Merge branch 'core-hweight-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'core-hweight-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  x86, hweight: Use a 32-bit popcnt for __arch_hweight32()
  arch, hweight: Fix compilation errors
  x86: Add optimized popcnt variants
  bitops: Optimize hweight() by making use of compile-time evaluation

4 files changed, 74 insertions, 31 deletions

diff --git a/include/asm-generic/bitops/arch_hweight.h b/include/asm-generic/bitops/arch_hweight.h
new file mode 100644
index 000000000000..6a211f40665c
--- /dev/null
+++ b/include/asm-generic/bitops/arch_hweight.h
@@ -0,0 +1,25 @@
+#ifndef _ASM_GENERIC_BITOPS_ARCH_HWEIGHT_H_
+#define _ASM_GENERIC_BITOPS_ARCH_HWEIGHT_H_
+
+#include <asm/types.h>
+
+static inline unsigned int __arch_hweight32(unsigned int w)
+{
+        return __sw_hweight32(w);
+}
+
+static inline unsigned int __arch_hweight16(unsigned int w)
+{
+        return __sw_hweight16(w);
+}
+
+static inline unsigned int __arch_hweight8(unsigned int w)
+{
+        return __sw_hweight8(w);
+}
+
+static inline unsigned long __arch_hweight64(__u64 w)
+{
+        return __sw_hweight64(w);
+}
+#endif /* _ASM_GENERIC_BITOPS_HWEIGHT_H_ */
diff --git a/include/asm-generic/bitops/const_hweight.h b/include/asm-generic/bitops/const_hweight.h
new file mode 100644
index 000000000000..fa2a50b7ee66
--- /dev/null
+++ b/include/asm-generic/bitops/const_hweight.h
@@ -0,0 +1,42 @@
+#ifndef _ASM_GENERIC_BITOPS_CONST_HWEIGHT_H_
+#define _ASM_GENERIC_BITOPS_CONST_HWEIGHT_H_
+
+/*
+ * Compile time versions of __arch_hweightN()
+ */
+#define __const_hweight8(w)             \
+      ( (!!((w) & (1ULL << 0))) +       \
+        (!!((w) & (1ULL << 1))) +       \
+        (!!((w) & (1ULL << 2))) +       \
+        (!!((w) & (1ULL << 3))) +       \
+        (!!((w) & (1ULL << 4))) +       \
+        (!!((w) & (1ULL << 5))) +       \
+        (!!((w) & (1ULL << 6))) +       \
+        (!!((w) & (1ULL << 7))) )
+
+#define __const_hweight16(w) (__const_hweight8(w)  + __const_hweight8((w)  >> 8 ))
+#define __const_hweight32(w) (__const_hweight16(w) + __const_hweight16((w) >> 16))
+#define __const_hweight64(w) (__const_hweight32(w) + __const_hweight32((w) >> 32))
+
+/*
+ * Generic interface.
+ */
+#define hweight8(w)  (__builtin_constant_p(w) ? __const_hweight8(w)  : __arch_hweight8(w))
+#define hweight16(w) (__builtin_constant_p(w) ? __const_hweight16(w) : __arch_hweight16(w))
+#define hweight32(w) (__builtin_constant_p(w) ? __const_hweight32(w) : __arch_hweight32(w))
+#define hweight64(w) (__builtin_constant_p(w) ? __const_hweight64(w) : __arch_hweight64(w))
+
+/*
+ * Interface for known constant arguments
+ */
+#define HWEIGHT8(w)  (BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + __const_hweight8(w))
+#define HWEIGHT16(w) (BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + __const_hweight16(w))
+#define HWEIGHT32(w) (BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + __const_hweight32(w))
+#define HWEIGHT64(w) (BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + __const_hweight64(w))
+
+/*
+ * Type invariant interface to the compile time constant hweight functions.
+ */
+#define HWEIGHT(w)   HWEIGHT64((u64)w)
+
+#endif /* _ASM_GENERIC_BITOPS_CONST_HWEIGHT_H_ */
diff --git a/include/asm-generic/bitops/hweight.h b/include/asm-generic/bitops/hweight.h
index fbbc383771da..a94d6519c7ed 100644
--- a/include/asm-generic/bitops/hweight.h
+++ b/include/asm-generic/bitops/hweight.h
@@ -1,11 +1,7 @@
 #ifndef _ASM_GENERIC_BITOPS_HWEIGHT_H_
 #define _ASM_GENERIC_BITOPS_HWEIGHT_H_
 
-#include <asm/types.h>
-
-extern unsigned int hweight32(unsigned int w);
-extern unsigned int hweight16(unsigned int w);
-extern unsigned int hweight8(unsigned int w);
-extern unsigned long hweight64(__u64 w);
+#include <asm-generic/bitops/arch_hweight.h>
+#include <asm-generic/bitops/const_hweight.h>
 
 #endif /* _ASM_GENERIC_BITOPS_HWEIGHT_H_ */
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index b796eab5ca75..fc68053378ce 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -10,6 +10,11 @@
 #define BITS_TO_LONGS(nr)       DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long))
 #endif
 
+extern unsigned int __sw_hweight8(unsigned int w);
+extern unsigned int __sw_hweight16(unsigned int w);
+extern unsigned int __sw_hweight32(unsigned int w);
+extern unsigned long __sw_hweight64(__u64 w);
+
 /*
  * Include this here because some architectures need generic_ffs/fls in
  * scope
@@ -44,31 +49,6 @@ static inline unsigned long hweight_long(unsigned long w)
         return sizeof(w) == 4 ? hweight32(w) : hweight64(w);
 }
 
-/*
- * Clearly slow versions of the hweightN() functions, their benefit is
- * of course compile time evaluation of constant arguments.
- */
-#define HWEIGHT8(w)                                     \
-      ( BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) +   \
-        (!!((w) & (1ULL << 0))) +                       \
-        (!!((w) & (1ULL << 1))) +                       \
-        (!!((w) & (1ULL << 2))) +                       \
-        (!!((w) & (1ULL << 3))) +                       \
-        (!!((w) & (1ULL << 4))) +                       \
-        (!!((w) & (1ULL << 5))) +                       \
-        (!!((w) & (1ULL << 6))) +                       \
-        (!!((w) & (1ULL << 7))) )
-
-#define HWEIGHT16(w) (HWEIGHT8(w)  + HWEIGHT8((w) >> 8))
-#define HWEIGHT32(w) (HWEIGHT16(w) + HWEIGHT16((w) >> 16))
-#define HWEIGHT64(w) (HWEIGHT32(w) + HWEIGHT32((w) >> 32))
-
-/*
- * Type invariant version that simply casts things to the
- * largest type.
- */
-#define HWEIGHT(w)   HWEIGHT64((u64)(w))
-
 /**
  * rol32 - rotate a 32-bit value left
  * @word: value to rotate