mirror of
https://github.com/torvalds/linux
synced 2024-11-05 18:23:50 +00:00
c8399943bd
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>
43 lines
881 B
C
43 lines
881 B
C
#ifndef _ASM_GENERIC_BITOPS___FLS_H_
|
|
#define _ASM_GENERIC_BITOPS___FLS_H_
|
|
|
|
#include <asm/types.h>
|
|
|
|
/**
|
|
* __fls - find last (most-significant) set bit in a long word
|
|
* @word: the word to search
|
|
*
|
|
* Undefined if no set bit exists, so code should check against 0 first.
|
|
*/
|
|
static __always_inline unsigned long __fls(unsigned long word)
|
|
{
|
|
int num = BITS_PER_LONG - 1;
|
|
|
|
#if BITS_PER_LONG == 64
|
|
if (!(word & (~0ul << 32))) {
|
|
num -= 32;
|
|
word <<= 32;
|
|
}
|
|
#endif
|
|
if (!(word & (~0ul << (BITS_PER_LONG-16)))) {
|
|
num -= 16;
|
|
word <<= 16;
|
|
}
|
|
if (!(word & (~0ul << (BITS_PER_LONG-8)))) {
|
|
num -= 8;
|
|
word <<= 8;
|
|
}
|
|
if (!(word & (~0ul << (BITS_PER_LONG-4)))) {
|
|
num -= 4;
|
|
word <<= 4;
|
|
}
|
|
if (!(word & (~0ul << (BITS_PER_LONG-2)))) {
|
|
num -= 2;
|
|
word <<= 2;
|
|
}
|
|
if (!(word & (~0ul << (BITS_PER_LONG-1))))
|
|
num -= 1;
|
|
return num;
|
|
}
|
|
|
|
#endif /* _ASM_GENERIC_BITOPS___FLS_H_ */
|