With the __ilog2() function as defined in
arch/powerpc/include/asm/bitops.h, GCC will not optimise the code
in case of constant parameter.
The generic ilog2() function in include/linux/log2.h is written
to handle the case of the constant parameter.
This patch discards the three __ilog2() functions and
defines __ilog2() as ilog2()
For non constant calls, the generated code is doing the same:
int test__ilog2(unsigned long x)
{
return __ilog2(x);
}
int test__ilog2_u32(u32 n)
{
return __ilog2_u32(n);
}
int test__ilog2_u64(u64 n)
{
return __ilog2_u64(n);
}
On PPC32 before the patch:
00000000 <test__ilog2>:
0: 7c 63 00 34 cntlzw r3,r3
4: 20 63 00 1f subfic r3,r3,31
8: 4e 80 00 20 blr
0000000c <test__ilog2_u32>:
c: 7c 63 00 34 cntlzw r3,r3
10: 20 63 00 1f subfic r3,r3,31
14: 4e 80 00 20 blr
On PPC32 after the patch:
00000000 <test__ilog2>:
0: 7c 63 00 34 cntlzw r3,r3
4: 20 63 00 1f subfic r3,r3,31
8: 4e 80 00 20 blr
0000000c <test__ilog2_u32>:
c: 7c 63 00 34 cntlzw r3,r3
10: 20 63 00 1f subfic r3,r3,31
14: 4e 80 00 20 blr
On PPC64 before the patch:
0000000000000000 <.test__ilog2>:
0: 7c 63 00 74 cntlzd r3,r3
4: 20 63 00 3f subfic r3,r3,63
8: 7c 63 07 b4 extsw r3,r3
c: 4e 80 00 20 blr
0000000000000010 <.test__ilog2_u32>:
10: 7c 63 00 34 cntlzw r3,r3
14: 20 63 00 1f subfic r3,r3,31
18: 7c 63 07 b4 extsw r3,r3
1c: 4e 80 00 20 blr
0000000000000020 <.test__ilog2_u64>:
20: 7c 63 00 74 cntlzd r3,r3
24: 20 63 00 3f subfic r3,r3,63
28: 7c 63 07 b4 extsw r3,r3
2c: 4e 80 00 20 blr
On PPC64 after the patch:
0000000000000000 <.test__ilog2>:
0: 7c 63 00 74 cntlzd r3,r3
4: 20 63 00 3f subfic r3,r3,63
8: 7c 63 07 b4 extsw r3,r3
c: 4e 80 00 20 blr
0000000000000010 <.test__ilog2_u32>:
10: 7c 63 00 34 cntlzw r3,r3
14: 20 63 00 1f subfic r3,r3,31
18: 7c 63 07 b4 extsw r3,r3
1c: 4e 80 00 20 blr
0000000000000020 <.test__ilog2_u64>:
20: 7c 63 00 74 cntlzd r3,r3
24: 20 63 00 3f subfic r3,r3,63
28: 7c 63 07 b4 extsw r3,r3
2c: 4e 80 00 20 blr
Signed-off-by: Christophe Leroy <christophe.le...@c-s.fr>
---
arch/powerpc/Kconfig | 8 --------
arch/powerpc/include/asm/bitops.h | 27 +--------------------------
2 files changed, 1 insertion(+), 34 deletions(-)
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 2bfd49098c5e..f231b0f190b5 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -62,14 +62,6 @@ config GENERIC_LOCKBREAK
default y
depends on SMP && PREEMPT
-config ARCH_HAS_ILOG2_U32
- bool
- default y
-
-config ARCH_HAS_ILOG2_U64
- bool
- default y if 64BIT
-
config GENERIC_HWEIGHT
bool
default y
diff --git a/arch/powerpc/include/asm/bitops.h
b/arch/powerpc/include/asm/bitops.h
index d835cd697d6b..b750ffef83c7 100644
--- a/arch/powerpc/include/asm/bitops.h
+++ b/arch/powerpc/include/asm/bitops.h
@@ -206,32 +206,7 @@ static __inline__ void __clear_bit_unlock(int nr, volatile
unsigned long *addr)
* Return the zero-based bit position (LE, not IBM bit numbering) of
* the most significant 1-bit in a double word.
*/
-static __inline__ __attribute__((const))
-int __ilog2(unsigned long x)
-{
- int lz;
-
- asm (PPC_CNTLZL "%0,%1" : "=r" (lz) : "r" (x));
- return BITS_PER_LONG - 1 - lz;
-}
-
-static inline __attribute__((const))
-int __ilog2_u32(u32 n)
-{
- int bit;
- asm ("cntlzw %0,%1" : "=r" (bit) : "r" (n));
- return 31 - bit;
-}
-
-#ifdef __powerpc64__
-static inline __attribute__((const))
-int __ilog2_u64(u64 n)
-{
- int bit;
- asm ("cntlzd %0,%1" : "=r" (bit) : "r" (n));
- return 63 - bit;
-}
-#endif
+#define __ilog2(x) ilog2(x)
#include <asm-generic/bitops/ffz.h>
--
2.12.0
