linux/include/asm-generic/bitops/__ffs.h
Andi Kleen c8399943bd x86, generic: mark complex bitops.h inlines as __always_inline
Impact: reduce kernel image size

Hugh Dickins noticed that older gcc versions when the kernel
is built for code size didn't inline some of the bitops.

Mark all complex x86 bitops that have more than a single
asm statement or two as always inline to avoid this problem.

Probably should be done for other architectures too.

Ingo then found a better fix that only requires
a single line change, but it unfortunately only
works on gcc 4.3.

On older gccs the original patch still makes a ~0.3% defconfig
difference with CONFIG_OPTIMIZE_INLINING=y.

With gcc 4.1 and a defconfig like build:

    6116998 1138540  883788 8139326  7c323e vmlinux-oi-with-patch
    6137043 1138540  883788 8159371  7c808b vmlinux-optimize-inlining

~20k / 0.3% difference.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-01-13 18:56:30 +01:00

43 lines
738 B
C

#ifndef _ASM_GENERIC_BITOPS___FFS_H_
#define _ASM_GENERIC_BITOPS___FFS_H_
#include <asm/types.h>
/**
* __ffs - find first bit in word.
* @word: The word to search
*
* Undefined if no bit exists, so code should check against 0 first.
*/
static __always_inline unsigned long __ffs(unsigned long word)
{
int num = 0;
#if BITS_PER_LONG == 64
if ((word & 0xffffffff) == 0) {
num += 32;
word >>= 32;
}
#endif
if ((word & 0xffff) == 0) {
num += 16;
word >>= 16;
}
if ((word & 0xff) == 0) {
num += 8;
word >>= 8;
}
if ((word & 0xf) == 0) {
num += 4;
word >>= 4;
}
if ((word & 0x3) == 0) {
num += 2;
word >>= 2;
}
if ((word & 0x1) == 0)
num += 1;
return num;
}
#endif /* _ASM_GENERIC_BITOPS___FFS_H_ */