Fixed MTP to work with TWRP

arch/arm/include/asm/Kbuild

@@ -0,0 +1,40 @@
+
+
+generic-y += auxvec.h
+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 += hash.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 += 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

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

arch/arm/include/asm/asm-offsets.h

@@ -0,0 +1 @@
+#include <generated/asm-offsets.h>

arch/arm/include/asm/assembler.h

@@ -0,0 +1,451 @@
+/*
+ *  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 != 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__ */

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

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

arch/arm/include/asm/barrier.h

@@ -0,0 +1,86 @@
+#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)
+#else
+#define mb()		barrier()
+#define rmb()		barrier()
+#define 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 */

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 */

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

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

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

arch/arm/include/asm/cacheflush.h

@@ -0,0 +1,492 @@
+/*
+ *  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);
+
+void flush_uprobe_xol_access(struct page *page, unsigned long uaddr,
+			     void *kaddr, unsigned long len);
+#endif

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

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

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

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 */

arch/arm/include/asm/compiler.h

@@ -0,0 +1,15 @@
+#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)
+ */
+#define __asmeq(x, y)  ".ifnc " x "," y " ; .err ; .endif\n\t"
+
+
+#endif /* __ASM_ARM_COMPILER_H */

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

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

arch/arm/include/asm/cpuidle.h

@@ -0,0 +1,29 @@
+#ifndef __ASM_ARM_CPUIDLE_H
+#define __ASM_ARM_CPUIDLE_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,\
+	.flags                  = CPUIDLE_FLAG_TIME_VALID,\
+	.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)
+
+#endif

arch/arm/include/asm/cputype.h

@@ -0,0 +1,256 @@
+#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
+#endif

arch/arm/include/asm/crypto/sha1.h

@@ -0,0 +1,10 @@
+#ifndef ASM_ARM_CRYPTO_SHA1_H
+#define ASM_ARM_CRYPTO_SHA1_H
+
+#include <linux/crypto.h>
+#include <crypto/sha.h>
+
+extern int sha1_update_arm(struct shash_desc *desc, const u8 *data,
+			   unsigned int len);
+
+#endif

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

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();
+}

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) */
+

arch/arm/include/asm/device.h

@@ -0,0 +1,36 @@
+/*
+ * 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
+};
+
+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

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

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

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, size_t 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

arch/arm/include/asm/dma-mapping.h

@@ -0,0 +1,332 @@
+#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)
+
+static inline int set_arch_dma_coherent_ops(struct device *dev)
+{
+	set_dma_ops(dev, &arm_coherent_dma_ops);
+	return 0;
+}
+#define set_arch_dma_coherent_ops(dev)	set_arch_dma_coherent_ops(dev)
+
+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

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 */

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 */

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

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

arch/arm/include/asm/elf.h

@@ -0,0 +1,138 @@
+#ifndef __ASMARM_ELF_H
+#define __ASMARM_ELF_H
+
+#include <asm/hwcap.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))
+
+struct mm_struct;
+extern unsigned long arch_randomize_brk(struct mm_struct *mm);
+#define arch_randomize_brk arch_randomize_brk
+
+#ifdef CONFIG_MMU
+#define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1
+struct linux_binprm;
+int arch_setup_additional_pages(struct linux_binprm *, int);
+#endif
+
+#endif

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

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 */

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_ */

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

arch/arm/include/asm/fiq_glue.h

@@ -0,0 +1,33 @@
+/*
+ * Copyright (C) 2010 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * 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_FIQ_GLUE_H
+#define __ASM_FIQ_GLUE_H
+
+struct fiq_glue_handler {
+	void (*fiq)(struct fiq_glue_handler *h, void *regs, void *svc_sp);
+	void (*resume)(struct fiq_glue_handler *h);
+};
+typedef void (*fiq_return_handler_t)(void);
+
+int fiq_glue_register_handler(struct fiq_glue_handler *handler);
+int fiq_glue_set_return_handler(fiq_return_handler_t fiq_return);
+int fiq_glue_clear_return_handler(fiq_return_handler_t fiq_return);
+
+#ifdef CONFIG_FIQ_GLUE
+void fiq_glue_resume(void);
+#else
+static inline void fiq_glue_resume(void) {}
+#endif
+
+#endif

arch/arm/include/asm/firmware.h

@@ -0,0 +1,70 @@
+/*
+ * 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)(void);
+	/*
+	 * 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);
+};
+
+/* 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

arch/arm/include/asm/fixmap.h

@@ -0,0 +1,28 @@
+#ifndef _ASM_FIXMAP_H
+#define _ASM_FIXMAP_H
+
+#define FIXADDR_START		0xffc00000UL
+#define FIXADDR_TOP		0xffe00000UL
+#define FIXADDR_SIZE		(FIXADDR_TOP - FIXADDR_START)
+
+#define FIX_KMAP_NR_PTES	(FIXADDR_SIZE >> PAGE_SHIFT)
+
+#define __fix_to_virt(x)	(FIXADDR_START + ((x) << PAGE_SHIFT))
+#define __virt_to_fix(x)	(((x) - FIXADDR_START) >> PAGE_SHIFT)
+
+extern void __this_fixmap_does_not_exist(void);
+
+static inline unsigned long fix_to_virt(const unsigned int idx)
+{
+	if (idx >= FIX_KMAP_NR_PTES)
+		__this_fixmap_does_not_exist();
+	return __fix_to_virt(idx);
+}
+
+static inline unsigned int virt_to_fix(const unsigned long vaddr)
+{
+	BUG_ON(vaddr >= FIXADDR_TOP || vaddr < FIXADDR_START);
+	return __virt_to_fix(vaddr);
+}
+
+#endif

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__ */

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

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 */

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

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 */

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 .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 */

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

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

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

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

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

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 */

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	9
+
+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 */

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

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);
+

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

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);

arch/arm/include/asm/hardware/coresight.h

@@ -0,0 +1,185 @@
+/*
+ * linux/arch/arm/include/asm/hardware/coresight.h
+ *
+ * CoreSight components' registers
+ *
+ * Copyright (C) 2009 Nokia Corporation.
+ * Alexander Shishkin
+ *
+ * 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_HARDWARE_CORESIGHT_H
+#define __ASM_HARDWARE_CORESIGHT_H
+
+#define TRACER_ACCESSED_BIT	0
+#define TRACER_RUNNING_BIT	1
+#define TRACER_CYCLE_ACC_BIT	2
+#define TRACER_TRACE_DATA_BIT	3
+#define TRACER_TIMESTAMP_BIT	4
+#define TRACER_BRANCHOUTPUT_BIT	5
+#define TRACER_RETURN_STACK_BIT	6
+#define TRACER_ACCESSED		BIT(TRACER_ACCESSED_BIT)
+#define TRACER_RUNNING		BIT(TRACER_RUNNING_BIT)
+#define TRACER_CYCLE_ACC	BIT(TRACER_CYCLE_ACC_BIT)
+#define TRACER_TRACE_DATA	BIT(TRACER_TRACE_DATA_BIT)
+#define TRACER_TIMESTAMP	BIT(TRACER_TIMESTAMP_BIT)
+#define TRACER_BRANCHOUTPUT	BIT(TRACER_BRANCHOUTPUT_BIT)
+#define TRACER_RETURN_STACK	BIT(TRACER_RETURN_STACK_BIT)
+
+#define TRACER_TIMEOUT 10000
+
+#define etm_writel(t, id, v, x) \
+	(writel_relaxed((v), (t)->etm_regs[(id)] + (x)))
+#define etm_readl(t, id, x) (readl_relaxed((t)->etm_regs[(id)] + (x)))
+
+/* CoreSight Management Registers */
+#define CSMR_LOCKACCESS 0xfb0
+#define CSMR_LOCKSTATUS 0xfb4
+#define CSMR_AUTHSTATUS 0xfb8
+#define CSMR_DEVID	0xfc8
+#define CSMR_DEVTYPE	0xfcc
+/* CoreSight Component Registers */
+#define CSCR_CLASS	0xff4
+
+#define CS_LAR_KEY	0xc5acce55
+
+/* ETM control register, "ETM Architecture", 3.3.1 */
+#define ETMR_CTRL		0
+#define ETMCTRL_POWERDOWN	1
+#define ETMCTRL_PROGRAM		(1 << 10)
+#define ETMCTRL_PORTSEL		(1 << 11)
+#define ETMCTRL_CONTEXTIDSIZE(x) (((x) & 3) << 14)
+#define ETMCTRL_PORTMASK1	(7 << 4)
+#define ETMCTRL_PORTMASK2	(1 << 21)
+#define ETMCTRL_PORTMASK	(ETMCTRL_PORTMASK1 | ETMCTRL_PORTMASK2)
+#define ETMCTRL_PORTSIZE(x) ((((x) & 7) << 4) | (!!((x) & 8)) << 21)
+#define ETMCTRL_DO_CPRT		(1 << 1)
+#define ETMCTRL_DATAMASK	(3 << 2)
+#define ETMCTRL_DATA_DO_DATA	(1 << 2)
+#define ETMCTRL_DATA_DO_ADDR	(1 << 3)
+#define ETMCTRL_DATA_DO_BOTH	(ETMCTRL_DATA_DO_DATA | ETMCTRL_DATA_DO_ADDR)
+#define ETMCTRL_BRANCH_OUTPUT	(1 << 8)
+#define ETMCTRL_CYCLEACCURATE	(1 << 12)
+#define ETMCTRL_TIMESTAMP_EN	(1 << 28)
+#define ETMCTRL_RETURN_STACK_EN	(1 << 29)
+
+/* ETM configuration code register */
+#define ETMR_CONFCODE		(0x04)
+#define ETMCCR_ETMIDR_PRESENT	BIT(31)
+
+/* ETM trace start/stop resource control register */
+#define ETMR_TRACESSCTRL	(0x18)
+
+/* ETM trigger event register */
+#define ETMR_TRIGEVT		(0x08)
+
+/* address access type register bits, "ETM architecture",
+ * table 3-27 */
+/* - access type */
+#define ETMAAT_IFETCH		0
+#define ETMAAT_IEXEC		1
+#define ETMAAT_IEXECPASS	2
+#define ETMAAT_IEXECFAIL	3
+#define ETMAAT_DLOADSTORE	4
+#define ETMAAT_DLOAD		5
+#define ETMAAT_DSTORE		6
+/* - comparison access size */
+#define ETMAAT_JAVA		(0 << 3)
+#define ETMAAT_THUMB		(1 << 3)
+#define ETMAAT_ARM		(3 << 3)
+/* - data value comparison control */
+#define ETMAAT_NOVALCMP		(0 << 5)
+#define ETMAAT_VALMATCH		(1 << 5)
+#define ETMAAT_VALNOMATCH	(3 << 5)
+/* - exact match */
+#define ETMAAT_EXACTMATCH	(1 << 7)
+/* - context id comparator control */
+#define ETMAAT_IGNCONTEXTID	(0 << 8)
+#define ETMAAT_VALUE1		(1 << 8)
+#define ETMAAT_VALUE2		(2 << 8)
+#define ETMAAT_VALUE3		(3 << 8)
+/* - security level control */
+#define ETMAAT_IGNSECURITY	(0 << 10)
+#define ETMAAT_NSONLY		(1 << 10)
+#define ETMAAT_SONLY		(2 << 10)
+
+#define ETMR_COMP_VAL(x)	(0x40 + (x) * 4)
+#define ETMR_COMP_ACC_TYPE(x)	(0x80 + (x) * 4)
+
+/* ETM status register, "ETM Architecture", 3.3.2 */
+#define ETMR_STATUS		(0x10)
+#define ETMST_OVERFLOW		BIT(0)
+#define ETMST_PROGBIT		BIT(1)
+#define ETMST_STARTSTOP		BIT(2)
+#define ETMST_TRIGGER		BIT(3)
+
+#define etm_progbit(t)		(etm_readl((t), ETMR_STATUS) & ETMST_PROGBIT)
+#define etm_started(t)		(etm_readl((t), ETMR_STATUS) & ETMST_STARTSTOP)
+#define etm_triggered(t)	(etm_readl((t), ETMR_STATUS) & ETMST_TRIGGER)
+
+#define ETMR_TRACEENCTRL2	0x1c
+#define ETMR_TRACEENCTRL	0x24
+#define ETMTE_INCLEXCL		BIT(24)
+#define ETMR_TRACEENEVT		0x20
+
+#define ETMR_VIEWDATAEVT	0x30
+#define ETMR_VIEWDATACTRL1	0x34
+#define ETMR_VIEWDATACTRL2	0x38
+#define ETMR_VIEWDATACTRL3	0x3c
+#define ETMVDC3_EXCLONLY	BIT(16)
+
+#define ETMCTRL_OPTS		(ETMCTRL_DO_CPRT)
+
+#define ETMR_ID			0x1e4
+#define ETMIDR_VERSION(x)	(((x) >> 4) & 0xff)
+#define ETMIDR_VERSION_3_1	0x21
+#define ETMIDR_VERSION_PFT_1_0	0x30
+
+#define ETMR_CCE		0x1e8
+#define ETMCCER_RETURN_STACK_IMPLEMENTED	BIT(23)
+#define ETMCCER_TIMESTAMPING_IMPLEMENTED	BIT(22)
+
+#define ETMR_TRACEIDR		0x200
+
+/* ETM management registers, "ETM Architecture", 3.5.24 */
+#define ETMMR_OSLAR	0x300
+#define ETMMR_OSLSR	0x304
+#define ETMMR_OSSRR	0x308
+#define ETMMR_PDSR	0x314
+
+/* ETB registers, "CoreSight Components TRM", 9.3 */
+#define ETBR_DEPTH		0x04
+#define ETBR_STATUS		0x0c
+#define ETBR_READMEM		0x10
+#define ETBR_READADDR		0x14
+#define ETBR_WRITEADDR		0x18
+#define ETBR_TRIGGERCOUNT	0x1c
+#define ETBR_CTRL		0x20
+#define ETBR_FORMATTERCTRL	0x304
+#define ETBFF_ENFTC		1
+#define ETBFF_ENFCONT		BIT(1)
+#define ETBFF_FONFLIN		BIT(4)
+#define ETBFF_MANUAL_FLUSH	BIT(6)
+#define ETBFF_TRIGIN		BIT(8)
+#define ETBFF_TRIGEVT		BIT(9)
+#define ETBFF_TRIGFL		BIT(10)
+#define ETBFF_STOPFL		BIT(12)
+
+#define etb_writel(t, v, x) \
+	(writel_relaxed((v), (t)->etb_regs + (x)))
+#define etb_readl(t, x) (readl_relaxed((t)->etb_regs + (x)))
+
+#define etm_lock(t, id) \
+	do { etm_writel((t), (id), 0, CSMR_LOCKACCESS); } while (0)
+#define etm_unlock(t, id) \
+	do { etm_writel((t), (id), CS_LAR_KEY, CSMR_LOCKACCESS); } while (0)
+
+#define etb_lock(t) do { etb_writel((t), 0, CSMR_LOCKACCESS); } while (0)
+#define etb_unlock(t) \
+	do { etb_writel((t), CS_LAR_KEY, CSMR_LOCKACCESS); } while (0)
+
+#endif /* __ASM_HARDWARE_CORESIGHT_H */
+

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)
+
+

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
+

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

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

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

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 */

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

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

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 */

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

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

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 */

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);

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

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);
+
+}

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

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 */

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 */

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 */

arch/arm/include/asm/hw_irq.h

@@ -0,0 +1,21 @@
+/*
+ * 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++;
+}
+
+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

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

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

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 */

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 */

arch/arm/include/asm/io.h

@@ -0,0 +1,423 @@
+/*
+ *  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.
+ */
+extern void __raw_writesb(void __iomem *addr, const void *data, int bytelen);
+extern void __raw_writesw(void __iomem *addr, const void *data, int wordlen);
+extern void __raw_writesl(void __iomem *addr, const void *data, int longlen);
+
+extern void __raw_readsb(const void __iomem *addr, void *data, int bytelen);
+extern void __raw_readsw(const void __iomem *addr, void *data, int wordlen);
+extern void __raw_readsl(const 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).
+ */
+static inline void __raw_writew(u16 val, volatile void __iomem *addr)
+{
+	asm volatile("strh %1, %0"
+		     : "+Q" (*(volatile u16 __force *)addr)
+		     : "r" (val));
+}
+
+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
+
+static inline void __raw_writeb(u8 val, volatile void __iomem *addr)
+{
+	asm volatile("strb %1, %0"
+		     : "+Qo" (*(volatile u8 __force *)addr)
+		     : "r" (val));
+}
+
+static inline void __raw_writel(u32 val, volatile void __iomem *addr)
+{
+	asm volatile("str %1, %0"
+		     : "+Qo" (*(volatile u32 __force *)addr)
+		     : "r" (val));
+}
+
+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;
+}
+
+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
+
+#define outb_p(val,port)	outb((val),(port))
+#define outw_p(val,port)	outw((val),(port))
+#define outl_p(val,port)	outl((val),(port))
+#define inb_p(port)		inb((port))
+#define inw_p(port)		inw((port))
+#define inl_p(port)		inl((port))
+
+#define outsb_p(port,from,len)	outsb(port,from,len)
+#define outsw_p(port,from,len)	outsw(port,from,len)
+#define outsl_p(port,from,len)	outsl(port,from,len)
+#define insb_p(port,to,len)	insb(port,to,len)
+#define insw_p(port,to,len)	insw(port,to,len)
+#define insl_p(port,to,len)	insl(port,to,len)
+
+/*
+ * 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}{8,16,32} macros
+ */
+#ifndef ioread8
+#define ioread8(p)	({ unsigned int __v = __raw_readb(p); __iormb(); __v; })
+#define ioread16(p)	({ unsigned int __v = le16_to_cpu((__force __le16)__raw_readw(p)); __iormb(); __v; })
+#define ioread32(p)	({ unsigned int __v = le32_to_cpu((__force __le32)__raw_readl(p)); __iormb(); __v; })
+
+#define ioread16be(p)	({ unsigned int __v = be16_to_cpu((__force __be16)__raw_readw(p)); __iormb(); __v; })
+#define ioread32be(p)	({ unsigned int __v = be32_to_cpu((__force __be32)__raw_readl(p)); __iormb(); __v; })
+
+#define iowrite8(v,p)	({ __iowmb(); __raw_writeb(v, p); })
+#define iowrite16(v,p)	({ __iowmb(); __raw_writew((__force __u16)cpu_to_le16(v), p); })
+#define iowrite32(v,p)	({ __iowmb(); __raw_writel((__force __u32)cpu_to_le32(v), p); })
+
+#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); })
+
+#define ioread8_rep(p,d,c)	__raw_readsb(p,d,c)
+#define ioread16_rep(p,d,c)	__raw_readsw(p,d,c)
+#define ioread32_rep(p,d,c)	__raw_readsl(p,d,c)
+
+#define iowrite8_rep(p,s,c)	__raw_writesb(p,s,c)
+#define iowrite16_rep(p,s,c)	__raw_writesw(p,s,c)
+#define iowrite32_rep(p,s,c)	__raw_writesl(p,s,c)
+
+extern void __iomem *ioport_map(unsigned long port, unsigned int nr);
+extern void ioport_unmap(void __iomem *addr);
+#endif
+
+struct pci_dev;
+
+extern void pci_iounmap(struct pci_dev *dev, void __iomem *addr);
+
+/*
+ * 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
+
+/*
+ * 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
+
+/*
+ * 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 */

arch/arm/include/asm/irq.h

@@ -0,0 +1,44 @@
+#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
+
+void arch_trigger_all_cpu_backtrace(void);
+#define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace
+
+#endif
+
+#endif
+

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 */

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 */

arch/arm/include/asm/jump_label.h

@@ -0,0 +1,40 @@
+#ifndef _ASM_ARM_JUMP_LABEL_H
+#define _ASM_ARM_JUMP_LABEL_H
+
+#ifdef __KERNEL__
+
+#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;
+}
+
+#endif /* __KERNEL__ */
+
+typedef u32 jump_label_t;
+
+struct jump_entry {
+	jump_label_t code;
+	jump_label_t target;
+	jump_label_t key;
+};
+
+#endif

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 */

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__ */

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

arch/arm/include/asm/kprobes.h

@@ -0,0 +1,55 @@
+/*
+ * 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 MAX_STACK_SIZE			64	/* 32 would probably be OK */
+
+#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);
+
+
+#endif /* _ARM_KPROBES_H */

arch/arm/include/asm/kvm_arm.h

@@ -0,0 +1,220 @@
+/*
+ * 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_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__ */

arch/arm/include/asm/kvm_asm.h

@@ -0,0 +1,103 @@
+/*
+ * 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 int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
+#endif
+
+#endif /* __ARM_KVM_ASM_H__ */

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__ */

arch/arm/include/asm/kvm_emulate.h

@@ -0,0 +1,235 @@
+/*
+ * 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>
+
+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 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(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.cp15[c0_MPIDR];
+}
+
+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__ */

arch/arm/include/asm/kvm_host.h

@@ -0,0 +1,245 @@
+/*
+ * 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>
+
+#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;
+};
+
+#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.
+	 */
+	/* dcache set/way operation pending */
+	int last_pcpu;
+	cpumask_t require_dcache_flush;
+
+	/* 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_wakeup;
+};
+
+int kvm_vcpu_set_target(struct kvm_vcpu *vcpu,
+			const struct kvm_vcpu_init *init);
+int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init);
+unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu);
+int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices);
+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);
+
+/* We do not have shadow page tables, hence the empty hooks */
+static inline int kvm_age_hva(struct kvm *kvm, unsigned long start,
+			      unsigned long end)
+{
+	return 0;
+}
+
+static inline int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
+{
+	return 0;
+}
+
+static inline void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm,
+							 unsigned long address)
+{
+}
+
+struct kvm_vcpu *kvm_arm_get_running_vcpu(void);
+struct kvm_vcpu __percpu **kvm_get_running_vcpus(void);
+
+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);
+
+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__ */

arch/arm/include/asm/kvm_mmio.h

@@ -0,0 +1,56 @@
+/*
+ * 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;
+};
+
+/*
+ * The in-kernel MMIO emulation code wants to use a copy of run->mmio,
+ * which is an anonymous type. Use our own type instead.
+ */
+struct kvm_exit_mmio {
+	phys_addr_t	phys_addr;
+	u8		data[8];
+	u32		len;
+	bool		is_write;
+};
+
+static inline void kvm_prepare_mmio(struct kvm_run *run,
+				    struct kvm_exit_mmio *mmio)
+{
+	run->mmio.phys_addr	= mmio->phys_addr;
+	run->mmio.len		= mmio->len;
+	run->mmio.is_write	= mmio->is_write;
+	memcpy(run->mmio.data, mmio->data, mmio->len);
+	run->exit_reason	= KVM_EXIT_MMIO;
+}
+
+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__ */

arch/arm/include/asm/kvm_mmu.h

@@ -0,0 +1,252 @@
+/*
+ * 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;
+}
+
+/* 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 stage2_flush_vm(struct kvm *kvm);
+
+#endif	/* !__ASSEMBLY__ */
+
+#endif /* __ARM_KVM_MMU_H__ */