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>
42 lines
635 B
C
42 lines
635 B
C
#ifndef _ASM_GENERIC_BITOPS_FLS_H_
|
|
#define _ASM_GENERIC_BITOPS_FLS_H_
|
|
|
|
/**
|
|
* fls - find last (most-significant) bit set
|
|
* @x: the word to search
|
|
*
|
|
* This is defined the same way as ffs.
|
|
* Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32.
|
|
*/
|
|
|
|
static __always_inline int fls(int x)
|
|
{
|
|
int r = 32;
|
|
|
|
if (!x)
|
|
return 0;
|
|
if (!(x & 0xffff0000u)) {
|
|
x <<= 16;
|
|
r -= 16;
|
|
}
|
|
if (!(x & 0xff000000u)) {
|
|
x <<= 8;
|
|
r -= 8;
|
|
}
|
|
if (!(x & 0xf0000000u)) {
|
|
x <<= 4;
|
|
r -= 4;
|
|
}
|
|
if (!(x & 0xc0000000u)) {
|
|
x <<= 2;
|
|
r -= 2;
|
|
}
|
|
if (!(x & 0x80000000u)) {
|
|
x <<= 1;
|
|
r -= 1;
|
|
}
|
|
return r;
|
|
}
|
|
|
|
#endif /* _ASM_GENERIC_BITOPS_FLS_H_ */
|