,0 +1,48 @@
+/*
+ * 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.
+ *
+ * Copyright (C) 2012 ARM Limited
+ */
+
+#ifndef __ASM_ARM_PSCI_H
+#define __ASM_ARM_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);
+	int (*affinity_info)(unsigned long target_affinity,
+			unsigned long lowest_affinity_level);
+	int (*migrate_info_type)(void);
+};
+
+extern struct psci_operations psci_ops;
+extern struct smp_operations psci_smp_ops;
+
+#ifdef CONFIG_ARM_PSCI
+int psci_init(void);
+bool psci_smp_available(void);
+#else
+static inline int psci_init(void) { return 0; }
+static inline bool psci_smp_available(void) { return false; }
+#endif
+
+#endif /* __ASM_ARM_PSCI_H */
diff --git a/arch/arm/include/asm/ptrace.h b/arch/arm/include/asm/ptrace.h
new file mode 100644
index 000000000..51622ba7c
--- /dev/null
+++ b/arch/arm/include/asm/ptrace.h
@@ -0,0 +1,162 @@
+/*
+ *  arch/arm/include/asm/ptrace.h
+ *
+ *  Copyright (C) 1996-2003 Russell King
+ *
+ * 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.
+ */
+#ifndef __ASM_ARM_PTRACE_H
+#define __ASM_ARM_PTRACE_H
+
+#include <uapi/asm/ptrace.h>
+
+#ifndef __ASSEMBLY__
+struct pt_regs {
+	unsigned long uregs[18];
+};
+
+#define user_mode(regs)	\
+	(((regs)->ARM_cpsr & 0xf) == 0)
+
+#ifdef CONFIG_ARM_THUMB
+#define thumb_mode(regs) \
+	(((regs)->ARM_cpsr & PSR_T_BIT))
+#else
+#define thumb_mode(regs) (0)
+#endif
+
+#ifndef CONFIG_CPU_V7M
+#define isa_mode(regs) \
+	((((regs)->ARM_cpsr & PSR_J_BIT) >> (__ffs(PSR_J_BIT) - 1)) | \
+	 (((regs)->ARM_cpsr & PSR_T_BIT) >> (__ffs(PSR_T_BIT))))
+#else
+#define isa_mode(regs) 1 /* Thumb */
+#endif
+
+#define processor_mode(regs) \
+	((regs)->ARM_cpsr & MODE_MASK)
+
+#define interrupts_enabled(regs) \
+	(!((regs)->ARM_cpsr & PSR_I_BIT))
+
+#define fast_interrupts_enabled(regs) \
+	(!((regs)->ARM_cpsr & PSR_F_BIT))
+
+/* Are the current registers suitable for user mode?
+ * (used to maintain security in signal handlers)
+ */
+static inline int valid_user_regs(struct pt_regs *regs)
+{
+#ifndef CONFIG_CPU_V7M
+	unsigned long mode = regs->ARM_cpsr & MODE_MASK;
+
+	/*
+	 * Always clear the F (FIQ) and A (delayed abort) bits
+	 */
+	regs->ARM_cpsr &= ~(PSR_F_BIT | PSR_A_BIT);
+
+	if ((regs->ARM_cpsr & PSR_I_BIT) == 0) {
+		if (mode == USR_MODE)
+			return 1;
+		if (elf_hwcap & HWCAP_26BIT && mode == USR26_MODE)
+			return 1;
+	}
+
+	/*
+	 * Force CPSR to something logical...
+	 */
+	regs->ARM_cpsr &= PSR_f | PSR_s | PSR_x | PSR_T_BIT | MODE32_BIT;
+	if (!(elf_hwcap & HWCAP_26BIT))
+		regs->ARM_cpsr |= USR_MODE;
+
+	return 0;
+#else /* ifndef CONFIG_CPU_V7M */
+	return 1;
+#endif
+}
+
+static inline long regs_return_value(struct pt_regs *regs)
+{
+	return regs->ARM_r0;
+}
+
+#define instruction_pointer(regs)	(regs)->ARM_pc
+
+#ifdef CONFIG_THUMB2_KERNEL
+#define frame_pointer(regs) (regs)->ARM_r7
+#else
+#define frame_pointer(regs) (regs)->ARM_fp
+#endif
+
+static inline void instruction_pointer_set(struct pt_regs *regs,
+					   unsigned long val)
+{
+	instruction_pointer(regs) = val;
+}
+
+#ifdef CONFIG_SMP
+extern unsigned long profile_pc(struct pt_regs *regs);
+#else
+#define profile_pc(regs) instruction_pointer(regs)
+#endif
+
+#define predicate(x)		((x) & 0xf0000000)
+#define PREDICATE_ALWAYS	0xe0000000
+
+/*
+ * True if instr is a 32-bit thumb instruction. This works if instr
+ * is the first or only half-word of a thumb instruction. It also works
+ * when instr holds all 32-bits of a wide thumb instruction if stored
+ * in the form (first_half<<16)|(second_half)
+ */
+#define is_wide_instruction(instr)	((unsigned)(instr) >= 0xe800)
+
+/*
+ * kprobe-based event tracer support
+ */
+#include <linux/stddef.h>
+#include <linux/types.h>
+#define MAX_REG_OFFSET (offsetof(struct pt_regs, ARM_ORIG_r0))
+
+extern int regs_query_register_offset(const char *name);
+extern const char *regs_query_register_name(unsigned int offset);
+extern bool regs_within_kernel_stack(struct pt_regs *regs, unsigned long addr);
+extern unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs,
+					       unsigned int n);
+
+/**
+ * regs_get_register() - get register value from its offset
+ * @regs:	   pt_regs from which register value is gotten
+ * @offset:    offset number of the register.
+ *
+ * regs_get_register returns the value of a register whose offset from @regs.
+ * The @offset is the offset of the register in struct pt_regs.
+ * If @offset is bigger than MAX_REG_OFFSET, this returns 0.
+ */
+static inline unsigned long regs_get_register(struct pt_regs *regs,
+					      unsigned int offset)
+{
+	if (unlikely(offset > MAX_REG_OFFSET))
+		return 0;
+	return *(unsigned long *)((unsigned long)regs + offset);
+}
+
+/* Valid only for Kernel mode traps. */
+static inline unsigned long kernel_stack_pointer(struct pt_regs *regs)
+{
+	return regs->ARM_sp;
+}
+
+static inline unsigned long user_stack_pointer(struct pt_regs *regs)
+{
+	return regs->ARM_sp;
+}
+
+#define current_pt_regs(void) ({ (struct pt_regs *)			\
+		((current_stack_pointer | (THREAD_SIZE - 1)) - 7) - 1;	\
+})
+
+#endif /* __ASSEMBLY__ */
+#endif
diff --git a/arch/arm/include/asm/setup.h b/arch/arm/include/asm/setup.h
new file mode 100644
index 000000000..e0adb9f1b
--- /dev/null
+++ b/arch/arm/include/asm/setup.h
@@ -0,0 +1,28 @@
+/*
+ *  linux/include/asm/setup.h
+ *
+ *  Copyright (C) 1997-1999 Russell King
+ *
+ * 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.
+ *
+ *  Structure passed to kernel to tell it about the
+ *  hardware it's running on.  See Documentation/arm/Setup
+ *  for more info.
+ */
+#ifndef __ASMARM_SETUP_H
+#define __ASMARM_SETUP_H
+
+#include <uapi/asm/setup.h>
+
+
+#define __tag __used __attribute__((__section__(".taglist.init")))
+#define __tagtable(tag, fn) \
+static const struct tagtable __tagtable_##fn __tag = { tag, fn }
+
+extern int arm_add_memory(u64 start, u64 size);
+extern void early_print(const char *str, ...);
+extern void dump_machine_table(void);
+
+#endif
diff --git a/arch/arm/include/asm/shmparam.h b/arch/arm/include/asm/shmparam.h
new file mode 100644
index 000000000..a5223b3a9
--- /dev/null
+++ b/arch/arm/include/asm/shmparam.h
@@ -0,0 +1,16 @@
+#ifndef _ASMARM_SHMPARAM_H
+#define _ASMARM_SHMPARAM_H
+
+/*
+ * This should be the size of the virtually indexed cache/ways,
+ * or page size, whichever is greater since the cache aliases
+ * every size/ways bytes.
+ */
+#define	SHMLBA	(4 * PAGE_SIZE)		 /* attach addr a multiple of this */
+
+/*
+ * Enforce SHMLBA in shmat
+ */
+#define __ARCH_FORCE_SHMLBA
+
+#endif /* _ASMARM_SHMPARAM_H */
diff --git a/arch/arm/include/asm/signal.h b/arch/arm/include/asm/signal.h
new file mode 100644
index 000000000..c0eb412af
--- /dev/null
+++ b/arch/arm/include/asm/signal.h
@@ -0,0 +1,22 @@
+#ifndef _ASMARM_SIGNAL_H
+#define _ASMARM_SIGNAL_H
+
+#include <uapi/asm/signal.h>
+
+/* Most things should be clean enough to redefine this at will, if care
+   is taken to make libc match.  */
+
+#define _NSIG		64
+#define _NSIG_BPW	32
+#define _NSIG_WORDS	(_NSIG / _NSIG_BPW)
+
+typedef unsigned long old_sigset_t;		/* at least 32 bits */
+
+typedef struct {
+	unsigned long sig[_NSIG_WORDS];
+} sigset_t;
+
+#define __ARCH_HAS_SA_RESTORER
+
+#include <asm/sigcontext.h>
+#endif
diff --git a/arch/arm/include/asm/smp.h b/arch/arm/include/asm/smp.h
new file mode 100644
index 000000000..18f5a5541
--- /dev/null
+++ b/arch/arm/include/asm/smp.h
@@ -0,0 +1,126 @@
+/*
+ *  arch/arm/include/asm/smp.h
+ *
+ *  Copyright (C) 2004-2005 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.
+ */
+#ifndef __ASM_ARM_SMP_H
+#define __ASM_ARM_SMP_H
+
+#include <linux/threads.h>
+#include <linux/cpumask.h>
+#include <linux/thread_info.h>
+
+#ifndef CONFIG_SMP
+# error "<asm/smp.h> included in non-SMP build"
+#endif
+
+#define raw_smp_processor_id() (current_thread_info()->cpu)
+
+struct seq_file;
+
+/*
+ * generate IPI list text
+ */
+extern void show_ipi_list(struct seq_file *, int);
+
+/*
+ * Called from assembly code, this handles an IPI.
+ */
+asmlinkage void do_IPI(int ipinr, struct pt_regs *regs);
+
+/*
+ * Called from C code, this handles an IPI.
+ */
+void handle_IPI(int ipinr, struct pt_regs *regs);
+
+/*
+ * Setup the set of possible CPUs (via set_cpu_possible)
+ */
+extern void smp_init_cpus(void);
+
+
+/*
+ * Provide a function to raise an IPI cross call on CPUs in callmap.
+ */
+extern void set_smp_cross_call(void (*)(const struct cpumask *, unsigned int));
+
+/*
+ * Called from platform specific assembly code, this is the
+ * secondary CPU entry point.
+ */
+asmlinkage void secondary_start_kernel(void);
+
+
+/*
+ * Initial data for bringing up a secondary CPU.
+ */
+struct secondary_data {
+	union {
+		unsigned long mpu_rgn_szr;
+		unsigned long pgdir;
+	};
+	unsigned long swapper_pg_dir;
+	void *stack;
+};
+extern struct secondary_data secondary_data;
+extern volatile int pen_release;
+extern void secondary_startup(void);
+
+extern int __cpu_disable(void);
+
+extern void __cpu_die(unsigned int cpu);
+extern void cpu_die(void);
+
+extern void arch_send_call_function_single_ipi(int cpu);
+extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
+extern void arch_send_wakeup_ipi_mask(const struct cpumask *mask);
+
+extern int register_ipi_completion(struct completion *completion, int cpu);
+
+struct smp_operations {
+#ifdef CONFIG_SMP
+	/*
+	 * Setup the set of possible CPUs (via set_cpu_possible)
+	 */
+	void (*smp_init_cpus)(void);
+	/*
+	 * Initialize cpu_possible map, and enable coherency
+	 */
+	void (*smp_prepare_cpus)(unsigned int max_cpus);
+
+	/*
+	 * Perform platform specific initialisation of the specified CPU.
+	 */
+	void (*smp_secondary_init)(unsigned int cpu);
+	/*
+	 * Boot a secondary CPU, and assign it the specified idle task.
+	 * This also gives us the initial stack to use for this CPU.
+	 */
+	int  (*smp_boot_secondary)(unsigned int cpu, struct task_struct *idle);
+#ifdef CONFIG_HOTPLUG_CPU
+	int  (*cpu_kill)(unsigned int cpu);
+	void (*cpu_die)(unsigned int cpu);
+	int  (*cpu_disable)(unsigned int cpu);
+#endif
+#endif
+};
+
+struct of_cpu_method {
+	const char *method;
+	struct smp_operations *ops;
+};
+
+#define CPU_METHOD_OF_DECLARE(name, _method, _ops)			\
+	static const struct of_cpu_method __cpu_method_of_table_##name	\
+		__used __section(__cpu_method_of_table)			\
+		= { .method = _method, .ops = _ops }
+/*
+ * set platform specific SMP operations
+ */
+extern void smp_set_ops(struct smp_operations *);
+
+#endif /* ifndef __ASM_ARM_SMP_H */
diff --git a/arch/arm/include/asm/smp_plat.h b/arch/arm/include/asm/smp_plat.h
new file mode 100644
index 000000000..993e5224d
--- /dev/null
+++ b/arch/arm/include/asm/smp_plat.h
@@ -0,0 +1,110 @@
+/*
+ * ARM specific SMP header, this contains our implementation
+ * details.
+ */
+#ifndef __ASMARM_SMP_PLAT_H
+#define __ASMARM_SMP_PLAT_H
+
+#include <linux/cpumask.h>
+#include <linux/err.h>
+
+#include <asm/cpu.h>
+#include <asm/cputype.h>
+
+/*
+ * Return true if we are running on a SMP platform
+ */
+static inline bool is_smp(void)
+{
+#ifndef CONFIG_SMP
+	return false;
+#elif defined(CONFIG_SMP_ON_UP)
+	extern unsigned int smp_on_up;
+	return !!smp_on_up;
+#else
+	return true;
+#endif
+}
+
+/**
+ * smp_cpuid_part() - return part id for a given cpu
+ * @cpu:	logical cpu id.
+ *
+ * Return: part id of logical cpu passed as argument.
+ */
+static inline unsigned int smp_cpuid_part(int cpu)
+{
+	struct cpuinfo_arm *cpu_info = &per_cpu(cpu_data, cpu);
+
+	return is_smp() ? cpu_info->cpuid & ARM_CPU_PART_MASK :
+			  read_cpuid_part();
+}
+
+/* all SMP configurations have the extended CPUID registers */
+#ifndef CONFIG_MMU
+#define tlb_ops_need_broadcast()	0
+#else
+static inline int tlb_ops_need_broadcast(void)
+{
+	if (!is_smp())
+		return 0;
+
+	return ((read_cpuid_ext(CPUID_EXT_MMFR3) >> 12) & 0xf) < 2;
+}
+#endif
+
+#if !defined(CONFIG_SMP) || __LINUX_ARM_ARCH__ >= 7
+#define cache_ops_need_broadcast()	0
+#else
+static inline int cache_ops_need_broadcast(void)
+{
+	if (!is_smp())
+		return 0;
+
+	return ((read_cpuid_ext(CPUID_EXT_MMFR3) >> 12) & 0xf) < 1;
+}
+#endif
+
+/*
+ * Logical CPU mapping.
+ */
+extern u32 __cpu_logical_map[];
+#define cpu_logical_map(cpu)	__cpu_logical_map[cpu]
+/*
+ * Retrieve logical cpu index corresponding to a given MPIDR[23:0]
+ *  - mpidr: MPIDR[23:0] to be used for the look-up
+ *
+ * Returns the cpu logical index or -EINVAL on look-up error
+ */
+static inline int get_logical_index(u32 mpidr)
+{
+	int cpu;
+	for (cpu = 0; cpu < nr_cpu_ids; cpu++)
+		if (cpu_logical_map(cpu) == mpidr)
+			return cpu;
+	return -EINVAL;
+}
+
+/*
+ * NOTE ! Assembly code relies on the following
+ * structure memory layout in order to carry out load
+ * multiple from its base address. For more
+ * information check arch/arm/kernel/sleep.S
+ */
+struct mpidr_hash {
+	u32	mask; /* used by sleep.S */
+	u32	shift_aff[3]; /* used by sleep.S */
+	u32	bits;
+};
+
+extern struct mpidr_hash mpidr_hash;
+
+static inline u32 mpidr_hash_size(void)
+{
+	return 1 << mpidr_hash.bits;
+}
+
+extern int platform_can_secondary_boot(void);
+extern int platform_can_cpu_hotplug(void);
+
+#endif
diff --git a/arch/arm/include/asm/smp_scu.h b/arch/arm/include/asm/smp_scu.h
new file mode 100644
index 000000000..bfe163c40
--- /dev/null
+++ b/arch/arm/include/asm/smp_scu.h
@@ -0,0 +1,48 @@
+#ifndef __ASMARM_ARCH_SCU_H
+#define __ASMARM_ARCH_SCU_H
+
+#define SCU_PM_NORMAL	0
+#define SCU_PM_DORMANT	2
+#define SCU_PM_POWEROFF	3
+
+#ifndef __ASSEMBLER__
+
+#include <asm/cputype.h>
+
+static inline bool scu_a9_has_base(void)
+{
+	return read_cpuid_part() == ARM_CPU_PART_CORTEX_A9;
+}
+
+static inline unsigned long scu_a9_get_base(void)
+{
+	unsigned long pa;
+
+	asm("mrc p15, 4, %0, c15, c0, 0" : "=r" (pa));
+
+	return pa;
+}
+
+#ifdef CONFIG_HAVE_ARM_SCU
+unsigned int scu_get_core_count(void __iomem *);
+int scu_power_mode(void __iomem *, unsigned int);
+#else
+static inline unsigned int scu_get_core_count(void __iomem *scu_base)
+{
+	return 0;
+}
+static inline int scu_power_mode(void __iomem *scu_base, unsigned int mode)
+{
+	return -EINVAL;
+}
+#endif
+
+#if defined(CONFIG_SMP) && defined(CONFIG_HAVE_ARM_SCU)
+void scu_enable(void __iomem *scu_base);
+#else
+static inline void scu_enable(void __iomem *scu_base) {}
+#endif
+
+#endif
+
+#endif
diff --git a/arch/arm/include/asm/smp_twd.h b/arch/arm/include/asm/smp_twd.h
new file mode 100644
index 000000000..7b2899c2f
--- /dev/null
+++ b/arch/arm/include/asm/smp_twd.h
@@ -0,0 +1,37 @@
+#ifndef __ASMARM_SMP_TWD_H
+#define __ASMARM_SMP_TWD_H
+
+#define TWD_TIMER_LOAD			0x00
+#define TWD_TIMER_COUNTER		0x04
+#define TWD_TIMER_CONTROL		0x08
+#define TWD_TIMER_INTSTAT		0x0C
+
+#define TWD_WDOG_LOAD			0x20
+#define TWD_WDOG_COUNTER		0x24
+#define TWD_WDOG_CONTROL		0x28
+#define TWD_WDOG_INTSTAT		0x2C
+#define TWD_WDOG_RESETSTAT		0x30
+#define TWD_WDOG_DISABLE		0x34
+
+#define TWD_TIMER_CONTROL_ENABLE	(1 << 0)
+#define TWD_TIMER_CONTROL_ONESHOT	(0 << 1)
+#define TWD_TIMER_CONTROL_PERIODIC	(1 << 1)
+#define TWD_TIMER_CONTROL_IT_ENABLE	(1 << 2)
+
+#include <linux/ioport.h>
+
+struct twd_local_timer {
+	struct resource	res[2];
+};
+
+#define DEFINE_TWD_LOCAL_TIMER(name,base,irq)	\
+struct twd_local_timer name __initdata = {	\
+	.res	= {				\
+		DEFINE_RES_MEM(base, 0x10),	\
+		DEFINE_RES_IRQ(irq),		\
+	},					\
+};
+
+int twd_local_timer_register(struct twd_local_timer *);
+
+#endif
diff --git a/arch/arm/include/asm/sparsemem.h b/arch/arm/include/asm/sparsemem.h
new file mode 100644
index 000000000..00098615c
--- /dev/null
+++ b/arch/arm/include/asm/sparsemem.h
@@ -0,0 +1,24 @@
+#ifndef ASMARM_SPARSEMEM_H
+#define ASMARM_SPARSEMEM_H
+
+#include <asm/memory.h>
+
+/*
+ * Two definitions are required for sparsemem:
+ *
+ * MAX_PHYSMEM_BITS: The number of physical address bits required
+ *   to address the last byte of memory.
+ *
+ * SECTION_SIZE_BITS: The number of physical address bits to cover
+ *   the maximum amount of memory in a section.
+ *
+ * Eg, if you have 2 banks of up to 64MB at 0x80000000, 0x84000000,
+ * then MAX_PHYSMEM_BITS is 32, SECTION_SIZE_BITS is 26.
+ *
+ * Define these in your mach/memory.h.
+ */
+#if !defined(SECTION_SIZE_BITS) || !defined(MAX_PHYSMEM_BITS)
+#error Sparsemem is not supported on this platform
+#endif
+
+#endif
diff --git a/arch/arm/include/asm/spinlock.h b/arch/arm/include/asm/spinlock.h
new file mode 100644
index 000000000..0fa418463
--- /dev/null
+++ b/arch/arm/include/asm/spinlock.h
@@ -0,0 +1,287 @@
+#ifndef __ASM_SPINLOCK_H
+#define __ASM_SPINLOCK_H
+
+#if __LINUX_ARM_ARCH__ < 6
+#error SMP not supported on pre-ARMv6 CPUs
+#endif
+
+#include <linux/prefetch.h>
+
+/*
+ * sev and wfe are ARMv6K extensions.  Uniprocessor ARMv6 may not have the K
+ * extensions, so when running on UP, we have to patch these instructions away.
+ */
+#ifdef CONFIG_THUMB2_KERNEL
+/*
+ * For Thumb-2, special care is needed to ensure that the conditional WFE
+ * instruction really does assemble to exactly 4 bytes (as required by
+ * the SMP_ON_UP fixup code).   By itself "wfene" might cause the
+ * assembler to insert a extra (16-bit) IT instruction, depending on the
+ * presence or absence of neighbouring conditional instructions.
+ *
+ * To avoid this unpredictableness, an approprite IT is inserted explicitly:
+ * the assembler won't change IT instructions which are explicitly present
+ * in the input.
+ */
+#define WFE(cond)	__ALT_SMP_ASM(		\
+	"it " cond "\n\t"			\
+	"wfe" cond ".n",			\
+						\
+	"nop.w"					\
+)
+#else
+#define WFE(cond)	__ALT_SMP_ASM("wfe" cond, "nop")
+#endif
+
+#define SEV		__ALT_SMP_ASM(WASM(sev), WASM(nop))
+
+static inline void dsb_sev(void)
+{
+
+	dsb(ishst);
+	__asm__(SEV);
+}
+
+/*
+ * ARMv6 ticket-based spin-locking.
+ *
+ * A memory barrier is required after we get a lock, and before we
+ * release it, because V6 CPUs are assumed to have weakly ordered
+ * memory.
+ */
+
+#define arch_spin_unlock_wait(lock) \
+	do { while (arch_spin_is_locked(lock)) cpu_relax(); } while (0)
+
+#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
+
+static inline void arch_spin_lock(arch_spinlock_t *lock)
+{
+	unsigned long tmp;
+	u32 newval;
+	arch_spinlock_t lockval;
+
+	prefetchw(&lock->slock);
+	__asm__ __volatile__(
+"1:	ldrex	%0, [%3]\n"
+"	add	%1, %0, %4\n"
+"	strex	%2, %1, [%3]\n"
+"	teq	%2, #0\n"
+"	bne	1b"
+	: "=&r" (lockval), "=&r" (newval), "=&r" (tmp)
+	: "r" (&lock->slock), "I" (1 << TICKET_SHIFT)
+	: "cc");
+
+	while (lockval.tickets.next != lockval.tickets.owner) {
+		wfe();
+		lockval.tickets.owner = ACCESS_ONCE(lock->tickets.owner);
+	}
+
+	smp_mb();
+}
+
+static inline int arch_spin_trylock(arch_spinlock_t *lock)
+{
+	unsigned long contended, res;
+	u32 slock;
+
+	prefetchw(&lock->slock);
+	do {
+		__asm__ __volatile__(
+		"	ldrex	%0, [%3]\n"
+		"	mov	%2, #0\n"
+		"	subs	%1, %0, %0, ror #16\n"
+		"	addeq	%0, %0, %4\n"
+		"	strexeq	%2, %0, [%3]"
+		: "=&r" (slock), "=&r" (contended), "=&r" (res)
+		: "r" (&lock->slock), "I" (1 << TICKET_SHIFT)
+		: "cc");
+	} while (res);
+
+	if (!contended) {
+		smp_mb();
+		return 1;
+	} else {
+		return 0;
+	}
+}
+
+static inline void arch_spin_unlock(arch_spinlock_t *lock)
+{
+	smp_mb();
+	lock->tickets.owner++;
+	dsb_sev();
+}
+
+static inline int arch_spin_value_unlocked(arch_spinlock_t lock)
+{
+	return lock.tickets.owner == lock.tickets.next;
+}
+
+static inline int arch_spin_is_locked(arch_spinlock_t *lock)
+{
+	return !arch_spin_value_unlocked(READ_ONCE(*lock));
+}
+
+static inline int arch_spin_is_contended(arch_spinlock_t *lock)
+{
+	struct __raw_tickets tickets = READ_ONCE(lock->tickets);
+	return (tickets.next - tickets.owner) > 1;
+}
+#define arch_spin_is_contended	arch_spin_is_contended
+
+/*
+ * RWLOCKS
+ *
+ *
+ * Write locks are easy - we just set bit 31.  When unlocking, we can
+ * just write zero since the lock is exclusively held.
+ */
+
+static inline void arch_write_lock(arch_rwlock_t *rw)
+{
+	unsigned long tmp;
+
+	prefetchw(&rw->lock);
+	__asm__ __volatile__(
+"1:	ldrex	%0, [%1]\n"
+"	teq	%0, #0\n"
+	WFE("ne")
+"	strexeq	%0, %2, [%1]\n"
+"	teq	%0, #0\n"
+"	bne	1b"
+	: "=&r" (tmp)
+	: "r" (&rw->lock), "r" (0x80000000)
+	: "cc");
+
+	smp_mb();
+}
+
+static inline int arch_write_trylock(arch_rwlock_t *rw)
+{
+	unsigned long contended, res;
+
+	prefetchw(&rw->lock);
+	do {
+		__asm__ __volatile__(
+		"	ldrex	%0, [%2]\n"
+		"	mov	%1, #0\n"
+		"	teq	%0, #0\n"
+		"	strexeq	%1, %3, [%2]"
+		: "=&r" (contended), "=&r" (res)
+		: "r" (&rw->lock), "r" (0x80000000)
+		: "cc");
+	} while (res);
+
+	if (!contended) {
+		smp_mb();
+		return 1;
+	} else {
+		return 0;
+	}
+}
+
+static inline void arch_write_unlock(arch_rwlock_t *rw)
+{
+	smp_mb();
+
+	__asm__ __volatile__(
+	"str	%1, [%0]\n"
+	:
+	: "r" (&rw->lock), "r" (0)
+	: "cc");
+
+	dsb_sev();
+}
+
+/* write_can_lock - would write_trylock() succeed? */
+#define arch_write_can_lock(x)		(ACCESS_ONCE((x)->lock) == 0)
+
+/*
+ * Read locks are a bit more hairy:
+ *  - Exclusively load the lock value.
+ *  - Increment it.
+ *  - Store new lock value if positive, and we still own this location.
+ *    If the value is negative, we've already failed.
+ *  - If we failed to store the value, we want a negative result.
+ *  - If we failed, try again.
+ * Unlocking is similarly hairy.  We may have multiple read locks
+ * currently active.  However, we know we won't have any write
+ * locks.
+ */
+static inline void arch_read_lock(arch_rwlock_t *rw)
+{
+	unsigned long tmp, tmp2;
+
+	prefetchw(&rw->lock);
+	__asm__ __volatile__(
+"1:	ldrex	%0, [%2]\n"
+"	adds	%0, %0, #1\n"
+"	strexpl	%1, %0, [%2]\n"
+	WFE("mi")
+"	rsbpls	%0, %1, #0\n"
+"	bmi	1b"
+	: "=&r" (tmp), "=&r" (tmp2)
+	: "r" (&rw->lock)
+	: "cc");
+
+	smp_mb();
+}
+
+static inline void arch_read_unlock(arch_rwlock_t *rw)
+{
+	unsigned long tmp, tmp2;
+
+	smp_mb();
+
+	prefetchw(&rw->lock);
+	__asm__ __volatile__(
+"1:	ldrex	%0, [%2]\n"
+"	sub	%0, %0, #1\n"
+"	strex	%1, %0, [%2]\n"
+"	teq	%1, #0\n"
+"	bne	1b"
+	: "=&r" (tmp), "=&r" (tmp2)
+	: "r" (&rw->lock)
+	: "cc");
+
+	if (tmp == 0)
+		dsb_sev();
+}
+
+static inline int arch_read_trylock(arch_rwlock_t *rw)
+{
+	unsigned long contended, res;
+
+	prefetchw(&rw->lock);
+	do {
+		__asm__ __volatile__(
+		"	ldrex	%0, [%2]\n"
+		"	mov	%1, #0\n"
+		"	adds	%0, %0, #1\n"
+		"	strexpl	%1, %0, [%2]"
+		: "=&r" (contended), "=&r" (res)
+		: "r" (&rw->lock)
+		: "cc");
+	} while (res);
+
+	/* If the lock is negative, then it is already held for write. */
+	if (contended < 0x80000000) {
+		smp_mb();
+		return 1;
+	} else {
+		return 0;
+	}
+}
+
+/* read_can_lock - would read_trylock() succeed? */
+#define arch_read_can_lock(x)		(ACCESS_ONCE((x)->lock) < 0x80000000)
+
+#define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
+#define arch_write_lock_flags(lock, flags) arch_write_lock(lock)
+
+#define arch_spin_relax(lock)	cpu_relax()
+#define arch_read_relax(lock)	cpu_relax()
+#define arch_write_relax(lock)	cpu_relax()
+
+#endif /* __ASM_SPINLOCK_H */
diff --git a/arch/arm/include/asm/spinlock_types.h b/arch/arm/include/asm/spinlock_types.h
new file mode 100644
index 000000000..47663fcb1
--- /dev/null
+++ b/arch/arm/include/asm/spinlock_types.h
@@ -0,0 +1,33 @@
+#ifndef __ASM_SPINLOCK_TYPES_H
+#define __ASM_SPINLOCK_TYPES_H
+
+#ifndef __LINUX_SPINLOCK_TYPES_H
+# error "please don't include this file directly"
+#endif
+
+#define TICKET_SHIFT	16
+
+typedef struct {
+	union {
+		u32 slock;
+		struct __raw_tickets {
+#ifdef __ARMEB__
+			u16 next;
+			u16 owner;
+#else
+			u16 owner;
+			u16 next;
+#endif
+		} tickets;
+	};
+} arch_spinlock_t;
+
+#define __ARCH_SPIN_LOCK_UNLOCKED	{ { 0 } }
+
+typedef struct {
+	u32 lock;
+} arch_rwlock_t;
+
+#define __ARCH_RW_LOCK_UNLOCKED		{ 0 }
+
+#endif
diff --git a/arch/arm/include/asm/stackprotector.h b/arch/arm/include/asm/stackprotector.h
new file mode 100644
index 000000000..de003327b
--- /dev/null
+++ b/arch/arm/include/asm/stackprotector.h
@@ -0,0 +1,38 @@
+/*
+ * GCC stack protector support.
+ *
+ * Stack protector works by putting predefined pattern at the start of
+ * the stack frame and verifying that it hasn't been overwritten when
+ * returning from the function.  The pattern is called stack canary
+ * and gcc expects it to be defined by a global variable called
+ * "__stack_chk_guard" on ARM.  This unfortunately means that on SMP
+ * we cannot have a different canary value per task.
+ */
+
+#ifndef _ASM_STACKPROTECTOR_H
+#define _ASM_STACKPROTECTOR_H 1
+
+#include <linux/random.h>
+#include <linux/version.h>
+
+extern unsigned long __stack_chk_guard;
+
+/*
+ * Initialize the stackprotector canary value.
+ *
+ * NOTE: this must only be called from functions that never return,
+ * and it must always be inlined.
+ */
+static __always_inline void boot_init_stack_canary(void)
+{
+	unsigned long canary;
+
+	/* Try to get a semi random initial value. */
+	get_random_bytes(&canary, sizeof(canary));
+	canary ^= LINUX_VERSION_CODE;
+
+	current->stack_canary = canary;
+	__stack_chk_guard = current->stack_canary;
+}
+
+#endif	/* _ASM_STACKPROTECTOR_H */
diff --git a/arch/arm/include/asm/stacktrace.h b/arch/arm/include/asm/stacktrace.h
new file mode 100644
index 000000000..7722201ea
--- /dev/null
+++ b/arch/arm/include/asm/stacktrace.h
@@ -0,0 +1,30 @@
+#ifndef __ASM_STACKTRACE_H
+#define __ASM_STACKTRACE_H
+
+#include <asm/ptrace.h>
+
+struct stackframe {
+	/*
+	 * FP member should hold R7 when CONFIG_THUMB2_KERNEL is enabled
+	 * and R11 otherwise.
+	 */
+	unsigned long fp;
+	unsigned long sp;
+	unsigned long lr;
+	unsigned long pc;
+};
+
+static __always_inline
+void arm_get_current_stackframe(struct pt_regs *regs, struct stackframe *frame)
+{
+		frame->fp = frame_pointer(regs);
+		frame->sp = regs->ARM_sp;
+		frame->lr = regs->ARM_lr;
+		frame->pc = regs->ARM_pc;
+}
+
+extern int unwind_frame(struct stackframe *frame);
+extern void walk_stackframe(struct stackframe *frame,
+			    int (*fn)(struct stackframe *, void *), void *data);
+
+#endif	/* __ASM_STACKTRACE_H */
diff --git a/arch/arm/include/asm/string.h b/arch/arm/include/asm/string.h
new file mode 100644
index 000000000..cf4f3aad0
--- /dev/null
+++ b/arch/arm/include/asm/string.h
@@ -0,0 +1,41 @@
+#ifndef __ASM_ARM_STRING_H
+#define __ASM_ARM_STRING_H
+
+/*
+ * We don't do inline string functions, since the
+ * optimised inline asm versions are not small.
+ */
+
+#define __HAVE_ARCH_STRRCHR
+extern char * strrchr(const char * s, int c);
+
+#define __HAVE_ARCH_STRCHR
+extern char * strchr(const char * s, int c);
+
+#define __HAVE_ARCH_MEMCPY
+extern void * memcpy(void *, const void *, __kernel_size_t);
+
+#define __HAVE_ARCH_MEMMOVE
+extern void * memmove(void *, const void *, __kernel_size_t);
+
+#define __HAVE_ARCH_MEMCHR
+extern void * memchr(const void *, int, __kernel_size_t);
+
+#define __HAVE_ARCH_MEMSET
+extern void * memset(void *, int, __kernel_size_t);
+
+extern void __memzero(void *ptr, __kernel_size_t n);
+
+#define memset(p,v,n)							\
+	({								\
+	 	void *__p = (p); size_t __n = n;			\
+		if ((__n) != 0) {					\
+			if (__builtin_constant_p((v)) && (v) == 0)	\
+				__memzero((__p),(__n));			\
+			else						\
+				memset((__p),(v),(__n));		\
+		}							\
+		(__p);							\
+	})
+
+#endif
diff --git a/arch/arm/include/asm/suspend.h b/arch/arm/include/asm/suspend.h
new file mode 100644
index 000000000..cd20029bc
--- /dev/null
+++ b/arch/arm/include/asm/suspend.h
@@ -0,0 +1,12 @@
+#ifndef __ASM_ARM_SUSPEND_H
+#define __ASM_ARM_SUSPEND_H
+
+struct sleep_save_sp {
+	u32 *save_ptr_stash;
+	u32 save_ptr_stash_phys;
+};
+
+extern void cpu_resume(void);
+extern int cpu_suspend(unsigned long, int (*)(unsigned long));
+
+#endif
diff --git a/arch/arm/include/asm/swab.h b/arch/arm/include/asm/swab.h
new file mode 100644
index 000000000..537fc9b91
--- /dev/null
+++ b/arch/arm/include/asm/swab.h
@@ -0,0 +1,38 @@
+/*
+ *  arch/arm/include/asm/byteorder.h
+ *
+ * ARM Endian-ness.  In little endian mode, the data bus is connected such
+ * that byte accesses appear as:
+ *  0 = d0...d7, 1 = d8...d15, 2 = d16...d23, 3 = d24...d31
+ * and word accesses (data or instruction) appear as:
+ *  d0...d31
+ *
+ * When in big endian mode, byte accesses appear as:
+ *  0 = d24...d31, 1 = d16...d23, 2 = d8...d15, 3 = d0...d7
+ * and word accesses (data or instruction) appear as:
+ *  d0...d31
+ */
+#ifndef __ASM_ARM_SWAB_H
+#define __ASM_ARM_SWAB_H
+
+#include <uapi/asm/swab.h>
+
+#if __LINUX_ARM_ARCH__ >= 6
+
+static inline __attribute_const__ __u32 __arch_swahb32(__u32 x)
+{
+	__asm__ ("rev16 %0, %1" : "=r" (x) : "r" (x));
+	return x;
+}
+#define __arch_swahb32 __arch_swahb32
+#define __arch_swab16(x) ((__u16)__arch_swahb32(x))
+
+static inline __attribute_const__ __u32 __arch_swab32(__u32 x)
+{
+	__asm__ ("rev %0, %1" : "=r" (x) : "r" (x));
+	return x;
+}
+#define __arch_swab32 __arch_swab32
+
+#endif
+#endif
diff --git a/arch/arm/include/asm/switch_to.h b/arch/arm/include/asm/switch_to.h
new file mode 100644
index 000000000..c99e25946
--- /dev/null
+++ b/arch/arm/include/asm/switch_to.h
@@ -0,0 +1,28 @@
+#ifndef __ASM_ARM_SWITCH_TO_H
+#define __ASM_ARM_SWITCH_TO_H
+
+#include <linux/thread_info.h>
+
+/*
+ * For v7 SMP cores running a preemptible kernel we may be pre-empted
+ * during a TLB maintenance operation, so execute an inner-shareable dsb
+ * to ensure that the maintenance completes in case we migrate to another
+ * CPU.
+ */
+#if defined(CONFIG_PREEMPT) && defined(CONFIG_SMP) && defined(CONFIG_CPU_V7)
+#define finish_arch_switch(prev)	dsb(ish)
+#endif
+
+/*
+ * switch_to(prev, next) should switch from task `prev' to `next'
+ * `prev' will never be the same as `next'.  schedule() itself
+ * contains the memory barrier to tell GCC not to cache `current'.
+ */
+extern struct task_struct *__switch_to(struct task_struct *, struct thread_info *, struct thread_info *);
+
+#define switch_to(prev,next,last)					\
+do {									\
+	last = __switch_to(prev,task_thread_info(prev), task_thread_info(next));	\
+} while (0)
+
+#endif /* __ASM_ARM_SWITCH_TO_H */
diff --git a/arch/arm/include/asm/sync_bitops.h b/arch/arm/include/asm/sync_bitops.h
new file mode 100644
index 000000000..9732b8e11
--- /dev/null
+++ b/arch/arm/include/asm/sync_bitops.h
@@ -0,0 +1,26 @@
+#ifndef __ASM_SYNC_BITOPS_H__
+#define __ASM_SYNC_BITOPS_H__
+
+#include <asm/bitops.h>
+
+/* sync_bitops functions are equivalent to the SMP implementation of the
+ * original functions, independently from CONFIG_SMP being defined.
+ *
+ * We need them because _set_bit etc are not SMP safe if !CONFIG_SMP. But
+ * under Xen you might be communicating with a completely external entity
+ * who might be on another CPU (e.g. two uniprocessor guests communicating
+ * via event channels and grant tables). So we need a variant of the bit
+ * ops which are SMP safe even on a UP kernel.
+ */
+
+#define sync_set_bit(nr, p)		_set_bit(nr, p)
+#define sync_clear_bit(nr, p)		_clear_bit(nr, p)
+#define sync_change_bit(nr, p)		_change_bit(nr, p)
+#define sync_test_and_set_bit(nr, p)	_test_and_set_bit(nr, p)
+#define sync_test_and_clear_bit(nr, p)	_test_and_clear_bit(nr, p)
+#define sync_test_and_change_bit(nr, p)	_test_and_change_bit(nr, p)
+#define sync_test_bit(nr, addr)		test_bit(nr, addr)
+#define sync_cmpxchg			cmpxchg
+
+
+#endif
diff --git a/arch/arm/include/asm/syscall.h b/arch/arm/include/asm/syscall.h
new file mode 100644
index 000000000..e86c985b8
--- /dev/null
+++ b/arch/arm/include/asm/syscall.h
@@ -0,0 +1,112 @@
+/*
+ * Access to user system call parameters and results
+ *
+ * See asm-generic/syscall.h for descriptions of what we must do here.
+ */
+
+#ifndef _ASM_ARM_SYSCALL_H
+#define _ASM_ARM_SYSCALL_H
+
+#include <uapi/linux/audit.h> /* for AUDIT_ARCH_* */
+#include <linux/elf.h> /* for ELF_EM */
+#include <linux/err.h>
+#include <linux/sched.h>
+
+#include <asm/unistd.h>
+
+#define NR_syscalls (__NR_syscalls)
+
+extern const unsigned long sys_call_table[];
+
+static inline int syscall_get_nr(struct task_struct *task,
+				 struct pt_regs *regs)
+{
+	return task_thread_info(task)->syscall;
+}
+
+static inline void syscall_rollback(struct task_struct *task,
+				    struct pt_regs *regs)
+{
+	regs->ARM_r0 = regs->ARM_ORIG_r0;
+}
+
+static inline long syscall_get_error(struct task_struct *task,
+				     struct pt_regs *regs)
+{
+	unsigned long error = regs->ARM_r0;
+	return IS_ERR_VALUE(error) ? error : 0;
+}
+
+static inline long syscall_get_return_value(struct task_struct *task,
+					    struct pt_regs *regs)
+{
+	return regs->ARM_r0;
+}
+
+static inline void syscall_set_return_value(struct task_struct *task,
+					    struct pt_regs *regs,
+					    int error, long val)
+{
+	regs->ARM_r0 = (long) error ? error : val;
+}
+
+#define SYSCALL_MAX_ARGS 7
+
+static inline void syscall_get_arguments(struct task_struct *task,
+					 struct pt_regs *regs,
+					 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;
+		pr_warn("%s called with max args %d, handling only %d\n",
+			__func__, i + n, SYSCALL_MAX_ARGS);
+		memset(args_bad, 0, n_bad * sizeof(args[0]));
+		n = SYSCALL_MAX_ARGS - i;
+	}
+
+	if (i == 0) {
+		args[0] = regs->ARM_ORIG_r0;
+		args++;
+		i++;
+		n--;
+	}
+
+	memcpy(args, &regs->ARM_r0 + i, n * sizeof(args[0]));
+}
+
+static inline void syscall_set_arguments(struct task_struct *task,
+					 struct pt_regs *regs,
+					 unsigned int i, unsigned int n,
+					 const unsigned long *args)
+{
+	if (n == 0)
+		return;
+
+	if (i + n > SYSCALL_MAX_ARGS) {
+		pr_warn("%s called with max args %d, handling only %d\n",
+			__func__, i + n, SYSCALL_MAX_ARGS);
+		n = SYSCALL_MAX_ARGS - i;
+	}
+
+	if (i == 0) {
+		regs->ARM_ORIG_r0 = args[0];
+		args++;
+		i++;
+		n--;
+	}
+
+	memcpy(&regs->ARM_r0 + i, args, n * sizeof(args[0]));
+}
+
+static inline int syscall_get_arch(void)
+{
+	/* ARM tasks don't change audit architectures on the fly. */
+	return AUDIT_ARCH_ARM;
+}
+
+#endif /* _ASM_ARM_SYSCALL_H */
diff --git a/arch/arm/include/asm/system_info.h b/arch/arm/include/asm/system_info.h
new file mode 100644
index 000000000..720ea0320
--- /dev/null
+++ b/arch/arm/include/asm/system_info.h
@@ -0,0 +1,28 @@
+#ifndef __ASM_ARM_SYSTEM_INFO_H
+#define __ASM_ARM_SYSTEM_INFO_H
+
+#define CPU_ARCH_UNKNOWN	0
+#define CPU_ARCH_ARMv3		1
+#define CPU_ARCH_ARMv4		2
+#define CPU_ARCH_ARMv4T		3
+#define CPU_ARCH_ARMv5		4
+#define CPU_ARCH_ARMv5T		5
+#define CPU_ARCH_ARMv5TE	6
+#define CPU_ARCH_ARMv5TEJ	7
+#define CPU_ARCH_ARMv6		8
+#define CPU_ARCH_ARMv7		9
+#define CPU_ARCH_ARMv7M		10
+
+#ifndef __ASSEMBLY__
+
+/* information about the system we're running on */
+extern unsigned int system_rev;
+extern unsigned int system_serial_low;
+extern unsigned int system_serial_high;
+extern unsigned int mem_fclk_21285;
+
+extern int __pure cpu_architecture(void);
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* __ASM_ARM_SYSTEM_INFO_H */
diff --git a/arch/arm/include/asm/system_misc.h b/arch/arm/include/asm/system_misc.h
new file mode 100644
index 000000000..a3d61ad98
--- /dev/null
+++ b/arch/arm/include/asm/system_misc.h
@@ -0,0 +1,27 @@
+#ifndef __ASM_ARM_SYSTEM_MISC_H
+#define __ASM_ARM_SYSTEM_MISC_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/compiler.h>
+#include <linux/linkage.h>
+#include <linux/irqflags.h>
+#include <linux/reboot.h>
+
+extern void cpu_init(void);
+
+void soft_restart(unsigned long);
+extern void (*arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd);
+extern void (*arm_pm_idle)(void);
+
+#define UDBG_UNDEFINED	(1 << 0)
+#define UDBG_SYSCALL	(1 << 1)
+#define UDBG_BADABORT	(1 << 2)
+#define UDBG_SEGV	(1 << 3)
+#define UDBG_BUS	(1 << 4)
+
+extern unsigned int user_debug;
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* __ASM_ARM_SYSTEM_MISC_H */
diff --git a/arch/arm/include/asm/tcm.h b/arch/arm/include/asm/tcm.h
new file mode 100644
index 000000000..8578d726a
--- /dev/null
+++ b/arch/arm/include/asm/tcm.h
@@ -0,0 +1,33 @@
+/*
+ *
+ * Copyright (C) 2008-2009 ST-Ericsson AB
+ * License terms: GNU General Public License (GPL) version 2
+ *
+ * Author: Rickard Andersson <rickard.andersson@stericsson.com>
+ * Author: Linus Walleij <linus.walleij@stericsson.com>
+ *
+ */
+#ifndef __ASMARM_TCM_H
+#define __ASMARM_TCM_H
+
+#ifndef CONFIG_HAVE_TCM
+#error "You should not be including tcm.h unless you have a TCM!"
+#endif
+
+#include <linux/compiler.h>
+
+/* Tag variables with this */
+#define __tcmdata __section(.tcm.data)
+/* Tag constants with this */
+#define __tcmconst __section(.tcm.rodata)
+/* Tag functions inside TCM called from outside TCM with this */
+#define __tcmfunc __attribute__((long_call)) __section(.tcm.text) noinline
+/* Tag function inside TCM called from inside TCM  with this */
+#define __tcmlocalfunc __section(.tcm.text)
+
+void *tcm_alloc(size_t len);
+void tcm_free(void *addr, size_t len);
+bool tcm_dtcm_present(void);
+bool tcm_itcm_present(void);
+
+#endif
diff --git a/arch/arm/include/asm/therm.h b/arch/arm/include/asm/therm.h
new file mode 100644
index 000000000..f002f0197
--- /dev/null
+++ b/arch/arm/include/asm/therm.h
@@ -0,0 +1,28 @@
+/*
+ * arch/arm/include/asm/therm.h: Definitions for Dallas Semiconductor
+ *  DS1620 thermometer driver (as used in the Rebel.com NetWinder)
+ */
+#ifndef __ASM_THERM_H
+#define __ASM_THERM_H
+
+/* ioctl numbers for /dev/therm */
+#define CMD_SET_THERMOSTATE	0x53
+#define CMD_GET_THERMOSTATE	0x54
+#define CMD_GET_STATUS		0x56
+#define CMD_GET_TEMPERATURE	0x57
+#define CMD_SET_THERMOSTATE2	0x58
+#define CMD_GET_THERMOSTATE2	0x59
+#define CMD_GET_TEMPERATURE2	0x5a
+#define CMD_GET_FAN		0x5b
+#define CMD_SET_FAN		0x5c
+
+#define FAN_OFF			0
+#define FAN_ON			1
+#define FAN_ALWAYS_ON		2
+
+struct therm {
+	int hi;
+	int lo;
+};
+
+#endif
diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
new file mode 100644
index 000000000..bd32eded3
--- /dev/null
+++ b/arch/arm/include/asm/thread_info.h
@@ -0,0 +1,181 @@
+/*
+ *  arch/arm/include/asm/thread_info.h
+ *
+ *  Copyright (C) 2002 Russell King.
+ *
+ * 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.
+ */
+#ifndef __ASM_ARM_THREAD_INFO_H
+#define __ASM_ARM_THREAD_INFO_H
+
+#ifdef __KERNEL__
+
+#include <linux/compiler.h>
+#include <asm/fpstate.h>
+#include <asm/page.h>
+
+#define THREAD_SIZE_ORDER	1
+#define THREAD_SIZE		(PAGE_SIZE << THREAD_SIZE_ORDER)
+#define THREAD_START_SP		(THREAD_SIZE - 8)
+
+#ifndef __ASSEMBLY__
+
+struct task_struct;
+
+#include <asm/types.h>
+#include <asm/domain.h>
+
+typedef unsigned long mm_segment_t;
+
+struct cpu_context_save {
+	__u32	r4;
+	__u32	r5;
+	__u32	r6;
+	__u32	r7;
+	__u32	r8;
+	__u32	r9;
+	__u32	sl;
+	__u32	fp;
+	__u32	sp;
+	__u32	pc;
+	__u32	extra[2];		/* Xscale 'acc' register, etc */
+};
+
+/*
+ * low level task data that entry.S needs immediate access to.
+ * __switch_to() assumes cpu_context follows immediately after cpu_domain.
+ */
+struct thread_info {
+	unsigned long		flags;		/* low level flags */
+	int			preempt_count;	/* 0 => preemptable, <0 => bug */
+	mm_segment_t		addr_limit;	/* address limit */
+	struct task_struct	*task;		/* main task structure */
+	__u32			cpu;		/* cpu */
+	__u32			cpu_domain;	/* cpu domain */
+	struct cpu_context_save	cpu_context;	/* cpu context */
+	__u32			syscall;	/* syscall number */
+	__u8			used_cp[16];	/* thread used copro */
+	unsigned long		tp_value[2];	/* TLS registers */
+#ifdef CONFIG_CRUNCH
+	struct crunch_state	crunchstate;
+#endif
+	union fp_state		fpstate __attribute__((aligned(8)));
+	union vfp_state		vfpstate;
+#ifdef CONFIG_ARM_THUMBEE
+	unsigned long		thumbee_state;	/* ThumbEE Handler Base register */
+#endif
+};
+
+#define INIT_THREAD_INFO(tsk)						\
+{									\
+	.task		= &tsk,						\
+	.flags		= 0,						\
+	.preempt_count	= INIT_PREEMPT_COUNT,				\
+	.addr_limit	= KERNEL_DS,					\
+	.cpu_domain	= domain_val(DOMAIN_USER, DOMAIN_MANAGER) |	\
+			  domain_val(DOMAIN_KERNEL, DOMAIN_MANAGER) |	\
+			  domain_val(DOMAIN_IO, DOMAIN_CLIENT),		\
+}
+
+#define init_thread_info	(init_thread_union.thread_info)
+#define init_stack		(init_thread_union.stack)
+
+/*
+ * how to get the current stack pointer in 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)
+{
+	return (struct thread_info *)
+		(current_stack_pointer & ~(THREAD_SIZE - 1));
+}
+
+#define thread_saved_pc(tsk)	\
+	((unsigned long)(task_thread_info(tsk)->cpu_context.pc))
+#define thread_saved_sp(tsk)	\
+	((unsigned long)(task_thread_info(tsk)->cpu_context.sp))
+
+#ifndef CONFIG_THUMB2_KERNEL
+#define thread_saved_fp(tsk)	\
+	((unsigned long)(task_thread_info(tsk)->cpu_context.fp))
+#else
+#define thread_saved_fp(tsk)	\
+	((unsigned long)(task_thread_info(tsk)->cpu_context.r7))
+#endif
+
+extern void crunch_task_disable(struct thread_info *);
+extern void crunch_task_copy(struct thread_info *, void *);
+extern void crunch_task_restore(struct thread_info *, void *);
+extern void crunch_task_release(struct thread_info *);
+
+extern void iwmmxt_task_disable(struct thread_info *);
+extern void iwmmxt_task_copy(struct thread_info *, void *);
+extern void iwmmxt_task_restore(struct thread_info *, void *);
+extern void iwmmxt_task_release(struct thread_info *);
+extern void iwmmxt_task_switch(struct thread_info *);
+
+extern void vfp_sync_hwstate(struct thread_info *);
+extern void vfp_flush_hwstate(struct thread_info *);
+
+struct user_vfp;
+struct user_vfp_exc;
+
+extern int vfp_preserve_user_clear_hwstate(struct user_vfp __user *,
+					   struct user_vfp_exc __user *);
+extern int vfp_restore_user_hwstate(struct user_vfp __user *,
+				    struct user_vfp_exc __user *);
+#endif
+
+/*
+ * thread information flags:
+ *  TIF_SYSCALL_TRACE	- syscall trace active
+ *  TIF_SYSCAL_AUDIT	- syscall auditing active
+ *  TIF_SIGPENDING	- signal pending
+ *  TIF_NEED_RESCHED	- rescheduling necessary
+ *  TIF_NOTIFY_RESUME	- callback before returning to user
+ *  TIF_USEDFPU		- FPU was used by this task this quantum (SMP)
+ *  TIF_POLLING_NRFLAG	- true if poll_idle() is polling TIF_NEED_RESCHED
+ */
+#define TIF_SIGPENDING		0
+#define TIF_NEED_RESCHED	1
+#define TIF_NOTIFY_RESUME	2	/* callback before returning to user */
+#define TIF_UPROBE		7
+#define TIF_SYSCALL_TRACE	8
+#define TIF_SYSCALL_AUDIT	9
+#define TIF_SYSCALL_TRACEPOINT	10
+#define TIF_SECCOMP		11	/* seccomp syscall filtering active */
+#define TIF_NOHZ		12	/* in adaptive nohz mode */
+#define TIF_USING_IWMMXT	17
+#define TIF_MEMDIE		18	/* is terminating due to OOM killer */
+#define TIF_RESTORE_SIGMASK	20
+
+#define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
+#define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
+#define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
+#define _TIF_UPROBE		(1 << TIF_UPROBE)
+#define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
+#define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
+#define _TIF_SYSCALL_TRACEPOINT	(1 << TIF_SYSCALL_TRACEPOINT)
+#define _TIF_SECCOMP		(1 << TIF_SECCOMP)
+#define _TIF_USING_IWMMXT	(1 << TIF_USING_IWMMXT)
+
+/* Checks for any syscall work in entry-common.S */
+#define _TIF_SYSCALL_WORK (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
+			   _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP)
+
+/*
+ * Change these and you break ASM code in entry-common.S
+ */
+#define _TIF_WORK_MASK		(_TIF_NEED_RESCHED | _TIF_SIGPENDING | \
+				 _TIF_NOTIFY_RESUME | _TIF_UPROBE)
+
+#endif /* __KERNEL__ */
+#endif /* __ASM_ARM_THREAD_INFO_H */
diff --git a/arch/arm/include/asm/thread_notify.h b/arch/arm/include/asm/thread_notify.h
new file mode 100644
index 000000000..1dc980675
--- /dev/null
+++ b/arch/arm/include/asm/thread_notify.h
@@ -0,0 +1,49 @@
+/*
+ *  arch/arm/include/asm/thread_notify.h
+ *
+ *  Copyright (C) 2006 Russell King.
+ *
+ * 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.
+ */
+#ifndef ASMARM_THREAD_NOTIFY_H
+#define ASMARM_THREAD_NOTIFY_H
+
+#ifdef __KERNEL__
+
+#ifndef __ASSEMBLY__
+
+#include <linux/notifier.h>
+#include <asm/thread_info.h>
+
+static inline int thread_register_notifier(struct notifier_block *n)
+{
+	extern struct atomic_notifier_head thread_notify_head;
+	return atomic_notifier_chain_register(&thread_notify_head, n);
+}
+
+static inline void thread_unregister_notifier(struct notifier_block *n)
+{
+	extern struct atomic_notifier_head thread_notify_head;
+	atomic_notifier_chain_unregister(&thread_notify_head, n);
+}
+
+static inline void thread_notify(unsigned long rc, struct thread_info *thread)
+{
+	extern struct atomic_notifier_head thread_notify_head;
+	atomic_notifier_call_chain(&thread_notify_head, rc, thread);
+}
+
+#endif
+
+/*
+ * These are the reason codes for the thread notifier.
+ */
+#define THREAD_NOTIFY_FLUSH	0
+#define THREAD_NOTIFY_EXIT	1
+#define THREAD_NOTIFY_SWITCH	2
+#define THREAD_NOTIFY_COPY	3
+
+#endif
+#endif
diff --git a/arch/arm/include/asm/timex.h b/arch/arm/include/asm/timex.h
new file mode 100644
index 000000000..f6fcc67ef
--- /dev/null
+++ b/arch/arm/include/asm/timex.h
@@ -0,0 +1,18 @@
+/*
+ *  arch/arm/include/asm/timex.h
+ *
+ *  Copyright (C) 1997,1998 Russell King
+ *
+ * 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.
+ *
+ *  Architecture Specific TIME specifications
+ */
+#ifndef _ASMARM_TIMEX_H
+#define _ASMARM_TIMEX_H
+
+typedef unsigned long cycles_t;
+#define get_cycles()	({ cycles_t c; read_current_timer(&c) ? 0 : c; })
+
+#endif
diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h
new file mode 100644
index 000000000..3cadb726e
--- /dev/null
+++ b/arch/arm/include/asm/tlb.h
@@ -0,0 +1,267 @@
+/*
+ *  arch/arm/include/asm/tlb.h
+ *
+ *  Copyright (C) 2002 Russell King
+ *
+ * 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.
+ *
+ *  Experimentation shows that on a StrongARM, it appears to be faster
+ *  to use the "invalidate whole tlb" rather than "invalidate single
+ *  tlb" for this.
+ *
+ *  This appears true for both the process fork+exit case, as well as
+ *  the munmap-large-area case.
+ */
+#ifndef __ASMARM_TLB_H
+#define __ASMARM_TLB_H
+
+#include <asm/cacheflush.h>
+
+#ifndef CONFIG_MMU
+
+#include <linux/pagemap.h>
+
+#define tlb_flush(tlb)	((void) tlb)
+
+#include <asm-generic/tlb.h>
+
+#else /* !CONFIG_MMU */
+
+#include <linux/swap.h>
+#include <asm/pgalloc.h>
+#include <asm/tlbflush.h>
+
+#define MMU_GATHER_BUNDLE	8
+
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+static inline void __tlb_remove_table(void *_table)
+{
+	free_page_and_swap_cache((struct page *)_table);
+}
+
+struct mmu_table_batch {
+	struct rcu_head		rcu;
+	unsigned int		nr;
+	void			*tables[0];
+};
+
+#define MAX_TABLE_BATCH		\
+	((PAGE_SIZE - sizeof(struct mmu_table_batch)) / sizeof(void *))
+
+extern void tlb_table_flush(struct mmu_gather *tlb);
+extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
+
+#define tlb_remove_entry(tlb, entry)	tlb_remove_table(tlb, entry)
+#else
+#define tlb_remove_entry(tlb, entry)	tlb_remove_page(tlb, entry)
+#endif /* CONFIG_HAVE_RCU_TABLE_FREE */
+
+/*
+ * TLB handling.  This allows us to remove pages from the page
+ * tables, and efficiently handle the TLB issues.
+ */
+struct mmu_gather {
+	struct mm_struct	*mm;
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+	struct mmu_table_batch	*batch;
+	unsigned int		need_flush;
+#endif
+	unsigned int		fullmm;
+	struct vm_area_struct	*vma;
+	unsigned long		start, end;
+	unsigned long		range_start;
+	unsigned long		range_end;
+	unsigned int		nr;
+	unsigned int		max;
+	struct page		**pages;
+	struct page		*local[MMU_GATHER_BUNDLE];
+};
+
+DECLARE_PER_CPU(struct mmu_gather, mmu_gathers);
+
+/*
+ * This is unnecessarily complex.  There's three ways the TLB shootdown
+ * code is used:
+ *  1. Unmapping a range of vmas.  See zap_page_range(), unmap_region().
+ *     tlb->fullmm = 0, and tlb_start_vma/tlb_end_vma will be called.
+ *     tlb->vma will be non-NULL.
+ *  2. Unmapping all vmas.  See exit_mmap().
+ *     tlb->fullmm = 1, and tlb_start_vma/tlb_end_vma will be called.
+ *     tlb->vma will be non-NULL.  Additionally, page tables will be freed.
+ *  3. Unmapping argument pages.  See shift_arg_pages().
+ *     tlb->fullmm = 0, but tlb_start_vma/tlb_end_vma will not be called.
+ *     tlb->vma will be NULL.
+ */
+static inline void tlb_flush(struct mmu_gather *tlb)
+{
+	if (tlb->fullmm || !tlb->vma)
+		flush_tlb_mm(tlb->mm);
+	else if (tlb->range_end > 0) {
+		flush_tlb_range(tlb->vma, tlb->range_start, tlb->range_end);
+		tlb->range_start = TASK_SIZE;
+		tlb->range_end = 0;
+	}
+}
+
+static inline void tlb_add_flush(struct mmu_gather *tlb, unsigned long addr)
+{
+	if (!tlb->fullmm) {
+		if (addr < tlb->range_start)
+			tlb->range_start = addr;
+		if (addr + PAGE_SIZE > tlb->range_end)
+			tlb->range_end = addr + PAGE_SIZE;
+	}
+}
+
+static inline void __tlb_alloc_page(struct mmu_gather *tlb)
+{
+	unsigned long addr = __get_free_pages(GFP_NOWAIT | __GFP_NOWARN, 0);
+
+	if (addr) {
+		tlb->pages = (void *)addr;
+		tlb->max = PAGE_SIZE / sizeof(struct page *);
+	}
+}
+
+static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
+{
+	tlb_flush(tlb);
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+	tlb_table_flush(tlb);
+#endif
+}
+
+static inline void tlb_flush_mmu_free(struct mmu_gather *tlb)
+{
+	free_pages_and_swap_cache(tlb->pages, tlb->nr);
+	tlb->nr = 0;
+	if (tlb->pages == tlb->local)
+		__tlb_alloc_page(tlb);
+}
+
+static inline void tlb_flush_mmu(struct mmu_gather *tlb)
+{
+	tlb_flush_mmu_tlbonly(tlb);
+	tlb_flush_mmu_free(tlb);
+}
+
+static inline void
+tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
+{
+	tlb->mm = mm;
+	tlb->fullmm = !(start | (end+1));
+	tlb->start = start;
+	tlb->end = end;
+	tlb->vma = NULL;
+	tlb->max = ARRAY_SIZE(tlb->local);
+	tlb->pages = tlb->local;
+	tlb->nr = 0;
+	__tlb_alloc_page(tlb);
+
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+	tlb->batch = NULL;
+#endif
+}
+
+static inline void
+tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
+{
+	tlb_flush_mmu(tlb);
+
+	/* keep the page table cache within bounds */
+	check_pgt_cache();
+
+	if (tlb->pages != tlb->local)
+		free_pages((unsigned long)tlb->pages, 0);
+}
+
+/*
+ * Memorize the range for the TLB flush.
+ */
+static inline void
+tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep, unsigned long addr)
+{
+	tlb_add_flush(tlb, addr);
+}
+
+/*
+ * In the case of tlb vma handling, we can optimise these away in the
+ * case where we're doing a full MM flush.  When we're doing a munmap,
+ * the vmas are adjusted to only cover the region to be torn down.
+ */
+static inline void
+tlb_start_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
+{
+	if (!tlb->fullmm) {
+		flush_cache_range(vma, vma->vm_start, vma->vm_end);
+		tlb->vma = vma;
+		tlb->range_start = TASK_SIZE;
+		tlb->range_end = 0;
+	}
+}
+
+static inline void
+tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
+{
+	if (!tlb->fullmm)
+		tlb_flush(tlb);
+}
+
+static inline int __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
+{
+	tlb->pages[tlb->nr++] = page;
+	VM_BUG_ON(tlb->nr > tlb->max);
+	return tlb->max - tlb->nr;
+}
+
+static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
+{
+	if (!__tlb_remove_page(tlb, page))
+		tlb_flush_mmu(tlb);
+}
+
+static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
+	unsigned long addr)
+{
+	pgtable_page_dtor(pte);
+
+#ifdef CONFIG_ARM_LPAE
+	tlb_add_flush(tlb, addr);
+#else
+	/*
+	 * With the classic ARM MMU, a pte page has two corresponding pmd
+	 * entries, each covering 1MB.
+	 */
+	addr &= PMD_MASK;
+	tlb_add_flush(tlb, addr + SZ_1M - PAGE_SIZE);
+	tlb_add_flush(tlb, addr + SZ_1M);
+#endif
+
+	tlb_remove_entry(tlb, pte);
+}
+
+static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
+				  unsigned long addr)
+{
+#ifdef CONFIG_ARM_LPAE
+	tlb_add_flush(tlb, addr);
+	tlb_remove_entry(tlb, virt_to_page(pmdp));
+#endif
+}
+
+static inline void
+tlb_remove_pmd_tlb_entry(struct mmu_gather *tlb, pmd_t *pmdp, unsigned long addr)
+{
+	tlb_add_flush(tlb, addr);
+}
+
+#define pte_free_tlb(tlb, ptep, addr)	__pte_free_tlb(tlb, ptep, addr)
+#define pmd_free_tlb(tlb, pmdp, addr)	__pmd_free_tlb(tlb, pmdp, addr)
+#define pud_free_tlb(tlb, pudp, addr)	pud_free((tlb)->mm, pudp)
+
+#define tlb_migrate_finish(mm)		do { } while (0)
+
+#endif /* CONFIG_MMU */
+#endif
diff --git a/arch/arm/include/asm/tlbflush.h b/arch/arm/include/asm/tlbflush.h
new file mode 100644
index 000000000..def9e5701
--- /dev/null
+++ b/arch/arm/include/asm/tlbflush.h
@@ -0,0 +1,686 @@
+/*
+ *  arch/arm/include/asm/tlbflush.h
+ *
+ *  Copyright (C) 1999-2003 Russell King
+ *
+ * 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.
+ */
+#ifndef _ASMARM_TLBFLUSH_H
+#define _ASMARM_TLBFLUSH_H
+
+#ifdef CONFIG_MMU
+
+#include <asm/glue.h>
+
+#define TLB_V4_U_PAGE	(1 << 1)
+#define TLB_V4_D_PAGE	(1 << 2)
+#define TLB_V4_I_PAGE	(1 << 3)
+#define TLB_V6_U_PAGE	(1 << 4)
+#define TLB_V6_D_PAGE	(1 << 5)
+#define TLB_V6_I_PAGE	(1 << 6)
+
+#define TLB_V4_U_FULL	(1 << 9)
+#define TLB_V4_D_FULL	(1 << 10)
+#define TLB_V4_I_FULL	(1 << 11)
+#define TLB_V6_U_FULL	(1 << 12)
+#define TLB_V6_D_FULL	(1 << 13)
+#define TLB_V6_I_FULL	(1 << 14)
+
+#define TLB_V6_U_ASID	(1 << 16)
+#define TLB_V6_D_ASID	(1 << 17)
+#define TLB_V6_I_ASID	(1 << 18)
+
+#define TLB_V6_BP	(1 << 19)
+
+/* Unified Inner Shareable TLB operations (ARMv7 MP extensions) */
+#define TLB_V7_UIS_PAGE	(1 << 20)
+#define TLB_V7_UIS_FULL (1 << 21)
+#define TLB_V7_UIS_ASID (1 << 22)
+#define TLB_V7_UIS_BP	(1 << 23)
+
+#define TLB_BARRIER	(1 << 28)
+#define TLB_L2CLEAN_FR	(1 << 29)		/* Feroceon */
+#define TLB_DCLEAN	(1 << 30)
+#define TLB_WB		(1 << 31)
+
+/*
+ *	MMU TLB Model
+ *	=============
+ *
+ *	We have the following to choose from:
+ *	  v4    - ARMv4 without write buffer
+ *	  v4wb  - ARMv4 with write buffer without I TLB flush entry instruction
+ *	  v4wbi - ARMv4 with write buffer with I TLB flush entry instruction
+ *	  fr    - Feroceon (v4wbi with non-outer-cacheable page table walks)
+ *	  fa    - Faraday (v4 with write buffer with UTLB)
+ *	  v6wbi - ARMv6 with write buffer with I TLB flush entry instruction
+ *	  v7wbi - identical to v6wbi
+ */
+#undef _TLB
+#undef MULTI_TLB
+
+#ifdef CONFIG_SMP_ON_UP
+#define MULTI_TLB 1
+#endif
+
+#define v4_tlb_flags	(TLB_V4_U_FULL | TLB_V4_U_PAGE)
+
+#ifdef CONFIG_CPU_TLB_V4WT
+# define v4_possible_flags	v4_tlb_flags
+# define v4_always_flags	v4_tlb_flags
+# ifdef _TLB
+#  define MULTI_TLB 1
+# else
+#  define _TLB v4
+# endif
+#else
+# define v4_possible_flags	0
+# define v4_always_flags	(-1UL)
+#endif
+
+#define fa_tlb_flags	(TLB_WB | TLB_DCLEAN | TLB_BARRIER | \
+			 TLB_V4_U_FULL | TLB_V4_U_PAGE)
+
+#ifdef CONFIG_CPU_TLB_FA
+# define fa_possible_flags	fa_tlb_flags
+# define fa_always_flags	fa_tlb_flags
+# ifdef _TLB
+#  define MULTI_TLB 1
+# else
+#  define _TLB fa
+# endif
+#else
+# define fa_possible_flags	0
+# define fa_always_flags	(-1UL)
+#endif
+
+#define v4wbi_tlb_flags	(TLB_WB | TLB_DCLEAN | \
+			 TLB_V4_I_FULL | TLB_V4_D_FULL | \
+			 TLB_V4_I_PAGE | TLB_V4_D_PAGE)
+
+#ifdef CONFIG_CPU_TLB_V4WBI
+# define v4wbi_possible_flags	v4wbi_tlb_flags
+# define v4wbi_always_flags	v4wbi_tlb_flags
+# ifdef _TLB
+#  define MULTI_TLB 1
+# else
+#  define _TLB v4wbi
+# endif
+#else
+# define v4wbi_possible_flags	0
+# define v4wbi_always_flags	(-1UL)
+#endif
+
+#define fr_tlb_flags	(TLB_WB | TLB_DCLEAN | TLB_L2CLEAN_FR | \
+			 TLB_V4_I_FULL | TLB_V4_D_FULL | \
+			 TLB_V4_I_PAGE | TLB_V4_D_PAGE)
+
+#ifdef CONFIG_CPU_TLB_FEROCEON
+# define fr_possible_flags	fr_tlb_flags
+# define fr_always_flags	fr_tlb_flags
+# ifdef _TLB
+#  define MULTI_TLB 1
+# else
+#  define _TLB v4wbi
+# endif
+#else
+# define fr_possible_flags	0
+# define fr_always_flags	(-1UL)
+#endif
+
+#define v4wb_tlb_flags	(TLB_WB | TLB_DCLEAN | \
+			 TLB_V4_I_FULL | TLB_V4_D_FULL | \
+			 TLB_V4_D_PAGE)
+
+#ifdef CONFIG_CPU_TLB_V4WB
+# define v4wb_possible_flags	v4wb_tlb_flags
+# define v4wb_always_flags	v4wb_tlb_flags
+# ifdef _TLB
+#  define MULTI_TLB 1
+# else
+#  define _TLB v4wb
+# endif
+#else
+# define v4wb_possible_flags	0
+# define v4wb_always_flags	(-1UL)
+#endif
+
+#define v6wbi_tlb_flags (TLB_WB | TLB_DCLEAN | TLB_BARRIER | \
+			 TLB_V6_I_FULL | TLB_V6_D_FULL | \
+			 TLB_V6_I_PAGE | TLB_V6_D_PAGE | \
+			 TLB_V6_I_ASID | TLB_V6_D_ASID | \
+			 TLB_V6_BP)
+
+#ifdef CONFIG_CPU_TLB_V6
+# define v6wbi_possible_flags	v6wbi_tlb_flags
+# define v6wbi_always_flags	v6wbi_tlb_flags
+# ifdef _TLB
+#  define MULTI_TLB 1
+# else
+#  define _TLB v6wbi
+# endif
+#else
+# define v6wbi_possible_flags	0
+# define v6wbi_always_flags	(-1UL)
+#endif
+
+#define v7wbi_tlb_flags_smp	(TLB_WB | TLB_BARRIER | \
+				 TLB_V7_UIS_FULL | TLB_V7_UIS_PAGE | \
+				 TLB_V7_UIS_ASID | TLB_V7_UIS_BP)
+#define v7wbi_tlb_flags_up	(TLB_WB | TLB_DCLEAN | TLB_BARRIER | \
+				 TLB_V6_U_FULL | TLB_V6_U_PAGE | \
+				 TLB_V6_U_ASID | TLB_V6_BP)
+
+#ifdef CONFIG_CPU_TLB_V7
+
+# ifdef CONFIG_SMP_ON_UP
+#  define v7wbi_possible_flags	(v7wbi_tlb_flags_smp | v7wbi_tlb_flags_up)
+#  define v7wbi_always_flags	(v7wbi_tlb_flags_smp & v7wbi_tlb_flags_up)
+# elif defined(CONFIG_SMP)
+#  define v7wbi_possible_flags	v7wbi_tlb_flags_smp
+#  define v7wbi_always_flags	v7wbi_tlb_flags_smp
+# else
+#  define v7wbi_possible_flags	v7wbi_tlb_flags_up
+#  define v7wbi_always_flags	v7wbi_tlb_flags_up
+# endif
+# ifdef _TLB
+#  define MULTI_TLB 1
+# else
+#  define _TLB v7wbi
+# endif
+#else
+# define v7wbi_possible_flags	0
+# define v7wbi_always_flags	(-1UL)
+#endif
+
+#ifndef _TLB
+#error Unknown TLB model
+#endif
+
+#ifndef __ASSEMBLY__
+
+#include <linux/sched.h>
+
+struct cpu_tlb_fns {
+	void (*flush_user_range)(unsigned long, unsigned long, struct vm_area_struct *);
+	void (*flush_kern_range)(unsigned long, unsigned long);
+	unsigned long tlb_flags;
+};
+
+/*
+ * Select the calling method
+ */
+#ifdef MULTI_TLB
+
+#define __cpu_flush_user_tlb_range	cpu_tlb.flush_user_range
+#define __cpu_flush_kern_tlb_range	cpu_tlb.flush_kern_range
+
+#else
+
+#define __cpu_flush_user_tlb_range	__glue(_TLB,_flush_user_tlb_range)
+#define __cpu_flush_kern_tlb_range	__glue(_TLB,_flush_kern_tlb_range)
+
+extern void __cpu_flush_user_tlb_range(unsigned long, unsigned long, struct vm_area_struct *);
+extern void __cpu_flush_kern_tlb_range(unsigned long, unsigned long);
+
+#endif
+
+extern struct cpu_tlb_fns cpu_tlb;
+
+#define __cpu_tlb_flags			cpu_tlb.tlb_flags
+
+/*
+ *	TLB Management
+ *	==============
+ *
+ *	The arch/arm/mm/tlb-*.S files implement these methods.
+ *
+ *	The TLB specific code is expected to perform whatever tests it
+ *	needs to determine if it should invalidate the TLB for each
+ *	call.  Start addresses are inclusive and end addresses are
+ *	exclusive; it is safe to round these addresses down.
+ *
+ *	flush_tlb_all()
+ *
+ *		Invalidate the entire TLB.
+ *
+ *	flush_tlb_mm(mm)
+ *
+ *		Invalidate all TLB entries in a particular address
+ *		space.
+ *		- mm	- mm_struct describing address space
+ *
+ *	flush_tlb_range(mm,start,end)
+ *
+ *		Invalidate a range of TLB entries in the specified
+ *		address space.
+ *		- mm	- mm_struct describing address space
+ *		- start - start address (may not be aligned)
+ *		- end	- end address (exclusive, may not be aligned)
+ *
+ *	flush_tlb_page(vaddr,vma)
+ *
+ *		Invalidate the specified page in the specified address range.
+ *		- vaddr - virtual address (may not be aligned)
+ *		- vma	- vma_struct describing address range
+ *
+ *	flush_kern_tlb_page(kaddr)
+ *
+ *		Invalidate the TLB entry for the specified page.  The address
+ *		will be in the kernels virtual memory space.  Current uses
+ *		only require the D-TLB to be invalidated.
+ *		- kaddr - Kernel virtual memory address
+ */
+
+/*
+ * We optimise the code below by:
+ *  - building a set of TLB flags that might be set in __cpu_tlb_flags
+ *  - building a set of TLB flags that will always be set in __cpu_tlb_flags
+ *  - if we're going to need __cpu_tlb_flags, access it once and only once
+ *
+ * This allows us to build optimal assembly for the single-CPU type case,
+ * and as close to optimal given the compiler constrants for multi-CPU
+ * case.  We could do better for the multi-CPU case if the compiler
+ * implemented the "%?" method, but this has been discontinued due to too
+ * many people getting it wrong.
+ */
+#define possible_tlb_flags	(v4_possible_flags | \
+				 v4wbi_possible_flags | \
+				 fr_possible_flags | \
+				 v4wb_possible_flags | \
+				 fa_possible_flags | \
+				 v6wbi_possible_flags | \
+				 v7wbi_possible_flags)
+
+#define always_tlb_flags	(v4_always_flags & \
+				 v4wbi_always_flags & \
+				 fr_always_flags & \
+				 v4wb_always_flags & \
+				 fa_always_flags & \
+				 v6wbi_always_flags & \
+				 v7wbi_always_flags)
+
+#define tlb_flag(f)	((always_tlb_flags & (f)) || (__tlb_flag & possible_tlb_flags & (f)))
+
+#define __tlb_op(f, insnarg, arg)					\
+	do {								\
+		if (always_tlb_flags & (f))				\
+			asm("mcr " insnarg				\
+			    : : "r" (arg) : "cc");			\
+		else if (possible_tlb_flags & (f))			\
+			asm("tst %1, %2\n\t"				\
+			    "mcrne " insnarg				\
+			    : : "r" (arg), "r" (__tlb_flag), "Ir" (f)	\
+			    : "cc");					\
+	} while (0)
+
+#define tlb_op(f, regs, arg)	__tlb_op(f, "p15, 0, %0, " regs, arg)
+#define tlb_l2_op(f, regs, arg)	__tlb_op(f, "p15, 1, %0, " regs, arg)
+
+static inline void __local_flush_tlb_all(void)
+{
+	const int zero = 0;
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
+
+	tlb_op(TLB_V4_U_FULL | TLB_V6_U_FULL, "c8, c7, 0", zero);
+	tlb_op(TLB_V4_D_FULL | TLB_V6_D_FULL, "c8, c6, 0", zero);
+	tlb_op(TLB_V4_I_FULL | TLB_V6_I_FULL, "c8, c5, 0", zero);
+}
+
+static inline void local_flush_tlb_all(void)
+{
+	const int zero = 0;
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
+
+	if (tlb_flag(TLB_WB))
+		dsb(nshst);
+
+	__local_flush_tlb_all();
+	tlb_op(TLB_V7_UIS_FULL, "c8, c7, 0", zero);
+
+	if (tlb_flag(TLB_BARRIER)) {
+		dsb(nsh);
+		isb();
+	}
+}
+
+static inline void __flush_tlb_all(void)
+{
+	const int zero = 0;
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
+
+	if (tlb_flag(TLB_WB))
+		dsb(ishst);
+
+	__local_flush_tlb_all();
+	tlb_op(TLB_V7_UIS_FULL, "c8, c3, 0", zero);
+
+	if (tlb_flag(TLB_BARRIER)) {
+		dsb(ish);
+		isb();
+	}
+}
+
+static inline void __local_flush_tlb_mm(struct mm_struct *mm)
+{
+	const int zero = 0;
+	const int asid = ASID(mm);
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
+
+	if (possible_tlb_flags & (TLB_V4_U_FULL|TLB_V4_D_FULL|TLB_V4_I_FULL)) {
+		if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(mm))) {
+			tlb_op(TLB_V4_U_FULL, "c8, c7, 0", zero);
+			tlb_op(TLB_V4_D_FULL, "c8, c6, 0", zero);
+			tlb_op(TLB_V4_I_FULL, "c8, c5, 0", zero);
+		}
+	}
+
+	tlb_op(TLB_V6_U_ASID, "c8, c7, 2", asid);
+	tlb_op(TLB_V6_D_ASID, "c8, c6, 2", asid);
+	tlb_op(TLB_V6_I_ASID, "c8, c5, 2", asid);
+}
+
+static inline void local_flush_tlb_mm(struct mm_struct *mm)
+{
+	const int asid = ASID(mm);
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
+
+	if (tlb_flag(TLB_WB))
+		dsb(nshst);
+
+	__local_flush_tlb_mm(mm);
+	tlb_op(TLB_V7_UIS_ASID, "c8, c7, 2", asid);
+
+	if (tlb_flag(TLB_BARRIER))
+		dsb(nsh);
+}
+
+static inline void __flush_tlb_mm(struct mm_struct *mm)
+{
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
+
+	if (tlb_flag(TLB_WB))
+		dsb(ishst);
+
+	__local_flush_tlb_mm(mm);
+#ifdef CONFIG_ARM_ERRATA_720789
+	tlb_op(TLB_V7_UIS_ASID, "c8, c3, 0", 0);
+#else
+	tlb_op(TLB_V7_UIS_ASID, "c8, c3, 2", ASID(mm));
+#endif
+
+	if (tlb_flag(TLB_BARRIER))
+		dsb(ish);
+}
+
+static inline void
+__local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
+{
+	const int zero = 0;
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
+
+	uaddr = (uaddr & PAGE_MASK) | ASID(vma->vm_mm);
+
+	if (possible_tlb_flags & (TLB_V4_U_PAGE|TLB_V4_D_PAGE|TLB_V4_I_PAGE|TLB_V4_I_FULL) &&
+	    cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) {
+		tlb_op(TLB_V4_U_PAGE, "c8, c7, 1", uaddr);
+		tlb_op(TLB_V4_D_PAGE, "c8, c6, 1", uaddr);
+		tlb_op(TLB_V4_I_PAGE, "c8, c5, 1", uaddr);
+		if (!tlb_flag(TLB_V4_I_PAGE) && tlb_flag(TLB_V4_I_FULL))
+			asm("mcr p15, 0, %0, c8, c5, 0" : : "r" (zero) : "cc");
+	}
+
+	tlb_op(TLB_V6_U_PAGE, "c8, c7, 1", uaddr);
+	tlb_op(TLB_V6_D_PAGE, "c8, c6, 1", uaddr);
+	tlb_op(TLB_V6_I_PAGE, "c8, c5, 1", uaddr);
+}
+
+static inline void
+local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
+{
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
+
+	uaddr = (uaddr & PAGE_MASK) | ASID(vma->vm_mm);
+
+	if (tlb_flag(TLB_WB))
+		dsb(nshst);
+
+	__local_flush_tlb_page(vma, uaddr);
+	tlb_op(TLB_V7_UIS_PAGE, "c8, c7, 1", uaddr);
+
+	if (tlb_flag(TLB_BARRIER))
+		dsb(nsh);
+}
+
+static inline void
+__flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
+{
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
+
+	uaddr = (uaddr & PAGE_MASK) | ASID(vma->vm_mm);
+
+	if (tlb_flag(TLB_WB))
+		dsb(ishst);
+
+	__local_flush_tlb_page(vma, uaddr);
+#ifdef CONFIG_ARM_ERRATA_720789
+	tlb_op(TLB_V7_UIS_PAGE, "c8, c3, 3", uaddr & PAGE_MASK);
+#else
+	tlb_op(TLB_V7_UIS_PAGE, "c8, c3, 1", uaddr);
+#endif
+
+	if (tlb_flag(TLB_BARRIER))
+		dsb(ish);
+}
+
+static inline void __local_flush_tlb_kernel_page(unsigned long kaddr)
+{
+	const int zero = 0;
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
+
+	tlb_op(TLB_V4_U_PAGE, "c8, c7, 1", kaddr);
+	tlb_op(TLB_V4_D_PAGE, "c8, c6, 1", kaddr);
+	tlb_op(TLB_V4_I_PAGE, "c8, c5, 1", kaddr);
+	if (!tlb_flag(TLB_V4_I_PAGE) && tlb_flag(TLB_V4_I_FULL))
+		asm("mcr p15, 0, %0, c8, c5, 0" : : "r" (zero) : "cc");
+
+	tlb_op(TLB_V6_U_PAGE, "c8, c7, 1", kaddr);
+	tlb_op(TLB_V6_D_PAGE, "c8, c6, 1", kaddr);
+	tlb_op(TLB_V6_I_PAGE, "c8, c5, 1", kaddr);
+}
+
+static inline void local_flush_tlb_kernel_page(unsigned long kaddr)
+{
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
+
+	kaddr &= PAGE_MASK;
+
+	if (tlb_flag(TLB_WB))
+		dsb(nshst);
+
+	__local_flush_tlb_kernel_page(kaddr);
+	tlb_op(TLB_V7_UIS_PAGE, "c8, c7, 1", kaddr);
+
+	if (tlb_flag(TLB_BARRIER)) {
+		dsb(nsh);
+		isb();
+	}
+}
+
+static inline void __flush_tlb_kernel_page(unsigned long kaddr)
+{
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
+
+	kaddr &= PAGE_MASK;
+
+	if (tlb_flag(TLB_WB))
+		dsb(ishst);
+
+	__local_flush_tlb_kernel_page(kaddr);
+	tlb_op(TLB_V7_UIS_PAGE, "c8, c3, 1", kaddr);
+
+	if (tlb_flag(TLB_BARRIER)) {
+		dsb(ish);
+		isb();
+	}
+}
+
+/*
+ * Branch predictor maintenance is paired with full TLB invalidation, so
+ * there is no need for any barriers here.
+ */
+static inline void __local_flush_bp_all(void)
+{
+	const int zero = 0;
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
+
+	if (tlb_flag(TLB_V6_BP))
+		asm("mcr p15, 0, %0, c7, c5, 6" : : "r" (zero));
+}
+
+static inline void local_flush_bp_all(void)
+{
+	const int zero = 0;
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
+
+	__local_flush_bp_all();
+	if (tlb_flag(TLB_V7_UIS_BP))
+		asm("mcr p15, 0, %0, c7, c5, 6" : : "r" (zero));
+}
+
+static inline void __flush_bp_all(void)
+{
+	const int zero = 0;
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
+
+	__local_flush_bp_all();
+	if (tlb_flag(TLB_V7_UIS_BP))
+		asm("mcr p15, 0, %0, c7, c1, 6" : : "r" (zero));
+}
+
+/*
+ *	flush_pmd_entry
+ *
+ *	Flush a PMD entry (word aligned, or double-word aligned) to
+ *	RAM if the TLB for the CPU we are running on requires this.
+ *	This is typically used when we are creating PMD entries.
+ *
+ *	clean_pmd_entry
+ *
+ *	Clean (but don't drain the write buffer) if the CPU requires
+ *	these operations.  This is typically used when we are removing
+ *	PMD entries.
+ */
+static inline void flush_pmd_entry(void *pmd)
+{
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
+
+	tlb_op(TLB_DCLEAN, "c7, c10, 1	@ flush_pmd", pmd);
+	tlb_l2_op(TLB_L2CLEAN_FR, "c15, c9, 1  @ L2 flush_pmd", pmd);
+
+	if (tlb_flag(TLB_WB))
+		dsb(ishst);
+}
+
+static inline void clean_pmd_entry(void *pmd)
+{
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
+
+	tlb_op(TLB_DCLEAN, "c7, c10, 1	@ flush_pmd", pmd);
+	tlb_l2_op(TLB_L2CLEAN_FR, "c15, c9, 1  @ L2 flush_pmd", pmd);
+}
+
+#undef tlb_op
+#undef tlb_flag
+#undef always_tlb_flags
+#undef possible_tlb_flags
+
+/*
+ * Convert calls to our calling convention.
+ */
+#define local_flush_tlb_range(vma,start,end)	__cpu_flush_user_tlb_range(start,end,vma)
+#define local_flush_tlb_kernel_range(s,e)	__cpu_flush_kern_tlb_range(s,e)
+
+#ifndef CONFIG_SMP
+#define flush_tlb_all		local_flush_tlb_all
+#define flush_tlb_mm		local_flush_tlb_mm
+#define flush_tlb_page		local_flush_tlb_page
+#define flush_tlb_kernel_page	local_flush_tlb_kernel_page
+#define flush_tlb_range		local_flush_tlb_range
+#define flush_tlb_kernel_range	local_flush_tlb_kernel_range
+#define flush_bp_all		local_flush_bp_all
+#else
+extern void flush_tlb_all(void);
+extern void flush_tlb_mm(struct mm_struct *mm);
+extern void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr);
+extern void flush_tlb_kernel_page(unsigned long kaddr);
+extern void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end);
+extern void flush_tlb_kernel_range(unsigned long start, unsigned long end);
+extern void flush_bp_all(void);
+#endif
+
+/*
+ * If PG_dcache_clean is not set for the page, we need to ensure that any
+ * cache entries for the kernels virtual memory range are written
+ * back to the page. On ARMv6 and later, the cache coherency is handled via
+ * the set_pte_at() function.
+ */
+#if __LINUX_ARM_ARCH__ < 6
+extern void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr,
+	pte_t *ptep);
+#else
+static inline void update_mmu_cache(struct vm_area_struct *vma,
+				    unsigned long addr, pte_t *ptep)
+{
+}
+#endif
+
+#define update_mmu_cache_pmd(vma, address, pmd) do { } while (0)
+
+#endif
+
+#elif defined(CONFIG_SMP)	/* !CONFIG_MMU */
+
+#ifndef __ASSEMBLY__
+
+#include <linux/mm_types.h>
+
+static inline void local_flush_tlb_all(void)									{ }
+static inline void local_flush_tlb_mm(struct mm_struct *mm)							{ }
+static inline void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)			{ }
+static inline void local_flush_tlb_kernel_page(unsigned long kaddr)						{ }
+static inline void local_flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end)	{ }
+static inline void local_flush_tlb_kernel_range(unsigned long start, unsigned long end)				{ }
+static inline void local_flush_bp_all(void)									{ }
+
+extern void flush_tlb_all(void);
+extern void flush_tlb_mm(struct mm_struct *mm);
+extern void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr);
+extern void flush_tlb_kernel_page(unsigned long kaddr);
+extern void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end);
+extern void flush_tlb_kernel_range(unsigned long start, unsigned long end);
+extern void flush_bp_all(void);
+#endif	/* __ASSEMBLY__ */
+
+#endif
+
+#ifndef __ASSEMBLY__
+#ifdef CONFIG_ARM_ERRATA_798181
+extern void erratum_a15_798181_init(void);
+#else
+static inline void erratum_a15_798181_init(void) {}
+#endif
+extern bool (*erratum_a15_798181_handler)(void);
+
+static inline bool erratum_a15_798181(void)
+{
+	if (unlikely(IS_ENABLED(CONFIG_ARM_ERRATA_798181) &&
+		erratum_a15_798181_handler))
+		return erratum_a15_798181_handler();
+	return false;
+}
+#endif
+
+#endif
diff --git a/arch/arm/include/asm/tls.h b/arch/arm/include/asm/tls.h
new file mode 100644
index 000000000..5f833f7ad
--- /dev/null
+++ b/arch/arm/include/asm/tls.h
@@ -0,0 +1,127 @@
+#ifndef __ASMARM_TLS_H
+#define __ASMARM_TLS_H
+
+#include <linux/compiler.h>
+#include <asm/thread_info.h>
+
+#ifdef __ASSEMBLY__
+#include <asm/asm-offsets.h>
+	.macro switch_tls_none, base, tp, tpuser, tmp1, tmp2
+	.endm
+
+	.macro switch_tls_v6k, base, tp, tpuser, tmp1, tmp2
+	mrc	p15, 0, \tmp2, c13, c0, 2	@ get the user r/w register
+	mcr	p15, 0, \tp, c13, c0, 3		@ set TLS register
+	mcr	p15, 0, \tpuser, c13, c0, 2	@ and the user r/w register
+	str	\tmp2, [\base, #TI_TP_VALUE + 4] @ save it
+	.endm
+
+	.macro switch_tls_v6, base, tp, tpuser, tmp1, tmp2
+	ldr	\tmp1, =elf_hwcap
+	ldr	\tmp1, [\tmp1, #0]
+	mov	\tmp2, #0xffff0fff
+	tst	\tmp1, #HWCAP_TLS		@ hardware TLS available?
+	streq	\tp, [\tmp2, #-15]		@ set TLS value at 0xffff0ff0
+	mrcne	p15, 0, \tmp2, c13, c0, 2	@ get the user r/w register
+	mcrne	p15, 0, \tp, c13, c0, 3		@ yes, set TLS register
+	mcrne	p15, 0, \tpuser, c13, c0, 2	@ set user r/w register
+	strne	\tmp2, [\base, #TI_TP_VALUE + 4] @ save it
+	.endm
+
+	.macro switch_tls_software, base, tp, tpuser, tmp1, tmp2
+	mov	\tmp1, #0xffff0fff
+	str	\tp, [\tmp1, #-15]		@ set TLS value at 0xffff0ff0
+	.endm
+#endif
+
+#ifdef CONFIG_TLS_REG_EMUL
+#define tls_emu		1
+#define has_tls_reg		1
+#define switch_tls	switch_tls_none
+#elif defined(CONFIG_CPU_V6)
+#define tls_emu		0
+#define has_tls_reg		(elf_hwcap & HWCAP_TLS)
+#define switch_tls	switch_tls_v6
+#elif defined(CONFIG_CPU_32v6K)
+#define tls_emu		0
+#define has_tls_reg		1
+#define switch_tls	switch_tls_v6k
+#else
+#define tls_emu		0
+#define has_tls_reg		0
+#define switch_tls	switch_tls_software
+#endif
+
+#ifndef __ASSEMBLY__
+
+static inline void set_tls(unsigned long val)
+{
+	struct thread_info *thread;
+
+	thread = current_thread_info();
+
+	thread->tp_value[0] = val;
+
+	/*
+	 * This code runs with preemption enabled and therefore must
+	 * be reentrant with respect to switch_tls.
+	 *
+	 * We need to ensure ordering between the shadow state and the
+	 * hardware state, so that we don't corrupt the hardware state
+	 * with a stale shadow state during context switch.
+	 *
+	 * If we're preempted here, switch_tls will load TPIDRURO from
+	 * thread_info upon resuming execution and the following mcr
+	 * is merely redundant.
+	 */
+	barrier();
+
+	if (!tls_emu) {
+		if (has_tls_reg) {
+			asm("mcr p15, 0, %0, c13, c0, 3"
+			    : : "r" (val));
+		} else {
+#ifdef CONFIG_KUSER_HELPERS
+			/*
+			 * User space must never try to access this
+			 * directly.  Expect your app to break
+			 * eventually if you do so.  The user helper
+			 * at 0xffff0fe0 must be used instead.  (see
+			 * entry-armv.S for details)
+			 */
+			*((unsigned int *)0xffff0ff0) = val;
+#endif
+		}
+
+	}
+}
+
+static inline unsigned long get_tpuser(void)
+{
+	unsigned long reg = 0;
+
+	if (has_tls_reg && !tls_emu)
+		__asm__("mrc p15, 0, %0, c13, c0, 2" : "=r" (reg));
+
+	return reg;
+}
+
+static inline void set_tpuser(unsigned long val)
+{
+	/* Since TPIDRURW is fully context-switched (unlike TPIDRURO),
+	 * we need not update thread_info.
+	 */
+	if (has_tls_reg && !tls_emu) {
+		asm("mcr p15, 0, %0, c13, c0, 2"
+		    : : "r" (val));
+	}
+}
+
+static inline void flush_tls(void)
+{
+	set_tls(0);
+	set_tpuser(0);
+}
+
+#endif
+#endif	/* __ASMARM_TLS_H */
diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h
new file mode 100644
index 000000000..2fe85fff5
--- /dev/null
+++ b/arch/arm/include/asm/topology.h
@@ -0,0 +1,36 @@
+#ifndef _ASM_ARM_TOPOLOGY_H
+#define _ASM_ARM_TOPOLOGY_H
+
+#ifdef CONFIG_ARM_CPU_TOPOLOGY
+
+#include <linux/cpumask.h>
+
+struct cputopo_arm {
+	int thread_id;
+	int core_id;
+	int socket_id;
+	cpumask_t thread_sibling;
+	cpumask_t core_sibling;
+};
+
+extern struct cputopo_arm cpu_topology[NR_CPUS];
+
+#define topology_physical_package_id(cpu)	(cpu_topology[cpu].socket_id)
+#define topology_core_id(cpu)		(cpu_topology[cpu].core_id)
+#define topology_core_cpumask(cpu)	(&cpu_topology[cpu].core_sibling)
+#define topology_thread_cpumask(cpu)	(&cpu_topology[cpu].thread_sibling)
+
+void init_cpu_topology(void);
+void store_cpu_topology(unsigned int cpuid);
+const struct cpumask *cpu_coregroup_mask(int cpu);
+
+#else
+
+static inline void init_cpu_topology(void) { }
+static inline void store_cpu_topology(unsigned int cpuid) { }
+
+#endif
+
+#include <asm-generic/topology.h>
+
+#endif /* _ASM_ARM_TOPOLOGY_H */
diff --git a/arch/arm/include/asm/traps.h b/arch/arm/include/asm/traps.h
new file mode 100644
index 000000000..f555bb366
--- /dev/null
+++ b/arch/arm/include/asm/traps.h
@@ -0,0 +1,55 @@
+#ifndef _ASMARM_TRAP_H
+#define _ASMARM_TRAP_H
+
+#include <linux/list.h>
+
+struct pt_regs;
+struct task_struct;
+
+struct undef_hook {
+	struct list_head node;
+	u32 instr_mask;
+	u32 instr_val;
+	u32 cpsr_mask;
+	u32 cpsr_val;
+	int (*fn)(struct pt_regs *regs, unsigned int instr);
+};
+
+void register_undef_hook(struct undef_hook *hook);
+void unregister_undef_hook(struct undef_hook *hook);
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+static inline int __in_irqentry_text(unsigned long ptr)
+{
+	extern char __irqentry_text_start[];
+	extern char __irqentry_text_end[];
+
+	return ptr >= (unsigned long)&__irqentry_text_start &&
+	       ptr < (unsigned long)&__irqentry_text_end;
+}
+#else
+static inline int __in_irqentry_text(unsigned long ptr)
+{
+	return 0;
+}
+#endif
+
+static inline int in_exception_text(unsigned long ptr)
+{
+	extern char __exception_text_start[];
+	extern char __exception_text_end[];
+	int in;
+
+	in = ptr >= (unsigned long)&__exception_text_start &&
+	     ptr < (unsigned long)&__exception_text_end;
+
+	return in ? : __in_irqentry_text(ptr);
+}
+
+extern void __init early_trap_init(void *);
+extern void dump_backtrace_entry(unsigned long where, unsigned long from, unsigned long frame);
+extern void ptrace_break(struct task_struct *tsk, struct pt_regs *regs);
+
+extern void *vectors_page;
+
+#endif
diff --git a/arch/arm/include/asm/trusted_foundations.h b/arch/arm/include/asm/trusted_foundations.h
new file mode 100644
index 000000000..624e1d436
--- /dev/null
+++ b/arch/arm/include/asm/trusted_foundations.h
@@ -0,0 +1,74 @@
+/*
+ * Copyright (c) 2013, NVIDIA Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * 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.
+ */
+
+/*
+ * Support for the Trusted Foundations secure monitor.
+ *
+ * Trusted Foundation comes active on some ARM consumer devices (most
+ * Tegra-based devices sold on the market are concerned). Such devices can only
+ * perform some basic operations, like setting the CPU reset vector, through
+ * SMC calls to the secure monitor. The calls are completely specific to
+ * Trusted Foundations, and do *not* follow the SMC calling convention or the
+ * PSCI standard.
+ */
+
+#ifndef __ASM_ARM_TRUSTED_FOUNDATIONS_H
+#define __ASM_ARM_TRUSTED_FOUNDATIONS_H
+
+#include <linux/kconfig.h>
+#include <linux/printk.h>
+#include <linux/bug.h>
+#include <linux/of.h>
+#include <linux/cpu.h>
+#include <linux/smp.h>
+
+struct trusted_foundations_platform_data {
+	unsigned int version_major;
+	unsigned int version_minor;
+};
+
+#if IS_ENABLED(CONFIG_TRUSTED_FOUNDATIONS)
+
+void register_trusted_foundations(struct trusted_foundations_platform_data *pd);
+void of_register_trusted_foundations(void);
+
+#else /* CONFIG_TRUSTED_FOUNDATIONS */
+
+static inline void register_trusted_foundations(
+				   struct trusted_foundations_platform_data *pd)
+{
+	/*
+	 * If the system requires TF and we cannot provide it, continue booting
+	 * but disable features that cannot be provided.
+	 */
+	pr_err("No support for Trusted Foundations, continuing in degraded mode.\n");
+	pr_err("Secondary processors as well as CPU PM will be disabled.\n");
+#if IS_ENABLED(CONFIG_SMP)
+	setup_max_cpus = 0;
+#endif
+	cpu_idle_poll_ctrl(true);
+}
+
+static inline void of_register_trusted_foundations(void)
+{
+	/*
+	 * If we find the target should enable TF but does not support it,
+	 * fail as the system won't be able to do much anyway
+	 */
+	if (of_find_compatible_node(NULL, NULL, "tlm,trusted-foundations"))
+		register_trusted_foundations(NULL);
+}
+#endif /* CONFIG_TRUSTED_FOUNDATIONS */
+
+#endif
diff --git a/arch/arm/include/asm/types.h b/arch/arm/include/asm/types.h
new file mode 100644
index 000000000..a53cdb8f0
--- /dev/null
+++ b/arch/arm/include/asm/types.h
@@ -0,0 +1,40 @@
+#ifndef _ASM_TYPES_H
+#define _ASM_TYPES_H
+
+#include <asm-generic/int-ll64.h>
+
+/*
+ * The C99 types uintXX_t that are usually defined in 'stdint.h' are not as
+ * unambiguous on ARM as you would expect. For the types below, there is a
+ * difference on ARM between GCC built for bare metal ARM, GCC built for glibc
+ * and the kernel itself, which results in build errors if you try to build with
+ * -ffreestanding and include 'stdint.h' (such as when you include 'arm_neon.h'
+ * in order to use NEON intrinsics)
+ *
+ * As the typedefs for these types in 'stdint.h' are based on builtin defines
+ * supplied by GCC, we can tweak these to align with the kernel's idea of those
+ * types, so 'linux/types.h' and 'stdint.h' can be safely included from the same
+ * source file (provided that -ffreestanding is used).
+ *
+ *                    int32_t         uint32_t               uintptr_t
+ * bare metal GCC     long            unsigned long          unsigned int
+ * glibc GCC          int             unsigned int           unsigned int
+ * kernel             int             unsigned int           unsigned long
+ */
+
+#ifdef __INT32_TYPE__
+#undef __INT32_TYPE__
+#define __INT32_TYPE__		int
+#endif
+
+#ifdef __UINT32_TYPE__
+#undef __UINT32_TYPE__
+#define __UINT32_TYPE__	unsigned int
+#endif
+
+#ifdef __UINTPTR_TYPE__
+#undef __UINTPTR_TYPE__
+#define __UINTPTR_TYPE__	unsigned long
+#endif
+
+#endif /* _ASM_TYPES_H */
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
new file mode 100644
index 000000000..74b17d09e
--- /dev/null
+++ b/arch/arm/include/asm/uaccess.h
@@ -0,0 +1,519 @@
+/*
+ *  arch/arm/include/asm/uaccess.h
+ *
+ * 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.
+ */
+#ifndef _ASMARM_UACCESS_H
+#define _ASMARM_UACCESS_H
+
+/*
+ * User space memory access functions
+ */
+#include <linux/string.h>
+#include <linux/thread_info.h>
+#include <asm/errno.h>
+#include <asm/memory.h>
+#include <asm/domain.h>
+#include <asm/unified.h>
+#include <asm/compiler.h>
+
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+#include <asm-generic/uaccess-unaligned.h>
+#else
+#define __get_user_unaligned __get_user
+#define __put_user_unaligned __put_user
+#endif
+
+#define VERIFY_READ 0
+#define VERIFY_WRITE 1
+
+/*
+ * The exception table consists of pairs of addresses: the first is the
+ * address of an instruction that is allowed to fault, and the second is
+ * the address at which the program should continue.  No registers are
+ * modified, so it is entirely up to the continuation code to figure out
+ * what to do.
+ *
+ * All the routines below use bits of fixup code that are out of line
+ * with the main instruction path.  This means when everything is well,
+ * we don't even have to jump over them.  Further, they do not intrude
+ * on our cache or tlb entries.
+ */
+
+struct exception_table_entry
+{
+	unsigned long insn, fixup;
+};
+
+extern int fixup_exception(struct pt_regs *regs);
+
+/*
+ * These two are intentionally not defined anywhere - if the kernel
+ * code generates any references to them, that's a bug.
+ */
+extern int __get_user_bad(void);
+extern int __put_user_bad(void);
+
+/*
+ * Note that this is actually 0x1,0000,0000
+ */
+#define KERNEL_DS	0x00000000
+#define get_ds()	(KERNEL_DS)
+
+#ifdef CONFIG_MMU
+
+#define USER_DS		TASK_SIZE
+#define get_fs()	(current_thread_info()->addr_limit)
+
+static inline void set_fs(mm_segment_t fs)
+{
+	current_thread_info()->addr_limit = fs;
+	modify_domain(DOMAIN_KERNEL, fs ? DOMAIN_CLIENT : DOMAIN_MANAGER);
+}
+
+#define segment_eq(a, b)	((a) == (b))
+
+#define __addr_ok(addr) ({ \
+	unsigned long flag; \
+	__asm__("cmp %2, %0; movlo %0, #0" \
+		: "=&r" (flag) \
+		: "0" (current_thread_info()->addr_limit), "r" (addr) \
+		: "cc"); \
+	(flag == 0); })
+
+/* We use 33-bit arithmetic here... */
+#define __range_ok(addr, size) ({ \
+	unsigned long flag, roksum; \
+	__chk_user_ptr(addr);	\
+	__asm__("adds %1, %2, %3; sbcccs %1, %1, %0; movcc %0, #0" \
+		: "=&r" (flag), "=&r" (roksum) \
+		: "r" (addr), "Ir" (size), "0" (current_thread_info()->addr_limit) \
+		: "cc"); \
+	flag; })
+
+/*
+ * Single-value transfer routines.  They automatically use the right
+ * size if we just have the right pointer type.  Note that the functions
+ * which read from user space (*get_*) need to take care not to leak
+ * kernel data even if the calling code is buggy and fails to check
+ * the return value.  This means zeroing out the destination variable
+ * or buffer on error.  Normally this is done out of line by the
+ * fixup code, but there are a few places where it intrudes on the
+ * main code path.  When we only write to user space, there is no
+ * problem.
+ */
+extern int __get_user_1(void *);
+extern int __get_user_2(void *);
+extern int __get_user_4(void *);
+extern int __get_user_32t_8(void *);
+extern int __get_user_8(void *);
+extern int __get_user_64t_1(void *);
+extern int __get_user_64t_2(void *);
+extern int __get_user_64t_4(void *);
+
+#define __GUP_CLOBBER_1	"lr", "cc"
+#ifdef CONFIG_CPU_USE_DOMAINS
+#define __GUP_CLOBBER_2	"ip", "lr", "cc"
+#else
+#define __GUP_CLOBBER_2 "lr", "cc"
+#endif
+#define __GUP_CLOBBER_4	"lr", "cc"
+#define __GUP_CLOBBER_32t_8 "lr", "cc"
+#define __GUP_CLOBBER_8	"lr", "cc"
+
+#define __get_user_x(__r2, __p, __e, __l, __s)				\
+	   __asm__ __volatile__ (					\
+		__asmeq("%0", "r0") __asmeq("%1", "r2")			\
+		__asmeq("%3", "r1")					\
+		"bl	__get_user_" #__s				\
+		: "=&r" (__e), "=r" (__r2)				\
+		: "0" (__p), "r" (__l)					\
+		: __GUP_CLOBBER_##__s)
+
+/* narrowing a double-word get into a single 32bit word register: */
+#ifdef __ARMEB__
+#define __get_user_x_32t(__r2, __p, __e, __l, __s)			\
+	__get_user_x(__r2, __p, __e, __l, 32t_8)
+#else
+#define __get_user_x_32t __get_user_x
+#endif
+
+/*
+ * storing result into proper least significant word of 64bit target var,
+ * different only for big endian case where 64 bit __r2 lsw is r3:
+ */
+#ifdef __ARMEB__
+#define __get_user_x_64t(__r2, __p, __e, __l, __s)		        \
+	   __asm__ __volatile__ (					\
+		__asmeq("%0", "r0") __asmeq("%1", "r2")			\
+		__asmeq("%3", "r1")					\
+		"bl	__get_user_64t_" #__s				\
+		: "=&r" (__e), "=r" (__r2)				\
+		: "0" (__p), "r" (__l)					\
+		: __GUP_CLOBBER_##__s)
+#else
+#define __get_user_x_64t __get_user_x
+#endif
+
+
+#define __get_user_check(x, p)						\
+	({								\
+		unsigned long __limit = current_thread_info()->addr_limit - 1; \
+		register const typeof(*(p)) __user *__p asm("r0") = (p);\
+		register typeof(x) __r2 asm("r2");			\
+		register unsigned long __l asm("r1") = __limit;		\
+		register int __e asm("r0");				\
+		switch (sizeof(*(__p))) {				\
+		case 1:							\
+			if (sizeof((x)) >= 8)				\
+				__get_user_x_64t(__r2, __p, __e, __l, 1); \
+			else						\
+				__get_user_x(__r2, __p, __e, __l, 1);	\
+			break;						\
+		case 2:							\
+			if (sizeof((x)) >= 8)				\
+				__get_user_x_64t(__r2, __p, __e, __l, 2); \
+			else						\
+				__get_user_x(__r2, __p, __e, __l, 2);	\
+			break;						\
+		case 4:							\
+			if (sizeof((x)) >= 8)				\
+				__get_user_x_64t(__r2, __p, __e, __l, 4); \
+			else						\
+				__get_user_x(__r2, __p, __e, __l, 4);	\
+			break;						\
+		case 8:							\
+			if (sizeof((x)) < 8)				\
+				__get_user_x_32t(__r2, __p, __e, __l, 4); \
+			else						\
+				__get_user_x(__r2, __p, __e, __l, 8);	\
+			break;						\
+		default: __e = __get_user_bad(); break;			\
+		}							\
+		x = (typeof(*(p))) __r2;				\
+		__e;							\
+	})
+
+#define get_user(x, p)							\
+	({								\
+		might_fault();						\
+		__get_user_check(x, p);					\
+	 })
+
+extern int __put_user_1(void *, unsigned int);
+extern int __put_user_2(void *, unsigned int);
+extern int __put_user_4(void *, unsigned int);
+extern int __put_user_8(void *, unsigned long long);
+
+#define __put_user_x(__r2, __p, __e, __l, __s)				\
+	   __asm__ __volatile__ (					\
+		__asmeq("%0", "r0") __asmeq("%2", "r2")			\
+		__asmeq("%3", "r1")					\
+		"bl	__put_user_" #__s				\
+		: "=&r" (__e)						\
+		: "0" (__p), "r" (__r2), "r" (__l)			\
+		: "ip", "lr", "cc")
+
+#define __put_user_check(x, p)						\
+	({								\
+		unsigned long __limit = current_thread_info()->addr_limit - 1; \
+		const typeof(*(p)) __user *__tmp_p = (p);		\
+		register const typeof(*(p)) __r2 asm("r2") = (x);	\
+		register const typeof(*(p)) __user *__p asm("r0") = __tmp_p; \
+		register unsigned long __l asm("r1") = __limit;		\
+		register int __e asm("r0");				\
+		switch (sizeof(*(__p))) {				\
+		case 1:							\
+			__put_user_x(__r2, __p, __e, __l, 1);		\
+			break;						\
+		case 2:							\
+			__put_user_x(__r2, __p, __e, __l, 2);		\
+			break;						\
+		case 4:							\
+			__put_user_x(__r2, __p, __e, __l, 4);		\
+			break;						\
+		case 8:							\
+			__put_user_x(__r2, __p, __e, __l, 8);		\
+			break;						\
+		default: __e = __put_user_bad(); break;			\
+		}							\
+		__e;							\
+	})
+
+#define put_user(x, p)							\
+	({								\
+		might_fault();						\
+		__put_user_check(x, p);					\
+	 })
+
+#else /* CONFIG_MMU */
+
+/*
+ * uClinux has only one addr space, so has simplified address limits.
+ */
+#define USER_DS			KERNEL_DS
+
+#define segment_eq(a, b)		(1)
+#define __addr_ok(addr)		((void)(addr), 1)
+#define __range_ok(addr, size)	((void)(addr), 0)
+#define get_fs()		(KERNEL_DS)
+
+static inline void set_fs(mm_segment_t fs)
+{
+}
+
+#define get_user(x, p)	__get_user(x, p)
+#define put_user(x, p)	__put_user(x, p)
+
+#endif /* CONFIG_MMU */
+
+#define access_ok(type, addr, size)	(__range_ok(addr, size) == 0)
+
+#define user_addr_max() \
+	(segment_eq(get_fs(), KERNEL_DS) ? ~0UL : get_fs())
+
+/*
+ * The "__xxx" versions of the user access functions do not verify the
+ * address space - it must have been done previously with a separate
+ * "access_ok()" call.
+ *
+ * The "xxx_error" versions set the third argument to EFAULT if an
+ * error occurs, and leave it unchanged on success.  Note that these
+ * versions are void (ie, don't return a value as such).
+ */
+#define __get_user(x, ptr)						\
+({									\
+	long __gu_err = 0;						\
+	__get_user_err((x), (ptr), __gu_err);				\
+	__gu_err;							\
+})
+
+#define __get_user_error(x, ptr, err)					\
+({									\
+	__get_user_err((x), (ptr), err);				\
+	(void) 0;							\
+})
+
+#define __get_user_err(x, ptr, err)					\
+do {									\
+	unsigned long __gu_addr = (unsigned long)(ptr);			\
+	unsigned long __gu_val;						\
+	__chk_user_ptr(ptr);						\
+	might_fault();							\
+	switch (sizeof(*(ptr))) {					\
+	case 1:	__get_user_asm_byte(__gu_val, __gu_addr, err);	break;	\
+	case 2:	__get_user_asm_half(__gu_val, __gu_addr, err);	break;	\
+	case 4:	__get_user_asm_word(__gu_val, __gu_addr, err);	break;	\
+	default: (__gu_val) = __get_user_bad();				\
+	}								\
+	(x) = (__typeof__(*(ptr)))__gu_val;				\
+} while (0)
+
+#define __get_user_asm_byte(x, addr, err)			\
+	__asm__ __volatile__(					\
+	"1:	" TUSER(ldrb) "	%1,[%2],#0\n"			\
+	"2:\n"							\
+	"	.pushsection .text.fixup,\"ax\"\n"		\
+	"	.align	2\n"					\
+	"3:	mov	%0, %3\n"				\
+	"	mov	%1, #0\n"				\
+	"	b	2b\n"					\
+	"	.popsection\n"					\
+	"	.pushsection __ex_table,\"a\"\n"		\
+	"	.align	3\n"					\
+	"	.long	1b, 3b\n"				\
+	"	.popsection"					\
+	: "+r" (err), "=&r" (x)					\
+	: "r" (addr), "i" (-EFAULT)				\
+	: "cc")
+
+#ifndef __ARMEB__
+#define __get_user_asm_half(x, __gu_addr, err)			\
+({								\
+	unsigned long __b1, __b2;				\
+	__get_user_asm_byte(__b1, __gu_addr, err);		\
+	__get_user_asm_byte(__b2, __gu_addr + 1, err);		\
+	(x) = __b1 | (__b2 << 8);				\
+})
+#else
+#define __get_user_asm_half(x, __gu_addr, err)			\
+({								\
+	unsigned long __b1, __b2;				\
+	__get_user_asm_byte(__b1, __gu_addr, err);		\
+	__get_user_asm_byte(__b2, __gu_addr + 1, err);		\
+	(x) = (__b1 << 8) | __b2;				\
+})
+#endif
+
+#define __get_user_asm_word(x, addr, err)			\
+	__asm__ __volatile__(					\
+	"1:	" TUSER(ldr) "	%1,[%2],#0\n"			\
+	"2:\n"							\
+	"	.pushsection .text.fixup,\"ax\"\n"		\
+	"	.align	2\n"					\
+	"3:	mov	%0, %3\n"				\
+	"	mov	%1, #0\n"				\
+	"	b	2b\n"					\
+	"	.popsection\n"					\
+	"	.pushsection __ex_table,\"a\"\n"		\
+	"	.align	3\n"					\
+	"	.long	1b, 3b\n"				\
+	"	.popsection"					\
+	: "+r" (err), "=&r" (x)					\
+	: "r" (addr), "i" (-EFAULT)				\
+	: "cc")
+
+#define __put_user(x, ptr)						\
+({									\
+	long __pu_err = 0;						\
+	__put_user_err((x), (ptr), __pu_err);				\
+	__pu_err;							\
+})
+
+#define __put_user_error(x, ptr, err)					\
+({									\
+	__put_user_err((x), (ptr), err);				\
+	(void) 0;							\
+})
+
+#define __put_user_err(x, ptr, err)					\
+do {									\
+	unsigned long __pu_addr = (unsigned long)(ptr);			\
+	__typeof__(*(ptr)) __pu_val = (x);				\
+	__chk_user_ptr(ptr);						\
+	might_fault();							\
+	switch (sizeof(*(ptr))) {					\
+	case 1: __put_user_asm_byte(__pu_val, __pu_addr, err);	break;	\
+	case 2: __put_user_asm_half(__pu_val, __pu_addr, err);	break;	\
+	case 4: __put_user_asm_word(__pu_val, __pu_addr, err);	break;	\
+	case 8:	__put_user_asm_dword(__pu_val, __pu_addr, err);	break;	\
+	default: __put_user_bad();					\
+	}								\
+} while (0)
+
+#define __put_user_asm_byte(x, __pu_addr, err)			\
+	__asm__ __volatile__(					\
+	"1:	" TUSER(strb) "	%1,[%2],#0\n"			\
+	"2:\n"							\
+	"	.pushsection .text.fixup,\"ax\"\n"		\
+	"	.align	2\n"					\
+	"3:	mov	%0, %3\n"				\
+	"	b	2b\n"					\
+	"	.popsection\n"					\
+	"	.pushsection __ex_table,\"a\"\n"		\
+	"	.align	3\n"					\
+	"	.long	1b, 3b\n"				\
+	"	.popsection"					\
+	: "+r" (err)						\
+	: "r" (x), "r" (__pu_addr), "i" (-EFAULT)		\
+	: "cc")
+
+#ifndef __ARMEB__
+#define __put_user_asm_half(x, __pu_addr, err)			\
+({								\
+	unsigned long __temp = (__force unsigned long)(x);	\
+	__put_user_asm_byte(__temp, __pu_addr, err);		\
+	__put_user_asm_byte(__temp >> 8, __pu_addr + 1, err);	\
+})
+#else
+#define __put_user_asm_half(x, __pu_addr, err)			\
+({								\
+	unsigned long __temp = (__force unsigned long)(x);	\
+	__put_user_asm_byte(__temp >> 8, __pu_addr, err);	\
+	__put_user_asm_byte(__temp, __pu_addr + 1, err);	\
+})
+#endif
+
+#define __put_user_asm_word(x, __pu_addr, err)			\
+	__asm__ __volatile__(					\
+	"1:	" TUSER(str) "	%1,[%2],#0\n"			\
+	"2:\n"							\
+	"	.pushsection .text.fixup,\"ax\"\n"		\
+	"	.align	2\n"					\
+	"3:	mov	%0, %3\n"				\
+	"	b	2b\n"					\
+	"	.popsection\n"					\
+	"	.pushsection __ex_table,\"a\"\n"		\
+	"	.align	3\n"					\
+	"	.long	1b, 3b\n"				\
+	"	.popsection"					\
+	: "+r" (err)						\
+	: "r" (x), "r" (__pu_addr), "i" (-EFAULT)		\
+	: "cc")
+
+#ifndef __ARMEB__
+#define	__reg_oper0	"%R2"
+#define	__reg_oper1	"%Q2"
+#else
+#define	__reg_oper0	"%Q2"
+#define	__reg_oper1	"%R2"
+#endif
+
+#define __put_user_asm_dword(x, __pu_addr, err)			\
+	__asm__ __volatile__(					\
+ ARM(	"1:	" TUSER(str) "	" __reg_oper1 ", [%1], #4\n"	) \
+ ARM(	"2:	" TUSER(str) "	" __reg_oper0 ", [%1]\n"	) \
+ THUMB(	"1:	" TUSER(str) "	" __reg_oper1 ", [%1]\n"	) \
+ THUMB(	"2:	" TUSER(str) "	" __reg_oper0 ", [%1, #4]\n"	) \
+	"3:\n"							\
+	"	.pushsection .text.fixup,\"ax\"\n"		\
+	"	.align	2\n"					\
+	"4:	mov	%0, %3\n"				\
+	"	b	3b\n"					\
+	"	.popsection\n"					\
+	"	.pushsection __ex_table,\"a\"\n"		\
+	"	.align	3\n"					\
+	"	.long	1b, 4b\n"				\
+	"	.long	2b, 4b\n"				\
+	"	.popsection"					\
+	: "+r" (err), "+r" (__pu_addr)				\
+	: "r" (x), "i" (-EFAULT)				\
+	: "cc")
+
+
+#ifdef CONFIG_MMU
+extern unsigned long __must_check __copy_from_user(void *to, const void __user *from, unsigned long n);
+extern unsigned long __must_check __copy_to_user(void __user *to, const void *from, unsigned long n);
+extern unsigned long __must_check __copy_to_user_std(void __user *to, const void *from, unsigned long n);
+extern unsigned long __must_check __clear_user(void __user *addr, unsigned long n);
+extern unsigned long __must_check __clear_user_std(void __user *addr, unsigned long n);
+#else
+#define __copy_from_user(to, from, n)	(memcpy(to, (void __force *)from, n), 0)
+#define __copy_to_user(to, from, n)	(memcpy((void __force *)to, from, n), 0)
+#define __clear_user(addr, n)		(memset((void __force *)addr, 0, n), 0)
+#endif
+
+static inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+	if (access_ok(VERIFY_READ, from, n))
+		n = __copy_from_user(to, from, n);
+	else /* security hole - plug it */
+		memset(to, 0, n);
+	return n;
+}
+
+static inline unsigned long __must_check copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+	if (access_ok(VERIFY_WRITE, to, n))
+		n = __copy_to_user(to, from, n);
+	return n;
+}
+
+#define __copy_to_user_inatomic __copy_to_user
+#define __copy_from_user_inatomic __copy_from_user
+
+static inline unsigned long __must_check clear_user(void __user *to, unsigned long n)
+{
+	if (access_ok(VERIFY_WRITE, to, n))
+		n = __clear_user(to, n);
+	return n;
+}
+
+extern long strncpy_from_user(char *dest, const char __user *src, long count);
+
+extern __must_check long strlen_user(const char __user *str);
+extern __must_check long strnlen_user(const char __user *str, long n);
+
+#endif /* _ASMARM_UACCESS_H */
diff --git a/arch/arm/include/asm/ucontext.h b/arch/arm/include/asm/ucontext.h
new file mode 100644
index 000000000..14749aec9
--- /dev/null
+++ b/arch/arm/include/asm/ucontext.h
@@ -0,0 +1,102 @@
+#ifndef _ASMARM_UCONTEXT_H
+#define _ASMARM_UCONTEXT_H
+
+#include <asm/fpstate.h>
+
+/*
+ * struct sigcontext only has room for the basic registers, but struct
+ * ucontext now has room for all registers which need to be saved and
+ * restored.  Coprocessor registers are stored in uc_regspace.  Each
+ * coprocessor's saved state should start with a documented 32-bit magic
+ * number, followed by a 32-bit word giving the coproccesor's saved size.
+ * uc_regspace may be expanded if necessary, although this takes some
+ * coordination with glibc.
+ */
+
+struct ucontext {
+	unsigned long	  uc_flags;
+	struct ucontext  *uc_link;
+	stack_t		  uc_stack;
+	struct sigcontext uc_mcontext;
+	sigset_t	  uc_sigmask;
+	/* Allow for uc_sigmask growth.  Glibc uses a 1024-bit sigset_t.  */
+	int		  __unused[32 - (sizeof (sigset_t) / sizeof (int))];
+	/* Last for extensibility.  Eight byte aligned because some
+	   coprocessors require eight byte alignment.  */
+ 	unsigned long	  uc_regspace[128] __attribute__((__aligned__(8)));
+};
+
+#ifdef __KERNEL__
+
+/*
+ * Coprocessor save state.  The magic values and specific
+ * coprocessor's layouts are part of the userspace ABI.  Each one of
+ * these should be a multiple of eight bytes and aligned to eight
+ * bytes, to prevent unpredictable padding in the signal frame.
+ */
+
+#ifdef CONFIG_CRUNCH
+#define CRUNCH_MAGIC		0x5065cf03
+#define CRUNCH_STORAGE_SIZE	(CRUNCH_SIZE + 8)
+
+struct crunch_sigframe {
+	unsigned long	magic;
+	unsigned long	size;
+	struct crunch_state	storage;
+} __attribute__((__aligned__(8)));
+#endif
+
+#ifdef CONFIG_IWMMXT
+/* iwmmxt_area is 0x98 bytes long, preceded by 8 bytes of signature */
+#define IWMMXT_MAGIC		0x12ef842a
+#define IWMMXT_STORAGE_SIZE	(IWMMXT_SIZE + 8)
+
+struct iwmmxt_sigframe {
+	unsigned long	magic;
+	unsigned long	size;
+	struct iwmmxt_struct storage;
+} __attribute__((__aligned__(8)));
+#endif /* CONFIG_IWMMXT */
+
+#ifdef CONFIG_VFP
+#define VFP_MAGIC		0x56465001
+
+struct vfp_sigframe
+{
+	unsigned long		magic;
+	unsigned long		size;
+	struct user_vfp		ufp;
+	struct user_vfp_exc	ufp_exc;
+} __attribute__((__aligned__(8)));
+
+/*
+ *  8 byte for magic and size, 264 byte for ufp, 12 bytes for ufp_exc,
+ *  4 bytes padding.
+ */
+#define VFP_STORAGE_SIZE	sizeof(struct vfp_sigframe)
+
+#endif /* CONFIG_VFP */
+
+/*
+ * Auxiliary signal frame.  This saves stuff like FP state.
+ * The layout of this structure is not part of the user ABI,
+ * because the config options aren't.  uc_regspace is really
+ * one of these.
+ */
+struct aux_sigframe {
+#ifdef CONFIG_CRUNCH
+	struct crunch_sigframe	crunch;
+#endif
+#ifdef CONFIG_IWMMXT
+	struct iwmmxt_sigframe	iwmmxt;
+#endif
+#ifdef CONFIG_VFP
+	struct vfp_sigframe	vfp;
+#endif
+	/* Something that isn't a valid magic number for any coprocessor.  */
+	unsigned long		end_magic;
+} __attribute__((__aligned__(8)));
+
+#endif
+
+#endif /* !_ASMARM_UCONTEXT_H */
diff --git a/arch/arm/include/asm/unified.h b/arch/arm/include/asm/unified.h
new file mode 100644
index 000000000..200f9a7cd
--- /dev/null
+++ b/arch/arm/include/asm/unified.h
@@ -0,0 +1,142 @@
+/*
+ * include/asm-arm/unified.h - Unified Assembler Syntax helper macros
+ *
+ * Copyright (C) 2008 ARM Limited
+ *
+ * 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, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#ifndef __ASM_UNIFIED_H
+#define __ASM_UNIFIED_H
+
+#if defined(__ASSEMBLY__) && defined(CONFIG_ARM_ASM_UNIFIED)
+	.syntax unified
+#endif
+
+#ifdef CONFIG_CPU_V7M
+#define AR_CLASS(x...)
+#define M_CLASS(x...)	x
+#else
+#define AR_CLASS(x...)	x
+#define M_CLASS(x...)
+#endif
+
+#ifdef CONFIG_THUMB2_KERNEL
+
+#if __GNUC__ < 4
+#error Thumb-2 kernel requires gcc >= 4
+#endif
+
+/* The CPSR bit describing the instruction set (Thumb) */
+#define PSR_ISETSTATE	PSR_T_BIT
+
+#define ARM(x...)
+#define THUMB(x...)	x
+#ifdef __ASSEMBLY__
+#define W(instr)	instr.w
+#define BSYM(sym)	sym + 1
+#else
+#define WASM(instr)	#instr ".w"
+#endif
+
+#else	/* !CONFIG_THUMB2_KERNEL */
+
+/* The CPSR bit describing the instruction set (ARM) */
+#define PSR_ISETSTATE	0
+
+#define ARM(x...)	x
+#define THUMB(x...)
+#ifdef __ASSEMBLY__
+#define W(instr)	instr
+#define BSYM(sym)	sym
+#else
+#define WASM(instr)	#instr
+#endif
+
+#endif	/* CONFIG_THUMB2_KERNEL */
+
+#ifndef CONFIG_ARM_ASM_UNIFIED
+
+/*
+ * If the unified assembly syntax isn't used (in ARM mode), these
+ * macros expand to an empty string
+ */
+#ifdef __ASSEMBLY__
+	.macro	it, cond
+	.endm
+	.macro	itt, cond
+	.endm
+	.macro	ite, cond
+	.endm
+	.macro	ittt, cond
+	.endm
+	.macro	itte, cond
+	.endm
+	.macro	itet, cond
+	.endm
+	.macro	itee, cond
+	.endm
+	.macro	itttt, cond
+	.endm
+	.macro	ittte, cond
+	.endm
+	.macro	ittet, cond
+	.endm
+	.macro	ittee, cond
+	.endm
+	.macro	itett, cond
+	.endm
+	.macro	itete, cond
+	.endm
+	.macro	iteet, cond
+	.endm
+	.macro	iteee, cond
+	.endm
+#else	/* !__ASSEMBLY__ */
+__asm__(
+"	.macro	it, cond\n"
+"	.endm\n"
+"	.macro	itt, cond\n"
+"	.endm\n"
+"	.macro	ite, cond\n"
+"	.endm\n"
+"	.macro	ittt, cond\n"
+"	.endm\n"
+"	.macro	itte, cond\n"
+"	.endm\n"
+"	.macro	itet, cond\n"
+"	.endm\n"
+"	.macro	itee, cond\n"
+"	.endm\n"
+"	.macro	itttt, cond\n"
+"	.endm\n"
+"	.macro	ittte, cond\n"
+"	.endm\n"
+"	.macro	ittet, cond\n"
+"	.endm\n"
+"	.macro	ittee, cond\n"
+"	.endm\n"
+"	.macro	itett, cond\n"
+"	.endm\n"
+"	.macro	itete, cond\n"
+"	.endm\n"
+"	.macro	iteet, cond\n"
+"	.endm\n"
+"	.macro	iteee, cond\n"
+"	.endm\n");
+#endif	/* __ASSEMBLY__ */
+
+#endif	/* CONFIG_ARM_ASM_UNIFIED */
+
+#endif	/* !__ASM_UNIFIED_H */
diff --git a/arch/arm/include/asm/unistd.h b/arch/arm/include/asm/unistd.h
new file mode 100644
index 000000000..32640c431
--- /dev/null
+++ b/arch/arm/include/asm/unistd.h
@@ -0,0 +1,62 @@
+/*
+ *  arch/arm/include/asm/unistd.h
+ *
+ *  Copyright (C) 2001-2005 Russell King
+ *
+ * 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.
+ *
+ * Please forward _all_ changes to this file to rmk@arm.linux.org.uk,
+ * no matter what the change is.  Thanks!
+ */
+#ifndef __ASM_ARM_UNISTD_H
+#define __ASM_ARM_UNISTD_H
+
+#include <uapi/asm/unistd.h>
+
+/*
+ * This may need to be greater than __NR_last_syscall+1 in order to
+ * account for the padding in the syscall table
+ */
+#define __NR_syscalls  (388)
+
+/*
+ * *NOTE*: This is a ghost syscall private to the kernel.  Only the
+ * __kuser_cmpxchg code in entry-armv.S should be aware of its
+ * existence.  Don't ever use this from user code.
+ */
+#define __ARM_NR_cmpxchg		(__ARM_NR_BASE+0x00fff0)
+
+#define __ARCH_WANT_STAT64
+#define __ARCH_WANT_SYS_GETHOSTNAME
+#define __ARCH_WANT_SYS_PAUSE
+#define __ARCH_WANT_SYS_GETPGRP
+#define __ARCH_WANT_SYS_LLSEEK
+#define __ARCH_WANT_SYS_NICE
+#define __ARCH_WANT_SYS_SIGPENDING
+#define __ARCH_WANT_SYS_SIGPROCMASK
+#define __ARCH_WANT_SYS_OLD_MMAP
+#define __ARCH_WANT_SYS_OLD_SELECT
+
+#if !defined(CONFIG_AEABI) || defined(CONFIG_OABI_COMPAT)
+#define __ARCH_WANT_SYS_TIME
+#define __ARCH_WANT_SYS_IPC
+#define __ARCH_WANT_SYS_OLDUMOUNT
+#define __ARCH_WANT_SYS_ALARM
+#define __ARCH_WANT_SYS_UTIME
+#define __ARCH_WANT_SYS_OLD_GETRLIMIT
+#define __ARCH_WANT_OLD_READDIR
+#define __ARCH_WANT_SYS_SOCKETCALL
+#endif
+#define __ARCH_WANT_SYS_FORK
+#define __ARCH_WANT_SYS_VFORK
+#define __ARCH_WANT_SYS_CLONE
+
+/*
+ * Unimplemented (or alternatively implemented) syscalls
+ */
+#define __IGNORE_fadvise64_64
+#define __IGNORE_migrate_pages
+
+#endif /* __ASM_ARM_UNISTD_H */
diff --git a/arch/arm/include/asm/unwind.h b/arch/arm/include/asm/unwind.h
new file mode 100644
index 000000000..d1c3f3a71
--- /dev/null
+++ b/arch/arm/include/asm/unwind.h
@@ -0,0 +1,61 @@
+/*
+ * arch/arm/include/asm/unwind.h
+ *
+ * Copyright (C) 2008 ARM Limited
+ *
+ * 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, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#ifndef __ASM_UNWIND_H
+#define __ASM_UNWIND_H
+
+#ifndef __ASSEMBLY__
+
+/* Unwind reason code according the the ARM EABI documents */
+enum unwind_reason_code {
+	URC_OK = 0,			/* operation completed successfully */
+	URC_CONTINUE_UNWIND = 8,
+	URC_FAILURE = 9			/* unspecified failure of some kind */
+};
+
+struct unwind_idx {
+	unsigned long addr_offset;
+	unsigned long insn;
+};
+
+struct unwind_table {
+	struct list_head list;
+	const struct unwind_idx *start;
+	const struct unwind_idx *origin;
+	const struct unwind_idx *stop;
+	unsigned long begin_addr;
+	unsigned long end_addr;
+};
+
+extern struct unwind_table *unwind_table_add(unsigned long start,
+					     unsigned long size,
+					     unsigned long text_addr,
+					     unsigned long text_size);
+extern void unwind_table_del(struct unwind_table *tab);
+extern void unwind_backtrace(struct pt_regs *regs, struct task_struct *tsk);
+
+#endif	/* !__ASSEMBLY__ */
+
+#ifdef CONFIG_ARM_UNWIND
+#define UNWIND(code...)		code
+#else
+#define UNWIND(code...)
+#endif
+
+#endif	/* __ASM_UNWIND_H */
diff --git a/arch/arm/include/asm/uprobes.h b/arch/arm/include/asm/uprobes.h
new file mode 100644
index 000000000..9472c20b7
--- /dev/null
+++ b/arch/arm/include/asm/uprobes.h
@@ -0,0 +1,45 @@
+/*
+ * Copyright (C) 2012 Rabin Vincent <rabin at rab.in>
+ *
+ * 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.
+ */
+
+#ifndef _ASM_UPROBES_H
+#define _ASM_UPROBES_H
+
+#include <asm/probes.h>
+#include <asm/opcodes.h>
+
+typedef u32 uprobe_opcode_t;
+
+#define MAX_UINSN_BYTES		4
+#define UPROBE_XOL_SLOT_BYTES	64
+
+#define UPROBE_SWBP_ARM_INSN	0xe7f001f9
+#define UPROBE_SS_ARM_INSN	0xe7f001fa
+#define UPROBE_SWBP_INSN	__opcode_to_mem_arm(UPROBE_SWBP_ARM_INSN)
+#define UPROBE_SWBP_INSN_SIZE	4
+
+struct arch_uprobe_task {
+	u32 backup;
+	unsigned long	saved_trap_no;
+};
+
+struct arch_uprobe {
+	u8 insn[MAX_UINSN_BYTES];
+	unsigned long ixol[2];
+	uprobe_opcode_t bpinsn;
+	bool simulate;
+	u32 pcreg;
+	void (*prehandler)(struct arch_uprobe *auprobe,
+			   struct arch_uprobe_task *autask,
+			   struct pt_regs *regs);
+	void (*posthandler)(struct arch_uprobe *auprobe,
+			    struct arch_uprobe_task *autask,
+			    struct pt_regs *regs);
+	struct arch_probes_insn asi;
+};
+
+#endif
diff --git a/arch/arm/include/asm/user.h b/arch/arm/include/asm/user.h
new file mode 100644
index 000000000..35917b3a9
--- /dev/null
+++ b/arch/arm/include/asm/user.h
@@ -0,0 +1,103 @@
+#ifndef _ARM_USER_H
+#define _ARM_USER_H
+
+#include <asm/page.h>
+#include <asm/ptrace.h>
+/* Core file format: The core file is written in such a way that gdb
+   can understand it and provide useful information to the user (under
+   linux we use the 'trad-core' bfd).  There are quite a number of
+   obstacles to being able to view the contents of the floating point
+   registers, and until these are solved you will not be able to view the
+   contents of them.  Actually, you can read in the core file and look at
+   the contents of the user struct to find out what the floating point
+   registers contain.
+   The actual file contents are as follows:
+   UPAGE: 1 page consisting of a user struct that tells gdb what is present
+   in the file.  Directly after this is a copy of the task_struct, which
+   is currently not used by gdb, but it may come in useful at some point.
+   All of the registers are stored as part of the upage.  The upage should
+   always be only one page.
+   DATA: The data area is stored.  We use current->end_text to
+   current->brk to pick up all of the user variables, plus any memory
+   that may have been malloced.  No attempt is made to determine if a page
+   is demand-zero or if a page is totally unused, we just cover the entire
+   range.  All of the addresses are rounded in such a way that an integral
+   number of pages is written.
+   STACK: We need the stack information in order to get a meaningful
+   backtrace.  We need to write the data from (esp) to
+   current->start_stack, so we round each of these off in order to be able
+   to write an integer number of pages.
+   The minimum core file size is 3 pages, or 12288 bytes.
+*/
+
+struct user_fp {
+	struct fp_reg {
+		unsigned int sign1:1;
+		unsigned int unused:15;
+		unsigned int sign2:1;
+		unsigned int exponent:14;
+		unsigned int j:1;
+		unsigned int mantissa1:31;
+		unsigned int mantissa0:32;
+	} fpregs[8];
+	unsigned int fpsr:32;
+	unsigned int fpcr:32;
+	unsigned char ftype[8];
+	unsigned int init_flag;
+};
+
+/* When the kernel dumps core, it starts by dumping the user struct -
+   this will be used by gdb to figure out where the data and stack segments
+   are within the file, and what virtual addresses to use. */
+struct user{
+/* We start with the registers, to mimic the way that "memory" is returned
+   from the ptrace(3,...) function.  */
+  struct pt_regs regs;		/* Where the registers are actually stored */
+/* ptrace does not yet supply these.  Someday.... */
+  int u_fpvalid;		/* True if math co-processor being used. */
+                                /* for this mess. Not yet used. */
+/* The rest of this junk is to help gdb figure out what goes where */
+  unsigned long int u_tsize;	/* Text segment size (pages). */
+  unsigned long int u_dsize;	/* Data segment size (pages). */
+  unsigned long int u_ssize;	/* Stack segment size (pages). */
+  unsigned long start_code;     /* Starting virtual address of text. */
+  unsigned long start_stack;	/* Starting virtual address of stack area.
+				   This is actually the bottom of the stack,
+				   the top of the stack is always found in the
+				   esp register.  */
+  long int signal;     		/* Signal that caused the core dump. */
+  int reserved;			/* No longer used */
+  unsigned long u_ar0;		/* Used by gdb to help find the values for */
+				/* the registers. */
+  unsigned long magic;		/* To uniquely identify a core file */
+  char u_comm[32];		/* User command that was responsible */
+  int u_debugreg[8];		/* No longer used */
+  struct user_fp u_fp;		/* FP state */
+  struct user_fp_struct * u_fp0;/* Used by gdb to help find the values for */
+  				/* the FP registers. */
+};
+#define NBPG PAGE_SIZE
+#define UPAGES 1
+#define HOST_TEXT_START_ADDR (u.start_code)
+#define HOST_STACK_END_ADDR (u.start_stack + u.u_ssize * NBPG)
+
+/*
+ * User specific VFP registers. If only VFPv2 is present, registers 16 to 31
+ * are ignored by the ptrace system call and the signal handler.
+ */
+struct user_vfp {
+	unsigned long long fpregs[32];
+	unsigned long fpscr;
+};
+
+/*
+ * VFP exception registers exposed to user space during signal delivery.
+ * Fields not relavant to the current VFP architecture are ignored.
+ */
+struct user_vfp_exc {
+	unsigned long	fpexc;
+	unsigned long	fpinst;
+	unsigned long	fpinst2;
+};
+
+#endif /* _ARM_USER_H */
diff --git a/arch/arm/include/asm/v7m.h b/arch/arm/include/asm/v7m.h
new file mode 100644
index 000000000..615781c61
--- /dev/null
+++ b/arch/arm/include/asm/v7m.h
@@ -0,0 +1,56 @@
+/*
+ * Common defines for v7m cpus
+ */
+#define V7M_SCS_ICTR			IOMEM(0xe000e004)
+#define V7M_SCS_ICTR_INTLINESNUM_MASK		0x0000000f
+
+#define BASEADDR_V7M_SCB		IOMEM(0xe000ed00)
+
+#define V7M_SCB_CPUID			0x00
+
+#define V7M_SCB_ICSR			0x04
+#define V7M_SCB_ICSR_PENDSVSET			(1 << 28)
+#define V7M_SCB_ICSR_PENDSVCLR			(1 << 27)
+#define V7M_SCB_ICSR_RETTOBASE			(1 << 11)
+
+#define V7M_SCB_VTOR			0x08
+
+#define V7M_SCB_AIRCR			0x0c
+#define V7M_SCB_AIRCR_VECTKEY			(0x05fa << 16)
+#define V7M_SCB_AIRCR_SYSRESETREQ		(1 << 2)
+
+#define V7M_SCB_SCR			0x10
+#define V7M_SCB_SCR_SLEEPDEEP			(1 << 2)
+
+#define V7M_SCB_CCR			0x14
+#define V7M_SCB_CCR_STKALIGN			(1 << 9)
+
+#define V7M_SCB_SHPR2			0x1c
+#define V7M_SCB_SHPR3			0x20
+
+#define V7M_SCB_SHCSR			0x24
+#define V7M_SCB_SHCSR_USGFAULTENA		(1 << 18)
+#define V7M_SCB_SHCSR_BUSFAULTENA		(1 << 17)
+#define V7M_SCB_SHCSR_MEMFAULTENA		(1 << 16)
+
+#define V7M_xPSR_FRAMEPTRALIGN			0x00000200
+#define V7M_xPSR_EXCEPTIONNO			0x000001ff
+
+/*
+ * When branching to an address that has bits [31:28] == 0xf an exception return
+ * occurs. Bits [27:5] are reserved (SBOP). If the processor implements the FP
+ * extension Bit [4] defines if the exception frame has space allocated for FP
+ * state information, SBOP otherwise. Bit [3] defines the mode that is returned
+ * to (0 -> handler mode; 1 -> thread mode). Bit [2] defines which sp is used
+ * (0 -> msp; 1 -> psp). Bits [1:0] are fixed to 0b01.
+ */
+#define EXC_RET_STACK_MASK			0x00000004
+#define EXC_RET_THREADMODE_PROCESSSTACK		0xfffffffd
+
+#ifndef __ASSEMBLY__
+
+enum reboot_mode;
+
+void armv7m_restart(enum reboot_mode mode, const char *cmd);
+
+#endif /* __ASSEMBLY__ */
diff --git a/arch/arm/include/asm/vdso.h b/arch/arm/include/asm/vdso.h
new file mode 100644
index 000000000..d0295f1dd
--- /dev/null
+++ b/arch/arm/include/asm/vdso.h
@@ -0,0 +1,32 @@
+#ifndef __ASM_VDSO_H
+#define __ASM_VDSO_H
+
+#ifdef __KERNEL__
+
+#ifndef __ASSEMBLY__
+
+struct mm_struct;
+
+#ifdef CONFIG_VDSO
+
+void arm_install_vdso(struct mm_struct *mm, unsigned long addr);
+
+extern char vdso_start, vdso_end;
+
+extern unsigned int vdso_total_pages;
+
+#else /* CONFIG_VDSO */
+
+static inline void arm_install_vdso(struct mm_struct *mm, unsigned long addr)
+{
+}
+
+#define vdso_total_pages 0
+
+#endif /* CONFIG_VDSO */
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* __KERNEL__ */
+
+#endif /* __ASM_VDSO_H */
diff --git a/arch/arm/include/asm/vdso_datapage.h b/arch/arm/include/asm/vdso_datapage.h
new file mode 100644
index 000000000..9be259442
--- /dev/null
+++ b/arch/arm/include/asm/vdso_datapage.h
@@ -0,0 +1,60 @@
+/*
+ * Adapted from arm64 version.
+ *
+ * Copyright (C) 2012 ARM Limited
+ *
+ * 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_VDSO_DATAPAGE_H
+#define __ASM_VDSO_DATAPAGE_H
+
+#ifdef __KERNEL__
+
+#ifndef __ASSEMBLY__
+
+#include <asm/page.h>
+
+/* Try to be cache-friendly on systems that don't implement the
+ * generic timer: fit the unconditionally updated fields in the first
+ * 32 bytes.
+ */
+struct vdso_data {
+	u32 seq_count;		/* sequence count - odd during updates */
+	u16 tk_is_cntvct;	/* fall back to syscall if false */
+	u16 cs_shift;		/* clocksource shift */
+	u32 xtime_coarse_sec;	/* coarse time */
+	u32 xtime_coarse_nsec;
+
+	u32 wtm_clock_sec;	/* wall to monotonic offset */
+	u32 wtm_clock_nsec;
+	u32 xtime_clock_sec;	/* CLOCK_REALTIME - seconds */
+	u32 cs_mult;		/* clocksource multiplier */
+
+	u64 cs_cycle_last;	/* last cycle value */
+	u64 cs_mask;		/* clocksource mask */
+
+	u64 xtime_clock_snsec;	/* CLOCK_REALTIME sub-ns base */
+	u32 tz_minuteswest;	/* timezone info for gettimeofday(2) */
+	u32 tz_dsttime;
+};
+
+union vdso_data_store {
+	struct vdso_data data;
+	u8 page[PAGE_SIZE];
+};
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* __KERNEL__ */
+
+#endif /* __ASM_VDSO_DATAPAGE_H */
diff --git a/arch/arm/include/asm/vfp.h b/arch/arm/include/asm/vfp.h
new file mode 100644
index 000000000..ee5f30842
--- /dev/null
+++ b/arch/arm/include/asm/vfp.h
@@ -0,0 +1,89 @@
+/*
+ * arch/arm/include/asm/vfp.h
+ *
+ * VFP register definitions.
+ * First, the standard VFP set.
+ */
+
+#define FPSID			cr0
+#define FPSCR			cr1
+#define MVFR1			cr6
+#define MVFR0			cr7
+#define FPEXC			cr8
+#define FPINST			cr9
+#define FPINST2			cr10
+
+/* FPSID bits */
+#define FPSID_IMPLEMENTER_BIT	(24)
+#define FPSID_IMPLEMENTER_MASK	(0xff << FPSID_IMPLEMENTER_BIT)
+#define FPSID_SOFTWARE		(1<<23)
+#define FPSID_FORMAT_BIT	(21)
+#define FPSID_FORMAT_MASK	(0x3  << FPSID_FORMAT_BIT)
+#define FPSID_NODOUBLE		(1<<20)
+#define FPSID_ARCH_BIT		(16)
+#define FPSID_ARCH_MASK		(0xF  << FPSID_ARCH_BIT)
+#define FPSID_CPUID_ARCH_MASK	(0x7F  << FPSID_ARCH_BIT)
+#define FPSID_PART_BIT		(8)
+#define FPSID_PART_MASK		(0xFF << FPSID_PART_BIT)
+#define FPSID_VARIANT_BIT	(4)
+#define FPSID_VARIANT_MASK	(0xF  << FPSID_VARIANT_BIT)
+#define FPSID_REV_BIT		(0)
+#define FPSID_REV_MASK		(0xF  << FPSID_REV_BIT)
+
+/* FPEXC bits */
+#define FPEXC_EX		(1 << 31)
+#define FPEXC_EN		(1 << 30)
+#define FPEXC_DEX		(1 << 29)
+#define FPEXC_FP2V		(1 << 28)
+#define FPEXC_VV		(1 << 27)
+#define FPEXC_TFV		(1 << 26)
+#define FPEXC_LENGTH_BIT	(8)
+#define FPEXC_LENGTH_MASK	(7 << FPEXC_LENGTH_BIT)
+#define FPEXC_IDF		(1 << 7)
+#define FPEXC_IXF		(1 << 4)
+#define FPEXC_UFF		(1 << 3)
+#define FPEXC_OFF		(1 << 2)
+#define FPEXC_DZF		(1 << 1)
+#define FPEXC_IOF		(1 << 0)
+#define FPEXC_TRAP_MASK		(FPEXC_IDF|FPEXC_IXF|FPEXC_UFF|FPEXC_OFF|FPEXC_DZF|FPEXC_IOF)
+
+/* FPSCR bits */
+#define FPSCR_DEFAULT_NAN	(1<<25)
+#define FPSCR_FLUSHTOZERO	(1<<24)
+#define FPSCR_ROUND_NEAREST	(0<<22)
+#define FPSCR_ROUND_PLUSINF	(1<<22)
+#define FPSCR_ROUND_MINUSINF	(2<<22)
+#define FPSCR_ROUND_TOZERO	(3<<22)
+#define FPSCR_RMODE_BIT		(22)
+#define FPSCR_RMODE_MASK	(3 << FPSCR_RMODE_BIT)
+#define FPSCR_STRIDE_BIT	(20)
+#define FPSCR_STRIDE_MASK	(3 << FPSCR_STRIDE_BIT)
+#define FPSCR_LENGTH_BIT	(16)
+#define FPSCR_LENGTH_MASK	(7 << FPSCR_LENGTH_BIT)
+#define FPSCR_IOE		(1<<8)
+#define FPSCR_DZE		(1<<9)
+#define FPSCR_OFE		(1<<10)
+#define FPSCR_UFE		(1<<11)
+#define FPSCR_IXE		(1<<12)
+#define FPSCR_IDE		(1<<15)
+#define FPSCR_IOC		(1<<0)
+#define FPSCR_DZC		(1<<1)
+#define FPSCR_OFC		(1<<2)
+#define FPSCR_UFC		(1<<3)
+#define FPSCR_IXC		(1<<4)
+#define FPSCR_IDC		(1<<7)
+
+/* MVFR0 bits */
+#define MVFR0_A_SIMD_BIT	(0)
+#define MVFR0_A_SIMD_MASK	(0xf << MVFR0_A_SIMD_BIT)
+#define MVFR0_SP_BIT		(4)
+#define MVFR0_SP_MASK		(0xf << MVFR0_SP_BIT)
+#define MVFR0_DP_BIT		(8)
+#define MVFR0_DP_MASK		(0xf << MVFR0_DP_BIT)
+
+/* Bit patterns for decoding the packaged operation descriptors */
+#define VFPOPDESC_LENGTH_BIT	(9)
+#define VFPOPDESC_LENGTH_MASK	(0x07 << VFPOPDESC_LENGTH_BIT)
+#define VFPOPDESC_UNUSED_BIT	(24)
+#define VFPOPDESC_UNUSED_MASK	(0xFF << VFPOPDESC_UNUSED_BIT)
+#define VFPOPDESC_OPDESC_MASK	(~(VFPOPDESC_LENGTH_MASK | VFPOPDESC_UNUSED_MASK))
diff --git a/arch/arm/include/asm/vfpmacros.h b/arch/arm/include/asm/vfpmacros.h
new file mode 100644
index 000000000..301c1db3e
--- /dev/null
+++ b/arch/arm/include/asm/vfpmacros.h
@@ -0,0 +1,65 @@
+/*
+ * arch/arm/include/asm/vfpmacros.h
+ *
+ * Assembler-only file containing VFP macros and register definitions.
+ */
+#include <asm/hwcap.h>
+
+#include <asm/vfp.h>
+
+@ Macros to allow building with old toolkits (with no VFP support)
+	.macro	VFPFMRX, rd, sysreg, cond
+	MRC\cond	p10, 7, \rd, \sysreg, cr0, 0	@ FMRX	\rd, \sysreg
+	.endm
+
+	.macro	VFPFMXR, sysreg, rd, cond
+	MCR\cond	p10, 7, \rd, \sysreg, cr0, 0	@ FMXR	\sysreg, \rd
+	.endm
+
+	@ read all the working registers back into the VFP
+	.macro	VFPFLDMIA, base, tmp
+#if __LINUX_ARM_ARCH__ < 6
+	LDC	p11, cr0, [\base],#33*4		    @ FLDMIAX \base!, {d0-d15}
+#else
+	LDC	p11, cr0, [\base],#32*4		    @ FLDMIAD \base!, {d0-d15}
+#endif
+#ifdef CONFIG_VFPv3
+#if __LINUX_ARM_ARCH__ <= 6
+	ldr	\tmp, =elf_hwcap		    @ may not have MVFR regs
+	ldr	\tmp, [\tmp, #0]
+	tst	\tmp, #HWCAP_VFPD32
+	ldcnel	p11, cr0, [\base],#32*4		    @ FLDMIAD \base!, {d16-d31}
+	addeq	\base, \base, #32*4		    @ step over unused register space
+#else
+	VFPFMRX	\tmp, MVFR0			    @ Media and VFP Feature Register 0
+	and	\tmp, \tmp, #MVFR0_A_SIMD_MASK	    @ A_SIMD field
+	cmp	\tmp, #2			    @ 32 x 64bit registers?
+	ldceql	p11, cr0, [\base],#32*4		    @ FLDMIAD \base!, {d16-d31}
+	addne	\base, \base, #32*4		    @ step over unused register space
+#endif
+#endif
+	.endm
+
+	@ write all the working registers out of the VFP
+	.macro	VFPFSTMIA, base, tmp
+#if __LINUX_ARM_ARCH__ < 6
+	STC	p11, cr0, [\base],#33*4		    @ FSTMIAX \base!, {d0-d15}
+#else
+	STC	p11, cr0, [\base],#32*4		    @ FSTMIAD \base!, {d0-d15}
+#endif
+#ifdef CONFIG_VFPv3
+#if __LINUX_ARM_ARCH__ <= 6
+	ldr	\tmp, =elf_hwcap		    @ may not have MVFR regs
+	ldr	\tmp, [\tmp, #0]
+	tst	\tmp, #HWCAP_VFPD32
+	stcnel	p11, cr0, [\base],#32*4		    @ FSTMIAD \base!, {d16-d31}
+	addeq	\base, \base, #32*4		    @ step over unused register space
+#else
+	VFPFMRX	\tmp, MVFR0			    @ Media and VFP Feature Register 0
+	and	\tmp, \tmp, #MVFR0_A_SIMD_MASK	    @ A_SIMD field
+	cmp	\tmp, #2			    @ 32 x 64bit registers?
+	stceql	p11, cr0, [\base],#32*4		    @ FSTMIAD \base!, {d16-d31}
+	addne	\base, \base, #32*4		    @ step over unused register space
+#endif
+#endif
+	.endm
diff --git a/arch/arm/include/asm/vga.h b/arch/arm/include/asm/vga.h
new file mode 100644
index 000000000..91f40217b
--- /dev/null
+++ b/arch/arm/include/asm/vga.h
@@ -0,0 +1,13 @@
+#ifndef ASMARM_VGA_H
+#define ASMARM_VGA_H
+
+#include <linux/io.h>
+
+extern unsigned long vga_base;
+
+#define VGA_MAP_MEM(x,s)	(vga_base + (x))
+
+#define vga_readb(x)	(*((volatile unsigned char *)x))
+#define vga_writeb(x,y)	(*((volatile unsigned char *)y) = (x))
+
+#endif
diff --git a/arch/arm/include/asm/virt.h b/arch/arm/include/asm/virt.h
new file mode 100644
index 000000000..4371f45c5
--- /dev/null
+++ b/arch/arm/include/asm/virt.h
@@ -0,0 +1,81 @@
+/*
+ * Copyright (c) 2012 Linaro Limited.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * 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, write to the Free Software Foundation, Inc.,
+ * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+ */
+
+#ifndef VIRT_H
+#define VIRT_H
+
+#include <asm/ptrace.h>
+
+/*
+ * Flag indicating that the kernel was not entered in the same mode on every
+ * CPU.  The zImage loader stashes this value in an SPSR, so we need an
+ * architecturally defined flag bit here.
+ */
+#define BOOT_CPU_MODE_MISMATCH	PSR_N_BIT
+
+#ifndef __ASSEMBLY__
+#include <asm/cacheflush.h>
+
+#ifdef CONFIG_ARM_VIRT_EXT
+/*
+ * __boot_cpu_mode records what mode the primary CPU was booted in.
+ * A correctly-implemented bootloader must start all CPUs in the same mode:
+ * if it fails to do this, the flag BOOT_CPU_MODE_MISMATCH is set to indicate
+ * that some CPU(s) were booted in a different mode.
+ *
+ * This allows the kernel to flag an error when the secondaries have come up.
+ */
+extern int __boot_cpu_mode;
+
+static inline void sync_boot_mode(void)
+{
+	/*
+	 * As secondaries write to __boot_cpu_mode with caches disabled, we
+	 * must flush the corresponding cache entries to ensure the visibility
+	 * of their writes.
+	 */
+	sync_cache_r(&__boot_cpu_mode);
+}
+
+void __hyp_set_vectors(unsigned long phys_vector_base);
+unsigned long __hyp_get_vectors(void);
+#else
+#define __boot_cpu_mode	(SVC_MODE)
+#define sync_boot_mode()
+#endif
+
+#ifndef ZIMAGE
+void hyp_mode_check(void);
+
+/* Reports the availability of HYP mode */
+static inline bool is_hyp_mode_available(void)
+{
+	return ((__boot_cpu_mode & MODE_MASK) == HYP_MODE &&
+		!(__boot_cpu_mode & BOOT_CPU_MODE_MISMATCH));
+}
+
+/* Check if the bootloader has booted CPUs in different modes */
+static inline bool is_hyp_mode_mismatched(void)
+{
+	return !!(__boot_cpu_mode & BOOT_CPU_MODE_MISMATCH);
+}
+#endif
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* ! VIRT_H */
diff --git a/arch/arm/include/asm/word-at-a-time.h b/arch/arm/include/asm/word-at-a-time.h
new file mode 100644
index 000000000..5831dce4b
--- /dev/null
+++ b/arch/arm/include/asm/word-at-a-time.h
@@ -0,0 +1,98 @@
+#ifndef __ASM_ARM_WORD_AT_A_TIME_H
+#define __ASM_ARM_WORD_AT_A_TIME_H
+
+#ifndef __ARMEB__
+
+/*
+ * Little-endian word-at-a-time zero byte handling.
+ * Heavily based on the x86 algorithm.
+ */
+#include <linux/kernel.h>
+
+struct word_at_a_time {
+	const unsigned long one_bits, high_bits;
+};
+
+#define WORD_AT_A_TIME_CONSTANTS { REPEAT_BYTE(0x01), REPEAT_BYTE(0x80) }
+
+static inline unsigned long has_zero(unsigned long a, unsigned long *bits,
+				     const struct word_at_a_time *c)
+{
+	unsigned long mask = ((a - c->one_bits) & ~a) & c->high_bits;
+	*bits = mask;
+	return mask;
+}
+
+#define prep_zero_mask(a, bits, c) (bits)
+
+static inline unsigned long create_zero_mask(unsigned long bits)
+{
+	bits = (bits - 1) & ~bits;
+	return bits >> 7;
+}
+
+static inline unsigned long find_zero(unsigned long mask)
+{
+	unsigned long ret;
+
+#if __LINUX_ARM_ARCH__ >= 5
+	/* We have clz available. */
+	ret = fls(mask) >> 3;
+#else
+	/* (000000 0000ff 00ffff ffffff) -> ( 1 1 2 3 ) */
+	ret = (0x0ff0001 + mask) >> 23;
+	/* Fix the 1 for 00 case */
+	ret &= mask;
+#endif
+
+	return ret;
+}
+
+#define zero_bytemask(mask) (mask)
+
+#else	/* __ARMEB__ */
+#include <asm-generic/word-at-a-time.h>
+#endif
+
+#ifdef CONFIG_DCACHE_WORD_ACCESS
+
+/*
+ * Load an unaligned word from kernel space.
+ *
+ * In the (very unlikely) case of the word being a page-crosser
+ * and the next page not being mapped, take the exception and
+ * return zeroes in the non-existing part.
+ */
+static inline unsigned long load_unaligned_zeropad(const void *addr)
+{
+	unsigned long ret, offset;
+
+	/* Load word from unaligned pointer addr */
+	asm(
+	"1:	ldr	%0, [%2]\n"
+	"2:\n"
+	"	.pushsection .text.fixup,\"ax\"\n"
+	"	.align 2\n"
+	"3:	and	%1, %2, #0x3\n"
+	"	bic	%2, %2, #0x3\n"
+	"	ldr	%0, [%2]\n"
+	"	lsl	%1, %1, #0x3\n"
+#ifndef __ARMEB__
+	"	lsr	%0, %0, %1\n"
+#else
+	"	lsl	%0, %0, %1\n"
+#endif
+	"	b	2b\n"
+	"	.popsection\n"
+	"	.pushsection __ex_table,\"a\"\n"
+	"	.align	3\n"
+	"	.long	1b, 3b\n"
+	"	.popsection"
+	: "=&r" (ret), "=&r" (offset)
+	: "r" (addr), "Qo" (*(unsigned long *)addr));
+
+	return ret;
+}
+
+#endif	/* DCACHE_WORD_ACCESS */
+#endif /* __ASM_ARM_WORD_AT_A_TIME_H */
diff --git a/arch/arm/include/asm/xen/events.h b/arch/arm/include/asm/xen/events.h
new file mode 100644
index 000000000..8b1f37bfe
--- /dev/null
+++ b/arch/arm/include/asm/xen/events.h
@@ -0,0 +1,23 @@
+#ifndef _ASM_ARM_XEN_EVENTS_H
+#define _ASM_ARM_XEN_EVENTS_H
+
+#include <asm/ptrace.h>
+#include <asm/atomic.h>
+
+enum ipi_vector {
+	XEN_PLACEHOLDER_VECTOR,
+
+	/* Xen IPIs go here */
+	XEN_NR_IPIS,
+};
+
+static inline int xen_irqs_disabled(struct pt_regs *regs)
+{
+	return raw_irqs_disabled_flags(regs->ARM_cpsr);
+}
+
+#define xchg_xen_ulong(ptr, val) atomic64_xchg(container_of((ptr),	\
+							    atomic64_t,	\
+							    counter), (val))
+
+#endif /* _ASM_ARM_XEN_EVENTS_H */
diff --git a/arch/arm/include/asm/xen/hypercall.h b/arch/arm/include/asm/xen/hypercall.h
new file mode 100644
index 000000000..712b50e0a
--- /dev/null
+++ b/arch/arm/include/asm/xen/hypercall.h
@@ -0,0 +1,77 @@
+/******************************************************************************
+ * hypercall.h
+ *
+ * Linux-specific hypervisor handling.
+ *
+ * Stefano Stabellini <stefano.stabellini@eu.citrix.com>, Citrix, 2012
+ *
+ * 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; or, when distributed
+ * separately from the Linux kernel or incorporated into other
+ * software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#ifndef _ASM_ARM_XEN_HYPERCALL_H
+#define _ASM_ARM_XEN_HYPERCALL_H
+
+#include <xen/interface/xen.h>
+#include <xen/interface/sched.h>
+
+long privcmd_call(unsigned call, unsigned long a1,
+		unsigned long a2, unsigned long a3,
+		unsigned long a4, unsigned long a5);
+int HYPERVISOR_xen_version(int cmd, void *arg);
+int HYPERVISOR_console_io(int cmd, int count, char *str);
+int HYPERVISOR_grant_table_op(unsigned int cmd, void *uop, unsigned int count);
+int HYPERVISOR_sched_op(int cmd, void *arg);
+int HYPERVISOR_event_channel_op(int cmd, void *arg);
+unsigned long HYPERVISOR_hvm_op(int op, void *arg);
+int HYPERVISOR_memory_op(unsigned int cmd, void *arg);
+int HYPERVISOR_physdev_op(int cmd, void *arg);
+int HYPERVISOR_vcpu_op(int cmd, int vcpuid, void *extra_args);
+int HYPERVISOR_tmem_op(void *arg);
+int HYPERVISOR_multicall(struct multicall_entry *calls, uint32_t nr);
+
+static inline int
+HYPERVISOR_suspend(unsigned long start_info_mfn)
+{
+	struct sched_shutdown r = { .reason = SHUTDOWN_suspend };
+
+	/* start_info_mfn is unused on ARM */
+	return HYPERVISOR_sched_op(SCHEDOP_shutdown, &r);
+}
+
+static inline void
+MULTI_update_va_mapping(struct multicall_entry *mcl, unsigned long va,
+			unsigned int new_val, unsigned long flags)
+{
+	BUG();
+}
+
+static inline void
+MULTI_mmu_update(struct multicall_entry *mcl, struct mmu_update *req,
+		 int count, int *success_count, domid_t domid)
+{
+	BUG();
+}
+
+#endif /* _ASM_ARM_XEN_HYPERCALL_H */
diff --git a/arch/arm/include/asm/xen/hypervisor.h b/arch/arm/include/asm/xen/hypervisor.h
new file mode 100644
index 000000000..1317ee40f
--- /dev/null
+++ b/arch/arm/include/asm/xen/hypervisor.h
@@ -0,0 +1,21 @@
+#ifndef _ASM_ARM_XEN_HYPERVISOR_H
+#define _ASM_ARM_XEN_HYPERVISOR_H
+
+extern struct shared_info *HYPERVISOR_shared_info;
+extern struct start_info *xen_start_info;
+
+/* Lazy mode for batching updates / context switch */
+enum paravirt_lazy_mode {
+	PARAVIRT_LAZY_NONE,
+	PARAVIRT_LAZY_MMU,
+	PARAVIRT_LAZY_CPU,
+};
+
+static inline enum paravirt_lazy_mode paravirt_get_lazy_mode(void)
+{
+	return PARAVIRT_LAZY_NONE;
+}
+
+extern struct dma_map_ops *xen_dma_ops;
+
+#endif /* _ASM_ARM_XEN_HYPERVISOR_H */
diff --git a/arch/arm/include/asm/xen/interface.h b/arch/arm/include/asm/xen/interface.h
new file mode 100644
index 000000000..50066006e
--- /dev/null
+++ b/arch/arm/include/asm/xen/interface.h
@@ -0,0 +1,82 @@
+/******************************************************************************
+ * Guest OS interface to ARM Xen.
+ *
+ * Stefano Stabellini <stefano.stabellini@eu.citrix.com>, Citrix, 2012
+ */
+
+#ifndef _ASM_ARM_XEN_INTERFACE_H
+#define _ASM_ARM_XEN_INTERFACE_H
+
+#include <linux/types.h>
+
+#define uint64_aligned_t uint64_t __attribute__((aligned(8)))
+
+#define __DEFINE_GUEST_HANDLE(name, type) \
+	typedef struct { union { type *p; uint64_aligned_t q; }; }  \
+        __guest_handle_ ## name
+
+#define DEFINE_GUEST_HANDLE_STRUCT(name) \
+	__DEFINE_GUEST_HANDLE(name, struct name)
+#define DEFINE_GUEST_HANDLE(name) __DEFINE_GUEST_HANDLE(name, name)
+#define GUEST_HANDLE(name)        __guest_handle_ ## name
+
+#define set_xen_guest_handle(hnd, val)			\
+	do {						\
+		if (sizeof(hnd) == 8)			\
+			*(uint64_t *)&(hnd) = 0;	\
+		(hnd).p = val;				\
+	} while (0)
+
+#ifndef __ASSEMBLY__
+/* Explicitly size integers that represent pfns in the interface with
+ * Xen so that we can have one ABI that works for 32 and 64 bit guests.
+ * Note that this means that the xen_pfn_t type may be capable of
+ * representing pfn's which the guest cannot represent in its own pfn
+ * type. However since pfn space is controlled by the guest this is
+ * fine since it simply wouldn't be able to create any sure pfns in
+ * the first place.
+ */
+typedef uint64_t xen_pfn_t;
+#define PRI_xen_pfn "llx"
+typedef uint64_t xen_ulong_t;
+#define PRI_xen_ulong "llx"
+typedef int64_t xen_long_t;
+#define PRI_xen_long "llx"
+/* Guest handles for primitive C types. */
+__DEFINE_GUEST_HANDLE(uchar, unsigned char);
+__DEFINE_GUEST_HANDLE(uint,  unsigned int);
+DEFINE_GUEST_HANDLE(char);
+DEFINE_GUEST_HANDLE(int);
+DEFINE_GUEST_HANDLE(void);
+DEFINE_GUEST_HANDLE(uint64_t);
+DEFINE_GUEST_HANDLE(uint32_t);
+DEFINE_GUEST_HANDLE(xen_pfn_t);
+DEFINE_GUEST_HANDLE(xen_ulong_t);
+
+/* Maximum number of virtual CPUs in multi-processor guests. */
+#define MAX_VIRT_CPUS 1
+
+struct arch_vcpu_info { };
+struct arch_shared_info { };
+
+/* TODO: Move pvclock definitions some place arch independent */
+struct pvclock_vcpu_time_info {
+	u32   version;
+	u32   pad0;
+	u64   tsc_timestamp;
+	u64   system_time;
+	u32   tsc_to_system_mul;
+	s8    tsc_shift;
+	u8    flags;
+	u8    pad[2];
+} __attribute__((__packed__)); /* 32 bytes */
+
+/* It is OK to have a 12 bytes struct with no padding because it is packed */
+struct pvclock_wall_clock {
+	u32   version;
+	u32   sec;
+	u32   nsec;
+} __attribute__((__packed__));
+#endif
+
+#endif /* _ASM_ARM_XEN_INTERFACE_H */
diff --git a/arch/arm/include/asm/xen/page-coherent.h b/arch/arm/include/asm/xen/page-coherent.h
new file mode 100644
index 000000000..efd562412
--- /dev/null
+++ b/arch/arm/include/asm/xen/page-coherent.h
@@ -0,0 +1,87 @@
+#ifndef _ASM_ARM_XEN_PAGE_COHERENT_H
+#define _ASM_ARM_XEN_PAGE_COHERENT_H
+
+#include <asm/page.h>
+#include <linux/dma-attrs.h>
+#include <linux/dma-mapping.h>
+
+void __xen_dma_map_page(struct device *hwdev, struct page *page,
+	     dma_addr_t dev_addr, unsigned long offset, size_t size,
+	     enum dma_data_direction dir, struct dma_attrs *attrs);
+void __xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
+		size_t size, enum dma_data_direction dir,
+		struct dma_attrs *attrs);
+void __xen_dma_sync_single_for_cpu(struct device *hwdev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir);
+
+void __xen_dma_sync_single_for_device(struct device *hwdev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir);
+
+static inline void *xen_alloc_coherent_pages(struct device *hwdev, size_t size,
+		dma_addr_t *dma_handle, gfp_t flags,
+		struct dma_attrs *attrs)
+{
+	return __generic_dma_ops(hwdev)->alloc(hwdev, size, dma_handle, flags, attrs);
+}
+
+static inline void xen_free_coherent_pages(struct device *hwdev, size_t size,
+		void *cpu_addr, dma_addr_t dma_handle,
+		struct dma_attrs *attrs)
+{
+	__generic_dma_ops(hwdev)->free(hwdev, size, cpu_addr, dma_handle, attrs);
+}
+
+static inline void xen_dma_map_page(struct device *hwdev, struct page *page,
+	     dma_addr_t dev_addr, unsigned long offset, size_t size,
+	     enum dma_data_direction dir, struct dma_attrs *attrs)
+{
+	bool local = PFN_DOWN(dev_addr) == page_to_pfn(page);
+	/* Dom0 is mapped 1:1, so if pfn == mfn the page is local otherwise
+	 * is a foreign page grant-mapped in dom0. If the page is local we
+	 * can safely call the native dma_ops function, otherwise we call
+	 * the xen specific function. */
+	if (local)
+		__generic_dma_ops(hwdev)->map_page(hwdev, page, offset, size, dir, attrs);
+	else
+		__xen_dma_map_page(hwdev, page, dev_addr, offset, size, dir, attrs);
+}
+
+static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
+		size_t size, enum dma_data_direction dir,
+		struct dma_attrs *attrs)
+{
+	unsigned long pfn = PFN_DOWN(handle);
+	/* Dom0 is mapped 1:1, so calling pfn_valid on a foreign mfn will
+	 * always return false. If the page is local we can safely call the
+	 * native dma_ops function, otherwise we call the xen specific
+	 * function. */
+	if (pfn_valid(pfn)) {
+		if (__generic_dma_ops(hwdev)->unmap_page)
+			__generic_dma_ops(hwdev)->unmap_page(hwdev, handle, size, dir, attrs);
+	} else
+		__xen_dma_unmap_page(hwdev, handle, size, dir, attrs);
+}
+
+static inline void xen_dma_sync_single_for_cpu(struct device *hwdev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir)
+{
+	unsigned long pfn = PFN_DOWN(handle);
+	if (pfn_valid(pfn)) {
+		if (__generic_dma_ops(hwdev)->sync_single_for_cpu)
+			__generic_dma_ops(hwdev)->sync_single_for_cpu(hwdev, handle, size, dir);
+	} else
+		__xen_dma_sync_single_for_cpu(hwdev, handle, size, dir);
+}
+
+static inline void xen_dma_sync_single_for_device(struct device *hwdev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir)
+{
+	unsigned long pfn = PFN_DOWN(handle);
+	if (pfn_valid(pfn)) {
+		if (__generic_dma_ops(hwdev)->sync_single_for_device)
+			__generic_dma_ops(hwdev)->sync_single_for_device(hwdev, handle, size, dir);
+	} else
+		__xen_dma_sync_single_for_device(hwdev, handle, size, dir);
+}
+
+#endif /* _ASM_ARM_XEN_PAGE_COHERENT_H */
diff --git a/arch/arm/include/asm/xen/page.h b/arch/arm/include/asm/xen/page.h
new file mode 100644
index 000000000..0b579b2f4
--- /dev/null
+++ b/arch/arm/include/asm/xen/page.h
@@ -0,0 +1,115 @@
+#ifndef _ASM_ARM_XEN_PAGE_H
+#define _ASM_ARM_XEN_PAGE_H
+
+#include <asm/page.h>
+#include <asm/pgtable.h>
+
+#include <linux/pfn.h>
+#include <linux/types.h>
+#include <linux/dma-mapping.h>
+
+#include <xen/xen.h>
+#include <xen/interface/grant_table.h>
+
+#define phys_to_machine_mapping_valid(pfn) (1)
+#define mfn_to_virt(m)			(__va(mfn_to_pfn(m) << PAGE_SHIFT))
+
+#define pte_mfn	    pte_pfn
+#define mfn_pte	    pfn_pte
+
+/* Xen machine address */
+typedef struct xmaddr {
+	phys_addr_t maddr;
+} xmaddr_t;
+
+/* Xen pseudo-physical address */
+typedef struct xpaddr {
+	phys_addr_t paddr;
+} xpaddr_t;
+
+#define XMADDR(x)	((xmaddr_t) { .maddr = (x) })
+#define XPADDR(x)	((xpaddr_t) { .paddr = (x) })
+
+#define INVALID_P2M_ENTRY      (~0UL)
+
+unsigned long __pfn_to_mfn(unsigned long pfn);
+extern struct rb_root phys_to_mach;
+
+static inline unsigned long pfn_to_mfn(unsigned long pfn)
+{
+	unsigned long mfn;
+
+	if (phys_to_mach.rb_node != NULL) {
+		mfn = __pfn_to_mfn(pfn);
+		if (mfn != INVALID_P2M_ENTRY)
+			return mfn;
+	}
+
+	return pfn;
+}
+
+static inline unsigned long mfn_to_pfn(unsigned long mfn)
+{
+	return mfn;
+}
+
+#define mfn_to_local_pfn(mfn) mfn_to_pfn(mfn)
+
+static inline xmaddr_t phys_to_machine(xpaddr_t phys)
+{
+	unsigned offset = phys.paddr & ~PAGE_MASK;
+	return XMADDR(PFN_PHYS(pfn_to_mfn(PFN_DOWN(phys.paddr))) | offset);
+}
+
+static inline xpaddr_t machine_to_phys(xmaddr_t machine)
+{
+	unsigned offset = machine.maddr & ~PAGE_MASK;
+	return XPADDR(PFN_PHYS(mfn_to_pfn(PFN_DOWN(machine.maddr))) | offset);
+}
+/* VIRT <-> MACHINE conversion */
+#define virt_to_machine(v)	(phys_to_machine(XPADDR(__pa(v))))
+#define virt_to_mfn(v)		(pfn_to_mfn(virt_to_pfn(v)))
+#define mfn_to_virt(m)		(__va(mfn_to_pfn(m) << PAGE_SHIFT))
+
+static inline xmaddr_t arbitrary_virt_to_machine(void *vaddr)
+{
+	/* TODO: assuming it is mapped in the kernel 1:1 */
+	return virt_to_machine(vaddr);
+}
+
+/* TODO: this shouldn't be here but it is because the frontend drivers
+ * are using it (its rolled in headers) even though we won't hit the code path.
+ * So for right now just punt with this.
+ */
+static inline pte_t *lookup_address(unsigned long address, unsigned int *level)
+{
+	BUG();
+	return NULL;
+}
+
+extern int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops,
+				   struct gnttab_map_grant_ref *kmap_ops,
+				   struct page **pages, unsigned int count);
+
+extern int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops,
+				     struct gnttab_unmap_grant_ref *kunmap_ops,
+				     struct page **pages, unsigned int count);
+
+bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn);
+bool __set_phys_to_machine_multi(unsigned long pfn, unsigned long mfn,
+		unsigned long nr_pages);
+
+static inline bool set_phys_to_machine(unsigned long pfn, unsigned long mfn)
+{
+	return __set_phys_to_machine(pfn, mfn);
+}
+
+#define xen_remap(cookie, size) ioremap_cache((cookie), (size))
+#define xen_unmap(cookie) iounmap((cookie))
+
+bool xen_arch_need_swiotlb(struct device *dev,
+			   unsigned long pfn,
+			   unsigned long mfn);
+unsigned long xen_get_swiotlb_free_pages(unsigned int order);
+
+#endif /* _ASM_ARM_XEN_PAGE_H */
diff --git a/arch/arm/include/asm/xor.h b/arch/arm/include/asm/xor.h
new file mode 100644
index 000000000..4ffb26d4c
--- /dev/null
+++ b/arch/arm/include/asm/xor.h
@@ -0,0 +1,214 @@
+/*
+ *  arch/arm/include/asm/xor.h
+ *
+ *  Copyright (C) 2001 Russell King
+ *
+ * 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.
+ */
+#include <linux/hardirq.h>
+#include <asm-generic/xor.h>
+#include <asm/hwcap.h>
+#include <asm/neon.h>
+
+#define __XOR(a1, a2) a1 ^= a2
+
+#define GET_BLOCK_2(dst) \
+	__asm__("ldmia	%0, {%1, %2}" \
+		: "=r" (dst), "=r" (a1), "=r" (a2) \
+		: "0" (dst))
+
+#define GET_BLOCK_4(dst) \
+	__asm__("ldmia	%0, {%1, %2, %3, %4}" \
+		: "=r" (dst), "=r" (a1), "=r" (a2), "=r" (a3), "=r" (a4) \
+		: "0" (dst))
+
+#define XOR_BLOCK_2(src) \
+	__asm__("ldmia	%0!, {%1, %2}" \
+		: "=r" (src), "=r" (b1), "=r" (b2) \
+		: "0" (src)); \
+	__XOR(a1, b1); __XOR(a2, b2);
+
+#define XOR_BLOCK_4(src) \
+	__asm__("ldmia	%0!, {%1, %2, %3, %4}" \
+		: "=r" (src), "=r" (b1), "=r" (b2), "=r" (b3), "=r" (b4) \
+		: "0" (src)); \
+	__XOR(a1, b1); __XOR(a2, b2); __XOR(a3, b3); __XOR(a4, b4)
+
+#define PUT_BLOCK_2(dst) \
+	__asm__ __volatile__("stmia	%0!, {%2, %3}" \
+		: "=r" (dst) \
+		: "0" (dst), "r" (a1), "r" (a2))
+
+#define PUT_BLOCK_4(dst) \
+	__asm__ __volatile__("stmia	%0!, {%2, %3, %4, %5}" \
+		: "=r" (dst) \
+		: "0" (dst), "r" (a1), "r" (a2), "r" (a3), "r" (a4))
+
+static void
+xor_arm4regs_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
+{
+	unsigned int lines = bytes / sizeof(unsigned long) / 4;
+	register unsigned int a1 __asm__("r4");
+	register unsigned int a2 __asm__("r5");
+	register unsigned int a3 __asm__("r6");
+	register unsigned int a4 __asm__("r7");
+	register unsigned int b1 __asm__("r8");
+	register unsigned int b2 __asm__("r9");
+	register unsigned int b3 __asm__("ip");
+	register unsigned int b4 __asm__("lr");
+
+	do {
+		GET_BLOCK_4(p1);
+		XOR_BLOCK_4(p2);
+		PUT_BLOCK_4(p1);
+	} while (--lines);
+}
+
+static void
+xor_arm4regs_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+		unsigned long *p3)
+{
+	unsigned int lines = bytes / sizeof(unsigned long) / 4;
+	register unsigned int a1 __asm__("r4");
+	register unsigned int a2 __asm__("r5");
+	register unsigned int a3 __asm__("r6");
+	register unsigned int a4 __asm__("r7");
+	register unsigned int b1 __asm__("r8");
+	register unsigned int b2 __asm__("r9");
+	register unsigned int b3 __asm__("ip");
+	register unsigned int b4 __asm__("lr");
+
+	do {
+		GET_BLOCK_4(p1);
+		XOR_BLOCK_4(p2);
+		XOR_BLOCK_4(p3);
+		PUT_BLOCK_4(p1);
+	} while (--lines);
+}
+
+static void
+xor_arm4regs_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+		unsigned long *p3, unsigned long *p4)
+{
+	unsigned int lines = bytes / sizeof(unsigned long) / 2;
+	register unsigned int a1 __asm__("r8");
+	register unsigned int a2 __asm__("r9");
+	register unsigned int b1 __asm__("ip");
+	register unsigned int b2 __asm__("lr");
+
+	do {
+		GET_BLOCK_2(p1);
+		XOR_BLOCK_2(p2);
+		XOR_BLOCK_2(p3);
+		XOR_BLOCK_2(p4);
+		PUT_BLOCK_2(p1);
+	} while (--lines);
+}
+
+static void
+xor_arm4regs_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+		unsigned long *p3, unsigned long *p4, unsigned long *p5)
+{
+	unsigned int lines = bytes / sizeof(unsigned long) / 2;
+	register unsigned int a1 __asm__("r8");
+	register unsigned int a2 __asm__("r9");
+	register unsigned int b1 __asm__("ip");
+	register unsigned int b2 __asm__("lr");
+
+	do {
+		GET_BLOCK_2(p1);
+		XOR_BLOCK_2(p2);
+		XOR_BLOCK_2(p3);
+		XOR_BLOCK_2(p4);
+		XOR_BLOCK_2(p5);
+		PUT_BLOCK_2(p1);
+	} while (--lines);
+}
+
+static struct xor_block_template xor_block_arm4regs = {
+	.name	= "arm4regs",
+	.do_2	= xor_arm4regs_2,
+	.do_3	= xor_arm4regs_3,
+	.do_4	= xor_arm4regs_4,
+	.do_5	= xor_arm4regs_5,
+};
+
+#undef XOR_TRY_TEMPLATES
+#define XOR_TRY_TEMPLATES			\
+	do {					\
+		xor_speed(&xor_block_arm4regs);	\
+		xor_speed(&xor_block_8regs);	\
+		xor_speed(&xor_block_32regs);	\
+		NEON_TEMPLATES;			\
+	} while (0)
+
+#ifdef CONFIG_KERNEL_MODE_NEON
+
+extern struct xor_block_template const xor_block_neon_inner;
+
+static void
+xor_neon_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
+{
+	if (in_interrupt()) {
+		xor_arm4regs_2(bytes, p1, p2);
+	} else {
+		kernel_neon_begin();
+		xor_block_neon_inner.do_2(bytes, p1, p2);
+		kernel_neon_end();
+	}
+}
+
+static void
+xor_neon_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+		unsigned long *p3)
+{
+	if (in_interrupt()) {
+		xor_arm4regs_3(bytes, p1, p2, p3);
+	} else {
+		kernel_neon_begin();
+		xor_block_neon_inner.do_3(bytes, p1, p2, p3);
+		kernel_neon_end();
+	}
+}
+
+static void
+xor_neon_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+		unsigned long *p3, unsigned long *p4)
+{
+	if (in_interrupt()) {
+		xor_arm4regs_4(bytes, p1, p2, p3, p4);
+	} else {
+		kernel_neon_begin();
+		xor_block_neon_inner.do_4(bytes, p1, p2, p3, p4);
+		kernel_neon_end();
+	}
+}
+
+static void
+xor_neon_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+		unsigned long *p3, unsigned long *p4, unsigned long *p5)
+{
+	if (in_interrupt()) {
+		xor_arm4regs_5(bytes, p1, p2, p3, p4, p5);
+	} else {
+		kernel_neon_begin();
+		xor_block_neon_inner.do_5(bytes, p1, p2, p3, p4, p5);
+		kernel_neon_end();
+	}
+}
+
+static struct xor_block_template xor_block_neon = {
+	.name	= "neon",
+	.do_2	= xor_neon_2,
+	.do_3	= xor_neon_3,
+	.do_4	= xor_neon_4,
+	.do_5	= xor_neon_5
+};
+
+#define NEON_TEMPLATES	\
+	do { if (cpu_has_neon()) xor_speed(&xor_block_neon); } while (0)
+#else
+#define NEON_TEMPLATES
+#endif