[PATCH v3] x86: merge the simple bitops and move them to bitops.h

[Alexander van Heukelum <heukelum@mailshack.com>]

x86: merge the simple bitops and move them to bitops.h.

Some of those can be written in such a way that the same
inline assembly can be used to generate both 32 bit and
64 bit code.

For ffs and fls, x86_64 unconditionally used the cmov
instruction and i386 unconditionally used a conditional
branch over a mov instruction. In the current patch I
chose to select the version based on the availability
of the cmov instruction instead. A small detail here is
that x86_64 did not previously set CONFIG_X86_CMOV=y.

Improved comments for ffs, ffz, fls and variations.

Signed-off-by: Alexander van Heukelum <heukelum@fastmail.fm>

---

Hi Randy, Ingo,

Version 3, for x86#testing. Compared to v1 there are only
changes in the comments as suggested by Jeremy and Randy.

Thanks to both for their comments.

Greetings,
	Alexander

 arch/x86/Kconfig.cpu        |    2 +-
 include/asm-x86/bitops.h    |   99 ++++++++++++++++++++++++++++++++++++++++++-
 include/asm-x86/bitops_32.h |   64 ----------------------------
 include/asm-x86/bitops_64.h |   76 ---------------------------------
 4 files changed, 99 insertions(+), 142 deletions(-)

diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index 31e92fb..fb7399b 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -399,7 +399,7 @@ config X86_TSC
 # generates cmov.
 config X86_CMOV
 	def_bool y
-	depends on (MK7 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7)
+	depends on (MK7 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || X86_64)
 
 config X86_MINIMUM_CPU_FAMILY
 	int
diff --git a/include/asm-x86/bitops.h b/include/asm-x86/bitops.h
index 1a23ce1..923bdc2 100644
--- a/include/asm-x86/bitops.h
+++ b/include/asm-x86/bitops.h
@@ -66,7 +66,6 @@ static inline void __set_bit(int nr, volatile void *addr)
 		     : "Ir" (nr) : "memory");
 }
 
-
 /**
  * clear_bit - Clears a bit in memory
  * @nr: Bit to clear
@@ -310,6 +309,104 @@ static int test_bit(int nr, const volatile unsigned long *addr);
 	 constant_test_bit((nr),(addr)) :	\
 	 variable_test_bit((nr),(addr)))
 
+/**
+ * __ffs - find first set 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)
+{
+	__asm__("bsf %1,%0"
+		:"=r" (word)
+		:"rm" (word));
+	return word;
+}
+
+/**
+ * ffz - find first zero bit in word
+ * @word: The word to search
+ *
+ * Undefined if no zero exists, so code should check against ~0UL first.
+ */
+static inline unsigned long ffz(unsigned long word)
+{
+	__asm__("bsf %1,%0"
+		:"=r" (word)
+		:"r" (~word));
+	return word;
+}
+
+/*
+ * __fls: find last set bit in word
+ * @word: The word to search
+ *
+ * Undefined if no zero exists, so code should check against ~0UL first.
+ */
+static inline unsigned long __fls(unsigned long word)
+{
+	__asm__("bsr %1,%0"
+		:"=r" (word)
+		:"rm" (word));
+	return word;
+}
+
+#ifdef __KERNEL__
+/**
+ * ffs - find first set bit in word
+ * @x: the word to search
+ *
+ * This is defined the same way as the libc and compiler builtin ffs
+ * routines, therefore differs in spirit from the other bitops.
+ *
+ * ffs(value) returns 0 if value is 0 or the position of the first
+ * set bit if value is nonzero. The first (least significant) bit
+ * is at position 1.
+ */
+static inline int ffs(int x)
+{
+	int r;
+#ifdef CONFIG_X86_CMOV
+	__asm__("bsfl %1,%0\n\t"
+		"cmovzl %2,%0"
+		: "=r" (r) : "rm" (x), "r" (-1));
+#else
+	__asm__("bsfl %1,%0\n\t"
+		"jnz 1f\n\t"
+		"movl $-1,%0\n"
+		"1:" : "=r" (r) : "rm" (x));
+#endif
+	return r + 1;
+}
+
+/**
+ * fls - find last set bit in word
+ * @x: the word to search
+ *
+ * This is defined in a similar way as the libc and compiler builtin
+ * ffs, but returns the position of the most significant set bit.
+ *
+ * fls(value) returns 0 if value is 0 or the position of the last
+ * set bit if value is nonzero. The last (most significant) bit is
+ * at position 32.
+ */
+static inline int fls(int x)
+{
+	int r;
+#ifdef CONFIG_X86_CMOV
+	__asm__("bsrl %1,%0\n\t"
+		"cmovzl %2,%0"
+		: "=&r" (r) : "rm" (x), "rm" (-1));
+#else
+	__asm__("bsrl %1,%0\n\t"
+		"jnz 1f\n\t"
+		"movl $-1,%0\n"
+		"1:" : "=r" (r) : "rm" (x));
+#endif
+	return r + 1;
+}
+#endif /* __KERNEL__ */
+
 #undef ADDR
 
 #ifdef CONFIG_X86_32
diff --git a/include/asm-x86/bitops_32.h b/include/asm-x86/bitops_32.h
index 570f0fa..c19fbe9 100644
--- a/include/asm-x86/bitops_32.h
+++ b/include/asm-x86/bitops_32.h
@@ -38,20 +38,6 @@ static inline int find_first_zero_bit(const unsigned long *addr, unsigned size)
 }
 
 /**
- * __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)
-{
-	__asm__("bsfl %1,%0"
-		:"=r" (word)
-		:"rm" (word));
-	return word;
-}
-
-/**
  * find_first_bit - find the first set bit in a memory region
  * @addr: The address to start the search at
  * @size: The maximum size to search
@@ -72,60 +58,10 @@ static inline unsigned find_first_bit(const unsigned long *addr, unsigned size)
 	return x;
 }
 
-/**
- * ffz - find first zero in word.
- * @word: The word to search
- *
- * Undefined if no zero exists, so code should check against ~0UL first.
- */
-static inline unsigned long ffz(unsigned long word)
-{
-	__asm__("bsfl %1,%0"
-		:"=r" (word)
-		:"r" (~word));
-	return word;
-}
-
 #ifdef __KERNEL__
 
 #include <asm-generic/bitops/sched.h>
 
-/**
- * ffs - find first bit set
- * @x: the word to search
- *
- * 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 r;
-
-	__asm__("bsfl %1,%0\n\t"
-		"jnz 1f\n\t"
-		"movl $-1,%0\n"
-		"1:" : "=r" (r) : "rm" (x));
-	return r+1;
-}
-
-/**
- * fls - find last bit set
- * @x: the word to search
- *
- * This is defined the same way as ffs().
- */
-static inline int fls(int x)
-{
-	int r;
-
-	__asm__("bsrl %1,%0\n\t"
-		"jnz 1f\n\t"
-		"movl $-1,%0\n"
-		"1:" : "=r" (r) : "rm" (x));
-	return r+1;
-}
-
 #include <asm-generic/bitops/hweight.h>
 
 #endif /* __KERNEL__ */
diff --git a/include/asm-x86/bitops_64.h b/include/asm-x86/bitops_64.h
index 87e1a17..866ed56 100644
--- a/include/asm-x86/bitops_64.h
+++ b/include/asm-x86/bitops_64.h
@@ -35,71 +35,11 @@ static inline void set_bit_string(unsigned long *bitmap, unsigned long i,
 	}
 } 
 
-/**
- * ffz - find first zero in word.
- * @word: The word to search
- *
- * Undefined if no zero exists, so code should check against ~0UL first.
- */
-static inline unsigned long ffz(unsigned long word)
-{
-	__asm__("bsfq %1,%0"
-		:"=r" (word)
-		:"r" (~word));
-	return word;
-}
-
-/**
- * __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)
-{
-	__asm__("bsfq %1,%0"
-		:"=r" (word)
-		:"rm" (word));
-	return word;
-}
-
-/*
- * __fls: find last bit set.
- * @word: The word to search
- *
- * Undefined if no zero exists, so code should check against ~0UL first.
- */
-static inline unsigned long __fls(unsigned long word)
-{
-	__asm__("bsrq %1,%0"
-		:"=r" (word)
-		:"rm" (word));
-	return word;
-}
-
 #ifdef __KERNEL__
 
 #include <asm-generic/bitops/sched.h>
 
 /**
- * ffs - find first bit set
- * @x: the word to search
- *
- * 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 r;
-
-	__asm__("bsfl %1,%0\n\t"
-		"cmovzl %2,%0" 
-		: "=r" (r) : "rm" (x), "r" (-1));
-	return r+1;
-}
-
-/**
  * fls64 - find last bit set in 64 bit word
  * @x: the word to search
  *
@@ -112,22 +52,6 @@ static inline int fls64(__u64 x)
 	return __fls(x) + 1;
 }
 
-/**
- * fls - find last bit set
- * @x: the word to search
- *
- * This is defined the same way as ffs.
- */
-static inline int fls(int x)
-{
-	int r;
-
-	__asm__("bsrl %1,%0\n\t"
-		"cmovzl %2,%0"
-		: "=&r" (r) : "rm" (x), "rm" (-1));
-	return r+1;
-}
-
 #define ARCH_HAS_FAST_MULTIPLIER 1
 
 #include <asm-generic/bitops/hweight.h>