19 files changed, 876 insertions, 1406 deletions

diff --git a/arch/m68k/include/asm/atomic.h b/arch/m68k/include/asm/atomic.h
index 03ae3d14cd4a..307a573881ad 100644
--- a/arch/m68k/include/asm/atomic.h
+++ b/arch/m68k/include/asm/atomic.h
@@ -169,18 +169,18 @@ static inline int atomic_add_negative(int i, atomic_t *v)
 	char c;
 	__asm__ __volatile__("addl %2,%1; smi %0"
 			     : "=d" (c), "+m" (*v)
-			     : "id" (i));
+			     : ASM_DI (i));
 	return c != 0;
 }
 
 static inline void atomic_clear_mask(unsigned long mask, unsigned long *v)
 {
-	__asm__ __volatile__("andl %1,%0" : "+m" (*v) : "id" (~(mask)));
+	__asm__ __volatile__("andl %1,%0" : "+m" (*v) : ASM_DI (~(mask)));
 }
 
 static inline void atomic_set_mask(unsigned long mask, unsigned long *v)
 {
-	__asm__ __volatile__("orl %1,%0" : "+m" (*v) : "id" (mask));
+	__asm__ __volatile__("orl %1,%0" : "+m" (*v) : ASM_DI (mask));
 }
 
 static __inline__ int atomic_add_unless(atomic_t *v, int a, int u)
diff --git a/arch/m68k/include/asm/bitops.h b/arch/m68k/include/asm/bitops.h
index ce163abddaba..c6baa913592a 100644
--- a/arch/m68k/include/asm/bitops.h
+++ b/arch/m68k/include/asm/bitops.h
@@ -1,5 +1,530 @@
-#ifdef __uClinux__
-#include "bitops_no.h"
+#ifndef _M68K_BITOPS_H
+#define _M68K_BITOPS_H
+/*
+ * Copyright 1992, Linus Torvalds.
+ *
+ * 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 _LINUX_BITOPS_H
+#error only <linux/bitops.h> can be included directly
+#endif
+
+#include <linux/compiler.h>
+
+/*
+ *	Bit access functions vary across the ColdFire and 68k families.
+ *	So we will break them out here, and then macro in the ones we want.
+ *
+ *	ColdFire - supports standard bset/bclr/bchg with register operand only
+ *	68000    - supports standard bset/bclr/bchg with memory operand
+ *	>= 68020 - also supports the bfset/bfclr/bfchg instructions
+ *
+ *	Although it is possible to use only the bset/bclr/bchg with register
+ *	operands on all platforms you end up with larger generated code.
+ *	So we use the best form possible on a given platform.
+ */
+
+static inline void bset_reg_set_bit(int nr, volatile unsigned long *vaddr)
+{
+	char *p = (char *)vaddr + (nr ^ 31) / 8;
+
+	__asm__ __volatile__ ("bset %1,(%0)"
+		:
+		: "a" (p), "di" (nr & 7)
+		: "memory");
+}
+
+static inline void bset_mem_set_bit(int nr, volatile unsigned long *vaddr)
+{
+	char *p = (char *)vaddr + (nr ^ 31) / 8;
+
+	__asm__ __volatile__ ("bset %1,%0"
+		: "+m" (*p)
+		: "di" (nr & 7));
+}
+
+static inline void bfset_mem_set_bit(int nr, volatile unsigned long *vaddr)
+{
+	__asm__ __volatile__ ("bfset %1{%0:#1}"
+		:
+		: "d" (nr ^ 31), "o" (*vaddr)
+		: "memory");
+}
+
+#if defined(CONFIG_COLDFIRE)
+#define	set_bit(nr, vaddr)	bset_reg_set_bit(nr, vaddr)
+#elif defined(CONFIG_CPU_HAS_NO_BITFIELDS)
+#define	set_bit(nr, vaddr)	bset_mem_set_bit(nr, vaddr)
+#else
+#define set_bit(nr, vaddr)	(__builtin_constant_p(nr) ? \
+				bset_mem_set_bit(nr, vaddr) : \
+				bfset_mem_set_bit(nr, vaddr))
+#endif
+
+#define __set_bit(nr, vaddr)	set_bit(nr, vaddr)
+
+
+/*
+ * clear_bit() doesn't provide any barrier for the compiler.
+ */
+#define smp_mb__before_clear_bit()	barrier()
+#define smp_mb__after_clear_bit()	barrier()
+
+static inline void bclr_reg_clear_bit(int nr, volatile unsigned long *vaddr)
+{
+	char *p = (char *)vaddr + (nr ^ 31) / 8;
+
+	__asm__ __volatile__ ("bclr %1,(%0)"
+		:
+		: "a" (p), "di" (nr & 7)
+		: "memory");
+}
+
+static inline void bclr_mem_clear_bit(int nr, volatile unsigned long *vaddr)
+{
+	char *p = (char *)vaddr + (nr ^ 31) / 8;
+
+	__asm__ __volatile__ ("bclr %1,%0"
+		: "+m" (*p)
+		: "di" (nr & 7));
+}
+
+static inline void bfclr_mem_clear_bit(int nr, volatile unsigned long *vaddr)
+{
+	__asm__ __volatile__ ("bfclr %1{%0:#1}"
+		:
+		: "d" (nr ^ 31), "o" (*vaddr)
+		: "memory");
+}
+
+#if defined(CONFIG_COLDFIRE)
+#define	clear_bit(nr, vaddr)	bclr_reg_clear_bit(nr, vaddr)
+#elif defined(CONFIG_CPU_HAS_NO_BITFIELDS)
+#define	clear_bit(nr, vaddr)	bclr_mem_clear_bit(nr, vaddr)
+#else
+#define clear_bit(nr, vaddr)	(__builtin_constant_p(nr) ? \
+				bclr_mem_clear_bit(nr, vaddr) : \
+				bfclr_mem_clear_bit(nr, vaddr))
+#endif
+
+#define __clear_bit(nr, vaddr)	clear_bit(nr, vaddr)
+
+
+static inline void bchg_reg_change_bit(int nr, volatile unsigned long *vaddr)
+{
+	char *p = (char *)vaddr + (nr ^ 31) / 8;
+
+	__asm__ __volatile__ ("bchg %1,(%0)"
+		:
+		: "a" (p), "di" (nr & 7)
+		: "memory");
+}
+
+static inline void bchg_mem_change_bit(int nr, volatile unsigned long *vaddr)
+{
+	char *p = (char *)vaddr + (nr ^ 31) / 8;
+
+	__asm__ __volatile__ ("bchg %1,%0"
+		: "+m" (*p)
+		: "di" (nr & 7));
+}
+
+static inline void bfchg_mem_change_bit(int nr, volatile unsigned long *vaddr)
+{
+	__asm__ __volatile__ ("bfchg %1{%0:#1}"
+		:
+		: "d" (nr ^ 31), "o" (*vaddr)
+		: "memory");
+}
+
+#if defined(CONFIG_COLDFIRE)
+#define	change_bit(nr, vaddr)	bchg_reg_change_bit(nr, vaddr)
+#elif defined(CONFIG_CPU_HAS_NO_BITFIELDS)
+#define	change_bit(nr, vaddr)	bchg_mem_change_bit(nr, vaddr)
+#else
+#define change_bit(nr, vaddr)	(__builtin_constant_p(nr) ? \
+				bchg_mem_change_bit(nr, vaddr) : \
+				bfchg_mem_change_bit(nr, vaddr))
+#endif
+
+#define __change_bit(nr, vaddr)	change_bit(nr, vaddr)
+
+
+static inline int test_bit(int nr, const unsigned long *vaddr)
+{
+	return (vaddr[nr >> 5] & (1UL << (nr & 31))) != 0;
+}
+
+
+static inline int bset_reg_test_and_set_bit(int nr,
+					    volatile unsigned long *vaddr)
+{
+	char *p = (char *)vaddr + (nr ^ 31) / 8;
+	char retval;
+
+	__asm__ __volatile__ ("bset %2,(%1); sne %0"
+		: "=d" (retval)
+		: "a" (p), "di" (nr & 7)
+		: "memory");
+	return retval;
+}
+
+static inline int bset_mem_test_and_set_bit(int nr,
+					    volatile unsigned long *vaddr)
+{
+	char *p = (char *)vaddr + (nr ^ 31) / 8;
+	char retval;
+
+	__asm__ __volatile__ ("bset %2,%1; sne %0"
+		: "=d" (retval), "+m" (*p)
+		: "di" (nr & 7));
+	return retval;
+}
+
+static inline int bfset_mem_test_and_set_bit(int nr,
+					     volatile unsigned long *vaddr)
+{
+	char retval;
+
+	__asm__ __volatile__ ("bfset %2{%1:#1}; sne %0"
+		: "=d" (retval)
+		: "d" (nr ^ 31), "o" (*vaddr)
+		: "memory");
+	return retval;
+}
+
+#if defined(CONFIG_COLDFIRE)
+#define	test_and_set_bit(nr, vaddr)	bset_reg_test_and_set_bit(nr, vaddr)
+#elif defined(CONFIG_CPU_HAS_NO_BITFIELDS)
+#define	test_and_set_bit(nr, vaddr)	bset_mem_test_and_set_bit(nr, vaddr)
+#else
+#define test_and_set_bit(nr, vaddr)	(__builtin_constant_p(nr) ? \
+					bset_mem_test_and_set_bit(nr, vaddr) : \
+					bfset_mem_test_and_set_bit(nr, vaddr))
+#endif
+
+#define __test_and_set_bit(nr, vaddr)	test_and_set_bit(nr, vaddr)
+
+
+static inline int bclr_reg_test_and_clear_bit(int nr,
+					      volatile unsigned long *vaddr)
+{
+	char *p = (char *)vaddr + (nr ^ 31) / 8;
+	char retval;
+
+	__asm__ __volatile__ ("bclr %2,(%1); sne %0"
+		: "=d" (retval)
+		: "a" (p), "di" (nr & 7)
+		: "memory");
+	return retval;
+}
+
+static inline int bclr_mem_test_and_clear_bit(int nr,
+					      volatile unsigned long *vaddr)
+{
+	char *p = (char *)vaddr + (nr ^ 31) / 8;
+	char retval;
+
+	__asm__ __volatile__ ("bclr %2,%1; sne %0"
+		: "=d" (retval), "+m" (*p)
+		: "di" (nr & 7));
+	return retval;
+}
+
+static inline int bfclr_mem_test_and_clear_bit(int nr,
+					       volatile unsigned long *vaddr)
+{
+	char retval;
+
+	__asm__ __volatile__ ("bfclr %2{%1:#1}; sne %0"
+		: "=d" (retval)
+		: "d" (nr ^ 31), "o" (*vaddr)
+		: "memory");
+	return retval;
+}
+
+#if defined(CONFIG_COLDFIRE)
+#define	test_and_clear_bit(nr, vaddr)	bclr_reg_test_and_clear_bit(nr, vaddr)
+#elif defined(CONFIG_CPU_HAS_NO_BITFIELDS)
+#define	test_and_clear_bit(nr, vaddr)	bclr_mem_test_and_clear_bit(nr, vaddr)
+#else
+#define test_and_clear_bit(nr, vaddr)	(__builtin_constant_p(nr) ? \
+					bclr_mem_test_and_clear_bit(nr, vaddr) : \
+					bfclr_mem_test_and_clear_bit(nr, vaddr))
+#endif
+
+#define __test_and_clear_bit(nr, vaddr)	test_and_clear_bit(nr, vaddr)
+
+
+static inline int bchg_reg_test_and_change_bit(int nr,
+					       volatile unsigned long *vaddr)
+{
+	char *p = (char *)vaddr + (nr ^ 31) / 8;
+	char retval;
+
+	__asm__ __volatile__ ("bchg %2,(%1); sne %0"
+		: "=d" (retval)
+		: "a" (p), "di" (nr & 7)
+		: "memory");
+	return retval;
+}
+
+static inline int bchg_mem_test_and_change_bit(int nr,
+					       volatile unsigned long *vaddr)
+{
+	char *p = (char *)vaddr + (nr ^ 31) / 8;
+	char retval;
+
+	__asm__ __volatile__ ("bchg %2,%1; sne %0"
+		: "=d" (retval), "+m" (*p)
+		: "di" (nr & 7));
+	return retval;
+}
+
+static inline int bfchg_mem_test_and_change_bit(int nr,
+						volatile unsigned long *vaddr)
+{
+	char retval;
+
+	__asm__ __volatile__ ("bfchg %2{%1:#1}; sne %0"
+		: "=d" (retval)
+		: "d" (nr ^ 31), "o" (*vaddr)
+		: "memory");
+	return retval;
+}
+
+#if defined(CONFIG_COLDFIRE)
+#define	test_and_change_bit(nr, vaddr)	bchg_reg_test_and_change_bit(nr, vaddr)
+#elif defined(CONFIG_CPU_HAS_NO_BITFIELDS)
+#define	test_and_change_bit(nr, vaddr)	bchg_mem_test_and_change_bit(nr, vaddr)
+#else
+#define test_and_change_bit(nr, vaddr)	(__builtin_constant_p(nr) ? \
+					bchg_mem_test_and_change_bit(nr, vaddr) : \
+					bfchg_mem_test_and_change_bit(nr, vaddr))
+#endif
+
+#define __test_and_change_bit(nr, vaddr) test_and_change_bit(nr, vaddr)
+
+
+/*
+ *	The true 68020 and more advanced processors support the "bfffo"
+ *	instruction for finding bits. ColdFire and simple 68000 parts
+ *	(including CPU32) do not support this. They simply use the generic
+ *	functions.
+ */
+#if defined(CONFIG_CPU_HAS_NO_BITFIELDS)
+#include <asm-generic/bitops/find.h>
+#include <asm-generic/bitops/ffz.h>
+#else
+
+static inline int find_first_zero_bit(const unsigned long *vaddr,
+				      unsigned size)
+{
+	const unsigned long *p = vaddr;
+	int res = 32;
+	unsigned int words;
+	unsigned long num;
+
+	if (!size)
+		return 0;
+
+	words = (size + 31) >> 5;
+	while (!(num = ~*p++)) {
+		if (!--words)
+			goto out;
+	}
+
+	__asm__ __volatile__ ("bfffo %1{#0,#0},%0"
+			      : "=d" (res) : "d" (num & -num));
+	res ^= 31;
+out:
+	res += ((long)p - (long)vaddr - 4) * 8;
+	return res < size ? res : size;
+}
+#define find_first_zero_bit find_first_zero_bit
+
+static inline int find_next_zero_bit(const unsigned long *vaddr, int size,
+				     int offset)
+{
+	const unsigned long *p = vaddr + (offset >> 5);
+	int bit = offset & 31UL, res;
+
+	if (offset >= size)
+		return size;
+
+	if (bit) {
+		unsigned long num = ~*p++ & (~0UL << bit);
+		offset -= bit;
+
+		/* Look for zero in first longword */
+		__asm__ __volatile__ ("bfffo %1{#0,#0},%0"
+				      : "=d" (res) : "d" (num & -num));
+		if (res < 32) {
+			offset += res ^ 31;
+			return offset < size ? offset : size;
+		}
+		offset += 32;
+
+		if (offset >= size)
+			return size;
+	}
+	/* No zero yet, search remaining full bytes for a zero */
+	return offset + find_first_zero_bit(p, size - offset);
+}
+#define find_next_zero_bit find_next_zero_bit
+
+static inline int find_first_bit(const unsigned long *vaddr, unsigned size)
+{
+	const unsigned long *p = vaddr;
+	int res = 32;
+	unsigned int words;
+	unsigned long num;
+
+	if (!size)
+		return 0;
+
+	words = (size + 31) >> 5;
+	while (!(num = *p++)) {
+		if (!--words)
+			goto out;
+	}
+
+	__asm__ __volatile__ ("bfffo %1{#0,#0},%0"
+			      : "=d" (res) : "d" (num & -num));
+	res ^= 31;
+out:
+	res += ((long)p - (long)vaddr - 4) * 8;
+	return res < size ? res : size;
+}
+#define find_first_bit find_first_bit
+
+static inline int find_next_bit(const unsigned long *vaddr, int size,
+				int offset)
+{
+	const unsigned long *p = vaddr + (offset >> 5);
+	int bit = offset & 31UL, res;
+
+	if (offset >= size)
+		return size;
+
+	if (bit) {
+		unsigned long num = *p++ & (~0UL << bit);
+		offset -= bit;
+
+		/* Look for one in first longword */
+		__asm__ __volatile__ ("bfffo %1{#0,#0},%0"
+				      : "=d" (res) : "d" (num & -num));
+		if (res < 32) {
+			offset += res ^ 31;
+			return offset < size ? offset : size;
+		}
+		offset += 32;
+
+		if (offset >= size)
+			return size;
+	}
+	/* No one yet, search remaining full bytes for a one */
+	return offset + find_first_bit(p, size - offset);
+}
+#define find_next_bit find_next_bit
+
+/*
+ * ffz = Find First Zero in word. Undefined if no zero exists,
+ * so code should check against ~0UL first..
+ */
+static inline unsigned long ffz(unsigned long word)
+{
+	int res;
+
+	__asm__ __volatile__ ("bfffo %1{#0,#0},%0"
+			      : "=d" (res) : "d" (~word & -~word));
+	return res ^ 31;
+}
+
+#endif
+
+#ifdef __KERNEL__
+
+#if defined(CONFIG_CPU_HAS_NO_BITFIELDS)
+
+/*
+ *	The newer ColdFire family members support a "bitrev" instruction
+ *	and we can use that to implement a fast ffs. Older Coldfire parts,
+ *	and normal 68000 parts don't have anything special, so we use the
+ *	generic functions for those.
+ */
+#if (defined(__mcfisaaplus__) || defined(__mcfisac__)) && \
+	!defined(CONFIG_M68000) && !defined(CONFIG_MCPU32)
+static inline int __ffs(int x)
+{
+	__asm__ __volatile__ ("bitrev %0; ff1 %0"
+		: "=d" (x)
+		: "0" (x));
+	return x;
+}
+
+static inline int ffs(int x)
+{
+	if (!x)
+		return 0;
+	return __ffs(x) + 1;
+}
+
+#else
+#include <asm-generic/bitops/ffs.h>
+#include <asm-generic/bitops/__ffs.h>
+#endif
+
+#include <asm-generic/bitops/fls.h>
+#include <asm-generic/bitops/__fls.h>
+
 #else
-#include "bitops_mm.h"
+
+/*
+ *	ffs: find first bit set. This is defined the same way as
+ *	the libc and compiler builtin ffs routines, therefore
+ *	differs in spirit from the above ffz (man ffs).
+ */
+static inline int ffs(int x)
+{
+	int cnt;
+
+	__asm__ ("bfffo %1{#0:#0},%0"
+		: "=d" (cnt)
+		: "dm" (x & -x));
+	return 32 - cnt;
+}
+#define __ffs(x) (ffs(x) - 1)
+
+/*
+ *	fls: find last bit set.
+ */
+static inline int fls(int x)
+{
+	int cnt;
+
+	__asm__ ("bfffo %1{#0,#0},%0"
+		: "=d" (cnt)
+		: "dm" (x));
+	return 32 - cnt;
+}
+
+static inline int __fls(int x)
+{
+	return fls(x) - 1;
+}
+
 #endif
+
+#include <asm-generic/bitops/ext2-atomic.h>
+#include <asm-generic/bitops/le.h>
+#include <asm-generic/bitops/fls64.h>
+#include <asm-generic/bitops/sched.h>
+#include <asm-generic/bitops/hweight.h>
+#include <asm-generic/bitops/lock.h>
+#endif /* __KERNEL__ */
+
+#endif /* _M68K_BITOPS_H */
diff --git a/arch/m68k/include/asm/bitops_mm.h b/arch/m68k/include/asm/bitops_mm.h
deleted file mode 100644
index 89cf5b814a4d..000000000000
--- a/arch/m68k/include/asm/bitops_mm.h
+++ /dev/null
@@ -1,501 +0,0 @@
-#ifndef _M68K_BITOPS_H
-#define _M68K_BITOPS_H
-/*
- * Copyright 1992, Linus Torvalds.
- *
- * 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 _LINUX_BITOPS_H
-#error only <linux/bitops.h> can be included directly
-#endif
-
-#include <linux/compiler.h>
-
-/*
- * Require 68020 or better.
- *
- * They use the standard big-endian m680x0 bit ordering.
- */
-
-#define test_and_set_bit(nr,vaddr) \
-  (__builtin_constant_p(nr) ? \
-   __constant_test_and_set_bit(nr, vaddr) : \
-   __generic_test_and_set_bit(nr, vaddr))
-
-#define __test_and_set_bit(nr,vaddr) test_and_set_bit(nr,vaddr)
-
-static inline int __constant_test_and_set_bit(int nr, unsigned long *vaddr)
-{
-	char *p = (char *)vaddr + (nr ^ 31) / 8;
-	char retval;
-
-	__asm__ __volatile__ ("bset %2,%1; sne %0"
-			: "=d" (retval), "+m" (*p)
-			: "di" (nr & 7));
-
-	return retval;
-}
-
-static inline int __generic_test_and_set_bit(int nr, unsigned long *vaddr)
-{
-	char retval;
-
-	__asm__ __volatile__ ("bfset %2{%1:#1}; sne %0"
-			: "=d" (retval) : "d" (nr^31), "o" (*vaddr) : "memory");
-
-	return retval;
-}
-
-#define set_bit(nr,vaddr) \
-  (__builtin_constant_p(nr) ? \
-   __constant_set_bit(nr, vaddr) : \
-   __generic_set_bit(nr, vaddr))
-
-#define __set_bit(nr,vaddr) set_bit(nr,vaddr)
-
-static inline void __constant_set_bit(int nr, volatile unsigned long *vaddr)
-{
-	char *p = (char *)vaddr + (nr ^ 31) / 8;
-	__asm__ __volatile__ ("bset %1,%0"
-			: "+m" (*p) : "di" (nr & 7));
-}
-
-static inline void __generic_set_bit(int nr, volatile unsigned long *vaddr)
-{
-	__asm__ __volatile__ ("bfset %1{%0:#1}"
-			: : "d" (nr^31), "o" (*vaddr) : "memory");
-}
-
-#define test_and_clear_bit(nr,vaddr) \
-  (__builtin_constant_p(nr) ? \
-   __constant_test_and_clear_bit(nr, vaddr) : \
-   __generic_test_and_clear_bit(nr, vaddr))
-
-#define __test_and_clear_bit(nr,vaddr) test_and_clear_bit(nr,vaddr)
-
-static inline int __constant_test_and_clear_bit(int nr, unsigned long *vaddr)
-{
-	char *p = (char *)vaddr + (nr ^ 31) / 8;
-	char retval;
-
-	__asm__ __volatile__ ("bclr %2,%1; sne %0"
-			: "=d" (retval), "+m" (*p)
-			: "di" (nr & 7));
-
-	return retval;
-}
-
-static inline int __generic_test_and_clear_bit(int nr, unsigned long *vaddr)
-{
-	char retval;
-
-	__asm__ __volatile__ ("bfclr %2{%1:#1}; sne %0"
-			: "=d" (retval) : "d" (nr^31), "o" (*vaddr) : "memory");
-
-	return retval;
-}
-
-/*
- * clear_bit() doesn't provide any barrier for the compiler.
- */
-#define smp_mb__before_clear_bit()	barrier()
-#define smp_mb__after_clear_bit()	barrier()
-
-#define clear_bit(nr,vaddr) \
-  (__builtin_constant_p(nr) ? \
-   __constant_clear_bit(nr, vaddr) : \
-   __generic_clear_bit(nr, vaddr))
-#define __clear_bit(nr,vaddr) clear_bit(nr,vaddr)
-
-static inline void __constant_clear_bit(int nr, volatile unsigned long *vaddr)
-{
-	char *p = (char *)vaddr + (nr ^ 31) / 8;
-	__asm__ __volatile__ ("bclr %1,%0"
-			: "+m" (*p) : "di" (nr & 7));
-}
-
-static inline void __generic_clear_bit(int nr, volatile unsigned long *vaddr)
-{
-	__asm__ __volatile__ ("bfclr %1{%0:#1}"
-			: : "d" (nr^31), "o" (*vaddr) : "memory");
-}
-
-#define test_and_change_bit(nr,vaddr) \
-  (__builtin_constant_p(nr) ? \
-   __constant_test_and_change_bit(nr, vaddr) : \
-   __generic_test_and_change_bit(nr, vaddr))
-
-#define __test_and_change_bit(nr,vaddr) test_and_change_bit(nr,vaddr)
-#define __change_bit(nr,vaddr) change_bit(nr,vaddr)
-
-static inline int __constant_test_and_change_bit(int nr, unsigned long *vaddr)
-{
-	char *p = (char *)vaddr + (nr ^ 31) / 8;
-	char retval;
-
-	__asm__ __volatile__ ("bchg %2,%1; sne %0"
-			: "=d" (retval), "+m" (*p)
-			: "di" (nr & 7));
-
-	return retval;
-}
-
-static inline int __generic_test_and_change_bit(int nr, unsigned long *vaddr)
-{
-	char retval;
-
-	__asm__ __volatile__ ("bfchg %2{%1:#1}; sne %0"
-			: "=d" (retval) : "d" (nr^31), "o" (*vaddr) : "memory");
-
-	return retval;
-}
-
-#define change_bit(nr,vaddr) \
-  (__builtin_constant_p(nr) ? \
-   __constant_change_bit(nr, vaddr) : \
-   __generic_change_bit(nr, vaddr))
-
-static inline void __constant_change_bit(int nr, unsigned long *vaddr)
-{
-	char *p = (char *)vaddr + (nr ^ 31) / 8;
-	__asm__ __volatile__ ("bchg %1,%0"
-			: "+m" (*p) : "di" (nr & 7));
-}
-
-static inline void __generic_change_bit(int nr, unsigned long *vaddr)
-{
-	__asm__ __volatile__ ("bfchg %1{%0:#1}"
-			: : "d" (nr^31), "o" (*vaddr) : "memory");
-}
-
-static inline int test_bit(int nr, const unsigned long *vaddr)
-{
-	return (vaddr[nr >> 5] & (1UL << (nr & 31))) != 0;
-}
-
-static inline int find_first_zero_bit(const unsigned long *vaddr,
-				      unsigned size)
-{
-	const unsigned long *p = vaddr;
-	int res = 32;
-	unsigned int words;
-	unsigned long num;
-
-	if (!size)
-		return 0;
-
-	words = (size + 31) >> 5;
-	while (!(num = ~*p++)) {
-		if (!--words)
-			goto out;
-	}
-
-	__asm__ __volatile__ ("bfffo %1{#0,#0},%0"
-			      : "=d" (res) : "d" (num & -num));
-	res ^= 31;
-out:
-	res += ((long)p - (long)vaddr - 4) * 8;
-	return res < size ? res : size;
-}
-#define find_first_zero_bit find_first_zero_bit
-
-static inline int find_next_zero_bit(const unsigned long *vaddr, int size,
-				     int offset)
-{
-	const unsigned long *p = vaddr + (offset >> 5);
-	int bit = offset & 31UL, res;
-
-	if (offset >= size)
-		return size;
-
-	if (bit) {
-		unsigned long num = ~*p++ & (~0UL << bit);
-		offset -= bit;
-
-		/* Look for zero in first longword */
-		__asm__ __volatile__ ("bfffo %1{#0,#0},%0"
-				      : "=d" (res) : "d" (num & -num));
-		if (res < 32) {
-			offset += res ^ 31;
-			return offset < size ? offset : size;
-		}
-		offset += 32;
-
-		if (offset >= size)
-			return size;
-	}
-	/* No zero yet, search remaining full bytes for a zero */
-	return offset + find_first_zero_bit(p, size - offset);
-}
-#define find_next_zero_bit find_next_zero_bit
-
-static inline int find_first_bit(const unsigned long *vaddr, unsigned size)
-{
-	const unsigned long *p = vaddr;
-	int res = 32;
-	unsigned int words;
-	unsigned long num;
-
-	if (!size)
-		return 0;
-
-	words = (size + 31) >> 5;
-	while (!(num = *p++)) {
-		if (!--words)
-			goto out;
-	}
-
-	__asm__ __volatile__ ("bfffo %1{#0,#0},%0"
-			      : "=d" (res) : "d" (num & -num));
-	res ^= 31;
-out:
-	res += ((long)p - (long)vaddr - 4) * 8;
-	return res < size ? res : size;
-}
-#define find_first_bit find_first_bit
-
-static inline int find_next_bit(const unsigned long *vaddr, int size,
-				int offset)
-{
-	const unsigned long *p = vaddr + (offset >> 5);
-	int bit = offset & 31UL, res;
-
-	if (offset >= size)
-		return size;
-
-	if (bit) {
-		unsigned long num = *p++ & (~0UL << bit);
-		offset -= bit;
-
-		/* Look for one in first longword */
-		__asm__ __volatile__ ("bfffo %1{#0,#0},%0"
-				      : "=d" (res) : "d" (num & -num));
-		if (res < 32) {
-			offset += res ^ 31;
-			return offset < size ? offset : size;
-		}
-		offset += 32;
-
-		if (offset >= size)
-			return size;
-	}
-	/* No one yet, search remaining full bytes for a one */
-	return offset + find_first_bit(p, size - offset);
-}
-#define find_next_bit find_next_bit
-
-/*
- * ffz = Find First Zero in word. Undefined if no zero exists,
- * so code should check against ~0UL first..
- */
-static inline unsigned long ffz(unsigned long word)
-{
-	int res;
-
-	__asm__ __volatile__ ("bfffo %1{#0,#0},%0"
-			      : "=d" (res) : "d" (~word & -~word));
-	return res ^ 31;
-}
-
-#ifdef __KERNEL__
-
-/*
- * ffs: find first bit set. This is defined the same way as
- * the libc and compiler builtin ffs routines, therefore
- * differs in spirit from the above ffz (man ffs).
- */
-
-static inline int ffs(int x)
-{
-	int cnt;
-
-	asm ("bfffo %1{#0:#0},%0" : "=d" (cnt) : "dm" (x & -x));
-
-	return 32 - cnt;
-}
-#define __ffs(x) (ffs(x) - 1)
-
-/*
- * fls: find last bit set.
- */
-
-static inline int fls(int x)
-{
-	int cnt;
-
-	asm ("bfffo %1{#0,#0},%0" : "=d" (cnt) : "dm" (x));
-
-	return 32 - cnt;
-}
-
-static inline int __fls(int x)
-{
-	return fls(x) - 1;
-}
-
-#include <asm-generic/bitops/fls64.h>
-#include <asm-generic/bitops/sched.h>
-#include <asm-generic/bitops/hweight.h>
-#include <asm-generic/bitops/lock.h>
-
-/* Bitmap functions for the little endian bitmap. */
-
-static inline void __set_bit_le(int nr, void *addr)
-{
-	__set_bit(nr ^ 24, addr);
-}
-
-static inline void __clear_bit_le(int nr, void *addr)
-{
-	__clear_bit(nr ^ 24, addr);
-}
-
-static inline int __test_and_set_bit_le(int nr, void *addr)
-{
-	return __test_and_set_bit(nr ^ 24, addr);
-}
-
-static inline int test_and_set_bit_le(int nr, void *addr)
-{
-	return test_and_set_bit(nr ^ 24, addr);
-}
-
-static inline int __test_and_clear_bit_le(int nr, void *addr)
-{
-	return __test_and_clear_bit(nr ^ 24, addr);
-}
-
-static inline int test_and_clear_bit_le(int nr, void *addr)
-{
-	return test_and_clear_bit(nr ^ 24, addr);
-}
-
-static inline int test_bit_le(int nr, const void *vaddr)
-{
-	const unsigned char *p = vaddr;
-	return (p[nr >> 3] & (1U << (nr & 7))) != 0;
-}
-
-static inline int find_first_zero_bit_le(const void *vaddr, unsigned size)
-{
-	const unsigned long *p = vaddr, *addr = vaddr;
-	int res = 0;
-	unsigned int words;
-
-	if (!size)
-		return 0;
-
-	words = (size >> 5) + ((size & 31) > 0);
-	while (*p++ == ~0UL) {
-		if (--words == 0)
-			goto out;
-	}
-
-	--p;
-	for (res = 0; res < 32; res++)
-		if (!test_bit_le(res, p))
-			break;
-out:
-	res += (p - addr) * 32;
-	return res < size ? res : size;
-}
-#define find_first_zero_bit_le find_first_zero_bit_le
-
-static inline unsigned long find_next_zero_bit_le(const void *addr,
-		unsigned long size, unsigned long offset)
-{
-	const unsigned long *p = addr;
-	int bit = offset & 31UL, res;
-
-	if (offset >= size)
-		return size;
-
-	p += offset >> 5;
-
-	if (bit) {
-		offset -= bit;
-		/* Look for zero in first longword */
-		for (res = bit; res < 32; res++)
-			if (!test_bit_le(res, p)) {
-				offset += res;
-				return offset < size ? offset : size;
-			}
-		p++;
-		offset += 32;
-
-		if (offset >= size)
-			return size;
-	}
-	/* No zero yet, search remaining full bytes for a zero */
-	return offset + find_first_zero_bit_le(p, size - offset);
-}
-#define find_next_zero_bit_le find_next_zero_bit_le
-
-static inline int find_first_bit_le(const void *vaddr, unsigned size)
-{
-	const unsigned long *p = vaddr, *addr = vaddr;
-	int res = 0;
-	unsigned int words;
-
-	if (!size)
-		return 0;
-
-	words = (size >> 5) + ((size & 31) > 0);
-	while (*p++ == 0UL) {
-		if (--words == 0)
-			goto out;
-	}
-
-	--p;
-	for (res = 0; res < 32; res++)
-		if (test_bit_le(res, p))
-			break;
-out:
-	res += (p - addr) * 32;
-	return res < size ? res : size;
-}
-#define find_first_bit_le find_first_bit_le
-
-static inline unsigned long find_next_bit_le(const void *addr,
-		unsigned long size, unsigned long offset)
-{
-	const unsigned long *p = addr;
-	int bit = offset & 31UL, res;
-
-	if (offset >= size)
-		return size;
-
-	p += offset >> 5;
-
-	if (bit) {
-		offset -= bit;
-		/* Look for one in first longword */
-		for (res = bit; res < 32; res++)
-			if (test_bit_le(res, p)) {
-				offset += res;
-				return offset < size ? offset : size;
-			}
-		p++;
-		offset += 32;
-
-		if (offset >= size)
-			return size;
-	}
-	/* No set bit yet, search remaining full bytes for a set bit */
-	return offset + find_first_bit_le(p, size - offset);
-}
-#define find_next_bit_le find_next_bit_le
-
-/* Bitmap functions for the ext2 filesystem. */
-
-#define ext2_set_bit_atomic(lock, nr, addr)	\
-	test_and_set_bit_le(nr, addr)
-#define ext2_clear_bit_atomic(lock, nr, addr)	\
-	test_and_clear_bit_le(nr, addr)
-
-#endif /* __KERNEL__ */
-
-#endif /* _M68K_BITOPS_H */
diff --git a/arch/m68k/include/asm/bitops_no.h b/arch/m68k/include/asm/bitops_no.h
deleted file mode 100644
index 72e85acdd7bd..000000000000
--- a/arch/m68k/include/asm/bitops_no.h
+++ /dev/null
@@ -1,333 +0,0 @@
-#ifndef _M68KNOMMU_BITOPS_H
-#define _M68KNOMMU_BITOPS_H
-
-/*
- * Copyright 1992, Linus Torvalds.
- */
-
-#include <linux/compiler.h>
-#include <asm/byteorder.h>	/* swab32 */
-
-#ifdef __KERNEL__
-
-#ifndef _LINUX_BITOPS_H
-#error only <linux/bitops.h> can be included directly
-#endif
-
-#if defined (__mcfisaaplus__) || defined (__mcfisac__)
-static inline int ffs(unsigned int val)
-{
-        if (!val)
-                return 0;
-
-        asm volatile(
-                        "bitrev %0\n\t"
-                        "ff1 %0\n\t"
-                        : "=d" (val)
-                        : "0" (val)
-		    );
-        val++;
-        return val;
-}
-
-static inline int __ffs(unsigned int val)
-{
-        asm volatile(
-                        "bitrev %0\n\t"
-                        "ff1 %0\n\t"
-                        : "=d" (val)
-                        : "0" (val)
-		    );
-        return val;
-}
-
-#else
-#include <asm-generic/bitops/ffs.h>
-#include <asm-generic/bitops/__ffs.h>
-#endif
-
-#include <asm-generic/bitops/sched.h>
-#include <asm-generic/bitops/ffz.h>
-
-static __inline__ void set_bit(int nr, volatile unsigned long * addr)
-{
-#ifdef CONFIG_COLDFIRE
-	__asm__ __volatile__ ("lea %0,%%a0; bset %1,(%%a0)"
-	     : "+m" (((volatile char *)addr)[(nr^31) >> 3])
-	     : "d" (nr)
-	     : "%a0", "cc");
-#else
-	__asm__ __volatile__ ("bset %1,%0"
-	     : "+m" (((volatile char *)addr)[(nr^31) >> 3])
-	     : "di" (nr)
-	     : "cc");
-#endif
-}
-
-#define __set_bit(nr, addr) set_bit(nr, addr)
-
-/*
- * clear_bit() doesn't provide any barrier for the compiler.
- */
-#define smp_mb__before_clear_bit()	barrier()
-#define smp_mb__after_clear_bit()	barrier()
-
-static __inline__ void clear_bit(int nr, volatile unsigned long * addr)
-{
-#ifdef CONFIG_COLDFIRE
-	__asm__ __volatile__ ("lea %0,%%a0; bclr %1,(%%a0)"
-	     : "+m" (((volatile char *)addr)[(nr^31) >> 3])
-	     : "d" (nr)
-	     : "%a0", "cc");
-#else
-	__asm__ __volatile__ ("bclr %1,%0"
-	     : "+m" (((volatile char *)addr)[(nr^31) >> 3])
-	     : "di" (nr)
-	     : "cc");
-#endif
-}
-
-#define __clear_bit(nr, addr) clear_bit(nr, addr)
-
-static __inline__ void change_bit(int nr, volatile unsigned long * addr)
-{
-#ifdef CONFIG_COLDFIRE
-	__asm__ __volatile__ ("lea %0,%%a0; bchg %1,(%%a0)"
-	     : "+m" (((volatile char *)addr)[(nr^31) >> 3])
-	     : "d" (nr)
-	     : "%a0", "cc");
-#else
-	__asm__ __volatile__ ("bchg %1,%0"
-	     : "+m" (((volatile char *)addr)[(nr^31) >> 3])
-	     : "di" (nr)
-	     : "cc");
-#endif
-}
-
-#define __change_bit(nr, addr) change_bit(nr, addr)
-
-static __inline__ int test_and_set_bit(int nr, volatile unsigned long * addr)
-{
-	char retval;
-
-#ifdef CONFIG_COLDFIRE
-	__asm__ __volatile__ ("lea %1,%%a0; bset %2,(%%a0); sne %0"
-	     : "=d" (retval), "+m" (((volatile char *)addr)[(nr^31) >> 3])
-	     : "d" (nr)
-	     : "%a0");
-#else
-	__asm__ __volatile__ ("bset %2,%1; sne %0"
-	     : "=d" (retval), "+m" (((volatile char *)addr)[(nr^31) >> 3])
-	     : "di" (nr)
-	     /* No clobber */);
-#endif
-
-	return retval;
-}
-
-#define __test_and_set_bit(nr, addr) test_and_set_bit(nr, addr)
-
-static __inline__ int test_and_clear_bit(int nr, volatile unsigned long * addr)
-{
-	char retval;
-
-#ifdef CONFIG_COLDFIRE
-	__asm__ __volatile__ ("lea %1,%%a0; bclr %2,(%%a0); sne %0"
-	     : "=d" (retval), "+m" (((volatile char *)addr)[(nr^31) >> 3])
-	     : "d" (nr)
-	     : "%a0");
-#else
-	__asm__ __volatile__ ("bclr %2,%1; sne %0"
-	     : "=d" (retval), "+m" (((volatile char *)addr)[(nr^31) >> 3])
-	     : "di" (nr)
-	     /* No clobber */);
-#endif
-
-	return retval;
-}
-
-#define __test_and_clear_bit(nr, addr) test_and_clear_bit(nr, addr)
-
-static __inline__ int test_and_change_bit(int nr, volatile unsigned long * addr)
-{
-	char retval;
-
-#ifdef CONFIG_COLDFIRE
-	__asm__ __volatile__ ("lea %1,%%a0\n\tbchg %2,(%%a0)\n\tsne %0"
-	     : "=d" (retval), "+m" (((volatile char *)addr)[(nr^31) >> 3])
-	     : "d" (nr)
-	     : "%a0");
-#else
-	__asm__ __volatile__ ("bchg %2,%1; sne %0"
-	     : "=d" (retval), "+m" (((volatile char *)addr)[(nr^31) >> 3])
-	     : "di" (nr)
-	     /* No clobber */);
-#endif
-
-	return retval;
-}
-
-#define __test_and_change_bit(nr, addr) test_and_change_bit(nr, addr)
-
-/*
- * This routine doesn't need to be atomic.
- */
-static __inline__ int __constant_test_bit(int nr, const volatile unsigned long * addr)
-{
-	return ((1UL << (nr & 31)) & (((const volatile unsigned int *) addr)[nr >> 5])) != 0;
-}
-
-static __inline__ int __test_bit(int nr, const volatile unsigned long * addr)
-{
-	int 	* a = (int *) addr;
-	int	mask;
-
-	a += nr >> 5;
-	mask = 1 << (nr & 0x1f);
-	return ((mask & *a) != 0);
-}
-
-#define test_bit(nr,addr) \
-(__builtin_constant_p(nr) ? \
- __constant_test_bit((nr),(addr)) : \
- __test_bit((nr),(addr)))
-
-#include <asm-generic/bitops/find.h>
-#include <asm-generic/bitops/hweight.h>
-#include <asm-generic/bitops/lock.h>
-
-#define BITOP_LE_SWIZZLE	((BITS_PER_LONG-1) & ~0x7)
-
-static inline void __set_bit_le(int nr, void *addr)
-{
-	__set_bit(nr ^ BITOP_LE_SWIZZLE, addr);
-}
-
-static inline void __clear_bit_le(int nr, void *addr)
-{
-	__clear_bit(nr ^ BITOP_LE_SWIZZLE, addr);
-}
-
-static inline int __test_and_set_bit_le(int nr, volatile void *addr)
-{
-	char retval;
-
-#ifdef CONFIG_COLDFIRE
-	__asm__ __volatile__ ("lea %1,%%a0; bset %2,(%%a0); sne %0"
-	     : "=d" (retval), "+m" (((volatile char *)addr)[nr >> 3])
-	     : "d" (nr)
-	     : "%a0");
-#else
-	__asm__ __volatile__ ("bset %2,%1; sne %0"
-	     : "=d" (retval), "+m" (((volatile char *)addr)[nr >> 3])
-	     : "di" (nr)
-	     /* No clobber */);
-#endif
-
-	return retval;
-}
-
-static inline int __test_and_clear_bit_le(int nr, volatile void *addr)
-{
-	char retval;
-
-#ifdef CONFIG_COLDFIRE
-	__asm__ __volatile__ ("lea %1,%%a0; bclr %2,(%%a0); sne %0"
-	     : "=d" (retval), "+m" (((volatile char *)addr)[nr >> 3])
-	     : "d" (nr)
-	     : "%a0");
-#else
-	__asm__ __volatile__ ("bclr %2,%1; sne %0"
-	     : "=d" (retval), "+m" (((volatile char *)addr)[nr >> 3])
-	     : "di" (nr)
-	     /* No clobber */);
-#endif
-
-	return retval;
-}
-
-#include <asm-generic/bitops/ext2-atomic.h>
-
-static inline int test_bit_le(int nr, const volatile void *addr)
-{
-	char retval;
-
-#ifdef CONFIG_COLDFIRE
-	__asm__ __volatile__ ("lea %1,%%a0; btst %2,(%%a0); sne %0"
-	     : "=d" (retval)
-	     : "m" (((const volatile char *)addr)[nr >> 3]), "d" (nr)
-	     : "%a0");
-#else
-	__asm__ __volatile__ ("btst %2,%1; sne %0"
-	     : "=d" (retval)
-	     : "m" (((const volatile char *)addr)[nr >> 3]), "di" (nr)
-	     /* No clobber */);
-#endif
-
-	return retval;
-}
-
-#define find_first_zero_bit_le(addr, size)	\
-	find_next_zero_bit_le((addr), (size), 0)
-
-static inline unsigned long find_next_zero_bit_le(void *addr, unsigned long size, unsigned long offset)
-{
-	unsigned long *p = ((unsigned long *) addr) + (offset >> 5);
-	unsigned long result = offset & ~31UL;
-	unsigned long tmp;
-
-	if (offset >= size)
-		return size;
-	size -= result;
-	offset &= 31UL;
-	if(offset) {
-		/* We hold the little endian value in tmp, but then the
-		 * shift is illegal. So we could keep a big endian value
-		 * in tmp, like this:
-		 *
-		 * tmp = __swab32(*(p++));
-		 * tmp |= ~0UL >> (32-offset);
-		 *
-		 * but this would decrease performance, so we change the
-		 * shift:
-		 */
-		tmp = *(p++);
-		tmp |= __swab32(~0UL >> (32-offset));
-		if(size < 32)
-			goto found_first;
-		if(~tmp)
-			goto found_middle;
-		size -= 32;
-		result += 32;
-	}
-	while(size & ~31UL) {
-		if(~(tmp = *(p++)))
-			goto found_middle;
-		result += 32;
-		size -= 32;
-	}
-	if(!size)
-		return result;
-	tmp = *p;
-
-found_first:
-	/* tmp is little endian, so we would have to swab the shift,
-	 * see above. But then we have to swab tmp below for ffz, so
-	 * we might as well do this here.
-	 */
-	return result + ffz(__swab32(tmp) | (~0UL << size));
-found_middle:
-	return result + ffz(__swab32(tmp));
-}
-#define find_next_zero_bit_le find_next_zero_bit_le
-
-extern unsigned long find_next_bit_le(const void *addr,
-		unsigned long size, unsigned long offset);
-
-#endif /* __KERNEL__ */
-
-#include <asm-generic/bitops/fls.h>
-#include <asm-generic/bitops/__fls.h>
-#include <asm-generic/bitops/fls64.h>
-
-#endif /* _M68KNOMMU_BITOPS_H */
diff --git a/arch/m68k/include/asm/delay.h b/arch/m68k/include/asm/delay.h
index d2598e3dd7b2..9c09becfd4c9 100644
--- a/arch/m68k/include/asm/delay.h
+++ b/arch/m68k/include/asm/delay.h
@@ -1,5 +1,96 @@
-#ifdef __uClinux__
-#include "delay_no.h"
+#ifndef _M68K_DELAY_H
+#define _M68K_DELAY_H
+
+#include <asm/param.h>
+
+/*
+ * Copyright (C) 1994 Hamish Macdonald
+ * Copyright (C) 2004 Greg Ungerer <gerg@uclinux.com>
+ *
+ * Delay routines, using a pre-computed "loops_per_jiffy" value.
+ */
+
+#if defined(CONFIG_COLDFIRE)
+/*
+ * The ColdFire runs the delay loop at significantly different speeds
+ * depending upon long word alignment or not.  We'll pad it to
+ * long word alignment which is the faster version.
+ * The 0x4a8e is of course a 'tstl %fp' instruction.  This is better
+ * than using a NOP (0x4e71) instruction because it executes in one
+ * cycle not three and doesn't allow for an arbitrary delay waiting
+ * for bus cycles to finish.  Also fp/a6 isn't likely to cause a
+ * stall waiting for the register to become valid if such is added
+ * to the coldfire at some stage.
+ */
+#define	DELAY_ALIGN	".balignw 4, 0x4a8e\n\t"
 #else
-#include "delay_mm.h"
+/*
+ * No instruction alignment required for other m68k types.
+ */
+#define	DELAY_ALIGN
 #endif
+
+static inline void __delay(unsigned long loops)
+{
+	__asm__ __volatile__ (
+		DELAY_ALIGN
+		"1: subql #1,%0\n\t"
+		"jcc 1b"
+		: "=d" (loops)
+		: "0" (loops));
+}
+
+extern void __bad_udelay(void);
+
+
+#if defined(CONFIG_M68000) || defined(CONFIG_COLDFIRE)
+/*
+ * The simpler m68k and ColdFire processors do not have a 32*32->64
+ * multiply instruction. So we need to handle them a little differently.
+ * We use a bit of shifting and a single 32*32->32 multiply to get close.
+ * This is a macro so that the const version can factor out the first
+ * multiply and shift.
+ */
+#define	HZSCALE		(268435456 / (1000000 / HZ))
+
+#define	__const_udelay(u) \
+	__delay(((((u) * HZSCALE) >> 11) * (loops_per_jiffy >> 11)) >> 6)
+
+#else
+
+static inline void __xdelay(unsigned long xloops)
+{
+	unsigned long tmp;
+
+	__asm__ ("mulul %2,%0:%1"
+		: "=d" (xloops), "=d" (tmp)
+		: "d" (xloops), "1" (loops_per_jiffy));
+	__delay(xloops * HZ);
+}
+
+/*
+ * The definition of __const_udelay is specifically made a macro so that
+ * the const factor (4295 = 2**32 / 1000000) can be optimized out when
+ * the delay is a const.
+ */
+#define	__const_udelay(n)	(__xdelay((n) * 4295))
+
+#endif
+
+static inline void __udelay(unsigned long usecs)
+{
+	__const_udelay(usecs);
+}
+
+/*
+ * Use only for very small delays ( < 1 msec).  Should probably use a
+ * lookup table, really, as the multiplications take much too long with
+ * short delays.  This is a "reasonable" implementation, though (and the
+ * first constant multiplications gets optimized away if the delay is
+ * a constant)
+ */
+#define udelay(n) (__builtin_constant_p(n) ? \
+	((n) > 20000 ? __bad_udelay() : __const_udelay(n)) : __udelay(n))
+
+
+#endif /* defined(_M68K_DELAY_H) */
diff --git a/arch/m68k/include/asm/delay_mm.h b/arch/m68k/include/asm/delay_mm.h
deleted file mode 100644
index 5ed92851bc6f..000000000000
--- a/arch/m68k/include/asm/delay_mm.h
+++ /dev/null
@@ -1,57 +0,0 @@
-#ifndef _M68K_DELAY_H
-#define _M68K_DELAY_H
-
-#include <asm/param.h>
-
-/*
- * Copyright (C) 1994 Hamish Macdonald
- *
- * Delay routines, using a pre-computed "loops_per_jiffy" value.
- */
-
-static inline void __delay(unsigned long loops)
-{
-	__asm__ __volatile__ ("1: subql #1,%0; jcc 1b"
-		: "=d" (loops) : "0" (loops));
-}
-
-extern void __bad_udelay(void);
-
-/*
- * Use only for very small delays ( < 1 msec).  Should probably use a
- * lookup table, really, as the multiplications take much too long with
- * short delays.  This is a "reasonable" implementation, though (and the
- * first constant multiplications gets optimized away if the delay is
- * a constant)
- */
-static inline void __const_udelay(unsigned long xloops)
-{
-	unsigned long tmp;
-
-	__asm__ ("mulul %2,%0:%1"
-		: "=d" (xloops), "=d" (tmp)
-		: "d" (xloops), "1" (loops_per_jiffy));
-	__delay(xloops * HZ);
-}
-
-static inline void __udelay(unsigned long usecs)
-{
-	__const_udelay(usecs * 4295);	/* 2**32 / 1000000 */
-}
-
-#define udelay(n) (__builtin_constant_p(n) ? \
-	((n) > 20000 ? __bad_udelay() : __const_udelay((n) * 4295)) : \
-	__udelay(n))
-
-static inline unsigned long muldiv(unsigned long a, unsigned long b,
-				   unsigned long c)
-{
-	unsigned long tmp;
-
-	__asm__ ("mulul %2,%0:%1; divul %3,%0:%1"
-		: "=d" (tmp), "=d" (a)
-		: "d" (b), "d" (c), "1" (a));
-	return a;
-}
-
-#endif /* defined(_M68K_DELAY_H) */
diff --git a/arch/m68k/include/asm/delay_no.h b/arch/m68k/include/asm/delay_no.h
deleted file mode 100644
index c3a0edc90f21..000000000000
--- a/arch/m68k/include/asm/delay_no.h
+++ /dev/null
@@ -1,76 +0,0 @@
-#ifndef _M68KNOMMU_DELAY_H
-#define _M68KNOMMU_DELAY_H
-
-/*
- * Copyright (C) 1994 Hamish Macdonald
- * Copyright (C) 2004 Greg Ungerer <gerg@snapgear.com>
- */
-
-#include <asm/param.h>
-
-static inline void __delay(unsigned long loops)
-{
-#if defined(CONFIG_COLDFIRE)
-	/* The coldfire runs this loop at significantly different speeds
-	 * depending upon long word alignment or not.  We'll pad it to
-	 * long word alignment which is the faster version.
-	 * The 0x4a8e is of course a 'tstl %fp' instruction.  This is better
-	 * than using a NOP (0x4e71) instruction because it executes in one
-	 * cycle not three and doesn't allow for an arbitrary delay waiting
-	 * for bus cycles to finish.  Also fp/a6 isn't likely to cause a
-	 * stall waiting for the register to become valid if such is added
-	 * to the coldfire at some stage.
-	 */
-	__asm__ __volatile__ (	".balignw 4, 0x4a8e\n\t"
-				"1: subql #1, %0\n\t"
-				"jcc 1b"
-		: "=d" (loops) : "0" (loops));
-#else
-	__asm__ __volatile__ (	"1: subql #1, %0\n\t"
-				"jcc 1b"
-		: "=d" (loops) : "0" (loops));
-#endif
-}
-
-/*
- *	Ideally we use a 32*32->64 multiply to calculate the number of
- *	loop iterations, but the older standard 68k and ColdFire do not
- *	have this instruction. So for them we have a clsoe approximation
- *	loop using 32*32->32 multiplies only. This calculation based on
- *	the ARM version of delay.
- *
- *	We want to implement:
- *
- *	loops = (usecs * 0x10c6 * HZ * loops_per_jiffy) / 2^32
- */
-
-#define	HZSCALE		(268435456 / (1000000/HZ))
-
-extern unsigned long loops_per_jiffy;
-
-static inline void _udelay(unsigned long usecs)
-{
-#if defined(CONFIG_M68328) || defined(CONFIG_M68EZ328) || \
-    defined(CONFIG_M68VZ328) || defined(CONFIG_M68360) || \
-    defined(CONFIG_COLDFIRE)
-	__delay((((usecs * HZSCALE) >> 11) * (loops_per_jiffy >> 11)) >> 6);
-#else
-	unsigned long tmp;
-
-	usecs *= 4295;		/* 2**32 / 1000000 */
-	__asm__ ("mulul %2,%0:%1"
-		: "=d" (usecs), "=d" (tmp)
-		: "d" (usecs), "1" (loops_per_jiffy*HZ));
-	__delay(usecs);
-#endif
-}
-
-/*
- *	Moved the udelay() function into library code, no longer inlined.
- *	I had to change the algorithm because we are overflowing now on
- *	the faster ColdFire parts. The code is a little bigger, so it makes
- *	sense to library it.
- */
-extern void udelay(unsigned long usecs);
-
-#endif /* defined(_M68KNOMMU_DELAY_H) */
diff --git a/arch/m68k/include/asm/entry_no.h b/arch/m68k/include/asm/entry_no.h
index 627d69bacc58..68611e3dbb1d 100644
--- a/arch/m68k/include/asm/entry_no.h
+++ b/arch/m68k/include/asm/entry_no.h
@@ -96,11 +96,11 @@
 .endm
 
 .macro RDUSP
-	movel	sw_usp,%a2
+	movel	sw_usp,%a3
 .endm
 
 .macro WRUSP
-	movel	%a0,sw_usp
+	movel	%a3,sw_usp
 .endm
 
 #else /* !CONFIG_COLDFIRE_SW_A7 */
@@ -127,13 +127,13 @@
 .endm
 
 .macro RDUSP
-	/*move	%usp,%a2*/
-	.word	0x4e6a
+	/*move	%usp,%a3*/
+	.word	0x4e6b
 .endm
 
 .macro WRUSP
-	/*move	%a0,%usp*/
-	.word	0x4e60
+	/*move	%a3,%usp*/
+	.word	0x4e63
 .endm
 
 #endif /* !CONFIG_COLDFIRE_SW_A7 */
diff --git a/arch/m68k/include/asm/hardirq.h b/arch/m68k/include/asm/hardirq.h
index 56d0d5db231c..870e5347155b 100644
--- a/arch/m68k/include/asm/hardirq.h
+++ b/arch/m68k/include/asm/hardirq.h
@@ -1,5 +1,34 @@
-#ifdef __uClinux__
-#include "hardirq_no.h"
+#ifndef __M68K_HARDIRQ_H
+#define __M68K_HARDIRQ_H
+
+#include <linux/threads.h>
+#include <linux/cache.h>
+#include <asm/irq.h>
+
+#define HARDIRQ_BITS	8
+
+/*
+ * The hardirq mask has to be large enough to have
+ * space for potentially all IRQ sources in the system
+ * nesting on a single CPU:
+ */
+#if (1 << HARDIRQ_BITS) < NR_IRQS
+# error HARDIRQ_BITS is too low!
+#endif
+
+#ifdef CONFIG_MMU
+
+/* entry.S is sensitive to the offsets of these fields */
+typedef struct {
+	unsigned int __softirq_pending;
+} ____cacheline_aligned irq_cpustat_t;
+
+#include <linux/irq_cpustat.h>	/* Standard mappings for irq_cpustat_t above */
+
 #else
-#include "hardirq_mm.h"
+
+#include <asm-generic/hardirq.h>
+
+#endif /* !CONFIG_MMU */
+
 #endif
diff --git a/arch/m68k/include/asm/hardirq_mm.h b/arch/m68k/include/asm/hardirq_mm.h
deleted file mode 100644
index 394ee946015c..000000000000
--- a/arch/m68k/include/asm/hardirq_mm.h
+++ /dev/null
@@ -1,16 +0,0 @@
-#ifndef __M68K_HARDIRQ_H
-#define __M68K_HARDIRQ_H
-
-#include <linux/threads.h>
-#include <linux/cache.h>
-
-/* entry.S is sensitive to the offsets of these fields */
-typedef struct {
-	unsigned int __softirq_pending;
-} ____cacheline_aligned irq_cpustat_t;
-
-#include <linux/irq_cpustat.h>	/* Standard mappings for irq_cpustat_t above */
-
-#define HARDIRQ_BITS	8
-
-#endif
diff --git a/arch/m68k/include/asm/hardirq_no.h b/arch/m68k/include/asm/hardirq_no.h
deleted file mode 100644
index b44b14be87d9..000000000000
--- a/arch/m68k/include/asm/hardirq_no.h
+++ /dev/null
@@ -1,19 +0,0 @@
-#ifndef __M68K_HARDIRQ_H
-#define __M68K_HARDIRQ_H
-
-#include <asm/irq.h>
-
-#define HARDIRQ_BITS	8
-
-/*
- * The hardirq mask has to be large enough to have
- * space for potentially all IRQ sources in the system
- * nesting on a single CPU:
- */
-#if (1 << HARDIRQ_BITS) < NR_IRQS
-# error HARDIRQ_BITS is too low!
-#endif
-
-#include <asm-generic/hardirq.h>
-
-#endif /* __M68K_HARDIRQ_H */
diff --git a/arch/m68k/include/asm/irq.h b/arch/m68k/include/asm/irq.h
index 907eff1edd2f..69ed0d74d532 100644
--- a/arch/m68k/include/asm/irq.h
+++ b/arch/m68k/include/asm/irq.h
@@ -33,15 +33,6 @@
 #include <linux/spinlock_types.h>
 
 /*
- * The hardirq mask has to be large enough to have
- * space for potentially all IRQ sources in the system
- * nesting on a single CPU:
- */
-#if (1 << HARDIRQ_BITS) < NR_IRQS
-# error HARDIRQ_BITS is too low!
-#endif
-
-/*
  * Interrupt source definitions
  * General interrupt sources are the level 1-7.
  * Adding an interrupt service routine for one of these sources
@@ -131,4 +122,6 @@ asmlinkage void __m68k_handle_int(unsigned int, struct pt_regs *);
 #define irq_canonicalize(irq)  (irq)
 #endif /* CONFIG_MMU */
 
+asmlinkage void do_IRQ(int irq, struct pt_regs *regs);
+
 #endif /* _M68K_IRQ_H_ */
diff --git a/arch/m68k/include/asm/machdep.h b/arch/m68k/include/asm/machdep.h
index 415d5484916c..789f3b2de0e9 100644
--- a/arch/m68k/include/asm/machdep.h
+++ b/arch/m68k/include/asm/machdep.h
@@ -40,6 +40,5 @@ extern unsigned long hw_timer_offset(void);
 extern irqreturn_t arch_timer_interrupt(int irq, void *dummy);
 
 extern void config_BSP(char *command, int len);
-extern void do_IRQ(int irq, struct pt_regs *fp);
 
 #endif /* _M68K_MACHDEP_H */
diff --git a/arch/m68k/include/asm/module.h b/arch/m68k/include/asm/module.h
index 5f21e11071bd..edffe66b7f49 100644
--- a/arch/m68k/include/asm/module.h
+++ b/arch/m68k/include/asm/module.h
@@ -1,46 +1,41 @@
 #ifndef _ASM_M68K_MODULE_H
 #define _ASM_M68K_MODULE_H
 
-#ifdef CONFIG_MMU
+enum m68k_fixup_type {
+	m68k_fixup_memoffset,
+	m68k_fixup_vnode_shift,
+};
+
+struct m68k_fixup_info {
+	enum m68k_fixup_type type;
+	void *addr;
+};
 
 struct mod_arch_specific {
 	struct m68k_fixup_info *fixup_start, *fixup_end;
 };
 
+#ifdef CONFIG_MMU
+
 #define MODULE_ARCH_INIT {				\
 	.fixup_start		= __start_fixup,	\
 	.fixup_end		= __stop_fixup,		\
 }
 
 
-enum m68k_fixup_type {
-	m68k_fixup_memoffset,
-	m68k_fixup_vnode_shift,
-};
-
-struct m68k_fixup_info {
-	enum m68k_fixup_type type;
-	void *addr;
-};
-
 #define m68k_fixup(type, addr)			\
 	"	.section \".m68k_fixup\",\"aw\"\n"	\
 	"	.long " #type "," #addr "\n"	\
 	"	.previous\n"
 
+#endif /* CONFIG_MMU */
+
 extern struct m68k_fixup_info __start_fixup[], __stop_fixup[];
 
 struct module;
 extern void module_fixup(struct module *mod, struct m68k_fixup_info *start,
 			 struct m68k_fixup_info *end);
 
-#else
-
-struct mod_arch_specific {
-};
-
-#endif /* CONFIG_MMU */
-
 #define Elf_Shdr Elf32_Shdr
 #define Elf_Sym Elf32_Sym
 #define Elf_Ehdr Elf32_Ehdr
diff --git a/arch/m68k/include/asm/signal.h b/arch/m68k/include/asm/signal.h
index 5bc09c787a11..60e88660169c 100644
--- a/arch/m68k/include/asm/signal.h
+++ b/arch/m68k/include/asm/signal.h
@@ -150,7 +150,7 @@ typedef struct sigaltstack {
 #ifdef __KERNEL__
 #include <asm/sigcontext.h>
 
-#ifndef __uClinux__
+#ifndef CONFIG_CPU_HAS_NO_BITFIELDS
 #define __HAVE_ARCH_SIG_BITOPS
 
 static inline void sigaddset(sigset_t *set, int _sig)
@@ -199,15 +199,14 @@ static inline int sigfindinword(unsigned long word)
 	return word ^ 31;
 }
 
-struct pt_regs;
-extern void ptrace_signal_deliver(struct pt_regs *regs, void *cookie);
+#endif /* !CONFIG_CPU_HAS_NO_BITFIELDS */
 
-#else
-
-#undef __HAVE_ARCH_SIG_BITOPS
+#ifdef __uClinux__
 #define ptrace_signal_deliver(regs, cookie) do { } while (0)
-
+#else
+struct pt_regs;
+extern void ptrace_signal_deliver(struct pt_regs *regs, void *cookie);
 #endif /* __uClinux__ */
-#endif /* __KERNEL__ */
 
+#endif /* __KERNEL__ */
 #endif /* _M68K_SIGNAL_H */
diff --git a/arch/m68k/include/asm/system.h b/arch/m68k/include/asm/system.h
index ccea925ff4f5..47b01f4726bc 100644
--- a/arch/m68k/include/asm/system.h
+++ b/arch/m68k/include/asm/system.h
@@ -1,5 +1,193 @@
-#ifdef __uClinux__
-#include "system_no.h"
+#ifndef _M68K_SYSTEM_H
+#define _M68K_SYSTEM_H
+
+#include <linux/linkage.h>
+#include <linux/kernel.h>
+#include <linux/irqflags.h>
+#include <asm/segment.h>
+#include <asm/entry.h>
+
+#ifdef __KERNEL__
+
+/*
+ * switch_to(n) should switch tasks to task ptr, first checking that
+ * ptr isn't the current task, in which case it does nothing.  This
+ * also clears the TS-flag if the task we switched to has used the
+ * math co-processor latest.
+ */
+/*
+ * switch_to() saves the extra registers, that are not saved
+ * automatically by SAVE_SWITCH_STACK in resume(), ie. d0-d5 and
+ * a0-a1. Some of these are used by schedule() and its predecessors
+ * and so we might get see unexpected behaviors when a task returns
+ * with unexpected register values.
+ *
+ * syscall stores these registers itself and none of them are used
+ * by syscall after the function in the syscall has been called.
+ *
+ * Beware that resume now expects *next to be in d1 and the offset of
+ * tss to be in a1. This saves a few instructions as we no longer have
+ * to push them onto the stack and read them back right after.
+ *
+ * 02/17/96 - Jes Sorensen (jds@kom.auc.dk)
+ *
+ * Changed 96/09/19 by Andreas Schwab
+ * pass prev in a0, next in a1
+ */
+asmlinkage void resume(void);
+#define switch_to(prev,next,last) do { \
+  register void *_prev __asm__ ("a0") = (prev); \
+  register void *_next __asm__ ("a1") = (next); \
+  register void *_last __asm__ ("d1"); \
+  __asm__ __volatile__("jbsr resume" \
+		       : "=a" (_prev), "=a" (_next), "=d" (_last) \
+		       : "0" (_prev), "1" (_next) \
+		       : "d0", "d2", "d3", "d4", "d5"); \
+  (last) = _last; \
+} while (0)
+
+
+/*
+ * Force strict CPU ordering.
+ * Not really required on m68k...
+ */
+#define nop()		do { asm volatile ("nop"); barrier(); } while (0)
+#define mb()		barrier()
+#define rmb()		barrier()
+#define wmb()		barrier()
+#define read_barrier_depends()	((void)0)
+#define set_mb(var, value)	({ (var) = (value); wmb(); })
+
+#define smp_mb()	barrier()
+#define smp_rmb()	barrier()
+#define smp_wmb()	barrier()
+#define smp_read_barrier_depends()	((void)0)
+
+#define xchg(ptr,x) ((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr))))
+
+struct __xchg_dummy { unsigned long a[100]; };
+#define __xg(x) ((volatile struct __xchg_dummy *)(x))
+
+#ifndef CONFIG_RMW_INSNS
+static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int size)
+{
+	unsigned long flags, tmp;
+
+	local_irq_save(flags);
+
+	switch (size) {
+	case 1:
+		tmp = *(u8 *)ptr;
+		*(u8 *)ptr = x;
+		x = tmp;
+		break;
+	case 2:
+		tmp = *(u16 *)ptr;
+		*(u16 *)ptr = x;
+		x = tmp;
+		break;
+	case 4:
+		tmp = *(u32 *)ptr;
+		*(u32 *)ptr = x;
+		x = tmp;
+		break;
+	default:
+		BUG();
+	}
+
+	local_irq_restore(flags);
+	return x;
+}
 #else
-#include "system_mm.h"
+static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int size)
+{
+	switch (size) {
+	    case 1:
+		__asm__ __volatile__
+			("moveb %2,%0\n\t"
+			 "1:\n\t"
+			 "casb %0,%1,%2\n\t"
+			 "jne 1b"
+			 : "=&d" (x) : "d" (x), "m" (*__xg(ptr)) : "memory");
+		break;
+	    case 2:
+		__asm__ __volatile__
+			("movew %2,%0\n\t"
+			 "1:\n\t"
+			 "casw %0,%1,%2\n\t"
+			 "jne 1b"
+			 : "=&d" (x) : "d" (x), "m" (*__xg(ptr)) : "memory");
+		break;
+	    case 4:
+		__asm__ __volatile__
+			("movel %2,%0\n\t"
+			 "1:\n\t"
+			 "casl %0,%1,%2\n\t"
+			 "jne 1b"
+			 : "=&d" (x) : "d" (x), "m" (*__xg(ptr)) : "memory");
+		break;
+	}
+	return x;
+}
 #endif
+
+#include <asm-generic/cmpxchg-local.h>
+
+#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
+
+/*
+ * Atomic compare and exchange.  Compare OLD with MEM, if identical,
+ * store NEW in MEM.  Return the initial value in MEM.  Success is
+ * indicated by comparing RETURN with OLD.
+ */
+#ifdef CONFIG_RMW_INSNS
+#define __HAVE_ARCH_CMPXCHG	1
+
+static inline unsigned long __cmpxchg(volatile void *p, unsigned long old,
+				      unsigned long new, int size)
+{
+	switch (size) {
+	case 1:
+		__asm__ __volatile__ ("casb %0,%2,%1"
+				      : "=d" (old), "=m" (*(char *)p)
+				      : "d" (new), "0" (old), "m" (*(char *)p));
+		break;
+	case 2:
+		__asm__ __volatile__ ("casw %0,%2,%1"
+				      : "=d" (old), "=m" (*(short *)p)
+				      : "d" (new), "0" (old), "m" (*(short *)p));
+		break;
+	case 4:
+		__asm__ __volatile__ ("casl %0,%2,%1"
+				      : "=d" (old), "=m" (*(int *)p)
+				      : "d" (new), "0" (old), "m" (*(int *)p));
+		break;
+	}
+	return old;
+}
+
+#define cmpxchg(ptr, o, n)						    \
+	((__typeof__(*(ptr)))__cmpxchg((ptr), (unsigned long)(o),	    \
+			(unsigned long)(n), sizeof(*(ptr))))
+#define cmpxchg_local(ptr, o, n)					    \
+	((__typeof__(*(ptr)))__cmpxchg((ptr), (unsigned long)(o),	    \
+			(unsigned long)(n), sizeof(*(ptr))))
+#else
+
+/*
+ * cmpxchg_local and cmpxchg64_local are atomic wrt current CPU. Always make
+ * them available.
+ */
+#define cmpxchg_local(ptr, o, n)				  	       \
+	((__typeof__(*(ptr)))__cmpxchg_local_generic((ptr), (unsigned long)(o),\
+			(unsigned long)(n), sizeof(*(ptr))))
+
+#include <asm-generic/cmpxchg.h>
+
+#endif
+
+#define arch_align_stack(x) (x)
+
+#endif /* __KERNEL__ */
+
+#endif /* _M68K_SYSTEM_H */
diff --git a/arch/m68k/include/asm/system_mm.h b/arch/m68k/include/asm/system_mm.h
deleted file mode 100644
index 47b01f4726bc..000000000000
--- a/arch/m68k/include/asm/system_mm.h
+++ /dev/null
@@ -1,193 +0,0 @@
-#ifndef _M68K_SYSTEM_H
-#define _M68K_SYSTEM_H
-
-#include <linux/linkage.h>
-#include <linux/kernel.h>
-#include <linux/irqflags.h>
-#include <asm/segment.h>
-#include <asm/entry.h>
-
-#ifdef __KERNEL__
-
-/*
- * switch_to(n) should switch tasks to task ptr, first checking that
- * ptr isn't the current task, in which case it does nothing.  This
- * also clears the TS-flag if the task we switched to has used the
- * math co-processor latest.
- */
-/*
- * switch_to() saves the extra registers, that are not saved
- * automatically by SAVE_SWITCH_STACK in resume(), ie. d0-d5 and
- * a0-a1. Some of these are used by schedule() and its predecessors
- * and so we might get see unexpected behaviors when a task returns
- * with unexpected register values.
- *
- * syscall stores these registers itself and none of them are used
- * by syscall after the function in the syscall has been called.
- *
- * Beware that resume now expects *next to be in d1 and the offset of
- * tss to be in a1. This saves a few instructions as we no longer have
- * to push them onto the stack and read them back right after.
- *
- * 02/17/96 - Jes Sorensen (jds@kom.auc.dk)
- *
- * Changed 96/09/19 by Andreas Schwab
- * pass prev in a0, next in a1
- */
-asmlinkage void resume(void);
-#define switch_to(prev,next,last) do { \
-  register void *_prev __asm__ ("a0") = (prev); \
-  register void *_next __asm__ ("a1") = (next); \
-  register void *_last __asm__ ("d1"); \
-  __asm__ __volatile__("jbsr resume" \
-		       : "=a" (_prev), "=a" (_next), "=d" (_last) \
-		       : "0" (_prev), "1" (_next) \
-		       : "d0", "d2", "d3", "d4", "d5"); \
-  (last) = _last; \
-} while (0)
-
-
-/*
- * Force strict CPU ordering.
- * Not really required on m68k...
- */
-#define nop()		do { asm volatile ("nop"); barrier(); } while (0)
-#define mb()		barrier()
-#define rmb()		barrier()
-#define wmb()		barrier()
-#define read_barrier_depends()	((void)0)
-#define set_mb(var, value)	({ (var) = (value); wmb(); })
-
-#define smp_mb()	barrier()
-#define smp_rmb()	barrier()
-#define smp_wmb()	barrier()
-#define smp_read_barrier_depends()	((void)0)
-
-#define xchg(ptr,x) ((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr))))
-
-struct __xchg_dummy { unsigned long a[100]; };
-#define __xg(x) ((volatile struct __xchg_dummy *)(x))
-
-#ifndef CONFIG_RMW_INSNS
-static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int size)
-{
-	unsigned long flags, tmp;
-
-	local_irq_save(flags);
-
-	switch (size) {
-	case 1:
-		tmp = *(u8 *)ptr;
-		*(u8 *)ptr = x;
-		x = tmp;
-		break;
-	case 2:
-		tmp = *(u16 *)ptr;
-		*(u16 *)ptr = x;
-		x = tmp;
-		break;
-	case 4:
-		tmp = *(u32 *)ptr;
-		*(u32 *)ptr = x;
-		x = tmp;
-		break;
-	default:
-		BUG();
-	}
-
-	local_irq_restore(flags);
-	return x;
-}
-#else
-static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int size)
-{
-	switch (size) {
-	    case 1:
-		__asm__ __volatile__
-			("moveb %2,%0\n\t"
-			 "1:\n\t"
-			 "casb %0,%1,%2\n\t"
-			 "jne 1b"
-			 : "=&d" (x) : "d" (x), "m" (*__xg(ptr)) : "memory");
-		break;
-	    case 2:
-		__asm__ __volatile__
-			("movew %2,%0\n\t"
-			 "1:\n\t"
-			 "casw %0,%1,%2\n\t"
-			 "jne 1b"
-			 : "=&d" (x) : "d" (x), "m" (*__xg(ptr)) : "memory");
-		break;
-	    case 4:
-		__asm__ __volatile__
-			("movel %2,%0\n\t"
-			 "1:\n\t"
-			 "casl %0,%1,%2\n\t"
-			 "jne 1b"
-			 : "=&d" (x) : "d" (x), "m" (*__xg(ptr)) : "memory");
-		break;
-	}
-	return x;
-}
-#endif
-
-#include <asm-generic/cmpxchg-local.h>
-
-#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
-
-/*
- * Atomic compare and exchange.  Compare OLD with MEM, if identical,
- * store NEW in MEM.  Return the initial value in MEM.  Success is
- * indicated by comparing RETURN with OLD.
- */
-#ifdef CONFIG_RMW_INSNS
-#define __HAVE_ARCH_CMPXCHG	1
-
-static inline unsigned long __cmpxchg(volatile void *p, unsigned long old,
-				      unsigned long new, int size)
-{
-	switch (size) {
-	case 1:
-		__asm__ __volatile__ ("casb %0,%2,%1"
-				      : "=d" (old), "=m" (*(char *)p)
-				      : "d" (new), "0" (old), "m" (*(char *)p));
-		break;
-	case 2:
-		__asm__ __volatile__ ("casw %0,%2,%1"
-				      : "=d" (old), "=m" (*(short *)p)
-				      : "d" (new), "0" (old), "m" (*(short *)p));
-		break;
-	case 4:
-		__asm__ __volatile__ ("casl %0,%2,%1"
-				      : "=d" (old), "=m" (*(int *)p)
-				      : "d" (new), "0" (old), "m" (*(int *)p));
-		break;
-	}
-	return old;
-}
-
-#define cmpxchg(ptr, o, n)						    \
-	((__typeof__(*(ptr)))__cmpxchg((ptr), (unsigned long)(o),	    \
-			(unsigned long)(n), sizeof(*(ptr))))
-#define cmpxchg_local(ptr, o, n)					    \
-	((__typeof__(*(ptr)))__cmpxchg((ptr), (unsigned long)(o),	    \
-			(unsigned long)(n), sizeof(*(ptr))))
-#else
-
-/*
- * cmpxchg_local and cmpxchg64_local are atomic wrt current CPU. Always make
- * them available.
- */
-#define cmpxchg_local(ptr, o, n)				  	       \
-	((__typeof__(*(ptr)))__cmpxchg_local_generic((ptr), (unsigned long)(o),\
-			(unsigned long)(n), sizeof(*(ptr))))
-
-#include <asm-generic/cmpxchg.h>
-
-#endif
-
-#define arch_align_stack(x) (x)
-
-#endif /* __KERNEL__ */
-
-#endif /* _M68K_SYSTEM_H */
diff --git a/arch/m68k/include/asm/system_no.h b/arch/m68k/include/asm/system_no.h
deleted file mode 100644
index 6fe9f93bc3ff..000000000000
--- a/arch/m68k/include/asm/system_no.h
+++ /dev/null
@@ -1,153 +0,0 @@
-#ifndef _M68KNOMMU_SYSTEM_H
-#define _M68KNOMMU_SYSTEM_H
-
-#include <linux/linkage.h>
-#include <linux/irqflags.h>
-#include <asm/segment.h>
-#include <asm/entry.h>
-
-/*
- * switch_to(n) should switch tasks to task ptr, first checking that
- * ptr isn't the current task, in which case it does nothing.  This
- * also clears the TS-flag if the task we switched to has used the
- * math co-processor latest.
- */
-/*
- * switch_to() saves the extra registers, that are not saved
- * automatically by SAVE_SWITCH_STACK in resume(), ie. d0-d5 and
- * a0-a1. Some of these are used by schedule() and its predecessors
- * and so we might get see unexpected behaviors when a task returns
- * with unexpected register values.
- *
- * syscall stores these registers itself and none of them are used
- * by syscall after the function in the syscall has been called.
- *
- * Beware that resume now expects *next to be in d1 and the offset of
- * tss to be in a1. This saves a few instructions as we no longer have
- * to push them onto the stack and read them back right after.
- *
- * 02/17/96 - Jes Sorensen (jds@kom.auc.dk)
- *
- * Changed 96/09/19 by Andreas Schwab
- * pass prev in a0, next in a1, offset of tss in d1, and whether
- * the mm structures are shared in d2 (to avoid atc flushing).
- */
-asmlinkage void resume(void);
-#define switch_to(prev,next,last)				\
-{								\
-  void *_last;							\
-  __asm__ __volatile__(						\
-  	"movel	%1, %%a0\n\t"					\
-	"movel	%2, %%a1\n\t"					\
-	"jbsr resume\n\t"					\
-	"movel	%%d1, %0\n\t"					\
-       : "=d" (_last)						\
-       : "d" (prev), "d" (next)					\
-       : "cc", "d0", "d1", "d2", "d3", "d4", "d5", "a0", "a1");	\
-  (last) = _last;						\
-}
-
-#define iret() __asm__ __volatile__ ("rte": : :"memory", "sp", "cc")
-
-/*
- * Force strict CPU ordering.
- * Not really required on m68k...
- */
-#define nop()  asm volatile ("nop"::)
-#define mb()   asm volatile (""   : : :"memory")
-#define rmb()  asm volatile (""   : : :"memory")
-#define wmb()  asm volatile (""   : : :"memory")
-#define set_mb(var, value)	({ (var) = (value); wmb(); })
-
-#define smp_mb()	barrier()
-#define smp_rmb()	barrier()
-#define smp_wmb()	barrier()
-#define smp_read_barrier_depends()	do { } while(0)
-
-#define read_barrier_depends()  ((void)0)
-
-#define xchg(ptr,x) ((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr))))
-
-struct __xchg_dummy { unsigned long a[100]; };
-#define __xg(x) ((volatile struct __xchg_dummy *)(x))
-
-#ifndef CONFIG_RMW_INSNS
-static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int size)
-{
-  unsigned long tmp, flags;
-
-  local_irq_save(flags);
-
-  switch (size) {
-  case 1:
-    __asm__ __volatile__
-    ("moveb %2,%0\n\t"
-     "moveb %1,%2"
-    : "=&d" (tmp) : "d" (x), "m" (*__xg(ptr)) : "memory");
-    break;
-  case 2:
-    __asm__ __volatile__
-    ("movew %2,%0\n\t"
-     "movew %1,%2"
-    : "=&d" (tmp) : "d" (x), "m" (*__xg(ptr)) : "memory");
-    break;
-  case 4:
-    __asm__ __volatile__
-    ("movel %2,%0\n\t"
-     "movel %1,%2"
-    : "=&d" (tmp) : "d" (x), "m" (*__xg(ptr)) : "memory");
-    break;
-  }
-  local_irq_restore(flags);
-  return tmp;
-}
-#else
-static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int size)
-{
-	switch (size) {
-	    case 1:
-		__asm__ __volatile__
-			("moveb %2,%0\n\t"
-			 "1:\n\t"
-			 "casb %0,%1,%2\n\t"
-			 "jne 1b"
-			 : "=&d" (x) : "d" (x), "m" (*__xg(ptr)) : "memory");
-		break;
-	    case 2:
-		__asm__ __volatile__
-			("movew %2,%0\n\t"
-			 "1:\n\t"
-			 "casw %0,%1,%2\n\t"
-			 "jne 1b"
-			 : "=&d" (x) : "d" (x), "m" (*__xg(ptr)) : "memory");
-		break;
-	    case 4:
-		__asm__ __volatile__
-			("movel %2,%0\n\t"
-			 "1:\n\t"
-			 "casl %0,%1,%2\n\t"
-			 "jne 1b"
-			 : "=&d" (x) : "d" (x), "m" (*__xg(ptr)) : "memory");
-		break;
-	}
-	return x;
-}
-#endif
-
-#include <asm-generic/cmpxchg-local.h>
-
-/*
- * cmpxchg_local and cmpxchg64_local are atomic wrt current CPU. Always make
- * them available.
- */
-#define cmpxchg_local(ptr, o, n)				  	       \
-	((__typeof__(*(ptr)))__cmpxchg_local_generic((ptr), (unsigned long)(o),\
-			(unsigned long)(n), sizeof(*(ptr))))
-#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
-
-#include <asm-generic/cmpxchg.h>
-
-#define arch_align_stack(x) (x)
-
-
-#endif /* _M68KNOMMU_SYSTEM_H */
diff --git a/arch/m68k/include/asm/traps.h b/arch/m68k/include/asm/traps.h
index 0bffb17d5db7..151068f64f44 100644
--- a/arch/m68k/include/asm/traps.h
+++ b/arch/m68k/include/asm/traps.h
@@ -22,7 +22,6 @@ extern e_vector vectors[];
 asmlinkage void auto_inthandler(void);
 asmlinkage void user_inthandler(void);
 asmlinkage void bad_inthandler(void);
-extern void init_vectors(void);
 
 #endif