ARM: fix ffs/fls implementations to match x86

ARMs ffs/fls implementations are not type compatible with x86, so when
they're used in combination with min()/max(), they provoke warnings.
Change these to be inline functions with the correct types, providing
the clz as a separate documentation, and document their individual
behaviours.
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

arch/arm/include/asm/bitops.h

@@ -254,25 +254,59 @@ static inline int constant_fls(int x)
 }
 
 /*
- * On ARMv5 and above those functions can be implemented around
- * the clz instruction for much better code efficiency.
+ * On ARMv5 and above those functions can be implemented around the
+ * clz instruction for much better code efficiency.  __clz returns
+ * the number of leading zeros, zero input will return 32, and
+ * 0x80000000 will return 0.
  */
+static inline unsigned int __clz(unsigned int x)
+{
+	unsigned int ret;
+
+	asm("clz\t%0, %1" : "=r" (ret) : "r" (x));
 
+	return ret;
+}
+
+/*
+ * fls() returns zero if the input is zero, otherwise returns the bit
+ * position of the last set bit, where the LSB is 1 and MSB is 32.
+ */
 static inline int fls(int x)
 {
-	int ret;
-
 	if (__builtin_constant_p(x))
 	       return constant_fls(x);
 
-	asm("clz\t%0, %1" : "=r" (ret) : "r" (x));
-       	ret = 32 - ret;
-	return ret;
+	return 32 - __clz(x);
+}
+
+/*
+ * __fls() returns the bit position of the last bit set, where the
+ * LSB is 0 and MSB is 31.  Zero input is undefined.
+ */
+static inline unsigned long __fls(unsigned long x)
+{
+	return fls(x) - 1;
+}
+
+/*
+ * ffs() returns zero if the input was zero, otherwise returns the bit
+ * position of the first set bit, where the LSB is 1 and MSB is 32.
+ */
+static inline int ffs(int x)
+{
+	return fls(x & -x);
+}
+
+/*
+ * __ffs() returns the bit position of the first bit set, where the
+ * LSB is 0 and MSB is 31.  Zero input is undefined.
+ */
+static inline unsigned long __ffs(unsigned long x)
+{
+	return ffs(x) - 1;
 }
 
-#define __fls(x) (fls(x) - 1)
-#define ffs(x) ({ unsigned long __t = (x); fls(__t & -__t); })
-#define __ffs(x) (ffs(x) - 1)
 #define ffz(x) __ffs( ~(x) )
 
 #endif