Initial import

154 files changed, 11862 insertions, 0 deletions

diff --git a/arch/sh/include/asm/Kbuild b/arch/sh/include/asm/Kbuild
new file mode 100644
index 000000000..654ebb6bd
--- /dev/null
+++ b/arch/sh/include/asm/Kbuild
@@ -0,0 +1,39 @@
+
+generic-y += bitsperlong.h
+generic-y += cputime.h
+generic-y += current.h
+generic-y += delay.h
+generic-y += div64.h
+generic-y += emergency-restart.h
+generic-y += errno.h
+generic-y += exec.h
+generic-y += fcntl.h
+generic-y += ioctl.h
+generic-y += ipcbuf.h
+generic-y += irq_regs.h
+generic-y += irq_work.h
+generic-y += kvm_para.h
+generic-y += local.h
+generic-y += local64.h
+generic-y += mcs_spinlock.h
+generic-y += mman.h
+generic-y += msgbuf.h
+generic-y += param.h
+generic-y += parport.h
+generic-y += percpu.h
+generic-y += poll.h
+generic-y += preempt.h
+generic-y += resource.h
+generic-y += scatterlist.h
+generic-y += sembuf.h
+generic-y += serial.h
+generic-y += shmbuf.h
+generic-y += siginfo.h
+generic-y += sizes.h
+generic-y += socket.h
+generic-y += statfs.h
+generic-y += termbits.h
+generic-y += termios.h
+generic-y += trace_clock.h
+generic-y += ucontext.h
+generic-y += xor.h
diff --git a/arch/sh/include/asm/adc.h b/arch/sh/include/asm/adc.h
new file mode 100644
index 000000000..48824c1fa
--- /dev/null
+++ b/arch/sh/include/asm/adc.h
@@ -0,0 +1,13 @@
+#ifndef __ASM_ADC_H
+#define __ASM_ADC_H
+#ifdef __KERNEL__
+/*
+ * Copyright (C) 2004  Andriy Skulysh
+ */
+
+#include <cpu/adc.h>
+
+int adc_single(unsigned int channel);
+
+#endif /* __KERNEL__ */
+#endif /* __ASM_ADC_H */
diff --git a/arch/sh/include/asm/addrspace.h b/arch/sh/include/asm/addrspace.h
new file mode 100644
index 000000000..3d1ae2bfa
--- /dev/null
+++ b/arch/sh/include/asm/addrspace.h
@@ -0,0 +1,69 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 1999 by Kaz Kojima
+ *
+ * Defitions for the address spaces of the SH CPUs.
+ */
+#ifndef __ASM_SH_ADDRSPACE_H
+#define __ASM_SH_ADDRSPACE_H
+
+#ifdef __KERNEL__
+
+#include <cpu/addrspace.h>
+
+/* If this CPU supports segmentation, hook up the helpers */
+#ifdef P1SEG
+
+/*
+   [ P0/U0 (virtual) ]		0x00000000     <------ User space
+   [ P1 (fixed)   cached ]	0x80000000     <------ Kernel space
+   [ P2 (fixed)  non-cachable]	0xA0000000     <------ Physical access
+   [ P3 (virtual) cached]	0xC0000000     <------ vmalloced area
+   [ P4 control   ]		0xE0000000
+ */
+
+/* Returns the privileged segment base of a given address  */
+#define PXSEG(a)	(((unsigned long)(a)) & 0xe0000000)
+
+#ifdef CONFIG_29BIT
+/*
+ * Map an address to a certain privileged segment
+ */
+#define P1SEGADDR(a)	\
+	((__typeof__(a))(((unsigned long)(a) & 0x1fffffff) | P1SEG))
+#define P2SEGADDR(a)	\
+	((__typeof__(a))(((unsigned long)(a) & 0x1fffffff) | P2SEG))
+#define P3SEGADDR(a)	\
+	((__typeof__(a))(((unsigned long)(a) & 0x1fffffff) | P3SEG))
+#define P4SEGADDR(a)	\
+	((__typeof__(a))(((unsigned long)(a) & 0x1fffffff) | P4SEG))
+#else
+/*
+ * These will never work in 32-bit, don't even bother.
+ */
+#define P1SEGADDR(a)	({ (void)(a); BUG(); NULL; })
+#define P2SEGADDR(a)	({ (void)(a); BUG(); NULL; })
+#define P3SEGADDR(a)	({ (void)(a); BUG(); NULL; })
+#define P4SEGADDR(a)	({ (void)(a); BUG(); NULL; })
+#endif
+#endif /* P1SEG */
+
+/* Check if an address can be reached in 29 bits */
+#define IS_29BIT(a)	(((unsigned long)(a)) < 0x20000000)
+
+#ifdef CONFIG_SH_STORE_QUEUES
+/*
+ * This is a special case for the SH-4 store queues, as pages for this
+ * space still need to be faulted in before it's possible to flush the
+ * store queue cache for writeout to the remapped region.
+ */
+#define P3_ADDR_MAX		(P4SEG_STORE_QUE + 0x04000000)
+#else
+#define P3_ADDR_MAX		P4SEG
+#endif
+
+#endif /* __KERNEL__ */
+#endif /* __ASM_SH_ADDRSPACE_H */
diff --git a/arch/sh/include/asm/alignment.h b/arch/sh/include/asm/alignment.h
new file mode 100644
index 000000000..b12efecf5
--- /dev/null
+++ b/arch/sh/include/asm/alignment.h
@@ -0,0 +1,21 @@
+#ifndef __ASM_SH_ALIGNMENT_H
+#define __ASM_SH_ALIGNMENT_H
+
+#include <linux/types.h>
+
+extern void inc_unaligned_byte_access(void);
+extern void inc_unaligned_word_access(void);
+extern void inc_unaligned_dword_access(void);
+extern void inc_unaligned_multi_access(void);
+extern void inc_unaligned_user_access(void);
+extern void inc_unaligned_kernel_access(void);
+
+#define UM_WARN		(1 << 0)
+#define UM_FIXUP	(1 << 1)
+#define UM_SIGNAL	(1 << 2)
+
+extern unsigned int unaligned_user_action(void);
+
+extern void unaligned_fixups_notify(struct task_struct *, insn_size_t, struct pt_regs *);
+
+#endif /* __ASM_SH_ALIGNMENT_H */
diff --git a/arch/sh/include/asm/asm-offsets.h b/arch/sh/include/asm/asm-offsets.h
new file mode 100644
index 000000000..d370ee36a
--- /dev/null
+++ b/arch/sh/include/asm/asm-offsets.h
@@ -0,0 +1 @@
+#include <generated/asm-offsets.h>
diff --git a/arch/sh/include/asm/atomic-grb.h b/arch/sh/include/asm/atomic-grb.h
new file mode 100644
index 000000000..97a5fda83
--- /dev/null
+++ b/arch/sh/include/asm/atomic-grb.h
@@ -0,0 +1,94 @@
+#ifndef __ASM_SH_ATOMIC_GRB_H
+#define __ASM_SH_ATOMIC_GRB_H
+
+#define ATOMIC_OP(op)							\
+static inline void atomic_##op(int i, atomic_t *v)			\
+{									\
+	int tmp;							\
+									\
+	__asm__ __volatile__ (						\
+		"   .align 2              \n\t"				\
+		"   mova    1f,   r0      \n\t" /* r0 = end point */	\
+		"   mov    r15,   r1      \n\t" /* r1 = saved sp */	\
+		"   mov    #-6,   r15     \n\t" /* LOGIN: r15 = size */	\
+		"   mov.l  @%1,   %0      \n\t" /* load  old value */	\
+		" " #op "   %2,   %0      \n\t" /* $op */		\
+		"   mov.l   %0,   @%1     \n\t" /* store new value */	\
+		"1: mov     r1,   r15     \n\t" /* LOGOUT */		\
+		: "=&r" (tmp),						\
+		  "+r"  (v)						\
+		: "r"   (i)						\
+		: "memory" , "r0", "r1");				\
+}									\
+
+#define ATOMIC_OP_RETURN(op)						\
+static inline int atomic_##op##_return(int i, atomic_t *v)		\
+{									\
+	int tmp;							\
+									\
+	__asm__ __volatile__ (						\
+		"   .align 2              \n\t"				\
+		"   mova    1f,   r0      \n\t" /* r0 = end point */	\
+		"   mov    r15,   r1      \n\t" /* r1 = saved sp */	\
+		"   mov    #-6,   r15     \n\t" /* LOGIN: r15 = size */	\
+		"   mov.l  @%1,   %0      \n\t" /* load  old value */	\
+		" " #op "   %2,   %0      \n\t" /* $op */		\
+		"   mov.l   %0,   @%1     \n\t" /* store new value */	\
+		"1: mov     r1,   r15     \n\t" /* LOGOUT */		\
+		: "=&r" (tmp),						\
+		  "+r"  (v)						\
+		: "r"   (i)						\
+		: "memory" , "r0", "r1");				\
+									\
+	return tmp;							\
+}
+
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op)
+
+ATOMIC_OPS(add)
+ATOMIC_OPS(sub)
+
+#undef ATOMIC_OPS
+#undef ATOMIC_OP_RETURN
+#undef ATOMIC_OP
+
+static inline void atomic_clear_mask(unsigned int mask, atomic_t *v)
+{
+	int tmp;
+	unsigned int _mask = ~mask;
+
+	__asm__ __volatile__ (
+		"   .align 2              \n\t"
+		"   mova    1f,   r0      \n\t" /* r0 = end point */
+		"   mov    r15,   r1      \n\t" /* r1 = saved sp */
+		"   mov    #-6,   r15     \n\t" /* LOGIN: r15 = size */
+		"   mov.l  @%1,   %0      \n\t" /* load  old value */
+		"   and     %2,   %0      \n\t" /* add */
+		"   mov.l   %0,   @%1     \n\t" /* store new value */
+		"1: mov     r1,   r15     \n\t" /* LOGOUT */
+		: "=&r" (tmp),
+		  "+r"  (v)
+		: "r"   (_mask)
+		: "memory" , "r0", "r1");
+}
+
+static inline void atomic_set_mask(unsigned int mask, atomic_t *v)
+{
+	int tmp;
+
+	__asm__ __volatile__ (
+		"   .align 2              \n\t"
+		"   mova    1f,   r0      \n\t" /* r0 = end point */
+		"   mov    r15,   r1      \n\t" /* r1 = saved sp */
+		"   mov    #-6,   r15     \n\t" /* LOGIN: r15 = size */
+		"   mov.l  @%1,   %0      \n\t" /* load  old value */
+		"   or      %2,   %0      \n\t" /* or */
+		"   mov.l   %0,   @%1     \n\t" /* store new value */
+		"1: mov     r1,   r15     \n\t" /* LOGOUT */
+		: "=&r" (tmp),
+		  "+r"  (v)
+		: "r"   (mask)
+		: "memory" , "r0", "r1");
+}
+
+#endif /* __ASM_SH_ATOMIC_GRB_H */
diff --git a/arch/sh/include/asm/atomic-irq.h b/arch/sh/include/asm/atomic-irq.h
new file mode 100644
index 000000000..61d107523
--- /dev/null
+++ b/arch/sh/include/asm/atomic-irq.h
@@ -0,0 +1,63 @@
+#ifndef __ASM_SH_ATOMIC_IRQ_H
+#define __ASM_SH_ATOMIC_IRQ_H
+
+#include <linux/irqflags.h>
+
+/*
+ * To get proper branch prediction for the main line, we must branch
+ * forward to code at the end of this object's .text section, then
+ * branch back to restart the operation.
+ */
+
+#define ATOMIC_OP(op, c_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)					\
+static inline int atomic_##op##_return(int i, atomic_t *v)		\
+{									\
+	unsigned long temp, flags;					\
+									\
+	raw_local_irq_save(flags);					\
+	temp = v->counter;						\
+	temp c_op i;							\
+	v->counter = temp;						\
+	raw_local_irq_restore(flags);					\
+									\
+	return temp;							\
+}
+
+#define ATOMIC_OPS(op, c_op) ATOMIC_OP(op, c_op) ATOMIC_OP_RETURN(op, c_op)
+
+ATOMIC_OPS(add, +=)
+ATOMIC_OPS(sub, -=)
+
+#undef ATOMIC_OPS
+#undef ATOMIC_OP_RETURN
+#undef ATOMIC_OP
+
+static inline void atomic_clear_mask(unsigned int mask, atomic_t *v)
+{
+	unsigned long flags;
+
+	raw_local_irq_save(flags);
+	v->counter &= ~mask;
+	raw_local_irq_restore(flags);
+}
+
+static inline void atomic_set_mask(unsigned int mask, atomic_t *v)
+{
+	unsigned long flags;
+
+	raw_local_irq_save(flags);
+	v->counter |= mask;
+	raw_local_irq_restore(flags);
+}
+
+#endif /* __ASM_SH_ATOMIC_IRQ_H */
diff --git a/arch/sh/include/asm/atomic-llsc.h b/arch/sh/include/asm/atomic-llsc.h
new file mode 100644
index 000000000..8575dccb9
--- /dev/null
+++ b/arch/sh/include/asm/atomic-llsc.h
@@ -0,0 +1,88 @@
+#ifndef __ASM_SH_ATOMIC_LLSC_H
+#define __ASM_SH_ATOMIC_LLSC_H
+
+/*
+ * SH-4A note:
+ *
+ * We basically get atomic_xxx_return() for free compared with
+ * atomic_xxx(). movli.l/movco.l require r0 due to the instruction
+ * encoding, so the retval is automatically set without having to
+ * do any special work.
+ */
+/*
+ * To get proper branch prediction for the main line, we must branch
+ * forward to code at the end of this object's .text section, then
+ * branch back to restart the operation.
+ */
+
+#define ATOMIC_OP(op)							\
+static inline void atomic_##op(int i, atomic_t *v)			\
+{									\
+	unsigned long tmp;						\
+									\
+	__asm__ __volatile__ (						\
+"1:	movli.l @%2, %0		! atomic_" #op "\n"			\
+"	" #op "	%1, %0				\n"			\
+"	movco.l	%0, @%2				\n"			\
+"	bf	1b				\n"			\
+	: "=&z" (tmp)							\
+	: "r" (i), "r" (&v->counter)					\
+	: "t");								\
+}
+
+#define ATOMIC_OP_RETURN(op)						\
+static inline int atomic_##op##_return(int i, atomic_t *v)		\
+{									\
+	unsigned long temp;						\
+									\
+	__asm__ __volatile__ (						\
+"1:	movli.l @%2, %0		! atomic_" #op "_return	\n"		\
+"	" #op "	%1, %0					\n"		\
+"	movco.l	%0, @%2					\n"		\
+"	bf	1b					\n"		\
+"	synco						\n"		\
+	: "=&z" (temp)							\
+	: "r" (i), "r" (&v->counter)					\
+	: "t");								\
+									\
+	return temp;							\
+}
+
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op)
+
+ATOMIC_OPS(add)
+ATOMIC_OPS(sub)
+
+#undef ATOMIC_OPS
+#undef ATOMIC_OP_RETURN
+#undef ATOMIC_OP
+
+static inline void atomic_clear_mask(unsigned int mask, atomic_t *v)
+{
+	unsigned long tmp;
+
+	__asm__ __volatile__ (
+"1:	movli.l @%2, %0		! atomic_clear_mask	\n"
+"	and	%1, %0					\n"
+"	movco.l	%0, @%2					\n"
+"	bf	1b					\n"
+	: "=&z" (tmp)
+	: "r" (~mask), "r" (&v->counter)
+	: "t");
+}
+
+static inline void atomic_set_mask(unsigned int mask, atomic_t *v)
+{
+	unsigned long tmp;
+
+	__asm__ __volatile__ (
+"1:	movli.l @%2, %0		! atomic_set_mask	\n"
+"	or	%1, %0					\n"
+"	movco.l	%0, @%2					\n"
+"	bf	1b					\n"
+	: "=&z" (tmp)
+	: "r" (mask), "r" (&v->counter)
+	: "t");
+}
+
+#endif /* __ASM_SH_ATOMIC_LLSC_H */
diff --git a/arch/sh/include/asm/atomic.h b/arch/sh/include/asm/atomic.h
new file mode 100644
index 000000000..05b9f74ce
--- /dev/null
+++ b/arch/sh/include/asm/atomic.h
@@ -0,0 +1,66 @@
+#ifndef __ASM_SH_ATOMIC_H
+#define __ASM_SH_ATOMIC_H
+
+/*
+ * Atomic operations that C can't guarantee us.  Useful for
+ * resource counting etc..
+ *
+ */
+
+#include <linux/compiler.h>
+#include <linux/types.h>
+#include <asm/cmpxchg.h>
+#include <asm/barrier.h>
+
+#define ATOMIC_INIT(i)	{ (i) }
+
+#define atomic_read(v)		ACCESS_ONCE((v)->counter)
+#define atomic_set(v,i)		((v)->counter = (i))
+
+#if defined(CONFIG_GUSA_RB)
+#include <asm/atomic-grb.h>
+#elif defined(CONFIG_CPU_SH4A)
+#include <asm/atomic-llsc.h>
+#else
+#include <asm/atomic-irq.h>
+#endif
+
+#define atomic_add_negative(a, v)	(atomic_add_return((a), (v)) < 0)
+#define atomic_dec_return(v)		atomic_sub_return(1, (v))
+#define atomic_inc_return(v)		atomic_add_return(1, (v))
+#define atomic_inc_and_test(v)		(atomic_inc_return(v) == 0)
+#define atomic_sub_and_test(i,v)	(atomic_sub_return((i), (v)) == 0)
+#define atomic_dec_and_test(v)		(atomic_sub_return(1, (v)) == 0)
+
+#define atomic_inc(v)			atomic_add(1, (v))
+#define atomic_dec(v)			atomic_sub(1, (v))
+
+#define atomic_xchg(v, new)		(xchg(&((v)->counter), new))
+#define atomic_cmpxchg(v, o, n)		(cmpxchg(&((v)->counter), (o), (n)))
+
+/**
+ * __atomic_add_unless - add unless the number is a given value
+ * @v: pointer of type atomic_t
+ * @a: the amount to add to v...
+ * @u: ...unless v is equal to u.
+ *
+ * Atomically adds @a to @v, so long as it was not @u.
+ * Returns the old value of @v.
+ */
+static inline int __atomic_add_unless(atomic_t *v, int a, int u)
+{
+	int c, old;
+	c = atomic_read(v);
+	for (;;) {
+		if (unlikely(c == (u)))
+			break;
+		old = atomic_cmpxchg((v), c, c + (a));
+		if (likely(old == c))
+			break;
+		c = old;
+	}
+
+	return c;
+}
+
+#endif /* __ASM_SH_ATOMIC_H */
diff --git a/arch/sh/include/asm/barrier.h b/arch/sh/include/asm/barrier.h
new file mode 100644
index 000000000..43715308b
--- /dev/null
+++ b/arch/sh/include/asm/barrier.h
@@ -0,0 +1,39 @@
+/*
+ * Copyright (C) 1999, 2000  Niibe Yutaka  &  Kaz Kojima
+ * Copyright (C) 2002 Paul Mundt
+ */
+#ifndef __ASM_SH_BARRIER_H
+#define __ASM_SH_BARRIER_H
+
+#if defined(CONFIG_CPU_SH4A) || defined(CONFIG_CPU_SH5)
+#include <asm/cache_insns.h>
+#endif
+
+/*
+ * A brief note on ctrl_barrier(), the control register write barrier.
+ *
+ * Legacy SH cores typically require a sequence of 8 nops after
+ * modification of a control register in order for the changes to take
+ * effect. On newer cores (like the sh4a and sh5) this is accomplished
+ * with icbi.
+ *
+ * Also note that on sh4a in the icbi case we can forego a synco for the
+ * write barrier, as it's not necessary for control registers.
+ *
+ * Historically we have only done this type of barrier for the MMUCR, but
+ * it's also necessary for the CCR, so we make it generic here instead.
+ */
+#if defined(CONFIG_CPU_SH4A) || defined(CONFIG_CPU_SH5)
+#define mb()		__asm__ __volatile__ ("synco": : :"memory")
+#define rmb()		mb()
+#define wmb()		mb()
+#define ctrl_barrier()	__icbi(PAGE_OFFSET)
+#else
+#define ctrl_barrier()	__asm__ __volatile__ ("nop;nop;nop;nop;nop;nop;nop;nop")
+#endif
+
+#define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
+
+#include <asm-generic/barrier.h>
+
+#endif /* __ASM_SH_BARRIER_H */
diff --git a/arch/sh/include/asm/bitops-grb.h b/arch/sh/include/asm/bitops-grb.h
new file mode 100644
index 000000000..e73af33ac
--- /dev/null
+++ b/arch/sh/include/asm/bitops-grb.h
@@ -0,0 +1,172 @@
+#ifndef __ASM_SH_BITOPS_GRB_H
+#define __ASM_SH_BITOPS_GRB_H
+
+static inline void set_bit(int nr, volatile void * addr)
+{
+	int	mask;
+	volatile unsigned int *a = addr;
+	unsigned long tmp;
+
+	a += nr >> 5;
+	mask = 1 << (nr & 0x1f);
+
+        __asm__ __volatile__ (
+                "   .align 2              \n\t"
+                "   mova    1f,   r0      \n\t" /* r0 = end point */
+                "   mov    r15,   r1      \n\t" /* r1 = saved sp */
+                "   mov    #-6,   r15     \n\t" /* LOGIN: r15 = size */
+                "   mov.l  @%1,   %0      \n\t" /* load  old value */
+                "   or      %2,   %0      \n\t" /* or */
+                "   mov.l   %0,   @%1     \n\t" /* store new value */
+                "1: mov     r1,   r15     \n\t" /* LOGOUT */
+                : "=&r" (tmp),
+                  "+r"  (a)
+                : "r"   (mask)
+                : "memory" , "r0", "r1");
+}
+
+static inline void clear_bit(int nr, volatile void * addr)
+{
+	int	mask;
+	volatile unsigned int *a = addr;
+        unsigned long tmp;
+
+	a += nr >> 5;
+        mask = ~(1 << (nr & 0x1f));
+        __asm__ __volatile__ (
+                "   .align 2              \n\t"
+                "   mova    1f,   r0      \n\t" /* r0 = end point */
+                "   mov    r15,   r1      \n\t" /* r1 = saved sp */
+                "   mov    #-6,   r15     \n\t" /* LOGIN: r15 = size */
+                "   mov.l  @%1,   %0      \n\t" /* load  old value */
+                "   and     %2,   %0      \n\t" /* and */
+                "   mov.l   %0,   @%1     \n\t" /* store new value */
+                "1: mov     r1,   r15     \n\t" /* LOGOUT */
+                : "=&r" (tmp),
+                  "+r"  (a)
+                : "r"   (mask)
+                : "memory" , "r0", "r1");
+}
+
+static inline void change_bit(int nr, volatile void * addr)
+{
+        int     mask;
+        volatile unsigned int *a = addr;
+        unsigned long tmp;
+
+        a += nr >> 5;
+        mask = 1 << (nr & 0x1f);
+        __asm__ __volatile__ (
+                "   .align 2              \n\t"
+                "   mova    1f,   r0      \n\t" /* r0 = end point */
+                "   mov    r15,   r1      \n\t" /* r1 = saved sp */
+                "   mov    #-6,   r15     \n\t" /* LOGIN: r15 = size */
+                "   mov.l  @%1,   %0      \n\t" /* load  old value */
+                "   xor     %2,   %0      \n\t" /* xor */
+                "   mov.l   %0,   @%1     \n\t" /* store new value */
+                "1: mov     r1,   r15     \n\t" /* LOGOUT */
+                : "=&r" (tmp),
+                  "+r"  (a)
+                : "r"   (mask)
+                : "memory" , "r0", "r1");
+}
+
+static inline int test_and_set_bit(int nr, volatile void * addr)
+{
+        int     mask, retval;
+	volatile unsigned int *a = addr;
+        unsigned long tmp;
+
+	a += nr >> 5;
+	mask = 1 << (nr & 0x1f);
+
+        __asm__ __volatile__ (
+                "   .align 2              \n\t"
+                "   mova    1f,   r0      \n\t" /* r0 = end point */
+                "   mov    r15,   r1      \n\t" /* r1 = saved sp */
+                "   mov   #-14,   r15     \n\t" /* LOGIN: r15 = size */
+                "   mov.l  @%2,   %0      \n\t" /* load old value */
+                "   mov     %0,   %1      \n\t"
+                "   tst     %1,   %3      \n\t" /* T = ((*a & mask) == 0) */
+                "   mov    #-1,   %1      \n\t" /* retvat = -1 */
+                "   negc    %1,   %1      \n\t" /* retval = (mask & *a) != 0 */
+                "   or      %3,   %0      \n\t"
+                "   mov.l   %0,  @%2      \n\t" /* store new value */
+                "1: mov     r1,  r15      \n\t" /* LOGOUT */
+                : "=&r" (tmp),
+                  "=&r" (retval),
+                  "+r"  (a)
+                : "r"   (mask)
+                : "memory" , "r0", "r1" ,"t");
+
+        return retval;
+}
+
+static inline int test_and_clear_bit(int nr, volatile void * addr)
+{
+        int     mask, retval,not_mask;
+        volatile unsigned int *a = addr;
+        unsigned long tmp;
+
+        a += nr >> 5;
+        mask = 1 << (nr & 0x1f);
+
+	not_mask = ~mask;
+
+        __asm__ __volatile__ (
+                "   .align 2              \n\t"
+		"   mova    1f,   r0      \n\t" /* r0 = end point */
+                "   mov    r15,   r1      \n\t" /* r1 = saved sp */
+		"   mov   #-14,   r15     \n\t" /* LOGIN */
+		"   mov.l  @%2,   %0      \n\t" /* load old value */
+                "   mov     %0,   %1      \n\t" /* %1 = *a */
+                "   tst     %1,   %3      \n\t" /* T = ((*a & mask) == 0) */
+		"   mov    #-1,   %1      \n\t" /* retvat = -1 */
+                "   negc    %1,   %1      \n\t" /* retval = (mask & *a) != 0 */
+                "   and     %4,   %0      \n\t"
+                "   mov.l   %0,  @%2      \n\t" /* store new value */
+		"1: mov     r1,   r15     \n\t" /* LOGOUT */
+		: "=&r" (tmp),
+		  "=&r" (retval),
+		  "+r"  (a)
+		: "r"   (mask),
+		  "r"   (not_mask)
+		: "memory" , "r0", "r1", "t");
+
+        return retval;
+}
+
+static inline int test_and_change_bit(int nr, volatile void * addr)
+{
+        int     mask, retval;
+        volatile unsigned int *a = addr;
+        unsigned long tmp;
+
+        a += nr >> 5;
+        mask = 1 << (nr & 0x1f);
+
+        __asm__ __volatile__ (
+                "   .align 2              \n\t"
+                "   mova    1f,   r0      \n\t" /* r0 = end point */
+                "   mov    r15,   r1      \n\t" /* r1 = saved sp */
+                "   mov   #-14,   r15     \n\t" /* LOGIN */
+                "   mov.l  @%2,   %0      \n\t" /* load old value */
+                "   mov     %0,   %1      \n\t" /* %1 = *a */
+                "   tst     %1,   %3      \n\t" /* T = ((*a & mask) == 0) */
+                "   mov    #-1,   %1      \n\t" /* retvat = -1 */
+                "   negc    %1,   %1      \n\t" /* retval = (mask & *a) != 0 */
+                "   xor     %3,   %0      \n\t"
+                "   mov.l   %0,  @%2      \n\t" /* store new value */
+                "1: mov     r1,   r15     \n\t" /* LOGOUT */
+                : "=&r" (tmp),
+                  "=&r" (retval),
+                  "+r"  (a)
+                : "r"   (mask)
+                : "memory" , "r0", "r1", "t");
+
+        return retval;
+}
+
+#include <asm-generic/bitops/non-atomic.h>
+
+#endif /* __ASM_SH_BITOPS_GRB_H */
diff --git a/arch/sh/include/asm/bitops-llsc.h b/arch/sh/include/asm/bitops-llsc.h
new file mode 100644
index 000000000..d8328be06
--- /dev/null
+++ b/arch/sh/include/asm/bitops-llsc.h
@@ -0,0 +1,146 @@
+#ifndef __ASM_SH_BITOPS_LLSC_H
+#define __ASM_SH_BITOPS_LLSC_H
+
+static inline void set_bit(int nr, volatile void *addr)
+{
+	int	mask;
+	volatile unsigned int *a = addr;
+	unsigned long tmp;
+
+	a += nr >> 5;
+	mask = 1 << (nr & 0x1f);
+
+	__asm__ __volatile__ (
+		"1:						\n\t"
+		"movli.l	@%1, %0	! set_bit		\n\t"
+		"or		%2, %0				\n\t"
+		"movco.l	%0, @%1				\n\t"
+		"bf		1b				\n\t"
+		: "=&z" (tmp)
+		: "r" (a), "r" (mask)
+		: "t", "memory"
+	);
+}
+
+static inline void clear_bit(int nr, volatile void *addr)
+{
+	int	mask;
+	volatile unsigned int *a = addr;
+	unsigned long tmp;
+
+	a += nr >> 5;
+	mask = 1 << (nr & 0x1f);
+
+	__asm__ __volatile__ (
+		"1:						\n\t"
+		"movli.l	@%1, %0	! clear_bit		\n\t"
+		"and		%2, %0				\n\t"
+		"movco.l	%0, @%1				\n\t"
+		"bf		1b				\n\t"
+		: "=&z" (tmp)
+		: "r" (a), "r" (~mask)
+		: "t", "memory"
+	);
+}
+
+static inline void change_bit(int nr, volatile void *addr)
+{
+	int	mask;
+	volatile unsigned int *a = addr;
+	unsigned long tmp;
+
+	a += nr >> 5;
+	mask = 1 << (nr & 0x1f);
+
+	__asm__ __volatile__ (
+		"1:						\n\t"
+		"movli.l	@%1, %0	! change_bit		\n\t"
+		"xor		%2, %0				\n\t"
+		"movco.l	%0, @%1				\n\t"
+		"bf		1b				\n\t"
+		: "=&z" (tmp)
+		: "r" (a), "r" (mask)
+		: "t", "memory"
+	);
+}
+
+static inline int test_and_set_bit(int nr, volatile void *addr)
+{
+	int	mask, retval;
+	volatile unsigned int *a = addr;
+	unsigned long tmp;
+
+	a += nr >> 5;
+	mask = 1 << (nr & 0x1f);
+
+	__asm__ __volatile__ (
+		"1:						\n\t"
+		"movli.l	@%2, %0	! test_and_set_bit	\n\t"
+		"mov		%0, %1				\n\t"
+		"or		%3, %0				\n\t"
+		"movco.l	%0, @%2				\n\t"
+		"bf		1b				\n\t"
+		"and		%3, %1				\n\t"
+		: "=&z" (tmp), "=&r" (retval)
+		: "r" (a), "r" (mask)
+		: "t", "memory"
+	);
+
+	return retval != 0;
+}
+
+static inline int test_and_clear_bit(int nr, volatile void *addr)
+{
+	int	mask, retval;
+	volatile unsigned int *a = addr;
+	unsigned long tmp;
+
+	a += nr >> 5;
+	mask = 1 << (nr & 0x1f);
+
+	__asm__ __volatile__ (
+		"1:						\n\t"
+		"movli.l	@%2, %0	! test_and_clear_bit	\n\t"
+		"mov		%0, %1				\n\t"
+		"and		%4, %0				\n\t"
+		"movco.l	%0, @%2				\n\t"
+		"bf		1b				\n\t"
+		"and		%3, %1				\n\t"
+		"synco						\n\t"
+		: "=&z" (tmp), "=&r" (retval)
+		: "r" (a), "r" (mask), "r" (~mask)
+		: "t", "memory"
+	);
+
+	return retval != 0;
+}
+
+static inline int test_and_change_bit(int nr, volatile void *addr)
+{
+	int	mask, retval;
+	volatile unsigned int *a = addr;
+	unsigned long tmp;
+
+	a += nr >> 5;
+	mask = 1 << (nr & 0x1f);
+
+	__asm__ __volatile__ (
+		"1:						\n\t"
+		"movli.l	@%2, %0	! test_and_change_bit	\n\t"
+		"mov		%0, %1				\n\t"
+		"xor		%3, %0				\n\t"
+		"movco.l	%0, @%2				\n\t"
+		"bf		1b				\n\t"
+		"and		%3, %1				\n\t"
+		"synco						\n\t"
+		: "=&z" (tmp), "=&r" (retval)
+		: "r" (a), "r" (mask)
+		: "t", "memory"
+	);
+
+	return retval != 0;
+}
+
+#include <asm-generic/bitops/non-atomic.h>
+
+#endif /* __ASM_SH_BITOPS_LLSC_H */
diff --git a/arch/sh/include/asm/bitops-op32.h b/arch/sh/include/asm/bitops-op32.h
new file mode 100644
index 000000000..f0ae7e921
--- /dev/null
+++ b/arch/sh/include/asm/bitops-op32.h
@@ -0,0 +1,142 @@
+#ifndef __ASM_SH_BITOPS_OP32_H
+#define __ASM_SH_BITOPS_OP32_H
+
+/*
+ * The bit modifying instructions on SH-2A are only capable of working
+ * with a 3-bit immediate, which signifies the shift position for the bit
+ * being worked on.
+ */
+#if defined(__BIG_ENDIAN)
+#define BITOP_LE_SWIZZLE	((BITS_PER_LONG-1) & ~0x7)
+#define BYTE_NUMBER(nr)		((nr ^ BITOP_LE_SWIZZLE) / BITS_PER_BYTE)
+#define BYTE_OFFSET(nr)		((nr ^ BITOP_LE_SWIZZLE) % BITS_PER_BYTE)
+#else
+#define BYTE_NUMBER(nr)		((nr) / BITS_PER_BYTE)
+#define BYTE_OFFSET(nr)		((nr) % BITS_PER_BYTE)
+#endif
+
+#define IS_IMMEDIATE(nr)	(__builtin_constant_p(nr))
+
+static inline void __set_bit(int nr, volatile unsigned long *addr)
+{
+	if (IS_IMMEDIATE(nr)) {
+		__asm__ __volatile__ (
+			"bset.b %1, @(%O2,%0)		! __set_bit\n\t"
+			: "+r" (addr)
+			: "i" (BYTE_OFFSET(nr)), "i" (BYTE_NUMBER(nr))
+			: "t", "memory"
+		);
+	} else {
+		unsigned long mask = BIT_MASK(nr);
+		unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+
+		*p |= mask;
+	}
+}
+
+static inline void __clear_bit(int nr, volatile unsigned long *addr)
+{
+	if (IS_IMMEDIATE(nr)) {
+		__asm__ __volatile__ (
+			"bclr.b %1, @(%O2,%0)		! __clear_bit\n\t"
+			: "+r" (addr)
+			: "i" (BYTE_OFFSET(nr)),
+			  "i" (BYTE_NUMBER(nr))
+			: "t", "memory"
+		);
+	} else {
+		unsigned long mask = BIT_MASK(nr);
+		unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+
+		*p &= ~mask;
+	}
+}
+
+/**
+ * __change_bit - Toggle a bit in memory
+ * @nr: the bit to change
+ * @addr: the address to start counting from
+ *
+ * Unlike change_bit(), this function is non-atomic and may be reordered.
+ * If it's called on the same region of memory simultaneously, the effect
+ * may be that only one operation succeeds.
+ */
+static inline void __change_bit(int nr, volatile unsigned long *addr)
+{
+	if (IS_IMMEDIATE(nr)) {
+		__asm__ __volatile__ (
+			"bxor.b %1, @(%O2,%0)		! __change_bit\n\t"
+			: "+r" (addr)
+			: "i" (BYTE_OFFSET(nr)),
+			  "i" (BYTE_NUMBER(nr))
+			: "t", "memory"
+		);
+	} else {
+		unsigned long mask = BIT_MASK(nr);
+		unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+
+		*p ^= mask;
+	}
+}
+
+/**
+ * __test_and_set_bit - Set a bit and return its old value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation is non-atomic and can be reordered.
+ * If two examples of this operation race, one can appear to succeed
+ * but actually fail.  You must protect multiple accesses with a lock.
+ */
+static inline int __test_and_set_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	unsigned long old = *p;
+
+	*p = old | mask;
+	return (old & mask) != 0;
+}
+
+/**
+ * __test_and_clear_bit - Clear a bit and return its old value
+ * @nr: Bit to clear
+ * @addr: Address to count from
+ *
+ * This operation is non-atomic and can be reordered.
+ * If two examples of this operation race, one can appear to succeed
+ * but actually fail.  You must protect multiple accesses with a lock.
+ */
+static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	unsigned long old = *p;
+
+	*p = old & ~mask;
+	return (old & mask) != 0;
+}
+
+/* WARNING: non atomic and it can be reordered! */
+static inline int __test_and_change_bit(int nr,
+					    volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	unsigned long old = *p;
+
+	*p = old ^ mask;
+	return (old & mask) != 0;
+}
+
+/**
+ * test_bit - Determine whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static inline int test_bit(int nr, const volatile unsigned long *addr)
+{
+	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
+}
+
+#endif /* __ASM_SH_BITOPS_OP32_H */
diff --git a/arch/sh/include/asm/bitops.h b/arch/sh/include/asm/bitops.h
new file mode 100644
index 000000000..fc8e652cf
--- /dev/null
+++ b/arch/sh/include/asm/bitops.h
@@ -0,0 +1,99 @@
+#ifndef __ASM_SH_BITOPS_H
+#define __ASM_SH_BITOPS_H
+
+#ifdef __KERNEL__
+
+#ifndef _LINUX_BITOPS_H
+#error only <linux/bitops.h> can be included directly
+#endif
+
+/* For __swab32 */
+#include <asm/byteorder.h>
+#include <asm/barrier.h>
+
+#ifdef CONFIG_GUSA_RB
+#include <asm/bitops-grb.h>
+#elif defined(CONFIG_CPU_SH2A)
+#include <asm-generic/bitops/atomic.h>
+#include <asm/bitops-op32.h>
+#elif defined(CONFIG_CPU_SH4A)
+#include <asm/bitops-llsc.h>
+#else
+#include <asm-generic/bitops/atomic.h>
+#include <asm-generic/bitops/non-atomic.h>
+#endif
+
+#ifdef CONFIG_SUPERH32
+static inline unsigned long ffz(unsigned long word)
+{
+	unsigned long result;
+
+	__asm__("1:\n\t"
+		"shlr	%1\n\t"
+		"bt/s	1b\n\t"
+		" add	#1, %0"
+		: "=r" (result), "=r" (word)
+		: "0" (~0L), "1" (word)
+		: "t");
+	return result;
+}
+
+/**
+ * __ffs - find first bit in word.
+ * @word: The word to search
+ *
+ * Undefined if no bit exists, so code should check against 0 first.
+ */
+static inline unsigned long __ffs(unsigned long word)
+{
+	unsigned long result;
+
+	__asm__("1:\n\t"
+		"shlr	%1\n\t"
+		"bf/s	1b\n\t"
+		" add	#1, %0"
+		: "=r" (result), "=r" (word)
+		: "0" (~0L), "1" (word)
+		: "t");
+	return result;
+}
+#else
+static inline unsigned long ffz(unsigned long word)
+{
+	unsigned long result, __d2, __d3;
+
+        __asm__("gettr  tr0, %2\n\t"
+                "pta    $+32, tr0\n\t"
+                "andi   %1, 1, %3\n\t"
+                "beq    %3, r63, tr0\n\t"
+                "pta    $+4, tr0\n"
+                "0:\n\t"
+                "shlri.l        %1, 1, %1\n\t"
+                "addi   %0, 1, %0\n\t"
+                "andi   %1, 1, %3\n\t"
+                "beqi   %3, 1, tr0\n"
+                "1:\n\t"
+                "ptabs  %2, tr0\n\t"
+                : "=r" (result), "=r" (word), "=r" (__d2), "=r" (__d3)
+                : "0" (0L), "1" (word));
+
+	return result;
+}
+
+#include <asm-generic/bitops/__ffs.h>
+#endif
+
+#include <asm-generic/bitops/find.h>
+#include <asm-generic/bitops/ffs.h>
+#include <asm-generic/bitops/hweight.h>
+#include <asm-generic/bitops/lock.h>
+#include <asm-generic/bitops/sched.h>
+#include <asm-generic/bitops/le.h>
+#include <asm-generic/bitops/ext2-atomic.h>
+#include <asm-generic/bitops/fls.h>
+#include <asm-generic/bitops/__fls.h>
+#include <asm-generic/bitops/fls64.h>
+
+#endif /* __KERNEL__ */
+
+#endif /* __ASM_SH_BITOPS_H */
diff --git a/arch/sh/include/asm/bl_bit.h b/arch/sh/include/asm/bl_bit.h
new file mode 100644
index 000000000..06e4163c6
--- /dev/null
+++ b/arch/sh/include/asm/bl_bit.h
@@ -0,0 +1,10 @@
+#ifndef __ASM_SH_BL_BIT_H
+#define __ASM_SH_BL_BIT_H
+
+#ifdef CONFIG_SUPERH32
+# include <asm/bl_bit_32.h>
+#else
+# include <asm/bl_bit_64.h>
+#endif
+
+#endif /* __ASM_SH_BL_BIT_H */
diff --git a/arch/sh/include/asm/bl_bit_32.h b/arch/sh/include/asm/bl_bit_32.h
new file mode 100644
index 000000000..fd21eee62
--- /dev/null
+++ b/arch/sh/include/asm/bl_bit_32.h
@@ -0,0 +1,33 @@
+#ifndef __ASM_SH_BL_BIT_32_H
+#define __ASM_SH_BL_BIT_32_H
+
+static inline void set_bl_bit(void)
+{
+	unsigned long __dummy0, __dummy1;
+
+	__asm__ __volatile__ (
+		"stc	sr, %0\n\t"
+		"or	%2, %0\n\t"
+		"and	%3, %0\n\t"
+		"ldc	%0, sr\n\t"
+		: "=&r" (__dummy0), "=r" (__dummy1)
+		: "r" (0x10000000), "r" (0xffffff0f)
+		: "memory"
+	);
+}
+
+static inline void clear_bl_bit(void)
+{
+	unsigned long __dummy0, __dummy1;
+
+	__asm__ __volatile__ (
+		"stc	sr, %0\n\t"
+		"and	%2, %0\n\t"
+		"ldc	%0, sr\n\t"
+		: "=&r" (__dummy0), "=r" (__dummy1)
+		: "1" (~0x10000000)
+		: "memory"
+	);
+}
+
+#endif /* __ASM_SH_BL_BIT_32_H */
diff --git a/arch/sh/include/asm/bl_bit_64.h b/arch/sh/include/asm/bl_bit_64.h
new file mode 100644
index 000000000..6cc8711af
--- /dev/null
+++ b/arch/sh/include/asm/bl_bit_64.h
@@ -0,0 +1,40 @@
+/*
+ * Copyright (C) 2000, 2001  Paolo Alberelli
+ * Copyright (C) 2003  Paul Mundt
+ * Copyright (C) 2004  Richard Curnow
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+#ifndef __ASM_SH_BL_BIT_64_H
+#define __ASM_SH_BL_BIT_64_H
+
+#include <asm/processor.h>
+
+#define SR_BL_LL	0x0000000010000000LL
+
+static inline void set_bl_bit(void)
+{
+	unsigned long long __dummy0, __dummy1 = SR_BL_LL;
+
+	__asm__ __volatile__("getcon	" __SR ", %0\n\t"
+			     "or	%0, %1, %0\n\t"
+			     "putcon	%0, " __SR "\n\t"
+			     : "=&r" (__dummy0)
+			     : "r" (__dummy1));
+
+}
+
+static inline void clear_bl_bit(void)
+{
+	unsigned long long __dummy0, __dummy1 = ~SR_BL_LL;
+
+	__asm__ __volatile__("getcon	" __SR ", %0\n\t"
+			     "and	%0, %1, %0\n\t"
+			     "putcon	%0, " __SR "\n\t"
+			     : "=&r" (__dummy0)
+			     : "r" (__dummy1));
+}
+
+#endif /* __ASM_SH_BL_BIT_64_H */
diff --git a/arch/sh/include/asm/bug.h b/arch/sh/include/asm/bug.h
new file mode 100644
index 000000000..dcf278075
--- /dev/null
+++ b/arch/sh/include/asm/bug.h
@@ -0,0 +1,119 @@
+#ifndef __ASM_SH_BUG_H
+#define __ASM_SH_BUG_H
+
+#include <linux/linkage.h>
+
+#define TRAPA_BUG_OPCODE	0xc33e	/* trapa #0x3e */
+#define BUGFLAG_UNWINDER	(1 << 1)
+
+#ifdef CONFIG_GENERIC_BUG
+#define HAVE_ARCH_BUG
+#define HAVE_ARCH_WARN_ON
+
+/**
+ * _EMIT_BUG_ENTRY
+ * %1 - __FILE__
+ * %2 - __LINE__
+ * %3 - trap type
+ * %4 - sizeof(struct bug_entry)
+ *
+ * The trapa opcode itself sits in %0.
+ * The %O notation is used to avoid # generation.
+ *
+ * The offending file and line are encoded in the __bug_table section.
+ */
+#ifdef CONFIG_DEBUG_BUGVERBOSE
+#define _EMIT_BUG_ENTRY				\
+	"\t.pushsection __bug_table,\"a\"\n"	\
+	"2:\t.long 1b, %O1\n"			\
+	"\t.short %O2, %O3\n"			\
+	"\t.org 2b+%O4\n"			\
+	"\t.popsection\n"
+#else
+#define _EMIT_BUG_ENTRY				\
+	"\t.pushsection __bug_table,\"a\"\n"	\
+	"2:\t.long 1b\n"			\
+	"\t.short %O3\n"			\
+	"\t.org 2b+%O4\n"			\
+	"\t.popsection\n"
+#endif
+
+#define BUG()						\
+do {							\
+	__asm__ __volatile__ (				\
+		"1:\t.short %O0\n"			\
+		_EMIT_BUG_ENTRY				\
+		 :					\
+		 : "n" (TRAPA_BUG_OPCODE),		\
+		   "i" (__FILE__),			\
+		   "i" (__LINE__), "i" (0),		\
+		   "i" (sizeof(struct bug_entry)));	\
+} while (0)
+
+#define __WARN_TAINT(taint)				\
+do {							\
+	__asm__ __volatile__ (				\
+		"1:\t.short %O0\n"			\
+		 _EMIT_BUG_ENTRY			\
+		 :					\
+		 : "n" (TRAPA_BUG_OPCODE),		\
+		   "i" (__FILE__),			\
+		   "i" (__LINE__),			\
+		   "i" (BUGFLAG_TAINT(taint)),		\
+		   "i" (sizeof(struct bug_entry)));	\
+} while (0)
+
+#define WARN_ON(x) ({						\
+	int __ret_warn_on = !!(x);				\
+	if (__builtin_constant_p(__ret_warn_on)) {		\
+		if (__ret_warn_on)				\
+			__WARN();				\
+	} else {						\
+		if (unlikely(__ret_warn_on))			\
+			__WARN();				\
+	}							\
+	unlikely(__ret_warn_on);				\
+})
+
+#define UNWINDER_BUG()					\
+do {							\
+	__asm__ __volatile__ (				\
+		"1:\t.short %O0\n"			\
+		_EMIT_BUG_ENTRY				\
+		 :					\
+		 : "n" (TRAPA_BUG_OPCODE),		\
+		   "i" (__FILE__),			\
+		   "i" (__LINE__),			\
+		   "i" (BUGFLAG_UNWINDER),		\
+		   "i" (sizeof(struct bug_entry)));	\
+} while (0)
+
+#define UNWINDER_BUG_ON(x) ({					\
+	int __ret_unwinder_on = !!(x);				\
+	if (__builtin_constant_p(__ret_unwinder_on)) {		\
+		if (__ret_unwinder_on)				\
+			UNWINDER_BUG();				\
+	} else {						\
+		if (unlikely(__ret_unwinder_on))		\
+			UNWINDER_BUG();				\
+	}							\
+	unlikely(__ret_unwinder_on);				\
+})
+
+#else
+
+#define UNWINDER_BUG	BUG
+#define UNWINDER_BUG_ON	BUG_ON
+
+#endif /* CONFIG_GENERIC_BUG */
+
+#include <asm-generic/bug.h>
+
+struct pt_regs;
+
+/* arch/sh/kernel/traps.c */
+extern void die(const char *str, struct pt_regs *regs, long err) __attribute__ ((noreturn));
+extern void die_if_kernel(const char *str, struct pt_regs *regs, long err);
+extern void die_if_no_fixup(const char *str, struct pt_regs *regs, long err);
+
+#endif /* __ASM_SH_BUG_H */
diff --git a/arch/sh/include/asm/bugs.h b/arch/sh/include/asm/bugs.h
new file mode 100644
index 000000000..02a19a1c0
--- /dev/null
+++ b/arch/sh/include/asm/bugs.h
@@ -0,0 +1,77 @@
+#ifndef __ASM_SH_BUGS_H
+#define __ASM_SH_BUGS_H
+
+/*
+ * This is included by init/main.c to check for architecture-dependent bugs.
+ *
+ * Needs:
+ *	void check_bugs(void);
+ */
+
+/*
+ * I don't know of any Super-H bugs yet.
+ */
+
+#include <asm/processor.h>
+
+extern void select_idle_routine(void);
+
+static void __init check_bugs(void)
+{
+	extern unsigned long loops_per_jiffy;
+	char *p = &init_utsname()->machine[2]; /* "sh" */
+
+	select_idle_routine();
+
+	current_cpu_data.loops_per_jiffy = loops_per_jiffy;
+
+	switch (current_cpu_data.family) {
+	case CPU_FAMILY_SH2:
+		*p++ = '2';
+		break;
+	case CPU_FAMILY_SH2A:
+		*p++ = '2';
+		*p++ = 'a';
+		break;
+	case CPU_FAMILY_SH3:
+		*p++ = '3';
+		break;
+	case CPU_FAMILY_SH4:
+		*p++ = '4';
+		break;
+	case CPU_FAMILY_SH4A:
+		*p++ = '4';
+		*p++ = 'a';
+		break;
+	case CPU_FAMILY_SH4AL_DSP:
+		*p++ = '4';
+		*p++ = 'a';
+		*p++ = 'l';
+		*p++ = '-';
+		*p++ = 'd';
+		*p++ = 's';
+		*p++ = 'p';
+		break;
+	case CPU_FAMILY_SH5:
+		*p++ = '6';
+		*p++ = '4';
+		break;
+	case CPU_FAMILY_UNKNOWN:
+		/*
+		 * Specifically use CPU_FAMILY_UNKNOWN rather than
+		 * default:, so we're able to have the compiler whine
+		 * about unhandled enumerations.
+		 */
+		break;
+	}
+
+	printk("CPU: %s\n", get_cpu_subtype(&current_cpu_data));
+
+#ifndef __LITTLE_ENDIAN__
+	/* 'eb' means 'Endian Big' */
+	*p++ = 'e';
+	*p++ = 'b';
+#endif
+	*p = '\0';
+}
+#endif /* __ASM_SH_BUGS_H */
diff --git a/arch/sh/include/asm/cache.h b/arch/sh/include/asm/cache.h
new file mode 100644
index 000000000..ef9e555aa
--- /dev/null
+++ b/arch/sh/include/asm/cache.h
@@ -0,0 +1,47 @@
+/* $Id: cache.h,v 1.6 2004/03/11 18:08:05 lethal Exp $
+ *
+ * include/asm-sh/cache.h
+ *
+ * Copyright 1999 (C) Niibe Yutaka
+ * Copyright 2002, 2003 (C) Paul Mundt
+ */
+#ifndef __ASM_SH_CACHE_H
+#define __ASM_SH_CACHE_H
+#ifdef __KERNEL__
+
+#include <linux/init.h>
+#include <cpu/cache.h>
+
+#define L1_CACHE_BYTES		(1 << L1_CACHE_SHIFT)
+
+#define __read_mostly __attribute__((__section__(".data..read_mostly")))
+
+#ifndef __ASSEMBLY__
+struct cache_info {
+	unsigned int ways;		/* Number of cache ways */
+	unsigned int sets;		/* Number of cache sets */
+	unsigned int linesz;		/* Cache line size (bytes) */
+
+	unsigned int way_size;		/* sets * line size */
+
+	/*
+	 * way_incr is the address offset for accessing the next way
+	 * in memory mapped cache array ops.
+	 */
+	unsigned int way_incr;
+	unsigned int entry_shift;
+	unsigned int entry_mask;
+
+	/*
+	 * Compute a mask which selects the address bits which overlap between
+	 * 1. those used to select the cache set during indexing
+	 * 2. those in the physical page number.
+	 */
+	unsigned int alias_mask;
+	unsigned int n_aliases;		/* Number of aliases */
+
+	unsigned long flags;
+};
+#endif /* __ASSEMBLY__ */
+#endif /* __KERNEL__ */
+#endif /* __ASM_SH_CACHE_H */
diff --git a/arch/sh/include/asm/cache_insns.h b/arch/sh/include/asm/cache_insns.h
new file mode 100644
index 000000000..355cb06b7
--- /dev/null
+++ b/arch/sh/include/asm/cache_insns.h
@@ -0,0 +1,11 @@
+#ifndef __ASM_SH_CACHE_INSNS_H
+#define __ASM_SH_CACHE_INSNS_H
+
+
+#ifdef CONFIG_SUPERH32
+# include <asm/cache_insns_32.h>
+#else
+# include <asm/cache_insns_64.h>
+#endif
+
+#endif /* __ASM_SH_CACHE_INSNS_H */
diff --git a/arch/sh/include/asm/cache_insns_32.h b/arch/sh/include/asm/cache_insns_32.h
new file mode 100644
index 000000000..b92fe5416
--- /dev/null
+++ b/arch/sh/include/asm/cache_insns_32.h
@@ -0,0 +1,21 @@
+#ifndef __ASM_SH_CACHE_INSNS_32_H
+#define __ASM_SH_CACHE_INSNS_32_H
+
+#include <linux/types.h>
+
+#if defined(CONFIG_CPU_SH4A)
+#define __icbi(addr)	__asm__ __volatile__ ( "icbi @%0\n\t" : : "r" (addr))
+#else
+#define __icbi(addr)	mb()
+#endif
+
+#define __ocbp(addr)	__asm__ __volatile__ ( "ocbp @%0\n\t" : : "r" (addr))
+#define __ocbi(addr)	__asm__ __volatile__ ( "ocbi @%0\n\t" : : "r" (addr))
+#define __ocbwb(addr)	__asm__ __volatile__ ( "ocbwb @%0\n\t" : : "r" (addr))
+
+static inline reg_size_t register_align(void *val)
+{
+	return (unsigned long)(signed long)val;
+}
+
+#endif /* __ASM_SH_CACHE_INSNS_32_H */
diff --git a/arch/sh/include/asm/cache_insns_64.h b/arch/sh/include/asm/cache_insns_64.h
new file mode 100644
index 000000000..70b6357ea
--- /dev/null
+++ b/arch/sh/include/asm/cache_insns_64.h
@@ -0,0 +1,23 @@
+/*
+ * Copyright (C) 2000, 2001  Paolo Alberelli
+ * Copyright (C) 2003  Paul Mundt
+ * Copyright (C) 2004  Richard Curnow
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+#ifndef __ASM_SH_CACHE_INSNS_64_H
+#define __ASM_SH_CACHE_INSNS_64_H
+
+#define __icbi(addr)	__asm__ __volatile__ ( "icbi %0, 0\n\t" : : "r" (addr))
+#define __ocbp(addr)	__asm__ __volatile__ ( "ocbp %0, 0\n\t" : : "r" (addr))
+#define __ocbi(addr)	__asm__ __volatile__ ( "ocbi %0, 0\n\t" : : "r" (addr))
+#define __ocbwb(addr)	__asm__ __volatile__ ( "ocbwb %0, 0\n\t" : : "r" (addr))
+
+static inline reg_size_t register_align(void *val)
+{
+	return (unsigned long long)(signed long long)(signed long)val;
+}
+
+#endif /* __ASM_SH_CACHE_INSNS_64_H */
diff --git a/arch/sh/include/asm/cacheflush.h b/arch/sh/include/asm/cacheflush.h
new file mode 100644
index 000000000..82e1eabea
--- /dev/null
+++ b/arch/sh/include/asm/cacheflush.h
@@ -0,0 +1,104 @@
+#ifndef __ASM_SH_CACHEFLUSH_H
+#define __ASM_SH_CACHEFLUSH_H
+
+#ifdef __KERNEL__
+
+#include <linux/mm.h>
+
+/*
+ * Cache flushing:
+ *
+ *  - flush_cache_all() flushes entire cache
+ *  - flush_cache_mm(mm) flushes the specified mm context's cache lines
+ *  - flush_cache_dup mm(mm) handles cache flushing when forking
+ *  - flush_cache_page(mm, vmaddr, pfn) flushes a single page
+ *  - flush_cache_range(vma, start, end) flushes a range of pages
+ *
+ *  - flush_dcache_page(pg) flushes(wback&invalidates) a page for dcache
+ *  - flush_icache_range(start, end) flushes(invalidates) a range for icache
+ *  - flush_icache_page(vma, pg) flushes(invalidates) a page for icache
+ *  - flush_cache_sigtramp(vaddr) flushes the signal trampoline
+ */
+extern void (*local_flush_cache_all)(void *args);
+extern void (*local_flush_cache_mm)(void *args);
+extern void (*local_flush_cache_dup_mm)(void *args);
+extern void (*local_flush_cache_page)(void *args);
+extern void (*local_flush_cache_range)(void *args);
+extern void (*local_flush_dcache_page)(void *args);
+extern void (*local_flush_icache_range)(void *args);
+extern void (*local_flush_icache_page)(void *args);
+extern void (*local_flush_cache_sigtramp)(void *args);
+
+static inline void cache_noop(void *args) { }
+
+extern void (*__flush_wback_region)(void *start, int size);
+extern void (*__flush_purge_region)(void *start, int size);
+extern void (*__flush_invalidate_region)(void *start, int size);
+
+extern void flush_cache_all(void);
+extern void flush_cache_mm(struct mm_struct *mm);
+extern void flush_cache_dup_mm(struct mm_struct *mm);
+extern void flush_cache_page(struct vm_area_struct *vma,
+				unsigned long addr, unsigned long pfn);
+extern void flush_cache_range(struct vm_area_struct *vma,
+				 unsigned long start, unsigned long end);
+#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
+extern void flush_dcache_page(struct page *page);
+extern void flush_icache_range(unsigned long start, unsigned long end);
+extern void flush_icache_page(struct vm_area_struct *vma,
+				 struct page *page);
+extern void flush_cache_sigtramp(unsigned long address);
+
+struct flusher_data {
+	struct vm_area_struct *vma;
+	unsigned long addr1, addr2;
+};
+
+#define ARCH_HAS_FLUSH_ANON_PAGE
+extern void __flush_anon_page(struct page *page, unsigned long);
+
+static inline void flush_anon_page(struct vm_area_struct *vma,
+				   struct page *page, unsigned long vmaddr)
+{
+	if (boot_cpu_data.dcache.n_aliases && PageAnon(page))
+		__flush_anon_page(page, vmaddr);
+}
+static inline void flush_kernel_vmap_range(void *addr, int size)
+{
+	__flush_wback_region(addr, size);
+}
+static inline void invalidate_kernel_vmap_range(void *addr, int size)
+{
+	__flush_invalidate_region(addr, size);
+}
+
+#define ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE
+static inline void flush_kernel_dcache_page(struct page *page)
+{
+	flush_dcache_page(page);
+}
+
+extern void copy_to_user_page(struct vm_area_struct *vma,
+	struct page *page, unsigned long vaddr, void *dst, const void *src,
+	unsigned long len);
+
+extern void copy_from_user_page(struct vm_area_struct *vma,
+	struct page *page, unsigned long vaddr, void *dst, const void *src,
+	unsigned long len);
+
+#define flush_cache_vmap(start, end)		local_flush_cache_all(NULL)
+#define flush_cache_vunmap(start, end)		local_flush_cache_all(NULL)
+
+#define flush_dcache_mmap_lock(mapping)		do { } while (0)
+#define flush_dcache_mmap_unlock(mapping)	do { } while (0)
+
+void kmap_coherent_init(void);
+void *kmap_coherent(struct page *page, unsigned long addr);
+void kunmap_coherent(void *kvaddr);
+
+#define PG_dcache_clean	PG_arch_1
+
+void cpu_cache_init(void);
+
+#endif /* __KERNEL__ */
+#endif /* __ASM_SH_CACHEFLUSH_H */
diff --git a/arch/sh/include/asm/checksum.h b/arch/sh/include/asm/checksum.h
new file mode 100644
index 000000000..34ae26204
--- /dev/null
+++ b/arch/sh/include/asm/checksum.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_SUPERH32
+# include <asm/checksum_32.h>
+#else
+# include <asm-generic/checksum.h>
+#endif
diff --git a/arch/sh/include/asm/checksum_32.h b/arch/sh/include/asm/checksum_32.h
new file mode 100644
index 000000000..14b7ac2f0
--- /dev/null
+++ b/arch/sh/include/asm/checksum_32.h
@@ -0,0 +1,215 @@
+#ifndef __ASM_SH_CHECKSUM_H
+#define __ASM_SH_CHECKSUM_H
+
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 1999 by Kaz Kojima & Niibe Yutaka
+ */
+
+#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
+ */
+asmlinkage __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
+ */
+
+asmlinkage __wsum csum_partial_copy_generic(const void *src, void *dst,
+					    int len, __wsum sum,
+					    int *src_err_ptr, int *dst_err_ptr);
+
+/*
+ *	Note: when you get a NULL pointer exception here this means someone
+ *	passed in an incorrect kernel address to one of these functions.
+ *
+ *	If you use these functions directly please don't forget the
+ *	access_ok().
+ */
+static inline
+__wsum csum_partial_copy_nocheck(const void *src, void *dst,
+				 int len, __wsum sum)
+{
+	return csum_partial_copy_generic(src, dst, len, sum, NULL, NULL);
+}
+
+static inline
+__wsum csum_partial_copy_from_user(const void __user *src, void *dst,
+				   int len, __wsum sum, int *err_ptr)
+{
+	return csum_partial_copy_generic((__force const void *)src, dst,
+					len, sum, err_ptr, NULL);
+}
+
+/*
+ *	Fold a partial checksum
+ */
+
+static inline __sum16 csum_fold(__wsum sum)
+{
+	unsigned int __dummy;
+	__asm__("swap.w %0, %1\n\t"
+		"extu.w	%0, %0\n\t"
+		"extu.w	%1, %1\n\t"
+		"add	%1, %0\n\t"
+		"swap.w	%0, %1\n\t"
+		"add	%1, %0\n\t"
+		"not	%0, %0\n\t"
+		: "=r" (sum), "=&r" (__dummy)
+		: "0" (sum)
+		: "t");
+	return (__force __sum16)sum;
+}
+
+/*
+ *	This is a version of ip_compute_csum() optimized for IP headers,
+ *	which always checksum on 4 octet boundaries.
+ *
+ *      i386 version by Jorge Cwik <jorge@laser.satlink.net>, adapted
+ *      for linux by * Arnt Gulbrandsen.
+ */
+static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
+{
+	unsigned int sum, __dummy0, __dummy1;
+
+	__asm__ __volatile__(
+		"mov.l	@%1+, %0\n\t"
+		"mov.l	@%1+, %3\n\t"
+		"add	#-2, %2\n\t"
+		"clrt\n\t"
+		"1:\t"
+		"addc	%3, %0\n\t"
+		"movt	%4\n\t"
+		"mov.l	@%1+, %3\n\t"
+		"dt	%2\n\t"
+		"bf/s	1b\n\t"
+		" cmp/eq #1, %4\n\t"
+		"addc	%3, %0\n\t"
+		"addc	%2, %0"	    /* Here %2 is 0, add carry-bit */
+	/* Since the input registers which are loaded with iph and ihl
+	   are modified, we must also specify them as outputs, or gcc
+	   will assume they contain their original values. */
+	: "=r" (sum), "=r" (iph), "=r" (ihl), "=&r" (__dummy0), "=&z" (__dummy1)
+	: "1" (iph), "2" (ihl)
+	: "t", "memory");
+
+	return	csum_fold(sum);
+}
+
+static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
+					unsigned short len,
+					unsigned short proto,
+					__wsum sum)
+{
+#ifdef __LITTLE_ENDIAN__
+	unsigned long len_proto = (proto + len) << 8;
+#else
+	unsigned long len_proto = proto + len;
+#endif
+	__asm__("clrt\n\t"
+		"addc	%0, %1\n\t"
+		"addc	%2, %1\n\t"
+		"addc	%3, %1\n\t"
+		"movt	%0\n\t"
+		"add	%1, %0"
+		: "=r" (sum), "=r" (len_proto)
+		: "r" (daddr), "r" (saddr), "1" (len_proto), "0" (sum)
+		: "t");
+
+	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
+static inline __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
+				      const struct in6_addr *daddr,
+				      __u32 len, unsigned short proto,
+				      __wsum sum)
+{
+	unsigned int __dummy;
+	__asm__("clrt\n\t"
+		"mov.l	@(0,%2), %1\n\t"
+		"addc	%1, %0\n\t"
+		"mov.l	@(4,%2), %1\n\t"
+		"addc	%1, %0\n\t"
+		"mov.l	@(8,%2), %1\n\t"
+		"addc	%1, %0\n\t"
+		"mov.l	@(12,%2), %1\n\t"
+		"addc	%1, %0\n\t"
+		"mov.l	@(0,%3), %1\n\t"
+		"addc	%1, %0\n\t"
+		"mov.l	@(4,%3), %1\n\t"
+		"addc	%1, %0\n\t"
+		"mov.l	@(8,%3), %1\n\t"
+		"addc	%1, %0\n\t"
+		"mov.l	@(12,%3), %1\n\t"
+		"addc	%1, %0\n\t"
+		"addc	%4, %0\n\t"
+		"addc	%5, %0\n\t"
+		"movt	%1\n\t"
+		"add	%1, %0\n"
+		: "=r" (sum), "=&r" (__dummy)
+		: "r" (saddr), "r" (daddr),
+		  "r" (htonl(len)), "r" (htonl(proto)), "0" (sum)
+		: "t");
+
+	return csum_fold(sum);
+}
+
+/*
+ *	Copy and checksum to user
+ */
+#define HAVE_CSUM_COPY_USER
+static inline __wsum csum_and_copy_to_user(const void *src,
+					   void __user *dst,
+					   int len, __wsum sum,
+					   int *err_ptr)
+{
+	if (access_ok(VERIFY_WRITE, dst, len))
+		return csum_partial_copy_generic((__force const void *)src,
+						dst, len, sum, NULL, err_ptr);
+
+	if (len)
+		*err_ptr = -EFAULT;
+
+	return (__force __wsum)-1; /* invalid checksum */
+}
+#endif /* __ASM_SH_CHECKSUM_H */
diff --git a/arch/sh/include/asm/clkdev.h b/arch/sh/include/asm/clkdev.h
new file mode 100644
index 000000000..c41901465
--- /dev/null
+++ b/arch/sh/include/asm/clkdev.h
@@ -0,0 +1,33 @@
+/*
+ *  Copyright (C) 2010 Paul Mundt <lethal@linux-sh.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Helper for the clk API to assist looking up a struct clk.
+ */
+
+#ifndef __CLKDEV__H_
+#define __CLKDEV__H_
+
+#include <linux/bootmem.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+
+#include <asm/clock.h>
+
+static inline struct clk_lookup_alloc *__clkdev_alloc(size_t size)
+{
+	if (!slab_is_available())
+		return alloc_bootmem_low_pages(size);
+	else
+		return kzalloc(size, GFP_KERNEL);
+}
+
+#ifndef CONFIG_COMMON_CLK
+#define __clk_put(clk)
+#define __clk_get(clk) ({ 1; })
+#endif
+
+#endif /* __CLKDEV_H__ */
diff --git a/arch/sh/include/asm/clock.h b/arch/sh/include/asm/clock.h
new file mode 100644
index 000000000..0390a07e7
--- /dev/null
+++ b/arch/sh/include/asm/clock.h
@@ -0,0 +1,16 @@
+#ifndef __ASM_SH_CLOCK_H
+#define __ASM_SH_CLOCK_H
+
+#include <linux/sh_clk.h>
+
+/* Should be defined by processor-specific code */
+void __deprecated arch_init_clk_ops(struct sh_clk_ops **, int type);
+int __init arch_clk_init(void);
+
+/* arch/sh/kernel/cpu/clock-cpg.c */
+int __init __deprecated cpg_clk_init(void);
+
+/* arch/sh/kernel/cpu/clock.c */
+int clk_init(void);
+
+#endif /* __ASM_SH_CLOCK_H */
diff --git a/arch/sh/include/asm/cmpxchg-grb.h b/arch/sh/include/asm/cmpxchg-grb.h
new file mode 100644
index 000000000..f848dec9e
--- /dev/null
+++ b/arch/sh/include/asm/cmpxchg-grb.h
@@ -0,0 +1,72 @@
+#ifndef __ASM_SH_CMPXCHG_GRB_H
+#define __ASM_SH_CMPXCHG_GRB_H
+
+static inline unsigned long xchg_u32(volatile u32 *m, unsigned long val)
+{
+	unsigned long retval;
+
+	__asm__ __volatile__ (
+		"   .align 2              \n\t"
+		"   mova    1f,   r0      \n\t" /* r0 = end point */
+		"   nop                   \n\t"
+		"   mov    r15,   r1      \n\t" /* r1 = saved sp */
+		"   mov    #-4,   r15     \n\t" /* LOGIN */
+		"   mov.l  @%1,   %0      \n\t" /* load  old value */
+		"   mov.l   %2,   @%1     \n\t" /* store new value */
+		"1: mov     r1,   r15     \n\t" /* LOGOUT */
+		: "=&r" (retval),
+		  "+r"  (m),
+		  "+r"  (val)		/* inhibit r15 overloading */
+		:
+		: "memory", "r0", "r1");
+
+	return retval;
+}
+
+static inline unsigned long xchg_u8(volatile u8 *m, unsigned long val)
+{
+	unsigned long retval;
+
+	__asm__ __volatile__ (
+		"   .align  2             \n\t"
+		"   mova    1f,   r0      \n\t" /* r0 = end point */
+		"   mov    r15,   r1      \n\t" /* r1 = saved sp */
+		"   mov    #-6,   r15     \n\t" /* LOGIN */
+		"   mov.b  @%1,   %0      \n\t" /* load  old value */
+		"   extu.b  %0,   %0      \n\t" /* extend as unsigned */
+		"   mov.b   %2,   @%1     \n\t" /* store new value */
+		"1: mov     r1,   r15     \n\t" /* LOGOUT */
+		: "=&r" (retval),
+		  "+r"  (m),
+		  "+r"  (val)		/* inhibit r15 overloading */
+		:
+		: "memory" , "r0", "r1");
+
+	return retval;
+}
+
+static inline unsigned long __cmpxchg_u32(volatile int *m, unsigned long old,
+					  unsigned long new)
+{
+	unsigned long retval;
+
+	__asm__ __volatile__ (
+		"   .align  2             \n\t"
+		"   mova    1f,   r0      \n\t" /* r0 = end point */
+		"   nop                   \n\t"
+		"   mov    r15,   r1      \n\t" /* r1 = saved sp */
+		"   mov    #-8,   r15     \n\t" /* LOGIN */
+		"   mov.l  @%3,   %0      \n\t" /* load  old value */
+		"   cmp/eq  %0,   %1      \n\t"
+		"   bf            1f      \n\t" /* if not equal */
+		"   mov.l   %2,   @%3     \n\t" /* store new value */
+		"1: mov     r1,   r15     \n\t" /* LOGOUT */
+		: "=&r" (retval),
+		  "+r"  (old), "+r"  (new) /* old or new can be r15 */
+		:  "r"  (m)
+		: "memory" , "r0", "r1", "t");
+
+	return retval;
+}
+
+#endif /* __ASM_SH_CMPXCHG_GRB_H */
diff --git a/arch/sh/include/asm/cmpxchg-irq.h b/arch/sh/include/asm/cmpxchg-irq.h
new file mode 100644
index 000000000..bd11f6304
--- /dev/null
+++ b/arch/sh/include/asm/cmpxchg-irq.h
@@ -0,0 +1,42 @@
+#ifndef __ASM_SH_CMPXCHG_IRQ_H
+#define __ASM_SH_CMPXCHG_IRQ_H
+
+#include <linux/irqflags.h>
+
+static inline unsigned long xchg_u32(volatile u32 *m, unsigned long val)
+{
+	unsigned long flags, retval;
+
+	local_irq_save(flags);
+	retval = *m;
+	*m = val;
+	local_irq_restore(flags);
+	return retval;
+}
+
+static inline unsigned long xchg_u8(volatile u8 *m, unsigned long val)
+{
+	unsigned long flags, retval;
+
+	local_irq_save(flags);
+	retval = *m;
+	*m = val & 0xff;
+	local_irq_restore(flags);
+	return retval;
+}
+
+static inline unsigned long __cmpxchg_u32(volatile int *m, unsigned long old,
+	unsigned long new)
+{
+	__u32 retval;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	retval = *m;
+	if (retval == old)
+		*m = new;
+	local_irq_restore(flags);       /* implies memory barrier  */
+	return retval;
+}
+
+#endif /* __ASM_SH_CMPXCHG_IRQ_H */
diff --git a/arch/sh/include/asm/cmpxchg-llsc.h b/arch/sh/include/asm/cmpxchg-llsc.h
new file mode 100644
index 000000000..47136661a
--- /dev/null
+++ b/arch/sh/include/asm/cmpxchg-llsc.h
@@ -0,0 +1,71 @@
+#ifndef __ASM_SH_CMPXCHG_LLSC_H
+#define __ASM_SH_CMPXCHG_LLSC_H
+
+static inline unsigned long xchg_u32(volatile u32 *m, unsigned long val)
+{
+	unsigned long retval;
+	unsigned long tmp;
+
+	__asm__ __volatile__ (
+		"1:					\n\t"
+		"movli.l	@%2, %0	! xchg_u32	\n\t"
+		"mov		%0, %1			\n\t"
+		"mov		%3, %0			\n\t"
+		"movco.l	%0, @%2			\n\t"
+		"bf		1b			\n\t"
+		"synco					\n\t"
+		: "=&z"(tmp), "=&r" (retval)
+		: "r" (m), "r" (val)
+		: "t", "memory"
+	);
+
+	return retval;
+}
+
+static inline unsigned long xchg_u8(volatile u8 *m, unsigned long val)
+{
+	unsigned long retval;
+	unsigned long tmp;
+
+	__asm__ __volatile__ (
+		"1:					\n\t"
+		"movli.l	@%2, %0	! xchg_u8	\n\t"
+		"mov		%0, %1			\n\t"
+		"mov		%3, %0			\n\t"
+		"movco.l	%0, @%2			\n\t"
+		"bf		1b			\n\t"
+		"synco					\n\t"
+		: "=&z"(tmp), "=&r" (retval)
+		: "r" (m), "r" (val & 0xff)
+		: "t", "memory"
+	);
+
+	return retval;
+}
+
+static inline unsigned long
+__cmpxchg_u32(volatile int *m, unsigned long old, unsigned long new)
+{
+	unsigned long retval;
+	unsigned long tmp;
+
+	__asm__ __volatile__ (
+		"1:						\n\t"
+		"movli.l	@%2, %0	! __cmpxchg_u32		\n\t"
+		"mov		%0, %1				\n\t"
+		"cmp/eq		%1, %3				\n\t"
+		"bf		2f				\n\t"
+		"mov		%4, %0				\n\t"
+		"2:						\n\t"
+		"movco.l	%0, @%2				\n\t"
+		"bf		1b				\n\t"
+		"synco						\n\t"
+		: "=&z" (tmp), "=&r" (retval)
+		: "r" (m), "r" (old), "r" (new)
+		: "t", "memory"
+	);
+
+	return retval;
+}
+
+#endif /* __ASM_SH_CMPXCHG_LLSC_H */
diff --git a/arch/sh/include/asm/cmpxchg.h b/arch/sh/include/asm/cmpxchg.h
new file mode 100644
index 000000000..f6bd1406b
--- /dev/null
+++ b/arch/sh/include/asm/cmpxchg.h
@@ -0,0 +1,70 @@
+#ifndef __ASM_SH_CMPXCHG_H
+#define __ASM_SH_CMPXCHG_H
+
+/*
+ * Atomic operations that C can't guarantee us.  Useful for
+ * resource counting etc..
+ */
+
+#include <linux/compiler.h>
+#include <linux/types.h>
+
+#if defined(CONFIG_GUSA_RB)
+#include <asm/cmpxchg-grb.h>
+#elif defined(CONFIG_CPU_SH4A)
+#include <asm/cmpxchg-llsc.h>
+#else
+#include <asm/cmpxchg-irq.h>
+#endif
+
+extern void __xchg_called_with_bad_pointer(void);
+
+#define __xchg(ptr, x, size)				\
+({							\
+	unsigned long __xchg__res;			\
+	volatile void *__xchg_ptr = (ptr);		\
+	switch (size) {					\
+	case 4:						\
+		__xchg__res = xchg_u32(__xchg_ptr, x);	\
+		break;					\
+	case 1:						\
+		__xchg__res = xchg_u8(__xchg_ptr, x);	\
+		break;					\
+	default:					\
+		__xchg_called_with_bad_pointer();	\
+		__xchg__res = x;			\
+		break;					\
+	}						\
+							\
+	__xchg__res;					\
+})
+
+#define xchg(ptr,x)	\
+	((__typeof__(*(ptr)))__xchg((ptr),(unsigned long)(x), sizeof(*(ptr))))
+
+/* This function doesn't exist, so you'll get a linker error
+ * if something tries to do an invalid cmpxchg(). */
+extern void __cmpxchg_called_with_bad_pointer(void);
+
+#define __HAVE_ARCH_CMPXCHG 1
+
+static inline unsigned long __cmpxchg(volatile void * ptr, unsigned long old,
+		unsigned long new, int size)
+{
+	switch (size) {
+	case 4:
+		return __cmpxchg_u32(ptr, old, new);
+	}
+	__cmpxchg_called_with_bad_pointer();
+	return old;
+}
+
+#define cmpxchg(ptr,o,n)						 \
+  ({									 \
+     __typeof__(*(ptr)) _o_ = (o);					 \
+     __typeof__(*(ptr)) _n_ = (n);					 \
+     (__typeof__(*(ptr))) __cmpxchg((ptr), (unsigned long)_o_,		 \
+				    (unsigned long)_n_, sizeof(*(ptr))); \
+  })
+
+#endif /* __ASM_SH_CMPXCHG_H */
diff --git a/arch/sh/include/asm/device.h b/arch/sh/include/asm/device.h
new file mode 100644
index 000000000..071bcb4d4
--- /dev/null
+++ b/arch/sh/include/asm/device.h
@@ -0,0 +1,18 @@
+/*
+ * Arch specific extensions to struct device
+ *
+ * This file is released under the GPLv2
+ */
+#ifndef __ASM_SH_DEVICE_H
+#define __ASM_SH_DEVICE_H
+
+#include <asm-generic/device.h>
+
+struct platform_device;
+/* allocate contiguous memory chunk and fill in struct resource */
+int platform_resource_setup_memory(struct platform_device *pdev,
+				   char *name, unsigned long memsize);
+
+void plat_early_device_setup(void);
+
+#endif /* __ASM_SH_DEVICE_H */
diff --git a/arch/sh/include/asm/dma-mapping.h b/arch/sh/include/asm/dma-mapping.h
new file mode 100644
index 000000000..b437f2c78
--- /dev/null
+++ b/arch/sh/include/asm/dma-mapping.h
@@ -0,0 +1,100 @@
+#ifndef __ASM_SH_DMA_MAPPING_H
+#define __ASM_SH_DMA_MAPPING_H
+
+extern struct dma_map_ops *dma_ops;
+extern void no_iommu_init(void);
+
+static inline struct dma_map_ops *get_dma_ops(struct device *dev)
+{
+	return dma_ops;
+}
+
+#include <asm-generic/dma-coherent.h>
+#include <asm-generic/dma-mapping-common.h>
+
+static inline int dma_supported(struct device *dev, u64 mask)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+
+	if (ops->dma_supported)
+		return ops->dma_supported(dev, mask);
+
+	return 1;
+}
+
+static inline int dma_set_mask(struct device *dev, u64 mask)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+
+	if (!dev->dma_mask || !dma_supported(dev, mask))
+		return -EIO;
+	if (ops->set_dma_mask)
+		return ops->set_dma_mask(dev, mask);
+
+	*dev->dma_mask = mask;
+
+	return 0;
+}
+
+void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
+		    enum dma_data_direction dir);
+
+#define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
+#define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h)
+
+static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+
+	debug_dma_mapping_error(dev, dma_addr);
+	if (ops->mapping_error)
+		return ops->mapping_error(dev, dma_addr);
+
+	return dma_addr == 0;
+}
+
+#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 gfp,
+				    struct dma_attrs *attrs)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+	void *memory;
+
+	if (dma_alloc_from_coherent(dev, size, dma_handle, &memory))
+		return memory;
+	if (!ops->alloc)
+		return NULL;
+
+	memory = ops->alloc(dev, size, dma_handle, gfp, attrs);
+	debug_dma_alloc_coherent(dev, size, *dma_handle, memory);
+
+	return memory;
+}
+
+#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 *vaddr, dma_addr_t dma_handle,
+				  struct dma_attrs *attrs)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+
+	if (dma_release_from_coherent(dev, get_order(size), vaddr))
+		return;
+
+	debug_dma_free_coherent(dev, size, vaddr, dma_handle);
+	if (ops->free)
+		ops->free(dev, size, vaddr, dma_handle, attrs);
+}
+
+/* arch/sh/mm/consistent.c */
+extern void *dma_generic_alloc_coherent(struct device *dev, size_t size,
+					dma_addr_t *dma_addr, gfp_t flag,
+					struct dma_attrs *attrs);
+extern void dma_generic_free_coherent(struct device *dev, size_t size,
+				      void *vaddr, dma_addr_t dma_handle,
+				      struct dma_attrs *attrs);
+
+#endif /* __ASM_SH_DMA_MAPPING_H */
diff --git a/arch/sh/include/asm/dma-register.h b/arch/sh/include/asm/dma-register.h
new file mode 100644
index 000000000..c757b47e6
--- /dev/null
+++ b/arch/sh/include/asm/dma-register.h
@@ -0,0 +1,53 @@
+/*
+ * Common header for the legacy SH DMA driver and the new dmaengine driver
+ *
+ * extracted from arch/sh/include/asm/dma-sh.h:
+ *
+ * Copyright (C) 2000  Takashi YOSHII
+ * Copyright (C) 2003  Paul Mundt
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+#ifndef DMA_REGISTER_H
+#define DMA_REGISTER_H
+
+/* DMA registers */
+#define SAR	0x00	/* Source Address Register */
+#define DAR	0x04	/* Destination Address Register */
+#define TCR	0x08	/* Transfer Count Register */
+#define CHCR	0x0C	/* Channel Control Register */
+#define DMAOR	0x40	/* DMA Operation Register */
+
+/* DMAOR definitions */
+#define DMAOR_AE	0x00000004	/* Address Error Flag */
+#define DMAOR_NMIF	0x00000002
+#define DMAOR_DME	0x00000001	/* DMA Master Enable */
+
+/* Definitions for the SuperH DMAC */
+#define REQ_L	0x00000000
+#define REQ_E	0x00080000
+#define RACK_H	0x00000000
+#define RACK_L	0x00040000
+#define ACK_R	0x00000000
+#define ACK_W	0x00020000
+#define ACK_H	0x00000000
+#define ACK_L	0x00010000
+#define DM_INC	0x00004000	/* Destination addresses are incremented */
+#define DM_DEC	0x00008000	/* Destination addresses are decremented */
+#define DM_FIX	0x0000c000	/* Destination address is fixed */
+#define SM_INC	0x00001000	/* Source addresses are incremented */
+#define SM_DEC	0x00002000	/* Source addresses are decremented */
+#define SM_FIX	0x00003000	/* Source address is fixed */
+#define RS_IN	0x00000200
+#define RS_OUT	0x00000300
+#define RS_AUTO	0x00000400	/* Auto Request */
+#define RS_ERS	0x00000800	/* DMA extended resource selector */
+#define TS_BLK	0x00000040
+#define TM_BUR	0x00000020
+#define CHCR_DE	0x00000001	/* DMA Enable */
+#define CHCR_TE	0x00000002	/* Transfer End Flag */
+#define CHCR_IE	0x00000004	/* Interrupt Enable */
+
+#endif
diff --git a/arch/sh/include/asm/dma.h b/arch/sh/include/asm/dma.h
new file mode 100644
index 000000000..fb6e4f7b0
--- /dev/null
+++ b/arch/sh/include/asm/dma.h
@@ -0,0 +1,151 @@
+/*
+ * include/asm-sh/dma.h
+ *
+ * Copyright (C) 2003, 2004  Paul Mundt
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+#ifndef __ASM_SH_DMA_H
+#define __ASM_SH_DMA_H
+#ifdef __KERNEL__
+
+#include <linux/spinlock.h>
+#include <linux/wait.h>
+#include <linux/sched.h>
+#include <linux/device.h>
+#include <asm-generic/dma.h>
+
+/*
+ * Read and write modes can mean drastically different things depending on the
+ * channel configuration. Consult your DMAC documentation and module
+ * implementation for further clues.
+ */
+#define DMA_MODE_READ		0x00
+#define DMA_MODE_WRITE		0x01
+#define DMA_MODE_MASK		0x01
+
+#define DMA_AUTOINIT		0x10
+
+/*
+ * DMAC (dma_info) flags
+ */
+enum {
+	DMAC_CHANNELS_CONFIGURED	= 0x01,
+	DMAC_CHANNELS_TEI_CAPABLE	= 0x02,	/* Transfer end interrupt */
+};
+
+/*
+ * DMA channel capabilities / flags
+ */
+enum {
+	DMA_CONFIGURED			= 0x01,
+
+	/*
+	 * Transfer end interrupt, inherited from DMAC.
+	 * wait_queue used in dma_wait_for_completion.
+	 */
+	DMA_TEI_CAPABLE			= 0x02,
+};
+
+extern spinlock_t dma_spin_lock;
+
+struct dma_channel;
+
+struct dma_ops {
+	int (*request)(struct dma_channel *chan);
+	void (*free)(struct dma_channel *chan);
+
+	int (*get_residue)(struct dma_channel *chan);
+	int (*xfer)(struct dma_channel *chan);
+	int (*configure)(struct dma_channel *chan, unsigned long flags);
+	int (*extend)(struct dma_channel *chan, unsigned long op, void *param);
+};
+
+struct dma_channel {
+	char dev_id[16];		/* unique name per DMAC of channel */
+
+	unsigned int chan;		/* DMAC channel number */
+	unsigned int vchan;		/* Virtual channel number */
+
+	unsigned int mode;
+	unsigned int count;
+
+	unsigned long sar;
+	unsigned long dar;
+
+	const char **caps;
+
+	unsigned long flags;
+	atomic_t busy;
+
+	wait_queue_head_t wait_queue;
+
+	struct device dev;
+	void *priv_data;
+};
+
+struct dma_info {
+	struct platform_device *pdev;
+
+	const char *name;
+	unsigned int nr_channels;
+	unsigned long flags;
+
+	struct dma_ops *ops;
+	struct dma_channel *channels;
+
+	struct list_head list;
+	int first_channel_nr;
+	int first_vchannel_nr;
+};
+
+struct dma_chan_caps {
+	int ch_num;
+	const char **caplist;
+};
+
+#define to_dma_channel(channel) container_of(channel, struct dma_channel, dev)
+
+/* arch/sh/drivers/dma/dma-api.c */
+extern int dma_xfer(unsigned int chan, unsigned long from,
+		    unsigned long to, size_t size, unsigned int mode);
+
+#define dma_write(chan, from, to, size)	\
+	dma_xfer(chan, from, to, size, DMA_MODE_WRITE)
+#define dma_write_page(chan, from, to)	\
+	dma_write(chan, from, to, PAGE_SIZE)
+
+#define dma_read(chan, from, to, size)	\
+	dma_xfer(chan, from, to, size, DMA_MODE_READ)
+#define dma_read_page(chan, from, to)	\
+	dma_read(chan, from, to, PAGE_SIZE)
+
+extern int request_dma_bycap(const char **dmac, const char **caps,
+			     const char *dev_id);
+extern int get_dma_residue(unsigned int chan);
+extern struct dma_info *get_dma_info(unsigned int chan);
+extern struct dma_channel *get_dma_channel(unsigned int chan);
+extern void dma_wait_for_completion(unsigned int chan);
+extern void dma_configure_channel(unsigned int chan, unsigned long flags);
+
+extern int register_dmac(struct dma_info *info);
+extern void unregister_dmac(struct dma_info *info);
+extern struct dma_info *get_dma_info_by_name(const char *dmac_name);
+
+extern int dma_extend(unsigned int chan, unsigned long op, void *param);
+extern int register_chan_caps(const char *dmac, struct dma_chan_caps *capslist);
+
+/* arch/sh/drivers/dma/dma-sysfs.c */
+extern int dma_create_sysfs_files(struct dma_channel *, struct dma_info *);
+extern void dma_remove_sysfs_files(struct dma_channel *, struct dma_info *);
+
+#ifdef CONFIG_PCI
+extern int isa_dma_bridge_buggy;
+#else
+#define isa_dma_bridge_buggy	(0)
+#endif
+
+#endif /* __KERNEL__ */
+#endif /* __ASM_SH_DMA_H */
diff --git a/arch/sh/include/asm/dmabrg.h b/arch/sh/include/asm/dmabrg.h
new file mode 100644
index 000000000..c5edba216
--- /dev/null
+++ b/arch/sh/include/asm/dmabrg.h
@@ -0,0 +1,23 @@
+/*
+ * SH7760 DMABRG (USB/Audio) support
+ */
+
+#ifndef _DMABRG_H_
+#define _DMABRG_H_
+
+/* IRQ sources */
+#define DMABRGIRQ_USBDMA	0
+#define DMABRGIRQ_USBDMAERR	1
+#define DMABRGIRQ_A0TXF		2
+#define DMABRGIRQ_A0TXH		3
+#define DMABRGIRQ_A0RXF		4
+#define DMABRGIRQ_A0RXH		5
+#define DMABRGIRQ_A1TXF		6
+#define DMABRGIRQ_A1TXH		7
+#define DMABRGIRQ_A1RXF		8
+#define DMABRGIRQ_A1RXH		9
+
+extern int dmabrg_request_irq(unsigned int, void(*)(void *), void *);
+extern void dmabrg_free_irq(unsigned int);
+
+#endif
diff --git a/arch/sh/include/asm/dwarf.h b/arch/sh/include/asm/dwarf.h
new file mode 100644
index 000000000..d62abd1d0
--- /dev/null
+++ b/arch/sh/include/asm/dwarf.h
@@ -0,0 +1,421 @@
+/*
+ * Copyright (C) 2009 Matt Fleming <matt@console-pimps.org>
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ */
+#ifndef __ASM_SH_DWARF_H
+#define __ASM_SH_DWARF_H
+
+#ifdef CONFIG_DWARF_UNWINDER
+
+/*
+ * DWARF expression operations
+ */
+#define DW_OP_addr	0x03
+#define DW_OP_deref	0x06
+#define DW_OP_const1u	0x08
+#define DW_OP_const1s	0x09
+#define DW_OP_const2u	0x0a
+#define DW_OP_const2s	0x0b
+#define DW_OP_const4u	0x0c
+#define DW_OP_const4s	0x0d
+#define DW_OP_const8u	0x0e
+#define DW_OP_const8s	0x0f
+#define DW_OP_constu	0x10
+#define DW_OP_consts	0x11
+#define DW_OP_dup	0x12
+#define DW_OP_drop	0x13
+#define DW_OP_over	0x14
+#define DW_OP_pick	0x15
+#define DW_OP_swap	0x16
+#define DW_OP_rot	0x17
+#define DW_OP_xderef	0x18
+#define DW_OP_abs	0x19
+#define DW_OP_and	0x1a
+#define DW_OP_div	0x1b
+#define DW_OP_minus	0x1c
+#define DW_OP_mod	0x1d
+#define DW_OP_mul	0x1e
+#define DW_OP_neg	0x1f
+#define DW_OP_not	0x20
+#define DW_OP_or	0x21
+#define DW_OP_plus	0x22
+#define DW_OP_plus_uconst	0x23
+#define DW_OP_shl	0x24
+#define DW_OP_shr	0x25
+#define DW_OP_shra	0x26
+#define DW_OP_xor	0x27
+#define DW_OP_skip	0x2f
+#define DW_OP_bra	0x28
+#define DW_OP_eq	0x29
+#define DW_OP_ge	0x2a
+#define DW_OP_gt	0x2b
+#define DW_OP_le	0x2c
+#define DW_OP_lt	0x2d
+#define DW_OP_ne	0x2e
+#define DW_OP_lit0	0x30
+#define DW_OP_lit1	0x31
+#define DW_OP_lit2	0x32
+#define DW_OP_lit3	0x33
+#define DW_OP_lit4	0x34
+#define DW_OP_lit5	0x35
+#define DW_OP_lit6	0x36
+#define DW_OP_lit7	0x37
+#define DW_OP_lit8	0x38
+#define DW_OP_lit9	0x39
+#define DW_OP_lit10	0x3a
+#define DW_OP_lit11	0x3b
+#define DW_OP_lit12	0x3c
+#define DW_OP_lit13	0x3d
+#define DW_OP_lit14	0x3e
+#define DW_OP_lit15	0x3f
+#define DW_OP_lit16	0x40
+#define DW_OP_lit17	0x41
+#define DW_OP_lit18	0x42
+#define DW_OP_lit19	0x43
+#define DW_OP_lit20	0x44
+#define DW_OP_lit21	0x45
+#define DW_OP_lit22	0x46
+#define DW_OP_lit23	0x47
+#define DW_OP_lit24	0x48
+#define DW_OP_lit25	0x49
+#define DW_OP_lit26	0x4a
+#define DW_OP_lit27	0x4b
+#define DW_OP_lit28	0x4c
+#define DW_OP_lit29	0x4d
+#define DW_OP_lit30	0x4e
+#define DW_OP_lit31	0x4f
+#define DW_OP_reg0	0x50
+#define DW_OP_reg1	0x51
+#define DW_OP_reg2	0x52
+#define DW_OP_reg3	0x53
+#define DW_OP_reg4	0x54
+#define DW_OP_reg5	0x55
+#define DW_OP_reg6	0x56
+#define DW_OP_reg7	0x57
+#define DW_OP_reg8	0x58
+#define DW_OP_reg9	0x59
+#define DW_OP_reg10	0x5a
+#define DW_OP_reg11	0x5b
+#define DW_OP_reg12	0x5c
+#define DW_OP_reg13	0x5d
+#define DW_OP_reg14	0x5e
+#define DW_OP_reg15	0x5f
+#define DW_OP_reg16	0x60
+#define DW_OP_reg17	0x61
+#define DW_OP_reg18	0x62
+#define DW_OP_reg19	0x63
+#define DW_OP_reg20	0x64
+#define DW_OP_reg21	0x65
+#define DW_OP_reg22	0x66
+#define DW_OP_reg23	0x67
+#define DW_OP_reg24	0x68
+#define DW_OP_reg25	0x69
+#define DW_OP_reg26	0x6a
+#define DW_OP_reg27	0x6b
+#define DW_OP_reg28	0x6c
+#define DW_OP_reg29	0x6d
+#define DW_OP_reg30	0x6e
+#define DW_OP_reg31	0x6f
+#define DW_OP_breg0	0x70
+#define DW_OP_breg1	0x71
+#define DW_OP_breg2	0x72
+#define DW_OP_breg3	0x73
+#define DW_OP_breg4	0x74
+#define DW_OP_breg5	0x75
+#define DW_OP_breg6	0x76
+#define DW_OP_breg7	0x77
+#define DW_OP_breg8	0x78
+#define DW_OP_breg9	0x79
+#define DW_OP_breg10	0x7a
+#define DW_OP_breg11	0x7b
+#define DW_OP_breg12	0x7c
+#define DW_OP_breg13	0x7d
+#define DW_OP_breg14	0x7e
+#define DW_OP_breg15	0x7f
+#define DW_OP_breg16	0x80
+#define DW_OP_breg17	0x81
+#define DW_OP_breg18	0x82
+#define DW_OP_breg19	0x83
+#define DW_OP_breg20	0x84
+#define DW_OP_breg21	0x85
+#define DW_OP_breg22	0x86
+#define DW_OP_breg23	0x87
+#define DW_OP_breg24	0x88
+#define DW_OP_breg25	0x89
+#define DW_OP_breg26	0x8a
+#define DW_OP_breg27	0x8b
+#define DW_OP_breg28	0x8c
+#define DW_OP_breg29	0x8d
+#define DW_OP_breg30	0x8e
+#define DW_OP_breg31	0x8f
+#define DW_OP_regx	0x90
+#define DW_OP_fbreg	0x91
+#define DW_OP_bregx	0x92
+#define DW_OP_piece	0x93
+#define DW_OP_deref_size	0x94
+#define DW_OP_xderef_size	0x95
+#define DW_OP_nop	0x96
+#define DW_OP_push_object_address	0x97
+#define DW_OP_call2	0x98
+#define DW_OP_call4	0x99
+#define DW_OP_call_ref	0x9a
+#define DW_OP_form_tls_address	0x9b
+#define DW_OP_call_frame_cfa	0x9c
+#define DW_OP_bit_piece	0x9d
+#define DW_OP_lo_user	0xe0
+#define DW_OP_hi_user	0xff
+
+/*
+ * Addresses used in FDE entries in the .eh_frame section may be encoded
+ * using one of the following encodings.
+ */
+#define DW_EH_PE_absptr	0x00
+#define DW_EH_PE_omit	0xff
+#define DW_EH_PE_uleb128	0x01
+#define DW_EH_PE_udata2	0x02
+#define DW_EH_PE_udata4	0x03
+#define DW_EH_PE_udata8	0x04
+#define DW_EH_PE_sleb128	0x09
+#define DW_EH_PE_sdata2	0x0a
+#define DW_EH_PE_sdata4	0x0b
+#define DW_EH_PE_sdata8	0x0c
+#define DW_EH_PE_signed	0x09
+
+#define DW_EH_PE_pcrel	0x10
+
+/*
+ * The architecture-specific register number that contains the return
+ * address in the .debug_frame table.
+ */
+#define DWARF_ARCH_RA_REG	17
+
+#ifndef __ASSEMBLY__
+
+#include <linux/compiler.h>
+#include <linux/bug.h>
+#include <linux/list.h>
+#include <linux/module.h>
+
+/*
+ * Read either the frame pointer (r14) or the stack pointer (r15).
+ * NOTE: this MUST be inlined.
+ */
+static __always_inline unsigned long dwarf_read_arch_reg(unsigned int reg)
+{
+	unsigned long value = 0;
+
+	switch (reg) {
+	case 14:
+		__asm__ __volatile__("mov r14, %0\n" : "=r" (value));
+		break;
+	case 15:
+		__asm__ __volatile__("mov r15, %0\n" : "=r" (value));
+		break;
+	default:
+		BUG();
+	}
+
+	return value;
+}
+
+/**
+ *	dwarf_cie - Common Information Entry
+ */
+struct dwarf_cie {
+	unsigned long length;
+	unsigned long cie_id;
+	unsigned char version;
+	const char *augmentation;
+	unsigned int code_alignment_factor;
+	int data_alignment_factor;
+
+	/* Which column in the rule table represents return addr of func. */
+	unsigned int return_address_reg;
+
+	unsigned char *initial_instructions;
+	unsigned char *instructions_end;
+
+	unsigned char encoding;
+
+	unsigned long cie_pointer;
+
+	unsigned long flags;
+#define DWARF_CIE_Z_AUGMENTATION	(1 << 0)
+
+	/* linked-list entry if this CIE is from a module */
+	struct list_head link;
+
+	struct rb_node node;
+};
+
+/**
+ *	dwarf_fde - Frame Description Entry
+ */
+struct dwarf_fde {
+	unsigned long length;
+	unsigned long cie_pointer;
+	struct dwarf_cie *cie;
+	unsigned long initial_location;
+	unsigned long address_range;
+	unsigned char *instructions;
+	unsigned char *end;
+
+	/* linked-list entry if this FDE is from a module */
+	struct list_head link;
+
+	struct rb_node node;
+};
+
+/**
+ *	dwarf_frame - DWARF information for a frame in the call stack
+ */
+struct dwarf_frame {
+	struct dwarf_frame *prev, *next;
+
+	unsigned long pc;
+
+	struct list_head reg_list;
+
+	unsigned long cfa;
+
+	/* Valid when DW_FRAME_CFA_REG_OFFSET is set in flags */
+	unsigned int cfa_register;
+	unsigned int cfa_offset;
+
+	/* Valid when DW_FRAME_CFA_REG_EXP is set in flags */
+	unsigned char *cfa_expr;
+	unsigned int cfa_expr_len;
+
+	unsigned long flags;
+#define DWARF_FRAME_CFA_REG_OFFSET	(1 << 0)
+#define DWARF_FRAME_CFA_REG_EXP		(1 << 1)
+
+	unsigned long return_addr;
+};
+
+/**
+ *	dwarf_reg - DWARF register
+ *	@flags: Describes how to calculate the value of this register
+ */
+struct dwarf_reg {
+	struct list_head link;
+
+	unsigned int number;
+
+	unsigned long addr;
+	unsigned long flags;
+#define DWARF_REG_OFFSET	(1 << 0)
+#define DWARF_VAL_OFFSET	(1 << 1)
+#define DWARF_UNDEFINED		(1 << 2)
+};
+
+/*
+ * Call Frame instruction opcodes.
+ */
+#define DW_CFA_advance_loc	0x40
+#define DW_CFA_offset		0x80
+#define DW_CFA_restore		0xc0
+#define DW_CFA_nop		0x00
+#define DW_CFA_set_loc		0x01
+#define DW_CFA_advance_loc1	0x02
+#define DW_CFA_advance_loc2	0x03
+#define DW_CFA_advance_loc4	0x04
+#define DW_CFA_offset_extended	0x05
+#define DW_CFA_restore_extended	0x06
+#define DW_CFA_undefined	0x07
+#define DW_CFA_same_value	0x08
+#define DW_CFA_register		0x09
+#define DW_CFA_remember_state	0x0a
+#define DW_CFA_restore_state	0x0b
+#define DW_CFA_def_cfa		0x0c
+#define DW_CFA_def_cfa_register	0x0d
+#define DW_CFA_def_cfa_offset	0x0e
+#define DW_CFA_def_cfa_expression	0x0f
+#define DW_CFA_expression	0x10
+#define DW_CFA_offset_extended_sf	0x11
+#define DW_CFA_def_cfa_sf	0x12
+#define DW_CFA_def_cfa_offset_sf	0x13
+#define DW_CFA_val_offset	0x14
+#define DW_CFA_val_offset_sf	0x15
+#define DW_CFA_val_expression	0x16
+#define DW_CFA_lo_user		0x1c
+#define DW_CFA_hi_user		0x3f
+
+/* GNU extension opcodes  */
+#define DW_CFA_GNU_args_size	0x2e
+#define DW_CFA_GNU_negative_offset_extended 0x2f
+
+/*
+ * Some call frame instructions encode their operands in the opcode. We
+ * need some helper functions to extract both the opcode and operands
+ * from an instruction.
+ */
+static inline unsigned int DW_CFA_opcode(unsigned long insn)
+{
+	return (insn & 0xc0);
+}
+
+static inline unsigned int DW_CFA_operand(unsigned long insn)
+{
+	return (insn & 0x3f);
+}
+
+#define DW_EH_FRAME_CIE	0		/* .eh_frame CIE IDs are 0 */
+#define DW_CIE_ID	0xffffffff
+#define DW64_CIE_ID	0xffffffffffffffffULL
+
+/*
+ * DWARF FDE/CIE length field values.
+ */
+#define DW_EXT_LO	0xfffffff0
+#define DW_EXT_HI	0xffffffff
+#define DW_EXT_DWARF64	DW_EXT_HI
+
+extern struct dwarf_frame *dwarf_unwind_stack(unsigned long,
+					      struct dwarf_frame *);
+extern void dwarf_free_frame(struct dwarf_frame *);
+
+extern int module_dwarf_finalize(const Elf_Ehdr *, const Elf_Shdr *,
+				 struct module *);
+extern void module_dwarf_cleanup(struct module *);
+
+#endif /* !__ASSEMBLY__ */
+
+#define CFI_STARTPROC	.cfi_startproc
+#define CFI_ENDPROC	.cfi_endproc
+#define CFI_DEF_CFA	.cfi_def_cfa
+#define CFI_REGISTER	.cfi_register
+#define CFI_REL_OFFSET	.cfi_rel_offset
+#define CFI_UNDEFINED	.cfi_undefined
+
+#else
+
+/*
+ * Use the asm comment character to ignore the rest of the line.
+ */
+#define CFI_IGNORE	!
+
+#define CFI_STARTPROC	CFI_IGNORE
+#define CFI_ENDPROC	CFI_IGNORE
+#define CFI_DEF_CFA	CFI_IGNORE
+#define CFI_REGISTER	CFI_IGNORE
+#define CFI_REL_OFFSET	CFI_IGNORE
+#define CFI_UNDEFINED	CFI_IGNORE
+
+#ifndef __ASSEMBLY__
+static inline void dwarf_unwinder_init(void)
+{
+}
+
+#define module_dwarf_finalize(hdr, sechdrs, me)	(0)
+#define module_dwarf_cleanup(mod)		do { } while (0)
+
+#endif
+
+#endif /* CONFIG_DWARF_UNWINDER */
+
+#endif /* __ASM_SH_DWARF_H */
diff --git a/arch/sh/include/asm/elf.h b/arch/sh/include/asm/elf.h
new file mode 100644
index 000000000..bf9f44f17
--- /dev/null
+++ b/arch/sh/include/asm/elf.h
@@ -0,0 +1,235 @@
+#ifndef __ASM_SH_ELF_H
+#define __ASM_SH_ELF_H
+
+#include <linux/utsname.h>
+#include <asm/auxvec.h>
+#include <asm/ptrace.h>
+#include <asm/user.h>
+
+/* ELF header e_flags defines */
+#define EF_SH_PIC		0x100	/* -fpic */
+#define EF_SH_FDPIC		0x8000	/* -mfdpic */
+
+/* SH (particularly SHcompact) relocation types  */
+#define	R_SH_NONE		0
+#define	R_SH_DIR32		1
+#define	R_SH_REL32		2
+#define	R_SH_DIR8WPN		3
+#define	R_SH_IND12W		4
+#define	R_SH_DIR8WPL		5
+#define	R_SH_DIR8WPZ		6
+#define	R_SH_DIR8BP		7
+#define	R_SH_DIR8W		8
+#define	R_SH_DIR8L		9
+#define	R_SH_SWITCH16		25
+#define	R_SH_SWITCH32		26
+#define	R_SH_USES		27
+#define	R_SH_COUNT		28
+#define	R_SH_ALIGN		29
+#define	R_SH_CODE		30
+#define	R_SH_DATA		31
+#define	R_SH_LABEL		32
+#define	R_SH_SWITCH8		33
+#define	R_SH_GNU_VTINHERIT	34
+#define	R_SH_GNU_VTENTRY	35
+#define	R_SH_TLS_GD_32		144
+#define	R_SH_TLS_LD_32		145
+#define	R_SH_TLS_LDO_32		146
+#define	R_SH_TLS_IE_32		147
+#define	R_SH_TLS_LE_32		148
+#define	R_SH_TLS_DTPMOD32	149
+#define	R_SH_TLS_DTPOFF32	150
+#define	R_SH_TLS_TPOFF32	151
+#define	R_SH_GOT32		160
+#define	R_SH_PLT32		161
+#define	R_SH_COPY		162
+#define	R_SH_GLOB_DAT		163
+#define	R_SH_JMP_SLOT		164
+#define	R_SH_RELATIVE		165
+#define	R_SH_GOTOFF		166
+#define	R_SH_GOTPC		167
+
+/* FDPIC relocs */
+#define R_SH_GOT20		201
+#define R_SH_GOTOFF20		202
+#define R_SH_GOTFUNCDESC	203
+#define R_SH_GOTFUNCDESC20	204
+#define R_SH_GOTOFFFUNCDESC	205
+#define R_SH_GOTOFFFUNCDESC20	206
+#define R_SH_FUNCDESC		207
+#define R_SH_FUNCDESC_VALUE	208
+
+/* SHmedia relocs */
+#define R_SH_IMM_LOW16		246
+#define R_SH_IMM_LOW16_PCREL	247
+#define R_SH_IMM_MEDLOW16	248
+#define R_SH_IMM_MEDLOW16_PCREL	249
+/* Keep this the last entry.  */
+#define	R_SH_NUM		256
+
+/*
+ * ELF register definitions..
+ */
+
+typedef unsigned long elf_greg_t;
+
+#define ELF_NGREG (sizeof (struct pt_regs) / sizeof(elf_greg_t))
+typedef elf_greg_t elf_gregset_t[ELF_NGREG];
+
+typedef struct user_fpu_struct elf_fpregset_t;
+
+/*
+ * These are used to set parameters in the core dumps.
+ */
+#define ELF_CLASS	ELFCLASS32
+#ifdef __LITTLE_ENDIAN__
+#define ELF_DATA	ELFDATA2LSB
+#else
+#define ELF_DATA	ELFDATA2MSB
+#endif
+#define ELF_ARCH	EM_SH
+
+#ifdef __KERNEL__
+/*
+ * This is used to ensure we don't load something for the wrong architecture.
+ */
+#define elf_check_arch(x)		((x)->e_machine == EM_SH)
+#define elf_check_fdpic(x)		((x)->e_flags & EF_SH_FDPIC)
+#define elf_check_const_displacement(x)	((x)->e_flags & EF_SH_PIC)
+
+/*
+ * Enable dump using regset.
+ * This covers all of general/DSP/FPU regs.
+ */
+#define CORE_DUMP_USE_REGSET
+
+#define ELF_FDPIC_CORE_EFLAGS	EF_SH_FDPIC
+#define ELF_EXEC_PAGESIZE	PAGE_SIZE
+
+/* 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         (2 * TASK_SIZE / 3)
+
+#define ELF_CORE_COPY_REGS(_dest,_regs)				\
+	memcpy((char *) &_dest, (char *) _regs,			\
+	       sizeof(struct pt_regs));
+
+/* This yields a mask that user programs can use to figure out what
+   instruction set this CPU supports.  This could be done in user space,
+   but it's not easy, and we've already done it here.  */
+
+#define ELF_HWCAP	(boot_cpu_data.flags)
+
+/* 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 the moment, we have only optimizations for the Intel generations,
+   but that could change... */
+
+#define ELF_PLATFORM	(utsname()->machine)
+
+#ifdef __SH5__
+#define ELF_PLAT_INIT(_r, load_addr) \
+  do { _r->regs[0]=0; _r->regs[1]=0; _r->regs[2]=0; _r->regs[3]=0; \
+       _r->regs[4]=0; _r->regs[5]=0; _r->regs[6]=0; _r->regs[7]=0; \
+       _r->regs[8]=0; _r->regs[9]=0; _r->regs[10]=0; _r->regs[11]=0; \
+       _r->regs[12]=0; _r->regs[13]=0; _r->regs[14]=0; _r->regs[15]=0; \
+       _r->regs[16]=0; _r->regs[17]=0; _r->regs[18]=0; _r->regs[19]=0; \
+       _r->regs[20]=0; _r->regs[21]=0; _r->regs[22]=0; _r->regs[23]=0; \
+       _r->regs[24]=0; _r->regs[25]=0; _r->regs[26]=0; _r->regs[27]=0; \
+       _r->regs[28]=0; _r->regs[29]=0; _r->regs[30]=0; _r->regs[31]=0; \
+       _r->regs[32]=0; _r->regs[33]=0; _r->regs[34]=0; _r->regs[35]=0; \
+       _r->regs[36]=0; _r->regs[37]=0; _r->regs[38]=0; _r->regs[39]=0; \
+       _r->regs[40]=0; _r->regs[41]=0; _r->regs[42]=0; _r->regs[43]=0; \
+       _r->regs[44]=0; _r->regs[45]=0; _r->regs[46]=0; _r->regs[47]=0; \
+       _r->regs[48]=0; _r->regs[49]=0; _r->regs[50]=0; _r->regs[51]=0; \
+       _r->regs[52]=0; _r->regs[53]=0; _r->regs[54]=0; _r->regs[55]=0; \
+       _r->regs[56]=0; _r->regs[57]=0; _r->regs[58]=0; _r->regs[59]=0; \
+       _r->regs[60]=0; _r->regs[61]=0; _r->regs[62]=0; \
+       _r->tregs[0]=0; _r->tregs[1]=0; _r->tregs[2]=0; _r->tregs[3]=0; \
+       _r->tregs[4]=0; _r->tregs[5]=0; _r->tregs[6]=0; _r->tregs[7]=0; \
+       _r->sr = SR_FD | SR_MMU; } while (0)
+#else
+#define ELF_PLAT_INIT(_r, load_addr) \
+  do { _r->regs[0]=0; _r->regs[1]=0; _r->regs[2]=0; _r->regs[3]=0; \
+       _r->regs[4]=0; _r->regs[5]=0; _r->regs[6]=0; _r->regs[7]=0; \
+       _r->regs[8]=0; _r->regs[9]=0; _r->regs[10]=0; _r->regs[11]=0; \
+       _r->regs[12]=0; _r->regs[13]=0; _r->regs[14]=0; \
+       _r->sr = SR_FD; } while (0)
+
+#define ELF_FDPIC_PLAT_INIT(_r, _exec_map_addr, _interp_map_addr,	\
+			    _dynamic_addr)				\
+do {									\
+	_r->regs[0]	= 0;						\
+	_r->regs[1]	= 0;						\
+	_r->regs[2]	= 0;						\
+	_r->regs[3]	= 0;						\
+	_r->regs[4]	= 0;						\
+	_r->regs[5]	= 0;						\
+	_r->regs[6]	= 0;						\
+	_r->regs[7]	= 0;						\
+	_r->regs[8]	= _exec_map_addr;				\
+	_r->regs[9]	= _interp_map_addr;				\
+	_r->regs[10]	= _dynamic_addr;				\
+	_r->regs[11]	= 0;						\
+	_r->regs[12]	= 0;						\
+	_r->regs[13]	= 0;						\
+	_r->regs[14]	= 0;						\
+	_r->sr		= SR_FD;					\
+} while (0)
+#endif
+
+#define SET_PERSONALITY(ex) \
+	set_personality(PER_LINUX_32BIT | (current->personality & (~PER_MASK)))
+
+#ifdef CONFIG_VSYSCALL
+/* vDSO has arch_setup_additional_pages */
+#define ARCH_HAS_SETUP_ADDITIONAL_PAGES
+struct linux_binprm;
+extern int arch_setup_additional_pages(struct linux_binprm *bprm,
+				       int uses_interp);
+
+extern unsigned int vdso_enabled;
+extern void __kernel_vsyscall;
+
+#define VDSO_BASE		((unsigned long)current->mm->context.vdso)
+#define VDSO_SYM(x)		(VDSO_BASE + (unsigned long)(x))
+
+#define VSYSCALL_AUX_ENT					\
+	if (vdso_enabled)					\
+		NEW_AUX_ENT(AT_SYSINFO_EHDR, VDSO_BASE);	\
+	else							\
+		NEW_AUX_ENT(AT_IGNORE, 0)
+#else
+#define VSYSCALL_AUX_ENT	NEW_AUX_ENT(AT_IGNORE, 0)
+#endif /* CONFIG_VSYSCALL */
+
+#ifdef CONFIG_SH_FPU
+#define FPU_AUX_ENT	NEW_AUX_ENT(AT_FPUCW, FPSCR_INIT)
+#else
+#define FPU_AUX_ENT	NEW_AUX_ENT(AT_IGNORE, 0)
+#endif
+
+extern int l1i_cache_shape, l1d_cache_shape, l2_cache_shape;
+
+/* update AT_VECTOR_SIZE_ARCH if the number of NEW_AUX_ENT entries changes */
+#define ARCH_DLINFO						\
+do {								\
+	/* Optional FPU initialization */			\
+	FPU_AUX_ENT;						\
+								\
+	/* Optional vsyscall entry */				\
+	VSYSCALL_AUX_ENT;					\
+								\
+	/* Cache desc */					\
+	NEW_AUX_ENT(AT_L1I_CACHESHAPE, l1i_cache_shape);	\
+	NEW_AUX_ENT(AT_L1D_CACHESHAPE, l1d_cache_shape);	\
+	NEW_AUX_ENT(AT_L2_CACHESHAPE, l2_cache_shape);		\
+} while (0)
+
+#endif /* __KERNEL__ */
+#endif /* __ASM_SH_ELF_H */
diff --git a/arch/sh/include/asm/entry-macros.S b/arch/sh/include/asm/entry-macros.S
new file mode 100644
index 000000000..cc43a55e1
--- /dev/null
+++ b/arch/sh/include/asm/entry-macros.S
@@ -0,0 +1,122 @@
+! entry.S macro define
+	
+	.macro	cli
+	stc	sr, r0
+	or	#0xf0, r0
+	ldc	r0, sr
+	.endm
+
+	.macro	sti
+	mov	#0xfffffff0, r11
+	extu.b	r11, r11
+	not	r11, r11
+	stc	sr, r10
+	and	r11, r10
+#ifdef CONFIG_CPU_HAS_SR_RB
+	stc	k_g_imask, r11
+	or	r11, r10
+#endif
+	ldc	r10, sr
+	.endm
+
+	.macro	get_current_thread_info, ti, tmp
+#ifdef CONFIG_CPU_HAS_SR_RB
+	stc	r7_bank, \ti
+#else
+	mov	#((THREAD_SIZE - 1) >> 10) ^ 0xff, \tmp
+	shll8	\tmp
+	shll2	\tmp
+	mov	r15, \ti
+	and	\tmp, \ti
+#endif	
+	.endm
+
+#ifdef CONFIG_TRACE_IRQFLAGS
+
+	.macro	TRACE_IRQS_ON
+	mov.l	r0, @-r15
+	mov.l	r1, @-r15
+	mov.l	r2, @-r15
+	mov.l	r3, @-r15
+	mov.l	r4, @-r15
+	mov.l	r5, @-r15
+	mov.l	r6, @-r15
+	mov.l	r7, @-r15
+
+	mov.l   7834f, r0
+	jsr	@r0
+	 nop
+
+	mov.l	@r15+, r7
+	mov.l	@r15+, r6
+	mov.l	@r15+, r5
+	mov.l	@r15+, r4
+	mov.l	@r15+, r3
+	mov.l	@r15+, r2
+	mov.l	@r15+, r1
+	mov.l	@r15+, r0
+	mov.l	7834f, r0
+
+	bra	7835f
+	 nop
+	.balign	4
+7834:	.long	trace_hardirqs_on
+7835:
+	.endm
+	.macro	TRACE_IRQS_OFF
+
+	mov.l	r0, @-r15
+	mov.l	r1, @-r15
+	mov.l	r2, @-r15
+	mov.l	r3, @-r15
+	mov.l	r4, @-r15
+	mov.l	r5, @-r15
+	mov.l	r6, @-r15
+	mov.l	r7, @-r15
+
+	mov.l	7834f, r0
+	jsr	@r0
+	 nop
+
+	mov.l	@r15+, r7
+	mov.l	@r15+, r6
+	mov.l	@r15+, r5
+	mov.l	@r15+, r4
+	mov.l	@r15+, r3
+	mov.l	@r15+, r2
+	mov.l	@r15+, r1
+	mov.l	@r15+, r0
+	mov.l	7834f, r0
+
+	bra	7835f
+	 nop
+	.balign	4
+7834:	.long	trace_hardirqs_off
+7835:
+	.endm
+
+#else
+	.macro	TRACE_IRQS_ON
+	.endm
+
+	.macro	TRACE_IRQS_OFF
+	.endm
+#endif
+
+#if defined(CONFIG_CPU_SH2A) || defined(CONFIG_CPU_SH4)
+# define PREF(x)	pref	@x
+#else
+# define PREF(x)	nop
+#endif
+
+	/*
+	 * Macro for use within assembly. Because the DWARF unwinder
+	 * needs to use the frame register to unwind the stack, we
+	 * need to setup r14 with the value of the stack pointer as
+	 * the return address is usually on the stack somewhere.
+	 */
+	.macro	setup_frame_reg
+#ifdef CONFIG_DWARF_UNWINDER
+	mov	r15, r14
+#endif
+	.endm
diff --git a/arch/sh/include/asm/fb.h b/arch/sh/include/asm/fb.h
new file mode 100644
index 000000000..d92e99cd8
--- /dev/null
+++ b/arch/sh/include/asm/fb.h
@@ -0,0 +1,19 @@
+#ifndef _ASM_FB_H_
+#define _ASM_FB_H_
+
+#include <linux/fb.h>
+#include <linux/fs.h>
+#include <asm/page.h>
+
+static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma,
+				unsigned long off)
+{
+	vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
+}
+
+static inline int fb_is_primary_device(struct fb_info *info)
+{
+	return 0;
+}
+
+#endif /* _ASM_FB_H_ */
diff --git a/arch/sh/include/asm/fixmap.h b/arch/sh/include/asm/fixmap.h
new file mode 100644
index 000000000..4daf91c3b
--- /dev/null
+++ b/arch/sh/include/asm/fixmap.h
@@ -0,0 +1,101 @@
+/*
+ * fixmap.h: compile-time virtual memory allocation
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 1998 Ingo Molnar
+ *
+ * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
+ */
+
+#ifndef _ASM_FIXMAP_H
+#define _ASM_FIXMAP_H
+
+#include <linux/kernel.h>
+#include <linux/threads.h>
+#include <asm/page.h>
+#ifdef CONFIG_HIGHMEM
+#include <asm/kmap_types.h>
+#endif
+
+/*
+ * Here we define all the compile-time 'special' virtual
+ * addresses. The point is to have a constant address at
+ * compile time, but to set the physical address only
+ * in the boot process. We allocate these special  addresses
+ * from the end of P3 backwards.
+ * Also this lets us do fail-safe vmalloc(), we
+ * can guarantee that these special addresses and
+ * vmalloc()-ed addresses never overlap.
+ *
+ * these 'compile-time allocated' memory buffers are
+ * fixed-size 4k pages. (or larger if used with an increment
+ * highger than 1) use fixmap_set(idx,phys) to associate
+ * physical memory with fixmap indices.
+ *
+ * TLB entries of such buffers will not be flushed across
+ * task switches.
+ */
+
+/*
+ * on UP currently we will have no trace of the fixmap mechanizm,
+ * no page table allocations, etc. This might change in the
+ * future, say framebuffers for the console driver(s) could be
+ * fix-mapped?
+ */
+enum fixed_addresses {
+	/*
+	 * The FIX_CMAP entries are used by kmap_coherent() to get virtual
+	 * addresses which are of a known color, and so their values are
+	 * important. __fix_to_virt(FIX_CMAP_END - n) must give an address
+	 * which is the same color as a page (n<<PAGE_SHIFT).
+	 */
+#define FIX_N_COLOURS 8
+	FIX_CMAP_BEGIN,
+	FIX_CMAP_END = FIX_CMAP_BEGIN + (FIX_N_COLOURS * NR_CPUS) - 1,
+
+#ifdef CONFIG_HIGHMEM
+	FIX_KMAP_BEGIN,	/* reserved pte's for temporary kernel mappings */
+	FIX_KMAP_END = FIX_KMAP_BEGIN + (KM_TYPE_NR * NR_CPUS) - 1,
+#endif
+
+#ifdef CONFIG_IOREMAP_FIXED
+	/*
+	 * FIX_IOREMAP entries are useful for mapping physical address
+	 * space before ioremap() is useable, e.g. really early in boot
+	 * before kmalloc() is working.
+	 */
+#define FIX_N_IOREMAPS	32
+	FIX_IOREMAP_BEGIN,
+	FIX_IOREMAP_END = FIX_IOREMAP_BEGIN + FIX_N_IOREMAPS - 1,
+#endif
+
+	__end_of_fixed_addresses
+};
+
+extern void __set_fixmap(enum fixed_addresses idx,
+			 unsigned long phys, pgprot_t flags);
+extern void __clear_fixmap(enum fixed_addresses idx, pgprot_t flags);
+
+/*
+ * used by vmalloc.c.
+ *
+ * Leave one empty page between vmalloc'ed areas and
+ * the start of the fixmap, and leave one page empty
+ * at the top of mem..
+ */
+#ifdef CONFIG_SUPERH32
+#define FIXADDR_TOP	(P4SEG - PAGE_SIZE)
+#else
+#define FIXADDR_TOP	((unsigned long)(-PAGE_SIZE))
+#endif
+#define FIXADDR_SIZE	(__end_of_fixed_addresses << PAGE_SHIFT)
+#define FIXADDR_START	(FIXADDR_TOP - FIXADDR_SIZE)
+
+#define FIXMAP_PAGE_NOCACHE PAGE_KERNEL_NOCACHE
+
+#include <asm-generic/fixmap.h>
+
+#endif
diff --git a/arch/sh/include/asm/flat.h b/arch/sh/include/asm/flat.h
new file mode 100644
index 000000000..5d84df5e2
--- /dev/null
+++ b/arch/sh/include/asm/flat.h
@@ -0,0 +1,30 @@
+/*
+ * include/asm-sh/flat.h
+ *
+ * uClinux flat-format executables
+ *
+ * Copyright (C) 2003  Paul Mundt
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive for
+ * more details.
+ */
+#ifndef __ASM_SH_FLAT_H
+#define __ASM_SH_FLAT_H
+
+#define	flat_argvp_envp_on_stack()		0
+#define	flat_old_ram_flag(flags)		(flags)
+#define	flat_reloc_valid(reloc, size)		((reloc) <= (size))
+#define	flat_get_addr_from_rp(rp, relval, flags, p)	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)		({ (void)p; 0; })
+
+#define FLAT_PLAT_INIT(_r) \
+  do { _r->regs[0]=0; _r->regs[1]=0; _r->regs[2]=0; _r->regs[3]=0; \
+       _r->regs[4]=0; _r->regs[5]=0; _r->regs[6]=0; _r->regs[7]=0; \
+       _r->regs[8]=0; _r->regs[9]=0; _r->regs[10]=0; _r->regs[11]=0; \
+       _r->regs[12]=0; _r->regs[13]=0; _r->regs[14]=0; \
+       _r->sr = SR_FD; } while (0)
+
+#endif /* __ASM_SH_FLAT_H */
diff --git a/arch/sh/include/asm/fpu.h b/arch/sh/include/asm/fpu.h
new file mode 100644
index 000000000..09fc2bc8a
--- /dev/null
+++ b/arch/sh/include/asm/fpu.h
@@ -0,0 +1,71 @@
+#ifndef __ASM_SH_FPU_H
+#define __ASM_SH_FPU_H
+
+#ifndef __ASSEMBLY__
+
+struct task_struct;
+
+#ifdef CONFIG_SH_FPU
+static inline void release_fpu(struct pt_regs *regs)
+{
+	regs->sr |= SR_FD;
+}
+
+static inline void grab_fpu(struct pt_regs *regs)
+{
+	regs->sr &= ~SR_FD;
+}
+
+extern void save_fpu(struct task_struct *__tsk);
+extern void restore_fpu(struct task_struct *__tsk);
+extern void fpu_state_restore(struct pt_regs *regs);
+extern void __fpu_state_restore(void);
+#else
+#define save_fpu(tsk)			do { } while (0)
+#define restore_fpu(tsk)		do { } while (0)
+#define release_fpu(regs)		do { } while (0)
+#define grab_fpu(regs)			do { } while (0)
+#define fpu_state_restore(regs)		do { } while (0)
+#define __fpu_state_restore(regs)	do { } while (0)
+#endif
+
+struct user_regset;
+
+extern int do_fpu_inst(unsigned short, struct pt_regs *);
+extern int init_fpu(struct task_struct *);
+
+extern int fpregs_get(struct task_struct *target,
+		      const struct user_regset *regset,
+		      unsigned int pos, unsigned int count,
+		      void *kbuf, void __user *ubuf);
+
+static inline void __unlazy_fpu(struct task_struct *tsk, struct pt_regs *regs)
+{
+	if (task_thread_info(tsk)->status & TS_USEDFPU) {
+		task_thread_info(tsk)->status &= ~TS_USEDFPU;
+		save_fpu(tsk);
+		release_fpu(regs);
+	} else
+		tsk->thread.fpu_counter = 0;
+}
+
+static inline void unlazy_fpu(struct task_struct *tsk, struct pt_regs *regs)
+{
+	preempt_disable();
+	__unlazy_fpu(tsk, regs);
+	preempt_enable();
+}
+
+static inline void clear_fpu(struct task_struct *tsk, struct pt_regs *regs)
+{
+	preempt_disable();
+	if (task_thread_info(tsk)->status & TS_USEDFPU) {
+		task_thread_info(tsk)->status &= ~TS_USEDFPU;
+		release_fpu(regs);
+	}
+	preempt_enable();
+}
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* __ASM_SH_FPU_H */
diff --git a/arch/sh/include/asm/freq.h b/arch/sh/include/asm/freq.h
new file mode 100644
index 000000000..4ece90b09
--- /dev/null
+++ b/arch/sh/include/asm/freq.h
@@ -0,0 +1,18 @@
+/*
+ * include/asm-sh/freq.h
+ *
+ * Copyright (C) 2002, 2003 Paul Mundt
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ */
+#ifndef __ASM_SH_FREQ_H
+#define __ASM_SH_FREQ_H
+#ifdef __KERNEL__
+
+#include <cpu/freq.h>
+
+#endif /* __KERNEL__ */
+#endif /* __ASM_SH_FREQ_H */
diff --git a/arch/sh/include/asm/ftrace.h b/arch/sh/include/asm/ftrace.h
new file mode 100644
index 000000000..e79fb6eba
--- /dev/null
+++ b/arch/sh/include/asm/ftrace.h
@@ -0,0 +1,47 @@
+#ifndef __ASM_SH_FTRACE_H
+#define __ASM_SH_FTRACE_H
+
+#ifdef CONFIG_FUNCTION_TRACER
+
+#define MCOUNT_INSN_SIZE	4 /* sizeof mcount call */
+#define FTRACE_SYSCALL_MAX	NR_syscalls
+
+#ifndef __ASSEMBLY__
+extern void mcount(void);
+
+#define MCOUNT_ADDR		((long)(mcount))
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+#define CALL_ADDR		((long)(ftrace_call))
+#define STUB_ADDR		((long)(ftrace_stub))
+#define GRAPH_ADDR		((long)(ftrace_graph_call))
+#define CALLER_ADDR		((long)(ftrace_caller))
+
+#define MCOUNT_INSN_OFFSET	((STUB_ADDR - CALL_ADDR) - 4)
+#define GRAPH_INSN_OFFSET	((CALLER_ADDR - GRAPH_ADDR) - 4)
+
+struct dyn_arch_ftrace {
+	/* No extra data needed on sh */
+};
+
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
+static inline unsigned long ftrace_call_adjust(unsigned long addr)
+{
+	/* 'addr' is the memory table address. */
+	return addr;
+}
+
+#endif /* __ASSEMBLY__ */
+#endif /* CONFIG_FUNCTION_TRACER */
+
+#ifndef __ASSEMBLY__
+
+/* arch/sh/kernel/return_address.c */
+extern void *return_address(unsigned int);
+
+#define ftrace_return_address(n) return_address(n)
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* __ASM_SH_FTRACE_H */
diff --git a/arch/sh/include/asm/futex-irq.h b/arch/sh/include/asm/futex-irq.h
new file mode 100644
index 000000000..63d33129e
--- /dev/null
+++ b/arch/sh/include/asm/futex-irq.h
@@ -0,0 +1,110 @@
+#ifndef __ASM_SH_FUTEX_IRQ_H
+#define __ASM_SH_FUTEX_IRQ_H
+
+
+static inline int atomic_futex_op_xchg_set(int oparg, u32 __user *uaddr,
+					   int *oldval)
+{
+	unsigned long flags;
+	int ret;
+
+	local_irq_save(flags);
+
+	ret = get_user(*oldval, uaddr);
+	if (!ret)
+		ret = put_user(oparg, uaddr);
+
+	local_irq_restore(flags);
+
+	return ret;
+}
+
+static inline int atomic_futex_op_xchg_add(int oparg, u32 __user *uaddr,
+					   int *oldval)
+{
+	unsigned long flags;
+	int ret;
+
+	local_irq_save(flags);
+
+	ret = get_user(*oldval, uaddr);
+	if (!ret)
+		ret = put_user(*oldval + oparg, uaddr);
+
+	local_irq_restore(flags);
+
+	return ret;
+}
+
+static inline int atomic_futex_op_xchg_or(int oparg, u32 __user *uaddr,
+					  int *oldval)
+{
+	unsigned long flags;
+	int ret;
+
+	local_irq_save(flags);
+
+	ret = get_user(*oldval, uaddr);
+	if (!ret)
+		ret = put_user(*oldval | oparg, uaddr);
+
+	local_irq_restore(flags);
+
+	return ret;
+}
+
+static inline int atomic_futex_op_xchg_and(int oparg, u32 __user *uaddr,
+					   int *oldval)
+{
+	unsigned long flags;
+	int ret;
+
+	local_irq_save(flags);
+
+	ret = get_user(*oldval, uaddr);
+	if (!ret)
+		ret = put_user(*oldval & oparg, uaddr);
+
+	local_irq_restore(flags);
+
+	return ret;
+}
+
+static inline int atomic_futex_op_xchg_xor(int oparg, u32 __user *uaddr,
+					   int *oldval)
+{
+	unsigned long flags;
+	int ret;
+
+	local_irq_save(flags);
+
+	ret = get_user(*oldval, uaddr);
+	if (!ret)
+		ret = put_user(*oldval ^ oparg, uaddr);
+
+	local_irq_restore(flags);
+
+	return ret;
+}
+
+static inline int atomic_futex_op_cmpxchg_inatomic(u32 *uval,
+						   u32 __user *uaddr,
+						   u32 oldval, u32 newval)
+{
+	unsigned long flags;
+	int ret;
+	u32 prev = 0;
+
+	local_irq_save(flags);
+
+	ret = get_user(prev, uaddr);
+	if (!ret && oldval == prev)
+		ret = put_user(newval, uaddr);
+
+	local_irq_restore(flags);
+
+	*uval = prev;
+	return ret;
+}
+
+#endif /* __ASM_SH_FUTEX_IRQ_H */
diff --git a/arch/sh/include/asm/futex.h b/arch/sh/include/asm/futex.h
new file mode 100644
index 000000000..7be39a646
--- /dev/null
+++ b/arch/sh/include/asm/futex.h
@@ -0,0 +1,78 @@
+#ifndef __ASM_SH_FUTEX_H
+#define __ASM_SH_FUTEX_H
+
+#ifdef __KERNEL__
+
+#include <linux/futex.h>
+#include <linux/uaccess.h>
+#include <asm/errno.h>
+
+/* XXX: UP variants, fix for SH-4A and SMP.. */
+#include <asm/futex-irq.h>
+
+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;
+
+	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
+		oparg = 1 << oparg;
+
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
+		return -EFAULT;
+
+	pagefault_disable();
+
+	switch (op) {
+	case FUTEX_OP_SET:
+		ret = atomic_futex_op_xchg_set(oparg, uaddr, &oldval);
+		break;
+	case FUTEX_OP_ADD:
+		ret = atomic_futex_op_xchg_add(oparg, uaddr, &oldval);
+		break;
+	case FUTEX_OP_OR:
+		ret = atomic_futex_op_xchg_or(oparg, uaddr, &oldval);
+		break;
+	case FUTEX_OP_ANDN:
+		ret = atomic_futex_op_xchg_and(~oparg, uaddr, &oldval);
+		break;
+	case FUTEX_OP_XOR:
+		ret = atomic_futex_op_xchg_xor(oparg, uaddr, &oldval);
+		break;
+	default:
+		ret = -ENOSYS;
+		break;
+	}
+
+	pagefault_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;
+}
+
+static inline int
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+			      u32 oldval, u32 newval)
+{
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
+		return -EFAULT;
+
+	return atomic_futex_op_cmpxchg_inatomic(uval, uaddr, oldval, newval);
+}
+
+#endif /* __KERNEL__ */
+#endif /* __ASM_SH_FUTEX_H */
diff --git a/arch/sh/include/asm/gpio.h b/arch/sh/include/asm/gpio.h
new file mode 100644
index 000000000..7dfe15e2e
--- /dev/null
+++ b/arch/sh/include/asm/gpio.h
@@ -0,0 +1,54 @@
+/*
+ *  include/asm-sh/gpio.h
+ *
+ * Generic GPIO API and pinmux table support for SuperH.
+ *
+ * Copyright (c) 2008 Magnus Damm
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+#ifndef __ASM_SH_GPIO_H
+#define __ASM_SH_GPIO_H
+
+#include <linux/kernel.h>
+#include <linux/errno.h>
+
+#if defined(CONFIG_CPU_SH3)
+#include <cpu/gpio.h>
+#endif
+
+#define ARCH_NR_GPIOS 512
+#include <asm-generic/gpio.h>
+
+#ifdef CONFIG_GPIOLIB
+
+static inline int gpio_get_value(unsigned gpio)
+{
+	return __gpio_get_value(gpio);
+}
+
+static inline void gpio_set_value(unsigned gpio, int value)
+{
+	__gpio_set_value(gpio, value);
+}
+
+static inline int gpio_cansleep(unsigned gpio)
+{
+	return __gpio_cansleep(gpio);
+}
+
+static inline int gpio_to_irq(unsigned gpio)
+{
+	return __gpio_to_irq(gpio);
+}
+
+static inline int irq_to_gpio(unsigned int irq)
+{
+	return -ENOSYS;
+}
+
+#endif /* CONFIG_GPIOLIB */
+
+#endif /* __ASM_SH_GPIO_H */
diff --git a/arch/sh/include/asm/hardirq.h b/arch/sh/include/asm/hardirq.h
new file mode 100644
index 000000000..48b191313
--- /dev/null
+++ b/arch/sh/include/asm/hardirq.h
@@ -0,0 +1,16 @@
+#ifndef __ASM_SH_HARDIRQ_H
+#define __ASM_SH_HARDIRQ_H
+
+#include <linux/threads.h>
+#include <linux/irq.h>
+
+typedef struct {
+	unsigned int __softirq_pending;
+	unsigned int __nmi_count;		/* arch dependent */
+} ____cacheline_aligned irq_cpustat_t;
+
+#include <linux/irq_cpustat.h>	/* Standard mappings for irq_cpustat_t above */
+
+extern void ack_bad_irq(unsigned int irq);
+
+#endif /* __ASM_SH_HARDIRQ_H */
diff --git a/arch/sh/include/asm/hd64461.h b/arch/sh/include/asm/hd64461.h
new file mode 100644
index 000000000..977355f0a
--- /dev/null
+++ b/arch/sh/include/asm/hd64461.h
@@ -0,0 +1,251 @@
+#ifndef __ASM_SH_HD64461
+#define __ASM_SH_HD64461
+/*
+ *	Copyright (C) 2007 Kristoffer Ericson <Kristoffer.Ericson@gmail.com>
+ *	Copyright (C) 2004 Paul Mundt
+ *	Copyright (C) 2000 YAEGASHI Takeshi
+ *
+ *		Hitachi HD64461 companion chip support
+ *	(please note manual reference 0x10000000 = 0xb0000000)
+ */
+
+/* Constants for PCMCIA mappings */
+#define	HD64461_PCC_WINDOW	0x01000000
+
+/* Area 6 - Slot 0 - memory and/or IO card */
+#define HD64461_IOBASE		0xb0000000
+#define HD64461_IO_OFFSET(x)	(HD64461_IOBASE + (x))
+#define	HD64461_PCC0_BASE	HD64461_IO_OFFSET(0x8000000)
+#define	HD64461_PCC0_ATTR	(HD64461_PCC0_BASE)				/* 0xb80000000 */
+#define	HD64461_PCC0_COMM	(HD64461_PCC0_BASE+HD64461_PCC_WINDOW)		/* 0xb90000000 */
+#define	HD64461_PCC0_IO		(HD64461_PCC0_BASE+2*HD64461_PCC_WINDOW)	/* 0xba0000000 */
+
+/* Area 5 - Slot 1 - memory card only */
+#define	HD64461_PCC1_BASE	HD64461_IO_OFFSET(0x4000000)
+#define	HD64461_PCC1_ATTR	(HD64461_PCC1_BASE)				/* 0xb4000000 */
+#define	HD64461_PCC1_COMM	(HD64461_PCC1_BASE+HD64461_PCC_WINDOW)		/* 0xb5000000 */
+
+/* Standby Control Register for HD64461 */
+#define	HD64461_STBCR			HD64461_IO_OFFSET(0x00000000)
+#define	HD64461_STBCR_CKIO_STBY		0x2000
+#define	HD64461_STBCR_SAFECKE_IST	0x1000
+#define	HD64461_STBCR_SLCKE_IST		0x0800
+#define	HD64461_STBCR_SAFECKE_OST	0x0400
+#define	HD64461_STBCR_SLCKE_OST		0x0200
+#define	HD64461_STBCR_SMIAST		0x0100
+#define	HD64461_STBCR_SLCDST		0x0080
+#define	HD64461_STBCR_SPC0ST		0x0040
+#define	HD64461_STBCR_SPC1ST		0x0020
+#define	HD64461_STBCR_SAFEST		0x0010
+#define	HD64461_STBCR_STM0ST		0x0008
+#define	HD64461_STBCR_STM1ST		0x0004
+#define	HD64461_STBCR_SIRST		0x0002
+#define	HD64461_STBCR_SURTST		0x0001
+
+/* System Configuration Register */
+#define	HD64461_SYSCR		HD64461_IO_OFFSET(0x02)
+
+/* CPU Data Bus Control Register */
+#define	HD64461_SCPUCR		HD64461_IO_OFFSET(0x04)
+
+/* Base Address Register */
+#define	HD64461_LCDCBAR		HD64461_IO_OFFSET(0x1000)
+
+/* Line increment address */
+#define	HD64461_LCDCLOR		HD64461_IO_OFFSET(0x1002)
+
+/* Controls LCD controller */
+#define	HD64461_LCDCCR		HD64461_IO_OFFSET(0x1004)
+
+/* LCCDR control bits */
+#define	HD64461_LCDCCR_STBACK	0x0400	/* Standby Back */
+#define	HD64461_LCDCCR_STREQ	0x0100	/* Standby Request */
+#define	HD64461_LCDCCR_MOFF	0x0080	/* Memory Off */
+#define	HD64461_LCDCCR_REFSEL	0x0040	/* Refresh Select */
+#define	HD64461_LCDCCR_EPON	0x0020	/* End Power On */
+#define	HD64461_LCDCCR_SPON	0x0010	/* Start Power On */
+
+/* Controls LCD (1) */
+#define	HD64461_LDR1		HD64461_IO_OFFSET(0x1010)
+#define	HD64461_LDR1_DON	0x01	/* Display On */
+#define	HD64461_LDR1_DINV	0x80	/* Display Invert */
+
+/* Controls LCD (2) */
+#define	HD64461_LDR2		HD64461_IO_OFFSET(0x1012)
+#define	HD64461_LDHNCR		HD64461_IO_OFFSET(0x1014)	/* Number of horizontal characters */
+#define	HD64461_LDHNSR		HD64461_IO_OFFSET(0x1016)	/* Specify output start position + width of CL1 */
+#define	HD64461_LDVNTR		HD64461_IO_OFFSET(0x1018)	/* Specify total vertical lines */
+#define	HD64461_LDVNDR		HD64461_IO_OFFSET(0x101a)	/* specify number of display vertical lines */
+#define	HD64461_LDVSPR		HD64461_IO_OFFSET(0x101c)	/* specify vertical synchronization pos and AC nr */
+
+/* Controls LCD (3) */
+#define	HD64461_LDR3		HD64461_IO_OFFSET(0x101e)
+
+/* Palette Registers */
+#define	HD64461_CPTWAR		HD64461_IO_OFFSET(0x1030)	/* Color Palette Write Address Register */
+#define	HD64461_CPTWDR		HD64461_IO_OFFSET(0x1032)	/* Color Palette Write Data Register */
+#define	HD64461_CPTRAR		HD64461_IO_OFFSET(0x1034)	/* Color Palette Read Address Register */
+#define	HD64461_CPTRDR		HD64461_IO_OFFSET(0x1036)	/* Color Palette Read Data Register */
+
+#define	HD64461_GRDOR		HD64461_IO_OFFSET(0x1040)	/* Display Resolution Offset Register */
+#define	HD64461_GRSCR		HD64461_IO_OFFSET(0x1042)	/* Solid Color Register */
+#define	HD64461_GRCFGR		HD64461_IO_OFFSET(0x1044)	/* Accelerator Configuration Register */
+
+#define	HD64461_GRCFGR_ACCSTATUS	0x10	/* Accelerator Status */
+#define	HD64461_GRCFGR_ACCRESET		0x08	/* Accelerator Reset */
+#define	HD64461_GRCFGR_ACCSTART_BITBLT	0x06	/* Accelerator Start BITBLT */
+#define	HD64461_GRCFGR_ACCSTART_LINE	0x04	/* Accelerator Start Line Drawing */
+#define	HD64461_GRCFGR_COLORDEPTH16	0x01	/* Sets Colordepth 16 for Accelerator */
+#define	HD64461_GRCFGR_COLORDEPTH8	0x01	/* Sets Colordepth 8 for Accelerator */
+
+/* Line Drawing Registers */
+#define	HD64461_LNSARH		HD64461_IO_OFFSET(0x1046)	/* Line Start Address Register (H) */
+#define	HD64461_LNSARL		HD64461_IO_OFFSET(0x1048)	/* Line Start Address Register (L) */
+#define	HD64461_LNAXLR		HD64461_IO_OFFSET(0x104a)	/* Axis Pixel Length Register */
+#define	HD64461_LNDGR		HD64461_IO_OFFSET(0x104c)	/* Diagonal Register */
+#define	HD64461_LNAXR		HD64461_IO_OFFSET(0x104e)	/* Axial Register */
+#define	HD64461_LNERTR		HD64461_IO_OFFSET(0x1050)	/* Start Error Term Register */
+#define	HD64461_LNMDR		HD64461_IO_OFFSET(0x1052)	/* Line Mode Register */
+
+/* BitBLT Registers */
+#define	HD64461_BBTSSARH	HD64461_IO_OFFSET(0x1054)	/* Source Start Address Register (H) */
+#define	HD64461_BBTSSARL	HD64461_IO_OFFSET(0x1056)	/* Source Start Address Register (L) */
+#define	HD64461_BBTDSARH	HD64461_IO_OFFSET(0x1058)	/* Destination Start Address Register (H) */
+#define	HD64461_BBTDSARL	HD64461_IO_OFFSET(0x105a)	/* Destination Start Address Register (L) */
+#define	HD64461_BBTDWR		HD64461_IO_OFFSET(0x105c)	/* Destination Block Width Register */
+#define	HD64461_BBTDHR		HD64461_IO_OFFSET(0x105e)	/* Destination Block Height Register */
+#define	HD64461_BBTPARH		HD64461_IO_OFFSET(0x1060)	/* Pattern Start Address Register (H) */
+#define	HD64461_BBTPARL		HD64461_IO_OFFSET(0x1062)	/* Pattern Start Address Register (L) */
+#define	HD64461_BBTMARH		HD64461_IO_OFFSET(0x1064)	/* Mask Start Address Register (H) */
+#define	HD64461_BBTMARL		HD64461_IO_OFFSET(0x1066)	/* Mask Start Address Register (L) */
+#define	HD64461_BBTROPR		HD64461_IO_OFFSET(0x1068)	/* ROP Register */
+#define	HD64461_BBTMDR		HD64461_IO_OFFSET(0x106a)	/* BitBLT Mode Register */
+
+/* PC Card Controller Registers */
+/* Maps to Physical Area 6 */
+#define	HD64461_PCC0ISR		HD64461_IO_OFFSET(0x2000)	/* socket 0 interface status */
+#define	HD64461_PCC0GCR		HD64461_IO_OFFSET(0x2002)	/* socket 0 general control */
+#define	HD64461_PCC0CSCR	HD64461_IO_OFFSET(0x2004)	/* socket 0 card status change */
+#define	HD64461_PCC0CSCIER	HD64461_IO_OFFSET(0x2006)	/* socket 0 card status change interrupt enable */
+#define	HD64461_PCC0SCR		HD64461_IO_OFFSET(0x2008)	/* socket 0 software control */
+/* Maps to Physical Area 5 */
+#define	HD64461_PCC1ISR		HD64461_IO_OFFSET(0x2010)	/* socket 1 interface status */
+#define	HD64461_PCC1GCR		HD64461_IO_OFFSET(0x2012)	/* socket 1 general control */
+#define	HD64461_PCC1CSCR	HD64461_IO_OFFSET(0x2014)	/* socket 1 card status change */
+#define	HD64461_PCC1CSCIER	HD64461_IO_OFFSET(0x2016)	/* socket 1 card status change interrupt enable */
+#define	HD64461_PCC1SCR		HD64461_IO_OFFSET(0x2018)	/* socket 1 software control */
+
+/* PCC Interface Status Register */
+#define	HD64461_PCCISR_READY		0x80	/* card ready */
+#define	HD64461_PCCISR_MWP		0x40	/* card write-protected */
+#define	HD64461_PCCISR_VS2		0x20	/* voltage select pin 2 */
+#define	HD64461_PCCISR_VS1		0x10	/* voltage select pin 1 */
+#define	HD64461_PCCISR_CD2		0x08	/* card detect 2 */
+#define	HD64461_PCCISR_CD1		0x04	/* card detect 1 */
+#define	HD64461_PCCISR_BVD2		0x02	/* battery 1 */
+#define	HD64461_PCCISR_BVD1		0x01	/* battery 1 */
+
+#define	HD64461_PCCISR_PCD_MASK		0x0c	/* card detect */
+#define	HD64461_PCCISR_BVD_MASK		0x03	/* battery voltage */
+#define	HD64461_PCCISR_BVD_BATGOOD	0x03	/* battery good */
+#define	HD64461_PCCISR_BVD_BATWARN	0x01	/* battery low warning */
+#define	HD64461_PCCISR_BVD_BATDEAD1	0x02	/* battery dead */
+#define	HD64461_PCCISR_BVD_BATDEAD2	0x00	/* battery dead */
+
+/* PCC General Control Register */
+#define	HD64461_PCCGCR_DRVE		0x80	/* output drive */
+#define	HD64461_PCCGCR_PCCR		0x40	/* PC card reset */
+#define	HD64461_PCCGCR_PCCT		0x20	/* PC card type, 1=IO&mem, 0=mem */
+#define	HD64461_PCCGCR_VCC0		0x10	/* voltage control pin VCC0SEL0 */
+#define	HD64461_PCCGCR_PMMOD		0x08	/* memory mode */
+#define	HD64461_PCCGCR_PA25		0x04	/* pin A25 */
+#define	HD64461_PCCGCR_PA24		0x02	/* pin A24 */
+#define	HD64461_PCCGCR_REG		0x01	/* pin PCC0REG# */
+
+/* PCC Card Status Change Register */
+#define	HD64461_PCCCSCR_SCDI		0x80	/* sw card detect intr */
+#define	HD64461_PCCCSCR_SRV1		0x40	/* reserved */
+#define	HD64461_PCCCSCR_IREQ		0x20	/* IREQ intr req */
+#define	HD64461_PCCCSCR_SC		0x10	/* STSCHG (status change) pin */
+#define	HD64461_PCCCSCR_CDC		0x08	/* CD (card detect) change */
+#define	HD64461_PCCCSCR_RC		0x04	/* READY change */
+#define	HD64461_PCCCSCR_BW		0x02	/* battery warning change */
+#define	HD64461_PCCCSCR_BD		0x01	/* battery dead change */
+
+/* PCC Card Status Change Interrupt Enable Register */
+#define	HD64461_PCCCSCIER_CRE		0x80	/* change reset enable */
+#define	HD64461_PCCCSCIER_IREQE_MASK	0x60	/* IREQ enable */
+#define	HD64461_PCCCSCIER_IREQE_DISABLED 0x00	/* IREQ disabled */
+#define	HD64461_PCCCSCIER_IREQE_LEVEL	0x20	/* IREQ level-triggered */
+#define	HD64461_PCCCSCIER_IREQE_FALLING	0x40	/* IREQ falling-edge-trig */
+#define	HD64461_PCCCSCIER_IREQE_RISING	0x60	/* IREQ rising-edge-trig */
+
+#define	HD64461_PCCCSCIER_SCE		0x10	/* status change enable */
+#define	HD64461_PCCCSCIER_CDE		0x08	/* card detect change enable */
+#define	HD64461_PCCCSCIER_RE		0x04	/* ready change enable */
+#define	HD64461_PCCCSCIER_BWE		0x02	/* battery warn change enable */
+#define	HD64461_PCCCSCIER_BDE		0x01	/* battery dead change enable*/
+
+/* PCC Software Control Register */
+#define	HD64461_PCCSCR_VCC1		0x02	/* voltage control pin 1 */
+#define	HD64461_PCCSCR_SWP		0x01	/* write protect */
+
+/* PCC0 Output Pins Control Register */
+#define	HD64461_P0OCR		HD64461_IO_OFFSET(0x202a)
+
+/* PCC1 Output Pins Control Register */
+#define	HD64461_P1OCR		HD64461_IO_OFFSET(0x202c)
+
+/* PC Card General Control Register */
+#define	HD64461_PGCR		HD64461_IO_OFFSET(0x202e)
+
+/* Port Control Registers */
+#define	HD64461_GPACR		HD64461_IO_OFFSET(0x4000)	/* Port A - Handles IRDA/TIMER */
+#define	HD64461_GPBCR		HD64461_IO_OFFSET(0x4002)	/* Port B - Handles UART */
+#define	HD64461_GPCCR		HD64461_IO_OFFSET(0x4004)	/* Port C - Handles PCMCIA 1 */
+#define	HD64461_GPDCR		HD64461_IO_OFFSET(0x4006)	/* Port D - Handles PCMCIA 1 */
+
+/* Port Control Data Registers */
+#define	HD64461_GPADR		HD64461_IO_OFFSET(0x4010)	/* A */
+#define	HD64461_GPBDR		HD64461_IO_OFFSET(0x4012)	/* B */
+#define	HD64461_GPCDR		HD64461_IO_OFFSET(0x4014)	/* C */
+#define	HD64461_GPDDR		HD64461_IO_OFFSET(0x4016)	/* D */
+
+/* Interrupt Control Registers */
+#define	HD64461_GPAICR		HD64461_IO_OFFSET(0x4020)	/* A */
+#define	HD64461_GPBICR		HD64461_IO_OFFSET(0x4022)	/* B */
+#define	HD64461_GPCICR		HD64461_IO_OFFSET(0x4024)	/* C */
+#define	HD64461_GPDICR		HD64461_IO_OFFSET(0x4026)	/* D */
+
+/* Interrupt Status Registers */
+#define	HD64461_GPAISR		HD64461_IO_OFFSET(0x4040)	/* A */
+#define	HD64461_GPBISR		HD64461_IO_OFFSET(0x4042)	/* B */
+#define	HD64461_GPCISR		HD64461_IO_OFFSET(0x4044)	/* C */
+#define	HD64461_GPDISR		HD64461_IO_OFFSET(0x4046)	/* D */
+
+/* Interrupt Request Register & Interrupt Mask Register */
+#define	HD64461_NIRR		HD64461_IO_OFFSET(0x5000)
+#define	HD64461_NIMR		HD64461_IO_OFFSET(0x5002)
+
+#define	HD64461_IRQBASE		OFFCHIP_IRQ_BASE
+#define	OFFCHIP_IRQ_BASE	64
+#define	HD64461_IRQ_NUM		16
+
+#define	HD64461_IRQ_UART	(HD64461_IRQBASE+5)
+#define	HD64461_IRQ_IRDA	(HD64461_IRQBASE+6)
+#define	HD64461_IRQ_TMU1	(HD64461_IRQBASE+9)
+#define	HD64461_IRQ_TMU0	(HD64461_IRQBASE+10)
+#define	HD64461_IRQ_GPIO	(HD64461_IRQBASE+11)
+#define	HD64461_IRQ_AFE		(HD64461_IRQBASE+12)
+#define	HD64461_IRQ_PCC1	(HD64461_IRQBASE+13)
+#define	HD64461_IRQ_PCC0	(HD64461_IRQBASE+14)
+
+#define __IO_PREFIX	hd64461
+#include <asm/io_generic.h>
+
+/* arch/sh/cchips/hd6446x/hd64461/setup.c */
+void hd64461_register_irq_demux(int irq,
+				int (*demux) (int irq, void *dev), void *dev);
+void hd64461_unregister_irq_demux(int irq);
+
+#endif
diff --git a/arch/sh/include/asm/heartbeat.h b/arch/sh/include/asm/heartbeat.h
new file mode 100644
index 000000000..caaafe5a3
--- /dev/null
+++ b/arch/sh/include/asm/heartbeat.h
@@ -0,0 +1,18 @@
+#ifndef __ASM_SH_HEARTBEAT_H
+#define __ASM_SH_HEARTBEAT_H
+
+#include <linux/timer.h>
+
+#define HEARTBEAT_INVERTED	(1 << 0)
+
+struct heartbeat_data {
+	void __iomem *base;
+	unsigned char *bit_pos;
+	unsigned int nr_bits;
+	struct timer_list timer;
+	unsigned int regsize;
+	unsigned int mask;
+	unsigned long flags;
+};
+
+#endif /* __ASM_SH_HEARTBEAT_H */
diff --git a/arch/sh/include/asm/hugetlb.h b/arch/sh/include/asm/hugetlb.h
new file mode 100644
index 000000000..699255d6d
--- /dev/null
+++ b/arch/sh/include/asm/hugetlb.h
@@ -0,0 +1,99 @@
+#ifndef _ASM_SH_HUGETLB_H
+#define _ASM_SH_HUGETLB_H
+
+#include <asm/cacheflush.h>
+#include <asm/page.h>
+#include <asm-generic/hugetlb.h>
+
+
+static inline int is_hugepage_only_range(struct mm_struct *mm,
+					 unsigned long addr,
+					 unsigned long len) {
+	return 0;
+}
+
+/*
+ * If the arch doesn't supply something else, assume that hugepage
+ * size aligned regions are ok without further preparation.
+ */
+static inline int prepare_hugepage_range(struct file *file,
+			unsigned long addr, unsigned long len)
+{
+	if (len & ~HPAGE_MASK)
+		return -EINVAL;
+	if (addr & ~HPAGE_MASK)
+		return -EINVAL;
+	return 0;
+}
+
+static inline void hugetlb_prefault_arch_hook(struct mm_struct *mm) {
+}
+
+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 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 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 void huge_ptep_clear_flush(struct vm_area_struct *vma,
+					 unsigned long addr, pte_t *ptep)
+{
+}
+
+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 void huge_ptep_set_wrprotect(struct mm_struct *mm,
+					   unsigned long addr, pte_t *ptep)
+{
+	ptep_set_wrprotect(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);
+}
+
+static inline pte_t huge_ptep_get(pte_t *ptep)
+{
+	return *ptep;
+}
+
+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_SH_HUGETLB_H */
diff --git a/arch/sh/include/asm/hw_breakpoint.h b/arch/sh/include/asm/hw_breakpoint.h
new file mode 100644
index 000000000..ec9ad593c
--- /dev/null
+++ b/arch/sh/include/asm/hw_breakpoint.h
@@ -0,0 +1,70 @@
+#ifndef __ASM_SH_HW_BREAKPOINT_H
+#define __ASM_SH_HW_BREAKPOINT_H
+
+#include <uapi/asm/hw_breakpoint.h>
+
+#define __ARCH_HW_BREAKPOINT_H
+
+#include <linux/kdebug.h>
+#include <linux/types.h>
+
+struct arch_hw_breakpoint {
+	char		*name; /* Contains name of the symbol to set bkpt */
+	unsigned long	address;
+	u16		len;
+	u16		type;
+};
+
+enum {
+	SH_BREAKPOINT_READ	= (1 << 1),
+	SH_BREAKPOINT_WRITE	= (1 << 2),
+	SH_BREAKPOINT_RW	= SH_BREAKPOINT_READ | SH_BREAKPOINT_WRITE,
+
+	SH_BREAKPOINT_LEN_1	= (1 << 12),
+	SH_BREAKPOINT_LEN_2	= (1 << 13),
+	SH_BREAKPOINT_LEN_4	= SH_BREAKPOINT_LEN_1 | SH_BREAKPOINT_LEN_2,
+	SH_BREAKPOINT_LEN_8	= (1 << 14),
+};
+
+struct sh_ubc {
+	const char	*name;
+	unsigned int	num_events;
+	unsigned int	trap_nr;
+	void		(*enable)(struct arch_hw_breakpoint *, int);
+	void		(*disable)(struct arch_hw_breakpoint *, int);
+	void		(*enable_all)(unsigned long);
+	void		(*disable_all)(void);
+	unsigned long	(*active_mask)(void);
+	unsigned long	(*triggered_mask)(void);
+	void		(*clear_triggered_mask)(unsigned long);
+	struct clk	*clk;	/* optional interface clock / MSTP bit */
+};
+
+struct perf_event;
+struct task_struct;
+struct pmu;
+
+/* Maximum number of UBC channels */
+#define HBP_NUM		2
+
+static inline int hw_breakpoint_slots(int type)
+{
+	return HBP_NUM;
+}
+
+/* arch/sh/kernel/hw_breakpoint.c */
+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);
+
+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);
+
+extern void arch_fill_perf_breakpoint(struct perf_event *bp);
+extern int register_sh_ubc(struct sh_ubc *);
+
+extern struct pmu perf_ops_bp;
+
+#endif /* __ASM_SH_HW_BREAKPOINT_H */
diff --git a/arch/sh/include/asm/hw_irq.h b/arch/sh/include/asm/hw_irq.h
new file mode 100644
index 000000000..693d44184
--- /dev/null
+++ b/arch/sh/include/asm/hw_irq.h
@@ -0,0 +1,35 @@
+#ifndef __ASM_SH_HW_IRQ_H
+#define __ASM_SH_HW_IRQ_H
+
+#include <linux/init.h>
+#include <linux/sh_intc.h>
+#include <linux/atomic.h>
+
+extern atomic_t irq_err_count;
+
+struct ipr_data {
+	unsigned char irq;
+	unsigned char ipr_idx;		/* Index for the IPR registered */
+	unsigned char shift;		/* Number of bits to shift the data */
+	unsigned char priority;		/* The priority */
+};
+
+struct ipr_desc {
+	unsigned long *ipr_offsets;
+	unsigned int nr_offsets;
+	struct ipr_data *ipr_data;
+	unsigned int nr_irqs;
+	struct irq_chip chip;
+};
+
+void register_ipr_controller(struct ipr_desc *);
+
+void __init plat_irq_setup(void);
+void __init plat_irq_setup_sh3(void);
+void __init plat_irq_setup_pins(int mode);
+
+enum { IRQ_MODE_IRQ, IRQ_MODE_IRQ7654, IRQ_MODE_IRQ3210,
+       IRQ_MODE_IRL7654_MASK, IRQ_MODE_IRL3210_MASK,
+       IRQ_MODE_IRL7654, IRQ_MODE_IRL3210 };
+
+#endif /* __ASM_SH_HW_IRQ_H */
diff --git a/arch/sh/include/asm/i2c-sh7760.h b/arch/sh/include/asm/i2c-sh7760.h
new file mode 100644
index 000000000..69fee1239
--- /dev/null
+++ b/arch/sh/include/asm/i2c-sh7760.h
@@ -0,0 +1,20 @@
+/*
+ * MMIO/IRQ and platform data for SH7760 I2C channels
+ */
+
+#ifndef _I2C_SH7760_H_
+#define _I2C_SH7760_H_
+
+#define SH7760_I2C_DEVNAME	"sh7760-i2c"
+
+#define SH7760_I2C0_MMIO	0xFE140000
+#define SH7760_I2C0_MMIOEND	0xFE14003B
+
+#define SH7760_I2C1_MMIO	0xFE150000
+#define SH7760_I2C1_MMIOEND	0xFE15003B
+
+struct sh7760_i2c_platdata {
+	unsigned int speed_khz;
+};
+
+#endif
diff --git a/arch/sh/include/asm/io.h b/arch/sh/include/asm/io.h
new file mode 100644
index 000000000..728c4c571
--- /dev/null
+++ b/arch/sh/include/asm/io.h
@@ -0,0 +1,390 @@
+#ifndef __ASM_SH_IO_H
+#define __ASM_SH_IO_H
+
+/*
+ * Convention:
+ *    read{b,w,l,q}/write{b,w,l,q} are for PCI,
+ *    while in{b,w,l}/out{b,w,l} are for ISA
+ *
+ * In addition we have 'pausing' versions: in{b,w,l}_p/out{b,w,l}_p
+ * and 'string' versions: ins{b,w,l}/outs{b,w,l}
+ *
+ * While read{b,w,l,q} and write{b,w,l,q} contain memory barriers
+ * automatically, there are also __raw versions, which do not.
+ */
+#include <linux/errno.h>
+#include <asm/cache.h>
+#include <asm/addrspace.h>
+#include <asm/machvec.h>
+#include <asm/pgtable.h>
+#include <asm-generic/iomap.h>
+
+#ifdef __KERNEL__
+#define __IO_PREFIX     generic
+#include <asm/io_generic.h>
+#include <asm/io_trapped.h>
+#include <mach/mangle-port.h>
+
+#define __raw_writeb(v,a)	(__chk_io_ptr(a), *(volatile u8  __force *)(a) = (v))
+#define __raw_writew(v,a)	(__chk_io_ptr(a), *(volatile u16 __force *)(a) = (v))
+#define __raw_writel(v,a)	(__chk_io_ptr(a), *(volatile u32 __force *)(a) = (v))
+#define __raw_writeq(v,a)	(__chk_io_ptr(a), *(volatile u64 __force *)(a) = (v))
+
+#define __raw_readb(a)		(__chk_io_ptr(a), *(volatile u8  __force *)(a))
+#define __raw_readw(a)		(__chk_io_ptr(a), *(volatile u16 __force *)(a))
+#define __raw_readl(a)		(__chk_io_ptr(a), *(volatile u32 __force *)(a))
+#define __raw_readq(a)		(__chk_io_ptr(a), *(volatile u64 __force *)(a))
+
+#define readb_relaxed(c)	({ u8  __v = ioswabb(__raw_readb(c)); __v; })
+#define readw_relaxed(c)	({ u16 __v = ioswabw(__raw_readw(c)); __v; })
+#define readl_relaxed(c)	({ u32 __v = ioswabl(__raw_readl(c)); __v; })
+#define readq_relaxed(c)	({ u64 __v = ioswabq(__raw_readq(c)); __v; })
+
+#define writeb_relaxed(v,c)	((void)__raw_writeb((__force  u8)ioswabb(v),c))
+#define writew_relaxed(v,c)	((void)__raw_writew((__force u16)ioswabw(v),c))
+#define writel_relaxed(v,c)	((void)__raw_writel((__force u32)ioswabl(v),c))
+#define writeq_relaxed(v,c)	((void)__raw_writeq((__force u64)ioswabq(v),c))
+
+#define readb(a)		({ u8  r_ = readb_relaxed(a); rmb(); r_; })
+#define readw(a)		({ u16 r_ = readw_relaxed(a); rmb(); r_; })
+#define readl(a)		({ u32 r_ = readl_relaxed(a); rmb(); r_; })
+#define readq(a)		({ u64 r_ = readq_relaxed(a); rmb(); r_; })
+
+#define writeb(v,a)		({ wmb(); writeb_relaxed((v),(a)); })
+#define writew(v,a)		({ wmb(); writew_relaxed((v),(a)); })
+#define writel(v,a)		({ wmb(); writel_relaxed((v),(a)); })
+#define writeq(v,a)		({ wmb(); writeq_relaxed((v),(a)); })
+
+#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 __BUILD_UNCACHED_IO(bwlq, type)					\
+static inline type read##bwlq##_uncached(unsigned long addr)		\
+{									\
+	type ret;							\
+	jump_to_uncached();						\
+	ret = __raw_read##bwlq(addr);					\
+	back_to_cached();						\
+	return ret;							\
+}									\
+									\
+static inline void write##bwlq##_uncached(type v, unsigned long addr)	\
+{									\
+	jump_to_uncached();						\
+	__raw_write##bwlq(v, addr);					\
+	back_to_cached();						\
+}
+
+__BUILD_UNCACHED_IO(b, u8)
+__BUILD_UNCACHED_IO(w, u16)
+__BUILD_UNCACHED_IO(l, u32)
+__BUILD_UNCACHED_IO(q, u64)
+
+#define __BUILD_MEMORY_STRING(pfx, bwlq, type)				\
+									\
+static inline void							\
+pfx##writes##bwlq(volatile void __iomem *mem, const void *addr,		\
+		  unsigned int count)					\
+{									\
+	const volatile type *__addr = addr;				\
+									\
+	while (count--) {						\
+		__raw_write##bwlq(*__addr, mem);			\
+		__addr++;						\
+	}								\
+}									\
+									\
+static inline void pfx##reads##bwlq(volatile void __iomem *mem,		\
+				    void *addr, unsigned int count)	\
+{									\
+	volatile type *__addr = addr;					\
+									\
+	while (count--) {						\
+		*__addr = __raw_read##bwlq(mem);			\
+		__addr++;						\
+	}								\
+}
+
+__BUILD_MEMORY_STRING(__raw_, b, u8)
+__BUILD_MEMORY_STRING(__raw_, w, u16)
+
+#ifdef CONFIG_SUPERH32
+void __raw_writesl(void __iomem *addr, const void *data, int longlen);
+void __raw_readsl(const void __iomem *addr, void *data, int longlen);
+#else
+__BUILD_MEMORY_STRING(__raw_, l, u32)
+#endif
+
+__BUILD_MEMORY_STRING(__raw_, q, u64)
+
+#ifdef CONFIG_HAS_IOPORT_MAP
+
+/*
+ * Slowdown I/O port space accesses for antique hardware.
+ */
+#undef CONF_SLOWDOWN_IO
+
+/*
+ * On SuperH I/O ports are memory mapped, so we access them using normal
+ * load/store instructions. sh_io_port_base is the virtual address to
+ * which all ports are being mapped.
+ */
+extern unsigned long sh_io_port_base;
+
+static inline void __set_io_port_base(unsigned long pbase)
+{
+	*(unsigned long *)&sh_io_port_base = pbase;
+	barrier();
+}
+
+#ifdef CONFIG_GENERIC_IOMAP
+#define __ioport_map ioport_map
+#else
+extern void __iomem *__ioport_map(unsigned long addr, unsigned int size);
+#endif
+
+#ifdef CONF_SLOWDOWN_IO
+#define SLOW_DOWN_IO __raw_readw(sh_io_port_base)
+#else
+#define SLOW_DOWN_IO
+#endif
+
+#define __BUILD_IOPORT_SINGLE(pfx, bwlq, type, p, slow)			\
+									\
+static inline void pfx##out##bwlq##p(type val, unsigned long port)	\
+{									\
+	volatile type *__addr;						\
+									\
+	__addr = __ioport_map(port, sizeof(type));			\
+	*__addr = val;							\
+	slow;								\
+}									\
+									\
+static inline type pfx##in##bwlq##p(unsigned long port)			\
+{									\
+	volatile type *__addr;						\
+	type __val;							\
+									\
+	__addr = __ioport_map(port, sizeof(type));			\
+	__val = *__addr;						\
+	slow;								\
+									\
+	return __val;							\
+}
+
+#define __BUILD_IOPORT_PFX(bus, bwlq, type)				\
+	__BUILD_IOPORT_SINGLE(bus, bwlq, type, ,)			\
+	__BUILD_IOPORT_SINGLE(bus, bwlq, type, _p, SLOW_DOWN_IO)
+
+#define BUILDIO_IOPORT(bwlq, type)					\
+	__BUILD_IOPORT_PFX(, bwlq, type)
+
+BUILDIO_IOPORT(b, u8)
+BUILDIO_IOPORT(w, u16)
+BUILDIO_IOPORT(l, u32)
+BUILDIO_IOPORT(q, u64)
+
+#define __BUILD_IOPORT_STRING(bwlq, type)				\
+									\
+static inline void outs##bwlq(unsigned long port, const void *addr,	\
+			      unsigned int count)			\
+{									\
+	const volatile type *__addr = addr;				\
+									\
+	while (count--) {						\
+		out##bwlq(*__addr, port);				\
+		__addr++;						\
+	}								\
+}									\
+									\
+static inline void ins##bwlq(unsigned long port, void *addr,		\
+			     unsigned int count)			\
+{									\
+	volatile type *__addr = addr;					\
+									\
+	while (count--) {						\
+		*__addr = in##bwlq(port);				\
+		__addr++;						\
+	}								\
+}
+
+__BUILD_IOPORT_STRING(b, u8)
+__BUILD_IOPORT_STRING(w, u16)
+__BUILD_IOPORT_STRING(l, u32)
+__BUILD_IOPORT_STRING(q, u64)
+
+#else /* !CONFIG_HAS_IOPORT_MAP */
+
+#include <asm/io_noioport.h>
+
+#endif
+
+
+#define IO_SPACE_LIMIT 0xffffffff
+
+/* synco on SH-4A, otherwise a nop */
+#define mmiowb()		wmb()
+
+/* We really want to try and get these to memcpy etc */
+void memcpy_fromio(void *, const volatile void __iomem *, unsigned long);
+void memcpy_toio(volatile void __iomem *, const void *, unsigned long);
+void memset_io(volatile void __iomem *, int, unsigned long);
+
+/* Quad-word real-mode I/O, don't ask.. */
+unsigned long long peek_real_address_q(unsigned long long addr);
+unsigned long long poke_real_address_q(unsigned long long addr,
+				       unsigned long long val);
+
+#if !defined(CONFIG_MMU)
+#define virt_to_phys(address)	((unsigned long)(address))
+#define phys_to_virt(address)	((void *)(address))
+#else
+#define virt_to_phys(address)	(__pa(address))
+#define phys_to_virt(address)	(__va(address))
+#endif
+
+/*
+ * On 32-bit SH, we traditionally have the whole physical address space
+ * mapped at all times (as MIPS does), so "ioremap()" and "iounmap()" do
+ * not need to do anything but place the address in the proper segment.
+ * This is true for P1 and P2 addresses, as well as some P3 ones.
+ * However, most of the P3 addresses and newer cores using extended
+ * addressing need to map through page tables, so the ioremap()
+ * implementation becomes a bit more complicated.
+ *
+ * See arch/sh/mm/ioremap.c for additional notes on this.
+ *
+ * We cheat a bit and always return uncachable areas until we've fixed
+ * the drivers to handle caching properly.
+ *
+ * On the SH-5 the concept of segmentation in the 1:1 PXSEG sense simply
+ * doesn't exist, so everything must go through page tables.
+ */
+#ifdef CONFIG_MMU
+void __iomem *__ioremap_caller(phys_addr_t offset, unsigned long size,
+			       pgprot_t prot, void *caller);
+void __iounmap(void __iomem *addr);
+
+static inline void __iomem *
+__ioremap(phys_addr_t offset, unsigned long size, pgprot_t prot)
+{
+	return __ioremap_caller(offset, size, prot, __builtin_return_address(0));
+}
+
+static inline void __iomem *
+__ioremap_29bit(phys_addr_t offset, unsigned long size, pgprot_t prot)
+{
+#ifdef CONFIG_29BIT
+	phys_addr_t last_addr = offset + size - 1;
+
+	/*
+	 * For P1 and P2 space this is trivial, as everything is already
+	 * mapped. Uncached access for P1 addresses are done through P2.
+	 * In the P3 case or for addresses outside of the 29-bit space,
+	 * mapping must be done by the PMB or by using page tables.
+	 */
+	if (likely(PXSEG(offset) < P3SEG && PXSEG(last_addr) < P3SEG)) {
+		u64 flags = pgprot_val(prot);
+
+		/*
+		 * Anything using the legacy PTEA space attributes needs
+		 * to be kicked down to page table mappings.
+		 */
+		if (unlikely(flags & _PAGE_PCC_MASK))
+			return NULL;
+		if (unlikely(flags & _PAGE_CACHABLE))
+			return (void __iomem *)P1SEGADDR(offset);
+
+		return (void __iomem *)P2SEGADDR(offset);
+	}
+
+	/* P4 above the store queues are always mapped. */
+	if (unlikely(offset >= P3_ADDR_MAX))
+		return (void __iomem *)P4SEGADDR(offset);
+#endif
+
+	return NULL;
+}
+
+static inline void __iomem *
+__ioremap_mode(phys_addr_t offset, unsigned long size, pgprot_t prot)
+{
+	void __iomem *ret;
+
+	ret = __ioremap_trapped(offset, size);
+	if (ret)
+		return ret;
+
+	ret = __ioremap_29bit(offset, size, prot);
+	if (ret)
+		return ret;
+
+	return __ioremap(offset, size, prot);
+}
+#else
+#define __ioremap(offset, size, prot)		((void __iomem *)(offset))
+#define __ioremap_mode(offset, size, prot)	((void __iomem *)(offset))
+#define __iounmap(addr)				do { } while (0)
+#endif /* CONFIG_MMU */
+
+static inline void __iomem *ioremap(phys_addr_t offset, unsigned long size)
+{
+	return __ioremap_mode(offset, size, PAGE_KERNEL_NOCACHE);
+}
+
+static inline void __iomem *
+ioremap_cache(phys_addr_t offset, unsigned long size)
+{
+	return __ioremap_mode(offset, size, PAGE_KERNEL);
+}
+
+#ifdef CONFIG_HAVE_IOREMAP_PROT
+static inline void __iomem *
+ioremap_prot(phys_addr_t offset, unsigned long size, unsigned long flags)
+{
+	return __ioremap_mode(offset, size, __pgprot(flags));
+}
+#endif
+
+#ifdef CONFIG_IOREMAP_FIXED
+extern void __iomem *ioremap_fixed(phys_addr_t, unsigned long, pgprot_t);
+extern int iounmap_fixed(void __iomem *);
+extern void ioremap_fixed_init(void);
+#else
+static inline void __iomem *
+ioremap_fixed(phys_addr_t phys_addr, unsigned long size, pgprot_t prot)
+{
+	BUG();
+	return NULL;
+}
+
+static inline void ioremap_fixed_init(void) { }
+static inline int iounmap_fixed(void __iomem *addr) { return -EINVAL; }
+#endif
+
+#define ioremap_nocache	ioremap
+#define iounmap		__iounmap
+
+/*
+ * 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
+
+#define ARCH_HAS_VALID_PHYS_ADDR_RANGE
+int valid_phys_addr_range(phys_addr_t addr, size_t size);
+int valid_mmap_phys_addr_range(unsigned long pfn, size_t size);
+
+#endif /* __KERNEL__ */
+
+#endif /* __ASM_SH_IO_H */
diff --git a/arch/sh/include/asm/io_generic.h b/arch/sh/include/asm/io_generic.h
new file mode 100644
index 000000000..b5f6956f1
--- /dev/null
+++ b/arch/sh/include/asm/io_generic.h
@@ -0,0 +1,18 @@
+/*
+ * Trivial I/O routine definitions, intentionally meant to be included
+ * multiple times. Ugly I/O routine concatenation helpers taken from
+ * alpha. Must be included _before_ io.h to avoid preprocessor-induced
+ * routine mismatch.
+ */
+#define IO_CONCAT(a,b)	_IO_CONCAT(a,b)
+#define _IO_CONCAT(a,b)	a ## _ ## b
+
+#ifndef __IO_PREFIX
+#error "Don't include this header without a valid system prefix"
+#endif
+
+void __iomem *IO_CONCAT(__IO_PREFIX,ioport_map)(unsigned long addr, unsigned int size);
+void IO_CONCAT(__IO_PREFIX,ioport_unmap)(void __iomem *addr);
+void IO_CONCAT(__IO_PREFIX,mem_init)(void);
+
+#undef __IO_PREFIX
diff --git a/arch/sh/include/asm/io_noioport.h b/arch/sh/include/asm/io_noioport.h
new file mode 100644
index 000000000..c727e6ddf
--- /dev/null
+++ b/arch/sh/include/asm/io_noioport.h
@@ -0,0 +1,63 @@
+#ifndef __ASM_SH_IO_NOIOPORT_H
+#define __ASM_SH_IO_NOIOPORT_H
+
+static inline u8 inb(unsigned long addr)
+{
+	BUG();
+	return -1;
+}
+
+static inline u16 inw(unsigned long addr)
+{
+	BUG();
+	return -1;
+}
+
+static inline u32 inl(unsigned long addr)
+{
+	BUG();
+	return -1;
+}
+
+static inline void outb(unsigned char x, unsigned long port)
+{
+	BUG();
+}
+
+static inline void outw(unsigned short x, unsigned long port)
+{
+	BUG();
+}
+
+static inline void outl(unsigned int x, unsigned long port)
+{
+	BUG();
+}
+
+static inline void __iomem *ioport_map(unsigned long port, unsigned int size)
+{
+	BUG();
+	return NULL;
+}
+
+static inline void ioport_unmap(void __iomem *addr)
+{
+	BUG();
+}
+
+#define inb_p(addr)	inb(addr)
+#define inw_p(addr)	inw(addr)
+#define inl_p(addr)	inl(addr)
+#define outb_p(x, addr)	outb((x), (addr))
+#define outw_p(x, addr)	outw((x), (addr))
+#define outl_p(x, addr)	outl((x), (addr))
+
+#define insb(a, b, c)	BUG()
+#define insw(a, b, c)	BUG()
+#define insl(a, b, c)	BUG()
+
+#define outsb(a, b, c)	BUG()
+#define outsw(a, b, c)	BUG()
+#define outsl(a, b, c)	BUG()
+
+#endif /* __ASM_SH_IO_NOIOPORT_H */
diff --git a/arch/sh/include/asm/io_trapped.h b/arch/sh/include/asm/io_trapped.h
new file mode 100644
index 000000000..4ab94ef51
--- /dev/null
+++ b/arch/sh/include/asm/io_trapped.h
@@ -0,0 +1,58 @@
+#ifndef __ASM_SH_IO_TRAPPED_H
+#define __ASM_SH_IO_TRAPPED_H
+
+#include <linux/list.h>
+#include <linux/ioport.h>
+#include <asm/page.h>
+
+#define IO_TRAPPED_MAGIC 0xfeedbeef
+
+struct trapped_io {
+	unsigned int magic;
+	struct resource *resource;
+	unsigned int num_resources;
+	unsigned int minimum_bus_width;
+	struct list_head list;
+	void __iomem *virt_base;
+} __aligned(PAGE_SIZE);
+
+#ifdef CONFIG_IO_TRAPPED
+int register_trapped_io(struct trapped_io *tiop);
+int handle_trapped_io(struct pt_regs *regs, unsigned long address);
+
+void __iomem *match_trapped_io_handler(struct list_head *list,
+				       unsigned long offset,
+				       unsigned long size);
+
+#ifdef CONFIG_HAS_IOMEM
+extern struct list_head trapped_mem;
+
+static inline void __iomem *
+__ioremap_trapped(unsigned long offset, unsigned long size)
+{
+	return match_trapped_io_handler(&trapped_mem, offset, size);
+}
+#else
+#define __ioremap_trapped(offset, size) NULL
+#endif
+
+#ifdef CONFIG_HAS_IOPORT_MAP
+extern struct list_head trapped_io;
+
+static inline void __iomem *
+__ioport_map_trapped(unsigned long offset, unsigned long size)
+{
+	return match_trapped_io_handler(&trapped_io, offset, size);
+}
+#else
+#define __ioport_map_trapped(offset, size) NULL
+#endif
+
+#else
+#define register_trapped_io(tiop) (-1)
+#define handle_trapped_io(tiop, address) 0
+#define __ioremap_trapped(offset, size) NULL
+#define __ioport_map_trapped(offset, size) NULL
+#endif
+
+#endif /* __ASM_SH_IO_TRAPPED_H */
diff --git a/arch/sh/include/asm/irq.h b/arch/sh/include/asm/irq.h
new file mode 100644
index 000000000..0e4f532e4
--- /dev/null
+++ b/arch/sh/include/asm/irq.h
@@ -0,0 +1,72 @@
+#ifndef __ASM_SH_IRQ_H
+#define __ASM_SH_IRQ_H
+
+#include <linux/cpumask.h>
+#include <asm/machvec.h>
+
+/*
+ * Only legacy non-sparseirq platforms have to set a reasonably sane
+ * value here. sparseirq platforms allocate their irq_descs on the fly,
+ * so will expand automatically based on the number of registered IRQs.
+ */
+#ifdef CONFIG_SPARSE_IRQ
+# define NR_IRQS		8
+#else
+# define NR_IRQS		512
+#endif
+
+/*
+ * This is a special IRQ number for indicating that no IRQ has been
+ * triggered and to simply ignore the IRQ dispatch. This is a special
+ * case that can happen with IRQ auto-distribution when multiple CPUs
+ * are woken up and signalled in parallel.
+ */
+#define NO_IRQ_IGNORE		((unsigned int)-1)
+
+/*
+ * Simple Mask Register Support
+ */
+extern void make_maskreg_irq(unsigned int irq);
+extern unsigned short *irq_mask_register;
+
+/*
+ * PINT IRQs
+ */
+void init_IRQ_pint(void);
+void make_imask_irq(unsigned int irq);
+
+static inline int generic_irq_demux(int irq)
+{
+	return irq;
+}
+
+#define irq_demux(irq)		sh_mv.mv_irq_demux(irq)
+
+void init_IRQ(void);
+void migrate_irqs(void);
+
+asmlinkage int do_IRQ(unsigned int irq, struct pt_regs *regs);
+
+#ifdef CONFIG_IRQSTACKS
+extern void irq_ctx_init(int cpu);
+extern void irq_ctx_exit(int cpu);
+# define __ARCH_HAS_DO_SOFTIRQ
+#else
+# define irq_ctx_init(cpu) do { } while (0)
+# define irq_ctx_exit(cpu) do { } while (0)
+#endif
+
+#ifdef CONFIG_INTC_BALANCING
+extern unsigned int irq_lookup(unsigned int irq);
+extern void irq_finish(unsigned int irq);
+#else
+#define irq_lookup(irq)		(irq)
+#define irq_finish(irq)		do { } while (0)
+#endif
+
+#include <asm-generic/irq.h>
+#ifdef CONFIG_CPU_SH5
+#include <cpu/irq.h>
+#endif
+
+#endif /* __ASM_SH_IRQ_H */
diff --git a/arch/sh/include/asm/irqflags.h b/arch/sh/include/asm/irqflags.h
new file mode 100644
index 000000000..43b760860
--- /dev/null
+++ b/arch/sh/include/asm/irqflags.h
@@ -0,0 +1,9 @@
+#ifndef __ASM_SH_IRQFLAGS_H
+#define __ASM_SH_IRQFLAGS_H
+
+#define ARCH_IRQ_DISABLED	0xf0
+#define ARCH_IRQ_ENABLED	0x00
+
+#include <asm-generic/irqflags.h>
+
+#endif /* __ASM_SH_IRQFLAGS_H */
diff --git a/arch/sh/include/asm/kdebug.h b/arch/sh/include/asm/kdebug.h
new file mode 100644
index 000000000..8d6a831e7
--- /dev/null
+++ b/arch/sh/include/asm/kdebug.h
@@ -0,0 +1,17 @@
+#ifndef __ASM_SH_KDEBUG_H
+#define __ASM_SH_KDEBUG_H
+
+/* Grossly misnamed. */
+enum die_val {
+	DIE_TRAP,
+	DIE_NMI,
+	DIE_OOPS,
+	DIE_BREAKPOINT,
+	DIE_SSTEP,
+};
+
+/* arch/sh/kernel/dumpstack.c */
+extern void printk_address(unsigned long address, int reliable);
+extern void dump_mem(const char *str, unsigned long bottom, unsigned long top);
+
+#endif /* __ASM_SH_KDEBUG_H */
diff --git a/arch/sh/include/asm/kexec.h b/arch/sh/include/asm/kexec.h
new file mode 100644
index 000000000..ad6ef8a27
--- /dev/null
+++ b/arch/sh/include/asm/kexec.h
@@ -0,0 +1,70 @@
+#ifndef __ASM_SH_KEXEC_H
+#define __ASM_SH_KEXEC_H
+
+#include <asm/ptrace.h>
+#include <asm/string.h>
+
+/*
+ * KEXEC_SOURCE_MEMORY_LIMIT maximum page get_free_page can return.
+ * I.e. Maximum page that is mapped directly into kernel memory,
+ * and kmap is not required.
+ *
+ * Someone correct me if FIXADDR_START - PAGEOFFSET is not the correct
+ * calculation for the amount of memory directly mappable into the
+ * kernel memory space.
+ */
+
+/* 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 TASK_SIZE
+
+#define KEXEC_CONTROL_PAGE_SIZE	4096
+
+/* The native architecture */
+#define KEXEC_ARCH KEXEC_ARCH_SH
+
+#ifdef CONFIG_KEXEC
+/* arch/sh/kernel/machine_kexec.c */
+void reserve_crashkernel(void);
+
+static inline void crash_setup_regs(struct pt_regs *newregs,
+				    struct pt_regs *oldregs)
+{
+	if (oldregs)
+		memcpy(newregs, oldregs, sizeof(*newregs));
+	else {
+		__asm__ __volatile__ ("mov r0, %0" : "=r" (newregs->regs[0]));
+		__asm__ __volatile__ ("mov r1, %0" : "=r" (newregs->regs[1]));
+		__asm__ __volatile__ ("mov r2, %0" : "=r" (newregs->regs[2]));
+		__asm__ __volatile__ ("mov r3, %0" : "=r" (newregs->regs[3]));
+		__asm__ __volatile__ ("mov r4, %0" : "=r" (newregs->regs[4]));
+		__asm__ __volatile__ ("mov r5, %0" : "=r" (newregs->regs[5]));
+		__asm__ __volatile__ ("mov r6, %0" : "=r" (newregs->regs[6]));
+		__asm__ __volatile__ ("mov r7, %0" : "=r" (newregs->regs[7]));
+		__asm__ __volatile__ ("mov r8, %0" : "=r" (newregs->regs[8]));
+		__asm__ __volatile__ ("mov r9, %0" : "=r" (newregs->regs[9]));
+		__asm__ __volatile__ ("mov r10, %0" : "=r" (newregs->regs[10]));
+		__asm__ __volatile__ ("mov r11, %0" : "=r" (newregs->regs[11]));
+		__asm__ __volatile__ ("mov r12, %0" : "=r" (newregs->regs[12]));
+		__asm__ __volatile__ ("mov r13, %0" : "=r" (newregs->regs[13]));
+		__asm__ __volatile__ ("mov r14, %0" : "=r" (newregs->regs[14]));
+		__asm__ __volatile__ ("mov r15, %0" : "=r" (newregs->regs[15]));
+
+		__asm__ __volatile__ ("sts pr, %0" : "=r" (newregs->pr));
+		__asm__ __volatile__ ("sts macl, %0" : "=r" (newregs->macl));
+		__asm__ __volatile__ ("sts mach, %0" : "=r" (newregs->mach));
+
+		__asm__ __volatile__ ("stc gbr, %0" : "=r" (newregs->gbr));
+		__asm__ __volatile__ ("stc sr, %0" : "=r" (newregs->sr));
+
+		newregs->pc = (unsigned long)current_text_addr();
+	}
+}
+#else
+static inline void reserve_crashkernel(void) { }
+#endif /* CONFIG_KEXEC */
+
+#endif /* __ASM_SH_KEXEC_H */
diff --git a/arch/sh/include/asm/kgdb.h b/arch/sh/include/asm/kgdb.h
new file mode 100644
index 000000000..9e7d2d1b0
--- /dev/null
+++ b/arch/sh/include/asm/kgdb.h
@@ -0,0 +1,37 @@
+#ifndef __ASM_SH_KGDB_H
+#define __ASM_SH_KGDB_H
+
+#include <asm/cacheflush.h>
+#include <asm/ptrace.h>
+
+enum regnames {
+	GDB_R0, GDB_R1, GDB_R2, GDB_R3, GDB_R4, GDB_R5, GDB_R6, GDB_R7,
+	GDB_R8, GDB_R9, GDB_R10, GDB_R11, GDB_R12, GDB_R13, GDB_R14, GDB_R15,
+
+	GDB_PC, GDB_PR, GDB_SR, GDB_GBR, GDB_MACH, GDB_MACL, GDB_VBR,
+};
+
+#define _GP_REGS	16
+#define _EXTRA_REGS	7
+#define GDB_SIZEOF_REG	sizeof(u32)
+
+#define DBG_MAX_REG_NUM	(_GP_REGS + _EXTRA_REGS)
+#define NUMREGBYTES	(DBG_MAX_REG_NUM * sizeof(GDB_SIZEOF_REG))
+
+static inline void arch_kgdb_breakpoint(void)
+{
+	__asm__ __volatile__ ("trapa #0x3c\n");
+}
+
+#define BREAK_INSTR_SIZE	2
+#define BUFMAX			2048
+
+#ifdef CONFIG_SMP
+# define CACHE_FLUSH_IS_SAFE	0
+#else
+# define CACHE_FLUSH_IS_SAFE	1
+#endif
+
+#define GDB_ADJUSTS_BREAK_OFFSET
+
+#endif /* __ASM_SH_KGDB_H */
diff --git a/arch/sh/include/asm/kmap_types.h b/arch/sh/include/asm/kmap_types.h
new file mode 100644
index 000000000..5962b08b6
--- /dev/null
+++ b/arch/sh/include/asm/kmap_types.h
@@ -0,0 +1,14 @@
+#ifndef __SH_KMAP_TYPES_H
+#define __SH_KMAP_TYPES_H
+
+/* Dummy header just to define km_type. */
+
+#ifdef CONFIG_DEBUG_HIGHMEM
+#define  __WITH_KM_FENCE
+#endif
+
+#include <asm-generic/kmap_types.h>
+
+#undef __WITH_KM_FENCE
+
+#endif
diff --git a/arch/sh/include/asm/kprobes.h b/arch/sh/include/asm/kprobes.h
new file mode 100644
index 000000000..134f3980e
--- /dev/null
+++ b/arch/sh/include/asm/kprobes.h
@@ -0,0 +1,57 @@
+#ifndef __ASM_SH_KPROBES_H
+#define __ASM_SH_KPROBES_H
+
+#ifdef CONFIG_KPROBES
+
+#include <linux/types.h>
+#include <linux/ptrace.h>
+
+typedef insn_size_t kprobe_opcode_t;
+#define BREAKPOINT_INSTRUCTION	0xc33a
+
+#define MAX_INSN_SIZE 16
+#define MAX_STACK_SIZE 64
+#define MIN_STACK_SIZE(ADDR) (((MAX_STACK_SIZE) < \
+	(((unsigned long)current_thread_info()) + THREAD_SIZE - (ADDR))) \
+	? (MAX_STACK_SIZE) \
+	: (((unsigned long)current_thread_info()) + THREAD_SIZE - (ADDR)))
+
+#define flush_insn_slot(p)		do { } while (0)
+#define kretprobe_blacklist_size	0
+
+struct kprobe;
+
+void arch_remove_kprobe(struct kprobe *);
+void kretprobe_trampoline(void);
+void jprobe_return_end(void);
+
+/* Architecture specific copy of original instruction*/
+struct arch_specific_insn {
+	/* copy of the original instruction */
+	kprobe_opcode_t insn[MAX_INSN_SIZE];
+};
+
+struct prev_kprobe {
+	struct kprobe *kp;
+	unsigned long status;
+};
+
+/* per-cpu kprobe control block */
+struct kprobe_ctlblk {
+	unsigned long kprobe_status;
+	unsigned long jprobe_saved_r15;
+	struct pt_regs jprobe_saved_regs;
+	kprobe_opcode_t jprobes_stack[MAX_STACK_SIZE];
+	struct prev_kprobe prev_kprobe;
+};
+
+extern int kprobe_fault_handler(struct pt_regs *regs, int trapnr);
+extern int kprobe_exceptions_notify(struct notifier_block *self,
+				    unsigned long val, void *data);
+extern int kprobe_handle_illslot(unsigned long pc);
+#else
+
+#define kprobe_handle_illslot(pc)	(-1)
+
+#endif /* CONFIG_KPROBES */
+#endif /* __ASM_SH_KPROBES_H */
diff --git a/arch/sh/include/asm/linkage.h b/arch/sh/include/asm/linkage.h
new file mode 100644
index 000000000..3565a4f40
--- /dev/null
+++ b/arch/sh/include/asm/linkage.h
@@ -0,0 +1,7 @@
+#ifndef __ASM_LINKAGE_H
+#define __ASM_LINKAGE_H
+
+#define __ALIGN .balign 4
+#define __ALIGN_STR ".balign 4"
+
+#endif
diff --git a/arch/sh/include/asm/machvec.h b/arch/sh/include/asm/machvec.h
new file mode 100644
index 000000000..d3324e4f3
--- /dev/null
+++ b/arch/sh/include/asm/machvec.h
@@ -0,0 +1,43 @@
+/*
+ * include/asm-sh/machvec.h
+ *
+ * Copyright 2000 Stuart Menefy (stuart.menefy@st.com)
+ *
+ * May be copied or modified under the terms of the GNU General Public
+ * License.  See linux/COPYING for more information.
+ */
+
+#ifndef _ASM_SH_MACHVEC_H
+#define _ASM_SH_MACHVEC_H
+
+#include <linux/types.h>
+#include <linux/time.h>
+#include <generated/machtypes.h>
+
+struct sh_machine_vector {
+	void (*mv_setup)(char **cmdline_p);
+	const char *mv_name;
+
+	int (*mv_irq_demux)(int irq);
+	void (*mv_init_irq)(void);
+
+#ifdef CONFIG_HAS_IOPORT_MAP
+	void __iomem *(*mv_ioport_map)(unsigned long port, unsigned int size);
+	void (*mv_ioport_unmap)(void __iomem *);
+#endif
+
+	int (*mv_clk_init)(void);
+	int (*mv_mode_pins)(void);
+
+	void (*mv_mem_init)(void);
+	void (*mv_mem_reserve)(void);
+};
+
+extern struct sh_machine_vector sh_mv;
+
+#define get_system_type()	sh_mv.mv_name
+
+#define __initmv \
+	__used __section(.machvec.init)
+
+#endif /* _ASM_SH_MACHVEC_H */
diff --git a/arch/sh/include/asm/mc146818rtc.h b/arch/sh/include/asm/mc146818rtc.h
new file mode 100644
index 000000000..0aee96a97
--- /dev/null
+++ b/arch/sh/include/asm/mc146818rtc.h
@@ -0,0 +1,7 @@
+/*
+ * Machine dependent access functions for RTC registers.
+ */
+#ifndef _ASM_MC146818RTC_H
+#define _ASM_MC146818RTC_H
+
+#endif /* _ASM_MC146818RTC_H */
diff --git a/arch/sh/include/asm/mmu.h b/arch/sh/include/asm/mmu.h
new file mode 100644
index 000000000..56e4418c1
--- /dev/null
+++ b/arch/sh/include/asm/mmu.h
@@ -0,0 +1,106 @@
+#ifndef __MMU_H
+#define __MMU_H
+
+/*
+ * Privileged Space Mapping Buffer (PMB) definitions
+ */
+#define PMB_PASCR		0xff000070
+#define PMB_IRMCR		0xff000078
+
+#define PASCR_SE		0x80000000
+
+#define PMB_ADDR		0xf6100000
+#define PMB_DATA		0xf7100000
+
+#define NR_PMB_ENTRIES		16
+
+#define PMB_E_MASK		0x0000000f
+#define PMB_E_SHIFT		8
+
+#define PMB_PFN_MASK		0xff000000
+
+#define PMB_SZ_16M		0x00000000
+#define PMB_SZ_64M		0x00000010
+#define PMB_SZ_128M		0x00000080
+#define PMB_SZ_512M		0x00000090
+#define PMB_SZ_MASK		PMB_SZ_512M
+#define PMB_C			0x00000008
+#define PMB_WT			0x00000001
+#define PMB_UB			0x00000200
+#define PMB_CACHE_MASK		(PMB_C | PMB_WT | PMB_UB)
+#define PMB_V			0x00000100
+
+#define PMB_NO_ENTRY		(-1)
+
+#ifndef __ASSEMBLY__
+#include <linux/errno.h>
+#include <linux/threads.h>
+#include <asm/page.h>
+
+/* Default "unsigned long" context */
+typedef unsigned long mm_context_id_t[NR_CPUS];
+
+typedef struct {
+#ifdef CONFIG_MMU
+	mm_context_id_t		id;
+	void			*vdso;
+#else
+	unsigned long		end_brk;
+#endif
+#ifdef CONFIG_BINFMT_ELF_FDPIC
+	unsigned long		exec_fdpic_loadmap;
+	unsigned long		interp_fdpic_loadmap;
+#endif
+} mm_context_t;
+
+#ifdef CONFIG_PMB
+/* arch/sh/mm/pmb.c */
+bool __in_29bit_mode(void);
+
+void pmb_init(void);
+int pmb_bolt_mapping(unsigned long virt, phys_addr_t phys,
+		     unsigned long size, pgprot_t prot);
+void __iomem *pmb_remap_caller(phys_addr_t phys, unsigned long size,
+			       pgprot_t prot, void *caller);
+int pmb_unmap(void __iomem *addr);
+
+#else
+
+static inline int
+pmb_bolt_mapping(unsigned long virt, phys_addr_t phys,
+		 unsigned long size, pgprot_t prot)
+{
+	return -EINVAL;
+}
+
+static inline void __iomem *
+pmb_remap_caller(phys_addr_t phys, unsigned long size,
+		 pgprot_t prot, void *caller)
+{
+	return NULL;
+}
+
+static inline int pmb_unmap(void __iomem *addr)
+{
+	return -EINVAL;
+}
+
+#define pmb_init(addr)		do { } while (0)
+
+#ifdef CONFIG_29BIT
+#define __in_29bit_mode()	(1)
+#else
+#define __in_29bit_mode()	(0)
+#endif
+
+#endif /* CONFIG_PMB */
+
+static inline void __iomem *
+pmb_remap(phys_addr_t phys, unsigned long size, pgprot_t prot)
+{
+	return pmb_remap_caller(phys, size, prot, __builtin_return_address(0));
+}
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* __MMU_H */
diff --git a/arch/sh/include/asm/mmu_context.h b/arch/sh/include/asm/mmu_context.h
new file mode 100644
index 000000000..9f417feaf
--- /dev/null
+++ b/arch/sh/include/asm/mmu_context.h
@@ -0,0 +1,190 @@
+/*
+ * Copyright (C) 1999 Niibe Yutaka
+ * Copyright (C) 2003 - 2007 Paul Mundt
+ *
+ * ASID handling idea taken from MIPS implementation.
+ */
+#ifndef __ASM_SH_MMU_CONTEXT_H
+#define __ASM_SH_MMU_CONTEXT_H
+
+#ifdef __KERNEL__
+#include <cpu/mmu_context.h>
+#include <asm/tlbflush.h>
+#include <asm/uaccess.h>
+#include <asm/io.h>
+#include <asm-generic/mm_hooks.h>
+
+/*
+ * The MMU "context" consists of two things:
+ *    (a) TLB cache version (or round, cycle whatever expression you like)
+ *    (b) ASID (Address Space IDentifier)
+ */
+#ifdef CONFIG_CPU_HAS_PTEAEX
+#define MMU_CONTEXT_ASID_MASK		0x0000ffff
+#else
+#define MMU_CONTEXT_ASID_MASK		0x000000ff
+#endif
+
+#define MMU_CONTEXT_VERSION_MASK	(~0UL & ~MMU_CONTEXT_ASID_MASK)
+#define MMU_CONTEXT_FIRST_VERSION	(MMU_CONTEXT_ASID_MASK + 1)
+
+/* Impossible ASID value, to differentiate from NO_CONTEXT. */
+#define MMU_NO_ASID			MMU_CONTEXT_FIRST_VERSION
+#define NO_CONTEXT			0UL
+
+#define asid_cache(cpu)		(cpu_data[cpu].asid_cache)
+
+#ifdef CONFIG_MMU
+#define cpu_context(cpu, mm)	((mm)->context.id[cpu])
+
+#define cpu_asid(cpu, mm)	\
+	(cpu_context((cpu), (mm)) & MMU_CONTEXT_ASID_MASK)
+
+/*
+ * Virtual Page Number mask
+ */
+#define MMU_VPN_MASK	0xfffff000
+
+#if defined(CONFIG_SUPERH32)
+#include <asm/mmu_context_32.h>
+#else
+#include <asm/mmu_context_64.h>
+#endif
+
+/*
+ * Get MMU context if needed.
+ */
+static inline void get_mmu_context(struct mm_struct *mm, unsigned int cpu)
+{
+	unsigned long asid = asid_cache(cpu);
+
+	/* Check if we have old version of context. */
+	if (((cpu_context(cpu, mm) ^ asid) & MMU_CONTEXT_VERSION_MASK) == 0)
+		/* It's up to date, do nothing */
+		return;
+
+	/* It's old, we need to get new context with new version. */
+	if (!(++asid & MMU_CONTEXT_ASID_MASK)) {
+		/*
+		 * We exhaust ASID of this version.
+		 * Flush all TLB and start new cycle.
+		 */
+		local_flush_tlb_all();
+
+#ifdef CONFIG_SUPERH64
+		/*
+		 * The SH-5 cache uses the ASIDs, requiring both the I and D
+		 * cache to be flushed when the ASID is exhausted. Weak.
+		 */
+		flush_cache_all();
+#endif
+
+		/*
+		 * Fix version; Note that we avoid version #0
+		 * to distinguish NO_CONTEXT.
+		 */
+		if (!asid)
+			asid = MMU_CONTEXT_FIRST_VERSION;
+	}
+
+	cpu_context(cpu, mm) = asid_cache(cpu) = asid;
+}
+
+/*
+ * Initialize the context related info for a new mm_struct
+ * instance.
+ */
+static inline int init_new_context(struct task_struct *tsk,
+				   struct mm_struct *mm)
+{
+	int i;
+
+	for_each_online_cpu(i)
+		cpu_context(i, mm) = NO_CONTEXT;
+
+	return 0;
+}
+
+/*
+ * After we have set current->mm to a new value, this activates
+ * the context for the new mm so we see the new mappings.
+ */
+static inline void activate_context(struct mm_struct *mm, unsigned int cpu)
+{
+	get_mmu_context(mm, cpu);
+	set_asid(cpu_asid(cpu, mm));
+}
+
+static inline void switch_mm(struct mm_struct *prev,
+			     struct mm_struct *next,
+			     struct task_struct *tsk)
+{
+	unsigned int cpu = smp_processor_id();
+
+	if (likely(prev != next)) {
+		cpumask_set_cpu(cpu, mm_cpumask(next));
+		set_TTB(next->pgd);
+		activate_context(next, cpu);
+	} else
+		if (!cpumask_test_and_set_cpu(cpu, mm_cpumask(next)))
+			activate_context(next, cpu);
+}
+
+#define activate_mm(prev, next)		switch_mm((prev),(next),NULL)
+#define deactivate_mm(tsk,mm)		do { } while (0)
+#define enter_lazy_tlb(mm,tsk)		do { } while (0)
+
+#else
+
+#define set_asid(asid)			do { } while (0)
+#define get_asid()			(0)
+#define cpu_asid(cpu, mm)		({ (void)cpu; NO_CONTEXT; })
+#define switch_and_save_asid(asid)	(0)
+#define set_TTB(pgd)			do { } while (0)
+#define get_TTB()			(0)
+
+#include <asm-generic/mmu_context.h>
+
+#endif /* CONFIG_MMU */
+
+#if defined(CONFIG_CPU_SH3) || defined(CONFIG_CPU_SH4)
+/*
+ * If this processor has an MMU, we need methods to turn it off/on ..
+ * paging_init() will also have to be updated for the processor in
+ * question.
+ */
+static inline void enable_mmu(void)
+{
+	unsigned int cpu = smp_processor_id();
+
+	/* Enable MMU */
+	__raw_writel(MMU_CONTROL_INIT, MMUCR);
+	ctrl_barrier();
+
+	if (asid_cache(cpu) == NO_CONTEXT)
+		asid_cache(cpu) = MMU_CONTEXT_FIRST_VERSION;
+
+	set_asid(asid_cache(cpu) & MMU_CONTEXT_ASID_MASK);
+}
+
+static inline void disable_mmu(void)
+{
+	unsigned long cr;
+
+	cr = __raw_readl(MMUCR);
+	cr &= ~MMU_CONTROL_INIT;
+	__raw_writel(cr, MMUCR);
+
+	ctrl_barrier();
+}
+#else
+/*
+ * MMU control handlers for processors lacking memory
+ * management hardware.
+ */
+#define enable_mmu()	do { } while (0)
+#define disable_mmu()	do { } while (0)
+#endif
+
+#endif /* __KERNEL__ */
+#endif /* __ASM_SH_MMU_CONTEXT_H */
diff --git a/arch/sh/include/asm/mmu_context_32.h b/arch/sh/include/asm/mmu_context_32.h
new file mode 100644
index 000000000..10e2e1721
--- /dev/null
+++ b/arch/sh/include/asm/mmu_context_32.h
@@ -0,0 +1,59 @@
+#ifndef __ASM_SH_MMU_CONTEXT_32_H
+#define __ASM_SH_MMU_CONTEXT_32_H
+
+/*
+ * Destroy context related info for an mm_struct that is about
+ * to be put to rest.
+ */
+static inline void destroy_context(struct mm_struct *mm)
+{
+	/* Do nothing */
+}
+
+#ifdef CONFIG_CPU_HAS_PTEAEX
+static inline void set_asid(unsigned long asid)
+{
+	__raw_writel(asid, MMU_PTEAEX);
+}
+
+static inline unsigned long get_asid(void)
+{
+	return __raw_readl(MMU_PTEAEX) & MMU_CONTEXT_ASID_MASK;
+}
+#else
+static inline void set_asid(unsigned long asid)
+{
+	unsigned long __dummy;
+
+	__asm__ __volatile__ ("mov.l	%2, %0\n\t"
+			      "and	%3, %0\n\t"
+			      "or	%1, %0\n\t"
+			      "mov.l	%0, %2"
+			      : "=&r" (__dummy)
+			      : "r" (asid), "m" (__m(MMU_PTEH)),
+			        "r" (0xffffff00));
+}
+
+static inline unsigned long get_asid(void)
+{
+	unsigned long asid;
+
+	__asm__ __volatile__ ("mov.l	%1, %0"
+			      : "=r" (asid)
+			      : "m" (__m(MMU_PTEH)));
+	asid &= MMU_CONTEXT_ASID_MASK;
+	return asid;
+}
+#endif /* CONFIG_CPU_HAS_PTEAEX */
+
+/* MMU_TTB is used for optimizing the fault handling. */
+static inline void set_TTB(pgd_t *pgd)
+{
+	__raw_writel((unsigned long)pgd, MMU_TTB);
+}
+
+static inline pgd_t *get_TTB(void)
+{
+	return (pgd_t *)__raw_readl(MMU_TTB);
+}
+#endif /* __ASM_SH_MMU_CONTEXT_32_H */
diff --git a/arch/sh/include/asm/mmu_context_64.h b/arch/sh/include/asm/mmu_context_64.h
new file mode 100644
index 000000000..de121025d
--- /dev/null
+++ b/arch/sh/include/asm/mmu_context_64.h
@@ -0,0 +1,78 @@
+#ifndef __ASM_SH_MMU_CONTEXT_64_H
+#define __ASM_SH_MMU_CONTEXT_64_H
+
+/*
+ * sh64-specific mmu_context interface.
+ *
+ * Copyright (C) 2000, 2001  Paolo Alberelli
+ * Copyright (C) 2003 - 2007  Paul Mundt
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+#include <cpu/registers.h>
+#include <asm/cacheflush.h>
+
+#define SR_ASID_MASK		0xffffffffff00ffffULL
+#define SR_ASID_SHIFT		16
+
+/*
+ * Destroy context related info for an mm_struct that is about
+ * to be put to rest.
+ */
+static inline void destroy_context(struct mm_struct *mm)
+{
+	/* Well, at least free TLB entries */
+	flush_tlb_mm(mm);
+}
+
+static inline unsigned long get_asid(void)
+{
+	unsigned long long sr;
+
+	asm volatile ("getcon   " __SR ", %0\n\t"
+		      : "=r" (sr));
+
+	sr = (sr >> SR_ASID_SHIFT) & MMU_CONTEXT_ASID_MASK;
+	return (unsigned long) sr;
+}
+
+/* Set ASID into SR */
+static inline void set_asid(unsigned long asid)
+{
+	unsigned long long sr, pc;
+
+	asm volatile ("getcon	" __SR ", %0" : "=r" (sr));
+
+	sr = (sr & SR_ASID_MASK) | (asid << SR_ASID_SHIFT);
+
+	/*
+	 * It is possible that this function may be inlined and so to avoid
+	 * the assembler reporting duplicate symbols we make use of the
+	 * gas trick of generating symbols using numerics and forward
+	 * reference.
+	 */
+	asm volatile ("movi	1, %1\n\t"
+		      "shlli	%1, 28, %1\n\t"
+		      "or	%0, %1, %1\n\t"
+		      "putcon	%1, " __SR "\n\t"
+		      "putcon	%0, " __SSR "\n\t"
+		      "movi	1f, %1\n\t"
+		      "ori	%1, 1 , %1\n\t"
+		      "putcon	%1, " __SPC "\n\t"
+		      "rte\n"
+		      "1:\n\t"
+		      : "=r" (sr), "=r" (pc) : "0" (sr));
+}
+
+/* arch/sh/kernel/cpu/sh5/entry.S */
+extern unsigned long switch_and_save_asid(unsigned long new_asid);
+
+/* No spare register to twiddle, so use a software cache */
+extern pgd_t *mmu_pdtp_cache;
+
+#define set_TTB(pgd)	(mmu_pdtp_cache = (pgd))
+#define get_TTB()	(mmu_pdtp_cache)
+
+#endif /* __ASM_SH_MMU_CONTEXT_64_H */
diff --git a/arch/sh/include/asm/mmzone.h b/arch/sh/include/asm/mmzone.h
new file mode 100644
index 000000000..15a849696
--- /dev/null
+++ b/arch/sh/include/asm/mmzone.h
@@ -0,0 +1,47 @@
+#ifndef __ASM_SH_MMZONE_H
+#define __ASM_SH_MMZONE_H
+
+#ifdef __KERNEL__
+
+#ifdef CONFIG_NEED_MULTIPLE_NODES
+#include <linux/numa.h>
+
+extern struct pglist_data *node_data[];
+#define NODE_DATA(nid)		(node_data[nid])
+
+static inline int pfn_to_nid(unsigned long pfn)
+{
+	int nid;
+
+	for (nid = 0; nid < MAX_NUMNODES; nid++)
+		if (pfn >= node_start_pfn(nid) && pfn <= node_end_pfn(nid))
+			break;
+
+	return nid;
+}
+
+static inline struct pglist_data *pfn_to_pgdat(unsigned long pfn)
+{
+	return NODE_DATA(pfn_to_nid(pfn));
+}
+
+/* arch/sh/mm/numa.c */
+void __init setup_bootmem_node(int nid, unsigned long start, unsigned long end);
+#else
+static inline void
+setup_bootmem_node(int nid, unsigned long start, unsigned long end)
+{
+}
+#endif /* CONFIG_NEED_MULTIPLE_NODES */
+
+/* Platform specific mem init */
+void __init plat_mem_setup(void);
+
+/* arch/sh/kernel/setup.c */
+void __init __add_active_range(unsigned int nid, unsigned long start_pfn,
+			       unsigned long end_pfn);
+/* arch/sh/mm/init.c */
+void __init allocate_pgdat(unsigned int nid);
+
+#endif /* __KERNEL__ */
+#endif /* __ASM_SH_MMZONE_H */
diff --git a/arch/sh/include/asm/module.h b/arch/sh/include/asm/module.h
new file mode 100644
index 000000000..81300d8b5
--- /dev/null
+++ b/arch/sh/include/asm/module.h
@@ -0,0 +1,41 @@
+#ifndef _ASM_SH_MODULE_H
+#define _ASM_SH_MODULE_H
+
+#include <asm-generic/module.h>
+
+#ifdef CONFIG_DWARF_UNWINDER
+struct mod_arch_specific {
+	struct list_head fde_list;
+	struct list_head cie_list;
+};
+#endif
+
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
+# ifdef CONFIG_CPU_SH2
+#  define MODULE_PROC_FAMILY "SH2LE "
+# elif defined  CONFIG_CPU_SH3
+#  define MODULE_PROC_FAMILY "SH3LE "
+# elif defined  CONFIG_CPU_SH4
+#  define MODULE_PROC_FAMILY "SH4LE "
+# elif defined  CONFIG_CPU_SH5
+#  define MODULE_PROC_FAMILY "SH5LE "
+# else
+#  error unknown processor family
+# endif
+#else
+# ifdef CONFIG_CPU_SH2
+#  define MODULE_PROC_FAMILY "SH2BE "
+# elif defined  CONFIG_CPU_SH3
+#  define MODULE_PROC_FAMILY "SH3BE "
+# elif defined  CONFIG_CPU_SH4
+#  define MODULE_PROC_FAMILY "SH4BE "
+# elif defined  CONFIG_CPU_SH5
+#  define MODULE_PROC_FAMILY "SH5BE "
+# else
+#  error unknown processor family
+# endif
+#endif
+
+#define MODULE_ARCH_VERMAGIC MODULE_PROC_FAMILY
+
+#endif /* _ASM_SH_MODULE_H */
diff --git a/arch/sh/include/asm/mutex-llsc.h b/arch/sh/include/asm/mutex-llsc.h
new file mode 100644
index 000000000..dad29b687
--- /dev/null
+++ b/arch/sh/include/asm/mutex-llsc.h
@@ -0,0 +1,109 @@
+/*
+ * arch/sh/include/asm/mutex-llsc.h
+ *
+ * SH-4A optimized mutex locking primitives
+ *
+ * Please look into asm-generic/mutex-xchg.h for a formal definition.
+ */
+#ifndef __ASM_SH_MUTEX_LLSC_H
+#define __ASM_SH_MUTEX_LLSC_H
+
+/*
+ * Attempting to lock a mutex on SH4A is done like in ARMv6+ architecure.
+ * with a bastardized atomic decrement (it is not a reliable atomic decrement
+ * but it satisfies the defined semantics for our purpose, while being
+ * smaller and faster than a real atomic decrement or atomic swap.
+ * The idea is to attempt  decrementing the lock value only once. If once
+ * decremented it isn't zero, or if its store-back fails due to a dispute
+ * on the exclusive store, we simply bail out immediately through the slow
+ * path where the lock will be reattempted until it succeeds.
+ */
+static inline void
+__mutex_fastpath_lock(atomic_t *count, void (*fail_fn)(atomic_t *))
+{
+	int __done, __res;
+
+	__asm__ __volatile__ (
+		"movli.l	@%2, %0	\n"
+		"add		#-1, %0	\n"
+		"movco.l	%0, @%2	\n"
+		"movt		%1	\n"
+		: "=&z" (__res), "=&r" (__done)
+		: "r" (&(count)->counter)
+		: "t");
+
+	if (unlikely(!__done || __res != 0))
+		fail_fn(count);
+}
+
+static inline int
+__mutex_fastpath_lock_retval(atomic_t *count)
+{
+	int __done, __res;
+
+	__asm__ __volatile__ (
+		"movli.l	@%2, %0	\n"
+		"add		#-1, %0	\n"
+		"movco.l	%0, @%2	\n"
+		"movt		%1	\n"
+		: "=&z" (__res), "=&r" (__done)
+		: "r" (&(count)->counter)
+		: "t");
+
+	if (unlikely(!__done || __res != 0))
+		__res = -1;
+
+	return __res;
+}
+
+static inline void
+__mutex_fastpath_unlock(atomic_t *count, void (*fail_fn)(atomic_t *))
+{
+	int __done, __res;
+
+	__asm__ __volatile__ (
+		"movli.l	@%2, %0	\n\t"
+		"add		#1, %0	\n\t"
+		"movco.l	%0, @%2 \n\t"
+		"movt		%1	\n\t"
+		: "=&z" (__res), "=&r" (__done)
+		: "r" (&(count)->counter)
+		: "t");
+
+	if (unlikely(!__done || __res <= 0))
+		fail_fn(count);
+}
+
+/*
+ * If the unlock was done on a contended lock, or if the unlock simply fails
+ * then the mutex remains locked.
+ */
+#define __mutex_slowpath_needs_to_unlock()	1
+
+/*
+ * For __mutex_fastpath_trylock we do an atomic decrement and check the
+ * result and put it in the __res variable.
+ */
+static inline int
+__mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *))
+{
+	int __res, __orig;
+
+	__asm__ __volatile__ (
+		"1: movli.l	@%2, %0		\n\t"
+		"dt		%0		\n\t"
+		"movco.l	%0,@%2		\n\t"
+		"bf		1b		\n\t"
+		"cmp/eq		#0,%0		\n\t"
+		"bt		2f		\n\t"
+		"mov		#0, %1		\n\t"
+		"bf		3f		\n\t"
+		"2: mov		#1, %1		\n\t"
+		"3:				"
+		: "=&z" (__orig), "=&r" (__res)
+		: "r" (&count->counter)
+		: "t");
+
+	return __res;
+}
+#endif /* __ASM_SH_MUTEX_LLSC_H */
diff --git a/arch/sh/include/asm/mutex.h b/arch/sh/include/asm/mutex.h
new file mode 100644
index 000000000..d8e37716a
--- /dev/null
+++ b/arch/sh/include/asm/mutex.h
@@ -0,0 +1,12 @@
+/*
+ * Pull in the generic implementation for the mutex fastpath.
+ *
+ * TODO: implement optimized primitives instead, or leave the generic
+ * implementation in place, or pick the atomic_xchg() based generic
+ * implementation. (see asm-generic/mutex-xchg.h for details)
+ */
+#if defined(CONFIG_CPU_SH4A)
+#include <asm/mutex-llsc.h>
+#else
+#include <asm-generic/mutex-dec.h>
+#endif
diff --git a/arch/sh/include/asm/page.h b/arch/sh/include/asm/page.h
new file mode 100644
index 000000000..fe20d14ae
--- /dev/null
+++ b/arch/sh/include/asm/page.h
@@ -0,0 +1,206 @@
+#ifndef __ASM_SH_PAGE_H
+#define __ASM_SH_PAGE_H
+
+/*
+ * Copyright (C) 1999  Niibe Yutaka
+ */
+
+#include <linux/const.h>
+
+/* PAGE_SHIFT determines the page size */
+#if defined(CONFIG_PAGE_SIZE_4KB)
+# define PAGE_SHIFT	12
+#elif defined(CONFIG_PAGE_SIZE_8KB)
+# define PAGE_SHIFT	13
+#elif defined(CONFIG_PAGE_SIZE_16KB)
+# define PAGE_SHIFT	14
+#elif defined(CONFIG_PAGE_SIZE_64KB)
+# define PAGE_SHIFT	16
+#else
+# error "Bogus kernel page size?"
+#endif
+
+#define PAGE_SIZE	(_AC(1, UL) << PAGE_SHIFT)
+#define PAGE_MASK	(~(PAGE_SIZE-1))
+#define PTE_MASK	PAGE_MASK
+
+#if defined(CONFIG_HUGETLB_PAGE_SIZE_64K)
+#define HPAGE_SHIFT	16
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_256K)
+#define HPAGE_SHIFT	18
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_1MB)
+#define HPAGE_SHIFT	20
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_4MB)
+#define HPAGE_SHIFT	22
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_64MB)
+#define HPAGE_SHIFT	26
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_512MB)
+#define HPAGE_SHIFT	29
+#endif
+
+#ifdef CONFIG_HUGETLB_PAGE
+#define HPAGE_SIZE		(1UL << HPAGE_SHIFT)
+#define HPAGE_MASK		(~(HPAGE_SIZE-1))
+#define HUGETLB_PAGE_ORDER	(HPAGE_SHIFT-PAGE_SHIFT)
+#endif
+
+#ifndef __ASSEMBLY__
+#include <asm/uncached.h>
+
+extern unsigned long shm_align_mask;
+extern unsigned long max_low_pfn, min_low_pfn;
+extern unsigned long memory_start, memory_end, memory_limit;
+
+static inline unsigned long
+pages_do_alias(unsigned long addr1, unsigned long addr2)
+{
+	return (addr1 ^ addr2) & shm_align_mask;
+}
+
+#define clear_page(page)	memset((void *)(page), 0, PAGE_SIZE)
+extern void copy_page(void *to, void *from);
+
+struct page;
+struct vm_area_struct;
+
+extern void copy_user_highpage(struct page *to, struct page *from,
+			       unsigned long vaddr, struct vm_area_struct *vma);
+#define __HAVE_ARCH_COPY_USER_HIGHPAGE
+extern void clear_user_highpage(struct page *page, unsigned long vaddr);
+#define clear_user_highpage	clear_user_highpage
+
+/*
+ * These are used to make use of C type-checking..
+ */
+#ifdef CONFIG_X2TLB
+typedef struct { unsigned long pte_low, pte_high; } pte_t;
+typedef struct { unsigned long long pgprot; } pgprot_t;
+typedef struct { unsigned long long pgd; } pgd_t;
+#define pte_val(x) \
+	((x).pte_low | ((unsigned long long)(x).pte_high << 32))
+#define __pte(x) \
+	({ pte_t __pte = {(x), ((unsigned long long)(x)) >> 32}; __pte; })
+#elif defined(CONFIG_SUPERH32)
+typedef struct { unsigned long pte_low; } pte_t;
+typedef struct { unsigned long pgprot; } pgprot_t;
+typedef struct { unsigned long pgd; } pgd_t;
+#define pte_val(x)	((x).pte_low)
+#define __pte(x)	((pte_t) { (x) } )
+#else
+typedef struct { unsigned long long pte_low; } pte_t;
+typedef struct { unsigned long long pgprot; } pgprot_t;
+typedef struct { unsigned long pgd; } pgd_t;
+#define pte_val(x)	((x).pte_low)
+#define __pte(x)	((pte_t) { (x) } )
+#endif
+
+#define pgd_val(x)	((x).pgd)
+#define pgprot_val(x)	((x).pgprot)
+
+#define __pgd(x) ((pgd_t) { (x) } )
+#define __pgprot(x)	((pgprot_t) { (x) } )
+
+typedef struct page *pgtable_t;
+
+#define pte_pgprot(x) __pgprot(pte_val(x) & PTE_FLAGS_MASK)
+
+#endif /* !__ASSEMBLY__ */
+
+/*
+ * __MEMORY_START and SIZE are the physical addresses and size of RAM.
+ */
+#define __MEMORY_START		CONFIG_MEMORY_START
+#define __MEMORY_SIZE		CONFIG_MEMORY_SIZE
+
+/*
+ * PHYSICAL_OFFSET is the offset in physical memory where the base
+ * of the kernel is loaded.
+ */
+#ifdef CONFIG_PHYSICAL_START
+#define PHYSICAL_OFFSET (CONFIG_PHYSICAL_START - __MEMORY_START)
+#else
+#define PHYSICAL_OFFSET 0
+#endif
+
+/*
+ * PAGE_OFFSET is the virtual address of the start of kernel address
+ * space.
+ */
+#define PAGE_OFFSET		CONFIG_PAGE_OFFSET
+
+/*
+ * Virtual to physical RAM address translation.
+ *
+ * In 29 bit mode, the physical offset of RAM from address 0 is visible in
+ * the kernel virtual address space, and thus we don't have to take
+ * this into account when translating. However in 32 bit mode this offset
+ * is not visible (it is part of the PMB mapping) and so needs to be
+ * added or subtracted as required.
+ */
+#ifdef CONFIG_PMB
+#define ___pa(x)	((x)-PAGE_OFFSET+__MEMORY_START)
+#define ___va(x)	((x)+PAGE_OFFSET-__MEMORY_START)
+#else
+#define ___pa(x)	((x)-PAGE_OFFSET)
+#define ___va(x)	((x)+PAGE_OFFSET)
+#endif
+
+#ifndef __ASSEMBLY__
+#define __pa(x)		___pa((unsigned long)x)
+#define __va(x)		(void *)___va((unsigned long)x)
+#endif /* !__ASSEMBLY__ */
+
+#ifdef CONFIG_UNCACHED_MAPPING
+#if defined(CONFIG_29BIT)
+#define UNCAC_ADDR(addr)	P2SEGADDR(addr)
+#define CAC_ADDR(addr)		P1SEGADDR(addr)
+#else
+#define UNCAC_ADDR(addr)	((addr) - PAGE_OFFSET + uncached_start)
+#define CAC_ADDR(addr)		((addr) - uncached_start + PAGE_OFFSET)
+#endif
+#else
+#define UNCAC_ADDR(addr)	((addr))
+#define CAC_ADDR(addr)		((addr))
+#endif
+
+#define pfn_to_kaddr(pfn)	__va((pfn) << PAGE_SHIFT)
+#define page_to_phys(page)	(page_to_pfn(page) << PAGE_SHIFT)
+
+/*
+ * PFN = physical frame number (ie PFN 0 == physical address 0)
+ * PFN_START is the PFN of the first page of RAM. By defining this we
+ * don't have struct page entries for the portion of address space
+ * between physical address 0 and the start of RAM.
+ */
+#define PFN_START		(__MEMORY_START >> PAGE_SHIFT)
+#define ARCH_PFN_OFFSET		(PFN_START)
+#define virt_to_page(kaddr)	pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
+#ifdef CONFIG_FLATMEM
+#define pfn_valid(pfn)		((pfn) >= min_low_pfn && (pfn) < max_low_pfn)
+#endif
+#define virt_addr_valid(kaddr)	pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
+
+#define VM_DATA_DEFAULT_FLAGS	(VM_READ | VM_WRITE | VM_EXEC | \
+				 VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
+
+#include <asm-generic/memory_model.h>
+#include <asm-generic/getorder.h>
+
+/*
+ * Some drivers need to perform DMA into kmalloc'ed buffers
+ * and so we have to increase the kmalloc minalign for this.
+ */
+#define ARCH_DMA_MINALIGN	L1_CACHE_BYTES
+
+#ifdef CONFIG_SUPERH64
+/*
+ * While BYTES_PER_WORD == 4 on the current sh64 ABI, GCC will still
+ * happily generate {ld/st}.q pairs, requiring us to have 8-byte
+ * alignment to avoid traps. The kmalloc alignment is guaranteed by
+ * virtue of L1_CACHE_BYTES, requiring this to only be special cased
+ * for slab caches.
+ */
+#define ARCH_SLAB_MINALIGN	8
+#endif
+
+#endif /* __ASM_SH_PAGE_H */
diff --git a/arch/sh/include/asm/pci.h b/arch/sh/include/asm/pci.h
new file mode 100644
index 000000000..5b4511552
--- /dev/null
+++ b/arch/sh/include/asm/pci.h
@@ -0,0 +1,131 @@
+#ifndef __ASM_SH_PCI_H
+#define __ASM_SH_PCI_H
+
+#ifdef __KERNEL__
+
+/* Can be used to override the logic in pci_scan_bus for skipping
+   already-configured bus numbers - to be used for buggy BIOSes
+   or architectures with incomplete PCI setup by the loader */
+
+#define pcibios_assign_all_busses()	1
+
+/*
+ * A board can define one or more PCI channels that represent built-in (or
+ * external) PCI controllers.
+ */
+struct pci_channel {
+	struct pci_channel	*next;
+	struct pci_bus		*bus;
+
+	struct pci_ops		*pci_ops;
+
+	struct resource		*resources;
+	unsigned int		nr_resources;
+
+	unsigned long		io_offset;
+	unsigned long		mem_offset;
+
+	unsigned long		reg_base;
+	unsigned long		io_map_base;
+
+	unsigned int		index;
+	unsigned int		need_domain_info;
+
+	/* Optional error handling */
+	struct timer_list	err_timer, serr_timer;
+	unsigned int		err_irq, serr_irq;
+};
+
+/* arch/sh/drivers/pci/pci.c */
+extern raw_spinlock_t pci_config_lock;
+
+extern int register_pci_controller(struct pci_channel *hose);
+extern void pcibios_report_status(unsigned int status_mask, int warn);
+
+/* arch/sh/drivers/pci/common.c */
+extern int early_read_config_byte(struct pci_channel *hose, int top_bus,
+				  int bus, int devfn, int offset, u8 *value);
+extern int early_read_config_word(struct pci_channel *hose, int top_bus,
+				  int bus, int devfn, int offset, u16 *value);
+extern int early_read_config_dword(struct pci_channel *hose, int top_bus,
+				   int bus, int devfn, int offset, u32 *value);
+extern int early_write_config_byte(struct pci_channel *hose, int top_bus,
+				   int bus, int devfn, int offset, u8 value);
+extern int early_write_config_word(struct pci_channel *hose, int top_bus,
+				   int bus, int devfn, int offset, u16 value);
+extern int early_write_config_dword(struct pci_channel *hose, int top_bus,
+				    int bus, int devfn, int offset, u32 value);
+extern void pcibios_enable_timers(struct pci_channel *hose);
+extern unsigned int pcibios_handle_status_errors(unsigned long addr,
+				 unsigned int status, struct pci_channel *hose);
+extern int pci_is_66mhz_capable(struct pci_channel *hose,
+				int top_bus, int current_bus);
+
+extern unsigned long PCIBIOS_MIN_IO, PCIBIOS_MIN_MEM;
+
+struct pci_dev;
+
+#define HAVE_PCI_MMAP
+extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
+	enum pci_mmap_state mmap_state, int write_combine);
+extern void pcibios_set_master(struct pci_dev *dev);
+
+/* Dynamic DMA mapping stuff.
+ * SuperH has everything mapped statically like x86.
+ */
+
+/* The PCI address space does equal the physical memory
+ * address space.  The networking and block device layers use
+ * this boolean for bounce buffer decisions.
+ */
+#define PCI_DMA_BUS_IS_PHYS	(dma_ops->is_phys)
+
+#ifdef CONFIG_PCI
+/*
+ * None of the SH PCI controllers support MWI, it is always treated as a
+ * direct memory write.
+ */
+#define PCI_DISABLE_MWI
+
+static inline void pci_dma_burst_advice(struct pci_dev *pdev,
+					enum pci_dma_burst_strategy *strat,
+					unsigned long *strategy_parameter)
+{
+	unsigned long cacheline_size;
+	u8 byte;
+
+	pci_read_config_byte(pdev, PCI_CACHE_LINE_SIZE, &byte);
+
+	if (byte == 0)
+		cacheline_size = L1_CACHE_BYTES;
+	else
+		cacheline_size = byte << 2;
+
+	*strat = PCI_DMA_BURST_MULTIPLE;
+	*strategy_parameter = cacheline_size;
+}
+#endif
+
+/* Board-specific fixup routines. */
+int pcibios_map_platform_irq(const struct pci_dev *dev, u8 slot, u8 pin);
+
+#define pci_domain_nr(bus) ((struct pci_channel *)(bus)->sysdata)->index
+
+static inline int pci_proc_domain(struct pci_bus *bus)
+{
+	struct pci_channel *hose = bus->sysdata;
+	return hose->need_domain_info;
+}
+
+/* Chances are this interrupt is wired PC-style ...  */
+static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
+{
+	return channel ? 15 : 14;
+}
+
+/* generic DMA-mapping stuff */
+#include <asm-generic/pci-dma-compat.h>
+
+#endif /* __KERNEL__ */
+#endif /* __ASM_SH_PCI_H */
+
diff --git a/arch/sh/include/asm/perf_event.h b/arch/sh/include/asm/perf_event.h
new file mode 100644
index 000000000..14308bed7
--- /dev/null
+++ b/arch/sh/include/asm/perf_event.h
@@ -0,0 +1,29 @@
+#ifndef __ASM_SH_PERF_EVENT_H
+#define __ASM_SH_PERF_EVENT_H
+
+struct hw_perf_event;
+
+#define MAX_HWEVENTS	2
+
+struct sh_pmu {
+	const char	*name;
+	unsigned int	num_events;
+	void		(*disable_all)(void);
+	void		(*enable_all)(void);
+	void		(*enable)(struct hw_perf_event *, int);
+	void		(*disable)(struct hw_perf_event *, int);
+	u64		(*read)(int);
+	int		(*event_map)(int);
+	unsigned int	max_events;
+	unsigned long	raw_event_mask;
+	const int	(*cache_events)[PERF_COUNT_HW_CACHE_MAX]
+				       [PERF_COUNT_HW_CACHE_OP_MAX]
+				       [PERF_COUNT_HW_CACHE_RESULT_MAX];
+};
+
+/* arch/sh/kernel/perf_event.c */
+extern int register_sh_pmu(struct sh_pmu *);
+extern int reserve_pmc_hardware(void);
+extern void release_pmc_hardware(void);
+
+#endif /* __ASM_SH_PERF_EVENT_H */
diff --git a/arch/sh/include/asm/pgalloc.h b/arch/sh/include/asm/pgalloc.h
new file mode 100644
index 000000000..a33673b36
--- /dev/null
+++ b/arch/sh/include/asm/pgalloc.h
@@ -0,0 +1,79 @@
+#ifndef __ASM_SH_PGALLOC_H
+#define __ASM_SH_PGALLOC_H
+
+#include <linux/quicklist.h>
+#include <asm/page.h>
+
+#define QUICK_PT 0	/* Other page table pages that are zero on free */
+
+extern pgd_t *pgd_alloc(struct mm_struct *);
+extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
+
+#if PAGETABLE_LEVELS > 2
+extern void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd);
+extern pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address);
+extern void pmd_free(struct mm_struct *mm, pmd_t *pmd);
+#endif
+
+static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd,
+				       pte_t *pte)
+{
+	set_pmd(pmd, __pmd((unsigned long)pte));
+}
+
+static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
+				pgtable_t pte)
+{
+	set_pmd(pmd, __pmd((unsigned long)page_address(pte)));
+}
+#define pmd_pgtable(pmd) pmd_page(pmd)
+
+/*
+ * Allocate and free page tables.
+ */
+static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
+					  unsigned long address)
+{
+	return quicklist_alloc(QUICK_PT, GFP_KERNEL | __GFP_REPEAT, NULL);
+}
+
+static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
+					unsigned long address)
+{
+	struct page *page;
+	void *pg;
+
+	pg = quicklist_alloc(QUICK_PT, GFP_KERNEL | __GFP_REPEAT, NULL);
+	if (!pg)
+		return NULL;
+	page = virt_to_page(pg);
+	if (!pgtable_page_ctor(page)) {
+		quicklist_free(QUICK_PT, NULL, pg);
+		return NULL;
+	}
+	return page;
+}
+
+static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
+{
+	quicklist_free(QUICK_PT, NULL, pte);
+}
+
+static inline void pte_free(struct mm_struct *mm, pgtable_t pte)
+{
+	pgtable_page_dtor(pte);
+	quicklist_free_page(QUICK_PT, NULL, pte);
+}
+
+#define __pte_free_tlb(tlb,pte,addr)			\
+do {							\
+	pgtable_page_dtor(pte);				\
+	tlb_remove_page((tlb), (pte));			\
+} while (0)
+
+static inline void check_pgt_cache(void)
+{
+	quicklist_trim(QUICK_PT, NULL, 25, 16);
+}
+
+#endif /* __ASM_SH_PGALLOC_H */
diff --git a/arch/sh/include/asm/pgtable-2level.h b/arch/sh/include/asm/pgtable-2level.h
new file mode 100644
index 000000000..19bd89db1
--- /dev/null
+++ b/arch/sh/include/asm/pgtable-2level.h
@@ -0,0 +1,23 @@
+#ifndef __ASM_SH_PGTABLE_2LEVEL_H
+#define __ASM_SH_PGTABLE_2LEVEL_H
+
+#include <asm-generic/pgtable-nopmd.h>
+
+/*
+ * traditional two-level paging structure
+ */
+#define PAGETABLE_LEVELS	2
+
+/* PTE bits */
+#define PTE_MAGNITUDE		2	/* 32-bit PTEs */
+
+#define PTE_SHIFT		PAGE_SHIFT
+#define PTE_BITS		(PTE_SHIFT - PTE_MAGNITUDE)
+
+/* PGD bits */
+#define PGDIR_SHIFT		(PTE_SHIFT + PTE_BITS)
+
+#define PTRS_PER_PGD		(PAGE_SIZE / (1 << PTE_MAGNITUDE))
+#define USER_PTRS_PER_PGD	(TASK_SIZE/PGDIR_SIZE)
+
+#endif /* __ASM_SH_PGTABLE_2LEVEL_H */
diff --git a/arch/sh/include/asm/pgtable-3level.h b/arch/sh/include/asm/pgtable-3level.h
new file mode 100644
index 000000000..249a985d9
--- /dev/null
+++ b/arch/sh/include/asm/pgtable-3level.h
@@ -0,0 +1,56 @@
+#ifndef __ASM_SH_PGTABLE_3LEVEL_H
+#define __ASM_SH_PGTABLE_3LEVEL_H
+
+#include <asm-generic/pgtable-nopud.h>
+
+/*
+ * Some cores need a 3-level page table layout, for example when using
+ * 64-bit PTEs and 4K pages.
+ */
+#define PAGETABLE_LEVELS	3
+
+#define PTE_MAGNITUDE		3	/* 64-bit PTEs on SH-X2 TLB */
+
+/* PGD bits */
+#define PGDIR_SHIFT		30
+
+#define PTRS_PER_PGD		4
+#define USER_PTRS_PER_PGD	2
+
+/* PMD bits */
+#define PMD_SHIFT	(PAGE_SHIFT + (PAGE_SHIFT - PTE_MAGNITUDE))
+#define PMD_SIZE	(1UL << PMD_SHIFT)
+#define PMD_MASK	(~(PMD_SIZE-1))
+
+#define PTRS_PER_PMD	((1 << PGDIR_SHIFT) / PMD_SIZE)
+
+#define pmd_ERROR(e) \
+	printk("%s:%d: bad pmd %016llx.\n", __FILE__, __LINE__, pmd_val(e))
+
+typedef struct { unsigned long long pmd; } pmd_t;
+#define pmd_val(x)	((x).pmd)
+#define __pmd(x)	((pmd_t) { (x) } )
+
+static inline unsigned long pud_page_vaddr(pud_t pud)
+{
+	return pud_val(pud);
+}
+
+#define pmd_index(address)	(((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1))
+static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address)
+{
+	return (pmd_t *)pud_page_vaddr(*pud) + pmd_index(address);
+}
+
+#define pud_none(x)	(!pud_val(x))
+#define pud_present(x)	(pud_val(x))
+#define pud_clear(xp)	do { set_pud(xp, __pud(0)); } while (0)
+#define	pud_bad(x)	(pud_val(x) & ~PAGE_MASK)
+
+/*
+ * (puds are folded into pgds so this doesn't get actually called,
+ * but the define is needed for a generic inline function.)
+ */
+#define set_pud(pudptr, pudval) do { *(pudptr) = (pudval); } while(0)
+
+#endif /* __ASM_SH_PGTABLE_3LEVEL_H */
diff --git a/arch/sh/include/asm/pgtable.h b/arch/sh/include/asm/pgtable.h
new file mode 100644
index 000000000..89c513a98
--- /dev/null
+++ b/arch/sh/include/asm/pgtable.h
@@ -0,0 +1,163 @@
+/*
+ * This file contains the functions and defines necessary to modify and
+ * use the SuperH page table tree.
+ *
+ * Copyright (C) 1999 Niibe Yutaka
+ * Copyright (C) 2002 - 2007 Paul Mundt
+ *
+ * This file is subject to the terms and conditions of the GNU General
+ * Public License.  See the file "COPYING" in the main directory of this
+ * archive for more details.
+ */
+#ifndef __ASM_SH_PGTABLE_H
+#define __ASM_SH_PGTABLE_H
+
+#ifdef CONFIG_X2TLB
+#include <asm/pgtable-3level.h>
+#else
+#include <asm/pgtable-2level.h>
+#endif
+#include <asm/page.h>
+#include <asm/mmu.h>
+
+#ifndef __ASSEMBLY__
+#include <asm/addrspace.h>
+#include <asm/fixmap.h>
+
+/*
+ * ZERO_PAGE is a global shared page that is always zero: used
+ * for zero-mapped memory areas etc..
+ */
+extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
+#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
+
+#endif /* !__ASSEMBLY__ */
+
+/*
+ * Effective and physical address definitions, to aid with sign
+ * extension.
+ */
+#define NEFF		32
+#define	NEFF_SIGN	(1LL << (NEFF - 1))
+#define	NEFF_MASK	(-1LL << NEFF)
+
+static inline unsigned long long neff_sign_extend(unsigned long val)
+{
+	unsigned long long extended = val;
+	return (extended & NEFF_SIGN) ? (extended | NEFF_MASK) : extended;
+}
+
+#ifdef CONFIG_29BIT
+#define NPHYS		29
+#else
+#define NPHYS		32
+#endif
+
+#define	NPHYS_SIGN	(1LL << (NPHYS - 1))
+#define	NPHYS_MASK	(-1LL << NPHYS)
+
+#define PGDIR_SIZE	(1UL << PGDIR_SHIFT)
+#define PGDIR_MASK	(~(PGDIR_SIZE-1))
+
+/* Entries per level */
+#define PTRS_PER_PTE	(PAGE_SIZE / (1 << PTE_MAGNITUDE))
+
+#define FIRST_USER_ADDRESS	0UL
+
+#define PHYS_ADDR_MASK29		0x1fffffff
+#define PHYS_ADDR_MASK32		0xffffffff
+
+static inline unsigned long phys_addr_mask(void)
+{
+	/* Is the MMU in 29bit mode? */
+	if (__in_29bit_mode())
+		return PHYS_ADDR_MASK29;
+
+	return PHYS_ADDR_MASK32;
+}
+
+#define PTE_PHYS_MASK		(phys_addr_mask() & PAGE_MASK)
+#define PTE_FLAGS_MASK		(~(PTE_PHYS_MASK) << PAGE_SHIFT)
+
+#ifdef CONFIG_SUPERH32
+#define VMALLOC_START	(P3SEG)
+#else
+#define VMALLOC_START	(0xf0000000)
+#endif
+#define VMALLOC_END	(FIXADDR_START-2*PAGE_SIZE)
+
+#if defined(CONFIG_SUPERH32)
+#include <asm/pgtable_32.h>
+#else
+#include <asm/pgtable_64.h>
+#endif
+
+/*
+ * SH-X and lower (legacy) SuperH parts (SH-3, SH-4, some SH-4A) can't do page
+ * protection for execute, and considers it the same as a read. Also, write
+ * permission implies read permission. This is the closest we can get..
+ *
+ * SH-X2 (SH7785) and later parts take this to the opposite end of the extreme,
+ * not only supporting separate execute, read, and write bits, but having
+ * completely separate permission bits for user and kernel space.
+ */
+	 /*xwr*/
+#define __P000	PAGE_NONE
+#define __P001	PAGE_READONLY
+#define __P010	PAGE_COPY
+#define __P011	PAGE_COPY
+#define __P100	PAGE_EXECREAD
+#define __P101	PAGE_EXECREAD
+#define __P110	PAGE_COPY
+#define __P111	PAGE_COPY
+
+#define __S000	PAGE_NONE
+#define __S001	PAGE_READONLY
+#define __S010	PAGE_WRITEONLY
+#define __S011	PAGE_SHARED
+#define __S100	PAGE_EXECREAD
+#define __S101	PAGE_EXECREAD
+#define __S110	PAGE_RWX
+#define __S111	PAGE_RWX
+
+typedef pte_t *pte_addr_t;
+
+#define kern_addr_valid(addr)	(1)
+
+#define pte_pfn(x)		((unsigned long)(((x).pte_low >> PAGE_SHIFT)))
+
+/*
+ * Initialise the page table caches
+ */
+extern void pgtable_cache_init(void);
+
+struct vm_area_struct;
+struct mm_struct;
+
+extern void __update_cache(struct vm_area_struct *vma,
+			   unsigned long address, pte_t pte);
+extern void __update_tlb(struct vm_area_struct *vma,
+			 unsigned long address, pte_t pte);
+
+static inline void
+update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep)
+{
+	pte_t pte = *ptep;
+	__update_cache(vma, address, pte);
+	__update_tlb(vma, address, pte);
+}
+
+extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
+extern void paging_init(void);
+extern void page_table_range_init(unsigned long start, unsigned long end,
+				  pgd_t *pgd);
+
+/* arch/sh/mm/mmap.c */
+#define HAVE_ARCH_UNMAPPED_AREA
+#define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
+
+#define __HAVE_ARCH_PTE_SPECIAL
+
+#include <asm-generic/pgtable.h>
+
+#endif /* __ASM_SH_PGTABLE_H */
diff --git a/arch/sh/include/asm/pgtable_32.h b/arch/sh/include/asm/pgtable_32.h
new file mode 100644
index 000000000..c646e563a
--- /dev/null
+++ b/arch/sh/include/asm/pgtable_32.h
@@ -0,0 +1,476 @@
+#ifndef __ASM_SH_PGTABLE_32_H
+#define __ASM_SH_PGTABLE_32_H
+
+/*
+ * Linux PTEL encoding.
+ *
+ * Hardware and software bit definitions for the PTEL value (see below for
+ * notes on SH-X2 MMUs and 64-bit PTEs):
+ *
+ * - Bits 0 and 7 are reserved on SH-3 (_PAGE_WT and _PAGE_SZ1 on SH-4).
+ *
+ * - Bit 1 is the SH-bit, but is unused on SH-3 due to an MMU bug (the
+ *   hardware PTEL value can't have the SH-bit set when MMUCR.IX is set,
+ *   which is the default in cpu-sh3/mmu_context.h:MMU_CONTROL_INIT).
+ *
+ *   In order to keep this relatively clean, do not use these for defining
+ *   SH-3 specific flags until all of the other unused bits have been
+ *   exhausted.
+ *
+ * - Bit 9 is reserved by everyone and used by _PAGE_PROTNONE.
+ *
+ * - Bits 10 and 11 are low bits of the PPN that are reserved on >= 4K pages.
+ *   Bit 10 is used for _PAGE_ACCESSED, and bit 11 is used for _PAGE_SPECIAL.
+ *
+ * - On 29 bit platforms, bits 31 to 29 are used for the space attributes
+ *   and timing control which (together with bit 0) are moved into the
+ *   old-style PTEA on the parts that support it.
+ *
+ * SH-X2 MMUs and extended PTEs
+ *
+ * SH-X2 supports an extended mode TLB with split data arrays due to the
+ * number of bits needed for PR and SZ (now EPR and ESZ) encodings. The PR and
+ * SZ bit placeholders still exist in data array 1, but are implemented as
+ * reserved bits, with the real logic existing in data array 2.
+ *
+ * The downside to this is that we can no longer fit everything in to a 32-bit
+ * PTE encoding, so a 64-bit pte_t is necessary for these parts. On the plus
+ * side, this gives us quite a few spare bits to play with for future usage.
+ */
+/* Legacy and compat mode bits */
+#define	_PAGE_WT	0x001		/* WT-bit on SH-4, 0 on SH-3 */
+#define _PAGE_HW_SHARED	0x002		/* SH-bit  : shared among processes */
+#define _PAGE_DIRTY	0x004		/* D-bit   : page changed */
+#define _PAGE_CACHABLE	0x008		/* C-bit   : cachable */
+#define _PAGE_SZ0	0x010		/* SZ0-bit : Size of page */
+#define _PAGE_RW	0x020		/* PR0-bit : write access allowed */
+#define _PAGE_USER	0x040		/* PR1-bit : user space access allowed*/
+#define _PAGE_SZ1	0x080		/* SZ1-bit : Size of page (on SH-4) */
+#define _PAGE_PRESENT	0x100		/* V-bit   : page is valid */
+#define _PAGE_PROTNONE	0x200		/* software: if not present  */
+#define _PAGE_ACCESSED	0x400		/* software: page referenced */
+#define _PAGE_SPECIAL	0x800		/* software: special page */
+
+#define _PAGE_SZ_MASK	(_PAGE_SZ0 | _PAGE_SZ1)
+#define _PAGE_PR_MASK	(_PAGE_RW | _PAGE_USER)
+
+/* Extended mode bits */
+#define _PAGE_EXT_ESZ0		0x0010	/* ESZ0-bit: Size of page */
+#define _PAGE_EXT_ESZ1		0x0020	/* ESZ1-bit: Size of page */
+#define _PAGE_EXT_ESZ2		0x0040	/* ESZ2-bit: Size of page */
+#define _PAGE_EXT_ESZ3		0x0080	/* ESZ3-bit: Size of page */
+
+#define _PAGE_EXT_USER_EXEC	0x0100	/* EPR0-bit: User space executable */
+#define _PAGE_EXT_USER_WRITE	0x0200	/* EPR1-bit: User space writable */
+#define _PAGE_EXT_USER_READ	0x0400	/* EPR2-bit: User space readable */
+
+#define _PAGE_EXT_KERN_EXEC	0x0800	/* EPR3-bit: Kernel space executable */
+#define _PAGE_EXT_KERN_WRITE	0x1000	/* EPR4-bit: Kernel space writable */
+#define _PAGE_EXT_KERN_READ	0x2000	/* EPR5-bit: Kernel space readable */
+
+#define _PAGE_EXT_WIRED		0x4000	/* software: Wire TLB entry */
+
+/* Wrapper for extended mode pgprot twiddling */
+#define _PAGE_EXT(x)		((unsigned long long)(x) << 32)
+
+#ifdef CONFIG_X2TLB
+#define _PAGE_PCC_MASK	0x00000000	/* No legacy PTEA support */
+#else
+
+/* software: moves to PTEA.TC (Timing Control) */
+#define _PAGE_PCC_AREA5	0x00000000	/* use BSC registers for area5 */
+#define _PAGE_PCC_AREA6	0x80000000	/* use BSC registers for area6 */
+
+/* software: moves to PTEA.SA[2:0] (Space Attributes) */
+#define _PAGE_PCC_IODYN 0x00000001	/* IO space, dynamically sized bus */
+#define _PAGE_PCC_IO8	0x20000000	/* IO space, 8 bit bus */
+#define _PAGE_PCC_IO16	0x20000001	/* IO space, 16 bit bus */
+#define _PAGE_PCC_COM8	0x40000000	/* Common Memory space, 8 bit bus */
+#define _PAGE_PCC_COM16	0x40000001	/* Common Memory space, 16 bit bus */
+#define _PAGE_PCC_ATR8	0x60000000	/* Attribute Memory space, 8 bit bus */
+#define _PAGE_PCC_ATR16	0x60000001	/* Attribute Memory space, 6 bit bus */
+
+#define _PAGE_PCC_MASK	0xe0000001
+
+/* copy the ptea attributes */
+static inline unsigned long copy_ptea_attributes(unsigned long x)
+{
+	return	((x >> 28) & 0xe) | (x & 0x1);
+}
+#endif
+
+/* Mask which drops unused bits from the PTEL value */
+#if defined(CONFIG_CPU_SH3)
+#define _PAGE_CLEAR_FLAGS	(_PAGE_PROTNONE | _PAGE_ACCESSED| \
+				  _PAGE_SZ1	| _PAGE_HW_SHARED)
+#elif defined(CONFIG_X2TLB)
+/* Get rid of the legacy PR/SZ bits when using extended mode */
+#define _PAGE_CLEAR_FLAGS	(_PAGE_PROTNONE | _PAGE_ACCESSED | \
+				 _PAGE_PR_MASK | _PAGE_SZ_MASK)
+#else
+#define _PAGE_CLEAR_FLAGS	(_PAGE_PROTNONE | _PAGE_ACCESSED)
+#endif
+
+#define _PAGE_FLAGS_HARDWARE_MASK	(phys_addr_mask() & ~(_PAGE_CLEAR_FLAGS))
+
+/* Hardware flags, page size encoding */
+#if !defined(CONFIG_MMU)
+# define _PAGE_FLAGS_HARD	0ULL
+#elif defined(CONFIG_X2TLB)
+# if defined(CONFIG_PAGE_SIZE_4KB)
+#  define _PAGE_FLAGS_HARD	_PAGE_EXT(_PAGE_EXT_ESZ0)
+# elif defined(CONFIG_PAGE_SIZE_8KB)
+#  define _PAGE_FLAGS_HARD	_PAGE_EXT(_PAGE_EXT_ESZ1)
+# elif defined(CONFIG_PAGE_SIZE_64KB)
+#  define _PAGE_FLAGS_HARD	_PAGE_EXT(_PAGE_EXT_ESZ2)
+# endif
+#else
+# if defined(CONFIG_PAGE_SIZE_4KB)
+#  define _PAGE_FLAGS_HARD	_PAGE_SZ0
+# elif defined(CONFIG_PAGE_SIZE_64KB)
+#  define _PAGE_FLAGS_HARD	_PAGE_SZ1
+# endif
+#endif
+
+#if defined(CONFIG_X2TLB)
+# if defined(CONFIG_HUGETLB_PAGE_SIZE_64K)
+#  define _PAGE_SZHUGE	(_PAGE_EXT_ESZ2)
+# elif defined(CONFIG_HUGETLB_PAGE_SIZE_256K)
+#  define _PAGE_SZHUGE	(_PAGE_EXT_ESZ0 | _PAGE_EXT_ESZ2)
+# elif defined(CONFIG_HUGETLB_PAGE_SIZE_1MB)
+#  define _PAGE_SZHUGE	(_PAGE_EXT_ESZ0 | _PAGE_EXT_ESZ1 | _PAGE_EXT_ESZ2)
+# elif defined(CONFIG_HUGETLB_PAGE_SIZE_4MB)
+#  define _PAGE_SZHUGE	(_PAGE_EXT_ESZ3)
+# elif defined(CONFIG_HUGETLB_PAGE_SIZE_64MB)
+#  define _PAGE_SZHUGE	(_PAGE_EXT_ESZ2 | _PAGE_EXT_ESZ3)
+# endif
+# define _PAGE_WIRED	(_PAGE_EXT(_PAGE_EXT_WIRED))
+#else
+# if defined(CONFIG_HUGETLB_PAGE_SIZE_64K)
+#  define _PAGE_SZHUGE	(_PAGE_SZ1)
+# elif defined(CONFIG_HUGETLB_PAGE_SIZE_1MB)
+#  define _PAGE_SZHUGE	(_PAGE_SZ0 | _PAGE_SZ1)
+# endif
+# define _PAGE_WIRED	(0)
+#endif
+
+/*
+ * Stub out _PAGE_SZHUGE if we don't have a good definition for it,
+ * to make pte_mkhuge() happy.
+ */
+#ifndef _PAGE_SZHUGE
+# define _PAGE_SZHUGE	(_PAGE_FLAGS_HARD)
+#endif
+
+/*
+ * Mask of bits that are to be preserved across pgprot changes.
+ */
+#define _PAGE_CHG_MASK \
+	(PTE_MASK | _PAGE_ACCESSED | _PAGE_CACHABLE | \
+	 _PAGE_DIRTY | _PAGE_SPECIAL)
+
+#ifndef __ASSEMBLY__
+
+#if defined(CONFIG_X2TLB) /* SH-X2 TLB */
+#define PAGE_NONE	__pgprot(_PAGE_PROTNONE | _PAGE_CACHABLE | \
+				 _PAGE_ACCESSED | _PAGE_FLAGS_HARD)
+
+#define PAGE_SHARED	__pgprot(_PAGE_PRESENT | _PAGE_ACCESSED | \
+				 _PAGE_CACHABLE | _PAGE_FLAGS_HARD | \
+				 _PAGE_EXT(_PAGE_EXT_KERN_READ  | \
+					   _PAGE_EXT_KERN_WRITE | \
+					   _PAGE_EXT_USER_READ  | \
+					   _PAGE_EXT_USER_WRITE))
+
+#define PAGE_EXECREAD	__pgprot(_PAGE_PRESENT | _PAGE_ACCESSED | \
+				 _PAGE_CACHABLE | _PAGE_FLAGS_HARD | \
+				 _PAGE_EXT(_PAGE_EXT_KERN_EXEC | \
+					   _PAGE_EXT_KERN_READ | \
+					   _PAGE_EXT_USER_EXEC | \
+					   _PAGE_EXT_USER_READ))
+
+#define PAGE_COPY	PAGE_EXECREAD
+
+#define PAGE_READONLY	__pgprot(_PAGE_PRESENT | _PAGE_ACCESSED | \
+				 _PAGE_CACHABLE | _PAGE_FLAGS_HARD | \
+				 _PAGE_EXT(_PAGE_EXT_KERN_READ | \
+					   _PAGE_EXT_USER_READ))
+
+#define PAGE_WRITEONLY	__pgprot(_PAGE_PRESENT | _PAGE_ACCESSED | \
+				 _PAGE_CACHABLE | _PAGE_FLAGS_HARD | \
+				 _PAGE_EXT(_PAGE_EXT_KERN_WRITE | \
+					   _PAGE_EXT_USER_WRITE))
+
+#define PAGE_RWX	__pgprot(_PAGE_PRESENT | _PAGE_ACCESSED | \
+				 _PAGE_CACHABLE | _PAGE_FLAGS_HARD | \
+				 _PAGE_EXT(_PAGE_EXT_KERN_WRITE | \
+					   _PAGE_EXT_KERN_READ  | \
+					   _PAGE_EXT_KERN_EXEC  | \
+					   _PAGE_EXT_USER_WRITE | \
+					   _PAGE_EXT_USER_READ  | \
+					   _PAGE_EXT_USER_EXEC))
+
+#define PAGE_KERNEL	__pgprot(_PAGE_PRESENT | _PAGE_CACHABLE | \
+				 _PAGE_DIRTY | _PAGE_ACCESSED | \
+				 _PAGE_HW_SHARED | _PAGE_FLAGS_HARD | \
+				 _PAGE_EXT(_PAGE_EXT_KERN_READ | \
+					   _PAGE_EXT_KERN_WRITE | \
+					   _PAGE_EXT_KERN_EXEC))
+
+#define PAGE_KERNEL_NOCACHE \
+			__pgprot(_PAGE_PRESENT | _PAGE_DIRTY | \
+				 _PAGE_ACCESSED | _PAGE_HW_SHARED | \
+				 _PAGE_FLAGS_HARD | \
+				 _PAGE_EXT(_PAGE_EXT_KERN_READ | \
+					   _PAGE_EXT_KERN_WRITE | \
+					   _PAGE_EXT_KERN_EXEC))
+
+#define PAGE_KERNEL_RO	__pgprot(_PAGE_PRESENT | _PAGE_CACHABLE | \
+				 _PAGE_DIRTY | _PAGE_ACCESSED | \
+				 _PAGE_HW_SHARED | _PAGE_FLAGS_HARD | \
+				 _PAGE_EXT(_PAGE_EXT_KERN_READ | \
+					   _PAGE_EXT_KERN_EXEC))
+
+#define PAGE_KERNEL_PCC(slot, type) \
+			__pgprot(0)
+
+#elif defined(CONFIG_MMU) /* SH-X TLB */
+#define PAGE_NONE	__pgprot(_PAGE_PROTNONE | _PAGE_CACHABLE | \
+				 _PAGE_ACCESSED | _PAGE_FLAGS_HARD)
+
+#define PAGE_SHARED	__pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | \
+				 _PAGE_CACHABLE | _PAGE_ACCESSED | \
+				 _PAGE_FLAGS_HARD)
+
+#define PAGE_COPY	__pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_CACHABLE | \
+				 _PAGE_ACCESSED | _PAGE_FLAGS_HARD)
+
+#define PAGE_READONLY	__pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_CACHABLE | \
+				 _PAGE_ACCESSED | _PAGE_FLAGS_HARD)
+
+#define PAGE_EXECREAD	PAGE_READONLY
+#define PAGE_RWX	PAGE_SHARED
+#define PAGE_WRITEONLY	PAGE_SHARED
+
+#define PAGE_KERNEL	__pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_CACHABLE | \
+				 _PAGE_DIRTY | _PAGE_ACCESSED | \
+				 _PAGE_HW_SHARED | _PAGE_FLAGS_HARD)
+
+#define PAGE_KERNEL_NOCACHE \
+			__pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | \
+				 _PAGE_ACCESSED | _PAGE_HW_SHARED | \
+				 _PAGE_FLAGS_HARD)
+
+#define PAGE_KERNEL_RO	__pgprot(_PAGE_PRESENT | _PAGE_CACHABLE | \
+				 _PAGE_DIRTY | _PAGE_ACCESSED | \
+				 _PAGE_HW_SHARED | _PAGE_FLAGS_HARD)
+
+#define PAGE_KERNEL_PCC(slot, type) \
+			__pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | \
+				 _PAGE_ACCESSED | _PAGE_FLAGS_HARD | \
+				 (slot ? _PAGE_PCC_AREA5 : _PAGE_PCC_AREA6) | \
+				 (type))
+#else /* no mmu */
+#define PAGE_NONE		__pgprot(0)
+#define PAGE_SHARED		__pgprot(0)
+#define PAGE_COPY		__pgprot(0)
+#define PAGE_EXECREAD		__pgprot(0)
+#define PAGE_RWX		__pgprot(0)
+#define PAGE_READONLY		__pgprot(0)
+#define PAGE_WRITEONLY		__pgprot(0)
+#define PAGE_KERNEL		__pgprot(0)
+#define PAGE_KERNEL_NOCACHE	__pgprot(0)
+#define PAGE_KERNEL_RO		__pgprot(0)
+
+#define PAGE_KERNEL_PCC(slot, type) \
+				__pgprot(0)
+#endif
+
+#endif /* __ASSEMBLY__ */
+
+#ifndef __ASSEMBLY__
+
+/*
+ * Certain architectures need to do special things when PTEs
+ * within a page table are directly modified.  Thus, the following
+ * hook is made available.
+ */
+#ifdef CONFIG_X2TLB
+static inline void set_pte(pte_t *ptep, pte_t pte)
+{
+	ptep->pte_high = pte.pte_high;
+	smp_wmb();
+	ptep->pte_low = pte.pte_low;
+}
+#else
+#define set_pte(pteptr, pteval) (*(pteptr) = pteval)
+#endif
+
+#define set_pte_at(mm,addr,ptep,pteval) set_pte(ptep,pteval)
+
+/*
+ * (pmds are folded into pgds so this doesn't get actually called,
+ * but the define is needed for a generic inline function.)
+ */
+#define set_pmd(pmdptr, pmdval) (*(pmdptr) = pmdval)
+
+#define pfn_pte(pfn, prot) \
+	__pte(((unsigned long long)(pfn) << PAGE_SHIFT) | pgprot_val(prot))
+#define pfn_pmd(pfn, prot) \
+	__pmd(((unsigned long long)(pfn) << PAGE_SHIFT) | pgprot_val(prot))
+
+#define pte_none(x)		(!pte_val(x))
+#define pte_present(x)		((x).pte_low & (_PAGE_PRESENT | _PAGE_PROTNONE))
+
+#define pte_clear(mm,addr,xp) do { set_pte_at(mm, addr, xp, __pte(0)); } while (0)
+
+#define pmd_none(x)	(!pmd_val(x))
+#define pmd_present(x)	(pmd_val(x))
+#define pmd_clear(xp)	do { set_pmd(xp, __pmd(0)); } while (0)
+#define	pmd_bad(x)	(pmd_val(x) & ~PAGE_MASK)
+
+#define pages_to_mb(x)	((x) >> (20-PAGE_SHIFT))
+#define pte_page(x)	pfn_to_page(pte_pfn(x))
+
+/*
+ * The following only work if pte_present() is true.
+ * Undefined behaviour if not..
+ */
+#define pte_not_present(pte)	(!((pte).pte_low & _PAGE_PRESENT))
+#define pte_dirty(pte)		((pte).pte_low & _PAGE_DIRTY)
+#define pte_young(pte)		((pte).pte_low & _PAGE_ACCESSED)
+#define pte_special(pte)	((pte).pte_low & _PAGE_SPECIAL)
+
+#ifdef CONFIG_X2TLB
+#define pte_write(pte) \
+	((pte).pte_high & (_PAGE_EXT_USER_WRITE | _PAGE_EXT_KERN_WRITE))
+#else
+#define pte_write(pte)		((pte).pte_low & _PAGE_RW)
+#endif
+
+#define PTE_BIT_FUNC(h,fn,op) \
+static inline pte_t pte_##fn(pte_t pte) { pte.pte_##h op; return pte; }
+
+#ifdef CONFIG_X2TLB
+/*
+ * We cheat a bit in the SH-X2 TLB case. As the permission bits are
+ * individually toggled (and user permissions are entirely decoupled from
+ * kernel permissions), we attempt to couple them a bit more sanely here.
+ */
+PTE_BIT_FUNC(high, wrprotect, &= ~(_PAGE_EXT_USER_WRITE | _PAGE_EXT_KERN_WRITE));
+PTE_BIT_FUNC(high, mkwrite, |= _PAGE_EXT_USER_WRITE | _PAGE_EXT_KERN_WRITE);
+PTE_BIT_FUNC(high, mkhuge, |= _PAGE_SZHUGE);
+#else
+PTE_BIT_FUNC(low, wrprotect, &= ~_PAGE_RW);
+PTE_BIT_FUNC(low, mkwrite, |= _PAGE_RW);
+PTE_BIT_FUNC(low, mkhuge, |= _PAGE_SZHUGE);
+#endif
+
+PTE_BIT_FUNC(low, mkclean, &= ~_PAGE_DIRTY);
+PTE_BIT_FUNC(low, mkdirty, |= _PAGE_DIRTY);
+PTE_BIT_FUNC(low, mkold, &= ~_PAGE_ACCESSED);
+PTE_BIT_FUNC(low, mkyoung, |= _PAGE_ACCESSED);
+PTE_BIT_FUNC(low, mkspecial, |= _PAGE_SPECIAL);
+
+/*
+ * Macro and implementation to make a page protection as uncachable.
+ */
+#define pgprot_writecombine(prot) \
+	__pgprot(pgprot_val(prot) & ~_PAGE_CACHABLE)
+
+#define pgprot_noncached	 pgprot_writecombine
+
+/*
+ * Conversion functions: convert a page and protection to a page entry,
+ * and a page entry and page directory to the page they refer to.
+ *
+ * extern pte_t mk_pte(struct page *page, pgprot_t pgprot)
+ */
+#define mk_pte(page, pgprot)	pfn_pte(page_to_pfn(page), (pgprot))
+
+static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
+{
+	pte.pte_low &= _PAGE_CHG_MASK;
+	pte.pte_low |= pgprot_val(newprot);
+
+#ifdef CONFIG_X2TLB
+	pte.pte_high |= pgprot_val(newprot) >> 32;
+#endif
+
+	return pte;
+}
+
+#define pmd_page_vaddr(pmd)	((unsigned long)pmd_val(pmd))
+#define pmd_page(pmd)		(virt_to_page(pmd_val(pmd)))
+
+/* to find an entry in a page-table-directory. */
+#define pgd_index(address)	(((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD-1))
+#define pgd_offset(mm, address)	((mm)->pgd + pgd_index(address))
+#define __pgd_offset(address)	pgd_index(address)
+
+/* to find an entry in a kernel page-table-directory */
+#define pgd_offset_k(address)	pgd_offset(&init_mm, address)
+
+#define __pud_offset(address)	(((address) >> PUD_SHIFT) & (PTRS_PER_PUD-1))
+#define __pmd_offset(address)	(((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1))
+
+/* Find an entry in the third-level page table.. */
+#define pte_index(address)	((address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
+#define __pte_offset(address)	pte_index(address)
+
+#define pte_offset_kernel(dir, address) \
+	((pte_t *) pmd_page_vaddr(*(dir)) + pte_index(address))
+#define pte_offset_map(dir, address)		pte_offset_kernel(dir, address)
+#define pte_unmap(pte)		do { } while (0)
+
+#ifdef CONFIG_X2TLB
+#define pte_ERROR(e) \
+	printk("%s:%d: bad pte %p(%08lx%08lx).\n", __FILE__, __LINE__, \
+	       &(e), (e).pte_high, (e).pte_low)
+#define pgd_ERROR(e) \
+	printk("%s:%d: bad pgd %016llx.\n", __FILE__, __LINE__, pgd_val(e))
+#else
+#define pte_ERROR(e) \
+	printk("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, pte_val(e))
+#define pgd_ERROR(e) \
+	printk("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e))
+#endif
+
+/*
+ * Encode and de-code a swap entry
+ *
+ * Constraints:
+ *	_PAGE_PRESENT at bit 8
+ *	_PAGE_PROTNONE at bit 9
+ *
+ * For the normal case, we encode the swap type into bits 0:7 and the
+ * swap offset into bits 10:30. For the 64-bit PTE case, we keep the
+ * preserved bits in the low 32-bits and use the upper 32 as the swap
+ * offset (along with a 5-bit type), following the same approach as x86
+ * PAE. This keeps the logic quite simple.
+ *
+ * As is evident by the Alpha code, if we ever get a 64-bit unsigned
+ * long (swp_entry_t) to match up with the 64-bit PTEs, this all becomes
+ * much cleaner..
+ *
+ * NOTE: We should set ZEROs at the position of _PAGE_PRESENT
+ *       and _PAGE_PROTNONE bits
+ */
+#ifdef CONFIG_X2TLB
+#define __swp_type(x)			((x).val & 0x1f)
+#define __swp_offset(x)			((x).val >> 5)
+#define __swp_entry(type, offset)	((swp_entry_t){ (type) | (offset) << 5})
+#define __pte_to_swp_entry(pte)		((swp_entry_t){ (pte).pte_high })
+#define __swp_entry_to_pte(x)		((pte_t){ 0, (x).val })
+
+#else
+#define __swp_type(x)			((x).val & 0xff)
+#define __swp_offset(x)			((x).val >> 10)
+#define __swp_entry(type, offset)	((swp_entry_t){(type) | (offset) <<10})
+
+#define __pte_to_swp_entry(pte)		((swp_entry_t) { pte_val(pte) >> 1 })
+#define __swp_entry_to_pte(x)		((pte_t) { (x).val << 1 })
+#endif
+
+#endif /* __ASSEMBLY__ */
+#endif /* __ASM_SH_PGTABLE_32_H */
diff --git a/arch/sh/include/asm/pgtable_64.h b/arch/sh/include/asm/pgtable_64.h
new file mode 100644
index 000000000..07424968d
--- /dev/null
+++ b/arch/sh/include/asm/pgtable_64.h
@@ -0,0 +1,310 @@
+#ifndef __ASM_SH_PGTABLE_64_H
+#define __ASM_SH_PGTABLE_64_H
+
+/*
+ * include/asm-sh/pgtable_64.h
+ *
+ * This file contains the functions and defines necessary to modify and use
+ * the SuperH page table tree.
+ *
+ * Copyright (C) 2000, 2001  Paolo Alberelli
+ * Copyright (C) 2003, 2004  Paul Mundt
+ * Copyright (C) 2003, 2004  Richard Curnow
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+#include <linux/threads.h>
+#include <asm/processor.h>
+#include <asm/page.h>
+
+/*
+ * Error outputs.
+ */
+#define pte_ERROR(e) \
+	printk("%s:%d: bad pte %016Lx.\n", __FILE__, __LINE__, pte_val(e))
+#define pgd_ERROR(e) \
+	printk("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e))
+
+/*
+ * Table setting routines. Used within arch/mm only.
+ */
+#define set_pmd(pmdptr, pmdval) (*(pmdptr) = pmdval)
+
+static __inline__ void set_pte(pte_t *pteptr, pte_t pteval)
+{
+	unsigned long long x = ((unsigned long long) pteval.pte_low);
+	unsigned long long *xp = (unsigned long long *) pteptr;
+	/*
+	 * Sign-extend based on NPHYS.
+	 */
+	*(xp) = (x & NPHYS_SIGN) ? (x | NPHYS_MASK) : x;
+}
+#define set_pte_at(mm,addr,ptep,pteval) set_pte(ptep,pteval)
+
+/*
+ * PGD defines. Top level.
+ */
+
+/* To find an entry in a generic PGD. */
+#define pgd_index(address) (((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD-1))
+#define __pgd_offset(address) pgd_index(address)
+#define pgd_offset(mm, address) ((mm)->pgd+pgd_index(address))
+
+/* To find an entry in a kernel PGD. */
+#define pgd_offset_k(address) pgd_offset(&init_mm, address)
+
+#define __pud_offset(address)	(((address) >> PUD_SHIFT) & (PTRS_PER_PUD-1))
+#define __pmd_offset(address)	(((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1))
+
+/*
+ * PMD level access routines. Same notes as above.
+ */
+#define _PMD_EMPTY		0x0
+/* Either the PMD is empty or present, it's not paged out */
+#define pmd_present(pmd_entry)	(pmd_val(pmd_entry) & _PAGE_PRESENT)
+#define pmd_clear(pmd_entry_p)	(set_pmd((pmd_entry_p), __pmd(_PMD_EMPTY)))
+#define pmd_none(pmd_entry)	(pmd_val((pmd_entry)) == _PMD_EMPTY)
+#define pmd_bad(pmd_entry)	((pmd_val(pmd_entry) & (~PAGE_MASK & ~_PAGE_USER)) != _KERNPG_TABLE)
+
+#define pmd_page_vaddr(pmd_entry) \
+	((unsigned long) __va(pmd_val(pmd_entry) & PAGE_MASK))
+
+#define pmd_page(pmd) \
+	(virt_to_page(pmd_val(pmd)))
+
+/* PMD to PTE dereferencing */
+#define pte_index(address) \
+		((address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
+
+#define __pte_offset(address)	pte_index(address)
+
+#define pte_offset_kernel(dir, addr) \
+		((pte_t *) ((pmd_val(*(dir))) & PAGE_MASK) + pte_index((addr)))
+
+#define pte_offset_map(dir,addr)	pte_offset_kernel(dir, addr)
+#define pte_unmap(pte)		do { } while (0)
+
+#ifndef __ASSEMBLY__
+/*
+ * PTEL coherent flags.
+ * See Chapter 17 ST50 CPU Core Volume 1, Architecture.
+ */
+/* The bits that are required in the SH-5 TLB are placed in the h/w-defined
+   positions, to avoid expensive bit shuffling on every refill.  The remaining
+   bits are used for s/w purposes and masked out on each refill.
+
+   Note, the PTE slots are used to hold data of type swp_entry_t when a page is
+   swapped out.  Only the _PAGE_PRESENT flag is significant when the page is
+   swapped out, and it must be placed so that it doesn't overlap either the
+   type or offset fields of swp_entry_t.  For x86, offset is at [31:8] and type
+   at [6:1], with _PAGE_PRESENT at bit 0 for both pte_t and swp_entry_t.  This
+   scheme doesn't map to SH-5 because bit [0] controls cacheability.  So bit
+   [2] is used for _PAGE_PRESENT and the type field of swp_entry_t is split
+   into 2 pieces.  That is handled by SWP_ENTRY and SWP_TYPE below. */
+#define _PAGE_WT	0x001  /* CB0: if cacheable, 1->write-thru, 0->write-back */
+#define _PAGE_DEVICE	0x001  /* CB0: if uncacheable, 1->device (i.e. no write-combining or reordering at bus level) */
+#define _PAGE_CACHABLE	0x002  /* CB1: uncachable/cachable */
+#define _PAGE_PRESENT	0x004  /* software: page referenced */
+#define _PAGE_SIZE0	0x008  /* SZ0-bit : size of page */
+#define _PAGE_SIZE1	0x010  /* SZ1-bit : size of page */
+#define _PAGE_SHARED	0x020  /* software: reflects PTEH's SH */
+#define _PAGE_READ	0x040  /* PR0-bit : read access allowed */
+#define _PAGE_EXECUTE	0x080  /* PR1-bit : execute access allowed */
+#define _PAGE_WRITE	0x100  /* PR2-bit : write access allowed */
+#define _PAGE_USER	0x200  /* PR3-bit : user space access allowed */
+#define _PAGE_DIRTY	0x400  /* software: page accessed in write */
+#define _PAGE_ACCESSED	0x800  /* software: page referenced */
+
+/* Wrapper for extended mode pgprot twiddling */
+#define _PAGE_EXT(x)		((unsigned long long)(x) << 32)
+
+/*
+ * We can use the sign-extended bits in the PTEL to get 32 bits of
+ * software flags. This works for now because no implementations uses
+ * anything above the PPN field.
+ */
+#define _PAGE_WIRED	_PAGE_EXT(0x001) /* software: wire the tlb entry */
+#define _PAGE_SPECIAL	_PAGE_EXT(0x002)
+
+#define _PAGE_CLEAR_FLAGS	(_PAGE_PRESENT | _PAGE_SHARED | \
+				 _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_WIRED)
+
+/* Mask which drops software flags */
+#define _PAGE_FLAGS_HARDWARE_MASK	(NEFF_MASK & ~(_PAGE_CLEAR_FLAGS))
+
+/*
+ * HugeTLB support
+ */
+#if defined(CONFIG_HUGETLB_PAGE_SIZE_64K)
+#define _PAGE_SZHUGE	(_PAGE_SIZE0)
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_1MB)
+#define _PAGE_SZHUGE	(_PAGE_SIZE1)
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_512MB)
+#define _PAGE_SZHUGE	(_PAGE_SIZE0 | _PAGE_SIZE1)
+#endif
+
+/*
+ * Stub out _PAGE_SZHUGE if we don't have a good definition for it,
+ * to make pte_mkhuge() happy.
+ */
+#ifndef _PAGE_SZHUGE
+# define _PAGE_SZHUGE	(0)
+#endif
+
+/*
+ * Default flags for a Kernel page.
+ * This is fundametally also SHARED because the main use of this define
+ * (other than for PGD/PMD entries) is for the VMALLOC pool which is
+ * contextless.
+ *
+ * _PAGE_EXECUTE is required for modules
+ *
+ */
+#define _KERNPG_TABLE	(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \
+			 _PAGE_EXECUTE | \
+			 _PAGE_CACHABLE | _PAGE_ACCESSED | _PAGE_DIRTY | \
+			 _PAGE_SHARED)
+
+/* Default flags for a User page */
+#define _PAGE_TABLE	(_KERNPG_TABLE | _PAGE_USER)
+
+#define _PAGE_CHG_MASK	(PTE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY | \
+			 _PAGE_SPECIAL)
+
+/*
+ * We have full permissions (Read/Write/Execute/Shared).
+ */
+#define _PAGE_COMMON	(_PAGE_PRESENT | _PAGE_USER | \
+			 _PAGE_CACHABLE | _PAGE_ACCESSED)
+
+#define PAGE_NONE	__pgprot(_PAGE_CACHABLE | _PAGE_ACCESSED)
+#define PAGE_SHARED	__pgprot(_PAGE_COMMON | _PAGE_READ | _PAGE_WRITE | \
+				 _PAGE_SHARED)
+#define PAGE_EXECREAD	__pgprot(_PAGE_COMMON | _PAGE_READ | _PAGE_EXECUTE)
+
+/*
+ * We need to include PAGE_EXECUTE in PAGE_COPY because it is the default
+ * protection mode for the stack.
+ */
+#define PAGE_COPY	PAGE_EXECREAD
+
+#define PAGE_READONLY	__pgprot(_PAGE_COMMON | _PAGE_READ)
+#define PAGE_WRITEONLY	__pgprot(_PAGE_COMMON | _PAGE_WRITE)
+#define PAGE_RWX	__pgprot(_PAGE_COMMON | _PAGE_READ | \
+				 _PAGE_WRITE | _PAGE_EXECUTE)
+#define PAGE_KERNEL	__pgprot(_KERNPG_TABLE)
+
+#define PAGE_KERNEL_NOCACHE \
+			__pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \
+				 _PAGE_EXECUTE | _PAGE_ACCESSED | \
+				 _PAGE_DIRTY | _PAGE_SHARED)
+
+/* Make it a device mapping for maximum safety (e.g. for mapping device
+   registers into user-space via /dev/map).  */
+#define pgprot_noncached(x) __pgprot(((x).pgprot & ~(_PAGE_CACHABLE)) | _PAGE_DEVICE)
+#define pgprot_writecombine(prot) __pgprot(pgprot_val(prot) & ~_PAGE_CACHABLE)
+
+/*
+ * PTE level access routines.
+ *
+ * Note1:
+ * It's the tree walk leaf. This is physical address to be stored.
+ *
+ * Note 2:
+ * Regarding the choice of _PTE_EMPTY:
+
+   We must choose a bit pattern that cannot be valid, whether or not the page
+   is present.  bit[2]==1 => present, bit[2]==0 => swapped out.  If swapped
+   out, bits [31:8], [6:3], [1:0] are under swapper control, so only bit[7] is
+   left for us to select.  If we force bit[7]==0 when swapped out, we could use
+   the combination bit[7,2]=2'b10 to indicate an empty PTE.  Alternatively, if
+   we force bit[7]==1 when swapped out, we can use all zeroes to indicate
+   empty.  This is convenient, because the page tables get cleared to zero
+   when they are allocated.
+
+ */
+#define _PTE_EMPTY	0x0
+#define pte_present(x)	(pte_val(x) & _PAGE_PRESENT)
+#define pte_clear(mm,addr,xp)	(set_pte_at(mm, addr, xp, __pte(_PTE_EMPTY)))
+#define pte_none(x)	(pte_val(x) == _PTE_EMPTY)
+
+/*
+ * Some definitions to translate between mem_map, PTEs, and page
+ * addresses:
+ */
+
+/*
+ * Given a PTE, return the index of the mem_map[] entry corresponding
+ * to the page frame the PTE. Get the absolute physical address, make
+ * a relative physical address and translate it to an index.
+ */
+#define pte_pagenr(x)		(((unsigned long) (pte_val(x)) - \
+				 __MEMORY_START) >> PAGE_SHIFT)
+
+/*
+ * Given a PTE, return the "struct page *".
+ */
+#define pte_page(x)		(mem_map + pte_pagenr(x))
+
+/*
+ * Return number of (down rounded) MB corresponding to x pages.
+ */
+#define pages_to_mb(x) ((x) >> (20-PAGE_SHIFT))
+
+
+/*
+ * The following have defined behavior only work if pte_present() is true.
+ */
+static inline int pte_dirty(pte_t pte)  { return pte_val(pte) & _PAGE_DIRTY; }
+static inline int pte_young(pte_t pte)  { return pte_val(pte) & _PAGE_ACCESSED; }
+static inline int pte_write(pte_t pte)  { return pte_val(pte) & _PAGE_WRITE; }
+static inline int pte_special(pte_t pte){ return pte_val(pte) & _PAGE_SPECIAL; }
+
+static inline pte_t pte_wrprotect(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_WRITE)); return pte; }
+static inline pte_t pte_mkclean(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_DIRTY)); return pte; }
+static inline pte_t pte_mkold(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_ACCESSED)); return pte; }
+static inline pte_t pte_mkwrite(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) | _PAGE_WRITE)); return pte; }
+static inline pte_t pte_mkdirty(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) | _PAGE_DIRTY)); return pte; }
+static inline pte_t pte_mkyoung(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) | _PAGE_ACCESSED)); return pte; }
+static inline pte_t pte_mkhuge(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) | _PAGE_SZHUGE)); return pte; }
+static inline pte_t pte_mkspecial(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) | _PAGE_SPECIAL)); return pte; }
+
+/*
+ * Conversion functions: convert a page and protection to a page entry.
+ *
+ * extern pte_t mk_pte(struct page *page, pgprot_t pgprot)
+ */
+#define mk_pte(page,pgprot)							\
+({										\
+	pte_t __pte;								\
+										\
+	set_pte(&__pte, __pte((((page)-mem_map) << PAGE_SHIFT) | 		\
+		__MEMORY_START | pgprot_val((pgprot))));			\
+	__pte;									\
+})
+
+/*
+ * This takes a (absolute) physical page address that is used
+ * by the remapping functions
+ */
+#define mk_pte_phys(physpage, pgprot) \
+({ pte_t __pte; set_pte(&__pte, __pte(physpage | pgprot_val(pgprot))); __pte; })
+
+static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
+{ set_pte(&pte, __pte((pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot))); return pte; }
+
+/* Encode and decode a swap entry */
+#define __swp_type(x)			(((x).val & 3) + (((x).val >> 1) & 0x3c))
+#define __swp_offset(x)			((x).val >> 8)
+#define __swp_entry(type, offset)	((swp_entry_t) { ((offset << 8) + ((type & 0x3c) << 1) + (type & 3)) })
+#define __pte_to_swp_entry(pte)		((swp_entry_t) { pte_val(pte) })
+#define __swp_entry_to_pte(x)		((pte_t) { (x).val })
+
+#endif /* !__ASSEMBLY__ */
+
+#define pfn_pte(pfn, prot)	__pte(((pfn) << PAGE_SHIFT) | pgprot_val(prot))
+#define pfn_pmd(pfn, prot)	__pmd(((pfn) << PAGE_SHIFT) | pgprot_val(prot))
+
+#endif /* __ASM_SH_PGTABLE_64_H */
diff --git a/arch/sh/include/asm/posix_types.h b/arch/sh/include/asm/posix_types.h
new file mode 100644
index 000000000..1aa781079
--- /dev/null
+++ b/arch/sh/include/asm/posix_types.h
@@ -0,0 +1,5 @@
+# ifdef CONFIG_SUPERH32
+#  include <asm/posix_types_32.h>
+# else
+#  include <asm/posix_types_64.h>
+# endif
diff --git a/arch/sh/include/asm/processor.h b/arch/sh/include/asm/processor.h
new file mode 100644
index 000000000..150689764
--- /dev/null
+++ b/arch/sh/include/asm/processor.h
@@ -0,0 +1,184 @@
+#ifndef __ASM_SH_PROCESSOR_H
+#define __ASM_SH_PROCESSOR_H
+
+#include <asm/cpu-features.h>
+#include <asm/segment.h>
+#include <asm/cache.h>
+
+#ifndef __ASSEMBLY__
+/*
+ *  CPU type and hardware bug flags. Kept separately for each CPU.
+ *
+ *  Each one of these also needs a CONFIG_CPU_SUBTYPE_xxx entry
+ *  in arch/sh/mm/Kconfig, as well as an entry in arch/sh/kernel/setup.c
+ *  for parsing the subtype in get_cpu_subtype().
+ */
+enum cpu_type {
+	/* SH-2 types */
+	CPU_SH7619,
+
+	/* SH-2A types */
+	CPU_SH7201, CPU_SH7203, CPU_SH7206, CPU_SH7263, CPU_SH7264, CPU_SH7269,
+	CPU_MXG,
+
+	/* SH-3 types */
+	CPU_SH7705, CPU_SH7706, CPU_SH7707,
+	CPU_SH7708, CPU_SH7708S, CPU_SH7708R,
+	CPU_SH7709, CPU_SH7709A, CPU_SH7710, CPU_SH7712,
+	CPU_SH7720, CPU_SH7721, CPU_SH7729,
+
+	/* SH-4 types */
+	CPU_SH7750, CPU_SH7750S, CPU_SH7750R, CPU_SH7751, CPU_SH7751R,
+	CPU_SH7760, CPU_SH4_202, CPU_SH4_501,
+
+	/* SH-4A types */
+	CPU_SH7763, CPU_SH7770, CPU_SH7780, CPU_SH7781, CPU_SH7785, CPU_SH7786,
+	CPU_SH7723, CPU_SH7724, CPU_SH7757, CPU_SH7734, CPU_SHX3,
+
+	/* SH4AL-DSP types */
+	CPU_SH7343, CPU_SH7722, CPU_SH7366, CPU_SH7372,
+
+	/* SH-5 types */
+        CPU_SH5_101, CPU_SH5_103,
+
+	/* Unknown subtype */
+	CPU_SH_NONE
+};
+
+enum cpu_family {
+	CPU_FAMILY_SH2,
+	CPU_FAMILY_SH2A,
+	CPU_FAMILY_SH3,
+	CPU_FAMILY_SH4,
+	CPU_FAMILY_SH4A,
+	CPU_FAMILY_SH4AL_DSP,
+	CPU_FAMILY_SH5,
+	CPU_FAMILY_UNKNOWN,
+};
+
+/*
+ * TLB information structure
+ *
+ * Defined for both I and D tlb, per-processor.
+ */
+struct tlb_info {
+	unsigned long long next;
+	unsigned long long first;
+	unsigned long long last;
+
+	unsigned int entries;
+	unsigned int step;
+
+	unsigned long flags;
+};
+
+struct sh_cpuinfo {
+	unsigned int type, family;
+	int cut_major, cut_minor;
+	unsigned long loops_per_jiffy;
+	unsigned long asid_cache;
+
+	struct cache_info icache;	/* Primary I-cache */
+	struct cache_info dcache;	/* Primary D-cache */
+	struct cache_info scache;	/* Secondary cache */
+
+	/* TLB info */
+	struct tlb_info itlb;
+	struct tlb_info dtlb;
+
+	unsigned int phys_bits;
+	unsigned long flags;
+} __attribute__ ((aligned(L1_CACHE_BYTES)));
+
+extern struct sh_cpuinfo cpu_data[];
+#define boot_cpu_data cpu_data[0]
+#define current_cpu_data cpu_data[smp_processor_id()]
+#define raw_current_cpu_data cpu_data[raw_smp_processor_id()]
+
+#define cpu_sleep()	__asm__ __volatile__ ("sleep" : : : "memory")
+#define cpu_relax()	barrier()
+#define cpu_relax_lowlatency() cpu_relax()
+
+void default_idle(void);
+void stop_this_cpu(void *);
+
+/* Forward decl */
+struct seq_operations;
+struct task_struct;
+
+extern struct pt_regs fake_swapper_regs;
+
+extern void cpu_init(void);
+extern void cpu_probe(void);
+
+/* arch/sh/kernel/process.c */
+extern unsigned int xstate_size;
+extern void free_thread_xstate(struct task_struct *);
+extern struct kmem_cache *task_xstate_cachep;
+
+/* arch/sh/mm/alignment.c */
+extern int get_unalign_ctl(struct task_struct *, unsigned long addr);
+extern int set_unalign_ctl(struct task_struct *, unsigned int val);
+
+#define GET_UNALIGN_CTL(tsk, addr)	get_unalign_ctl((tsk), (addr))
+#define SET_UNALIGN_CTL(tsk, val)	set_unalign_ctl((tsk), (val))
+
+/* arch/sh/mm/init.c */
+extern unsigned int mem_init_done;
+
+/* arch/sh/kernel/setup.c */
+const char *get_cpu_subtype(struct sh_cpuinfo *c);
+extern const struct seq_operations cpuinfo_op;
+
+/* thread_struct flags */
+#define SH_THREAD_UAC_NOPRINT	(1 << 0)
+#define SH_THREAD_UAC_SIGBUS	(1 << 1)
+#define SH_THREAD_UAC_MASK	(SH_THREAD_UAC_NOPRINT | SH_THREAD_UAC_SIGBUS)
+
+/* processor boot mode configuration */
+#define MODE_PIN0 (1 << 0)
+#define MODE_PIN1 (1 << 1)
+#define MODE_PIN2 (1 << 2)
+#define MODE_PIN3 (1 << 3)
+#define MODE_PIN4 (1 << 4)
+#define MODE_PIN5 (1 << 5)
+#define MODE_PIN6 (1 << 6)
+#define MODE_PIN7 (1 << 7)
+#define MODE_PIN8 (1 << 8)
+#define MODE_PIN9 (1 << 9)
+#define MODE_PIN10 (1 << 10)
+#define MODE_PIN11 (1 << 11)
+#define MODE_PIN12 (1 << 12)
+#define MODE_PIN13 (1 << 13)
+#define MODE_PIN14 (1 << 14)
+#define MODE_PIN15 (1 << 15)
+
+int generic_mode_pins(void);
+int test_mode_pin(int pin);
+
+#ifdef CONFIG_VSYSCALL
+int vsyscall_init(void);
+#else
+#define vsyscall_init() do { } while (0)
+#endif
+
+/*
+ * SH-2A has both 16 and 32-bit opcodes, do lame encoding checks.
+ */
+#ifdef CONFIG_CPU_SH2A
+extern unsigned int instruction_size(unsigned int insn);
+#elif defined(CONFIG_SUPERH32)
+#define instruction_size(insn)	(2)
+#else
+#define instruction_size(insn)	(4)
+#endif
+
+#endif /* __ASSEMBLY__ */
+
+#ifdef CONFIG_SUPERH32
+# include <asm/processor_32.h>
+#else
+# include <asm/processor_64.h>
+#endif
+
+#endif /* __ASM_SH_PROCESSOR_H */
diff --git a/arch/sh/include/asm/processor_32.h b/arch/sh/include/asm/processor_32.h
new file mode 100644
index 000000000..18e0377f7
--- /dev/null
+++ b/arch/sh/include/asm/processor_32.h
@@ -0,0 +1,216 @@
+/*
+ * include/asm-sh/processor.h
+ *
+ * Copyright (C) 1999, 2000  Niibe Yutaka
+ * Copyright (C) 2002, 2003  Paul Mundt
+ */
+
+#ifndef __ASM_SH_PROCESSOR_32_H
+#define __ASM_SH_PROCESSOR_32_H
+#ifdef __KERNEL__
+
+#include <linux/compiler.h>
+#include <linux/linkage.h>
+#include <asm/page.h>
+#include <asm/types.h>
+#include <asm/hw_breakpoint.h>
+
+/*
+ * Default implementation of macro that returns current
+ * instruction pointer ("program counter").
+ */
+#define current_text_addr() ({ void *pc; __asm__("mova	1f, %0\n.align 2\n1:":"=z" (pc)); pc; })
+
+/* Core Processor Version Register */
+#define CCN_PVR		0xff000030
+#define CCN_CVR		0xff000040
+#define CCN_PRR		0xff000044
+
+/*
+ * User space process size: 2GB.
+ *
+ * Since SH7709 and SH7750 have "area 7", we can't use 0x7c000000--0x7fffffff
+ */
+#define TASK_SIZE	0x7c000000UL
+
+#define STACK_TOP	TASK_SIZE
+#define STACK_TOP_MAX	STACK_TOP
+
+/* This decides where the kernel will search for a free chunk of vm
+ * space during mmap's.
+ */
+#define TASK_UNMAPPED_BASE	PAGE_ALIGN(TASK_SIZE / 3)
+
+/*
+ * Bit of SR register
+ *
+ * FD-bit:
+ *     When it's set, it means the processor doesn't have right to use FPU,
+ *     and it results exception when the floating operation is executed.
+ *
+ * IMASK-bit:
+ *     Interrupt level mask
+ */
+#define SR_DSP		0x00001000
+#define SR_IMASK	0x000000f0
+#define SR_FD		0x00008000
+#define SR_MD		0x40000000
+
+/*
+ * DSP structure and data
+ */
+struct sh_dsp_struct {
+	unsigned long dsp_regs[14];
+	long status;
+};
+
+/*
+ * FPU structure and data
+ */
+
+struct sh_fpu_hard_struct {
+	unsigned long fp_regs[16];
+	unsigned long xfp_regs[16];
+	unsigned long fpscr;
+	unsigned long fpul;
+
+	long status; /* software status information */
+};
+
+/* Dummy fpu emulator  */
+struct sh_fpu_soft_struct {
+	unsigned long fp_regs[16];
+	unsigned long xfp_regs[16];
+	unsigned long fpscr;
+	unsigned long fpul;
+
+	unsigned char lookahead;
+	unsigned long entry_pc;
+};
+
+union thread_xstate {
+	struct sh_fpu_hard_struct hardfpu;
+	struct sh_fpu_soft_struct softfpu;
+};
+
+struct thread_struct {
+	/* Saved registers when thread is descheduled */
+	unsigned long sp;
+	unsigned long pc;
+
+	/* Various thread flags, see SH_THREAD_xxx */
+	unsigned long flags;
+
+	/* Save middle states of ptrace breakpoints */
+	struct perf_event *ptrace_bps[HBP_NUM];
+
+#ifdef CONFIG_SH_DSP
+	/* Dsp status information */
+	struct sh_dsp_struct dsp_status;
+#endif
+
+	/* Extended processor state */
+	union thread_xstate *xstate;
+
+	/*
+	 * fpu_counter contains the number of consecutive context switches
+	 * that the FPU is used. If this is over a threshold, the lazy fpu
+	 * saving becomes unlazy to save the trap. This is an unsigned char
+	 * so that after 256 times the counter wraps and the behavior turns
+	 * lazy again; this to deal with bursty apps that only use FPU for
+	 * a short time
+	 */
+	unsigned char fpu_counter;
+};
+
+#define INIT_THREAD  {						\
+	.sp = sizeof(init_stack) + (long) &init_stack,		\
+	.flags = 0,						\
+}
+
+/* Forward declaration, a strange C thing */
+struct task_struct;
+
+extern void start_thread(struct pt_regs *regs, unsigned long new_pc, unsigned long new_sp);
+
+/* Free all resources held by a thread. */
+extern void release_thread(struct task_struct *);
+
+/* Copy and release all segment info associated with a VM */
+#define copy_segments(p, mm)	do { } while(0)
+#define release_segments(mm)	do { } while(0)
+
+/*
+ * FPU lazy state save handling.
+ */
+
+static __inline__ void disable_fpu(void)
+{
+	unsigned long __dummy;
+
+	/* Set FD flag in SR */
+	__asm__ __volatile__("stc	sr, %0\n\t"
+			     "or	%1, %0\n\t"
+			     "ldc	%0, sr"
+			     : "=&r" (__dummy)
+			     : "r" (SR_FD));
+}
+
+static __inline__ void enable_fpu(void)
+{
+	unsigned long __dummy;
+
+	/* Clear out FD flag in SR */
+	__asm__ __volatile__("stc	sr, %0\n\t"
+			     "and	%1, %0\n\t"
+			     "ldc	%0, sr"
+			     : "=&r" (__dummy)
+			     : "r" (~SR_FD));
+}
+
+/* Double presision, NANS as NANS, rounding to nearest, no exceptions */
+#define FPSCR_INIT  0x00080000
+
+#define	FPSCR_CAUSE_MASK	0x0001f000	/* Cause bits */
+#define	FPSCR_FLAG_MASK		0x0000007c	/* Flag bits */
+
+/*
+ * Return saved PC of a blocked thread.
+ */
+#define thread_saved_pc(tsk)	(tsk->thread.pc)
+
+void show_trace(struct task_struct *tsk, unsigned long *sp,
+		struct pt_regs *regs);
+
+#ifdef CONFIG_DUMP_CODE
+void show_code(struct pt_regs *regs);
+#else
+static inline void show_code(struct pt_regs *regs)
+{
+}
+#endif
+
+extern unsigned long get_wchan(struct task_struct *p);
+
+#define KSTK_EIP(tsk)  (task_pt_regs(tsk)->pc)
+#define KSTK_ESP(tsk)  (task_pt_regs(tsk)->regs[15])
+
+#if defined(CONFIG_CPU_SH2A) || defined(CONFIG_CPU_SH4)
+
+#define PREFETCH_STRIDE		L1_CACHE_BYTES
+#define ARCH_HAS_PREFETCH
+#define ARCH_HAS_PREFETCHW
+
+static inline void prefetch(const void *x)
+{
+	__builtin_prefetch(x, 0, 3);
+}
+
+static inline void prefetchw(const void *x)
+{
+	__builtin_prefetch(x, 1, 3);
+}
+#endif
+
+#endif /* __KERNEL__ */
+#endif /* __ASM_SH_PROCESSOR_32_H */
diff --git a/arch/sh/include/asm/processor_64.h b/arch/sh/include/asm/processor_64.h
new file mode 100644
index 000000000..eedd4f625
--- /dev/null
+++ b/arch/sh/include/asm/processor_64.h
@@ -0,0 +1,234 @@
+#ifndef __ASM_SH_PROCESSOR_64_H
+#define __ASM_SH_PROCESSOR_64_H
+
+/*
+ * include/asm-sh/processor_64.h
+ *
+ * Copyright (C) 2000, 2001  Paolo Alberelli
+ * Copyright (C) 2003  Paul Mundt
+ * Copyright (C) 2004  Richard Curnow
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+#ifndef __ASSEMBLY__
+
+#include <linux/compiler.h>
+#include <asm/page.h>
+#include <asm/types.h>
+#include <cpu/registers.h>
+
+/*
+ * Default implementation of macro that returns current
+ * instruction pointer ("program counter").
+ */
+#define current_text_addr() ({ \
+void *pc; \
+unsigned long long __dummy = 0; \
+__asm__("gettr	tr0, %1\n\t" \
+	"pta	4, tr0\n\t" \
+	"gettr	tr0, %0\n\t" \
+	"ptabs	%1, tr0\n\t"	\
+	:"=r" (pc), "=r" (__dummy) \
+	: "1" (__dummy)); \
+pc; })
+
+#endif
+
+/*
+ * User space process size: 2GB - 4k.
+ */
+#define TASK_SIZE	0x7ffff000UL
+
+#define STACK_TOP	TASK_SIZE
+#define STACK_TOP_MAX	STACK_TOP
+
+/* This decides where the kernel will search for a free chunk of vm
+ * space during mmap's.
+ */
+#define TASK_UNMAPPED_BASE	PAGE_ALIGN(TASK_SIZE / 3)
+
+/*
+ * Bit of SR register
+ *
+ * FD-bit:
+ *     When it's set, it means the processor doesn't have right to use FPU,
+ *     and it results exception when the floating operation is executed.
+ *
+ * IMASK-bit:
+ *     Interrupt level mask
+ *
+ * STEP-bit:
+ *     Single step bit
+ *
+ */
+#if defined(CONFIG_SH64_SR_WATCH)
+#define SR_MMU   0x84000000
+#else
+#define SR_MMU   0x80000000
+#endif
+
+#define SR_IMASK 0x000000f0
+#define SR_FD    0x00008000
+#define SR_SSTEP 0x08000000
+
+#ifndef __ASSEMBLY__
+
+/*
+ * FPU structure and data : require 8-byte alignment as we need to access it
+   with fld.p, fst.p
+ */
+
+struct sh_fpu_hard_struct {
+	unsigned long fp_regs[64];
+	unsigned int fpscr;
+	/* long status; * software status information */
+};
+
+/* Dummy fpu emulator  */
+struct sh_fpu_soft_struct {
+	unsigned long fp_regs[64];
+	unsigned int fpscr;
+	unsigned char lookahead;
+	unsigned long entry_pc;
+};
+
+union thread_xstate {
+	struct sh_fpu_hard_struct hardfpu;
+	struct sh_fpu_soft_struct softfpu;
+	/*
+	 * The structure definitions only produce 32 bit alignment, yet we need
+	 * to access them using 64 bit load/store as well.
+	 */
+	unsigned long long alignment_dummy;
+};
+
+struct thread_struct {
+	unsigned long sp;
+	unsigned long pc;
+
+	/* Various thread flags, see SH_THREAD_xxx */
+	unsigned long flags;
+
+	/* This stores the address of the pt_regs built during a context
+	   switch, or of the register save area built for a kernel mode
+	   exception.  It is used for backtracing the stack of a sleeping task
+	   or one that traps in kernel mode. */
+        struct pt_regs *kregs;
+	/* This stores the address of the pt_regs constructed on entry from
+	   user mode.  It is a fixed value over the lifetime of a process, or
+	   NULL for a kernel thread. */
+	struct pt_regs *uregs;
+
+	unsigned long address;
+	/* Hardware debugging registers may come here */
+
+	/* floating point info */
+	union thread_xstate *xstate;
+
+	/*
+	 * fpu_counter contains the number of consecutive context switches
+	 * that the FPU is used. If this is over a threshold, the lazy fpu
+	 * saving becomes unlazy to save the trap. This is an unsigned char
+	 * so that after 256 times the counter wraps and the behavior turns
+	 * lazy again; this to deal with bursty apps that only use FPU for
+	 * a short time
+	 */
+	unsigned char fpu_counter;
+};
+
+#define INIT_MMAP \
+{ &init_mm, 0, 0, NULL, PAGE_SHARED, VM_READ | VM_WRITE | VM_EXEC, 1, NULL, NULL }
+
+#define INIT_THREAD  {				\
+	.sp		= sizeof(init_stack) +	\
+			  (long) &init_stack,	\
+	.pc		= 0,			\
+        .kregs		= &fake_swapper_regs,	\
+	.uregs	        = NULL,			\
+	.address	= 0,			\
+	.flags		= 0,			\
+}
+
+/*
+ * Do necessary setup to start up a newly executed thread.
+ */
+#define SR_USER (SR_MMU | SR_FD)
+
+#define start_thread(_regs, new_pc, new_sp)			\
+	_regs->sr = SR_USER;	/* User mode. */		\
+	_regs->pc = new_pc - 4;	/* Compensate syscall exit */	\
+	_regs->pc |= 1;		/* Set SHmedia ! */		\
+	_regs->regs[18] = 0;					\
+	_regs->regs[15] = new_sp
+
+/* Forward declaration, a strange C thing */
+struct task_struct;
+struct mm_struct;
+
+/* Free all resources held by a thread. */
+extern void release_thread(struct task_struct *);
+
+/* Copy and release all segment info associated with a VM */
+#define copy_segments(p, mm)	do { } while (0)
+#define release_segments(mm)	do { } while (0)
+#define forget_segments()	do { } while (0)
+/*
+ * FPU lazy state save handling.
+ */
+
+static inline void disable_fpu(void)
+{
+	unsigned long long __dummy;
+
+	/* Set FD flag in SR */
+	__asm__ __volatile__("getcon	" __SR ", %0\n\t"
+			     "or	%0, %1, %0\n\t"
+			     "putcon	%0, " __SR "\n\t"
+			     : "=&r" (__dummy)
+			     : "r" (SR_FD));
+}
+
+static inline void enable_fpu(void)
+{
+	unsigned long long __dummy;
+
+	/* Clear out FD flag in SR */
+	__asm__ __volatile__("getcon	" __SR ", %0\n\t"
+			     "and	%0, %1, %0\n\t"
+			     "putcon	%0, " __SR "\n\t"
+			     : "=&r" (__dummy)
+			     : "r" (~SR_FD));
+}
+
+/* Round to nearest, no exceptions on inexact, overflow, underflow,
+   zero-divide, invalid.  Configure option for whether to flush denorms to
+   zero, or except if a denorm is encountered.  */
+#if defined(CONFIG_SH64_FPU_DENORM_FLUSH)
+#define FPSCR_INIT  0x00040000
+#else
+#define FPSCR_INIT  0x00000000
+#endif
+
+#ifdef CONFIG_SH_FPU
+/* Initialise the FP state of a task */
+void fpinit(struct sh_fpu_hard_struct *fpregs);
+#else
+#define fpinit(fpregs)	do { } while (0)
+#endif
+
+extern struct task_struct *last_task_used_math;
+
+/*
+ * Return saved PC of a blocked thread.
+ */
+#define thread_saved_pc(tsk)	(tsk->thread.pc)
+
+extern unsigned long get_wchan(struct task_struct *p);
+
+#define KSTK_EIP(tsk)  ((tsk)->thread.pc)
+#define KSTK_ESP(tsk)  ((tsk)->thread.sp)
+
+#endif	/* __ASSEMBLY__ */
+#endif /* __ASM_SH_PROCESSOR_64_H */
diff --git a/arch/sh/include/asm/ptrace.h b/arch/sh/include/asm/ptrace.h
new file mode 100644
index 000000000..2506c7db7
--- /dev/null
+++ b/arch/sh/include/asm/ptrace.h
@@ -0,0 +1,117 @@
+/*
+ * Copyright (C) 1999, 2000  Niibe Yutaka
+ */
+#ifndef __ASM_SH_PTRACE_H
+#define __ASM_SH_PTRACE_H
+
+
+#include <linux/stringify.h>
+#include <linux/stddef.h>
+#include <linux/thread_info.h>
+#include <asm/addrspace.h>
+#include <asm/page.h>
+#include <uapi/asm/ptrace.h>
+
+#define user_mode(regs)			(((regs)->sr & 0x40000000)==0)
+#define kernel_stack_pointer(_regs)	((unsigned long)(_regs)->regs[15])
+
+#define GET_FP(regs)	((regs)->regs[14])
+#define GET_USP(regs)	((regs)->regs[15])
+
+#define arch_has_single_step()	(1)
+
+/*
+ * kprobe-based event tracer support
+ */
+struct pt_regs_offset {
+	const char *name;
+	int offset;
+};
+
+#define REG_OFFSET_NAME(r) {.name = #r, .offset = offsetof(struct pt_regs, r)}
+#define REGS_OFFSET_NAME(num)	\
+	{.name = __stringify(r##num), .offset = offsetof(struct pt_regs, regs[num])}
+#define TREGS_OFFSET_NAME(num)	\
+	{.name = __stringify(tr##num), .offset = offsetof(struct pt_regs, tregs[num])}
+#define REG_OFFSET_END {.name = NULL, .offset = 0}
+
+/* Query offset/name of register from its name/offset */
+extern int regs_query_register_offset(const char *name);
+extern const char *regs_query_register_name(unsigned int offset);
+
+extern const struct pt_regs_offset regoffset_table[];
+
+/**
+ * regs_get_register() - get register value from its offset
+ * @regs:	pt_regs from which register value is gotten.
+ * @offset:	offset number of the register.
+ *
+ * regs_get_register returns the value of a register. The @offset is the
+ * offset of the register in struct pt_regs address which specified by @regs.
+ * If @offset is bigger than MAX_REG_OFFSET, this returns 0.
+ */
+static inline unsigned long regs_get_register(struct pt_regs *regs,
+					      unsigned int offset)
+{
+	if (unlikely(offset > MAX_REG_OFFSET))
+		return 0;
+	return *(unsigned long *)((unsigned long)regs + offset);
+}
+
+/**
+ * regs_within_kernel_stack() - check the address in the stack
+ * @regs:	pt_regs which contains kernel stack pointer.
+ * @addr:	address which is checked.
+ *
+ * regs_within_kernel_stack() checks @addr is within the kernel stack page(s).
+ * If @addr is within the kernel stack, it returns true. If not, returns false.
+ */
+static inline int regs_within_kernel_stack(struct pt_regs *regs,
+					   unsigned long addr)
+{
+	return ((addr & ~(THREAD_SIZE - 1))  ==
+		(kernel_stack_pointer(regs) & ~(THREAD_SIZE - 1)));
+}
+
+/**
+ * regs_get_kernel_stack_nth() - get Nth entry of the stack
+ * @regs:	pt_regs which contains kernel stack pointer.
+ * @n:		stack entry number.
+ *
+ * regs_get_kernel_stack_nth() returns @n th entry of the kernel stack which
+ * is specified by @regs. If the @n th entry is NOT in the kernel stack,
+ * this returns 0.
+ */
+static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs,
+						      unsigned int n)
+{
+	unsigned long *addr = (unsigned long *)kernel_stack_pointer(regs);
+	addr += n;
+	if (regs_within_kernel_stack(regs, (unsigned long)addr))
+		return *addr;
+	else
+		return 0;
+}
+
+struct perf_event;
+struct perf_sample_data;
+
+extern void ptrace_triggered(struct perf_event *bp,
+		      struct perf_sample_data *data, struct pt_regs *regs);
+
+#define task_pt_regs(task) \
+	((struct pt_regs *) (task_stack_page(task) + THREAD_SIZE) - 1)
+
+static inline unsigned long profile_pc(struct pt_regs *regs)
+{
+	unsigned long pc = regs->pc;
+
+	if (virt_addr_uncached(pc))
+		return CAC_ADDR(pc);
+
+	return pc;
+}
+#define profile_pc profile_pc
+
+#include <asm-generic/ptrace.h>
+#endif /* __ASM_SH_PTRACE_H */
diff --git a/arch/sh/include/asm/ptrace_32.h b/arch/sh/include/asm/ptrace_32.h
new file mode 100644
index 000000000..1dd4480c5
--- /dev/null
+++ b/arch/sh/include/asm/ptrace_32.h
@@ -0,0 +1,13 @@
+#ifndef __ASM_SH_PTRACE_32_H
+#define __ASM_SH_PTRACE_32_H
+
+#include <uapi/asm/ptrace_32.h>
+
+
+#define MAX_REG_OFFSET		offsetof(struct pt_regs, tra)
+static inline long regs_return_value(struct pt_regs *regs)
+{
+	return regs->regs[0];
+}
+
+#endif /* __ASM_SH_PTRACE_32_H */
diff --git a/arch/sh/include/asm/ptrace_64.h b/arch/sh/include/asm/ptrace_64.h
new file mode 100644
index 000000000..97f4b5660
--- /dev/null
+++ b/arch/sh/include/asm/ptrace_64.h
@@ -0,0 +1,13 @@
+#ifndef __ASM_SH_PTRACE_64_H
+#define __ASM_SH_PTRACE_64_H
+
+#include <uapi/asm/ptrace_64.h>
+
+
+#define MAX_REG_OFFSET		offsetof(struct pt_regs, tregs[7])
+static inline long regs_return_value(struct pt_regs *regs)
+{
+	return regs->regs[3];
+}
+
+#endif /* __ASM_SH_PTRACE_64_H */
diff --git a/arch/sh/include/asm/push-switch.h b/arch/sh/include/asm/push-switch.h
new file mode 100644
index 000000000..4903f9e52
--- /dev/null
+++ b/arch/sh/include/asm/push-switch.h
@@ -0,0 +1,31 @@
+#ifndef __ASM_SH_PUSH_SWITCH_H
+#define __ASM_SH_PUSH_SWITCH_H
+
+#include <linux/timer.h>
+#include <linux/interrupt.h>
+#include <linux/workqueue.h>
+#include <linux/platform_device.h>
+
+struct push_switch {
+	/* switch state */
+	unsigned int		state:1;
+	/* debounce timer */
+	struct timer_list	debounce;
+	/* workqueue */
+	struct work_struct	work;
+	/* platform device, for workqueue handler */
+	struct platform_device	*pdev;
+};
+
+struct push_switch_platform_info {
+	/* IRQ handler */
+	irqreturn_t		(*irq_handler)(int irq, void *data);
+	/* Special IRQ flags */
+	unsigned int		irq_flags;
+	/* Bit location of switch */
+	unsigned int		bit;
+	/* Symbolic switch name */
+	const char		*name;
+};
+
+#endif /* __ASM_SH_PUSH_SWITCH_H */
diff --git a/arch/sh/include/asm/reboot.h b/arch/sh/include/asm/reboot.h
new file mode 100644
index 000000000..b3da0c63f
--- /dev/null
+++ b/arch/sh/include/asm/reboot.h
@@ -0,0 +1,21 @@
+#ifndef __ASM_SH_REBOOT_H
+#define __ASM_SH_REBOOT_H
+
+#include <linux/kdebug.h>
+
+struct pt_regs;
+
+struct machine_ops {
+	void (*restart)(char *cmd);
+	void (*halt)(void);
+	void (*power_off)(void);
+	void (*shutdown)(void);
+	void (*crash_shutdown)(struct pt_regs *);
+};
+
+extern struct machine_ops machine_ops;
+
+/* arch/sh/kernel/machine_kexec.c */
+void native_machine_crash_shutdown(struct pt_regs *regs);
+
+#endif /* __ASM_SH_REBOOT_H */
diff --git a/arch/sh/include/asm/romimage-macros.h b/arch/sh/include/asm/romimage-macros.h
new file mode 100644
index 000000000..ae17a150b
--- /dev/null
+++ b/arch/sh/include/asm/romimage-macros.h
@@ -0,0 +1,73 @@
+#ifndef __ROMIMAGE_MACRO_H
+#define __ROMIMAGE_MACRO_H
+
+/* The LIST command is used to include comments in the script */
+.macro	LIST comment
+.endm
+
+/* The ED command is used to write a 32-bit word */
+.macro  ED, addr, data
+	mov.l 1f, r1
+	mov.l 2f, r0
+	mov.l r0, @r1
+	bra 3f
+	 nop
+	.align 2
+1 :	.long \addr
+2 :	.long \data
+3 :
+.endm
+
+/* The EW command is used to write a 16-bit word */
+.macro  EW, addr, data
+	mov.l 1f, r1
+	mov.l 2f, r0
+	mov.w r0, @r1
+	bra 3f
+	 nop
+	.align 2
+1 :	.long \addr
+2 :	.long \data
+3 :
+.endm
+
+/* The EB command is used to write an 8-bit word */
+.macro  EB, addr, data
+	mov.l 1f, r1
+	mov.l 2f, r0
+	mov.b r0, @r1
+	bra 3f
+	 nop
+	.align 2
+1 :	.long \addr
+2 :	.long \data
+3 :
+.endm
+
+/* The WAIT command is used to delay the execution */
+.macro  WAIT, time
+	mov.l  2f, r3
+1 :
+	nop
+	tst     r3, r3
+	bf/s    1b
+	dt      r3
+	bra	3f
+	 nop
+	.align 2
+2 :	.long \time * 100
+3 :
+.endm
+
+/* The DD command is used to read a 32-bit word */
+.macro  DD, addr, addr2, nr
+	mov.l 1f, r1
+	mov.l @r1, r0
+	bra 2f
+	 nop
+	.align 2
+1 :	.long \addr
+2 :
+.endm
+
+#endif /* __ROMIMAGE_MACRO_H */
diff --git a/arch/sh/include/asm/rtc.h b/arch/sh/include/asm/rtc.h
new file mode 100644
index 000000000..52b0c2dba
--- /dev/null
+++ b/arch/sh/include/asm/rtc.h
@@ -0,0 +1,28 @@
+#ifndef _ASM_RTC_H
+#define _ASM_RTC_H
+
+void time_init(void);
+extern void (*board_time_init)(void);
+extern void (*rtc_sh_get_time)(struct timespec *);
+extern int (*rtc_sh_set_time)(const time_t);
+
+/* some dummy definitions */
+#define RTC_BATT_BAD 0x100	/* battery bad */
+#define RTC_SQWE 0x08		/* enable square-wave output */
+#define RTC_DM_BINARY 0x04	/* all time/date values are BCD if clear */
+#define RTC_24H 0x02		/* 24 hour mode - else hours bit 7 means pm */
+#define RTC_DST_EN 0x01	        /* auto switch DST - works f. USA only */
+
+struct rtc_time;
+unsigned int get_rtc_time(struct rtc_time *);
+int set_rtc_time(struct rtc_time *);
+
+#define RTC_CAP_4_DIGIT_YEAR	(1 << 0)
+
+struct sh_rtc_platform_info {
+	unsigned long capabilities;
+};
+
+#include <cpu/rtc.h>
+
+#endif /* _ASM_RTC_H */
diff --git a/arch/sh/include/asm/rwsem.h b/arch/sh/include/asm/rwsem.h
new file mode 100644
index 000000000..edab57265
--- /dev/null
+++ b/arch/sh/include/asm/rwsem.h
@@ -0,0 +1,132 @@
+/*
+ * include/asm-sh/rwsem.h: R/W semaphores for SH using the stuff
+ * in lib/rwsem.c.
+ */
+
+#ifndef _ASM_SH_RWSEM_H
+#define _ASM_SH_RWSEM_H
+
+#ifndef _LINUX_RWSEM_H
+#error "please don't include asm/rwsem.h directly, use linux/rwsem.h instead"
+#endif
+
+#ifdef __KERNEL__
+
+#define RWSEM_UNLOCKED_VALUE		0x00000000
+#define RWSEM_ACTIVE_BIAS		0x00000001
+#define RWSEM_ACTIVE_MASK		0x0000ffff
+#define RWSEM_WAITING_BIAS		(-0x00010000)
+#define RWSEM_ACTIVE_READ_BIAS		RWSEM_ACTIVE_BIAS
+#define RWSEM_ACTIVE_WRITE_BIAS		(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
+
+/*
+ * lock for reading
+ */
+static inline void __down_read(struct rw_semaphore *sem)
+{
+	if (atomic_inc_return((atomic_t *)(&sem->count)) > 0)
+		smp_wmb();
+	else
+		rwsem_down_read_failed(sem);
+}
+
+static inline int __down_read_trylock(struct rw_semaphore *sem)
+{
+	int tmp;
+
+	while ((tmp = sem->count) >= 0) {
+		if (tmp == cmpxchg(&sem->count, tmp,
+				   tmp + RWSEM_ACTIVE_READ_BIAS)) {
+			smp_wmb();
+			return 1;
+		}
+	}
+	return 0;
+}
+
+/*
+ * lock for writing
+ */
+static inline void __down_write(struct rw_semaphore *sem)
+{
+	int tmp;
+
+	tmp = atomic_add_return(RWSEM_ACTIVE_WRITE_BIAS,
+				(atomic_t *)(&sem->count));
+	if (tmp == RWSEM_ACTIVE_WRITE_BIAS)
+		smp_wmb();
+	else
+		rwsem_down_write_failed(sem);
+}
+
+static inline int __down_write_trylock(struct rw_semaphore *sem)
+{
+	int tmp;
+
+	tmp = cmpxchg(&sem->count, RWSEM_UNLOCKED_VALUE,
+		      RWSEM_ACTIVE_WRITE_BIAS);
+	smp_wmb();
+	return tmp == RWSEM_UNLOCKED_VALUE;
+}
+
+/*
+ * unlock after reading
+ */
+static inline void __up_read(struct rw_semaphore *sem)
+{
+	int tmp;
+
+	smp_wmb();
+	tmp = atomic_dec_return((atomic_t *)(&sem->count));
+	if (tmp < -1 && (tmp & RWSEM_ACTIVE_MASK) == 0)
+		rwsem_wake(sem);
+}
+
+/*
+ * unlock after writing
+ */
+static inline void __up_write(struct rw_semaphore *sem)
+{
+	smp_wmb();
+	if (atomic_sub_return(RWSEM_ACTIVE_WRITE_BIAS,
+			      (atomic_t *)(&sem->count)) < 0)
+		rwsem_wake(sem);
+}
+
+/*
+ * implement atomic add functionality
+ */
+static inline void rwsem_atomic_add(int delta, struct rw_semaphore *sem)
+{
+	atomic_add(delta, (atomic_t *)(&sem->count));
+}
+
+/*
+ * downgrade write lock to read lock
+ */
+static inline void __downgrade_write(struct rw_semaphore *sem)
+{
+	int tmp;
+
+	smp_wmb();
+	tmp = atomic_add_return(-RWSEM_WAITING_BIAS, (atomic_t *)(&sem->count));
+	if (tmp < 0)
+		rwsem_downgrade_wake(sem);
+}
+
+static inline void __down_write_nested(struct rw_semaphore *sem, int subclass)
+{
+	__down_write(sem);
+}
+
+/*
+ * implement exchange and add functionality
+ */
+static inline int rwsem_atomic_update(int delta, struct rw_semaphore *sem)
+{
+	smp_mb();
+	return atomic_add_return(delta, (atomic_t *)(&sem->count));
+}
+
+#endif /* __KERNEL__ */
+#endif /* _ASM_SH_RWSEM_H */
diff --git a/arch/sh/include/asm/seccomp.h b/arch/sh/include/asm/seccomp.h
new file mode 100644
index 000000000..3280ed380
--- /dev/null
+++ b/arch/sh/include/asm/seccomp.h
@@ -0,0 +1,10 @@
+#ifndef __ASM_SECCOMP_H
+
+#include <linux/unistd.h>
+
+#define __NR_seccomp_read __NR_read
+#define __NR_seccomp_write __NR_write
+#define __NR_seccomp_exit __NR_exit
+#define __NR_seccomp_sigreturn __NR_rt_sigreturn
+
+#endif /* __ASM_SECCOMP_H */
diff --git a/arch/sh/include/asm/sections.h b/arch/sh/include/asm/sections.h
new file mode 100644
index 000000000..7a99e6af6
--- /dev/null
+++ b/arch/sh/include/asm/sections.h
@@ -0,0 +1,11 @@
+#ifndef __ASM_SH_SECTIONS_H
+#define __ASM_SH_SECTIONS_H
+
+#include <asm-generic/sections.h>
+
+extern long __machvec_start, __machvec_end;
+extern char __uncached_start, __uncached_end;
+extern char __start_eh_frame[], __stop_eh_frame[];
+
+#endif /* __ASM_SH_SECTIONS_H */
+
diff --git a/arch/sh/include/asm/segment.h b/arch/sh/include/asm/segment.h
new file mode 100644
index 000000000..ff795d3a6
--- /dev/null
+++ b/arch/sh/include/asm/segment.h
@@ -0,0 +1,34 @@
+#ifndef __ASM_SH_SEGMENT_H
+#define __ASM_SH_SEGMENT_H
+
+#ifndef __ASSEMBLY__
+
+typedef struct {
+	unsigned long seg;
+} mm_segment_t;
+
+#define MAKE_MM_SEG(s)	((mm_segment_t) { (s) })
+
+/*
+ * The fs value determines whether argument validity checking should be
+ * performed or not.  If get_fs() == USER_DS, checking is performed, with
+ * get_fs() == KERNEL_DS, checking is bypassed.
+ *
+ * For historical reasons, these macros are grossly misnamed.
+ */
+#define KERNEL_DS	MAKE_MM_SEG(0xFFFFFFFFUL)
+#ifdef CONFIG_MMU
+#define USER_DS		MAKE_MM_SEG(PAGE_OFFSET)
+#else
+#define USER_DS		KERNEL_DS
+#endif
+
+#define segment_eq(a, b) ((a).seg == (b).seg)
+
+#define get_ds()	(KERNEL_DS)
+
+#define get_fs()	(current_thread_info()->addr_limit)
+#define set_fs(x)	(current_thread_info()->addr_limit = (x))
+
+#endif /* __ASSEMBLY__ */
+#endif /* __ASM_SH_SEGMENT_H */
diff --git a/arch/sh/include/asm/setup.h b/arch/sh/include/asm/setup.h
new file mode 100644
index 000000000..99238108e
--- /dev/null
+++ b/arch/sh/include/asm/setup.h
@@ -0,0 +1,24 @@
+#ifndef _SH_SETUP_H
+#define _SH_SETUP_H
+
+#include <uapi/asm/setup.h>
+
+/*
+ * This is set up by the setup-routine at boot-time
+ */
+#define PARAM	((unsigned char *)empty_zero_page)
+
+#define MOUNT_ROOT_RDONLY (*(unsigned long *) (PARAM+0x000))
+#define RAMDISK_FLAGS (*(unsigned long *) (PARAM+0x004))
+#define ORIG_ROOT_DEV (*(unsigned long *) (PARAM+0x008))
+#define LOADER_TYPE (*(unsigned long *) (PARAM+0x00c))
+#define INITRD_START (*(unsigned long *) (PARAM+0x010))
+#define INITRD_SIZE (*(unsigned long *) (PARAM+0x014))
+/* ... */
+#define COMMAND_LINE ((char *) (PARAM+0x100))
+
+void sh_mv_setup(void);
+void check_for_initrd(void);
+void per_cpu_trap_init(void);
+
+#endif /* _SH_SETUP_H */
diff --git a/arch/sh/include/asm/sfp-machine.h b/arch/sh/include/asm/sfp-machine.h
new file mode 100644
index 000000000..d3c548443
--- /dev/null
+++ b/arch/sh/include/asm/sfp-machine.h
@@ -0,0 +1,84 @@
+/* Machine-dependent software floating-point definitions.
+   SuperH kernel version.
+   Copyright (C) 1997,1998,1999 Free Software Foundation, Inc.
+   This file is part of the GNU C Library.
+   Contributed by Richard Henderson (rth@cygnus.com),
+		  Jakub Jelinek (jj@ultra.linux.cz),
+		  David S. Miller (davem@redhat.com) and
+		  Peter Maydell (pmaydell@chiark.greenend.org.uk).
+
+   The GNU C Library is free software; you can redistribute it and/or
+   modify it under the terms of the GNU Library General Public License as
+   published by the Free Software Foundation; either version 2 of the
+   License, or (at your option) any later version.
+
+   The GNU C Library 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
+   Library General Public License for more details.
+
+   You should have received a copy of the GNU Library General Public
+   License along with the GNU C Library; see the file COPYING.LIB.  If
+   not, write to the Free Software Foundation, Inc.,
+   59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.  */
+
+#ifndef _SFP_MACHINE_H
+#define _SFP_MACHINE_H
+
+#define _FP_W_TYPE_SIZE		32
+#define _FP_W_TYPE		unsigned long
+#define _FP_WS_TYPE		signed long
+#define _FP_I_TYPE		long
+
+#define _FP_MUL_MEAT_S(R,X,Y)					\
+  _FP_MUL_MEAT_1_wide(_FP_WFRACBITS_S,R,X,Y,umul_ppmm)
+#define _FP_MUL_MEAT_D(R,X,Y)					\
+  _FP_MUL_MEAT_2_wide(_FP_WFRACBITS_D,R,X,Y,umul_ppmm)
+#define _FP_MUL_MEAT_Q(R,X,Y)					\
+  _FP_MUL_MEAT_4_wide(_FP_WFRACBITS_Q,R,X,Y,umul_ppmm)
+
+#define _FP_DIV_MEAT_S(R,X,Y)	_FP_DIV_MEAT_1_udiv(S,R,X,Y)
+#define _FP_DIV_MEAT_D(R,X,Y)	_FP_DIV_MEAT_2_udiv(D,R,X,Y)
+#define _FP_DIV_MEAT_Q(R,X,Y)	_FP_DIV_MEAT_4_udiv(Q,R,X,Y)
+
+#define _FP_NANFRAC_S		((_FP_QNANBIT_S << 1) - 1)
+#define _FP_NANFRAC_D		((_FP_QNANBIT_D << 1) - 1), -1
+#define _FP_NANFRAC_Q		((_FP_QNANBIT_Q << 1) - 1), -1, -1, -1
+#define _FP_NANSIGN_S		0
+#define _FP_NANSIGN_D		0
+#define _FP_NANSIGN_Q		0
+
+#define _FP_KEEPNANFRACP 1
+
+/*
+ * If one NaN is signaling and the other is not,
+ * we choose that one, otherwise we choose X.
+ */
+#define _FP_CHOOSENAN(fs, wc, R, X, Y, OP)                      \
+  do {                                                          \
+    if ((_FP_FRAC_HIGH_RAW_##fs(X) & _FP_QNANBIT_##fs)          \
+        && !(_FP_FRAC_HIGH_RAW_##fs(Y) & _FP_QNANBIT_##fs))     \
+      {                                                         \
+        R##_s = Y##_s;                                          \
+        _FP_FRAC_COPY_##wc(R,Y);                                \
+      }                                                         \
+    else                                                        \
+      {                                                         \
+        R##_s = X##_s;                                          \
+        _FP_FRAC_COPY_##wc(R,X);                                \
+      }                                                         \
+    R##_c = FP_CLS_NAN;                                         \
+  } while (0)
+
+//#define FP_ROUNDMODE		FPSCR_RM
+#define FP_DENORM_ZERO		1/*FPSCR_DN*/
+
+/* Exception flags. */
+#define FP_EX_INVALID		(1<<4)
+#define FP_EX_DIVZERO		(1<<3)
+#define FP_EX_OVERFLOW		(1<<2)
+#define FP_EX_UNDERFLOW		(1<<1)
+#define FP_EX_INEXACT		(1<<0)
+
+#endif
+
diff --git a/arch/sh/include/asm/sh7760fb.h b/arch/sh/include/asm/sh7760fb.h
new file mode 100644
index 000000000..8767f61ac
--- /dev/null
+++ b/arch/sh/include/asm/sh7760fb.h
@@ -0,0 +1,197 @@
+/*
+ * sh7760fb.h -- platform data for SH7760/SH7763 LCDC framebuffer driver.
+ *
+ * (c) 2006-2008 MSC Vertriebsges.m.b.H.,
+ * 			Manuel Lauss <mano@roarinelk.homelinux.net>
+ * (c) 2008 Nobuhiro Iwamatsu <iwamatsu.nobuhiro@renesas.com>
+ */
+
+#ifndef _ASM_SH_SH7760FB_H
+#define _ASM_SH_SH7760FB_H
+
+/*
+ * some bits of the colormap registers should be written as zero.
+ * create a mask for that.
+ */
+#define SH7760FB_PALETTE_MASK 0x00f8fcf8
+
+/* The LCDC dma engine always sets bits 27-26 to 1: this is Area3 */
+#define SH7760FB_DMA_MASK 0x0C000000
+
+/* palette */
+#define LDPR(x) (((x) << 2))
+
+/* framebuffer registers and bits */
+#define LDICKR 0x400
+#define LDMTR 0x402
+/* see sh7760fb.h for LDMTR bits */
+#define LDDFR 0x404
+#define LDDFR_PABD (1 << 8)
+#define LDDFR_COLOR_MASK 0x7F
+#define LDSMR 0x406
+#define LDSMR_ROT (1 << 13)
+#define LDSARU 0x408
+#define LDSARL 0x40c
+#define LDLAOR 0x410
+#define LDPALCR 0x412
+#define LDPALCR_PALS (1 << 4)
+#define LDPALCR_PALEN (1 << 0)
+#define LDHCNR 0x414
+#define LDHSYNR 0x416
+#define LDVDLNR 0x418
+#define LDVTLNR 0x41a
+#define LDVSYNR 0x41c
+#define LDACLNR 0x41e
+#define LDINTR 0x420
+#define LDPMMR 0x424
+#define LDPSPR 0x426
+#define LDCNTR 0x428
+#define LDCNTR_DON (1 << 0)
+#define LDCNTR_DON2 (1 << 4)
+
+#ifdef CONFIG_CPU_SUBTYPE_SH7763
+# define LDLIRNR       0x440
+/* LDINTR bit */
+# define LDINTR_MINTEN (1 << 15)
+# define LDINTR_FINTEN (1 << 14)
+# define LDINTR_VSINTEN (1 << 13)
+# define LDINTR_VEINTEN (1 << 12)
+# define LDINTR_MINTS (1 << 11)
+# define LDINTR_FINTS (1 << 10)
+# define LDINTR_VSINTS (1 << 9)
+# define LDINTR_VEINTS (1 << 8)
+# define VINT_START (LDINTR_VSINTEN)
+# define VINT_CHECK (LDINTR_VSINTS)
+#else
+/* LDINTR bit */
+# define LDINTR_VINTSEL (1 << 12)
+# define LDINTR_VINTE (1 << 8)
+# define LDINTR_VINTS (1 << 0)
+# define VINT_START (LDINTR_VINTSEL)
+# define VINT_CHECK (LDINTR_VINTS)
+#endif
+
+/* HSYNC polarity inversion */
+#define LDMTR_FLMPOL (1 << 15)
+
+/* VSYNC polarity inversion */
+#define LDMTR_CL1POL (1 << 14)
+
+/* DISPLAY-ENABLE polarity inversion */
+#define LDMTR_DISPEN_LOWACT (1 << 13)
+
+/* DISPLAY DATA BUS polarity inversion */
+#define LDMTR_DPOL_LOWACT (1 << 12)
+
+/* AC modulation signal enable */
+#define LDMTR_MCNT (1 << 10)
+
+/* Disable output of HSYNC during VSYNC period */
+#define LDMTR_CL1CNT (1 << 9)
+
+/* Disable output of VSYNC during VSYNC period */
+#define LDMTR_CL2CNT (1 << 8)
+
+/* Display types supported by the LCDC */
+#define LDMTR_STN_MONO_4       0x00
+#define LDMTR_STN_MONO_8       0x01
+#define LDMTR_STN_COLOR_4      0x08
+#define LDMTR_STN_COLOR_8      0x09
+#define LDMTR_STN_COLOR_12     0x0A
+#define LDMTR_STN_COLOR_16     0x0B
+#define LDMTR_DSTN_MONO_8      0x11
+#define LDMTR_DSTN_MONO_16     0x13
+#define LDMTR_DSTN_COLOR_8     0x19
+#define LDMTR_DSTN_COLOR_12    0x1A
+#define LDMTR_DSTN_COLOR_16    0x1B
+#define LDMTR_TFT_COLOR_16     0x2B
+
+/* framebuffer color layout */
+#define LDDFR_1BPP_MONO 0x00
+#define LDDFR_2BPP_MONO 0x01
+#define LDDFR_4BPP_MONO 0x02
+#define LDDFR_6BPP_MONO 0x04
+#define LDDFR_4BPP 0x0A
+#define LDDFR_8BPP 0x0C
+#define LDDFR_16BPP_RGB555 0x1D
+#define LDDFR_16BPP_RGB565 0x2D
+
+/* LCDC Pixclock sources */
+#define LCDC_CLKSRC_BUSCLOCK 0
+#define LCDC_CLKSRC_PERIPHERAL 1
+#define LCDC_CLKSRC_EXTERNAL 2
+
+#define LDICKR_CLKSRC(x) \
+       (((x) & 3) << 12)
+
+/* LCDC pixclock input divider. Set to 1 at a minimum! */
+#define LDICKR_CLKDIV(x) \
+       ((x) & 0x1f)
+
+struct sh7760fb_platdata {
+
+	/* Set this member to a valid fb_videmode for the display you
+	 * wish to use.  The following members must be initialized:
+	 * xres, yres, hsync_len, vsync_len, sync,
+	 * {left,right,upper,lower}_margin.
+	 * The driver uses the above members to calculate register values
+	 * and memory requirements. Other members are ignored but may
+	 * be used by other framebuffer layer components.
+	 */
+	struct fb_videomode *def_mode;
+
+	/* LDMTR includes display type and signal polarity.  The
+	 * HSYNC/VSYNC polarities are derived from the fb_var_screeninfo
+	 * data above; however the polarities of the following signals
+	 * must be encoded in the ldmtr member:
+	 * Display Enable signal (default high-active)  DISPEN_LOWACT
+	 * Display Data signals (default high-active)   DPOL_LOWACT
+	 * AC Modulation signal (default off)           MCNT
+	 * Hsync-During-Vsync suppression (default off) CL1CNT
+	 * Vsync-during-vsync suppression (default off) CL2CNT
+	 * NOTE: also set a display type!
+	 * (one of LDMTR_{STN,DSTN,TFT}_{MONO,COLOR}_{4,8,12,16})
+	 */
+	u16 ldmtr;
+
+	/* LDDFR controls framebuffer image format (depth, organization)
+	 * Use ONE of the LDDFR_?BPP_* macros!
+	 */
+	u16 lddfr;
+
+	/* LDPMMR and LDPSPR control the timing of the power signals
+	 * for the display. Please read the SH7760 Hardware Manual,
+	 * Chapters 30.3.17, 30.3.18 and 30.4.6!
+	 */
+	u16 ldpmmr;
+	u16 ldpspr;
+
+	/* LDACLNR contains the line numbers after which the AC modulation
+	 * signal is to toggle. Set to ZERO for TFTs or displays which
+	 * do not need it. (Chapter 30.3.15 in SH7760 Hardware Manual).
+	 */
+	u16 ldaclnr;
+
+	/* LDICKR contains information on pixelclock source and config.
+	 * Please use the LDICKR_CLKSRC() and LDICKR_CLKDIV() macros.
+	 * minimal value for CLKDIV() must be 1!.
+	 */
+	u16 ldickr;
+
+	/* set this member to 1 if you wish to use the LCDC's hardware
+	 * rotation function.  This is limited to displays <= 320x200
+	 * pixels resolution!
+	 */
+	int rotate;		/* set to 1 to rotate 90 CCW */
+
+	/* set this to 1 to suppress vsync irq use. */
+	int novsync;
+
+	/* blanking hook for platform. Set this if your platform can do
+	 * more than the LCDC in terms of blanking (e.g. disable clock
+	 * generator / backlight power supply / etc.
+	 */
+	void (*blank) (int);
+};
+
+#endif /* _ASM_SH_SH7760FB_H */
diff --git a/arch/sh/include/asm/sh_bios.h b/arch/sh/include/asm/sh_bios.h
new file mode 100644
index 000000000..95714c284
--- /dev/null
+++ b/arch/sh/include/asm/sh_bios.h
@@ -0,0 +1,27 @@
+#ifndef __ASM_SH_BIOS_H
+#define __ASM_SH_BIOS_H
+
+#ifdef CONFIG_SH_STANDARD_BIOS
+
+/*
+ * Copyright (C) 2000 Greg Banks, Mitch Davis
+ * C API to interface to the standard LinuxSH BIOS
+ * usually from within the early stages of kernel boot.
+ */
+extern void sh_bios_console_write(const char *buf, unsigned int len);
+extern void sh_bios_gdb_detach(void);
+
+extern void sh_bios_get_node_addr(unsigned char *node_addr);
+extern void sh_bios_shutdown(unsigned int how);
+
+extern void sh_bios_vbr_init(void);
+extern void sh_bios_vbr_reload(void);
+
+#else
+
+static inline void sh_bios_vbr_init(void) { }
+static inline void sh_bios_vbr_reload(void) { }
+
+#endif /* CONFIG_SH_STANDARD_BIOS */
+
+#endif /* __ASM_SH_BIOS_H */
diff --git a/arch/sh/include/asm/shmparam.h b/arch/sh/include/asm/shmparam.h
new file mode 100644
index 000000000..ba1758d90
--- /dev/null
+++ b/arch/sh/include/asm/shmparam.h
@@ -0,0 +1,22 @@
+/*
+ * include/asm-sh/shmparam.h
+ *
+ * Copyright (C) 1999 Niibe Yutaka
+ * Copyright (C) 2006 Paul Mundt
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+#ifndef __ASM_SH_SHMPARAM_H
+#define __ASM_SH_SHMPARAM_H
+
+/*
+ * SH-4 and SH-3 7705 have an aliasing dcache. Bump this up to a sensible value
+ * for everyone, and work out the specifics from the probed cache descriptor.
+ */
+#define	SHMLBA	0x4000		 /* attach addr a multiple of this */
+
+#define __ARCH_FORCE_SHMLBA
+
+#endif /* __ASM_SH_SHMPARAM_H */
diff --git a/arch/sh/include/asm/siu.h b/arch/sh/include/asm/siu.h
new file mode 100644
index 000000000..580b7ac22
--- /dev/null
+++ b/arch/sh/include/asm/siu.h
@@ -0,0 +1,23 @@
+/*
+ * platform header for the SIU ASoC driver
+ *
+ * Copyright (C) 2009-2010 Guennadi Liakhovetski <g.liakhovetski@gmx.de>
+ *
+ * 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_SIU_H
+#define ASM_SIU_H
+
+struct device;
+
+struct siu_platform {
+	unsigned int dma_slave_tx_a;
+	unsigned int dma_slave_rx_a;
+	unsigned int dma_slave_tx_b;
+	unsigned int dma_slave_rx_b;
+};
+
+#endif /* ASM_SIU_H */
diff --git a/arch/sh/include/asm/smc37c93x.h b/arch/sh/include/asm/smc37c93x.h
new file mode 100644
index 000000000..585da2a8f
--- /dev/null
+++ b/arch/sh/include/asm/smc37c93x.h
@@ -0,0 +1,190 @@
+#ifndef __ASM_SH_SMC37C93X_H
+#define __ASM_SH_SMC37C93X_H
+
+/*
+ * linux/include/asm-sh/smc37c93x.h
+ *
+ * Copyright (C) 2000  Kazumoto Kojima
+ *
+ * SMSC 37C93x Super IO Chip support
+ */
+
+/* Default base I/O address */
+#define FDC_PRIMARY_BASE	0x3f0
+#define IDE1_PRIMARY_BASE	0x1f0
+#define IDE1_SECONDARY_BASE	0x170
+#define PARPORT_PRIMARY_BASE	0x378
+#define COM1_PRIMARY_BASE	0x2f8
+#define COM2_PRIMARY_BASE	0x3f8
+#define RTC_PRIMARY_BASE	0x070
+#define KBC_PRIMARY_BASE	0x060
+#define AUXIO_PRIMARY_BASE	0x000	/* XXX */
+
+/* Logical device number */
+#define LDN_FDC			0
+#define LDN_IDE1		1
+#define LDN_IDE2		2
+#define LDN_PARPORT		3
+#define LDN_COM1		4
+#define LDN_COM2		5
+#define LDN_RTC			6
+#define LDN_KBC			7
+#define LDN_AUXIO		8
+
+/* Configuration port and key */
+#define CONFIG_PORT		0x3f0
+#define INDEX_PORT		CONFIG_PORT
+#define DATA_PORT		0x3f1
+#define CONFIG_ENTER		0x55
+#define CONFIG_EXIT		0xaa
+
+/* Configuration index */
+#define CURRENT_LDN_INDEX	0x07
+#define POWER_CONTROL_INDEX	0x22
+#define ACTIVATE_INDEX		0x30
+#define IO_BASE_HI_INDEX	0x60
+#define IO_BASE_LO_INDEX	0x61
+#define IRQ_SELECT_INDEX	0x70
+#define DMA_SELECT_INDEX	0x74
+
+#define GPIO46_INDEX		0xc6
+#define GPIO47_INDEX		0xc7
+
+/* UART stuff. Only for debugging.  */
+/* UART Register */
+
+#define UART_RBR	0x0	/* Receiver Buffer Register (Read Only) */
+#define UART_THR	0x0	/* Transmitter Holding Register (Write Only) */
+#define UART_IER	0x2	/* Interrupt Enable Register */
+#define UART_IIR	0x4	/* Interrupt Ident Register (Read Only) */
+#define UART_FCR	0x4	/* FIFO Control Register (Write Only) */
+#define UART_LCR	0x6	/* Line Control Register */
+#define UART_MCR	0x8	/* MODEM Control Register */
+#define UART_LSR	0xa	/* Line Status Register */
+#define UART_MSR	0xc	/* MODEM Status Register */
+#define UART_SCR	0xe	/* Scratch Register */
+#define UART_DLL	0x0	/* Divisor Latch (LS) */
+#define UART_DLM	0x2	/* Divisor Latch (MS) */
+
+#ifndef __ASSEMBLY__
+typedef struct uart_reg {
+	volatile __u16 rbr;
+	volatile __u16 ier;
+	volatile __u16 iir;
+	volatile __u16 lcr;
+	volatile __u16 mcr;
+	volatile __u16 lsr;
+	volatile __u16 msr;
+	volatile __u16 scr;
+} uart_reg;
+#endif /* ! __ASSEMBLY__ */
+
+/* Alias for Write Only Register */
+
+#define thr	rbr
+#define tcr	iir
+
+/* Alias for Divisor Latch Register */
+
+#define dll	rbr
+#define dlm	ier
+#define fcr	iir
+
+/* Interrupt Enable Register */
+
+#define IER_ERDAI	0x0100	/* Enable Received Data Available Interrupt */
+#define IER_ETHREI	0x0200	/* Enable Transmitter Holding Register Empty Interrupt */
+#define IER_ELSI	0x0400	/* Enable Receiver Line Status Interrupt */
+#define IER_EMSI	0x0800	/* Enable MODEM Status Interrupt */
+
+/* Interrupt Ident Register */
+
+#define IIR_IP		0x0100	/* "0" if Interrupt Pending */
+#define IIR_IIB0	0x0200	/* Interrupt ID Bit 0 */
+#define IIR_IIB1	0x0400	/* Interrupt ID Bit 1 */
+#define IIR_IIB2	0x0800	/* Interrupt ID Bit 2 */
+#define IIR_FIFO	0xc000	/* FIFOs enabled */
+
+/* FIFO Control Register */
+
+#define FCR_FEN		0x0100	/* FIFO enable */
+#define FCR_RFRES	0x0200	/* Receiver FIFO reset */
+#define FCR_TFRES	0x0400	/* Transmitter FIFO reset */
+#define FCR_DMA		0x0800	/* DMA mode select */
+#define FCR_RTL		0x4000	/* Receiver triger (LSB) */
+#define FCR_RTM		0x8000	/* Receiver triger (MSB) */
+
+/* Line Control Register */
+
+#define LCR_WLS0	0x0100	/* Word Length Select Bit 0 */
+#define LCR_WLS1	0x0200	/* Word Length Select Bit 1 */
+#define LCR_STB		0x0400	/* Number of Stop Bits */
+#define LCR_PEN		0x0800	/* Parity Enable */
+#define LCR_EPS		0x1000	/* Even Parity Select */
+#define LCR_SP		0x2000	/* Stick Parity */
+#define LCR_SB		0x4000	/* Set Break */
+#define LCR_DLAB	0x8000	/* Divisor Latch Access Bit */
+
+/* MODEM Control Register */
+
+#define MCR_DTR		0x0100	/* Data Terminal Ready */
+#define MCR_RTS		0x0200	/* Request to Send */
+#define MCR_OUT1	0x0400	/* Out 1 */
+#define MCR_IRQEN	0x0800	/* IRQ Enable */
+#define MCR_LOOP	0x1000	/* Loop */
+
+/* Line Status Register */
+
+#define LSR_DR		0x0100	/* Data Ready */
+#define LSR_OE		0x0200	/* Overrun Error */
+#define LSR_PE		0x0400	/* Parity Error */
+#define LSR_FE		0x0800	/* Framing Error */
+#define LSR_BI		0x1000	/* Break Interrupt */
+#define LSR_THRE	0x2000	/* Transmitter Holding Register Empty */
+#define LSR_TEMT	0x4000	/* Transmitter Empty */
+#define LSR_FIFOE	0x8000	/* Receiver FIFO error */
+
+/* MODEM Status Register */
+
+#define MSR_DCTS	0x0100	/* Delta Clear to Send */
+#define MSR_DDSR	0x0200	/* Delta Data Set Ready */
+#define MSR_TERI	0x0400	/* Trailing Edge Ring Indicator */
+#define MSR_DDCD	0x0800	/* Delta Data Carrier Detect */
+#define MSR_CTS		0x1000	/* Clear to Send */
+#define MSR_DSR		0x2000	/* Data Set Ready */
+#define MSR_RI		0x4000	/* Ring Indicator */
+#define MSR_DCD		0x8000	/* Data Carrier Detect */
+
+/* Baud Rate Divisor */
+
+#define UART_CLK	(1843200)	/* 1.8432 MHz */
+#define UART_BAUD(x)	(UART_CLK / (16 * (x)))
+
+/* RTC register definition */
+#define RTC_SECONDS             0
+#define RTC_SECONDS_ALARM       1
+#define RTC_MINUTES             2
+#define RTC_MINUTES_ALARM       3
+#define RTC_HOURS               4
+#define RTC_HOURS_ALARM         5
+#define RTC_DAY_OF_WEEK         6
+#define RTC_DAY_OF_MONTH        7
+#define RTC_MONTH               8
+#define RTC_YEAR                9
+#define RTC_FREQ_SELECT		10
+# define RTC_UIP 0x80
+# define RTC_DIV_CTL 0x70
+/* This RTC can work under 32.768KHz clock only.  */
+# define RTC_OSC_ENABLE 0x20
+# define RTC_OSC_DISABLE 0x00
+#define RTC_CONTROL     	11
+# define RTC_SET 0x80
+# define RTC_PIE 0x40
+# define RTC_AIE 0x20
+# define RTC_UIE 0x10
+# define RTC_SQWE 0x08
+# define RTC_DM_BINARY 0x04
+# define RTC_24H 0x02
+# define RTC_DST_EN 0x01
+
+#endif  /* __ASM_SH_SMC37C93X_H */
diff --git a/arch/sh/include/asm/smp-ops.h b/arch/sh/include/asm/smp-ops.h
new file mode 100644
index 000000000..c590f7685
--- /dev/null
+++ b/arch/sh/include/asm/smp-ops.h
@@ -0,0 +1,51 @@
+#ifndef __ASM_SH_SMP_OPS_H
+#define __ASM_SH_SMP_OPS_H
+
+struct plat_smp_ops {
+	void (*smp_setup)(void);
+	unsigned int (*smp_processor_id)(void);
+	void (*prepare_cpus)(unsigned int max_cpus);
+	void (*start_cpu)(unsigned int cpu, unsigned long entry_point);
+	void (*send_ipi)(unsigned int cpu, unsigned int message);
+	int (*cpu_disable)(unsigned int cpu);
+	void (*cpu_die)(unsigned int cpu);
+	void (*play_dead)(void);
+};
+
+extern struct plat_smp_ops *mp_ops;
+extern struct plat_smp_ops shx3_smp_ops;
+
+#ifdef CONFIG_SMP
+
+static inline void plat_smp_setup(void)
+{
+	BUG_ON(!mp_ops);
+	mp_ops->smp_setup();
+}
+
+static inline void play_dead(void)
+{
+	mp_ops->play_dead();
+}
+
+extern void register_smp_ops(struct plat_smp_ops *ops);
+
+#else
+
+static inline void plat_smp_setup(void)
+{
+	/* UP, nothing to do ... */
+}
+
+static inline void register_smp_ops(struct plat_smp_ops *ops)
+{
+}
+
+static inline void play_dead(void)
+{
+	BUG();
+}
+
+#endif /* CONFIG_SMP */
+
+#endif /* __ASM_SH_SMP_OPS_H */
diff --git a/arch/sh/include/asm/smp.h b/arch/sh/include/asm/smp.h
new file mode 100644
index 000000000..78b0d0f4b
--- /dev/null
+++ b/arch/sh/include/asm/smp.h
@@ -0,0 +1,78 @@
+#ifndef __ASM_SH_SMP_H
+#define __ASM_SH_SMP_H
+
+#include <linux/bitops.h>
+#include <linux/cpumask.h>
+#include <asm/smp-ops.h>
+
+#ifdef CONFIG_SMP
+
+#include <linux/spinlock.h>
+#include <linux/atomic.h>
+#include <asm/current.h>
+#include <asm/percpu.h>
+
+#define raw_smp_processor_id()	(current_thread_info()->cpu)
+
+/* Map from cpu id to sequential logical cpu number. */
+extern int __cpu_number_map[NR_CPUS];
+#define cpu_number_map(cpu)  __cpu_number_map[cpu]
+
+/* The reverse map from sequential logical cpu number to cpu id.  */
+extern int __cpu_logical_map[NR_CPUS];
+#define cpu_logical_map(cpu)  __cpu_logical_map[cpu]
+
+enum {
+	SMP_MSG_FUNCTION,
+	SMP_MSG_RESCHEDULE,
+	SMP_MSG_FUNCTION_SINGLE,
+	SMP_MSG_TIMER,
+
+	SMP_MSG_NR,	/* must be last */
+};
+
+DECLARE_PER_CPU(int, cpu_state);
+
+void smp_message_recv(unsigned int msg);
+void smp_timer_broadcast(const struct cpumask *mask);
+
+void local_timer_interrupt(void);
+void local_timer_setup(unsigned int cpu);
+void local_timer_stop(unsigned int cpu);
+
+void arch_send_call_function_single_ipi(int cpu);
+void arch_send_call_function_ipi_mask(const struct cpumask *mask);
+
+void native_play_dead(void);
+void native_cpu_die(unsigned int cpu);
+int native_cpu_disable(unsigned int cpu);
+
+#ifdef CONFIG_HOTPLUG_CPU
+void play_dead_common(void);
+extern int __cpu_disable(void);
+
+static inline void __cpu_die(unsigned int cpu)
+{
+	extern struct plat_smp_ops *mp_ops;     /* private */
+
+	mp_ops->cpu_die(cpu);
+}
+#endif
+
+static inline int hard_smp_processor_id(void)
+{
+	extern struct plat_smp_ops *mp_ops;	/* private */
+
+	if (!mp_ops)
+		return 0;	/* boot CPU */
+
+	return mp_ops->smp_processor_id();
+}
+
+#else
+
+#define hard_smp_processor_id()	(0)
+
+#endif /* CONFIG_SMP */
+
+#endif /* __ASM_SH_SMP_H */
diff --git a/arch/sh/include/asm/sparsemem.h b/arch/sh/include/asm/sparsemem.h
new file mode 100644
index 000000000..547a540b6
--- /dev/null
+++ b/arch/sh/include/asm/sparsemem.h
@@ -0,0 +1,16 @@
+#ifndef __ASM_SH_SPARSEMEM_H
+#define __ASM_SH_SPARSEMEM_H
+
+#ifdef __KERNEL__
+/*
+ * SECTION_SIZE_BITS		2^N: how big each section will be
+ * MAX_PHYSADDR_BITS		2^N: how much physical address space we have
+ * MAX_PHYSMEM_BITS		2^N: how much memory we can have in that space
+ */
+#define SECTION_SIZE_BITS	26
+#define MAX_PHYSADDR_BITS	32
+#define MAX_PHYSMEM_BITS	32
+
+#endif
+
+#endif /* __ASM_SH_SPARSEMEM_H */
diff --git a/arch/sh/include/asm/spi.h b/arch/sh/include/asm/spi.h
new file mode 100644
index 000000000..e96f5b095
--- /dev/null
+++ b/arch/sh/include/asm/spi.h
@@ -0,0 +1,13 @@
+#ifndef __ASM_SPI_H__
+#define __ASM_SPI_H__
+
+struct sh_spi_info;
+
+struct sh_spi_info {
+	int			 bus_num;
+	int			 num_chipselect;
+
+	void (*chip_select)(struct sh_spi_info *spi, int cs, int state);
+};
+
+#endif /* __ASM_SPI_H__ */
diff --git a/arch/sh/include/asm/spinlock.h b/arch/sh/include/asm/spinlock.h
new file mode 100644
index 000000000..bdc0f3b6c
--- /dev/null
+++ b/arch/sh/include/asm/spinlock.h
@@ -0,0 +1,226 @@
+/*
+ * include/asm-sh/spinlock.h
+ *
+ * Copyright (C) 2002, 2003 Paul Mundt
+ * Copyright (C) 2006, 2007 Akio Idehara
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+#ifndef __ASM_SH_SPINLOCK_H
+#define __ASM_SH_SPINLOCK_H
+
+/*
+ * The only locking implemented here uses SH-4A opcodes. For others,
+ * split this out as per atomic-*.h.
+ */
+#ifndef CONFIG_CPU_SH4A
+#error "Need movli.l/movco.l for spinlocks"
+#endif
+
+/*
+ * Your basic SMP spinlocks, allowing only a single CPU anywhere
+ */
+
+#define arch_spin_is_locked(x)		((x)->lock <= 0)
+#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
+#define arch_spin_unlock_wait(x) \
+	do { while (arch_spin_is_locked(x)) cpu_relax(); } while (0)
+
+/*
+ * Simple spin lock operations.  There are two variants, one clears IRQ's
+ * on the local processor, one does not.
+ *
+ * We make no fairness assumptions.  They have a cost.
+ */
+static inline void arch_spin_lock(arch_spinlock_t *lock)
+{
+	unsigned long tmp;
+	unsigned long oldval;
+
+	__asm__ __volatile__ (
+		"1:						\n\t"
+		"movli.l	@%2, %0	! arch_spin_lock	\n\t"
+		"mov		%0, %1				\n\t"
+		"mov		#0, %0				\n\t"
+		"movco.l	%0, @%2				\n\t"
+		"bf		1b				\n\t"
+		"cmp/pl		%1				\n\t"
+		"bf		1b				\n\t"
+		: "=&z" (tmp), "=&r" (oldval)
+		: "r" (&lock->lock)
+		: "t", "memory"
+	);
+}
+
+static inline void arch_spin_unlock(arch_spinlock_t *lock)
+{
+	unsigned long tmp;
+
+	__asm__ __volatile__ (
+		"mov		#1, %0 ! arch_spin_unlock	\n\t"
+		"mov.l		%0, @%1				\n\t"
+		: "=&z" (tmp)
+		: "r" (&lock->lock)
+		: "t", "memory"
+	);
+}
+
+static inline int arch_spin_trylock(arch_spinlock_t *lock)
+{
+	unsigned long tmp, oldval;
+
+	__asm__ __volatile__ (
+		"1:						\n\t"
+		"movli.l	@%2, %0	! arch_spin_trylock	\n\t"
+		"mov		%0, %1				\n\t"
+		"mov		#0, %0				\n\t"
+		"movco.l	%0, @%2				\n\t"
+		"bf		1b				\n\t"
+		"synco						\n\t"
+		: "=&z" (tmp), "=&r" (oldval)
+		: "r" (&lock->lock)
+		: "t", "memory"
+	);
+
+	return oldval;
+}
+
+/*
+ * Read-write spinlocks, allowing multiple readers but only one writer.
+ *
+ * NOTE! it is quite common to have readers in interrupts but no interrupt
+ * writers. For those circumstances we can "mix" irq-safe locks - any writer
+ * needs to get a irq-safe write-lock, but readers can get non-irqsafe
+ * read-locks.
+ */
+
+/**
+ * read_can_lock - would read_trylock() succeed?
+ * @lock: the rwlock in question.
+ */
+#define arch_read_can_lock(x)	((x)->lock > 0)
+
+/**
+ * write_can_lock - would write_trylock() succeed?
+ * @lock: the rwlock in question.
+ */
+#define arch_write_can_lock(x)	((x)->lock == RW_LOCK_BIAS)
+
+static inline void arch_read_lock(arch_rwlock_t *rw)
+{
+	unsigned long tmp;
+
+	__asm__ __volatile__ (
+		"1:						\n\t"
+		"movli.l	@%1, %0	! arch_read_lock	\n\t"
+		"cmp/pl		%0				\n\t"
+		"bf		1b				\n\t"
+		"add		#-1, %0				\n\t"
+		"movco.l	%0, @%1				\n\t"
+		"bf		1b				\n\t"
+		: "=&z" (tmp)
+		: "r" (&rw->lock)
+		: "t", "memory"
+	);
+}
+
+static inline void arch_read_unlock(arch_rwlock_t *rw)
+{
+	unsigned long tmp;
+
+	__asm__ __volatile__ (
+		"1:						\n\t"
+		"movli.l	@%1, %0	! arch_read_unlock	\n\t"
+		"add		#1, %0				\n\t"
+		"movco.l	%0, @%1				\n\t"
+		"bf		1b				\n\t"
+		: "=&z" (tmp)
+		: "r" (&rw->lock)
+		: "t", "memory"
+	);
+}
+
+static inline void arch_write_lock(arch_rwlock_t *rw)
+{
+	unsigned long tmp;
+
+	__asm__ __volatile__ (
+		"1:						\n\t"
+		"movli.l	@%1, %0	! arch_write_lock	\n\t"
+		"cmp/hs		%2, %0				\n\t"
+		"bf		1b				\n\t"
+		"sub		%2, %0				\n\t"
+		"movco.l	%0, @%1				\n\t"
+		"bf		1b				\n\t"
+		: "=&z" (tmp)
+		: "r" (&rw->lock), "r" (RW_LOCK_BIAS)
+		: "t", "memory"
+	);
+}
+
+static inline void arch_write_unlock(arch_rwlock_t *rw)
+{
+	__asm__ __volatile__ (
+		"mov.l		%1, @%0 ! arch_write_unlock	\n\t"
+		:
+		: "r" (&rw->lock), "r" (RW_LOCK_BIAS)
+		: "t", "memory"
+	);
+}
+
+static inline int arch_read_trylock(arch_rwlock_t *rw)
+{
+	unsigned long tmp, oldval;
+
+	__asm__ __volatile__ (
+		"1:						\n\t"
+		"movli.l	@%2, %0	! arch_read_trylock	\n\t"
+		"mov		%0, %1				\n\t"
+		"cmp/pl		%0				\n\t"
+		"bf		2f				\n\t"
+		"add		#-1, %0				\n\t"
+		"movco.l	%0, @%2				\n\t"
+		"bf		1b				\n\t"
+		"2:						\n\t"
+		"synco						\n\t"
+		: "=&z" (tmp), "=&r" (oldval)
+		: "r" (&rw->lock)
+		: "t", "memory"
+	);
+
+	return (oldval > 0);
+}
+
+static inline int arch_write_trylock(arch_rwlock_t *rw)
+{
+	unsigned long tmp, oldval;
+
+	__asm__ __volatile__ (
+		"1:						\n\t"
+		"movli.l	@%2, %0	! arch_write_trylock	\n\t"
+		"mov		%0, %1				\n\t"
+		"cmp/hs		%3, %0				\n\t"
+		"bf		2f				\n\t"
+		"sub		%3, %0				\n\t"
+		"2:						\n\t"
+		"movco.l	%0, @%2				\n\t"
+		"bf		1b				\n\t"
+		"synco						\n\t"
+		: "=&z" (tmp), "=&r" (oldval)
+		: "r" (&rw->lock), "r" (RW_LOCK_BIAS)
+		: "t", "memory"
+	);
+
+	return (oldval > (RW_LOCK_BIAS - 1));
+}
+
+#define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
+#define arch_write_lock_flags(lock, flags) arch_write_lock(lock)
+
+#define arch_spin_relax(lock)	cpu_relax()
+#define arch_read_relax(lock)	cpu_relax()
+#define arch_write_relax(lock)	cpu_relax()
+
+#endif /* __ASM_SH_SPINLOCK_H */
diff --git a/arch/sh/include/asm/spinlock_types.h b/arch/sh/include/asm/spinlock_types.h
new file mode 100644
index 000000000..9b7560db0
--- /dev/null
+++ b/arch/sh/include/asm/spinlock_types.h
@@ -0,0 +1,21 @@
+#ifndef __ASM_SH_SPINLOCK_TYPES_H
+#define __ASM_SH_SPINLOCK_TYPES_H
+
+#ifndef __LINUX_SPINLOCK_TYPES_H
+# error "please don't include this file directly"
+#endif
+
+typedef struct {
+	volatile unsigned int lock;
+} arch_spinlock_t;
+
+#define __ARCH_SPIN_LOCK_UNLOCKED		{ 1 }
+
+typedef struct {
+	volatile unsigned int lock;
+} arch_rwlock_t;
+
+#define RW_LOCK_BIAS			0x01000000
+#define __ARCH_RW_LOCK_UNLOCKED		{ RW_LOCK_BIAS }
+
+#endif
diff --git a/arch/sh/include/asm/sram.h b/arch/sh/include/asm/sram.h
new file mode 100644
index 000000000..a2808ce4c
--- /dev/null
+++ b/arch/sh/include/asm/sram.h
@@ -0,0 +1,38 @@
+#ifndef __ASM_SRAM_H
+#define __ASM_SRAM_H
+
+#ifdef CONFIG_HAVE_SRAM_POOL
+
+#include <linux/spinlock.h>
+#include <linux/genalloc.h>
+
+/* arch/sh/mm/sram.c */
+extern struct gen_pool *sram_pool;
+
+static inline unsigned long sram_alloc(size_t len)
+{
+	if (!sram_pool)
+		return 0UL;
+
+	return gen_pool_alloc(sram_pool, len);
+}
+
+static inline void sram_free(unsigned long addr, size_t len)
+{
+	return gen_pool_free(sram_pool, addr, len);
+}
+
+#else
+
+static inline unsigned long sram_alloc(size_t len)
+{
+	return 0;
+}
+
+static inline void sram_free(unsigned long addr, size_t len)
+{
+}
+
+#endif /* CONFIG_HAVE_SRAM_POOL */
+
+#endif /* __ASM_SRAM_H */
diff --git a/arch/sh/include/asm/stackprotector.h b/arch/sh/include/asm/stackprotector.h
new file mode 100644
index 000000000..d9df3a768
--- /dev/null
+++ b/arch/sh/include/asm/stackprotector.h
@@ -0,0 +1,27 @@
+#ifndef __ASM_SH_STACKPROTECTOR_H
+#define __ASM_SH_STACKPROTECTOR_H
+
+#include <linux/random.h>
+#include <linux/version.h>
+
+extern unsigned long __stack_chk_guard;
+
+/*
+ * Initialize the stackprotector canary value.
+ *
+ * NOTE: this must only be called from functions that never return,
+ * and it must always be inlined.
+ */
+static __always_inline void boot_init_stack_canary(void)
+{
+	unsigned long canary;
+
+	/* Try to get a semi random initial value. */
+	get_random_bytes(&canary, sizeof(canary));
+	canary ^= LINUX_VERSION_CODE;
+
+	current->stack_canary = canary;
+	__stack_chk_guard = current->stack_canary;
+}
+
+#endif /* __ASM_SH_STACKPROTECTOR_H */
diff --git a/arch/sh/include/asm/stacktrace.h b/arch/sh/include/asm/stacktrace.h
new file mode 100644
index 000000000..a7e2d4dfd
--- /dev/null
+++ b/arch/sh/include/asm/stacktrace.h
@@ -0,0 +1,22 @@
+/*
+ * Copyright (C) 2009  Matt Fleming
+ *
+ * Based on:
+ *	The x86 implementation - arch/x86/include/asm/stacktrace.h
+ */
+#ifndef _ASM_SH_STACKTRACE_H
+#define _ASM_SH_STACKTRACE_H
+
+/* Generic stack tracer with callbacks */
+
+struct stacktrace_ops {
+	void (*address)(void *data, unsigned long address, int reliable);
+	/* On negative return stop dumping */
+	int (*stack)(void *data, char *name);
+};
+
+void dump_trace(struct task_struct *tsk, struct pt_regs *regs,
+		unsigned long *stack,
+		const struct stacktrace_ops *ops, void *data);
+
+#endif /* _ASM_SH_STACKTRACE_H */
diff --git a/arch/sh/include/asm/string.h b/arch/sh/include/asm/string.h
new file mode 100644
index 000000000..114011fa0
--- /dev/null
+++ b/arch/sh/include/asm/string.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_SUPERH32
+# include <asm/string_32.h>
+#else
+# include <asm/string_64.h>
+#endif
diff --git a/arch/sh/include/asm/string_32.h b/arch/sh/include/asm/string_32.h
new file mode 100644
index 000000000..55f8db6bc
--- /dev/null
+++ b/arch/sh/include/asm/string_32.h
@@ -0,0 +1,131 @@
+#ifndef __ASM_SH_STRING_H
+#define __ASM_SH_STRING_H
+
+#ifdef __KERNEL__
+
+/*
+ * Copyright (C) 1999 Niibe Yutaka
+ * But consider these trivial functions to be public domain.
+ */
+
+#define __HAVE_ARCH_STRCPY
+static inline char *strcpy(char *__dest, const char *__src)
+{
+	register char *__xdest = __dest;
+	unsigned long __dummy;
+
+	__asm__ __volatile__("1:\n\t"
+			     "mov.b	@%1+, %2\n\t"
+			     "mov.b	%2, @%0\n\t"
+			     "cmp/eq	#0, %2\n\t"
+			     "bf/s	1b\n\t"
+			     " add	#1, %0\n\t"
+			     : "=r" (__dest), "=r" (__src), "=&z" (__dummy)
+			     : "0" (__dest), "1" (__src)
+			     : "memory", "t");
+
+	return __xdest;
+}
+
+#define __HAVE_ARCH_STRNCPY
+static inline char *strncpy(char *__dest, const char *__src, size_t __n)
+{
+	register char *__xdest = __dest;
+	unsigned long __dummy;
+
+	if (__n == 0)
+		return __xdest;
+
+	__asm__ __volatile__(
+		"1:\n"
+		"mov.b	@%1+, %2\n\t"
+		"mov.b	%2, @%0\n\t"
+		"cmp/eq	#0, %2\n\t"
+		"bt/s	2f\n\t"
+		" cmp/eq	%5,%1\n\t"
+		"bf/s	1b\n\t"
+		" add	#1, %0\n"
+		"2:"
+		: "=r" (__dest), "=r" (__src), "=&z" (__dummy)
+		: "0" (__dest), "1" (__src), "r" (__src+__n)
+		: "memory", "t");
+
+	return __xdest;
+}
+
+#define __HAVE_ARCH_STRCMP
+static inline int strcmp(const char *__cs, const char *__ct)
+{
+	register int __res;
+	unsigned long __dummy;
+
+	__asm__ __volatile__(
+		"mov.b	@%1+, %3\n"
+		"1:\n\t"
+		"mov.b	@%0+, %2\n\t"
+		"cmp/eq #0, %3\n\t"
+		"bt	2f\n\t"
+		"cmp/eq %2, %3\n\t"
+		"bt/s	1b\n\t"
+		" mov.b	@%1+, %3\n\t"
+		"add	#-2, %1\n\t"
+		"mov.b	@%1, %3\n\t"
+		"sub	%3, %2\n"
+		"2:"
+		: "=r" (__cs), "=r" (__ct), "=&r" (__res), "=&z" (__dummy)
+		: "0" (__cs), "1" (__ct)
+		: "t");
+
+	return __res;
+}
+
+#define __HAVE_ARCH_STRNCMP
+static inline int strncmp(const char *__cs, const char *__ct, size_t __n)
+{
+	register int __res;
+	unsigned long __dummy;
+
+	if (__n == 0)
+		return 0;
+
+	__asm__ __volatile__(
+		"mov.b	@%1+, %3\n"
+		"1:\n\t"
+		"mov.b	@%0+, %2\n\t"
+		"cmp/eq %6, %0\n\t"
+		"bt/s	2f\n\t"
+		" cmp/eq #0, %3\n\t"
+		"bt/s	3f\n\t"
+		" cmp/eq %3, %2\n\t"
+		"bt/s	1b\n\t"
+		" mov.b	@%1+, %3\n\t"
+		"add	#-2, %1\n\t"
+		"mov.b	@%1, %3\n"
+		"2:\n\t"
+		"sub	%3, %2\n"
+		"3:"
+		:"=r" (__cs), "=r" (__ct), "=&r" (__res), "=&z" (__dummy)
+		: "0" (__cs), "1" (__ct), "r" (__cs+__n)
+		: "t");
+
+	return __res;
+}
+
+#define __HAVE_ARCH_MEMSET
+extern void *memset(void *__s, int __c, size_t __count);
+
+#define __HAVE_ARCH_MEMCPY
+extern void *memcpy(void *__to, __const__ void *__from, size_t __n);
+
+#define __HAVE_ARCH_MEMMOVE
+extern void *memmove(void *__dest, __const__ void *__src, size_t __n);
+
+#define __HAVE_ARCH_MEMCHR
+extern void *memchr(const void *__s, int __c, size_t __n);
+
+#define __HAVE_ARCH_STRLEN
+extern size_t strlen(const char *);
+
+#endif /* __KERNEL__ */
+
+#endif /* __ASM_SH_STRING_H */
diff --git a/arch/sh/include/asm/string_64.h b/arch/sh/include/asm/string_64.h
new file mode 100644
index 000000000..742007172
--- /dev/null
+++ b/arch/sh/include/asm/string_64.h
@@ -0,0 +1,20 @@
+#ifndef __ASM_SH_STRING_64_H
+#define __ASM_SH_STRING_64_H
+
+#ifdef __KERNEL__
+
+#define __HAVE_ARCH_MEMSET
+extern void *memset(void *__s, int __c, size_t __count);
+
+#define __HAVE_ARCH_MEMCPY
+extern void *memcpy(void *dest, const void *src, size_t count);
+
+#define __HAVE_ARCH_STRLEN
+extern size_t strlen(const char *);
+
+#define __HAVE_ARCH_STRCPY
+extern char *strcpy(char *__dest, const char *__src);
+
+#endif /* __KERNEL__ */
+
+#endif /* __ASM_SH_STRING_64_H */
diff --git a/arch/sh/include/asm/suspend.h b/arch/sh/include/asm/suspend.h
new file mode 100644
index 000000000..70ae0b288
--- /dev/null
+++ b/arch/sh/include/asm/suspend.h
@@ -0,0 +1,96 @@
+#ifndef _ASM_SH_SUSPEND_H
+#define _ASM_SH_SUSPEND_H
+
+#ifndef __ASSEMBLY__
+#include <linux/notifier.h>
+
+#include <asm/ptrace.h>
+
+struct swsusp_arch_regs {
+	struct pt_regs user_regs;
+	unsigned long bank1_regs[8];
+};
+
+void sh_mobile_call_standby(unsigned long mode);
+
+#ifdef CONFIG_CPU_IDLE
+int sh_mobile_setup_cpuidle(void);
+#else
+static inline int sh_mobile_setup_cpuidle(void) { return 0; }
+#endif
+
+/* notifier chains for pre/post sleep hooks */
+extern struct atomic_notifier_head sh_mobile_pre_sleep_notifier_list;
+extern struct atomic_notifier_head sh_mobile_post_sleep_notifier_list;
+
+/* priority levels for notifiers */
+#define SH_MOBILE_SLEEP_BOARD	0
+#define SH_MOBILE_SLEEP_CPU	1
+#define SH_MOBILE_PRE(x)	(x)
+#define SH_MOBILE_POST(x)	(-(x))
+
+/* board code registration function for self-refresh assembly snippets */
+void sh_mobile_register_self_refresh(unsigned long flags,
+				     void *pre_start, void *pre_end,
+				     void *post_start, void *post_end);
+
+/* register structure for address/data information */
+struct sh_sleep_regs {
+	unsigned long stbcr;
+	unsigned long bar;
+
+	/* MMU */
+	unsigned long pteh;
+	unsigned long ptel;
+	unsigned long ttb;
+	unsigned long tea;
+	unsigned long mmucr;
+	unsigned long ptea;
+	unsigned long pascr;
+	unsigned long irmcr;
+
+	/* Cache */
+	unsigned long ccr;
+	unsigned long ramcr;
+};
+
+/* data area for low-level sleep code */
+struct sh_sleep_data {
+	/* current sleep mode (SUSP_SH_...) */
+	unsigned long mode;
+
+	/* addresses of board specific self-refresh snippets */
+	unsigned long sf_pre;
+	unsigned long sf_post;
+
+	/* address of resume code */
+	unsigned long resume;
+
+	/* register state saved and restored by the assembly code */
+	unsigned long vbr;
+	unsigned long spc;
+	unsigned long sr;
+	unsigned long sp;
+
+	/* structure for keeping register addresses */
+	struct sh_sleep_regs addr;
+
+	/* structure for saving/restoring register state */
+	struct sh_sleep_regs data;
+};
+
+/* a bitmap of supported sleep modes (SUSP_SH..) */
+extern unsigned long sh_mobile_sleep_supported;
+
+#endif
+
+/* flags passed to assembly suspend code */
+#define SUSP_SH_SLEEP		(1 << 0) /* Regular sleep mode */
+#define SUSP_SH_STANDBY		(1 << 1) /* SH-Mobile Software standby mode */
+#define SUSP_SH_RSTANDBY	(1 << 2) /* SH-Mobile R-standby mode */
+#define SUSP_SH_USTANDBY	(1 << 3) /* SH-Mobile U-standby mode */
+#define SUSP_SH_SF		(1 << 4) /* Enable self-refresh */
+#define SUSP_SH_MMU		(1 << 5) /* Save/restore MMU and cache */
+#define SUSP_SH_REGS		(1 << 6) /* Save/restore registers */
+
+#endif /* _ASM_SH_SUSPEND_H */
diff --git a/arch/sh/include/asm/switch_to.h b/arch/sh/include/asm/switch_to.h
new file mode 100644
index 000000000..bcd722fc8
--- /dev/null
+++ b/arch/sh/include/asm/switch_to.h
@@ -0,0 +1,19 @@
+/*
+ * Copyright (C) 2000, 2001  Paolo Alberelli
+ * Copyright (C) 2003  Paul Mundt
+ * Copyright (C) 2004  Richard Curnow
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+#ifndef __ASM_SH_SWITCH_TO_H
+#define __ASM_SH_SWITCH_TO_H
+
+#ifdef CONFIG_SUPERH32
+# include <asm/switch_to_32.h>
+#else
+# include <asm/switch_to_64.h>
+#endif
+
+#endif /* __ASM_SH_SWITCH_TO_H */
diff --git a/arch/sh/include/asm/switch_to_32.h b/arch/sh/include/asm/switch_to_32.h
new file mode 100644
index 000000000..0c065513e
--- /dev/null
+++ b/arch/sh/include/asm/switch_to_32.h
@@ -0,0 +1,134 @@
+#ifndef __ASM_SH_SWITCH_TO_32_H
+#define __ASM_SH_SWITCH_TO_32_H
+
+#ifdef CONFIG_SH_DSP
+
+#define is_dsp_enabled(tsk)						\
+	(!!(tsk->thread.dsp_status.status & SR_DSP))
+
+#define __restore_dsp(tsk)						\
+do {									\
+	register u32 *__ts2 __asm__ ("r2") =				\
+			(u32 *)&tsk->thread.dsp_status;			\
+	__asm__ __volatile__ (						\
+		".balign 4\n\t"						\
+		"movs.l	@r2+, a0\n\t"					\
+		"movs.l	@r2+, a1\n\t"					\
+		"movs.l	@r2+, a0g\n\t"					\
+		"movs.l	@r2+, a1g\n\t"					\
+		"movs.l	@r2+, m0\n\t"					\
+		"movs.l	@r2+, m1\n\t"					\
+		"movs.l	@r2+, x0\n\t"					\
+		"movs.l	@r2+, x1\n\t"					\
+		"movs.l	@r2+, y0\n\t"					\
+		"movs.l	@r2+, y1\n\t"					\
+		"lds.l	@r2+, dsr\n\t"					\
+		"ldc.l	@r2+, rs\n\t"					\
+		"ldc.l	@r2+, re\n\t"					\
+		"ldc.l	@r2+, mod\n\t"					\
+		: : "r" (__ts2));					\
+} while (0)
+
+#define __save_dsp(tsk)							\
+do {									\
+	register u32 *__ts2 __asm__ ("r2") =				\
+			(u32 *)&tsk->thread.dsp_status + 14;		\
+									\
+	__asm__ __volatile__ (						\
+		".balign 4\n\t"						\
+		"stc.l	mod, @-r2\n\t"					\
+		"stc.l	re, @-r2\n\t"					\
+		"stc.l	rs, @-r2\n\t"					\
+		"sts.l	dsr, @-r2\n\t"					\
+		"movs.l	y1, @-r2\n\t"					\
+		"movs.l	y0, @-r2\n\t"					\
+		"movs.l	x1, @-r2\n\t"					\
+		"movs.l	x0, @-r2\n\t"					\
+		"movs.l	m1, @-r2\n\t"					\
+		"movs.l	m0, @-r2\n\t"					\
+		"movs.l	a1g, @-r2\n\t"					\
+		"movs.l	a0g, @-r2\n\t"					\
+		"movs.l	a1, @-r2\n\t"					\
+		"movs.l	a0, @-r2\n\t"					\
+		: : "r" (__ts2));					\
+} while (0)
+
+#else
+
+#define is_dsp_enabled(tsk)	(0)
+#define __save_dsp(tsk)		do { } while (0)
+#define __restore_dsp(tsk)	do { } while (0)
+#endif
+
+struct task_struct *__switch_to(struct task_struct *prev,
+				struct task_struct *next);
+
+/*
+ *	switch_to() should switch tasks to task nr n, first
+ */
+#define switch_to(prev, next, last)				\
+do {								\
+	register u32 *__ts1 __asm__ ("r1");			\
+	register u32 *__ts2 __asm__ ("r2");			\
+	register u32 *__ts4 __asm__ ("r4");			\
+	register u32 *__ts5 __asm__ ("r5");			\
+	register u32 *__ts6 __asm__ ("r6");			\
+	register u32 __ts7 __asm__ ("r7");			\
+	struct task_struct *__last;				\
+								\
+	if (is_dsp_enabled(prev))				\
+		__save_dsp(prev);				\
+								\
+	__ts1 = (u32 *)&prev->thread.sp;			\
+	__ts2 = (u32 *)&prev->thread.pc;			\
+	__ts4 = (u32 *)prev;					\
+	__ts5 = (u32 *)next;					\
+	__ts6 = (u32 *)&next->thread.sp;			\
+	__ts7 = next->thread.pc;				\
+								\
+	__asm__ __volatile__ (					\
+		".balign 4\n\t"					\
+		"stc.l	gbr, @-r15\n\t"				\
+		"sts.l	pr, @-r15\n\t"				\
+		"mov.l	r8, @-r15\n\t"				\
+		"mov.l	r9, @-r15\n\t"				\
+		"mov.l	r10, @-r15\n\t"				\
+		"mov.l	r11, @-r15\n\t"				\
+		"mov.l	r12, @-r15\n\t"				\
+		"mov.l	r13, @-r15\n\t"				\
+		"mov.l	r14, @-r15\n\t"				\
+		"mov.l	r15, @r1\t! save SP\n\t"		\
+		"mov.l	@r6, r15\t! change to new stack\n\t"	\
+		"mova	1f, %0\n\t"				\
+		"mov.l	%0, @r2\t! save PC\n\t"			\
+		"mov.l	2f, %0\n\t"				\
+		"jmp	@%0\t! call __switch_to\n\t"		\
+		" lds	r7, pr\t!  with return to new PC\n\t"	\
+		".balign	4\n"				\
+		"2:\n\t"					\
+		".long	__switch_to\n"				\
+		"1:\n\t"					\
+		"mov.l	@r15+, r14\n\t"				\
+		"mov.l	@r15+, r13\n\t"				\
+		"mov.l	@r15+, r12\n\t"				\
+		"mov.l	@r15+, r11\n\t"				\
+		"mov.l	@r15+, r10\n\t"				\
+		"mov.l	@r15+, r9\n\t"				\
+		"mov.l	@r15+, r8\n\t"				\
+		"lds.l	@r15+, pr\n\t"				\
+		"ldc.l	@r15+, gbr\n\t"				\
+		: "=z" (__last)					\
+		: "r" (__ts1), "r" (__ts2), "r" (__ts4),	\
+		  "r" (__ts5), "r" (__ts6), "r" (__ts7)		\
+		: "r3", "t");					\
+								\
+	last = __last;						\
+} while (0)
+
+#define finish_arch_switch(prev)				\
+do {								\
+	if (is_dsp_enabled(prev))				\
+		__restore_dsp(prev);				\
+} while (0)
+
+#endif /* __ASM_SH_SWITCH_TO_32_H */
diff --git a/arch/sh/include/asm/switch_to_64.h b/arch/sh/include/asm/switch_to_64.h
new file mode 100644
index 000000000..ba3129d6b
--- /dev/null
+++ b/arch/sh/include/asm/switch_to_64.h
@@ -0,0 +1,35 @@
+/*
+ * Copyright (C) 2000, 2001  Paolo Alberelli
+ * Copyright (C) 2003  Paul Mundt
+ * Copyright (C) 2004  Richard Curnow
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+#ifndef __ASM_SH_SWITCH_TO_64_H
+#define __ASM_SH_SWITCH_TO_64_H
+
+struct thread_struct;
+struct task_struct;
+
+/*
+ *	switch_to() should switch tasks to task nr n, first
+ */
+struct task_struct *sh64_switch_to(struct task_struct *prev,
+				   struct thread_struct *prev_thread,
+				   struct task_struct *next,
+				   struct thread_struct *next_thread);
+
+#define switch_to(prev,next,last)				\
+do {								\
+	if (last_task_used_math != next) {			\
+		struct pt_regs *regs = next->thread.uregs;	\
+		if (regs) regs->sr |= SR_FD;			\
+	}							\
+	last = sh64_switch_to(prev, &prev->thread, next,	\
+			      &next->thread);			\
+} while (0)
+
+
+#endif /* __ASM_SH_SWITCH_TO_64_H */
diff --git a/arch/sh/include/asm/syscall.h b/arch/sh/include/asm/syscall.h
new file mode 100644
index 000000000..847128da6
--- /dev/null
+++ b/arch/sh/include/asm/syscall.h
@@ -0,0 +1,12 @@
+#ifndef __ASM_SH_SYSCALL_H
+#define __ASM_SH_SYSCALL_H
+
+extern const unsigned long sys_call_table[];
+
+#ifdef CONFIG_SUPERH32
+# include <asm/syscall_32.h>
+#else
+# include <asm/syscall_64.h>
+#endif
+
+#endif /* __ASM_SH_SYSCALL_H */
diff --git a/arch/sh/include/asm/syscall_32.h b/arch/sh/include/asm/syscall_32.h
new file mode 100644
index 000000000..95be3b0ce
--- /dev/null
+++ b/arch/sh/include/asm/syscall_32.h
@@ -0,0 +1,106 @@
+#ifndef __ASM_SH_SYSCALL_32_H
+#define __ASM_SH_SYSCALL_32_H
+
+#include <uapi/linux/audit.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/err.h>
+#include <asm/ptrace.h>
+
+/* The system call number is given by the user in R3 */
+static inline long syscall_get_nr(struct task_struct *task,
+				  struct pt_regs *regs)
+{
+	return (regs->tra >= 0) ? regs->regs[3] : -1L;
+}
+
+static inline void syscall_rollback(struct task_struct *task,
+				    struct pt_regs *regs)
+{
+	/*
+	 * XXX: This needs some thought. On SH we don't
+	 * save away the original r0 value anywhere.
+	 */
+}
+
+static inline long syscall_get_error(struct task_struct *task,
+				     struct pt_regs *regs)
+{
+	return IS_ERR_VALUE(regs->regs[0]) ? regs->regs[0] : 0;
+}
+
+static inline long syscall_get_return_value(struct task_struct *task,
+					    struct pt_regs *regs)
+{
+	return regs->regs[0];
+}
+
+static inline void syscall_set_return_value(struct task_struct *task,
+					    struct pt_regs *regs,
+					    int error, long val)
+{
+	if (error)
+		regs->regs[0] = -error;
+	else
+		regs->regs[0] = val;
+}
+
+static inline void syscall_get_arguments(struct task_struct *task,
+					 struct pt_regs *regs,
+					 unsigned int i, unsigned int n,
+					 unsigned long *args)
+{
+	/*
+	 * Do this simply for now. If we need to start supporting
+	 * fetching arguments from arbitrary indices, this will need some
+	 * extra logic. Presently there are no in-tree users that depend
+	 * on this behaviour.
+	 */
+	BUG_ON(i);
+
+	/* Argument pattern is: R4, R5, R6, R7, R0, R1 */
+	switch (n) {
+	case 6: args[5] = regs->regs[1];
+	case 5: args[4] = regs->regs[0];
+	case 4: args[3] = regs->regs[7];
+	case 3: args[2] = regs->regs[6];
+	case 2: args[1] = regs->regs[5];
+	case 1:	args[0] = regs->regs[4];
+	case 0:
+		break;
+	default:
+		BUG();
+	}
+}
+
+static inline void syscall_set_arguments(struct task_struct *task,
+					 struct pt_regs *regs,
+					 unsigned int i, unsigned int n,
+					 const unsigned long *args)
+{
+	/* Same note as above applies */
+	BUG_ON(i);
+
+	switch (n) {
+	case 6: regs->regs[1] = args[5];
+	case 5: regs->regs[0] = args[4];
+	case 4: regs->regs[7] = args[3];
+	case 3: regs->regs[6] = args[2];
+	case 2: regs->regs[5] = args[1];
+	case 1: regs->regs[4] = args[0];
+		break;
+	default:
+		BUG();
+	}
+}
+
+static inline int syscall_get_arch(void)
+{
+	int arch = AUDIT_ARCH_SH;
+
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
+	arch |= __AUDIT_ARCH_LE;
+#endif
+	return arch;
+}
+#endif /* __ASM_SH_SYSCALL_32_H */
diff --git a/arch/sh/include/asm/syscall_64.h b/arch/sh/include/asm/syscall_64.h
new file mode 100644
index 000000000..c6a797b90
--- /dev/null
+++ b/arch/sh/include/asm/syscall_64.h
@@ -0,0 +1,78 @@
+#ifndef __ASM_SH_SYSCALL_64_H
+#define __ASM_SH_SYSCALL_64_H
+
+#include <uapi/linux/audit.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <asm/ptrace.h>
+
+/* The system call number is given by the user in R9 */
+static inline long syscall_get_nr(struct task_struct *task,
+				  struct pt_regs *regs)
+{
+	return (regs->syscall_nr >= 0) ? regs->regs[9] : -1L;
+}
+
+static inline void syscall_rollback(struct task_struct *task,
+				    struct pt_regs *regs)
+{
+	/*
+	 * XXX: This needs some thought. On SH we don't
+	 * save away the original R9 value anywhere.
+	 */
+}
+
+static inline long syscall_get_error(struct task_struct *task,
+				     struct pt_regs *regs)
+{
+	return IS_ERR_VALUE(regs->regs[9]) ? regs->regs[9] : 0;
+}
+
+static inline long syscall_get_return_value(struct task_struct *task,
+					    struct pt_regs *regs)
+{
+	return regs->regs[9];
+}
+
+static inline void syscall_set_return_value(struct task_struct *task,
+					    struct pt_regs *regs,
+					    int error, long val)
+{
+	if (error)
+		regs->regs[9] = -error;
+	else
+		regs->regs[9] = val;
+}
+
+static inline void syscall_get_arguments(struct task_struct *task,
+					 struct pt_regs *regs,
+					 unsigned int i, unsigned int n,
+					 unsigned long *args)
+{
+	BUG_ON(i + n > 6);
+	memcpy(args, &regs->regs[2 + i], n * sizeof(args[0]));
+}
+
+static inline void syscall_set_arguments(struct task_struct *task,
+					 struct pt_regs *regs,
+					 unsigned int i, unsigned int n,
+					 const unsigned long *args)
+{
+	BUG_ON(i + n > 6);
+	memcpy(&regs->regs[2 + i], args, n * sizeof(args[0]));
+}
+
+static inline int syscall_get_arch(void)
+{
+	int arch = AUDIT_ARCH_SH;
+
+#ifdef CONFIG_64BIT
+	arch |= __AUDIT_ARCH_64BIT;
+#endif
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
+	arch |= __AUDIT_ARCH_LE;
+#endif
+
+	return arch;
+}
+#endif /* __ASM_SH_SYSCALL_64_H */
diff --git a/arch/sh/include/asm/syscalls.h b/arch/sh/include/asm/syscalls.h
new file mode 100644
index 000000000..3dbfef06f
--- /dev/null
+++ b/arch/sh/include/asm/syscalls.h
@@ -0,0 +1,20 @@
+#ifndef __ASM_SH_SYSCALLS_H
+#define __ASM_SH_SYSCALLS_H
+
+#ifdef __KERNEL__
+
+asmlinkage int old_mmap(unsigned long addr, unsigned long len,
+			unsigned long prot, unsigned long flags,
+			int fd, unsigned long off);
+asmlinkage long sys_mmap2(unsigned long addr, unsigned long len,
+			  unsigned long prot, unsigned long flags,
+			  unsigned long fd, unsigned long pgoff);
+
+#ifdef CONFIG_SUPERH32
+# include <asm/syscalls_32.h>
+#else
+# include <asm/syscalls_64.h>
+#endif
+
+#endif /* __KERNEL__ */
+#endif /* __ASM_SH_SYSCALLS_H */
diff --git a/arch/sh/include/asm/syscalls_32.h b/arch/sh/include/asm/syscalls_32.h
new file mode 100644
index 000000000..4f643aa71
--- /dev/null
+++ b/arch/sh/include/asm/syscalls_32.h
@@ -0,0 +1,29 @@
+#ifndef __ASM_SH_SYSCALLS_32_H
+#define __ASM_SH_SYSCALLS_32_H
+
+#ifdef __KERNEL__
+
+#include <linux/compiler.h>
+#include <linux/linkage.h>
+#include <linux/types.h>
+
+struct pt_regs;
+
+asmlinkage int sys_sigreturn(void);
+asmlinkage int sys_rt_sigreturn(void);
+asmlinkage int sys_sh_pipe(void);
+asmlinkage ssize_t sys_pread_wrapper(unsigned int fd, char __user *buf,
+				     size_t count, long dummy, loff_t pos);
+asmlinkage ssize_t sys_pwrite_wrapper(unsigned int fd, const char __user *buf,
+				      size_t count, long dummy, loff_t pos);
+asmlinkage int sys_fadvise64_64_wrapper(int fd, u32 offset0, u32 offset1,
+					u32 len0, u32 len1, int advice);
+
+/* Misc syscall related bits */
+asmlinkage long do_syscall_trace_enter(struct pt_regs *regs);
+asmlinkage void do_syscall_trace_leave(struct pt_regs *regs);
+asmlinkage void do_notify_resume(struct pt_regs *regs, unsigned int save_r0,
+				 unsigned long thread_info_flags);
+
+#endif /* __KERNEL__ */
+#endif /* __ASM_SH_SYSCALLS_32_H */
diff --git a/arch/sh/include/asm/syscalls_64.h b/arch/sh/include/asm/syscalls_64.h
new file mode 100644
index 000000000..d62e8eb22
--- /dev/null
+++ b/arch/sh/include/asm/syscalls_64.h
@@ -0,0 +1,17 @@
+#ifndef __ASM_SH_SYSCALLS_64_H
+#define __ASM_SH_SYSCALLS_64_H
+
+#ifdef __KERNEL__
+
+#include <linux/compiler.h>
+#include <linux/linkage.h>
+#include <linux/types.h>
+
+struct pt_regs;
+
+/* Misc syscall related bits */
+asmlinkage long long do_syscall_trace_enter(struct pt_regs *regs);
+asmlinkage void do_syscall_trace_leave(struct pt_regs *regs);
+
+#endif /* __KERNEL__ */
+#endif /* __ASM_SH_SYSCALLS_64_H */
diff --git a/arch/sh/include/asm/thread_info.h b/arch/sh/include/asm/thread_info.h
new file mode 100644
index 000000000..2afa32115
--- /dev/null
+++ b/arch/sh/include/asm/thread_info.h
@@ -0,0 +1,206 @@
+#ifndef __ASM_SH_THREAD_INFO_H
+#define __ASM_SH_THREAD_INFO_H
+
+/* SuperH version
+ * Copyright (C) 2002  Niibe Yutaka
+ *
+ * The copyright of original i386 version is:
+ *
+ *  Copyright (C) 2002  David Howells (dhowells@redhat.com)
+ *  - Incorporating suggestions made by Linus Torvalds and Dave Miller
+ */
+#ifdef __KERNEL__
+
+#include <asm/page.h>
+
+/*
+ * Page fault error code bits
+ */
+#define FAULT_CODE_WRITE	(1 << 0)	/* write access */
+#define FAULT_CODE_INITIAL	(1 << 1)	/* initial page write */
+#define FAULT_CODE_ITLB		(1 << 2)	/* ITLB miss */
+#define FAULT_CODE_PROT		(1 << 3)	/* protection fault */
+#define FAULT_CODE_USER		(1 << 4)	/* user-mode access */
+
+#ifndef __ASSEMBLY__
+#include <asm/processor.h>
+
+struct thread_info {
+	struct task_struct	*task;		/* main task structure */
+	unsigned long		flags;		/* low level flags */
+	__u32			status;		/* thread synchronous flags */
+	__u32			cpu;
+	int			preempt_count; /* 0 => preemptable, <0 => BUG */
+	mm_segment_t		addr_limit;	/* thread address space */
+	unsigned long		previous_sp;	/* sp of previous stack in case
+						   of nested IRQ stacks */
+	__u8			supervisor_stack[0];
+};
+
+#endif
+
+#if defined(CONFIG_4KSTACKS)
+#define THREAD_SHIFT	12
+#else
+#define THREAD_SHIFT	13
+#endif
+
+#define THREAD_SIZE	(1 << THREAD_SHIFT)
+#define STACK_WARN	(THREAD_SIZE >> 3)
+
+/*
+ * macros/functions for gaining access to the thread information structure
+ */
+#ifndef __ASSEMBLY__
+#define INIT_THREAD_INFO(tsk)			\
+{						\
+	.task		= &tsk,			\
+	.flags		= 0,			\
+	.status		= 0,			\
+	.cpu		= 0,			\
+	.preempt_count	= INIT_PREEMPT_COUNT,	\
+	.addr_limit	= KERNEL_DS,		\
+}
+
+#define init_thread_info	(init_thread_union.thread_info)
+#define init_stack		(init_thread_union.stack)
+
+/* how to get the current stack pointer from C */
+register unsigned long current_stack_pointer asm("r15") __used;
+
+/* how to get the thread information struct from C */
+static inline struct thread_info *current_thread_info(void)
+{
+	struct thread_info *ti;
+#if defined(CONFIG_SUPERH64)
+	__asm__ __volatile__ ("getcon	cr17, %0" : "=r" (ti));
+#elif defined(CONFIG_CPU_HAS_SR_RB)
+	__asm__ __volatile__ ("stc	r7_bank, %0" : "=r" (ti));
+#else
+	unsigned long __dummy;
+
+	__asm__ __volatile__ (
+		"mov	r15, %0\n\t"
+		"and	%1, %0\n\t"
+		: "=&r" (ti), "=r" (__dummy)
+		: "1" (~(THREAD_SIZE - 1))
+		: "memory");
+#endif
+
+	return ti;
+}
+
+#define THREAD_SIZE_ORDER	(THREAD_SHIFT - PAGE_SHIFT)
+
+extern void arch_task_cache_init(void);
+extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
+extern void arch_release_task_struct(struct task_struct *tsk);
+extern void init_thread_xstate(void);
+
+#endif /* __ASSEMBLY__ */
+
+/*
+ * Thread information flags
+ *
+ * - Limited to 24 bits, upper byte used for fault code encoding.
+ *
+ * - _TIF_ALLWORK_MASK and _TIF_WORK_MASK need to fit within 2 bytes, or
+ *   we blow the tst immediate size constraints and need to fix up
+ *   arch/sh/kernel/entry-common.S.
+ */
+#define TIF_SYSCALL_TRACE	0	/* syscall trace active */
+#define TIF_SIGPENDING		1	/* signal pending */
+#define TIF_NEED_RESCHED	2	/* rescheduling necessary */
+#define TIF_SINGLESTEP		4	/* singlestepping active */
+#define TIF_SYSCALL_AUDIT	5	/* syscall auditing active */
+#define TIF_SECCOMP		6	/* secure computing */
+#define TIF_NOTIFY_RESUME	7	/* callback before returning to user */
+#define TIF_SYSCALL_TRACEPOINT	8	/* for ftrace syscall instrumentation */
+#define TIF_POLLING_NRFLAG	17	/* true if poll_idle() is polling TIF_NEED_RESCHED */
+#define TIF_MEMDIE		18	/* is terminating due to OOM killer */
+
+#define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
+#define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
+#define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
+#define _TIF_SINGLESTEP		(1 << TIF_SINGLESTEP)
+#define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
+#define _TIF_SECCOMP		(1 << TIF_SECCOMP)
+#define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
+#define _TIF_SYSCALL_TRACEPOINT	(1 << TIF_SYSCALL_TRACEPOINT)
+#define _TIF_POLLING_NRFLAG	(1 << TIF_POLLING_NRFLAG)
+
+/* work to do in syscall trace */
+#define _TIF_WORK_SYSCALL_MASK	(_TIF_SYSCALL_TRACE | _TIF_SINGLESTEP | \
+				 _TIF_SYSCALL_AUDIT | _TIF_SECCOMP    | \
+				 _TIF_SYSCALL_TRACEPOINT)
+
+/* work to do on any return to u-space */
+#define _TIF_ALLWORK_MASK	(_TIF_SYSCALL_TRACE | _TIF_SIGPENDING      | \
+				 _TIF_NEED_RESCHED  | _TIF_SYSCALL_AUDIT   | \
+				 _TIF_SINGLESTEP    | _TIF_NOTIFY_RESUME   | \
+				 _TIF_SYSCALL_TRACEPOINT)
+
+/* work to do on interrupt/exception return */
+#define _TIF_WORK_MASK		(_TIF_ALLWORK_MASK & ~(_TIF_SYSCALL_TRACE | \
+				 _TIF_SYSCALL_AUDIT | _TIF_SINGLESTEP))
+
+/*
+ * Thread-synchronous status.
+ *
+ * This is different from the flags in that nobody else
+ * ever touches our thread-synchronous status, so we don't
+ * have to worry about atomic accesses.
+ */
+#define TS_RESTORE_SIGMASK	0x0001	/* restore signal mask in do_signal() */
+#define TS_USEDFPU		0x0002	/* FPU used by this task this quantum */
+
+#ifndef __ASSEMBLY__
+
+#define HAVE_SET_RESTORE_SIGMASK	1
+static inline void set_restore_sigmask(void)
+{
+	struct thread_info *ti = current_thread_info();
+	ti->status |= TS_RESTORE_SIGMASK;
+	WARN_ON(!test_bit(TIF_SIGPENDING, (unsigned long *)&ti->flags));
+}
+
+#define TI_FLAG_FAULT_CODE_SHIFT	24
+
+/*
+ * Additional thread flag encoding
+ */
+static inline void set_thread_fault_code(unsigned int val)
+{
+	struct thread_info *ti = current_thread_info();
+	ti->flags = (ti->flags & (~0 >> (32 - TI_FLAG_FAULT_CODE_SHIFT)))
+		| (val << TI_FLAG_FAULT_CODE_SHIFT);
+}
+
+static inline unsigned int get_thread_fault_code(void)
+{
+	struct thread_info *ti = current_thread_info();
+	return ti->flags >> TI_FLAG_FAULT_CODE_SHIFT;
+}
+
+static inline void clear_restore_sigmask(void)
+{
+	current_thread_info()->status &= ~TS_RESTORE_SIGMASK;
+}
+static inline bool test_restore_sigmask(void)
+{
+	return current_thread_info()->status & TS_RESTORE_SIGMASK;
+}
+static inline bool test_and_clear_restore_sigmask(void)
+{
+	struct thread_info *ti = current_thread_info();
+	if (!(ti->status & TS_RESTORE_SIGMASK))
+		return false;
+	ti->status &= ~TS_RESTORE_SIGMASK;
+	return true;
+}
+
+#endif	/* !__ASSEMBLY__ */
+
+#endif /* __KERNEL__ */
+
+#endif /* __ASM_SH_THREAD_INFO_H */
diff --git a/arch/sh/include/asm/timex.h b/arch/sh/include/asm/timex.h
new file mode 100644
index 000000000..18bf06d9c
--- /dev/null
+++ b/arch/sh/include/asm/timex.h
@@ -0,0 +1,23 @@
+/*
+ * linux/include/asm-sh/timex.h
+ *
+ * sh architecture timex specifications
+ */
+#ifndef __ASM_SH_TIMEX_H
+#define __ASM_SH_TIMEX_H
+
+/*
+ * Only parts using the legacy CPG code for their clock framework
+ * implementation need to define their own Pclk value. If provided, this
+ * can be used for accurately setting CLOCK_TICK_RATE, otherwise we
+ * simply fall back on the i8253 PIT value.
+ */
+#ifdef CONFIG_SH_PCLK_FREQ
+#define CLOCK_TICK_RATE		(CONFIG_SH_PCLK_FREQ / 4) /* Underlying HZ */
+#else
+#define CLOCK_TICK_RATE		1193180
+#endif
+
+#include <asm-generic/timex.h>
+
+#endif /* __ASM_SH_TIMEX_H */
diff --git a/arch/sh/include/asm/tlb.h b/arch/sh/include/asm/tlb.h
new file mode 100644
index 000000000..62f80d2a9
--- /dev/null
+++ b/arch/sh/include/asm/tlb.h
@@ -0,0 +1,145 @@
+#ifndef __ASM_SH_TLB_H
+#define __ASM_SH_TLB_H
+
+#ifdef CONFIG_SUPERH64
+# include <asm/tlb_64.h>
+#endif
+
+#ifndef __ASSEMBLY__
+#include <linux/pagemap.h>
+
+#ifdef CONFIG_MMU
+#include <linux/swap.h>
+#include <asm/pgalloc.h>
+#include <asm/tlbflush.h>
+#include <asm/mmu_context.h>
+
+/*
+ * TLB handling.  This allows us to remove pages from the page
+ * tables, and efficiently handle the TLB issues.
+ */
+struct mmu_gather {
+	struct mm_struct	*mm;
+	unsigned int		fullmm;
+	unsigned long		start, end;
+};
+
+static inline void init_tlb_gather(struct mmu_gather *tlb)
+{
+	tlb->start = TASK_SIZE;
+	tlb->end = 0;
+
+	if (tlb->fullmm) {
+		tlb->start = 0;
+		tlb->end = TASK_SIZE;
+	}
+}
+
+static inline void
+tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
+{
+	tlb->mm = mm;
+	tlb->start = start;
+	tlb->end = end;
+	tlb->fullmm = !(start | (end+1));
+
+	init_tlb_gather(tlb);
+}
+
+static inline void
+tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
+{
+	if (tlb->fullmm)
+		flush_tlb_mm(tlb->mm);
+
+	/* keep the page table cache within bounds */
+	check_pgt_cache();
+}
+
+static inline void
+tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep, unsigned long address)
+{
+	if (tlb->start > address)
+		tlb->start = address;
+	if (tlb->end < address + PAGE_SIZE)
+		tlb->end = address + PAGE_SIZE;
+}
+
+/*
+ * In the case of tlb vma handling, we can optimise these away in the
+ * case where we're doing a full MM flush.  When we're doing a munmap,
+ * the vmas are adjusted to only cover the region to be torn down.
+ */
+static inline void
+tlb_start_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
+{
+	if (!tlb->fullmm)
+		flush_cache_range(vma, vma->vm_start, vma->vm_end);
+}
+
+static inline void
+tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
+{
+	if (!tlb->fullmm && tlb->end) {
+		flush_tlb_range(vma, tlb->start, tlb->end);
+		init_tlb_gather(tlb);
+	}
+}
+
+static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
+{
+}
+
+static inline void tlb_flush_mmu_free(struct mmu_gather *tlb)
+{
+}
+
+static inline void tlb_flush_mmu(struct mmu_gather *tlb)
+{
+}
+
+static inline int __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
+{
+	free_page_and_swap_cache(page);
+	return 1; /* avoid calling tlb_flush_mmu */
+}
+
+static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
+{
+	__tlb_remove_page(tlb, page);
+}
+
+#define pte_free_tlb(tlb, ptep, addr)	pte_free((tlb)->mm, ptep)
+#define pmd_free_tlb(tlb, pmdp, addr)	pmd_free((tlb)->mm, pmdp)
+#define pud_free_tlb(tlb, pudp, addr)	pud_free((tlb)->mm, pudp)
+
+#define tlb_migrate_finish(mm)		do { } while (0)
+
+#if defined(CONFIG_CPU_SH4) || defined(CONFIG_SUPERH64)
+extern void tlb_wire_entry(struct vm_area_struct *, unsigned long, pte_t);
+extern void tlb_unwire_entry(void);
+#else
+static inline void tlb_wire_entry(struct vm_area_struct *vma ,
+				  unsigned long addr, pte_t pte)
+{
+	BUG();
+}
+
+static inline void tlb_unwire_entry(void)
+{
+	BUG();
+}
+#endif
+
+#else /* CONFIG_MMU */
+
+#define tlb_start_vma(tlb, vma)				do { } while (0)
+#define tlb_end_vma(tlb, vma)				do { } while (0)
+#define __tlb_remove_tlb_entry(tlb, pte, address)	do { } while (0)
+#define tlb_flush(tlb)					do { } while (0)
+
+#include <asm-generic/tlb.h>
+
+#endif /* CONFIG_MMU */
+#endif /* __ASSEMBLY__ */
+#endif /* __ASM_SH_TLB_H */
diff --git a/arch/sh/include/asm/tlb_64.h b/arch/sh/include/asm/tlb_64.h
new file mode 100644
index 000000000..ef0ae2a28
--- /dev/null
+++ b/arch/sh/include/asm/tlb_64.h
@@ -0,0 +1,71 @@
+/*
+ * include/asm-sh/tlb_64.h
+ *
+ * Copyright (C) 2003  Paul Mundt
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+#ifndef __ASM_SH_TLB_64_H
+#define __ASM_SH_TLB_64_H
+
+/* ITLB defines */
+#define ITLB_FIXED	0x00000000	/* First fixed ITLB, see head.S */
+#define ITLB_LAST_VAR_UNRESTRICTED	0x000003F0	/* Last ITLB */
+
+/* DTLB defines */
+#define DTLB_FIXED	0x00800000	/* First fixed DTLB, see head.S */
+#define DTLB_LAST_VAR_UNRESTRICTED	0x008003F0	/* Last DTLB */
+
+#ifndef __ASSEMBLY__
+
+/**
+ * for_each_dtlb_entry - Iterate over free (non-wired) DTLB entries
+ *
+ * @tlb:	TLB entry
+ */
+#define for_each_dtlb_entry(tlb)		\
+	for (tlb  = cpu_data->dtlb.first;	\
+	     tlb <= cpu_data->dtlb.last;	\
+	     tlb += cpu_data->dtlb.step)
+
+/**
+ * for_each_itlb_entry - Iterate over free (non-wired) ITLB entries
+ *
+ * @tlb:	TLB entry
+ */
+#define for_each_itlb_entry(tlb)		\
+	for (tlb  = cpu_data->itlb.first;	\
+	     tlb <= cpu_data->itlb.last;	\
+	     tlb += cpu_data->itlb.step)
+
+/**
+ * __flush_tlb_slot - Flushes TLB slot @slot.
+ *
+ * @slot:	Address of TLB slot.
+ */
+static inline void __flush_tlb_slot(unsigned long long slot)
+{
+	__asm__ __volatile__ ("putcfg %0, 0, r63\n" : : "r" (slot));
+}
+
+#ifdef CONFIG_MMU
+/* arch/sh64/mm/tlb.c */
+int sh64_tlb_init(void);
+unsigned long long sh64_next_free_dtlb_entry(void);
+unsigned long long sh64_get_wired_dtlb_entry(void);
+int sh64_put_wired_dtlb_entry(unsigned long long entry);
+void sh64_setup_tlb_slot(unsigned long long config_addr, unsigned long eaddr,
+			 unsigned long asid, unsigned long paddr);
+void sh64_teardown_tlb_slot(unsigned long long config_addr);
+#else
+#define sh64_tlb_init()					do { } while (0)
+#define sh64_next_free_dtlb_entry()			(0)
+#define sh64_get_wired_dtlb_entry()			(0)
+#define sh64_put_wired_dtlb_entry(entry)		do { } while (0)
+#define sh64_setup_tlb_slot(conf, virt, asid, phys)	do { } while (0)
+#define sh64_teardown_tlb_slot(addr)			do { } while (0)
+#endif /* CONFIG_MMU */
+#endif /* __ASSEMBLY__ */
+#endif /* __ASM_SH_TLB_64_H */
diff --git a/arch/sh/include/asm/tlbflush.h b/arch/sh/include/asm/tlbflush.h
new file mode 100644
index 000000000..0df66f0c7
--- /dev/null
+++ b/arch/sh/include/asm/tlbflush.h
@@ -0,0 +1,51 @@
+#ifndef __ASM_SH_TLBFLUSH_H
+#define __ASM_SH_TLBFLUSH_H
+
+/*
+ * TLB flushing:
+ *
+ *  - flush_tlb_all() flushes all processes TLBs
+ *  - flush_tlb_mm(mm) flushes the specified mm context TLB's
+ *  - flush_tlb_page(vma, vmaddr) flushes one page
+ *  - flush_tlb_range(vma, start, end) flushes a range of pages
+ *  - flush_tlb_kernel_range(start, end) flushes a range of kernel pages
+ */
+extern void local_flush_tlb_all(void);
+extern void local_flush_tlb_mm(struct mm_struct *mm);
+extern void local_flush_tlb_range(struct vm_area_struct *vma,
+				  unsigned long start,
+				  unsigned long end);
+extern void local_flush_tlb_page(struct vm_area_struct *vma,
+				 unsigned long page);
+extern void local_flush_tlb_kernel_range(unsigned long start,
+					 unsigned long end);
+extern void local_flush_tlb_one(unsigned long asid, unsigned long page);
+
+extern void __flush_tlb_global(void);
+
+#ifdef CONFIG_SMP
+
+extern void flush_tlb_all(void);
+extern void flush_tlb_mm(struct mm_struct *mm);
+extern void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
+			    unsigned long end);
+extern void flush_tlb_page(struct vm_area_struct *vma, unsigned long page);
+extern void flush_tlb_kernel_range(unsigned long start, unsigned long end);
+extern void flush_tlb_one(unsigned long asid, unsigned long page);
+
+#else
+
+#define flush_tlb_all()			local_flush_tlb_all()
+#define flush_tlb_mm(mm)		local_flush_tlb_mm(mm)
+#define flush_tlb_page(vma, page)	local_flush_tlb_page(vma, page)
+#define flush_tlb_one(asid, page)	local_flush_tlb_one(asid, page)
+
+#define flush_tlb_range(vma, start, end)	\
+	local_flush_tlb_range(vma, start, end)
+
+#define flush_tlb_kernel_range(start, end)	\
+	local_flush_tlb_kernel_range(start, end)
+
+#endif /* CONFIG_SMP */
+
+#endif /* __ASM_SH_TLBFLUSH_H */
diff --git a/arch/sh/include/asm/topology.h b/arch/sh/include/asm/topology.h
new file mode 100644
index 000000000..b0a282d65
--- /dev/null
+++ b/arch/sh/include/asm/topology.h
@@ -0,0 +1,28 @@
+#ifndef _ASM_SH_TOPOLOGY_H
+#define _ASM_SH_TOPOLOGY_H
+
+#ifdef CONFIG_NUMA
+
+#define cpu_to_node(cpu)	((void)(cpu),0)
+#define parent_node(node)	((void)(node),0)
+
+#define cpumask_of_node(node)	((void)node, cpu_online_mask)
+
+#define pcibus_to_node(bus)	((void)(bus), -1)
+#define cpumask_of_pcibus(bus)	(pcibus_to_node(bus) == -1 ? \
+					cpu_all_mask : \
+					cpumask_of_node(pcibus_to_node(bus)))
+
+#endif
+
+#define mc_capable()    (1)
+
+const struct cpumask *cpu_coregroup_mask(unsigned int cpu);
+
+extern cpumask_t cpu_core_map[NR_CPUS];
+
+#define topology_core_cpumask(cpu)	(&cpu_core_map[cpu])
+
+#include <asm-generic/topology.h>
+
+#endif /* _ASM_SH_TOPOLOGY_H */
diff --git a/arch/sh/include/asm/traps.h b/arch/sh/include/asm/traps.h
new file mode 100644
index 000000000..9cc149a0d
--- /dev/null
+++ b/arch/sh/include/asm/traps.h
@@ -0,0 +1,21 @@
+#ifndef __ASM_SH_TRAPS_H
+#define __ASM_SH_TRAPS_H
+
+#include <linux/compiler.h>
+
+#ifdef CONFIG_SUPERH32
+# include <asm/traps_32.h>
+#else
+# include <asm/traps_64.h>
+#endif
+
+BUILD_TRAP_HANDLER(address_error);
+BUILD_TRAP_HANDLER(debug);
+BUILD_TRAP_HANDLER(bug);
+BUILD_TRAP_HANDLER(breakpoint);
+BUILD_TRAP_HANDLER(singlestep);
+BUILD_TRAP_HANDLER(fpu_error);
+BUILD_TRAP_HANDLER(fpu_state_restore);
+BUILD_TRAP_HANDLER(nmi);
+
+#endif /* __ASM_SH_TRAPS_H */
diff --git a/arch/sh/include/asm/traps_32.h b/arch/sh/include/asm/traps_32.h
new file mode 100644
index 000000000..17e129fe4
--- /dev/null
+++ b/arch/sh/include/asm/traps_32.h
@@ -0,0 +1,60 @@
+#ifndef __ASM_SH_TRAPS_32_H
+#define __ASM_SH_TRAPS_32_H
+
+#include <linux/types.h>
+#include <asm/mmu.h>
+
+#ifdef CONFIG_CPU_HAS_SR_RB
+#define lookup_exception_vector()	\
+({					\
+	unsigned long _vec;		\
+					\
+	__asm__ __volatile__ (		\
+		"stc r2_bank, %0\n\t"	\
+		: "=r" (_vec)		\
+	);				\
+					\
+	_vec;				\
+})
+#else
+#define lookup_exception_vector()	\
+({					\
+	unsigned long _vec;		\
+	__asm__ __volatile__ (		\
+		"mov r4, %0\n\t"	\
+		: "=r" (_vec)		\
+	);				\
+					\
+	_vec;				\
+})
+#endif
+
+static inline void trigger_address_error(void)
+{
+	__asm__ __volatile__ (
+		"ldc %0, sr\n\t"
+		"mov.l @%1, %0"
+		:
+		: "r" (0x10000000), "r" (0x80000001)
+	);
+}
+
+asmlinkage void do_address_error(struct pt_regs *regs,
+				 unsigned long writeaccess,
+				 unsigned long address);
+asmlinkage void do_divide_error(unsigned long r4);
+asmlinkage void do_reserved_inst(void);
+asmlinkage void do_illegal_slot_inst(void);
+asmlinkage void do_exception_error(void);
+
+#define BUILD_TRAP_HANDLER(name)					\
+asmlinkage void name##_trap_handler(unsigned long r4, unsigned long r5,	\
+				    unsigned long r6, unsigned long r7,	\
+				    struct pt_regs __regs)
+
+#define TRAP_HANDLER_DECL				\
+	struct pt_regs *regs = RELOC_HIDE(&__regs, 0);	\
+	unsigned int vec = regs->tra;			\
+	(void)vec;
+
+#endif /* __ASM_SH_TRAPS_32_H */
diff --git a/arch/sh/include/asm/traps_64.h b/arch/sh/include/asm/traps_64.h
new file mode 100644
index 000000000..ef5eff919
--- /dev/null
+++ b/arch/sh/include/asm/traps_64.h
@@ -0,0 +1,38 @@
+/*
+ * Copyright (C) 2000, 2001  Paolo Alberelli
+ * Copyright (C) 2003  Paul Mundt
+ * Copyright (C) 2004  Richard Curnow
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+#ifndef __ASM_SH_TRAPS_64_H
+#define __ASM_SH_TRAPS_64_H
+
+#include <cpu/registers.h>
+
+extern void phys_stext(void);
+
+#define lookup_exception_vector()		\
+({						\
+	unsigned long _vec;			\
+						\
+	__asm__ __volatile__ (			\
+		"getcon " __EXPEVT ", %0\n\t"	\
+		: "=r" (_vec)			\
+	);					\
+						\
+	_vec;					\
+})
+
+static inline void trigger_address_error(void)
+{
+	phys_stext();
+}
+
+#define BUILD_TRAP_HANDLER(name)	\
+asmlinkage void name##_trap_handler(unsigned int vec, struct pt_regs *regs)
+#define TRAP_HANDLER_DECL
+
+#endif /* __ASM_SH_TRAPS_64_H */
diff --git a/arch/sh/include/asm/types.h b/arch/sh/include/asm/types.h
new file mode 100644
index 000000000..6a31053fa
--- /dev/null
+++ b/arch/sh/include/asm/types.h
@@ -0,0 +1,20 @@
+#ifndef __ASM_SH_TYPES_H
+#define __ASM_SH_TYPES_H
+
+#include <uapi/asm/types.h>
+
+/*
+ * These aren't exported outside the kernel to avoid name space clashes
+ */
+#ifndef __ASSEMBLY__
+
+#ifdef CONFIG_SUPERH32
+typedef u16 insn_size_t;
+typedef u32 reg_size_t;
+#else
+typedef u32 insn_size_t;
+typedef u64 reg_size_t;
+#endif
+
+#endif /* __ASSEMBLY__ */
+#endif /* __ASM_SH_TYPES_H */
diff --git a/arch/sh/include/asm/uaccess.h b/arch/sh/include/asm/uaccess.h
new file mode 100644
index 000000000..a49635c51
--- /dev/null
+++ b/arch/sh/include/asm/uaccess.h
@@ -0,0 +1,211 @@
+#ifndef __ASM_SH_UACCESS_H
+#define __ASM_SH_UACCESS_H
+
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <asm/segment.h>
+
+#define VERIFY_READ    0
+#define VERIFY_WRITE   1
+
+#define __addr_ok(addr) \
+	((unsigned long __force)(addr) < current_thread_info()->addr_limit.seg)
+
+/*
+ * __access_ok: Check if address with size is OK or not.
+ *
+ * Uhhuh, this needs 33-bit arithmetic. We have a carry..
+ *
+ * sum := addr + size;  carry? --> flag = true;
+ * if (sum >= addr_limit) flag = true;
+ */
+#define __access_ok(addr, size)		\
+	(__addr_ok((addr) + (size)))
+#define access_ok(type, addr, size)	\
+	(__chk_user_ptr(addr),		\
+	 __access_ok((unsigned long __force)(addr), (size)))
+
+#define user_addr_max()	(current_thread_info()->addr_limit.seg)
+
+/*
+ * Uh, these should become the main single-value transfer routines ...
+ * They automatically use the right size if we just have the right
+ * pointer type ...
+ *
+ * As SuperH uses the same address space for kernel and user data, we
+ * can just do these as direct assignments.
+ *
+ * Careful to not
+ * (a) re-use the arguments for side effects (sizeof is ok)
+ * (b) require any knowledge of processes at this stage
+ */
+#define put_user(x,ptr)		__put_user_check((x), (ptr), sizeof(*(ptr)))
+#define get_user(x,ptr)		__get_user_check((x), (ptr), sizeof(*(ptr)))
+
+/*
+ * The "__xxx" versions do not do address space checking, useful when
+ * doing multiple accesses to the same area (the user has to do the
+ * checks by hand with "access_ok()")
+ */
+#define __put_user(x,ptr)	__put_user_nocheck((x), (ptr), sizeof(*(ptr)))
+#define __get_user(x,ptr)	__get_user_nocheck((x), (ptr), sizeof(*(ptr)))
+
+struct __large_struct { unsigned long buf[100]; };
+#define __m(x) (*(struct __large_struct __user *)(x))
+
+#define __get_user_nocheck(x,ptr,size)				\
+({								\
+	long __gu_err;						\
+	unsigned long __gu_val;					\
+	const __typeof__(*(ptr)) __user *__gu_addr = (ptr);	\
+	__chk_user_ptr(ptr);					\
+	__get_user_size(__gu_val, __gu_addr, (size), __gu_err);	\
+	(x) = (__force __typeof__(*(ptr)))__gu_val;		\
+	__gu_err;						\
+})
+
+#define __get_user_check(x,ptr,size)					\
+({									\
+	long __gu_err = -EFAULT;					\
+	unsigned long __gu_val = 0;					\
+	const __typeof__(*(ptr)) *__gu_addr = (ptr);			\
+	if (likely(access_ok(VERIFY_READ, __gu_addr, (size))))		\
+		__get_user_size(__gu_val, __gu_addr, (size), __gu_err);	\
+	(x) = (__force __typeof__(*(ptr)))__gu_val;			\
+	__gu_err;							\
+})
+
+#define __put_user_nocheck(x,ptr,size)				\
+({								\
+	long __pu_err;						\
+	__typeof__(*(ptr)) __user *__pu_addr = (ptr);		\
+	__typeof__(*(ptr)) __pu_val = x;			\
+	__chk_user_ptr(ptr);					\
+	__put_user_size(__pu_val, __pu_addr, (size), __pu_err);	\
+	__pu_err;						\
+})
+
+#define __put_user_check(x,ptr,size)				\
+({								\
+	long __pu_err = -EFAULT;				\
+	__typeof__(*(ptr)) __user *__pu_addr = (ptr);		\
+	__typeof__(*(ptr)) __pu_val = x;			\
+	if (likely(access_ok(VERIFY_WRITE, __pu_addr, size)))	\
+		__put_user_size(__pu_val, __pu_addr, (size),	\
+				__pu_err);			\
+	__pu_err;						\
+})
+
+#ifdef CONFIG_SUPERH32
+# include <asm/uaccess_32.h>
+#else
+# include <asm/uaccess_64.h>
+#endif
+
+extern long strncpy_from_user(char *dest, const char __user *src, long count);
+
+extern __must_check long strlen_user(const char __user *str);
+extern __must_check long strnlen_user(const char __user *str, long n);
+
+/* Generic arbitrary sized copy.  */
+/* Return the number of bytes NOT copied */
+__kernel_size_t __copy_user(void *to, const void *from, __kernel_size_t n);
+
+static __always_inline unsigned long
+__copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+	return __copy_user(to, (__force void *)from, n);
+}
+
+static __always_inline unsigned long __must_check
+__copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+	return __copy_user((__force void *)to, from, n);
+}
+
+#define __copy_to_user_inatomic __copy_to_user
+#define __copy_from_user_inatomic __copy_from_user
+
+/*
+ * Clear the area and return remaining number of bytes
+ * (on failure.  Usually it's 0.)
+ */
+__kernel_size_t __clear_user(void *addr, __kernel_size_t size);
+
+#define clear_user(addr,n)						\
+({									\
+	void __user * __cl_addr = (addr);				\
+	unsigned long __cl_size = (n);					\
+									\
+	if (__cl_size && access_ok(VERIFY_WRITE,			\
+		((unsigned long)(__cl_addr)), __cl_size))		\
+		__cl_size = __clear_user(__cl_addr, __cl_size);		\
+									\
+	__cl_size;							\
+})
+
+static inline unsigned long
+copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+	unsigned long __copy_from = (unsigned long) from;
+	__kernel_size_t __copy_size = (__kernel_size_t) n;
+
+	if (__copy_size && __access_ok(__copy_from, __copy_size))
+		return __copy_user(to, from, __copy_size);
+
+	return __copy_size;
+}
+
+static inline unsigned long
+copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+	unsigned long __copy_to = (unsigned long) to;
+	__kernel_size_t __copy_size = (__kernel_size_t) n;
+
+	if (__copy_size && __access_ok(__copy_to, __copy_size))
+		return __copy_user(to, from, __copy_size);
+
+	return __copy_size;
+}
+
+/*
+ * The exception table consists of pairs of addresses: the first is the
+ * address of an instruction that is allowed to fault, and the second is
+ * the address at which the program should continue.  No registers are
+ * modified, so it is entirely up to the continuation code to figure out
+ * what to do.
+ *
+ * All the routines below use bits of fixup code that are out of line
+ * with the main instruction path.  This means when everything is well,
+ * we don't even have to jump over them.  Further, they do not intrude
+ * on our cache or tlb entries.
+ */
+struct exception_table_entry {
+	unsigned long insn, fixup;
+};
+
+#if defined(CONFIG_SUPERH64) && defined(CONFIG_MMU)
+#define ARCH_HAS_SEARCH_EXTABLE
+#endif
+
+int fixup_exception(struct pt_regs *regs);
+/* Returns 0 if exception not found and fixup.unit otherwise.  */
+unsigned long search_exception_table(unsigned long addr);
+const struct exception_table_entry *search_exception_tables(unsigned long addr);
+
+extern void *set_exception_table_vec(unsigned int vec, void *handler);
+
+static inline void *set_exception_table_evt(unsigned int evt, void *handler)
+{
+	return set_exception_table_vec(evt >> 5, handler);
+}
+
+struct mem_access {
+	unsigned long (*from)(void *dst, const void __user *src, unsigned long cnt);
+	unsigned long (*to)(void __user *dst, const void *src, unsigned long cnt);
+};
+
+int handle_unaligned_access(insn_size_t instruction, struct pt_regs *regs,
+			    struct mem_access *ma, int, unsigned long address);
+
+#endif /* __ASM_SH_UACCESS_H */
diff --git a/arch/sh/include/asm/uaccess_32.h b/arch/sh/include/asm/uaccess_32.h
new file mode 100644
index 000000000..c0de7ee35
--- /dev/null
+++ b/arch/sh/include/asm/uaccess_32.h
@@ -0,0 +1,173 @@
+/*
+ * User space memory access functions
+ *
+ * Copyright (C) 1999, 2002  Niibe Yutaka
+ * Copyright (C) 2003 - 2008  Paul Mundt
+ *
+ *  Based on:
+ *     MIPS implementation version 1.15 by
+ *              Copyright (C) 1996, 1997, 1998 by Ralf Baechle
+ *     and i386 version.
+ */
+#ifndef __ASM_SH_UACCESS_32_H
+#define __ASM_SH_UACCESS_32_H
+
+#define __get_user_size(x,ptr,size,retval)			\
+do {								\
+	retval = 0;						\
+	switch (size) {						\
+	case 1:							\
+		__get_user_asm(x, ptr, retval, "b");		\
+		break;						\
+	case 2:							\
+		__get_user_asm(x, ptr, retval, "w");		\
+		break;						\
+	case 4:							\
+		__get_user_asm(x, ptr, retval, "l");		\
+		break;						\
+	default:						\
+		__get_user_unknown();				\
+		break;						\
+	}							\
+} while (0)
+
+#ifdef CONFIG_MMU
+#define __get_user_asm(x, addr, err, insn) \
+({ \
+__asm__ __volatile__( \
+	"1:\n\t" \
+	"mov." insn "	%2, %1\n\t" \
+	"2:\n" \
+	".section	.fixup,\"ax\"\n" \
+	"3:\n\t" \
+	"mov	#0, %1\n\t" \
+	"mov.l	4f, %0\n\t" \
+	"jmp	@%0\n\t" \
+	" mov	%3, %0\n\t" \
+	".balign	4\n" \
+	"4:	.long	2b\n\t" \
+	".previous\n" \
+	".section	__ex_table,\"a\"\n\t" \
+	".long	1b, 3b\n\t" \
+	".previous" \
+	:"=&r" (err), "=&r" (x) \
+	:"m" (__m(addr)), "i" (-EFAULT), "0" (err)); })
+#else
+#define __get_user_asm(x, addr, err, insn)		\
+do {							\
+	__asm__ __volatile__ (				\
+		"mov." insn "	%1, %0\n\t"		\
+		: "=&r" (x)				\
+		: "m" (__m(addr))			\
+	);						\
+} while (0)
+#endif /* CONFIG_MMU */
+
+extern void __get_user_unknown(void);
+
+#define __put_user_size(x,ptr,size,retval)		\
+do {							\
+	retval = 0;					\
+	switch (size) {					\
+	case 1:						\
+		__put_user_asm(x, ptr, retval, "b");	\
+		break;					\
+	case 2:						\
+		__put_user_asm(x, ptr, retval, "w");	\
+		break;					\
+	case 4:						\
+		__put_user_asm(x, ptr, retval, "l");	\
+		break;					\
+	case 8:						\
+		__put_user_u64(x, ptr, retval);		\
+		break;					\
+	default:					\
+		__put_user_unknown();			\
+	}						\
+} while (0)
+
+#ifdef CONFIG_MMU
+#define __put_user_asm(x, addr, err, insn)			\
+do {								\
+	__asm__ __volatile__ (					\
+		"1:\n\t"					\
+		"mov." insn "	%1, %2\n\t"			\
+		"2:\n"						\
+		".section	.fixup,\"ax\"\n"		\
+		"3:\n\t"					\
+		"mov.l	4f, %0\n\t"				\
+		"jmp	@%0\n\t"				\
+		" mov	%3, %0\n\t"				\
+		".balign	4\n"				\
+		"4:	.long	2b\n\t"				\
+		".previous\n"					\
+		".section	__ex_table,\"a\"\n\t"		\
+		".long	1b, 3b\n\t"				\
+		".previous"					\
+		: "=&r" (err)					\
+		: "r" (x), "m" (__m(addr)), "i" (-EFAULT),	\
+		  "0" (err)					\
+		: "memory"					\
+	);							\
+} while (0)
+#else
+#define __put_user_asm(x, addr, err, insn)		\
+do {							\
+	__asm__ __volatile__ (				\
+		"mov." insn "	%0, %1\n\t"		\
+		: /* no outputs */			\
+		: "r" (x), "m" (__m(addr))		\
+		: "memory"				\
+	);						\
+} while (0)
+#endif /* CONFIG_MMU */
+
+#if defined(CONFIG_CPU_LITTLE_ENDIAN)
+#define __put_user_u64(val,addr,retval) \
+({ \
+__asm__ __volatile__( \
+	"1:\n\t" \
+	"mov.l	%R1,%2\n\t" \
+	"mov.l	%S1,%T2\n\t" \
+	"2:\n" \
+	".section	.fixup,\"ax\"\n" \
+	"3:\n\t" \
+	"mov.l	4f,%0\n\t" \
+	"jmp	@%0\n\t" \
+	" mov	%3,%0\n\t" \
+	".balign	4\n" \
+	"4:	.long	2b\n\t" \
+	".previous\n" \
+	".section	__ex_table,\"a\"\n\t" \
+	".long	1b, 3b\n\t" \
+	".previous" \
+	: "=r" (retval) \
+	: "r" (val), "m" (__m(addr)), "i" (-EFAULT), "0" (retval) \
+        : "memory"); })
+#else
+#define __put_user_u64(val,addr,retval) \
+({ \
+__asm__ __volatile__( \
+	"1:\n\t" \
+	"mov.l	%S1,%2\n\t" \
+	"mov.l	%R1,%T2\n\t" \
+	"2:\n" \
+	".section	.fixup,\"ax\"\n" \
+	"3:\n\t" \
+	"mov.l	4f,%0\n\t" \
+	"jmp	@%0\n\t" \
+	" mov	%3,%0\n\t" \
+	".balign	4\n" \
+	"4:	.long	2b\n\t" \
+	".previous\n" \
+	".section	__ex_table,\"a\"\n\t" \
+	".long	1b, 3b\n\t" \
+	".previous" \
+	: "=r" (retval) \
+	: "r" (val), "m" (__m(addr)), "i" (-EFAULT), "0" (retval) \
+        : "memory"); })
+#endif
+
+extern void __put_user_unknown(void);
+
+#endif /* __ASM_SH_UACCESS_32_H */
diff --git a/arch/sh/include/asm/uaccess_64.h b/arch/sh/include/asm/uaccess_64.h
new file mode 100644
index 000000000..c01376c76
--- /dev/null
+++ b/arch/sh/include/asm/uaccess_64.h
@@ -0,0 +1,87 @@
+#ifndef __ASM_SH_UACCESS_64_H
+#define __ASM_SH_UACCESS_64_H
+
+/*
+ * include/asm-sh/uaccess_64.h
+ *
+ * Copyright (C) 2000, 2001  Paolo Alberelli
+ * Copyright (C) 2003, 2004  Paul Mundt
+ *
+ * User space memory access functions
+ *
+ * Copyright (C) 1999  Niibe Yutaka
+ *
+ *  Based on:
+ *     MIPS implementation version 1.15 by
+ *              Copyright (C) 1996, 1997, 1998 by Ralf Baechle
+ *     and i386 version.
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+
+#define __get_user_size(x,ptr,size,retval)			\
+do {								\
+	retval = 0;						\
+	switch (size) {						\
+	case 1:							\
+		retval = __get_user_asm_b((void *)&x,		\
+					  (long)ptr);		\
+		break;						\
+	case 2:							\
+		retval = __get_user_asm_w((void *)&x,		\
+					  (long)ptr);		\
+		break;						\
+	case 4:							\
+		retval = __get_user_asm_l((void *)&x,		\
+					  (long)ptr);		\
+		break;						\
+	case 8:							\
+		retval = __get_user_asm_q((void *)&x,		\
+					  (long)ptr);		\
+		break;						\
+	default:						\
+		__get_user_unknown();				\
+		break;						\
+	}							\
+} while (0)
+
+extern long __get_user_asm_b(void *, long);
+extern long __get_user_asm_w(void *, long);
+extern long __get_user_asm_l(void *, long);
+extern long __get_user_asm_q(void *, long);
+extern void __get_user_unknown(void);
+
+#define __put_user_size(x,ptr,size,retval)			\
+do {								\
+	retval = 0;						\
+	switch (size) {						\
+	case 1:							\
+		retval = __put_user_asm_b((void *)&x,		\
+					  (__force long)ptr);	\
+		break;						\
+	case 2:							\
+		retval = __put_user_asm_w((void *)&x,		\
+					  (__force long)ptr);	\
+		break;						\
+	case 4:							\
+		retval = __put_user_asm_l((void *)&x,		\
+					  (__force long)ptr);	\
+		break;						\
+	case 8:							\
+		retval = __put_user_asm_q((void *)&x,		\
+					  (__force long)ptr);	\
+		break;						\
+	default:						\
+		__put_user_unknown();				\
+	}							\
+} while (0)
+
+extern long __put_user_asm_b(void *, long);
+extern long __put_user_asm_w(void *, long);
+extern long __put_user_asm_l(void *, long);
+extern long __put_user_asm_q(void *, long);
+extern void __put_user_unknown(void);
+
+#endif /* __ASM_SH_UACCESS_64_H */
diff --git a/arch/sh/include/asm/unaligned-sh4a.h b/arch/sh/include/asm/unaligned-sh4a.h
new file mode 100644
index 000000000..95adc500c
--- /dev/null
+++ b/arch/sh/include/asm/unaligned-sh4a.h
@@ -0,0 +1,198 @@
+#ifndef __ASM_SH_UNALIGNED_SH4A_H
+#define __ASM_SH_UNALIGNED_SH4A_H
+
+/*
+ * SH-4A has support for unaligned 32-bit loads, and 32-bit loads only.
+ * Support for 64-bit accesses are done through shifting and masking
+ * relative to the endianness. Unaligned stores are not supported by the
+ * instruction encoding, so these continue to use the packed
+ * struct.
+ *
+ * The same note as with the movli.l/movco.l pair applies here, as long
+ * as the load is guaranteed to be inlined, nothing else will hook in to
+ * r0 and we get the return value for free.
+ *
+ * NOTE: Due to the fact we require r0 encoding, care should be taken to
+ * avoid mixing these heavily with other r0 consumers, such as the atomic
+ * ops. Failure to adhere to this can result in the compiler running out
+ * of spill registers and blowing up when building at low optimization
+ * levels. See http://gcc.gnu.org/bugzilla/show_bug.cgi?id=34777.
+ */
+#include <linux/unaligned/packed_struct.h>
+#include <linux/types.h>
+#include <asm/byteorder.h>
+
+static inline u16 sh4a_get_unaligned_cpu16(const u8 *p)
+{
+#ifdef __LITTLE_ENDIAN
+	return p[0] | p[1] << 8;
+#else
+	return p[0] << 8 | p[1];
+#endif
+}
+
+static __always_inline u32 sh4a_get_unaligned_cpu32(const u8 *p)
+{
+	unsigned long unaligned;
+
+	__asm__ __volatile__ (
+		"movua.l	@%1, %0\n\t"
+		 : "=z" (unaligned)
+		 : "r" (p)
+	);
+
+	return unaligned;
+}
+
+/*
+ * Even though movua.l supports auto-increment on the read side, it can
+ * only store to r0 due to instruction encoding constraints, so just let
+ * the compiler sort it out on its own.
+ */
+static inline u64 sh4a_get_unaligned_cpu64(const u8 *p)
+{
+#ifdef __LITTLE_ENDIAN
+	return (u64)sh4a_get_unaligned_cpu32(p + 4) << 32 |
+		    sh4a_get_unaligned_cpu32(p);
+#else
+	return (u64)sh4a_get_unaligned_cpu32(p) << 32 |
+		    sh4a_get_unaligned_cpu32(p + 4);
+#endif
+}
+
+static inline u16 get_unaligned_le16(const void *p)
+{
+	return le16_to_cpu(sh4a_get_unaligned_cpu16(p));
+}
+
+static inline u32 get_unaligned_le32(const void *p)
+{
+	return le32_to_cpu(sh4a_get_unaligned_cpu32(p));
+}
+
+static inline u64 get_unaligned_le64(const void *p)
+{
+	return le64_to_cpu(sh4a_get_unaligned_cpu64(p));
+}
+
+static inline u16 get_unaligned_be16(const void *p)
+{
+	return be16_to_cpu(sh4a_get_unaligned_cpu16(p));
+}
+
+static inline u32 get_unaligned_be32(const void *p)
+{
+	return be32_to_cpu(sh4a_get_unaligned_cpu32(p));
+}
+
+static inline u64 get_unaligned_be64(const void *p)
+{
+	return be64_to_cpu(sh4a_get_unaligned_cpu64(p));
+}
+
+static inline void nonnative_put_le16(u16 val, u8 *p)
+{
+	*p++ = val;
+	*p++ = val >> 8;
+}
+
+static inline void nonnative_put_le32(u32 val, u8 *p)
+{
+	nonnative_put_le16(val, p);
+	nonnative_put_le16(val >> 16, p + 2);
+}
+
+static inline void nonnative_put_le64(u64 val, u8 *p)
+{
+	nonnative_put_le32(val, p);
+	nonnative_put_le32(val >> 32, p + 4);
+}
+
+static inline void nonnative_put_be16(u16 val, u8 *p)
+{
+	*p++ = val >> 8;
+	*p++ = val;
+}
+
+static inline void nonnative_put_be32(u32 val, u8 *p)
+{
+	nonnative_put_be16(val >> 16, p);
+	nonnative_put_be16(val, p + 2);
+}
+
+static inline void nonnative_put_be64(u64 val, u8 *p)
+{
+	nonnative_put_be32(val >> 32, p);
+	nonnative_put_be32(val, p + 4);
+}
+
+static inline void put_unaligned_le16(u16 val, void *p)
+{
+#ifdef __LITTLE_ENDIAN
+	__put_unaligned_cpu16(val, p);
+#else
+	nonnative_put_le16(val, p);
+#endif
+}
+
+static inline void put_unaligned_le32(u32 val, void *p)
+{
+#ifdef __LITTLE_ENDIAN
+	__put_unaligned_cpu32(val, p);
+#else
+	nonnative_put_le32(val, p);
+#endif
+}
+
+static inline void put_unaligned_le64(u64 val, void *p)
+{
+#ifdef __LITTLE_ENDIAN
+	__put_unaligned_cpu64(val, p);
+#else
+	nonnative_put_le64(val, p);
+#endif
+}
+
+static inline void put_unaligned_be16(u16 val, void *p)
+{
+#ifdef __BIG_ENDIAN
+	__put_unaligned_cpu16(val, p);
+#else
+	nonnative_put_be16(val, p);
+#endif
+}
+
+static inline void put_unaligned_be32(u32 val, void *p)
+{
+#ifdef __BIG_ENDIAN
+	__put_unaligned_cpu32(val, p);
+#else
+	nonnative_put_be32(val, p);
+#endif
+}
+
+static inline void put_unaligned_be64(u64 val, void *p)
+{
+#ifdef __BIG_ENDIAN
+	__put_unaligned_cpu64(val, p);
+#else
+	nonnative_put_be64(val, p);
+#endif
+}
+
+/*
+ * While it's a bit non-obvious, even though the generic le/be wrappers
+ * use the __get/put_xxx prefixing, they actually wrap in to the
+ * non-prefixed get/put_xxx variants as provided above.
+ */
+#include <linux/unaligned/generic.h>
+
+#ifdef __LITTLE_ENDIAN
+# define get_unaligned __get_unaligned_le
+# define put_unaligned __put_unaligned_le
+#else
+# define get_unaligned __get_unaligned_be
+# define put_unaligned __put_unaligned_be
+#endif
+
+#endif /* __ASM_SH_UNALIGNED_SH4A_H */
diff --git a/arch/sh/include/asm/unaligned.h b/arch/sh/include/asm/unaligned.h
new file mode 100644
index 000000000..7d14e0669
--- /dev/null
+++ b/arch/sh/include/asm/unaligned.h
@@ -0,0 +1,12 @@
+#ifndef _ASM_SH_UNALIGNED_H
+#define _ASM_SH_UNALIGNED_H
+
+#ifdef CONFIG_CPU_SH4A
+/* SH-4A can handle unaligned loads in a relatively neutered fashion. */
+#include <asm/unaligned-sh4a.h>
+#else
+/* Otherwise, SH can't handle unaligned accesses. */
+#include <asm-generic/unaligned.h>
+#endif
+
+#endif /* _ASM_SH_UNALIGNED_H */
diff --git a/arch/sh/include/asm/uncached.h b/arch/sh/include/asm/uncached.h
new file mode 100644
index 000000000..6f8816b79
--- /dev/null
+++ b/arch/sh/include/asm/uncached.h
@@ -0,0 +1,58 @@
+#ifndef __ASM_SH_UNCACHED_H
+#define __ASM_SH_UNCACHED_H
+
+#include <linux/bug.h>
+
+#ifdef CONFIG_UNCACHED_MAPPING
+extern unsigned long cached_to_uncached;
+extern unsigned long uncached_size;
+extern unsigned long uncached_start, uncached_end;
+
+extern int virt_addr_uncached(unsigned long kaddr);
+extern void uncached_init(void);
+extern void uncached_resize(unsigned long size);
+
+/*
+ * Jump to uncached area.
+ * When handling TLB or caches, we need to do it from an uncached area.
+ */
+#define jump_to_uncached()			\
+do {						\
+	unsigned long __dummy;			\
+						\
+	__asm__ __volatile__(			\
+		"mova	1f, %0\n\t"		\
+		"add	%1, %0\n\t"		\
+		"jmp	@%0\n\t"		\
+		" nop\n\t"			\
+		".balign 4\n"			\
+		"1:"				\
+		: "=&z" (__dummy)		\
+		: "r" (cached_to_uncached));	\
+} while (0)
+
+/*
+ * Back to cached area.
+ */
+#define back_to_cached()				\
+do {							\
+	unsigned long __dummy;				\
+	ctrl_barrier();					\
+	__asm__ __volatile__(				\
+		"mov.l	1f, %0\n\t"			\
+		"jmp	@%0\n\t"			\
+		" nop\n\t"				\
+		".balign 4\n"				\
+		"1:	.long 2f\n"			\
+		"2:"					\
+		: "=&r" (__dummy));			\
+} while (0)
+#else
+#define virt_addr_uncached(kaddr)	(0)
+#define uncached_init()			do { } while (0)
+#define uncached_resize(size)		BUG()
+#define jump_to_uncached()		do { } while (0)
+#define back_to_cached()		do { } while (0)
+#endif
+
+#endif /* __ASM_SH_UNCACHED_H */
diff --git a/arch/sh/include/asm/unistd.h b/arch/sh/include/asm/unistd.h
new file mode 100644
index 000000000..126fe8340
--- /dev/null
+++ b/arch/sh/include/asm/unistd.h
@@ -0,0 +1,32 @@
+# ifdef CONFIG_SUPERH32
+#  include <asm/unistd_32.h>
+# else
+#  include <asm/unistd_64.h>
+# endif
+
+# define __ARCH_WANT_OLD_READDIR
+# define __ARCH_WANT_OLD_STAT
+# define __ARCH_WANT_STAT64
+# define __ARCH_WANT_SYS_ALARM
+# define __ARCH_WANT_SYS_GETHOSTNAME
+# define __ARCH_WANT_SYS_IPC
+# define __ARCH_WANT_SYS_PAUSE
+# define __ARCH_WANT_SYS_SIGNAL
+# define __ARCH_WANT_SYS_TIME
+# define __ARCH_WANT_SYS_UTIME
+# define __ARCH_WANT_SYS_WAITPID
+# define __ARCH_WANT_SYS_SOCKETCALL
+# define __ARCH_WANT_SYS_FADVISE64
+# define __ARCH_WANT_SYS_GETPGRP
+# define __ARCH_WANT_SYS_LLSEEK
+# define __ARCH_WANT_SYS_NICE
+# define __ARCH_WANT_SYS_OLD_GETRLIMIT
+# define __ARCH_WANT_SYS_OLD_UNAME
+# define __ARCH_WANT_SYS_OLDUMOUNT
+# define __ARCH_WANT_SYS_SIGPENDING
+# define __ARCH_WANT_SYS_SIGPROCMASK
+# define __ARCH_WANT_SYS_FORK
+# define __ARCH_WANT_SYS_VFORK
+# define __ARCH_WANT_SYS_CLONE
+
+#include <uapi/asm/unistd.h>
diff --git a/arch/sh/include/asm/unwinder.h b/arch/sh/include/asm/unwinder.h
new file mode 100644
index 000000000..1e65c07b3
--- /dev/null
+++ b/arch/sh/include/asm/unwinder.h
@@ -0,0 +1,31 @@
+#ifndef _LINUX_UNWINDER_H
+#define _LINUX_UNWINDER_H
+
+#include <asm/stacktrace.h>
+
+struct unwinder {
+	const char *name;
+	struct list_head list;
+	int rating;
+	void (*dump)(struct task_struct *, struct pt_regs *,
+		     unsigned long *, const struct stacktrace_ops *, void *);
+};
+
+extern int unwinder_init(void);
+extern int unwinder_register(struct unwinder *);
+
+extern void unwind_stack(struct task_struct *, struct pt_regs *,
+			 unsigned long *, const struct stacktrace_ops *,
+			 void *);
+
+extern void stack_reader_dump(struct task_struct *, struct pt_regs *,
+			      unsigned long *, const struct stacktrace_ops *,
+			      void *);
+
+/*
+ * Used by fault handling code to signal to the unwinder code that it
+ * should switch to a different unwinder.
+ */
+extern int unwinder_faulted;
+
+#endif /* _LINUX_UNWINDER_H */
diff --git a/arch/sh/include/asm/user.h b/arch/sh/include/asm/user.h
new file mode 100644
index 000000000..8fd3cf6c5
--- /dev/null
+++ b/arch/sh/include/asm/user.h
@@ -0,0 +1,67 @@
+#ifndef __ASM_SH_USER_H
+#define __ASM_SH_USER_H
+
+#include <asm/ptrace.h>
+#include <asm/page.h>
+
+/*
+ * Core file format: The core file is written in such a way that gdb
+ * can understand it and provide useful information to the user (under
+ * linux we use the `trad-core' bfd).  The file contents are as follows:
+ *
+ *  upage: 1 page consisting of a user struct that tells gdb
+ *	what is present in the file.  Directly after this is a
+ *	copy of the task_struct, which is currently not used by gdb,
+ *	but it may come in handy at some point.  All of the registers
+ *	are stored as part of the upage.  The upage should always be
+ *	only one page long.
+ *  data: The data segment follows next.  We use current->end_text to
+ *	current->brk to pick up all of the user variables, plus any memory
+ *	that may have been sbrk'ed.  No attempt is made to determine if a
+ *	page is demand-zero or if a page is totally unused, we just cover
+ *	the entire range.  All of the addresses are rounded in such a way
+ *	that an integral number of pages is written.
+ *  stack: We need the stack information in order to get a meaningful
+ *	backtrace.  We need to write the data from usp to
+ *	current->start_stack, so we round each of these in order to be able
+ *	to write an integer number of pages.
+ */
+
+#if defined(__SH5__) || defined(CONFIG_CPU_SH5)
+struct user_fpu_struct {
+	unsigned long fp_regs[32];
+	unsigned int fpscr;
+};
+#else
+struct user_fpu_struct {
+	unsigned long fp_regs[16];
+	unsigned long xfp_regs[16];
+	unsigned long fpscr;
+	unsigned long fpul;
+};
+#endif
+
+struct user {
+	struct pt_regs	regs;			/* entire machine state */
+	struct user_fpu_struct fpu;	/* Math Co-processor registers  */
+	int u_fpvalid;		/* True if math co-processor being used */
+	size_t		u_tsize;		/* text size (pages) */
+	size_t		u_dsize;		/* data size (pages) */
+	size_t		u_ssize;		/* stack size (pages) */
+	unsigned long	start_code;		/* text starting address */
+	unsigned long	start_data;		/* data starting address */
+	unsigned long	start_stack;		/* stack starting address */
+	long int	signal;			/* signal causing core dump */
+	unsigned long	u_ar0;			/* help gdb find registers */
+	struct user_fpu_struct* u_fpstate;	/* Math Co-processor pointer */
+	unsigned long	magic;			/* identifies a core file */
+	char		u_comm[32];		/* user command name */
+};
+
+#define NBPG			PAGE_SIZE
+#define UPAGES			1
+#define HOST_TEXT_START_ADDR	(u.start_code)
+#define HOST_DATA_START_ADDR	(u.start_data)
+#define HOST_STACK_END_ADDR	(u.start_stack + u.u_ssize * NBPG)
+
+#endif /* __ASM_SH_USER_H */
diff --git a/arch/sh/include/asm/vga.h b/arch/sh/include/asm/vga.h
new file mode 100644
index 000000000..06a5de8ac
--- /dev/null
+++ b/arch/sh/include/asm/vga.h
@@ -0,0 +1,6 @@
+#ifndef __ASM_SH_VGA_H
+#define __ASM_SH_VGA_H
+
+/* Stupid drivers. */
+
+#endif /* __ASM_SH_VGA_H */
diff --git a/arch/sh/include/asm/vmlinux.lds.h b/arch/sh/include/asm/vmlinux.lds.h
new file mode 100644
index 000000000..d58ad493b
--- /dev/null
+++ b/arch/sh/include/asm/vmlinux.lds.h
@@ -0,0 +1,25 @@
+#ifndef __ASM_SH_VMLINUX_LDS_H
+#define __ASM_SH_VMLINUX_LDS_H
+
+#include <asm-generic/vmlinux.lds.h>
+
+#ifdef CONFIG_DWARF_UNWINDER
+#define DWARF_EH_FRAME							\
+	.eh_frame : AT(ADDR(.eh_frame) - LOAD_OFFSET) {			\
+		  VMLINUX_SYMBOL(__start_eh_frame) = .;			\
+		  *(.eh_frame)						\
+		  VMLINUX_SYMBOL(__stop_eh_frame) = .;			\
+	}
+#else
+#define DWARF_EH_FRAME
+#endif
+
+#ifdef CONFIG_SUPERH64
+#define EXTRA_TEXT		\
+	*(.text64)		\
+	*(.text..SHmedia32)
+#else
+#define EXTRA_TEXT
+#endif
+
+#endif /* __ASM_SH_VMLINUX_LDS_H */
diff --git a/arch/sh/include/asm/watchdog.h b/arch/sh/include/asm/watchdog.h
new file mode 100644
index 000000000..85a7aca7f
--- /dev/null
+++ b/arch/sh/include/asm/watchdog.h
@@ -0,0 +1,165 @@
+/*
+ * include/asm-sh/watchdog.h
+ *
+ * Copyright (C) 2002, 2003 Paul Mundt
+ * Copyright (C) 2009 Siemens AG
+ * Copyright (C) 2009 Valentin Sitdikov
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ */
+#ifndef __ASM_SH_WATCHDOG_H
+#define __ASM_SH_WATCHDOG_H
+#ifdef __KERNEL__
+
+#include <linux/types.h>
+#include <linux/io.h>
+
+#define WTCNT_HIGH	0x5a
+#define WTCSR_HIGH	0xa5
+
+#define WTCSR_CKS2	0x04
+#define WTCSR_CKS1	0x02
+#define WTCSR_CKS0	0x01
+
+#include <cpu/watchdog.h>
+
+/*
+ * See cpu-sh2/watchdog.h for explanation of this stupidity..
+ */
+#ifndef WTCNT_R
+#  define WTCNT_R	WTCNT
+#endif
+
+#ifndef WTCSR_R
+#  define WTCSR_R	WTCSR
+#endif
+
+/*
+ * CKS0-2 supports a number of clock division ratios. At the time the watchdog
+ * is enabled, it defaults to a 41 usec overflow period .. we overload this to
+ * something a little more reasonable, and really can't deal with anything
+ * lower than WTCSR_CKS_1024, else we drop back into the usec range.
+ *
+ * Clock Division Ratio         Overflow Period
+ * --------------------------------------------
+ *     1/32 (initial value)       41 usecs
+ *     1/64                       82 usecs
+ *     1/128                     164 usecs
+ *     1/256                     328 usecs
+ *     1/512                     656 usecs
+ *     1/1024                   1.31 msecs
+ *     1/2048                   2.62 msecs
+ *     1/4096                   5.25 msecs
+ */
+#define WTCSR_CKS_32	0x00
+#define WTCSR_CKS_64	0x01
+#define WTCSR_CKS_128	0x02
+#define WTCSR_CKS_256	0x03
+#define WTCSR_CKS_512	0x04
+#define WTCSR_CKS_1024	0x05
+#define WTCSR_CKS_2048	0x06
+#define WTCSR_CKS_4096	0x07
+
+#if defined(CONFIG_CPU_SUBTYPE_SH7785) || defined(CONFIG_CPU_SUBTYPE_SH7780)
+/**
+ * 	sh_wdt_read_cnt - Read from Counter
+ * 	Reads back the WTCNT value.
+ */
+static inline __u32 sh_wdt_read_cnt(void)
+{
+	return __raw_readl(WTCNT_R);
+}
+
+/**
+ *	sh_wdt_write_cnt - Write to Counter
+ *	@val: Value to write
+ *
+ *	Writes the given value @val to the lower byte of the timer counter.
+ *	The upper byte is set manually on each write.
+ */
+static inline void sh_wdt_write_cnt(__u32 val)
+{
+	__raw_writel((WTCNT_HIGH << 24) | (__u32)val, WTCNT);
+}
+
+/**
+ *	sh_wdt_write_bst - Write to Counter
+ *	@val: Value to write
+ *
+ *	Writes the given value @val to the lower byte of the timer counter.
+ *	The upper byte is set manually on each write.
+ */
+static inline void sh_wdt_write_bst(__u32 val)
+{
+	__raw_writel((WTBST_HIGH << 24) | (__u32)val, WTBST);
+}
+/**
+ * 	sh_wdt_read_csr - Read from Control/Status Register
+ *
+ *	Reads back the WTCSR value.
+ */
+static inline __u32 sh_wdt_read_csr(void)
+{
+	return __raw_readl(WTCSR_R);
+}
+
+/**
+ * 	sh_wdt_write_csr - Write to Control/Status Register
+ * 	@val: Value to write
+ *
+ * 	Writes the given value @val to the lower byte of the control/status
+ * 	register. The upper byte is set manually on each write.
+ */
+static inline void sh_wdt_write_csr(__u32 val)
+{
+	__raw_writel((WTCSR_HIGH << 24) | (__u32)val, WTCSR);
+}
+#else
+/**
+ * 	sh_wdt_read_cnt - Read from Counter
+ * 	Reads back the WTCNT value.
+ */
+static inline __u8 sh_wdt_read_cnt(void)
+{
+	return __raw_readb(WTCNT_R);
+}
+
+/**
+ *	sh_wdt_write_cnt - Write to Counter
+ *	@val: Value to write
+ *
+ *	Writes the given value @val to the lower byte of the timer counter.
+ *	The upper byte is set manually on each write.
+ */
+static inline void sh_wdt_write_cnt(__u8 val)
+{
+	__raw_writew((WTCNT_HIGH << 8) | (__u16)val, WTCNT);
+}
+
+/**
+ * 	sh_wdt_read_csr - Read from Control/Status Register
+ *
+ *	Reads back the WTCSR value.
+ */
+static inline __u8 sh_wdt_read_csr(void)
+{
+	return __raw_readb(WTCSR_R);
+}
+
+/**
+ * 	sh_wdt_write_csr - Write to Control/Status Register
+ * 	@val: Value to write
+ *
+ * 	Writes the given value @val to the lower byte of the control/status
+ * 	register. The upper byte is set manually on each write.
+ */
+static inline void sh_wdt_write_csr(__u8 val)
+{
+	__raw_writew((WTCSR_HIGH << 8) | (__u16)val, WTCSR);
+}
+#endif /* CONFIG_CPU_SUBTYPE_SH7785 || CONFIG_CPU_SUBTYPE_SH7780 */
+#endif /* __KERNEL__ */
+#endif /* __ASM_SH_WATCHDOG_H */
diff --git a/arch/sh/include/asm/word-at-a-time.h b/arch/sh/include/asm/word-at-a-time.h
new file mode 100644
index 000000000..6e38953ff
--- /dev/null
+++ b/arch/sh/include/asm/word-at-a-time.h
@@ -0,0 +1,53 @@
+#ifndef __ASM_SH_WORD_AT_A_TIME_H
+#define __ASM_SH_WORD_AT_A_TIME_H
+
+#ifdef CONFIG_CPU_BIG_ENDIAN
+# include <asm-generic/word-at-a-time.h>
+#else
+/*
+ * Little-endian version cribbed from x86.
+ */
+struct word_at_a_time {
+	const unsigned long one_bits, high_bits;
+};
+
+#define WORD_AT_A_TIME_CONSTANTS { REPEAT_BYTE(0x01), REPEAT_BYTE(0x80) }
+
+/* Carl Chatfield / Jan Achrenius G+ version for 32-bit */
+static inline long count_masked_bytes(long mask)
+{
+	/* (000000 0000ff 00ffff ffffff) -> ( 1 1 2 3 ) */
+	long a = (0x0ff0001+mask) >> 23;
+	/* Fix the 1 for 00 case */
+	return a & mask;
+}
+
+/* Return nonzero if it has a zero */
+static inline unsigned long has_zero(unsigned long a, unsigned long *bits, const struct word_at_a_time *c)
+{
+	unsigned long mask = ((a - c->one_bits) & ~a) & c->high_bits;
+	*bits = mask;
+	return mask;
+}
+
+static inline unsigned long prep_zero_mask(unsigned long a, unsigned long bits, const struct word_at_a_time *c)
+{
+	return bits;
+}
+
+static inline unsigned long create_zero_mask(unsigned long bits)
+{
+	bits = (bits - 1) & ~bits;
+	return bits >> 7;
+}
+
+/* The mask we created is directly usable as a bytemask */
+#define zero_bytemask(mask) (mask)
+
+static inline unsigned long find_zero(unsigned long mask)
+{
+	return count_masked_bytes(mask);
+}
+#endif
+
+#endif