generic: implement __fls on all 64-bit archs

Implement __fls on all 64-bit archs:

alpha has an implementation of fls64.
	Added __fls(x) = fls64(x) - 1.

ia64 has fls, but not __fls.
	Added __fls based on code of fls.

mips and powerpc have __ilog2, which is the same as __fls.
	Added __fls = __ilog2.

parisc, s390, sh and sparc64:
	Include generic __fls.

x86_64 already has __fls.

Signed-off-by: Alexander van Heukelum <heukelum@fastmail.fm>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
diff --git a/include/asm-alpha/bitops.h b/include/asm-alpha/bitops.h
index 9e19a70..15f3ae2 100644
--- a/include/asm-alpha/bitops.h
+++ b/include/asm-alpha/bitops.h
@@ -388,6 +388,11 @@
 }
 #endif
 
+static inline unsigned long __fls(unsigned long x)
+{
+	return fls64(x) - 1;
+}
+
 static inline int fls(int x)
 {
 	return fls64((unsigned int) x);
diff --git a/include/asm-ia64/bitops.h b/include/asm-ia64/bitops.h
index 953d3df..e2ca800 100644
--- a/include/asm-ia64/bitops.h
+++ b/include/asm-ia64/bitops.h
@@ -407,6 +407,22 @@
 	return ia64_popcnt(x);
 }
 
+/*
+ * Find the last (most significant) bit set.  Undefined for x==0.
+ * Bits are numbered from 0..63 (e.g., __fls(9) == 3).
+ */
+static inline unsigned long
+__fls (unsigned long x)
+{
+	x |= x >> 1;
+	x |= x >> 2;
+	x |= x >> 4;
+	x |= x >> 8;
+	x |= x >> 16;
+	x |= x >> 32;
+	return ia64_popcnt(x) - 1;
+}
+
 #include <asm-generic/bitops/fls64.h>
 
 /*
diff --git a/include/asm-mips/bitops.h b/include/asm-mips/bitops.h
index ec75ce4..c2bd126 100644
--- a/include/asm-mips/bitops.h
+++ b/include/asm-mips/bitops.h
@@ -591,6 +591,11 @@
 	return 63 - lz;
 }
 
+static inline unsigned long __fls(unsigned long x)
+{
+	return __ilog2(x);
+}
+
 #if defined(CONFIG_CPU_MIPS32) || defined(CONFIG_CPU_MIPS64)
 
 /*
diff --git a/include/asm-parisc/bitops.h b/include/asm-parisc/bitops.h
index f8eebcb..7a6ea10 100644
--- a/include/asm-parisc/bitops.h
+++ b/include/asm-parisc/bitops.h
@@ -210,6 +210,7 @@
 	return ret;
 }
 
+#include <asm-generic/bitops/__fls.h>
 #include <asm-generic/bitops/fls64.h>
 #include <asm-generic/bitops/hweight.h>
 #include <asm-generic/bitops/lock.h>
diff --git a/include/asm-powerpc/bitops.h b/include/asm-powerpc/bitops.h
index a99a749..897eade 100644
--- a/include/asm-powerpc/bitops.h
+++ b/include/asm-powerpc/bitops.h
@@ -313,6 +313,11 @@
 	return 32 - lz;
 }
 
+static __inline__ unsigned long __fls(unsigned long x)
+{
+	return __ilog2(x);
+}
+
 /*
  * 64-bit can do this using one cntlzd (count leading zeroes doubleword)
  * instruction; for 32-bit we use the generic version, which does two
diff --git a/include/asm-s390/bitops.h b/include/asm-s390/bitops.h
index 965394e..b4eb24a 100644
--- a/include/asm-s390/bitops.h
+++ b/include/asm-s390/bitops.h
@@ -769,6 +769,7 @@
 }
 
 #include <asm-generic/bitops/fls.h>
+#include <asm-generic/bitops/__fls.h>
 #include <asm-generic/bitops/fls64.h>
 
 #include <asm-generic/bitops/hweight.h>
diff --git a/include/asm-sh/bitops.h b/include/asm-sh/bitops.h
index b6ba5a6..d7d382f 100644
--- a/include/asm-sh/bitops.h
+++ b/include/asm-sh/bitops.h
@@ -95,6 +95,7 @@
 #include <asm-generic/bitops/ext2-atomic.h>
 #include <asm-generic/bitops/minix.h>
 #include <asm-generic/bitops/fls.h>
+#include <asm-generic/bitops/__fls.h>
 #include <asm-generic/bitops/fls64.h>
 
 #endif /* __KERNEL__ */
diff --git a/include/asm-sparc64/bitops.h b/include/asm-sparc64/bitops.h
index 982ce89..11f9d81 100644
--- a/include/asm-sparc64/bitops.h
+++ b/include/asm-sparc64/bitops.h
@@ -34,6 +34,7 @@
 #include <asm-generic/bitops/ffz.h>
 #include <asm-generic/bitops/__ffs.h>
 #include <asm-generic/bitops/fls.h>
+#include <asm-generic/bitops/__fls.h>
 #include <asm-generic/bitops/fls64.h>
 
 #ifdef __KERNEL__