m68k: merge mmu and non-mmu bitops.h

The following patch merges the mmu and non-mmu versions of the m68k
bitops.h files. Now there is a good deal of difference between the two
files, but none of it is actually an mmu specific difference. It is
all about the specific m68k/coldfire varient we are targeting. So it
makes an awful lot of sense to merge these into a single bitops.h.

There is a number of ways I can see to factor this code. The approach
I have taken here is to keep the various versions of each macro/function
type together. This means that there is some ifdefery with each to handle
each CPU type.

I have added some comments in a couple of appropriate places to try
and make it clear what the differences we are dealing with are.
Specifically the instruction and addressing mode differences we have
to deal with.

The merged form keeps the same underlying optimizations for each CPU
type for all the general bit clear/set/change and find bit operations.
It does switch to using the generic le operations though, instead of
any local varients.

Build tested on ColdFire, 68328, 68360 (which is cpu32) and 68020+.
Run tested on ColdFire and ARAnyM.

Signed-off-by: Greg Ungerer <gerg@uclinux.org>
Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>

1 files changed, 528 insertions, 3 deletions

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 */