Refactor parity8() to use __builtin_parity() when no
architecture-specific implementation is available. If the input is a
compile-time constant, expand it using the _parity_const() macro to
enable constant folding, allowing the compiler to optimize it at
compile time.
Additionally, mark parity8() with __attribute_const__ to indicate its
pure nature, ensuring better optimization opportunities.
This change improves efficiency by leveraging compiler intrinsics while
maintaining a fallback mechanism for architectures without specific
implementations.
Co-developed-by: Yu-Chun Lin <eleanor...@gmail.com>
Signed-off-by: Yu-Chun Lin <eleanor...@gmail.com>
Signed-off-by: Kuan-Wei Chiu <visitor...@gmail.com>
---
include/linux/bitops.h | 30 +++++++++++++++++++++++-------
1 file changed, 23 insertions(+), 7 deletions(-)
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index c1cb53cf2f0f..4c307d9c1545 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -229,6 +229,27 @@ static inline int get_count_order_long(unsigned long l)
return (int)fls_long(--l);
}
+#define _parity_const(val) \
+({ \
+ u64 __v = (val); \
+ int __ret; \
+ __v ^= __v >> 32; \
+ __v ^= __v >> 16; \
+ __v ^= __v >> 8; \
+ __v ^= __v >> 4; \
+ __v ^= __v >> 2; \
+ __v ^= __v >> 1; \
+ __ret = __v & 1; \
+ __ret; \
+})
+
+#ifndef _parity8
+static inline __attribute_const__ int _parity8(u8 val)
+{
+ return __builtin_parity(val);
+}
+#endif
+
/**
* parity8 - get the parity of an u8 value
* @value: the value to be examined
@@ -250,14 +271,9 @@ static inline int get_count_order_long(unsigned long l)
* if (parity8(val) == 0)
* val ^= BIT(7);
*/
-static inline int parity8(u8 val)
+static inline __attribute_const__ int parity8(u8 val)
{
- /*
- * One explanation of this algorithm:
- * https://funloop.org/codex/problem/parity/README.html
- */
- val ^= val >> 4;
- return (0x6996 >> (val & 0xf)) & 1;
+ return __builtin_constant_p(val) ? _parity_const(val) : _parity8(val);
}
/**
--
2.34.1
