bitops: Optimize hweight() by making use of compile-time evaluation

Rename the extisting runtime hweight() implementations to
__arch_hweight(), rename the compile-time versions to __const_hweight()
and then have hweight() pick between them.

Suggested-by: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <20100318111929.GB11152@aftab>
Acked-by: H. Peter Anvin <hpa@zytor.com>
LKML-Reference: <1265028224.24455.154.camel@laptop>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>

8 files changed, 87 insertions, 58 deletions

diff --git a/arch/alpha/include/asm/bitops.h b/arch/alpha/include/asm/bitops.h
index 15f3ae25c511..296da1d5ed57 100644
--- a/arch/alpha/include/asm/bitops.h
+++ b/arch/alpha/include/asm/bitops.h
@@ -405,29 +405,31 @@ static inline int fls(int x)
 
 #if defined(CONFIG_ALPHA_EV6) && defined(CONFIG_ALPHA_EV67)
 /* Whee.  EV67 can calculate it directly.  */
-static inline unsigned long hweight64(unsigned long w)
+static inline unsigned long __arch_hweight64(unsigned long w)
 {
         return __kernel_ctpop(w);
 }
 
-static inline unsigned int hweight32(unsigned int w)
+static inline unsigned int __arch_weight32(unsigned int w)
 {
-        return hweight64(w);
+        return __arch_hweight64(w);
 }
 
-static inline unsigned int hweight16(unsigned int w)
+static inline unsigned int __arch_hweight16(unsigned int w)
 {
-        return hweight64(w & 0xffff);
+        return __arch_hweight64(w & 0xffff);
 }
 
-static inline unsigned int hweight8(unsigned int w)
+static inline unsigned int __arch_hweight8(unsigned int w)
 {
-        return hweight64(w & 0xff);
+        return __arch_hweight64(w & 0xff);
 }
 #else
-#include <asm-generic/bitops/hweight.h>
+#include <asm-generic/bitops/arch_hweight.h>
 #endif
 
+#include <asm-generic/bitops/const_hweight.h>
+
 #endif /* __KERNEL__ */
 
 #include <asm-generic/bitops/find.h>
diff --git a/arch/ia64/include/asm/bitops.h b/arch/ia64/include/asm/bitops.h
index 6ebc229a1c51..9da3df6f1a52 100644
--- a/arch/ia64/include/asm/bitops.h
+++ b/arch/ia64/include/asm/bitops.h
@@ -437,17 +437,18 @@ __fls (unsigned long x)
  * hweightN: returns the hamming weight (i.e. the number
  * of bits set) of a N-bit word
  */
-static __inline__ unsigned long
-hweight64 (unsigned long x)
+static __inline__ unsigned long __arch_hweight64(unsigned long x)
 {
         unsigned long result;
         result = ia64_popcnt(x);
         return result;
 }
 
-#define hweight32(x)    (unsigned int) hweight64((x) & 0xfffffffful)
-#define hweight16(x)    (unsigned int) hweight64((x) & 0xfffful)
-#define hweight8(x)     (unsigned int) hweight64((x) & 0xfful)
+#define __arch_hweight32(x) ((unsigned int) __arch_hweight64((x) & 0xfffffffful))
+#define __arch_hweight16(x) ((unsigned int) __arch_hweight64((x) & 0xfffful))
+#define __arch_hweight8(x)  ((unsigned int) __arch_hweight64((x) & 0xfful))
+
+#include <asm-generic/bitops/const_hweight.h>
 
 #endif /* __KERNEL__ */
 
diff --git a/arch/sparc/include/asm/bitops_64.h b/arch/sparc/include/asm/bitops_64.h
index e72ac9cdfb98..766121a67a24 100644
--- a/arch/sparc/include/asm/bitops_64.h
+++ b/arch/sparc/include/asm/bitops_64.h
@@ -44,7 +44,7 @@ extern void change_bit(unsigned long nr, volatile unsigned long *addr);
 
 #ifdef ULTRA_HAS_POPULATION_COUNT
 
-static inline unsigned int hweight64(unsigned long w)
+static inline unsigned int __arch_hweight64(unsigned long w)
 {
         unsigned int res;
 
@@ -52,7 +52,7 @@ static inline unsigned int hweight64(unsigned long w)
         return res;
 }
 
-static inline unsigned int hweight32(unsigned int w)
+static inline unsigned int __arch_hweight32(unsigned int w)
 {
         unsigned int res;
 
@@ -60,7 +60,7 @@ static inline unsigned int hweight32(unsigned int w)
         return res;
 }
 
-static inline unsigned int hweight16(unsigned int w)
+static inline unsigned int __arch_hweight16(unsigned int w)
 {
         unsigned int res;
 
@@ -68,7 +68,7 @@ static inline unsigned int hweight16(unsigned int w)
         return res;
 }
 
-static inline unsigned int hweight8(unsigned int w)
+static inline unsigned int __arch_hweight8(unsigned int w)
 {
         unsigned int res;
 
@@ -78,9 +78,10 @@ static inline unsigned int hweight8(unsigned int w)
 
 #else
 
-#include <asm-generic/bitops/hweight.h>
+#include <asm-generic/bitops/arch_hweight.h>
 
 #endif
+#include <asm-generic/bitops/const_hweight.h>
 #include <asm-generic/bitops/lock.h>
 #endif /* __KERNEL__ */
 
diff --git a/include/asm-generic/bitops/arch_hweight.h b/include/asm-generic/bitops/arch_hweight.h
new file mode 100644
index 000000000000..3a7be842cdce
--- /dev/null
+++ b/include/asm-generic/bitops/arch_hweight.h
@@ -0,0 +1,11 @@
+#ifndef _ASM_GENERIC_BITOPS_ARCH_HWEIGHT_H_
+#define _ASM_GENERIC_BITOPS_ARCH_HWEIGHT_H_
+
+#include <asm/types.h>
+
+extern unsigned int __arch_hweight32(unsigned int w);
+extern unsigned int __arch_hweight16(unsigned int w);
+extern unsigned int __arch_hweight8(unsigned int w);
+extern unsigned long __arch_hweight64(__u64 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.
+ */