With the fls() functions as defined in arch/powerpc/include/asm/bitops.h
GCC will not optimise the code in case of constant parameter.
This patch replaces __fls() by the builtin function, and modifies
fls() and fls64() to use builtins instead of inline assembly
For non constant calls, the generated code is doing the same:
int testfls(unsigned int x)
{
return fls(x);
}
unsigned long test__fls(unsigned long x)
{
return __fls(x);
}
int testfls64(__u64 x)
{
return fls64(x);
}
On PPC32, before the patch:
00000064 <testfls>:
64: 7c 63 00 34 cntlzw r3,r3
68: 20 63 00 20 subfic r3,r3,32
6c: 4e 80 00 20 blr
00000070 <test__fls>:
70: 7c 63 00 34 cntlzw r3,r3
74: 20 63 00 1f subfic r3,r3,31
78: 4e 80 00 20 blr
0000007c <testfls64>:
7c: 2c 03 00 00 cmpwi r3,0
80: 40 82 00 10 bne 90 <testfls64+0x14>
84: 7c 83 00 34 cntlzw r3,r4
88: 20 63 00 20 subfic r3,r3,32
8c: 4e 80 00 20 blr
90: 7c 63 00 34 cntlzw r3,r3
94: 20 63 00 40 subfic r3,r3,64
98: 4e 80 00 20 blr
On PPC32, after the patch:
00000054 <testfls>:
54: 7c 63 00 34 cntlzw r3,r3
58: 20 63 00 20 subfic r3,r3,32
5c: 4e 80 00 20 blr
00000060 <test__fls>:
60: 7c 63 00 34 cntlzw r3,r3
64: 20 63 00 1f subfic r3,r3,31
68: 4e 80 00 20 blr
0000006c <testfls64>:
6c: 2c 03 00 00 cmpwi r3,0
70: 41 82 00 10 beq 80 <testfls64+0x14>
74: 7c 63 00 34 cntlzw r3,r3
78: 20 63 00 40 subfic r3,r3,64
7c: 4e 80 00 20 blr
80: 7c 83 00 34 cntlzw r3,r4
84: 20 63 00 40 subfic r3,r3,32
88: 4e 80 00 20 blr
On PPC64, before the patch:
00000000000000a0 <.testfls>:
a0: 7c 63 00 34 cntlzw r3,r3
a4: 20 63 00 20 subfic r3,r3,32
a8: 7c 63 07 b4 extsw r3,r3
ac: 4e 80 00 20 blr
00000000000000b0 <.test__fls>:
b0: 7c 63 00 74 cntlzd r3,r3
b4: 20 63 00 3f subfic r3,r3,63
b8: 7c 63 07 b4 extsw r3,r3
bc: 4e 80 00 20 blr
00000000000000c0 <.testfls64>:
c0: 7c 63 00 74 cntlzd r3,r3
c4: 20 63 00 40 subfic r3,r3,64
c8: 7c 63 07 b4 extsw r3,r3
cc: 4e 80 00 20 blr
On PPC64, after the patch:
0000000000000090 <.testfls>:
90: 7c 63 00 34 cntlzw r3,r3
94: 20 63 00 20 subfic r3,r3,32
98: 7c 63 07 b4 extsw r3,r3
9c: 4e 80 00 20 blr
00000000000000a0 <.test__fls>:
a0: 7c 63 00 74 cntlzd r3,r3
a4: 20 63 00 3f subfic r3,r3,63
a8: 4e 80 00 20 blr
ac: 60 00 00 00 nop
00000000000000b0 <.testfls64>:
b0: 7c 63 00 74 cntlzd r3,r3
b4: 20 63 00 40 subfic r3,r3,64
b8: 7c 63 07 b4 extsw r3,r3
bc: 4e 80 00 20 blr
Those builtins have been in GCC since at least 3.4.6 (see
https://gcc.gnu.org/onlinedocs/gcc-3.4.6/gcc/Other-Builtins.html )
Signed-off-by: Christophe Leroy <christophe.le...@c-s.fr>
---
arch/powerpc/include/asm/bitops.h | 24 +++---------------------
1 file changed, 3 insertions(+), 21 deletions(-)
diff --git a/arch/powerpc/include/asm/bitops.h
b/arch/powerpc/include/asm/bitops.h
index 71b05685f3a7..af36b404dbe8 100644
--- a/arch/powerpc/include/asm/bitops.h
+++ b/arch/powerpc/include/asm/bitops.h
@@ -263,33 +263,15 @@ static __inline__ unsigned long ffz(unsigned long x)
*/
static __inline__ int fls(unsigned int x)
{
- int lz;
-
- asm ("cntlzw %0,%1" : "=r" (lz) : "r" (x));
- return 32 - lz;
+ return 32 - __builtin_clz(x);
}
-static __inline__ unsigned long __fls(unsigned long x)
-{
- return __ilog2(x);
-}
+#include <asm-generic/bitops/builtin-__fls.h>
-/*
- * 64-bit can do this using one cntlzd (count leading zeroes doubleword)
- * instruction; for 32-bit we use the generic version, which does two
- * 32-bit fls calls.
- */
-#ifdef __powerpc64__
static __inline__ int fls64(__u64 x)
{
- int lz;
-
- asm ("cntlzd %0,%1" : "=r" (lz) : "r" (x));
- return 64 - lz;
+ return 64 - __builtin_clzll(x);
}
-#else
-#include <asm-generic/bitops/fls64.h>
-#endif /* __powerpc64__ */
#ifdef CONFIG_PPC64
unsigned int __arch_hweight8(unsigned int w);
--
2.12.0
